diff options
| author | Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> | 2012-09-12 11:14:33 -0400 |
|---|---|---|
| committer | Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> | 2012-09-12 11:14:33 -0400 |
| commit | 25a765b7f05cb8460fa01b54568894b20e184862 (patch) | |
| tree | 0b56db57b4d9f912393ab303c269e0fe6cdf8635 /net | |
| parent | 9d2be9287107695708e6aae5105a8a518a6cb4d0 (diff) | |
| parent | 64282278989d5b0398dcb3ba7904cb00c621dc35 (diff) | |
Merge branch 'x86/platform' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into stable/for-linus-3.7
* 'x86/platform' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (9690 commits)
x86: Document x86_init.paging.pagetable_init()
x86: xen: Cleanup and remove x86_init.paging.pagetable_setup_done()
x86: Move paging_init() call to x86_init.paging.pagetable_init()
x86: Rename pagetable_setup_start() to pagetable_init()
x86: Remove base argument from x86_init.paging.pagetable_setup_start
Linux 3.6-rc5
HID: tpkbd: work even if the new Lenovo Keyboard driver is not configured
Remove user-triggerable BUG from mpol_to_str
xen/pciback: Fix proper FLR steps.
uml: fix compile error in deliver_alarm()
dj: memory scribble in logi_dj
Fix order of arguments to compat_put_time[spec|val]
xen: Use correct masking in xen_swiotlb_alloc_coherent.
xen: fix logical error in tlb flushing
xen/p2m: Fix one-off error in checking the P2M tree directory.
powerpc: Don't use __put_user() in patch_instruction
powerpc: Make sure IPI handlers see data written by IPI senders
powerpc: Restore correct DSCR in context switch
powerpc: Fix DSCR inheritance in copy_thread()
powerpc: Keep thread.dscr and thread.dscr_inherit in sync
...
Diffstat (limited to 'net')
462 files changed, 26054 insertions, 17902 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index da1bc9c3cf3..402442402af 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -137,9 +137,21 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, return rc; } +static inline netdev_tx_t vlan_netpoll_send_skb(struct vlan_dev_priv *vlan, struct sk_buff *skb) +{ +#ifdef CONFIG_NET_POLL_CONTROLLER + if (vlan->netpoll) + netpoll_send_skb(vlan->netpoll, skb); +#else + BUG(); +#endif + return NETDEV_TX_OK; +} + static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) { + struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data); unsigned int len; int ret; @@ -150,29 +162,30 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, * OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs... */ if (veth->h_vlan_proto != htons(ETH_P_8021Q) || - vlan_dev_priv(dev)->flags & VLAN_FLAG_REORDER_HDR) { + vlan->flags & VLAN_FLAG_REORDER_HDR) { u16 vlan_tci; - vlan_tci = vlan_dev_priv(dev)->vlan_id; + vlan_tci = vlan->vlan_id; vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb); skb = __vlan_hwaccel_put_tag(skb, vlan_tci); } - skb->dev = vlan_dev_priv(dev)->real_dev; + skb->dev = vlan->real_dev; len = skb->len; - if (netpoll_tx_running(dev)) - return skb->dev->netdev_ops->ndo_start_xmit(skb, skb->dev); + if (unlikely(netpoll_tx_running(dev))) + return vlan_netpoll_send_skb(vlan, skb); + ret = dev_queue_xmit(skb); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct vlan_pcpu_stats *stats; - stats = this_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats); + stats = this_cpu_ptr(vlan->vlan_pcpu_stats); u64_stats_update_begin(&stats->syncp); stats->tx_packets++; stats->tx_bytes += len; u64_stats_update_end(&stats->syncp); } else { - this_cpu_inc(vlan_dev_priv(dev)->vlan_pcpu_stats->tx_dropped); + this_cpu_inc(vlan->vlan_pcpu_stats->tx_dropped); } return ret; @@ -669,28 +682,26 @@ static void vlan_dev_poll_controller(struct net_device *dev) return; } -static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo) +static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo, + gfp_t gfp) { - struct vlan_dev_priv *info = vlan_dev_priv(dev); - struct net_device *real_dev = info->real_dev; + struct vlan_dev_priv *vlan = vlan_dev_priv(dev); + struct net_device *real_dev = vlan->real_dev; struct netpoll *netpoll; int err = 0; - netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); + netpoll = kzalloc(sizeof(*netpoll), gfp); err = -ENOMEM; if (!netpoll) goto out; - netpoll->dev = real_dev; - strlcpy(netpoll->dev_name, real_dev->name, IFNAMSIZ); - - err = __netpoll_setup(netpoll); + err = __netpoll_setup(netpoll, real_dev, gfp); if (err) { kfree(netpoll); goto out; } - info->netpoll = netpoll; + vlan->netpoll = netpoll; out: return err; @@ -698,19 +709,15 @@ out: static void vlan_dev_netpoll_cleanup(struct net_device *dev) { - struct vlan_dev_priv *info = vlan_dev_priv(dev); - struct netpoll *netpoll = info->netpoll; + struct vlan_dev_priv *vlan= vlan_dev_priv(dev); + struct netpoll *netpoll = vlan->netpoll; if (!netpoll) return; - info->netpoll = NULL; - - /* Wait for transmitting packets to finish before freeing. */ - synchronize_rcu_bh(); + vlan->netpoll = NULL; - __netpoll_cleanup(netpoll); - kfree(netpoll); + __netpoll_free_rcu(netpoll); } #endif /* CONFIG_NET_POLL_CONTROLLER */ diff --git a/net/9p/client.c b/net/9p/client.c index a170893d70e..8260f132b32 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -1548,7 +1548,7 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset, kernel_buf = 1; indata = data; } else - indata = (char *)udata; + indata = (__force char *)udata; /* * response header len is 11 * PDU Header(7) + IO Size (4) diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 2a167658bb9..35b8911b1c8 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -212,7 +212,7 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req) * this takes a list of pages. * @sg: scatter/gather list to pack into * @start: which segment of the sg_list to start at - * @**pdata: a list of pages to add into sg. + * @pdata: a list of pages to add into sg. * @nr_pages: number of pages to pack into the scatter/gather list * @data: data to pack into scatter/gather list * @count: amount of data to pack into the scatter/gather list diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 86852963b7f..33475291c9c 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -129,8 +129,8 @@ found: /** * atalk_find_or_insert_socket - Try to find a socket matching ADDR - * @sk - socket to insert in the list if it is not there already - * @sat - address to search for + * @sk: socket to insert in the list if it is not there already + * @sat: address to search for * * Try to find a socket matching ADDR in the socket list, if found then return * it. If not, insert SK into the socket list. @@ -1066,8 +1066,8 @@ static int atalk_release(struct socket *sock) /** * atalk_pick_and_bind_port - Pick a source port when one is not given - * @sk - socket to insert into the tables - * @sat - address to search for + * @sk: socket to insert into the tables + * @sat: address to search for * * Pick a source port when one is not given. If we can find a suitable free * one, we insert the socket into the tables using it. diff --git a/net/atm/common.c b/net/atm/common.c index b4b44dbed64..0c0ad930a63 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -812,6 +812,7 @@ int vcc_getsockopt(struct socket *sock, int level, int optname, if (!vcc->dev || !test_bit(ATM_VF_ADDR, &vcc->flags)) return -ENOTCONN; + memset(&pvc, 0, sizeof(pvc)); pvc.sap_family = AF_ATMPVC; pvc.sap_addr.itf = vcc->dev->number; pvc.sap_addr.vpi = vcc->vpi; diff --git a/net/atm/lec.c b/net/atm/lec.c index a7d172105c9..2e3d942e77f 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -231,9 +231,11 @@ static netdev_tx_t lec_start_xmit(struct sk_buff *skb, if (skb_headroom(skb) < 2) { pr_debug("reallocating skb\n"); skb2 = skb_realloc_headroom(skb, LEC_HEADER_LEN); - kfree_skb(skb); - if (skb2 == NULL) + if (unlikely(!skb2)) { + kfree_skb(skb); return NETDEV_TX_OK; + } + consume_skb(skb); skb = skb2; } skb_push(skb, 2); @@ -1602,7 +1604,7 @@ static void lec_arp_expire_vcc(unsigned long data) { unsigned long flags; struct lec_arp_table *to_remove = (struct lec_arp_table *)data; - struct lec_priv *priv = (struct lec_priv *)to_remove->priv; + struct lec_priv *priv = to_remove->priv; del_timer(&to_remove->timer); diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index ce1e59fdae7..226dca98944 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -283,7 +283,7 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb) kfree_skb(n); goto nospace; } - kfree_skb(skb); + consume_skb(skb); skb = n; if (skb == NULL) return DROP_PACKET; diff --git a/net/atm/pvc.c b/net/atm/pvc.c index 3a734919c36..ae032402140 100644 --- a/net/atm/pvc.c +++ b/net/atm/pvc.c @@ -95,6 +95,7 @@ static int pvc_getname(struct socket *sock, struct sockaddr *sockaddr, return -ENOTCONN; *sockaddr_len = sizeof(struct sockaddr_atmpvc); addr = (struct sockaddr_atmpvc *)sockaddr; + memset(addr, 0, sizeof(*addr)); addr->sap_family = AF_ATMPVC; addr->sap_addr.itf = vcc->dev->number; addr->sap_addr.vpi = vcc->vpi; diff --git a/net/ax25/ax25_addr.c b/net/ax25/ax25_addr.c index 9162409559c..e7c9b0ea17a 100644 --- a/net/ax25/ax25_addr.c +++ b/net/ax25/ax25_addr.c @@ -189,8 +189,10 @@ const unsigned char *ax25_addr_parse(const unsigned char *buf, int len, digi->ndigi = 0; while (!(buf[-1] & AX25_EBIT)) { - if (d >= AX25_MAX_DIGIS) return NULL; /* Max of 6 digis */ - if (len < 7) return NULL; /* Short packet */ + if (d >= AX25_MAX_DIGIS) + return NULL; + if (len < AX25_ADDR_LEN) + return NULL; memcpy(&digi->calls[d], buf, AX25_ADDR_LEN); digi->ndigi = d + 1; diff --git a/net/ax25/ax25_out.c b/net/ax25/ax25_out.c index be8a25e0db6..be2acab9be9 100644 --- a/net/ax25/ax25_out.c +++ b/net/ax25/ax25_out.c @@ -350,7 +350,7 @@ void ax25_transmit_buffer(ax25_cb *ax25, struct sk_buff *skb, int type) if (skb->sk != NULL) skb_set_owner_w(skbn, skb->sk); - kfree_skb(skb); + consume_skb(skb); skb = skbn; } diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c index a65588040b9..d39097737e3 100644 --- a/net/ax25/ax25_route.c +++ b/net/ax25/ax25_route.c @@ -474,7 +474,7 @@ struct sk_buff *ax25_rt_build_path(struct sk_buff *skb, ax25_address *src, if (skb->sk != NULL) skb_set_owner_w(skbn, skb->sk); - kfree_skb(skb); + consume_skb(skb); skb = skbn; } diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index 6d5c1940667..8676d2b1d57 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -19,11 +19,10 @@ # obj-$(CONFIG_BATMAN_ADV) += batman-adv.o -batman-adv-y += bat_debugfs.o batman-adv-y += bat_iv_ogm.o -batman-adv-y += bat_sysfs.o batman-adv-y += bitarray.o batman-adv-$(CONFIG_BATMAN_ADV_BLA) += bridge_loop_avoidance.o +batman-adv-y += debugfs.o batman-adv-y += gateway_client.o batman-adv-y += gateway_common.o batman-adv-y += hard-interface.o @@ -35,6 +34,7 @@ batman-adv-y += ring_buffer.o batman-adv-y += routing.o batman-adv-y += send.o batman-adv-y += soft-interface.o +batman-adv-y += sysfs.o batman-adv-y += translation-table.o batman-adv-y += unicast.o batman-adv-y += vis.o diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index 9852a688ba4..a0ba3bff9b3 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -16,12 +15,11 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_BAT_ALGO_H_ #define _NET_BATMAN_ADV_BAT_ALGO_H_ -int bat_iv_init(void); +int batadv_iv_init(void); #endif /* _NET_BATMAN_ADV_BAT_ALGO_H_ */ diff --git a/net/batman-adv/bat_debugfs.c b/net/batman-adv/bat_debugfs.c deleted file mode 100644 index 3b588f86d77..00000000000 --- a/net/batman-adv/bat_debugfs.c +++ /dev/null @@ -1,388 +0,0 @@ -/* - * Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: - * - * Marek Lindner - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA - * - */ - -#include "main.h" - -#include <linux/debugfs.h> - -#include "bat_debugfs.h" -#include "translation-table.h" -#include "originator.h" -#include "hard-interface.h" -#include "gateway_common.h" -#include "gateway_client.h" -#include "soft-interface.h" -#include "vis.h" -#include "icmp_socket.h" -#include "bridge_loop_avoidance.h" - -static struct dentry *bat_debugfs; - -#ifdef CONFIG_BATMAN_ADV_DEBUG -#define LOG_BUFF_MASK (log_buff_len-1) -#define LOG_BUFF(idx) (debug_log->log_buff[(idx) & LOG_BUFF_MASK]) - -static int log_buff_len = LOG_BUF_LEN; - -static void emit_log_char(struct debug_log *debug_log, char c) -{ - LOG_BUFF(debug_log->log_end) = c; - debug_log->log_end++; - - if (debug_log->log_end - debug_log->log_start > log_buff_len) - debug_log->log_start = debug_log->log_end - log_buff_len; -} - -__printf(2, 3) -static int fdebug_log(struct debug_log *debug_log, const char *fmt, ...) -{ - va_list args; - static char debug_log_buf[256]; - char *p; - - if (!debug_log) - return 0; - - spin_lock_bh(&debug_log->lock); - va_start(args, fmt); - vscnprintf(debug_log_buf, sizeof(debug_log_buf), fmt, args); - va_end(args); - - for (p = debug_log_buf; *p != 0; p++) - emit_log_char(debug_log, *p); - - spin_unlock_bh(&debug_log->lock); - - wake_up(&debug_log->queue_wait); - - return 0; -} - -int debug_log(struct bat_priv *bat_priv, const char *fmt, ...) -{ - va_list args; - char tmp_log_buf[256]; - - va_start(args, fmt); - vscnprintf(tmp_log_buf, sizeof(tmp_log_buf), fmt, args); - fdebug_log(bat_priv->debug_log, "[%10u] %s", - jiffies_to_msecs(jiffies), tmp_log_buf); - va_end(args); - - return 0; -} - -static int log_open(struct inode *inode, struct file *file) -{ - nonseekable_open(inode, file); - file->private_data = inode->i_private; - inc_module_count(); - return 0; -} - -static int log_release(struct inode *inode, struct file *file) -{ - dec_module_count(); - return 0; -} - -static ssize_t log_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) -{ - struct bat_priv *bat_priv = file->private_data; - struct debug_log *debug_log = bat_priv->debug_log; - int error, i = 0; - char c; - - if ((file->f_flags & O_NONBLOCK) && - !(debug_log->log_end - debug_log->log_start)) - return -EAGAIN; - - if (!buf) - return -EINVAL; - - if (count == 0) - return 0; - - if (!access_ok(VERIFY_WRITE, buf, count)) - return -EFAULT; - - error = wait_event_interruptible(debug_log->queue_wait, - (debug_log->log_start - debug_log->log_end)); - - if (error) - return error; - - spin_lock_bh(&debug_log->lock); - - while ((!error) && (i < count) && - (debug_log->log_start != debug_log->log_end)) { - c = LOG_BUFF(debug_log->log_start); - - debug_log->log_start++; - - spin_unlock_bh(&debug_log->lock); - - error = __put_user(c, buf); - - spin_lock_bh(&debug_log->lock); - - buf++; - i++; - - } - - spin_unlock_bh(&debug_log->lock); - - if (!error) - return i; - - return error; -} - -static unsigned int log_poll(struct file *file, poll_table *wait) -{ - struct bat_priv *bat_priv = file->private_data; - struct debug_log *debug_log = bat_priv->debug_log; - - poll_wait(file, &debug_log->queue_wait, wait); - - if (debug_log->log_end - debug_log->log_start) - return POLLIN | POLLRDNORM; - - return 0; -} - -static const struct file_operations log_fops = { - .open = log_open, - .release = log_release, - .read = log_read, - .poll = log_poll, - .llseek = no_llseek, -}; - -static int debug_log_setup(struct bat_priv *bat_priv) -{ - struct dentry *d; - - if (!bat_priv->debug_dir) - goto err; - - bat_priv->debug_log = kzalloc(sizeof(*bat_priv->debug_log), GFP_ATOMIC); - if (!bat_priv->debug_log) - goto err; - - spin_lock_init(&bat_priv->debug_log->lock); - init_waitqueue_head(&bat_priv->debug_log->queue_wait); - - d = debugfs_create_file("log", S_IFREG | S_IRUSR, - bat_priv->debug_dir, bat_priv, &log_fops); - if (d) - goto err; - - return 0; - -err: - return 1; -} - -static void debug_log_cleanup(struct bat_priv *bat_priv) -{ - kfree(bat_priv->debug_log); - bat_priv->debug_log = NULL; -} -#else /* CONFIG_BATMAN_ADV_DEBUG */ -static int debug_log_setup(struct bat_priv *bat_priv) -{ - bat_priv->debug_log = NULL; - return 0; -} - -static void debug_log_cleanup(struct bat_priv *bat_priv) -{ - return; -} -#endif - -static int bat_algorithms_open(struct inode *inode, struct file *file) -{ - return single_open(file, bat_algo_seq_print_text, NULL); -} - -static int originators_open(struct inode *inode, struct file *file) -{ - struct net_device *net_dev = (struct net_device *)inode->i_private; - return single_open(file, orig_seq_print_text, net_dev); -} - -static int gateways_open(struct inode *inode, struct file *file) -{ - struct net_device *net_dev = (struct net_device *)inode->i_private; - return single_open(file, gw_client_seq_print_text, net_dev); -} - -static int transtable_global_open(struct inode *inode, struct file *file) -{ - struct net_device *net_dev = (struct net_device *)inode->i_private; - return single_open(file, tt_global_seq_print_text, net_dev); -} - -#ifdef CONFIG_BATMAN_ADV_BLA -static int bla_claim_table_open(struct inode *inode, struct file *file) -{ - struct net_device *net_dev = (struct net_device *)inode->i_private; - return single_open(file, bla_claim_table_seq_print_text, net_dev); -} -#endif - -static int transtable_local_open(struct inode *inode, struct file *file) -{ - struct net_device *net_dev = (struct net_device *)inode->i_private; - return single_open(file, tt_local_seq_print_text, net_dev); -} - -static int vis_data_open(struct inode *inode, struct file *file) -{ - struct net_device *net_dev = (struct net_device *)inode->i_private; - return single_open(file, vis_seq_print_text, net_dev); -} - -struct bat_debuginfo { - struct attribute attr; - const struct file_operations fops; -}; - -#define BAT_DEBUGINFO(_name, _mode, _open) \ -struct bat_debuginfo bat_debuginfo_##_name = { \ - .attr = { .name = __stringify(_name), \ - .mode = _mode, }, \ - .fops = { .owner = THIS_MODULE, \ - .open = _open, \ - .read = seq_read, \ - .llseek = seq_lseek, \ - .release = single_release, \ - } \ -}; - -static BAT_DEBUGINFO(routing_algos, S_IRUGO, bat_algorithms_open); -static BAT_DEBUGINFO(originators, S_IRUGO, originators_open); -static BAT_DEBUGINFO(gateways, S_IRUGO, gateways_open); -static BAT_DEBUGINFO(transtable_global, S_IRUGO, transtable_global_open); -#ifdef CONFIG_BATMAN_ADV_BLA -static BAT_DEBUGINFO(bla_claim_table, S_IRUGO, bla_claim_table_open); -#endif -static BAT_DEBUGINFO(transtable_local, S_IRUGO, transtable_local_open); -static BAT_DEBUGINFO(vis_data, S_IRUGO, vis_data_open); - -static struct bat_debuginfo *mesh_debuginfos[] = { - &bat_debuginfo_originators, - &bat_debuginfo_gateways, - &bat_debuginfo_transtable_global, -#ifdef CONFIG_BATMAN_ADV_BLA - &bat_debuginfo_bla_claim_table, -#endif - &bat_debuginfo_transtable_local, - &bat_debuginfo_vis_data, - NULL, -}; - -void debugfs_init(void) -{ - struct bat_debuginfo *bat_debug; - struct dentry *file; - - bat_debugfs = debugfs_create_dir(DEBUGFS_BAT_SUBDIR, NULL); - if (bat_debugfs == ERR_PTR(-ENODEV)) - bat_debugfs = NULL; - - if (!bat_debugfs) - goto out; - - bat_debug = &bat_debuginfo_routing_algos; - file = debugfs_create_file(bat_debug->attr.name, - S_IFREG | bat_debug->attr.mode, - bat_debugfs, NULL, &bat_debug->fops); - if (!file) - pr_err("Can't add debugfs file: %s\n", bat_debug->attr.name); - -out: - return; -} - -void debugfs_destroy(void) -{ - if (bat_debugfs) { - debugfs_remove_recursive(bat_debugfs); - bat_debugfs = NULL; - } -} - -int debugfs_add_meshif(struct net_device *dev) -{ - struct bat_priv *bat_priv = netdev_priv(dev); - struct bat_debuginfo **bat_debug; - struct dentry *file; - - if (!bat_debugfs) - goto out; - - bat_priv->debug_dir = debugfs_create_dir(dev->name, bat_debugfs); - if (!bat_priv->debug_dir) - goto out; - - bat_socket_setup(bat_priv); - debug_log_setup(bat_priv); - - for (bat_debug = mesh_debuginfos; *bat_debug; ++bat_debug) { - file = debugfs_create_file(((*bat_debug)->attr).name, - S_IFREG | ((*bat_debug)->attr).mode, - bat_priv->debug_dir, - dev, &(*bat_debug)->fops); - if (!file) { - bat_err(dev, "Can't add debugfs file: %s/%s\n", - dev->name, ((*bat_debug)->attr).name); - goto rem_attr; - } - } - - return 0; -rem_attr: - debugfs_remove_recursive(bat_priv->debug_dir); - bat_priv->debug_dir = NULL; -out: -#ifdef CONFIG_DEBUG_FS - return -ENOMEM; -#else - return 0; -#endif /* CONFIG_DEBUG_FS */ -} - -void debugfs_del_meshif(struct net_device *dev) -{ - struct bat_priv *bat_priv = netdev_priv(dev); - - debug_log_cleanup(bat_priv); - - if (bat_debugfs) { - debugfs_remove_recursive(bat_priv->debug_dir); - bat_priv->debug_dir = NULL; - } -} diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index dc53798ebb4..e877af8bdd1 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" @@ -30,15 +28,16 @@ #include "send.h" #include "bat_algo.h" -static struct neigh_node *bat_iv_ogm_neigh_new(struct hard_iface *hard_iface, - const uint8_t *neigh_addr, - struct orig_node *orig_node, - struct orig_node *orig_neigh, - uint32_t seqno) +static struct batadv_neigh_node * +batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface, + const uint8_t *neigh_addr, + struct batadv_orig_node *orig_node, + struct batadv_orig_node *orig_neigh, __be32 seqno) { - struct neigh_node *neigh_node; + struct batadv_neigh_node *neigh_node; - neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr, seqno); + neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr, + ntohl(seqno)); if (!neigh_node) goto out; @@ -55,30 +54,30 @@ out: return neigh_node; } -static int bat_iv_ogm_iface_enable(struct hard_iface *hard_iface) +static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) { - struct batman_ogm_packet *batman_ogm_packet; + struct batadv_ogm_packet *batadv_ogm_packet; uint32_t random_seqno; - int res = -1; + int res = -ENOMEM; /* randomize initial seqno to avoid collision */ get_random_bytes(&random_seqno, sizeof(random_seqno)); atomic_set(&hard_iface->seqno, random_seqno); - hard_iface->packet_len = BATMAN_OGM_HLEN; + hard_iface->packet_len = BATADV_OGM_HLEN; hard_iface->packet_buff = kmalloc(hard_iface->packet_len, GFP_ATOMIC); if (!hard_iface->packet_buff) goto out; - batman_ogm_packet = (struct batman_ogm_packet *)hard_iface->packet_buff; - batman_ogm_packet->header.packet_type = BAT_IV_OGM; - batman_ogm_packet->header.version = COMPAT_VERSION; - batman_ogm_packet->header.ttl = 2; - batman_ogm_packet->flags = NO_FLAGS; - batman_ogm_packet->tq = TQ_MAX_VALUE; - batman_ogm_packet->tt_num_changes = 0; - batman_ogm_packet->ttvn = 0; + batadv_ogm_packet = (struct batadv_ogm_packet *)hard_iface->packet_buff; + batadv_ogm_packet->header.packet_type = BATADV_IV_OGM; + batadv_ogm_packet->header.version = BATADV_COMPAT_VERSION; + batadv_ogm_packet->header.ttl = 2; + batadv_ogm_packet->flags = BATADV_NO_FLAGS; + batadv_ogm_packet->tq = BATADV_TQ_MAX_VALUE; + batadv_ogm_packet->tt_num_changes = 0; + batadv_ogm_packet->ttvn = 0; res = 0; @@ -86,133 +85,152 @@ out: return res; } -static void bat_iv_ogm_iface_disable(struct hard_iface *hard_iface) +static void batadv_iv_ogm_iface_disable(struct batadv_hard_iface *hard_iface) { kfree(hard_iface->packet_buff); hard_iface->packet_buff = NULL; } -static void bat_iv_ogm_iface_update_mac(struct hard_iface *hard_iface) +static void batadv_iv_ogm_iface_update_mac(struct batadv_hard_iface *hard_iface) { - struct batman_ogm_packet *batman_ogm_packet; + struct batadv_ogm_packet *batadv_ogm_packet; - batman_ogm_packet = (struct batman_ogm_packet *)hard_iface->packet_buff; - memcpy(batman_ogm_packet->orig, + batadv_ogm_packet = (struct batadv_ogm_packet *)hard_iface->packet_buff; + memcpy(batadv_ogm_packet->orig, hard_iface->net_dev->dev_addr, ETH_ALEN); - memcpy(batman_ogm_packet->prev_sender, + memcpy(batadv_ogm_packet->prev_sender, hard_iface->net_dev->dev_addr, ETH_ALEN); } -static void bat_iv_ogm_primary_iface_set(struct hard_iface *hard_iface) +static void +batadv_iv_ogm_primary_iface_set(struct batadv_hard_iface *hard_iface) { - struct batman_ogm_packet *batman_ogm_packet; + struct batadv_ogm_packet *batadv_ogm_packet; - batman_ogm_packet = (struct batman_ogm_packet *)hard_iface->packet_buff; - batman_ogm_packet->flags = PRIMARIES_FIRST_HOP; - batman_ogm_packet->header.ttl = TTL; + batadv_ogm_packet = (struct batadv_ogm_packet *)hard_iface->packet_buff; + batadv_ogm_packet->flags = BATADV_PRIMARIES_FIRST_HOP; + batadv_ogm_packet->header.ttl = BATADV_TTL; } /* when do we schedule our own ogm to be sent */ -static unsigned long bat_iv_ogm_emit_send_time(const struct bat_priv *bat_priv) +static unsigned long +batadv_iv_ogm_emit_send_time(const struct batadv_priv *bat_priv) { - return jiffies + msecs_to_jiffies( - atomic_read(&bat_priv->orig_interval) - - JITTER + (random32() % 2*JITTER)); + unsigned int msecs; + + msecs = atomic_read(&bat_priv->orig_interval) - BATADV_JITTER; + msecs += (random32() % 2 * BATADV_JITTER); + + return jiffies + msecs_to_jiffies(msecs); } /* when do we schedule a ogm packet to be sent */ -static unsigned long bat_iv_ogm_fwd_send_time(void) +static unsigned long batadv_iv_ogm_fwd_send_time(void) { - return jiffies + msecs_to_jiffies(random32() % (JITTER/2)); + return jiffies + msecs_to_jiffies(random32() % (BATADV_JITTER / 2)); } /* apply hop penalty for a normal link */ -static uint8_t hop_penalty(uint8_t tq, const struct bat_priv *bat_priv) +static uint8_t batadv_hop_penalty(uint8_t tq, + const struct batadv_priv *bat_priv) { int hop_penalty = atomic_read(&bat_priv->hop_penalty); - return (tq * (TQ_MAX_VALUE - hop_penalty)) / (TQ_MAX_VALUE); + int new_tq; + + new_tq = tq * (BATADV_TQ_MAX_VALUE - hop_penalty); + new_tq /= BATADV_TQ_MAX_VALUE; + + return new_tq; } /* is there another aggregated packet here? */ -static int bat_iv_ogm_aggr_packet(int buff_pos, int packet_len, - int tt_num_changes) +static int batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len, + int tt_num_changes) { - int next_buff_pos = buff_pos + BATMAN_OGM_HLEN + tt_len(tt_num_changes); + int next_buff_pos = 0; + + next_buff_pos += buff_pos + BATADV_OGM_HLEN; + next_buff_pos += batadv_tt_len(tt_num_changes); return (next_buff_pos <= packet_len) && - (next_buff_pos <= MAX_AGGREGATION_BYTES); + (next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES); } /* send a batman ogm to a given interface */ -static void bat_iv_ogm_send_to_if(struct forw_packet *forw_packet, - struct hard_iface *hard_iface) +static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, + struct batadv_hard_iface *hard_iface) { - struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); char *fwd_str; uint8_t packet_num; int16_t buff_pos; - struct batman_ogm_packet *batman_ogm_packet; + struct batadv_ogm_packet *batadv_ogm_packet; struct sk_buff *skb; - if (hard_iface->if_status != IF_ACTIVE) + if (hard_iface->if_status != BATADV_IF_ACTIVE) return; packet_num = 0; buff_pos = 0; - batman_ogm_packet = (struct batman_ogm_packet *)forw_packet->skb->data; + batadv_ogm_packet = (struct batadv_ogm_packet *)forw_packet->skb->data; /* adjust all flags and log packets */ - while (bat_iv_ogm_aggr_packet(buff_pos, forw_packet->packet_len, - batman_ogm_packet->tt_num_changes)) { + while (batadv_iv_ogm_aggr_packet(buff_pos, forw_packet->packet_len, + batadv_ogm_packet->tt_num_changes)) { /* we might have aggregated direct link packets with an - * ordinary base packet */ + * ordinary base packet + */ if ((forw_packet->direct_link_flags & (1 << packet_num)) && (forw_packet->if_incoming == hard_iface)) - batman_ogm_packet->flags |= DIRECTLINK; + batadv_ogm_packet->flags |= BATADV_DIRECTLINK; else - batman_ogm_packet->flags &= ~DIRECTLINK; + batadv_ogm_packet->flags &= ~BATADV_DIRECTLINK; fwd_str = (packet_num > 0 ? "Forwarding" : (forw_packet->own ? "Sending own" : "Forwarding")); - bat_dbg(DBG_BATMAN, bat_priv, - "%s %spacket (originator %pM, seqno %u, TQ %d, TTL %d, IDF %s, ttvn %d) on interface %s [%pM]\n", - fwd_str, (packet_num > 0 ? "aggregated " : ""), - batman_ogm_packet->orig, - ntohl(batman_ogm_packet->seqno), - batman_ogm_packet->tq, batman_ogm_packet->header.ttl, - (batman_ogm_packet->flags & DIRECTLINK ? - "on" : "off"), - batman_ogm_packet->ttvn, hard_iface->net_dev->name, - hard_iface->net_dev->dev_addr); - - buff_pos += BATMAN_OGM_HLEN + - tt_len(batman_ogm_packet->tt_num_changes); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "%s %spacket (originator %pM, seqno %u, TQ %d, TTL %d, IDF %s, ttvn %d) on interface %s [%pM]\n", + fwd_str, (packet_num > 0 ? "aggregated " : ""), + batadv_ogm_packet->orig, + ntohl(batadv_ogm_packet->seqno), + batadv_ogm_packet->tq, batadv_ogm_packet->header.ttl, + (batadv_ogm_packet->flags & BATADV_DIRECTLINK ? + "on" : "off"), + batadv_ogm_packet->ttvn, hard_iface->net_dev->name, + hard_iface->net_dev->dev_addr); + + buff_pos += BATADV_OGM_HLEN; + buff_pos += batadv_tt_len(batadv_ogm_packet->tt_num_changes); packet_num++; - batman_ogm_packet = (struct batman_ogm_packet *) + batadv_ogm_packet = (struct batadv_ogm_packet *) (forw_packet->skb->data + buff_pos); } /* create clone because function is called more than once */ skb = skb_clone(forw_packet->skb, GFP_ATOMIC); - if (skb) - send_skb_packet(skb, hard_iface, broadcast_addr); + if (skb) { + batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_TX); + batadv_add_counter(bat_priv, BATADV_CNT_MGMT_TX_BYTES, + skb->len + ETH_HLEN); + batadv_send_skb_packet(skb, hard_iface, batadv_broadcast_addr); + } } /* send a batman ogm packet */ -static void bat_iv_ogm_emit(struct forw_packet *forw_packet) +static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet) { - struct hard_iface *hard_iface; + struct batadv_hard_iface *hard_iface; struct net_device *soft_iface; - struct bat_priv *bat_priv; - struct hard_iface *primary_if = NULL; - struct batman_ogm_packet *batman_ogm_packet; + struct batadv_priv *bat_priv; + struct batadv_hard_iface *primary_if = NULL; + struct batadv_ogm_packet *batadv_ogm_packet; unsigned char directlink; - batman_ogm_packet = (struct batman_ogm_packet *) + batadv_ogm_packet = (struct batadv_ogm_packet *) (forw_packet->skb->data); - directlink = (batman_ogm_packet->flags & DIRECTLINK ? 1 : 0); + directlink = (batadv_ogm_packet->flags & BATADV_DIRECTLINK ? 1 : 0); if (!forw_packet->if_incoming) { pr_err("Error - can't forward packet: incoming iface not specified\n"); @@ -222,31 +240,33 @@ static void bat_iv_ogm_emit(struct forw_packet *forw_packet) soft_iface = forw_packet->if_incoming->soft_iface; bat_priv = netdev_priv(soft_iface); - if (forw_packet->if_incoming->if_status != IF_ACTIVE) + if (forw_packet->if_incoming->if_status != BATADV_IF_ACTIVE) goto out; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; - /* multihomed peer assumed */ - /* non-primary OGMs are only broadcasted on their interface */ - if ((directlink && (batman_ogm_packet->header.ttl == 1)) || + /* multihomed peer assumed + * non-primary OGMs are only broadcasted on their interface + */ + if ((directlink && (batadv_ogm_packet->header.ttl == 1)) || (forw_packet->own && (forw_packet->if_incoming != primary_if))) { /* FIXME: what about aggregated packets ? */ - bat_dbg(DBG_BATMAN, bat_priv, - "%s packet (originator %pM, seqno %u, TTL %d) on interface %s [%pM]\n", - (forw_packet->own ? "Sending own" : "Forwarding"), - batman_ogm_packet->orig, - ntohl(batman_ogm_packet->seqno), - batman_ogm_packet->header.ttl, - forw_packet->if_incoming->net_dev->name, - forw_packet->if_incoming->net_dev->dev_addr); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "%s packet (originator %pM, seqno %u, TTL %d) on interface %s [%pM]\n", + (forw_packet->own ? "Sending own" : "Forwarding"), + batadv_ogm_packet->orig, + ntohl(batadv_ogm_packet->seqno), + batadv_ogm_packet->header.ttl, + forw_packet->if_incoming->net_dev->name, + forw_packet->if_incoming->net_dev->dev_addr); /* skb is only used once and than forw_packet is free'd */ - send_skb_packet(forw_packet->skb, forw_packet->if_incoming, - broadcast_addr); + batadv_send_skb_packet(forw_packet->skb, + forw_packet->if_incoming, + batadv_broadcast_addr); forw_packet->skb = NULL; goto out; @@ -254,70 +274,70 @@ static void bat_iv_ogm_emit(struct forw_packet *forw_packet) /* broadcast on every interface */ rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &hardif_list, list) { + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->soft_iface != soft_iface) continue; - bat_iv_ogm_send_to_if(forw_packet, hard_iface); + batadv_iv_ogm_send_to_if(forw_packet, hard_iface); } rcu_read_unlock(); out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); } /* return true if new_packet can be aggregated with forw_packet */ -static bool bat_iv_ogm_can_aggregate(const struct batman_ogm_packet - *new_batman_ogm_packet, - struct bat_priv *bat_priv, - int packet_len, unsigned long send_time, - bool directlink, - const struct hard_iface *if_incoming, - const struct forw_packet *forw_packet) +static bool +batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet, + struct batadv_priv *bat_priv, + int packet_len, unsigned long send_time, + bool directlink, + const struct batadv_hard_iface *if_incoming, + const struct batadv_forw_packet *forw_packet) { - struct batman_ogm_packet *batman_ogm_packet; + struct batadv_ogm_packet *batadv_ogm_packet; int aggregated_bytes = forw_packet->packet_len + packet_len; - struct hard_iface *primary_if = NULL; + struct batadv_hard_iface *primary_if = NULL; bool res = false; + unsigned long aggregation_end_time; - batman_ogm_packet = (struct batman_ogm_packet *)forw_packet->skb->data; + batadv_ogm_packet = (struct batadv_ogm_packet *)forw_packet->skb->data; + aggregation_end_time = send_time; + aggregation_end_time += msecs_to_jiffies(BATADV_MAX_AGGREGATION_MS); - /** - * we can aggregate the current packet to this aggregated packet + /* we can aggregate the current packet to this aggregated packet * if: * * - the send time is within our MAX_AGGREGATION_MS time * - the resulting packet wont be bigger than * MAX_AGGREGATION_BYTES */ - if (time_before(send_time, forw_packet->send_time) && - time_after_eq(send_time + msecs_to_jiffies(MAX_AGGREGATION_MS), - forw_packet->send_time) && - (aggregated_bytes <= MAX_AGGREGATION_BYTES)) { + time_after_eq(aggregation_end_time, forw_packet->send_time) && + (aggregated_bytes <= BATADV_MAX_AGGREGATION_BYTES)) { - /** - * check aggregation compatibility + /* check aggregation compatibility * -> direct link packets are broadcasted on * their interface only * -> aggregate packet if the current packet is * a "global" packet as well as the base * packet */ - - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; /* packets without direct link flag and high TTL - * are flooded through the net */ + * are flooded through the net + */ if ((!directlink) && - (!(batman_ogm_packet->flags & DIRECTLINK)) && - (batman_ogm_packet->header.ttl != 1) && + (!(batadv_ogm_packet->flags & BATADV_DIRECTLINK)) && + (batadv_ogm_packet->header.ttl != 1) && /* own packets originating non-primary - * interfaces leave only that interface */ + * interfaces leave only that interface + */ ((!forw_packet->own) || (forw_packet->if_incoming == primary_if))) { res = true; @@ -325,15 +345,17 @@ static bool bat_iv_ogm_can_aggregate(const struct batman_ogm_packet } /* if the incoming packet is sent via this one - * interface only - we still can aggregate */ + * interface only - we still can aggregate + */ if ((directlink) && - (new_batman_ogm_packet->header.ttl == 1) && + (new_bat_ogm_packet->header.ttl == 1) && (forw_packet->if_incoming == if_incoming) && /* packets from direct neighbors or * own secondary interface packets - * (= secondary interface packets in general) */ - (batman_ogm_packet->flags & DIRECTLINK || + * (= secondary interface packets in general) + */ + (batadv_ogm_packet->flags & BATADV_DIRECTLINK || (forw_packet->own && forw_packet->if_incoming != primary_if))) { res = true; @@ -343,29 +365,30 @@ static bool bat_iv_ogm_can_aggregate(const struct batman_ogm_packet out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); return res; } /* create a new aggregated packet and add this packet to it */ -static void bat_iv_ogm_aggregate_new(const unsigned char *packet_buff, - int packet_len, unsigned long send_time, - bool direct_link, - struct hard_iface *if_incoming, - int own_packet) +static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, + int packet_len, unsigned long send_time, + bool direct_link, + struct batadv_hard_iface *if_incoming, + int own_packet) { - struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct forw_packet *forw_packet_aggr; + struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct batadv_forw_packet *forw_packet_aggr; unsigned char *skb_buff; + unsigned int skb_size; if (!atomic_inc_not_zero(&if_incoming->refcount)) return; /* own packet should always be scheduled */ if (!own_packet) { - if (!atomic_dec_not_zero(&bat_priv->batman_queue_left)) { - bat_dbg(DBG_BATMAN, bat_priv, - "batman packet queue full\n"); + if (!batadv_atomic_dec_not_zero(&bat_priv->batman_queue_left)) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "batman packet queue full\n"); goto out; } } @@ -378,12 +401,12 @@ static void bat_iv_ogm_aggregate_new(const unsigned char *packet_buff, } if ((atomic_read(&bat_priv->aggregated_ogms)) && - (packet_len < MAX_AGGREGATION_BYTES)) - forw_packet_aggr->skb = dev_alloc_skb(MAX_AGGREGATION_BYTES + - ETH_HLEN); + (packet_len < BATADV_MAX_AGGREGATION_BYTES)) + skb_size = BATADV_MAX_AGGREGATION_BYTES + ETH_HLEN; else - forw_packet_aggr->skb = dev_alloc_skb(packet_len + ETH_HLEN); + skb_size = packet_len + ETH_HLEN; + forw_packet_aggr->skb = dev_alloc_skb(skb_size); if (!forw_packet_aggr->skb) { if (!own_packet) atomic_inc(&bat_priv->batman_queue_left); @@ -401,7 +424,7 @@ static void bat_iv_ogm_aggregate_new(const unsigned char *packet_buff, forw_packet_aggr->own = own_packet; forw_packet_aggr->if_incoming = if_incoming; forw_packet_aggr->num_packets = 0; - forw_packet_aggr->direct_link_flags = NO_FLAGS; + forw_packet_aggr->direct_link_flags = BATADV_NO_FLAGS; forw_packet_aggr->send_time = send_time; /* save packet direct link flag status */ @@ -415,20 +438,20 @@ static void bat_iv_ogm_aggregate_new(const unsigned char *packet_buff, /* start timer for this packet */ INIT_DELAYED_WORK(&forw_packet_aggr->delayed_work, - send_outstanding_bat_ogm_packet); - queue_delayed_work(bat_event_workqueue, + batadv_send_outstanding_bat_ogm_packet); + queue_delayed_work(batadv_event_workqueue, &forw_packet_aggr->delayed_work, send_time - jiffies); return; out: - hardif_free_ref(if_incoming); + batadv_hardif_free_ref(if_incoming); } /* aggregate a new packet into the existing ogm packet */ -static void bat_iv_ogm_aggregate(struct forw_packet *forw_packet_aggr, - const unsigned char *packet_buff, - int packet_len, bool direct_link) +static void batadv_iv_ogm_aggregate(struct batadv_forw_packet *forw_packet_aggr, + const unsigned char *packet_buff, + int packet_len, bool direct_link) { unsigned char *skb_buff; @@ -443,22 +466,25 @@ static void bat_iv_ogm_aggregate(struct forw_packet *forw_packet_aggr, (1 << forw_packet_aggr->num_packets); } -static void bat_iv_ogm_queue_add(struct bat_priv *bat_priv, - unsigned char *packet_buff, - int packet_len, struct hard_iface *if_incoming, - int own_packet, unsigned long send_time) +static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, + unsigned char *packet_buff, + int packet_len, + struct batadv_hard_iface *if_incoming, + int own_packet, unsigned long send_time) { - /** - * _aggr -> pointer to the packet we want to aggregate with + /* _aggr -> pointer to the packet we want to aggregate with * _pos -> pointer to the position in the queue */ - struct forw_packet *forw_packet_aggr = NULL, *forw_packet_pos = NULL; + struct batadv_forw_packet *forw_packet_aggr = NULL; + struct batadv_forw_packet *forw_packet_pos = NULL; struct hlist_node *tmp_node; - struct batman_ogm_packet *batman_ogm_packet; + struct batadv_ogm_packet *batadv_ogm_packet; bool direct_link; + unsigned long max_aggregation_jiffies; - batman_ogm_packet = (struct batman_ogm_packet *)packet_buff; - direct_link = batman_ogm_packet->flags & DIRECTLINK ? 1 : 0; + batadv_ogm_packet = (struct batadv_ogm_packet *)packet_buff; + direct_link = batadv_ogm_packet->flags & BATADV_DIRECTLINK ? 1 : 0; + max_aggregation_jiffies = msecs_to_jiffies(BATADV_MAX_AGGREGATION_MS); /* find position for the packet in the forward queue */ spin_lock_bh(&bat_priv->forw_bat_list_lock); @@ -466,11 +492,11 @@ static void bat_iv_ogm_queue_add(struct bat_priv *bat_priv, if ((atomic_read(&bat_priv->aggregated_ogms)) && (!own_packet)) { hlist_for_each_entry(forw_packet_pos, tmp_node, &bat_priv->forw_bat_list, list) { - if (bat_iv_ogm_can_aggregate(batman_ogm_packet, - bat_priv, packet_len, - send_time, direct_link, - if_incoming, - forw_packet_pos)) { + if (batadv_iv_ogm_can_aggregate(batadv_ogm_packet, + bat_priv, packet_len, + send_time, direct_link, + if_incoming, + forw_packet_pos)) { forw_packet_aggr = forw_packet_pos; break; } @@ -478,42 +504,41 @@ static void bat_iv_ogm_queue_add(struct bat_priv *bat_priv, } /* nothing to aggregate with - either aggregation disabled or no - * suitable aggregation packet found */ + * suitable aggregation packet found + */ if (!forw_packet_aggr) { /* the following section can run without the lock */ spin_unlock_bh(&bat_priv->forw_bat_list_lock); - /** - * if we could not aggregate this packet with one of the others + /* if we could not aggregate this packet with one of the others * we hold it back for a while, so that it might be aggregated * later on */ - if ((!own_packet) && - (atomic_read(&bat_priv->aggregated_ogms))) - send_time += msecs_to_jiffies(MAX_AGGREGATION_MS); + if (!own_packet && atomic_read(&bat_priv->aggregated_ogms)) + send_time += max_aggregation_jiffies; - bat_iv_ogm_aggregate_new(packet_buff, packet_len, - send_time, direct_link, - if_incoming, own_packet); + batadv_iv_ogm_aggregate_new(packet_buff, packet_len, + send_time, direct_link, + if_incoming, own_packet); } else { - bat_iv_ogm_aggregate(forw_packet_aggr, packet_buff, - packet_len, direct_link); + batadv_iv_ogm_aggregate(forw_packet_aggr, packet_buff, + packet_len, direct_link); spin_unlock_bh(&bat_priv->forw_bat_list_lock); } } -static void bat_iv_ogm_forward(struct orig_node *orig_node, - const struct ethhdr *ethhdr, - struct batman_ogm_packet *batman_ogm_packet, - bool is_single_hop_neigh, - bool is_from_best_next_hop, - struct hard_iface *if_incoming) +static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node, + const struct ethhdr *ethhdr, + struct batadv_ogm_packet *batadv_ogm_packet, + bool is_single_hop_neigh, + bool is_from_best_next_hop, + struct batadv_hard_iface *if_incoming) { - struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); uint8_t tt_num_changes; - if (batman_ogm_packet->header.ttl <= 1) { - bat_dbg(DBG_BATMAN, bat_priv, "ttl exceeded\n"); + if (batadv_ogm_packet->header.ttl <= 1) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "ttl exceeded\n"); return; } @@ -525,110 +550,113 @@ static void bat_iv_ogm_forward(struct orig_node *orig_node, * simply drop the ogm. */ if (is_single_hop_neigh) - batman_ogm_packet->flags |= NOT_BEST_NEXT_HOP; + batadv_ogm_packet->flags |= BATADV_NOT_BEST_NEXT_HOP; else return; } - tt_num_changes = batman_ogm_packet->tt_num_changes; + tt_num_changes = batadv_ogm_packet->tt_num_changes; - batman_ogm_packet->header.ttl--; - memcpy(batman_ogm_packet->prev_sender, ethhdr->h_source, ETH_ALEN); + batadv_ogm_packet->header.ttl--; + memcpy(batadv_ogm_packet->prev_sender, ethhdr->h_source, ETH_ALEN); /* apply hop penalty */ - batman_ogm_packet->tq = hop_penalty(batman_ogm_packet->tq, bat_priv); + batadv_ogm_packet->tq = batadv_hop_penalty(batadv_ogm_packet->tq, + bat_priv); - bat_dbg(DBG_BATMAN, bat_priv, - "Forwarding packet: tq: %i, ttl: %i\n", - batman_ogm_packet->tq, batman_ogm_packet->header.ttl); - - batman_ogm_packet->seqno = htonl(batman_ogm_packet->seqno); - batman_ogm_packet->tt_crc = htons(batman_ogm_packet->tt_crc); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Forwarding packet: tq: %i, ttl: %i\n", + batadv_ogm_packet->tq, batadv_ogm_packet->header.ttl); /* switch of primaries first hop flag when forwarding */ - batman_ogm_packet->flags &= ~PRIMARIES_FIRST_HOP; + batadv_ogm_packet->flags &= ~BATADV_PRIMARIES_FIRST_HOP; if (is_single_hop_neigh) - batman_ogm_packet->flags |= DIRECTLINK; + batadv_ogm_packet->flags |= BATADV_DIRECTLINK; else - batman_ogm_packet->flags &= ~DIRECTLINK; + batadv_ogm_packet->flags &= ~BATADV_DIRECTLINK; - bat_iv_ogm_queue_add(bat_priv, (unsigned char *)batman_ogm_packet, - BATMAN_OGM_HLEN + tt_len(tt_num_changes), - if_incoming, 0, bat_iv_ogm_fwd_send_time()); + batadv_iv_ogm_queue_add(bat_priv, (unsigned char *)batadv_ogm_packet, + BATADV_OGM_HLEN + batadv_tt_len(tt_num_changes), + if_incoming, 0, batadv_iv_ogm_fwd_send_time()); } -static void bat_iv_ogm_schedule(struct hard_iface *hard_iface, - int tt_num_changes) +static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) { - struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - struct batman_ogm_packet *batman_ogm_packet; - struct hard_iface *primary_if; - int vis_server; + struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + struct batadv_ogm_packet *batadv_ogm_packet; + struct batadv_hard_iface *primary_if; + int vis_server, tt_num_changes = 0; vis_server = atomic_read(&bat_priv->vis_mode); - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); + + if (hard_iface == primary_if) + tt_num_changes = batadv_tt_append_diff(bat_priv, + &hard_iface->packet_buff, + &hard_iface->packet_len, + BATADV_OGM_HLEN); - batman_ogm_packet = (struct batman_ogm_packet *)hard_iface->packet_buff; + batadv_ogm_packet = (struct batadv_ogm_packet *)hard_iface->packet_buff; /* change sequence number to network order */ - batman_ogm_packet->seqno = + batadv_ogm_packet->seqno = htonl((uint32_t)atomic_read(&hard_iface->seqno)); + atomic_inc(&hard_iface->seqno); - batman_ogm_packet->ttvn = atomic_read(&bat_priv->ttvn); - batman_ogm_packet->tt_crc = htons((uint16_t) - atomic_read(&bat_priv->tt_crc)); + batadv_ogm_packet->ttvn = atomic_read(&bat_priv->ttvn); + batadv_ogm_packet->tt_crc = htons(bat_priv->tt_crc); if (tt_num_changes >= 0) - batman_ogm_packet->tt_num_changes = tt_num_changes; + batadv_ogm_packet->tt_num_changes = tt_num_changes; - if (vis_server == VIS_TYPE_SERVER_SYNC) - batman_ogm_packet->flags |= VIS_SERVER; + if (vis_server == BATADV_VIS_TYPE_SERVER_SYNC) + batadv_ogm_packet->flags |= BATADV_VIS_SERVER; else - batman_ogm_packet->flags &= ~VIS_SERVER; + batadv_ogm_packet->flags &= ~BATADV_VIS_SERVER; if ((hard_iface == primary_if) && - (atomic_read(&bat_priv->gw_mode) == GW_MODE_SERVER)) - batman_ogm_packet->gw_flags = + (atomic_read(&bat_priv->gw_mode) == BATADV_GW_MODE_SERVER)) + batadv_ogm_packet->gw_flags = (uint8_t)atomic_read(&bat_priv->gw_bandwidth); else - batman_ogm_packet->gw_flags = NO_FLAGS; - - atomic_inc(&hard_iface->seqno); + batadv_ogm_packet->gw_flags = BATADV_NO_FLAGS; - slide_own_bcast_window(hard_iface); - bat_iv_ogm_queue_add(bat_priv, hard_iface->packet_buff, - hard_iface->packet_len, hard_iface, 1, - bat_iv_ogm_emit_send_time(bat_priv)); + batadv_slide_own_bcast_window(hard_iface); + batadv_iv_ogm_queue_add(bat_priv, hard_iface->packet_buff, + hard_iface->packet_len, hard_iface, 1, + batadv_iv_ogm_emit_send_time(bat_priv)); if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); } -static void bat_iv_ogm_orig_update(struct bat_priv *bat_priv, - struct orig_node *orig_node, - const struct ethhdr *ethhdr, - const struct batman_ogm_packet - *batman_ogm_packet, - struct hard_iface *if_incoming, - const unsigned char *tt_buff, - int is_duplicate) +static void +batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + const struct ethhdr *ethhdr, + const struct batadv_ogm_packet *batadv_ogm_packet, + struct batadv_hard_iface *if_incoming, + const unsigned char *tt_buff, + int is_duplicate) { - struct neigh_node *neigh_node = NULL, *tmp_neigh_node = NULL; - struct neigh_node *router = NULL; - struct orig_node *orig_node_tmp; + struct batadv_neigh_node *neigh_node = NULL, *tmp_neigh_node = NULL; + struct batadv_neigh_node *router = NULL; + struct batadv_orig_node *orig_node_tmp; struct hlist_node *node; uint8_t bcast_own_sum_orig, bcast_own_sum_neigh; + uint8_t *neigh_addr; - bat_dbg(DBG_BATMAN, bat_priv, - "update_originator(): Searching and updating originator entry of received packet\n"); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "update_originator(): Searching and updating originator entry of received packet\n"); rcu_read_lock(); hlist_for_each_entry_rcu(tmp_neigh_node, node, &orig_node->neigh_list, list) { - if (compare_eth(tmp_neigh_node->addr, ethhdr->h_source) && - (tmp_neigh_node->if_incoming == if_incoming) && - atomic_inc_not_zero(&tmp_neigh_node->refcount)) { + neigh_addr = tmp_neigh_node->addr; + if (batadv_compare_eth(neigh_addr, ethhdr->h_source) && + tmp_neigh_node->if_incoming == if_incoming && + atomic_inc_not_zero(&tmp_neigh_node->refcount)) { if (neigh_node) - neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref(neigh_node); neigh_node = tmp_neigh_node; continue; } @@ -637,53 +665,55 @@ static void bat_iv_ogm_orig_update(struct bat_priv *bat_priv, continue; spin_lock_bh(&tmp_neigh_node->lq_update_lock); - ring_buffer_set(tmp_neigh_node->tq_recv, - &tmp_neigh_node->tq_index, 0); + batadv_ring_buffer_set(tmp_neigh_node->tq_recv, + &tmp_neigh_node->tq_index, 0); tmp_neigh_node->tq_avg = - ring_buffer_avg(tmp_neigh_node->tq_recv); + batadv_ring_buffer_avg(tmp_neigh_node->tq_recv); spin_unlock_bh(&tmp_neigh_node->lq_update_lock); } if (!neigh_node) { - struct orig_node *orig_tmp; + struct batadv_orig_node *orig_tmp; - orig_tmp = get_orig_node(bat_priv, ethhdr->h_source); + orig_tmp = batadv_get_orig_node(bat_priv, ethhdr->h_source); if (!orig_tmp) goto unlock; - neigh_node = bat_iv_ogm_neigh_new(if_incoming, ethhdr->h_source, - orig_node, orig_tmp, - batman_ogm_packet->seqno); + neigh_node = batadv_iv_ogm_neigh_new(if_incoming, + ethhdr->h_source, + orig_node, orig_tmp, + batadv_ogm_packet->seqno); - orig_node_free_ref(orig_tmp); + batadv_orig_node_free_ref(orig_tmp); if (!neigh_node) goto unlock; } else - bat_dbg(DBG_BATMAN, bat_priv, - "Updating existing last-hop neighbor of originator\n"); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Updating existing last-hop neighbor of originator\n"); rcu_read_unlock(); - orig_node->flags = batman_ogm_packet->flags; + orig_node->flags = batadv_ogm_packet->flags; neigh_node->last_seen = jiffies; spin_lock_bh(&neigh_node->lq_update_lock); - ring_buffer_set(neigh_node->tq_recv, - &neigh_node->tq_index, - batman_ogm_packet->tq); - neigh_node->tq_avg = ring_buffer_avg(neigh_node->tq_recv); + batadv_ring_buffer_set(neigh_node->tq_recv, + &neigh_node->tq_index, + batadv_ogm_packet->tq); + neigh_node->tq_avg = batadv_ring_buffer_avg(neigh_node->tq_recv); spin_unlock_bh(&neigh_node->lq_update_lock); if (!is_duplicate) { - orig_node->last_ttl = batman_ogm_packet->header.ttl; - neigh_node->last_ttl = batman_ogm_packet->header.ttl; + orig_node->last_ttl = batadv_ogm_packet->header.ttl; + neigh_node->last_ttl = batadv_ogm_packet->header.ttl; } - bonding_candidate_add(orig_node, neigh_node); + batadv_bonding_candidate_add(orig_node, neigh_node); /* if this neighbor already is our next hop there is nothing - * to change */ - router = orig_node_get_router(orig_node); + * to change + */ + router = batadv_orig_node_get_router(orig_node); if (router == neigh_node) goto update_tt; @@ -692,7 +722,8 @@ static void bat_iv_ogm_orig_update(struct bat_priv *bat_priv, goto update_tt; /* if the TQ is the same and the link not more symmetric we - * won't consider it either */ + * won't consider it either + */ if (router && (neigh_node->tq_avg == router->tq_avg)) { orig_node_tmp = router->orig_node; spin_lock_bh(&orig_node_tmp->ogm_cnt_lock); @@ -710,30 +741,31 @@ static void bat_iv_ogm_orig_update(struct bat_priv *bat_priv, goto update_tt; } - update_route(bat_priv, orig_node, neigh_node); + batadv_update_route(bat_priv, orig_node, neigh_node); update_tt: /* I have to check for transtable changes only if the OGM has been - * sent through a primary interface */ - if (((batman_ogm_packet->orig != ethhdr->h_source) && - (batman_ogm_packet->header.ttl > 2)) || - (batman_ogm_packet->flags & PRIMARIES_FIRST_HOP)) - tt_update_orig(bat_priv, orig_node, tt_buff, - batman_ogm_packet->tt_num_changes, - batman_ogm_packet->ttvn, - batman_ogm_packet->tt_crc); + * sent through a primary interface + */ + if (((batadv_ogm_packet->orig != ethhdr->h_source) && + (batadv_ogm_packet->header.ttl > 2)) || + (batadv_ogm_packet->flags & BATADV_PRIMARIES_FIRST_HOP)) + batadv_tt_update_orig(bat_priv, orig_node, tt_buff, + batadv_ogm_packet->tt_num_changes, + batadv_ogm_packet->ttvn, + ntohs(batadv_ogm_packet->tt_crc)); - if (orig_node->gw_flags != batman_ogm_packet->gw_flags) - gw_node_update(bat_priv, orig_node, - batman_ogm_packet->gw_flags); + if (orig_node->gw_flags != batadv_ogm_packet->gw_flags) + batadv_gw_node_update(bat_priv, orig_node, + batadv_ogm_packet->gw_flags); - orig_node->gw_flags = batman_ogm_packet->gw_flags; + orig_node->gw_flags = batadv_ogm_packet->gw_flags; /* restart gateway selection if fast or late switching was enabled */ if ((orig_node->gw_flags) && - (atomic_read(&bat_priv->gw_mode) == GW_MODE_CLIENT) && + (atomic_read(&bat_priv->gw_mode) == BATADV_GW_MODE_CLIENT) && (atomic_read(&bat_priv->gw_sel_class) > 2)) - gw_check_election(bat_priv, orig_node); + batadv_gw_check_election(bat_priv, orig_node); goto out; @@ -741,29 +773,32 @@ unlock: rcu_read_unlock(); out: if (neigh_node) - neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref(neigh_node); if (router) - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); } -static int bat_iv_ogm_calc_tq(struct orig_node *orig_node, - struct orig_node *orig_neigh_node, - struct batman_ogm_packet *batman_ogm_packet, - struct hard_iface *if_incoming) +static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, + struct batadv_orig_node *orig_neigh_node, + struct batadv_ogm_packet *batadv_ogm_packet, + struct batadv_hard_iface *if_incoming) { - struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct neigh_node *neigh_node = NULL, *tmp_neigh_node; + struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct batadv_neigh_node *neigh_node = NULL, *tmp_neigh_node; struct hlist_node *node; uint8_t total_count; - uint8_t orig_eq_count, neigh_rq_count, tq_own; - int tq_asym_penalty, ret = 0; + uint8_t orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own; + unsigned int neigh_rq_inv_cube, neigh_rq_max_cube; + int tq_asym_penalty, inv_asym_penalty, ret = 0; + unsigned int combined_tq; /* find corresponding one hop neighbor */ rcu_read_lock(); hlist_for_each_entry_rcu(tmp_neigh_node, node, &orig_neigh_node->neigh_list, list) { - if (!compare_eth(tmp_neigh_node->addr, orig_neigh_node->orig)) + if (!batadv_compare_eth(tmp_neigh_node->addr, + orig_neigh_node->orig)) continue; if (tmp_neigh_node->if_incoming != if_incoming) @@ -778,11 +813,11 @@ static int bat_iv_ogm_calc_tq(struct orig_node *orig_node, rcu_read_unlock(); if (!neigh_node) - neigh_node = bat_iv_ogm_neigh_new(if_incoming, - orig_neigh_node->orig, - orig_neigh_node, - orig_neigh_node, - batman_ogm_packet->seqno); + neigh_node = batadv_iv_ogm_neigh_new(if_incoming, + orig_neigh_node->orig, + orig_neigh_node, + orig_neigh_node, + batadv_ogm_packet->seqno); if (!neigh_node) goto out; @@ -803,47 +838,52 @@ static int bat_iv_ogm_calc_tq(struct orig_node *orig_node, total_count = (orig_eq_count > neigh_rq_count ? neigh_rq_count : orig_eq_count); - /* if we have too few packets (too less data) we set tq_own to zero */ - /* if we receive too few packets it is not considered bidirectional */ - if ((total_count < TQ_LOCAL_BIDRECT_SEND_MINIMUM) || - (neigh_rq_count < TQ_LOCAL_BIDRECT_RECV_MINIMUM)) + /* if we have too few packets (too less data) we set tq_own to zero + * if we receive too few packets it is not considered bidirectional + */ + if (total_count < BATADV_TQ_LOCAL_BIDRECT_SEND_MINIMUM || + neigh_rq_count < BATADV_TQ_LOCAL_BIDRECT_RECV_MINIMUM) tq_own = 0; else /* neigh_node->real_packet_count is never zero as we * only purge old information when getting new - * information */ - tq_own = (TQ_MAX_VALUE * total_count) / neigh_rq_count; + * information + */ + tq_own = (BATADV_TQ_MAX_VALUE * total_count) / neigh_rq_count; /* 1 - ((1-x) ** 3), normalized to TQ_MAX_VALUE this does * affect the nearly-symmetric links only a little, but * punishes asymmetric links more. This will give a value * between 0 and TQ_MAX_VALUE */ - tq_asym_penalty = TQ_MAX_VALUE - (TQ_MAX_VALUE * - (TQ_LOCAL_WINDOW_SIZE - neigh_rq_count) * - (TQ_LOCAL_WINDOW_SIZE - neigh_rq_count) * - (TQ_LOCAL_WINDOW_SIZE - neigh_rq_count)) / - (TQ_LOCAL_WINDOW_SIZE * - TQ_LOCAL_WINDOW_SIZE * - TQ_LOCAL_WINDOW_SIZE); - - batman_ogm_packet->tq = ((batman_ogm_packet->tq * tq_own - * tq_asym_penalty) / - (TQ_MAX_VALUE * TQ_MAX_VALUE)); - - bat_dbg(DBG_BATMAN, bat_priv, - "bidirectional: orig = %-15pM neigh = %-15pM => own_bcast = %2i, real recv = %2i, local tq: %3i, asym_penalty: %3i, total tq: %3i\n", - orig_node->orig, orig_neigh_node->orig, total_count, - neigh_rq_count, tq_own, tq_asym_penalty, batman_ogm_packet->tq); + neigh_rq_inv = BATADV_TQ_LOCAL_WINDOW_SIZE - neigh_rq_count; + neigh_rq_inv_cube = neigh_rq_inv * neigh_rq_inv * neigh_rq_inv; + neigh_rq_max_cube = BATADV_TQ_LOCAL_WINDOW_SIZE * + BATADV_TQ_LOCAL_WINDOW_SIZE * + BATADV_TQ_LOCAL_WINDOW_SIZE; + inv_asym_penalty = BATADV_TQ_MAX_VALUE * neigh_rq_inv_cube; + inv_asym_penalty /= neigh_rq_max_cube; + tq_asym_penalty = BATADV_TQ_MAX_VALUE - inv_asym_penalty; + + combined_tq = batadv_ogm_packet->tq * tq_own * tq_asym_penalty; + combined_tq /= BATADV_TQ_MAX_VALUE * BATADV_TQ_MAX_VALUE; + batadv_ogm_packet->tq = combined_tq; + + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "bidirectional: orig = %-15pM neigh = %-15pM => own_bcast = %2i, real recv = %2i, local tq: %3i, asym_penalty: %3i, total tq: %3i\n", + orig_node->orig, orig_neigh_node->orig, total_count, + neigh_rq_count, tq_own, + tq_asym_penalty, batadv_ogm_packet->tq); /* if link has the minimum required transmission quality - * consider it bidirectional */ - if (batman_ogm_packet->tq >= TQ_TOTAL_BIDRECT_LIMIT) + * consider it bidirectional + */ + if (batadv_ogm_packet->tq >= BATADV_TQ_TOTAL_BIDRECT_LIMIT) ret = 1; out: if (neigh_node) - neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref(neigh_node); return ret; } @@ -855,90 +895,94 @@ out: * -1 the packet is old and has been received while the seqno window * was protected. Caller should drop it. */ -static int bat_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, - const struct batman_ogm_packet - *batman_ogm_packet, - const struct hard_iface *if_incoming) +static int +batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, + const struct batadv_ogm_packet *batadv_ogm_packet, + const struct batadv_hard_iface *if_incoming) { - struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct orig_node *orig_node; - struct neigh_node *tmp_neigh_node; + struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct batadv_orig_node *orig_node; + struct batadv_neigh_node *tmp_neigh_node; struct hlist_node *node; int is_duplicate = 0; int32_t seq_diff; int need_update = 0; int set_mark, ret = -1; + uint32_t seqno = ntohl(batadv_ogm_packet->seqno); + uint8_t *neigh_addr; - orig_node = get_orig_node(bat_priv, batman_ogm_packet->orig); + orig_node = batadv_get_orig_node(bat_priv, batadv_ogm_packet->orig); if (!orig_node) return 0; spin_lock_bh(&orig_node->ogm_cnt_lock); - seq_diff = batman_ogm_packet->seqno - orig_node->last_real_seqno; + seq_diff = seqno - orig_node->last_real_seqno; /* signalize caller that the packet is to be dropped. */ if (!hlist_empty(&orig_node->neigh_list) && - window_protected(bat_priv, seq_diff, - &orig_node->batman_seqno_reset)) + batadv_window_protected(bat_priv, seq_diff, + &orig_node->batman_seqno_reset)) goto out; rcu_read_lock(); hlist_for_each_entry_rcu(tmp_neigh_node, node, &orig_node->neigh_list, list) { - is_duplicate |= bat_test_bit(tmp_neigh_node->real_bits, - orig_node->last_real_seqno, - batman_ogm_packet->seqno); + is_duplicate |= batadv_test_bit(tmp_neigh_node->real_bits, + orig_node->last_real_seqno, + seqno); - if (compare_eth(tmp_neigh_node->addr, ethhdr->h_source) && - (tmp_neigh_node->if_incoming == if_incoming)) + neigh_addr = tmp_neigh_node->addr; + if (batadv_compare_eth(neigh_addr, ethhdr->h_source) && + tmp_neigh_node->if_incoming == if_incoming) set_mark = 1; else set_mark = 0; /* if the window moved, set the update flag. */ - need_update |= bit_get_packet(bat_priv, - tmp_neigh_node->real_bits, - seq_diff, set_mark); + need_update |= batadv_bit_get_packet(bat_priv, + tmp_neigh_node->real_bits, + seq_diff, set_mark); tmp_neigh_node->real_packet_count = bitmap_weight(tmp_neigh_node->real_bits, - TQ_LOCAL_WINDOW_SIZE); + BATADV_TQ_LOCAL_WINDOW_SIZE); } rcu_read_unlock(); if (need_update) { - bat_dbg(DBG_BATMAN, bat_priv, - "updating last_seqno: old %u, new %u\n", - orig_node->last_real_seqno, batman_ogm_packet->seqno); - orig_node->last_real_seqno = batman_ogm_packet->seqno; + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "updating last_seqno: old %u, new %u\n", + orig_node->last_real_seqno, seqno); + orig_node->last_real_seqno = seqno; } ret = is_duplicate; out: spin_unlock_bh(&orig_node->ogm_cnt_lock); - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); return ret; } -static void bat_iv_ogm_process(const struct ethhdr *ethhdr, - struct batman_ogm_packet *batman_ogm_packet, - const unsigned char *tt_buff, - struct hard_iface *if_incoming) +static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, + struct batadv_ogm_packet *batadv_ogm_packet, + const unsigned char *tt_buff, + struct batadv_hard_iface *if_incoming) { - struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct hard_iface *hard_iface; - struct orig_node *orig_neigh_node, *orig_node; - struct neigh_node *router = NULL, *router_router = NULL; - struct neigh_node *orig_neigh_router = NULL; + struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct batadv_hard_iface *hard_iface; + struct batadv_orig_node *orig_neigh_node, *orig_node; + struct batadv_neigh_node *router = NULL, *router_router = NULL; + struct batadv_neigh_node *orig_neigh_router = NULL; int has_directlink_flag; int is_my_addr = 0, is_my_orig = 0, is_my_oldorig = 0; - int is_broadcast = 0, is_bidirectional; + int is_broadcast = 0, is_bidirect; bool is_single_hop_neigh = false; bool is_from_best_next_hop = false; - int is_duplicate; + int is_duplicate, sameseq, simlar_ttl; uint32_t if_incoming_seqno; + uint8_t *prev_sender; /* Silently drop when the batman packet is actually not a * correct packet. @@ -948,49 +992,53 @@ static void bat_iv_ogm_process(const struct ethhdr *ethhdr, * it as an additional length. * * TODO: A more sane solution would be to have a bit in the - * batman_ogm_packet to detect whether the packet is the last + * batadv_ogm_packet to detect whether the packet is the last * packet in an aggregation. Here we expect that the padding * is always zero (or not 0x01) */ - if (batman_ogm_packet->header.packet_type != BAT_IV_OGM) + if (batadv_ogm_packet->header.packet_type != BATADV_IV_OGM) return; /* could be changed by schedule_own_packet() */ if_incoming_seqno = atomic_read(&if_incoming->seqno); - has_directlink_flag = (batman_ogm_packet->flags & DIRECTLINK ? 1 : 0); + if (batadv_ogm_packet->flags & BATADV_DIRECTLINK) + has_directlink_flag = 1; + else + has_directlink_flag = 0; - if (compare_eth(ethhdr->h_source, batman_ogm_packet->orig)) + if (batadv_compare_eth(ethhdr->h_source, batadv_ogm_packet->orig)) is_single_hop_neigh = true; - bat_dbg(DBG_BATMAN, bat_priv, - "Received BATMAN packet via NB: %pM, IF: %s [%pM] (from OG: %pM, via prev OG: %pM, seqno %u, ttvn %u, crc %u, changes %u, td %d, TTL %d, V %d, IDF %d)\n", - ethhdr->h_source, if_incoming->net_dev->name, - if_incoming->net_dev->dev_addr, batman_ogm_packet->orig, - batman_ogm_packet->prev_sender, batman_ogm_packet->seqno, - batman_ogm_packet->ttvn, batman_ogm_packet->tt_crc, - batman_ogm_packet->tt_num_changes, batman_ogm_packet->tq, - batman_ogm_packet->header.ttl, - batman_ogm_packet->header.version, has_directlink_flag); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Received BATMAN packet via NB: %pM, IF: %s [%pM] (from OG: %pM, via prev OG: %pM, seqno %u, ttvn %u, crc %u, changes %u, td %d, TTL %d, V %d, IDF %d)\n", + ethhdr->h_source, if_incoming->net_dev->name, + if_incoming->net_dev->dev_addr, batadv_ogm_packet->orig, + batadv_ogm_packet->prev_sender, + ntohl(batadv_ogm_packet->seqno), batadv_ogm_packet->ttvn, + ntohs(batadv_ogm_packet->tt_crc), + batadv_ogm_packet->tt_num_changes, batadv_ogm_packet->tq, + batadv_ogm_packet->header.ttl, + batadv_ogm_packet->header.version, has_directlink_flag); rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &hardif_list, list) { - if (hard_iface->if_status != IF_ACTIVE) + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->if_status != BATADV_IF_ACTIVE) continue; if (hard_iface->soft_iface != if_incoming->soft_iface) continue; - if (compare_eth(ethhdr->h_source, - hard_iface->net_dev->dev_addr)) + if (batadv_compare_eth(ethhdr->h_source, + hard_iface->net_dev->dev_addr)) is_my_addr = 1; - if (compare_eth(batman_ogm_packet->orig, - hard_iface->net_dev->dev_addr)) + if (batadv_compare_eth(batadv_ogm_packet->orig, + hard_iface->net_dev->dev_addr)) is_my_orig = 1; - if (compare_eth(batman_ogm_packet->prev_sender, - hard_iface->net_dev->dev_addr)) + if (batadv_compare_eth(batadv_ogm_packet->prev_sender, + hard_iface->net_dev->dev_addr)) is_my_oldorig = 1; if (is_broadcast_ether_addr(ethhdr->h_source)) @@ -998,268 +1046,278 @@ static void bat_iv_ogm_process(const struct ethhdr *ethhdr, } rcu_read_unlock(); - if (batman_ogm_packet->header.version != COMPAT_VERSION) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: incompatible batman version (%i)\n", - batman_ogm_packet->header.version); + if (batadv_ogm_packet->header.version != BATADV_COMPAT_VERSION) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: incompatible batman version (%i)\n", + batadv_ogm_packet->header.version); return; } if (is_my_addr) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: received my own broadcast (sender: %pM)\n", - ethhdr->h_source); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: received my own broadcast (sender: %pM)\n", + ethhdr->h_source); return; } if (is_broadcast) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: ignoring all packets with broadcast source addr (sender: %pM)\n", - ethhdr->h_source); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: ignoring all packets with broadcast source addr (sender: %pM)\n", + ethhdr->h_source); return; } if (is_my_orig) { unsigned long *word; int offset; + int32_t bit_pos; + int16_t if_num; + uint8_t *weight; - orig_neigh_node = get_orig_node(bat_priv, ethhdr->h_source); + orig_neigh_node = batadv_get_orig_node(bat_priv, + ethhdr->h_source); if (!orig_neigh_node) return; /* neighbor has to indicate direct link and it has to - * come via the corresponding interface */ - /* save packet seqno for bidirectional check */ + * come via the corresponding interface + * save packet seqno for bidirectional check + */ if (has_directlink_flag && - compare_eth(if_incoming->net_dev->dev_addr, - batman_ogm_packet->orig)) { - offset = if_incoming->if_num * NUM_WORDS; + batadv_compare_eth(if_incoming->net_dev->dev_addr, + batadv_ogm_packet->orig)) { + if_num = if_incoming->if_num; + offset = if_num * BATADV_NUM_WORDS; spin_lock_bh(&orig_neigh_node->ogm_cnt_lock); word = &(orig_neigh_node->bcast_own[offset]); - bat_set_bit(word, - if_incoming_seqno - - batman_ogm_packet->seqno - 2); - orig_neigh_node->bcast_own_sum[if_incoming->if_num] = - bitmap_weight(word, TQ_LOCAL_WINDOW_SIZE); + bit_pos = if_incoming_seqno - 2; + bit_pos -= ntohl(batadv_ogm_packet->seqno); + batadv_set_bit(word, bit_pos); + weight = &orig_neigh_node->bcast_own_sum[if_num]; + *weight = bitmap_weight(word, + BATADV_TQ_LOCAL_WINDOW_SIZE); spin_unlock_bh(&orig_neigh_node->ogm_cnt_lock); } - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: originator packet from myself (via neighbor)\n"); - orig_node_free_ref(orig_neigh_node); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: originator packet from myself (via neighbor)\n"); + batadv_orig_node_free_ref(orig_neigh_node); return; } if (is_my_oldorig) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: ignoring all rebroadcast echos (sender: %pM)\n", - ethhdr->h_source); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: ignoring all rebroadcast echos (sender: %pM)\n", + ethhdr->h_source); return; } - if (batman_ogm_packet->flags & NOT_BEST_NEXT_HOP) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: ignoring all packets not forwarded from the best next hop (sender: %pM)\n", - ethhdr->h_source); + if (batadv_ogm_packet->flags & BATADV_NOT_BEST_NEXT_HOP) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: ignoring all packets not forwarded from the best next hop (sender: %pM)\n", + ethhdr->h_source); return; } - orig_node = get_orig_node(bat_priv, batman_ogm_packet->orig); + orig_node = batadv_get_orig_node(bat_priv, batadv_ogm_packet->orig); if (!orig_node) return; - is_duplicate = bat_iv_ogm_update_seqnos(ethhdr, batman_ogm_packet, - if_incoming); + is_duplicate = batadv_iv_ogm_update_seqnos(ethhdr, batadv_ogm_packet, + if_incoming); if (is_duplicate == -1) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: packet within seqno protection time (sender: %pM)\n", - ethhdr->h_source); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: packet within seqno protection time (sender: %pM)\n", + ethhdr->h_source); goto out; } - if (batman_ogm_packet->tq == 0) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: originator packet with tq equal 0\n"); + if (batadv_ogm_packet->tq == 0) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: originator packet with tq equal 0\n"); goto out; } - router = orig_node_get_router(orig_node); + router = batadv_orig_node_get_router(orig_node); if (router) - router_router = orig_node_get_router(router->orig_node); + router_router = batadv_orig_node_get_router(router->orig_node); if ((router && router->tq_avg != 0) && - (compare_eth(router->addr, ethhdr->h_source))) + (batadv_compare_eth(router->addr, ethhdr->h_source))) is_from_best_next_hop = true; + prev_sender = batadv_ogm_packet->prev_sender; /* avoid temporary routing loops */ if (router && router_router && - (compare_eth(router->addr, batman_ogm_packet->prev_sender)) && - !(compare_eth(batman_ogm_packet->orig, - batman_ogm_packet->prev_sender)) && - (compare_eth(router->addr, router_router->addr))) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: ignoring all rebroadcast packets that may make me loop (sender: %pM)\n", - ethhdr->h_source); + (batadv_compare_eth(router->addr, prev_sender)) && + !(batadv_compare_eth(batadv_ogm_packet->orig, prev_sender)) && + (batadv_compare_eth(router->addr, router_router->addr))) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: ignoring all rebroadcast packets that may make me loop (sender: %pM)\n", + ethhdr->h_source); goto out; } /* if sender is a direct neighbor the sender mac equals - * originator mac */ + * originator mac + */ orig_neigh_node = (is_single_hop_neigh ? orig_node : - get_orig_node(bat_priv, ethhdr->h_source)); + batadv_get_orig_node(bat_priv, ethhdr->h_source)); if (!orig_neigh_node) goto out; - orig_neigh_router = orig_node_get_router(orig_neigh_node); + orig_neigh_router = batadv_orig_node_get_router(orig_neigh_node); /* drop packet if sender is not a direct neighbor and if we - * don't route towards it */ + * don't route towards it + */ if (!is_single_hop_neigh && (!orig_neigh_router)) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: OGM via unknown neighbor!\n"); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: OGM via unknown neighbor!\n"); goto out_neigh; } - is_bidirectional = bat_iv_ogm_calc_tq(orig_node, orig_neigh_node, - batman_ogm_packet, if_incoming); + is_bidirect = batadv_iv_ogm_calc_tq(orig_node, orig_neigh_node, + batadv_ogm_packet, if_incoming); - bonding_save_primary(orig_node, orig_neigh_node, batman_ogm_packet); + batadv_bonding_save_primary(orig_node, orig_neigh_node, + batadv_ogm_packet); /* update ranking if it is not a duplicate or has the same - * seqno and similar ttl as the non-duplicate */ - if (is_bidirectional && - (!is_duplicate || - ((orig_node->last_real_seqno == batman_ogm_packet->seqno) && - (orig_node->last_ttl - 3 <= batman_ogm_packet->header.ttl)))) - bat_iv_ogm_orig_update(bat_priv, orig_node, ethhdr, - batman_ogm_packet, if_incoming, - tt_buff, is_duplicate); + * seqno and similar ttl as the non-duplicate + */ + sameseq = orig_node->last_real_seqno == ntohl(batadv_ogm_packet->seqno); + simlar_ttl = orig_node->last_ttl - 3 <= batadv_ogm_packet->header.ttl; + if (is_bidirect && (!is_duplicate || (sameseq && simlar_ttl))) + batadv_iv_ogm_orig_update(bat_priv, orig_node, ethhdr, + batadv_ogm_packet, if_incoming, + tt_buff, is_duplicate); /* is single hop (direct) neighbor */ if (is_single_hop_neigh) { /* mark direct link on incoming interface */ - bat_iv_ogm_forward(orig_node, ethhdr, batman_ogm_packet, - is_single_hop_neigh, is_from_best_next_hop, - if_incoming); + batadv_iv_ogm_forward(orig_node, ethhdr, batadv_ogm_packet, + is_single_hop_neigh, + is_from_best_next_hop, if_incoming); - bat_dbg(DBG_BATMAN, bat_priv, - "Forwarding packet: rebroadcast neighbor packet with direct link flag\n"); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Forwarding packet: rebroadcast neighbor packet with direct link flag\n"); goto out_neigh; } /* multihop originator */ - if (!is_bidirectional) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: not received via bidirectional link\n"); + if (!is_bidirect) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: not received via bidirectional link\n"); goto out_neigh; } if (is_duplicate) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: duplicate packet received\n"); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: duplicate packet received\n"); goto out_neigh; } - bat_dbg(DBG_BATMAN, bat_priv, - "Forwarding packet: rebroadcast originator packet\n"); - bat_iv_ogm_forward(orig_node, ethhdr, batman_ogm_packet, - is_single_hop_neigh, is_from_best_next_hop, - if_incoming); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Forwarding packet: rebroadcast originator packet\n"); + batadv_iv_ogm_forward(orig_node, ethhdr, batadv_ogm_packet, + is_single_hop_neigh, is_from_best_next_hop, + if_incoming); out_neigh: if ((orig_neigh_node) && (!is_single_hop_neigh)) - orig_node_free_ref(orig_neigh_node); + batadv_orig_node_free_ref(orig_neigh_node); out: if (router) - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); if (router_router) - neigh_node_free_ref(router_router); + batadv_neigh_node_free_ref(router_router); if (orig_neigh_router) - neigh_node_free_ref(orig_neigh_router); + batadv_neigh_node_free_ref(orig_neigh_router); - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); } -static int bat_iv_ogm_receive(struct sk_buff *skb, - struct hard_iface *if_incoming) +static int batadv_iv_ogm_receive(struct sk_buff *skb, + struct batadv_hard_iface *if_incoming) { - struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct batman_ogm_packet *batman_ogm_packet; + struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct batadv_ogm_packet *batadv_ogm_packet; struct ethhdr *ethhdr; int buff_pos = 0, packet_len; unsigned char *tt_buff, *packet_buff; bool ret; - ret = check_management_packet(skb, if_incoming, BATMAN_OGM_HLEN); + ret = batadv_check_management_packet(skb, if_incoming, BATADV_OGM_HLEN); if (!ret) return NET_RX_DROP; /* did we receive a B.A.T.M.A.N. IV OGM packet on an interface * that does not have B.A.T.M.A.N. IV enabled ? */ - if (bat_priv->bat_algo_ops->bat_ogm_emit != bat_iv_ogm_emit) + if (bat_priv->bat_algo_ops->bat_ogm_emit != batadv_iv_ogm_emit) return NET_RX_DROP; + batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_RX); + batadv_add_counter(bat_priv, BATADV_CNT_MGMT_RX_BYTES, + skb->len + ETH_HLEN); + packet_len = skb_headlen(skb); ethhdr = (struct ethhdr *)skb_mac_header(skb); packet_buff = skb->data; - batman_ogm_packet = (struct batman_ogm_packet *)packet_buff; + batadv_ogm_packet = (struct batadv_ogm_packet *)packet_buff; /* unpack the aggregated packets and process them one by one */ do { - /* network to host order for our 32bit seqno and the - orig_interval */ - batman_ogm_packet->seqno = ntohl(batman_ogm_packet->seqno); - batman_ogm_packet->tt_crc = ntohs(batman_ogm_packet->tt_crc); - - tt_buff = packet_buff + buff_pos + BATMAN_OGM_HLEN; + tt_buff = packet_buff + buff_pos + BATADV_OGM_HLEN; - bat_iv_ogm_process(ethhdr, batman_ogm_packet, - tt_buff, if_incoming); + batadv_iv_ogm_process(ethhdr, batadv_ogm_packet, tt_buff, + if_incoming); - buff_pos += BATMAN_OGM_HLEN + - tt_len(batman_ogm_packet->tt_num_changes); + buff_pos += BATADV_OGM_HLEN; + buff_pos += batadv_tt_len(batadv_ogm_packet->tt_num_changes); - batman_ogm_packet = (struct batman_ogm_packet *) + batadv_ogm_packet = (struct batadv_ogm_packet *) (packet_buff + buff_pos); - } while (bat_iv_ogm_aggr_packet(buff_pos, packet_len, - batman_ogm_packet->tt_num_changes)); + } while (batadv_iv_ogm_aggr_packet(buff_pos, packet_len, + batadv_ogm_packet->tt_num_changes)); kfree_skb(skb); return NET_RX_SUCCESS; } -static struct bat_algo_ops batman_iv __read_mostly = { - .name = "BATMAN IV", - .bat_iface_enable = bat_iv_ogm_iface_enable, - .bat_iface_disable = bat_iv_ogm_iface_disable, - .bat_iface_update_mac = bat_iv_ogm_iface_update_mac, - .bat_primary_iface_set = bat_iv_ogm_primary_iface_set, - .bat_ogm_schedule = bat_iv_ogm_schedule, - .bat_ogm_emit = bat_iv_ogm_emit, +static struct batadv_algo_ops batadv_batman_iv __read_mostly = { + .name = "BATMAN_IV", + .bat_iface_enable = batadv_iv_ogm_iface_enable, + .bat_iface_disable = batadv_iv_ogm_iface_disable, + .bat_iface_update_mac = batadv_iv_ogm_iface_update_mac, + .bat_primary_iface_set = batadv_iv_ogm_primary_iface_set, + .bat_ogm_schedule = batadv_iv_ogm_schedule, + .bat_ogm_emit = batadv_iv_ogm_emit, }; -int __init bat_iv_init(void) +int __init batadv_iv_init(void) { int ret; /* batman originator packet */ - ret = recv_handler_register(BAT_IV_OGM, bat_iv_ogm_receive); + ret = batadv_recv_handler_register(BATADV_IV_OGM, + batadv_iv_ogm_receive); if (ret < 0) goto out; - ret = bat_algo_register(&batman_iv); + ret = batadv_algo_register(&batadv_batman_iv); if (ret < 0) goto handler_unregister; goto out; handler_unregister: - recv_handler_unregister(BAT_IV_OGM); + batadv_recv_handler_unregister(BATADV_IV_OGM); out: return ret; } diff --git a/net/batman-adv/bat_sysfs.c b/net/batman-adv/bat_sysfs.c deleted file mode 100644 index 5bc7b66d32d..00000000000 --- a/net/batman-adv/bat_sysfs.c +++ /dev/null @@ -1,735 +0,0 @@ -/* - * Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: - * - * Marek Lindner - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA - * - */ - -#include "main.h" -#include "bat_sysfs.h" -#include "translation-table.h" -#include "originator.h" -#include "hard-interface.h" -#include "gateway_common.h" -#include "gateway_client.h" -#include "vis.h" - -static struct net_device *kobj_to_netdev(struct kobject *obj) -{ - struct device *dev = container_of(obj->parent, struct device, kobj); - return to_net_dev(dev); -} - -static struct bat_priv *kobj_to_batpriv(struct kobject *obj) -{ - struct net_device *net_dev = kobj_to_netdev(obj); - return netdev_priv(net_dev); -} - -#define UEV_TYPE_VAR "BATTYPE=" -#define UEV_ACTION_VAR "BATACTION=" -#define UEV_DATA_VAR "BATDATA=" - -static char *uev_action_str[] = { - "add", - "del", - "change" -}; - -static char *uev_type_str[] = { - "gw" -}; - -/* Use this, if you have customized show and store functions */ -#define BAT_ATTR(_name, _mode, _show, _store) \ -struct bat_attribute bat_attr_##_name = { \ - .attr = {.name = __stringify(_name), \ - .mode = _mode }, \ - .show = _show, \ - .store = _store, \ -}; - -#define BAT_ATTR_SIF_STORE_BOOL(_name, _post_func) \ -ssize_t store_##_name(struct kobject *kobj, struct attribute *attr, \ - char *buff, size_t count) \ -{ \ - struct net_device *net_dev = kobj_to_netdev(kobj); \ - struct bat_priv *bat_priv = netdev_priv(net_dev); \ - return __store_bool_attr(buff, count, _post_func, attr, \ - &bat_priv->_name, net_dev); \ -} - -#define BAT_ATTR_SIF_SHOW_BOOL(_name) \ -ssize_t show_##_name(struct kobject *kobj, \ - struct attribute *attr, char *buff) \ -{ \ - struct bat_priv *bat_priv = kobj_to_batpriv(kobj); \ - return sprintf(buff, "%s\n", \ - atomic_read(&bat_priv->_name) == 0 ? \ - "disabled" : "enabled"); \ -} \ - -/* Use this, if you are going to turn a [name] in the soft-interface - * (bat_priv) on or off */ -#define BAT_ATTR_SIF_BOOL(_name, _mode, _post_func) \ - static BAT_ATTR_SIF_STORE_BOOL(_name, _post_func) \ - static BAT_ATTR_SIF_SHOW_BOOL(_name) \ - static BAT_ATTR(_name, _mode, show_##_name, store_##_name) - - -#define BAT_ATTR_SIF_STORE_UINT(_name, _min, _max, _post_func) \ -ssize_t store_##_name(struct kobject *kobj, struct attribute *attr, \ - char *buff, size_t count) \ -{ \ - struct net_device *net_dev = kobj_to_netdev(kobj); \ - struct bat_priv *bat_priv = netdev_priv(net_dev); \ - return __store_uint_attr(buff, count, _min, _max, _post_func, \ - attr, &bat_priv->_name, net_dev); \ -} - -#define BAT_ATTR_SIF_SHOW_UINT(_name) \ -ssize_t show_##_name(struct kobject *kobj, \ - struct attribute *attr, char *buff) \ -{ \ - struct bat_priv *bat_priv = kobj_to_batpriv(kobj); \ - return sprintf(buff, "%i\n", atomic_read(&bat_priv->_name)); \ -} \ - -/* Use this, if you are going to set [name] in the soft-interface - * (bat_priv) to an unsigned integer value */ -#define BAT_ATTR_SIF_UINT(_name, _mode, _min, _max, _post_func) \ - static BAT_ATTR_SIF_STORE_UINT(_name, _min, _max, _post_func) \ - static BAT_ATTR_SIF_SHOW_UINT(_name) \ - static BAT_ATTR(_name, _mode, show_##_name, store_##_name) - - -#define BAT_ATTR_HIF_STORE_UINT(_name, _min, _max, _post_func) \ -ssize_t store_##_name(struct kobject *kobj, struct attribute *attr, \ - char *buff, size_t count) \ -{ \ - struct net_device *net_dev = kobj_to_netdev(kobj); \ - struct hard_iface *hard_iface = hardif_get_by_netdev(net_dev); \ - ssize_t length; \ - \ - if (!hard_iface) \ - return 0; \ - \ - length = __store_uint_attr(buff, count, _min, _max, _post_func, \ - attr, &hard_iface->_name, net_dev); \ - \ - hardif_free_ref(hard_iface); \ - return length; \ -} - -#define BAT_ATTR_HIF_SHOW_UINT(_name) \ -ssize_t show_##_name(struct kobject *kobj, \ - struct attribute *attr, char *buff) \ -{ \ - struct net_device *net_dev = kobj_to_netdev(kobj); \ - struct hard_iface *hard_iface = hardif_get_by_netdev(net_dev); \ - ssize_t length; \ - \ - if (!hard_iface) \ - return 0; \ - \ - length = sprintf(buff, "%i\n", atomic_read(&hard_iface->_name));\ - \ - hardif_free_ref(hard_iface); \ - return length; \ -} - -/* Use this, if you are going to set [name] in hard_iface to an - * unsigned integer value*/ -#define BAT_ATTR_HIF_UINT(_name, _mode, _min, _max, _post_func) \ - static BAT_ATTR_HIF_STORE_UINT(_name, _min, _max, _post_func) \ - static BAT_ATTR_HIF_SHOW_UINT(_name) \ - static BAT_ATTR(_name, _mode, show_##_name, store_##_name) - - -static int store_bool_attr(char *buff, size_t count, - struct net_device *net_dev, - const char *attr_name, atomic_t *attr) -{ - int enabled = -1; - - if (buff[count - 1] == '\n') - buff[count - 1] = '\0'; - - if ((strncmp(buff, "1", 2) == 0) || - (strncmp(buff, "enable", 7) == 0) || - (strncmp(buff, "enabled", 8) == 0)) - enabled = 1; - - if ((strncmp(buff, "0", 2) == 0) || - (strncmp(buff, "disable", 8) == 0) || - (strncmp(buff, "disabled", 9) == 0)) - enabled = 0; - - if (enabled < 0) { - bat_info(net_dev, - "%s: Invalid parameter received: %s\n", - attr_name, buff); - return -EINVAL; - } - - if (atomic_read(attr) == enabled) - return count; - - bat_info(net_dev, "%s: Changing from: %s to: %s\n", attr_name, - atomic_read(attr) == 1 ? "enabled" : "disabled", - enabled == 1 ? "enabled" : "disabled"); - - atomic_set(attr, (unsigned int)enabled); - return count; -} - -static inline ssize_t __store_bool_attr(char *buff, size_t count, - void (*post_func)(struct net_device *), - struct attribute *attr, - atomic_t *attr_store, struct net_device *net_dev) -{ - int ret; - - ret = store_bool_attr(buff, count, net_dev, attr->name, attr_store); - if (post_func && ret) - post_func(net_dev); - - return ret; -} - -static int store_uint_attr(const char *buff, size_t count, - struct net_device *net_dev, const char *attr_name, - unsigned int min, unsigned int max, atomic_t *attr) -{ - unsigned long uint_val; - int ret; - - ret = kstrtoul(buff, 10, &uint_val); - if (ret) { - bat_info(net_dev, - "%s: Invalid parameter received: %s\n", - attr_name, buff); - return -EINVAL; - } - - if (uint_val < min) { - bat_info(net_dev, "%s: Value is too small: %lu min: %u\n", - attr_name, uint_val, min); - return -EINVAL; - } - - if (uint_val > max) { - bat_info(net_dev, "%s: Value is too big: %lu max: %u\n", - attr_name, uint_val, max); - return -EINVAL; - } - - if (atomic_read(attr) == uint_val) - return count; - - bat_info(net_dev, "%s: Changing from: %i to: %lu\n", - attr_name, atomic_read(attr), uint_val); - - atomic_set(attr, uint_val); - return count; -} - -static inline ssize_t __store_uint_attr(const char *buff, size_t count, - int min, int max, - void (*post_func)(struct net_device *), - const struct attribute *attr, - atomic_t *attr_store, struct net_device *net_dev) -{ - int ret; - - ret = store_uint_attr(buff, count, net_dev, attr->name, - min, max, attr_store); - if (post_func && ret) - post_func(net_dev); - - return ret; -} - -static ssize_t show_vis_mode(struct kobject *kobj, struct attribute *attr, - char *buff) -{ - struct bat_priv *bat_priv = kobj_to_batpriv(kobj); - int vis_mode = atomic_read(&bat_priv->vis_mode); - - return sprintf(buff, "%s\n", - vis_mode == VIS_TYPE_CLIENT_UPDATE ? - "client" : "server"); -} - -static ssize_t store_vis_mode(struct kobject *kobj, struct attribute *attr, - char *buff, size_t count) -{ - struct net_device *net_dev = kobj_to_netdev(kobj); - struct bat_priv *bat_priv = netdev_priv(net_dev); - unsigned long val; - int ret, vis_mode_tmp = -1; - - ret = kstrtoul(buff, 10, &val); - - if (((count == 2) && (!ret) && (val == VIS_TYPE_CLIENT_UPDATE)) || - (strncmp(buff, "client", 6) == 0) || - (strncmp(buff, "off", 3) == 0)) - vis_mode_tmp = VIS_TYPE_CLIENT_UPDATE; - - if (((count == 2) && (!ret) && (val == VIS_TYPE_SERVER_SYNC)) || - (strncmp(buff, "server", 6) == 0)) - vis_mode_tmp = VIS_TYPE_SERVER_SYNC; - - if (vis_mode_tmp < 0) { - if (buff[count - 1] == '\n') - buff[count - 1] = '\0'; - - bat_info(net_dev, - "Invalid parameter for 'vis mode' setting received: %s\n", - buff); - return -EINVAL; - } - - if (atomic_read(&bat_priv->vis_mode) == vis_mode_tmp) - return count; - - bat_info(net_dev, "Changing vis mode from: %s to: %s\n", - atomic_read(&bat_priv->vis_mode) == VIS_TYPE_CLIENT_UPDATE ? - "client" : "server", vis_mode_tmp == VIS_TYPE_CLIENT_UPDATE ? - "client" : "server"); - - atomic_set(&bat_priv->vis_mode, (unsigned int)vis_mode_tmp); - return count; -} - -static ssize_t show_bat_algo(struct kobject *kobj, struct attribute *attr, - char *buff) -{ - struct bat_priv *bat_priv = kobj_to_batpriv(kobj); - return sprintf(buff, "%s\n", bat_priv->bat_algo_ops->name); -} - -static void post_gw_deselect(struct net_device *net_dev) -{ - struct bat_priv *bat_priv = netdev_priv(net_dev); - gw_deselect(bat_priv); -} - -static ssize_t show_gw_mode(struct kobject *kobj, struct attribute *attr, - char *buff) -{ - struct bat_priv *bat_priv = kobj_to_batpriv(kobj); - int bytes_written; - - switch (atomic_read(&bat_priv->gw_mode)) { - case GW_MODE_CLIENT: - bytes_written = sprintf(buff, "%s\n", GW_MODE_CLIENT_NAME); - break; - case GW_MODE_SERVER: - bytes_written = sprintf(buff, "%s\n", GW_MODE_SERVER_NAME); - break; - default: - bytes_written = sprintf(buff, "%s\n", GW_MODE_OFF_NAME); - break; - } - - return bytes_written; -} - -static ssize_t store_gw_mode(struct kobject *kobj, struct attribute *attr, - char *buff, size_t count) -{ - struct net_device *net_dev = kobj_to_netdev(kobj); - struct bat_priv *bat_priv = netdev_priv(net_dev); - char *curr_gw_mode_str; - int gw_mode_tmp = -1; - - if (buff[count - 1] == '\n') - buff[count - 1] = '\0'; - - if (strncmp(buff, GW_MODE_OFF_NAME, strlen(GW_MODE_OFF_NAME)) == 0) - gw_mode_tmp = GW_MODE_OFF; - - if (strncmp(buff, GW_MODE_CLIENT_NAME, - strlen(GW_MODE_CLIENT_NAME)) == 0) - gw_mode_tmp = GW_MODE_CLIENT; - - if (strncmp(buff, GW_MODE_SERVER_NAME, - strlen(GW_MODE_SERVER_NAME)) == 0) - gw_mode_tmp = GW_MODE_SERVER; - - if (gw_mode_tmp < 0) { - bat_info(net_dev, - "Invalid parameter for 'gw mode' setting received: %s\n", - buff); - return -EINVAL; - } - - if (atomic_read(&bat_priv->gw_mode) == gw_mode_tmp) - return count; - - switch (atomic_read(&bat_priv->gw_mode)) { - case GW_MODE_CLIENT: - curr_gw_mode_str = GW_MODE_CLIENT_NAME; - break; - case GW_MODE_SERVER: - curr_gw_mode_str = GW_MODE_SERVER_NAME; - break; - default: - curr_gw_mode_str = GW_MODE_OFF_NAME; - break; - } - - bat_info(net_dev, "Changing gw mode from: %s to: %s\n", - curr_gw_mode_str, buff); - - gw_deselect(bat_priv); - atomic_set(&bat_priv->gw_mode, (unsigned int)gw_mode_tmp); - return count; -} - -static ssize_t show_gw_bwidth(struct kobject *kobj, struct attribute *attr, - char *buff) -{ - struct bat_priv *bat_priv = kobj_to_batpriv(kobj); - int down, up; - int gw_bandwidth = atomic_read(&bat_priv->gw_bandwidth); - - gw_bandwidth_to_kbit(gw_bandwidth, &down, &up); - return sprintf(buff, "%i%s/%i%s\n", - (down > 2048 ? down / 1024 : down), - (down > 2048 ? "MBit" : "KBit"), - (up > 2048 ? up / 1024 : up), - (up > 2048 ? "MBit" : "KBit")); -} - -static ssize_t store_gw_bwidth(struct kobject *kobj, struct attribute *attr, - char *buff, size_t count) -{ - struct net_device *net_dev = kobj_to_netdev(kobj); - - if (buff[count - 1] == '\n') - buff[count - 1] = '\0'; - - return gw_bandwidth_set(net_dev, buff, count); -} - -BAT_ATTR_SIF_BOOL(aggregated_ogms, S_IRUGO | S_IWUSR, NULL); -BAT_ATTR_SIF_BOOL(bonding, S_IRUGO | S_IWUSR, NULL); -#ifdef CONFIG_BATMAN_ADV_BLA -BAT_ATTR_SIF_BOOL(bridge_loop_avoidance, S_IRUGO | S_IWUSR, NULL); -#endif -BAT_ATTR_SIF_BOOL(fragmentation, S_IRUGO | S_IWUSR, update_min_mtu); -BAT_ATTR_SIF_BOOL(ap_isolation, S_IRUGO | S_IWUSR, NULL); -static BAT_ATTR(vis_mode, S_IRUGO | S_IWUSR, show_vis_mode, store_vis_mode); -static BAT_ATTR(routing_algo, S_IRUGO, show_bat_algo, NULL); -static BAT_ATTR(gw_mode, S_IRUGO | S_IWUSR, show_gw_mode, store_gw_mode); -BAT_ATTR_SIF_UINT(orig_interval, S_IRUGO | S_IWUSR, 2 * JITTER, INT_MAX, NULL); -BAT_ATTR_SIF_UINT(hop_penalty, S_IRUGO | S_IWUSR, 0, TQ_MAX_VALUE, NULL); -BAT_ATTR_SIF_UINT(gw_sel_class, S_IRUGO | S_IWUSR, 1, TQ_MAX_VALUE, - post_gw_deselect); -static BAT_ATTR(gw_bandwidth, S_IRUGO | S_IWUSR, show_gw_bwidth, - store_gw_bwidth); -#ifdef CONFIG_BATMAN_ADV_DEBUG -BAT_ATTR_SIF_UINT(log_level, S_IRUGO | S_IWUSR, 0, 15, NULL); -#endif - -static struct bat_attribute *mesh_attrs[] = { - &bat_attr_aggregated_ogms, - &bat_attr_bonding, -#ifdef CONFIG_BATMAN_ADV_BLA - &bat_attr_bridge_loop_avoidance, -#endif - &bat_attr_fragmentation, - &bat_attr_ap_isolation, - &bat_attr_vis_mode, - &bat_attr_routing_algo, - &bat_attr_gw_mode, - &bat_attr_orig_interval, - &bat_attr_hop_penalty, - &bat_attr_gw_sel_class, - &bat_attr_gw_bandwidth, -#ifdef CONFIG_BATMAN_ADV_DEBUG - &bat_attr_log_level, -#endif - NULL, -}; - -int sysfs_add_meshif(struct net_device *dev) -{ - struct kobject *batif_kobject = &dev->dev.kobj; - struct bat_priv *bat_priv = netdev_priv(dev); - struct bat_attribute **bat_attr; - int err; - - bat_priv->mesh_obj = kobject_create_and_add(SYSFS_IF_MESH_SUBDIR, - batif_kobject); - if (!bat_priv->mesh_obj) { - bat_err(dev, "Can't add sysfs directory: %s/%s\n", dev->name, - SYSFS_IF_MESH_SUBDIR); - goto out; - } - - for (bat_attr = mesh_attrs; *bat_attr; ++bat_attr) { - err = sysfs_create_file(bat_priv->mesh_obj, - &((*bat_attr)->attr)); - if (err) { - bat_err(dev, "Can't add sysfs file: %s/%s/%s\n", - dev->name, SYSFS_IF_MESH_SUBDIR, - ((*bat_attr)->attr).name); - goto rem_attr; - } - } - - return 0; - -rem_attr: - for (bat_attr = mesh_attrs; *bat_attr; ++bat_attr) - sysfs_remove_file(bat_priv->mesh_obj, &((*bat_attr)->attr)); - - kobject_put(bat_priv->mesh_obj); - bat_priv->mesh_obj = NULL; -out: - return -ENOMEM; -} - -void sysfs_del_meshif(struct net_device *dev) -{ - struct bat_priv *bat_priv = netdev_priv(dev); - struct bat_attribute **bat_attr; - - for (bat_attr = mesh_attrs; *bat_attr; ++bat_attr) - sysfs_remove_file(bat_priv->mesh_obj, &((*bat_attr)->attr)); - - kobject_put(bat_priv->mesh_obj); - bat_priv->mesh_obj = NULL; -} - -static ssize_t show_mesh_iface(struct kobject *kobj, struct attribute *attr, - char *buff) -{ - struct net_device *net_dev = kobj_to_netdev(kobj); - struct hard_iface *hard_iface = hardif_get_by_netdev(net_dev); - ssize_t length; - - if (!hard_iface) - return 0; - - length = sprintf(buff, "%s\n", hard_iface->if_status == IF_NOT_IN_USE ? - "none" : hard_iface->soft_iface->name); - - hardif_free_ref(hard_iface); - - return length; -} - -static ssize_t store_mesh_iface(struct kobject *kobj, struct attribute *attr, - char *buff, size_t count) -{ - struct net_device *net_dev = kobj_to_netdev(kobj); - struct hard_iface *hard_iface = hardif_get_by_netdev(net_dev); - int status_tmp = -1; - int ret = count; - - if (!hard_iface) - return count; - - if (buff[count - 1] == '\n') - buff[count - 1] = '\0'; - - if (strlen(buff) >= IFNAMSIZ) { - pr_err("Invalid parameter for 'mesh_iface' setting received: interface name too long '%s'\n", - buff); - hardif_free_ref(hard_iface); - return -EINVAL; - } - - if (strncmp(buff, "none", 4) == 0) - status_tmp = IF_NOT_IN_USE; - else - status_tmp = IF_I_WANT_YOU; - - if (hard_iface->if_status == status_tmp) - goto out; - - if ((hard_iface->soft_iface) && - (strncmp(hard_iface->soft_iface->name, buff, IFNAMSIZ) == 0)) - goto out; - - if (!rtnl_trylock()) { - ret = -ERESTARTSYS; - goto out; - } - - if (status_tmp == IF_NOT_IN_USE) { - hardif_disable_interface(hard_iface); - goto unlock; - } - - /* if the interface already is in use */ - if (hard_iface->if_status != IF_NOT_IN_USE) - hardif_disable_interface(hard_iface); - - ret = hardif_enable_interface(hard_iface, buff); - -unlock: - rtnl_unlock(); -out: - hardif_free_ref(hard_iface); - return ret; -} - -static ssize_t show_iface_status(struct kobject *kobj, struct attribute *attr, - char *buff) -{ - struct net_device *net_dev = kobj_to_netdev(kobj); - struct hard_iface *hard_iface = hardif_get_by_netdev(net_dev); - ssize_t length; - - if (!hard_iface) - return 0; - - switch (hard_iface->if_status) { - case IF_TO_BE_REMOVED: - length = sprintf(buff, "disabling\n"); - break; - case IF_INACTIVE: - length = sprintf(buff, "inactive\n"); - break; - case IF_ACTIVE: - length = sprintf(buff, "active\n"); - break; - case IF_TO_BE_ACTIVATED: - length = sprintf(buff, "enabling\n"); - break; - case IF_NOT_IN_USE: - default: - length = sprintf(buff, "not in use\n"); - break; - } - - hardif_free_ref(hard_iface); - - return length; -} - -static BAT_ATTR(mesh_iface, S_IRUGO | S_IWUSR, - show_mesh_iface, store_mesh_iface); -static BAT_ATTR(iface_status, S_IRUGO, show_iface_status, NULL); - -static struct bat_attribute *batman_attrs[] = { - &bat_attr_mesh_iface, - &bat_attr_iface_status, - NULL, -}; - -int sysfs_add_hardif(struct kobject **hardif_obj, struct net_device *dev) -{ - struct kobject *hardif_kobject = &dev->dev.kobj; - struct bat_attribute **bat_attr; - int err; - - *hardif_obj = kobject_create_and_add(SYSFS_IF_BAT_SUBDIR, - hardif_kobject); - - if (!*hardif_obj) { - bat_err(dev, "Can't add sysfs directory: %s/%s\n", dev->name, - SYSFS_IF_BAT_SUBDIR); - goto out; - } - - for (bat_attr = batman_attrs; *bat_attr; ++bat_attr) { - err = sysfs_create_file(*hardif_obj, &((*bat_attr)->attr)); - if (err) { - bat_err(dev, "Can't add sysfs file: %s/%s/%s\n", - dev->name, SYSFS_IF_BAT_SUBDIR, - ((*bat_attr)->attr).name); - goto rem_attr; - } - } - - return 0; - -rem_attr: - for (bat_attr = batman_attrs; *bat_attr; ++bat_attr) - sysfs_remove_file(*hardif_obj, &((*bat_attr)->attr)); -out: - return -ENOMEM; -} - -void sysfs_del_hardif(struct kobject **hardif_obj) -{ - kobject_put(*hardif_obj); - *hardif_obj = NULL; -} - -int throw_uevent(struct bat_priv *bat_priv, enum uev_type type, - enum uev_action action, const char *data) -{ - int ret = -1; - struct hard_iface *primary_if = NULL; - struct kobject *bat_kobj; - char *uevent_env[4] = { NULL, NULL, NULL, NULL }; - - primary_if = primary_if_get_selected(bat_priv); - if (!primary_if) - goto out; - - bat_kobj = &primary_if->soft_iface->dev.kobj; - - uevent_env[0] = kmalloc(strlen(UEV_TYPE_VAR) + - strlen(uev_type_str[type]) + 1, - GFP_ATOMIC); - if (!uevent_env[0]) - goto out; - - sprintf(uevent_env[0], "%s%s", UEV_TYPE_VAR, uev_type_str[type]); - - uevent_env[1] = kmalloc(strlen(UEV_ACTION_VAR) + - strlen(uev_action_str[action]) + 1, - GFP_ATOMIC); - if (!uevent_env[1]) - goto out; - - sprintf(uevent_env[1], "%s%s", UEV_ACTION_VAR, uev_action_str[action]); - - /* If the event is DEL, ignore the data field */ - if (action != UEV_DEL) { - uevent_env[2] = kmalloc(strlen(UEV_DATA_VAR) + - strlen(data) + 1, GFP_ATOMIC); - if (!uevent_env[2]) - goto out; - - sprintf(uevent_env[2], "%s%s", UEV_DATA_VAR, data); - } - - ret = kobject_uevent_env(bat_kobj, KOBJ_CHANGE, uevent_env); -out: - kfree(uevent_env[0]); - kfree(uevent_env[1]); - kfree(uevent_env[2]); - - if (primary_if) - hardif_free_ref(primary_if); - - if (ret) - bat_dbg(DBG_BATMAN, bat_priv, - "Impossible to send uevent for (%s,%s,%s) event (err: %d)\n", - uev_type_str[type], uev_action_str[action], - (action == UEV_DEL ? "NULL" : data), ret); - return ret; -} diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index 07ae6e1b8ac..aea174cdbfb 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" @@ -25,12 +23,12 @@ #include <linux/bitops.h> /* shift the packet array by n places. */ -static void bat_bitmap_shift_left(unsigned long *seq_bits, int32_t n) +static void batadv_bitmap_shift_left(unsigned long *seq_bits, int32_t n) { - if (n <= 0 || n >= TQ_LOCAL_WINDOW_SIZE) + if (n <= 0 || n >= BATADV_TQ_LOCAL_WINDOW_SIZE) return; - bitmap_shift_left(seq_bits, seq_bits, n, TQ_LOCAL_WINDOW_SIZE); + bitmap_shift_left(seq_bits, seq_bits, n, BATADV_TQ_LOCAL_WINDOW_SIZE); } @@ -40,58 +38,57 @@ static void bat_bitmap_shift_left(unsigned long *seq_bits, int32_t n) * 1 if the window was moved (either new or very old) * 0 if the window was not moved/shifted. */ -int bit_get_packet(void *priv, unsigned long *seq_bits, - int32_t seq_num_diff, int set_mark) +int batadv_bit_get_packet(void *priv, unsigned long *seq_bits, + int32_t seq_num_diff, int set_mark) { - struct bat_priv *bat_priv = priv; + struct batadv_priv *bat_priv = priv; /* sequence number is slightly older. We already got a sequence number - * higher than this one, so we just mark it. */ - - if ((seq_num_diff <= 0) && (seq_num_diff > -TQ_LOCAL_WINDOW_SIZE)) { + * higher than this one, so we just mark it. + */ + if (seq_num_diff <= 0 && seq_num_diff > -BATADV_TQ_LOCAL_WINDOW_SIZE) { if (set_mark) - bat_set_bit(seq_bits, -seq_num_diff); + batadv_set_bit(seq_bits, -seq_num_diff); return 0; } /* sequence number is slightly newer, so we shift the window and - * set the mark if required */ - - if ((seq_num_diff > 0) && (seq_num_diff < TQ_LOCAL_WINDOW_SIZE)) { - bat_bitmap_shift_left(seq_bits, seq_num_diff); + * set the mark if required + */ + if (seq_num_diff > 0 && seq_num_diff < BATADV_TQ_LOCAL_WINDOW_SIZE) { + batadv_bitmap_shift_left(seq_bits, seq_num_diff); if (set_mark) - bat_set_bit(seq_bits, 0); + batadv_set_bit(seq_bits, 0); return 1; } /* sequence number is much newer, probably missed a lot of packets */ - - if ((seq_num_diff >= TQ_LOCAL_WINDOW_SIZE) && - (seq_num_diff < EXPECTED_SEQNO_RANGE)) { - bat_dbg(DBG_BATMAN, bat_priv, - "We missed a lot of packets (%i) !\n", - seq_num_diff - 1); - bitmap_zero(seq_bits, TQ_LOCAL_WINDOW_SIZE); + if (seq_num_diff >= BATADV_TQ_LOCAL_WINDOW_SIZE && + seq_num_diff < BATADV_EXPECTED_SEQNO_RANGE) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "We missed a lot of packets (%i) !\n", + seq_num_diff - 1); + bitmap_zero(seq_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); if (set_mark) - bat_set_bit(seq_bits, 0); + batadv_set_bit(seq_bits, 0); return 1; } /* received a much older packet. The other host either restarted * or the old packet got delayed somewhere in the network. The * packet should be dropped without calling this function if the - * seqno window is protected. */ - - if ((seq_num_diff <= -TQ_LOCAL_WINDOW_SIZE) || - (seq_num_diff >= EXPECTED_SEQNO_RANGE)) { + * seqno window is protected. + */ + if (seq_num_diff <= -BATADV_TQ_LOCAL_WINDOW_SIZE || + seq_num_diff >= BATADV_EXPECTED_SEQNO_RANGE) { - bat_dbg(DBG_BATMAN, bat_priv, - "Other host probably restarted!\n"); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Other host probably restarted!\n"); - bitmap_zero(seq_bits, TQ_LOCAL_WINDOW_SIZE); + bitmap_zero(seq_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); if (set_mark) - bat_set_bit(seq_bits, 0); + batadv_set_bit(seq_bits, 0); return 1; } diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index 1835c15cda4..a081ce1c051 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * @@ -16,39 +15,40 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_BITARRAY_H_ #define _NET_BATMAN_ADV_BITARRAY_H_ /* returns true if the corresponding bit in the given seq_bits indicates true - * and curr_seqno is within range of last_seqno */ -static inline int bat_test_bit(const unsigned long *seq_bits, - uint32_t last_seqno, uint32_t curr_seqno) + * and curr_seqno is within range of last_seqno + */ +static inline int batadv_test_bit(const unsigned long *seq_bits, + uint32_t last_seqno, uint32_t curr_seqno) { int32_t diff; diff = last_seqno - curr_seqno; - if (diff < 0 || diff >= TQ_LOCAL_WINDOW_SIZE) + if (diff < 0 || diff >= BATADV_TQ_LOCAL_WINDOW_SIZE) return 0; else return test_bit(diff, seq_bits); } /* turn corresponding bit on, so we can remember that we got the packet */ -static inline void bat_set_bit(unsigned long *seq_bits, int32_t n) +static inline void batadv_set_bit(unsigned long *seq_bits, int32_t n) { /* if too old, just drop it */ - if (n < 0 || n >= TQ_LOCAL_WINDOW_SIZE) + if (n < 0 || n >= BATADV_TQ_LOCAL_WINDOW_SIZE) return; set_bit(n, seq_bits); /* turn the position on */ } /* receive and process one packet, returns 1 if received seq_num is considered - * new, 0 if old */ -int bit_get_packet(void *priv, unsigned long *seq_bits, - int32_t seq_num_diff, int set_mark); + * new, 0 if old + */ +int batadv_bit_get_packet(void *priv, unsigned long *seq_bits, + int32_t seq_num_diff, int set_mark); #endif /* _NET_BATMAN_ADV_BITARRAY_H_ */ diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index c5863f49913..6705d35b17c 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: * * Simon Wunderlich * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" @@ -33,14 +31,14 @@ #include <net/arp.h> #include <linux/if_vlan.h> -static const uint8_t announce_mac[4] = {0x43, 0x05, 0x43, 0x05}; +static const uint8_t batadv_announce_mac[4] = {0x43, 0x05, 0x43, 0x05}; -static void bla_periodic_work(struct work_struct *work); -static void bla_send_announce(struct bat_priv *bat_priv, - struct backbone_gw *backbone_gw); +static void batadv_bla_periodic_work(struct work_struct *work); +static void batadv_bla_send_announce(struct batadv_priv *bat_priv, + struct batadv_backbone_gw *backbone_gw); /* return the index of the claim */ -static inline uint32_t choose_claim(const void *data, uint32_t size) +static inline uint32_t batadv_choose_claim(const void *data, uint32_t size) { const unsigned char *key = data; uint32_t hash = 0; @@ -60,7 +58,8 @@ static inline uint32_t choose_claim(const void *data, uint32_t size) } /* return the index of the backbone gateway */ -static inline uint32_t choose_backbone_gw(const void *data, uint32_t size) +static inline uint32_t batadv_choose_backbone_gw(const void *data, + uint32_t size) { const unsigned char *key = data; uint32_t hash = 0; @@ -81,74 +80,75 @@ static inline uint32_t choose_backbone_gw(const void *data, uint32_t size) /* compares address and vid of two backbone gws */ -static int compare_backbone_gw(const struct hlist_node *node, const void *data2) +static int batadv_compare_backbone_gw(const struct hlist_node *node, + const void *data2) { - const void *data1 = container_of(node, struct backbone_gw, + const void *data1 = container_of(node, struct batadv_backbone_gw, hash_entry); return (memcmp(data1, data2, ETH_ALEN + sizeof(short)) == 0 ? 1 : 0); } /* compares address and vid of two claims */ -static int compare_claim(const struct hlist_node *node, const void *data2) +static int batadv_compare_claim(const struct hlist_node *node, + const void *data2) { - const void *data1 = container_of(node, struct claim, + const void *data1 = container_of(node, struct batadv_claim, hash_entry); return (memcmp(data1, data2, ETH_ALEN + sizeof(short)) == 0 ? 1 : 0); } /* free a backbone gw */ -static void backbone_gw_free_ref(struct backbone_gw *backbone_gw) +static void batadv_backbone_gw_free_ref(struct batadv_backbone_gw *backbone_gw) { if (atomic_dec_and_test(&backbone_gw->refcount)) kfree_rcu(backbone_gw, rcu); } /* finally deinitialize the claim */ -static void claim_free_rcu(struct rcu_head *rcu) +static void batadv_claim_free_rcu(struct rcu_head *rcu) { - struct claim *claim; + struct batadv_claim *claim; - claim = container_of(rcu, struct claim, rcu); + claim = container_of(rcu, struct batadv_claim, rcu); - backbone_gw_free_ref(claim->backbone_gw); + batadv_backbone_gw_free_ref(claim->backbone_gw); kfree(claim); } /* free a claim, call claim_free_rcu if its the last reference */ -static void claim_free_ref(struct claim *claim) +static void batadv_claim_free_ref(struct batadv_claim *claim) { if (atomic_dec_and_test(&claim->refcount)) - call_rcu(&claim->rcu, claim_free_rcu); + call_rcu(&claim->rcu, batadv_claim_free_rcu); } -/** - * @bat_priv: the bat priv with all the soft interface information +/* @bat_priv: the bat priv with all the soft interface information * @data: search data (may be local/static data) * * looks for a claim in the hash, and returns it if found * or NULL otherwise. */ -static struct claim *claim_hash_find(struct bat_priv *bat_priv, - struct claim *data) +static struct batadv_claim *batadv_claim_hash_find(struct batadv_priv *bat_priv, + struct batadv_claim *data) { - struct hashtable_t *hash = bat_priv->claim_hash; + struct batadv_hashtable *hash = bat_priv->claim_hash; struct hlist_head *head; struct hlist_node *node; - struct claim *claim; - struct claim *claim_tmp = NULL; + struct batadv_claim *claim; + struct batadv_claim *claim_tmp = NULL; int index; if (!hash) return NULL; - index = choose_claim(data, hash->size); + index = batadv_choose_claim(data, hash->size); head = &hash->table[index]; rcu_read_lock(); hlist_for_each_entry_rcu(claim, node, head, hash_entry) { - if (!compare_claim(&claim->hash_entry, data)) + if (!batadv_compare_claim(&claim->hash_entry, data)) continue; if (!atomic_inc_not_zero(&claim->refcount)) @@ -163,21 +163,22 @@ static struct claim *claim_hash_find(struct bat_priv *bat_priv, } /** + * batadv_backbone_hash_find - looks for a claim in the hash * @bat_priv: the bat priv with all the soft interface information * @addr: the address of the originator * @vid: the VLAN ID * - * looks for a claim in the hash, and returns it if found - * or NULL otherwise. + * Returns claim if found or NULL otherwise. */ -static struct backbone_gw *backbone_hash_find(struct bat_priv *bat_priv, - uint8_t *addr, short vid) +static struct batadv_backbone_gw * +batadv_backbone_hash_find(struct batadv_priv *bat_priv, + uint8_t *addr, short vid) { - struct hashtable_t *hash = bat_priv->backbone_hash; + struct batadv_hashtable *hash = bat_priv->backbone_hash; struct hlist_head *head; struct hlist_node *node; - struct backbone_gw search_entry, *backbone_gw; - struct backbone_gw *backbone_gw_tmp = NULL; + struct batadv_backbone_gw search_entry, *backbone_gw; + struct batadv_backbone_gw *backbone_gw_tmp = NULL; int index; if (!hash) @@ -186,13 +187,13 @@ static struct backbone_gw *backbone_hash_find(struct bat_priv *bat_priv, memcpy(search_entry.orig, addr, ETH_ALEN); search_entry.vid = vid; - index = choose_backbone_gw(&search_entry, hash->size); + index = batadv_choose_backbone_gw(&search_entry, hash->size); head = &hash->table[index]; rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { - if (!compare_backbone_gw(&backbone_gw->hash_entry, - &search_entry)) + if (!batadv_compare_backbone_gw(&backbone_gw->hash_entry, + &search_entry)) continue; if (!atomic_inc_not_zero(&backbone_gw->refcount)) @@ -207,12 +208,13 @@ static struct backbone_gw *backbone_hash_find(struct bat_priv *bat_priv, } /* delete all claims for a backbone */ -static void bla_del_backbone_claims(struct backbone_gw *backbone_gw) +static void +batadv_bla_del_backbone_claims(struct batadv_backbone_gw *backbone_gw) { - struct hashtable_t *hash; + struct batadv_hashtable *hash; struct hlist_node *node, *node_tmp; struct hlist_head *head; - struct claim *claim; + struct batadv_claim *claim; int i; spinlock_t *list_lock; /* protects write access to the hash lists */ @@ -231,36 +233,35 @@ static void bla_del_backbone_claims(struct backbone_gw *backbone_gw) if (claim->backbone_gw != backbone_gw) continue; - claim_free_ref(claim); + batadv_claim_free_ref(claim); hlist_del_rcu(node); } spin_unlock_bh(list_lock); } /* all claims gone, intialize CRC */ - backbone_gw->crc = BLA_CRC_INIT; + backbone_gw->crc = BATADV_BLA_CRC_INIT; } /** + * batadv_bla_send_claim - sends a claim frame according to the provided info * @bat_priv: the bat priv with all the soft interface information * @orig: the mac address to be announced within the claim * @vid: the VLAN ID * @claimtype: the type of the claim (CLAIM, UNCLAIM, ANNOUNCE, ...) - * - * sends a claim frame according to the provided info. */ -static void bla_send_claim(struct bat_priv *bat_priv, uint8_t *mac, - short vid, int claimtype) +static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac, + short vid, int claimtype) { struct sk_buff *skb; struct ethhdr *ethhdr; - struct hard_iface *primary_if; + struct batadv_hard_iface *primary_if; struct net_device *soft_iface; uint8_t *hw_src; - struct bla_claim_dst local_claim_dest; - uint32_t zeroip = 0; + struct batadv_bla_claim_dst local_claim_dest; + __be32 zeroip = 0; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) return; @@ -294,40 +295,41 @@ static void bla_send_claim(struct bat_priv *bat_priv, uint8_t *mac, /* now we pretend that the client would have sent this ... */ switch (claimtype) { - case CLAIM_TYPE_ADD: + case BATADV_CLAIM_TYPE_ADD: /* normal claim frame * set Ethernet SRC to the clients mac */ memcpy(ethhdr->h_source, mac, ETH_ALEN); - bat_dbg(DBG_BLA, bat_priv, - "bla_send_claim(): CLAIM %pM on vid %d\n", mac, vid); + batadv_dbg(BATADV_DBG_BLA, bat_priv, + "bla_send_claim(): CLAIM %pM on vid %d\n", mac, vid); break; - case CLAIM_TYPE_DEL: + case BATADV_CLAIM_TYPE_DEL: /* unclaim frame * set HW SRC to the clients mac */ memcpy(hw_src, mac, ETH_ALEN); - bat_dbg(DBG_BLA, bat_priv, - "bla_send_claim(): UNCLAIM %pM on vid %d\n", mac, vid); + batadv_dbg(BATADV_DBG_BLA, bat_priv, + "bla_send_claim(): UNCLAIM %pM on vid %d\n", mac, + vid); break; - case CLAIM_TYPE_ANNOUNCE: + case BATADV_CLAIM_TYPE_ANNOUNCE: /* announcement frame * set HW SRC to the special mac containg the crc */ memcpy(hw_src, mac, ETH_ALEN); - bat_dbg(DBG_BLA, bat_priv, - "bla_send_claim(): ANNOUNCE of %pM on vid %d\n", - ethhdr->h_source, vid); + batadv_dbg(BATADV_DBG_BLA, bat_priv, + "bla_send_claim(): ANNOUNCE of %pM on vid %d\n", + ethhdr->h_source, vid); break; - case CLAIM_TYPE_REQUEST: + case BATADV_CLAIM_TYPE_REQUEST: /* request frame * set HW SRC to the special mac containg the crc */ memcpy(hw_src, mac, ETH_ALEN); memcpy(ethhdr->h_dest, mac, ETH_ALEN); - bat_dbg(DBG_BLA, bat_priv, - "bla_send_claim(): REQUEST of %pM to %pMon vid %d\n", - ethhdr->h_source, ethhdr->h_dest, vid); + batadv_dbg(BATADV_DBG_BLA, bat_priv, + "bla_send_claim(): REQUEST of %pM to %pMon vid %d\n", + ethhdr->h_source, ethhdr->h_dest, vid); break; } @@ -344,10 +346,11 @@ static void bla_send_claim(struct bat_priv *bat_priv, uint8_t *mac, netif_rx(skb); out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); } /** + * batadv_bla_get_backbone_gw * @bat_priv: the bat priv with all the soft interface information * @orig: the mac address of the originator * @vid: the VLAN ID @@ -355,21 +358,22 @@ out: * searches for the backbone gw or creates a new one if it could not * be found. */ -static struct backbone_gw *bla_get_backbone_gw(struct bat_priv *bat_priv, - uint8_t *orig, short vid) +static struct batadv_backbone_gw * +batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, uint8_t *orig, + short vid) { - struct backbone_gw *entry; - struct orig_node *orig_node; + struct batadv_backbone_gw *entry; + struct batadv_orig_node *orig_node; int hash_added; - entry = backbone_hash_find(bat_priv, orig, vid); + entry = batadv_backbone_hash_find(bat_priv, orig, vid); if (entry) return entry; - bat_dbg(DBG_BLA, bat_priv, - "bla_get_backbone_gw(): not found (%pM, %d), creating new entry\n", - orig, vid); + batadv_dbg(BATADV_DBG_BLA, bat_priv, + "bla_get_backbone_gw(): not found (%pM, %d), creating new entry\n", + orig, vid); entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) @@ -377,7 +381,7 @@ static struct backbone_gw *bla_get_backbone_gw(struct bat_priv *bat_priv, entry->vid = vid; entry->lasttime = jiffies; - entry->crc = BLA_CRC_INIT; + entry->crc = BATADV_BLA_CRC_INIT; entry->bat_priv = bat_priv; atomic_set(&entry->request_sent, 0); memcpy(entry->orig, orig, ETH_ALEN); @@ -385,8 +389,10 @@ static struct backbone_gw *bla_get_backbone_gw(struct bat_priv *bat_priv, /* one for the hash, one for returning */ atomic_set(&entry->refcount, 2); - hash_added = hash_add(bat_priv->backbone_hash, compare_backbone_gw, - choose_backbone_gw, entry, &entry->hash_entry); + hash_added = batadv_hash_add(bat_priv->backbone_hash, + batadv_compare_backbone_gw, + batadv_choose_backbone_gw, entry, + &entry->hash_entry); if (unlikely(hash_added != 0)) { /* hash failed, free the structure */ @@ -395,11 +401,11 @@ static struct backbone_gw *bla_get_backbone_gw(struct bat_priv *bat_priv, } /* this is a gateway now, remove any tt entries */ - orig_node = orig_hash_find(bat_priv, orig); + orig_node = batadv_orig_hash_find(bat_priv, orig); if (orig_node) { - tt_global_del_orig(bat_priv, orig_node, - "became a backbone gateway"); - orig_node_free_ref(orig_node); + batadv_tt_global_del_orig(bat_priv, orig_node, + "became a backbone gateway"); + batadv_orig_node_free_ref(orig_node); } return entry; } @@ -407,43 +413,46 @@ static struct backbone_gw *bla_get_backbone_gw(struct bat_priv *bat_priv, /* update or add the own backbone gw to make sure we announce * where we receive other backbone gws */ -static void bla_update_own_backbone_gw(struct bat_priv *bat_priv, - struct hard_iface *primary_if, - short vid) +static void +batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv, + struct batadv_hard_iface *primary_if, + short vid) { - struct backbone_gw *backbone_gw; + struct batadv_backbone_gw *backbone_gw; - backbone_gw = bla_get_backbone_gw(bat_priv, - primary_if->net_dev->dev_addr, vid); + backbone_gw = batadv_bla_get_backbone_gw(bat_priv, + primary_if->net_dev->dev_addr, + vid); if (unlikely(!backbone_gw)) return; backbone_gw->lasttime = jiffies; - backbone_gw_free_ref(backbone_gw); + batadv_backbone_gw_free_ref(backbone_gw); } -/** - * @bat_priv: the bat priv with all the soft interface information +/* @bat_priv: the bat priv with all the soft interface information * @vid: the vid where the request came on * * Repeat all of our own claims, and finally send an ANNOUNCE frame * to allow the requester another check if the CRC is correct now. */ -static void bla_answer_request(struct bat_priv *bat_priv, - struct hard_iface *primary_if, short vid) +static void batadv_bla_answer_request(struct batadv_priv *bat_priv, + struct batadv_hard_iface *primary_if, + short vid) { struct hlist_node *node; struct hlist_head *head; - struct hashtable_t *hash; - struct claim *claim; - struct backbone_gw *backbone_gw; + struct batadv_hashtable *hash; + struct batadv_claim *claim; + struct batadv_backbone_gw *backbone_gw; int i; - bat_dbg(DBG_BLA, bat_priv, - "bla_answer_request(): received a claim request, send all of our own claims again\n"); + batadv_dbg(BATADV_DBG_BLA, bat_priv, + "bla_answer_request(): received a claim request, send all of our own claims again\n"); - backbone_gw = backbone_hash_find(bat_priv, - primary_if->net_dev->dev_addr, vid); + backbone_gw = batadv_backbone_hash_find(bat_priv, + primary_if->net_dev->dev_addr, + vid); if (!backbone_gw) return; @@ -457,36 +466,34 @@ static void bla_answer_request(struct bat_priv *bat_priv, if (claim->backbone_gw != backbone_gw) continue; - bla_send_claim(bat_priv, claim->addr, claim->vid, - CLAIM_TYPE_ADD); + batadv_bla_send_claim(bat_priv, claim->addr, claim->vid, + BATADV_CLAIM_TYPE_ADD); } rcu_read_unlock(); } /* finally, send an announcement frame */ - bla_send_announce(bat_priv, backbone_gw); - backbone_gw_free_ref(backbone_gw); + batadv_bla_send_announce(bat_priv, backbone_gw); + batadv_backbone_gw_free_ref(backbone_gw); } -/** - * @backbone_gw: the backbone gateway from whom we are out of sync +/* @backbone_gw: the backbone gateway from whom we are out of sync * * When the crc is wrong, ask the backbone gateway for a full table update. * After the request, it will repeat all of his own claims and finally * send an announcement claim with which we can check again. */ -static void bla_send_request(struct backbone_gw *backbone_gw) +static void batadv_bla_send_request(struct batadv_backbone_gw *backbone_gw) { /* first, remove all old entries */ - bla_del_backbone_claims(backbone_gw); + batadv_bla_del_backbone_claims(backbone_gw); - bat_dbg(DBG_BLA, backbone_gw->bat_priv, - "Sending REQUEST to %pM\n", - backbone_gw->orig); + batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, + "Sending REQUEST to %pM\n", backbone_gw->orig); /* send request */ - bla_send_claim(backbone_gw->bat_priv, backbone_gw->orig, - backbone_gw->vid, CLAIM_TYPE_REQUEST); + batadv_bla_send_claim(backbone_gw->bat_priv, backbone_gw->orig, + backbone_gw->vid, BATADV_CLAIM_TYPE_REQUEST); /* no local broadcasts should be sent or received, for now. */ if (!atomic_read(&backbone_gw->request_sent)) { @@ -495,45 +502,45 @@ static void bla_send_request(struct backbone_gw *backbone_gw) } } -/** - * @bat_priv: the bat priv with all the soft interface information +/* @bat_priv: the bat priv with all the soft interface information * @backbone_gw: our backbone gateway which should be announced * * This function sends an announcement. It is called from multiple * places. */ -static void bla_send_announce(struct bat_priv *bat_priv, - struct backbone_gw *backbone_gw) +static void batadv_bla_send_announce(struct batadv_priv *bat_priv, + struct batadv_backbone_gw *backbone_gw) { uint8_t mac[ETH_ALEN]; - uint16_t crc; + __be16 crc; - memcpy(mac, announce_mac, 4); + memcpy(mac, batadv_announce_mac, 4); crc = htons(backbone_gw->crc); - memcpy(&mac[4], (uint8_t *)&crc, 2); + memcpy(&mac[4], &crc, 2); - bla_send_claim(bat_priv, mac, backbone_gw->vid, CLAIM_TYPE_ANNOUNCE); + batadv_bla_send_claim(bat_priv, mac, backbone_gw->vid, + BATADV_CLAIM_TYPE_ANNOUNCE); } /** + * batadv_bla_add_claim - Adds a claim in the claim hash * @bat_priv: the bat priv with all the soft interface information * @mac: the mac address of the claim * @vid: the VLAN ID of the frame * @backbone_gw: the backbone gateway which claims it - * - * Adds a claim in the claim hash. */ -static void bla_add_claim(struct bat_priv *bat_priv, const uint8_t *mac, - const short vid, struct backbone_gw *backbone_gw) +static void batadv_bla_add_claim(struct batadv_priv *bat_priv, + const uint8_t *mac, const short vid, + struct batadv_backbone_gw *backbone_gw) { - struct claim *claim; - struct claim search_claim; + struct batadv_claim *claim; + struct batadv_claim search_claim; int hash_added; memcpy(search_claim.addr, mac, ETH_ALEN); search_claim.vid = vid; - claim = claim_hash_find(bat_priv, &search_claim); + claim = batadv_claim_hash_find(bat_priv, &search_claim); /* create a new claim entry if it does not exist yet. */ if (!claim) { @@ -547,11 +554,13 @@ static void bla_add_claim(struct bat_priv *bat_priv, const uint8_t *mac, claim->backbone_gw = backbone_gw; atomic_set(&claim->refcount, 2); - bat_dbg(DBG_BLA, bat_priv, - "bla_add_claim(): adding new entry %pM, vid %d to hash ...\n", - mac, vid); - hash_added = hash_add(bat_priv->claim_hash, compare_claim, - choose_claim, claim, &claim->hash_entry); + batadv_dbg(BATADV_DBG_BLA, bat_priv, + "bla_add_claim(): adding new entry %pM, vid %d to hash ...\n", + mac, vid); + hash_added = batadv_hash_add(bat_priv->claim_hash, + batadv_compare_claim, + batadv_choose_claim, claim, + &claim->hash_entry); if (unlikely(hash_added != 0)) { /* only local changes happened. */ @@ -564,13 +573,13 @@ static void bla_add_claim(struct bat_priv *bat_priv, const uint8_t *mac, /* no need to register a new backbone */ goto claim_free_ref; - bat_dbg(DBG_BLA, bat_priv, - "bla_add_claim(): changing ownership for %pM, vid %d\n", - mac, vid); + batadv_dbg(BATADV_DBG_BLA, bat_priv, + "bla_add_claim(): changing ownership for %pM, vid %d\n", + mac, vid); claim->backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); - backbone_gw_free_ref(claim->backbone_gw); + batadv_backbone_gw_free_ref(claim->backbone_gw); } /* set (new) backbone gw */ @@ -581,45 +590,48 @@ static void bla_add_claim(struct bat_priv *bat_priv, const uint8_t *mac, backbone_gw->lasttime = jiffies; claim_free_ref: - claim_free_ref(claim); + batadv_claim_free_ref(claim); } /* Delete a claim from the claim hash which has the * given mac address and vid. */ -static void bla_del_claim(struct bat_priv *bat_priv, const uint8_t *mac, - const short vid) +static void batadv_bla_del_claim(struct batadv_priv *bat_priv, + const uint8_t *mac, const short vid) { - struct claim search_claim, *claim; + struct batadv_claim search_claim, *claim; memcpy(search_claim.addr, mac, ETH_ALEN); search_claim.vid = vid; - claim = claim_hash_find(bat_priv, &search_claim); + claim = batadv_claim_hash_find(bat_priv, &search_claim); if (!claim) return; - bat_dbg(DBG_BLA, bat_priv, "bla_del_claim(): %pM, vid %d\n", mac, vid); + batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_del_claim(): %pM, vid %d\n", + mac, vid); - hash_remove(bat_priv->claim_hash, compare_claim, choose_claim, claim); - claim_free_ref(claim); /* reference from the hash is gone */ + batadv_hash_remove(bat_priv->claim_hash, batadv_compare_claim, + batadv_choose_claim, claim); + batadv_claim_free_ref(claim); /* reference from the hash is gone */ claim->backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); /* don't need the reference from hash_find() anymore */ - claim_free_ref(claim); + batadv_claim_free_ref(claim); } /* check for ANNOUNCE frame, return 1 if handled */ -static int handle_announce(struct bat_priv *bat_priv, - uint8_t *an_addr, uint8_t *backbone_addr, short vid) +static int batadv_handle_announce(struct batadv_priv *bat_priv, + uint8_t *an_addr, uint8_t *backbone_addr, + short vid) { - struct backbone_gw *backbone_gw; + struct batadv_backbone_gw *backbone_gw; uint16_t crc; - if (memcmp(an_addr, announce_mac, 4) != 0) + if (memcmp(an_addr, batadv_announce_mac, 4) != 0) return 0; - backbone_gw = bla_get_backbone_gw(bat_priv, backbone_addr, vid); + backbone_gw = batadv_bla_get_backbone_gw(bat_priv, backbone_addr, vid); if (unlikely(!backbone_gw)) return 1; @@ -627,19 +639,19 @@ static int handle_announce(struct bat_priv *bat_priv, /* handle as ANNOUNCE frame */ backbone_gw->lasttime = jiffies; - crc = ntohs(*((uint16_t *)(&an_addr[4]))); + crc = ntohs(*((__be16 *)(&an_addr[4]))); - bat_dbg(DBG_BLA, bat_priv, - "handle_announce(): ANNOUNCE vid %d (sent by %pM)... CRC = %04x\n", - vid, backbone_gw->orig, crc); + batadv_dbg(BATADV_DBG_BLA, bat_priv, + "handle_announce(): ANNOUNCE vid %d (sent by %pM)... CRC = %04x\n", + vid, backbone_gw->orig, crc); if (backbone_gw->crc != crc) { - bat_dbg(DBG_BLA, backbone_gw->bat_priv, - "handle_announce(): CRC FAILED for %pM/%d (my = %04x, sent = %04x)\n", - backbone_gw->orig, backbone_gw->vid, backbone_gw->crc, - crc); + batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, + "handle_announce(): CRC FAILED for %pM/%d (my = %04x, sent = %04x)\n", + backbone_gw->orig, backbone_gw->vid, + backbone_gw->crc, crc); - bla_send_request(backbone_gw); + batadv_bla_send_request(backbone_gw); } else { /* if we have sent a request and the crc was OK, * we can allow traffic again. @@ -650,88 +662,92 @@ static int handle_announce(struct bat_priv *bat_priv, } } - backbone_gw_free_ref(backbone_gw); + batadv_backbone_gw_free_ref(backbone_gw); return 1; } /* check for REQUEST frame, return 1 if handled */ -static int handle_request(struct bat_priv *bat_priv, - struct hard_iface *primary_if, - uint8_t *backbone_addr, - struct ethhdr *ethhdr, short vid) +static int batadv_handle_request(struct batadv_priv *bat_priv, + struct batadv_hard_iface *primary_if, + uint8_t *backbone_addr, + struct ethhdr *ethhdr, short vid) { /* check for REQUEST frame */ - if (!compare_eth(backbone_addr, ethhdr->h_dest)) + if (!batadv_compare_eth(backbone_addr, ethhdr->h_dest)) return 0; /* sanity check, this should not happen on a normal switch, * we ignore it in this case. */ - if (!compare_eth(ethhdr->h_dest, primary_if->net_dev->dev_addr)) + if (!batadv_compare_eth(ethhdr->h_dest, primary_if->net_dev->dev_addr)) return 1; - bat_dbg(DBG_BLA, bat_priv, - "handle_request(): REQUEST vid %d (sent by %pM)...\n", - vid, ethhdr->h_source); + batadv_dbg(BATADV_DBG_BLA, bat_priv, + "handle_request(): REQUEST vid %d (sent by %pM)...\n", + vid, ethhdr->h_source); - bla_answer_request(bat_priv, primary_if, vid); + batadv_bla_answer_request(bat_priv, primary_if, vid); return 1; } /* check for UNCLAIM frame, return 1 if handled */ -static int handle_unclaim(struct bat_priv *bat_priv, - struct hard_iface *primary_if, - uint8_t *backbone_addr, - uint8_t *claim_addr, short vid) +static int batadv_handle_unclaim(struct batadv_priv *bat_priv, + struct batadv_hard_iface *primary_if, + uint8_t *backbone_addr, + uint8_t *claim_addr, short vid) { - struct backbone_gw *backbone_gw; + struct batadv_backbone_gw *backbone_gw; /* unclaim in any case if it is our own */ - if (primary_if && compare_eth(backbone_addr, - primary_if->net_dev->dev_addr)) - bla_send_claim(bat_priv, claim_addr, vid, CLAIM_TYPE_DEL); + if (primary_if && batadv_compare_eth(backbone_addr, + primary_if->net_dev->dev_addr)) + batadv_bla_send_claim(bat_priv, claim_addr, vid, + BATADV_CLAIM_TYPE_DEL); - backbone_gw = backbone_hash_find(bat_priv, backbone_addr, vid); + backbone_gw = batadv_backbone_hash_find(bat_priv, backbone_addr, vid); if (!backbone_gw) return 1; /* this must be an UNCLAIM frame */ - bat_dbg(DBG_BLA, bat_priv, - "handle_unclaim(): UNCLAIM %pM on vid %d (sent by %pM)...\n", - claim_addr, vid, backbone_gw->orig); + batadv_dbg(BATADV_DBG_BLA, bat_priv, + "handle_unclaim(): UNCLAIM %pM on vid %d (sent by %pM)...\n", + claim_addr, vid, backbone_gw->orig); - bla_del_claim(bat_priv, claim_addr, vid); - backbone_gw_free_ref(backbone_gw); + batadv_bla_del_claim(bat_priv, claim_addr, vid); + batadv_backbone_gw_free_ref(backbone_gw); return 1; } /* check for CLAIM frame, return 1 if handled */ -static int handle_claim(struct bat_priv *bat_priv, - struct hard_iface *primary_if, uint8_t *backbone_addr, - uint8_t *claim_addr, short vid) +static int batadv_handle_claim(struct batadv_priv *bat_priv, + struct batadv_hard_iface *primary_if, + uint8_t *backbone_addr, uint8_t *claim_addr, + short vid) { - struct backbone_gw *backbone_gw; + struct batadv_backbone_gw *backbone_gw; /* register the gateway if not yet available, and add the claim. */ - backbone_gw = bla_get_backbone_gw(bat_priv, backbone_addr, vid); + backbone_gw = batadv_bla_get_backbone_gw(bat_priv, backbone_addr, vid); if (unlikely(!backbone_gw)) return 1; /* this must be a CLAIM frame */ - bla_add_claim(bat_priv, claim_addr, vid, backbone_gw); - if (compare_eth(backbone_addr, primary_if->net_dev->dev_addr)) - bla_send_claim(bat_priv, claim_addr, vid, CLAIM_TYPE_ADD); + batadv_bla_add_claim(bat_priv, claim_addr, vid, backbone_gw); + if (batadv_compare_eth(backbone_addr, primary_if->net_dev->dev_addr)) + batadv_bla_send_claim(bat_priv, claim_addr, vid, + BATADV_CLAIM_TYPE_ADD); /* TODO: we could call something like tt_local_del() here. */ - backbone_gw_free_ref(backbone_gw); + batadv_backbone_gw_free_ref(backbone_gw); return 1; } /** + * batadv_check_claim_group * @bat_priv: the bat priv with all the soft interface information * @hw_src: the Hardware source in the ARP Header * @hw_dst: the Hardware destination in the ARP Header @@ -746,16 +762,16 @@ static int handle_claim(struct bat_priv *bat_priv, * 1 - if is a claim packet from another group * 0 - if it is not a claim packet */ -static int check_claim_group(struct bat_priv *bat_priv, - struct hard_iface *primary_if, - uint8_t *hw_src, uint8_t *hw_dst, - struct ethhdr *ethhdr) +static int batadv_check_claim_group(struct batadv_priv *bat_priv, + struct batadv_hard_iface *primary_if, + uint8_t *hw_src, uint8_t *hw_dst, + struct ethhdr *ethhdr) { uint8_t *backbone_addr; - struct orig_node *orig_node; - struct bla_claim_dst *bla_dst, *bla_dst_own; + struct batadv_orig_node *orig_node; + struct batadv_bla_claim_dst *bla_dst, *bla_dst_own; - bla_dst = (struct bla_claim_dst *)hw_dst; + bla_dst = (struct batadv_bla_claim_dst *)hw_dst; bla_dst_own = &bat_priv->claim_dest; /* check if it is a claim packet in general */ @@ -767,12 +783,12 @@ static int check_claim_group(struct bat_priv *bat_priv, * otherwise assume it is in the hw_src */ switch (bla_dst->type) { - case CLAIM_TYPE_ADD: + case BATADV_CLAIM_TYPE_ADD: backbone_addr = hw_src; break; - case CLAIM_TYPE_REQUEST: - case CLAIM_TYPE_ANNOUNCE: - case CLAIM_TYPE_DEL: + case BATADV_CLAIM_TYPE_REQUEST: + case BATADV_CLAIM_TYPE_ANNOUNCE: + case BATADV_CLAIM_TYPE_DEL: backbone_addr = ethhdr->h_source; break; default: @@ -780,7 +796,7 @@ static int check_claim_group(struct bat_priv *bat_priv, } /* don't accept claim frames from ourselves */ - if (compare_eth(backbone_addr, primary_if->net_dev->dev_addr)) + if (batadv_compare_eth(backbone_addr, primary_if->net_dev->dev_addr)) return 0; /* if its already the same group, it is fine. */ @@ -788,7 +804,7 @@ static int check_claim_group(struct bat_priv *bat_priv, return 2; /* lets see if this originator is in our mesh */ - orig_node = orig_hash_find(bat_priv, backbone_addr); + orig_node = batadv_orig_hash_find(bat_priv, backbone_addr); /* dont accept claims from gateways which are not in * the same mesh or group. @@ -798,20 +814,19 @@ static int check_claim_group(struct bat_priv *bat_priv, /* if our mesh friends mac is bigger, use it for ourselves. */ if (ntohs(bla_dst->group) > ntohs(bla_dst_own->group)) { - bat_dbg(DBG_BLA, bat_priv, - "taking other backbones claim group: %04x\n", - ntohs(bla_dst->group)); + batadv_dbg(BATADV_DBG_BLA, bat_priv, + "taking other backbones claim group: %04x\n", + ntohs(bla_dst->group)); bla_dst_own->group = bla_dst->group; } - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); return 2; } -/** - * @bat_priv: the bat priv with all the soft interface information +/* @bat_priv: the bat priv with all the soft interface information * @skb: the frame to be checked * * Check if this is a claim frame, and process it accordingly. @@ -819,15 +834,15 @@ static int check_claim_group(struct bat_priv *bat_priv, * returns 1 if it was a claim frame, otherwise return 0 to * tell the callee that it can use the frame on its own. */ -static int bla_process_claim(struct bat_priv *bat_priv, - struct hard_iface *primary_if, - struct sk_buff *skb) +static int batadv_bla_process_claim(struct batadv_priv *bat_priv, + struct batadv_hard_iface *primary_if, + struct sk_buff *skb) { struct ethhdr *ethhdr; struct vlan_ethhdr *vhdr; struct arphdr *arphdr; uint8_t *hw_src, *hw_dst; - struct bla_claim_dst *bla_dst; + struct batadv_bla_claim_dst *bla_dst; uint16_t proto; int headlen; short vid = -1; @@ -860,7 +875,6 @@ static int bla_process_claim(struct bat_priv *bat_priv, /* Check whether the ARP frame carries a valid * IP information */ - if (arphdr->ar_hrd != htons(ARPHRD_ETHER)) return 0; if (arphdr->ar_pro != htons(ETH_P_IP)) @@ -872,59 +886,62 @@ static int bla_process_claim(struct bat_priv *bat_priv, hw_src = (uint8_t *)arphdr + sizeof(struct arphdr); hw_dst = hw_src + ETH_ALEN + 4; - bla_dst = (struct bla_claim_dst *)hw_dst; + bla_dst = (struct batadv_bla_claim_dst *)hw_dst; /* check if it is a claim frame. */ - ret = check_claim_group(bat_priv, primary_if, hw_src, hw_dst, ethhdr); + ret = batadv_check_claim_group(bat_priv, primary_if, hw_src, hw_dst, + ethhdr); if (ret == 1) - bat_dbg(DBG_BLA, bat_priv, - "bla_process_claim(): received a claim frame from another group. From: %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", - ethhdr->h_source, vid, hw_src, hw_dst); + batadv_dbg(BATADV_DBG_BLA, bat_priv, + "bla_process_claim(): received a claim frame from another group. From: %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", + ethhdr->h_source, vid, hw_src, hw_dst); if (ret < 2) return ret; /* become a backbone gw ourselves on this vlan if not happened yet */ - bla_update_own_backbone_gw(bat_priv, primary_if, vid); + batadv_bla_update_own_backbone_gw(bat_priv, primary_if, vid); /* check for the different types of claim frames ... */ switch (bla_dst->type) { - case CLAIM_TYPE_ADD: - if (handle_claim(bat_priv, primary_if, hw_src, - ethhdr->h_source, vid)) + case BATADV_CLAIM_TYPE_ADD: + if (batadv_handle_claim(bat_priv, primary_if, hw_src, + ethhdr->h_source, vid)) return 1; break; - case CLAIM_TYPE_DEL: - if (handle_unclaim(bat_priv, primary_if, - ethhdr->h_source, hw_src, vid)) + case BATADV_CLAIM_TYPE_DEL: + if (batadv_handle_unclaim(bat_priv, primary_if, + ethhdr->h_source, hw_src, vid)) return 1; break; - case CLAIM_TYPE_ANNOUNCE: - if (handle_announce(bat_priv, hw_src, ethhdr->h_source, vid)) + case BATADV_CLAIM_TYPE_ANNOUNCE: + if (batadv_handle_announce(bat_priv, hw_src, ethhdr->h_source, + vid)) return 1; break; - case CLAIM_TYPE_REQUEST: - if (handle_request(bat_priv, primary_if, hw_src, ethhdr, vid)) + case BATADV_CLAIM_TYPE_REQUEST: + if (batadv_handle_request(bat_priv, primary_if, hw_src, ethhdr, + vid)) return 1; break; } - bat_dbg(DBG_BLA, bat_priv, - "bla_process_claim(): ERROR - this looks like a claim frame, but is useless. eth src %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", - ethhdr->h_source, vid, hw_src, hw_dst); + batadv_dbg(BATADV_DBG_BLA, bat_priv, + "bla_process_claim(): ERROR - this looks like a claim frame, but is useless. eth src %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", + ethhdr->h_source, vid, hw_src, hw_dst); return 1; } /* Check when we last heard from other nodes, and remove them in case of * a time out, or clean all backbone gws if now is set. */ -static void bla_purge_backbone_gw(struct bat_priv *bat_priv, int now) +static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) { - struct backbone_gw *backbone_gw; + struct batadv_backbone_gw *backbone_gw; struct hlist_node *node, *node_tmp; struct hlist_head *head; - struct hashtable_t *hash; + struct batadv_hashtable *hash; spinlock_t *list_lock; /* protects write access to the hash lists */ int i; @@ -941,29 +958,30 @@ static void bla_purge_backbone_gw(struct bat_priv *bat_priv, int now) head, hash_entry) { if (now) goto purge_now; - if (!has_timed_out(backbone_gw->lasttime, - BLA_BACKBONE_TIMEOUT)) + if (!batadv_has_timed_out(backbone_gw->lasttime, + BATADV_BLA_BACKBONE_TIMEOUT)) continue; - bat_dbg(DBG_BLA, backbone_gw->bat_priv, - "bla_purge_backbone_gw(): backbone gw %pM timed out\n", - backbone_gw->orig); + batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, + "bla_purge_backbone_gw(): backbone gw %pM timed out\n", + backbone_gw->orig); purge_now: /* don't wait for the pending request anymore */ if (atomic_read(&backbone_gw->request_sent)) atomic_dec(&bat_priv->bla_num_requests); - bla_del_backbone_claims(backbone_gw); + batadv_bla_del_backbone_claims(backbone_gw); hlist_del_rcu(node); - backbone_gw_free_ref(backbone_gw); + batadv_backbone_gw_free_ref(backbone_gw); } spin_unlock_bh(list_lock); } } /** + * batadv_bla_purge_claims * @bat_priv: the bat priv with all the soft interface information * @primary_if: the selected primary interface, may be NULL if now is set * @now: whether the whole hash shall be wiped now @@ -971,13 +989,14 @@ purge_now: * Check when we heard last time from our own claims, and remove them in case of * a time out, or clean all claims if now is set */ -static void bla_purge_claims(struct bat_priv *bat_priv, - struct hard_iface *primary_if, int now) +static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, + struct batadv_hard_iface *primary_if, + int now) { - struct claim *claim; + struct batadv_claim *claim; struct hlist_node *node; struct hlist_head *head; - struct hashtable_t *hash; + struct batadv_hashtable *hash; int i; hash = bat_priv->claim_hash; @@ -991,42 +1010,42 @@ static void bla_purge_claims(struct bat_priv *bat_priv, hlist_for_each_entry_rcu(claim, node, head, hash_entry) { if (now) goto purge_now; - if (!compare_eth(claim->backbone_gw->orig, - primary_if->net_dev->dev_addr)) + if (!batadv_compare_eth(claim->backbone_gw->orig, + primary_if->net_dev->dev_addr)) continue; - if (!has_timed_out(claim->lasttime, - BLA_CLAIM_TIMEOUT)) + if (!batadv_has_timed_out(claim->lasttime, + BATADV_BLA_CLAIM_TIMEOUT)) continue; - bat_dbg(DBG_BLA, bat_priv, - "bla_purge_claims(): %pM, vid %d, time out\n", - claim->addr, claim->vid); + batadv_dbg(BATADV_DBG_BLA, bat_priv, + "bla_purge_claims(): %pM, vid %d, time out\n", + claim->addr, claim->vid); purge_now: - handle_unclaim(bat_priv, primary_if, - claim->backbone_gw->orig, - claim->addr, claim->vid); + batadv_handle_unclaim(bat_priv, primary_if, + claim->backbone_gw->orig, + claim->addr, claim->vid); } rcu_read_unlock(); } } /** + * batadv_bla_update_orig_address * @bat_priv: the bat priv with all the soft interface information * @primary_if: the new selected primary_if * @oldif: the old primary interface, may be NULL * * Update the backbone gateways when the own orig address changes. - * */ -void bla_update_orig_address(struct bat_priv *bat_priv, - struct hard_iface *primary_if, - struct hard_iface *oldif) +void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, + struct batadv_hard_iface *primary_if, + struct batadv_hard_iface *oldif) { - struct backbone_gw *backbone_gw; + struct batadv_backbone_gw *backbone_gw; struct hlist_node *node; struct hlist_head *head; - struct hashtable_t *hash; + struct batadv_hashtable *hash; int i; /* reset bridge loop avoidance group id */ @@ -1034,8 +1053,8 @@ void bla_update_orig_address(struct bat_priv *bat_priv, htons(crc16(0, primary_if->net_dev->dev_addr, ETH_ALEN)); if (!oldif) { - bla_purge_claims(bat_priv, NULL, 1); - bla_purge_backbone_gw(bat_priv, 1); + batadv_bla_purge_claims(bat_priv, NULL, 1); + batadv_bla_purge_backbone_gw(bat_priv, 1); return; } @@ -1049,8 +1068,8 @@ void bla_update_orig_address(struct bat_priv *bat_priv, rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { /* own orig still holds the old value. */ - if (!compare_eth(backbone_gw->orig, - oldif->net_dev->dev_addr)) + if (!batadv_compare_eth(backbone_gw->orig, + oldif->net_dev->dev_addr)) continue; memcpy(backbone_gw->orig, @@ -1058,7 +1077,7 @@ void bla_update_orig_address(struct bat_priv *bat_priv, /* send an announce frame so others will ask for our * claims and update their tables. */ - bla_send_announce(bat_priv, backbone_gw); + batadv_bla_send_announce(bat_priv, backbone_gw); } rcu_read_unlock(); } @@ -1067,36 +1086,36 @@ void bla_update_orig_address(struct bat_priv *bat_priv, /* (re)start the timer */ -static void bla_start_timer(struct bat_priv *bat_priv) +static void batadv_bla_start_timer(struct batadv_priv *bat_priv) { - INIT_DELAYED_WORK(&bat_priv->bla_work, bla_periodic_work); - queue_delayed_work(bat_event_workqueue, &bat_priv->bla_work, - msecs_to_jiffies(BLA_PERIOD_LENGTH)); + INIT_DELAYED_WORK(&bat_priv->bla_work, batadv_bla_periodic_work); + queue_delayed_work(batadv_event_workqueue, &bat_priv->bla_work, + msecs_to_jiffies(BATADV_BLA_PERIOD_LENGTH)); } /* periodic work to do: * * purge structures when they are too old * * send announcements */ -static void bla_periodic_work(struct work_struct *work) +static void batadv_bla_periodic_work(struct work_struct *work) { struct delayed_work *delayed_work = container_of(work, struct delayed_work, work); - struct bat_priv *bat_priv = - container_of(delayed_work, struct bat_priv, bla_work); + struct batadv_priv *bat_priv; struct hlist_node *node; struct hlist_head *head; - struct backbone_gw *backbone_gw; - struct hashtable_t *hash; - struct hard_iface *primary_if; + struct batadv_backbone_gw *backbone_gw; + struct batadv_hashtable *hash; + struct batadv_hard_iface *primary_if; int i; - primary_if = primary_if_get_selected(bat_priv); + bat_priv = container_of(delayed_work, struct batadv_priv, bla_work); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; - bla_purge_claims(bat_priv, primary_if, 0); - bla_purge_backbone_gw(bat_priv, 0); + batadv_bla_purge_claims(bat_priv, primary_if, 0); + batadv_bla_purge_backbone_gw(bat_priv, 0); if (!atomic_read(&bat_priv->bridge_loop_avoidance)) goto out; @@ -1110,67 +1129,81 @@ static void bla_periodic_work(struct work_struct *work) rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { - if (!compare_eth(backbone_gw->orig, - primary_if->net_dev->dev_addr)) + if (!batadv_compare_eth(backbone_gw->orig, + primary_if->net_dev->dev_addr)) continue; backbone_gw->lasttime = jiffies; - bla_send_announce(bat_priv, backbone_gw); + batadv_bla_send_announce(bat_priv, backbone_gw); } rcu_read_unlock(); } out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); - bla_start_timer(bat_priv); + batadv_bla_start_timer(bat_priv); } +/* The hash for claim and backbone hash receive the same key because they + * are getting initialized by hash_new with the same key. Reinitializing + * them with to different keys to allow nested locking without generating + * lockdep warnings + */ +static struct lock_class_key batadv_claim_hash_lock_class_key; +static struct lock_class_key batadv_backbone_hash_lock_class_key; + /* initialize all bla structures */ -int bla_init(struct bat_priv *bat_priv) +int batadv_bla_init(struct batadv_priv *bat_priv) { int i; uint8_t claim_dest[ETH_ALEN] = {0xff, 0x43, 0x05, 0x00, 0x00, 0x00}; - struct hard_iface *primary_if; + struct batadv_hard_iface *primary_if; - bat_dbg(DBG_BLA, bat_priv, "bla hash registering\n"); + batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla hash registering\n"); /* setting claim destination address */ memcpy(&bat_priv->claim_dest.magic, claim_dest, 3); bat_priv->claim_dest.type = 0; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (primary_if) { bat_priv->claim_dest.group = htons(crc16(0, primary_if->net_dev->dev_addr, ETH_ALEN)); - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); } else { bat_priv->claim_dest.group = 0; /* will be set later */ } /* initialize the duplicate list */ - for (i = 0; i < DUPLIST_SIZE; i++) + for (i = 0; i < BATADV_DUPLIST_SIZE; i++) bat_priv->bcast_duplist[i].entrytime = - jiffies - msecs_to_jiffies(DUPLIST_TIMEOUT); + jiffies - msecs_to_jiffies(BATADV_DUPLIST_TIMEOUT); bat_priv->bcast_duplist_curr = 0; if (bat_priv->claim_hash) - return 1; + return 0; - bat_priv->claim_hash = hash_new(128); - bat_priv->backbone_hash = hash_new(32); + bat_priv->claim_hash = batadv_hash_new(128); + bat_priv->backbone_hash = batadv_hash_new(32); if (!bat_priv->claim_hash || !bat_priv->backbone_hash) - return -1; + return -ENOMEM; - bat_dbg(DBG_BLA, bat_priv, "bla hashes initialized\n"); + batadv_hash_set_lock_class(bat_priv->claim_hash, + &batadv_claim_hash_lock_class_key); + batadv_hash_set_lock_class(bat_priv->backbone_hash, + &batadv_backbone_hash_lock_class_key); - bla_start_timer(bat_priv); - return 1; + batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla hashes initialized\n"); + + batadv_bla_start_timer(bat_priv); + return 0; } /** + * batadv_bla_check_bcast_duplist * @bat_priv: the bat priv with all the soft interface information * @bcast_packet: originator mac address * @hdr_size: maximum length of the frame @@ -1183,17 +1216,15 @@ int bla_init(struct bat_priv *bat_priv) * with a good chance that it is the same packet. If it is furthermore * sent by another host, drop it. We allow equal packets from * the same host however as this might be intended. - * - **/ - -int bla_check_bcast_duplist(struct bat_priv *bat_priv, - struct bcast_packet *bcast_packet, - int hdr_size) + */ +int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, + struct batadv_bcast_packet *bcast_packet, + int hdr_size) { int i, length, curr; uint8_t *content; uint16_t crc; - struct bcast_duplist_entry *entry; + struct batadv_bcast_duplist_entry *entry; length = hdr_size - sizeof(*bcast_packet); content = (uint8_t *)bcast_packet; @@ -1202,20 +1233,21 @@ int bla_check_bcast_duplist(struct bat_priv *bat_priv, /* calculate the crc ... */ crc = crc16(0, content, length); - for (i = 0 ; i < DUPLIST_SIZE; i++) { - curr = (bat_priv->bcast_duplist_curr + i) % DUPLIST_SIZE; + for (i = 0; i < BATADV_DUPLIST_SIZE; i++) { + curr = (bat_priv->bcast_duplist_curr + i) % BATADV_DUPLIST_SIZE; entry = &bat_priv->bcast_duplist[curr]; /* we can stop searching if the entry is too old ; * later entries will be even older */ - if (has_timed_out(entry->entrytime, DUPLIST_TIMEOUT)) + if (batadv_has_timed_out(entry->entrytime, + BATADV_DUPLIST_TIMEOUT)) break; if (entry->crc != crc) continue; - if (compare_eth(entry->orig, bcast_packet->orig)) + if (batadv_compare_eth(entry->orig, bcast_packet->orig)) continue; /* this entry seems to match: same crc, not too old, @@ -1224,7 +1256,8 @@ int bla_check_bcast_duplist(struct bat_priv *bat_priv, return 1; } /* not found, add a new entry (overwrite the oldest entry) */ - curr = (bat_priv->bcast_duplist_curr + DUPLIST_SIZE - 1) % DUPLIST_SIZE; + curr = (bat_priv->bcast_duplist_curr + BATADV_DUPLIST_SIZE - 1); + curr %= BATADV_DUPLIST_SIZE; entry = &bat_priv->bcast_duplist[curr]; entry->crc = crc; entry->entrytime = jiffies; @@ -1237,22 +1270,19 @@ int bla_check_bcast_duplist(struct bat_priv *bat_priv, -/** - * @bat_priv: the bat priv with all the soft interface information +/* @bat_priv: the bat priv with all the soft interface information * @orig: originator mac address * * check if the originator is a gateway for any VLAN ID. * * returns 1 if it is found, 0 otherwise - * */ - -int bla_is_backbone_gw_orig(struct bat_priv *bat_priv, uint8_t *orig) +int batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, uint8_t *orig) { - struct hashtable_t *hash = bat_priv->backbone_hash; + struct batadv_hashtable *hash = bat_priv->backbone_hash; struct hlist_head *head; struct hlist_node *node; - struct backbone_gw *backbone_gw; + struct batadv_backbone_gw *backbone_gw; int i; if (!atomic_read(&bat_priv->bridge_loop_avoidance)) @@ -1266,7 +1296,7 @@ int bla_is_backbone_gw_orig(struct bat_priv *bat_priv, uint8_t *orig) rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { - if (compare_eth(backbone_gw->orig, orig)) { + if (batadv_compare_eth(backbone_gw->orig, orig)) { rcu_read_unlock(); return 1; } @@ -1279,6 +1309,7 @@ int bla_is_backbone_gw_orig(struct bat_priv *bat_priv, uint8_t *orig) /** + * batadv_bla_is_backbone_gw * @skb: the frame to be checked * @orig_node: the orig_node of the frame * @hdr_size: maximum length of the frame @@ -1286,14 +1317,13 @@ int bla_is_backbone_gw_orig(struct bat_priv *bat_priv, uint8_t *orig) * bla_is_backbone_gw inspects the skb for the VLAN ID and returns 1 * if the orig_node is also a gateway on the soft interface, otherwise it * returns 0. - * */ -int bla_is_backbone_gw(struct sk_buff *skb, - struct orig_node *orig_node, int hdr_size) +int batadv_bla_is_backbone_gw(struct sk_buff *skb, + struct batadv_orig_node *orig_node, int hdr_size) { struct ethhdr *ethhdr; struct vlan_ethhdr *vhdr; - struct backbone_gw *backbone_gw; + struct batadv_backbone_gw *backbone_gw; short vid = -1; if (!atomic_read(&orig_node->bat_priv->bridge_loop_avoidance)) @@ -1315,39 +1345,39 @@ int bla_is_backbone_gw(struct sk_buff *skb, } /* see if this originator is a backbone gw for this VLAN */ - - backbone_gw = backbone_hash_find(orig_node->bat_priv, - orig_node->orig, vid); + backbone_gw = batadv_backbone_hash_find(orig_node->bat_priv, + orig_node->orig, vid); if (!backbone_gw) return 0; - backbone_gw_free_ref(backbone_gw); + batadv_backbone_gw_free_ref(backbone_gw); return 1; } /* free all bla structures (for softinterface free or module unload) */ -void bla_free(struct bat_priv *bat_priv) +void batadv_bla_free(struct batadv_priv *bat_priv) { - struct hard_iface *primary_if; + struct batadv_hard_iface *primary_if; cancel_delayed_work_sync(&bat_priv->bla_work); - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (bat_priv->claim_hash) { - bla_purge_claims(bat_priv, primary_if, 1); - hash_destroy(bat_priv->claim_hash); + batadv_bla_purge_claims(bat_priv, primary_if, 1); + batadv_hash_destroy(bat_priv->claim_hash); bat_priv->claim_hash = NULL; } if (bat_priv->backbone_hash) { - bla_purge_backbone_gw(bat_priv, 1); - hash_destroy(bat_priv->backbone_hash); + batadv_bla_purge_backbone_gw(bat_priv, 1); + batadv_hash_destroy(bat_priv->backbone_hash); bat_priv->backbone_hash = NULL; } if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); } /** + * batadv_bla_rx * @bat_priv: the bat priv with all the soft interface information * @skb: the frame to be checked * @vid: the VLAN ID of the frame @@ -1360,19 +1390,18 @@ void bla_free(struct bat_priv *bat_priv) * in these cases, the skb is further handled by this function and * returns 1, otherwise it returns 0 and the caller shall further * process the skb. - * */ -int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid, - bool is_bcast) +int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid, + bool is_bcast) { struct ethhdr *ethhdr; - struct claim search_claim, *claim = NULL; - struct hard_iface *primary_if; + struct batadv_claim search_claim, *claim = NULL; + struct batadv_hard_iface *primary_if; int ret; ethhdr = (struct ethhdr *)skb_mac_header(skb); - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto handled; @@ -1387,21 +1416,21 @@ int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid, memcpy(search_claim.addr, ethhdr->h_source, ETH_ALEN); search_claim.vid = vid; - claim = claim_hash_find(bat_priv, &search_claim); + claim = batadv_claim_hash_find(bat_priv, &search_claim); if (!claim) { /* possible optimization: race for a claim */ /* No claim exists yet, claim it for us! */ - handle_claim(bat_priv, primary_if, - primary_if->net_dev->dev_addr, - ethhdr->h_source, vid); + batadv_handle_claim(bat_priv, primary_if, + primary_if->net_dev->dev_addr, + ethhdr->h_source, vid); goto allow; } /* if it is our own claim ... */ - if (compare_eth(claim->backbone_gw->orig, - primary_if->net_dev->dev_addr)) { + if (batadv_compare_eth(claim->backbone_gw->orig, + primary_if->net_dev->dev_addr)) { /* ... allow it in any case */ claim->lasttime = jiffies; goto allow; @@ -1421,13 +1450,13 @@ int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid, * send a claim and update the claim table * immediately. */ - handle_claim(bat_priv, primary_if, - primary_if->net_dev->dev_addr, - ethhdr->h_source, vid); + batadv_handle_claim(bat_priv, primary_if, + primary_if->net_dev->dev_addr, + ethhdr->h_source, vid); goto allow; } allow: - bla_update_own_backbone_gw(bat_priv, primary_if, vid); + batadv_bla_update_own_backbone_gw(bat_priv, primary_if, vid); ret = 0; goto out; @@ -1437,13 +1466,14 @@ handled: out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); if (claim) - claim_free_ref(claim); + batadv_claim_free_ref(claim); return ret; } /** + * batadv_bla_tx * @bat_priv: the bat priv with all the soft interface information * @skb: the frame to be checked * @vid: the VLAN ID of the frame @@ -1455,16 +1485,15 @@ out: * in these cases, the skb is further handled by this function and * returns 1, otherwise it returns 0 and the caller shall further * process the skb. - * */ -int bla_tx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid) +int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid) { struct ethhdr *ethhdr; - struct claim search_claim, *claim = NULL; - struct hard_iface *primary_if; + struct batadv_claim search_claim, *claim = NULL; + struct batadv_hard_iface *primary_if; int ret = 0; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; @@ -1474,7 +1503,7 @@ int bla_tx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid) /* in VLAN case, the mac header might not be set. */ skb_reset_mac_header(skb); - if (bla_process_claim(bat_priv, primary_if, skb)) + if (batadv_bla_process_claim(bat_priv, primary_if, skb)) goto handled; ethhdr = (struct ethhdr *)skb_mac_header(skb); @@ -1487,21 +1516,21 @@ int bla_tx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid) memcpy(search_claim.addr, ethhdr->h_source, ETH_ALEN); search_claim.vid = vid; - claim = claim_hash_find(bat_priv, &search_claim); + claim = batadv_claim_hash_find(bat_priv, &search_claim); /* if no claim exists, allow it. */ if (!claim) goto allow; /* check if we are responsible. */ - if (compare_eth(claim->backbone_gw->orig, - primary_if->net_dev->dev_addr)) { + if (batadv_compare_eth(claim->backbone_gw->orig, + primary_if->net_dev->dev_addr)) { /* if yes, the client has roamed and we have * to unclaim it. */ - handle_unclaim(bat_priv, primary_if, - primary_if->net_dev->dev_addr, - ethhdr->h_source, vid); + batadv_handle_unclaim(bat_priv, primary_if, + primary_if->net_dev->dev_addr, + ethhdr->h_source, vid); goto allow; } @@ -1518,33 +1547,34 @@ int bla_tx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid) goto allow; } allow: - bla_update_own_backbone_gw(bat_priv, primary_if, vid); + batadv_bla_update_own_backbone_gw(bat_priv, primary_if, vid); ret = 0; goto out; handled: ret = 1; out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); if (claim) - claim_free_ref(claim); + batadv_claim_free_ref(claim); return ret; } -int bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) +int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) { struct net_device *net_dev = (struct net_device *)seq->private; - struct bat_priv *bat_priv = netdev_priv(net_dev); - struct hashtable_t *hash = bat_priv->claim_hash; - struct claim *claim; - struct hard_iface *primary_if; + struct batadv_priv *bat_priv = netdev_priv(net_dev); + struct batadv_hashtable *hash = bat_priv->claim_hash; + struct batadv_claim *claim; + struct batadv_hard_iface *primary_if; struct hlist_node *node; struct hlist_head *head; uint32_t i; bool is_own; int ret = 0; + uint8_t *primary_addr; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) { ret = seq_printf(seq, "BATMAN mesh %s disabled - please specify interfaces to enable it\n", @@ -1552,16 +1582,17 @@ int bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) goto out; } - if (primary_if->if_status != IF_ACTIVE) { + if (primary_if->if_status != BATADV_IF_ACTIVE) { ret = seq_printf(seq, "BATMAN mesh %s disabled - primary interface not active\n", net_dev->name); goto out; } + primary_addr = primary_if->net_dev->dev_addr; seq_printf(seq, "Claims announced for the mesh %s (orig %pM, group id %04x)\n", - net_dev->name, primary_if->net_dev->dev_addr, + net_dev->name, primary_addr, ntohs(bat_priv->claim_dest.group)); seq_printf(seq, " %-17s %-5s %-17s [o] (%-4s)\n", "Client", "VID", "Originator", "CRC"); @@ -1570,8 +1601,8 @@ int bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) rcu_read_lock(); hlist_for_each_entry_rcu(claim, node, head, hash_entry) { - is_own = compare_eth(claim->backbone_gw->orig, - primary_if->net_dev->dev_addr); + is_own = batadv_compare_eth(claim->backbone_gw->orig, + primary_addr); seq_printf(seq, " * %pM on % 5d by %pM [%c] (%04x)\n", claim->addr, claim->vid, claim->backbone_gw->orig, @@ -1582,6 +1613,6 @@ int bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) } out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); return ret; } diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index dc5227b398d..563cfbf94a7 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: * * Simon Wunderlich * @@ -16,81 +15,84 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_BLA_H_ #define _NET_BATMAN_ADV_BLA_H_ #ifdef CONFIG_BATMAN_ADV_BLA -int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid, - bool is_bcast); -int bla_tx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid); -int bla_is_backbone_gw(struct sk_buff *skb, - struct orig_node *orig_node, int hdr_size); -int bla_claim_table_seq_print_text(struct seq_file *seq, void *offset); -int bla_is_backbone_gw_orig(struct bat_priv *bat_priv, uint8_t *orig); -int bla_check_bcast_duplist(struct bat_priv *bat_priv, - struct bcast_packet *bcast_packet, int hdr_size); -void bla_update_orig_address(struct bat_priv *bat_priv, - struct hard_iface *primary_if, - struct hard_iface *oldif); -int bla_init(struct bat_priv *bat_priv); -void bla_free(struct bat_priv *bat_priv); +int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid, + bool is_bcast); +int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid); +int batadv_bla_is_backbone_gw(struct sk_buff *skb, + struct batadv_orig_node *orig_node, int hdr_size); +int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset); +int batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, uint8_t *orig); +int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, + struct batadv_bcast_packet *bcast_packet, + int hdr_size); +void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, + struct batadv_hard_iface *primary_if, + struct batadv_hard_iface *oldif); +int batadv_bla_init(struct batadv_priv *bat_priv); +void batadv_bla_free(struct batadv_priv *bat_priv); -#define BLA_CRC_INIT 0 +#define BATADV_BLA_CRC_INIT 0 #else /* ifdef CONFIG_BATMAN_ADV_BLA */ -static inline int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, - short vid, bool is_bcast) +static inline int batadv_bla_rx(struct batadv_priv *bat_priv, + struct sk_buff *skb, short vid, + bool is_bcast) { return 0; } -static inline int bla_tx(struct bat_priv *bat_priv, struct sk_buff *skb, - short vid) +static inline int batadv_bla_tx(struct batadv_priv *bat_priv, + struct sk_buff *skb, short vid) { return 0; } -static inline int bla_is_backbone_gw(struct sk_buff *skb, - struct orig_node *orig_node, - int hdr_size) +static inline int batadv_bla_is_backbone_gw(struct sk_buff *skb, + struct batadv_orig_node *orig_node, + int hdr_size) { return 0; } -static inline int bla_claim_table_seq_print_text(struct seq_file *seq, - void *offset) +static inline int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, + void *offset) { return 0; } -static inline int bla_is_backbone_gw_orig(struct bat_priv *bat_priv, - uint8_t *orig) +static inline int batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, + uint8_t *orig) { return 0; } -static inline int bla_check_bcast_duplist(struct bat_priv *bat_priv, - struct bcast_packet *bcast_packet, - int hdr_size) +static inline int +batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, + struct batadv_bcast_packet *bcast_packet, + int hdr_size) { return 0; } -static inline void bla_update_orig_address(struct bat_priv *bat_priv, - struct hard_iface *primary_if, - struct hard_iface *oldif) +static inline void +batadv_bla_update_orig_address(struct batadv_priv *bat_priv, + struct batadv_hard_iface *primary_if, + struct batadv_hard_iface *oldif) { } -static inline int bla_init(struct bat_priv *bat_priv) +static inline int batadv_bla_init(struct batadv_priv *bat_priv) { return 1; } -static inline void bla_free(struct bat_priv *bat_priv) +static inline void batadv_bla_free(struct batadv_priv *bat_priv) { } diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c new file mode 100644 index 00000000000..34fbb1667bc --- /dev/null +++ b/net/batman-adv/debugfs.c @@ -0,0 +1,409 @@ +/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: + * + * Marek Lindner + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA + */ + +#include "main.h" + +#include <linux/debugfs.h> + +#include "debugfs.h" +#include "translation-table.h" +#include "originator.h" +#include "hard-interface.h" +#include "gateway_common.h" +#include "gateway_client.h" +#include "soft-interface.h" +#include "vis.h" +#include "icmp_socket.h" +#include "bridge_loop_avoidance.h" + +static struct dentry *batadv_debugfs; + +#ifdef CONFIG_BATMAN_ADV_DEBUG +#define BATADV_LOG_BUFF_MASK (batadv_log_buff_len - 1) + +static const int batadv_log_buff_len = BATADV_LOG_BUF_LEN; + +static char *batadv_log_char_addr(struct batadv_debug_log *debug_log, + size_t idx) +{ + return &debug_log->log_buff[idx & BATADV_LOG_BUFF_MASK]; +} + +static void batadv_emit_log_char(struct batadv_debug_log *debug_log, char c) +{ + char *char_addr; + + char_addr = batadv_log_char_addr(debug_log, debug_log->log_end); + *char_addr = c; + debug_log->log_end++; + + if (debug_log->log_end - debug_log->log_start > batadv_log_buff_len) + debug_log->log_start = debug_log->log_end - batadv_log_buff_len; +} + +__printf(2, 3) +static int batadv_fdebug_log(struct batadv_debug_log *debug_log, + const char *fmt, ...) +{ + va_list args; + static char debug_log_buf[256]; + char *p; + + if (!debug_log) + return 0; + + spin_lock_bh(&debug_log->lock); + va_start(args, fmt); + vscnprintf(debug_log_buf, sizeof(debug_log_buf), fmt, args); + va_end(args); + + for (p = debug_log_buf; *p != 0; p++) + batadv_emit_log_char(debug_log, *p); + + spin_unlock_bh(&debug_log->lock); + + wake_up(&debug_log->queue_wait); + + return 0; +} + +int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...) +{ + va_list args; + char tmp_log_buf[256]; + + va_start(args, fmt); + vscnprintf(tmp_log_buf, sizeof(tmp_log_buf), fmt, args); + batadv_fdebug_log(bat_priv->debug_log, "[%10u] %s", + jiffies_to_msecs(jiffies), tmp_log_buf); + va_end(args); + + return 0; +} + +static int batadv_log_open(struct inode *inode, struct file *file) +{ + nonseekable_open(inode, file); + file->private_data = inode->i_private; + batadv_inc_module_count(); + return 0; +} + +static int batadv_log_release(struct inode *inode, struct file *file) +{ + batadv_dec_module_count(); + return 0; +} + +static int batadv_log_empty(struct batadv_debug_log *debug_log) +{ + return !(debug_log->log_start - debug_log->log_end); +} + +static ssize_t batadv_log_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct batadv_priv *bat_priv = file->private_data; + struct batadv_debug_log *debug_log = bat_priv->debug_log; + int error, i = 0; + char *char_addr; + char c; + + if ((file->f_flags & O_NONBLOCK) && batadv_log_empty(debug_log)) + return -EAGAIN; + + if (!buf) + return -EINVAL; + + if (count == 0) + return 0; + + if (!access_ok(VERIFY_WRITE, buf, count)) + return -EFAULT; + + error = wait_event_interruptible(debug_log->queue_wait, + (!batadv_log_empty(debug_log))); + + if (error) + return error; + + spin_lock_bh(&debug_log->lock); + + while ((!error) && (i < count) && + (debug_log->log_start != debug_log->log_end)) { + char_addr = batadv_log_char_addr(debug_log, + debug_log->log_start); + c = *char_addr; + + debug_log->log_start++; + + spin_unlock_bh(&debug_log->lock); + + error = __put_user(c, buf); + + spin_lock_bh(&debug_log->lock); + + buf++; + i++; + + } + + spin_unlock_bh(&debug_log->lock); + + if (!error) + return i; + + return error; +} + +static unsigned int batadv_log_poll(struct file *file, poll_table *wait) +{ + struct batadv_priv *bat_priv = file->private_data; + struct batadv_debug_log *debug_log = bat_priv->debug_log; + + poll_wait(file, &debug_log->queue_wait, wait); + + if (!batadv_log_empty(debug_log)) + return POLLIN | POLLRDNORM; + + return 0; +} + +static const struct file_operations batadv_log_fops = { + .open = batadv_log_open, + .release = batadv_log_release, + .read = batadv_log_read, + .poll = batadv_log_poll, + .llseek = no_llseek, +}; + +static int batadv_debug_log_setup(struct batadv_priv *bat_priv) +{ + struct dentry *d; + + if (!bat_priv->debug_dir) + goto err; + + bat_priv->debug_log = kzalloc(sizeof(*bat_priv->debug_log), GFP_ATOMIC); + if (!bat_priv->debug_log) + goto err; + + spin_lock_init(&bat_priv->debug_log->lock); + init_waitqueue_head(&bat_priv->debug_log->queue_wait); + + d = debugfs_create_file("log", S_IFREG | S_IRUSR, + bat_priv->debug_dir, bat_priv, + &batadv_log_fops); + if (!d) + goto err; + + return 0; + +err: + return -ENOMEM; +} + +static void batadv_debug_log_cleanup(struct batadv_priv *bat_priv) +{ + kfree(bat_priv->debug_log); + bat_priv->debug_log = NULL; +} +#else /* CONFIG_BATMAN_ADV_DEBUG */ +static int batadv_debug_log_setup(struct batadv_priv *bat_priv) +{ + bat_priv->debug_log = NULL; + return 0; +} + +static void batadv_debug_log_cleanup(struct batadv_priv *bat_priv) +{ + return; +} +#endif + +static int batadv_algorithms_open(struct inode *inode, struct file *file) +{ + return single_open(file, batadv_algo_seq_print_text, NULL); +} + +static int batadv_originators_open(struct inode *inode, struct file *file) +{ + struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_orig_seq_print_text, net_dev); +} + +static int batadv_gateways_open(struct inode *inode, struct file *file) +{ + struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_gw_client_seq_print_text, net_dev); +} + +static int batadv_transtable_global_open(struct inode *inode, struct file *file) +{ + struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_tt_global_seq_print_text, net_dev); +} + +#ifdef CONFIG_BATMAN_ADV_BLA +static int batadv_bla_claim_table_open(struct inode *inode, struct file *file) +{ + struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_bla_claim_table_seq_print_text, + net_dev); +} +#endif + +static int batadv_transtable_local_open(struct inode *inode, struct file *file) +{ + struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_tt_local_seq_print_text, net_dev); +} + +static int batadv_vis_data_open(struct inode *inode, struct file *file) +{ + struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_vis_seq_print_text, net_dev); +} + +struct batadv_debuginfo { + struct attribute attr; + const struct file_operations fops; +}; + +#define BATADV_DEBUGINFO(_name, _mode, _open) \ +struct batadv_debuginfo batadv_debuginfo_##_name = { \ + .attr = { .name = __stringify(_name), \ + .mode = _mode, }, \ + .fops = { .owner = THIS_MODULE, \ + .open = _open, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = single_release, \ + } \ +}; + +static BATADV_DEBUGINFO(routing_algos, S_IRUGO, batadv_algorithms_open); +static BATADV_DEBUGINFO(originators, S_IRUGO, batadv_originators_open); +static BATADV_DEBUGINFO(gateways, S_IRUGO, batadv_gateways_open); +static BATADV_DEBUGINFO(transtable_global, S_IRUGO, + batadv_transtable_global_open); +#ifdef CONFIG_BATMAN_ADV_BLA +static BATADV_DEBUGINFO(bla_claim_table, S_IRUGO, batadv_bla_claim_table_open); +#endif +static BATADV_DEBUGINFO(transtable_local, S_IRUGO, + batadv_transtable_local_open); +static BATADV_DEBUGINFO(vis_data, S_IRUGO, batadv_vis_data_open); + +static struct batadv_debuginfo *batadv_mesh_debuginfos[] = { + &batadv_debuginfo_originators, + &batadv_debuginfo_gateways, + &batadv_debuginfo_transtable_global, +#ifdef CONFIG_BATMAN_ADV_BLA + &batadv_debuginfo_bla_claim_table, +#endif + &batadv_debuginfo_transtable_local, + &batadv_debuginfo_vis_data, + NULL, +}; + +void batadv_debugfs_init(void) +{ + struct batadv_debuginfo *bat_debug; + struct dentry *file; + + batadv_debugfs = debugfs_create_dir(BATADV_DEBUGFS_SUBDIR, NULL); + if (batadv_debugfs == ERR_PTR(-ENODEV)) + batadv_debugfs = NULL; + + if (!batadv_debugfs) + goto out; + + bat_debug = &batadv_debuginfo_routing_algos; + file = debugfs_create_file(bat_debug->attr.name, + S_IFREG | bat_debug->attr.mode, + batadv_debugfs, NULL, &bat_debug->fops); + if (!file) + pr_err("Can't add debugfs file: %s\n", bat_debug->attr.name); + +out: + return; +} + +void batadv_debugfs_destroy(void) +{ + if (batadv_debugfs) { + debugfs_remove_recursive(batadv_debugfs); + batadv_debugfs = NULL; + } +} + +int batadv_debugfs_add_meshif(struct net_device *dev) +{ + struct batadv_priv *bat_priv = netdev_priv(dev); + struct batadv_debuginfo **bat_debug; + struct dentry *file; + + if (!batadv_debugfs) + goto out; + + bat_priv->debug_dir = debugfs_create_dir(dev->name, batadv_debugfs); + if (!bat_priv->debug_dir) + goto out; + + if (batadv_socket_setup(bat_priv) < 0) + goto rem_attr; + + if (batadv_debug_log_setup(bat_priv) < 0) + goto rem_attr; + + for (bat_debug = batadv_mesh_debuginfos; *bat_debug; ++bat_debug) { + file = debugfs_create_file(((*bat_debug)->attr).name, + S_IFREG | ((*bat_debug)->attr).mode, + bat_priv->debug_dir, + dev, &(*bat_debug)->fops); + if (!file) { + batadv_err(dev, "Can't add debugfs file: %s/%s\n", + dev->name, ((*bat_debug)->attr).name); + goto rem_attr; + } + } + + return 0; +rem_attr: + debugfs_remove_recursive(bat_priv->debug_dir); + bat_priv->debug_dir = NULL; +out: +#ifdef CONFIG_DEBUG_FS + return -ENOMEM; +#else + return 0; +#endif /* CONFIG_DEBUG_FS */ +} + +void batadv_debugfs_del_meshif(struct net_device *dev) +{ + struct batadv_priv *bat_priv = netdev_priv(dev); + + batadv_debug_log_cleanup(bat_priv); + + if (batadv_debugfs) { + debugfs_remove_recursive(bat_priv->debug_dir); + bat_priv->debug_dir = NULL; + } +} diff --git a/net/batman-adv/bat_debugfs.h b/net/batman-adv/debugfs.h index d605c674642..3319e1f21f5 100644 --- a/net/batman-adv/bat_debugfs.h +++ b/net/batman-adv/debugfs.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -16,18 +15,16 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ - #ifndef _NET_BATMAN_ADV_DEBUGFS_H_ #define _NET_BATMAN_ADV_DEBUGFS_H_ -#define DEBUGFS_BAT_SUBDIR "batman_adv" +#define BATADV_DEBUGFS_SUBDIR "batman_adv" -void debugfs_init(void); -void debugfs_destroy(void); -int debugfs_add_meshif(struct net_device *dev); -void debugfs_del_meshif(struct net_device *dev); +void batadv_debugfs_init(void); +void batadv_debugfs_destroy(void); +int batadv_debugfs_add_meshif(struct net_device *dev); +void batadv_debugfs_del_meshif(struct net_device *dev); #endif /* _NET_BATMAN_ADV_DEBUGFS_H_ */ diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 47f7186dcef..fc866f2e452 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -16,11 +15,10 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" -#include "bat_sysfs.h" +#include "sysfs.h" #include "gateway_client.h" #include "gateway_common.h" #include "hard-interface.h" @@ -33,19 +31,21 @@ #include <linux/if_vlan.h> /* This is the offset of the options field in a dhcp packet starting at - * the beginning of the dhcp header */ -#define DHCP_OPTIONS_OFFSET 240 -#define DHCP_REQUEST 3 + * the beginning of the dhcp header + */ +#define BATADV_DHCP_OPTIONS_OFFSET 240 +#define BATADV_DHCP_REQUEST 3 -static void gw_node_free_ref(struct gw_node *gw_node) +static void batadv_gw_node_free_ref(struct batadv_gw_node *gw_node) { if (atomic_dec_and_test(&gw_node->refcount)) kfree_rcu(gw_node, rcu); } -static struct gw_node *gw_get_selected_gw_node(struct bat_priv *bat_priv) +static struct batadv_gw_node * +batadv_gw_get_selected_gw_node(struct batadv_priv *bat_priv) { - struct gw_node *gw_node; + struct batadv_gw_node *gw_node; rcu_read_lock(); gw_node = rcu_dereference(bat_priv->curr_gw); @@ -60,12 +60,13 @@ out: return gw_node; } -struct orig_node *gw_get_selected_orig(struct bat_priv *bat_priv) +struct batadv_orig_node * +batadv_gw_get_selected_orig(struct batadv_priv *bat_priv) { - struct gw_node *gw_node; - struct orig_node *orig_node = NULL; + struct batadv_gw_node *gw_node; + struct batadv_orig_node *orig_node = NULL; - gw_node = gw_get_selected_gw_node(bat_priv); + gw_node = batadv_gw_get_selected_gw_node(bat_priv); if (!gw_node) goto out; @@ -81,13 +82,14 @@ unlock: rcu_read_unlock(); out: if (gw_node) - gw_node_free_ref(gw_node); + batadv_gw_node_free_ref(gw_node); return orig_node; } -static void gw_select(struct bat_priv *bat_priv, struct gw_node *new_gw_node) +static void batadv_gw_select(struct batadv_priv *bat_priv, + struct batadv_gw_node *new_gw_node) { - struct gw_node *curr_gw_node; + struct batadv_gw_node *curr_gw_node; spin_lock_bh(&bat_priv->gw_list_lock); @@ -98,31 +100,34 @@ static void gw_select(struct bat_priv *bat_priv, struct gw_node *new_gw_node) rcu_assign_pointer(bat_priv->curr_gw, new_gw_node); if (curr_gw_node) - gw_node_free_ref(curr_gw_node); + batadv_gw_node_free_ref(curr_gw_node); spin_unlock_bh(&bat_priv->gw_list_lock); } -void gw_deselect(struct bat_priv *bat_priv) +void batadv_gw_deselect(struct batadv_priv *bat_priv) { atomic_set(&bat_priv->gw_reselect, 1); } -static struct gw_node *gw_get_best_gw_node(struct bat_priv *bat_priv) +static struct batadv_gw_node * +batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv) { - struct neigh_node *router; + struct batadv_neigh_node *router; struct hlist_node *node; - struct gw_node *gw_node, *curr_gw = NULL; + struct batadv_gw_node *gw_node, *curr_gw = NULL; uint32_t max_gw_factor = 0, tmp_gw_factor = 0; uint8_t max_tq = 0; int down, up; + struct batadv_orig_node *orig_node; rcu_read_lock(); hlist_for_each_entry_rcu(gw_node, node, &bat_priv->gw_list, list) { if (gw_node->deleted) continue; - router = orig_node_get_router(gw_node->orig_node); + orig_node = gw_node->orig_node; + router = batadv_orig_node_get_router(orig_node); if (!router) continue; @@ -131,35 +136,34 @@ static struct gw_node *gw_get_best_gw_node(struct bat_priv *bat_priv) switch (atomic_read(&bat_priv->gw_sel_class)) { case 1: /* fast connection */ - gw_bandwidth_to_kbit(gw_node->orig_node->gw_flags, - &down, &up); + batadv_gw_bandwidth_to_kbit(orig_node->gw_flags, + &down, &up); tmp_gw_factor = (router->tq_avg * router->tq_avg * down * 100 * 100) / - (TQ_LOCAL_WINDOW_SIZE * - TQ_LOCAL_WINDOW_SIZE * 64); + (BATADV_TQ_LOCAL_WINDOW_SIZE * + BATADV_TQ_LOCAL_WINDOW_SIZE * 64); if ((tmp_gw_factor > max_gw_factor) || ((tmp_gw_factor == max_gw_factor) && (router->tq_avg > max_tq))) { if (curr_gw) - gw_node_free_ref(curr_gw); + batadv_gw_node_free_ref(curr_gw); curr_gw = gw_node; atomic_inc(&curr_gw->refcount); } break; - default: /** - * 2: stable connection (use best statistic) + default: /* 2: stable connection (use best statistic) * 3: fast-switch (use best statistic but change as * soon as a better gateway appears) * XX: late-switch (use best statistic but change as * soon as a better gateway appears which has * $routing_class more tq points) - **/ + */ if (router->tq_avg > max_tq) { if (curr_gw) - gw_node_free_ref(curr_gw); + batadv_gw_node_free_ref(curr_gw); curr_gw = gw_node; atomic_inc(&curr_gw->refcount); } @@ -172,37 +176,36 @@ static struct gw_node *gw_get_best_gw_node(struct bat_priv *bat_priv) if (tmp_gw_factor > max_gw_factor) max_gw_factor = tmp_gw_factor; - gw_node_free_ref(gw_node); + batadv_gw_node_free_ref(gw_node); next: - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); } rcu_read_unlock(); return curr_gw; } -void gw_election(struct bat_priv *bat_priv) +void batadv_gw_election(struct batadv_priv *bat_priv) { - struct gw_node *curr_gw = NULL, *next_gw = NULL; - struct neigh_node *router = NULL; + struct batadv_gw_node *curr_gw = NULL, *next_gw = NULL; + struct batadv_neigh_node *router = NULL; char gw_addr[18] = { '\0' }; - /** - * The batman daemon checks here if we already passed a full originator + /* The batman daemon checks here if we already passed a full originator * cycle in order to make sure we don't choose the first gateway we * hear about. This check is based on the daemon's uptime which we * don't have. - **/ - if (atomic_read(&bat_priv->gw_mode) != GW_MODE_CLIENT) + */ + if (atomic_read(&bat_priv->gw_mode) != BATADV_GW_MODE_CLIENT) goto out; - if (!atomic_dec_not_zero(&bat_priv->gw_reselect)) - goto out; + curr_gw = batadv_gw_get_selected_gw_node(bat_priv); - curr_gw = gw_get_selected_gw_node(bat_priv); + if (!batadv_atomic_dec_not_zero(&bat_priv->gw_reselect) && curr_gw) + goto out; - next_gw = gw_get_best_gw_node(bat_priv); + next_gw = batadv_gw_get_best_gw_node(bat_priv); if (curr_gw == next_gw) goto out; @@ -210,53 +213,57 @@ void gw_election(struct bat_priv *bat_priv) if (next_gw) { sprintf(gw_addr, "%pM", next_gw->orig_node->orig); - router = orig_node_get_router(next_gw->orig_node); + router = batadv_orig_node_get_router(next_gw->orig_node); if (!router) { - gw_deselect(bat_priv); + batadv_gw_deselect(bat_priv); goto out; } } if ((curr_gw) && (!next_gw)) { - bat_dbg(DBG_BATMAN, bat_priv, - "Removing selected gateway - no gateway in range\n"); - throw_uevent(bat_priv, UEV_GW, UEV_DEL, NULL); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Removing selected gateway - no gateway in range\n"); + batadv_throw_uevent(bat_priv, BATADV_UEV_GW, BATADV_UEV_DEL, + NULL); } else if ((!curr_gw) && (next_gw)) { - bat_dbg(DBG_BATMAN, bat_priv, - "Adding route to gateway %pM (gw_flags: %i, tq: %i)\n", - next_gw->orig_node->orig, next_gw->orig_node->gw_flags, - router->tq_avg); - throw_uevent(bat_priv, UEV_GW, UEV_ADD, gw_addr); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Adding route to gateway %pM (gw_flags: %i, tq: %i)\n", + next_gw->orig_node->orig, + next_gw->orig_node->gw_flags, router->tq_avg); + batadv_throw_uevent(bat_priv, BATADV_UEV_GW, BATADV_UEV_ADD, + gw_addr); } else { - bat_dbg(DBG_BATMAN, bat_priv, - "Changing route to gateway %pM (gw_flags: %i, tq: %i)\n", - next_gw->orig_node->orig, next_gw->orig_node->gw_flags, - router->tq_avg); - throw_uevent(bat_priv, UEV_GW, UEV_CHANGE, gw_addr); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Changing route to gateway %pM (gw_flags: %i, tq: %i)\n", + next_gw->orig_node->orig, + next_gw->orig_node->gw_flags, router->tq_avg); + batadv_throw_uevent(bat_priv, BATADV_UEV_GW, BATADV_UEV_CHANGE, + gw_addr); } - gw_select(bat_priv, next_gw); + batadv_gw_select(bat_priv, next_gw); out: if (curr_gw) - gw_node_free_ref(curr_gw); + batadv_gw_node_free_ref(curr_gw); if (next_gw) - gw_node_free_ref(next_gw); + batadv_gw_node_free_ref(next_gw); if (router) - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); } -void gw_check_election(struct bat_priv *bat_priv, struct orig_node *orig_node) +void batadv_gw_check_election(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node) { - struct orig_node *curr_gw_orig; - struct neigh_node *router_gw = NULL, *router_orig = NULL; + struct batadv_orig_node *curr_gw_orig; + struct batadv_neigh_node *router_gw = NULL, *router_orig = NULL; uint8_t gw_tq_avg, orig_tq_avg; - curr_gw_orig = gw_get_selected_orig(bat_priv); + curr_gw_orig = batadv_gw_get_selected_orig(bat_priv); if (!curr_gw_orig) goto deselect; - router_gw = orig_node_get_router(curr_gw_orig); + router_gw = batadv_orig_node_get_router(curr_gw_orig); if (!router_gw) goto deselect; @@ -264,7 +271,7 @@ void gw_check_election(struct bat_priv *bat_priv, struct orig_node *orig_node) if (curr_gw_orig == orig_node) goto out; - router_orig = orig_node_get_router(orig_node); + router_orig = batadv_orig_node_get_router(orig_node); if (!router_orig) goto out; @@ -275,35 +282,35 @@ void gw_check_election(struct bat_priv *bat_priv, struct orig_node *orig_node) if (orig_tq_avg < gw_tq_avg) goto out; - /** - * if the routing class is greater than 3 the value tells us how much + /* if the routing class is greater than 3 the value tells us how much * greater the TQ value of the new gateway must be - **/ + */ if ((atomic_read(&bat_priv->gw_sel_class) > 3) && (orig_tq_avg - gw_tq_avg < atomic_read(&bat_priv->gw_sel_class))) goto out; - bat_dbg(DBG_BATMAN, bat_priv, - "Restarting gateway selection: better gateway found (tq curr: %i, tq new: %i)\n", - gw_tq_avg, orig_tq_avg); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Restarting gateway selection: better gateway found (tq curr: %i, tq new: %i)\n", + gw_tq_avg, orig_tq_avg); deselect: - gw_deselect(bat_priv); + batadv_gw_deselect(bat_priv); out: if (curr_gw_orig) - orig_node_free_ref(curr_gw_orig); + batadv_orig_node_free_ref(curr_gw_orig); if (router_gw) - neigh_node_free_ref(router_gw); + batadv_neigh_node_free_ref(router_gw); if (router_orig) - neigh_node_free_ref(router_orig); + batadv_neigh_node_free_ref(router_orig); return; } -static void gw_node_add(struct bat_priv *bat_priv, - struct orig_node *orig_node, uint8_t new_gwflags) +static void batadv_gw_node_add(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + uint8_t new_gwflags) { - struct gw_node *gw_node; + struct batadv_gw_node *gw_node; int down, up; gw_node = kzalloc(sizeof(*gw_node), GFP_ATOMIC); @@ -318,47 +325,47 @@ static void gw_node_add(struct bat_priv *bat_priv, hlist_add_head_rcu(&gw_node->list, &bat_priv->gw_list); spin_unlock_bh(&bat_priv->gw_list_lock); - gw_bandwidth_to_kbit(new_gwflags, &down, &up); - bat_dbg(DBG_BATMAN, bat_priv, - "Found new gateway %pM -> gw_class: %i - %i%s/%i%s\n", - orig_node->orig, new_gwflags, - (down > 2048 ? down / 1024 : down), - (down > 2048 ? "MBit" : "KBit"), - (up > 2048 ? up / 1024 : up), - (up > 2048 ? "MBit" : "KBit")); + batadv_gw_bandwidth_to_kbit(new_gwflags, &down, &up); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Found new gateway %pM -> gw_class: %i - %i%s/%i%s\n", + orig_node->orig, new_gwflags, + (down > 2048 ? down / 1024 : down), + (down > 2048 ? "MBit" : "KBit"), + (up > 2048 ? up / 1024 : up), + (up > 2048 ? "MBit" : "KBit")); } -void gw_node_update(struct bat_priv *bat_priv, - struct orig_node *orig_node, uint8_t new_gwflags) +void batadv_gw_node_update(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + uint8_t new_gwflags) { struct hlist_node *node; - struct gw_node *gw_node, *curr_gw; + struct batadv_gw_node *gw_node, *curr_gw; - /** - * Note: We don't need a NULL check here, since curr_gw never gets + /* Note: We don't need a NULL check here, since curr_gw never gets * dereferenced. If curr_gw is NULL we also should not exit as we may * have this gateway in our list (duplication check!) even though we * have no currently selected gateway. */ - curr_gw = gw_get_selected_gw_node(bat_priv); + curr_gw = batadv_gw_get_selected_gw_node(bat_priv); rcu_read_lock(); hlist_for_each_entry_rcu(gw_node, node, &bat_priv->gw_list, list) { if (gw_node->orig_node != orig_node) continue; - bat_dbg(DBG_BATMAN, bat_priv, - "Gateway class of originator %pM changed from %i to %i\n", - orig_node->orig, gw_node->orig_node->gw_flags, - new_gwflags); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Gateway class of originator %pM changed from %i to %i\n", + orig_node->orig, gw_node->orig_node->gw_flags, + new_gwflags); gw_node->deleted = 0; - if (new_gwflags == NO_FLAGS) { + if (new_gwflags == BATADV_NO_FLAGS) { gw_node->deleted = jiffies; - bat_dbg(DBG_BATMAN, bat_priv, - "Gateway %pM removed from gateway list\n", - orig_node->orig); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Gateway %pM removed from gateway list\n", + orig_node->orig); if (gw_node == curr_gw) goto deselect; @@ -367,34 +374,35 @@ void gw_node_update(struct bat_priv *bat_priv, goto unlock; } - if (new_gwflags == NO_FLAGS) + if (new_gwflags == BATADV_NO_FLAGS) goto unlock; - gw_node_add(bat_priv, orig_node, new_gwflags); + batadv_gw_node_add(bat_priv, orig_node, new_gwflags); goto unlock; deselect: - gw_deselect(bat_priv); + batadv_gw_deselect(bat_priv); unlock: rcu_read_unlock(); if (curr_gw) - gw_node_free_ref(curr_gw); + batadv_gw_node_free_ref(curr_gw); } -void gw_node_delete(struct bat_priv *bat_priv, struct orig_node *orig_node) +void batadv_gw_node_delete(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node) { - gw_node_update(bat_priv, orig_node, 0); + batadv_gw_node_update(bat_priv, orig_node, 0); } -void gw_node_purge(struct bat_priv *bat_priv) +void batadv_gw_node_purge(struct batadv_priv *bat_priv) { - struct gw_node *gw_node, *curr_gw; + struct batadv_gw_node *gw_node, *curr_gw; struct hlist_node *node, *node_tmp; - unsigned long timeout = msecs_to_jiffies(2 * PURGE_TIMEOUT); + unsigned long timeout = msecs_to_jiffies(2 * BATADV_PURGE_TIMEOUT); int do_deselect = 0; - curr_gw = gw_get_selected_gw_node(bat_priv); + curr_gw = batadv_gw_get_selected_gw_node(bat_priv); spin_lock_bh(&bat_priv->gw_list_lock); @@ -402,43 +410,42 @@ void gw_node_purge(struct bat_priv *bat_priv) &bat_priv->gw_list, list) { if (((!gw_node->deleted) || (time_before(jiffies, gw_node->deleted + timeout))) && - atomic_read(&bat_priv->mesh_state) == MESH_ACTIVE) + atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE) continue; if (curr_gw == gw_node) do_deselect = 1; hlist_del_rcu(&gw_node->list); - gw_node_free_ref(gw_node); + batadv_gw_node_free_ref(gw_node); } spin_unlock_bh(&bat_priv->gw_list_lock); /* gw_deselect() needs to acquire the gw_list_lock */ if (do_deselect) - gw_deselect(bat_priv); + batadv_gw_deselect(bat_priv); if (curr_gw) - gw_node_free_ref(curr_gw); + batadv_gw_node_free_ref(curr_gw); } -/** - * fails if orig_node has no router - */ -static int _write_buffer_text(struct bat_priv *bat_priv, struct seq_file *seq, - const struct gw_node *gw_node) +/* fails if orig_node has no router */ +static int batadv_write_buffer_text(struct batadv_priv *bat_priv, + struct seq_file *seq, + const struct batadv_gw_node *gw_node) { - struct gw_node *curr_gw; - struct neigh_node *router; + struct batadv_gw_node *curr_gw; + struct batadv_neigh_node *router; int down, up, ret = -1; - gw_bandwidth_to_kbit(gw_node->orig_node->gw_flags, &down, &up); + batadv_gw_bandwidth_to_kbit(gw_node->orig_node->gw_flags, &down, &up); - router = orig_node_get_router(gw_node->orig_node); + router = batadv_orig_node_get_router(gw_node->orig_node); if (!router) goto out; - curr_gw = gw_get_selected_gw_node(bat_priv); + curr_gw = batadv_gw_get_selected_gw_node(bat_priv); ret = seq_printf(seq, "%s %pM (%3i) %pM [%10s]: %3i - %i%s/%i%s\n", (curr_gw == gw_node ? "=>" : " "), @@ -451,23 +458,23 @@ static int _write_buffer_text(struct bat_priv *bat_priv, struct seq_file *seq, (up > 2048 ? up / 1024 : up), (up > 2048 ? "MBit" : "KBit")); - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); if (curr_gw) - gw_node_free_ref(curr_gw); + batadv_gw_node_free_ref(curr_gw); out: return ret; } -int gw_client_seq_print_text(struct seq_file *seq, void *offset) +int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset) { struct net_device *net_dev = (struct net_device *)seq->private; - struct bat_priv *bat_priv = netdev_priv(net_dev); - struct hard_iface *primary_if; - struct gw_node *gw_node; + struct batadv_priv *bat_priv = netdev_priv(net_dev); + struct batadv_hard_iface *primary_if; + struct batadv_gw_node *gw_node; struct hlist_node *node; int gw_count = 0, ret = 0; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) { ret = seq_printf(seq, "BATMAN mesh %s disabled - please specify interfaces to enable it\n", @@ -475,7 +482,7 @@ int gw_client_seq_print_text(struct seq_file *seq, void *offset) goto out; } - if (primary_if->if_status != IF_ACTIVE) { + if (primary_if->if_status != BATADV_IF_ACTIVE) { ret = seq_printf(seq, "BATMAN mesh %s disabled - primary interface not active\n", net_dev->name); @@ -484,8 +491,8 @@ int gw_client_seq_print_text(struct seq_file *seq, void *offset) seq_printf(seq, " %-12s (%s/%i) %17s [%10s]: gw_class ... [B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s)]\n", - "Gateway", "#", TQ_MAX_VALUE, "Nexthop", "outgoingIF", - SOURCE_VERSION, primary_if->net_dev->name, + "Gateway", "#", BATADV_TQ_MAX_VALUE, "Nexthop", "outgoingIF", + BATADV_SOURCE_VERSION, primary_if->net_dev->name, primary_if->net_dev->dev_addr, net_dev->name); rcu_read_lock(); @@ -494,7 +501,7 @@ int gw_client_seq_print_text(struct seq_file *seq, void *offset) continue; /* fails if orig_node has no router */ - if (_write_buffer_text(bat_priv, seq, gw_node) < 0) + if (batadv_write_buffer_text(bat_priv, seq, gw_node) < 0) continue; gw_count++; @@ -506,11 +513,11 @@ int gw_client_seq_print_text(struct seq_file *seq, void *offset) out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); return ret; } -static bool is_type_dhcprequest(struct sk_buff *skb, int header_len) +static bool batadv_is_type_dhcprequest(struct sk_buff *skb, int header_len) { int ret = false; unsigned char *p; @@ -521,27 +528,29 @@ static bool is_type_dhcprequest(struct sk_buff *skb, int header_len) pkt_len = skb_headlen(skb); - if (pkt_len < header_len + DHCP_OPTIONS_OFFSET + 1) + if (pkt_len < header_len + BATADV_DHCP_OPTIONS_OFFSET + 1) goto out; - p = skb->data + header_len + DHCP_OPTIONS_OFFSET; - pkt_len -= header_len + DHCP_OPTIONS_OFFSET + 1; + p = skb->data + header_len + BATADV_DHCP_OPTIONS_OFFSET; + pkt_len -= header_len + BATADV_DHCP_OPTIONS_OFFSET + 1; /* Access the dhcp option lists. Each entry is made up by: * - octet 1: option type * - octet 2: option data len (only if type != 255 and 0) - * - octet 3: option data */ + * - octet 3: option data + */ while (*p != 255 && !ret) { /* p now points to the first octet: option type */ if (*p == 53) { /* type 53 is the message type option. - * Jump the len octet and go to the data octet */ + * Jump the len octet and go to the data octet + */ if (pkt_len < 2) goto out; p += 2; /* check if the message type is what we need */ - if (*p == DHCP_REQUEST) + if (*p == BATADV_DHCP_REQUEST) ret = true; break; } else if (*p == 0) { @@ -568,7 +577,7 @@ out: return ret; } -bool gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) +bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) { struct ethhdr *ethhdr; struct iphdr *iphdr; @@ -634,40 +643,41 @@ bool gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) return true; } -bool gw_out_of_range(struct bat_priv *bat_priv, - struct sk_buff *skb, struct ethhdr *ethhdr) +bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, + struct sk_buff *skb, struct ethhdr *ethhdr) { - struct neigh_node *neigh_curr = NULL, *neigh_old = NULL; - struct orig_node *orig_dst_node = NULL; - struct gw_node *curr_gw = NULL; + struct batadv_neigh_node *neigh_curr = NULL, *neigh_old = NULL; + struct batadv_orig_node *orig_dst_node = NULL; + struct batadv_gw_node *curr_gw = NULL; bool ret, out_of_range = false; unsigned int header_len = 0; uint8_t curr_tq_avg; - ret = gw_is_dhcp_target(skb, &header_len); + ret = batadv_gw_is_dhcp_target(skb, &header_len); if (!ret) goto out; - orig_dst_node = transtable_search(bat_priv, ethhdr->h_source, - ethhdr->h_dest); + orig_dst_node = batadv_transtable_search(bat_priv, ethhdr->h_source, + ethhdr->h_dest); if (!orig_dst_node) goto out; if (!orig_dst_node->gw_flags) goto out; - ret = is_type_dhcprequest(skb, header_len); + ret = batadv_is_type_dhcprequest(skb, header_len); if (!ret) goto out; switch (atomic_read(&bat_priv->gw_mode)) { - case GW_MODE_SERVER: + case BATADV_GW_MODE_SERVER: /* If we are a GW then we are our best GW. We can artificially - * set the tq towards ourself as the maximum value */ - curr_tq_avg = TQ_MAX_VALUE; + * set the tq towards ourself as the maximum value + */ + curr_tq_avg = BATADV_TQ_MAX_VALUE; break; - case GW_MODE_CLIENT: - curr_gw = gw_get_selected_gw_node(bat_priv); + case BATADV_GW_MODE_CLIENT: + curr_gw = batadv_gw_get_selected_gw_node(bat_priv); if (!curr_gw) goto out; @@ -677,33 +687,35 @@ bool gw_out_of_range(struct bat_priv *bat_priv, /* If the dhcp packet has been sent to a different gw, * we have to evaluate whether the old gw is still - * reliable enough */ - neigh_curr = find_router(bat_priv, curr_gw->orig_node, NULL); + * reliable enough + */ + neigh_curr = batadv_find_router(bat_priv, curr_gw->orig_node, + NULL); if (!neigh_curr) goto out; curr_tq_avg = neigh_curr->tq_avg; break; - case GW_MODE_OFF: + case BATADV_GW_MODE_OFF: default: goto out; } - neigh_old = find_router(bat_priv, orig_dst_node, NULL); + neigh_old = batadv_find_router(bat_priv, orig_dst_node, NULL); if (!neigh_old) goto out; - if (curr_tq_avg - neigh_old->tq_avg > GW_THRESHOLD) + if (curr_tq_avg - neigh_old->tq_avg > BATADV_GW_THRESHOLD) out_of_range = true; out: if (orig_dst_node) - orig_node_free_ref(orig_dst_node); + batadv_orig_node_free_ref(orig_dst_node); if (curr_gw) - gw_node_free_ref(curr_gw); + batadv_gw_node_free_ref(curr_gw); if (neigh_old) - neigh_node_free_ref(neigh_old); + batadv_neigh_node_free_ref(neigh_old); if (neigh_curr) - neigh_node_free_ref(neigh_curr); + batadv_neigh_node_free_ref(neigh_curr); return out_of_range; } diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index bf56a5aea10..f0d129e323c 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -16,23 +15,26 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ #define _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ -void gw_deselect(struct bat_priv *bat_priv); -void gw_election(struct bat_priv *bat_priv); -struct orig_node *gw_get_selected_orig(struct bat_priv *bat_priv); -void gw_check_election(struct bat_priv *bat_priv, struct orig_node *orig_node); -void gw_node_update(struct bat_priv *bat_priv, - struct orig_node *orig_node, uint8_t new_gwflags); -void gw_node_delete(struct bat_priv *bat_priv, struct orig_node *orig_node); -void gw_node_purge(struct bat_priv *bat_priv); -int gw_client_seq_print_text(struct seq_file *seq, void *offset); -bool gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len); -bool gw_out_of_range(struct bat_priv *bat_priv, - struct sk_buff *skb, struct ethhdr *ethhdr); +void batadv_gw_deselect(struct batadv_priv *bat_priv); +void batadv_gw_election(struct batadv_priv *bat_priv); +struct batadv_orig_node * +batadv_gw_get_selected_orig(struct batadv_priv *bat_priv); +void batadv_gw_check_election(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node); +void batadv_gw_node_update(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + uint8_t new_gwflags); +void batadv_gw_node_delete(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node); +void batadv_gw_node_purge(struct batadv_priv *bat_priv); +int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset); +bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len); +bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, + struct sk_buff *skb, struct ethhdr *ethhdr); #endif /* _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ */ diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index ca57ac7d73b..9001208d175 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" @@ -24,7 +22,7 @@ #include "gateway_client.h" /* calculates the gateway class from kbit */ -static void kbit_to_gw_bandwidth(int down, int up, long *gw_srv_class) +static void batadv_kbit_to_gw_bandwidth(int down, int up, long *gw_srv_class) { int mdown = 0, tdown, tup, difference; uint8_t sbit, part; @@ -59,7 +57,7 @@ static void kbit_to_gw_bandwidth(int down, int up, long *gw_srv_class) } /* returns the up and downspeeds in kbit, calculated from the class */ -void gw_bandwidth_to_kbit(uint8_t gw_srv_class, int *down, int *up) +void batadv_gw_bandwidth_to_kbit(uint8_t gw_srv_class, int *down, int *up) { int sbit = (gw_srv_class & 0x80) >> 7; int dpart = (gw_srv_class & 0x78) >> 3; @@ -75,8 +73,8 @@ void gw_bandwidth_to_kbit(uint8_t gw_srv_class, int *down, int *up) *up = ((upart + 1) * (*down)) / 8; } -static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff, - int *up, int *down) +static bool batadv_parse_gw_bandwidth(struct net_device *net_dev, char *buff, + int *up, int *down) { int ret, multi = 1; char *slash_ptr, *tmp_ptr; @@ -99,9 +97,9 @@ static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff, ret = kstrtol(buff, 10, &ldown); if (ret) { - bat_err(net_dev, - "Download speed of gateway mode invalid: %s\n", - buff); + batadv_err(net_dev, + "Download speed of gateway mode invalid: %s\n", + buff); return false; } @@ -124,9 +122,9 @@ static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff, ret = kstrtol(slash_ptr + 1, 10, &lup); if (ret) { - bat_err(net_dev, - "Upload speed of gateway mode invalid: %s\n", - slash_ptr + 1); + batadv_err(net_dev, + "Upload speed of gateway mode invalid: %s\n", + slash_ptr + 1); return false; } @@ -136,14 +134,15 @@ static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff, return true; } -ssize_t gw_bandwidth_set(struct net_device *net_dev, char *buff, size_t count) +ssize_t batadv_gw_bandwidth_set(struct net_device *net_dev, char *buff, + size_t count) { - struct bat_priv *bat_priv = netdev_priv(net_dev); + struct batadv_priv *bat_priv = netdev_priv(net_dev); long gw_bandwidth_tmp = 0; int up = 0, down = 0; bool ret; - ret = parse_gw_bandwidth(net_dev, buff, &up, &down); + ret = batadv_parse_gw_bandwidth(net_dev, buff, &up, &down); if (!ret) goto end; @@ -153,23 +152,25 @@ ssize_t gw_bandwidth_set(struct net_device *net_dev, char *buff, size_t count) if (!up) up = down / 5; - kbit_to_gw_bandwidth(down, up, &gw_bandwidth_tmp); + batadv_kbit_to_gw_bandwidth(down, up, &gw_bandwidth_tmp); - /** - * the gw bandwidth we guessed above might not match the given + /* the gw bandwidth we guessed above might not match the given * speeds, hence we need to calculate it back to show the number * that is going to be propagated - **/ - gw_bandwidth_to_kbit((uint8_t)gw_bandwidth_tmp, &down, &up); - - gw_deselect(bat_priv); - bat_info(net_dev, - "Changing gateway bandwidth from: '%i' to: '%ld' (propagating: %d%s/%d%s)\n", - atomic_read(&bat_priv->gw_bandwidth), gw_bandwidth_tmp, - (down > 2048 ? down / 1024 : down), - (down > 2048 ? "MBit" : "KBit"), - (up > 2048 ? up / 1024 : up), - (up > 2048 ? "MBit" : "KBit")); + */ + batadv_gw_bandwidth_to_kbit((uint8_t)gw_bandwidth_tmp, &down, &up); + + if (atomic_read(&bat_priv->gw_bandwidth) == gw_bandwidth_tmp) + return count; + + batadv_gw_deselect(bat_priv); + batadv_info(net_dev, + "Changing gateway bandwidth from: '%i' to: '%ld' (propagating: %d%s/%d%s)\n", + atomic_read(&bat_priv->gw_bandwidth), gw_bandwidth_tmp, + (down > 2048 ? down / 1024 : down), + (down > 2048 ? "MBit" : "KBit"), + (up > 2048 ? up / 1024 : up), + (up > 2048 ? "MBit" : "KBit")); atomic_set(&bat_priv->gw_bandwidth, gw_bandwidth_tmp); diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index b8fb11c4f92..13697f6e711 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -16,23 +15,23 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_GATEWAY_COMMON_H_ #define _NET_BATMAN_ADV_GATEWAY_COMMON_H_ -enum gw_modes { - GW_MODE_OFF, - GW_MODE_CLIENT, - GW_MODE_SERVER, +enum batadv_gw_modes { + BATADV_GW_MODE_OFF, + BATADV_GW_MODE_CLIENT, + BATADV_GW_MODE_SERVER, }; -#define GW_MODE_OFF_NAME "off" -#define GW_MODE_CLIENT_NAME "client" -#define GW_MODE_SERVER_NAME "server" +#define BATADV_GW_MODE_OFF_NAME "off" +#define BATADV_GW_MODE_CLIENT_NAME "client" +#define BATADV_GW_MODE_SERVER_NAME "server" -void gw_bandwidth_to_kbit(uint8_t gw_class, int *down, int *up); -ssize_t gw_bandwidth_set(struct net_device *net_dev, char *buff, size_t count); +void batadv_gw_bandwidth_to_kbit(uint8_t gw_class, int *down, int *up); +ssize_t batadv_gw_bandwidth_set(struct net_device *net_dev, char *buff, + size_t count); #endif /* _NET_BATMAN_ADV_GATEWAY_COMMON_H_ */ diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index dc334fa8984..282bf6e9353 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" @@ -25,28 +23,29 @@ #include "send.h" #include "translation-table.h" #include "routing.h" -#include "bat_sysfs.h" +#include "sysfs.h" #include "originator.h" #include "hash.h" #include "bridge_loop_avoidance.h" #include <linux/if_arp.h> -void hardif_free_rcu(struct rcu_head *rcu) +void batadv_hardif_free_rcu(struct rcu_head *rcu) { - struct hard_iface *hard_iface; + struct batadv_hard_iface *hard_iface; - hard_iface = container_of(rcu, struct hard_iface, rcu); + hard_iface = container_of(rcu, struct batadv_hard_iface, rcu); dev_put(hard_iface->net_dev); kfree(hard_iface); } -struct hard_iface *hardif_get_by_netdev(const struct net_device *net_dev) +struct batadv_hard_iface * +batadv_hardif_get_by_netdev(const struct net_device *net_dev) { - struct hard_iface *hard_iface; + struct batadv_hard_iface *hard_iface; rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &hardif_list, list) { + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->net_dev == net_dev && atomic_inc_not_zero(&hard_iface->refcount)) goto out; @@ -59,7 +58,7 @@ out: return hard_iface; } -static int is_valid_iface(const struct net_device *net_dev) +static int batadv_is_valid_iface(const struct net_device *net_dev) { if (net_dev->flags & IFF_LOOPBACK) return 0; @@ -71,26 +70,23 @@ static int is_valid_iface(const struct net_device *net_dev) return 0; /* no batman over batman */ - if (softif_is_valid(net_dev)) + if (batadv_softif_is_valid(net_dev)) return 0; - /* Device is being bridged */ - /* if (net_dev->priv_flags & IFF_BRIDGE_PORT) - return 0; */ - return 1; } -static struct hard_iface *hardif_get_active(const struct net_device *soft_iface) +static struct batadv_hard_iface * +batadv_hardif_get_active(const struct net_device *soft_iface) { - struct hard_iface *hard_iface; + struct batadv_hard_iface *hard_iface; rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &hardif_list, list) { + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->soft_iface != soft_iface) continue; - if (hard_iface->if_status == IF_ACTIVE && + if (hard_iface->if_status == BATADV_IF_ACTIVE && atomic_inc_not_zero(&hard_iface->refcount)) goto out; } @@ -102,32 +98,32 @@ out: return hard_iface; } -static void primary_if_update_addr(struct bat_priv *bat_priv, - struct hard_iface *oldif) +static void batadv_primary_if_update_addr(struct batadv_priv *bat_priv, + struct batadv_hard_iface *oldif) { - struct vis_packet *vis_packet; - struct hard_iface *primary_if; + struct batadv_vis_packet *vis_packet; + struct batadv_hard_iface *primary_if; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; - vis_packet = (struct vis_packet *) + vis_packet = (struct batadv_vis_packet *) bat_priv->my_vis_info->skb_packet->data; memcpy(vis_packet->vis_orig, primary_if->net_dev->dev_addr, ETH_ALEN); memcpy(vis_packet->sender_orig, primary_if->net_dev->dev_addr, ETH_ALEN); - bla_update_orig_address(bat_priv, primary_if, oldif); + batadv_bla_update_orig_address(bat_priv, primary_if, oldif); out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); } -static void primary_if_select(struct bat_priv *bat_priv, - struct hard_iface *new_hard_iface) +static void batadv_primary_if_select(struct batadv_priv *bat_priv, + struct batadv_hard_iface *new_hard_iface) { - struct hard_iface *curr_hard_iface; + struct batadv_hard_iface *curr_hard_iface; ASSERT_RTNL(); @@ -141,14 +137,15 @@ static void primary_if_select(struct bat_priv *bat_priv, goto out; bat_priv->bat_algo_ops->bat_primary_iface_set(new_hard_iface); - primary_if_update_addr(bat_priv, curr_hard_iface); + batadv_primary_if_update_addr(bat_priv, curr_hard_iface); out: if (curr_hard_iface) - hardif_free_ref(curr_hard_iface); + batadv_hardif_free_ref(curr_hard_iface); } -static bool hardif_is_iface_up(const struct hard_iface *hard_iface) +static bool +batadv_hardif_is_iface_up(const struct batadv_hard_iface *hard_iface) { if (hard_iface->net_dev->flags & IFF_UP) return true; @@ -156,21 +153,21 @@ static bool hardif_is_iface_up(const struct hard_iface *hard_iface) return false; } -static void check_known_mac_addr(const struct net_device *net_dev) +static void batadv_check_known_mac_addr(const struct net_device *net_dev) { - const struct hard_iface *hard_iface; + const struct batadv_hard_iface *hard_iface; rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &hardif_list, list) { - if ((hard_iface->if_status != IF_ACTIVE) && - (hard_iface->if_status != IF_TO_BE_ACTIVATED)) + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if ((hard_iface->if_status != BATADV_IF_ACTIVE) && + (hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)) continue; if (hard_iface->net_dev == net_dev) continue; - if (!compare_eth(hard_iface->net_dev->dev_addr, - net_dev->dev_addr)) + if (!batadv_compare_eth(hard_iface->net_dev->dev_addr, + net_dev->dev_addr)) continue; pr_warn("The newly added mac address (%pM) already exists on: %s\n", @@ -180,27 +177,29 @@ static void check_known_mac_addr(const struct net_device *net_dev) rcu_read_unlock(); } -int hardif_min_mtu(struct net_device *soft_iface) +int batadv_hardif_min_mtu(struct net_device *soft_iface) { - const struct bat_priv *bat_priv = netdev_priv(soft_iface); - const struct hard_iface *hard_iface; + const struct batadv_priv *bat_priv = netdev_priv(soft_iface); + const struct batadv_hard_iface *hard_iface; /* allow big frames if all devices are capable to do so - * (have MTU > 1500 + BAT_HEADER_LEN) */ + * (have MTU > 1500 + BAT_HEADER_LEN) + */ int min_mtu = ETH_DATA_LEN; if (atomic_read(&bat_priv->fragmentation)) goto out; rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &hardif_list, list) { - if ((hard_iface->if_status != IF_ACTIVE) && - (hard_iface->if_status != IF_TO_BE_ACTIVATED)) + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if ((hard_iface->if_status != BATADV_IF_ACTIVE) && + (hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)) continue; if (hard_iface->soft_iface != soft_iface) continue; - min_mtu = min_t(int, hard_iface->net_dev->mtu - BAT_HEADER_LEN, + min_mtu = min_t(int, + hard_iface->net_dev->mtu - BATADV_HEADER_LEN, min_mtu); } rcu_read_unlock(); @@ -209,68 +208,70 @@ out: } /* adjusts the MTU if a new interface with a smaller MTU appeared. */ -void update_min_mtu(struct net_device *soft_iface) +void batadv_update_min_mtu(struct net_device *soft_iface) { int min_mtu; - min_mtu = hardif_min_mtu(soft_iface); + min_mtu = batadv_hardif_min_mtu(soft_iface); if (soft_iface->mtu != min_mtu) soft_iface->mtu = min_mtu; } -static void hardif_activate_interface(struct hard_iface *hard_iface) +static void +batadv_hardif_activate_interface(struct batadv_hard_iface *hard_iface) { - struct bat_priv *bat_priv; - struct hard_iface *primary_if = NULL; + struct batadv_priv *bat_priv; + struct batadv_hard_iface *primary_if = NULL; - if (hard_iface->if_status != IF_INACTIVE) + if (hard_iface->if_status != BATADV_IF_INACTIVE) goto out; bat_priv = netdev_priv(hard_iface->soft_iface); bat_priv->bat_algo_ops->bat_iface_update_mac(hard_iface); - hard_iface->if_status = IF_TO_BE_ACTIVATED; + hard_iface->if_status = BATADV_IF_TO_BE_ACTIVATED; - /** - * the first active interface becomes our primary interface or + /* the first active interface becomes our primary interface or * the next active interface after the old primary interface was removed */ - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) - primary_if_select(bat_priv, hard_iface); + batadv_primary_if_select(bat_priv, hard_iface); - bat_info(hard_iface->soft_iface, "Interface activated: %s\n", - hard_iface->net_dev->name); + batadv_info(hard_iface->soft_iface, "Interface activated: %s\n", + hard_iface->net_dev->name); - update_min_mtu(hard_iface->soft_iface); + batadv_update_min_mtu(hard_iface->soft_iface); out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); } -static void hardif_deactivate_interface(struct hard_iface *hard_iface) +static void +batadv_hardif_deactivate_interface(struct batadv_hard_iface *hard_iface) { - if ((hard_iface->if_status != IF_ACTIVE) && - (hard_iface->if_status != IF_TO_BE_ACTIVATED)) + if ((hard_iface->if_status != BATADV_IF_ACTIVE) && + (hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)) return; - hard_iface->if_status = IF_INACTIVE; + hard_iface->if_status = BATADV_IF_INACTIVE; - bat_info(hard_iface->soft_iface, "Interface deactivated: %s\n", - hard_iface->net_dev->name); + batadv_info(hard_iface->soft_iface, "Interface deactivated: %s\n", + hard_iface->net_dev->name); - update_min_mtu(hard_iface->soft_iface); + batadv_update_min_mtu(hard_iface->soft_iface); } -int hardif_enable_interface(struct hard_iface *hard_iface, - const char *iface_name) +int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, + const char *iface_name) { - struct bat_priv *bat_priv; + struct batadv_priv *bat_priv; struct net_device *soft_iface; + __be16 ethertype = __constant_htons(BATADV_ETH_P_BATMAN); int ret; - if (hard_iface->if_status != IF_NOT_IN_USE) + if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) goto out; if (!atomic_inc_not_zero(&hard_iface->refcount)) @@ -284,7 +285,7 @@ int hardif_enable_interface(struct hard_iface *hard_iface, soft_iface = dev_get_by_name(&init_net, iface_name); if (!soft_iface) { - soft_iface = softif_create(iface_name); + soft_iface = batadv_softif_create(iface_name); if (!soft_iface) { ret = -ENOMEM; @@ -295,7 +296,7 @@ int hardif_enable_interface(struct hard_iface *hard_iface, dev_hold(soft_iface); } - if (!softif_is_valid(soft_iface)) { + if (!batadv_softif_is_valid(soft_iface)) { pr_err("Can't create batman mesh interface %s: already exists as regular interface\n", soft_iface->name); ret = -EINVAL; @@ -306,48 +307,46 @@ int hardif_enable_interface(struct hard_iface *hard_iface, bat_priv = netdev_priv(hard_iface->soft_iface); ret = bat_priv->bat_algo_ops->bat_iface_enable(hard_iface); - if (ret < 0) { - ret = -ENOMEM; + if (ret < 0) goto err_dev; - } hard_iface->if_num = bat_priv->num_ifaces; bat_priv->num_ifaces++; - hard_iface->if_status = IF_INACTIVE; - orig_hash_add_if(hard_iface, bat_priv->num_ifaces); + hard_iface->if_status = BATADV_IF_INACTIVE; + batadv_orig_hash_add_if(hard_iface, bat_priv->num_ifaces); - hard_iface->batman_adv_ptype.type = __constant_htons(ETH_P_BATMAN); - hard_iface->batman_adv_ptype.func = batman_skb_recv; + hard_iface->batman_adv_ptype.type = ethertype; + hard_iface->batman_adv_ptype.func = batadv_batman_skb_recv; hard_iface->batman_adv_ptype.dev = hard_iface->net_dev; dev_add_pack(&hard_iface->batman_adv_ptype); atomic_set(&hard_iface->frag_seqno, 1); - bat_info(hard_iface->soft_iface, "Adding interface: %s\n", - hard_iface->net_dev->name); - - if (atomic_read(&bat_priv->fragmentation) && hard_iface->net_dev->mtu < - ETH_DATA_LEN + BAT_HEADER_LEN) - bat_info(hard_iface->soft_iface, - "The MTU of interface %s is too small (%i) to handle the transport of batman-adv packets. Packets going over this interface will be fragmented on layer2 which could impact the performance. Setting the MTU to %zi would solve the problem.\n", - hard_iface->net_dev->name, hard_iface->net_dev->mtu, - ETH_DATA_LEN + BAT_HEADER_LEN); - - if (!atomic_read(&bat_priv->fragmentation) && hard_iface->net_dev->mtu < - ETH_DATA_LEN + BAT_HEADER_LEN) - bat_info(hard_iface->soft_iface, - "The MTU of interface %s is too small (%i) to handle the transport of batman-adv packets. If you experience problems getting traffic through try increasing the MTU to %zi.\n", - hard_iface->net_dev->name, hard_iface->net_dev->mtu, - ETH_DATA_LEN + BAT_HEADER_LEN); - - if (hardif_is_iface_up(hard_iface)) - hardif_activate_interface(hard_iface); + batadv_info(hard_iface->soft_iface, "Adding interface: %s\n", + hard_iface->net_dev->name); + + if (atomic_read(&bat_priv->fragmentation) && + hard_iface->net_dev->mtu < ETH_DATA_LEN + BATADV_HEADER_LEN) + batadv_info(hard_iface->soft_iface, + "The MTU of interface %s is too small (%i) to handle the transport of batman-adv packets. Packets going over this interface will be fragmented on layer2 which could impact the performance. Setting the MTU to %zi would solve the problem.\n", + hard_iface->net_dev->name, hard_iface->net_dev->mtu, + ETH_DATA_LEN + BATADV_HEADER_LEN); + + if (!atomic_read(&bat_priv->fragmentation) && + hard_iface->net_dev->mtu < ETH_DATA_LEN + BATADV_HEADER_LEN) + batadv_info(hard_iface->soft_iface, + "The MTU of interface %s is too small (%i) to handle the transport of batman-adv packets. If you experience problems getting traffic through try increasing the MTU to %zi.\n", + hard_iface->net_dev->name, hard_iface->net_dev->mtu, + ETH_DATA_LEN + BATADV_HEADER_LEN); + + if (batadv_hardif_is_iface_up(hard_iface)) + batadv_hardif_activate_interface(hard_iface); else - bat_err(hard_iface->soft_iface, - "Not using interface %s (retrying later): interface not active\n", - hard_iface->net_dev->name); + batadv_err(hard_iface->soft_iface, + "Not using interface %s (retrying later): interface not active\n", + hard_iface->net_dev->name); /* begin scheduling originator messages on that interface */ - schedule_bat_ogm(hard_iface); + batadv_schedule_bat_ogm(hard_iface); out: return 0; @@ -355,67 +354,68 @@ out: err_dev: dev_put(soft_iface); err: - hardif_free_ref(hard_iface); + batadv_hardif_free_ref(hard_iface); return ret; } -void hardif_disable_interface(struct hard_iface *hard_iface) +void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface) { - struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - struct hard_iface *primary_if = NULL; + struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + struct batadv_hard_iface *primary_if = NULL; - if (hard_iface->if_status == IF_ACTIVE) - hardif_deactivate_interface(hard_iface); + if (hard_iface->if_status == BATADV_IF_ACTIVE) + batadv_hardif_deactivate_interface(hard_iface); - if (hard_iface->if_status != IF_INACTIVE) + if (hard_iface->if_status != BATADV_IF_INACTIVE) goto out; - bat_info(hard_iface->soft_iface, "Removing interface: %s\n", - hard_iface->net_dev->name); + batadv_info(hard_iface->soft_iface, "Removing interface: %s\n", + hard_iface->net_dev->name); dev_remove_pack(&hard_iface->batman_adv_ptype); bat_priv->num_ifaces--; - orig_hash_del_if(hard_iface, bat_priv->num_ifaces); + batadv_orig_hash_del_if(hard_iface, bat_priv->num_ifaces); - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (hard_iface == primary_if) { - struct hard_iface *new_if; + struct batadv_hard_iface *new_if; - new_if = hardif_get_active(hard_iface->soft_iface); - primary_if_select(bat_priv, new_if); + new_if = batadv_hardif_get_active(hard_iface->soft_iface); + batadv_primary_if_select(bat_priv, new_if); if (new_if) - hardif_free_ref(new_if); + batadv_hardif_free_ref(new_if); } bat_priv->bat_algo_ops->bat_iface_disable(hard_iface); - hard_iface->if_status = IF_NOT_IN_USE; + hard_iface->if_status = BATADV_IF_NOT_IN_USE; /* delete all references to this hard_iface */ - purge_orig_ref(bat_priv); - purge_outstanding_packets(bat_priv, hard_iface); + batadv_purge_orig_ref(bat_priv); + batadv_purge_outstanding_packets(bat_priv, hard_iface); dev_put(hard_iface->soft_iface); /* nobody uses this interface anymore */ if (!bat_priv->num_ifaces) - softif_destroy(hard_iface->soft_iface); + batadv_softif_destroy(hard_iface->soft_iface); hard_iface->soft_iface = NULL; - hardif_free_ref(hard_iface); + batadv_hardif_free_ref(hard_iface); out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); } -static struct hard_iface *hardif_add_interface(struct net_device *net_dev) +static struct batadv_hard_iface * +batadv_hardif_add_interface(struct net_device *net_dev) { - struct hard_iface *hard_iface; + struct batadv_hard_iface *hard_iface; int ret; ASSERT_RTNL(); - ret = is_valid_iface(net_dev); + ret = batadv_is_valid_iface(net_dev); if (ret != 1) goto out; @@ -425,23 +425,22 @@ static struct hard_iface *hardif_add_interface(struct net_device *net_dev) if (!hard_iface) goto release_dev; - ret = sysfs_add_hardif(&hard_iface->hardif_obj, net_dev); + ret = batadv_sysfs_add_hardif(&hard_iface->hardif_obj, net_dev); if (ret) goto free_if; hard_iface->if_num = -1; hard_iface->net_dev = net_dev; hard_iface->soft_iface = NULL; - hard_iface->if_status = IF_NOT_IN_USE; + hard_iface->if_status = BATADV_IF_NOT_IN_USE; INIT_LIST_HEAD(&hard_iface->list); /* extra reference for return */ atomic_set(&hard_iface->refcount, 2); - check_known_mac_addr(hard_iface->net_dev); - list_add_tail_rcu(&hard_iface->list, &hardif_list); + batadv_check_known_mac_addr(hard_iface->net_dev); + list_add_tail_rcu(&hard_iface->list, &batadv_hardif_list); - /** - * This can't be called via a bat_priv callback because + /* This can't be called via a bat_priv callback because * we have no bat_priv yet. */ atomic_set(&hard_iface->seqno, 1); @@ -457,102 +456,104 @@ out: return NULL; } -static void hardif_remove_interface(struct hard_iface *hard_iface) +static void batadv_hardif_remove_interface(struct batadv_hard_iface *hard_iface) { ASSERT_RTNL(); /* first deactivate interface */ - if (hard_iface->if_status != IF_NOT_IN_USE) - hardif_disable_interface(hard_iface); + if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) + batadv_hardif_disable_interface(hard_iface); - if (hard_iface->if_status != IF_NOT_IN_USE) + if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) return; - hard_iface->if_status = IF_TO_BE_REMOVED; - sysfs_del_hardif(&hard_iface->hardif_obj); - hardif_free_ref(hard_iface); + hard_iface->if_status = BATADV_IF_TO_BE_REMOVED; + batadv_sysfs_del_hardif(&hard_iface->hardif_obj); + batadv_hardif_free_ref(hard_iface); } -void hardif_remove_interfaces(void) +void batadv_hardif_remove_interfaces(void) { - struct hard_iface *hard_iface, *hard_iface_tmp; + struct batadv_hard_iface *hard_iface, *hard_iface_tmp; rtnl_lock(); list_for_each_entry_safe(hard_iface, hard_iface_tmp, - &hardif_list, list) { + &batadv_hardif_list, list) { list_del_rcu(&hard_iface->list); - hardif_remove_interface(hard_iface); + batadv_hardif_remove_interface(hard_iface); } rtnl_unlock(); } -static int hard_if_event(struct notifier_block *this, - unsigned long event, void *ptr) +static int batadv_hard_if_event(struct notifier_block *this, + unsigned long event, void *ptr) { struct net_device *net_dev = ptr; - struct hard_iface *hard_iface = hardif_get_by_netdev(net_dev); - struct hard_iface *primary_if = NULL; - struct bat_priv *bat_priv; + struct batadv_hard_iface *hard_iface; + struct batadv_hard_iface *primary_if = NULL; + struct batadv_priv *bat_priv; + hard_iface = batadv_hardif_get_by_netdev(net_dev); if (!hard_iface && event == NETDEV_REGISTER) - hard_iface = hardif_add_interface(net_dev); + hard_iface = batadv_hardif_add_interface(net_dev); if (!hard_iface) goto out; switch (event) { case NETDEV_UP: - hardif_activate_interface(hard_iface); + batadv_hardif_activate_interface(hard_iface); break; case NETDEV_GOING_DOWN: case NETDEV_DOWN: - hardif_deactivate_interface(hard_iface); + batadv_hardif_deactivate_interface(hard_iface); break; case NETDEV_UNREGISTER: list_del_rcu(&hard_iface->list); - hardif_remove_interface(hard_iface); + batadv_hardif_remove_interface(hard_iface); break; case NETDEV_CHANGEMTU: if (hard_iface->soft_iface) - update_min_mtu(hard_iface->soft_iface); + batadv_update_min_mtu(hard_iface->soft_iface); break; case NETDEV_CHANGEADDR: - if (hard_iface->if_status == IF_NOT_IN_USE) + if (hard_iface->if_status == BATADV_IF_NOT_IN_USE) goto hardif_put; - check_known_mac_addr(hard_iface->net_dev); + batadv_check_known_mac_addr(hard_iface->net_dev); bat_priv = netdev_priv(hard_iface->soft_iface); bat_priv->bat_algo_ops->bat_iface_update_mac(hard_iface); - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto hardif_put; if (hard_iface == primary_if) - primary_if_update_addr(bat_priv, NULL); + batadv_primary_if_update_addr(bat_priv, NULL); break; default: break; } hardif_put: - hardif_free_ref(hard_iface); + batadv_hardif_free_ref(hard_iface); out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); return NOTIFY_DONE; } /* This function returns true if the interface represented by ifindex is a - * 802.11 wireless device */ -bool is_wifi_iface(int ifindex) + * 802.11 wireless device + */ +bool batadv_is_wifi_iface(int ifindex) { struct net_device *net_device = NULL; bool ret = false; - if (ifindex == NULL_IFINDEX) + if (ifindex == BATADV_NULL_IFINDEX) goto out; net_device = dev_get_by_index(&init_net, ifindex); @@ -561,7 +562,8 @@ bool is_wifi_iface(int ifindex) #ifdef CONFIG_WIRELESS_EXT /* pre-cfg80211 drivers have to implement WEXT, so it is possible to - * check for wireless_handlers != NULL */ + * check for wireless_handlers != NULL + */ if (net_device->wireless_handlers) ret = true; else @@ -575,6 +577,6 @@ out: return ret; } -struct notifier_block hard_if_notifier = { - .notifier_call = hard_if_event, +struct notifier_block batadv_hard_if_notifier = { + .notifier_call = batadv_hard_if_event, }; diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index e68c5655e61..3732366e744 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -16,44 +15,44 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_HARD_INTERFACE_H_ #define _NET_BATMAN_ADV_HARD_INTERFACE_H_ -enum hard_if_state { - IF_NOT_IN_USE, - IF_TO_BE_REMOVED, - IF_INACTIVE, - IF_ACTIVE, - IF_TO_BE_ACTIVATED, - IF_I_WANT_YOU +enum batadv_hard_if_state { + BATADV_IF_NOT_IN_USE, + BATADV_IF_TO_BE_REMOVED, + BATADV_IF_INACTIVE, + BATADV_IF_ACTIVE, + BATADV_IF_TO_BE_ACTIVATED, + BATADV_IF_I_WANT_YOU, }; -extern struct notifier_block hard_if_notifier; +extern struct notifier_block batadv_hard_if_notifier; -struct hard_iface* -hardif_get_by_netdev(const struct net_device *net_dev); -int hardif_enable_interface(struct hard_iface *hard_iface, - const char *iface_name); -void hardif_disable_interface(struct hard_iface *hard_iface); -void hardif_remove_interfaces(void); -int hardif_min_mtu(struct net_device *soft_iface); -void update_min_mtu(struct net_device *soft_iface); -void hardif_free_rcu(struct rcu_head *rcu); -bool is_wifi_iface(int ifindex); +struct batadv_hard_iface* +batadv_hardif_get_by_netdev(const struct net_device *net_dev); +int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, + const char *iface_name); +void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface); +void batadv_hardif_remove_interfaces(void); +int batadv_hardif_min_mtu(struct net_device *soft_iface); +void batadv_update_min_mtu(struct net_device *soft_iface); +void batadv_hardif_free_rcu(struct rcu_head *rcu); +bool batadv_is_wifi_iface(int ifindex); -static inline void hardif_free_ref(struct hard_iface *hard_iface) +static inline void +batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface) { if (atomic_dec_and_test(&hard_iface->refcount)) - call_rcu(&hard_iface->rcu, hardif_free_rcu); + call_rcu(&hard_iface->rcu, batadv_hardif_free_rcu); } -static inline struct hard_iface *primary_if_get_selected( - struct bat_priv *bat_priv) +static inline struct batadv_hard_iface * +batadv_primary_if_get_selected(struct batadv_priv *bat_priv) { - struct hard_iface *hard_iface; + struct batadv_hard_iface *hard_iface; rcu_read_lock(); hard_iface = rcu_dereference(bat_priv->primary_if); diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index 117687bedf2..15a849c2d41 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * @@ -16,25 +15,24 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" #include "hash.h" /* clears the hash */ -static void hash_init(struct hashtable_t *hash) +static void batadv_hash_init(struct batadv_hashtable *hash) { uint32_t i; - for (i = 0 ; i < hash->size; i++) { + for (i = 0; i < hash->size; i++) { INIT_HLIST_HEAD(&hash->table[i]); spin_lock_init(&hash->list_locks[i]); } } /* free only the hashtable and the hash itself. */ -void hash_destroy(struct hashtable_t *hash) +void batadv_hash_destroy(struct batadv_hashtable *hash) { kfree(hash->list_locks); kfree(hash->table); @@ -42,9 +40,9 @@ void hash_destroy(struct hashtable_t *hash) } /* allocates and clears the hash */ -struct hashtable_t *hash_new(uint32_t size) +struct batadv_hashtable *batadv_hash_new(uint32_t size) { - struct hashtable_t *hash; + struct batadv_hashtable *hash; hash = kmalloc(sizeof(*hash), GFP_ATOMIC); if (!hash) @@ -60,7 +58,7 @@ struct hashtable_t *hash_new(uint32_t size) goto free_table; hash->size = size; - hash_init(hash); + batadv_hash_init(hash); return hash; free_table: @@ -69,3 +67,12 @@ free_hash: kfree(hash); return NULL; } + +void batadv_hash_set_lock_class(struct batadv_hashtable *hash, + struct lock_class_key *key) +{ + uint32_t i; + + for (i = 0; i < hash->size; i++) + lockdep_set_class(&hash->list_locks[i], key); +} diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index d4bd7862719..977de9c75fc 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_HASH_H_ @@ -24,35 +22,42 @@ #include <linux/list.h> -/* callback to a compare function. should - * compare 2 element datas for their keys, - * return 0 if same and not 0 if not - * same */ -typedef int (*hashdata_compare_cb)(const struct hlist_node *, const void *); +/* callback to a compare function. should compare 2 element datas for their + * keys, return 0 if same and not 0 if not same + */ +typedef int (*batadv_hashdata_compare_cb)(const struct hlist_node *, + const void *); /* the hashfunction, should return an index * based on the key in the data of the first - * argument and the size the second */ -typedef uint32_t (*hashdata_choose_cb)(const void *, uint32_t); -typedef void (*hashdata_free_cb)(struct hlist_node *, void *); + * argument and the size the second + */ +typedef uint32_t (*batadv_hashdata_choose_cb)(const void *, uint32_t); +typedef void (*batadv_hashdata_free_cb)(struct hlist_node *, void *); -struct hashtable_t { +struct batadv_hashtable { struct hlist_head *table; /* the hashtable itself with the buckets */ spinlock_t *list_locks; /* spinlock for each hash list entry */ uint32_t size; /* size of hashtable */ }; /* allocates and clears the hash */ -struct hashtable_t *hash_new(uint32_t size); +struct batadv_hashtable *batadv_hash_new(uint32_t size); + +/* set class key for all locks */ +void batadv_hash_set_lock_class(struct batadv_hashtable *hash, + struct lock_class_key *key); /* free only the hashtable and the hash itself. */ -void hash_destroy(struct hashtable_t *hash); +void batadv_hash_destroy(struct batadv_hashtable *hash); /* remove the hash structure. if hashdata_free_cb != NULL, this function will be * called to remove the elements inside of the hash. if you don't remove the - * elements, memory might be leaked. */ -static inline void hash_delete(struct hashtable_t *hash, - hashdata_free_cb free_cb, void *arg) + * elements, memory might be leaked. + */ +static inline void batadv_hash_delete(struct batadv_hashtable *hash, + batadv_hashdata_free_cb free_cb, + void *arg) { struct hlist_head *head; struct hlist_node *node, *node_tmp; @@ -73,11 +78,11 @@ static inline void hash_delete(struct hashtable_t *hash, spin_unlock_bh(list_lock); } - hash_destroy(hash); + batadv_hash_destroy(hash); } /** - * hash_add - adds data to the hashtable + * batadv_hash_add - adds data to the hashtable * @hash: storage hash table * @compare: callback to determine if 2 hash elements are identical * @choose: callback calculating the hash index @@ -87,11 +92,11 @@ static inline void hash_delete(struct hashtable_t *hash, * Returns 0 on success, 1 if the element already is in the hash * and -1 on error. */ - -static inline int hash_add(struct hashtable_t *hash, - hashdata_compare_cb compare, - hashdata_choose_cb choose, - const void *data, struct hlist_node *data_node) +static inline int batadv_hash_add(struct batadv_hashtable *hash, + batadv_hashdata_compare_cb compare, + batadv_hashdata_choose_cb choose, + const void *data, + struct hlist_node *data_node) { uint32_t index; int ret = -1; @@ -106,26 +111,23 @@ static inline int hash_add(struct hashtable_t *hash, head = &hash->table[index]; list_lock = &hash->list_locks[index]; - rcu_read_lock(); - __hlist_for_each_rcu(node, head) { + spin_lock_bh(list_lock); + + hlist_for_each(node, head) { if (!compare(node, data)) continue; ret = 1; - goto err_unlock; + goto unlock; } - rcu_read_unlock(); /* no duplicate found in list, add new element */ - spin_lock_bh(list_lock); hlist_add_head_rcu(data_node, head); - spin_unlock_bh(list_lock); ret = 0; - goto out; -err_unlock: - rcu_read_unlock(); +unlock: + spin_unlock_bh(list_lock); out: return ret; } @@ -133,10 +135,12 @@ out: /* removes data from hash, if found. returns pointer do data on success, so you * can remove the used structure yourself, or NULL on error . data could be the * structure you use with just the key filled, we just need the key for - * comparing. */ -static inline void *hash_remove(struct hashtable_t *hash, - hashdata_compare_cb compare, - hashdata_choose_cb choose, void *data) + * comparing. + */ +static inline void *batadv_hash_remove(struct batadv_hashtable *hash, + batadv_hashdata_compare_cb compare, + batadv_hashdata_choose_cb choose, + void *data) { uint32_t index; struct hlist_node *node; diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 2e98a57f340..bde3cf74750 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" @@ -28,21 +26,21 @@ #include "originator.h" #include "hard-interface.h" -static struct socket_client *socket_client_hash[256]; +static struct batadv_socket_client *batadv_socket_client_hash[256]; -static void bat_socket_add_packet(struct socket_client *socket_client, - struct icmp_packet_rr *icmp_packet, - size_t icmp_len); +static void batadv_socket_add_packet(struct batadv_socket_client *socket_client, + struct batadv_icmp_packet_rr *icmp_packet, + size_t icmp_len); -void bat_socket_init(void) +void batadv_socket_init(void) { - memset(socket_client_hash, 0, sizeof(socket_client_hash)); + memset(batadv_socket_client_hash, 0, sizeof(batadv_socket_client_hash)); } -static int bat_socket_open(struct inode *inode, struct file *file) +static int batadv_socket_open(struct inode *inode, struct file *file) { unsigned int i; - struct socket_client *socket_client; + struct batadv_socket_client *socket_client; nonseekable_open(inode, file); @@ -51,14 +49,14 @@ static int bat_socket_open(struct inode *inode, struct file *file) if (!socket_client) return -ENOMEM; - for (i = 0; i < ARRAY_SIZE(socket_client_hash); i++) { - if (!socket_client_hash[i]) { - socket_client_hash[i] = socket_client; + for (i = 0; i < ARRAY_SIZE(batadv_socket_client_hash); i++) { + if (!batadv_socket_client_hash[i]) { + batadv_socket_client_hash[i] = socket_client; break; } } - if (i == ARRAY_SIZE(socket_client_hash)) { + if (i == ARRAY_SIZE(batadv_socket_client_hash)) { pr_err("Error - can't add another packet client: maximum number of clients reached\n"); kfree(socket_client); return -EXFULL; @@ -73,14 +71,14 @@ static int bat_socket_open(struct inode *inode, struct file *file) file->private_data = socket_client; - inc_module_count(); + batadv_inc_module_count(); return 0; } -static int bat_socket_release(struct inode *inode, struct file *file) +static int batadv_socket_release(struct inode *inode, struct file *file) { - struct socket_client *socket_client = file->private_data; - struct socket_packet *socket_packet; + struct batadv_socket_client *socket_client = file->private_data; + struct batadv_socket_packet *socket_packet; struct list_head *list_pos, *list_pos_tmp; spin_lock_bh(&socket_client->lock); @@ -88,33 +86,33 @@ static int bat_socket_release(struct inode *inode, struct file *file) /* for all packets in the queue ... */ list_for_each_safe(list_pos, list_pos_tmp, &socket_client->queue_list) { socket_packet = list_entry(list_pos, - struct socket_packet, list); + struct batadv_socket_packet, list); list_del(list_pos); kfree(socket_packet); } - socket_client_hash[socket_client->index] = NULL; + batadv_socket_client_hash[socket_client->index] = NULL; spin_unlock_bh(&socket_client->lock); kfree(socket_client); - dec_module_count(); + batadv_dec_module_count(); return 0; } -static ssize_t bat_socket_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) +static ssize_t batadv_socket_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) { - struct socket_client *socket_client = file->private_data; - struct socket_packet *socket_packet; + struct batadv_socket_client *socket_client = file->private_data; + struct batadv_socket_packet *socket_packet; size_t packet_len; int error; if ((file->f_flags & O_NONBLOCK) && (socket_client->queue_len == 0)) return -EAGAIN; - if ((!buf) || (count < sizeof(struct icmp_packet))) + if ((!buf) || (count < sizeof(struct batadv_icmp_packet))) return -EINVAL; if (!access_ok(VERIFY_WRITE, buf, count)) @@ -129,7 +127,7 @@ static ssize_t bat_socket_read(struct file *file, char __user *buf, spin_lock_bh(&socket_client->lock); socket_packet = list_first_entry(&socket_client->queue_list, - struct socket_packet, list); + struct batadv_socket_packet, list); list_del(&socket_packet->list); socket_client->queue_len--; @@ -146,34 +144,34 @@ static ssize_t bat_socket_read(struct file *file, char __user *buf, return packet_len; } -static ssize_t bat_socket_write(struct file *file, const char __user *buff, - size_t len, loff_t *off) +static ssize_t batadv_socket_write(struct file *file, const char __user *buff, + size_t len, loff_t *off) { - struct socket_client *socket_client = file->private_data; - struct bat_priv *bat_priv = socket_client->bat_priv; - struct hard_iface *primary_if = NULL; + struct batadv_socket_client *socket_client = file->private_data; + struct batadv_priv *bat_priv = socket_client->bat_priv; + struct batadv_hard_iface *primary_if = NULL; struct sk_buff *skb; - struct icmp_packet_rr *icmp_packet; + struct batadv_icmp_packet_rr *icmp_packet; - struct orig_node *orig_node = NULL; - struct neigh_node *neigh_node = NULL; - size_t packet_len = sizeof(struct icmp_packet); + struct batadv_orig_node *orig_node = NULL; + struct batadv_neigh_node *neigh_node = NULL; + size_t packet_len = sizeof(struct batadv_icmp_packet); - if (len < sizeof(struct icmp_packet)) { - bat_dbg(DBG_BATMAN, bat_priv, - "Error - can't send packet from char device: invalid packet size\n"); + if (len < sizeof(struct batadv_icmp_packet)) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Error - can't send packet from char device: invalid packet size\n"); return -EINVAL; } - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) { len = -EFAULT; goto out; } - if (len >= sizeof(struct icmp_packet_rr)) - packet_len = sizeof(struct icmp_packet_rr); + if (len >= sizeof(struct batadv_icmp_packet_rr)) + packet_len = sizeof(struct batadv_icmp_packet_rr); skb = dev_alloc_skb(packet_len + ETH_HLEN); if (!skb) { @@ -182,81 +180,82 @@ static ssize_t bat_socket_write(struct file *file, const char __user *buff, } skb_reserve(skb, ETH_HLEN); - icmp_packet = (struct icmp_packet_rr *)skb_put(skb, packet_len); + icmp_packet = (struct batadv_icmp_packet_rr *)skb_put(skb, packet_len); if (copy_from_user(icmp_packet, buff, packet_len)) { len = -EFAULT; goto free_skb; } - if (icmp_packet->header.packet_type != BAT_ICMP) { - bat_dbg(DBG_BATMAN, bat_priv, - "Error - can't send packet from char device: got bogus packet type (expected: BAT_ICMP)\n"); + if (icmp_packet->header.packet_type != BATADV_ICMP) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Error - can't send packet from char device: got bogus packet type (expected: BAT_ICMP)\n"); len = -EINVAL; goto free_skb; } - if (icmp_packet->msg_type != ECHO_REQUEST) { - bat_dbg(DBG_BATMAN, bat_priv, - "Error - can't send packet from char device: got bogus message type (expected: ECHO_REQUEST)\n"); + if (icmp_packet->msg_type != BATADV_ECHO_REQUEST) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Error - can't send packet from char device: got bogus message type (expected: ECHO_REQUEST)\n"); len = -EINVAL; goto free_skb; } icmp_packet->uid = socket_client->index; - if (icmp_packet->header.version != COMPAT_VERSION) { - icmp_packet->msg_type = PARAMETER_PROBLEM; - icmp_packet->header.version = COMPAT_VERSION; - bat_socket_add_packet(socket_client, icmp_packet, packet_len); + if (icmp_packet->header.version != BATADV_COMPAT_VERSION) { + icmp_packet->msg_type = BATADV_PARAMETER_PROBLEM; + icmp_packet->header.version = BATADV_COMPAT_VERSION; + batadv_socket_add_packet(socket_client, icmp_packet, + packet_len); goto free_skb; } - if (atomic_read(&bat_priv->mesh_state) != MESH_ACTIVE) + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) goto dst_unreach; - orig_node = orig_hash_find(bat_priv, icmp_packet->dst); + orig_node = batadv_orig_hash_find(bat_priv, icmp_packet->dst); if (!orig_node) goto dst_unreach; - neigh_node = orig_node_get_router(orig_node); + neigh_node = batadv_orig_node_get_router(orig_node); if (!neigh_node) goto dst_unreach; if (!neigh_node->if_incoming) goto dst_unreach; - if (neigh_node->if_incoming->if_status != IF_ACTIVE) + if (neigh_node->if_incoming->if_status != BATADV_IF_ACTIVE) goto dst_unreach; memcpy(icmp_packet->orig, primary_if->net_dev->dev_addr, ETH_ALEN); - if (packet_len == sizeof(struct icmp_packet_rr)) + if (packet_len == sizeof(struct batadv_icmp_packet_rr)) memcpy(icmp_packet->rr, neigh_node->if_incoming->net_dev->dev_addr, ETH_ALEN); - send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); goto out; dst_unreach: - icmp_packet->msg_type = DESTINATION_UNREACHABLE; - bat_socket_add_packet(socket_client, icmp_packet, packet_len); + icmp_packet->msg_type = BATADV_DESTINATION_UNREACHABLE; + batadv_socket_add_packet(socket_client, icmp_packet, packet_len); free_skb: kfree_skb(skb); out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); if (neigh_node) - neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref(neigh_node); if (orig_node) - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); return len; } -static unsigned int bat_socket_poll(struct file *file, poll_table *wait) +static unsigned int batadv_socket_poll(struct file *file, poll_table *wait) { - struct socket_client *socket_client = file->private_data; + struct batadv_socket_client *socket_client = file->private_data; poll_wait(file, &socket_client->queue_wait, wait); @@ -266,39 +265,39 @@ static unsigned int bat_socket_poll(struct file *file, poll_table *wait) return 0; } -static const struct file_operations fops = { +static const struct file_operations batadv_fops = { .owner = THIS_MODULE, - .open = bat_socket_open, - .release = bat_socket_release, - .read = bat_socket_read, - .write = bat_socket_write, - .poll = bat_socket_poll, + .open = batadv_socket_open, + .release = batadv_socket_release, + .read = batadv_socket_read, + .write = batadv_socket_write, + .poll = batadv_socket_poll, .llseek = no_llseek, }; -int bat_socket_setup(struct bat_priv *bat_priv) +int batadv_socket_setup(struct batadv_priv *bat_priv) { struct dentry *d; if (!bat_priv->debug_dir) goto err; - d = debugfs_create_file(ICMP_SOCKET, S_IFREG | S_IWUSR | S_IRUSR, - bat_priv->debug_dir, bat_priv, &fops); - if (d) + d = debugfs_create_file(BATADV_ICMP_SOCKET, S_IFREG | S_IWUSR | S_IRUSR, + bat_priv->debug_dir, bat_priv, &batadv_fops); + if (!d) goto err; return 0; err: - return 1; + return -ENOMEM; } -static void bat_socket_add_packet(struct socket_client *socket_client, - struct icmp_packet_rr *icmp_packet, - size_t icmp_len) +static void batadv_socket_add_packet(struct batadv_socket_client *socket_client, + struct batadv_icmp_packet_rr *icmp_packet, + size_t icmp_len) { - struct socket_packet *socket_packet; + struct batadv_socket_packet *socket_packet; socket_packet = kmalloc(sizeof(*socket_packet), GFP_ATOMIC); @@ -312,8 +311,9 @@ static void bat_socket_add_packet(struct socket_client *socket_client, spin_lock_bh(&socket_client->lock); /* while waiting for the lock the socket_client could have been - * deleted */ - if (!socket_client_hash[icmp_packet->uid]) { + * deleted + */ + if (!batadv_socket_client_hash[icmp_packet->uid]) { spin_unlock_bh(&socket_client->lock); kfree(socket_packet); return; @@ -324,7 +324,8 @@ static void bat_socket_add_packet(struct socket_client *socket_client, if (socket_client->queue_len > 100) { socket_packet = list_first_entry(&socket_client->queue_list, - struct socket_packet, list); + struct batadv_socket_packet, + list); list_del(&socket_packet->list); kfree(socket_packet); @@ -336,11 +337,12 @@ static void bat_socket_add_packet(struct socket_client *socket_client, wake_up(&socket_client->queue_wait); } -void bat_socket_receive_packet(struct icmp_packet_rr *icmp_packet, - size_t icmp_len) +void batadv_socket_receive_packet(struct batadv_icmp_packet_rr *icmp_packet, + size_t icmp_len) { - struct socket_client *hash = socket_client_hash[icmp_packet->uid]; + struct batadv_socket_client *hash; + hash = batadv_socket_client_hash[icmp_packet->uid]; if (hash) - bat_socket_add_packet(hash, icmp_packet, icmp_len); + batadv_socket_add_packet(hash, icmp_packet, icmp_len); } diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 380ed4c2443..29443a1dbb5 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -16,17 +15,16 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_ICMP_SOCKET_H_ #define _NET_BATMAN_ADV_ICMP_SOCKET_H_ -#define ICMP_SOCKET "socket" +#define BATADV_ICMP_SOCKET "socket" -void bat_socket_init(void); -int bat_socket_setup(struct bat_priv *bat_priv); -void bat_socket_receive_packet(struct icmp_packet_rr *icmp_packet, - size_t icmp_len); +void batadv_socket_init(void); +int batadv_socket_setup(struct batadv_priv *bat_priv); +void batadv_socket_receive_packet(struct batadv_icmp_packet_rr *icmp_packet, + size_t icmp_len); #endif /* _NET_BATMAN_ADV_ICMP_SOCKET_H_ */ diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 083a2993efe..13c88b25ab3 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -16,12 +15,11 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" -#include "bat_sysfs.h" -#include "bat_debugfs.h" +#include "sysfs.h" +#include "debugfs.h" #include "routing.h" #include "send.h" #include "originator.h" @@ -37,61 +35,65 @@ /* List manipulations on hardif_list have to be rtnl_lock()'ed, - * list traversals just rcu-locked */ -struct list_head hardif_list; -static int (*recv_packet_handler[256])(struct sk_buff *, struct hard_iface *); -char bat_routing_algo[20] = "BATMAN IV"; -static struct hlist_head bat_algo_list; + * list traversals just rcu-locked + */ +struct list_head batadv_hardif_list; +static int (*batadv_rx_handler[256])(struct sk_buff *, + struct batadv_hard_iface *); +char batadv_routing_algo[20] = "BATMAN_IV"; +static struct hlist_head batadv_algo_list; -unsigned char broadcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; +unsigned char batadv_broadcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; -struct workqueue_struct *bat_event_workqueue; +struct workqueue_struct *batadv_event_workqueue; -static void recv_handler_init(void); +static void batadv_recv_handler_init(void); -static int __init batman_init(void) +static int __init batadv_init(void) { - INIT_LIST_HEAD(&hardif_list); - INIT_HLIST_HEAD(&bat_algo_list); + INIT_LIST_HEAD(&batadv_hardif_list); + INIT_HLIST_HEAD(&batadv_algo_list); - recv_handler_init(); + batadv_recv_handler_init(); - bat_iv_init(); + batadv_iv_init(); /* the name should not be longer than 10 chars - see - * http://lwn.net/Articles/23634/ */ - bat_event_workqueue = create_singlethread_workqueue("bat_events"); + * http://lwn.net/Articles/23634/ + */ + batadv_event_workqueue = create_singlethread_workqueue("bat_events"); - if (!bat_event_workqueue) + if (!batadv_event_workqueue) return -ENOMEM; - bat_socket_init(); - debugfs_init(); + batadv_socket_init(); + batadv_debugfs_init(); - register_netdevice_notifier(&hard_if_notifier); + register_netdevice_notifier(&batadv_hard_if_notifier); pr_info("B.A.T.M.A.N. advanced %s (compatibility version %i) loaded\n", - SOURCE_VERSION, COMPAT_VERSION); + BATADV_SOURCE_VERSION, BATADV_COMPAT_VERSION); return 0; } -static void __exit batman_exit(void) +static void __exit batadv_exit(void) { - debugfs_destroy(); - unregister_netdevice_notifier(&hard_if_notifier); - hardif_remove_interfaces(); + batadv_debugfs_destroy(); + unregister_netdevice_notifier(&batadv_hard_if_notifier); + batadv_hardif_remove_interfaces(); - flush_workqueue(bat_event_workqueue); - destroy_workqueue(bat_event_workqueue); - bat_event_workqueue = NULL; + flush_workqueue(batadv_event_workqueue); + destroy_workqueue(batadv_event_workqueue); + batadv_event_workqueue = NULL; rcu_barrier(); } -int mesh_init(struct net_device *soft_iface) +int batadv_mesh_init(struct net_device *soft_iface) { - struct bat_priv *bat_priv = netdev_priv(soft_iface); + struct batadv_priv *bat_priv = netdev_priv(soft_iface); + int ret; spin_lock_init(&bat_priv->forw_bat_list_lock); spin_lock_init(&bat_priv->forw_bcast_list_lock); @@ -110,72 +112,77 @@ int mesh_init(struct net_device *soft_iface) INIT_LIST_HEAD(&bat_priv->tt_req_list); INIT_LIST_HEAD(&bat_priv->tt_roam_list); - if (originator_init(bat_priv) < 1) + ret = batadv_originator_init(bat_priv); + if (ret < 0) goto err; - if (tt_init(bat_priv) < 1) + ret = batadv_tt_init(bat_priv); + if (ret < 0) goto err; - tt_local_add(soft_iface, soft_iface->dev_addr, NULL_IFINDEX); + batadv_tt_local_add(soft_iface, soft_iface->dev_addr, + BATADV_NULL_IFINDEX); - if (vis_init(bat_priv) < 1) + ret = batadv_vis_init(bat_priv); + if (ret < 0) goto err; - if (bla_init(bat_priv) < 1) + ret = batadv_bla_init(bat_priv); + if (ret < 0) goto err; atomic_set(&bat_priv->gw_reselect, 0); - atomic_set(&bat_priv->mesh_state, MESH_ACTIVE); - goto end; - -err: - mesh_free(soft_iface); - return -1; + atomic_set(&bat_priv->mesh_state, BATADV_MESH_ACTIVE); -end: return 0; + +err: + batadv_mesh_free(soft_iface); + return ret; } -void mesh_free(struct net_device *soft_iface) +void batadv_mesh_free(struct net_device *soft_iface) { - struct bat_priv *bat_priv = netdev_priv(soft_iface); + struct batadv_priv *bat_priv = netdev_priv(soft_iface); - atomic_set(&bat_priv->mesh_state, MESH_DEACTIVATING); + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); - purge_outstanding_packets(bat_priv, NULL); + batadv_purge_outstanding_packets(bat_priv, NULL); - vis_quit(bat_priv); + batadv_vis_quit(bat_priv); - gw_node_purge(bat_priv); - originator_free(bat_priv); + batadv_gw_node_purge(bat_priv); + batadv_originator_free(bat_priv); - tt_free(bat_priv); + batadv_tt_free(bat_priv); - bla_free(bat_priv); + batadv_bla_free(bat_priv); - atomic_set(&bat_priv->mesh_state, MESH_INACTIVE); + free_percpu(bat_priv->bat_counters); + + atomic_set(&bat_priv->mesh_state, BATADV_MESH_INACTIVE); } -void inc_module_count(void) +void batadv_inc_module_count(void) { try_module_get(THIS_MODULE); } -void dec_module_count(void) +void batadv_dec_module_count(void) { module_put(THIS_MODULE); } -int is_my_mac(const uint8_t *addr) +int batadv_is_my_mac(const uint8_t *addr) { - const struct hard_iface *hard_iface; + const struct batadv_hard_iface *hard_iface; rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &hardif_list, list) { - if (hard_iface->if_status != IF_ACTIVE) + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->if_status != BATADV_IF_ACTIVE) continue; - if (compare_eth(hard_iface->net_dev->dev_addr, addr)) { + if (batadv_compare_eth(hard_iface->net_dev->dev_addr, addr)) { rcu_read_unlock(); return 1; } @@ -184,8 +191,8 @@ int is_my_mac(const uint8_t *addr) return 0; } -static int recv_unhandled_packet(struct sk_buff *skb, - struct hard_iface *recv_if) +static int batadv_recv_unhandled_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if) { return NET_RX_DROP; } @@ -193,16 +200,18 @@ static int recv_unhandled_packet(struct sk_buff *skb, /* incoming packets with the batman ethertype received on any active hard * interface */ -int batman_skb_recv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *ptype, struct net_device *orig_dev) +int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *ptype, + struct net_device *orig_dev) { - struct bat_priv *bat_priv; - struct batman_ogm_packet *batman_ogm_packet; - struct hard_iface *hard_iface; + struct batadv_priv *bat_priv; + struct batadv_ogm_packet *batadv_ogm_packet; + struct batadv_hard_iface *hard_iface; uint8_t idx; int ret; - hard_iface = container_of(ptype, struct hard_iface, batman_adv_ptype); + hard_iface = container_of(ptype, struct batadv_hard_iface, + batman_adv_ptype); skb = skb_share_check(skb, GFP_ATOMIC); /* skb was released by skb_share_check() */ @@ -222,27 +231,27 @@ int batman_skb_recv(struct sk_buff *skb, struct net_device *dev, bat_priv = netdev_priv(hard_iface->soft_iface); - if (atomic_read(&bat_priv->mesh_state) != MESH_ACTIVE) + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) goto err_free; /* discard frames on not active interfaces */ - if (hard_iface->if_status != IF_ACTIVE) + if (hard_iface->if_status != BATADV_IF_ACTIVE) goto err_free; - batman_ogm_packet = (struct batman_ogm_packet *)skb->data; + batadv_ogm_packet = (struct batadv_ogm_packet *)skb->data; - if (batman_ogm_packet->header.version != COMPAT_VERSION) { - bat_dbg(DBG_BATMAN, bat_priv, - "Drop packet: incompatible batman version (%i)\n", - batman_ogm_packet->header.version); + if (batadv_ogm_packet->header.version != BATADV_COMPAT_VERSION) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: incompatible batman version (%i)\n", + batadv_ogm_packet->header.version); goto err_free; } /* all receive handlers return whether they received or reused * the supplied skb. if not, we have to free the skb. */ - idx = batman_ogm_packet->header.packet_type; - ret = (*recv_packet_handler[idx])(skb, hard_iface); + idx = batadv_ogm_packet->header.packet_type; + ret = (*batadv_rx_handler[idx])(skb, hard_iface); if (ret == NET_RX_DROP) kfree_skb(skb); @@ -259,51 +268,52 @@ err_out: return NET_RX_DROP; } -static void recv_handler_init(void) +static void batadv_recv_handler_init(void) { int i; - for (i = 0; i < ARRAY_SIZE(recv_packet_handler); i++) - recv_packet_handler[i] = recv_unhandled_packet; + for (i = 0; i < ARRAY_SIZE(batadv_rx_handler); i++) + batadv_rx_handler[i] = batadv_recv_unhandled_packet; /* batman icmp packet */ - recv_packet_handler[BAT_ICMP] = recv_icmp_packet; + batadv_rx_handler[BATADV_ICMP] = batadv_recv_icmp_packet; /* unicast packet */ - recv_packet_handler[BAT_UNICAST] = recv_unicast_packet; + batadv_rx_handler[BATADV_UNICAST] = batadv_recv_unicast_packet; /* fragmented unicast packet */ - recv_packet_handler[BAT_UNICAST_FRAG] = recv_ucast_frag_packet; + batadv_rx_handler[BATADV_UNICAST_FRAG] = batadv_recv_ucast_frag_packet; /* broadcast packet */ - recv_packet_handler[BAT_BCAST] = recv_bcast_packet; + batadv_rx_handler[BATADV_BCAST] = batadv_recv_bcast_packet; /* vis packet */ - recv_packet_handler[BAT_VIS] = recv_vis_packet; + batadv_rx_handler[BATADV_VIS] = batadv_recv_vis_packet; /* Translation table query (request or response) */ - recv_packet_handler[BAT_TT_QUERY] = recv_tt_query; + batadv_rx_handler[BATADV_TT_QUERY] = batadv_recv_tt_query; /* Roaming advertisement */ - recv_packet_handler[BAT_ROAM_ADV] = recv_roam_adv; + batadv_rx_handler[BATADV_ROAM_ADV] = batadv_recv_roam_adv; } -int recv_handler_register(uint8_t packet_type, - int (*recv_handler)(struct sk_buff *, - struct hard_iface *)) +int +batadv_recv_handler_register(uint8_t packet_type, + int (*recv_handler)(struct sk_buff *, + struct batadv_hard_iface *)) { - if (recv_packet_handler[packet_type] != &recv_unhandled_packet) + if (batadv_rx_handler[packet_type] != &batadv_recv_unhandled_packet) return -EBUSY; - recv_packet_handler[packet_type] = recv_handler; + batadv_rx_handler[packet_type] = recv_handler; return 0; } -void recv_handler_unregister(uint8_t packet_type) +void batadv_recv_handler_unregister(uint8_t packet_type) { - recv_packet_handler[packet_type] = recv_unhandled_packet; + batadv_rx_handler[packet_type] = batadv_recv_unhandled_packet; } -static struct bat_algo_ops *bat_algo_get(char *name) +static struct batadv_algo_ops *batadv_algo_get(char *name) { - struct bat_algo_ops *bat_algo_ops = NULL, *bat_algo_ops_tmp; + struct batadv_algo_ops *bat_algo_ops = NULL, *bat_algo_ops_tmp; struct hlist_node *node; - hlist_for_each_entry(bat_algo_ops_tmp, node, &bat_algo_list, list) { + hlist_for_each_entry(bat_algo_ops_tmp, node, &batadv_algo_list, list) { if (strcmp(bat_algo_ops_tmp->name, name) != 0) continue; @@ -314,15 +324,16 @@ static struct bat_algo_ops *bat_algo_get(char *name) return bat_algo_ops; } -int bat_algo_register(struct bat_algo_ops *bat_algo_ops) +int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops) { - struct bat_algo_ops *bat_algo_ops_tmp; - int ret = -1; + struct batadv_algo_ops *bat_algo_ops_tmp; + int ret; - bat_algo_ops_tmp = bat_algo_get(bat_algo_ops->name); + bat_algo_ops_tmp = batadv_algo_get(bat_algo_ops->name); if (bat_algo_ops_tmp) { pr_info("Trying to register already registered routing algorithm: %s\n", bat_algo_ops->name); + ret = -EEXIST; goto out; } @@ -335,23 +346,24 @@ int bat_algo_register(struct bat_algo_ops *bat_algo_ops) !bat_algo_ops->bat_ogm_emit) { pr_info("Routing algo '%s' does not implement required ops\n", bat_algo_ops->name); + ret = -EINVAL; goto out; } INIT_HLIST_NODE(&bat_algo_ops->list); - hlist_add_head(&bat_algo_ops->list, &bat_algo_list); + hlist_add_head(&bat_algo_ops->list, &batadv_algo_list); ret = 0; out: return ret; } -int bat_algo_select(struct bat_priv *bat_priv, char *name) +int batadv_algo_select(struct batadv_priv *bat_priv, char *name) { - struct bat_algo_ops *bat_algo_ops; - int ret = -1; + struct batadv_algo_ops *bat_algo_ops; + int ret = -EINVAL; - bat_algo_ops = bat_algo_get(name); + bat_algo_ops = batadv_algo_get(name); if (!bat_algo_ops) goto out; @@ -362,50 +374,56 @@ out: return ret; } -int bat_algo_seq_print_text(struct seq_file *seq, void *offset) +int batadv_algo_seq_print_text(struct seq_file *seq, void *offset) { - struct bat_algo_ops *bat_algo_ops; + struct batadv_algo_ops *bat_algo_ops; struct hlist_node *node; seq_printf(seq, "Available routing algorithms:\n"); - hlist_for_each_entry(bat_algo_ops, node, &bat_algo_list, list) { + hlist_for_each_entry(bat_algo_ops, node, &batadv_algo_list, list) { seq_printf(seq, "%s\n", bat_algo_ops->name); } return 0; } -static int param_set_ra(const char *val, const struct kernel_param *kp) +static int batadv_param_set_ra(const char *val, const struct kernel_param *kp) { - struct bat_algo_ops *bat_algo_ops; + struct batadv_algo_ops *bat_algo_ops; + char *algo_name = (char *)val; + size_t name_len = strlen(algo_name); + + if (algo_name[name_len - 1] == '\n') + algo_name[name_len - 1] = '\0'; - bat_algo_ops = bat_algo_get((char *)val); + bat_algo_ops = batadv_algo_get(algo_name); if (!bat_algo_ops) { - pr_err("Routing algorithm '%s' is not supported\n", val); + pr_err("Routing algorithm '%s' is not supported\n", algo_name); return -EINVAL; } - return param_set_copystring(val, kp); + return param_set_copystring(algo_name, kp); } -static const struct kernel_param_ops param_ops_ra = { - .set = param_set_ra, +static const struct kernel_param_ops batadv_param_ops_ra = { + .set = batadv_param_set_ra, .get = param_get_string, }; -static struct kparam_string __param_string_ra = { - .maxlen = sizeof(bat_routing_algo), - .string = bat_routing_algo, +static struct kparam_string batadv_param_string_ra = { + .maxlen = sizeof(batadv_routing_algo), + .string = batadv_routing_algo, }; -module_param_cb(routing_algo, ¶m_ops_ra, &__param_string_ra, 0644); -module_init(batman_init); -module_exit(batman_exit); +module_param_cb(routing_algo, &batadv_param_ops_ra, &batadv_param_string_ra, + 0644); +module_init(batadv_init); +module_exit(batadv_exit); MODULE_LICENSE("GPL"); -MODULE_AUTHOR(DRIVER_AUTHOR); -MODULE_DESCRIPTION(DRIVER_DESC); -MODULE_SUPPORTED_DEVICE(DRIVER_DEVICE); -MODULE_VERSION(SOURCE_VERSION); +MODULE_AUTHOR(BATADV_DRIVER_AUTHOR); +MODULE_DESCRIPTION(BATADV_DRIVER_DESC); +MODULE_SUPPORTED_DEVICE(BATADV_DRIVER_DEVICE); +MODULE_VERSION(BATADV_SOURCE_VERSION); diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index f4a3ec00347..5d8fa075794 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -16,100 +15,106 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_MAIN_H_ #define _NET_BATMAN_ADV_MAIN_H_ -#define DRIVER_AUTHOR "Marek Lindner <lindner_marek@yahoo.de>, " \ - "Simon Wunderlich <siwu@hrz.tu-chemnitz.de>" -#define DRIVER_DESC "B.A.T.M.A.N. advanced" -#define DRIVER_DEVICE "batman-adv" +#define BATADV_DRIVER_AUTHOR "Marek Lindner <lindner_marek@yahoo.de>, " \ + "Simon Wunderlich <siwu@hrz.tu-chemnitz.de>" +#define BATADV_DRIVER_DESC "B.A.T.M.A.N. advanced" +#define BATADV_DRIVER_DEVICE "batman-adv" -#ifndef SOURCE_VERSION -#define SOURCE_VERSION "2012.2.0" +#ifndef BATADV_SOURCE_VERSION +#define BATADV_SOURCE_VERSION "2012.3.0" #endif /* B.A.T.M.A.N. parameters */ -#define TQ_MAX_VALUE 255 -#define JITTER 20 +#define BATADV_TQ_MAX_VALUE 255 +#define BATADV_JITTER 20 - /* Time To Live of broadcast messages */ -#define TTL 50 +/* Time To Live of broadcast messages */ +#define BATADV_TTL 50 /* purge originators after time in seconds if no valid packet comes in - * -> TODO: check influence on TQ_LOCAL_WINDOW_SIZE */ -#define PURGE_TIMEOUT 200000 /* 200 seconds */ -#define TT_LOCAL_TIMEOUT 3600000 /* in miliseconds */ -#define TT_CLIENT_ROAM_TIMEOUT 600000 /* in miliseconds */ + * -> TODO: check influence on BATADV_TQ_LOCAL_WINDOW_SIZE + */ +#define BATADV_PURGE_TIMEOUT 200000 /* 200 seconds */ +#define BATADV_TT_LOCAL_TIMEOUT 3600000 /* in miliseconds */ +#define BATADV_TT_CLIENT_ROAM_TIMEOUT 600000 /* in miliseconds */ /* sliding packet range of received originator messages in sequence numbers - * (should be a multiple of our word size) */ -#define TQ_LOCAL_WINDOW_SIZE 64 -#define TT_REQUEST_TIMEOUT 3000 /* miliseconds we have to keep - * pending tt_req */ + * (should be a multiple of our word size) + */ +#define BATADV_TQ_LOCAL_WINDOW_SIZE 64 +/* miliseconds we have to keep pending tt_req */ +#define BATADV_TT_REQUEST_TIMEOUT 3000 -#define TQ_GLOBAL_WINDOW_SIZE 5 -#define TQ_LOCAL_BIDRECT_SEND_MINIMUM 1 -#define TQ_LOCAL_BIDRECT_RECV_MINIMUM 1 -#define TQ_TOTAL_BIDRECT_LIMIT 1 +#define BATADV_TQ_GLOBAL_WINDOW_SIZE 5 +#define BATADV_TQ_LOCAL_BIDRECT_SEND_MINIMUM 1 +#define BATADV_TQ_LOCAL_BIDRECT_RECV_MINIMUM 1 +#define BATADV_TQ_TOTAL_BIDRECT_LIMIT 1 -#define TT_OGM_APPEND_MAX 3 /* number of OGMs sent with the last tt diff */ +/* number of OGMs sent with the last tt diff */ +#define BATADV_TT_OGM_APPEND_MAX 3 -#define ROAMING_MAX_TIME 20000 /* Time in which a client can roam at most - * ROAMING_MAX_COUNT times in miliseconds*/ -#define ROAMING_MAX_COUNT 5 +/* Time in which a client can roam at most ROAMING_MAX_COUNT times in + * miliseconds + */ +#define BATADV_ROAMING_MAX_TIME 20000 +#define BATADV_ROAMING_MAX_COUNT 5 -#define NO_FLAGS 0 +#define BATADV_NO_FLAGS 0 -#define NULL_IFINDEX 0 /* dummy ifindex used to avoid iface checks */ +#define BATADV_NULL_IFINDEX 0 /* dummy ifindex used to avoid iface checks */ -#define NUM_WORDS BITS_TO_LONGS(TQ_LOCAL_WINDOW_SIZE) +#define BATADV_NUM_WORDS BITS_TO_LONGS(BATADV_TQ_LOCAL_WINDOW_SIZE) -#define LOG_BUF_LEN 8192 /* has to be a power of 2 */ +#define BATADV_LOG_BUF_LEN 8192 /* has to be a power of 2 */ -#define VIS_INTERVAL 5000 /* 5 seconds */ +#define BATADV_VIS_INTERVAL 5000 /* 5 seconds */ /* how much worse secondary interfaces may be to be considered as bonding - * candidates */ -#define BONDING_TQ_THRESHOLD 50 + * candidates + */ +#define BATADV_BONDING_TQ_THRESHOLD 50 /* should not be bigger than 512 bytes or change the size of - * forw_packet->direct_link_flags */ -#define MAX_AGGREGATION_BYTES 512 -#define MAX_AGGREGATION_MS 100 + * forw_packet->direct_link_flags + */ +#define BATADV_MAX_AGGREGATION_BYTES 512 +#define BATADV_MAX_AGGREGATION_MS 100 -#define BLA_PERIOD_LENGTH 10000 /* 10 seconds */ -#define BLA_BACKBONE_TIMEOUT (BLA_PERIOD_LENGTH * 3) -#define BLA_CLAIM_TIMEOUT (BLA_PERIOD_LENGTH * 10) +#define BATADV_BLA_PERIOD_LENGTH 10000 /* 10 seconds */ +#define BATADV_BLA_BACKBONE_TIMEOUT (BATADV_BLA_PERIOD_LENGTH * 3) +#define BATADV_BLA_CLAIM_TIMEOUT (BATADV_BLA_PERIOD_LENGTH * 10) -#define DUPLIST_SIZE 16 -#define DUPLIST_TIMEOUT 500 /* 500 ms */ +#define BATADV_DUPLIST_SIZE 16 +#define BATADV_DUPLIST_TIMEOUT 500 /* 500 ms */ /* don't reset again within 30 seconds */ -#define RESET_PROTECTION_MS 30000 -#define EXPECTED_SEQNO_RANGE 65536 +#define BATADV_RESET_PROTECTION_MS 30000 +#define BATADV_EXPECTED_SEQNO_RANGE 65536 -enum mesh_state { - MESH_INACTIVE, - MESH_ACTIVE, - MESH_DEACTIVATING +enum batadv_mesh_state { + BATADV_MESH_INACTIVE, + BATADV_MESH_ACTIVE, + BATADV_MESH_DEACTIVATING, }; -#define BCAST_QUEUE_LEN 256 -#define BATMAN_QUEUE_LEN 256 +#define BATADV_BCAST_QUEUE_LEN 256 +#define BATADV_BATMAN_QUEUE_LEN 256 -enum uev_action { - UEV_ADD = 0, - UEV_DEL, - UEV_CHANGE +enum batadv_uev_action { + BATADV_UEV_ADD = 0, + BATADV_UEV_DEL, + BATADV_UEV_CHANGE, }; -enum uev_type { - UEV_GW = 0 +enum batadv_uev_type { + BATADV_UEV_GW = 0, }; -#define GW_THRESHOLD 50 +#define BATADV_GW_THRESHOLD 50 /* Debug Messages */ #ifdef pr_fmt @@ -119,12 +124,12 @@ enum uev_type { #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt /* all messages related to routing / flooding / broadcasting / etc */ -enum dbg_level { - DBG_BATMAN = 1 << 0, - DBG_ROUTES = 1 << 1, /* route added / changed / deleted */ - DBG_TT = 1 << 2, /* translation table operations */ - DBG_BLA = 1 << 3, /* bridge loop avoidance */ - DBG_ALL = 15 +enum batadv_dbg_level { + BATADV_DBG_BATMAN = 1 << 0, + BATADV_DBG_ROUTES = 1 << 1, /* route added / changed / deleted */ + BATADV_DBG_TT = 1 << 2, /* translation table operations */ + BATADV_DBG_BLA = 1 << 3, /* bridge loop avoidance */ + BATADV_DBG_ALL = 15, }; /* Kernel headers */ @@ -138,73 +143,75 @@ enum dbg_level { #include <linux/kthread.h> /* kernel threads */ #include <linux/pkt_sched.h> /* schedule types */ #include <linux/workqueue.h> /* workqueue */ +#include <linux/percpu.h> #include <linux/slab.h> #include <net/sock.h> /* struct sock */ #include <linux/jiffies.h> #include <linux/seq_file.h> #include "types.h" -extern char bat_routing_algo[]; -extern struct list_head hardif_list; - -extern unsigned char broadcast_addr[]; -extern struct workqueue_struct *bat_event_workqueue; - -int mesh_init(struct net_device *soft_iface); -void mesh_free(struct net_device *soft_iface); -void inc_module_count(void); -void dec_module_count(void); -int is_my_mac(const uint8_t *addr); -int batman_skb_recv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *ptype, struct net_device *orig_dev); -int recv_handler_register(uint8_t packet_type, - int (*recv_handler)(struct sk_buff *, - struct hard_iface *)); -void recv_handler_unregister(uint8_t packet_type); -int bat_algo_register(struct bat_algo_ops *bat_algo_ops); -int bat_algo_select(struct bat_priv *bat_priv, char *name); -int bat_algo_seq_print_text(struct seq_file *seq, void *offset); +extern char batadv_routing_algo[]; +extern struct list_head batadv_hardif_list; + +extern unsigned char batadv_broadcast_addr[]; +extern struct workqueue_struct *batadv_event_workqueue; + +int batadv_mesh_init(struct net_device *soft_iface); +void batadv_mesh_free(struct net_device *soft_iface); +void batadv_inc_module_count(void); +void batadv_dec_module_count(void); +int batadv_is_my_mac(const uint8_t *addr); +int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *ptype, + struct net_device *orig_dev); +int +batadv_recv_handler_register(uint8_t packet_type, + int (*recv_handler)(struct sk_buff *, + struct batadv_hard_iface *)); +void batadv_recv_handler_unregister(uint8_t packet_type); +int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops); +int batadv_algo_select(struct batadv_priv *bat_priv, char *name); +int batadv_algo_seq_print_text(struct seq_file *seq, void *offset); #ifdef CONFIG_BATMAN_ADV_DEBUG -int debug_log(struct bat_priv *bat_priv, const char *fmt, ...) __printf(2, 3); +int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...) +__printf(2, 3); -#define bat_dbg(type, bat_priv, fmt, arg...) \ +#define batadv_dbg(type, bat_priv, fmt, arg...) \ do { \ if (atomic_read(&bat_priv->log_level) & type) \ - debug_log(bat_priv, fmt, ## arg); \ + batadv_debug_log(bat_priv, fmt, ## arg);\ } \ while (0) #else /* !CONFIG_BATMAN_ADV_DEBUG */ __printf(3, 4) -static inline void bat_dbg(int type __always_unused, - struct bat_priv *bat_priv __always_unused, - const char *fmt __always_unused, ...) +static inline void batadv_dbg(int type __always_unused, + struct batadv_priv *bat_priv __always_unused, + const char *fmt __always_unused, ...) { } #endif -#define bat_info(net_dev, fmt, arg...) \ +#define batadv_info(net_dev, fmt, arg...) \ do { \ struct net_device *_netdev = (net_dev); \ - struct bat_priv *_batpriv = netdev_priv(_netdev); \ - bat_dbg(DBG_ALL, _batpriv, fmt, ## arg); \ + struct batadv_priv *_batpriv = netdev_priv(_netdev); \ + batadv_dbg(BATADV_DBG_ALL, _batpriv, fmt, ## arg); \ pr_info("%s: " fmt, _netdev->name, ## arg); \ } while (0) -#define bat_err(net_dev, fmt, arg...) \ +#define batadv_err(net_dev, fmt, arg...) \ do { \ struct net_device *_netdev = (net_dev); \ - struct bat_priv *_batpriv = netdev_priv(_netdev); \ - bat_dbg(DBG_ALL, _batpriv, fmt, ## arg); \ + struct batadv_priv *_batpriv = netdev_priv(_netdev); \ + batadv_dbg(BATADV_DBG_ALL, _batpriv, fmt, ## arg); \ pr_err("%s: " fmt, _netdev->name, ## arg); \ } while (0) -/** - * returns 1 if they are the same ethernet addr +/* returns 1 if they are the same ethernet addr * * note: can't use compare_ether_addr() as it requires aligned memory */ - -static inline int compare_eth(const void *data1, const void *data2) +static inline int batadv_compare_eth(const void *data1, const void *data2) { return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); } @@ -216,15 +223,16 @@ static inline int compare_eth(const void *data1, const void *data2) * * Returns true if current time is after timestamp + timeout */ -static inline bool has_timed_out(unsigned long timestamp, unsigned int timeout) +static inline bool batadv_has_timed_out(unsigned long timestamp, + unsigned int timeout) { return time_is_before_jiffies(timestamp + msecs_to_jiffies(timeout)); } -#define atomic_dec_not_zero(v) atomic_add_unless((v), -1, 0) +#define batadv_atomic_dec_not_zero(v) atomic_add_unless((v), -1, 0) /* Returns the smallest signed integer in two's complement with the sizeof x */ -#define smallest_signed_int(x) (1u << (7u + 8u * (sizeof(x) - 1u))) +#define batadv_smallest_signed_int(x) (1u << (7u + 8u * (sizeof(x) - 1u))) /* Checks if a sequence number x is a predecessor/successor of y. * they handle overflows/underflows and can correctly check for a @@ -234,12 +242,39 @@ static inline bool has_timed_out(unsigned long timestamp, unsigned int timeout) * - when adding nothing - it is neither a predecessor nor a successor * - before adding more than 127 to the starting value - it is a predecessor, * - when adding 128 - it is neither a predecessor nor a successor, - * - after adding more than 127 to the starting value - it is a successor */ -#define seq_before(x, y) ({typeof(x) _d1 = (x); \ - typeof(y) _d2 = (y); \ - typeof(x) _dummy = (_d1 - _d2); \ - (void) (&_d1 == &_d2); \ - _dummy > smallest_signed_int(_dummy); }) -#define seq_after(x, y) seq_before(y, x) + * - after adding more than 127 to the starting value - it is a successor + */ +#define batadv_seq_before(x, y) ({typeof(x) _d1 = (x); \ + typeof(y) _d2 = (y); \ + typeof(x) _dummy = (_d1 - _d2); \ + (void) (&_d1 == &_d2); \ + _dummy > batadv_smallest_signed_int(_dummy); }) +#define batadv_seq_after(x, y) batadv_seq_before(y, x) + +/* Stop preemption on local cpu while incrementing the counter */ +static inline void batadv_add_counter(struct batadv_priv *bat_priv, size_t idx, + size_t count) +{ + int cpu = get_cpu(); + per_cpu_ptr(bat_priv->bat_counters, cpu)[idx] += count; + put_cpu(); +} + +#define batadv_inc_counter(b, i) batadv_add_counter(b, i, 1) + +/* Sum and return the cpu-local counters for index 'idx' */ +static inline uint64_t batadv_sum_counter(struct batadv_priv *bat_priv, + size_t idx) +{ + uint64_t *counters, sum = 0; + int cpu; + + for_each_possible_cpu(cpu) { + counters = per_cpu_ptr(bat_priv->bat_counters, cpu); + sum += counters[idx]; + } + + return sum; +} #endif /* _NET_BATMAN_ADV_MAIN_H_ */ diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 41147942ba5..ac9bdf8f80a 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" @@ -30,50 +28,52 @@ #include "soft-interface.h" #include "bridge_loop_avoidance.h" -static void purge_orig(struct work_struct *work); +static void batadv_purge_orig(struct work_struct *work); -static void start_purge_timer(struct bat_priv *bat_priv) +static void batadv_start_purge_timer(struct batadv_priv *bat_priv) { - INIT_DELAYED_WORK(&bat_priv->orig_work, purge_orig); - queue_delayed_work(bat_event_workqueue, + INIT_DELAYED_WORK(&bat_priv->orig_work, batadv_purge_orig); + queue_delayed_work(batadv_event_workqueue, &bat_priv->orig_work, msecs_to_jiffies(1000)); } /* returns 1 if they are the same originator */ -static int compare_orig(const struct hlist_node *node, const void *data2) +static int batadv_compare_orig(const struct hlist_node *node, const void *data2) { - const void *data1 = container_of(node, struct orig_node, hash_entry); + const void *data1 = container_of(node, struct batadv_orig_node, + hash_entry); return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); } -int originator_init(struct bat_priv *bat_priv) +int batadv_originator_init(struct batadv_priv *bat_priv) { if (bat_priv->orig_hash) - return 1; + return 0; - bat_priv->orig_hash = hash_new(1024); + bat_priv->orig_hash = batadv_hash_new(1024); if (!bat_priv->orig_hash) goto err; - start_purge_timer(bat_priv); - return 1; + batadv_start_purge_timer(bat_priv); + return 0; err: - return 0; + return -ENOMEM; } -void neigh_node_free_ref(struct neigh_node *neigh_node) +void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node) { if (atomic_dec_and_test(&neigh_node->refcount)) kfree_rcu(neigh_node, rcu); } /* increases the refcounter of a found router */ -struct neigh_node *orig_node_get_router(struct orig_node *orig_node) +struct batadv_neigh_node * +batadv_orig_node_get_router(struct batadv_orig_node *orig_node) { - struct neigh_node *router; + struct batadv_neigh_node *router; rcu_read_lock(); router = rcu_dereference(orig_node->router); @@ -85,12 +85,12 @@ struct neigh_node *orig_node_get_router(struct orig_node *orig_node) return router; } -struct neigh_node *batadv_neigh_node_new(struct hard_iface *hard_iface, - const uint8_t *neigh_addr, - uint32_t seqno) +struct batadv_neigh_node * +batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, + const uint8_t *neigh_addr, uint32_t seqno) { - struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - struct neigh_node *neigh_node; + struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + struct batadv_neigh_node *neigh_node; neigh_node = kzalloc(sizeof(*neigh_node), GFP_ATOMIC); if (!neigh_node) @@ -104,21 +104,21 @@ struct neigh_node *batadv_neigh_node_new(struct hard_iface *hard_iface, /* extra reference for return */ atomic_set(&neigh_node->refcount, 2); - bat_dbg(DBG_BATMAN, bat_priv, - "Creating new neighbor %pM, initial seqno %d\n", - neigh_addr, seqno); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Creating new neighbor %pM, initial seqno %d\n", + neigh_addr, seqno); out: return neigh_node; } -static void orig_node_free_rcu(struct rcu_head *rcu) +static void batadv_orig_node_free_rcu(struct rcu_head *rcu) { struct hlist_node *node, *node_tmp; - struct neigh_node *neigh_node, *tmp_neigh_node; - struct orig_node *orig_node; + struct batadv_neigh_node *neigh_node, *tmp_neigh_node; + struct batadv_orig_node *orig_node; - orig_node = container_of(rcu, struct orig_node, rcu); + orig_node = container_of(rcu, struct batadv_orig_node, rcu); spin_lock_bh(&orig_node->neigh_list_lock); @@ -126,21 +126,21 @@ static void orig_node_free_rcu(struct rcu_head *rcu) list_for_each_entry_safe(neigh_node, tmp_neigh_node, &orig_node->bond_list, bonding_list) { list_del_rcu(&neigh_node->bonding_list); - neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref(neigh_node); } /* for all neighbors towards this originator ... */ hlist_for_each_entry_safe(neigh_node, node, node_tmp, &orig_node->neigh_list, list) { hlist_del_rcu(&neigh_node->list); - neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref(neigh_node); } spin_unlock_bh(&orig_node->neigh_list_lock); - frag_list_free(&orig_node->frag_list); - tt_global_del_orig(orig_node->bat_priv, orig_node, - "originator timed out"); + batadv_frag_list_free(&orig_node->frag_list); + batadv_tt_global_del_orig(orig_node->bat_priv, orig_node, + "originator timed out"); kfree(orig_node->tt_buff); kfree(orig_node->bcast_own); @@ -148,19 +148,19 @@ static void orig_node_free_rcu(struct rcu_head *rcu) kfree(orig_node); } -void orig_node_free_ref(struct orig_node *orig_node) +void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node) { if (atomic_dec_and_test(&orig_node->refcount)) - call_rcu(&orig_node->rcu, orig_node_free_rcu); + call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu); } -void originator_free(struct bat_priv *bat_priv) +void batadv_originator_free(struct batadv_priv *bat_priv) { - struct hashtable_t *hash = bat_priv->orig_hash; + struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_node *node, *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* spinlock to protect write access */ - struct orig_node *orig_node; + struct batadv_orig_node *orig_node; uint32_t i; if (!hash) @@ -179,28 +179,31 @@ void originator_free(struct bat_priv *bat_priv) head, hash_entry) { hlist_del_rcu(node); - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); } spin_unlock_bh(list_lock); } - hash_destroy(hash); + batadv_hash_destroy(hash); } /* this function finds or creates an originator entry for the given - * address if it does not exits */ -struct orig_node *get_orig_node(struct bat_priv *bat_priv, const uint8_t *addr) + * address if it does not exits + */ +struct batadv_orig_node *batadv_get_orig_node(struct batadv_priv *bat_priv, + const uint8_t *addr) { - struct orig_node *orig_node; + struct batadv_orig_node *orig_node; int size; int hash_added; + unsigned long reset_time; - orig_node = orig_hash_find(bat_priv, addr); + orig_node = batadv_orig_hash_find(bat_priv, addr); if (orig_node) return orig_node; - bat_dbg(DBG_BATMAN, bat_priv, - "Creating new originator: %pM\n", addr); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Creating new originator: %pM\n", addr); orig_node = kzalloc(sizeof(*orig_node), GFP_ATOMIC); if (!orig_node) @@ -226,14 +229,13 @@ struct orig_node *get_orig_node(struct bat_priv *bat_priv, const uint8_t *addr) orig_node->tt_buff = NULL; orig_node->tt_buff_len = 0; atomic_set(&orig_node->tt_size, 0); - orig_node->bcast_seqno_reset = jiffies - 1 - - msecs_to_jiffies(RESET_PROTECTION_MS); - orig_node->batman_seqno_reset = jiffies - 1 - - msecs_to_jiffies(RESET_PROTECTION_MS); + reset_time = jiffies - 1 - msecs_to_jiffies(BATADV_RESET_PROTECTION_MS); + orig_node->bcast_seqno_reset = reset_time; + orig_node->batman_seqno_reset = reset_time; atomic_set(&orig_node->bond_candidates, 0); - size = bat_priv->num_ifaces * sizeof(unsigned long) * NUM_WORDS; + size = bat_priv->num_ifaces * sizeof(unsigned long) * BATADV_NUM_WORDS; orig_node->bcast_own = kzalloc(size, GFP_ATOMIC); if (!orig_node->bcast_own) @@ -248,8 +250,9 @@ struct orig_node *get_orig_node(struct bat_priv *bat_priv, const uint8_t *addr) if (!orig_node->bcast_own_sum) goto free_bcast_own; - hash_added = hash_add(bat_priv->orig_hash, compare_orig, - choose_orig, orig_node, &orig_node->hash_entry); + hash_added = batadv_hash_add(bat_priv->orig_hash, batadv_compare_orig, + batadv_choose_orig, orig_node, + &orig_node->hash_entry); if (hash_added != 0) goto free_bcast_own_sum; @@ -263,14 +266,16 @@ free_orig_node: return NULL; } -static bool purge_orig_neighbors(struct bat_priv *bat_priv, - struct orig_node *orig_node, - struct neigh_node **best_neigh_node) +static bool +batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + struct batadv_neigh_node **best_neigh_node) { struct hlist_node *node, *node_tmp; - struct neigh_node *neigh_node; + struct batadv_neigh_node *neigh_node; bool neigh_purged = false; unsigned long last_seen; + struct batadv_hard_iface *if_incoming; *best_neigh_node = NULL; @@ -280,34 +285,32 @@ static bool purge_orig_neighbors(struct bat_priv *bat_priv, hlist_for_each_entry_safe(neigh_node, node, node_tmp, &orig_node->neigh_list, list) { - if ((has_timed_out(neigh_node->last_seen, PURGE_TIMEOUT)) || - (neigh_node->if_incoming->if_status == IF_INACTIVE) || - (neigh_node->if_incoming->if_status == IF_NOT_IN_USE) || - (neigh_node->if_incoming->if_status == IF_TO_BE_REMOVED)) { - - last_seen = neigh_node->last_seen; - - if ((neigh_node->if_incoming->if_status == - IF_INACTIVE) || - (neigh_node->if_incoming->if_status == - IF_NOT_IN_USE) || - (neigh_node->if_incoming->if_status == - IF_TO_BE_REMOVED)) - bat_dbg(DBG_BATMAN, bat_priv, - "neighbor purge: originator %pM, neighbor: %pM, iface: %s\n", - orig_node->orig, neigh_node->addr, - neigh_node->if_incoming->net_dev->name); + last_seen = neigh_node->last_seen; + if_incoming = neigh_node->if_incoming; + + if ((batadv_has_timed_out(last_seen, BATADV_PURGE_TIMEOUT)) || + (if_incoming->if_status == BATADV_IF_INACTIVE) || + (if_incoming->if_status == BATADV_IF_NOT_IN_USE) || + (if_incoming->if_status == BATADV_IF_TO_BE_REMOVED)) { + + if ((if_incoming->if_status == BATADV_IF_INACTIVE) || + (if_incoming->if_status == BATADV_IF_NOT_IN_USE) || + (if_incoming->if_status == BATADV_IF_TO_BE_REMOVED)) + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "neighbor purge: originator %pM, neighbor: %pM, iface: %s\n", + orig_node->orig, neigh_node->addr, + if_incoming->net_dev->name); else - bat_dbg(DBG_BATMAN, bat_priv, - "neighbor timeout: originator %pM, neighbor: %pM, last_seen: %u\n", - orig_node->orig, neigh_node->addr, - jiffies_to_msecs(last_seen)); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "neighbor timeout: originator %pM, neighbor: %pM, last_seen: %u\n", + orig_node->orig, neigh_node->addr, + jiffies_to_msecs(last_seen)); neigh_purged = true; hlist_del_rcu(&neigh_node->list); - bonding_candidate_del(orig_node, neigh_node); - neigh_node_free_ref(neigh_node); + batadv_bonding_candidate_del(orig_node, neigh_node); + batadv_neigh_node_free_ref(neigh_node); } else { if ((!*best_neigh_node) || (neigh_node->tq_avg > (*best_neigh_node)->tq_avg)) @@ -319,33 +322,35 @@ static bool purge_orig_neighbors(struct bat_priv *bat_priv, return neigh_purged; } -static bool purge_orig_node(struct bat_priv *bat_priv, - struct orig_node *orig_node) +static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node) { - struct neigh_node *best_neigh_node; - - if (has_timed_out(orig_node->last_seen, 2 * PURGE_TIMEOUT)) { - bat_dbg(DBG_BATMAN, bat_priv, - "Originator timeout: originator %pM, last_seen %u\n", - orig_node->orig, - jiffies_to_msecs(orig_node->last_seen)); + struct batadv_neigh_node *best_neigh_node; + + if (batadv_has_timed_out(orig_node->last_seen, + 2 * BATADV_PURGE_TIMEOUT)) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Originator timeout: originator %pM, last_seen %u\n", + orig_node->orig, + jiffies_to_msecs(orig_node->last_seen)); return true; } else { - if (purge_orig_neighbors(bat_priv, orig_node, - &best_neigh_node)) - update_route(bat_priv, orig_node, best_neigh_node); + if (batadv_purge_orig_neighbors(bat_priv, orig_node, + &best_neigh_node)) + batadv_update_route(bat_priv, orig_node, + best_neigh_node); } return false; } -static void _purge_orig(struct bat_priv *bat_priv) +static void _batadv_purge_orig(struct batadv_priv *bat_priv) { - struct hashtable_t *hash = bat_priv->orig_hash; + struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_node *node, *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* spinlock to protect write access */ - struct orig_node *orig_node; + struct batadv_orig_node *orig_node; uint32_t i; if (!hash) @@ -359,58 +364,60 @@ static void _purge_orig(struct bat_priv *bat_priv) spin_lock_bh(list_lock); hlist_for_each_entry_safe(orig_node, node, node_tmp, head, hash_entry) { - if (purge_orig_node(bat_priv, orig_node)) { + if (batadv_purge_orig_node(bat_priv, orig_node)) { if (orig_node->gw_flags) - gw_node_delete(bat_priv, orig_node); + batadv_gw_node_delete(bat_priv, + orig_node); hlist_del_rcu(node); - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); continue; } - if (has_timed_out(orig_node->last_frag_packet, - FRAG_TIMEOUT)) - frag_list_free(&orig_node->frag_list); + if (batadv_has_timed_out(orig_node->last_frag_packet, + BATADV_FRAG_TIMEOUT)) + batadv_frag_list_free(&orig_node->frag_list); } spin_unlock_bh(list_lock); } - gw_node_purge(bat_priv); - gw_election(bat_priv); + batadv_gw_node_purge(bat_priv); + batadv_gw_election(bat_priv); } -static void purge_orig(struct work_struct *work) +static void batadv_purge_orig(struct work_struct *work) { - struct delayed_work *delayed_work = - container_of(work, struct delayed_work, work); - struct bat_priv *bat_priv = - container_of(delayed_work, struct bat_priv, orig_work); + struct delayed_work *delayed_work; + struct batadv_priv *bat_priv; - _purge_orig(bat_priv); - start_purge_timer(bat_priv); + delayed_work = container_of(work, struct delayed_work, work); + bat_priv = container_of(delayed_work, struct batadv_priv, orig_work); + _batadv_purge_orig(bat_priv); + batadv_start_purge_timer(bat_priv); } -void purge_orig_ref(struct bat_priv *bat_priv) +void batadv_purge_orig_ref(struct batadv_priv *bat_priv) { - _purge_orig(bat_priv); + _batadv_purge_orig(bat_priv); } -int orig_seq_print_text(struct seq_file *seq, void *offset) +int batadv_orig_seq_print_text(struct seq_file *seq, void *offset) { struct net_device *net_dev = (struct net_device *)seq->private; - struct bat_priv *bat_priv = netdev_priv(net_dev); - struct hashtable_t *hash = bat_priv->orig_hash; + struct batadv_priv *bat_priv = netdev_priv(net_dev); + struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_node *node, *node_tmp; struct hlist_head *head; - struct hard_iface *primary_if; - struct orig_node *orig_node; - struct neigh_node *neigh_node, *neigh_node_tmp; + struct batadv_hard_iface *primary_if; + struct batadv_orig_node *orig_node; + struct batadv_neigh_node *neigh_node, *neigh_node_tmp; int batman_count = 0; int last_seen_secs; int last_seen_msecs; + unsigned long last_seen_jiffies; uint32_t i; int ret = 0; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) { ret = seq_printf(seq, @@ -419,7 +426,7 @@ int orig_seq_print_text(struct seq_file *seq, void *offset) goto out; } - if (primary_if->if_status != IF_ACTIVE) { + if (primary_if->if_status != BATADV_IF_ACTIVE) { ret = seq_printf(seq, "BATMAN mesh %s disabled - primary interface not active\n", net_dev->name); @@ -427,28 +434,28 @@ int orig_seq_print_text(struct seq_file *seq, void *offset) } seq_printf(seq, "[B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s)]\n", - SOURCE_VERSION, primary_if->net_dev->name, + BATADV_SOURCE_VERSION, primary_if->net_dev->name, primary_if->net_dev->dev_addr, net_dev->name); seq_printf(seq, " %-15s %s (%s/%i) %17s [%10s]: %20s ...\n", - "Originator", "last-seen", "#", TQ_MAX_VALUE, "Nexthop", - "outgoingIF", "Potential nexthops"); + "Originator", "last-seen", "#", BATADV_TQ_MAX_VALUE, + "Nexthop", "outgoingIF", "Potential nexthops"); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { - neigh_node = orig_node_get_router(orig_node); + neigh_node = batadv_orig_node_get_router(orig_node); if (!neigh_node) continue; if (neigh_node->tq_avg == 0) goto next; - last_seen_secs = jiffies_to_msecs(jiffies - - orig_node->last_seen) / 1000; - last_seen_msecs = jiffies_to_msecs(jiffies - - orig_node->last_seen) % 1000; + last_seen_jiffies = jiffies - orig_node->last_seen; + last_seen_msecs = jiffies_to_msecs(last_seen_jiffies); + last_seen_secs = last_seen_msecs / 1000; + last_seen_msecs = last_seen_msecs % 1000; seq_printf(seq, "%pM %4i.%03is (%3i) %pM [%10s]:", orig_node->orig, last_seen_secs, @@ -467,7 +474,7 @@ int orig_seq_print_text(struct seq_file *seq, void *offset) batman_count++; next: - neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref(neigh_node); } rcu_read_unlock(); } @@ -477,27 +484,29 @@ next: out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); return ret; } -static int orig_node_add_if(struct orig_node *orig_node, int max_if_num) +static int batadv_orig_node_add_if(struct batadv_orig_node *orig_node, + int max_if_num) { void *data_ptr; + size_t data_size, old_size; - data_ptr = kmalloc(max_if_num * sizeof(unsigned long) * NUM_WORDS, - GFP_ATOMIC); + data_size = max_if_num * sizeof(unsigned long) * BATADV_NUM_WORDS; + old_size = (max_if_num - 1) * sizeof(unsigned long) * BATADV_NUM_WORDS; + data_ptr = kmalloc(data_size, GFP_ATOMIC); if (!data_ptr) - return -1; + return -ENOMEM; - memcpy(data_ptr, orig_node->bcast_own, - (max_if_num - 1) * sizeof(unsigned long) * NUM_WORDS); + memcpy(data_ptr, orig_node->bcast_own, old_size); kfree(orig_node->bcast_own); orig_node->bcast_own = data_ptr; data_ptr = kmalloc(max_if_num * sizeof(uint8_t), GFP_ATOMIC); if (!data_ptr) - return -1; + return -ENOMEM; memcpy(data_ptr, orig_node->bcast_own_sum, (max_if_num - 1) * sizeof(uint8_t)); @@ -507,28 +516,30 @@ static int orig_node_add_if(struct orig_node *orig_node, int max_if_num) return 0; } -int orig_hash_add_if(struct hard_iface *hard_iface, int max_if_num) +int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, + int max_if_num) { - struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - struct hashtable_t *hash = bat_priv->orig_hash; + struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_node *node; struct hlist_head *head; - struct orig_node *orig_node; + struct batadv_orig_node *orig_node; uint32_t i; int ret; /* resize all orig nodes because orig_node->bcast_own(_sum) depend on - * if_num */ + * if_num + */ for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { spin_lock_bh(&orig_node->ogm_cnt_lock); - ret = orig_node_add_if(orig_node, max_if_num); + ret = batadv_orig_node_add_if(orig_node, max_if_num); spin_unlock_bh(&orig_node->ogm_cnt_lock); - if (ret == -1) + if (ret == -ENOMEM) goto err; } rcu_read_unlock(); @@ -541,8 +552,8 @@ err: return -ENOMEM; } -static int orig_node_del_if(struct orig_node *orig_node, - int max_if_num, int del_if_num) +static int batadv_orig_node_del_if(struct batadv_orig_node *orig_node, + int max_if_num, int del_if_num) { void *data_ptr = NULL; int chunk_size; @@ -551,10 +562,10 @@ static int orig_node_del_if(struct orig_node *orig_node, if (max_if_num == 0) goto free_bcast_own; - chunk_size = sizeof(unsigned long) * NUM_WORDS; + chunk_size = sizeof(unsigned long) * BATADV_NUM_WORDS; data_ptr = kmalloc(max_if_num * chunk_size, GFP_ATOMIC); if (!data_ptr) - return -1; + return -ENOMEM; /* copy first part */ memcpy(data_ptr, orig_node->bcast_own, del_if_num * chunk_size); @@ -573,7 +584,7 @@ free_bcast_own: data_ptr = kmalloc(max_if_num * sizeof(uint8_t), GFP_ATOMIC); if (!data_ptr) - return -1; + return -ENOMEM; memcpy(data_ptr, orig_node->bcast_own_sum, del_if_num * sizeof(uint8_t)); @@ -589,30 +600,32 @@ free_own_sum: return 0; } -int orig_hash_del_if(struct hard_iface *hard_iface, int max_if_num) +int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, + int max_if_num) { - struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - struct hashtable_t *hash = bat_priv->orig_hash; + struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_node *node; struct hlist_head *head; - struct hard_iface *hard_iface_tmp; - struct orig_node *orig_node; + struct batadv_hard_iface *hard_iface_tmp; + struct batadv_orig_node *orig_node; uint32_t i; int ret; /* resize all orig nodes because orig_node->bcast_own(_sum) depend on - * if_num */ + * if_num + */ for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { spin_lock_bh(&orig_node->ogm_cnt_lock); - ret = orig_node_del_if(orig_node, max_if_num, - hard_iface->if_num); + ret = batadv_orig_node_del_if(orig_node, max_if_num, + hard_iface->if_num); spin_unlock_bh(&orig_node->ogm_cnt_lock); - if (ret == -1) + if (ret == -ENOMEM) goto err; } rcu_read_unlock(); @@ -620,8 +633,8 @@ int orig_hash_del_if(struct hard_iface *hard_iface, int max_if_num) /* renumber remaining batman interfaces _inside_ of orig_hash_lock */ rcu_read_lock(); - list_for_each_entry_rcu(hard_iface_tmp, &hardif_list, list) { - if (hard_iface_tmp->if_status == IF_NOT_IN_USE) + list_for_each_entry_rcu(hard_iface_tmp, &batadv_hardif_list, list) { + if (hard_iface_tmp->if_status == BATADV_IF_NOT_IN_USE) continue; if (hard_iface == hard_iface_tmp) diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index f74d0d69335..9778e656dec 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_ORIGINATOR_H_ @@ -24,24 +22,29 @@ #include "hash.h" -int originator_init(struct bat_priv *bat_priv); -void originator_free(struct bat_priv *bat_priv); -void purge_orig_ref(struct bat_priv *bat_priv); -void orig_node_free_ref(struct orig_node *orig_node); -struct orig_node *get_orig_node(struct bat_priv *bat_priv, const uint8_t *addr); -struct neigh_node *batadv_neigh_node_new(struct hard_iface *hard_iface, - const uint8_t *neigh_addr, - uint32_t seqno); -void neigh_node_free_ref(struct neigh_node *neigh_node); -struct neigh_node *orig_node_get_router(struct orig_node *orig_node); -int orig_seq_print_text(struct seq_file *seq, void *offset); -int orig_hash_add_if(struct hard_iface *hard_iface, int max_if_num); -int orig_hash_del_if(struct hard_iface *hard_iface, int max_if_num); - - -/* hashfunction to choose an entry in a hash table of given size */ -/* hash algorithm from http://en.wikipedia.org/wiki/Hash_table */ -static inline uint32_t choose_orig(const void *data, uint32_t size) +int batadv_originator_init(struct batadv_priv *bat_priv); +void batadv_originator_free(struct batadv_priv *bat_priv); +void batadv_purge_orig_ref(struct batadv_priv *bat_priv); +void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node); +struct batadv_orig_node *batadv_get_orig_node(struct batadv_priv *bat_priv, + const uint8_t *addr); +struct batadv_neigh_node * +batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, + const uint8_t *neigh_addr, uint32_t seqno); +void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node); +struct batadv_neigh_node * +batadv_orig_node_get_router(struct batadv_orig_node *orig_node); +int batadv_orig_seq_print_text(struct seq_file *seq, void *offset); +int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, + int max_if_num); +int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, + int max_if_num); + + +/* hashfunction to choose an entry in a hash table of given size + * hash algorithm from http://en.wikipedia.org/wiki/Hash_table + */ +static inline uint32_t batadv_choose_orig(const void *data, uint32_t size) { const unsigned char *key = data; uint32_t hash = 0; @@ -60,24 +63,24 @@ static inline uint32_t choose_orig(const void *data, uint32_t size) return hash % size; } -static inline struct orig_node *orig_hash_find(struct bat_priv *bat_priv, - const void *data) +static inline struct batadv_orig_node * +batadv_orig_hash_find(struct batadv_priv *bat_priv, const void *data) { - struct hashtable_t *hash = bat_priv->orig_hash; + struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_head *head; struct hlist_node *node; - struct orig_node *orig_node, *orig_node_tmp = NULL; + struct batadv_orig_node *orig_node, *orig_node_tmp = NULL; int index; if (!hash) return NULL; - index = choose_orig(data, hash->size); + index = batadv_choose_orig(data, hash->size); head = &hash->table[index]; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { - if (!compare_eth(orig_node, data)) + if (!batadv_compare_eth(orig_node, data)) continue; if (!atomic_inc_not_zero(&orig_node->refcount)) diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index 0ee1af77079..8d3e55a96ad 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -16,171 +15,172 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_PACKET_H_ #define _NET_BATMAN_ADV_PACKET_H_ -#define ETH_P_BATMAN 0x4305 /* unofficial/not registered Ethertype */ - -enum bat_packettype { - BAT_IV_OGM = 0x01, - BAT_ICMP = 0x02, - BAT_UNICAST = 0x03, - BAT_BCAST = 0x04, - BAT_VIS = 0x05, - BAT_UNICAST_FRAG = 0x06, - BAT_TT_QUERY = 0x07, - BAT_ROAM_ADV = 0x08 +#define BATADV_ETH_P_BATMAN 0x4305 /* unofficial/not registered Ethertype */ + +enum batadv_packettype { + BATADV_IV_OGM = 0x01, + BATADV_ICMP = 0x02, + BATADV_UNICAST = 0x03, + BATADV_BCAST = 0x04, + BATADV_VIS = 0x05, + BATADV_UNICAST_FRAG = 0x06, + BATADV_TT_QUERY = 0x07, + BATADV_ROAM_ADV = 0x08, }; /* this file is included by batctl which needs these defines */ -#define COMPAT_VERSION 14 +#define BATADV_COMPAT_VERSION 14 -enum batman_iv_flags { - NOT_BEST_NEXT_HOP = 1 << 3, - PRIMARIES_FIRST_HOP = 1 << 4, - VIS_SERVER = 1 << 5, - DIRECTLINK = 1 << 6 +enum batadv_iv_flags { + BATADV_NOT_BEST_NEXT_HOP = 1 << 3, + BATADV_PRIMARIES_FIRST_HOP = 1 << 4, + BATADV_VIS_SERVER = 1 << 5, + BATADV_DIRECTLINK = 1 << 6, }; /* ICMP message types */ -enum icmp_packettype { - ECHO_REPLY = 0, - DESTINATION_UNREACHABLE = 3, - ECHO_REQUEST = 8, - TTL_EXCEEDED = 11, - PARAMETER_PROBLEM = 12 +enum batadv_icmp_packettype { + BATADV_ECHO_REPLY = 0, + BATADV_DESTINATION_UNREACHABLE = 3, + BATADV_ECHO_REQUEST = 8, + BATADV_TTL_EXCEEDED = 11, + BATADV_PARAMETER_PROBLEM = 12, }; /* vis defines */ -enum vis_packettype { - VIS_TYPE_SERVER_SYNC = 0, - VIS_TYPE_CLIENT_UPDATE = 1 +enum batadv_vis_packettype { + BATADV_VIS_TYPE_SERVER_SYNC = 0, + BATADV_VIS_TYPE_CLIENT_UPDATE = 1, }; /* fragmentation defines */ -enum unicast_frag_flags { - UNI_FRAG_HEAD = 1 << 0, - UNI_FRAG_LARGETAIL = 1 << 1 +enum batadv_unicast_frag_flags { + BATADV_UNI_FRAG_HEAD = 1 << 0, + BATADV_UNI_FRAG_LARGETAIL = 1 << 1, }; /* TT_QUERY subtypes */ -#define TT_QUERY_TYPE_MASK 0x3 +#define BATADV_TT_QUERY_TYPE_MASK 0x3 -enum tt_query_packettype { - TT_REQUEST = 0, - TT_RESPONSE = 1 +enum batadv_tt_query_packettype { + BATADV_TT_REQUEST = 0, + BATADV_TT_RESPONSE = 1, }; /* TT_QUERY flags */ -enum tt_query_flags { - TT_FULL_TABLE = 1 << 2 +enum batadv_tt_query_flags { + BATADV_TT_FULL_TABLE = 1 << 2, }; -/* TT_CLIENT flags. +/* BATADV_TT_CLIENT flags. * Flags from 1 to 1 << 7 are sent on the wire, while flags from 1 << 8 to - * 1 << 15 are used for local computation only */ -enum tt_client_flags { - TT_CLIENT_DEL = 1 << 0, - TT_CLIENT_ROAM = 1 << 1, - TT_CLIENT_WIFI = 1 << 2, - TT_CLIENT_NOPURGE = 1 << 8, - TT_CLIENT_NEW = 1 << 9, - TT_CLIENT_PENDING = 1 << 10 + * 1 << 15 are used for local computation only + */ +enum batadv_tt_client_flags { + BATADV_TT_CLIENT_DEL = 1 << 0, + BATADV_TT_CLIENT_ROAM = 1 << 1, + BATADV_TT_CLIENT_WIFI = 1 << 2, + BATADV_TT_CLIENT_NOPURGE = 1 << 8, + BATADV_TT_CLIENT_NEW = 1 << 9, + BATADV_TT_CLIENT_PENDING = 1 << 10, }; /* claim frame types for the bridge loop avoidance */ -enum bla_claimframe { - CLAIM_TYPE_ADD = 0x00, - CLAIM_TYPE_DEL = 0x01, - CLAIM_TYPE_ANNOUNCE = 0x02, - CLAIM_TYPE_REQUEST = 0x03 +enum batadv_bla_claimframe { + BATADV_CLAIM_TYPE_ADD = 0x00, + BATADV_CLAIM_TYPE_DEL = 0x01, + BATADV_CLAIM_TYPE_ANNOUNCE = 0x02, + BATADV_CLAIM_TYPE_REQUEST = 0x03, }; /* the destination hardware field in the ARP frame is used to * transport the claim type and the group id */ -struct bla_claim_dst { +struct batadv_bla_claim_dst { uint8_t magic[3]; /* FF:43:05 */ uint8_t type; /* bla_claimframe */ - uint16_t group; /* group id */ + __be16 group; /* group id */ } __packed; -struct batman_header { +struct batadv_header { uint8_t packet_type; uint8_t version; /* batman version field */ uint8_t ttl; } __packed; -struct batman_ogm_packet { - struct batman_header header; +struct batadv_ogm_packet { + struct batadv_header header; uint8_t flags; /* 0x40: DIRECTLINK flag, 0x20 VIS_SERVER flag... */ - uint32_t seqno; + __be32 seqno; uint8_t orig[ETH_ALEN]; uint8_t prev_sender[ETH_ALEN]; uint8_t gw_flags; /* flags related to gateway class */ uint8_t tq; uint8_t tt_num_changes; uint8_t ttvn; /* translation table version number */ - uint16_t tt_crc; + __be16 tt_crc; } __packed; -#define BATMAN_OGM_HLEN sizeof(struct batman_ogm_packet) +#define BATADV_OGM_HLEN sizeof(struct batadv_ogm_packet) -struct icmp_packet { - struct batman_header header; +struct batadv_icmp_packet { + struct batadv_header header; uint8_t msg_type; /* see ICMP message types above */ uint8_t dst[ETH_ALEN]; uint8_t orig[ETH_ALEN]; - uint16_t seqno; + __be16 seqno; uint8_t uid; uint8_t reserved; } __packed; -#define BAT_RR_LEN 16 +#define BATADV_RR_LEN 16 /* icmp_packet_rr must start with all fields from imcp_packet - * as this is assumed by code that handles ICMP packets */ -struct icmp_packet_rr { - struct batman_header header; + * as this is assumed by code that handles ICMP packets + */ +struct batadv_icmp_packet_rr { + struct batadv_header header; uint8_t msg_type; /* see ICMP message types above */ uint8_t dst[ETH_ALEN]; uint8_t orig[ETH_ALEN]; - uint16_t seqno; + __be16 seqno; uint8_t uid; uint8_t rr_cur; - uint8_t rr[BAT_RR_LEN][ETH_ALEN]; + uint8_t rr[BATADV_RR_LEN][ETH_ALEN]; } __packed; -struct unicast_packet { - struct batman_header header; +struct batadv_unicast_packet { + struct batadv_header header; uint8_t ttvn; /* destination translation table version number */ uint8_t dest[ETH_ALEN]; } __packed; -struct unicast_frag_packet { - struct batman_header header; +struct batadv_unicast_frag_packet { + struct batadv_header header; uint8_t ttvn; /* destination translation table version number */ uint8_t dest[ETH_ALEN]; uint8_t flags; uint8_t align; uint8_t orig[ETH_ALEN]; - uint16_t seqno; + __be16 seqno; } __packed; -struct bcast_packet { - struct batman_header header; +struct batadv_bcast_packet { + struct batadv_header header; uint8_t reserved; - uint32_t seqno; + __be32 seqno; uint8_t orig[ETH_ALEN]; } __packed; -struct vis_packet { - struct batman_header header; +struct batadv_vis_packet { + struct batadv_header header; uint8_t vis_type; /* which type of vis-participant sent this? */ - uint32_t seqno; /* sequence number */ + __be32 seqno; /* sequence number */ uint8_t entries; /* number of entries behind this struct */ uint8_t reserved; uint8_t vis_orig[ETH_ALEN]; /* originator reporting its neighbors */ @@ -188,11 +188,12 @@ struct vis_packet { uint8_t sender_orig[ETH_ALEN]; /* who sent or forwarded this packet */ } __packed; -struct tt_query_packet { - struct batman_header header; +struct batadv_tt_query_packet { + struct batadv_header header; /* the flag field is a combination of: * - TT_REQUEST or TT_RESPONSE - * - TT_FULL_TABLE */ + * - TT_FULL_TABLE + */ uint8_t flags; uint8_t dst[ETH_ALEN]; uint8_t src[ETH_ALEN]; @@ -200,24 +201,26 @@ struct tt_query_packet { * if TT_REQUEST: ttvn that triggered the * request * if TT_RESPONSE: new ttvn for the src - * orig_node */ + * orig_node + */ uint8_t ttvn; /* tt_data field is: * if TT_REQUEST: crc associated with the * ttvn - * if TT_RESPONSE: table_size */ - uint16_t tt_data; + * if TT_RESPONSE: table_size + */ + __be16 tt_data; } __packed; -struct roam_adv_packet { - struct batman_header header; +struct batadv_roam_adv_packet { + struct batadv_header header; uint8_t reserved; uint8_t dst[ETH_ALEN]; uint8_t src[ETH_ALEN]; uint8_t client[ETH_ALEN]; } __packed; -struct tt_change { +struct batadv_tt_change { uint8_t flags; uint8_t addr[ETH_ALEN]; } __packed; diff --git a/net/batman-adv/ring_buffer.c b/net/batman-adv/ring_buffer.c index fd63951d118..c8f61e395b7 100644 --- a/net/batman-adv/ring_buffer.c +++ b/net/batman-adv/ring_buffer.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -16,26 +15,26 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" #include "ring_buffer.h" -void ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index, uint8_t value) +void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index, + uint8_t value) { lq_recv[*lq_index] = value; - *lq_index = (*lq_index + 1) % TQ_GLOBAL_WINDOW_SIZE; + *lq_index = (*lq_index + 1) % BATADV_TQ_GLOBAL_WINDOW_SIZE; } -uint8_t ring_buffer_avg(const uint8_t lq_recv[]) +uint8_t batadv_ring_buffer_avg(const uint8_t lq_recv[]) { const uint8_t *ptr; uint16_t count = 0, i = 0, sum = 0; ptr = lq_recv; - while (i < TQ_GLOBAL_WINDOW_SIZE) { + while (i < BATADV_TQ_GLOBAL_WINDOW_SIZE) { if (*ptr != 0) { count++; sum += *ptr; diff --git a/net/batman-adv/ring_buffer.h b/net/batman-adv/ring_buffer.h index 8b58bd82767..fda8c17df27 100644 --- a/net/batman-adv/ring_buffer.h +++ b/net/batman-adv/ring_buffer.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -16,13 +15,13 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_RING_BUFFER_H_ #define _NET_BATMAN_ADV_RING_BUFFER_H_ -void ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index, uint8_t value); -uint8_t ring_buffer_avg(const uint8_t lq_recv[]); +void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index, + uint8_t value); +uint8_t batadv_ring_buffer_avg(const uint8_t lq_recv[]); #endif /* _NET_BATMAN_ADV_RING_BUFFER_H_ */ diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 015471d801b..bc2b88bbea1 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" @@ -31,19 +29,20 @@ #include "unicast.h" #include "bridge_loop_avoidance.h" -static int route_unicast_packet(struct sk_buff *skb, - struct hard_iface *recv_if); +static int batadv_route_unicast_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if); -void slide_own_bcast_window(struct hard_iface *hard_iface) +void batadv_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) { - struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - struct hashtable_t *hash = bat_priv->orig_hash; + struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_node *node; struct hlist_head *head; - struct orig_node *orig_node; + struct batadv_orig_node *orig_node; unsigned long *word; uint32_t i; size_t word_index; + uint8_t *w; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -51,49 +50,49 @@ void slide_own_bcast_window(struct hard_iface *hard_iface) rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { spin_lock_bh(&orig_node->ogm_cnt_lock); - word_index = hard_iface->if_num * NUM_WORDS; + word_index = hard_iface->if_num * BATADV_NUM_WORDS; word = &(orig_node->bcast_own[word_index]); - bit_get_packet(bat_priv, word, 1, 0); - orig_node->bcast_own_sum[hard_iface->if_num] = - bitmap_weight(word, TQ_LOCAL_WINDOW_SIZE); + batadv_bit_get_packet(bat_priv, word, 1, 0); + w = &orig_node->bcast_own_sum[hard_iface->if_num]; + *w = bitmap_weight(word, BATADV_TQ_LOCAL_WINDOW_SIZE); spin_unlock_bh(&orig_node->ogm_cnt_lock); } rcu_read_unlock(); } } -static void _update_route(struct bat_priv *bat_priv, - struct orig_node *orig_node, - struct neigh_node *neigh_node) +static void _batadv_update_route(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + struct batadv_neigh_node *neigh_node) { - struct neigh_node *curr_router; + struct batadv_neigh_node *curr_router; - curr_router = orig_node_get_router(orig_node); + curr_router = batadv_orig_node_get_router(orig_node); /* route deleted */ if ((curr_router) && (!neigh_node)) { - bat_dbg(DBG_ROUTES, bat_priv, "Deleting route towards: %pM\n", - orig_node->orig); - tt_global_del_orig(bat_priv, orig_node, - "Deleted route towards originator"); + batadv_dbg(BATADV_DBG_ROUTES, bat_priv, + "Deleting route towards: %pM\n", orig_node->orig); + batadv_tt_global_del_orig(bat_priv, orig_node, + "Deleted route towards originator"); /* route added */ } else if ((!curr_router) && (neigh_node)) { - bat_dbg(DBG_ROUTES, bat_priv, - "Adding route towards: %pM (via %pM)\n", - orig_node->orig, neigh_node->addr); + batadv_dbg(BATADV_DBG_ROUTES, bat_priv, + "Adding route towards: %pM (via %pM)\n", + orig_node->orig, neigh_node->addr); /* route changed */ } else if (neigh_node && curr_router) { - bat_dbg(DBG_ROUTES, bat_priv, - "Changing route towards: %pM (now via %pM - was via %pM)\n", - orig_node->orig, neigh_node->addr, - curr_router->addr); + batadv_dbg(BATADV_DBG_ROUTES, bat_priv, + "Changing route towards: %pM (now via %pM - was via %pM)\n", + orig_node->orig, neigh_node->addr, + curr_router->addr); } if (curr_router) - neigh_node_free_ref(curr_router); + batadv_neigh_node_free_ref(curr_router); /* increase refcount of new best neighbor */ if (neigh_node && !atomic_inc_not_zero(&neigh_node->refcount)) @@ -105,30 +104,31 @@ static void _update_route(struct bat_priv *bat_priv, /* decrease refcount of previous best neighbor */ if (curr_router) - neigh_node_free_ref(curr_router); + batadv_neigh_node_free_ref(curr_router); } -void update_route(struct bat_priv *bat_priv, struct orig_node *orig_node, - struct neigh_node *neigh_node) +void batadv_update_route(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + struct batadv_neigh_node *neigh_node) { - struct neigh_node *router = NULL; + struct batadv_neigh_node *router = NULL; if (!orig_node) goto out; - router = orig_node_get_router(orig_node); + router = batadv_orig_node_get_router(orig_node); if (router != neigh_node) - _update_route(bat_priv, orig_node, neigh_node); + _batadv_update_route(bat_priv, orig_node, neigh_node); out: if (router) - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); } /* caller must hold the neigh_list_lock */ -void bonding_candidate_del(struct orig_node *orig_node, - struct neigh_node *neigh_node) +void batadv_bonding_candidate_del(struct batadv_orig_node *orig_node, + struct batadv_neigh_node *neigh_node) { /* this neighbor is not part of our candidate list */ if (list_empty(&neigh_node->bonding_list)) @@ -136,37 +136,36 @@ void bonding_candidate_del(struct orig_node *orig_node, list_del_rcu(&neigh_node->bonding_list); INIT_LIST_HEAD(&neigh_node->bonding_list); - neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref(neigh_node); atomic_dec(&orig_node->bond_candidates); out: return; } -void bonding_candidate_add(struct orig_node *orig_node, - struct neigh_node *neigh_node) +void batadv_bonding_candidate_add(struct batadv_orig_node *orig_node, + struct batadv_neigh_node *neigh_node) { struct hlist_node *node; - struct neigh_node *tmp_neigh_node, *router = NULL; + struct batadv_neigh_node *tmp_neigh_node, *router = NULL; uint8_t interference_candidate = 0; spin_lock_bh(&orig_node->neigh_list_lock); /* only consider if it has the same primary address ... */ - if (!compare_eth(orig_node->orig, - neigh_node->orig_node->primary_addr)) + if (!batadv_compare_eth(orig_node->orig, + neigh_node->orig_node->primary_addr)) goto candidate_del; - router = orig_node_get_router(orig_node); + router = batadv_orig_node_get_router(orig_node); if (!router) goto candidate_del; /* ... and is good enough to be considered */ - if (neigh_node->tq_avg < router->tq_avg - BONDING_TQ_THRESHOLD) + if (neigh_node->tq_avg < router->tq_avg - BATADV_BONDING_TQ_THRESHOLD) goto candidate_del; - /** - * check if we have another candidate with the same mac address or + /* check if we have another candidate with the same mac address or * interface. If we do, we won't select this candidate because of * possible interference. */ @@ -177,12 +176,14 @@ void bonding_candidate_add(struct orig_node *orig_node, continue; /* we only care if the other candidate is even - * considered as candidate. */ + * considered as candidate. + */ if (list_empty(&tmp_neigh_node->bonding_list)) continue; if ((neigh_node->if_incoming == tmp_neigh_node->if_incoming) || - (compare_eth(neigh_node->addr, tmp_neigh_node->addr))) { + (batadv_compare_eth(neigh_node->addr, + tmp_neigh_node->addr))) { interference_candidate = 1; break; } @@ -204,21 +205,22 @@ void bonding_candidate_add(struct orig_node *orig_node, goto out; candidate_del: - bonding_candidate_del(orig_node, neigh_node); + batadv_bonding_candidate_del(orig_node, neigh_node); out: spin_unlock_bh(&orig_node->neigh_list_lock); if (router) - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); } /* copy primary address for bonding */ -void bonding_save_primary(const struct orig_node *orig_node, - struct orig_node *orig_neigh_node, - const struct batman_ogm_packet *batman_ogm_packet) +void +batadv_bonding_save_primary(const struct batadv_orig_node *orig_node, + struct batadv_orig_node *orig_neigh_node, + const struct batadv_ogm_packet *batman_ogm_packet) { - if (!(batman_ogm_packet->flags & PRIMARIES_FIRST_HOP)) + if (!(batman_ogm_packet->flags & BATADV_PRIMARIES_FIRST_HOP)) return; memcpy(orig_neigh_node->primary_addr, orig_node->orig, ETH_ALEN); @@ -229,25 +231,26 @@ void bonding_save_primary(const struct orig_node *orig_node, * 0 if the packet is to be accepted * 1 if the packet is to be ignored. */ -int window_protected(struct bat_priv *bat_priv, int32_t seq_num_diff, - unsigned long *last_reset) +int batadv_window_protected(struct batadv_priv *bat_priv, int32_t seq_num_diff, + unsigned long *last_reset) { - if ((seq_num_diff <= -TQ_LOCAL_WINDOW_SIZE) || - (seq_num_diff >= EXPECTED_SEQNO_RANGE)) { - if (!has_timed_out(*last_reset, RESET_PROTECTION_MS)) + if (seq_num_diff <= -BATADV_TQ_LOCAL_WINDOW_SIZE || + seq_num_diff >= BATADV_EXPECTED_SEQNO_RANGE) { + if (!batadv_has_timed_out(*last_reset, + BATADV_RESET_PROTECTION_MS)) return 1; *last_reset = jiffies; - bat_dbg(DBG_BATMAN, bat_priv, - "old packet received, start protection\n"); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "old packet received, start protection\n"); } return 0; } -bool check_management_packet(struct sk_buff *skb, - struct hard_iface *hard_iface, - int header_len) +bool batadv_check_management_packet(struct sk_buff *skb, + struct batadv_hard_iface *hard_iface, + int header_len) { struct ethhdr *ethhdr; @@ -276,34 +279,34 @@ bool check_management_packet(struct sk_buff *skb, return true; } -static int recv_my_icmp_packet(struct bat_priv *bat_priv, - struct sk_buff *skb, size_t icmp_len) +static int batadv_recv_my_icmp_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, size_t icmp_len) { - struct hard_iface *primary_if = NULL; - struct orig_node *orig_node = NULL; - struct neigh_node *router = NULL; - struct icmp_packet_rr *icmp_packet; + struct batadv_hard_iface *primary_if = NULL; + struct batadv_orig_node *orig_node = NULL; + struct batadv_neigh_node *router = NULL; + struct batadv_icmp_packet_rr *icmp_packet; int ret = NET_RX_DROP; - icmp_packet = (struct icmp_packet_rr *)skb->data; + icmp_packet = (struct batadv_icmp_packet_rr *)skb->data; /* add data to device queue */ - if (icmp_packet->msg_type != ECHO_REQUEST) { - bat_socket_receive_packet(icmp_packet, icmp_len); + if (icmp_packet->msg_type != BATADV_ECHO_REQUEST) { + batadv_socket_receive_packet(icmp_packet, icmp_len); goto out; } - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; /* answer echo request (ping) */ /* get routing information */ - orig_node = orig_hash_find(bat_priv, icmp_packet->orig); + orig_node = batadv_orig_hash_find(bat_priv, icmp_packet->orig); if (!orig_node) goto out; - router = orig_node_get_router(orig_node); + router = batadv_orig_node_get_router(orig_node); if (!router) goto out; @@ -311,54 +314,54 @@ static int recv_my_icmp_packet(struct bat_priv *bat_priv, if (skb_cow(skb, ETH_HLEN) < 0) goto out; - icmp_packet = (struct icmp_packet_rr *)skb->data; + icmp_packet = (struct batadv_icmp_packet_rr *)skb->data; memcpy(icmp_packet->dst, icmp_packet->orig, ETH_ALEN); memcpy(icmp_packet->orig, primary_if->net_dev->dev_addr, ETH_ALEN); - icmp_packet->msg_type = ECHO_REPLY; - icmp_packet->header.ttl = TTL; + icmp_packet->msg_type = BATADV_ECHO_REPLY; + icmp_packet->header.ttl = BATADV_TTL; - send_skb_packet(skb, router->if_incoming, router->addr); + batadv_send_skb_packet(skb, router->if_incoming, router->addr); ret = NET_RX_SUCCESS; out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); if (router) - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); if (orig_node) - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); return ret; } -static int recv_icmp_ttl_exceeded(struct bat_priv *bat_priv, - struct sk_buff *skb) +static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv, + struct sk_buff *skb) { - struct hard_iface *primary_if = NULL; - struct orig_node *orig_node = NULL; - struct neigh_node *router = NULL; - struct icmp_packet *icmp_packet; + struct batadv_hard_iface *primary_if = NULL; + struct batadv_orig_node *orig_node = NULL; + struct batadv_neigh_node *router = NULL; + struct batadv_icmp_packet *icmp_packet; int ret = NET_RX_DROP; - icmp_packet = (struct icmp_packet *)skb->data; + icmp_packet = (struct batadv_icmp_packet *)skb->data; /* send TTL exceeded if packet is an echo request (traceroute) */ - if (icmp_packet->msg_type != ECHO_REQUEST) { + if (icmp_packet->msg_type != BATADV_ECHO_REQUEST) { pr_debug("Warning - can't forward icmp packet from %pM to %pM: ttl exceeded\n", icmp_packet->orig, icmp_packet->dst); goto out; } - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; /* get routing information */ - orig_node = orig_hash_find(bat_priv, icmp_packet->orig); + orig_node = batadv_orig_hash_find(bat_priv, icmp_packet->orig); if (!orig_node) goto out; - router = orig_node_get_router(orig_node); + router = batadv_orig_node_get_router(orig_node); if (!router) goto out; @@ -366,42 +369,41 @@ static int recv_icmp_ttl_exceeded(struct bat_priv *bat_priv, if (skb_cow(skb, ETH_HLEN) < 0) goto out; - icmp_packet = (struct icmp_packet *)skb->data; + icmp_packet = (struct batadv_icmp_packet *)skb->data; memcpy(icmp_packet->dst, icmp_packet->orig, ETH_ALEN); memcpy(icmp_packet->orig, primary_if->net_dev->dev_addr, ETH_ALEN); - icmp_packet->msg_type = TTL_EXCEEDED; - icmp_packet->header.ttl = TTL; + icmp_packet->msg_type = BATADV_TTL_EXCEEDED; + icmp_packet->header.ttl = BATADV_TTL; - send_skb_packet(skb, router->if_incoming, router->addr); + batadv_send_skb_packet(skb, router->if_incoming, router->addr); ret = NET_RX_SUCCESS; out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); if (router) - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); if (orig_node) - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); return ret; } -int recv_icmp_packet(struct sk_buff *skb, struct hard_iface *recv_if) +int batadv_recv_icmp_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if) { - struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface); - struct icmp_packet_rr *icmp_packet; + struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); + struct batadv_icmp_packet_rr *icmp_packet; struct ethhdr *ethhdr; - struct orig_node *orig_node = NULL; - struct neigh_node *router = NULL; - int hdr_size = sizeof(struct icmp_packet); + struct batadv_orig_node *orig_node = NULL; + struct batadv_neigh_node *router = NULL; + int hdr_size = sizeof(struct batadv_icmp_packet); int ret = NET_RX_DROP; - /** - * we truncate all incoming icmp packets if they don't match our size - */ - if (skb->len >= sizeof(struct icmp_packet_rr)) - hdr_size = sizeof(struct icmp_packet_rr); + /* we truncate all incoming icmp packets if they don't match our size */ + if (skb->len >= sizeof(struct batadv_icmp_packet_rr)) + hdr_size = sizeof(struct batadv_icmp_packet_rr); /* drop packet if it has not necessary minimum size */ if (unlikely(!pskb_may_pull(skb, hdr_size))) @@ -418,33 +420,33 @@ int recv_icmp_packet(struct sk_buff *skb, struct hard_iface *recv_if) goto out; /* not for me */ - if (!is_my_mac(ethhdr->h_dest)) + if (!batadv_is_my_mac(ethhdr->h_dest)) goto out; - icmp_packet = (struct icmp_packet_rr *)skb->data; + icmp_packet = (struct batadv_icmp_packet_rr *)skb->data; /* add record route information if not full */ - if ((hdr_size == sizeof(struct icmp_packet_rr)) && - (icmp_packet->rr_cur < BAT_RR_LEN)) { + if ((hdr_size == sizeof(struct batadv_icmp_packet_rr)) && + (icmp_packet->rr_cur < BATADV_RR_LEN)) { memcpy(&(icmp_packet->rr[icmp_packet->rr_cur]), ethhdr->h_dest, ETH_ALEN); icmp_packet->rr_cur++; } /* packet for me */ - if (is_my_mac(icmp_packet->dst)) - return recv_my_icmp_packet(bat_priv, skb, hdr_size); + if (batadv_is_my_mac(icmp_packet->dst)) + return batadv_recv_my_icmp_packet(bat_priv, skb, hdr_size); /* TTL exceeded */ if (icmp_packet->header.ttl < 2) - return recv_icmp_ttl_exceeded(bat_priv, skb); + return batadv_recv_icmp_ttl_exceeded(bat_priv, skb); /* get routing information */ - orig_node = orig_hash_find(bat_priv, icmp_packet->dst); + orig_node = batadv_orig_hash_find(bat_priv, icmp_packet->dst); if (!orig_node) goto out; - router = orig_node_get_router(orig_node); + router = batadv_orig_node_get_router(orig_node); if (!router) goto out; @@ -452,20 +454,20 @@ int recv_icmp_packet(struct sk_buff *skb, struct hard_iface *recv_if) if (skb_cow(skb, ETH_HLEN) < 0) goto out; - icmp_packet = (struct icmp_packet_rr *)skb->data; + icmp_packet = (struct batadv_icmp_packet_rr *)skb->data; /* decrement ttl */ icmp_packet->header.ttl--; /* route it */ - send_skb_packet(skb, router->if_incoming, router->addr); + batadv_send_skb_packet(skb, router->if_incoming, router->addr); ret = NET_RX_SUCCESS; out: if (router) - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); if (orig_node) - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); return ret; } @@ -473,12 +475,14 @@ out: * robin fashion over the remaining interfaces. * * This method rotates the bonding list and increases the - * returned router's refcount. */ -static struct neigh_node *find_bond_router(struct orig_node *primary_orig, - const struct hard_iface *recv_if) + * returned router's refcount. + */ +static struct batadv_neigh_node * +batadv_find_bond_router(struct batadv_orig_node *primary_orig, + const struct batadv_hard_iface *recv_if) { - struct neigh_node *tmp_neigh_node; - struct neigh_node *router = NULL, *first_candidate = NULL; + struct batadv_neigh_node *tmp_neigh_node; + struct batadv_neigh_node *router = NULL, *first_candidate = NULL; rcu_read_lock(); list_for_each_entry_rcu(tmp_neigh_node, &primary_orig->bond_list, @@ -506,10 +510,12 @@ static struct neigh_node *find_bond_router(struct orig_node *primary_orig, goto out; /* selected should point to the next element - * after the current router */ + * after the current router + */ spin_lock_bh(&primary_orig->neigh_list_lock); /* this is a list_move(), which unfortunately - * does not exist as rcu version */ + * does not exist as rcu version + */ list_del_rcu(&primary_orig->bond_list); list_add_rcu(&primary_orig->bond_list, &router->bonding_list); @@ -524,12 +530,14 @@ out: * remaining candidates which are not using * this interface. * - * Increases the returned router's refcount */ -static struct neigh_node *find_ifalter_router(struct orig_node *primary_orig, - const struct hard_iface *recv_if) + * Increases the returned router's refcount + */ +static struct batadv_neigh_node * +batadv_find_ifalter_router(struct batadv_orig_node *primary_orig, + const struct batadv_hard_iface *recv_if) { - struct neigh_node *tmp_neigh_node; - struct neigh_node *router = NULL, *first_candidate = NULL; + struct batadv_neigh_node *tmp_neigh_node; + struct batadv_neigh_node *router = NULL, *first_candidate = NULL; rcu_read_lock(); list_for_each_entry_rcu(tmp_neigh_node, &primary_orig->bond_list, @@ -545,19 +553,21 @@ static struct neigh_node *find_ifalter_router(struct orig_node *primary_orig, continue; /* if we don't have a router yet - * or this one is better, choose it. */ + * or this one is better, choose it. + */ if ((!router) || (tmp_neigh_node->tq_avg > router->tq_avg)) { /* decrement refcount of - * previously selected router */ + * previously selected router + */ if (router) - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); router = tmp_neigh_node; atomic_inc_not_zero(&router->refcount); } - neigh_node_free_ref(tmp_neigh_node); + batadv_neigh_node_free_ref(tmp_neigh_node); } /* use the first candidate if nothing was found. */ @@ -569,19 +579,22 @@ static struct neigh_node *find_ifalter_router(struct orig_node *primary_orig, return router; } -int recv_tt_query(struct sk_buff *skb, struct hard_iface *recv_if) +int batadv_recv_tt_query(struct sk_buff *skb, struct batadv_hard_iface *recv_if) { - struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface); - struct tt_query_packet *tt_query; - uint16_t tt_len; + struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); + struct batadv_tt_query_packet *tt_query; + uint16_t tt_size; struct ethhdr *ethhdr; + char tt_flag; + size_t packet_size; /* drop packet if it has not necessary minimum size */ - if (unlikely(!pskb_may_pull(skb, sizeof(struct tt_query_packet)))) + if (unlikely(!pskb_may_pull(skb, + sizeof(struct batadv_tt_query_packet)))) goto out; /* I could need to modify it */ - if (skb_cow(skb, sizeof(struct tt_query_packet)) < 0) + if (skb_cow(skb, sizeof(struct batadv_tt_query_packet)) < 0) goto out; ethhdr = (struct ethhdr *)skb_mac_header(skb); @@ -594,47 +607,59 @@ int recv_tt_query(struct sk_buff *skb, struct hard_iface *recv_if) if (is_broadcast_ether_addr(ethhdr->h_source)) goto out; - tt_query = (struct tt_query_packet *)skb->data; + tt_query = (struct batadv_tt_query_packet *)skb->data; - tt_query->tt_data = ntohs(tt_query->tt_data); + switch (tt_query->flags & BATADV_TT_QUERY_TYPE_MASK) { + case BATADV_TT_REQUEST: + batadv_inc_counter(bat_priv, BATADV_CNT_TT_REQUEST_RX); - switch (tt_query->flags & TT_QUERY_TYPE_MASK) { - case TT_REQUEST: /* If we cannot provide an answer the tt_request is - * forwarded */ - if (!send_tt_response(bat_priv, tt_query)) { - bat_dbg(DBG_TT, bat_priv, - "Routing TT_REQUEST to %pM [%c]\n", - tt_query->dst, - (tt_query->flags & TT_FULL_TABLE ? 'F' : '.')); - tt_query->tt_data = htons(tt_query->tt_data); - return route_unicast_packet(skb, recv_if); + * forwarded + */ + if (!batadv_send_tt_response(bat_priv, tt_query)) { + if (tt_query->flags & BATADV_TT_FULL_TABLE) + tt_flag = 'F'; + else + tt_flag = '.'; + + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Routing TT_REQUEST to %pM [%c]\n", + tt_query->dst, + tt_flag); + return batadv_route_unicast_packet(skb, recv_if); } break; - case TT_RESPONSE: - if (is_my_mac(tt_query->dst)) { + case BATADV_TT_RESPONSE: + batadv_inc_counter(bat_priv, BATADV_CNT_TT_RESPONSE_RX); + + if (batadv_is_my_mac(tt_query->dst)) { /* packet needs to be linearized to access the TT - * changes */ + * changes + */ if (skb_linearize(skb) < 0) goto out; /* skb_linearize() possibly changed skb->data */ - tt_query = (struct tt_query_packet *)skb->data; + tt_query = (struct batadv_tt_query_packet *)skb->data; - tt_len = tt_query->tt_data * sizeof(struct tt_change); + tt_size = batadv_tt_len(ntohs(tt_query->tt_data)); /* Ensure we have all the claimed data */ - if (unlikely(skb_headlen(skb) < - sizeof(struct tt_query_packet) + tt_len)) + packet_size = sizeof(struct batadv_tt_query_packet); + packet_size += tt_size; + if (unlikely(skb_headlen(skb) < packet_size)) goto out; - handle_tt_response(bat_priv, tt_query); + batadv_handle_tt_response(bat_priv, tt_query); } else { - bat_dbg(DBG_TT, bat_priv, - "Routing TT_RESPONSE to %pM [%c]\n", - tt_query->dst, - (tt_query->flags & TT_FULL_TABLE ? 'F' : '.')); - tt_query->tt_data = htons(tt_query->tt_data); - return route_unicast_packet(skb, recv_if); + if (tt_query->flags & BATADV_TT_FULL_TABLE) + tt_flag = 'F'; + else + tt_flag = '.'; + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Routing TT_RESPONSE to %pM [%c]\n", + tt_query->dst, + tt_flag); + return batadv_route_unicast_packet(skb, recv_if); } break; } @@ -644,15 +669,16 @@ out: return NET_RX_DROP; } -int recv_roam_adv(struct sk_buff *skb, struct hard_iface *recv_if) +int batadv_recv_roam_adv(struct sk_buff *skb, struct batadv_hard_iface *recv_if) { - struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface); - struct roam_adv_packet *roam_adv_packet; - struct orig_node *orig_node; + struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); + struct batadv_roam_adv_packet *roam_adv_packet; + struct batadv_orig_node *orig_node; struct ethhdr *ethhdr; /* drop packet if it has not necessary minimum size */ - if (unlikely(!pskb_may_pull(skb, sizeof(struct roam_adv_packet)))) + if (unlikely(!pskb_may_pull(skb, + sizeof(struct batadv_roam_adv_packet)))) goto out; ethhdr = (struct ethhdr *)skb_mac_header(skb); @@ -665,35 +691,39 @@ int recv_roam_adv(struct sk_buff *skb, struct hard_iface *recv_if) if (is_broadcast_ether_addr(ethhdr->h_source)) goto out; - roam_adv_packet = (struct roam_adv_packet *)skb->data; + batadv_inc_counter(bat_priv, BATADV_CNT_TT_ROAM_ADV_RX); + + roam_adv_packet = (struct batadv_roam_adv_packet *)skb->data; - if (!is_my_mac(roam_adv_packet->dst)) - return route_unicast_packet(skb, recv_if); + if (!batadv_is_my_mac(roam_adv_packet->dst)) + return batadv_route_unicast_packet(skb, recv_if); /* check if it is a backbone gateway. we don't accept * roaming advertisement from it, as it has the same * entries as we have. */ - if (bla_is_backbone_gw_orig(bat_priv, roam_adv_packet->src)) + if (batadv_bla_is_backbone_gw_orig(bat_priv, roam_adv_packet->src)) goto out; - orig_node = orig_hash_find(bat_priv, roam_adv_packet->src); + orig_node = batadv_orig_hash_find(bat_priv, roam_adv_packet->src); if (!orig_node) goto out; - bat_dbg(DBG_TT, bat_priv, - "Received ROAMING_ADV from %pM (client %pM)\n", - roam_adv_packet->src, roam_adv_packet->client); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Received ROAMING_ADV from %pM (client %pM)\n", + roam_adv_packet->src, roam_adv_packet->client); - tt_global_add(bat_priv, orig_node, roam_adv_packet->client, - atomic_read(&orig_node->last_ttvn) + 1, true, false); + batadv_tt_global_add(bat_priv, orig_node, roam_adv_packet->client, + BATADV_TT_CLIENT_ROAM, + atomic_read(&orig_node->last_ttvn) + 1); /* Roaming phase starts: I have new information but the ttvn has not * been incremented yet. This flag will make me check all the incoming - * packets for the correct destination. */ + * packets for the correct destination. + */ bat_priv->tt_poss_change = true; - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); out: /* returning NET_RX_DROP will make the caller function kfree the skb */ return NET_RX_DROP; @@ -701,26 +731,30 @@ out: /* find a suitable router for this originator, and use * bonding if possible. increases the found neighbors - * refcount.*/ -struct neigh_node *find_router(struct bat_priv *bat_priv, - struct orig_node *orig_node, - const struct hard_iface *recv_if) + * refcount. + */ +struct batadv_neigh_node * +batadv_find_router(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + const struct batadv_hard_iface *recv_if) { - struct orig_node *primary_orig_node; - struct orig_node *router_orig; - struct neigh_node *router; + struct batadv_orig_node *primary_orig_node; + struct batadv_orig_node *router_orig; + struct batadv_neigh_node *router; static uint8_t zero_mac[ETH_ALEN] = {0, 0, 0, 0, 0, 0}; int bonding_enabled; + uint8_t *primary_addr; if (!orig_node) return NULL; - router = orig_node_get_router(orig_node); + router = batadv_orig_node_get_router(orig_node); if (!router) goto err; /* without bonding, the first node should - * always choose the default router. */ + * always choose the default router. + */ bonding_enabled = atomic_read(&bat_priv->bonding); rcu_read_lock(); @@ -732,43 +766,47 @@ struct neigh_node *find_router(struct bat_priv *bat_priv, if ((!recv_if) && (!bonding_enabled)) goto return_router; + primary_addr = router_orig->primary_addr; + /* if we have something in the primary_addr, we can search - * for a potential bonding candidate. */ - if (compare_eth(router_orig->primary_addr, zero_mac)) + * for a potential bonding candidate. + */ + if (batadv_compare_eth(primary_addr, zero_mac)) goto return_router; /* find the orig_node which has the primary interface. might - * even be the same as our router_orig in many cases */ - - if (compare_eth(router_orig->primary_addr, router_orig->orig)) { + * even be the same as our router_orig in many cases + */ + if (batadv_compare_eth(primary_addr, router_orig->orig)) { primary_orig_node = router_orig; } else { - primary_orig_node = orig_hash_find(bat_priv, - router_orig->primary_addr); + primary_orig_node = batadv_orig_hash_find(bat_priv, + primary_addr); if (!primary_orig_node) goto return_router; - orig_node_free_ref(primary_orig_node); + batadv_orig_node_free_ref(primary_orig_node); } /* with less than 2 candidates, we can't do any - * bonding and prefer the original router. */ + * bonding and prefer the original router. + */ if (atomic_read(&primary_orig_node->bond_candidates) < 2) goto return_router; /* all nodes between should choose a candidate which * is is not on the interface where the packet came - * in. */ - - neigh_node_free_ref(router); + * in. + */ + batadv_neigh_node_free_ref(router); if (bonding_enabled) - router = find_bond_router(primary_orig_node, recv_if); + router = batadv_find_bond_router(primary_orig_node, recv_if); else - router = find_ifalter_router(primary_orig_node, recv_if); + router = batadv_find_ifalter_router(primary_orig_node, recv_if); return_router: - if (router && router->if_incoming->if_status != IF_ACTIVE) + if (router && router->if_incoming->if_status != BATADV_IF_ACTIVE) goto err_unlock; rcu_read_unlock(); @@ -777,11 +815,11 @@ err_unlock: rcu_read_unlock(); err: if (router) - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); return NULL; } -static int check_unicast_packet(struct sk_buff *skb, int hdr_size) +static int batadv_check_unicast_packet(struct sk_buff *skb, int hdr_size) { struct ethhdr *ethhdr; @@ -800,23 +838,24 @@ static int check_unicast_packet(struct sk_buff *skb, int hdr_size) return -1; /* not for me */ - if (!is_my_mac(ethhdr->h_dest)) + if (!batadv_is_my_mac(ethhdr->h_dest)) return -1; return 0; } -static int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if) +static int batadv_route_unicast_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if) { - struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface); - struct orig_node *orig_node = NULL; - struct neigh_node *neigh_node = NULL; - struct unicast_packet *unicast_packet; + struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); + struct batadv_orig_node *orig_node = NULL; + struct batadv_neigh_node *neigh_node = NULL; + struct batadv_unicast_packet *unicast_packet; struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb); int ret = NET_RX_DROP; struct sk_buff *new_skb; - unicast_packet = (struct unicast_packet *)skb->data; + unicast_packet = (struct batadv_unicast_packet *)skb->data; /* TTL exceeded */ if (unicast_packet->header.ttl < 2) { @@ -826,13 +865,13 @@ static int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if) } /* get routing information */ - orig_node = orig_hash_find(bat_priv, unicast_packet->dest); + orig_node = batadv_orig_hash_find(bat_priv, unicast_packet->dest); if (!orig_node) goto out; /* find_router() increases neigh_nodes refcount if found. */ - neigh_node = find_router(bat_priv, orig_node, recv_if); + neigh_node = batadv_find_router(bat_priv, orig_node, recv_if); if (!neigh_node) goto out; @@ -841,20 +880,22 @@ static int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if) if (skb_cow(skb, ETH_HLEN) < 0) goto out; - unicast_packet = (struct unicast_packet *)skb->data; + unicast_packet = (struct batadv_unicast_packet *)skb->data; - if (unicast_packet->header.packet_type == BAT_UNICAST && + if (unicast_packet->header.packet_type == BATADV_UNICAST && atomic_read(&bat_priv->fragmentation) && skb->len > neigh_node->if_incoming->net_dev->mtu) { - ret = frag_send_skb(skb, bat_priv, - neigh_node->if_incoming, neigh_node->addr); + ret = batadv_frag_send_skb(skb, bat_priv, + neigh_node->if_incoming, + neigh_node->addr); goto out; } - if (unicast_packet->header.packet_type == BAT_UNICAST_FRAG && - frag_can_reassemble(skb, neigh_node->if_incoming->net_dev->mtu)) { + if (unicast_packet->header.packet_type == BATADV_UNICAST_FRAG && + batadv_frag_can_reassemble(skb, + neigh_node->if_incoming->net_dev->mtu)) { - ret = frag_reassemble_skb(skb, bat_priv, &new_skb); + ret = batadv_frag_reassemble_skb(skb, bat_priv, &new_skb); if (ret == NET_RX_DROP) goto out; @@ -866,141 +907,153 @@ static int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if) } skb = new_skb; - unicast_packet = (struct unicast_packet *)skb->data; + unicast_packet = (struct batadv_unicast_packet *)skb->data; } /* decrement ttl */ unicast_packet->header.ttl--; + /* Update stats counter */ + batadv_inc_counter(bat_priv, BATADV_CNT_FORWARD); + batadv_add_counter(bat_priv, BATADV_CNT_FORWARD_BYTES, + skb->len + ETH_HLEN); + /* route it */ - send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); ret = NET_RX_SUCCESS; out: if (neigh_node) - neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref(neigh_node); if (orig_node) - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); return ret; } -static int check_unicast_ttvn(struct bat_priv *bat_priv, - struct sk_buff *skb) { +static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, + struct sk_buff *skb) { uint8_t curr_ttvn; - struct orig_node *orig_node; + struct batadv_orig_node *orig_node; struct ethhdr *ethhdr; - struct hard_iface *primary_if; - struct unicast_packet *unicast_packet; + struct batadv_hard_iface *primary_if; + struct batadv_unicast_packet *unicast_packet; bool tt_poss_change; + int is_old_ttvn; /* I could need to modify it */ - if (skb_cow(skb, sizeof(struct unicast_packet)) < 0) + if (skb_cow(skb, sizeof(struct batadv_unicast_packet)) < 0) return 0; - unicast_packet = (struct unicast_packet *)skb->data; + unicast_packet = (struct batadv_unicast_packet *)skb->data; - if (is_my_mac(unicast_packet->dest)) { + if (batadv_is_my_mac(unicast_packet->dest)) { tt_poss_change = bat_priv->tt_poss_change; curr_ttvn = (uint8_t)atomic_read(&bat_priv->ttvn); } else { - orig_node = orig_hash_find(bat_priv, unicast_packet->dest); + orig_node = batadv_orig_hash_find(bat_priv, + unicast_packet->dest); if (!orig_node) return 0; curr_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); tt_poss_change = orig_node->tt_poss_change; - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); } /* Check whether I have to reroute the packet */ - if (seq_before(unicast_packet->ttvn, curr_ttvn) || tt_poss_change) { + is_old_ttvn = batadv_seq_before(unicast_packet->ttvn, curr_ttvn); + if (is_old_ttvn || tt_poss_change) { /* check if there is enough data before accessing it */ - if (pskb_may_pull(skb, sizeof(struct unicast_packet) + + if (pskb_may_pull(skb, sizeof(struct batadv_unicast_packet) + ETH_HLEN) < 0) return 0; - ethhdr = (struct ethhdr *)(skb->data + - sizeof(struct unicast_packet)); + ethhdr = (struct ethhdr *)(skb->data + sizeof(*unicast_packet)); /* we don't have an updated route for this client, so we should * not try to reroute the packet!! */ - if (tt_global_client_is_roaming(bat_priv, ethhdr->h_dest)) + if (batadv_tt_global_client_is_roaming(bat_priv, + ethhdr->h_dest)) return 1; - orig_node = transtable_search(bat_priv, NULL, ethhdr->h_dest); + orig_node = batadv_transtable_search(bat_priv, NULL, + ethhdr->h_dest); if (!orig_node) { - if (!is_my_client(bat_priv, ethhdr->h_dest)) + if (!batadv_is_my_client(bat_priv, ethhdr->h_dest)) return 0; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) return 0; memcpy(unicast_packet->dest, primary_if->net_dev->dev_addr, ETH_ALEN); - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); } else { memcpy(unicast_packet->dest, orig_node->orig, ETH_ALEN); curr_ttvn = (uint8_t) atomic_read(&orig_node->last_ttvn); - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); } - bat_dbg(DBG_ROUTES, bat_priv, - "TTVN mismatch (old_ttvn %u new_ttvn %u)! Rerouting unicast packet (for %pM) to %pM\n", - unicast_packet->ttvn, curr_ttvn, ethhdr->h_dest, - unicast_packet->dest); + batadv_dbg(BATADV_DBG_ROUTES, bat_priv, + "TTVN mismatch (old_ttvn %u new_ttvn %u)! Rerouting unicast packet (for %pM) to %pM\n", + unicast_packet->ttvn, curr_ttvn, ethhdr->h_dest, + unicast_packet->dest); unicast_packet->ttvn = curr_ttvn; } return 1; } -int recv_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if) +int batadv_recv_unicast_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if) { - struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface); - struct unicast_packet *unicast_packet; + struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); + struct batadv_unicast_packet *unicast_packet; int hdr_size = sizeof(*unicast_packet); - if (check_unicast_packet(skb, hdr_size) < 0) + if (batadv_check_unicast_packet(skb, hdr_size) < 0) return NET_RX_DROP; - if (!check_unicast_ttvn(bat_priv, skb)) + if (!batadv_check_unicast_ttvn(bat_priv, skb)) return NET_RX_DROP; - unicast_packet = (struct unicast_packet *)skb->data; + unicast_packet = (struct batadv_unicast_packet *)skb->data; /* packet for me */ - if (is_my_mac(unicast_packet->dest)) { - interface_rx(recv_if->soft_iface, skb, recv_if, hdr_size); + if (batadv_is_my_mac(unicast_packet->dest)) { + batadv_interface_rx(recv_if->soft_iface, skb, recv_if, + hdr_size); return NET_RX_SUCCESS; } - return route_unicast_packet(skb, recv_if); + return batadv_route_unicast_packet(skb, recv_if); } -int recv_ucast_frag_packet(struct sk_buff *skb, struct hard_iface *recv_if) +int batadv_recv_ucast_frag_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if) { - struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface); - struct unicast_frag_packet *unicast_packet; + struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); + struct batadv_unicast_frag_packet *unicast_packet; int hdr_size = sizeof(*unicast_packet); struct sk_buff *new_skb = NULL; int ret; - if (check_unicast_packet(skb, hdr_size) < 0) + if (batadv_check_unicast_packet(skb, hdr_size) < 0) return NET_RX_DROP; - if (!check_unicast_ttvn(bat_priv, skb)) + if (!batadv_check_unicast_ttvn(bat_priv, skb)) return NET_RX_DROP; - unicast_packet = (struct unicast_frag_packet *)skb->data; + unicast_packet = (struct batadv_unicast_frag_packet *)skb->data; /* packet for me */ - if (is_my_mac(unicast_packet->dest)) { + if (batadv_is_my_mac(unicast_packet->dest)) { - ret = frag_reassemble_skb(skb, bat_priv, &new_skb); + ret = batadv_frag_reassemble_skb(skb, bat_priv, &new_skb); if (ret == NET_RX_DROP) return NET_RX_DROP; @@ -1009,20 +1062,21 @@ int recv_ucast_frag_packet(struct sk_buff *skb, struct hard_iface *recv_if) if (!new_skb) return NET_RX_SUCCESS; - interface_rx(recv_if->soft_iface, new_skb, recv_if, - sizeof(struct unicast_packet)); + batadv_interface_rx(recv_if->soft_iface, new_skb, recv_if, + sizeof(struct batadv_unicast_packet)); return NET_RX_SUCCESS; } - return route_unicast_packet(skb, recv_if); + return batadv_route_unicast_packet(skb, recv_if); } -int recv_bcast_packet(struct sk_buff *skb, struct hard_iface *recv_if) +int batadv_recv_bcast_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if) { - struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface); - struct orig_node *orig_node = NULL; - struct bcast_packet *bcast_packet; + struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); + struct batadv_orig_node *orig_node = NULL; + struct batadv_bcast_packet *bcast_packet; struct ethhdr *ethhdr; int hdr_size = sizeof(*bcast_packet); int ret = NET_RX_DROP; @@ -1043,19 +1097,19 @@ int recv_bcast_packet(struct sk_buff *skb, struct hard_iface *recv_if) goto out; /* ignore broadcasts sent by myself */ - if (is_my_mac(ethhdr->h_source)) + if (batadv_is_my_mac(ethhdr->h_source)) goto out; - bcast_packet = (struct bcast_packet *)skb->data; + bcast_packet = (struct batadv_bcast_packet *)skb->data; /* ignore broadcasts originated by myself */ - if (is_my_mac(bcast_packet->orig)) + if (batadv_is_my_mac(bcast_packet->orig)) goto out; if (bcast_packet->header.ttl < 2) goto out; - orig_node = orig_hash_find(bat_priv, bcast_packet->orig); + orig_node = batadv_orig_hash_find(bat_priv, bcast_packet->orig); if (!orig_node) goto out; @@ -1063,39 +1117,40 @@ int recv_bcast_packet(struct sk_buff *skb, struct hard_iface *recv_if) spin_lock_bh(&orig_node->bcast_seqno_lock); /* check whether the packet is a duplicate */ - if (bat_test_bit(orig_node->bcast_bits, orig_node->last_bcast_seqno, - ntohl(bcast_packet->seqno))) + if (batadv_test_bit(orig_node->bcast_bits, orig_node->last_bcast_seqno, + ntohl(bcast_packet->seqno))) goto spin_unlock; seq_diff = ntohl(bcast_packet->seqno) - orig_node->last_bcast_seqno; /* check whether the packet is old and the host just restarted. */ - if (window_protected(bat_priv, seq_diff, - &orig_node->bcast_seqno_reset)) + if (batadv_window_protected(bat_priv, seq_diff, + &orig_node->bcast_seqno_reset)) goto spin_unlock; /* mark broadcast in flood history, update window position - * if required. */ - if (bit_get_packet(bat_priv, orig_node->bcast_bits, seq_diff, 1)) + * if required. + */ + if (batadv_bit_get_packet(bat_priv, orig_node->bcast_bits, seq_diff, 1)) orig_node->last_bcast_seqno = ntohl(bcast_packet->seqno); spin_unlock_bh(&orig_node->bcast_seqno_lock); /* check whether this has been sent by another originator before */ - if (bla_check_bcast_duplist(bat_priv, bcast_packet, hdr_size)) + if (batadv_bla_check_bcast_duplist(bat_priv, bcast_packet, hdr_size)) goto out; /* rebroadcast packet */ - add_bcast_packet_to_list(bat_priv, skb, 1); + batadv_add_bcast_packet_to_list(bat_priv, skb, 1); /* don't hand the broadcast up if it is from an originator * from the same backbone. */ - if (bla_is_backbone_gw(skb, orig_node, hdr_size)) + if (batadv_bla_is_backbone_gw(skb, orig_node, hdr_size)) goto out; /* broadcast for me */ - interface_rx(recv_if->soft_iface, skb, recv_if, hdr_size); + batadv_interface_rx(recv_if->soft_iface, skb, recv_if, hdr_size); ret = NET_RX_SUCCESS; goto out; @@ -1103,15 +1158,16 @@ spin_unlock: spin_unlock_bh(&orig_node->bcast_seqno_lock); out: if (orig_node) - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); return ret; } -int recv_vis_packet(struct sk_buff *skb, struct hard_iface *recv_if) +int batadv_recv_vis_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if) { - struct vis_packet *vis_packet; + struct batadv_vis_packet *vis_packet; struct ethhdr *ethhdr; - struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface); + struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); int hdr_size = sizeof(*vis_packet); /* keep skb linear */ @@ -1121,29 +1177,29 @@ int recv_vis_packet(struct sk_buff *skb, struct hard_iface *recv_if) if (unlikely(!pskb_may_pull(skb, hdr_size))) return NET_RX_DROP; - vis_packet = (struct vis_packet *)skb->data; + vis_packet = (struct batadv_vis_packet *)skb->data; ethhdr = (struct ethhdr *)skb_mac_header(skb); /* not for me */ - if (!is_my_mac(ethhdr->h_dest)) + if (!batadv_is_my_mac(ethhdr->h_dest)) return NET_RX_DROP; /* ignore own packets */ - if (is_my_mac(vis_packet->vis_orig)) + if (batadv_is_my_mac(vis_packet->vis_orig)) return NET_RX_DROP; - if (is_my_mac(vis_packet->sender_orig)) + if (batadv_is_my_mac(vis_packet->sender_orig)) return NET_RX_DROP; switch (vis_packet->vis_type) { - case VIS_TYPE_SERVER_SYNC: - receive_server_sync_packet(bat_priv, vis_packet, - skb_headlen(skb)); + case BATADV_VIS_TYPE_SERVER_SYNC: + batadv_receive_server_sync_packet(bat_priv, vis_packet, + skb_headlen(skb)); break; - case VIS_TYPE_CLIENT_UPDATE: - receive_client_update_packet(bat_priv, vis_packet, - skb_headlen(skb)); + case BATADV_VIS_TYPE_CLIENT_UPDATE: + batadv_receive_client_update_packet(bat_priv, vis_packet, + skb_headlen(skb)); break; default: /* ignore unknown packet */ @@ -1151,6 +1207,7 @@ int recv_vis_packet(struct sk_buff *skb, struct hard_iface *recv_if) } /* We take a copy of the data in the packet, so we should - always free the skbuf. */ + * always free the skbuf. + */ return NET_RX_DROP; } diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index d6bbbebb656..9262279ea66 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -16,36 +15,45 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_ROUTING_H_ #define _NET_BATMAN_ADV_ROUTING_H_ -void slide_own_bcast_window(struct hard_iface *hard_iface); -bool check_management_packet(struct sk_buff *skb, - struct hard_iface *hard_iface, - int header_len); -void update_route(struct bat_priv *bat_priv, struct orig_node *orig_node, - struct neigh_node *neigh_node); -int recv_icmp_packet(struct sk_buff *skb, struct hard_iface *recv_if); -int recv_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if); -int recv_ucast_frag_packet(struct sk_buff *skb, struct hard_iface *recv_if); -int recv_bcast_packet(struct sk_buff *skb, struct hard_iface *recv_if); -int recv_vis_packet(struct sk_buff *skb, struct hard_iface *recv_if); -int recv_tt_query(struct sk_buff *skb, struct hard_iface *recv_if); -int recv_roam_adv(struct sk_buff *skb, struct hard_iface *recv_if); -struct neigh_node *find_router(struct bat_priv *bat_priv, - struct orig_node *orig_node, - const struct hard_iface *recv_if); -void bonding_candidate_del(struct orig_node *orig_node, - struct neigh_node *neigh_node); -void bonding_candidate_add(struct orig_node *orig_node, - struct neigh_node *neigh_node); -void bonding_save_primary(const struct orig_node *orig_node, - struct orig_node *orig_neigh_node, - const struct batman_ogm_packet *batman_ogm_packet); -int window_protected(struct bat_priv *bat_priv, int32_t seq_num_diff, - unsigned long *last_reset); +void batadv_slide_own_bcast_window(struct batadv_hard_iface *hard_iface); +bool batadv_check_management_packet(struct sk_buff *skb, + struct batadv_hard_iface *hard_iface, + int header_len); +void batadv_update_route(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + struct batadv_neigh_node *neigh_node); +int batadv_recv_icmp_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if); +int batadv_recv_unicast_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if); +int batadv_recv_ucast_frag_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if); +int batadv_recv_bcast_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if); +int batadv_recv_vis_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if); +int batadv_recv_tt_query(struct sk_buff *skb, + struct batadv_hard_iface *recv_if); +int batadv_recv_roam_adv(struct sk_buff *skb, + struct batadv_hard_iface *recv_if); +struct batadv_neigh_node * +batadv_find_router(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + const struct batadv_hard_iface *recv_if); +void batadv_bonding_candidate_del(struct batadv_orig_node *orig_node, + struct batadv_neigh_node *neigh_node); +void batadv_bonding_candidate_add(struct batadv_orig_node *orig_node, + struct batadv_neigh_node *neigh_node); +void batadv_bonding_save_primary(const struct batadv_orig_node *orig_node, + struct batadv_orig_node *orig_neigh_node, + const struct batadv_ogm_packet + *batman_ogm_packet); +int batadv_window_protected(struct batadv_priv *bat_priv, int32_t seq_num_diff, + unsigned long *last_reset); #endif /* _NET_BATMAN_ADV_ROUTING_H_ */ diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index f47299f22c6..3b4b2daa3b3 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" @@ -29,16 +27,18 @@ #include "gateway_common.h" #include "originator.h" -static void send_outstanding_bcast_packet(struct work_struct *work); +static void batadv_send_outstanding_bcast_packet(struct work_struct *work); /* send out an already prepared packet to the given address via the - * specified batman interface */ -int send_skb_packet(struct sk_buff *skb, struct hard_iface *hard_iface, - const uint8_t *dst_addr) + * specified batman interface + */ +int batadv_send_skb_packet(struct sk_buff *skb, + struct batadv_hard_iface *hard_iface, + const uint8_t *dst_addr) { struct ethhdr *ethhdr; - if (hard_iface->if_status != IF_ACTIVE) + if (hard_iface->if_status != BATADV_IF_ACTIVE) goto send_skb_err; if (unlikely(!hard_iface->net_dev)) @@ -51,7 +51,7 @@ int send_skb_packet(struct sk_buff *skb, struct hard_iface *hard_iface, } /* push to the ethernet header. */ - if (my_skb_head_push(skb, ETH_HLEN) < 0) + if (batadv_skb_head_push(skb, ETH_HLEN) < 0) goto send_skb_err; skb_reset_mac_header(skb); @@ -59,129 +59,57 @@ int send_skb_packet(struct sk_buff *skb, struct hard_iface *hard_iface, ethhdr = (struct ethhdr *)skb_mac_header(skb); memcpy(ethhdr->h_source, hard_iface->net_dev->dev_addr, ETH_ALEN); memcpy(ethhdr->h_dest, dst_addr, ETH_ALEN); - ethhdr->h_proto = __constant_htons(ETH_P_BATMAN); + ethhdr->h_proto = __constant_htons(BATADV_ETH_P_BATMAN); skb_set_network_header(skb, ETH_HLEN); skb->priority = TC_PRIO_CONTROL; - skb->protocol = __constant_htons(ETH_P_BATMAN); + skb->protocol = __constant_htons(BATADV_ETH_P_BATMAN); skb->dev = hard_iface->net_dev; /* dev_queue_xmit() returns a negative result on error. However on * congestion and traffic shaping, it drops and returns NET_XMIT_DROP - * (which is > 0). This will not be treated as an error. */ - + * (which is > 0). This will not be treated as an error. + */ return dev_queue_xmit(skb); send_skb_err: kfree_skb(skb); return NET_XMIT_DROP; } -static void realloc_packet_buffer(struct hard_iface *hard_iface, - int new_len) +void batadv_schedule_bat_ogm(struct batadv_hard_iface *hard_iface) { - unsigned char *new_buff; - - new_buff = kmalloc(new_len, GFP_ATOMIC); - - /* keep old buffer if kmalloc should fail */ - if (new_buff) { - memcpy(new_buff, hard_iface->packet_buff, - BATMAN_OGM_HLEN); - - kfree(hard_iface->packet_buff); - hard_iface->packet_buff = new_buff; - hard_iface->packet_len = new_len; - } -} + struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); -/* when calling this function (hard_iface == primary_if) has to be true */ -static int prepare_packet_buffer(struct bat_priv *bat_priv, - struct hard_iface *hard_iface) -{ - int new_len; - - new_len = BATMAN_OGM_HLEN + - tt_len((uint8_t)atomic_read(&bat_priv->tt_local_changes)); - - /* if we have too many changes for one packet don't send any - * and wait for the tt table request which will be fragmented */ - if (new_len > hard_iface->soft_iface->mtu) - new_len = BATMAN_OGM_HLEN; - - realloc_packet_buffer(hard_iface, new_len); - - atomic_set(&bat_priv->tt_crc, tt_local_crc(bat_priv)); - - /* reset the sending counter */ - atomic_set(&bat_priv->tt_ogm_append_cnt, TT_OGM_APPEND_MAX); - - return tt_changes_fill_buffer(bat_priv, - hard_iface->packet_buff + BATMAN_OGM_HLEN, - hard_iface->packet_len - BATMAN_OGM_HLEN); -} - -static int reset_packet_buffer(struct bat_priv *bat_priv, - struct hard_iface *hard_iface) -{ - realloc_packet_buffer(hard_iface, BATMAN_OGM_HLEN); - return 0; -} - -void schedule_bat_ogm(struct hard_iface *hard_iface) -{ - struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - struct hard_iface *primary_if; - int tt_num_changes = -1; - - if ((hard_iface->if_status == IF_NOT_IN_USE) || - (hard_iface->if_status == IF_TO_BE_REMOVED)) + if ((hard_iface->if_status == BATADV_IF_NOT_IN_USE) || + (hard_iface->if_status == BATADV_IF_TO_BE_REMOVED)) return; - /** - * the interface gets activated here to avoid race conditions between + /* the interface gets activated here to avoid race conditions between * the moment of activating the interface in * hardif_activate_interface() where the originator mac is set and * outdated packets (especially uninitialized mac addresses) in the * packet queue */ - if (hard_iface->if_status == IF_TO_BE_ACTIVATED) - hard_iface->if_status = IF_ACTIVE; - - primary_if = primary_if_get_selected(bat_priv); - - if (hard_iface == primary_if) { - /* if at least one change happened */ - if (atomic_read(&bat_priv->tt_local_changes) > 0) { - tt_commit_changes(bat_priv); - tt_num_changes = prepare_packet_buffer(bat_priv, - hard_iface); - } - - /* if the changes have been sent often enough */ - if (!atomic_dec_not_zero(&bat_priv->tt_ogm_append_cnt)) - tt_num_changes = reset_packet_buffer(bat_priv, - hard_iface); - } - - if (primary_if) - hardif_free_ref(primary_if); + if (hard_iface->if_status == BATADV_IF_TO_BE_ACTIVATED) + hard_iface->if_status = BATADV_IF_ACTIVE; - bat_priv->bat_algo_ops->bat_ogm_schedule(hard_iface, tt_num_changes); + bat_priv->bat_algo_ops->bat_ogm_schedule(hard_iface); } -static void forw_packet_free(struct forw_packet *forw_packet) +static void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet) { if (forw_packet->skb) kfree_skb(forw_packet->skb); if (forw_packet->if_incoming) - hardif_free_ref(forw_packet->if_incoming); + batadv_hardif_free_ref(forw_packet->if_incoming); kfree(forw_packet); } -static void _add_bcast_packet_to_list(struct bat_priv *bat_priv, - struct forw_packet *forw_packet, - unsigned long send_time) +static void +_batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, + struct batadv_forw_packet *forw_packet, + unsigned long send_time) { INIT_HLIST_NODE(&forw_packet->list); @@ -192,8 +120,8 @@ static void _add_bcast_packet_to_list(struct bat_priv *bat_priv, /* start timer for this packet */ INIT_DELAYED_WORK(&forw_packet->delayed_work, - send_outstanding_bcast_packet); - queue_delayed_work(bat_event_workqueue, &forw_packet->delayed_work, + batadv_send_outstanding_bcast_packet); + queue_delayed_work(batadv_event_workqueue, &forw_packet->delayed_work, send_time); } @@ -204,21 +132,24 @@ static void _add_bcast_packet_to_list(struct bat_priv *bat_priv, * errors. * * The skb is not consumed, so the caller should make sure that the - * skb is freed. */ -int add_bcast_packet_to_list(struct bat_priv *bat_priv, - const struct sk_buff *skb, unsigned long delay) + * skb is freed. + */ +int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, + const struct sk_buff *skb, + unsigned long delay) { - struct hard_iface *primary_if = NULL; - struct forw_packet *forw_packet; - struct bcast_packet *bcast_packet; + struct batadv_hard_iface *primary_if = NULL; + struct batadv_forw_packet *forw_packet; + struct batadv_bcast_packet *bcast_packet; struct sk_buff *newskb; - if (!atomic_dec_not_zero(&bat_priv->bcast_queue_left)) { - bat_dbg(DBG_BATMAN, bat_priv, "bcast packet queue full\n"); + if (!batadv_atomic_dec_not_zero(&bat_priv->bcast_queue_left)) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "bcast packet queue full\n"); goto out; } - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out_and_inc; @@ -232,7 +163,7 @@ int add_bcast_packet_to_list(struct bat_priv *bat_priv, goto packet_free; /* as we have a copy now, it is safe to decrease the TTL */ - bcast_packet = (struct bcast_packet *)newskb->data; + bcast_packet = (struct batadv_bcast_packet *)newskb->data; bcast_packet->header.ttl--; skb_reset_mac_header(newskb); @@ -243,7 +174,7 @@ int add_bcast_packet_to_list(struct bat_priv *bat_priv, /* how often did we send the bcast packet ? */ forw_packet->num_packets = 0; - _add_bcast_packet_to_list(bat_priv, forw_packet, delay); + _batadv_add_bcast_packet_to_list(bat_priv, forw_packet, delay); return NETDEV_TX_OK; packet_free: @@ -252,38 +183,43 @@ out_and_inc: atomic_inc(&bat_priv->bcast_queue_left); out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); return NETDEV_TX_BUSY; } -static void send_outstanding_bcast_packet(struct work_struct *work) +static void batadv_send_outstanding_bcast_packet(struct work_struct *work) { - struct hard_iface *hard_iface; + struct batadv_hard_iface *hard_iface; struct delayed_work *delayed_work = container_of(work, struct delayed_work, work); - struct forw_packet *forw_packet = - container_of(delayed_work, struct forw_packet, delayed_work); + struct batadv_forw_packet *forw_packet; struct sk_buff *skb1; - struct net_device *soft_iface = forw_packet->if_incoming->soft_iface; - struct bat_priv *bat_priv = netdev_priv(soft_iface); + struct net_device *soft_iface; + struct batadv_priv *bat_priv; + + forw_packet = container_of(delayed_work, struct batadv_forw_packet, + delayed_work); + soft_iface = forw_packet->if_incoming->soft_iface; + bat_priv = netdev_priv(soft_iface); spin_lock_bh(&bat_priv->forw_bcast_list_lock); hlist_del(&forw_packet->list); spin_unlock_bh(&bat_priv->forw_bcast_list_lock); - if (atomic_read(&bat_priv->mesh_state) == MESH_DEACTIVATING) + if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) goto out; /* rebroadcast packet */ rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &hardif_list, list) { + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->soft_iface != soft_iface) continue; /* send a copy of the saved skb */ skb1 = skb_clone(forw_packet->skb, GFP_ATOMIC); if (skb1) - send_skb_packet(skb1, hard_iface, broadcast_addr); + batadv_send_skb_packet(skb1, hard_iface, + batadv_broadcast_addr); } rcu_read_unlock(); @@ -291,72 +227,72 @@ static void send_outstanding_bcast_packet(struct work_struct *work) /* if we still have some more bcasts to send */ if (forw_packet->num_packets < 3) { - _add_bcast_packet_to_list(bat_priv, forw_packet, - msecs_to_jiffies(5)); + _batadv_add_bcast_packet_to_list(bat_priv, forw_packet, + msecs_to_jiffies(5)); return; } out: - forw_packet_free(forw_packet); + batadv_forw_packet_free(forw_packet); atomic_inc(&bat_priv->bcast_queue_left); } -void send_outstanding_bat_ogm_packet(struct work_struct *work) +void batadv_send_outstanding_bat_ogm_packet(struct work_struct *work) { struct delayed_work *delayed_work = container_of(work, struct delayed_work, work); - struct forw_packet *forw_packet = - container_of(delayed_work, struct forw_packet, delayed_work); - struct bat_priv *bat_priv; + struct batadv_forw_packet *forw_packet; + struct batadv_priv *bat_priv; + forw_packet = container_of(delayed_work, struct batadv_forw_packet, + delayed_work); bat_priv = netdev_priv(forw_packet->if_incoming->soft_iface); spin_lock_bh(&bat_priv->forw_bat_list_lock); hlist_del(&forw_packet->list); spin_unlock_bh(&bat_priv->forw_bat_list_lock); - if (atomic_read(&bat_priv->mesh_state) == MESH_DEACTIVATING) + if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) goto out; bat_priv->bat_algo_ops->bat_ogm_emit(forw_packet); - /** - * we have to have at least one packet in the queue + /* we have to have at least one packet in the queue * to determine the queues wake up time unless we are * shutting down */ if (forw_packet->own) - schedule_bat_ogm(forw_packet->if_incoming); + batadv_schedule_bat_ogm(forw_packet->if_incoming); out: /* don't count own packet */ if (!forw_packet->own) atomic_inc(&bat_priv->batman_queue_left); - forw_packet_free(forw_packet); + batadv_forw_packet_free(forw_packet); } -void purge_outstanding_packets(struct bat_priv *bat_priv, - const struct hard_iface *hard_iface) +void +batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, + const struct batadv_hard_iface *hard_iface) { - struct forw_packet *forw_packet; + struct batadv_forw_packet *forw_packet; struct hlist_node *tmp_node, *safe_tmp_node; bool pending; if (hard_iface) - bat_dbg(DBG_BATMAN, bat_priv, - "purge_outstanding_packets(): %s\n", - hard_iface->net_dev->name); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "purge_outstanding_packets(): %s\n", + hard_iface->net_dev->name); else - bat_dbg(DBG_BATMAN, bat_priv, - "purge_outstanding_packets()\n"); + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "purge_outstanding_packets()\n"); /* free bcast list */ spin_lock_bh(&bat_priv->forw_bcast_list_lock); hlist_for_each_entry_safe(forw_packet, tmp_node, safe_tmp_node, &bat_priv->forw_bcast_list, list) { - /** - * if purge_outstanding_packets() was called with an argument + /* if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface */ if ((hard_iface) && @@ -365,8 +301,7 @@ void purge_outstanding_packets(struct bat_priv *bat_priv, spin_unlock_bh(&bat_priv->forw_bcast_list_lock); - /** - * send_outstanding_bcast_packet() will lock the list to + /* batadv_send_outstanding_bcast_packet() will lock the list to * delete the item from the list */ pending = cancel_delayed_work_sync(&forw_packet->delayed_work); @@ -374,7 +309,7 @@ void purge_outstanding_packets(struct bat_priv *bat_priv, if (pending) { hlist_del(&forw_packet->list); - forw_packet_free(forw_packet); + batadv_forw_packet_free(forw_packet); } } spin_unlock_bh(&bat_priv->forw_bcast_list_lock); @@ -384,8 +319,7 @@ void purge_outstanding_packets(struct bat_priv *bat_priv, hlist_for_each_entry_safe(forw_packet, tmp_node, safe_tmp_node, &bat_priv->forw_bat_list, list) { - /** - * if purge_outstanding_packets() was called with an argument + /* if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface */ if ((hard_iface) && @@ -394,8 +328,7 @@ void purge_outstanding_packets(struct bat_priv *bat_priv, spin_unlock_bh(&bat_priv->forw_bat_list_lock); - /** - * send_outstanding_bat_packet() will lock the list to + /* send_outstanding_bat_packet() will lock the list to * delete the item from the list */ pending = cancel_delayed_work_sync(&forw_packet->delayed_work); @@ -403,7 +336,7 @@ void purge_outstanding_packets(struct bat_priv *bat_priv, if (pending) { hlist_del(&forw_packet->list); - forw_packet_free(forw_packet); + batadv_forw_packet_free(forw_packet); } } spin_unlock_bh(&bat_priv->forw_bat_list_lock); diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 824ef06f9b0..643329b787e 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -16,19 +15,21 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_SEND_H_ #define _NET_BATMAN_ADV_SEND_H_ -int send_skb_packet(struct sk_buff *skb, struct hard_iface *hard_iface, - const uint8_t *dst_addr); -void schedule_bat_ogm(struct hard_iface *hard_iface); -int add_bcast_packet_to_list(struct bat_priv *bat_priv, - const struct sk_buff *skb, unsigned long delay); -void send_outstanding_bat_ogm_packet(struct work_struct *work); -void purge_outstanding_packets(struct bat_priv *bat_priv, - const struct hard_iface *hard_iface); +int batadv_send_skb_packet(struct sk_buff *skb, + struct batadv_hard_iface *hard_iface, + const uint8_t *dst_addr); +void batadv_schedule_bat_ogm(struct batadv_hard_iface *hard_iface); +int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, + const struct sk_buff *skb, + unsigned long delay); +void batadv_send_outstanding_bat_ogm_packet(struct work_struct *work); +void +batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, + const struct batadv_hard_iface *hard_iface); #endif /* _NET_BATMAN_ADV_SEND_H_ */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index a0ec0e4ada4..109ea2aae96 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" @@ -24,12 +22,12 @@ #include "hard-interface.h" #include "routing.h" #include "send.h" -#include "bat_debugfs.h" +#include "debugfs.h" #include "translation-table.h" #include "hash.h" #include "gateway_common.h" #include "gateway_client.h" -#include "bat_sysfs.h" +#include "sysfs.h" #include "originator.h" #include <linux/slab.h> #include <linux/ethtool.h> @@ -39,27 +37,33 @@ #include "bridge_loop_avoidance.h" -static int bat_get_settings(struct net_device *dev, struct ethtool_cmd *cmd); -static void bat_get_drvinfo(struct net_device *dev, - struct ethtool_drvinfo *info); -static u32 bat_get_msglevel(struct net_device *dev); -static void bat_set_msglevel(struct net_device *dev, u32 value); -static u32 bat_get_link(struct net_device *dev); - -static const struct ethtool_ops bat_ethtool_ops = { - .get_settings = bat_get_settings, - .get_drvinfo = bat_get_drvinfo, - .get_msglevel = bat_get_msglevel, - .set_msglevel = bat_set_msglevel, - .get_link = bat_get_link, +static int batadv_get_settings(struct net_device *dev, struct ethtool_cmd *cmd); +static void batadv_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info); +static u32 batadv_get_msglevel(struct net_device *dev); +static void batadv_set_msglevel(struct net_device *dev, u32 value); +static u32 batadv_get_link(struct net_device *dev); +static void batadv_get_strings(struct net_device *dev, u32 stringset, u8 *data); +static void batadv_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data); +static int batadv_get_sset_count(struct net_device *dev, int stringset); + +static const struct ethtool_ops batadv_ethtool_ops = { + .get_settings = batadv_get_settings, + .get_drvinfo = batadv_get_drvinfo, + .get_msglevel = batadv_get_msglevel, + .set_msglevel = batadv_set_msglevel, + .get_link = batadv_get_link, + .get_strings = batadv_get_strings, + .get_ethtool_stats = batadv_get_ethtool_stats, + .get_sset_count = batadv_get_sset_count, }; -int my_skb_head_push(struct sk_buff *skb, unsigned int len) +int batadv_skb_head_push(struct sk_buff *skb, unsigned int len) { int result; - /** - * TODO: We must check if we can release all references to non-payload + /* TODO: We must check if we can release all references to non-payload * data using skb_header_release in our skbs to allow skb_cow_header to * work optimally. This means that those skbs are not allowed to read * or write any data which is before the current position of skb->data @@ -74,37 +78,37 @@ int my_skb_head_push(struct sk_buff *skb, unsigned int len) return 0; } -static int interface_open(struct net_device *dev) +static int batadv_interface_open(struct net_device *dev) { netif_start_queue(dev); return 0; } -static int interface_release(struct net_device *dev) +static int batadv_interface_release(struct net_device *dev) { netif_stop_queue(dev); return 0; } -static struct net_device_stats *interface_stats(struct net_device *dev) +static struct net_device_stats *batadv_interface_stats(struct net_device *dev) { - struct bat_priv *bat_priv = netdev_priv(dev); + struct batadv_priv *bat_priv = netdev_priv(dev); return &bat_priv->stats; } -static int interface_set_mac_addr(struct net_device *dev, void *p) +static int batadv_interface_set_mac_addr(struct net_device *dev, void *p) { - struct bat_priv *bat_priv = netdev_priv(dev); + struct batadv_priv *bat_priv = netdev_priv(dev); struct sockaddr *addr = p; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; /* only modify transtable if it has been initialized before */ - if (atomic_read(&bat_priv->mesh_state) == MESH_ACTIVE) { - tt_local_remove(bat_priv, dev->dev_addr, - "mac address changed", false); - tt_local_add(dev, addr->sa_data, NULL_IFINDEX); + if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE) { + batadv_tt_local_remove(bat_priv, dev->dev_addr, + "mac address changed", false); + batadv_tt_local_add(dev, addr->sa_data, BATADV_NULL_IFINDEX); } memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); @@ -112,10 +116,10 @@ static int interface_set_mac_addr(struct net_device *dev, void *p) return 0; } -static int interface_change_mtu(struct net_device *dev, int new_mtu) +static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu) { /* check ranges */ - if ((new_mtu < 68) || (new_mtu > hardif_min_mtu(dev))) + if ((new_mtu < 68) || (new_mtu > batadv_hardif_min_mtu(dev))) return -EINVAL; dev->mtu = new_mtu; @@ -123,13 +127,15 @@ static int interface_change_mtu(struct net_device *dev, int new_mtu) return 0; } -static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) +static int batadv_interface_tx(struct sk_buff *skb, + struct net_device *soft_iface) { struct ethhdr *ethhdr = (struct ethhdr *)skb->data; - struct bat_priv *bat_priv = netdev_priv(soft_iface); - struct hard_iface *primary_if = NULL; - struct bcast_packet *bcast_packet; + struct batadv_priv *bat_priv = netdev_priv(soft_iface); + struct batadv_hard_iface *primary_if = NULL; + struct batadv_bcast_packet *bcast_packet; struct vlan_ethhdr *vhdr; + __be16 ethertype = __constant_htons(BATADV_ETH_P_BATMAN); static const uint8_t stp_addr[ETH_ALEN] = {0x01, 0x80, 0xC2, 0x00, 0x00, 0x00}; unsigned int header_len = 0; @@ -137,7 +143,7 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) short vid __maybe_unused = -1; bool do_bcast = false; - if (atomic_read(&bat_priv->mesh_state) != MESH_ACTIVE) + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) goto dropped; soft_iface->trans_start = jiffies; @@ -147,45 +153,47 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) vhdr = (struct vlan_ethhdr *)skb->data; vid = ntohs(vhdr->h_vlan_TCI) & VLAN_VID_MASK; - if (ntohs(vhdr->h_vlan_encapsulated_proto) != ETH_P_BATMAN) + if (vhdr->h_vlan_encapsulated_proto != ethertype) break; /* fall through */ - case ETH_P_BATMAN: + case BATADV_ETH_P_BATMAN: goto dropped; } - if (bla_tx(bat_priv, skb, vid)) + if (batadv_bla_tx(bat_priv, skb, vid)) goto dropped; /* Register the client MAC in the transtable */ - tt_local_add(soft_iface, ethhdr->h_source, skb->skb_iif); + batadv_tt_local_add(soft_iface, ethhdr->h_source, skb->skb_iif); /* don't accept stp packets. STP does not help in meshes. * better use the bridge loop avoidance ... */ - if (compare_eth(ethhdr->h_dest, stp_addr)) + if (batadv_compare_eth(ethhdr->h_dest, stp_addr)) goto dropped; if (is_multicast_ether_addr(ethhdr->h_dest)) { do_bcast = true; switch (atomic_read(&bat_priv->gw_mode)) { - case GW_MODE_SERVER: + case BATADV_GW_MODE_SERVER: /* gateway servers should not send dhcp - * requests into the mesh */ - ret = gw_is_dhcp_target(skb, &header_len); + * requests into the mesh + */ + ret = batadv_gw_is_dhcp_target(skb, &header_len); if (ret) goto dropped; break; - case GW_MODE_CLIENT: + case BATADV_GW_MODE_CLIENT: /* gateway clients should send dhcp requests - * via unicast to their gateway */ - ret = gw_is_dhcp_target(skb, &header_len); + * via unicast to their gateway + */ + ret = batadv_gw_is_dhcp_target(skb, &header_len); if (ret) do_bcast = false; break; - case GW_MODE_OFF: + case BATADV_GW_MODE_OFF: default: break; } @@ -193,22 +201,24 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) /* ethernet packet should be broadcasted */ if (do_bcast) { - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto dropped; - if (my_skb_head_push(skb, sizeof(*bcast_packet)) < 0) + if (batadv_skb_head_push(skb, sizeof(*bcast_packet)) < 0) goto dropped; - bcast_packet = (struct bcast_packet *)skb->data; - bcast_packet->header.version = COMPAT_VERSION; - bcast_packet->header.ttl = TTL; + bcast_packet = (struct batadv_bcast_packet *)skb->data; + bcast_packet->header.version = BATADV_COMPAT_VERSION; + bcast_packet->header.ttl = BATADV_TTL; /* batman packet type: broadcast */ - bcast_packet->header.packet_type = BAT_BCAST; + bcast_packet->header.packet_type = BATADV_BCAST; + bcast_packet->reserved = 0; /* hw address of first interface is the orig mac because only - * this mac is known throughout the mesh */ + * this mac is known throughout the mesh + */ memcpy(bcast_packet->orig, primary_if->net_dev->dev_addr, ETH_ALEN); @@ -216,21 +226,22 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) bcast_packet->seqno = htonl(atomic_inc_return(&bat_priv->bcast_seqno)); - add_bcast_packet_to_list(bat_priv, skb, 1); + batadv_add_bcast_packet_to_list(bat_priv, skb, 1); /* a copy is stored in the bcast list, therefore removing - * the original skb. */ + * the original skb. + */ kfree_skb(skb); /* unicast packet */ } else { - if (atomic_read(&bat_priv->gw_mode) != GW_MODE_OFF) { - ret = gw_out_of_range(bat_priv, skb, ethhdr); + if (atomic_read(&bat_priv->gw_mode) != BATADV_GW_MODE_OFF) { + ret = batadv_gw_out_of_range(bat_priv, skb, ethhdr); if (ret) goto dropped; } - ret = unicast_send_skb(skb, bat_priv); + ret = batadv_unicast_send_skb(skb, bat_priv); if (ret != 0) goto dropped_freed; } @@ -245,22 +256,23 @@ dropped_freed: bat_priv->stats.tx_dropped++; end: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); return NETDEV_TX_OK; } -void interface_rx(struct net_device *soft_iface, - struct sk_buff *skb, struct hard_iface *recv_if, - int hdr_size) +void batadv_interface_rx(struct net_device *soft_iface, + struct sk_buff *skb, struct batadv_hard_iface *recv_if, + int hdr_size) { - struct bat_priv *bat_priv = netdev_priv(soft_iface); + struct batadv_priv *bat_priv = netdev_priv(soft_iface); struct ethhdr *ethhdr; struct vlan_ethhdr *vhdr; - struct batman_header *batadv_header = (struct batman_header *)skb->data; + struct batadv_header *batadv_header = (struct batadv_header *)skb->data; short vid __maybe_unused = -1; + __be16 ethertype = __constant_htons(BATADV_ETH_P_BATMAN); bool is_bcast; - is_bcast = (batadv_header->packet_type == BAT_BCAST); + is_bcast = (batadv_header->packet_type == BATADV_BCAST); /* check if enough space is available for pulling, and pull */ if (!pskb_may_pull(skb, hdr_size)) @@ -276,11 +288,11 @@ void interface_rx(struct net_device *soft_iface, vhdr = (struct vlan_ethhdr *)skb->data; vid = ntohs(vhdr->h_vlan_TCI) & VLAN_VID_MASK; - if (ntohs(vhdr->h_vlan_encapsulated_proto) != ETH_P_BATMAN) + if (vhdr->h_vlan_encapsulated_proto != ethertype) break; /* fall through */ - case ETH_P_BATMAN: + case BATADV_ETH_P_BATMAN: goto dropped; } @@ -291,22 +303,23 @@ void interface_rx(struct net_device *soft_iface, /* should not be necessary anymore as we use skb_pull_rcsum() * TODO: please verify this and remove this TODO - * -- Dec 21st 2009, Simon Wunderlich */ + * -- Dec 21st 2009, Simon Wunderlich + */ -/* skb->ip_summed = CHECKSUM_UNNECESSARY;*/ + /* skb->ip_summed = CHECKSUM_UNNECESSARY; */ bat_priv->stats.rx_packets++; bat_priv->stats.rx_bytes += skb->len + ETH_HLEN; soft_iface->last_rx = jiffies; - if (is_ap_isolated(bat_priv, ethhdr->h_source, ethhdr->h_dest)) + if (batadv_is_ap_isolated(bat_priv, ethhdr->h_source, ethhdr->h_dest)) goto dropped; /* Let the bridge loop avoidance check the packet. If will * not handle it, we can safely push it up. */ - if (bla_rx(bat_priv, skb, vid, is_bcast)) + if (batadv_bla_rx(bat_priv, skb, vid, is_bcast)) goto out; netif_rx(skb); @@ -318,49 +331,50 @@ out: return; } -static const struct net_device_ops bat_netdev_ops = { - .ndo_open = interface_open, - .ndo_stop = interface_release, - .ndo_get_stats = interface_stats, - .ndo_set_mac_address = interface_set_mac_addr, - .ndo_change_mtu = interface_change_mtu, - .ndo_start_xmit = interface_tx, +static const struct net_device_ops batadv_netdev_ops = { + .ndo_open = batadv_interface_open, + .ndo_stop = batadv_interface_release, + .ndo_get_stats = batadv_interface_stats, + .ndo_set_mac_address = batadv_interface_set_mac_addr, + .ndo_change_mtu = batadv_interface_change_mtu, + .ndo_start_xmit = batadv_interface_tx, .ndo_validate_addr = eth_validate_addr }; -static void interface_setup(struct net_device *dev) +static void batadv_interface_setup(struct net_device *dev) { - struct bat_priv *priv = netdev_priv(dev); + struct batadv_priv *priv = netdev_priv(dev); ether_setup(dev); - dev->netdev_ops = &bat_netdev_ops; + dev->netdev_ops = &batadv_netdev_ops; dev->destructor = free_netdev; dev->tx_queue_len = 0; - /** - * can't call min_mtu, because the needed variables + /* can't call min_mtu, because the needed variables * have not been initialized yet */ dev->mtu = ETH_DATA_LEN; /* reserve more space in the skbuff for our header */ - dev->hard_header_len = BAT_HEADER_LEN; + dev->hard_header_len = BATADV_HEADER_LEN; /* generate random address */ eth_hw_addr_random(dev); - SET_ETHTOOL_OPS(dev, &bat_ethtool_ops); + SET_ETHTOOL_OPS(dev, &batadv_ethtool_ops); memset(priv, 0, sizeof(*priv)); } -struct net_device *softif_create(const char *name) +struct net_device *batadv_softif_create(const char *name) { struct net_device *soft_iface; - struct bat_priv *bat_priv; + struct batadv_priv *bat_priv; int ret; + size_t cnt_len = sizeof(uint64_t) * BATADV_CNT_NUM; - soft_iface = alloc_netdev(sizeof(*bat_priv), name, interface_setup); + soft_iface = alloc_netdev(sizeof(*bat_priv), name, + batadv_interface_setup); if (!soft_iface) goto out; @@ -378,18 +392,18 @@ struct net_device *softif_create(const char *name) atomic_set(&bat_priv->bonding, 0); atomic_set(&bat_priv->bridge_loop_avoidance, 0); atomic_set(&bat_priv->ap_isolation, 0); - atomic_set(&bat_priv->vis_mode, VIS_TYPE_CLIENT_UPDATE); - atomic_set(&bat_priv->gw_mode, GW_MODE_OFF); + atomic_set(&bat_priv->vis_mode, BATADV_VIS_TYPE_CLIENT_UPDATE); + atomic_set(&bat_priv->gw_mode, BATADV_GW_MODE_OFF); atomic_set(&bat_priv->gw_sel_class, 20); atomic_set(&bat_priv->gw_bandwidth, 41); atomic_set(&bat_priv->orig_interval, 1000); atomic_set(&bat_priv->hop_penalty, 30); atomic_set(&bat_priv->log_level, 0); atomic_set(&bat_priv->fragmentation, 1); - atomic_set(&bat_priv->bcast_queue_left, BCAST_QUEUE_LEN); - atomic_set(&bat_priv->batman_queue_left, BATMAN_QUEUE_LEN); + atomic_set(&bat_priv->bcast_queue_left, BATADV_BCAST_QUEUE_LEN); + atomic_set(&bat_priv->batman_queue_left, BATADV_BATMAN_QUEUE_LEN); - atomic_set(&bat_priv->mesh_state, MESH_INACTIVE); + atomic_set(&bat_priv->mesh_state, BATADV_MESH_INACTIVE); atomic_set(&bat_priv->bcast_seqno, 1); atomic_set(&bat_priv->ttvn, 0); atomic_set(&bat_priv->tt_local_changes, 0); @@ -403,28 +417,34 @@ struct net_device *softif_create(const char *name) bat_priv->primary_if = NULL; bat_priv->num_ifaces = 0; - ret = bat_algo_select(bat_priv, bat_routing_algo); - if (ret < 0) + bat_priv->bat_counters = __alloc_percpu(cnt_len, __alignof__(uint64_t)); + if (!bat_priv->bat_counters) goto unreg_soft_iface; - ret = sysfs_add_meshif(soft_iface); + ret = batadv_algo_select(bat_priv, batadv_routing_algo); if (ret < 0) - goto unreg_soft_iface; + goto free_bat_counters; - ret = debugfs_add_meshif(soft_iface); + ret = batadv_sysfs_add_meshif(soft_iface); + if (ret < 0) + goto free_bat_counters; + + ret = batadv_debugfs_add_meshif(soft_iface); if (ret < 0) goto unreg_sysfs; - ret = mesh_init(soft_iface); + ret = batadv_mesh_init(soft_iface); if (ret < 0) goto unreg_debugfs; return soft_iface; unreg_debugfs: - debugfs_del_meshif(soft_iface); + batadv_debugfs_del_meshif(soft_iface); unreg_sysfs: - sysfs_del_meshif(soft_iface); + batadv_sysfs_del_meshif(soft_iface); +free_bat_counters: + free_percpu(bat_priv->bat_counters); unreg_soft_iface: unregister_netdevice(soft_iface); return NULL; @@ -435,24 +455,24 @@ out: return NULL; } -void softif_destroy(struct net_device *soft_iface) +void batadv_softif_destroy(struct net_device *soft_iface) { - debugfs_del_meshif(soft_iface); - sysfs_del_meshif(soft_iface); - mesh_free(soft_iface); + batadv_debugfs_del_meshif(soft_iface); + batadv_sysfs_del_meshif(soft_iface); + batadv_mesh_free(soft_iface); unregister_netdevice(soft_iface); } -int softif_is_valid(const struct net_device *net_dev) +int batadv_softif_is_valid(const struct net_device *net_dev) { - if (net_dev->netdev_ops->ndo_start_xmit == interface_tx) + if (net_dev->netdev_ops->ndo_start_xmit == batadv_interface_tx) return 1; return 0; } /* ethtool */ -static int bat_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int batadv_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { cmd->supported = 0; cmd->advertising = 0; @@ -468,25 +488,73 @@ static int bat_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) return 0; } -static void bat_get_drvinfo(struct net_device *dev, - struct ethtool_drvinfo *info) +static void batadv_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) { strcpy(info->driver, "B.A.T.M.A.N. advanced"); - strcpy(info->version, SOURCE_VERSION); + strcpy(info->version, BATADV_SOURCE_VERSION); strcpy(info->fw_version, "N/A"); strcpy(info->bus_info, "batman"); } -static u32 bat_get_msglevel(struct net_device *dev) +static u32 batadv_get_msglevel(struct net_device *dev) { return -EOPNOTSUPP; } -static void bat_set_msglevel(struct net_device *dev, u32 value) +static void batadv_set_msglevel(struct net_device *dev, u32 value) { } -static u32 bat_get_link(struct net_device *dev) +static u32 batadv_get_link(struct net_device *dev) { return 1; } + +/* Inspired by drivers/net/ethernet/dlink/sundance.c:1702 + * Declare each description string in struct.name[] to get fixed sized buffer + * and compile time checking for strings longer than ETH_GSTRING_LEN. + */ +static const struct { + const char name[ETH_GSTRING_LEN]; +} batadv_counters_strings[] = { + { "forward" }, + { "forward_bytes" }, + { "mgmt_tx" }, + { "mgmt_tx_bytes" }, + { "mgmt_rx" }, + { "mgmt_rx_bytes" }, + { "tt_request_tx" }, + { "tt_request_rx" }, + { "tt_response_tx" }, + { "tt_response_rx" }, + { "tt_roam_adv_tx" }, + { "tt_roam_adv_rx" }, +}; + +static void batadv_get_strings(struct net_device *dev, uint32_t stringset, + uint8_t *data) +{ + if (stringset == ETH_SS_STATS) + memcpy(data, batadv_counters_strings, + sizeof(batadv_counters_strings)); +} + +static void batadv_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, + uint64_t *data) +{ + struct batadv_priv *bat_priv = netdev_priv(dev); + int i; + + for (i = 0; i < BATADV_CNT_NUM; i++) + data[i] = batadv_sum_counter(bat_priv, i); +} + +static int batadv_get_sset_count(struct net_device *dev, int stringset) +{ + if (stringset == ETH_SS_STATS) + return BATADV_CNT_NUM; + + return -EOPNOTSUPP; +} diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 02030067388..852c683b06a 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -16,18 +15,16 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_SOFT_INTERFACE_H_ #define _NET_BATMAN_ADV_SOFT_INTERFACE_H_ -int my_skb_head_push(struct sk_buff *skb, unsigned int len); -void interface_rx(struct net_device *soft_iface, - struct sk_buff *skb, struct hard_iface *recv_if, - int hdr_size); -struct net_device *softif_create(const char *name); -void softif_destroy(struct net_device *soft_iface); -int softif_is_valid(const struct net_device *net_dev); +int batadv_skb_head_push(struct sk_buff *skb, unsigned int len); +void batadv_interface_rx(struct net_device *soft_iface, struct sk_buff *skb, + struct batadv_hard_iface *recv_if, int hdr_size); +struct net_device *batadv_softif_create(const char *name); +void batadv_softif_destroy(struct net_device *soft_iface); +int batadv_softif_is_valid(const struct net_device *net_dev); #endif /* _NET_BATMAN_ADV_SOFT_INTERFACE_H_ */ diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c new file mode 100644 index 00000000000..66518c75c21 --- /dev/null +++ b/net/batman-adv/sysfs.c @@ -0,0 +1,787 @@ +/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: + * + * Marek Lindner + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA + */ + +#include "main.h" +#include "sysfs.h" +#include "translation-table.h" +#include "originator.h" +#include "hard-interface.h" +#include "gateway_common.h" +#include "gateway_client.h" +#include "vis.h" + +static struct net_device *batadv_kobj_to_netdev(struct kobject *obj) +{ + struct device *dev = container_of(obj->parent, struct device, kobj); + return to_net_dev(dev); +} + +static struct batadv_priv *batadv_kobj_to_batpriv(struct kobject *obj) +{ + struct net_device *net_dev = batadv_kobj_to_netdev(obj); + return netdev_priv(net_dev); +} + +#define BATADV_UEV_TYPE_VAR "BATTYPE=" +#define BATADV_UEV_ACTION_VAR "BATACTION=" +#define BATADV_UEV_DATA_VAR "BATDATA=" + +static char *batadv_uev_action_str[] = { + "add", + "del", + "change" +}; + +static char *batadv_uev_type_str[] = { + "gw" +}; + +/* Use this, if you have customized show and store functions */ +#define BATADV_ATTR(_name, _mode, _show, _store) \ +struct batadv_attribute batadv_attr_##_name = { \ + .attr = {.name = __stringify(_name), \ + .mode = _mode }, \ + .show = _show, \ + .store = _store, \ +}; + +#define BATADV_ATTR_SIF_STORE_BOOL(_name, _post_func) \ +ssize_t batadv_store_##_name(struct kobject *kobj, \ + struct attribute *attr, char *buff, \ + size_t count) \ +{ \ + struct net_device *net_dev = batadv_kobj_to_netdev(kobj); \ + struct batadv_priv *bat_priv = netdev_priv(net_dev); \ + return __batadv_store_bool_attr(buff, count, _post_func, attr, \ + &bat_priv->_name, net_dev); \ +} + +#define BATADV_ATTR_SIF_SHOW_BOOL(_name) \ +ssize_t batadv_show_##_name(struct kobject *kobj, \ + struct attribute *attr, char *buff) \ +{ \ + struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); \ + return sprintf(buff, "%s\n", \ + atomic_read(&bat_priv->_name) == 0 ? \ + "disabled" : "enabled"); \ +} \ + +/* Use this, if you are going to turn a [name] in the soft-interface + * (bat_priv) on or off + */ +#define BATADV_ATTR_SIF_BOOL(_name, _mode, _post_func) \ + static BATADV_ATTR_SIF_STORE_BOOL(_name, _post_func) \ + static BATADV_ATTR_SIF_SHOW_BOOL(_name) \ + static BATADV_ATTR(_name, _mode, batadv_show_##_name, \ + batadv_store_##_name) + + +#define BATADV_ATTR_SIF_STORE_UINT(_name, _min, _max, _post_func) \ +ssize_t batadv_store_##_name(struct kobject *kobj, \ + struct attribute *attr, char *buff, \ + size_t count) \ +{ \ + struct net_device *net_dev = batadv_kobj_to_netdev(kobj); \ + struct batadv_priv *bat_priv = netdev_priv(net_dev); \ + return __batadv_store_uint_attr(buff, count, _min, _max, \ + _post_func, attr, \ + &bat_priv->_name, net_dev); \ +} + +#define BATADV_ATTR_SIF_SHOW_UINT(_name) \ +ssize_t batadv_show_##_name(struct kobject *kobj, \ + struct attribute *attr, char *buff) \ +{ \ + struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); \ + return sprintf(buff, "%i\n", atomic_read(&bat_priv->_name)); \ +} \ + +/* Use this, if you are going to set [name] in the soft-interface + * (bat_priv) to an unsigned integer value + */ +#define BATADV_ATTR_SIF_UINT(_name, _mode, _min, _max, _post_func) \ + static BATADV_ATTR_SIF_STORE_UINT(_name, _min, _max, _post_func)\ + static BATADV_ATTR_SIF_SHOW_UINT(_name) \ + static BATADV_ATTR(_name, _mode, batadv_show_##_name, \ + batadv_store_##_name) + + +#define BATADV_ATTR_HIF_STORE_UINT(_name, _min, _max, _post_func) \ +ssize_t batadv_store_##_name(struct kobject *kobj, \ + struct attribute *attr, char *buff, \ + size_t count) \ +{ \ + struct net_device *net_dev = batadv_kobj_to_netdev(kobj); \ + struct batadv_hard_iface *hard_iface; \ + ssize_t length; \ + \ + hard_iface = batadv_hardif_get_by_netdev(net_dev); \ + if (!hard_iface) \ + return 0; \ + \ + length = __batadv_store_uint_attr(buff, count, _min, _max, \ + _post_func, attr, \ + &hard_iface->_name, net_dev); \ + \ + batadv_hardif_free_ref(hard_iface); \ + return length; \ +} + +#define BATADV_ATTR_HIF_SHOW_UINT(_name) \ +ssize_t batadv_show_##_name(struct kobject *kobj, \ + struct attribute *attr, char *buff) \ +{ \ + struct net_device *net_dev = batadv_kobj_to_netdev(kobj); \ + struct batadv_hard_iface *hard_iface; \ + ssize_t length; \ + \ + hard_iface = batadv_hardif_get_by_netdev(net_dev); \ + if (!hard_iface) \ + return 0; \ + \ + length = sprintf(buff, "%i\n", atomic_read(&hard_iface->_name));\ + \ + batadv_hardif_free_ref(hard_iface); \ + return length; \ +} + +/* Use this, if you are going to set [name] in hard_iface to an + * unsigned integer value + */ +#define BATADV_ATTR_HIF_UINT(_name, _mode, _min, _max, _post_func) \ + static BATADV_ATTR_HIF_STORE_UINT(_name, _min, _max, _post_func)\ + static BATADV_ATTR_HIF_SHOW_UINT(_name) \ + static BATADV_ATTR(_name, _mode, batadv_show_##_name, \ + batadv_store_##_name) + + +static int batadv_store_bool_attr(char *buff, size_t count, + struct net_device *net_dev, + const char *attr_name, atomic_t *attr) +{ + int enabled = -1; + + if (buff[count - 1] == '\n') + buff[count - 1] = '\0'; + + if ((strncmp(buff, "1", 2) == 0) || + (strncmp(buff, "enable", 7) == 0) || + (strncmp(buff, "enabled", 8) == 0)) + enabled = 1; + + if ((strncmp(buff, "0", 2) == 0) || + (strncmp(buff, "disable", 8) == 0) || + (strncmp(buff, "disabled", 9) == 0)) + enabled = 0; + + if (enabled < 0) { + batadv_info(net_dev, "%s: Invalid parameter received: %s\n", + attr_name, buff); + return -EINVAL; + } + + if (atomic_read(attr) == enabled) + return count; + + batadv_info(net_dev, "%s: Changing from: %s to: %s\n", attr_name, + atomic_read(attr) == 1 ? "enabled" : "disabled", + enabled == 1 ? "enabled" : "disabled"); + + atomic_set(attr, (unsigned int)enabled); + return count; +} + +static inline ssize_t +__batadv_store_bool_attr(char *buff, size_t count, + void (*post_func)(struct net_device *), + struct attribute *attr, + atomic_t *attr_store, struct net_device *net_dev) +{ + int ret; + + ret = batadv_store_bool_attr(buff, count, net_dev, attr->name, + attr_store); + if (post_func && ret) + post_func(net_dev); + + return ret; +} + +static int batadv_store_uint_attr(const char *buff, size_t count, + struct net_device *net_dev, + const char *attr_name, + unsigned int min, unsigned int max, + atomic_t *attr) +{ + unsigned long uint_val; + int ret; + + ret = kstrtoul(buff, 10, &uint_val); + if (ret) { + batadv_info(net_dev, "%s: Invalid parameter received: %s\n", + attr_name, buff); + return -EINVAL; + } + + if (uint_val < min) { + batadv_info(net_dev, "%s: Value is too small: %lu min: %u\n", + attr_name, uint_val, min); + return -EINVAL; + } + + if (uint_val > max) { + batadv_info(net_dev, "%s: Value is too big: %lu max: %u\n", + attr_name, uint_val, max); + return -EINVAL; + } + + if (atomic_read(attr) == uint_val) + return count; + + batadv_info(net_dev, "%s: Changing from: %i to: %lu\n", + attr_name, atomic_read(attr), uint_val); + + atomic_set(attr, uint_val); + return count; +} + +static inline ssize_t +__batadv_store_uint_attr(const char *buff, size_t count, + int min, int max, + void (*post_func)(struct net_device *), + const struct attribute *attr, + atomic_t *attr_store, struct net_device *net_dev) +{ + int ret; + + ret = batadv_store_uint_attr(buff, count, net_dev, attr->name, min, max, + attr_store); + if (post_func && ret) + post_func(net_dev); + + return ret; +} + +static ssize_t batadv_show_vis_mode(struct kobject *kobj, + struct attribute *attr, char *buff) +{ + struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); + int vis_mode = atomic_read(&bat_priv->vis_mode); + const char *mode; + + if (vis_mode == BATADV_VIS_TYPE_CLIENT_UPDATE) + mode = "client"; + else + mode = "server"; + + return sprintf(buff, "%s\n", mode); +} + +static ssize_t batadv_store_vis_mode(struct kobject *kobj, + struct attribute *attr, char *buff, + size_t count) +{ + struct net_device *net_dev = batadv_kobj_to_netdev(kobj); + struct batadv_priv *bat_priv = netdev_priv(net_dev); + unsigned long val; + int ret, vis_mode_tmp = -1; + const char *old_mode, *new_mode; + + ret = kstrtoul(buff, 10, &val); + + if (((count == 2) && (!ret) && + (val == BATADV_VIS_TYPE_CLIENT_UPDATE)) || + (strncmp(buff, "client", 6) == 0) || + (strncmp(buff, "off", 3) == 0)) + vis_mode_tmp = BATADV_VIS_TYPE_CLIENT_UPDATE; + + if (((count == 2) && (!ret) && + (val == BATADV_VIS_TYPE_SERVER_SYNC)) || + (strncmp(buff, "server", 6) == 0)) + vis_mode_tmp = BATADV_VIS_TYPE_SERVER_SYNC; + + if (vis_mode_tmp < 0) { + if (buff[count - 1] == '\n') + buff[count - 1] = '\0'; + + batadv_info(net_dev, + "Invalid parameter for 'vis mode' setting received: %s\n", + buff); + return -EINVAL; + } + + if (atomic_read(&bat_priv->vis_mode) == vis_mode_tmp) + return count; + + if (atomic_read(&bat_priv->vis_mode) == BATADV_VIS_TYPE_CLIENT_UPDATE) + old_mode = "client"; + else + old_mode = "server"; + + if (vis_mode_tmp == BATADV_VIS_TYPE_CLIENT_UPDATE) + new_mode = "client"; + else + new_mode = "server"; + + batadv_info(net_dev, "Changing vis mode from: %s to: %s\n", old_mode, + new_mode); + + atomic_set(&bat_priv->vis_mode, (unsigned int)vis_mode_tmp); + return count; +} + +static ssize_t batadv_show_bat_algo(struct kobject *kobj, + struct attribute *attr, char *buff) +{ + struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); + return sprintf(buff, "%s\n", bat_priv->bat_algo_ops->name); +} + +static void batadv_post_gw_deselect(struct net_device *net_dev) +{ + struct batadv_priv *bat_priv = netdev_priv(net_dev); + batadv_gw_deselect(bat_priv); +} + +static ssize_t batadv_show_gw_mode(struct kobject *kobj, struct attribute *attr, + char *buff) +{ + struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); + int bytes_written; + + switch (atomic_read(&bat_priv->gw_mode)) { + case BATADV_GW_MODE_CLIENT: + bytes_written = sprintf(buff, "%s\n", + BATADV_GW_MODE_CLIENT_NAME); + break; + case BATADV_GW_MODE_SERVER: + bytes_written = sprintf(buff, "%s\n", + BATADV_GW_MODE_SERVER_NAME); + break; + default: + bytes_written = sprintf(buff, "%s\n", + BATADV_GW_MODE_OFF_NAME); + break; + } + + return bytes_written; +} + +static ssize_t batadv_store_gw_mode(struct kobject *kobj, + struct attribute *attr, char *buff, + size_t count) +{ + struct net_device *net_dev = batadv_kobj_to_netdev(kobj); + struct batadv_priv *bat_priv = netdev_priv(net_dev); + char *curr_gw_mode_str; + int gw_mode_tmp = -1; + + if (buff[count - 1] == '\n') + buff[count - 1] = '\0'; + + if (strncmp(buff, BATADV_GW_MODE_OFF_NAME, + strlen(BATADV_GW_MODE_OFF_NAME)) == 0) + gw_mode_tmp = BATADV_GW_MODE_OFF; + + if (strncmp(buff, BATADV_GW_MODE_CLIENT_NAME, + strlen(BATADV_GW_MODE_CLIENT_NAME)) == 0) + gw_mode_tmp = BATADV_GW_MODE_CLIENT; + + if (strncmp(buff, BATADV_GW_MODE_SERVER_NAME, + strlen(BATADV_GW_MODE_SERVER_NAME)) == 0) + gw_mode_tmp = BATADV_GW_MODE_SERVER; + + if (gw_mode_tmp < 0) { + batadv_info(net_dev, + "Invalid parameter for 'gw mode' setting received: %s\n", + buff); + return -EINVAL; + } + + if (atomic_read(&bat_priv->gw_mode) == gw_mode_tmp) + return count; + + switch (atomic_read(&bat_priv->gw_mode)) { + case BATADV_GW_MODE_CLIENT: + curr_gw_mode_str = BATADV_GW_MODE_CLIENT_NAME; + break; + case BATADV_GW_MODE_SERVER: + curr_gw_mode_str = BATADV_GW_MODE_SERVER_NAME; + break; + default: + curr_gw_mode_str = BATADV_GW_MODE_OFF_NAME; + break; + } + + batadv_info(net_dev, "Changing gw mode from: %s to: %s\n", + curr_gw_mode_str, buff); + + batadv_gw_deselect(bat_priv); + atomic_set(&bat_priv->gw_mode, (unsigned int)gw_mode_tmp); + return count; +} + +static ssize_t batadv_show_gw_bwidth(struct kobject *kobj, + struct attribute *attr, char *buff) +{ + struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); + int down, up; + int gw_bandwidth = atomic_read(&bat_priv->gw_bandwidth); + + batadv_gw_bandwidth_to_kbit(gw_bandwidth, &down, &up); + return sprintf(buff, "%i%s/%i%s\n", + (down > 2048 ? down / 1024 : down), + (down > 2048 ? "MBit" : "KBit"), + (up > 2048 ? up / 1024 : up), + (up > 2048 ? "MBit" : "KBit")); +} + +static ssize_t batadv_store_gw_bwidth(struct kobject *kobj, + struct attribute *attr, char *buff, + size_t count) +{ + struct net_device *net_dev = batadv_kobj_to_netdev(kobj); + + if (buff[count - 1] == '\n') + buff[count - 1] = '\0'; + + return batadv_gw_bandwidth_set(net_dev, buff, count); +} + +BATADV_ATTR_SIF_BOOL(aggregated_ogms, S_IRUGO | S_IWUSR, NULL); +BATADV_ATTR_SIF_BOOL(bonding, S_IRUGO | S_IWUSR, NULL); +#ifdef CONFIG_BATMAN_ADV_BLA +BATADV_ATTR_SIF_BOOL(bridge_loop_avoidance, S_IRUGO | S_IWUSR, NULL); +#endif +BATADV_ATTR_SIF_BOOL(fragmentation, S_IRUGO | S_IWUSR, batadv_update_min_mtu); +BATADV_ATTR_SIF_BOOL(ap_isolation, S_IRUGO | S_IWUSR, NULL); +static BATADV_ATTR(vis_mode, S_IRUGO | S_IWUSR, batadv_show_vis_mode, + batadv_store_vis_mode); +static BATADV_ATTR(routing_algo, S_IRUGO, batadv_show_bat_algo, NULL); +static BATADV_ATTR(gw_mode, S_IRUGO | S_IWUSR, batadv_show_gw_mode, + batadv_store_gw_mode); +BATADV_ATTR_SIF_UINT(orig_interval, S_IRUGO | S_IWUSR, 2 * BATADV_JITTER, + INT_MAX, NULL); +BATADV_ATTR_SIF_UINT(hop_penalty, S_IRUGO | S_IWUSR, 0, BATADV_TQ_MAX_VALUE, + NULL); +BATADV_ATTR_SIF_UINT(gw_sel_class, S_IRUGO | S_IWUSR, 1, BATADV_TQ_MAX_VALUE, + batadv_post_gw_deselect); +static BATADV_ATTR(gw_bandwidth, S_IRUGO | S_IWUSR, batadv_show_gw_bwidth, + batadv_store_gw_bwidth); +#ifdef CONFIG_BATMAN_ADV_DEBUG +BATADV_ATTR_SIF_UINT(log_level, S_IRUGO | S_IWUSR, 0, BATADV_DBG_ALL, NULL); +#endif + +static struct batadv_attribute *batadv_mesh_attrs[] = { + &batadv_attr_aggregated_ogms, + &batadv_attr_bonding, +#ifdef CONFIG_BATMAN_ADV_BLA + &batadv_attr_bridge_loop_avoidance, +#endif + &batadv_attr_fragmentation, + &batadv_attr_ap_isolation, + &batadv_attr_vis_mode, + &batadv_attr_routing_algo, + &batadv_attr_gw_mode, + &batadv_attr_orig_interval, + &batadv_attr_hop_penalty, + &batadv_attr_gw_sel_class, + &batadv_attr_gw_bandwidth, +#ifdef CONFIG_BATMAN_ADV_DEBUG + &batadv_attr_log_level, +#endif + NULL, +}; + +int batadv_sysfs_add_meshif(struct net_device *dev) +{ + struct kobject *batif_kobject = &dev->dev.kobj; + struct batadv_priv *bat_priv = netdev_priv(dev); + struct batadv_attribute **bat_attr; + int err; + + bat_priv->mesh_obj = kobject_create_and_add(BATADV_SYSFS_IF_MESH_SUBDIR, + batif_kobject); + if (!bat_priv->mesh_obj) { + batadv_err(dev, "Can't add sysfs directory: %s/%s\n", dev->name, + BATADV_SYSFS_IF_MESH_SUBDIR); + goto out; + } + + for (bat_attr = batadv_mesh_attrs; *bat_attr; ++bat_attr) { + err = sysfs_create_file(bat_priv->mesh_obj, + &((*bat_attr)->attr)); + if (err) { + batadv_err(dev, "Can't add sysfs file: %s/%s/%s\n", + dev->name, BATADV_SYSFS_IF_MESH_SUBDIR, + ((*bat_attr)->attr).name); + goto rem_attr; + } + } + + return 0; + +rem_attr: + for (bat_attr = batadv_mesh_attrs; *bat_attr; ++bat_attr) + sysfs_remove_file(bat_priv->mesh_obj, &((*bat_attr)->attr)); + + kobject_put(bat_priv->mesh_obj); + bat_priv->mesh_obj = NULL; +out: + return -ENOMEM; +} + +void batadv_sysfs_del_meshif(struct net_device *dev) +{ + struct batadv_priv *bat_priv = netdev_priv(dev); + struct batadv_attribute **bat_attr; + + for (bat_attr = batadv_mesh_attrs; *bat_attr; ++bat_attr) + sysfs_remove_file(bat_priv->mesh_obj, &((*bat_attr)->attr)); + + kobject_put(bat_priv->mesh_obj); + bat_priv->mesh_obj = NULL; +} + +static ssize_t batadv_show_mesh_iface(struct kobject *kobj, + struct attribute *attr, char *buff) +{ + struct net_device *net_dev = batadv_kobj_to_netdev(kobj); + struct batadv_hard_iface *hard_iface; + ssize_t length; + const char *ifname; + + hard_iface = batadv_hardif_get_by_netdev(net_dev); + if (!hard_iface) + return 0; + + if (hard_iface->if_status == BATADV_IF_NOT_IN_USE) + ifname = "none"; + else + ifname = hard_iface->soft_iface->name; + + length = sprintf(buff, "%s\n", ifname); + + batadv_hardif_free_ref(hard_iface); + + return length; +} + +static ssize_t batadv_store_mesh_iface(struct kobject *kobj, + struct attribute *attr, char *buff, + size_t count) +{ + struct net_device *net_dev = batadv_kobj_to_netdev(kobj); + struct batadv_hard_iface *hard_iface; + int status_tmp = -1; + int ret = count; + + hard_iface = batadv_hardif_get_by_netdev(net_dev); + if (!hard_iface) + return count; + + if (buff[count - 1] == '\n') + buff[count - 1] = '\0'; + + if (strlen(buff) >= IFNAMSIZ) { + pr_err("Invalid parameter for 'mesh_iface' setting received: interface name too long '%s'\n", + buff); + batadv_hardif_free_ref(hard_iface); + return -EINVAL; + } + + if (strncmp(buff, "none", 4) == 0) + status_tmp = BATADV_IF_NOT_IN_USE; + else + status_tmp = BATADV_IF_I_WANT_YOU; + + if (hard_iface->if_status == status_tmp) + goto out; + + if ((hard_iface->soft_iface) && + (strncmp(hard_iface->soft_iface->name, buff, IFNAMSIZ) == 0)) + goto out; + + if (!rtnl_trylock()) { + ret = -ERESTARTSYS; + goto out; + } + + if (status_tmp == BATADV_IF_NOT_IN_USE) { + batadv_hardif_disable_interface(hard_iface); + goto unlock; + } + + /* if the interface already is in use */ + if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) + batadv_hardif_disable_interface(hard_iface); + + ret = batadv_hardif_enable_interface(hard_iface, buff); + +unlock: + rtnl_unlock(); +out: + batadv_hardif_free_ref(hard_iface); + return ret; +} + +static ssize_t batadv_show_iface_status(struct kobject *kobj, + struct attribute *attr, char *buff) +{ + struct net_device *net_dev = batadv_kobj_to_netdev(kobj); + struct batadv_hard_iface *hard_iface; + ssize_t length; + + hard_iface = batadv_hardif_get_by_netdev(net_dev); + if (!hard_iface) + return 0; + + switch (hard_iface->if_status) { + case BATADV_IF_TO_BE_REMOVED: + length = sprintf(buff, "disabling\n"); + break; + case BATADV_IF_INACTIVE: + length = sprintf(buff, "inactive\n"); + break; + case BATADV_IF_ACTIVE: + length = sprintf(buff, "active\n"); + break; + case BATADV_IF_TO_BE_ACTIVATED: + length = sprintf(buff, "enabling\n"); + break; + case BATADV_IF_NOT_IN_USE: + default: + length = sprintf(buff, "not in use\n"); + break; + } + + batadv_hardif_free_ref(hard_iface); + + return length; +} + +static BATADV_ATTR(mesh_iface, S_IRUGO | S_IWUSR, batadv_show_mesh_iface, + batadv_store_mesh_iface); +static BATADV_ATTR(iface_status, S_IRUGO, batadv_show_iface_status, NULL); + +static struct batadv_attribute *batadv_batman_attrs[] = { + &batadv_attr_mesh_iface, + &batadv_attr_iface_status, + NULL, +}; + +int batadv_sysfs_add_hardif(struct kobject **hardif_obj, struct net_device *dev) +{ + struct kobject *hardif_kobject = &dev->dev.kobj; + struct batadv_attribute **bat_attr; + int err; + + *hardif_obj = kobject_create_and_add(BATADV_SYSFS_IF_BAT_SUBDIR, + hardif_kobject); + + if (!*hardif_obj) { + batadv_err(dev, "Can't add sysfs directory: %s/%s\n", dev->name, + BATADV_SYSFS_IF_BAT_SUBDIR); + goto out; + } + + for (bat_attr = batadv_batman_attrs; *bat_attr; ++bat_attr) { + err = sysfs_create_file(*hardif_obj, &((*bat_attr)->attr)); + if (err) { + batadv_err(dev, "Can't add sysfs file: %s/%s/%s\n", + dev->name, BATADV_SYSFS_IF_BAT_SUBDIR, + ((*bat_attr)->attr).name); + goto rem_attr; + } + } + + return 0; + +rem_attr: + for (bat_attr = batadv_batman_attrs; *bat_attr; ++bat_attr) + sysfs_remove_file(*hardif_obj, &((*bat_attr)->attr)); +out: + return -ENOMEM; +} + +void batadv_sysfs_del_hardif(struct kobject **hardif_obj) +{ + kobject_put(*hardif_obj); + *hardif_obj = NULL; +} + +int batadv_throw_uevent(struct batadv_priv *bat_priv, enum batadv_uev_type type, + enum batadv_uev_action action, const char *data) +{ + int ret = -ENOMEM; + struct batadv_hard_iface *primary_if = NULL; + struct kobject *bat_kobj; + char *uevent_env[4] = { NULL, NULL, NULL, NULL }; + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + + bat_kobj = &primary_if->soft_iface->dev.kobj; + + uevent_env[0] = kmalloc(strlen(BATADV_UEV_TYPE_VAR) + + strlen(batadv_uev_type_str[type]) + 1, + GFP_ATOMIC); + if (!uevent_env[0]) + goto out; + + sprintf(uevent_env[0], "%s%s", BATADV_UEV_TYPE_VAR, + batadv_uev_type_str[type]); + + uevent_env[1] = kmalloc(strlen(BATADV_UEV_ACTION_VAR) + + strlen(batadv_uev_action_str[action]) + 1, + GFP_ATOMIC); + if (!uevent_env[1]) + goto out; + + sprintf(uevent_env[1], "%s%s", BATADV_UEV_ACTION_VAR, + batadv_uev_action_str[action]); + + /* If the event is DEL, ignore the data field */ + if (action != BATADV_UEV_DEL) { + uevent_env[2] = kmalloc(strlen(BATADV_UEV_DATA_VAR) + + strlen(data) + 1, GFP_ATOMIC); + if (!uevent_env[2]) + goto out; + + sprintf(uevent_env[2], "%s%s", BATADV_UEV_DATA_VAR, data); + } + + ret = kobject_uevent_env(bat_kobj, KOBJ_CHANGE, uevent_env); +out: + kfree(uevent_env[0]); + kfree(uevent_env[1]); + kfree(uevent_env[2]); + + if (primary_if) + batadv_hardif_free_ref(primary_if); + + if (ret) + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Impossible to send uevent for (%s,%s,%s) event (err: %d)\n", + batadv_uev_type_str[type], + batadv_uev_action_str[action], + (action == BATADV_UEV_DEL ? "NULL" : data), ret); + return ret; +} diff --git a/net/batman-adv/bat_sysfs.h b/net/batman-adv/sysfs.h index fece77ae586..3fd1412b062 100644 --- a/net/batman-adv/bat_sysfs.h +++ b/net/batman-adv/sysfs.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -16,17 +15,15 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ - #ifndef _NET_BATMAN_ADV_SYSFS_H_ #define _NET_BATMAN_ADV_SYSFS_H_ -#define SYSFS_IF_MESH_SUBDIR "mesh" -#define SYSFS_IF_BAT_SUBDIR "batman_adv" +#define BATADV_SYSFS_IF_MESH_SUBDIR "mesh" +#define BATADV_SYSFS_IF_BAT_SUBDIR "batman_adv" -struct bat_attribute { +struct batadv_attribute { struct attribute attr; ssize_t (*show)(struct kobject *kobj, struct attribute *attr, char *buf); @@ -34,11 +31,12 @@ struct bat_attribute { char *buf, size_t count); }; -int sysfs_add_meshif(struct net_device *dev); -void sysfs_del_meshif(struct net_device *dev); -int sysfs_add_hardif(struct kobject **hardif_obj, struct net_device *dev); -void sysfs_del_hardif(struct kobject **hardif_obj); -int throw_uevent(struct bat_priv *bat_priv, enum uev_type type, - enum uev_action action, const char *data); +int batadv_sysfs_add_meshif(struct net_device *dev); +void batadv_sysfs_del_meshif(struct net_device *dev); +int batadv_sysfs_add_hardif(struct kobject **hardif_obj, + struct net_device *dev); +void batadv_sysfs_del_hardif(struct kobject **hardif_obj); +int batadv_throw_uevent(struct batadv_priv *bat_priv, enum batadv_uev_type type, + enum batadv_uev_action action, const char *data); #endif /* _NET_BATMAN_ADV_SYSFS_H_ */ diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 2ab83d7fb1f..99dd8f75b3f 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" @@ -31,44 +29,46 @@ #include <linux/crc16.h> -static void send_roam_adv(struct bat_priv *bat_priv, uint8_t *client, - struct orig_node *orig_node); -static void tt_purge(struct work_struct *work); -static void tt_global_del_orig_list(struct tt_global_entry *tt_global_entry); +static void batadv_send_roam_adv(struct batadv_priv *bat_priv, uint8_t *client, + struct batadv_orig_node *orig_node); +static void batadv_tt_purge(struct work_struct *work); +static void +batadv_tt_global_del_orig_list(struct batadv_tt_global_entry *tt_global_entry); /* returns 1 if they are the same mac addr */ -static int compare_tt(const struct hlist_node *node, const void *data2) +static int batadv_compare_tt(const struct hlist_node *node, const void *data2) { - const void *data1 = container_of(node, struct tt_common_entry, + const void *data1 = container_of(node, struct batadv_tt_common_entry, hash_entry); return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); } -static void tt_start_timer(struct bat_priv *bat_priv) +static void batadv_tt_start_timer(struct batadv_priv *bat_priv) { - INIT_DELAYED_WORK(&bat_priv->tt_work, tt_purge); - queue_delayed_work(bat_event_workqueue, &bat_priv->tt_work, + INIT_DELAYED_WORK(&bat_priv->tt_work, batadv_tt_purge); + queue_delayed_work(batadv_event_workqueue, &bat_priv->tt_work, msecs_to_jiffies(5000)); } -static struct tt_common_entry *tt_hash_find(struct hashtable_t *hash, - const void *data) +static struct batadv_tt_common_entry * +batadv_tt_hash_find(struct batadv_hashtable *hash, const void *data) { struct hlist_head *head; struct hlist_node *node; - struct tt_common_entry *tt_common_entry, *tt_common_entry_tmp = NULL; + struct batadv_tt_common_entry *tt_common_entry; + struct batadv_tt_common_entry *tt_common_entry_tmp = NULL; uint32_t index; if (!hash) return NULL; - index = choose_orig(data, hash->size); + index = batadv_choose_orig(data, hash->size); head = &hash->table[index]; rcu_read_lock(); hlist_for_each_entry_rcu(tt_common_entry, node, head, hash_entry) { - if (!compare_eth(tt_common_entry, data)) + if (!batadv_compare_eth(tt_common_entry, data)) continue; if (!atomic_inc_not_zero(&tt_common_entry->refcount)) @@ -82,80 +82,87 @@ static struct tt_common_entry *tt_hash_find(struct hashtable_t *hash, return tt_common_entry_tmp; } -static struct tt_local_entry *tt_local_hash_find(struct bat_priv *bat_priv, - const void *data) +static struct batadv_tt_local_entry * +batadv_tt_local_hash_find(struct batadv_priv *bat_priv, const void *data) { - struct tt_common_entry *tt_common_entry; - struct tt_local_entry *tt_local_entry = NULL; + struct batadv_tt_common_entry *tt_common_entry; + struct batadv_tt_local_entry *tt_local_entry = NULL; - tt_common_entry = tt_hash_find(bat_priv->tt_local_hash, data); + tt_common_entry = batadv_tt_hash_find(bat_priv->tt_local_hash, data); if (tt_common_entry) tt_local_entry = container_of(tt_common_entry, - struct tt_local_entry, common); + struct batadv_tt_local_entry, + common); return tt_local_entry; } -static struct tt_global_entry *tt_global_hash_find(struct bat_priv *bat_priv, - const void *data) +static struct batadv_tt_global_entry * +batadv_tt_global_hash_find(struct batadv_priv *bat_priv, const void *data) { - struct tt_common_entry *tt_common_entry; - struct tt_global_entry *tt_global_entry = NULL; + struct batadv_tt_common_entry *tt_common_entry; + struct batadv_tt_global_entry *tt_global_entry = NULL; - tt_common_entry = tt_hash_find(bat_priv->tt_global_hash, data); + tt_common_entry = batadv_tt_hash_find(bat_priv->tt_global_hash, data); if (tt_common_entry) tt_global_entry = container_of(tt_common_entry, - struct tt_global_entry, common); + struct batadv_tt_global_entry, + common); return tt_global_entry; } -static void tt_local_entry_free_ref(struct tt_local_entry *tt_local_entry) +static void +batadv_tt_local_entry_free_ref(struct batadv_tt_local_entry *tt_local_entry) { if (atomic_dec_and_test(&tt_local_entry->common.refcount)) kfree_rcu(tt_local_entry, common.rcu); } -static void tt_global_entry_free_rcu(struct rcu_head *rcu) +static void batadv_tt_global_entry_free_rcu(struct rcu_head *rcu) { - struct tt_common_entry *tt_common_entry; - struct tt_global_entry *tt_global_entry; + struct batadv_tt_common_entry *tt_common_entry; + struct batadv_tt_global_entry *tt_global_entry; - tt_common_entry = container_of(rcu, struct tt_common_entry, rcu); - tt_global_entry = container_of(tt_common_entry, struct tt_global_entry, - common); + tt_common_entry = container_of(rcu, struct batadv_tt_common_entry, rcu); + tt_global_entry = container_of(tt_common_entry, + struct batadv_tt_global_entry, common); kfree(tt_global_entry); } -static void tt_global_entry_free_ref(struct tt_global_entry *tt_global_entry) +static void +batadv_tt_global_entry_free_ref(struct batadv_tt_global_entry *tt_global_entry) { if (atomic_dec_and_test(&tt_global_entry->common.refcount)) { - tt_global_del_orig_list(tt_global_entry); + batadv_tt_global_del_orig_list(tt_global_entry); call_rcu(&tt_global_entry->common.rcu, - tt_global_entry_free_rcu); + batadv_tt_global_entry_free_rcu); } } -static void tt_orig_list_entry_free_rcu(struct rcu_head *rcu) +static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu) { - struct tt_orig_list_entry *orig_entry; + struct batadv_tt_orig_list_entry *orig_entry; - orig_entry = container_of(rcu, struct tt_orig_list_entry, rcu); - orig_node_free_ref(orig_entry->orig_node); + orig_entry = container_of(rcu, struct batadv_tt_orig_list_entry, rcu); + batadv_orig_node_free_ref(orig_entry->orig_node); kfree(orig_entry); } -static void tt_orig_list_entry_free_ref(struct tt_orig_list_entry *orig_entry) +static void +batadv_tt_orig_list_entry_free_ref(struct batadv_tt_orig_list_entry *orig_entry) { /* to avoid race conditions, immediately decrease the tt counter */ atomic_dec(&orig_entry->orig_node->tt_size); - call_rcu(&orig_entry->rcu, tt_orig_list_entry_free_rcu); + call_rcu(&orig_entry->rcu, batadv_tt_orig_list_entry_free_rcu); } -static void tt_local_event(struct bat_priv *bat_priv, const uint8_t *addr, - uint8_t flags) +static void batadv_tt_local_event(struct batadv_priv *bat_priv, + const uint8_t *addr, uint8_t flags) { - struct tt_change_node *tt_change_node; + struct batadv_tt_change_node *tt_change_node, *entry, *safe; + bool event_removed = false; + bool del_op_requested, del_op_entry; tt_change_node = kmalloc(sizeof(*tt_change_node), GFP_ATOMIC); @@ -165,50 +172,83 @@ static void tt_local_event(struct bat_priv *bat_priv, const uint8_t *addr, tt_change_node->change.flags = flags; memcpy(tt_change_node->change.addr, addr, ETH_ALEN); + del_op_requested = flags & BATADV_TT_CLIENT_DEL; + + /* check for ADD+DEL or DEL+ADD events */ spin_lock_bh(&bat_priv->tt_changes_list_lock); + list_for_each_entry_safe(entry, safe, &bat_priv->tt_changes_list, + list) { + if (!batadv_compare_eth(entry->change.addr, addr)) + continue; + + /* DEL+ADD in the same orig interval have no effect and can be + * removed to avoid silly behaviour on the receiver side. The + * other way around (ADD+DEL) can happen in case of roaming of + * a client still in the NEW state. Roaming of NEW clients is + * now possible due to automatically recognition of "temporary" + * clients + */ + del_op_entry = entry->change.flags & BATADV_TT_CLIENT_DEL; + if (!del_op_requested && del_op_entry) + goto del; + if (del_op_requested && !del_op_entry) + goto del; + continue; +del: + list_del(&entry->list); + kfree(entry); + kfree(tt_change_node); + event_removed = true; + goto unlock; + } + /* track the change in the OGMinterval list */ list_add_tail(&tt_change_node->list, &bat_priv->tt_changes_list); - atomic_inc(&bat_priv->tt_local_changes); + +unlock: spin_unlock_bh(&bat_priv->tt_changes_list_lock); - atomic_set(&bat_priv->tt_ogm_append_cnt, 0); + if (event_removed) + atomic_dec(&bat_priv->tt_local_changes); + else + atomic_inc(&bat_priv->tt_local_changes); } -int tt_len(int changes_num) +int batadv_tt_len(int changes_num) { - return changes_num * sizeof(struct tt_change); + return changes_num * sizeof(struct batadv_tt_change); } -static int tt_local_init(struct bat_priv *bat_priv) +static int batadv_tt_local_init(struct batadv_priv *bat_priv) { if (bat_priv->tt_local_hash) - return 1; + return 0; - bat_priv->tt_local_hash = hash_new(1024); + bat_priv->tt_local_hash = batadv_hash_new(1024); if (!bat_priv->tt_local_hash) - return 0; + return -ENOMEM; - return 1; + return 0; } -void tt_local_add(struct net_device *soft_iface, const uint8_t *addr, - int ifindex) +void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, + int ifindex) { - struct bat_priv *bat_priv = netdev_priv(soft_iface); - struct tt_local_entry *tt_local_entry = NULL; - struct tt_global_entry *tt_global_entry = NULL; + struct batadv_priv *bat_priv = netdev_priv(soft_iface); + struct batadv_tt_local_entry *tt_local_entry = NULL; + struct batadv_tt_global_entry *tt_global_entry = NULL; struct hlist_head *head; struct hlist_node *node; - struct tt_orig_list_entry *orig_entry; + struct batadv_tt_orig_list_entry *orig_entry; int hash_added; - tt_local_entry = tt_local_hash_find(bat_priv, addr); + tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr); if (tt_local_entry) { tt_local_entry->last_seen = jiffies; - /* possibly unset the TT_CLIENT_PENDING flag */ - tt_local_entry->common.flags &= ~TT_CLIENT_PENDING; + /* possibly unset the BATADV_TT_CLIENT_PENDING flag */ + tt_local_entry->common.flags &= ~BATADV_TT_CLIENT_PENDING; goto out; } @@ -216,40 +256,42 @@ void tt_local_add(struct net_device *soft_iface, const uint8_t *addr, if (!tt_local_entry) goto out; - bat_dbg(DBG_TT, bat_priv, - "Creating new local tt entry: %pM (ttvn: %d)\n", addr, - (uint8_t)atomic_read(&bat_priv->ttvn)); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Creating new local tt entry: %pM (ttvn: %d)\n", addr, + (uint8_t)atomic_read(&bat_priv->ttvn)); memcpy(tt_local_entry->common.addr, addr, ETH_ALEN); - tt_local_entry->common.flags = NO_FLAGS; - if (is_wifi_iface(ifindex)) - tt_local_entry->common.flags |= TT_CLIENT_WIFI; + tt_local_entry->common.flags = BATADV_NO_FLAGS; + if (batadv_is_wifi_iface(ifindex)) + tt_local_entry->common.flags |= BATADV_TT_CLIENT_WIFI; atomic_set(&tt_local_entry->common.refcount, 2); tt_local_entry->last_seen = jiffies; /* the batman interface mac address should never be purged */ - if (compare_eth(addr, soft_iface->dev_addr)) - tt_local_entry->common.flags |= TT_CLIENT_NOPURGE; + if (batadv_compare_eth(addr, soft_iface->dev_addr)) + tt_local_entry->common.flags |= BATADV_TT_CLIENT_NOPURGE; /* The local entry has to be marked as NEW to avoid to send it in * a full table response going out before the next ttvn increment - * (consistency check) */ - tt_local_entry->common.flags |= TT_CLIENT_NEW; + * (consistency check) + */ + tt_local_entry->common.flags |= BATADV_TT_CLIENT_NEW; - hash_added = hash_add(bat_priv->tt_local_hash, compare_tt, choose_orig, - &tt_local_entry->common, - &tt_local_entry->common.hash_entry); + hash_added = batadv_hash_add(bat_priv->tt_local_hash, batadv_compare_tt, + batadv_choose_orig, + &tt_local_entry->common, + &tt_local_entry->common.hash_entry); if (unlikely(hash_added != 0)) { /* remove the reference for the hash */ - tt_local_entry_free_ref(tt_local_entry); + batadv_tt_local_entry_free_ref(tt_local_entry); goto out; } - tt_local_event(bat_priv, addr, tt_local_entry->common.flags); + batadv_tt_local_event(bat_priv, addr, tt_local_entry->common.flags); /* remove address from global hash if present */ - tt_global_entry = tt_global_hash_find(bat_priv, addr); + tt_global_entry = batadv_tt_global_hash_find(bat_priv, addr); /* Check whether it is a roaming! */ if (tt_global_entry) { @@ -259,31 +301,85 @@ void tt_local_add(struct net_device *soft_iface, const uint8_t *addr, hlist_for_each_entry_rcu(orig_entry, node, head, list) { orig_entry->orig_node->tt_poss_change = true; - send_roam_adv(bat_priv, tt_global_entry->common.addr, - orig_entry->orig_node); + batadv_send_roam_adv(bat_priv, + tt_global_entry->common.addr, + orig_entry->orig_node); } rcu_read_unlock(); /* The global entry has to be marked as ROAMING and * has to be kept for consistency purpose */ - tt_global_entry->common.flags |= TT_CLIENT_ROAM; + tt_global_entry->common.flags |= BATADV_TT_CLIENT_ROAM; tt_global_entry->roam_at = jiffies; } out: if (tt_local_entry) - tt_local_entry_free_ref(tt_local_entry); + batadv_tt_local_entry_free_ref(tt_local_entry); if (tt_global_entry) - tt_global_entry_free_ref(tt_global_entry); + batadv_tt_global_entry_free_ref(tt_global_entry); +} + +static void batadv_tt_realloc_packet_buff(unsigned char **packet_buff, + int *packet_buff_len, + int min_packet_len, + int new_packet_len) +{ + unsigned char *new_buff; + + new_buff = kmalloc(new_packet_len, GFP_ATOMIC); + + /* keep old buffer if kmalloc should fail */ + if (new_buff) { + memcpy(new_buff, *packet_buff, min_packet_len); + kfree(*packet_buff); + *packet_buff = new_buff; + *packet_buff_len = new_packet_len; + } +} + +static void batadv_tt_prepare_packet_buff(struct batadv_priv *bat_priv, + unsigned char **packet_buff, + int *packet_buff_len, + int min_packet_len) +{ + struct batadv_hard_iface *primary_if; + int req_len; + + primary_if = batadv_primary_if_get_selected(bat_priv); + + req_len = min_packet_len; + req_len += batadv_tt_len(atomic_read(&bat_priv->tt_local_changes)); + + /* if we have too many changes for one packet don't send any + * and wait for the tt table request which will be fragmented + */ + if ((!primary_if) || (req_len > primary_if->soft_iface->mtu)) + req_len = min_packet_len; + + batadv_tt_realloc_packet_buff(packet_buff, packet_buff_len, + min_packet_len, req_len); + + if (primary_if) + batadv_hardif_free_ref(primary_if); } -int tt_changes_fill_buffer(struct bat_priv *bat_priv, - unsigned char *buff, int buff_len) +static int batadv_tt_changes_fill_buff(struct batadv_priv *bat_priv, + unsigned char **packet_buff, + int *packet_buff_len, + int min_packet_len) { - int count = 0, tot_changes = 0; - struct tt_change_node *entry, *safe; + struct batadv_tt_change_node *entry, *safe; + int count = 0, tot_changes = 0, new_len; + unsigned char *tt_buff; - if (buff_len > 0) - tot_changes = buff_len / tt_len(1); + batadv_tt_prepare_packet_buff(bat_priv, packet_buff, + packet_buff_len, min_packet_len); + + new_len = *packet_buff_len - min_packet_len; + tt_buff = *packet_buff + min_packet_len; + + if (new_len > 0) + tot_changes = new_len / batadv_tt_len(1); spin_lock_bh(&bat_priv->tt_changes_list_lock); atomic_set(&bat_priv->tt_local_changes, 0); @@ -291,8 +387,8 @@ int tt_changes_fill_buffer(struct bat_priv *bat_priv, list_for_each_entry_safe(entry, safe, &bat_priv->tt_changes_list, list) { if (count < tot_changes) { - memcpy(buff + tt_len(count), - &entry->change, sizeof(struct tt_change)); + memcpy(tt_buff + batadv_tt_len(count), + &entry->change, sizeof(struct batadv_tt_change)); count++; } list_del(&entry->list); @@ -305,37 +401,35 @@ int tt_changes_fill_buffer(struct bat_priv *bat_priv, kfree(bat_priv->tt_buff); bat_priv->tt_buff_len = 0; bat_priv->tt_buff = NULL; - /* We check whether this new OGM has no changes due to size - * problems */ - if (buff_len > 0) { - /** - * if kmalloc() fails we will reply with the full table + /* check whether this new OGM has no changes due to size problems */ + if (new_len > 0) { + /* if kmalloc() fails we will reply with the full table * instead of providing the diff */ - bat_priv->tt_buff = kmalloc(buff_len, GFP_ATOMIC); + bat_priv->tt_buff = kmalloc(new_len, GFP_ATOMIC); if (bat_priv->tt_buff) { - memcpy(bat_priv->tt_buff, buff, buff_len); - bat_priv->tt_buff_len = buff_len; + memcpy(bat_priv->tt_buff, tt_buff, new_len); + bat_priv->tt_buff_len = new_len; } } spin_unlock_bh(&bat_priv->tt_buff_lock); - return tot_changes; + return count; } -int tt_local_seq_print_text(struct seq_file *seq, void *offset) +int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) { struct net_device *net_dev = (struct net_device *)seq->private; - struct bat_priv *bat_priv = netdev_priv(net_dev); - struct hashtable_t *hash = bat_priv->tt_local_hash; - struct tt_common_entry *tt_common_entry; - struct hard_iface *primary_if; + struct batadv_priv *bat_priv = netdev_priv(net_dev); + struct batadv_hashtable *hash = bat_priv->tt_local_hash; + struct batadv_tt_common_entry *tt_common_entry; + struct batadv_hard_iface *primary_if; struct hlist_node *node; struct hlist_head *head; uint32_t i; int ret = 0; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) { ret = seq_printf(seq, "BATMAN mesh %s disabled - please specify interfaces to enable it\n", @@ -343,7 +437,7 @@ int tt_local_seq_print_text(struct seq_file *seq, void *offset) goto out; } - if (primary_if->if_status != IF_ACTIVE) { + if (primary_if->if_status != BATADV_IF_ACTIVE) { ret = seq_printf(seq, "BATMAN mesh %s disabled - primary interface not active\n", net_dev->name); @@ -363,63 +457,94 @@ int tt_local_seq_print_text(struct seq_file *seq, void *offset) seq_printf(seq, " * %pM [%c%c%c%c%c]\n", tt_common_entry->addr, (tt_common_entry->flags & - TT_CLIENT_ROAM ? 'R' : '.'), + BATADV_TT_CLIENT_ROAM ? 'R' : '.'), (tt_common_entry->flags & - TT_CLIENT_NOPURGE ? 'P' : '.'), + BATADV_TT_CLIENT_NOPURGE ? 'P' : '.'), (tt_common_entry->flags & - TT_CLIENT_NEW ? 'N' : '.'), + BATADV_TT_CLIENT_NEW ? 'N' : '.'), (tt_common_entry->flags & - TT_CLIENT_PENDING ? 'X' : '.'), + BATADV_TT_CLIENT_PENDING ? 'X' : '.'), (tt_common_entry->flags & - TT_CLIENT_WIFI ? 'W' : '.')); + BATADV_TT_CLIENT_WIFI ? 'W' : '.')); } rcu_read_unlock(); } out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); return ret; } -static void tt_local_set_pending(struct bat_priv *bat_priv, - struct tt_local_entry *tt_local_entry, - uint16_t flags, const char *message) +static void +batadv_tt_local_set_pending(struct batadv_priv *bat_priv, + struct batadv_tt_local_entry *tt_local_entry, + uint16_t flags, const char *message) { - tt_local_event(bat_priv, tt_local_entry->common.addr, - tt_local_entry->common.flags | flags); + batadv_tt_local_event(bat_priv, tt_local_entry->common.addr, + tt_local_entry->common.flags | flags); /* The local client has to be marked as "pending to be removed" but has * to be kept in the table in order to send it in a full table - * response issued before the net ttvn increment (consistency check) */ - tt_local_entry->common.flags |= TT_CLIENT_PENDING; + * response issued before the net ttvn increment (consistency check) + */ + tt_local_entry->common.flags |= BATADV_TT_CLIENT_PENDING; - bat_dbg(DBG_TT, bat_priv, - "Local tt entry (%pM) pending to be removed: %s\n", - tt_local_entry->common.addr, message); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Local tt entry (%pM) pending to be removed: %s\n", + tt_local_entry->common.addr, message); } -void tt_local_remove(struct bat_priv *bat_priv, const uint8_t *addr, - const char *message, bool roaming) +void batadv_tt_local_remove(struct batadv_priv *bat_priv, const uint8_t *addr, + const char *message, bool roaming) { - struct tt_local_entry *tt_local_entry = NULL; + struct batadv_tt_local_entry *tt_local_entry = NULL; + uint16_t flags; - tt_local_entry = tt_local_hash_find(bat_priv, addr); + tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr); if (!tt_local_entry) goto out; - tt_local_set_pending(bat_priv, tt_local_entry, TT_CLIENT_DEL | - (roaming ? TT_CLIENT_ROAM : NO_FLAGS), message); + flags = BATADV_TT_CLIENT_DEL; + if (roaming) + flags |= BATADV_TT_CLIENT_ROAM; + + batadv_tt_local_set_pending(bat_priv, tt_local_entry, flags, message); out: if (tt_local_entry) - tt_local_entry_free_ref(tt_local_entry); + batadv_tt_local_entry_free_ref(tt_local_entry); } -static void tt_local_purge(struct bat_priv *bat_priv) +static void batadv_tt_local_purge_list(struct batadv_priv *bat_priv, + struct hlist_head *head) { - struct hashtable_t *hash = bat_priv->tt_local_hash; - struct tt_local_entry *tt_local_entry; - struct tt_common_entry *tt_common_entry; + struct batadv_tt_local_entry *tt_local_entry; + struct batadv_tt_common_entry *tt_common_entry; struct hlist_node *node, *node_tmp; + + hlist_for_each_entry_safe(tt_common_entry, node, node_tmp, head, + hash_entry) { + tt_local_entry = container_of(tt_common_entry, + struct batadv_tt_local_entry, + common); + if (tt_local_entry->common.flags & BATADV_TT_CLIENT_NOPURGE) + continue; + + /* entry already marked for deletion */ + if (tt_local_entry->common.flags & BATADV_TT_CLIENT_PENDING) + continue; + + if (!batadv_has_timed_out(tt_local_entry->last_seen, + BATADV_TT_LOCAL_TIMEOUT)) + continue; + + batadv_tt_local_set_pending(bat_priv, tt_local_entry, + BATADV_TT_CLIENT_DEL, "timed out"); + } +} + +static void batadv_tt_local_purge(struct batadv_priv *bat_priv) +{ + struct batadv_hashtable *hash = bat_priv->tt_local_hash; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ uint32_t i; @@ -429,36 +554,18 @@ static void tt_local_purge(struct bat_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(tt_common_entry, node, node_tmp, - head, hash_entry) { - tt_local_entry = container_of(tt_common_entry, - struct tt_local_entry, - common); - if (tt_local_entry->common.flags & TT_CLIENT_NOPURGE) - continue; - - /* entry already marked for deletion */ - if (tt_local_entry->common.flags & TT_CLIENT_PENDING) - continue; - - if (!has_timed_out(tt_local_entry->last_seen, - TT_LOCAL_TIMEOUT)) - continue; - - tt_local_set_pending(bat_priv, tt_local_entry, - TT_CLIENT_DEL, "timed out"); - } + batadv_tt_local_purge_list(bat_priv, head); spin_unlock_bh(list_lock); } } -static void tt_local_table_free(struct bat_priv *bat_priv) +static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) { - struct hashtable_t *hash; + struct batadv_hashtable *hash; spinlock_t *list_lock; /* protects write access to the hash lists */ - struct tt_common_entry *tt_common_entry; - struct tt_local_entry *tt_local_entry; + struct batadv_tt_common_entry *tt_common_entry; + struct batadv_tt_local_entry *tt_local; struct hlist_node *node, *node_tmp; struct hlist_head *head; uint32_t i; @@ -476,35 +583,35 @@ static void tt_local_table_free(struct bat_priv *bat_priv) hlist_for_each_entry_safe(tt_common_entry, node, node_tmp, head, hash_entry) { hlist_del_rcu(node); - tt_local_entry = container_of(tt_common_entry, - struct tt_local_entry, - common); - tt_local_entry_free_ref(tt_local_entry); + tt_local = container_of(tt_common_entry, + struct batadv_tt_local_entry, + common); + batadv_tt_local_entry_free_ref(tt_local); } spin_unlock_bh(list_lock); } - hash_destroy(hash); + batadv_hash_destroy(hash); bat_priv->tt_local_hash = NULL; } -static int tt_global_init(struct bat_priv *bat_priv) +static int batadv_tt_global_init(struct batadv_priv *bat_priv) { if (bat_priv->tt_global_hash) - return 1; + return 0; - bat_priv->tt_global_hash = hash_new(1024); + bat_priv->tt_global_hash = batadv_hash_new(1024); if (!bat_priv->tt_global_hash) - return 0; + return -ENOMEM; - return 1; + return 0; } -static void tt_changes_list_free(struct bat_priv *bat_priv) +static void batadv_tt_changes_list_free(struct batadv_priv *bat_priv) { - struct tt_change_node *entry, *safe; + struct batadv_tt_change_node *entry, *safe; spin_lock_bh(&bat_priv->tt_changes_list_lock); @@ -521,10 +628,11 @@ static void tt_changes_list_free(struct bat_priv *bat_priv) /* find out if an orig_node is already in the list of a tt_global_entry. * returns 1 if found, 0 otherwise */ -static bool tt_global_entry_has_orig(const struct tt_global_entry *entry, - const struct orig_node *orig_node) +static bool +batadv_tt_global_entry_has_orig(const struct batadv_tt_global_entry *entry, + const struct batadv_orig_node *orig_node) { - struct tt_orig_list_entry *tmp_orig_entry; + struct batadv_tt_orig_list_entry *tmp_orig_entry; const struct hlist_head *head; struct hlist_node *node; bool found = false; @@ -541,11 +649,11 @@ static bool tt_global_entry_has_orig(const struct tt_global_entry *entry, return found; } -static void tt_global_add_orig_entry(struct tt_global_entry *tt_global_entry, - struct orig_node *orig_node, - int ttvn) +static void +batadv_tt_global_add_orig_entry(struct batadv_tt_global_entry *tt_global_entry, + struct batadv_orig_node *orig_node, int ttvn) { - struct tt_orig_list_entry *orig_entry; + struct batadv_tt_orig_list_entry *orig_entry; orig_entry = kzalloc(sizeof(*orig_entry), GFP_ATOMIC); if (!orig_entry) @@ -564,91 +672,95 @@ static void tt_global_add_orig_entry(struct tt_global_entry *tt_global_entry, } /* caller must hold orig_node refcount */ -int tt_global_add(struct bat_priv *bat_priv, struct orig_node *orig_node, - const unsigned char *tt_addr, uint8_t ttvn, bool roaming, - bool wifi) +int batadv_tt_global_add(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + const unsigned char *tt_addr, uint8_t flags, + uint8_t ttvn) { - struct tt_global_entry *tt_global_entry = NULL; + struct batadv_tt_global_entry *tt_global_entry = NULL; int ret = 0; int hash_added; + struct batadv_tt_common_entry *common; - tt_global_entry = tt_global_hash_find(bat_priv, tt_addr); + tt_global_entry = batadv_tt_global_hash_find(bat_priv, tt_addr); if (!tt_global_entry) { - tt_global_entry = kzalloc(sizeof(*tt_global_entry), - GFP_ATOMIC); + tt_global_entry = kzalloc(sizeof(*tt_global_entry), GFP_ATOMIC); if (!tt_global_entry) goto out; - memcpy(tt_global_entry->common.addr, tt_addr, ETH_ALEN); + common = &tt_global_entry->common; + memcpy(common->addr, tt_addr, ETH_ALEN); - tt_global_entry->common.flags = NO_FLAGS; + common->flags = flags; tt_global_entry->roam_at = 0; - atomic_set(&tt_global_entry->common.refcount, 2); + atomic_set(&common->refcount, 2); INIT_HLIST_HEAD(&tt_global_entry->orig_list); spin_lock_init(&tt_global_entry->list_lock); - hash_added = hash_add(bat_priv->tt_global_hash, compare_tt, - choose_orig, &tt_global_entry->common, - &tt_global_entry->common.hash_entry); + hash_added = batadv_hash_add(bat_priv->tt_global_hash, + batadv_compare_tt, + batadv_choose_orig, common, + &common->hash_entry); if (unlikely(hash_added != 0)) { /* remove the reference for the hash */ - tt_global_entry_free_ref(tt_global_entry); + batadv_tt_global_entry_free_ref(tt_global_entry); goto out_remove; } - tt_global_add_orig_entry(tt_global_entry, orig_node, ttvn); + batadv_tt_global_add_orig_entry(tt_global_entry, orig_node, + ttvn); } else { /* there is already a global entry, use this one. */ - /* If there is the TT_CLIENT_ROAM flag set, there is only one - * originator left in the list and we previously received a + /* If there is the BATADV_TT_CLIENT_ROAM flag set, there is only + * one originator left in the list and we previously received a * delete + roaming change for this originator. * * We should first delete the old originator before adding the * new one. */ - if (tt_global_entry->common.flags & TT_CLIENT_ROAM) { - tt_global_del_orig_list(tt_global_entry); - tt_global_entry->common.flags &= ~TT_CLIENT_ROAM; + if (tt_global_entry->common.flags & BATADV_TT_CLIENT_ROAM) { + batadv_tt_global_del_orig_list(tt_global_entry); + tt_global_entry->common.flags &= ~BATADV_TT_CLIENT_ROAM; tt_global_entry->roam_at = 0; } - if (!tt_global_entry_has_orig(tt_global_entry, orig_node)) - tt_global_add_orig_entry(tt_global_entry, orig_node, - ttvn); + if (!batadv_tt_global_entry_has_orig(tt_global_entry, + orig_node)) + batadv_tt_global_add_orig_entry(tt_global_entry, + orig_node, ttvn); } - if (wifi) - tt_global_entry->common.flags |= TT_CLIENT_WIFI; - - bat_dbg(DBG_TT, bat_priv, - "Creating new global tt entry: %pM (via %pM)\n", - tt_global_entry->common.addr, orig_node->orig); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Creating new global tt entry: %pM (via %pM)\n", + tt_global_entry->common.addr, orig_node->orig); out_remove: /* remove address from local hash if present */ - tt_local_remove(bat_priv, tt_global_entry->common.addr, - "global tt received", roaming); + batadv_tt_local_remove(bat_priv, tt_global_entry->common.addr, + "global tt received", + flags & BATADV_TT_CLIENT_ROAM); ret = 1; out: if (tt_global_entry) - tt_global_entry_free_ref(tt_global_entry); + batadv_tt_global_entry_free_ref(tt_global_entry); return ret; } /* print all orig nodes who announce the address for this global entry. * it is assumed that the caller holds rcu_read_lock(); */ -static void tt_global_print_entry(struct tt_global_entry *tt_global_entry, - struct seq_file *seq) +static void +batadv_tt_global_print_entry(struct batadv_tt_global_entry *tt_global_entry, + struct seq_file *seq) { struct hlist_head *head; struct hlist_node *node; - struct tt_orig_list_entry *orig_entry; - struct tt_common_entry *tt_common_entry; + struct batadv_tt_orig_list_entry *orig_entry; + struct batadv_tt_common_entry *tt_common_entry; uint16_t flags; uint8_t last_ttvn; @@ -662,25 +774,25 @@ static void tt_global_print_entry(struct tt_global_entry *tt_global_entry, seq_printf(seq, " * %pM (%3u) via %pM (%3u) [%c%c]\n", tt_global_entry->common.addr, orig_entry->ttvn, orig_entry->orig_node->orig, last_ttvn, - (flags & TT_CLIENT_ROAM ? 'R' : '.'), - (flags & TT_CLIENT_WIFI ? 'W' : '.')); + (flags & BATADV_TT_CLIENT_ROAM ? 'R' : '.'), + (flags & BATADV_TT_CLIENT_WIFI ? 'W' : '.')); } } -int tt_global_seq_print_text(struct seq_file *seq, void *offset) +int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset) { struct net_device *net_dev = (struct net_device *)seq->private; - struct bat_priv *bat_priv = netdev_priv(net_dev); - struct hashtable_t *hash = bat_priv->tt_global_hash; - struct tt_common_entry *tt_common_entry; - struct tt_global_entry *tt_global_entry; - struct hard_iface *primary_if; + struct batadv_priv *bat_priv = netdev_priv(net_dev); + struct batadv_hashtable *hash = bat_priv->tt_global_hash; + struct batadv_tt_common_entry *tt_common_entry; + struct batadv_tt_global_entry *tt_global; + struct batadv_hard_iface *primary_if; struct hlist_node *node; struct hlist_head *head; uint32_t i; int ret = 0; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) { ret = seq_printf(seq, "BATMAN mesh %s disabled - please specify interfaces to enable it\n", @@ -688,7 +800,7 @@ int tt_global_seq_print_text(struct seq_file *seq, void *offset) goto out; } - if (primary_if->if_status != IF_ACTIVE) { + if (primary_if->if_status != BATADV_IF_ACTIVE) { ret = seq_printf(seq, "BATMAN mesh %s disabled - primary interface not active\n", net_dev->name); @@ -707,87 +819,91 @@ int tt_global_seq_print_text(struct seq_file *seq, void *offset) rcu_read_lock(); hlist_for_each_entry_rcu(tt_common_entry, node, head, hash_entry) { - tt_global_entry = container_of(tt_common_entry, - struct tt_global_entry, - common); - tt_global_print_entry(tt_global_entry, seq); + tt_global = container_of(tt_common_entry, + struct batadv_tt_global_entry, + common); + batadv_tt_global_print_entry(tt_global, seq); } rcu_read_unlock(); } out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); return ret; } /* deletes the orig list of a tt_global_entry */ -static void tt_global_del_orig_list(struct tt_global_entry *tt_global_entry) +static void +batadv_tt_global_del_orig_list(struct batadv_tt_global_entry *tt_global_entry) { struct hlist_head *head; struct hlist_node *node, *safe; - struct tt_orig_list_entry *orig_entry; + struct batadv_tt_orig_list_entry *orig_entry; spin_lock_bh(&tt_global_entry->list_lock); head = &tt_global_entry->orig_list; hlist_for_each_entry_safe(orig_entry, node, safe, head, list) { hlist_del_rcu(node); - tt_orig_list_entry_free_ref(orig_entry); + batadv_tt_orig_list_entry_free_ref(orig_entry); } spin_unlock_bh(&tt_global_entry->list_lock); } -static void tt_global_del_orig_entry(struct bat_priv *bat_priv, - struct tt_global_entry *tt_global_entry, - struct orig_node *orig_node, - const char *message) +static void +batadv_tt_global_del_orig_entry(struct batadv_priv *bat_priv, + struct batadv_tt_global_entry *tt_global_entry, + struct batadv_orig_node *orig_node, + const char *message) { struct hlist_head *head; struct hlist_node *node, *safe; - struct tt_orig_list_entry *orig_entry; + struct batadv_tt_orig_list_entry *orig_entry; spin_lock_bh(&tt_global_entry->list_lock); head = &tt_global_entry->orig_list; hlist_for_each_entry_safe(orig_entry, node, safe, head, list) { if (orig_entry->orig_node == orig_node) { - bat_dbg(DBG_TT, bat_priv, - "Deleting %pM from global tt entry %pM: %s\n", - orig_node->orig, tt_global_entry->common.addr, - message); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Deleting %pM from global tt entry %pM: %s\n", + orig_node->orig, + tt_global_entry->common.addr, message); hlist_del_rcu(node); - tt_orig_list_entry_free_ref(orig_entry); + batadv_tt_orig_list_entry_free_ref(orig_entry); } } spin_unlock_bh(&tt_global_entry->list_lock); } -static void tt_global_del_struct(struct bat_priv *bat_priv, - struct tt_global_entry *tt_global_entry, - const char *message) +static void +batadv_tt_global_del_struct(struct batadv_priv *bat_priv, + struct batadv_tt_global_entry *tt_global_entry, + const char *message) { - bat_dbg(DBG_TT, bat_priv, - "Deleting global tt entry %pM: %s\n", - tt_global_entry->common.addr, message); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Deleting global tt entry %pM: %s\n", + tt_global_entry->common.addr, message); - hash_remove(bat_priv->tt_global_hash, compare_tt, choose_orig, - tt_global_entry->common.addr); - tt_global_entry_free_ref(tt_global_entry); + batadv_hash_remove(bat_priv->tt_global_hash, batadv_compare_tt, + batadv_choose_orig, tt_global_entry->common.addr); + batadv_tt_global_entry_free_ref(tt_global_entry); } /* If the client is to be deleted, we check if it is the last origantor entry - * within tt_global entry. If yes, we set the TT_CLIENT_ROAM flag and the timer, - * otherwise we simply remove the originator scheduled for deletion. + * within tt_global entry. If yes, we set the BATADV_TT_CLIENT_ROAM flag and the + * timer, otherwise we simply remove the originator scheduled for deletion. */ -static void tt_global_del_roaming(struct bat_priv *bat_priv, - struct tt_global_entry *tt_global_entry, - struct orig_node *orig_node, - const char *message) +static void +batadv_tt_global_del_roaming(struct batadv_priv *bat_priv, + struct batadv_tt_global_entry *tt_global_entry, + struct batadv_orig_node *orig_node, + const char *message) { bool last_entry = true; struct hlist_head *head; struct hlist_node *node; - struct tt_orig_list_entry *orig_entry; + struct batadv_tt_orig_list_entry *orig_entry; /* no local entry exists, case 1: * Check if this is the last one or if other entries exist. @@ -805,37 +921,37 @@ static void tt_global_del_roaming(struct bat_priv *bat_priv, if (last_entry) { /* its the last one, mark for roaming. */ - tt_global_entry->common.flags |= TT_CLIENT_ROAM; + tt_global_entry->common.flags |= BATADV_TT_CLIENT_ROAM; tt_global_entry->roam_at = jiffies; } else /* there is another entry, we can simply delete this * one and can still use the other one. */ - tt_global_del_orig_entry(bat_priv, tt_global_entry, - orig_node, message); + batadv_tt_global_del_orig_entry(bat_priv, tt_global_entry, + orig_node, message); } -static void tt_global_del(struct bat_priv *bat_priv, - struct orig_node *orig_node, - const unsigned char *addr, - const char *message, bool roaming) +static void batadv_tt_global_del(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + const unsigned char *addr, + const char *message, bool roaming) { - struct tt_global_entry *tt_global_entry = NULL; - struct tt_local_entry *tt_local_entry = NULL; + struct batadv_tt_global_entry *tt_global_entry = NULL; + struct batadv_tt_local_entry *local_entry = NULL; - tt_global_entry = tt_global_hash_find(bat_priv, addr); + tt_global_entry = batadv_tt_global_hash_find(bat_priv, addr); if (!tt_global_entry) goto out; if (!roaming) { - tt_global_del_orig_entry(bat_priv, tt_global_entry, orig_node, - message); + batadv_tt_global_del_orig_entry(bat_priv, tt_global_entry, + orig_node, message); if (hlist_empty(&tt_global_entry->orig_list)) - tt_global_del_struct(bat_priv, tt_global_entry, - message); + batadv_tt_global_del_struct(bat_priv, tt_global_entry, + message); goto out; } @@ -844,41 +960,42 @@ static void tt_global_del(struct bat_priv *bat_priv, * event, there are two possibilities: * 1) the client roamed from node A to node B => if there * is only one originator left for this client, we mark - * it with TT_CLIENT_ROAM, we start a timer and we + * it with BATADV_TT_CLIENT_ROAM, we start a timer and we * wait for node B to claim it. In case of timeout * the entry is purged. * * If there are other originators left, we directly delete * the originator. * 2) the client roamed to us => we can directly delete - * the global entry, since it is useless now. */ - - tt_local_entry = tt_local_hash_find(bat_priv, - tt_global_entry->common.addr); - if (tt_local_entry) { + * the global entry, since it is useless now. + */ + local_entry = batadv_tt_local_hash_find(bat_priv, + tt_global_entry->common.addr); + if (local_entry) { /* local entry exists, case 2: client roamed to us. */ - tt_global_del_orig_list(tt_global_entry); - tt_global_del_struct(bat_priv, tt_global_entry, message); + batadv_tt_global_del_orig_list(tt_global_entry); + batadv_tt_global_del_struct(bat_priv, tt_global_entry, message); } else /* no local entry exists, case 1: check for roaming */ - tt_global_del_roaming(bat_priv, tt_global_entry, orig_node, - message); + batadv_tt_global_del_roaming(bat_priv, tt_global_entry, + orig_node, message); out: if (tt_global_entry) - tt_global_entry_free_ref(tt_global_entry); - if (tt_local_entry) - tt_local_entry_free_ref(tt_local_entry); + batadv_tt_global_entry_free_ref(tt_global_entry); + if (local_entry) + batadv_tt_local_entry_free_ref(local_entry); } -void tt_global_del_orig(struct bat_priv *bat_priv, - struct orig_node *orig_node, const char *message) +void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + const char *message) { - struct tt_global_entry *tt_global_entry; - struct tt_common_entry *tt_common_entry; + struct batadv_tt_global_entry *tt_global; + struct batadv_tt_common_entry *tt_common_entry; uint32_t i; - struct hashtable_t *hash = bat_priv->tt_global_hash; + struct batadv_hashtable *hash = bat_priv->tt_global_hash; struct hlist_node *node, *safe; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ @@ -893,20 +1010,19 @@ void tt_global_del_orig(struct bat_priv *bat_priv, spin_lock_bh(list_lock); hlist_for_each_entry_safe(tt_common_entry, node, safe, head, hash_entry) { - tt_global_entry = container_of(tt_common_entry, - struct tt_global_entry, - common); - - tt_global_del_orig_entry(bat_priv, tt_global_entry, - orig_node, message); - - if (hlist_empty(&tt_global_entry->orig_list)) { - bat_dbg(DBG_TT, bat_priv, - "Deleting global tt entry %pM: %s\n", - tt_global_entry->common.addr, - message); + tt_global = container_of(tt_common_entry, + struct batadv_tt_global_entry, + common); + + batadv_tt_global_del_orig_entry(bat_priv, tt_global, + orig_node, message); + + if (hlist_empty(&tt_global->orig_list)) { + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Deleting global tt entry %pM: %s\n", + tt_global->common.addr, message); hlist_del_rcu(node); - tt_global_entry_free_ref(tt_global_entry); + batadv_tt_global_entry_free_ref(tt_global); } } spin_unlock_bh(list_lock); @@ -914,12 +1030,36 @@ void tt_global_del_orig(struct bat_priv *bat_priv, orig_node->tt_initialised = false; } -static void tt_global_roam_purge(struct bat_priv *bat_priv) +static void batadv_tt_global_roam_purge_list(struct batadv_priv *bat_priv, + struct hlist_head *head) { - struct hashtable_t *hash = bat_priv->tt_global_hash; - struct tt_common_entry *tt_common_entry; - struct tt_global_entry *tt_global_entry; + struct batadv_tt_common_entry *tt_common_entry; + struct batadv_tt_global_entry *tt_global_entry; struct hlist_node *node, *node_tmp; + + hlist_for_each_entry_safe(tt_common_entry, node, node_tmp, head, + hash_entry) { + tt_global_entry = container_of(tt_common_entry, + struct batadv_tt_global_entry, + common); + if (!(tt_global_entry->common.flags & BATADV_TT_CLIENT_ROAM)) + continue; + if (!batadv_has_timed_out(tt_global_entry->roam_at, + BATADV_TT_CLIENT_ROAM_TIMEOUT)) + continue; + + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Deleting global tt entry (%pM): Roaming timeout\n", + tt_global_entry->common.addr); + + hlist_del_rcu(node); + batadv_tt_global_entry_free_ref(tt_global_entry); + } +} + +static void batadv_tt_global_roam_purge(struct batadv_priv *bat_priv) +{ + struct batadv_hashtable *hash = bat_priv->tt_global_hash; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ uint32_t i; @@ -929,35 +1069,18 @@ static void tt_global_roam_purge(struct bat_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(tt_common_entry, node, node_tmp, - head, hash_entry) { - tt_global_entry = container_of(tt_common_entry, - struct tt_global_entry, - common); - if (!(tt_global_entry->common.flags & TT_CLIENT_ROAM)) - continue; - if (!has_timed_out(tt_global_entry->roam_at, - TT_CLIENT_ROAM_TIMEOUT)) - continue; - - bat_dbg(DBG_TT, bat_priv, - "Deleting global tt entry (%pM): Roaming timeout\n", - tt_global_entry->common.addr); - - hlist_del_rcu(node); - tt_global_entry_free_ref(tt_global_entry); - } + batadv_tt_global_roam_purge_list(bat_priv, head); spin_unlock_bh(list_lock); } } -static void tt_global_table_free(struct bat_priv *bat_priv) +static void batadv_tt_global_table_free(struct batadv_priv *bat_priv) { - struct hashtable_t *hash; + struct batadv_hashtable *hash; spinlock_t *list_lock; /* protects write access to the hash lists */ - struct tt_common_entry *tt_common_entry; - struct tt_global_entry *tt_global_entry; + struct batadv_tt_common_entry *tt_common_entry; + struct batadv_tt_global_entry *tt_global; struct hlist_node *node, *node_tmp; struct hlist_head *head; uint32_t i; @@ -975,56 +1098,60 @@ static void tt_global_table_free(struct bat_priv *bat_priv) hlist_for_each_entry_safe(tt_common_entry, node, node_tmp, head, hash_entry) { hlist_del_rcu(node); - tt_global_entry = container_of(tt_common_entry, - struct tt_global_entry, - common); - tt_global_entry_free_ref(tt_global_entry); + tt_global = container_of(tt_common_entry, + struct batadv_tt_global_entry, + common); + batadv_tt_global_entry_free_ref(tt_global); } spin_unlock_bh(list_lock); } - hash_destroy(hash); + batadv_hash_destroy(hash); bat_priv->tt_global_hash = NULL; } -static bool _is_ap_isolated(struct tt_local_entry *tt_local_entry, - struct tt_global_entry *tt_global_entry) +static bool +_batadv_is_ap_isolated(struct batadv_tt_local_entry *tt_local_entry, + struct batadv_tt_global_entry *tt_global_entry) { bool ret = false; - if (tt_local_entry->common.flags & TT_CLIENT_WIFI && - tt_global_entry->common.flags & TT_CLIENT_WIFI) + if (tt_local_entry->common.flags & BATADV_TT_CLIENT_WIFI && + tt_global_entry->common.flags & BATADV_TT_CLIENT_WIFI) ret = true; return ret; } -struct orig_node *transtable_search(struct bat_priv *bat_priv, - const uint8_t *src, const uint8_t *addr) +struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv, + const uint8_t *src, + const uint8_t *addr) { - struct tt_local_entry *tt_local_entry = NULL; - struct tt_global_entry *tt_global_entry = NULL; - struct orig_node *orig_node = NULL; - struct neigh_node *router = NULL; + struct batadv_tt_local_entry *tt_local_entry = NULL; + struct batadv_tt_global_entry *tt_global_entry = NULL; + struct batadv_orig_node *orig_node = NULL; + struct batadv_neigh_node *router = NULL; struct hlist_head *head; struct hlist_node *node; - struct tt_orig_list_entry *orig_entry; + struct batadv_tt_orig_list_entry *orig_entry; int best_tq; if (src && atomic_read(&bat_priv->ap_isolation)) { - tt_local_entry = tt_local_hash_find(bat_priv, src); + tt_local_entry = batadv_tt_local_hash_find(bat_priv, src); if (!tt_local_entry) goto out; } - tt_global_entry = tt_global_hash_find(bat_priv, addr); + tt_global_entry = batadv_tt_global_hash_find(bat_priv, addr); if (!tt_global_entry) goto out; /* check whether the clients should not communicate due to AP - * isolation */ - if (tt_local_entry && _is_ap_isolated(tt_local_entry, tt_global_entry)) + * isolation + */ + if (tt_local_entry && + _batadv_is_ap_isolated(tt_local_entry, tt_global_entry)) goto out; best_tq = 0; @@ -1032,7 +1159,7 @@ struct orig_node *transtable_search(struct bat_priv *bat_priv, rcu_read_lock(); head = &tt_global_entry->orig_list; hlist_for_each_entry_rcu(orig_entry, node, head, list) { - router = orig_node_get_router(orig_entry->orig_node); + router = batadv_orig_node_get_router(orig_entry->orig_node); if (!router) continue; @@ -1040,7 +1167,7 @@ struct orig_node *transtable_search(struct bat_priv *bat_priv, orig_node = orig_entry->orig_node; best_tq = router->tq_avg; } - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); } /* found anything? */ if (orig_node && !atomic_inc_not_zero(&orig_node->refcount)) @@ -1048,21 +1175,21 @@ struct orig_node *transtable_search(struct bat_priv *bat_priv, rcu_read_unlock(); out: if (tt_global_entry) - tt_global_entry_free_ref(tt_global_entry); + batadv_tt_global_entry_free_ref(tt_global_entry); if (tt_local_entry) - tt_local_entry_free_ref(tt_local_entry); + batadv_tt_local_entry_free_ref(tt_local_entry); return orig_node; } /* Calculates the checksum of the local table of a given orig_node */ -static uint16_t tt_global_crc(struct bat_priv *bat_priv, - struct orig_node *orig_node) +static uint16_t batadv_tt_global_crc(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node) { uint16_t total = 0, total_one; - struct hashtable_t *hash = bat_priv->tt_global_hash; - struct tt_common_entry *tt_common_entry; - struct tt_global_entry *tt_global_entry; + struct batadv_hashtable *hash = bat_priv->tt_global_hash; + struct batadv_tt_common_entry *tt_common; + struct batadv_tt_global_entry *tt_global; struct hlist_node *node; struct hlist_head *head; uint32_t i; @@ -1072,30 +1199,29 @@ static uint16_t tt_global_crc(struct bat_priv *bat_priv, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common_entry, node, - head, hash_entry) { - tt_global_entry = container_of(tt_common_entry, - struct tt_global_entry, - common); + hlist_for_each_entry_rcu(tt_common, node, head, hash_entry) { + tt_global = container_of(tt_common, + struct batadv_tt_global_entry, + common); /* Roaming clients are in the global table for * consistency only. They don't have to be * taken into account while computing the * global crc */ - if (tt_global_entry->common.flags & TT_CLIENT_ROAM) + if (tt_common->flags & BATADV_TT_CLIENT_ROAM) continue; /* find out if this global entry is announced by this * originator */ - if (!tt_global_entry_has_orig(tt_global_entry, - orig_node)) + if (!batadv_tt_global_entry_has_orig(tt_global, + orig_node)) continue; total_one = 0; for (j = 0; j < ETH_ALEN; j++) total_one = crc16_byte(total_one, - tt_global_entry->common.addr[j]); + tt_common->addr[j]); total ^= total_one; } rcu_read_unlock(); @@ -1105,11 +1231,11 @@ static uint16_t tt_global_crc(struct bat_priv *bat_priv, } /* Calculates the checksum of the local table */ -uint16_t tt_local_crc(struct bat_priv *bat_priv) +static uint16_t batadv_tt_local_crc(struct batadv_priv *bat_priv) { uint16_t total = 0, total_one; - struct hashtable_t *hash = bat_priv->tt_local_hash; - struct tt_common_entry *tt_common_entry; + struct batadv_hashtable *hash = bat_priv->tt_local_hash; + struct batadv_tt_common_entry *tt_common; struct hlist_node *node; struct hlist_head *head; uint32_t i; @@ -1119,16 +1245,16 @@ uint16_t tt_local_crc(struct bat_priv *bat_priv) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common_entry, node, - head, hash_entry) { + hlist_for_each_entry_rcu(tt_common, node, head, hash_entry) { /* not yet committed clients have not to be taken into - * account while computing the CRC */ - if (tt_common_entry->flags & TT_CLIENT_NEW) + * account while computing the CRC + */ + if (tt_common->flags & BATADV_TT_CLIENT_NEW) continue; total_one = 0; for (j = 0; j < ETH_ALEN; j++) total_one = crc16_byte(total_one, - tt_common_entry->addr[j]); + tt_common->addr[j]); total ^= total_one; } rcu_read_unlock(); @@ -1137,9 +1263,9 @@ uint16_t tt_local_crc(struct bat_priv *bat_priv) return total; } -static void tt_req_list_free(struct bat_priv *bat_priv) +static void batadv_tt_req_list_free(struct batadv_priv *bat_priv) { - struct tt_req_node *node, *safe; + struct batadv_tt_req_node *node, *safe; spin_lock_bh(&bat_priv->tt_req_list_lock); @@ -1151,15 +1277,16 @@ static void tt_req_list_free(struct bat_priv *bat_priv) spin_unlock_bh(&bat_priv->tt_req_list_lock); } -static void tt_save_orig_buffer(struct bat_priv *bat_priv, - struct orig_node *orig_node, - const unsigned char *tt_buff, - uint8_t tt_num_changes) +static void batadv_tt_save_orig_buffer(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + const unsigned char *tt_buff, + uint8_t tt_num_changes) { - uint16_t tt_buff_len = tt_len(tt_num_changes); + uint16_t tt_buff_len = batadv_tt_len(tt_num_changes); /* Replace the old buffer only if I received something in the - * last OGM (the OGM could carry no changes) */ + * last OGM (the OGM could carry no changes) + */ spin_lock_bh(&orig_node->tt_buff_lock); if (tt_buff_len > 0) { kfree(orig_node->tt_buff); @@ -1173,13 +1300,14 @@ static void tt_save_orig_buffer(struct bat_priv *bat_priv, spin_unlock_bh(&orig_node->tt_buff_lock); } -static void tt_req_purge(struct bat_priv *bat_priv) +static void batadv_tt_req_purge(struct batadv_priv *bat_priv) { - struct tt_req_node *node, *safe; + struct batadv_tt_req_node *node, *safe; spin_lock_bh(&bat_priv->tt_req_list_lock); list_for_each_entry_safe(node, safe, &bat_priv->tt_req_list, list) { - if (has_timed_out(node->issued_at, TT_REQUEST_TIMEOUT)) { + if (batadv_has_timed_out(node->issued_at, + BATADV_TT_REQUEST_TIMEOUT)) { list_del(&node->list); kfree(node); } @@ -1188,17 +1316,19 @@ static void tt_req_purge(struct bat_priv *bat_priv) } /* returns the pointer to the new tt_req_node struct if no request - * has already been issued for this orig_node, NULL otherwise */ -static struct tt_req_node *new_tt_req_node(struct bat_priv *bat_priv, - struct orig_node *orig_node) + * has already been issued for this orig_node, NULL otherwise + */ +static struct batadv_tt_req_node * +batadv_new_tt_req_node(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node) { - struct tt_req_node *tt_req_node_tmp, *tt_req_node = NULL; + struct batadv_tt_req_node *tt_req_node_tmp, *tt_req_node = NULL; spin_lock_bh(&bat_priv->tt_req_list_lock); list_for_each_entry(tt_req_node_tmp, &bat_priv->tt_req_list, list) { - if (compare_eth(tt_req_node_tmp, orig_node) && - !has_timed_out(tt_req_node_tmp->issued_at, - TT_REQUEST_TIMEOUT)) + if (batadv_compare_eth(tt_req_node_tmp, orig_node) && + !batadv_has_timed_out(tt_req_node_tmp->issued_at, + BATADV_TT_REQUEST_TIMEOUT)) goto unlock; } @@ -1216,63 +1346,67 @@ unlock: } /* data_ptr is useless here, but has to be kept to respect the prototype */ -static int tt_local_valid_entry(const void *entry_ptr, const void *data_ptr) +static int batadv_tt_local_valid_entry(const void *entry_ptr, + const void *data_ptr) { - const struct tt_common_entry *tt_common_entry = entry_ptr; + const struct batadv_tt_common_entry *tt_common_entry = entry_ptr; - if (tt_common_entry->flags & TT_CLIENT_NEW) + if (tt_common_entry->flags & BATADV_TT_CLIENT_NEW) return 0; return 1; } -static int tt_global_valid_entry(const void *entry_ptr, const void *data_ptr) +static int batadv_tt_global_valid(const void *entry_ptr, + const void *data_ptr) { - const struct tt_common_entry *tt_common_entry = entry_ptr; - const struct tt_global_entry *tt_global_entry; - const struct orig_node *orig_node = data_ptr; + const struct batadv_tt_common_entry *tt_common_entry = entry_ptr; + const struct batadv_tt_global_entry *tt_global_entry; + const struct batadv_orig_node *orig_node = data_ptr; - if (tt_common_entry->flags & TT_CLIENT_ROAM) + if (tt_common_entry->flags & BATADV_TT_CLIENT_ROAM) return 0; - tt_global_entry = container_of(tt_common_entry, struct tt_global_entry, + tt_global_entry = container_of(tt_common_entry, + struct batadv_tt_global_entry, common); - return tt_global_entry_has_orig(tt_global_entry, orig_node); + return batadv_tt_global_entry_has_orig(tt_global_entry, orig_node); } -static struct sk_buff *tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, - struct hashtable_t *hash, - struct hard_iface *primary_if, - int (*valid_cb)(const void *, - const void *), - void *cb_data) +static struct sk_buff * +batadv_tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, + struct batadv_hashtable *hash, + struct batadv_hard_iface *primary_if, + int (*valid_cb)(const void *, const void *), + void *cb_data) { - struct tt_common_entry *tt_common_entry; - struct tt_query_packet *tt_response; - struct tt_change *tt_change; + struct batadv_tt_common_entry *tt_common_entry; + struct batadv_tt_query_packet *tt_response; + struct batadv_tt_change *tt_change; struct hlist_node *node; struct hlist_head *head; struct sk_buff *skb = NULL; uint16_t tt_tot, tt_count; - ssize_t tt_query_size = sizeof(struct tt_query_packet); + ssize_t tt_query_size = sizeof(struct batadv_tt_query_packet); uint32_t i; + size_t len; if (tt_query_size + tt_len > primary_if->soft_iface->mtu) { tt_len = primary_if->soft_iface->mtu - tt_query_size; - tt_len -= tt_len % sizeof(struct tt_change); + tt_len -= tt_len % sizeof(struct batadv_tt_change); } - tt_tot = tt_len / sizeof(struct tt_change); + tt_tot = tt_len / sizeof(struct batadv_tt_change); - skb = dev_alloc_skb(tt_query_size + tt_len + ETH_HLEN); + len = tt_query_size + tt_len; + skb = dev_alloc_skb(len + ETH_HLEN); if (!skb) goto out; skb_reserve(skb, ETH_HLEN); - tt_response = (struct tt_query_packet *)skb_put(skb, - tt_query_size + tt_len); + tt_response = (struct batadv_tt_query_packet *)skb_put(skb, len); tt_response->ttvn = ttvn; - tt_change = (struct tt_change *)(skb->data + tt_query_size); + tt_change = (struct batadv_tt_change *)(skb->data + tt_query_size); tt_count = 0; rcu_read_lock(); @@ -1289,7 +1423,7 @@ static struct sk_buff *tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, memcpy(tt_change->addr, tt_common_entry->addr, ETH_ALEN); - tt_change->flags = NO_FLAGS; + tt_change->flags = BATADV_NO_FLAGS; tt_count++; tt_change++; @@ -1298,72 +1432,78 @@ static struct sk_buff *tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, rcu_read_unlock(); /* store in the message the number of entries we have successfully - * copied */ + * copied + */ tt_response->tt_data = htons(tt_count); out: return skb; } -static int send_tt_request(struct bat_priv *bat_priv, - struct orig_node *dst_orig_node, - uint8_t ttvn, uint16_t tt_crc, bool full_table) +static int batadv_send_tt_request(struct batadv_priv *bat_priv, + struct batadv_orig_node *dst_orig_node, + uint8_t ttvn, uint16_t tt_crc, + bool full_table) { struct sk_buff *skb = NULL; - struct tt_query_packet *tt_request; - struct neigh_node *neigh_node = NULL; - struct hard_iface *primary_if; - struct tt_req_node *tt_req_node = NULL; + struct batadv_tt_query_packet *tt_request; + struct batadv_neigh_node *neigh_node = NULL; + struct batadv_hard_iface *primary_if; + struct batadv_tt_req_node *tt_req_node = NULL; int ret = 1; + size_t tt_req_len; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; /* The new tt_req will be issued only if I'm not waiting for a - * reply from the same orig_node yet */ - tt_req_node = new_tt_req_node(bat_priv, dst_orig_node); + * reply from the same orig_node yet + */ + tt_req_node = batadv_new_tt_req_node(bat_priv, dst_orig_node); if (!tt_req_node) goto out; - skb = dev_alloc_skb(sizeof(struct tt_query_packet) + ETH_HLEN); + skb = dev_alloc_skb(sizeof(*tt_request) + ETH_HLEN); if (!skb) goto out; skb_reserve(skb, ETH_HLEN); - tt_request = (struct tt_query_packet *)skb_put(skb, - sizeof(struct tt_query_packet)); + tt_req_len = sizeof(*tt_request); + tt_request = (struct batadv_tt_query_packet *)skb_put(skb, tt_req_len); - tt_request->header.packet_type = BAT_TT_QUERY; - tt_request->header.version = COMPAT_VERSION; + tt_request->header.packet_type = BATADV_TT_QUERY; + tt_request->header.version = BATADV_COMPAT_VERSION; memcpy(tt_request->src, primary_if->net_dev->dev_addr, ETH_ALEN); memcpy(tt_request->dst, dst_orig_node->orig, ETH_ALEN); - tt_request->header.ttl = TTL; + tt_request->header.ttl = BATADV_TTL; tt_request->ttvn = ttvn; tt_request->tt_data = htons(tt_crc); - tt_request->flags = TT_REQUEST; + tt_request->flags = BATADV_TT_REQUEST; if (full_table) - tt_request->flags |= TT_FULL_TABLE; + tt_request->flags |= BATADV_TT_FULL_TABLE; - neigh_node = orig_node_get_router(dst_orig_node); + neigh_node = batadv_orig_node_get_router(dst_orig_node); if (!neigh_node) goto out; - bat_dbg(DBG_TT, bat_priv, - "Sending TT_REQUEST to %pM via %pM [%c]\n", - dst_orig_node->orig, neigh_node->addr, - (full_table ? 'F' : '.')); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Sending TT_REQUEST to %pM via %pM [%c]\n", + dst_orig_node->orig, neigh_node->addr, + (full_table ? 'F' : '.')); + + batadv_inc_counter(bat_priv, BATADV_CNT_TT_REQUEST_TX); - send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); ret = 0; out: if (neigh_node) - neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref(neigh_node); if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); if (ret) kfree_skb(skb); if (ret && tt_req_node) { @@ -1375,39 +1515,42 @@ out: return ret; } -static bool send_other_tt_response(struct bat_priv *bat_priv, - struct tt_query_packet *tt_request) +static bool +batadv_send_other_tt_response(struct batadv_priv *bat_priv, + struct batadv_tt_query_packet *tt_request) { - struct orig_node *req_dst_orig_node = NULL, *res_dst_orig_node = NULL; - struct neigh_node *neigh_node = NULL; - struct hard_iface *primary_if = NULL; + struct batadv_orig_node *req_dst_orig_node = NULL; + struct batadv_orig_node *res_dst_orig_node = NULL; + struct batadv_neigh_node *neigh_node = NULL; + struct batadv_hard_iface *primary_if = NULL; uint8_t orig_ttvn, req_ttvn, ttvn; int ret = false; unsigned char *tt_buff; bool full_table; uint16_t tt_len, tt_tot; struct sk_buff *skb = NULL; - struct tt_query_packet *tt_response; + struct batadv_tt_query_packet *tt_response; + size_t len; - bat_dbg(DBG_TT, bat_priv, - "Received TT_REQUEST from %pM for ttvn: %u (%pM) [%c]\n", - tt_request->src, tt_request->ttvn, tt_request->dst, - (tt_request->flags & TT_FULL_TABLE ? 'F' : '.')); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Received TT_REQUEST from %pM for ttvn: %u (%pM) [%c]\n", + tt_request->src, tt_request->ttvn, tt_request->dst, + (tt_request->flags & BATADV_TT_FULL_TABLE ? 'F' : '.')); /* Let's get the orig node of the REAL destination */ - req_dst_orig_node = orig_hash_find(bat_priv, tt_request->dst); + req_dst_orig_node = batadv_orig_hash_find(bat_priv, tt_request->dst); if (!req_dst_orig_node) goto out; - res_dst_orig_node = orig_hash_find(bat_priv, tt_request->src); + res_dst_orig_node = batadv_orig_hash_find(bat_priv, tt_request->src); if (!res_dst_orig_node) goto out; - neigh_node = orig_node_get_router(res_dst_orig_node); + neigh_node = batadv_orig_node_get_router(res_dst_orig_node); if (!neigh_node) goto out; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; @@ -1416,71 +1559,75 @@ static bool send_other_tt_response(struct bat_priv *bat_priv, /* I don't have the requested data */ if (orig_ttvn != req_ttvn || - tt_request->tt_data != req_dst_orig_node->tt_crc) + tt_request->tt_data != htons(req_dst_orig_node->tt_crc)) goto out; /* If the full table has been explicitly requested */ - if (tt_request->flags & TT_FULL_TABLE || + if (tt_request->flags & BATADV_TT_FULL_TABLE || !req_dst_orig_node->tt_buff) full_table = true; else full_table = false; /* In this version, fragmentation is not implemented, then - * I'll send only one packet with as much TT entries as I can */ + * I'll send only one packet with as much TT entries as I can + */ if (!full_table) { spin_lock_bh(&req_dst_orig_node->tt_buff_lock); tt_len = req_dst_orig_node->tt_buff_len; - tt_tot = tt_len / sizeof(struct tt_change); + tt_tot = tt_len / sizeof(struct batadv_tt_change); - skb = dev_alloc_skb(sizeof(struct tt_query_packet) + - tt_len + ETH_HLEN); + len = sizeof(*tt_response) + tt_len; + skb = dev_alloc_skb(len + ETH_HLEN); if (!skb) goto unlock; skb_reserve(skb, ETH_HLEN); - tt_response = (struct tt_query_packet *)skb_put(skb, - sizeof(struct tt_query_packet) + tt_len); + tt_response = (struct batadv_tt_query_packet *)skb_put(skb, + len); tt_response->ttvn = req_ttvn; tt_response->tt_data = htons(tt_tot); - tt_buff = skb->data + sizeof(struct tt_query_packet); + tt_buff = skb->data + sizeof(*tt_response); /* Copy the last orig_node's OGM buffer */ memcpy(tt_buff, req_dst_orig_node->tt_buff, req_dst_orig_node->tt_buff_len); spin_unlock_bh(&req_dst_orig_node->tt_buff_lock); } else { - tt_len = (uint16_t)atomic_read(&req_dst_orig_node->tt_size) * - sizeof(struct tt_change); + tt_len = (uint16_t)atomic_read(&req_dst_orig_node->tt_size); + tt_len *= sizeof(struct batadv_tt_change); ttvn = (uint8_t)atomic_read(&req_dst_orig_node->last_ttvn); - skb = tt_response_fill_table(tt_len, ttvn, - bat_priv->tt_global_hash, - primary_if, tt_global_valid_entry, - req_dst_orig_node); + skb = batadv_tt_response_fill_table(tt_len, ttvn, + bat_priv->tt_global_hash, + primary_if, + batadv_tt_global_valid, + req_dst_orig_node); if (!skb) goto out; - tt_response = (struct tt_query_packet *)skb->data; + tt_response = (struct batadv_tt_query_packet *)skb->data; } - tt_response->header.packet_type = BAT_TT_QUERY; - tt_response->header.version = COMPAT_VERSION; - tt_response->header.ttl = TTL; + tt_response->header.packet_type = BATADV_TT_QUERY; + tt_response->header.version = BATADV_COMPAT_VERSION; + tt_response->header.ttl = BATADV_TTL; memcpy(tt_response->src, req_dst_orig_node->orig, ETH_ALEN); memcpy(tt_response->dst, tt_request->src, ETH_ALEN); - tt_response->flags = TT_RESPONSE; + tt_response->flags = BATADV_TT_RESPONSE; if (full_table) - tt_response->flags |= TT_FULL_TABLE; + tt_response->flags |= BATADV_TT_FULL_TABLE; - bat_dbg(DBG_TT, bat_priv, - "Sending TT_RESPONSE %pM via %pM for %pM (ttvn: %u)\n", - res_dst_orig_node->orig, neigh_node->addr, - req_dst_orig_node->orig, req_ttvn); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Sending TT_RESPONSE %pM via %pM for %pM (ttvn: %u)\n", + res_dst_orig_node->orig, neigh_node->addr, + req_dst_orig_node->orig, req_ttvn); - send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + batadv_inc_counter(bat_priv, BATADV_CNT_TT_RESPONSE_TX); + + batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); ret = true; goto out; @@ -1489,114 +1636,122 @@ unlock: out: if (res_dst_orig_node) - orig_node_free_ref(res_dst_orig_node); + batadv_orig_node_free_ref(res_dst_orig_node); if (req_dst_orig_node) - orig_node_free_ref(req_dst_orig_node); + batadv_orig_node_free_ref(req_dst_orig_node); if (neigh_node) - neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref(neigh_node); if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); if (!ret) kfree_skb(skb); return ret; } -static bool send_my_tt_response(struct bat_priv *bat_priv, - struct tt_query_packet *tt_request) + +static bool +batadv_send_my_tt_response(struct batadv_priv *bat_priv, + struct batadv_tt_query_packet *tt_request) { - struct orig_node *orig_node = NULL; - struct neigh_node *neigh_node = NULL; - struct hard_iface *primary_if = NULL; + struct batadv_orig_node *orig_node = NULL; + struct batadv_neigh_node *neigh_node = NULL; + struct batadv_hard_iface *primary_if = NULL; uint8_t my_ttvn, req_ttvn, ttvn; int ret = false; unsigned char *tt_buff; bool full_table; uint16_t tt_len, tt_tot; struct sk_buff *skb = NULL; - struct tt_query_packet *tt_response; + struct batadv_tt_query_packet *tt_response; + size_t len; - bat_dbg(DBG_TT, bat_priv, - "Received TT_REQUEST from %pM for ttvn: %u (me) [%c]\n", - tt_request->src, tt_request->ttvn, - (tt_request->flags & TT_FULL_TABLE ? 'F' : '.')); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Received TT_REQUEST from %pM for ttvn: %u (me) [%c]\n", + tt_request->src, tt_request->ttvn, + (tt_request->flags & BATADV_TT_FULL_TABLE ? 'F' : '.')); my_ttvn = (uint8_t)atomic_read(&bat_priv->ttvn); req_ttvn = tt_request->ttvn; - orig_node = orig_hash_find(bat_priv, tt_request->src); + orig_node = batadv_orig_hash_find(bat_priv, tt_request->src); if (!orig_node) goto out; - neigh_node = orig_node_get_router(orig_node); + neigh_node = batadv_orig_node_get_router(orig_node); if (!neigh_node) goto out; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; /* If the full table has been explicitly requested or the gap - * is too big send the whole local translation table */ - if (tt_request->flags & TT_FULL_TABLE || my_ttvn != req_ttvn || + * is too big send the whole local translation table + */ + if (tt_request->flags & BATADV_TT_FULL_TABLE || my_ttvn != req_ttvn || !bat_priv->tt_buff) full_table = true; else full_table = false; /* In this version, fragmentation is not implemented, then - * I'll send only one packet with as much TT entries as I can */ + * I'll send only one packet with as much TT entries as I can + */ if (!full_table) { spin_lock_bh(&bat_priv->tt_buff_lock); tt_len = bat_priv->tt_buff_len; - tt_tot = tt_len / sizeof(struct tt_change); + tt_tot = tt_len / sizeof(struct batadv_tt_change); - skb = dev_alloc_skb(sizeof(struct tt_query_packet) + - tt_len + ETH_HLEN); + len = sizeof(*tt_response) + tt_len; + skb = dev_alloc_skb(len + ETH_HLEN); if (!skb) goto unlock; skb_reserve(skb, ETH_HLEN); - tt_response = (struct tt_query_packet *)skb_put(skb, - sizeof(struct tt_query_packet) + tt_len); + tt_response = (struct batadv_tt_query_packet *)skb_put(skb, + len); tt_response->ttvn = req_ttvn; tt_response->tt_data = htons(tt_tot); - tt_buff = skb->data + sizeof(struct tt_query_packet); + tt_buff = skb->data + sizeof(*tt_response); memcpy(tt_buff, bat_priv->tt_buff, bat_priv->tt_buff_len); spin_unlock_bh(&bat_priv->tt_buff_lock); } else { - tt_len = (uint16_t)atomic_read(&bat_priv->num_local_tt) * - sizeof(struct tt_change); + tt_len = (uint16_t)atomic_read(&bat_priv->num_local_tt); + tt_len *= sizeof(struct batadv_tt_change); ttvn = (uint8_t)atomic_read(&bat_priv->ttvn); - skb = tt_response_fill_table(tt_len, ttvn, - bat_priv->tt_local_hash, - primary_if, tt_local_valid_entry, - NULL); + skb = batadv_tt_response_fill_table(tt_len, ttvn, + bat_priv->tt_local_hash, + primary_if, + batadv_tt_local_valid_entry, + NULL); if (!skb) goto out; - tt_response = (struct tt_query_packet *)skb->data; + tt_response = (struct batadv_tt_query_packet *)skb->data; } - tt_response->header.packet_type = BAT_TT_QUERY; - tt_response->header.version = COMPAT_VERSION; - tt_response->header.ttl = TTL; + tt_response->header.packet_type = BATADV_TT_QUERY; + tt_response->header.version = BATADV_COMPAT_VERSION; + tt_response->header.ttl = BATADV_TTL; memcpy(tt_response->src, primary_if->net_dev->dev_addr, ETH_ALEN); memcpy(tt_response->dst, tt_request->src, ETH_ALEN); - tt_response->flags = TT_RESPONSE; + tt_response->flags = BATADV_TT_RESPONSE; if (full_table) - tt_response->flags |= TT_FULL_TABLE; + tt_response->flags |= BATADV_TT_FULL_TABLE; - bat_dbg(DBG_TT, bat_priv, - "Sending TT_RESPONSE to %pM via %pM [%c]\n", - orig_node->orig, neigh_node->addr, - (tt_response->flags & TT_FULL_TABLE ? 'F' : '.')); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Sending TT_RESPONSE to %pM via %pM [%c]\n", + orig_node->orig, neigh_node->addr, + (tt_response->flags & BATADV_TT_FULL_TABLE ? 'F' : '.')); - send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + batadv_inc_counter(bat_priv, BATADV_CNT_TT_RESPONSE_TX); + + batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); ret = true; goto out; @@ -1604,49 +1759,50 @@ unlock: spin_unlock_bh(&bat_priv->tt_buff_lock); out: if (orig_node) - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); if (neigh_node) - neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref(neigh_node); if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); if (!ret) kfree_skb(skb); /* This packet was for me, so it doesn't need to be re-routed */ return true; } -bool send_tt_response(struct bat_priv *bat_priv, - struct tt_query_packet *tt_request) +bool batadv_send_tt_response(struct batadv_priv *bat_priv, + struct batadv_tt_query_packet *tt_request) { - if (is_my_mac(tt_request->dst)) { + if (batadv_is_my_mac(tt_request->dst)) { /* don't answer backbone gws! */ - if (bla_is_backbone_gw_orig(bat_priv, tt_request->src)) + if (batadv_bla_is_backbone_gw_orig(bat_priv, tt_request->src)) return true; - return send_my_tt_response(bat_priv, tt_request); + return batadv_send_my_tt_response(bat_priv, tt_request); } else { - return send_other_tt_response(bat_priv, tt_request); + return batadv_send_other_tt_response(bat_priv, tt_request); } } -static void _tt_update_changes(struct bat_priv *bat_priv, - struct orig_node *orig_node, - struct tt_change *tt_change, - uint16_t tt_num_changes, uint8_t ttvn) +static void _batadv_tt_update_changes(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + struct batadv_tt_change *tt_change, + uint16_t tt_num_changes, uint8_t ttvn) { int i; + int roams; for (i = 0; i < tt_num_changes; i++) { - if ((tt_change + i)->flags & TT_CLIENT_DEL) - tt_global_del(bat_priv, orig_node, - (tt_change + i)->addr, - "tt removed by changes", - (tt_change + i)->flags & TT_CLIENT_ROAM); - else - if (!tt_global_add(bat_priv, orig_node, - (tt_change + i)->addr, ttvn, false, - (tt_change + i)->flags & - TT_CLIENT_WIFI)) + if ((tt_change + i)->flags & BATADV_TT_CLIENT_DEL) { + roams = (tt_change + i)->flags & BATADV_TT_CLIENT_ROAM; + batadv_tt_global_del(bat_priv, orig_node, + (tt_change + i)->addr, + "tt removed by changes", + roams); + } else { + if (!batadv_tt_global_add(bat_priv, orig_node, + (tt_change + i)->addr, + (tt_change + i)->flags, ttvn)) /* In case of problem while storing a * global_entry, we stop the updating * procedure without committing the @@ -1654,25 +1810,27 @@ static void _tt_update_changes(struct bat_priv *bat_priv, * corrupted data on tt_request */ return; + } } orig_node->tt_initialised = true; } -static void tt_fill_gtable(struct bat_priv *bat_priv, - struct tt_query_packet *tt_response) +static void batadv_tt_fill_gtable(struct batadv_priv *bat_priv, + struct batadv_tt_query_packet *tt_response) { - struct orig_node *orig_node = NULL; + struct batadv_orig_node *orig_node = NULL; - orig_node = orig_hash_find(bat_priv, tt_response->src); + orig_node = batadv_orig_hash_find(bat_priv, tt_response->src); if (!orig_node) goto out; /* Purge the old table first.. */ - tt_global_del_orig(bat_priv, orig_node, "Received full table"); + batadv_tt_global_del_orig(bat_priv, orig_node, "Received full table"); - _tt_update_changes(bat_priv, orig_node, - (struct tt_change *)(tt_response + 1), - tt_response->tt_data, tt_response->ttvn); + _batadv_tt_update_changes(bat_priv, orig_node, + (struct batadv_tt_change *)(tt_response + 1), + ntohs(tt_response->tt_data), + tt_response->ttvn); spin_lock_bh(&orig_node->tt_buff_lock); kfree(orig_node->tt_buff); @@ -1684,71 +1842,76 @@ static void tt_fill_gtable(struct bat_priv *bat_priv, out: if (orig_node) - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); } -static void tt_update_changes(struct bat_priv *bat_priv, - struct orig_node *orig_node, - uint16_t tt_num_changes, uint8_t ttvn, - struct tt_change *tt_change) +static void batadv_tt_update_changes(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + uint16_t tt_num_changes, uint8_t ttvn, + struct batadv_tt_change *tt_change) { - _tt_update_changes(bat_priv, orig_node, tt_change, tt_num_changes, - ttvn); + _batadv_tt_update_changes(bat_priv, orig_node, tt_change, + tt_num_changes, ttvn); - tt_save_orig_buffer(bat_priv, orig_node, (unsigned char *)tt_change, - tt_num_changes); + batadv_tt_save_orig_buffer(bat_priv, orig_node, + (unsigned char *)tt_change, tt_num_changes); atomic_set(&orig_node->last_ttvn, ttvn); } -bool is_my_client(struct bat_priv *bat_priv, const uint8_t *addr) +bool batadv_is_my_client(struct batadv_priv *bat_priv, const uint8_t *addr) { - struct tt_local_entry *tt_local_entry = NULL; + struct batadv_tt_local_entry *tt_local_entry = NULL; bool ret = false; - tt_local_entry = tt_local_hash_find(bat_priv, addr); + tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr); if (!tt_local_entry) goto out; /* Check if the client has been logically deleted (but is kept for - * consistency purpose) */ - if (tt_local_entry->common.flags & TT_CLIENT_PENDING) + * consistency purpose) + */ + if (tt_local_entry->common.flags & BATADV_TT_CLIENT_PENDING) goto out; ret = true; out: if (tt_local_entry) - tt_local_entry_free_ref(tt_local_entry); + batadv_tt_local_entry_free_ref(tt_local_entry); return ret; } -void handle_tt_response(struct bat_priv *bat_priv, - struct tt_query_packet *tt_response) +void batadv_handle_tt_response(struct batadv_priv *bat_priv, + struct batadv_tt_query_packet *tt_response) { - struct tt_req_node *node, *safe; - struct orig_node *orig_node = NULL; + struct batadv_tt_req_node *node, *safe; + struct batadv_orig_node *orig_node = NULL; + struct batadv_tt_change *tt_change; - bat_dbg(DBG_TT, bat_priv, - "Received TT_RESPONSE from %pM for ttvn %d t_size: %d [%c]\n", - tt_response->src, tt_response->ttvn, tt_response->tt_data, - (tt_response->flags & TT_FULL_TABLE ? 'F' : '.')); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Received TT_RESPONSE from %pM for ttvn %d t_size: %d [%c]\n", + tt_response->src, tt_response->ttvn, + ntohs(tt_response->tt_data), + (tt_response->flags & BATADV_TT_FULL_TABLE ? 'F' : '.')); /* we should have never asked a backbone gw */ - if (bla_is_backbone_gw_orig(bat_priv, tt_response->src)) + if (batadv_bla_is_backbone_gw_orig(bat_priv, tt_response->src)) goto out; - orig_node = orig_hash_find(bat_priv, tt_response->src); + orig_node = batadv_orig_hash_find(bat_priv, tt_response->src); if (!orig_node) goto out; - if (tt_response->flags & TT_FULL_TABLE) - tt_fill_gtable(bat_priv, tt_response); - else - tt_update_changes(bat_priv, orig_node, tt_response->tt_data, - tt_response->ttvn, - (struct tt_change *)(tt_response + 1)); + if (tt_response->flags & BATADV_TT_FULL_TABLE) { + batadv_tt_fill_gtable(bat_priv, tt_response); + } else { + tt_change = (struct batadv_tt_change *)(tt_response + 1); + batadv_tt_update_changes(bat_priv, orig_node, + ntohs(tt_response->tt_data), + tt_response->ttvn, tt_change); + } /* Delete the tt_req_node from pending tt_requests list */ spin_lock_bh(&bat_priv->tt_req_list_lock); list_for_each_entry_safe(node, safe, &bat_priv->tt_req_list, list) { - if (!compare_eth(node->addr, tt_response->src)) + if (!batadv_compare_eth(node->addr, tt_response->src)) continue; list_del(&node->list); kfree(node); @@ -1756,31 +1919,36 @@ void handle_tt_response(struct bat_priv *bat_priv, spin_unlock_bh(&bat_priv->tt_req_list_lock); /* Recalculate the CRC for this orig_node and store it */ - orig_node->tt_crc = tt_global_crc(bat_priv, orig_node); + orig_node->tt_crc = batadv_tt_global_crc(bat_priv, orig_node); /* Roaming phase is over: tables are in sync again. I can - * unset the flag */ + * unset the flag + */ orig_node->tt_poss_change = false; out: if (orig_node) - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); } -int tt_init(struct bat_priv *bat_priv) +int batadv_tt_init(struct batadv_priv *bat_priv) { - if (!tt_local_init(bat_priv)) - return 0; + int ret; - if (!tt_global_init(bat_priv)) - return 0; + ret = batadv_tt_local_init(bat_priv); + if (ret < 0) + return ret; - tt_start_timer(bat_priv); + ret = batadv_tt_global_init(bat_priv); + if (ret < 0) + return ret; + + batadv_tt_start_timer(bat_priv); return 1; } -static void tt_roam_list_free(struct bat_priv *bat_priv) +static void batadv_tt_roam_list_free(struct batadv_priv *bat_priv) { - struct tt_roam_node *node, *safe; + struct batadv_tt_roam_node *node, *safe; spin_lock_bh(&bat_priv->tt_roam_list_lock); @@ -1792,13 +1960,14 @@ static void tt_roam_list_free(struct bat_priv *bat_priv) spin_unlock_bh(&bat_priv->tt_roam_list_lock); } -static void tt_roam_purge(struct bat_priv *bat_priv) +static void batadv_tt_roam_purge(struct batadv_priv *bat_priv) { - struct tt_roam_node *node, *safe; + struct batadv_tt_roam_node *node, *safe; spin_lock_bh(&bat_priv->tt_roam_list_lock); list_for_each_entry_safe(node, safe, &bat_priv->tt_roam_list, list) { - if (!has_timed_out(node->first_time, ROAMING_MAX_TIME)) + if (!batadv_has_timed_out(node->first_time, + BATADV_ROAMING_MAX_TIME)) continue; list_del(&node->list); @@ -1811,24 +1980,27 @@ static void tt_roam_purge(struct bat_priv *bat_priv) * maximum number of possible roaming phases. In this case the ROAMING_ADV * will not be sent. * - * returns true if the ROAMING_ADV can be sent, false otherwise */ -static bool tt_check_roam_count(struct bat_priv *bat_priv, - uint8_t *client) + * returns true if the ROAMING_ADV can be sent, false otherwise + */ +static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, + uint8_t *client) { - struct tt_roam_node *tt_roam_node; + struct batadv_tt_roam_node *tt_roam_node; bool ret = false; spin_lock_bh(&bat_priv->tt_roam_list_lock); /* The new tt_req will be issued only if I'm not waiting for a - * reply from the same orig_node yet */ + * reply from the same orig_node yet + */ list_for_each_entry(tt_roam_node, &bat_priv->tt_roam_list, list) { - if (!compare_eth(tt_roam_node->addr, client)) + if (!batadv_compare_eth(tt_roam_node->addr, client)) continue; - if (has_timed_out(tt_roam_node->first_time, ROAMING_MAX_TIME)) + if (batadv_has_timed_out(tt_roam_node->first_time, + BATADV_ROAMING_MAX_TIME)) continue; - if (!atomic_dec_not_zero(&tt_roam_node->counter)) + if (!batadv_atomic_dec_not_zero(&tt_roam_node->counter)) /* Sorry, you roamed too many times! */ goto unlock; ret = true; @@ -1841,7 +2013,8 @@ static bool tt_check_roam_count(struct bat_priv *bat_priv, goto unlock; tt_roam_node->first_time = jiffies; - atomic_set(&tt_roam_node->counter, ROAMING_MAX_COUNT - 1); + atomic_set(&tt_roam_node->counter, + BATADV_ROAMING_MAX_COUNT - 1); memcpy(tt_roam_node->addr, client, ETH_ALEN); list_add(&tt_roam_node->list, &bat_priv->tt_roam_list); @@ -1853,97 +2026,103 @@ unlock: return ret; } -static void send_roam_adv(struct bat_priv *bat_priv, uint8_t *client, - struct orig_node *orig_node) +static void batadv_send_roam_adv(struct batadv_priv *bat_priv, uint8_t *client, + struct batadv_orig_node *orig_node) { - struct neigh_node *neigh_node = NULL; + struct batadv_neigh_node *neigh_node = NULL; struct sk_buff *skb = NULL; - struct roam_adv_packet *roam_adv_packet; + struct batadv_roam_adv_packet *roam_adv_packet; int ret = 1; - struct hard_iface *primary_if; + struct batadv_hard_iface *primary_if; + size_t len = sizeof(*roam_adv_packet); /* before going on we have to check whether the client has - * already roamed to us too many times */ - if (!tt_check_roam_count(bat_priv, client)) + * already roamed to us too many times + */ + if (!batadv_tt_check_roam_count(bat_priv, client)) goto out; - skb = dev_alloc_skb(sizeof(struct roam_adv_packet) + ETH_HLEN); + skb = dev_alloc_skb(sizeof(*roam_adv_packet) + ETH_HLEN); if (!skb) goto out; skb_reserve(skb, ETH_HLEN); - roam_adv_packet = (struct roam_adv_packet *)skb_put(skb, - sizeof(struct roam_adv_packet)); + roam_adv_packet = (struct batadv_roam_adv_packet *)skb_put(skb, len); - roam_adv_packet->header.packet_type = BAT_ROAM_ADV; - roam_adv_packet->header.version = COMPAT_VERSION; - roam_adv_packet->header.ttl = TTL; - primary_if = primary_if_get_selected(bat_priv); + roam_adv_packet->header.packet_type = BATADV_ROAM_ADV; + roam_adv_packet->header.version = BATADV_COMPAT_VERSION; + roam_adv_packet->header.ttl = BATADV_TTL; + roam_adv_packet->reserved = 0; + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; memcpy(roam_adv_packet->src, primary_if->net_dev->dev_addr, ETH_ALEN); - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); memcpy(roam_adv_packet->dst, orig_node->orig, ETH_ALEN); memcpy(roam_adv_packet->client, client, ETH_ALEN); - neigh_node = orig_node_get_router(orig_node); + neigh_node = batadv_orig_node_get_router(orig_node); if (!neigh_node) goto out; - bat_dbg(DBG_TT, bat_priv, - "Sending ROAMING_ADV to %pM (client %pM) via %pM\n", - orig_node->orig, client, neigh_node->addr); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Sending ROAMING_ADV to %pM (client %pM) via %pM\n", + orig_node->orig, client, neigh_node->addr); + + batadv_inc_counter(bat_priv, BATADV_CNT_TT_ROAM_ADV_TX); - send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); ret = 0; out: if (neigh_node) - neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref(neigh_node); if (ret) kfree_skb(skb); return; } -static void tt_purge(struct work_struct *work) +static void batadv_tt_purge(struct work_struct *work) { - struct delayed_work *delayed_work = - container_of(work, struct delayed_work, work); - struct bat_priv *bat_priv = - container_of(delayed_work, struct bat_priv, tt_work); + struct delayed_work *delayed_work; + struct batadv_priv *bat_priv; - tt_local_purge(bat_priv); - tt_global_roam_purge(bat_priv); - tt_req_purge(bat_priv); - tt_roam_purge(bat_priv); + delayed_work = container_of(work, struct delayed_work, work); + bat_priv = container_of(delayed_work, struct batadv_priv, tt_work); - tt_start_timer(bat_priv); + batadv_tt_local_purge(bat_priv); + batadv_tt_global_roam_purge(bat_priv); + batadv_tt_req_purge(bat_priv); + batadv_tt_roam_purge(bat_priv); + + batadv_tt_start_timer(bat_priv); } -void tt_free(struct bat_priv *bat_priv) +void batadv_tt_free(struct batadv_priv *bat_priv) { cancel_delayed_work_sync(&bat_priv->tt_work); - tt_local_table_free(bat_priv); - tt_global_table_free(bat_priv); - tt_req_list_free(bat_priv); - tt_changes_list_free(bat_priv); - tt_roam_list_free(bat_priv); + batadv_tt_local_table_free(bat_priv); + batadv_tt_global_table_free(bat_priv); + batadv_tt_req_list_free(bat_priv); + batadv_tt_changes_list_free(bat_priv); + batadv_tt_roam_list_free(bat_priv); kfree(bat_priv->tt_buff); } /* This function will enable or disable the specified flags for all the entries - * in the given hash table and returns the number of modified entries */ -static uint16_t tt_set_flags(struct hashtable_t *hash, uint16_t flags, - bool enable) + * in the given hash table and returns the number of modified entries + */ +static uint16_t batadv_tt_set_flags(struct batadv_hashtable *hash, + uint16_t flags, bool enable) { uint32_t i; uint16_t changed_num = 0; struct hlist_head *head; struct hlist_node *node; - struct tt_common_entry *tt_common_entry; + struct batadv_tt_common_entry *tt_common_entry; if (!hash) goto out; @@ -1971,12 +2150,12 @@ out: return changed_num; } -/* Purge out all the tt local entries marked with TT_CLIENT_PENDING */ -static void tt_local_purge_pending_clients(struct bat_priv *bat_priv) +/* Purge out all the tt local entries marked with BATADV_TT_CLIENT_PENDING */ +static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) { - struct hashtable_t *hash = bat_priv->tt_local_hash; - struct tt_common_entry *tt_common_entry; - struct tt_local_entry *tt_local_entry; + struct batadv_hashtable *hash = bat_priv->tt_local_hash; + struct batadv_tt_common_entry *tt_common; + struct batadv_tt_local_entry *tt_local; struct hlist_node *node, *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ @@ -1990,103 +2169,149 @@ static void tt_local_purge_pending_clients(struct bat_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(tt_common_entry, node, node_tmp, - head, hash_entry) { - if (!(tt_common_entry->flags & TT_CLIENT_PENDING)) + hlist_for_each_entry_safe(tt_common, node, node_tmp, head, + hash_entry) { + if (!(tt_common->flags & BATADV_TT_CLIENT_PENDING)) continue; - bat_dbg(DBG_TT, bat_priv, - "Deleting local tt entry (%pM): pending\n", - tt_common_entry->addr); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Deleting local tt entry (%pM): pending\n", + tt_common->addr); atomic_dec(&bat_priv->num_local_tt); hlist_del_rcu(node); - tt_local_entry = container_of(tt_common_entry, - struct tt_local_entry, - common); - tt_local_entry_free_ref(tt_local_entry); + tt_local = container_of(tt_common, + struct batadv_tt_local_entry, + common); + batadv_tt_local_entry_free_ref(tt_local); } spin_unlock_bh(list_lock); } } -void tt_commit_changes(struct bat_priv *bat_priv) +static int batadv_tt_commit_changes(struct batadv_priv *bat_priv, + unsigned char **packet_buff, + int *packet_buff_len, int packet_min_len) { - uint16_t changed_num = tt_set_flags(bat_priv->tt_local_hash, - TT_CLIENT_NEW, false); - /* all the reset entries have now to be effectively counted as local - * entries */ + uint16_t changed_num = 0; + + if (atomic_read(&bat_priv->tt_local_changes) < 1) + return -ENOENT; + + changed_num = batadv_tt_set_flags(bat_priv->tt_local_hash, + BATADV_TT_CLIENT_NEW, false); + + /* all reset entries have to be counted as local entries */ atomic_add(changed_num, &bat_priv->num_local_tt); - tt_local_purge_pending_clients(bat_priv); + batadv_tt_local_purge_pending_clients(bat_priv); + bat_priv->tt_crc = batadv_tt_local_crc(bat_priv); /* Increment the TTVN only once per OGM interval */ atomic_inc(&bat_priv->ttvn); - bat_dbg(DBG_TT, bat_priv, "Local changes committed, updating to ttvn %u\n", - (uint8_t)atomic_read(&bat_priv->ttvn)); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Local changes committed, updating to ttvn %u\n", + (uint8_t)atomic_read(&bat_priv->ttvn)); bat_priv->tt_poss_change = false; + + /* reset the sending counter */ + atomic_set(&bat_priv->tt_ogm_append_cnt, BATADV_TT_OGM_APPEND_MAX); + + return batadv_tt_changes_fill_buff(bat_priv, packet_buff, + packet_buff_len, packet_min_len); +} + +/* when calling this function (hard_iface == primary_if) has to be true */ +int batadv_tt_append_diff(struct batadv_priv *bat_priv, + unsigned char **packet_buff, int *packet_buff_len, + int packet_min_len) +{ + int tt_num_changes; + + /* if at least one change happened */ + tt_num_changes = batadv_tt_commit_changes(bat_priv, packet_buff, + packet_buff_len, + packet_min_len); + + /* if the changes have been sent often enough */ + if ((tt_num_changes < 0) && + (!batadv_atomic_dec_not_zero(&bat_priv->tt_ogm_append_cnt))) { + batadv_tt_realloc_packet_buff(packet_buff, packet_buff_len, + packet_min_len, packet_min_len); + tt_num_changes = 0; + } + + return tt_num_changes; } -bool is_ap_isolated(struct bat_priv *bat_priv, uint8_t *src, uint8_t *dst) +bool batadv_is_ap_isolated(struct batadv_priv *bat_priv, uint8_t *src, + uint8_t *dst) { - struct tt_local_entry *tt_local_entry = NULL; - struct tt_global_entry *tt_global_entry = NULL; + struct batadv_tt_local_entry *tt_local_entry = NULL; + struct batadv_tt_global_entry *tt_global_entry = NULL; bool ret = false; if (!atomic_read(&bat_priv->ap_isolation)) goto out; - tt_local_entry = tt_local_hash_find(bat_priv, dst); + tt_local_entry = batadv_tt_local_hash_find(bat_priv, dst); if (!tt_local_entry) goto out; - tt_global_entry = tt_global_hash_find(bat_priv, src); + tt_global_entry = batadv_tt_global_hash_find(bat_priv, src); if (!tt_global_entry) goto out; - if (!_is_ap_isolated(tt_local_entry, tt_global_entry)) + if (!_batadv_is_ap_isolated(tt_local_entry, tt_global_entry)) goto out; ret = true; out: if (tt_global_entry) - tt_global_entry_free_ref(tt_global_entry); + batadv_tt_global_entry_free_ref(tt_global_entry); if (tt_local_entry) - tt_local_entry_free_ref(tt_local_entry); + batadv_tt_local_entry_free_ref(tt_local_entry); return ret; } -void tt_update_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, - const unsigned char *tt_buff, uint8_t tt_num_changes, - uint8_t ttvn, uint16_t tt_crc) +void batadv_tt_update_orig(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + const unsigned char *tt_buff, uint8_t tt_num_changes, + uint8_t ttvn, uint16_t tt_crc) { uint8_t orig_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); bool full_table = true; + struct batadv_tt_change *tt_change; /* don't care about a backbone gateways updates. */ - if (bla_is_backbone_gw_orig(bat_priv, orig_node->orig)) + if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig)) return; /* orig table not initialised AND first diff is in the OGM OR the ttvn - * increased by one -> we can apply the attached changes */ + * increased by one -> we can apply the attached changes + */ if ((!orig_node->tt_initialised && ttvn == 1) || ttvn - orig_ttvn == 1) { /* the OGM could not contain the changes due to their size or - * because they have already been sent TT_OGM_APPEND_MAX times. - * In this case send a tt request */ + * because they have already been sent BATADV_TT_OGM_APPEND_MAX + * times. + * In this case send a tt request + */ if (!tt_num_changes) { full_table = false; goto request_table; } - tt_update_changes(bat_priv, orig_node, tt_num_changes, ttvn, - (struct tt_change *)tt_buff); + tt_change = (struct batadv_tt_change *)tt_buff; + batadv_tt_update_changes(bat_priv, orig_node, tt_num_changes, + ttvn, tt_change); /* Even if we received the precomputed crc with the OGM, we * prefer to recompute it to spot any possible inconsistency - * in the global table */ - orig_node->tt_crc = tt_global_crc(bat_priv, orig_node); + * in the global table + */ + orig_node->tt_crc = batadv_tt_global_crc(bat_priv, orig_node); /* The ttvn alone is not enough to guarantee consistency * because a single value could represent different states @@ -2095,26 +2320,28 @@ void tt_update_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, * consistent or not. E.g. a node could disconnect while its * ttvn is X and reconnect on ttvn = X + TTVN_MAX: in this case * checking the CRC value is mandatory to detect the - * inconsistency */ + * inconsistency + */ if (orig_node->tt_crc != tt_crc) goto request_table; /* Roaming phase is over: tables are in sync again. I can - * unset the flag */ + * unset the flag + */ orig_node->tt_poss_change = false; } else { /* if we missed more than one change or our tables are not - * in sync anymore -> request fresh tt data */ - + * in sync anymore -> request fresh tt data + */ if (!orig_node->tt_initialised || ttvn != orig_ttvn || orig_node->tt_crc != tt_crc) { request_table: - bat_dbg(DBG_TT, bat_priv, - "TT inconsistency for %pM. Need to retrieve the correct information (ttvn: %u last_ttvn: %u crc: %u last_crc: %u num_changes: %u)\n", - orig_node->orig, ttvn, orig_ttvn, tt_crc, - orig_node->tt_crc, tt_num_changes); - send_tt_request(bat_priv, orig_node, ttvn, tt_crc, - full_table); + batadv_dbg(BATADV_DBG_TT, bat_priv, + "TT inconsistency for %pM. Need to retrieve the correct information (ttvn: %u last_ttvn: %u crc: %u last_crc: %u num_changes: %u)\n", + orig_node->orig, ttvn, orig_ttvn, tt_crc, + orig_node->tt_crc, tt_num_changes); + batadv_send_tt_request(bat_priv, orig_node, ttvn, + tt_crc, full_table); return; } } @@ -2124,17 +2351,18 @@ request_table: * originator to another one. This entry is kept is still kept for consistency * purposes */ -bool tt_global_client_is_roaming(struct bat_priv *bat_priv, uint8_t *addr) +bool batadv_tt_global_client_is_roaming(struct batadv_priv *bat_priv, + uint8_t *addr) { - struct tt_global_entry *tt_global_entry; + struct batadv_tt_global_entry *tt_global_entry; bool ret = false; - tt_global_entry = tt_global_hash_find(bat_priv, addr); + tt_global_entry = batadv_tt_global_hash_find(bat_priv, addr); if (!tt_global_entry) goto out; - ret = tt_global_entry->common.flags & TT_CLIENT_ROAM; - tt_global_entry_free_ref(tt_global_entry); + ret = tt_global_entry->common.flags & BATADV_TT_CLIENT_ROAM; + batadv_tt_global_entry_free_ref(tt_global_entry); out: return ret; } diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index c43374dc364..ffa87355096 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * @@ -16,44 +15,50 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ #define _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ -int tt_len(int changes_num); -int tt_changes_fill_buffer(struct bat_priv *bat_priv, - unsigned char *buff, int buff_len); -int tt_init(struct bat_priv *bat_priv); -void tt_local_add(struct net_device *soft_iface, const uint8_t *addr, - int ifindex); -void tt_local_remove(struct bat_priv *bat_priv, - const uint8_t *addr, const char *message, bool roaming); -int tt_local_seq_print_text(struct seq_file *seq, void *offset); -void tt_global_add_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, - const unsigned char *tt_buff, int tt_buff_len); -int tt_global_add(struct bat_priv *bat_priv, struct orig_node *orig_node, - const unsigned char *addr, uint8_t ttvn, bool roaming, - bool wifi); -int tt_global_seq_print_text(struct seq_file *seq, void *offset); -void tt_global_del_orig(struct bat_priv *bat_priv, - struct orig_node *orig_node, const char *message); -struct orig_node *transtable_search(struct bat_priv *bat_priv, - const uint8_t *src, const uint8_t *addr); -uint16_t tt_local_crc(struct bat_priv *bat_priv); -void tt_free(struct bat_priv *bat_priv); -bool send_tt_response(struct bat_priv *bat_priv, - struct tt_query_packet *tt_request); -bool is_my_client(struct bat_priv *bat_priv, const uint8_t *addr); -void handle_tt_response(struct bat_priv *bat_priv, - struct tt_query_packet *tt_response); -void tt_commit_changes(struct bat_priv *bat_priv); -bool is_ap_isolated(struct bat_priv *bat_priv, uint8_t *src, uint8_t *dst); -void tt_update_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, - const unsigned char *tt_buff, uint8_t tt_num_changes, - uint8_t ttvn, uint16_t tt_crc); -bool tt_global_client_is_roaming(struct bat_priv *bat_priv, uint8_t *addr); +int batadv_tt_len(int changes_num); +int batadv_tt_init(struct batadv_priv *bat_priv); +void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, + int ifindex); +void batadv_tt_local_remove(struct batadv_priv *bat_priv, + const uint8_t *addr, const char *message, + bool roaming); +int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset); +void batadv_tt_global_add_orig(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + const unsigned char *tt_buff, int tt_buff_len); +int batadv_tt_global_add(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + const unsigned char *addr, uint8_t flags, + uint8_t ttvn); +int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset); +void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + const char *message); +struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv, + const uint8_t *src, + const uint8_t *addr); +void batadv_tt_free(struct batadv_priv *bat_priv); +bool batadv_send_tt_response(struct batadv_priv *bat_priv, + struct batadv_tt_query_packet *tt_request); +bool batadv_is_my_client(struct batadv_priv *bat_priv, const uint8_t *addr); +void batadv_handle_tt_response(struct batadv_priv *bat_priv, + struct batadv_tt_query_packet *tt_response); +bool batadv_is_ap_isolated(struct batadv_priv *bat_priv, uint8_t *src, + uint8_t *dst); +void batadv_tt_update_orig(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + const unsigned char *tt_buff, uint8_t tt_num_changes, + uint8_t ttvn, uint16_t tt_crc); +int batadv_tt_append_diff(struct batadv_priv *bat_priv, + unsigned char **packet_buff, int *packet_buff_len, + int packet_min_len); +bool batadv_tt_global_client_is_roaming(struct batadv_priv *bat_priv, + uint8_t *addr); #endif /* _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 61308e8016f..12635fd2c3d 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -16,24 +15,20 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ - - #ifndef _NET_BATMAN_ADV_TYPES_H_ #define _NET_BATMAN_ADV_TYPES_H_ #include "packet.h" #include "bitarray.h" +#include <linux/kernel.h> -#define BAT_HEADER_LEN (ETH_HLEN + \ - ((sizeof(struct unicast_packet) > sizeof(struct bcast_packet) ? \ - sizeof(struct unicast_packet) : \ - sizeof(struct bcast_packet)))) - +#define BATADV_HEADER_LEN \ + (ETH_HLEN + max(sizeof(struct batadv_unicast_packet), \ + sizeof(struct batadv_bcast_packet))) -struct hard_iface { +struct batadv_hard_iface { struct list_head list; int16_t if_num; char if_status; @@ -50,7 +45,7 @@ struct hard_iface { }; /** - * orig_node - structure for orig_list maintaining nodes of mesh + * struct batadv_orig_node - structure for orig_list maintaining nodes of mesh * @primary_addr: hosts primary interface address * @last_seen: when last packet from this node was received * @bcast_seqno_reset: time when the broadcast seqno window was reset @@ -64,10 +59,10 @@ struct hard_iface { * @candidates: how many candidates are available * @selected: next bonding candidate */ -struct orig_node { +struct batadv_orig_node { uint8_t orig[ETH_ALEN]; uint8_t primary_addr[ETH_ALEN]; - struct neigh_node __rcu *router; /* rcu protected pointer */ + struct batadv_neigh_node __rcu *router; /* rcu protected pointer */ unsigned long *bcast_own; uint8_t *bcast_own_sum; unsigned long last_seen; @@ -86,11 +81,12 @@ struct orig_node { * If true, then I sent a Roaming_adv to this orig_node and I have to * inspect every packet directed to it to check whether it is still * the true destination or not. This flag will be reset to false as - * soon as I receive a new TTVN from this orig_node */ + * soon as I receive a new TTVN from this orig_node + */ bool tt_poss_change; uint32_t last_real_seqno; uint8_t last_ttl; - DECLARE_BITMAP(bcast_bits, TQ_LOCAL_WINDOW_SIZE); + DECLARE_BITMAP(bcast_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); uint32_t last_bcast_seqno; struct hlist_head neigh_list; struct list_head frag_list; @@ -98,10 +94,11 @@ struct orig_node { atomic_t refcount; struct rcu_head rcu; struct hlist_node hash_entry; - struct bat_priv *bat_priv; + struct batadv_priv *bat_priv; unsigned long last_frag_packet; /* ogm_cnt_lock protects: bcast_own, bcast_own_sum, - * neigh_node->real_bits, neigh_node->real_packet_count */ + * neigh_node->real_bits, neigh_node->real_packet_count + */ spinlock_t ogm_cnt_lock; /* bcast_seqno_lock protects bcast_bits, last_bcast_seqno */ spinlock_t bcast_seqno_lock; @@ -110,47 +107,63 @@ struct orig_node { struct list_head bond_list; }; -struct gw_node { +struct batadv_gw_node { struct hlist_node list; - struct orig_node *orig_node; + struct batadv_orig_node *orig_node; unsigned long deleted; atomic_t refcount; struct rcu_head rcu; }; -/** - * neigh_node +/* batadv_neigh_node * @last_seen: when last packet via this neighbor was received */ -struct neigh_node { +struct batadv_neigh_node { struct hlist_node list; uint8_t addr[ETH_ALEN]; uint8_t real_packet_count; - uint8_t tq_recv[TQ_GLOBAL_WINDOW_SIZE]; + uint8_t tq_recv[BATADV_TQ_GLOBAL_WINDOW_SIZE]; uint8_t tq_index; uint8_t tq_avg; uint8_t last_ttl; struct list_head bonding_list; unsigned long last_seen; - DECLARE_BITMAP(real_bits, TQ_LOCAL_WINDOW_SIZE); + DECLARE_BITMAP(real_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); atomic_t refcount; struct rcu_head rcu; - struct orig_node *orig_node; - struct hard_iface *if_incoming; + struct batadv_orig_node *orig_node; + struct batadv_hard_iface *if_incoming; spinlock_t lq_update_lock; /* protects: tq_recv, tq_index */ }; #ifdef CONFIG_BATMAN_ADV_BLA -struct bcast_duplist_entry { +struct batadv_bcast_duplist_entry { uint8_t orig[ETH_ALEN]; uint16_t crc; unsigned long entrytime; }; #endif -struct bat_priv { +enum batadv_counters { + BATADV_CNT_FORWARD, + BATADV_CNT_FORWARD_BYTES, + BATADV_CNT_MGMT_TX, + BATADV_CNT_MGMT_TX_BYTES, + BATADV_CNT_MGMT_RX, + BATADV_CNT_MGMT_RX_BYTES, + BATADV_CNT_TT_REQUEST_TX, + BATADV_CNT_TT_REQUEST_RX, + BATADV_CNT_TT_RESPONSE_TX, + BATADV_CNT_TT_RESPONSE_RX, + BATADV_CNT_TT_ROAM_ADV_TX, + BATADV_CNT_TT_ROAM_ADV_RX, + BATADV_CNT_NUM, +}; + +struct batadv_priv { atomic_t mesh_state; struct net_device_stats stats; + uint64_t __percpu *bat_counters; /* Per cpu counters */ atomic_t aggregated_ogms; /* boolean */ atomic_t bonding; /* boolean */ atomic_t fragmentation; /* boolean */ @@ -174,10 +187,11 @@ struct bat_priv { * If true, then I received a Roaming_adv and I have to inspect every * packet directed to me to check whether I am still the true * destination or not. This flag will be reset to false as soon as I - * increase my TTVN */ + * increase my TTVN + */ bool tt_poss_change; char num_ifaces; - struct debug_log *debug_log; + struct batadv_debug_log *debug_log; struct kobject *mesh_obj; struct dentry *debug_dir; struct hlist_head forw_bat_list; @@ -185,20 +199,20 @@ struct bat_priv { struct hlist_head gw_list; struct list_head tt_changes_list; /* tracks changes in a OGM int */ struct list_head vis_send_list; - struct hashtable_t *orig_hash; - struct hashtable_t *tt_local_hash; - struct hashtable_t *tt_global_hash; + struct batadv_hashtable *orig_hash; + struct batadv_hashtable *tt_local_hash; + struct batadv_hashtable *tt_global_hash; #ifdef CONFIG_BATMAN_ADV_BLA - struct hashtable_t *claim_hash; - struct hashtable_t *backbone_hash; + struct batadv_hashtable *claim_hash; + struct batadv_hashtable *backbone_hash; #endif struct list_head tt_req_list; /* list of pending tt_requests */ struct list_head tt_roam_list; - struct hashtable_t *vis_hash; + struct batadv_hashtable *vis_hash; #ifdef CONFIG_BATMAN_ADV_BLA - struct bcast_duplist_entry bcast_duplist[DUPLIST_SIZE]; + struct batadv_bcast_duplist_entry bcast_duplist[BATADV_DUPLIST_SIZE]; int bcast_duplist_curr; - struct bla_claim_dst claim_dest; + struct batadv_bla_claim_dst claim_dest; #endif spinlock_t forw_bat_list_lock; /* protects forw_bat_list */ spinlock_t forw_bcast_list_lock; /* protects */ @@ -210,7 +224,7 @@ struct bat_priv { spinlock_t vis_list_lock; /* protects vis_info::recv_list */ atomic_t num_local_tt; /* Checksum of the local table, recomputed before sending a new OGM */ - atomic_t tt_crc; + uint16_t tt_crc; unsigned char *tt_buff; int16_t tt_buff_len; spinlock_t tt_buff_lock; /* protects tt_buff */ @@ -218,29 +232,29 @@ struct bat_priv { struct delayed_work orig_work; struct delayed_work vis_work; struct delayed_work bla_work; - struct gw_node __rcu *curr_gw; /* rcu protected pointer */ + struct batadv_gw_node __rcu *curr_gw; /* rcu protected pointer */ atomic_t gw_reselect; - struct hard_iface __rcu *primary_if; /* rcu protected pointer */ - struct vis_info *my_vis_info; - struct bat_algo_ops *bat_algo_ops; + struct batadv_hard_iface __rcu *primary_if; /* rcu protected pointer */ + struct batadv_vis_info *my_vis_info; + struct batadv_algo_ops *bat_algo_ops; }; -struct socket_client { +struct batadv_socket_client { struct list_head queue_list; unsigned int queue_len; unsigned char index; spinlock_t lock; /* protects queue_list, queue_len, index */ wait_queue_head_t queue_wait; - struct bat_priv *bat_priv; + struct batadv_priv *bat_priv; }; -struct socket_packet { +struct batadv_socket_packet { struct list_head list; size_t icmp_len; - struct icmp_packet_rr icmp_packet; + struct batadv_icmp_packet_rr icmp_packet; }; -struct tt_common_entry { +struct batadv_tt_common_entry { uint8_t addr[ETH_ALEN]; struct hlist_node hash_entry; uint16_t flags; @@ -248,31 +262,31 @@ struct tt_common_entry { struct rcu_head rcu; }; -struct tt_local_entry { - struct tt_common_entry common; +struct batadv_tt_local_entry { + struct batadv_tt_common_entry common; unsigned long last_seen; }; -struct tt_global_entry { - struct tt_common_entry common; +struct batadv_tt_global_entry { + struct batadv_tt_common_entry common; struct hlist_head orig_list; spinlock_t list_lock; /* protects the list */ unsigned long roam_at; /* time at which TT_GLOBAL_ROAM was set */ }; -struct tt_orig_list_entry { - struct orig_node *orig_node; +struct batadv_tt_orig_list_entry { + struct batadv_orig_node *orig_node; uint8_t ttvn; struct rcu_head rcu; struct hlist_node list; }; #ifdef CONFIG_BATMAN_ADV_BLA -struct backbone_gw { +struct batadv_backbone_gw { uint8_t orig[ETH_ALEN]; short vid; /* used VLAN ID */ struct hlist_node hash_entry; - struct bat_priv *bat_priv; + struct batadv_priv *bat_priv; unsigned long lasttime; /* last time we heard of this backbone gw */ atomic_t request_sent; atomic_t refcount; @@ -280,10 +294,10 @@ struct backbone_gw { uint16_t crc; /* crc checksum over all claims */ }; -struct claim { +struct batadv_claim { uint8_t addr[ETH_ALEN]; short vid; - struct backbone_gw *backbone_gw; + struct batadv_backbone_gw *backbone_gw; unsigned long lasttime; /* last time we heard of claim (locals only) */ struct rcu_head rcu; atomic_t refcount; @@ -291,29 +305,28 @@ struct claim { }; #endif -struct tt_change_node { +struct batadv_tt_change_node { struct list_head list; - struct tt_change change; + struct batadv_tt_change change; }; -struct tt_req_node { +struct batadv_tt_req_node { uint8_t addr[ETH_ALEN]; unsigned long issued_at; struct list_head list; }; -struct tt_roam_node { +struct batadv_tt_roam_node { uint8_t addr[ETH_ALEN]; atomic_t counter; unsigned long first_time; struct list_head list; }; -/** - * forw_packet - structure for forw_list maintaining packets to be +/* forw_packet - structure for forw_list maintaining packets to be * send/forwarded */ -struct forw_packet { +struct batadv_forw_packet { struct hlist_node list; unsigned long send_time; uint8_t own; @@ -322,76 +335,76 @@ struct forw_packet { uint32_t direct_link_flags; uint8_t num_packets; struct delayed_work delayed_work; - struct hard_iface *if_incoming; + struct batadv_hard_iface *if_incoming; }; /* While scanning for vis-entries of a particular vis-originator * this list collects its interfaces to create a subgraph/cluster * out of them later */ -struct if_list_entry { +struct batadv_if_list_entry { uint8_t addr[ETH_ALEN]; bool primary; struct hlist_node list; }; -struct debug_log { - char log_buff[LOG_BUF_LEN]; +struct batadv_debug_log { + char log_buff[BATADV_LOG_BUF_LEN]; unsigned long log_start; unsigned long log_end; spinlock_t lock; /* protects log_buff, log_start and log_end */ wait_queue_head_t queue_wait; }; -struct frag_packet_list_entry { +struct batadv_frag_packet_list_entry { struct list_head list; uint16_t seqno; struct sk_buff *skb; }; -struct vis_info { +struct batadv_vis_info { unsigned long first_seen; /* list of server-neighbors we received a vis-packet - * from. we should not reply to them. */ + * from. we should not reply to them. + */ struct list_head recv_list; struct list_head send_list; struct kref refcount; struct hlist_node hash_entry; - struct bat_priv *bat_priv; + struct batadv_priv *bat_priv; /* this packet might be part of the vis send queue. */ struct sk_buff *skb_packet; - /* vis_info may follow here*/ + /* vis_info may follow here */ } __packed; -struct vis_info_entry { +struct batadv_vis_info_entry { uint8_t src[ETH_ALEN]; uint8_t dest[ETH_ALEN]; uint8_t quality; /* quality = 0 client */ } __packed; -struct recvlist_node { +struct batadv_recvlist_node { struct list_head list; uint8_t mac[ETH_ALEN]; }; -struct bat_algo_ops { +struct batadv_algo_ops { struct hlist_node list; char *name; /* init routing info when hard-interface is enabled */ - int (*bat_iface_enable)(struct hard_iface *hard_iface); + int (*bat_iface_enable)(struct batadv_hard_iface *hard_iface); /* de-init routing info when hard-interface is disabled */ - void (*bat_iface_disable)(struct hard_iface *hard_iface); + void (*bat_iface_disable)(struct batadv_hard_iface *hard_iface); /* (re-)init mac addresses of the protocol information * belonging to this hard-interface */ - void (*bat_iface_update_mac)(struct hard_iface *hard_iface); + void (*bat_iface_update_mac)(struct batadv_hard_iface *hard_iface); /* called when primary interface is selected / changed */ - void (*bat_primary_iface_set)(struct hard_iface *hard_iface); + void (*bat_primary_iface_set)(struct batadv_hard_iface *hard_iface); /* prepare a new outgoing OGM for the send queue */ - void (*bat_ogm_schedule)(struct hard_iface *hard_iface, - int tt_num_changes); + void (*bat_ogm_schedule)(struct batadv_hard_iface *hard_iface); /* send scheduled OGM */ - void (*bat_ogm_emit)(struct forw_packet *forw_packet); + void (*bat_ogm_emit)(struct batadv_forw_packet *forw_packet); }; #endif /* _NET_BATMAN_ADV_TYPES_H_ */ diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index 74175c21085..00164645b3f 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: * * Andreas Langer * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" @@ -31,19 +29,20 @@ #include "hard-interface.h" -static struct sk_buff *frag_merge_packet(struct list_head *head, - struct frag_packet_list_entry *tfp, - struct sk_buff *skb) +static struct sk_buff * +batadv_frag_merge_packet(struct list_head *head, + struct batadv_frag_packet_list_entry *tfp, + struct sk_buff *skb) { - struct unicast_frag_packet *up = - (struct unicast_frag_packet *)skb->data; + struct batadv_unicast_frag_packet *up; struct sk_buff *tmp_skb; - struct unicast_packet *unicast_packet; + struct batadv_unicast_packet *unicast_packet; int hdr_len = sizeof(*unicast_packet); int uni_diff = sizeof(*up) - hdr_len; + up = (struct batadv_unicast_frag_packet *)skb->data; /* set skb to the first part and tmp_skb to the second part */ - if (up->flags & UNI_FRAG_HEAD) { + if (up->flags & BATADV_UNI_FRAG_HEAD) { tmp_skb = tfp->skb; } else { tmp_skb = skb; @@ -66,8 +65,9 @@ static struct sk_buff *frag_merge_packet(struct list_head *head, kfree_skb(tmp_skb); memmove(skb->data + uni_diff, skb->data, hdr_len); - unicast_packet = (struct unicast_packet *)skb_pull(skb, uni_diff); - unicast_packet->header.packet_type = BAT_UNICAST; + unicast_packet = (struct batadv_unicast_packet *)skb_pull(skb, + uni_diff); + unicast_packet->header.packet_type = BATADV_UNICAST; return skb; @@ -77,11 +77,13 @@ err: return NULL; } -static void frag_create_entry(struct list_head *head, struct sk_buff *skb) +static void batadv_frag_create_entry(struct list_head *head, + struct sk_buff *skb) { - struct frag_packet_list_entry *tfp; - struct unicast_frag_packet *up = - (struct unicast_frag_packet *)skb->data; + struct batadv_frag_packet_list_entry *tfp; + struct batadv_unicast_frag_packet *up; + + up = (struct batadv_unicast_frag_packet *)skb->data; /* free and oldest packets stand at the end */ tfp = list_entry((head)->prev, typeof(*tfp), list); @@ -93,15 +95,15 @@ static void frag_create_entry(struct list_head *head, struct sk_buff *skb) return; } -static int frag_create_buffer(struct list_head *head) +static int batadv_frag_create_buffer(struct list_head *head) { int i; - struct frag_packet_list_entry *tfp; + struct batadv_frag_packet_list_entry *tfp; - for (i = 0; i < FRAG_BUFFER_SIZE; i++) { + for (i = 0; i < BATADV_FRAG_BUFFER_SIZE; i++) { tfp = kmalloc(sizeof(*tfp), GFP_ATOMIC); if (!tfp) { - frag_list_free(head); + batadv_frag_list_free(head); return -ENOMEM; } tfp->skb = NULL; @@ -113,14 +115,15 @@ static int frag_create_buffer(struct list_head *head) return 0; } -static struct frag_packet_list_entry *frag_search_packet(struct list_head *head, - const struct unicast_frag_packet *up) +static struct batadv_frag_packet_list_entry * +batadv_frag_search_packet(struct list_head *head, + const struct batadv_unicast_frag_packet *up) { - struct frag_packet_list_entry *tfp; - struct unicast_frag_packet *tmp_up = NULL; + struct batadv_frag_packet_list_entry *tfp; + struct batadv_unicast_frag_packet *tmp_up = NULL; uint16_t search_seqno; - if (up->flags & UNI_FRAG_HEAD) + if (up->flags & BATADV_UNI_FRAG_HEAD) search_seqno = ntohs(up->seqno)+1; else search_seqno = ntohs(up->seqno)-1; @@ -133,12 +136,12 @@ static struct frag_packet_list_entry *frag_search_packet(struct list_head *head, if (tfp->seqno == ntohs(up->seqno)) goto mov_tail; - tmp_up = (struct unicast_frag_packet *)tfp->skb->data; + tmp_up = (struct batadv_unicast_frag_packet *)tfp->skb->data; if (tfp->seqno == search_seqno) { - if ((tmp_up->flags & UNI_FRAG_HEAD) != - (up->flags & UNI_FRAG_HEAD)) + if ((tmp_up->flags & BATADV_UNI_FRAG_HEAD) != + (up->flags & BATADV_UNI_FRAG_HEAD)) return tfp; else goto mov_tail; @@ -151,9 +154,9 @@ mov_tail: return NULL; } -void frag_list_free(struct list_head *head) +void batadv_frag_list_free(struct list_head *head) { - struct frag_packet_list_entry *pf, *tmp_pf; + struct batadv_frag_packet_list_entry *pf, *tmp_pf; if (!list_empty(head)) { @@ -172,64 +175,66 @@ void frag_list_free(struct list_head *head) * or the skb could be reassembled (skb_new will point to the new packet and * skb was freed) */ -int frag_reassemble_skb(struct sk_buff *skb, struct bat_priv *bat_priv, - struct sk_buff **new_skb) +int batadv_frag_reassemble_skb(struct sk_buff *skb, + struct batadv_priv *bat_priv, + struct sk_buff **new_skb) { - struct orig_node *orig_node; - struct frag_packet_list_entry *tmp_frag_entry; + struct batadv_orig_node *orig_node; + struct batadv_frag_packet_list_entry *tmp_frag_entry; int ret = NET_RX_DROP; - struct unicast_frag_packet *unicast_packet = - (struct unicast_frag_packet *)skb->data; + struct batadv_unicast_frag_packet *unicast_packet; + unicast_packet = (struct batadv_unicast_frag_packet *)skb->data; *new_skb = NULL; - orig_node = orig_hash_find(bat_priv, unicast_packet->orig); + orig_node = batadv_orig_hash_find(bat_priv, unicast_packet->orig); if (!orig_node) goto out; orig_node->last_frag_packet = jiffies; if (list_empty(&orig_node->frag_list) && - frag_create_buffer(&orig_node->frag_list)) { + batadv_frag_create_buffer(&orig_node->frag_list)) { pr_debug("couldn't create frag buffer\n"); goto out; } - tmp_frag_entry = frag_search_packet(&orig_node->frag_list, - unicast_packet); + tmp_frag_entry = batadv_frag_search_packet(&orig_node->frag_list, + unicast_packet); if (!tmp_frag_entry) { - frag_create_entry(&orig_node->frag_list, skb); + batadv_frag_create_entry(&orig_node->frag_list, skb); ret = NET_RX_SUCCESS; goto out; } - *new_skb = frag_merge_packet(&orig_node->frag_list, tmp_frag_entry, - skb); + *new_skb = batadv_frag_merge_packet(&orig_node->frag_list, + tmp_frag_entry, skb); /* if not, merge failed */ if (*new_skb) ret = NET_RX_SUCCESS; out: if (orig_node) - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); return ret; } -int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, - struct hard_iface *hard_iface, const uint8_t dstaddr[]) +int batadv_frag_send_skb(struct sk_buff *skb, struct batadv_priv *bat_priv, + struct batadv_hard_iface *hard_iface, + const uint8_t dstaddr[]) { - struct unicast_packet tmp_uc, *unicast_packet; - struct hard_iface *primary_if; + struct batadv_unicast_packet tmp_uc, *unicast_packet; + struct batadv_hard_iface *primary_if; struct sk_buff *frag_skb; - struct unicast_frag_packet *frag1, *frag2; + struct batadv_unicast_frag_packet *frag1, *frag2; int uc_hdr_len = sizeof(*unicast_packet); int ucf_hdr_len = sizeof(*frag1); int data_len = skb->len - uc_hdr_len; int large_tail = 0, ret = NET_RX_DROP; uint16_t seqno; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto dropped; @@ -238,38 +243,38 @@ int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, goto dropped; skb_reserve(frag_skb, ucf_hdr_len); - unicast_packet = (struct unicast_packet *)skb->data; + unicast_packet = (struct batadv_unicast_packet *)skb->data; memcpy(&tmp_uc, unicast_packet, uc_hdr_len); skb_split(skb, frag_skb, data_len / 2 + uc_hdr_len); - if (my_skb_head_push(skb, ucf_hdr_len - uc_hdr_len) < 0 || - my_skb_head_push(frag_skb, ucf_hdr_len) < 0) + if (batadv_skb_head_push(skb, ucf_hdr_len - uc_hdr_len) < 0 || + batadv_skb_head_push(frag_skb, ucf_hdr_len) < 0) goto drop_frag; - frag1 = (struct unicast_frag_packet *)skb->data; - frag2 = (struct unicast_frag_packet *)frag_skb->data; + frag1 = (struct batadv_unicast_frag_packet *)skb->data; + frag2 = (struct batadv_unicast_frag_packet *)frag_skb->data; memcpy(frag1, &tmp_uc, sizeof(tmp_uc)); frag1->header.ttl--; - frag1->header.version = COMPAT_VERSION; - frag1->header.packet_type = BAT_UNICAST_FRAG; + frag1->header.version = BATADV_COMPAT_VERSION; + frag1->header.packet_type = BATADV_UNICAST_FRAG; memcpy(frag1->orig, primary_if->net_dev->dev_addr, ETH_ALEN); memcpy(frag2, frag1, sizeof(*frag2)); if (data_len & 1) - large_tail = UNI_FRAG_LARGETAIL; + large_tail = BATADV_UNI_FRAG_LARGETAIL; - frag1->flags = UNI_FRAG_HEAD | large_tail; + frag1->flags = BATADV_UNI_FRAG_HEAD | large_tail; frag2->flags = large_tail; seqno = atomic_add_return(2, &hard_iface->frag_seqno); frag1->seqno = htons(seqno - 1); frag2->seqno = htons(seqno); - send_skb_packet(skb, hard_iface, dstaddr); - send_skb_packet(frag_skb, hard_iface, dstaddr); + batadv_send_skb_packet(skb, hard_iface, dstaddr); + batadv_send_skb_packet(frag_skb, hard_iface, dstaddr); ret = NET_RX_SUCCESS; goto out; @@ -279,52 +284,53 @@ dropped: kfree_skb(skb); out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); return ret; } -int unicast_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv) +int batadv_unicast_send_skb(struct sk_buff *skb, struct batadv_priv *bat_priv) { struct ethhdr *ethhdr = (struct ethhdr *)skb->data; - struct unicast_packet *unicast_packet; - struct orig_node *orig_node; - struct neigh_node *neigh_node; + struct batadv_unicast_packet *unicast_packet; + struct batadv_orig_node *orig_node; + struct batadv_neigh_node *neigh_node; int data_len = skb->len; int ret = 1; + unsigned int dev_mtu; /* get routing information */ if (is_multicast_ether_addr(ethhdr->h_dest)) { - orig_node = gw_get_selected_orig(bat_priv); + orig_node = batadv_gw_get_selected_orig(bat_priv); if (orig_node) goto find_router; } /* check for tt host - increases orig_node refcount. - * returns NULL in case of AP isolation */ - orig_node = transtable_search(bat_priv, ethhdr->h_source, - ethhdr->h_dest); + * returns NULL in case of AP isolation + */ + orig_node = batadv_transtable_search(bat_priv, ethhdr->h_source, + ethhdr->h_dest); find_router: - /** - * find_router(): + /* find_router(): * - if orig_node is NULL it returns NULL * - increases neigh_nodes refcount if found. */ - neigh_node = find_router(bat_priv, orig_node, NULL); + neigh_node = batadv_find_router(bat_priv, orig_node, NULL); if (!neigh_node) goto out; - if (my_skb_head_push(skb, sizeof(*unicast_packet)) < 0) + if (batadv_skb_head_push(skb, sizeof(*unicast_packet)) < 0) goto out; - unicast_packet = (struct unicast_packet *)skb->data; + unicast_packet = (struct batadv_unicast_packet *)skb->data; - unicast_packet->header.version = COMPAT_VERSION; + unicast_packet->header.version = BATADV_COMPAT_VERSION; /* batman packet type: unicast */ - unicast_packet->header.packet_type = BAT_UNICAST; + unicast_packet->header.packet_type = BATADV_UNICAST; /* set unicast ttl */ - unicast_packet->header.ttl = TTL; + unicast_packet->header.ttl = BATADV_TTL; /* copy the destination for faster routing */ memcpy(unicast_packet->dest, orig_node->orig, ETH_ALEN); /* set the destination tt version number */ @@ -336,28 +342,29 @@ find_router: * try to reroute it because the ttvn contained in the header is less * than the current one */ - if (tt_global_client_is_roaming(bat_priv, ethhdr->h_dest)) + if (batadv_tt_global_client_is_roaming(bat_priv, ethhdr->h_dest)) unicast_packet->ttvn = unicast_packet->ttvn - 1; + dev_mtu = neigh_node->if_incoming->net_dev->mtu; if (atomic_read(&bat_priv->fragmentation) && - data_len + sizeof(*unicast_packet) > - neigh_node->if_incoming->net_dev->mtu) { + data_len + sizeof(*unicast_packet) > dev_mtu) { /* send frag skb decreases ttl */ unicast_packet->header.ttl++; - ret = frag_send_skb(skb, bat_priv, - neigh_node->if_incoming, neigh_node->addr); + ret = batadv_frag_send_skb(skb, bat_priv, + neigh_node->if_incoming, + neigh_node->addr); goto out; } - send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); ret = 0; goto out; out: if (neigh_node) - neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref(neigh_node); if (orig_node) - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); if (ret == 1) kfree_skb(skb); return ret; diff --git a/net/batman-adv/unicast.h b/net/batman-adv/unicast.h index a9faf6b1db1..1c46e2eb1ef 100644 --- a/net/batman-adv/unicast.h +++ b/net/batman-adv/unicast.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: * * Andreas Langer * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_UNICAST_H_ @@ -24,33 +22,35 @@ #include "packet.h" -#define FRAG_TIMEOUT 10000 /* purge frag list entries after time in ms */ -#define FRAG_BUFFER_SIZE 6 /* number of list elements in buffer */ +#define BATADV_FRAG_TIMEOUT 10000 /* purge frag list entries after time in ms */ +#define BATADV_FRAG_BUFFER_SIZE 6 /* number of list elements in buffer */ -int frag_reassemble_skb(struct sk_buff *skb, struct bat_priv *bat_priv, - struct sk_buff **new_skb); -void frag_list_free(struct list_head *head); -int unicast_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv); -int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, - struct hard_iface *hard_iface, const uint8_t dstaddr[]); +int batadv_frag_reassemble_skb(struct sk_buff *skb, + struct batadv_priv *bat_priv, + struct sk_buff **new_skb); +void batadv_frag_list_free(struct list_head *head); +int batadv_unicast_send_skb(struct sk_buff *skb, struct batadv_priv *bat_priv); +int batadv_frag_send_skb(struct sk_buff *skb, struct batadv_priv *bat_priv, + struct batadv_hard_iface *hard_iface, + const uint8_t dstaddr[]); -static inline int frag_can_reassemble(const struct sk_buff *skb, int mtu) +static inline int batadv_frag_can_reassemble(const struct sk_buff *skb, int mtu) { - const struct unicast_frag_packet *unicast_packet; + const struct batadv_unicast_frag_packet *unicast_packet; int uneven_correction = 0; unsigned int merged_size; - unicast_packet = (struct unicast_frag_packet *)skb->data; + unicast_packet = (struct batadv_unicast_frag_packet *)skb->data; - if (unicast_packet->flags & UNI_FRAG_LARGETAIL) { - if (unicast_packet->flags & UNI_FRAG_HEAD) + if (unicast_packet->flags & BATADV_UNI_FRAG_LARGETAIL) { + if (unicast_packet->flags & BATADV_UNI_FRAG_HEAD) uneven_correction = 1; else uneven_correction = -1; } merged_size = (skb->len - sizeof(*unicast_packet)) * 2; - merged_size += sizeof(struct unicast_packet) + uneven_correction; + merged_size += sizeof(struct batadv_unicast_packet) + uneven_correction; return merged_size <= mtu; } diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index cec216fb77c..2a2ea068146 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2008-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2008-2012 B.A.T.M.A.N. contributors: * * Simon Wunderlich * @@ -16,7 +15,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #include "main.h" @@ -28,16 +26,19 @@ #include "hash.h" #include "originator.h" -#define MAX_VIS_PACKET_SIZE 1000 +#define BATADV_MAX_VIS_PACKET_SIZE 1000 -static void start_vis_timer(struct bat_priv *bat_priv); +static void batadv_start_vis_timer(struct batadv_priv *bat_priv); /* free the info */ -static void free_info(struct kref *ref) +static void batadv_free_info(struct kref *ref) { - struct vis_info *info = container_of(ref, struct vis_info, refcount); - struct bat_priv *bat_priv = info->bat_priv; - struct recvlist_node *entry, *tmp; + struct batadv_vis_info *info; + struct batadv_priv *bat_priv; + struct batadv_recvlist_node *entry, *tmp; + + info = container_of(ref, struct batadv_vis_info, refcount); + bat_priv = info->bat_priv; list_del_init(&info->send_list); spin_lock_bh(&bat_priv->vis_list_lock); @@ -52,29 +53,30 @@ static void free_info(struct kref *ref) } /* Compare two vis packets, used by the hashing algorithm */ -static int vis_info_cmp(const struct hlist_node *node, const void *data2) +static int batadv_vis_info_cmp(const struct hlist_node *node, const void *data2) { - const struct vis_info *d1, *d2; - const struct vis_packet *p1, *p2; + const struct batadv_vis_info *d1, *d2; + const struct batadv_vis_packet *p1, *p2; - d1 = container_of(node, struct vis_info, hash_entry); + d1 = container_of(node, struct batadv_vis_info, hash_entry); d2 = data2; - p1 = (struct vis_packet *)d1->skb_packet->data; - p2 = (struct vis_packet *)d2->skb_packet->data; - return compare_eth(p1->vis_orig, p2->vis_orig); + p1 = (struct batadv_vis_packet *)d1->skb_packet->data; + p2 = (struct batadv_vis_packet *)d2->skb_packet->data; + return batadv_compare_eth(p1->vis_orig, p2->vis_orig); } -/* hash function to choose an entry in a hash table of given size */ -/* hash algorithm from http://en.wikipedia.org/wiki/Hash_table */ -static uint32_t vis_info_choose(const void *data, uint32_t size) +/* hash function to choose an entry in a hash table of given size + * hash algorithm from http://en.wikipedia.org/wiki/Hash_table + */ +static uint32_t batadv_vis_info_choose(const void *data, uint32_t size) { - const struct vis_info *vis_info = data; - const struct vis_packet *packet; + const struct batadv_vis_info *vis_info = data; + const struct batadv_vis_packet *packet; const unsigned char *key; uint32_t hash = 0; size_t i; - packet = (struct vis_packet *)vis_info->skb_packet->data; + packet = (struct batadv_vis_packet *)vis_info->skb_packet->data; key = packet->vis_orig; for (i = 0; i < ETH_ALEN; i++) { hash += key[i]; @@ -89,24 +91,24 @@ static uint32_t vis_info_choose(const void *data, uint32_t size) return hash % size; } -static struct vis_info *vis_hash_find(struct bat_priv *bat_priv, - const void *data) +static struct batadv_vis_info * +batadv_vis_hash_find(struct batadv_priv *bat_priv, const void *data) { - struct hashtable_t *hash = bat_priv->vis_hash; + struct batadv_hashtable *hash = bat_priv->vis_hash; struct hlist_head *head; struct hlist_node *node; - struct vis_info *vis_info, *vis_info_tmp = NULL; + struct batadv_vis_info *vis_info, *vis_info_tmp = NULL; uint32_t index; if (!hash) return NULL; - index = vis_info_choose(data, hash->size); + index = batadv_vis_info_choose(data, hash->size); head = &hash->table[index]; rcu_read_lock(); hlist_for_each_entry_rcu(vis_info, node, head, hash_entry) { - if (!vis_info_cmp(node, data)) + if (!batadv_vis_info_cmp(node, data)) continue; vis_info_tmp = vis_info; @@ -118,16 +120,17 @@ static struct vis_info *vis_hash_find(struct bat_priv *bat_priv, } /* insert interface to the list of interfaces of one originator, if it - * does not already exist in the list */ -static void vis_data_insert_interface(const uint8_t *interface, - struct hlist_head *if_list, - bool primary) + * does not already exist in the list + */ +static void batadv_vis_data_insert_interface(const uint8_t *interface, + struct hlist_head *if_list, + bool primary) { - struct if_list_entry *entry; + struct batadv_if_list_entry *entry; struct hlist_node *pos; hlist_for_each_entry(entry, pos, if_list, list) { - if (compare_eth(entry->addr, interface)) + if (batadv_compare_eth(entry->addr, interface)) return; } @@ -140,195 +143,145 @@ static void vis_data_insert_interface(const uint8_t *interface, hlist_add_head(&entry->list, if_list); } -static ssize_t vis_data_read_prim_sec(char *buff, - const struct hlist_head *if_list) +static void batadv_vis_data_read_prim_sec(struct seq_file *seq, + const struct hlist_head *if_list) { - struct if_list_entry *entry; + struct batadv_if_list_entry *entry; struct hlist_node *pos; - size_t len = 0; hlist_for_each_entry(entry, pos, if_list, list) { if (entry->primary) - len += sprintf(buff + len, "PRIMARY, "); + seq_printf(seq, "PRIMARY, "); else - len += sprintf(buff + len, "SEC %pM, ", entry->addr); + seq_printf(seq, "SEC %pM, ", entry->addr); } +} - return len; +/* read an entry */ +static ssize_t +batadv_vis_data_read_entry(struct seq_file *seq, + const struct batadv_vis_info_entry *entry, + const uint8_t *src, bool primary) +{ + if (primary && entry->quality == 0) + return seq_printf(seq, "TT %pM, ", entry->dest); + else if (batadv_compare_eth(entry->src, src)) + return seq_printf(seq, "TQ %pM %d, ", entry->dest, + entry->quality); + + return 0; } -static size_t vis_data_count_prim_sec(struct hlist_head *if_list) +static void +batadv_vis_data_insert_interfaces(struct hlist_head *list, + struct batadv_vis_packet *packet, + struct batadv_vis_info_entry *entries) { - struct if_list_entry *entry; - struct hlist_node *pos; - size_t count = 0; + int i; - hlist_for_each_entry(entry, pos, if_list, list) { - if (entry->primary) - count += 9; - else - count += 23; - } + for (i = 0; i < packet->entries; i++) { + if (entries[i].quality == 0) + continue; - return count; + if (batadv_compare_eth(entries[i].src, packet->vis_orig)) + continue; + + batadv_vis_data_insert_interface(entries[i].src, list, false); + } } -/* read an entry */ -static ssize_t vis_data_read_entry(char *buff, - const struct vis_info_entry *entry, - const uint8_t *src, bool primary) +static void batadv_vis_data_read_entries(struct seq_file *seq, + struct hlist_head *list, + struct batadv_vis_packet *packet, + struct batadv_vis_info_entry *entries) { - /* maximal length: max(4+17+2, 3+17+1+3+2) == 26 */ - if (primary && entry->quality == 0) - return sprintf(buff, "TT %pM, ", entry->dest); - else if (compare_eth(entry->src, src)) - return sprintf(buff, "TQ %pM %d, ", entry->dest, - entry->quality); + int i; + struct batadv_if_list_entry *entry; + struct hlist_node *pos; - return 0; + hlist_for_each_entry(entry, pos, list, list) { + seq_printf(seq, "%pM,", entry->addr); + + for (i = 0; i < packet->entries; i++) + batadv_vis_data_read_entry(seq, &entries[i], + entry->addr, entry->primary); + + /* add primary/secondary records */ + if (batadv_compare_eth(entry->addr, packet->vis_orig)) + batadv_vis_data_read_prim_sec(seq, list); + + seq_printf(seq, "\n"); + } } -int vis_seq_print_text(struct seq_file *seq, void *offset) +static void batadv_vis_seq_print_text_bucket(struct seq_file *seq, + const struct hlist_head *head) { - struct hard_iface *primary_if; struct hlist_node *node; + struct batadv_vis_info *info; + struct batadv_vis_packet *packet; + uint8_t *entries_pos; + struct batadv_vis_info_entry *entries; + struct batadv_if_list_entry *entry; + struct hlist_node *pos, *n; + + HLIST_HEAD(vis_if_list); + + hlist_for_each_entry_rcu(info, node, head, hash_entry) { + packet = (struct batadv_vis_packet *)info->skb_packet->data; + entries_pos = (uint8_t *)packet + sizeof(*packet); + entries = (struct batadv_vis_info_entry *)entries_pos; + + batadv_vis_data_insert_interface(packet->vis_orig, &vis_if_list, + true); + batadv_vis_data_insert_interfaces(&vis_if_list, packet, + entries); + batadv_vis_data_read_entries(seq, &vis_if_list, packet, + entries); + + hlist_for_each_entry_safe(entry, pos, n, &vis_if_list, list) { + hlist_del(&entry->list); + kfree(entry); + } + } +} + +int batadv_vis_seq_print_text(struct seq_file *seq, void *offset) +{ + struct batadv_hard_iface *primary_if; struct hlist_head *head; - struct vis_info *info; - struct vis_packet *packet; - struct vis_info_entry *entries; struct net_device *net_dev = (struct net_device *)seq->private; - struct bat_priv *bat_priv = netdev_priv(net_dev); - struct hashtable_t *hash = bat_priv->vis_hash; - HLIST_HEAD(vis_if_list); - struct if_list_entry *entry; - struct hlist_node *pos, *n; + struct batadv_priv *bat_priv = netdev_priv(net_dev); + struct batadv_hashtable *hash = bat_priv->vis_hash; uint32_t i; - int j, ret = 0; + int ret = 0; int vis_server = atomic_read(&bat_priv->vis_mode); - size_t buff_pos, buf_size; - char *buff; - int compare; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; - if (vis_server == VIS_TYPE_CLIENT_UPDATE) + if (vis_server == BATADV_VIS_TYPE_CLIENT_UPDATE) goto out; - buf_size = 1; - /* Estimate length */ spin_lock_bh(&bat_priv->vis_hash_lock); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; - - rcu_read_lock(); - hlist_for_each_entry_rcu(info, node, head, hash_entry) { - packet = (struct vis_packet *)info->skb_packet->data; - entries = (struct vis_info_entry *) - ((char *)packet + sizeof(*packet)); - - for (j = 0; j < packet->entries; j++) { - if (entries[j].quality == 0) - continue; - compare = - compare_eth(entries[j].src, packet->vis_orig); - vis_data_insert_interface(entries[j].src, - &vis_if_list, - compare); - } - - hlist_for_each_entry(entry, pos, &vis_if_list, list) { - buf_size += 18 + 26 * packet->entries; - - /* add primary/secondary records */ - if (compare_eth(entry->addr, packet->vis_orig)) - buf_size += - vis_data_count_prim_sec(&vis_if_list); - - buf_size += 1; - } - - hlist_for_each_entry_safe(entry, pos, n, &vis_if_list, - list) { - hlist_del(&entry->list); - kfree(entry); - } - } - rcu_read_unlock(); - } - - buff = kmalloc(buf_size, GFP_ATOMIC); - if (!buff) { - spin_unlock_bh(&bat_priv->vis_hash_lock); - ret = -ENOMEM; - goto out; - } - buff[0] = '\0'; - buff_pos = 0; - - for (i = 0; i < hash->size; i++) { - head = &hash->table[i]; - - rcu_read_lock(); - hlist_for_each_entry_rcu(info, node, head, hash_entry) { - packet = (struct vis_packet *)info->skb_packet->data; - entries = (struct vis_info_entry *) - ((char *)packet + sizeof(*packet)); - - for (j = 0; j < packet->entries; j++) { - if (entries[j].quality == 0) - continue; - compare = - compare_eth(entries[j].src, packet->vis_orig); - vis_data_insert_interface(entries[j].src, - &vis_if_list, - compare); - } - - hlist_for_each_entry(entry, pos, &vis_if_list, list) { - buff_pos += sprintf(buff + buff_pos, "%pM,", - entry->addr); - - for (j = 0; j < packet->entries; j++) - buff_pos += vis_data_read_entry( - buff + buff_pos, - &entries[j], - entry->addr, - entry->primary); - - /* add primary/secondary records */ - if (compare_eth(entry->addr, packet->vis_orig)) - buff_pos += - vis_data_read_prim_sec(buff + buff_pos, - &vis_if_list); - - buff_pos += sprintf(buff + buff_pos, "\n"); - } - - hlist_for_each_entry_safe(entry, pos, n, &vis_if_list, - list) { - hlist_del(&entry->list); - kfree(entry); - } - } - rcu_read_unlock(); + batadv_vis_seq_print_text_bucket(seq, head); } - spin_unlock_bh(&bat_priv->vis_hash_lock); - seq_printf(seq, "%s", buff); - kfree(buff); - out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); return ret; } /* add the info packet to the send list, if it was not - * already linked in. */ -static void send_list_add(struct bat_priv *bat_priv, struct vis_info *info) + * already linked in. + */ +static void batadv_send_list_add(struct batadv_priv *bat_priv, + struct batadv_vis_info *info) { if (list_empty(&info->send_list)) { kref_get(&info->refcount); @@ -337,20 +290,21 @@ static void send_list_add(struct bat_priv *bat_priv, struct vis_info *info) } /* delete the info packet from the send list, if it was - * linked in. */ -static void send_list_del(struct vis_info *info) + * linked in. + */ +static void batadv_send_list_del(struct batadv_vis_info *info) { if (!list_empty(&info->send_list)) { list_del_init(&info->send_list); - kref_put(&info->refcount, free_info); + kref_put(&info->refcount, batadv_free_info); } } /* tries to add one entry to the receive list. */ -static void recv_list_add(struct bat_priv *bat_priv, - struct list_head *recv_list, const char *mac) +static void batadv_recv_list_add(struct batadv_priv *bat_priv, + struct list_head *recv_list, const char *mac) { - struct recvlist_node *entry; + struct batadv_recvlist_node *entry; entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) @@ -363,14 +317,15 @@ static void recv_list_add(struct bat_priv *bat_priv, } /* returns 1 if this mac is in the recv_list */ -static int recv_list_is_in(struct bat_priv *bat_priv, - const struct list_head *recv_list, const char *mac) +static int batadv_recv_list_is_in(struct batadv_priv *bat_priv, + const struct list_head *recv_list, + const char *mac) { - const struct recvlist_node *entry; + const struct batadv_recvlist_node *entry; spin_lock_bh(&bat_priv->vis_list_lock); list_for_each_entry(entry, recv_list, list) { - if (compare_eth(entry->mac, mac)) { + if (batadv_compare_eth(entry->mac, mac)) { spin_unlock_bh(&bat_priv->vis_list_lock); return 1; } @@ -381,17 +336,21 @@ static int recv_list_is_in(struct bat_priv *bat_priv, /* try to add the packet to the vis_hash. return NULL if invalid (e.g. too old, * broken.. ). vis hash must be locked outside. is_new is set when the packet - * is newer than old entries in the hash. */ -static struct vis_info *add_packet(struct bat_priv *bat_priv, - struct vis_packet *vis_packet, - int vis_info_len, int *is_new, - int make_broadcast) + * is newer than old entries in the hash. + */ +static struct batadv_vis_info * +batadv_add_packet(struct batadv_priv *bat_priv, + struct batadv_vis_packet *vis_packet, int vis_info_len, + int *is_new, int make_broadcast) { - struct vis_info *info, *old_info; - struct vis_packet *search_packet, *old_packet; - struct vis_info search_elem; - struct vis_packet *packet; + struct batadv_vis_info *info, *old_info; + struct batadv_vis_packet *search_packet, *old_packet; + struct batadv_vis_info search_elem; + struct batadv_vis_packet *packet; + struct sk_buff *tmp_skb; int hash_added; + size_t len; + size_t max_entries; *is_new = 0; /* sanity check */ @@ -402,20 +361,23 @@ static struct vis_info *add_packet(struct bat_priv *bat_priv, search_elem.skb_packet = dev_alloc_skb(sizeof(*search_packet)); if (!search_elem.skb_packet) return NULL; - search_packet = (struct vis_packet *)skb_put(search_elem.skb_packet, - sizeof(*search_packet)); + len = sizeof(*search_packet); + tmp_skb = search_elem.skb_packet; + search_packet = (struct batadv_vis_packet *)skb_put(tmp_skb, len); memcpy(search_packet->vis_orig, vis_packet->vis_orig, ETH_ALEN); - old_info = vis_hash_find(bat_priv, &search_elem); + old_info = batadv_vis_hash_find(bat_priv, &search_elem); kfree_skb(search_elem.skb_packet); if (old_info) { - old_packet = (struct vis_packet *)old_info->skb_packet->data; - if (!seq_after(ntohl(vis_packet->seqno), - ntohl(old_packet->seqno))) { + tmp_skb = old_info->skb_packet; + old_packet = (struct batadv_vis_packet *)tmp_skb->data; + if (!batadv_seq_after(ntohl(vis_packet->seqno), + ntohl(old_packet->seqno))) { if (old_packet->seqno == vis_packet->seqno) { - recv_list_add(bat_priv, &old_info->recv_list, - vis_packet->sender_orig); + batadv_recv_list_add(bat_priv, + &old_info->recv_list, + vis_packet->sender_orig); return old_info; } else { /* newer packet is already in hash. */ @@ -423,52 +385,53 @@ static struct vis_info *add_packet(struct bat_priv *bat_priv, } } /* remove old entry */ - hash_remove(bat_priv->vis_hash, vis_info_cmp, vis_info_choose, - old_info); - send_list_del(old_info); - kref_put(&old_info->refcount, free_info); + batadv_hash_remove(bat_priv->vis_hash, batadv_vis_info_cmp, + batadv_vis_info_choose, old_info); + batadv_send_list_del(old_info); + kref_put(&old_info->refcount, batadv_free_info); } info = kmalloc(sizeof(*info), GFP_ATOMIC); if (!info) return NULL; - info->skb_packet = dev_alloc_skb(sizeof(*packet) + vis_info_len + - ETH_HLEN); + len = sizeof(*packet) + vis_info_len; + info->skb_packet = dev_alloc_skb(len + ETH_HLEN); if (!info->skb_packet) { kfree(info); return NULL; } skb_reserve(info->skb_packet, ETH_HLEN); - packet = (struct vis_packet *)skb_put(info->skb_packet, sizeof(*packet) - + vis_info_len); + packet = (struct batadv_vis_packet *)skb_put(info->skb_packet, len); kref_init(&info->refcount); INIT_LIST_HEAD(&info->send_list); INIT_LIST_HEAD(&info->recv_list); info->first_seen = jiffies; info->bat_priv = bat_priv; - memcpy(packet, vis_packet, sizeof(*packet) + vis_info_len); + memcpy(packet, vis_packet, len); /* initialize and add new packet. */ *is_new = 1; /* Make it a broadcast packet, if required */ if (make_broadcast) - memcpy(packet->target_orig, broadcast_addr, ETH_ALEN); + memcpy(packet->target_orig, batadv_broadcast_addr, ETH_ALEN); /* repair if entries is longer than packet. */ - if (packet->entries * sizeof(struct vis_info_entry) > vis_info_len) - packet->entries = vis_info_len / sizeof(struct vis_info_entry); + max_entries = vis_info_len / sizeof(struct batadv_vis_info_entry); + if (packet->entries > max_entries) + packet->entries = max_entries; - recv_list_add(bat_priv, &info->recv_list, packet->sender_orig); + batadv_recv_list_add(bat_priv, &info->recv_list, packet->sender_orig); /* try to add it */ - hash_added = hash_add(bat_priv->vis_hash, vis_info_cmp, vis_info_choose, - info, &info->hash_entry); + hash_added = batadv_hash_add(bat_priv->vis_hash, batadv_vis_info_cmp, + batadv_vis_info_choose, info, + &info->hash_entry); if (hash_added != 0) { /* did not work (for some reason) */ - kref_put(&info->refcount, free_info); + kref_put(&info->refcount, batadv_free_info); info = NULL; } @@ -476,37 +439,38 @@ static struct vis_info *add_packet(struct bat_priv *bat_priv, } /* handle the server sync packet, forward if needed. */ -void receive_server_sync_packet(struct bat_priv *bat_priv, - struct vis_packet *vis_packet, - int vis_info_len) +void batadv_receive_server_sync_packet(struct batadv_priv *bat_priv, + struct batadv_vis_packet *vis_packet, + int vis_info_len) { - struct vis_info *info; + struct batadv_vis_info *info; int is_new, make_broadcast; int vis_server = atomic_read(&bat_priv->vis_mode); - make_broadcast = (vis_server == VIS_TYPE_SERVER_SYNC); + make_broadcast = (vis_server == BATADV_VIS_TYPE_SERVER_SYNC); spin_lock_bh(&bat_priv->vis_hash_lock); - info = add_packet(bat_priv, vis_packet, vis_info_len, - &is_new, make_broadcast); + info = batadv_add_packet(bat_priv, vis_packet, vis_info_len, + &is_new, make_broadcast); if (!info) goto end; /* only if we are server ourselves and packet is newer than the one in - * hash.*/ - if (vis_server == VIS_TYPE_SERVER_SYNC && is_new) - send_list_add(bat_priv, info); + * hash. + */ + if (vis_server == BATADV_VIS_TYPE_SERVER_SYNC && is_new) + batadv_send_list_add(bat_priv, info); end: spin_unlock_bh(&bat_priv->vis_hash_lock); } /* handle an incoming client update packet and schedule forward if needed. */ -void receive_client_update_packet(struct bat_priv *bat_priv, - struct vis_packet *vis_packet, - int vis_info_len) +void batadv_receive_client_update_packet(struct batadv_priv *bat_priv, + struct batadv_vis_packet *vis_packet, + int vis_info_len) { - struct vis_info *info; - struct vis_packet *packet; + struct batadv_vis_info *info; + struct batadv_vis_packet *packet; int is_new; int vis_server = atomic_read(&bat_priv->vis_mode); int are_target = 0; @@ -516,28 +480,28 @@ void receive_client_update_packet(struct bat_priv *bat_priv, return; /* Are we the target for this VIS packet? */ - if (vis_server == VIS_TYPE_SERVER_SYNC && - is_my_mac(vis_packet->target_orig)) + if (vis_server == BATADV_VIS_TYPE_SERVER_SYNC && + batadv_is_my_mac(vis_packet->target_orig)) are_target = 1; spin_lock_bh(&bat_priv->vis_hash_lock); - info = add_packet(bat_priv, vis_packet, vis_info_len, - &is_new, are_target); + info = batadv_add_packet(bat_priv, vis_packet, vis_info_len, + &is_new, are_target); if (!info) goto end; /* note that outdated packets will be dropped at this point. */ - packet = (struct vis_packet *)info->skb_packet->data; + packet = (struct batadv_vis_packet *)info->skb_packet->data; /* send only if we're the target server or ... */ if (are_target && is_new) { - packet->vis_type = VIS_TYPE_SERVER_SYNC; /* upgrade! */ - send_list_add(bat_priv, info); + packet->vis_type = BATADV_VIS_TYPE_SERVER_SYNC; /* upgrade! */ + batadv_send_list_add(bat_priv, info); /* ... we're not the recipient (and thus need to forward). */ - } else if (!is_my_mac(packet->target_orig)) { - send_list_add(bat_priv, info); + } else if (!batadv_is_my_mac(packet->target_orig)) { + batadv_send_list_add(bat_priv, info); } end: @@ -547,37 +511,38 @@ end: /* Walk the originators and find the VIS server with the best tq. Set the packet * address to its address and return the best_tq. * - * Must be called with the originator hash locked */ -static int find_best_vis_server(struct bat_priv *bat_priv, - struct vis_info *info) + * Must be called with the originator hash locked + */ +static int batadv_find_best_vis_server(struct batadv_priv *bat_priv, + struct batadv_vis_info *info) { - struct hashtable_t *hash = bat_priv->orig_hash; - struct neigh_node *router; + struct batadv_hashtable *hash = bat_priv->orig_hash; + struct batadv_neigh_node *router; struct hlist_node *node; struct hlist_head *head; - struct orig_node *orig_node; - struct vis_packet *packet; + struct batadv_orig_node *orig_node; + struct batadv_vis_packet *packet; int best_tq = -1; uint32_t i; - packet = (struct vis_packet *)info->skb_packet->data; + packet = (struct batadv_vis_packet *)info->skb_packet->data; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { - router = orig_node_get_router(orig_node); + router = batadv_orig_node_get_router(orig_node); if (!router) continue; - if ((orig_node->flags & VIS_SERVER) && + if ((orig_node->flags & BATADV_VIS_SERVER) && (router->tq_avg > best_tq)) { best_tq = router->tq_avg; memcpy(packet->target_orig, orig_node->orig, ETH_ALEN); } - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); } rcu_read_unlock(); } @@ -586,47 +551,52 @@ static int find_best_vis_server(struct bat_priv *bat_priv, } /* Return true if the vis packet is full. */ -static bool vis_packet_full(const struct vis_info *info) +static bool batadv_vis_packet_full(const struct batadv_vis_info *info) { - const struct vis_packet *packet; - packet = (struct vis_packet *)info->skb_packet->data; + const struct batadv_vis_packet *packet; + size_t num; + + packet = (struct batadv_vis_packet *)info->skb_packet->data; + num = BATADV_MAX_VIS_PACKET_SIZE / sizeof(struct batadv_vis_info_entry); - if (MAX_VIS_PACKET_SIZE / sizeof(struct vis_info_entry) - < packet->entries + 1) + if (num < packet->entries + 1) return true; return false; } /* generates a packet of own vis data, - * returns 0 on success, -1 if no packet could be generated */ -static int generate_vis_packet(struct bat_priv *bat_priv) + * returns 0 on success, -1 if no packet could be generated + */ +static int batadv_generate_vis_packet(struct batadv_priv *bat_priv) { - struct hashtable_t *hash = bat_priv->orig_hash; + struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_node *node; struct hlist_head *head; - struct orig_node *orig_node; - struct neigh_node *router; - struct vis_info *info = bat_priv->my_vis_info; - struct vis_packet *packet = (struct vis_packet *)info->skb_packet->data; - struct vis_info_entry *entry; - struct tt_common_entry *tt_common_entry; + struct batadv_orig_node *orig_node; + struct batadv_neigh_node *router; + struct batadv_vis_info *info = bat_priv->my_vis_info; + struct batadv_vis_packet *packet; + struct batadv_vis_info_entry *entry; + struct batadv_tt_common_entry *tt_common_entry; int best_tq = -1; uint32_t i; info->first_seen = jiffies; + packet = (struct batadv_vis_packet *)info->skb_packet->data; packet->vis_type = atomic_read(&bat_priv->vis_mode); - memcpy(packet->target_orig, broadcast_addr, ETH_ALEN); - packet->header.ttl = TTL; + memcpy(packet->target_orig, batadv_broadcast_addr, ETH_ALEN); + packet->header.ttl = BATADV_TTL; packet->seqno = htonl(ntohl(packet->seqno) + 1); packet->entries = 0; + packet->reserved = 0; skb_trim(info->skb_packet, sizeof(*packet)); - if (packet->vis_type == VIS_TYPE_CLIENT_UPDATE) { - best_tq = find_best_vis_server(bat_priv, info); + if (packet->vis_type == BATADV_VIS_TYPE_CLIENT_UPDATE) { + best_tq = batadv_find_best_vis_server(bat_priv, info); if (best_tq < 0) - return -1; + return best_tq; } for (i = 0; i < hash->size; i++) { @@ -634,21 +604,21 @@ static int generate_vis_packet(struct bat_priv *bat_priv) rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { - router = orig_node_get_router(orig_node); + router = batadv_orig_node_get_router(orig_node); if (!router) continue; - if (!compare_eth(router->addr, orig_node->orig)) + if (!batadv_compare_eth(router->addr, orig_node->orig)) goto next; - if (router->if_incoming->if_status != IF_ACTIVE) + if (router->if_incoming->if_status != BATADV_IF_ACTIVE) goto next; if (router->tq_avg < 1) goto next; /* fill one entry into buffer. */ - entry = (struct vis_info_entry *) + entry = (struct batadv_vis_info_entry *) skb_put(info->skb_packet, sizeof(*entry)); memcpy(entry->src, router->if_incoming->net_dev->dev_addr, @@ -658,9 +628,9 @@ static int generate_vis_packet(struct bat_priv *bat_priv) packet->entries++; next: - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); - if (vis_packet_full(info)) + if (batadv_vis_packet_full(info)) goto unlock; } rcu_read_unlock(); @@ -674,7 +644,7 @@ next: rcu_read_lock(); hlist_for_each_entry_rcu(tt_common_entry, node, head, hash_entry) { - entry = (struct vis_info_entry *) + entry = (struct batadv_vis_info_entry *) skb_put(info->skb_packet, sizeof(*entry)); memset(entry->src, 0, ETH_ALEN); @@ -682,7 +652,7 @@ next: entry->quality = 0; /* 0 means TT */ packet->entries++; - if (vis_packet_full(info)) + if (batadv_vis_packet_full(info)) goto unlock; } rcu_read_unlock(); @@ -696,14 +666,15 @@ unlock: } /* free old vis packets. Must be called with this vis_hash_lock - * held */ -static void purge_vis_packets(struct bat_priv *bat_priv) + * held + */ +static void batadv_purge_vis_packets(struct batadv_priv *bat_priv) { uint32_t i; - struct hashtable_t *hash = bat_priv->vis_hash; + struct batadv_hashtable *hash = bat_priv->vis_hash; struct hlist_node *node, *node_tmp; struct hlist_head *head; - struct vis_info *info; + struct batadv_vis_info *info; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -714,31 +685,32 @@ static void purge_vis_packets(struct bat_priv *bat_priv) if (info == bat_priv->my_vis_info) continue; - if (has_timed_out(info->first_seen, VIS_TIMEOUT)) { + if (batadv_has_timed_out(info->first_seen, + BATADV_VIS_TIMEOUT)) { hlist_del(node); - send_list_del(info); - kref_put(&info->refcount, free_info); + batadv_send_list_del(info); + kref_put(&info->refcount, batadv_free_info); } } } } -static void broadcast_vis_packet(struct bat_priv *bat_priv, - struct vis_info *info) +static void batadv_broadcast_vis_packet(struct batadv_priv *bat_priv, + struct batadv_vis_info *info) { - struct neigh_node *router; - struct hashtable_t *hash = bat_priv->orig_hash; + struct batadv_neigh_node *router; + struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_node *node; struct hlist_head *head; - struct orig_node *orig_node; - struct vis_packet *packet; + struct batadv_orig_node *orig_node; + struct batadv_vis_packet *packet; struct sk_buff *skb; - struct hard_iface *hard_iface; + struct batadv_hard_iface *hard_iface; uint8_t dstaddr[ETH_ALEN]; uint32_t i; - packet = (struct vis_packet *)info->skb_packet->data; + packet = (struct batadv_vis_packet *)info->skb_packet->data; /* send to all routers in range. */ for (i = 0; i < hash->size; i++) { @@ -747,18 +719,19 @@ static void broadcast_vis_packet(struct bat_priv *bat_priv, rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { /* if it's a vis server and reachable, send it. */ - if (!(orig_node->flags & VIS_SERVER)) + if (!(orig_node->flags & BATADV_VIS_SERVER)) continue; - router = orig_node_get_router(orig_node); + router = batadv_orig_node_get_router(orig_node); if (!router) continue; /* don't send it if we already received the packet from - * this node. */ - if (recv_list_is_in(bat_priv, &info->recv_list, - orig_node->orig)) { - neigh_node_free_ref(router); + * this node. + */ + if (batadv_recv_list_is_in(bat_priv, &info->recv_list, + orig_node->orig)) { + batadv_neigh_node_free_ref(router); continue; } @@ -766,57 +739,59 @@ static void broadcast_vis_packet(struct bat_priv *bat_priv, hard_iface = router->if_incoming; memcpy(dstaddr, router->addr, ETH_ALEN); - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); skb = skb_clone(info->skb_packet, GFP_ATOMIC); if (skb) - send_skb_packet(skb, hard_iface, dstaddr); + batadv_send_skb_packet(skb, hard_iface, + dstaddr); } rcu_read_unlock(); } } -static void unicast_vis_packet(struct bat_priv *bat_priv, - struct vis_info *info) +static void batadv_unicast_vis_packet(struct batadv_priv *bat_priv, + struct batadv_vis_info *info) { - struct orig_node *orig_node; - struct neigh_node *router = NULL; + struct batadv_orig_node *orig_node; + struct batadv_neigh_node *router = NULL; struct sk_buff *skb; - struct vis_packet *packet; + struct batadv_vis_packet *packet; - packet = (struct vis_packet *)info->skb_packet->data; + packet = (struct batadv_vis_packet *)info->skb_packet->data; - orig_node = orig_hash_find(bat_priv, packet->target_orig); + orig_node = batadv_orig_hash_find(bat_priv, packet->target_orig); if (!orig_node) goto out; - router = orig_node_get_router(orig_node); + router = batadv_orig_node_get_router(orig_node); if (!router) goto out; skb = skb_clone(info->skb_packet, GFP_ATOMIC); if (skb) - send_skb_packet(skb, router->if_incoming, router->addr); + batadv_send_skb_packet(skb, router->if_incoming, router->addr); out: if (router) - neigh_node_free_ref(router); + batadv_neigh_node_free_ref(router); if (orig_node) - orig_node_free_ref(orig_node); + batadv_orig_node_free_ref(orig_node); } -/* only send one vis packet. called from send_vis_packets() */ -static void send_vis_packet(struct bat_priv *bat_priv, struct vis_info *info) +/* only send one vis packet. called from batadv_send_vis_packets() */ +static void batadv_send_vis_packet(struct batadv_priv *bat_priv, + struct batadv_vis_info *info) { - struct hard_iface *primary_if; - struct vis_packet *packet; + struct batadv_hard_iface *primary_if; + struct batadv_vis_packet *packet; - primary_if = primary_if_get_selected(bat_priv); + primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; - packet = (struct vis_packet *)info->skb_packet->data; + packet = (struct batadv_vis_packet *)info->skb_packet->data; if (packet->header.ttl < 2) { pr_debug("Error - can't send vis packet: ttl exceeded\n"); goto out; @@ -826,31 +801,31 @@ static void send_vis_packet(struct bat_priv *bat_priv, struct vis_info *info) packet->header.ttl--; if (is_broadcast_ether_addr(packet->target_orig)) - broadcast_vis_packet(bat_priv, info); + batadv_broadcast_vis_packet(bat_priv, info); else - unicast_vis_packet(bat_priv, info); + batadv_unicast_vis_packet(bat_priv, info); packet->header.ttl++; /* restore TTL */ out: if (primary_if) - hardif_free_ref(primary_if); + batadv_hardif_free_ref(primary_if); } /* called from timer; send (and maybe generate) vis packet. */ -static void send_vis_packets(struct work_struct *work) +static void batadv_send_vis_packets(struct work_struct *work) { struct delayed_work *delayed_work = container_of(work, struct delayed_work, work); - struct bat_priv *bat_priv = - container_of(delayed_work, struct bat_priv, vis_work); - struct vis_info *info; + struct batadv_priv *bat_priv; + struct batadv_vis_info *info; + bat_priv = container_of(delayed_work, struct batadv_priv, vis_work); spin_lock_bh(&bat_priv->vis_hash_lock); - purge_vis_packets(bat_priv); + batadv_purge_vis_packets(bat_priv); - if (generate_vis_packet(bat_priv) == 0) { + if (batadv_generate_vis_packet(bat_priv) == 0) { /* schedule if generation was successful */ - send_list_add(bat_priv, bat_priv->my_vis_info); + batadv_send_list_add(bat_priv, bat_priv->my_vis_info); } while (!list_empty(&bat_priv->vis_send_list)) { @@ -860,98 +835,103 @@ static void send_vis_packets(struct work_struct *work) kref_get(&info->refcount); spin_unlock_bh(&bat_priv->vis_hash_lock); - send_vis_packet(bat_priv, info); + batadv_send_vis_packet(bat_priv, info); spin_lock_bh(&bat_priv->vis_hash_lock); - send_list_del(info); - kref_put(&info->refcount, free_info); + batadv_send_list_del(info); + kref_put(&info->refcount, batadv_free_info); } spin_unlock_bh(&bat_priv->vis_hash_lock); - start_vis_timer(bat_priv); + batadv_start_vis_timer(bat_priv); } /* init the vis server. this may only be called when if_list is already - * initialized (e.g. bat0 is initialized, interfaces have been added) */ -int vis_init(struct bat_priv *bat_priv) + * initialized (e.g. bat0 is initialized, interfaces have been added) + */ +int batadv_vis_init(struct batadv_priv *bat_priv) { - struct vis_packet *packet; + struct batadv_vis_packet *packet; int hash_added; + unsigned int len; + unsigned long first_seen; + struct sk_buff *tmp_skb; if (bat_priv->vis_hash) - return 1; + return 0; spin_lock_bh(&bat_priv->vis_hash_lock); - bat_priv->vis_hash = hash_new(256); + bat_priv->vis_hash = batadv_hash_new(256); if (!bat_priv->vis_hash) { pr_err("Can't initialize vis_hash\n"); goto err; } - bat_priv->my_vis_info = kmalloc(MAX_VIS_PACKET_SIZE, GFP_ATOMIC); + bat_priv->my_vis_info = kmalloc(BATADV_MAX_VIS_PACKET_SIZE, GFP_ATOMIC); if (!bat_priv->my_vis_info) goto err; - bat_priv->my_vis_info->skb_packet = dev_alloc_skb(sizeof(*packet) + - MAX_VIS_PACKET_SIZE + - ETH_HLEN); + len = sizeof(*packet) + BATADV_MAX_VIS_PACKET_SIZE + ETH_HLEN; + bat_priv->my_vis_info->skb_packet = dev_alloc_skb(len); if (!bat_priv->my_vis_info->skb_packet) goto free_info; skb_reserve(bat_priv->my_vis_info->skb_packet, ETH_HLEN); - packet = (struct vis_packet *)skb_put(bat_priv->my_vis_info->skb_packet, - sizeof(*packet)); + tmp_skb = bat_priv->my_vis_info->skb_packet; + packet = (struct batadv_vis_packet *)skb_put(tmp_skb, sizeof(*packet)); /* prefill the vis info */ - bat_priv->my_vis_info->first_seen = jiffies - - msecs_to_jiffies(VIS_INTERVAL); + first_seen = jiffies - msecs_to_jiffies(BATADV_VIS_INTERVAL); + bat_priv->my_vis_info->first_seen = first_seen; INIT_LIST_HEAD(&bat_priv->my_vis_info->recv_list); INIT_LIST_HEAD(&bat_priv->my_vis_info->send_list); kref_init(&bat_priv->my_vis_info->refcount); bat_priv->my_vis_info->bat_priv = bat_priv; - packet->header.version = COMPAT_VERSION; - packet->header.packet_type = BAT_VIS; - packet->header.ttl = TTL; + packet->header.version = BATADV_COMPAT_VERSION; + packet->header.packet_type = BATADV_VIS; + packet->header.ttl = BATADV_TTL; packet->seqno = 0; + packet->reserved = 0; packet->entries = 0; INIT_LIST_HEAD(&bat_priv->vis_send_list); - hash_added = hash_add(bat_priv->vis_hash, vis_info_cmp, vis_info_choose, - bat_priv->my_vis_info, - &bat_priv->my_vis_info->hash_entry); + hash_added = batadv_hash_add(bat_priv->vis_hash, batadv_vis_info_cmp, + batadv_vis_info_choose, + bat_priv->my_vis_info, + &bat_priv->my_vis_info->hash_entry); if (hash_added != 0) { pr_err("Can't add own vis packet into hash\n"); /* not in hash, need to remove it manually. */ - kref_put(&bat_priv->my_vis_info->refcount, free_info); + kref_put(&bat_priv->my_vis_info->refcount, batadv_free_info); goto err; } spin_unlock_bh(&bat_priv->vis_hash_lock); - start_vis_timer(bat_priv); - return 1; + batadv_start_vis_timer(bat_priv); + return 0; free_info: kfree(bat_priv->my_vis_info); bat_priv->my_vis_info = NULL; err: spin_unlock_bh(&bat_priv->vis_hash_lock); - vis_quit(bat_priv); - return 0; + batadv_vis_quit(bat_priv); + return -ENOMEM; } /* Decrease the reference count on a hash item info */ -static void free_info_ref(struct hlist_node *node, void *arg) +static void batadv_free_info_ref(struct hlist_node *node, void *arg) { - struct vis_info *info; + struct batadv_vis_info *info; - info = container_of(node, struct vis_info, hash_entry); - send_list_del(info); - kref_put(&info->refcount, free_info); + info = container_of(node, struct batadv_vis_info, hash_entry); + batadv_send_list_del(info); + kref_put(&info->refcount, batadv_free_info); } /* shutdown vis-server */ -void vis_quit(struct bat_priv *bat_priv) +void batadv_vis_quit(struct batadv_priv *bat_priv) { if (!bat_priv->vis_hash) return; @@ -960,16 +940,16 @@ void vis_quit(struct bat_priv *bat_priv) spin_lock_bh(&bat_priv->vis_hash_lock); /* properly remove, kill timers ... */ - hash_delete(bat_priv->vis_hash, free_info_ref, NULL); + batadv_hash_delete(bat_priv->vis_hash, batadv_free_info_ref, NULL); bat_priv->vis_hash = NULL; bat_priv->my_vis_info = NULL; spin_unlock_bh(&bat_priv->vis_hash_lock); } /* schedule packets for (re)transmission */ -static void start_vis_timer(struct bat_priv *bat_priv) +static void batadv_start_vis_timer(struct batadv_priv *bat_priv) { - INIT_DELAYED_WORK(&bat_priv->vis_work, send_vis_packets); - queue_delayed_work(bat_event_workqueue, &bat_priv->vis_work, - msecs_to_jiffies(VIS_INTERVAL)); + INIT_DELAYED_WORK(&bat_priv->vis_work, batadv_send_vis_packets); + queue_delayed_work(batadv_event_workqueue, &bat_priv->vis_work, + msecs_to_jiffies(BATADV_VIS_INTERVAL)); } diff --git a/net/batman-adv/vis.h b/net/batman-adv/vis.h index ee2e46e5347..84e716ed896 100644 --- a/net/batman-adv/vis.h +++ b/net/batman-adv/vis.h @@ -1,5 +1,4 @@ -/* - * Copyright (C) 2008-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2008-2012 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * @@ -16,23 +15,22 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA - * */ #ifndef _NET_BATMAN_ADV_VIS_H_ #define _NET_BATMAN_ADV_VIS_H_ -#define VIS_TIMEOUT 200000 /* timeout of vis packets - * in miliseconds */ +/* timeout of vis packets in miliseconds */ +#define BATADV_VIS_TIMEOUT 200000 -int vis_seq_print_text(struct seq_file *seq, void *offset); -void receive_server_sync_packet(struct bat_priv *bat_priv, - struct vis_packet *vis_packet, - int vis_info_len); -void receive_client_update_packet(struct bat_priv *bat_priv, - struct vis_packet *vis_packet, - int vis_info_len); -int vis_init(struct bat_priv *bat_priv); -void vis_quit(struct bat_priv *bat_priv); +int batadv_vis_seq_print_text(struct seq_file *seq, void *offset); +void batadv_receive_server_sync_packet(struct batadv_priv *bat_priv, + struct batadv_vis_packet *vis_packet, + int vis_info_len); +void batadv_receive_client_update_packet(struct batadv_priv *bat_priv, + struct batadv_vis_packet *vis_packet, + int vis_info_len); +int batadv_vis_init(struct batadv_priv *bat_priv); +void batadv_vis_quit(struct batadv_priv *bat_priv); #endif /* _NET_BATMAN_ADV_VIS_H_ */ diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index 2dc5a5700f5..fa6d94a4602 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -9,4 +9,5 @@ obj-$(CONFIG_BT_CMTP) += cmtp/ obj-$(CONFIG_BT_HIDP) += hidp/ bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \ - hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o sco.o lib.o + hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o sco.o lib.o \ + a2mp.o diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c new file mode 100644 index 00000000000..4ff0bf3ba9a --- /dev/null +++ b/net/bluetooth/a2mp.c @@ -0,0 +1,568 @@ +/* + Copyright (c) 2010,2011 Code Aurora Forum. All rights reserved. + Copyright (c) 2011,2012 Intel Corp. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License version 2 and + only version 2 as published by the Free Software Foundation. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. +*/ + +#include <net/bluetooth/bluetooth.h> +#include <net/bluetooth/hci_core.h> +#include <net/bluetooth/l2cap.h> +#include <net/bluetooth/a2mp.h> + +/* A2MP build & send command helper functions */ +static struct a2mp_cmd *__a2mp_build(u8 code, u8 ident, u16 len, void *data) +{ + struct a2mp_cmd *cmd; + int plen; + + plen = sizeof(*cmd) + len; + cmd = kzalloc(plen, GFP_KERNEL); + if (!cmd) + return NULL; + + cmd->code = code; + cmd->ident = ident; + cmd->len = cpu_to_le16(len); + + memcpy(cmd->data, data, len); + + return cmd; +} + +static void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, + void *data) +{ + struct l2cap_chan *chan = mgr->a2mp_chan; + struct a2mp_cmd *cmd; + u16 total_len = len + sizeof(*cmd); + struct kvec iv; + struct msghdr msg; + + cmd = __a2mp_build(code, ident, len, data); + if (!cmd) + return; + + iv.iov_base = cmd; + iv.iov_len = total_len; + + memset(&msg, 0, sizeof(msg)); + + msg.msg_iov = (struct iovec *) &iv; + msg.msg_iovlen = 1; + + l2cap_chan_send(chan, &msg, total_len, 0); + + kfree(cmd); +} + +static inline void __a2mp_cl_bredr(struct a2mp_cl *cl) +{ + cl->id = 0; + cl->type = 0; + cl->status = 1; +} + +/* hci_dev_list shall be locked */ +static void __a2mp_add_cl(struct amp_mgr *mgr, struct a2mp_cl *cl, u8 num_ctrl) +{ + int i = 0; + struct hci_dev *hdev; + + __a2mp_cl_bredr(cl); + + list_for_each_entry(hdev, &hci_dev_list, list) { + /* Iterate through AMP controllers */ + if (hdev->id == HCI_BREDR_ID) + continue; + + /* Starting from second entry */ + if (++i >= num_ctrl) + return; + + cl[i].id = hdev->id; + cl[i].type = hdev->amp_type; + cl[i].status = hdev->amp_status; + } +} + +/* Processing A2MP messages */ +static int a2mp_command_rej(struct amp_mgr *mgr, struct sk_buff *skb, + struct a2mp_cmd *hdr) +{ + struct a2mp_cmd_rej *rej = (void *) skb->data; + + if (le16_to_cpu(hdr->len) < sizeof(*rej)) + return -EINVAL; + + BT_DBG("ident %d reason %d", hdr->ident, le16_to_cpu(rej->reason)); + + skb_pull(skb, sizeof(*rej)); + + return 0; +} + +static int a2mp_discover_req(struct amp_mgr *mgr, struct sk_buff *skb, + struct a2mp_cmd *hdr) +{ + struct a2mp_discov_req *req = (void *) skb->data; + u16 len = le16_to_cpu(hdr->len); + struct a2mp_discov_rsp *rsp; + u16 ext_feat; + u8 num_ctrl; + + if (len < sizeof(*req)) + return -EINVAL; + + skb_pull(skb, sizeof(*req)); + + ext_feat = le16_to_cpu(req->ext_feat); + + BT_DBG("mtu %d efm 0x%4.4x", le16_to_cpu(req->mtu), ext_feat); + + /* check that packet is not broken for now */ + while (ext_feat & A2MP_FEAT_EXT) { + if (len < sizeof(ext_feat)) + return -EINVAL; + + ext_feat = get_unaligned_le16(skb->data); + BT_DBG("efm 0x%4.4x", ext_feat); + len -= sizeof(ext_feat); + skb_pull(skb, sizeof(ext_feat)); + } + + read_lock(&hci_dev_list_lock); + + num_ctrl = __hci_num_ctrl(); + len = num_ctrl * sizeof(struct a2mp_cl) + sizeof(*rsp); + rsp = kmalloc(len, GFP_ATOMIC); + if (!rsp) { + read_unlock(&hci_dev_list_lock); + return -ENOMEM; + } + + rsp->mtu = __constant_cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU); + rsp->ext_feat = 0; + + __a2mp_add_cl(mgr, rsp->cl, num_ctrl); + + read_unlock(&hci_dev_list_lock); + + a2mp_send(mgr, A2MP_DISCOVER_RSP, hdr->ident, len, rsp); + + kfree(rsp); + return 0; +} + +static int a2mp_change_notify(struct amp_mgr *mgr, struct sk_buff *skb, + struct a2mp_cmd *hdr) +{ + struct a2mp_cl *cl = (void *) skb->data; + + while (skb->len >= sizeof(*cl)) { + BT_DBG("Controller id %d type %d status %d", cl->id, cl->type, + cl->status); + cl = (struct a2mp_cl *) skb_pull(skb, sizeof(*cl)); + } + + /* TODO send A2MP_CHANGE_RSP */ + + return 0; +} + +static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb, + struct a2mp_cmd *hdr) +{ + struct a2mp_info_req *req = (void *) skb->data; + struct a2mp_info_rsp rsp; + struct hci_dev *hdev; + + if (le16_to_cpu(hdr->len) < sizeof(*req)) + return -EINVAL; + + BT_DBG("id %d", req->id); + + rsp.id = req->id; + rsp.status = A2MP_STATUS_INVALID_CTRL_ID; + + hdev = hci_dev_get(req->id); + if (hdev && hdev->amp_type != HCI_BREDR) { + rsp.status = 0; + rsp.total_bw = cpu_to_le32(hdev->amp_total_bw); + rsp.max_bw = cpu_to_le32(hdev->amp_max_bw); + rsp.min_latency = cpu_to_le32(hdev->amp_min_latency); + rsp.pal_cap = cpu_to_le16(hdev->amp_pal_cap); + rsp.assoc_size = cpu_to_le16(hdev->amp_assoc_size); + } + + if (hdev) + hci_dev_put(hdev); + + a2mp_send(mgr, A2MP_GETINFO_RSP, hdr->ident, sizeof(rsp), &rsp); + + skb_pull(skb, sizeof(*req)); + return 0; +} + +static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb, + struct a2mp_cmd *hdr) +{ + struct a2mp_amp_assoc_req *req = (void *) skb->data; + struct hci_dev *hdev; + + if (le16_to_cpu(hdr->len) < sizeof(*req)) + return -EINVAL; + + BT_DBG("id %d", req->id); + + hdev = hci_dev_get(req->id); + if (!hdev || hdev->amp_type == HCI_BREDR) { + struct a2mp_amp_assoc_rsp rsp; + rsp.id = req->id; + rsp.status = A2MP_STATUS_INVALID_CTRL_ID; + + a2mp_send(mgr, A2MP_GETAMPASSOC_RSP, hdr->ident, sizeof(rsp), + &rsp); + goto clean; + } + + /* Placeholder for HCI Read AMP Assoc */ + +clean: + if (hdev) + hci_dev_put(hdev); + + skb_pull(skb, sizeof(*req)); + return 0; +} + +static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, + struct a2mp_cmd *hdr) +{ + struct a2mp_physlink_req *req = (void *) skb->data; + + struct a2mp_physlink_rsp rsp; + struct hci_dev *hdev; + + if (le16_to_cpu(hdr->len) < sizeof(*req)) + return -EINVAL; + + BT_DBG("local_id %d, remote_id %d", req->local_id, req->remote_id); + + rsp.local_id = req->remote_id; + rsp.remote_id = req->local_id; + + hdev = hci_dev_get(req->remote_id); + if (!hdev || hdev->amp_type != HCI_AMP) { + rsp.status = A2MP_STATUS_INVALID_CTRL_ID; + goto send_rsp; + } + + /* TODO process physlink create */ + + rsp.status = A2MP_STATUS_SUCCESS; + +send_rsp: + if (hdev) + hci_dev_put(hdev); + + a2mp_send(mgr, A2MP_CREATEPHYSLINK_RSP, hdr->ident, sizeof(rsp), + &rsp); + + skb_pull(skb, le16_to_cpu(hdr->len)); + return 0; +} + +static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, + struct a2mp_cmd *hdr) +{ + struct a2mp_physlink_req *req = (void *) skb->data; + struct a2mp_physlink_rsp rsp; + struct hci_dev *hdev; + + if (le16_to_cpu(hdr->len) < sizeof(*req)) + return -EINVAL; + + BT_DBG("local_id %d remote_id %d", req->local_id, req->remote_id); + + rsp.local_id = req->remote_id; + rsp.remote_id = req->local_id; + rsp.status = A2MP_STATUS_SUCCESS; + + hdev = hci_dev_get(req->local_id); + if (!hdev) { + rsp.status = A2MP_STATUS_INVALID_CTRL_ID; + goto send_rsp; + } + + /* TODO Disconnect Phys Link here */ + + hci_dev_put(hdev); + +send_rsp: + a2mp_send(mgr, A2MP_DISCONNPHYSLINK_RSP, hdr->ident, sizeof(rsp), &rsp); + + skb_pull(skb, sizeof(*req)); + return 0; +} + +static inline int a2mp_cmd_rsp(struct amp_mgr *mgr, struct sk_buff *skb, + struct a2mp_cmd *hdr) +{ + BT_DBG("ident %d code %d", hdr->ident, hdr->code); + + skb_pull(skb, le16_to_cpu(hdr->len)); + return 0; +} + +/* Handle A2MP signalling */ +static int a2mp_chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) +{ + struct a2mp_cmd *hdr = (void *) skb->data; + struct amp_mgr *mgr = chan->data; + int err = 0; + + amp_mgr_get(mgr); + + while (skb->len >= sizeof(*hdr)) { + struct a2mp_cmd *hdr = (void *) skb->data; + u16 len = le16_to_cpu(hdr->len); + + BT_DBG("code 0x%02x id %d len %d", hdr->code, hdr->ident, len); + + skb_pull(skb, sizeof(*hdr)); + + if (len > skb->len || !hdr->ident) { + err = -EINVAL; + break; + } + + mgr->ident = hdr->ident; + + switch (hdr->code) { + case A2MP_COMMAND_REJ: + a2mp_command_rej(mgr, skb, hdr); + break; + + case A2MP_DISCOVER_REQ: + err = a2mp_discover_req(mgr, skb, hdr); + break; + + case A2MP_CHANGE_NOTIFY: + err = a2mp_change_notify(mgr, skb, hdr); + break; + + case A2MP_GETINFO_REQ: + err = a2mp_getinfo_req(mgr, skb, hdr); + break; + + case A2MP_GETAMPASSOC_REQ: + err = a2mp_getampassoc_req(mgr, skb, hdr); + break; + + case A2MP_CREATEPHYSLINK_REQ: + err = a2mp_createphyslink_req(mgr, skb, hdr); + break; + + case A2MP_DISCONNPHYSLINK_REQ: + err = a2mp_discphyslink_req(mgr, skb, hdr); + break; + + case A2MP_CHANGE_RSP: + case A2MP_DISCOVER_RSP: + case A2MP_GETINFO_RSP: + case A2MP_GETAMPASSOC_RSP: + case A2MP_CREATEPHYSLINK_RSP: + case A2MP_DISCONNPHYSLINK_RSP: + err = a2mp_cmd_rsp(mgr, skb, hdr); + break; + + default: + BT_ERR("Unknown A2MP sig cmd 0x%2.2x", hdr->code); + err = -EINVAL; + break; + } + } + + if (err) { + struct a2mp_cmd_rej rej; + rej.reason = __constant_cpu_to_le16(0); + + BT_DBG("Send A2MP Rej: cmd 0x%2.2x err %d", hdr->code, err); + + a2mp_send(mgr, A2MP_COMMAND_REJ, hdr->ident, sizeof(rej), + &rej); + } + + /* Always free skb and return success error code to prevent + from sending L2CAP Disconnect over A2MP channel */ + kfree_skb(skb); + + amp_mgr_put(mgr); + + return 0; +} + +static void a2mp_chan_close_cb(struct l2cap_chan *chan) +{ + l2cap_chan_destroy(chan); +} + +static void a2mp_chan_state_change_cb(struct l2cap_chan *chan, int state) +{ + struct amp_mgr *mgr = chan->data; + + if (!mgr) + return; + + BT_DBG("chan %p state %s", chan, state_to_string(state)); + + chan->state = state; + + switch (state) { + case BT_CLOSED: + if (mgr) + amp_mgr_put(mgr); + break; + } +} + +static struct sk_buff *a2mp_chan_alloc_skb_cb(struct l2cap_chan *chan, + unsigned long len, int nb) +{ + return bt_skb_alloc(len, GFP_KERNEL); +} + +static struct l2cap_ops a2mp_chan_ops = { + .name = "L2CAP A2MP channel", + .recv = a2mp_chan_recv_cb, + .close = a2mp_chan_close_cb, + .state_change = a2mp_chan_state_change_cb, + .alloc_skb = a2mp_chan_alloc_skb_cb, + + /* Not implemented for A2MP */ + .new_connection = l2cap_chan_no_new_connection, + .teardown = l2cap_chan_no_teardown, + .ready = l2cap_chan_no_ready, +}; + +static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn) +{ + struct l2cap_chan *chan; + int err; + + chan = l2cap_chan_create(); + if (!chan) + return NULL; + + BT_DBG("chan %p", chan); + + chan->chan_type = L2CAP_CHAN_CONN_FIX_A2MP; + chan->flush_to = L2CAP_DEFAULT_FLUSH_TO; + + chan->ops = &a2mp_chan_ops; + + l2cap_chan_set_defaults(chan); + chan->remote_max_tx = chan->max_tx; + chan->remote_tx_win = chan->tx_win; + + chan->retrans_timeout = L2CAP_DEFAULT_RETRANS_TO; + chan->monitor_timeout = L2CAP_DEFAULT_MONITOR_TO; + + skb_queue_head_init(&chan->tx_q); + + chan->mode = L2CAP_MODE_ERTM; + + err = l2cap_ertm_init(chan); + if (err < 0) { + l2cap_chan_del(chan, 0); + return NULL; + } + + chan->conf_state = 0; + + l2cap_chan_add(conn, chan); + + chan->remote_mps = chan->omtu; + chan->mps = chan->omtu; + + chan->state = BT_CONNECTED; + + return chan; +} + +/* AMP Manager functions */ +void amp_mgr_get(struct amp_mgr *mgr) +{ + BT_DBG("mgr %p orig refcnt %d", mgr, atomic_read(&mgr->kref.refcount)); + + kref_get(&mgr->kref); +} + +static void amp_mgr_destroy(struct kref *kref) +{ + struct amp_mgr *mgr = container_of(kref, struct amp_mgr, kref); + + BT_DBG("mgr %p", mgr); + + kfree(mgr); +} + +int amp_mgr_put(struct amp_mgr *mgr) +{ + BT_DBG("mgr %p orig refcnt %d", mgr, atomic_read(&mgr->kref.refcount)); + + return kref_put(&mgr->kref, &_mgr_destroy); +} + +static struct amp_mgr *amp_mgr_create(struct l2cap_conn *conn) +{ + struct amp_mgr *mgr; + struct l2cap_chan *chan; + + mgr = kzalloc(sizeof(*mgr), GFP_KERNEL); + if (!mgr) + return NULL; + + BT_DBG("conn %p mgr %p", conn, mgr); + + mgr->l2cap_conn = conn; + + chan = a2mp_chan_open(conn); + if (!chan) { + kfree(mgr); + return NULL; + } + + mgr->a2mp_chan = chan; + chan->data = mgr; + + conn->hcon->amp_mgr = mgr; + + kref_init(&mgr->kref); + + return mgr; +} + +struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, + struct sk_buff *skb) +{ + struct amp_mgr *mgr; + + mgr = amp_mgr_create(conn); + if (!mgr) { + BT_ERR("Could not create AMP manager"); + return NULL; + } + + BT_DBG("mgr: %p chan %p", mgr, mgr->a2mp_chan); + + return mgr->a2mp_chan; +} diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 3e18af4dadc..f7db5792ec6 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -25,18 +25,7 @@ /* Bluetooth address family and sockets. */ #include <linux/module.h> - -#include <linux/types.h> -#include <linux/list.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/skbuff.h> -#include <linux/init.h> -#include <linux/poll.h> -#include <net/sock.h> #include <asm/ioctls.h> -#include <linux/kmod.h> #include <net/bluetooth/bluetooth.h> @@ -418,7 +407,8 @@ static inline unsigned int bt_accept_poll(struct sock *parent) return 0; } -unsigned int bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait) +unsigned int bt_sock_poll(struct file *file, struct socket *sock, + poll_table *wait) { struct sock *sk = sock->sk; unsigned int mask = 0; diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 031d7d65675..4a6620bc157 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -26,26 +26,9 @@ */ #include <linux/module.h> - -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/signal.h> -#include <linux/init.h> -#include <linux/wait.h> -#include <linux/freezer.h> -#include <linux/errno.h> -#include <linux/net.h> -#include <linux/slab.h> #include <linux/kthread.h> -#include <net/sock.h> - -#include <linux/socket.h> #include <linux/file.h> - -#include <linux/netdevice.h> #include <linux/etherdevice.h> -#include <linux/skbuff.h> - #include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> @@ -306,7 +289,7 @@ static u8 __bnep_rx_hlen[] = { ETH_ALEN + 2 /* BNEP_COMPRESSED_DST_ONLY */ }; -static inline int bnep_rx_frame(struct bnep_session *s, struct sk_buff *skb) +static int bnep_rx_frame(struct bnep_session *s, struct sk_buff *skb) { struct net_device *dev = s->dev; struct sk_buff *nskb; @@ -404,7 +387,7 @@ static u8 __bnep_tx_types[] = { BNEP_COMPRESSED }; -static inline int bnep_tx_frame(struct bnep_session *s, struct sk_buff *skb) +static int bnep_tx_frame(struct bnep_session *s, struct sk_buff *skb) { struct ethhdr *eh = (void *) skb->data; struct socket *sock = s->sock; diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c index bc4086480d9..98f86f91d47 100644 --- a/net/bluetooth/bnep/netdev.c +++ b/net/bluetooth/bnep/netdev.c @@ -25,16 +25,8 @@ SOFTWARE IS DISCLAIMED. */ -#include <linux/module.h> -#include <linux/slab.h> - -#include <linux/socket.h> -#include <linux/netdevice.h> +#include <linux/export.h> #include <linux/etherdevice.h> -#include <linux/skbuff.h> -#include <linux/wait.h> - -#include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -128,7 +120,7 @@ static void bnep_net_timeout(struct net_device *dev) } #ifdef CONFIG_BT_BNEP_MC_FILTER -static inline int bnep_net_mc_filter(struct sk_buff *skb, struct bnep_session *s) +static int bnep_net_mc_filter(struct sk_buff *skb, struct bnep_session *s) { struct ethhdr *eh = (void *) skb->data; @@ -140,7 +132,7 @@ static inline int bnep_net_mc_filter(struct sk_buff *skb, struct bnep_session *s #ifdef CONFIG_BT_BNEP_PROTO_FILTER /* Determine ether protocol. Based on eth_type_trans. */ -static inline u16 bnep_net_eth_proto(struct sk_buff *skb) +static u16 bnep_net_eth_proto(struct sk_buff *skb) { struct ethhdr *eh = (void *) skb->data; u16 proto = ntohs(eh->h_proto); @@ -154,7 +146,7 @@ static inline u16 bnep_net_eth_proto(struct sk_buff *skb) return ETH_P_802_2; } -static inline int bnep_net_proto_filter(struct sk_buff *skb, struct bnep_session *s) +static int bnep_net_proto_filter(struct sk_buff *skb, struct bnep_session *s) { u16 proto = bnep_net_eth_proto(skb); struct bnep_proto_filter *f = s->proto_filter; diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c index 180bfc45810..5e5f5b410e0 100644 --- a/net/bluetooth/bnep/sock.c +++ b/net/bluetooth/bnep/sock.c @@ -24,24 +24,8 @@ SOFTWARE IS DISCLAIMED. */ -#include <linux/module.h> - -#include <linux/types.h> -#include <linux/capability.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/poll.h> -#include <linux/fcntl.h> -#include <linux/skbuff.h> -#include <linux/socket.h> -#include <linux/ioctl.h> +#include <linux/export.h> #include <linux/file.h> -#include <linux/init.h> -#include <linux/compat.h> -#include <linux/gfp.h> -#include <linux/uaccess.h> -#include <net/sock.h> - #include "bnep.h" diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 3f18a6ed973..5ad7da21747 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -24,24 +24,11 @@ /* Bluetooth HCI connection handling. */ -#include <linux/module.h> - -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/poll.h> -#include <linux/fcntl.h> -#include <linux/init.h> -#include <linux/skbuff.h> -#include <linux/interrupt.h> -#include <net/sock.h> - -#include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/export.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> +#include <net/bluetooth/a2mp.h> static void hci_le_connect(struct hci_conn *conn) { @@ -54,15 +41,15 @@ static void hci_le_connect(struct hci_conn *conn) conn->sec_level = BT_SECURITY_LOW; memset(&cp, 0, sizeof(cp)); - cp.scan_interval = cpu_to_le16(0x0060); - cp.scan_window = cpu_to_le16(0x0030); + cp.scan_interval = __constant_cpu_to_le16(0x0060); + cp.scan_window = __constant_cpu_to_le16(0x0030); bacpy(&cp.peer_addr, &conn->dst); cp.peer_addr_type = conn->dst_type; - cp.conn_interval_min = cpu_to_le16(0x0028); - cp.conn_interval_max = cpu_to_le16(0x0038); - cp.supervision_timeout = cpu_to_le16(0x002a); - cp.min_ce_len = cpu_to_le16(0x0000); - cp.max_ce_len = cpu_to_le16(0x0000); + cp.conn_interval_min = __constant_cpu_to_le16(0x0028); + cp.conn_interval_max = __constant_cpu_to_le16(0x0038); + cp.supervision_timeout = __constant_cpu_to_le16(0x002a); + cp.min_ce_len = __constant_cpu_to_le16(0x0000); + cp.max_ce_len = __constant_cpu_to_le16(0x0000); hci_send_cmd(hdev, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp); } @@ -99,7 +86,7 @@ void hci_acl_connect(struct hci_conn *conn) cp.pscan_rep_mode = ie->data.pscan_rep_mode; cp.pscan_mode = ie->data.pscan_mode; cp.clock_offset = ie->data.clock_offset | - cpu_to_le16(0x8000); + __constant_cpu_to_le16(0x8000); } memcpy(conn->dev_class, ie->data.dev_class, 3); @@ -120,7 +107,7 @@ static void hci_acl_connect_cancel(struct hci_conn *conn) { struct hci_cp_create_conn_cancel cp; - BT_DBG("%p", conn); + BT_DBG("hcon %p", conn); if (conn->hdev->hci_ver < BLUETOOTH_VER_1_2) return; @@ -133,7 +120,7 @@ void hci_acl_disconn(struct hci_conn *conn, __u8 reason) { struct hci_cp_disconnect cp; - BT_DBG("%p", conn); + BT_DBG("hcon %p", conn); conn->state = BT_DISCONN; @@ -147,7 +134,7 @@ void hci_add_sco(struct hci_conn *conn, __u16 handle) struct hci_dev *hdev = conn->hdev; struct hci_cp_add_sco cp; - BT_DBG("%p", conn); + BT_DBG("hcon %p", conn); conn->state = BT_CONNECT; conn->out = true; @@ -165,7 +152,7 @@ void hci_setup_sync(struct hci_conn *conn, __u16 handle) struct hci_dev *hdev = conn->hdev; struct hci_cp_setup_sync_conn cp; - BT_DBG("%p", conn); + BT_DBG("hcon %p", conn); conn->state = BT_CONNECT; conn->out = true; @@ -175,9 +162,9 @@ void hci_setup_sync(struct hci_conn *conn, __u16 handle) cp.handle = cpu_to_le16(handle); cp.pkt_type = cpu_to_le16(conn->pkt_type); - cp.tx_bandwidth = cpu_to_le32(0x00001f40); - cp.rx_bandwidth = cpu_to_le32(0x00001f40); - cp.max_latency = cpu_to_le16(0xffff); + cp.tx_bandwidth = __constant_cpu_to_le32(0x00001f40); + cp.rx_bandwidth = __constant_cpu_to_le32(0x00001f40); + cp.max_latency = __constant_cpu_to_le16(0xffff); cp.voice_setting = cpu_to_le16(hdev->voice_setting); cp.retrans_effort = 0xff; @@ -185,7 +172,7 @@ void hci_setup_sync(struct hci_conn *conn, __u16 handle) } void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, - u16 latency, u16 to_multiplier) + u16 latency, u16 to_multiplier) { struct hci_cp_le_conn_update cp; struct hci_dev *hdev = conn->hdev; @@ -197,20 +184,19 @@ void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, cp.conn_interval_max = cpu_to_le16(max); cp.conn_latency = cpu_to_le16(latency); cp.supervision_timeout = cpu_to_le16(to_multiplier); - cp.min_ce_len = cpu_to_le16(0x0001); - cp.max_ce_len = cpu_to_le16(0x0001); + cp.min_ce_len = __constant_cpu_to_le16(0x0001); + cp.max_ce_len = __constant_cpu_to_le16(0x0001); hci_send_cmd(hdev, HCI_OP_LE_CONN_UPDATE, sizeof(cp), &cp); } -EXPORT_SYMBOL(hci_le_conn_update); void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __u8 rand[8], - __u8 ltk[16]) + __u8 ltk[16]) { struct hci_dev *hdev = conn->hdev; struct hci_cp_le_start_enc cp; - BT_DBG("%p", conn); + BT_DBG("hcon %p", conn); memset(&cp, 0, sizeof(cp)); @@ -221,18 +207,17 @@ void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __u8 rand[8], hci_send_cmd(hdev, HCI_OP_LE_START_ENC, sizeof(cp), &cp); } -EXPORT_SYMBOL(hci_le_start_enc); /* Device _must_ be locked */ void hci_sco_setup(struct hci_conn *conn, __u8 status) { struct hci_conn *sco = conn->link; - BT_DBG("%p", conn); - if (!sco) return; + BT_DBG("hcon %p", conn); + if (!status) { if (lmp_esco_capable(conn->hdev)) hci_setup_sync(sco, conn->handle); @@ -247,10 +232,10 @@ void hci_sco_setup(struct hci_conn *conn, __u8 status) static void hci_conn_timeout(struct work_struct *work) { struct hci_conn *conn = container_of(work, struct hci_conn, - disc_work.work); + disc_work.work); __u8 reason; - BT_DBG("conn %p state %s", conn, state_to_string(conn->state)); + BT_DBG("hcon %p state %s", conn, state_to_string(conn->state)); if (atomic_read(&conn->refcnt)) return; @@ -281,7 +266,7 @@ static void hci_conn_enter_sniff_mode(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - BT_DBG("conn %p mode %d", conn, conn->mode); + BT_DBG("hcon %p mode %d", conn, conn->mode); if (test_bit(HCI_RAW, &hdev->flags)) return; @@ -295,9 +280,9 @@ static void hci_conn_enter_sniff_mode(struct hci_conn *conn) if (lmp_sniffsubr_capable(hdev) && lmp_sniffsubr_capable(conn)) { struct hci_cp_sniff_subrate cp; cp.handle = cpu_to_le16(conn->handle); - cp.max_latency = cpu_to_le16(0); - cp.min_remote_timeout = cpu_to_le16(0); - cp.min_local_timeout = cpu_to_le16(0); + cp.max_latency = __constant_cpu_to_le16(0); + cp.min_remote_timeout = __constant_cpu_to_le16(0); + cp.min_local_timeout = __constant_cpu_to_le16(0); hci_send_cmd(hdev, HCI_OP_SNIFF_SUBRATE, sizeof(cp), &cp); } @@ -306,8 +291,8 @@ static void hci_conn_enter_sniff_mode(struct hci_conn *conn) cp.handle = cpu_to_le16(conn->handle); cp.max_interval = cpu_to_le16(hdev->sniff_max_interval); cp.min_interval = cpu_to_le16(hdev->sniff_min_interval); - cp.attempt = cpu_to_le16(4); - cp.timeout = cpu_to_le16(1); + cp.attempt = __constant_cpu_to_le16(4); + cp.timeout = __constant_cpu_to_le16(1); hci_send_cmd(hdev, HCI_OP_SNIFF_MODE, sizeof(cp), &cp); } } @@ -316,7 +301,7 @@ static void hci_conn_idle(unsigned long arg) { struct hci_conn *conn = (void *) arg; - BT_DBG("conn %p mode %d", conn, conn->mode); + BT_DBG("hcon %p mode %d", conn, conn->mode); hci_conn_enter_sniff_mode(conn); } @@ -327,7 +312,7 @@ static void hci_conn_auto_accept(unsigned long arg) struct hci_dev *hdev = conn->hdev; hci_send_cmd(hdev, HCI_OP_USER_CONFIRM_REPLY, sizeof(conn->dst), - &conn->dst); + &conn->dst); } struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) @@ -376,7 +361,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) INIT_DELAYED_WORK(&conn->disc_work, hci_conn_timeout); setup_timer(&conn->idle_timer, hci_conn_idle, (unsigned long)conn); setup_timer(&conn->auto_accept_timer, hci_conn_auto_accept, - (unsigned long) conn); + (unsigned long) conn); atomic_set(&conn->refcnt, 0); @@ -397,7 +382,7 @@ int hci_conn_del(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - BT_DBG("%s conn %p handle %d", hdev->name, conn, conn->handle); + BT_DBG("%s hcon %p handle %d", hdev->name, conn, conn->handle); del_timer(&conn->idle_timer); @@ -425,9 +410,11 @@ int hci_conn_del(struct hci_conn *conn) } } - hci_chan_list_flush(conn); + if (conn->amp_mgr) + amp_mgr_put(conn->amp_mgr); + hci_conn_hash_del(hdev, conn); if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); @@ -454,7 +441,9 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src) read_lock(&hci_dev_list_lock); list_for_each_entry(d, &hci_dev_list, list) { - if (!test_bit(HCI_UP, &d->flags) || test_bit(HCI_RAW, &d->flags)) + if (!test_bit(HCI_UP, &d->flags) || + test_bit(HCI_RAW, &d->flags) || + d->dev_type != HCI_BREDR) continue; /* Simple routing: @@ -495,6 +484,11 @@ struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, if (type == LE_LINK) { le = hci_conn_hash_lookup_ba(hdev, LE_LINK, dst); if (!le) { + le = hci_conn_hash_lookup_state(hdev, LE_LINK, + BT_CONNECT); + if (le) + return ERR_PTR(-EBUSY); + le = hci_conn_add(hdev, LE_LINK, dst); if (!le) return ERR_PTR(-ENOMEM); @@ -545,7 +539,7 @@ struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, hci_conn_hold(sco); if (acl->state == BT_CONNECTED && - (sco->state == BT_OPEN || sco->state == BT_CLOSED)) { + (sco->state == BT_OPEN || sco->state == BT_CLOSED)) { set_bit(HCI_CONN_POWER_SAVE, &acl->flags); hci_conn_enter_active_mode(acl, BT_POWER_FORCE_ACTIVE_ON); @@ -560,24 +554,22 @@ struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, return sco; } -EXPORT_SYMBOL(hci_connect); /* Check link security requirement */ int hci_conn_check_link_mode(struct hci_conn *conn) { - BT_DBG("conn %p", conn); + BT_DBG("hcon %p", conn); if (hci_conn_ssp_enabled(conn) && !(conn->link_mode & HCI_LM_ENCRYPT)) return 0; return 1; } -EXPORT_SYMBOL(hci_conn_check_link_mode); /* Authenticate remote device */ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) { - BT_DBG("conn %p", conn); + BT_DBG("hcon %p", conn); if (conn->pending_sec_level > sec_level) sec_level = conn->pending_sec_level; @@ -600,7 +592,7 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED, - sizeof(cp), &cp); + sizeof(cp), &cp); if (conn->key_type != 0xff) set_bit(HCI_CONN_REAUTH_PEND, &conn->flags); } @@ -611,21 +603,21 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) /* Encrypt the the link */ static void hci_conn_encrypt(struct hci_conn *conn) { - BT_DBG("conn %p", conn); + BT_DBG("hcon %p", conn); if (!test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) { struct hci_cp_set_conn_encrypt cp; cp.handle = cpu_to_le16(conn->handle); cp.encrypt = 0x01; hci_send_cmd(conn->hdev, HCI_OP_SET_CONN_ENCRYPT, sizeof(cp), - &cp); + &cp); } } /* Enable security */ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) { - BT_DBG("conn %p", conn); + BT_DBG("hcon %p", conn); /* For sdp we don't need the link key. */ if (sec_level == BT_SECURITY_SDP) @@ -648,8 +640,7 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) /* An unauthenticated combination key has sufficient security for security level 1 and 2. */ if (conn->key_type == HCI_LK_UNAUTH_COMBINATION && - (sec_level == BT_SECURITY_MEDIUM || - sec_level == BT_SECURITY_LOW)) + (sec_level == BT_SECURITY_MEDIUM || sec_level == BT_SECURITY_LOW)) goto encrypt; /* A combination key has always sufficient security for the security @@ -657,8 +648,7 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) is generated using maximum PIN code length (16). For pre 2.1 units. */ if (conn->key_type == HCI_LK_COMBINATION && - (sec_level != BT_SECURITY_HIGH || - conn->pin_length == 16)) + (sec_level != BT_SECURITY_HIGH || conn->pin_length == 16)) goto encrypt; auth: @@ -680,7 +670,7 @@ EXPORT_SYMBOL(hci_conn_security); /* Check secure link requirement */ int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level) { - BT_DBG("conn %p", conn); + BT_DBG("hcon %p", conn); if (sec_level != BT_SECURITY_HIGH) return 1; /* Accept if non-secure is required */ @@ -695,23 +685,22 @@ EXPORT_SYMBOL(hci_conn_check_secure); /* Change link key */ int hci_conn_change_link_key(struct hci_conn *conn) { - BT_DBG("conn %p", conn); + BT_DBG("hcon %p", conn); if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) { struct hci_cp_change_conn_link_key cp; cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(conn->hdev, HCI_OP_CHANGE_CONN_LINK_KEY, - sizeof(cp), &cp); + sizeof(cp), &cp); } return 0; } -EXPORT_SYMBOL(hci_conn_change_link_key); /* Switch role */ int hci_conn_switch_role(struct hci_conn *conn, __u8 role) { - BT_DBG("conn %p", conn); + BT_DBG("hcon %p", conn); if (!role && conn->link_mode & HCI_LM_MASTER) return 1; @@ -732,7 +721,7 @@ void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active) { struct hci_dev *hdev = conn->hdev; - BT_DBG("conn %p mode %d", conn, conn->mode); + BT_DBG("hcon %p mode %d", conn, conn->mode); if (test_bit(HCI_RAW, &hdev->flags)) return; @@ -752,7 +741,7 @@ void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active) timer: if (hdev->idle_timeout > 0) mod_timer(&conn->idle_timer, - jiffies + msecs_to_jiffies(hdev->idle_timeout)); + jiffies + msecs_to_jiffies(hdev->idle_timeout)); } /* Drop all connection on the device */ @@ -802,7 +791,7 @@ EXPORT_SYMBOL(hci_conn_put_device); int hci_get_conn_list(void __user *arg) { - register struct hci_conn *c; + struct hci_conn *c; struct hci_conn_list_req req, *cl; struct hci_conn_info *ci; struct hci_dev *hdev; @@ -906,7 +895,7 @@ struct hci_chan *hci_chan_create(struct hci_conn *conn) struct hci_dev *hdev = conn->hdev; struct hci_chan *chan; - BT_DBG("%s conn %p", hdev->name, conn); + BT_DBG("%s hcon %p", hdev->name, conn); chan = kzalloc(sizeof(struct hci_chan), GFP_KERNEL); if (!chan) @@ -925,7 +914,7 @@ int hci_chan_del(struct hci_chan *chan) struct hci_conn *conn = chan->conn; struct hci_dev *hdev = conn->hdev; - BT_DBG("%s conn %p chan %p", hdev->name, conn, chan); + BT_DBG("%s hcon %p chan %p", hdev->name, conn, chan); list_del_rcu(&chan->list); @@ -941,7 +930,7 @@ void hci_chan_list_flush(struct hci_conn *conn) { struct hci_chan *chan, *n; - BT_DBG("conn %p", conn); + BT_DBG("hcon %p", conn); list_for_each_entry_safe(chan, n, &conn->chan_list, list) hci_chan_del(chan); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 411ace8e647..d4de5db18d5 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -25,34 +25,14 @@ /* Bluetooth HCI core. */ -#include <linux/jiffies.h> -#include <linux/module.h> -#include <linux/kmod.h> - -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/poll.h> -#include <linux/fcntl.h> -#include <linux/init.h> -#include <linux/skbuff.h> -#include <linux/workqueue.h> -#include <linux/interrupt.h> -#include <linux/rfkill.h> -#include <linux/timer.h> -#include <linux/crypto.h> -#include <net/sock.h> +#include <linux/export.h> +#include <linux/idr.h> -#include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/rfkill.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> -#define AUTO_OFF_TIMEOUT 2000 - static void hci_rx_work(struct work_struct *work); static void hci_cmd_work(struct work_struct *work); static void hci_tx_work(struct work_struct *work); @@ -65,6 +45,9 @@ DEFINE_RWLOCK(hci_dev_list_lock); LIST_HEAD(hci_cb_list); DEFINE_RWLOCK(hci_cb_list_lock); +/* HCI ID Numbering */ +static DEFINE_IDA(hci_index_ida); + /* ---- HCI notifications ---- */ static void hci_notify(struct hci_dev *hdev, int event) @@ -76,7 +59,7 @@ static void hci_notify(struct hci_dev *hdev, int event) void hci_req_complete(struct hci_dev *hdev, __u16 cmd, int result) { - BT_DBG("%s command 0x%04x result 0x%2.2x", hdev->name, cmd, result); + BT_DBG("%s command 0x%4.4x result 0x%2.2x", hdev->name, cmd, result); /* If this is the init phase check if the completed command matches * the last init command, and if not just return. @@ -124,8 +107,9 @@ static void hci_req_cancel(struct hci_dev *hdev, int err) } /* Execute request and wait for completion. */ -static int __hci_request(struct hci_dev *hdev, void (*req)(struct hci_dev *hdev, unsigned long opt), - unsigned long opt, __u32 timeout) +static int __hci_request(struct hci_dev *hdev, + void (*req)(struct hci_dev *hdev, unsigned long opt), + unsigned long opt, __u32 timeout) { DECLARE_WAITQUEUE(wait, current); int err = 0; @@ -166,8 +150,9 @@ static int __hci_request(struct hci_dev *hdev, void (*req)(struct hci_dev *hdev, return err; } -static inline int hci_request(struct hci_dev *hdev, void (*req)(struct hci_dev *hdev, unsigned long opt), - unsigned long opt, __u32 timeout) +static int hci_request(struct hci_dev *hdev, + void (*req)(struct hci_dev *hdev, unsigned long opt), + unsigned long opt, __u32 timeout) { int ret; @@ -201,12 +186,6 @@ static void bredr_init(struct hci_dev *hdev) /* Mandatory initialization */ - /* Reset */ - if (!test_bit(HCI_QUIRK_NO_RESET, &hdev->quirks)) { - set_bit(HCI_RESET, &hdev->flags); - hci_send_cmd(hdev, HCI_OP_RESET, 0, NULL); - } - /* Read Local Supported Features */ hci_send_cmd(hdev, HCI_OP_READ_LOCAL_FEATURES, 0, NULL); @@ -235,7 +214,7 @@ static void bredr_init(struct hci_dev *hdev) hci_send_cmd(hdev, HCI_OP_SET_EVENT_FLT, 1, &flt_type); /* Connection accept timeout ~20 secs */ - param = cpu_to_le16(0x7d00); + param = __constant_cpu_to_le16(0x7d00); hci_send_cmd(hdev, HCI_OP_WRITE_CA_TIMEOUT, 2, ¶m); bacpy(&cp.bdaddr, BDADDR_ANY); @@ -247,9 +226,6 @@ static void amp_init(struct hci_dev *hdev) { hdev->flow_ctl_mode = HCI_FLOW_CTL_MODE_BLOCK_BASED; - /* Reset */ - hci_send_cmd(hdev, HCI_OP_RESET, 0, NULL); - /* Read Local Version */ hci_send_cmd(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL); @@ -275,6 +251,10 @@ static void hci_init_req(struct hci_dev *hdev, unsigned long opt) } skb_queue_purge(&hdev->driver_init); + /* Reset */ + if (!test_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks)) + hci_reset_req(hdev, 0); + switch (hdev->dev_type) { case HCI_BREDR: bredr_init(hdev); @@ -417,7 +397,8 @@ static void inquiry_cache_flush(struct hci_dev *hdev) INIT_LIST_HEAD(&cache->resolve); } -struct inquiry_entry *hci_inquiry_cache_lookup(struct hci_dev *hdev, bdaddr_t *bdaddr) +struct inquiry_entry *hci_inquiry_cache_lookup(struct hci_dev *hdev, + bdaddr_t *bdaddr) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *e; @@ -478,7 +459,7 @@ void hci_inquiry_cache_update_resolve(struct hci_dev *hdev, list_for_each_entry(p, &cache->resolve, list) { if (p->name_state != NAME_PENDING && - abs(p->data.rssi) >= abs(ie->data.rssi)) + abs(p->data.rssi) >= abs(ie->data.rssi)) break; pos = &p->list; } @@ -503,7 +484,7 @@ bool hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data, *ssp = true; if (ie->name_state == NAME_NEEDED && - data->rssi != ie->data.rssi) { + data->rssi != ie->data.rssi) { ie->data.rssi = data->rssi; hci_inquiry_cache_update_resolve(hdev, ie); } @@ -527,7 +508,7 @@ bool hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data, update: if (name_known && ie->name_state != NAME_KNOWN && - ie->name_state != NAME_PENDING) { + ie->name_state != NAME_PENDING) { ie->name_state = NAME_KNOWN; list_del(&ie->list); } @@ -605,8 +586,7 @@ int hci_inquiry(void __user *arg) hci_dev_lock(hdev); if (inquiry_cache_age(hdev) > INQUIRY_CACHE_AGE_MAX || - inquiry_cache_empty(hdev) || - ir.flags & IREQ_CACHE_FLUSH) { + inquiry_cache_empty(hdev) || ir.flags & IREQ_CACHE_FLUSH) { inquiry_cache_flush(hdev); do_inquiry = 1; } @@ -620,7 +600,9 @@ int hci_inquiry(void __user *arg) goto done; } - /* for unlimited number of responses we will use buffer with 255 entries */ + /* for unlimited number of responses we will use buffer with + * 255 entries + */ max_rsp = (ir.num_rsp == 0) ? 255 : ir.num_rsp; /* cache_dump can't sleep. Therefore we allocate temp buffer and then @@ -641,7 +623,7 @@ int hci_inquiry(void __user *arg) if (!copy_to_user(ptr, &ir, sizeof(ir))) { ptr += sizeof(ir); if (copy_to_user(ptr, buf, sizeof(struct inquiry_info) * - ir.num_rsp)) + ir.num_rsp)) err = -EFAULT; } else err = -EFAULT; @@ -701,12 +683,11 @@ int hci_dev_open(__u16 dev) set_bit(HCI_INIT, &hdev->flags); hdev->init_last_cmd = 0; - ret = __hci_request(hdev, hci_init_req, 0, - msecs_to_jiffies(HCI_INIT_TIMEOUT)); + ret = __hci_request(hdev, hci_init_req, 0, HCI_INIT_TIMEOUT); if (lmp_host_le_capable(hdev)) ret = __hci_request(hdev, hci_le_init_req, 0, - msecs_to_jiffies(HCI_INIT_TIMEOUT)); + HCI_INIT_TIMEOUT); clear_bit(HCI_INIT, &hdev->flags); } @@ -791,10 +772,9 @@ static int hci_dev_do_close(struct hci_dev *hdev) skb_queue_purge(&hdev->cmd_q); atomic_set(&hdev->cmd_cnt, 1); if (!test_bit(HCI_RAW, &hdev->flags) && - test_bit(HCI_QUIRK_NO_RESET, &hdev->quirks)) { + test_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks)) { set_bit(HCI_INIT, &hdev->flags); - __hci_request(hdev, hci_reset_req, 0, - msecs_to_jiffies(250)); + __hci_request(hdev, hci_reset_req, 0, HCI_CMD_TIMEOUT); clear_bit(HCI_INIT, &hdev->flags); } @@ -883,8 +863,7 @@ int hci_dev_reset(__u16 dev) hdev->acl_cnt = 0; hdev->sco_cnt = 0; hdev->le_cnt = 0; if (!test_bit(HCI_RAW, &hdev->flags)) - ret = __hci_request(hdev, hci_reset_req, 0, - msecs_to_jiffies(HCI_INIT_TIMEOUT)); + ret = __hci_request(hdev, hci_reset_req, 0, HCI_INIT_TIMEOUT); done: hci_req_unlock(hdev); @@ -924,7 +903,7 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) switch (cmd) { case HCISETAUTH: err = hci_request(hdev, hci_auth_req, dr.dev_opt, - msecs_to_jiffies(HCI_INIT_TIMEOUT)); + HCI_INIT_TIMEOUT); break; case HCISETENCRYPT: @@ -936,23 +915,23 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) if (!test_bit(HCI_AUTH, &hdev->flags)) { /* Auth must be enabled first */ err = hci_request(hdev, hci_auth_req, dr.dev_opt, - msecs_to_jiffies(HCI_INIT_TIMEOUT)); + HCI_INIT_TIMEOUT); if (err) break; } err = hci_request(hdev, hci_encrypt_req, dr.dev_opt, - msecs_to_jiffies(HCI_INIT_TIMEOUT)); + HCI_INIT_TIMEOUT); break; case HCISETSCAN: err = hci_request(hdev, hci_scan_req, dr.dev_opt, - msecs_to_jiffies(HCI_INIT_TIMEOUT)); + HCI_INIT_TIMEOUT); break; case HCISETLINKPOL: err = hci_request(hdev, hci_linkpol_req, dr.dev_opt, - msecs_to_jiffies(HCI_INIT_TIMEOUT)); + HCI_INIT_TIMEOUT); break; case HCISETLINKMODE: @@ -1102,8 +1081,7 @@ static void hci_power_on(struct work_struct *work) return; if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) - schedule_delayed_work(&hdev->power_off, - msecs_to_jiffies(AUTO_OFF_TIMEOUT)); + schedule_delayed_work(&hdev->power_off, HCI_AUTO_OFF_TIMEOUT); if (test_and_clear_bit(HCI_SETUP, &hdev->dev_flags)) mgmt_index_added(hdev); @@ -1112,7 +1090,7 @@ static void hci_power_on(struct work_struct *work) static void hci_power_off(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, - power_off.work); + power_off.work); BT_DBG("%s", hdev->name); @@ -1193,7 +1171,7 @@ struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) } static bool hci_persistent_key(struct hci_dev *hdev, struct hci_conn *conn, - u8 key_type, u8 old_key_type) + u8 key_type, u8 old_key_type) { /* Legacy key */ if (key_type < 0x03) @@ -1234,7 +1212,7 @@ struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, u8 rand[8]) list_for_each_entry(k, &hdev->long_term_keys, list) { if (k->ediv != ediv || - memcmp(rand, k->rand, sizeof(k->rand))) + memcmp(rand, k->rand, sizeof(k->rand))) continue; return k; @@ -1242,7 +1220,6 @@ struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, u8 rand[8]) return NULL; } -EXPORT_SYMBOL(hci_find_ltk); struct smp_ltk *hci_find_ltk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) @@ -1251,12 +1228,11 @@ struct smp_ltk *hci_find_ltk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, list_for_each_entry(k, &hdev->long_term_keys, list) if (addr_type == k->bdaddr_type && - bacmp(bdaddr, &k->bdaddr) == 0) + bacmp(bdaddr, &k->bdaddr) == 0) return k; return NULL; } -EXPORT_SYMBOL(hci_find_ltk_by_addr); int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, bdaddr_t *bdaddr, u8 *val, u8 type, u8 pin_len) @@ -1283,15 +1259,14 @@ int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, * combination key for legacy pairing even when there's no * previous key */ if (type == HCI_LK_CHANGED_COMBINATION && - (!conn || conn->remote_auth == 0xff) && - old_key_type == 0xff) { + (!conn || conn->remote_auth == 0xff) && old_key_type == 0xff) { type = HCI_LK_COMBINATION; if (conn) conn->key_type = type; } bacpy(&key->bdaddr, bdaddr); - memcpy(key->val, val, 16); + memcpy(key->val, val, HCI_LINK_KEY_SIZE); key->pin_len = pin_len; if (type == HCI_LK_CHANGED_COMBINATION) @@ -1383,11 +1358,19 @@ int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr) } /* HCI command timer function */ -static void hci_cmd_timer(unsigned long arg) +static void hci_cmd_timeout(unsigned long arg) { struct hci_dev *hdev = (void *) arg; - BT_ERR("%s command tx timeout", hdev->name); + if (hdev->sent_cmd) { + struct hci_command_hdr *sent = (void *) hdev->sent_cmd->data; + u16 opcode = __le16_to_cpu(sent->opcode); + + BT_ERR("%s command 0x%4.4x tx timeout", hdev->name, opcode); + } else { + BT_ERR("%s command tx timeout", hdev->name); + } + atomic_set(&hdev->cmd_cnt, 1); queue_work(hdev->workqueue, &hdev->cmd_work); } @@ -1540,6 +1523,7 @@ static void le_scan_enable_req(struct hci_dev *hdev, unsigned long opt) memset(&cp, 0, sizeof(cp)); cp.enable = 1; + cp.filter_dup = 1; hci_send_cmd(hdev, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); } @@ -1684,7 +1668,7 @@ struct hci_dev *hci_alloc_dev(void) init_waitqueue_head(&hdev->req_wait_q); - setup_timer(&hdev->cmd_timer, hci_cmd_timer, (unsigned long) hdev); + setup_timer(&hdev->cmd_timer, hci_cmd_timeout, (unsigned long) hdev); hci_init_sysfs(hdev); discovery_init(hdev); @@ -1707,41 +1691,39 @@ EXPORT_SYMBOL(hci_free_dev); /* Register HCI device */ int hci_register_dev(struct hci_dev *hdev) { - struct list_head *head, *p; int id, error; if (!hdev->open || !hdev->close) return -EINVAL; - write_lock(&hci_dev_list_lock); - /* Do not allow HCI_AMP devices to register at index 0, * so the index can be used as the AMP controller ID. */ - id = (hdev->dev_type == HCI_BREDR) ? 0 : 1; - head = &hci_dev_list; - - /* Find first available device id */ - list_for_each(p, &hci_dev_list) { - int nid = list_entry(p, struct hci_dev, list)->id; - if (nid > id) - break; - if (nid == id) - id++; - head = p; + switch (hdev->dev_type) { + case HCI_BREDR: + id = ida_simple_get(&hci_index_ida, 0, 0, GFP_KERNEL); + break; + case HCI_AMP: + id = ida_simple_get(&hci_index_ida, 1, 0, GFP_KERNEL); + break; + default: + return -EINVAL; } + if (id < 0) + return id; + sprintf(hdev->name, "hci%d", id); hdev->id = id; BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); - list_add(&hdev->list, head); - + write_lock(&hci_dev_list_lock); + list_add(&hdev->list, &hci_dev_list); write_unlock(&hci_dev_list_lock); hdev->workqueue = alloc_workqueue(hdev->name, WQ_HIGHPRI | WQ_UNBOUND | - WQ_MEM_RECLAIM, 1); + WQ_MEM_RECLAIM, 1); if (!hdev->workqueue) { error = -ENOMEM; goto err; @@ -1752,7 +1734,8 @@ int hci_register_dev(struct hci_dev *hdev) goto err_wqueue; hdev->rfkill = rfkill_alloc(hdev->name, &hdev->dev, - RFKILL_TYPE_BLUETOOTH, &hci_rfkill_ops, hdev); + RFKILL_TYPE_BLUETOOTH, &hci_rfkill_ops, + hdev); if (hdev->rfkill) { if (rfkill_register(hdev->rfkill) < 0) { rfkill_destroy(hdev->rfkill); @@ -1760,8 +1743,11 @@ int hci_register_dev(struct hci_dev *hdev) } } - set_bit(HCI_AUTO_OFF, &hdev->dev_flags); set_bit(HCI_SETUP, &hdev->dev_flags); + + if (hdev->dev_type != HCI_AMP) + set_bit(HCI_AUTO_OFF, &hdev->dev_flags); + schedule_work(&hdev->power_on); hci_notify(hdev, HCI_DEV_REG); @@ -1772,6 +1758,7 @@ int hci_register_dev(struct hci_dev *hdev) err_wqueue: destroy_workqueue(hdev->workqueue); err: + ida_simple_remove(&hci_index_ida, hdev->id); write_lock(&hci_dev_list_lock); list_del(&hdev->list); write_unlock(&hci_dev_list_lock); @@ -1783,12 +1770,14 @@ EXPORT_SYMBOL(hci_register_dev); /* Unregister HCI device */ void hci_unregister_dev(struct hci_dev *hdev) { - int i; + int i, id; BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); set_bit(HCI_UNREGISTER, &hdev->dev_flags); + id = hdev->id; + write_lock(&hci_dev_list_lock); list_del(&hdev->list); write_unlock(&hci_dev_list_lock); @@ -1799,7 +1788,7 @@ void hci_unregister_dev(struct hci_dev *hdev) kfree_skb(hdev->reassembly[i]); if (!test_bit(HCI_INIT, &hdev->flags) && - !test_bit(HCI_SETUP, &hdev->dev_flags)) { + !test_bit(HCI_SETUP, &hdev->dev_flags)) { hci_dev_lock(hdev); mgmt_index_removed(hdev); hci_dev_unlock(hdev); @@ -1829,6 +1818,8 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_dev_unlock(hdev); hci_dev_put(hdev); + + ida_simple_remove(&hci_index_ida, id); } EXPORT_SYMBOL(hci_unregister_dev); @@ -1853,7 +1844,7 @@ int hci_recv_frame(struct sk_buff *skb) { struct hci_dev *hdev = (struct hci_dev *) skb->dev; if (!hdev || (!test_bit(HCI_UP, &hdev->flags) - && !test_bit(HCI_INIT, &hdev->flags))) { + && !test_bit(HCI_INIT, &hdev->flags))) { kfree_skb(skb); return -ENXIO; } @@ -1872,7 +1863,7 @@ int hci_recv_frame(struct sk_buff *skb) EXPORT_SYMBOL(hci_recv_frame); static int hci_reassembly(struct hci_dev *hdev, int type, void *data, - int count, __u8 index) + int count, __u8 index) { int len = 0; int hlen = 0; @@ -1881,7 +1872,7 @@ static int hci_reassembly(struct hci_dev *hdev, int type, void *data, struct bt_skb_cb *scb; if ((type < HCI_ACLDATA_PKT || type > HCI_EVENT_PKT) || - index >= NUM_REASSEMBLY) + index >= NUM_REASSEMBLY) return -EILSEQ; skb = hdev->reassembly[index]; @@ -2023,7 +2014,7 @@ int hci_recv_stream_fragment(struct hci_dev *hdev, void *data, int count) type = bt_cb(skb)->pkt_type; rem = hci_reassembly(hdev, type, data, count, - STREAM_REASSEMBLY); + STREAM_REASSEMBLY); if (rem < 0) return rem; @@ -2096,7 +2087,7 @@ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, void *param) struct hci_command_hdr *hdr; struct sk_buff *skb; - BT_DBG("%s opcode 0x%x plen %d", hdev->name, opcode, plen); + BT_DBG("%s opcode 0x%4.4x plen %d", hdev->name, opcode, plen); skb = bt_skb_alloc(len, GFP_ATOMIC); if (!skb) { @@ -2138,7 +2129,7 @@ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) if (hdr->opcode != cpu_to_le16(opcode)) return NULL; - BT_DBG("%s opcode 0x%x", hdev->name, opcode); + BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); return hdev->sent_cmd->data + HCI_COMMAND_HDR_SIZE; } @@ -2157,7 +2148,7 @@ static void hci_add_acl_hdr(struct sk_buff *skb, __u16 handle, __u16 flags) } static void hci_queue_acl(struct hci_conn *conn, struct sk_buff_head *queue, - struct sk_buff *skb, __u16 flags) + struct sk_buff *skb, __u16 flags) { struct hci_dev *hdev = conn->hdev; struct sk_buff *list; @@ -2208,7 +2199,7 @@ void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags) struct hci_conn *conn = chan->conn; struct hci_dev *hdev = conn->hdev; - BT_DBG("%s chan %p flags 0x%x", hdev->name, chan, flags); + BT_DBG("%s chan %p flags 0x%4.4x", hdev->name, chan, flags); skb->dev = (void *) hdev; @@ -2216,7 +2207,6 @@ void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags) queue_work(hdev->workqueue, &hdev->tx_work); } -EXPORT_SYMBOL(hci_send_acl); /* Send SCO data */ void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb) @@ -2239,12 +2229,12 @@ void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb) skb_queue_tail(&conn->data_q, skb); queue_work(hdev->workqueue, &hdev->tx_work); } -EXPORT_SYMBOL(hci_send_sco); /* ---- HCI TX task (outgoing data) ---- */ /* HCI Connection scheduler */ -static inline struct hci_conn *hci_low_sent(struct hci_dev *hdev, __u8 type, int *quote) +static struct hci_conn *hci_low_sent(struct hci_dev *hdev, __u8 type, + int *quote) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *conn = NULL, *c; @@ -2303,7 +2293,7 @@ static inline struct hci_conn *hci_low_sent(struct hci_dev *hdev, __u8 type, int return conn; } -static inline void hci_link_tx_to(struct hci_dev *hdev, __u8 type) +static void hci_link_tx_to(struct hci_dev *hdev, __u8 type) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; @@ -2316,16 +2306,16 @@ static inline void hci_link_tx_to(struct hci_dev *hdev, __u8 type) list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && c->sent) { BT_ERR("%s killing stalled connection %s", - hdev->name, batostr(&c->dst)); - hci_acl_disconn(c, 0x13); + hdev->name, batostr(&c->dst)); + hci_acl_disconn(c, HCI_ERROR_REMOTE_USER_TERM); } } rcu_read_unlock(); } -static inline struct hci_chan *hci_chan_sent(struct hci_dev *hdev, __u8 type, - int *quote) +static struct hci_chan *hci_chan_sent(struct hci_dev *hdev, __u8 type, + int *quote) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_chan *chan = NULL; @@ -2442,7 +2432,7 @@ static void hci_prio_recalculate(struct hci_dev *hdev, __u8 type) skb->priority = HCI_PRIO_MAX - 1; BT_DBG("chan %p skb %p promoted to %d", chan, skb, - skb->priority); + skb->priority); } if (hci_conn_num(hdev, type) == num) @@ -2459,18 +2449,18 @@ static inline int __get_blocks(struct hci_dev *hdev, struct sk_buff *skb) return DIV_ROUND_UP(skb->len - HCI_ACL_HDR_SIZE, hdev->block_len); } -static inline void __check_timeout(struct hci_dev *hdev, unsigned int cnt) +static void __check_timeout(struct hci_dev *hdev, unsigned int cnt) { if (!test_bit(HCI_RAW, &hdev->flags)) { /* ACL tx timeout must be longer than maximum * link supervision timeout (40.9 seconds) */ if (!cnt && time_after(jiffies, hdev->acl_last_tx + - msecs_to_jiffies(HCI_ACL_TX_TIMEOUT))) + HCI_ACL_TX_TIMEOUT)) hci_link_tx_to(hdev, ACL_LINK); } } -static inline void hci_sched_acl_pkt(struct hci_dev *hdev) +static void hci_sched_acl_pkt(struct hci_dev *hdev) { unsigned int cnt = hdev->acl_cnt; struct hci_chan *chan; @@ -2480,11 +2470,11 @@ static inline void hci_sched_acl_pkt(struct hci_dev *hdev) __check_timeout(hdev, cnt); while (hdev->acl_cnt && - (chan = hci_chan_sent(hdev, ACL_LINK, "e))) { + (chan = hci_chan_sent(hdev, ACL_LINK, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote-- && (skb = skb_peek(&chan->data_q))) { BT_DBG("chan %p skb %p len %d priority %u", chan, skb, - skb->len, skb->priority); + skb->len, skb->priority); /* Stop if priority has changed */ if (skb->priority < priority) @@ -2508,7 +2498,7 @@ static inline void hci_sched_acl_pkt(struct hci_dev *hdev) hci_prio_recalculate(hdev, ACL_LINK); } -static inline void hci_sched_acl_blk(struct hci_dev *hdev) +static void hci_sched_acl_blk(struct hci_dev *hdev) { unsigned int cnt = hdev->block_cnt; struct hci_chan *chan; @@ -2518,13 +2508,13 @@ static inline void hci_sched_acl_blk(struct hci_dev *hdev) __check_timeout(hdev, cnt); while (hdev->block_cnt > 0 && - (chan = hci_chan_sent(hdev, ACL_LINK, "e))) { + (chan = hci_chan_sent(hdev, ACL_LINK, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote > 0 && (skb = skb_peek(&chan->data_q))) { int blocks; BT_DBG("chan %p skb %p len %d priority %u", chan, skb, - skb->len, skb->priority); + skb->len, skb->priority); /* Stop if priority has changed */ if (skb->priority < priority) @@ -2537,7 +2527,7 @@ static inline void hci_sched_acl_blk(struct hci_dev *hdev) return; hci_conn_enter_active_mode(chan->conn, - bt_cb(skb)->force_active); + bt_cb(skb)->force_active); hci_send_frame(skb); hdev->acl_last_tx = jiffies; @@ -2554,7 +2544,7 @@ static inline void hci_sched_acl_blk(struct hci_dev *hdev) hci_prio_recalculate(hdev, ACL_LINK); } -static inline void hci_sched_acl(struct hci_dev *hdev) +static void hci_sched_acl(struct hci_dev *hdev) { BT_DBG("%s", hdev->name); @@ -2573,7 +2563,7 @@ static inline void hci_sched_acl(struct hci_dev *hdev) } /* Schedule SCO */ -static inline void hci_sched_sco(struct hci_dev *hdev) +static void hci_sched_sco(struct hci_dev *hdev) { struct hci_conn *conn; struct sk_buff *skb; @@ -2596,7 +2586,7 @@ static inline void hci_sched_sco(struct hci_dev *hdev) } } -static inline void hci_sched_esco(struct hci_dev *hdev) +static void hci_sched_esco(struct hci_dev *hdev) { struct hci_conn *conn; struct sk_buff *skb; @@ -2607,7 +2597,8 @@ static inline void hci_sched_esco(struct hci_dev *hdev) if (!hci_conn_num(hdev, ESCO_LINK)) return; - while (hdev->sco_cnt && (conn = hci_low_sent(hdev, ESCO_LINK, "e))) { + while (hdev->sco_cnt && (conn = hci_low_sent(hdev, ESCO_LINK, + "e))) { while (quote-- && (skb = skb_dequeue(&conn->data_q))) { BT_DBG("skb %p len %d", skb, skb->len); hci_send_frame(skb); @@ -2619,7 +2610,7 @@ static inline void hci_sched_esco(struct hci_dev *hdev) } } -static inline void hci_sched_le(struct hci_dev *hdev) +static void hci_sched_le(struct hci_dev *hdev) { struct hci_chan *chan; struct sk_buff *skb; @@ -2634,7 +2625,7 @@ static inline void hci_sched_le(struct hci_dev *hdev) /* LE tx timeout must be longer than maximum * link supervision timeout (40.9 seconds) */ if (!hdev->le_cnt && hdev->le_pkts && - time_after(jiffies, hdev->le_last_tx + HZ * 45)) + time_after(jiffies, hdev->le_last_tx + HZ * 45)) hci_link_tx_to(hdev, LE_LINK); } @@ -2644,7 +2635,7 @@ static inline void hci_sched_le(struct hci_dev *hdev) u32 priority = (skb_peek(&chan->data_q))->priority; while (quote-- && (skb = skb_peek(&chan->data_q))) { BT_DBG("chan %p skb %p len %d priority %u", chan, skb, - skb->len, skb->priority); + skb->len, skb->priority); /* Stop if priority has changed */ if (skb->priority < priority) @@ -2676,7 +2667,7 @@ static void hci_tx_work(struct work_struct *work) struct sk_buff *skb; BT_DBG("%s acl %d sco %d le %d", hdev->name, hdev->acl_cnt, - hdev->sco_cnt, hdev->le_cnt); + hdev->sco_cnt, hdev->le_cnt); /* Schedule queues and send stuff to HCI driver */ @@ -2696,7 +2687,7 @@ static void hci_tx_work(struct work_struct *work) /* ----- HCI RX task (incoming data processing) ----- */ /* ACL data packet */ -static inline void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_acl_hdr *hdr = (void *) skb->data; struct hci_conn *conn; @@ -2708,7 +2699,8 @@ static inline void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) flags = hci_flags(handle); handle = hci_handle(handle); - BT_DBG("%s len %d handle 0x%x flags 0x%x", hdev->name, skb->len, handle, flags); + BT_DBG("%s len %d handle 0x%4.4x flags 0x%4.4x", hdev->name, skb->len, + handle, flags); hdev->stat.acl_rx++; @@ -2732,14 +2724,14 @@ static inline void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) return; } else { BT_ERR("%s ACL packet for unknown connection handle %d", - hdev->name, handle); + hdev->name, handle); } kfree_skb(skb); } /* SCO data packet */ -static inline void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_sco_hdr *hdr = (void *) skb->data; struct hci_conn *conn; @@ -2749,7 +2741,7 @@ static inline void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb) handle = __le16_to_cpu(hdr->handle); - BT_DBG("%s len %d handle 0x%x", hdev->name, skb->len, handle); + BT_DBG("%s len %d handle 0x%4.4x", hdev->name, skb->len, handle); hdev->stat.sco_rx++; @@ -2763,7 +2755,7 @@ static inline void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb) return; } else { BT_ERR("%s SCO packet for unknown connection handle %d", - hdev->name, handle); + hdev->name, handle); } kfree_skb(skb); @@ -2829,7 +2821,8 @@ static void hci_cmd_work(struct work_struct *work) struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_work); struct sk_buff *skb; - BT_DBG("%s cmd %d", hdev->name, atomic_read(&hdev->cmd_cnt)); + BT_DBG("%s cmd_cnt %d cmd queued %d", hdev->name, + atomic_read(&hdev->cmd_cnt), skb_queue_len(&hdev->cmd_q)); /* Send queued commands */ if (atomic_read(&hdev->cmd_cnt)) { @@ -2847,7 +2840,7 @@ static void hci_cmd_work(struct work_struct *work) del_timer(&hdev->cmd_timer); else mod_timer(&hdev->cmd_timer, - jiffies + msecs_to_jiffies(HCI_CMD_TIMEOUT)); + jiffies + HCI_CMD_TIMEOUT); } else { skb_queue_head(&hdev->cmd_q, skb); queue_work(hdev->workqueue, &hdev->cmd_work); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 94ad124a4ea..715d7e33fba 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -24,20 +24,7 @@ /* Bluetooth HCI event handling. */ -#include <linux/module.h> - -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/poll.h> -#include <linux/fcntl.h> -#include <linux/init.h> -#include <linux/skbuff.h> -#include <linux/interrupt.h> -#include <net/sock.h> - -#include <linux/uaccess.h> +#include <linux/export.h> #include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> @@ -49,7 +36,7 @@ static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); if (status) { hci_dev_lock(hdev); @@ -73,7 +60,7 @@ static void hci_cc_periodic_inq(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); if (status) return; @@ -85,7 +72,7 @@ static void hci_cc_exit_periodic_inq(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); if (status) return; @@ -95,7 +82,8 @@ static void hci_cc_exit_periodic_inq(struct hci_dev *hdev, struct sk_buff *skb) hci_conn_check_pending(hdev); } -static void hci_cc_remote_name_req_cancel(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_cc_remote_name_req_cancel(struct hci_dev *hdev, + struct sk_buff *skb) { BT_DBG("%s", hdev->name); } @@ -105,7 +93,7 @@ static void hci_cc_role_discovery(struct hci_dev *hdev, struct sk_buff *skb) struct hci_rp_role_discovery *rp = (void *) skb->data; struct hci_conn *conn; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return; @@ -128,7 +116,7 @@ static void hci_cc_read_link_policy(struct hci_dev *hdev, struct sk_buff *skb) struct hci_rp_read_link_policy *rp = (void *) skb->data; struct hci_conn *conn; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return; @@ -148,7 +136,7 @@ static void hci_cc_write_link_policy(struct hci_dev *hdev, struct sk_buff *skb) struct hci_conn *conn; void *sent; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return; @@ -166,11 +154,12 @@ static void hci_cc_write_link_policy(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } -static void hci_cc_read_def_link_policy(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_cc_read_def_link_policy(struct hci_dev *hdev, + struct sk_buff *skb) { struct hci_rp_read_def_link_policy *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return; @@ -178,12 +167,13 @@ static void hci_cc_read_def_link_policy(struct hci_dev *hdev, struct sk_buff *sk hdev->link_policy = __le16_to_cpu(rp->policy); } -static void hci_cc_write_def_link_policy(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_cc_write_def_link_policy(struct hci_dev *hdev, + struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); void *sent; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_DEF_LINK_POLICY); if (!sent) @@ -199,7 +189,7 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); clear_bit(HCI_RESET, &hdev->flags); @@ -217,7 +207,7 @@ static void hci_cc_write_local_name(struct hci_dev *hdev, struct sk_buff *skb) __u8 status = *((__u8 *) skb->data); void *sent; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_LOCAL_NAME); if (!sent) @@ -239,7 +229,7 @@ static void hci_cc_read_local_name(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_read_local_name *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return; @@ -253,7 +243,7 @@ static void hci_cc_write_auth_enable(struct hci_dev *hdev, struct sk_buff *skb) __u8 status = *((__u8 *) skb->data); void *sent; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_AUTH_ENABLE); if (!sent) @@ -279,7 +269,7 @@ static void hci_cc_write_encrypt_mode(struct hci_dev *hdev, struct sk_buff *skb) __u8 status = *((__u8 *) skb->data); void *sent; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_ENCRYPT_MODE); if (!sent) @@ -303,7 +293,7 @@ static void hci_cc_write_scan_enable(struct hci_dev *hdev, struct sk_buff *skb) int old_pscan, old_iscan; void *sent; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_SCAN_ENABLE); if (!sent) @@ -329,7 +319,7 @@ static void hci_cc_write_scan_enable(struct hci_dev *hdev, struct sk_buff *skb) if (hdev->discov_timeout > 0) { int to = msecs_to_jiffies(hdev->discov_timeout * 1000); queue_delayed_work(hdev->workqueue, &hdev->discov_off, - to); + to); } } else if (old_iscan) mgmt_discoverable(hdev, 0); @@ -350,7 +340,7 @@ static void hci_cc_read_class_of_dev(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_read_class_of_dev *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return; @@ -358,7 +348,7 @@ static void hci_cc_read_class_of_dev(struct hci_dev *hdev, struct sk_buff *skb) memcpy(hdev->dev_class, rp->dev_class, 3); BT_DBG("%s class 0x%.2x%.2x%.2x", hdev->name, - hdev->dev_class[2], hdev->dev_class[1], hdev->dev_class[0]); + hdev->dev_class[2], hdev->dev_class[1], hdev->dev_class[0]); } static void hci_cc_write_class_of_dev(struct hci_dev *hdev, struct sk_buff *skb) @@ -366,7 +356,7 @@ static void hci_cc_write_class_of_dev(struct hci_dev *hdev, struct sk_buff *skb) __u8 status = *((__u8 *) skb->data); void *sent; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_CLASS_OF_DEV); if (!sent) @@ -388,7 +378,7 @@ static void hci_cc_read_voice_setting(struct hci_dev *hdev, struct sk_buff *skb) struct hci_rp_read_voice_setting *rp = (void *) skb->data; __u16 setting; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return; @@ -400,19 +390,20 @@ static void hci_cc_read_voice_setting(struct hci_dev *hdev, struct sk_buff *skb) hdev->voice_setting = setting; - BT_DBG("%s voice setting 0x%04x", hdev->name, setting); + BT_DBG("%s voice setting 0x%4.4x", hdev->name, setting); if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_VOICE_SETTING); } -static void hci_cc_write_voice_setting(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_cc_write_voice_setting(struct hci_dev *hdev, + struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); __u16 setting; void *sent; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); if (status) return; @@ -428,7 +419,7 @@ static void hci_cc_write_voice_setting(struct hci_dev *hdev, struct sk_buff *skb hdev->voice_setting = setting; - BT_DBG("%s voice setting 0x%04x", hdev->name, setting); + BT_DBG("%s voice setting 0x%4.4x", hdev->name, setting); if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_VOICE_SETTING); @@ -438,7 +429,7 @@ static void hci_cc_host_buffer_size(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); hci_req_complete(hdev, HCI_OP_HOST_BUFFER_SIZE, status); } @@ -448,7 +439,7 @@ static void hci_cc_write_ssp_mode(struct hci_dev *hdev, struct sk_buff *skb) __u8 status = *((__u8 *) skb->data); void *sent; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_SSP_MODE); if (!sent) @@ -473,7 +464,7 @@ static u8 hci_get_inquiry_mode(struct hci_dev *hdev) return 1; if (hdev->manufacturer == 11 && hdev->hci_rev == 0x00 && - hdev->lmp_subver == 0x0757) + hdev->lmp_subver == 0x0757) return 1; if (hdev->manufacturer == 15) { @@ -486,7 +477,7 @@ static u8 hci_get_inquiry_mode(struct hci_dev *hdev) } if (hdev->manufacturer == 31 && hdev->hci_rev == 0x2005 && - hdev->lmp_subver == 0x1805) + hdev->lmp_subver == 0x1805) return 1; return 0; @@ -566,7 +557,7 @@ static void hci_setup(struct hci_dev *hdev) if (hdev->hci_ver > BLUETOOTH_VER_1_1) hci_send_cmd(hdev, HCI_OP_READ_LOCAL_COMMANDS, 0, NULL); - if (hdev->features[6] & LMP_SIMPLE_PAIR) { + if (lmp_ssp_capable(hdev)) { if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) { u8 mode = 0x01; hci_send_cmd(hdev, HCI_OP_WRITE_SSP_MODE, @@ -606,7 +597,7 @@ static void hci_cc_read_local_version(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_read_local_version *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) goto done; @@ -617,9 +608,8 @@ static void hci_cc_read_local_version(struct hci_dev *hdev, struct sk_buff *skb) hdev->manufacturer = __le16_to_cpu(rp->manufacturer); hdev->lmp_subver = __le16_to_cpu(rp->lmp_subver); - BT_DBG("%s manufacturer %d hci ver %d:%d", hdev->name, - hdev->manufacturer, - hdev->hci_ver, hdev->hci_rev); + BT_DBG("%s manufacturer 0x%4.4x hci ver %d:%d", hdev->name, + hdev->manufacturer, hdev->hci_ver, hdev->hci_rev); if (test_bit(HCI_INIT, &hdev->flags)) hci_setup(hdev); @@ -646,11 +636,12 @@ static void hci_setup_link_policy(struct hci_dev *hdev) hci_send_cmd(hdev, HCI_OP_WRITE_DEF_LINK_POLICY, sizeof(cp), &cp); } -static void hci_cc_read_local_commands(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_cc_read_local_commands(struct hci_dev *hdev, + struct sk_buff *skb) { struct hci_rp_read_local_commands *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) goto done; @@ -664,11 +655,12 @@ done: hci_req_complete(hdev, HCI_OP_READ_LOCAL_COMMANDS, rp->status); } -static void hci_cc_read_local_features(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_cc_read_local_features(struct hci_dev *hdev, + struct sk_buff *skb) { struct hci_rp_read_local_features *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return; @@ -713,10 +705,10 @@ static void hci_cc_read_local_features(struct hci_dev *hdev, struct sk_buff *skb hdev->esco_type |= (ESCO_2EV5 | ESCO_3EV5); BT_DBG("%s features 0x%.2x%.2x%.2x%.2x%.2x%.2x%.2x%.2x", hdev->name, - hdev->features[0], hdev->features[1], - hdev->features[2], hdev->features[3], - hdev->features[4], hdev->features[5], - hdev->features[6], hdev->features[7]); + hdev->features[0], hdev->features[1], + hdev->features[2], hdev->features[3], + hdev->features[4], hdev->features[5], + hdev->features[6], hdev->features[7]); } static void hci_set_le_support(struct hci_dev *hdev) @@ -736,11 +728,11 @@ static void hci_set_le_support(struct hci_dev *hdev) } static void hci_cc_read_local_ext_features(struct hci_dev *hdev, - struct sk_buff *skb) + struct sk_buff *skb) { struct hci_rp_read_local_ext_features *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) goto done; @@ -762,11 +754,11 @@ done: } static void hci_cc_read_flow_control_mode(struct hci_dev *hdev, - struct sk_buff *skb) + struct sk_buff *skb) { struct hci_rp_read_flow_control_mode *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return; @@ -780,7 +772,7 @@ static void hci_cc_read_buffer_size(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_read_buffer_size *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return; @@ -798,16 +790,15 @@ static void hci_cc_read_buffer_size(struct hci_dev *hdev, struct sk_buff *skb) hdev->acl_cnt = hdev->acl_pkts; hdev->sco_cnt = hdev->sco_pkts; - BT_DBG("%s acl mtu %d:%d sco mtu %d:%d", hdev->name, - hdev->acl_mtu, hdev->acl_pkts, - hdev->sco_mtu, hdev->sco_pkts); + BT_DBG("%s acl mtu %d:%d sco mtu %d:%d", hdev->name, hdev->acl_mtu, + hdev->acl_pkts, hdev->sco_mtu, hdev->sco_pkts); } static void hci_cc_read_bd_addr(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_read_bd_addr *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (!rp->status) bacpy(&hdev->bdaddr, &rp->bdaddr); @@ -816,11 +807,11 @@ static void hci_cc_read_bd_addr(struct hci_dev *hdev, struct sk_buff *skb) } static void hci_cc_read_data_block_size(struct hci_dev *hdev, - struct sk_buff *skb) + struct sk_buff *skb) { struct hci_rp_read_data_block_size *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return; @@ -832,7 +823,7 @@ static void hci_cc_read_data_block_size(struct hci_dev *hdev, hdev->block_cnt = hdev->num_blocks; BT_DBG("%s blk mtu %d cnt %d len %d", hdev->name, hdev->block_mtu, - hdev->block_cnt, hdev->block_len); + hdev->block_cnt, hdev->block_len); hci_req_complete(hdev, HCI_OP_READ_DATA_BLOCK_SIZE, rp->status); } @@ -841,17 +832,17 @@ static void hci_cc_write_ca_timeout(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); hci_req_complete(hdev, HCI_OP_WRITE_CA_TIMEOUT, status); } static void hci_cc_read_local_amp_info(struct hci_dev *hdev, - struct sk_buff *skb) + struct sk_buff *skb) { struct hci_rp_read_local_amp_info *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return; @@ -871,11 +862,11 @@ static void hci_cc_read_local_amp_info(struct hci_dev *hdev, } static void hci_cc_delete_stored_link_key(struct hci_dev *hdev, - struct sk_buff *skb) + struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); hci_req_complete(hdev, HCI_OP_DELETE_STORED_LINK_KEY, status); } @@ -884,27 +875,27 @@ static void hci_cc_set_event_mask(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); hci_req_complete(hdev, HCI_OP_SET_EVENT_MASK, status); } static void hci_cc_write_inquiry_mode(struct hci_dev *hdev, - struct sk_buff *skb) + struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); hci_req_complete(hdev, HCI_OP_WRITE_INQUIRY_MODE, status); } static void hci_cc_read_inq_rsp_tx_power(struct hci_dev *hdev, - struct sk_buff *skb) + struct sk_buff *skb) { struct hci_rp_read_inq_rsp_tx_power *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (!rp->status) hdev->inq_tx_power = rp->tx_power; @@ -916,7 +907,7 @@ static void hci_cc_set_event_flt(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); hci_req_complete(hdev, HCI_OP_SET_EVENT_FLT, status); } @@ -927,7 +918,7 @@ static void hci_cc_pin_code_reply(struct hci_dev *hdev, struct sk_buff *skb) struct hci_cp_pin_code_reply *cp; struct hci_conn *conn; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); hci_dev_lock(hdev); @@ -953,13 +944,13 @@ static void hci_cc_pin_code_neg_reply(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_pin_code_neg_reply *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); hci_dev_lock(hdev); if (test_bit(HCI_MGMT, &hdev->dev_flags)) mgmt_pin_code_neg_reply_complete(hdev, &rp->bdaddr, - rp->status); + rp->status); hci_dev_unlock(hdev); } @@ -969,7 +960,7 @@ static void hci_cc_le_read_buffer_size(struct hci_dev *hdev, { struct hci_rp_le_read_buffer_size *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return; @@ -988,7 +979,7 @@ static void hci_cc_user_confirm_reply(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_user_confirm_reply *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); hci_dev_lock(hdev); @@ -1000,11 +991,11 @@ static void hci_cc_user_confirm_reply(struct hci_dev *hdev, struct sk_buff *skb) } static void hci_cc_user_confirm_neg_reply(struct hci_dev *hdev, - struct sk_buff *skb) + struct sk_buff *skb) { struct hci_rp_user_confirm_reply *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); hci_dev_lock(hdev); @@ -1019,7 +1010,7 @@ static void hci_cc_user_passkey_reply(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_user_confirm_reply *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); hci_dev_lock(hdev); @@ -1031,11 +1022,11 @@ static void hci_cc_user_passkey_reply(struct hci_dev *hdev, struct sk_buff *skb) } static void hci_cc_user_passkey_neg_reply(struct hci_dev *hdev, - struct sk_buff *skb) + struct sk_buff *skb) { struct hci_rp_user_confirm_reply *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); hci_dev_lock(hdev); @@ -1047,11 +1038,11 @@ static void hci_cc_user_passkey_neg_reply(struct hci_dev *hdev, } static void hci_cc_read_local_oob_data_reply(struct hci_dev *hdev, - struct sk_buff *skb) + struct sk_buff *skb) { struct hci_rp_read_local_oob_data *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); hci_dev_lock(hdev); mgmt_read_local_oob_data_reply_complete(hdev, rp->hash, @@ -1063,7 +1054,7 @@ static void hci_cc_le_set_scan_param(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); hci_req_complete(hdev, HCI_OP_LE_SET_SCAN_PARAM, status); @@ -1076,12 +1067,12 @@ static void hci_cc_le_set_scan_param(struct hci_dev *hdev, struct sk_buff *skb) } static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, - struct sk_buff *skb) + struct sk_buff *skb) { struct hci_cp_le_set_scan_enable *cp; __u8 status = *((__u8 *) skb->data); - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_SCAN_ENABLE); if (!cp) @@ -1136,7 +1127,7 @@ static void hci_cc_le_ltk_reply(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_le_ltk_reply *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return; @@ -1148,7 +1139,7 @@ static void hci_cc_le_ltk_neg_reply(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_le_ltk_neg_reply *rp = (void *) skb->data; - BT_DBG("%s status 0x%x", hdev->name, rp->status); + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return; @@ -1156,13 +1147,13 @@ static void hci_cc_le_ltk_neg_reply(struct hci_dev *hdev, struct sk_buff *skb) hci_req_complete(hdev, HCI_OP_LE_LTK_NEG_REPLY, rp->status); } -static inline void hci_cc_write_le_host_supported(struct hci_dev *hdev, - struct sk_buff *skb) +static void hci_cc_write_le_host_supported(struct hci_dev *hdev, + struct sk_buff *skb) { struct hci_cp_write_le_host_supported *sent; __u8 status = *((__u8 *) skb->data); - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_LE_HOST_SUPPORTED); if (!sent) @@ -1176,15 +1167,15 @@ static inline void hci_cc_write_le_host_supported(struct hci_dev *hdev, } if (test_bit(HCI_MGMT, &hdev->dev_flags) && - !test_bit(HCI_INIT, &hdev->flags)) + !test_bit(HCI_INIT, &hdev->flags)) mgmt_le_enable_complete(hdev, sent->le, status); hci_req_complete(hdev, HCI_OP_WRITE_LE_HOST_SUPPORTED, status); } -static inline void hci_cs_inquiry(struct hci_dev *hdev, __u8 status) +static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status) { - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); if (status) { hci_req_complete(hdev, HCI_OP_INQUIRY, status); @@ -1203,12 +1194,12 @@ static inline void hci_cs_inquiry(struct hci_dev *hdev, __u8 status) hci_dev_unlock(hdev); } -static inline void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) +static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) { struct hci_cp_create_conn *cp; struct hci_conn *conn; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); cp = hci_sent_cmd_data(hdev, HCI_OP_CREATE_CONN); if (!cp) @@ -1218,7 +1209,7 @@ static inline void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->bdaddr); - BT_DBG("%s bdaddr %s conn %p", hdev->name, batostr(&cp->bdaddr), conn); + BT_DBG("%s bdaddr %s hcon %p", hdev->name, batostr(&cp->bdaddr), conn); if (status) { if (conn && conn->state == BT_CONNECT) { @@ -1249,7 +1240,7 @@ static void hci_cs_add_sco(struct hci_dev *hdev, __u8 status) struct hci_conn *acl, *sco; __u16 handle; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); if (!status) return; @@ -1260,7 +1251,7 @@ static void hci_cs_add_sco(struct hci_dev *hdev, __u8 status) handle = __le16_to_cpu(cp->handle); - BT_DBG("%s handle %d", hdev->name, handle); + BT_DBG("%s handle 0x%4.4x", hdev->name, handle); hci_dev_lock(hdev); @@ -1283,7 +1274,7 @@ static void hci_cs_auth_requested(struct hci_dev *hdev, __u8 status) struct hci_cp_auth_requested *cp; struct hci_conn *conn; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); if (!status) return; @@ -1310,7 +1301,7 @@ static void hci_cs_set_conn_encrypt(struct hci_dev *hdev, __u8 status) struct hci_cp_set_conn_encrypt *cp; struct hci_conn *conn; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); if (!status) return; @@ -1333,7 +1324,7 @@ static void hci_cs_set_conn_encrypt(struct hci_dev *hdev, __u8 status) } static int hci_outgoing_auth_needed(struct hci_dev *hdev, - struct hci_conn *conn) + struct hci_conn *conn) { if (conn->state != BT_CONFIG || !conn->out) return 0; @@ -1343,15 +1334,14 @@ static int hci_outgoing_auth_needed(struct hci_dev *hdev, /* Only request authentication for SSP connections or non-SSP * devices with sec_level HIGH or if MITM protection is requested */ - if (!hci_conn_ssp_enabled(conn) && - conn->pending_sec_level != BT_SECURITY_HIGH && - !(conn->auth_type & 0x01)) + if (!hci_conn_ssp_enabled(conn) && !(conn->auth_type & 0x01) && + conn->pending_sec_level != BT_SECURITY_HIGH) return 0; return 1; } -static inline int hci_resolve_name(struct hci_dev *hdev, +static int hci_resolve_name(struct hci_dev *hdev, struct inquiry_entry *e) { struct hci_cp_remote_name_req cp; @@ -1375,6 +1365,9 @@ static bool hci_resolve_next_name(struct hci_dev *hdev) return false; e = hci_inquiry_cache_lookup_resolve(hdev, BDADDR_ANY, NAME_NEEDED); + if (!e) + return false; + if (hci_resolve_name(hdev, e) == 0) { e->name_state = NAME_PENDING; return true; @@ -1403,12 +1396,20 @@ static void hci_check_pending_name(struct hci_dev *hdev, struct hci_conn *conn, return; e = hci_inquiry_cache_lookup_resolve(hdev, bdaddr, NAME_PENDING); - if (e) { + /* If the device was not found in a list of found devices names of which + * are pending. there is no need to continue resolving a next name as it + * will be done upon receiving another Remote Name Request Complete + * Event */ + if (!e) + return; + + list_del(&e->list); + if (name) { e->name_state = NAME_KNOWN; - list_del(&e->list); - if (name) - mgmt_remote_name(hdev, bdaddr, ACL_LINK, 0x00, - e->data.rssi, name, name_len); + mgmt_remote_name(hdev, bdaddr, ACL_LINK, 0x00, + e->data.rssi, name, name_len); + } else { + e->name_state = NAME_NOT_KNOWN; } if (hci_resolve_next_name(hdev)) @@ -1423,7 +1424,7 @@ static void hci_cs_remote_name_req(struct hci_dev *hdev, __u8 status) struct hci_cp_remote_name_req *cp; struct hci_conn *conn; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); /* If successful wait for the name req complete event before * checking for the need to do authentication */ @@ -1462,7 +1463,7 @@ static void hci_cs_read_remote_features(struct hci_dev *hdev, __u8 status) struct hci_cp_read_remote_features *cp; struct hci_conn *conn; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); if (!status) return; @@ -1489,7 +1490,7 @@ static void hci_cs_read_remote_ext_features(struct hci_dev *hdev, __u8 status) struct hci_cp_read_remote_ext_features *cp; struct hci_conn *conn; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); if (!status) return; @@ -1517,7 +1518,7 @@ static void hci_cs_setup_sync_conn(struct hci_dev *hdev, __u8 status) struct hci_conn *acl, *sco; __u16 handle; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); if (!status) return; @@ -1528,7 +1529,7 @@ static void hci_cs_setup_sync_conn(struct hci_dev *hdev, __u8 status) handle = __le16_to_cpu(cp->handle); - BT_DBG("%s handle %d", hdev->name, handle); + BT_DBG("%s handle 0x%4.4x", hdev->name, handle); hci_dev_lock(hdev); @@ -1551,7 +1552,7 @@ static void hci_cs_sniff_mode(struct hci_dev *hdev, __u8 status) struct hci_cp_sniff_mode *cp; struct hci_conn *conn; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); if (!status) return; @@ -1578,7 +1579,7 @@ static void hci_cs_exit_sniff_mode(struct hci_dev *hdev, __u8 status) struct hci_cp_exit_sniff_mode *cp; struct hci_conn *conn; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); if (!status) return; @@ -1627,7 +1628,7 @@ static void hci_cs_le_create_conn(struct hci_dev *hdev, __u8 status) struct hci_cp_le_create_conn *cp; struct hci_conn *conn; - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); cp = hci_sent_cmd_data(hdev, HCI_OP_LE_CREATE_CONN); if (!cp) @@ -1638,7 +1639,7 @@ static void hci_cs_le_create_conn(struct hci_dev *hdev, __u8 status) conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &cp->peer_addr); BT_DBG("%s bdaddr %s conn %p", hdev->name, batostr(&cp->peer_addr), - conn); + conn); if (status) { if (conn && conn->state == BT_CONNECT) { @@ -1665,16 +1666,16 @@ static void hci_cs_le_create_conn(struct hci_dev *hdev, __u8 status) static void hci_cs_le_start_enc(struct hci_dev *hdev, u8 status) { - BT_DBG("%s status 0x%x", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); } -static inline void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); struct discovery_state *discov = &hdev->discovery; struct inquiry_entry *e; - BT_DBG("%s status %d", hdev->name, status); + BT_DBG("%s status 0x%2.2x", hdev->name, status); hci_req_complete(hdev, HCI_OP_INQUIRY, status); @@ -1708,7 +1709,7 @@ unlock: hci_dev_unlock(hdev); } -static inline void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct inquiry_data data; struct inquiry_info *info = (void *) (skb->data + 1); @@ -1745,7 +1746,7 @@ static inline void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff * hci_dev_unlock(hdev); } -static inline void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_conn_complete *ev = (void *) skb->data; struct hci_conn *conn; @@ -1772,7 +1773,12 @@ static inline void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *s if (conn->type == ACL_LINK) { conn->state = BT_CONFIG; hci_conn_hold(conn); - conn->disc_timeout = HCI_DISCONN_TIMEOUT; + + if (!conn->out && !hci_conn_ssp_enabled(conn) && + !hci_find_link_key(hdev, &ev->bdaddr)) + conn->disc_timeout = HCI_PAIRING_TIMEOUT; + else + conn->disc_timeout = HCI_DISCONN_TIMEOUT; } else conn->state = BT_CONNECTED; @@ -1823,18 +1829,18 @@ unlock: hci_conn_check_pending(hdev); } -static inline void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_conn_request *ev = (void *) skb->data; int mask = hdev->link_mode; - BT_DBG("%s bdaddr %s type 0x%x", hdev->name, - batostr(&ev->bdaddr), ev->link_type); + BT_DBG("%s bdaddr %s type 0x%x", hdev->name, batostr(&ev->bdaddr), + ev->link_type); mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ev->link_type); if ((mask & HCI_LM_ACCEPT) && - !hci_blacklist_lookup(hdev, &ev->bdaddr)) { + !hci_blacklist_lookup(hdev, &ev->bdaddr)) { /* Connection accepted */ struct inquiry_entry *ie; struct hci_conn *conn; @@ -1845,7 +1851,8 @@ static inline void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *sk if (ie) memcpy(ie->data.dev_class, ev->dev_class, 3); - conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr); + conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, + &ev->bdaddr); if (!conn) { conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr); if (!conn) { @@ -1878,9 +1885,9 @@ static inline void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *sk bacpy(&cp.bdaddr, &ev->bdaddr); cp.pkt_type = cpu_to_le16(conn->pkt_type); - cp.tx_bandwidth = cpu_to_le32(0x00001f40); - cp.rx_bandwidth = cpu_to_le32(0x00001f40); - cp.max_latency = cpu_to_le16(0xffff); + cp.tx_bandwidth = __constant_cpu_to_le32(0x00001f40); + cp.rx_bandwidth = __constant_cpu_to_le32(0x00001f40); + cp.max_latency = __constant_cpu_to_le16(0xffff); cp.content_format = cpu_to_le16(hdev->voice_setting); cp.retrans_effort = 0xff; @@ -1897,12 +1904,12 @@ static inline void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *sk } } -static inline void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_disconn_complete *ev = (void *) skb->data; struct hci_conn *conn; - BT_DBG("%s status %d", hdev->name, ev->status); + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); hci_dev_lock(hdev); @@ -1914,10 +1921,10 @@ static inline void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff conn->state = BT_CLOSED; if (test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags) && - (conn->type == ACL_LINK || conn->type == LE_LINK)) { + (conn->type == ACL_LINK || conn->type == LE_LINK)) { if (ev->status != 0) mgmt_disconnect_failed(hdev, &conn->dst, conn->type, - conn->dst_type, ev->status); + conn->dst_type, ev->status); else mgmt_device_disconnected(hdev, &conn->dst, conn->type, conn->dst_type); @@ -1934,12 +1941,12 @@ unlock: hci_dev_unlock(hdev); } -static inline void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_auth_complete *ev = (void *) skb->data; struct hci_conn *conn; - BT_DBG("%s status %d", hdev->name, ev->status); + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); hci_dev_lock(hdev); @@ -1949,7 +1956,7 @@ static inline void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *s if (!ev->status) { if (!hci_conn_ssp_enabled(conn) && - test_bit(HCI_CONN_REAUTH_PEND, &conn->flags)) { + test_bit(HCI_CONN_REAUTH_PEND, &conn->flags)) { BT_INFO("re-auth of legacy device is not possible."); } else { conn->link_mode |= HCI_LM_AUTH; @@ -1969,7 +1976,7 @@ static inline void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *s cp.handle = ev->handle; cp.encrypt = 0x01; hci_send_cmd(hdev, HCI_OP_SET_CONN_ENCRYPT, sizeof(cp), - &cp); + &cp); } else { conn->state = BT_CONNECTED; hci_proto_connect_cfm(conn, ev->status); @@ -1989,7 +1996,7 @@ static inline void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *s cp.handle = ev->handle; cp.encrypt = 0x01; hci_send_cmd(hdev, HCI_OP_SET_CONN_ENCRYPT, sizeof(cp), - &cp); + &cp); } else { clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); hci_encrypt_cfm(conn, ev->status, 0x00); @@ -2000,7 +2007,7 @@ unlock: hci_dev_unlock(hdev); } -static inline void hci_remote_name_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_remote_name_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_remote_name *ev = (void *) skb->data; struct hci_conn *conn; @@ -2039,12 +2046,12 @@ unlock: hci_dev_unlock(hdev); } -static inline void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_encrypt_change *ev = (void *) skb->data; struct hci_conn *conn; - BT_DBG("%s status %d", hdev->name, ev->status); + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); hci_dev_lock(hdev); @@ -2082,12 +2089,13 @@ unlock: hci_dev_unlock(hdev); } -static inline void hci_change_link_key_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_change_link_key_complete_evt(struct hci_dev *hdev, + struct sk_buff *skb) { struct hci_ev_change_link_key_complete *ev = (void *) skb->data; struct hci_conn *conn; - BT_DBG("%s status %d", hdev->name, ev->status); + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); hci_dev_lock(hdev); @@ -2104,12 +2112,13 @@ static inline void hci_change_link_key_complete_evt(struct hci_dev *hdev, struct hci_dev_unlock(hdev); } -static inline void hci_remote_features_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_remote_features_evt(struct hci_dev *hdev, + struct sk_buff *skb) { struct hci_ev_remote_features *ev = (void *) skb->data; struct hci_conn *conn; - BT_DBG("%s status %d", hdev->name, ev->status); + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); hci_dev_lock(hdev); @@ -2128,7 +2137,7 @@ static inline void hci_remote_features_evt(struct hci_dev *hdev, struct sk_buff cp.handle = ev->handle; cp.page = 0x01; hci_send_cmd(hdev, HCI_OP_READ_REMOTE_EXT_FEATURES, - sizeof(cp), &cp); + sizeof(cp), &cp); goto unlock; } @@ -2153,17 +2162,18 @@ unlock: hci_dev_unlock(hdev); } -static inline void hci_remote_version_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_remote_version_evt(struct hci_dev *hdev, struct sk_buff *skb) { BT_DBG("%s", hdev->name); } -static inline void hci_qos_setup_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_qos_setup_complete_evt(struct hci_dev *hdev, + struct sk_buff *skb) { BT_DBG("%s", hdev->name); } -static inline void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_cmd_complete *ev = (void *) skb->data; __u16 opcode; @@ -2370,7 +2380,7 @@ static inline void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *sk break; default: - BT_DBG("%s opcode 0x%x", hdev->name, opcode); + BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); break; } @@ -2384,7 +2394,7 @@ static inline void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *sk } } -static inline void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_cmd_status *ev = (void *) skb->data; __u16 opcode; @@ -2451,7 +2461,7 @@ static inline void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb) break; default: - BT_DBG("%s opcode 0x%x", hdev->name, opcode); + BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); break; } @@ -2465,12 +2475,12 @@ static inline void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb) } } -static inline void hci_role_change_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_role_change_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_role_change *ev = (void *) skb->data; struct hci_conn *conn; - BT_DBG("%s status %d", hdev->name, ev->status); + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); hci_dev_lock(hdev); @@ -2491,7 +2501,7 @@ static inline void hci_role_change_evt(struct hci_dev *hdev, struct sk_buff *skb hci_dev_unlock(hdev); } -static inline void hci_num_comp_pkts_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_num_comp_pkts_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_num_comp_pkts *ev = (void *) skb->data; int i; @@ -2502,7 +2512,7 @@ static inline void hci_num_comp_pkts_evt(struct hci_dev *hdev, struct sk_buff *s } if (skb->len < sizeof(*ev) || skb->len < sizeof(*ev) + - ev->num_hndl * sizeof(struct hci_comp_pkts_info)) { + ev->num_hndl * sizeof(struct hci_comp_pkts_info)) { BT_DBG("%s bad parameters", hdev->name); return; } @@ -2557,8 +2567,7 @@ static inline void hci_num_comp_pkts_evt(struct hci_dev *hdev, struct sk_buff *s queue_work(hdev->workqueue, &hdev->tx_work); } -static inline void hci_num_comp_blocks_evt(struct hci_dev *hdev, - struct sk_buff *skb) +static void hci_num_comp_blocks_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_num_comp_blocks *ev = (void *) skb->data; int i; @@ -2569,13 +2578,13 @@ static inline void hci_num_comp_blocks_evt(struct hci_dev *hdev, } if (skb->len < sizeof(*ev) || skb->len < sizeof(*ev) + - ev->num_hndl * sizeof(struct hci_comp_blocks_info)) { + ev->num_hndl * sizeof(struct hci_comp_blocks_info)) { BT_DBG("%s bad parameters", hdev->name); return; } BT_DBG("%s num_blocks %d num_hndl %d", hdev->name, ev->num_blocks, - ev->num_hndl); + ev->num_hndl); for (i = 0; i < ev->num_hndl; i++) { struct hci_comp_blocks_info *info = &ev->handles[i]; @@ -2607,12 +2616,12 @@ static inline void hci_num_comp_blocks_evt(struct hci_dev *hdev, queue_work(hdev->workqueue, &hdev->tx_work); } -static inline void hci_mode_change_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_mode_change_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_mode_change *ev = (void *) skb->data; struct hci_conn *conn; - BT_DBG("%s status %d", hdev->name, ev->status); + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); hci_dev_lock(hdev); @@ -2621,7 +2630,8 @@ static inline void hci_mode_change_evt(struct hci_dev *hdev, struct sk_buff *skb conn->mode = ev->mode; conn->interval = __le16_to_cpu(ev->interval); - if (!test_and_clear_bit(HCI_CONN_MODE_CHANGE_PEND, &conn->flags)) { + if (!test_and_clear_bit(HCI_CONN_MODE_CHANGE_PEND, + &conn->flags)) { if (conn->mode == HCI_CM_ACTIVE) set_bit(HCI_CONN_POWER_SAVE, &conn->flags); else @@ -2635,7 +2645,7 @@ static inline void hci_mode_change_evt(struct hci_dev *hdev, struct sk_buff *skb hci_dev_unlock(hdev); } -static inline void hci_pin_code_request_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_pin_code_request_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_pin_code_req *ev = (void *) skb->data; struct hci_conn *conn; @@ -2656,7 +2666,7 @@ static inline void hci_pin_code_request_evt(struct hci_dev *hdev, struct sk_buff if (!test_bit(HCI_PAIRABLE, &hdev->dev_flags)) hci_send_cmd(hdev, HCI_OP_PIN_CODE_NEG_REPLY, - sizeof(ev->bdaddr), &ev->bdaddr); + sizeof(ev->bdaddr), &ev->bdaddr); else if (test_bit(HCI_MGMT, &hdev->dev_flags)) { u8 secure; @@ -2672,7 +2682,7 @@ unlock: hci_dev_unlock(hdev); } -static inline void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_link_key_req *ev = (void *) skb->data; struct hci_cp_link_key_reply cp; @@ -2689,15 +2699,15 @@ static inline void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff key = hci_find_link_key(hdev, &ev->bdaddr); if (!key) { BT_DBG("%s link key not found for %s", hdev->name, - batostr(&ev->bdaddr)); + batostr(&ev->bdaddr)); goto not_found; } BT_DBG("%s found key type %u for %s", hdev->name, key->type, - batostr(&ev->bdaddr)); + batostr(&ev->bdaddr)); if (!test_bit(HCI_DEBUG_KEYS, &hdev->dev_flags) && - key->type == HCI_LK_DEBUG_COMBINATION) { + key->type == HCI_LK_DEBUG_COMBINATION) { BT_DBG("%s ignoring debug key", hdev->name); goto not_found; } @@ -2705,16 +2715,15 @@ static inline void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (conn) { if (key->type == HCI_LK_UNAUTH_COMBINATION && - conn->auth_type != 0xff && - (conn->auth_type & 0x01)) { + conn->auth_type != 0xff && (conn->auth_type & 0x01)) { BT_DBG("%s ignoring unauthenticated key", hdev->name); goto not_found; } if (key->type == HCI_LK_COMBINATION && key->pin_len < 16 && - conn->pending_sec_level == BT_SECURITY_HIGH) { - BT_DBG("%s ignoring key unauthenticated for high \ - security", hdev->name); + conn->pending_sec_level == BT_SECURITY_HIGH) { + BT_DBG("%s ignoring key unauthenticated for high security", + hdev->name); goto not_found; } @@ -2723,7 +2732,7 @@ static inline void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff } bacpy(&cp.bdaddr, &ev->bdaddr); - memcpy(cp.link_key, key->val, 16); + memcpy(cp.link_key, key->val, HCI_LINK_KEY_SIZE); hci_send_cmd(hdev, HCI_OP_LINK_KEY_REPLY, sizeof(cp), &cp); @@ -2736,7 +2745,7 @@ not_found: hci_dev_unlock(hdev); } -static inline void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_link_key_notify *ev = (void *) skb->data; struct hci_conn *conn; @@ -2760,17 +2769,17 @@ static inline void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff if (test_bit(HCI_LINK_KEYS, &hdev->dev_flags)) hci_add_link_key(hdev, conn, 1, &ev->bdaddr, ev->link_key, - ev->key_type, pin_len); + ev->key_type, pin_len); hci_dev_unlock(hdev); } -static inline void hci_clock_offset_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_clock_offset_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_clock_offset *ev = (void *) skb->data; struct hci_conn *conn; - BT_DBG("%s status %d", hdev->name, ev->status); + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); hci_dev_lock(hdev); @@ -2788,12 +2797,12 @@ static inline void hci_clock_offset_evt(struct hci_dev *hdev, struct sk_buff *sk hci_dev_unlock(hdev); } -static inline void hci_pkt_type_change_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_pkt_type_change_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_pkt_type_change *ev = (void *) skb->data; struct hci_conn *conn; - BT_DBG("%s status %d", hdev->name, ev->status); + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); hci_dev_lock(hdev); @@ -2804,7 +2813,7 @@ static inline void hci_pkt_type_change_evt(struct hci_dev *hdev, struct sk_buff hci_dev_unlock(hdev); } -static inline void hci_pscan_rep_mode_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_pscan_rep_mode_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_pscan_rep_mode *ev = (void *) skb->data; struct inquiry_entry *ie; @@ -2822,7 +2831,8 @@ static inline void hci_pscan_rep_mode_evt(struct hci_dev *hdev, struct sk_buff * hci_dev_unlock(hdev); } -static inline void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, + struct sk_buff *skb) { struct inquiry_data data; int num_rsp = *((__u8 *) skb->data); @@ -2881,7 +2891,8 @@ static inline void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, struct hci_dev_unlock(hdev); } -static inline void hci_remote_ext_features_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_remote_ext_features_evt(struct hci_dev *hdev, + struct sk_buff *skb) { struct hci_ev_remote_ext_features *ev = (void *) skb->data; struct hci_conn *conn; @@ -2929,12 +2940,13 @@ unlock: hci_dev_unlock(hdev); } -static inline void hci_sync_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_sync_conn_complete_evt(struct hci_dev *hdev, + struct sk_buff *skb) { struct hci_ev_sync_conn_complete *ev = (void *) skb->data; struct hci_conn *conn; - BT_DBG("%s status %d", hdev->name, ev->status); + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); hci_dev_lock(hdev); @@ -2984,19 +2996,20 @@ unlock: hci_dev_unlock(hdev); } -static inline void hci_sync_conn_changed_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_sync_conn_changed_evt(struct hci_dev *hdev, struct sk_buff *skb) { BT_DBG("%s", hdev->name); } -static inline void hci_sniff_subrate_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_sniff_subrate_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_sniff_subrate *ev = (void *) skb->data; - BT_DBG("%s status %d", hdev->name, ev->status); + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); } -static inline void hci_extended_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_extended_inquiry_result_evt(struct hci_dev *hdev, + struct sk_buff *skb) { struct inquiry_data data; struct extended_inquiry_info *info = (void *) (skb->data + 1); @@ -3049,7 +3062,7 @@ static void hci_key_refresh_complete_evt(struct hci_dev *hdev, struct hci_ev_key_refresh_complete *ev = (void *) skb->data; struct hci_conn *conn; - BT_DBG("%s status %u handle %u", hdev->name, ev->status, + BT_DBG("%s status 0x%2.2x handle 0x%4.4x", hdev->name, ev->status, __le16_to_cpu(ev->handle)); hci_dev_lock(hdev); @@ -3087,7 +3100,7 @@ unlock: hci_dev_unlock(hdev); } -static inline u8 hci_get_auth_req(struct hci_conn *conn) +static u8 hci_get_auth_req(struct hci_conn *conn) { /* If remote requests dedicated bonding follow that lead */ if (conn->remote_auth == 0x02 || conn->remote_auth == 0x03) { @@ -3106,7 +3119,7 @@ static inline u8 hci_get_auth_req(struct hci_conn *conn) return conn->auth_type; } -static inline void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_io_capa_request *ev = (void *) skb->data; struct hci_conn *conn; @@ -3125,7 +3138,7 @@ static inline void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff goto unlock; if (test_bit(HCI_PAIRABLE, &hdev->dev_flags) || - (conn->remote_auth & ~0x01) == HCI_AT_NO_BONDING) { + (conn->remote_auth & ~0x01) == HCI_AT_NO_BONDING) { struct hci_cp_io_capability_reply cp; bacpy(&cp.bdaddr, &ev->bdaddr); @@ -3136,14 +3149,14 @@ static inline void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff conn->auth_type = hci_get_auth_req(conn); cp.authentication = conn->auth_type; - if ((conn->out || test_bit(HCI_CONN_REMOTE_OOB, &conn->flags)) && - hci_find_remote_oob_data(hdev, &conn->dst)) + if (hci_find_remote_oob_data(hdev, &conn->dst) && + (conn->out || test_bit(HCI_CONN_REMOTE_OOB, &conn->flags))) cp.oob_data = 0x01; else cp.oob_data = 0x00; hci_send_cmd(hdev, HCI_OP_IO_CAPABILITY_REPLY, - sizeof(cp), &cp); + sizeof(cp), &cp); } else { struct hci_cp_io_capability_neg_reply cp; @@ -3151,14 +3164,14 @@ static inline void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff cp.reason = HCI_ERROR_PAIRING_NOT_ALLOWED; hci_send_cmd(hdev, HCI_OP_IO_CAPABILITY_NEG_REPLY, - sizeof(cp), &cp); + sizeof(cp), &cp); } unlock: hci_dev_unlock(hdev); } -static inline void hci_io_capa_reply_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_io_capa_reply_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_io_capa_reply *ev = (void *) skb->data; struct hci_conn *conn; @@ -3180,8 +3193,8 @@ unlock: hci_dev_unlock(hdev); } -static inline void hci_user_confirm_request_evt(struct hci_dev *hdev, - struct sk_buff *skb) +static void hci_user_confirm_request_evt(struct hci_dev *hdev, + struct sk_buff *skb) { struct hci_ev_user_confirm_req *ev = (void *) skb->data; int loc_mitm, rem_mitm, confirm_hint = 0; @@ -3209,13 +3222,13 @@ static inline void hci_user_confirm_request_evt(struct hci_dev *hdev, if (!conn->connect_cfm_cb && loc_mitm && conn->remote_cap == 0x03) { BT_DBG("Rejecting request: remote device can't provide MITM"); hci_send_cmd(hdev, HCI_OP_USER_CONFIRM_NEG_REPLY, - sizeof(ev->bdaddr), &ev->bdaddr); + sizeof(ev->bdaddr), &ev->bdaddr); goto unlock; } /* If no side requires MITM protection; auto-accept */ if ((!loc_mitm || conn->remote_cap == 0x03) && - (!rem_mitm || conn->io_capability == 0x03)) { + (!rem_mitm || conn->io_capability == 0x03)) { /* If we're not the initiators request authorization to * proceed from user space (mgmt_user_confirm with @@ -3227,7 +3240,7 @@ static inline void hci_user_confirm_request_evt(struct hci_dev *hdev, } BT_DBG("Auto-accept of user confirmation with %ums delay", - hdev->auto_accept_delay); + hdev->auto_accept_delay); if (hdev->auto_accept_delay > 0) { int delay = msecs_to_jiffies(hdev->auto_accept_delay); @@ -3236,7 +3249,7 @@ static inline void hci_user_confirm_request_evt(struct hci_dev *hdev, } hci_send_cmd(hdev, HCI_OP_USER_CONFIRM_REPLY, - sizeof(ev->bdaddr), &ev->bdaddr); + sizeof(ev->bdaddr), &ev->bdaddr); goto unlock; } @@ -3248,8 +3261,8 @@ unlock: hci_dev_unlock(hdev); } -static inline void hci_user_passkey_request_evt(struct hci_dev *hdev, - struct sk_buff *skb) +static void hci_user_passkey_request_evt(struct hci_dev *hdev, + struct sk_buff *skb) { struct hci_ev_user_passkey_req *ev = (void *) skb->data; @@ -3263,7 +3276,8 @@ static inline void hci_user_passkey_request_evt(struct hci_dev *hdev, hci_dev_unlock(hdev); } -static inline void hci_simple_pair_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_simple_pair_complete_evt(struct hci_dev *hdev, + struct sk_buff *skb) { struct hci_ev_simple_pair_complete *ev = (void *) skb->data; struct hci_conn *conn; @@ -3291,7 +3305,8 @@ unlock: hci_dev_unlock(hdev); } -static inline void hci_remote_host_features_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_remote_host_features_evt(struct hci_dev *hdev, + struct sk_buff *skb) { struct hci_ev_remote_host_features *ev = (void *) skb->data; struct inquiry_entry *ie; @@ -3307,8 +3322,8 @@ static inline void hci_remote_host_features_evt(struct hci_dev *hdev, struct sk_ hci_dev_unlock(hdev); } -static inline void hci_remote_oob_data_request_evt(struct hci_dev *hdev, - struct sk_buff *skb) +static void hci_remote_oob_data_request_evt(struct hci_dev *hdev, + struct sk_buff *skb) { struct hci_ev_remote_oob_data_request *ev = (void *) skb->data; struct oob_data *data; @@ -3329,28 +3344,41 @@ static inline void hci_remote_oob_data_request_evt(struct hci_dev *hdev, memcpy(cp.randomizer, data->randomizer, sizeof(cp.randomizer)); hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_REPLY, sizeof(cp), - &cp); + &cp); } else { struct hci_cp_remote_oob_data_neg_reply cp; bacpy(&cp.bdaddr, &ev->bdaddr); hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_NEG_REPLY, sizeof(cp), - &cp); + &cp); } unlock: hci_dev_unlock(hdev); } -static inline void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_le_conn_complete *ev = (void *) skb->data; struct hci_conn *conn; - BT_DBG("%s status %d", hdev->name, ev->status); + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); hci_dev_lock(hdev); + if (ev->status) { + conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT); + if (!conn) + goto unlock; + + mgmt_connect_failed(hdev, &conn->dst, conn->type, + conn->dst_type, ev->status); + hci_proto_connect_cfm(conn, ev->status); + conn->state = BT_CLOSED; + hci_conn_del(conn); + goto unlock; + } + conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &ev->bdaddr); if (!conn) { conn = hci_conn_add(hdev, LE_LINK, &ev->bdaddr); @@ -3363,15 +3391,6 @@ static inline void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff conn->dst_type = ev->bdaddr_type; } - if (ev->status) { - mgmt_connect_failed(hdev, &ev->bdaddr, conn->type, - conn->dst_type, ev->status); - hci_proto_connect_cfm(conn, ev->status); - conn->state = BT_CLOSED; - hci_conn_del(conn); - goto unlock; - } - if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) mgmt_device_connected(hdev, &ev->bdaddr, conn->type, conn->dst_type, 0, NULL, 0, NULL); @@ -3389,8 +3408,7 @@ unlock: hci_dev_unlock(hdev); } -static inline void hci_le_adv_report_evt(struct hci_dev *hdev, - struct sk_buff *skb) +static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) { u8 num_reports = skb->data[0]; void *ptr = &skb->data[1]; @@ -3411,8 +3429,7 @@ static inline void hci_le_adv_report_evt(struct hci_dev *hdev, hci_dev_unlock(hdev); } -static inline void hci_le_ltk_request_evt(struct hci_dev *hdev, - struct sk_buff *skb) +static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_le_ltk_req *ev = (void *) skb->data; struct hci_cp_le_ltk_reply cp; @@ -3420,7 +3437,7 @@ static inline void hci_le_ltk_request_evt(struct hci_dev *hdev, struct hci_conn *conn; struct smp_ltk *ltk; - BT_DBG("%s handle %d", hdev->name, __le16_to_cpu(ev->handle)); + BT_DBG("%s handle 0x%4.4x", hdev->name, __le16_to_cpu(ev->handle)); hci_dev_lock(hdev); @@ -3455,7 +3472,7 @@ not_found: hci_dev_unlock(hdev); } -static inline void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_le_meta *le_ev = (void *) skb->data; @@ -3644,7 +3661,7 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) break; default: - BT_DBG("%s event 0x%x", hdev->name, event); + BT_DBG("%s event 0x%2.2x", hdev->name, event); break; } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 5914623f426..19fdac78e55 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -24,25 +24,7 @@ /* Bluetooth HCI sockets. */ -#include <linux/module.h> - -#include <linux/types.h> -#include <linux/capability.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/poll.h> -#include <linux/fcntl.h> -#include <linux/init.h> -#include <linux/skbuff.h> -#include <linux/workqueue.h> -#include <linux/interrupt.h> -#include <linux/compat.h> -#include <linux/socket.h> -#include <linux/ioctl.h> -#include <net/sock.h> - -#include <linux/uaccess.h> +#include <linux/export.h> #include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> @@ -113,11 +95,12 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb) flt = &hci_pi(sk)->filter; if (!test_bit((bt_cb(skb)->pkt_type == HCI_VENDOR_PKT) ? - 0 : (bt_cb(skb)->pkt_type & HCI_FLT_TYPE_BITS), &flt->type_mask)) + 0 : (bt_cb(skb)->pkt_type & HCI_FLT_TYPE_BITS), + &flt->type_mask)) continue; if (bt_cb(skb)->pkt_type == HCI_EVENT_PKT) { - register int evt = (*(__u8 *)skb->data & HCI_FLT_EVENT_BITS); + int evt = (*(__u8 *)skb->data & HCI_FLT_EVENT_BITS); if (!hci_test_bit(evt, &flt->event_mask)) continue; @@ -240,7 +223,8 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) struct hci_mon_hdr *hdr; /* Create a private copy with headroom */ - skb_copy = __pskb_copy(skb, HCI_MON_HDR_SIZE, GFP_ATOMIC); + skb_copy = __pskb_copy(skb, HCI_MON_HDR_SIZE, + GFP_ATOMIC); if (!skb_copy) continue; @@ -495,7 +479,8 @@ static int hci_sock_blacklist_del(struct hci_dev *hdev, void __user *arg) } /* Ioctls that require bound socket */ -static inline int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) +static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, + unsigned long arg) { struct hci_dev *hdev = hci_pi(sk)->hdev; @@ -540,7 +525,8 @@ static inline int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, unsign } } -static int hci_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +static int hci_sock_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg) { struct sock *sk = sock->sk; void __user *argp = (void __user *) arg; @@ -601,7 +587,8 @@ static int hci_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long a } } -static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) +static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, + int addr_len) { struct sockaddr_hci haddr; struct sock *sk = sock->sk; @@ -690,7 +677,8 @@ done: return err; } -static int hci_sock_getname(struct socket *sock, struct sockaddr *addr, int *addr_len, int peer) +static int hci_sock_getname(struct socket *sock, struct sockaddr *addr, + int *addr_len, int peer) { struct sockaddr_hci *haddr = (struct sockaddr_hci *) addr; struct sock *sk = sock->sk; @@ -706,18 +694,21 @@ static int hci_sock_getname(struct socket *sock, struct sockaddr *addr, int *add *addr_len = sizeof(*haddr); haddr->hci_family = AF_BLUETOOTH; haddr->hci_dev = hdev->id; + haddr->hci_channel= 0; release_sock(sk); return 0; } -static inline void hci_sock_cmsg(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) +static void hci_sock_cmsg(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) { __u32 mask = hci_pi(sk)->cmsg_mask; if (mask & HCI_CMSG_DIR) { int incoming = bt_cb(skb)->incoming; - put_cmsg(msg, SOL_HCI, HCI_CMSG_DIR, sizeof(incoming), &incoming); + put_cmsg(msg, SOL_HCI, HCI_CMSG_DIR, sizeof(incoming), + &incoming); } if (mask & HCI_CMSG_TSTAMP) { @@ -747,7 +738,7 @@ static inline void hci_sock_cmsg(struct sock *sk, struct msghdr *msg, struct sk_ } static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags) + struct msghdr *msg, size_t len, int flags) { int noblock = flags & MSG_DONTWAIT; struct sock *sk = sock->sk; @@ -857,8 +848,9 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock, u16 ocf = hci_opcode_ocf(opcode); if (((ogf > HCI_SFLT_MAX_OGF) || - !hci_test_bit(ocf & HCI_FLT_OCF_BITS, &hci_sec_filter.ocf_mask[ogf])) && - !capable(CAP_NET_RAW)) { + !hci_test_bit(ocf & HCI_FLT_OCF_BITS, + &hci_sec_filter.ocf_mask[ogf])) && + !capable(CAP_NET_RAW)) { err = -EPERM; goto drop; } @@ -891,7 +883,8 @@ drop: goto done; } -static int hci_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int len) +static int hci_sock_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, unsigned int len) { struct hci_ufilter uf = { .opcode = 0 }; struct sock *sk = sock->sk; @@ -973,7 +966,8 @@ done: return err; } -static int hci_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) +static int hci_sock_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) { struct hci_ufilter uf; struct sock *sk = sock->sk; @@ -1016,6 +1010,7 @@ static int hci_sock_getsockopt(struct socket *sock, int level, int optname, char { struct hci_filter *f = &hci_pi(sk)->filter; + memset(&uf, 0, sizeof(uf)); uf.type_mask = f->type_mask; uf.opcode = f->opcode; uf.event_mask[0] = *((u32 *) f->event_mask + 0); diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 937f3187eaf..a20e61c3653 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -1,10 +1,6 @@ /* Bluetooth HCI driver model support. */ -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/init.h> #include <linux/debugfs.h> -#include <linux/seq_file.h> #include <linux/module.h> #include <net/bluetooth/bluetooth.h> @@ -31,27 +27,30 @@ static inline char *link_typetostr(int type) } } -static ssize_t show_link_type(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_link_type(struct device *dev, + struct device_attribute *attr, char *buf) { struct hci_conn *conn = to_hci_conn(dev); return sprintf(buf, "%s\n", link_typetostr(conn->type)); } -static ssize_t show_link_address(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_link_address(struct device *dev, + struct device_attribute *attr, char *buf) { struct hci_conn *conn = to_hci_conn(dev); return sprintf(buf, "%s\n", batostr(&conn->dst)); } -static ssize_t show_link_features(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_link_features(struct device *dev, + struct device_attribute *attr, char *buf) { struct hci_conn *conn = to_hci_conn(dev); return sprintf(buf, "0x%02x%02x%02x%02x%02x%02x%02x%02x\n", - conn->features[0], conn->features[1], - conn->features[2], conn->features[3], - conn->features[4], conn->features[5], - conn->features[6], conn->features[7]); + conn->features[0], conn->features[1], + conn->features[2], conn->features[3], + conn->features[4], conn->features[5], + conn->features[6], conn->features[7]); } #define LINK_ATTR(_name, _mode, _show, _store) \ @@ -185,19 +184,22 @@ static inline char *host_typetostr(int type) } } -static ssize_t show_bus(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_bus(struct device *dev, + struct device_attribute *attr, char *buf) { struct hci_dev *hdev = to_hci_dev(dev); return sprintf(buf, "%s\n", host_bustostr(hdev->bus)); } -static ssize_t show_type(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_type(struct device *dev, + struct device_attribute *attr, char *buf) { struct hci_dev *hdev = to_hci_dev(dev); return sprintf(buf, "%s\n", host_typetostr(hdev->dev_type)); } -static ssize_t show_name(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_name(struct device *dev, + struct device_attribute *attr, char *buf) { struct hci_dev *hdev = to_hci_dev(dev); char name[HCI_MAX_NAME_LENGTH + 1]; @@ -210,55 +212,64 @@ static ssize_t show_name(struct device *dev, struct device_attribute *attr, char return sprintf(buf, "%s\n", name); } -static ssize_t show_class(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_class(struct device *dev, + struct device_attribute *attr, char *buf) { struct hci_dev *hdev = to_hci_dev(dev); - return sprintf(buf, "0x%.2x%.2x%.2x\n", - hdev->dev_class[2], hdev->dev_class[1], hdev->dev_class[0]); + return sprintf(buf, "0x%.2x%.2x%.2x\n", hdev->dev_class[2], + hdev->dev_class[1], hdev->dev_class[0]); } -static ssize_t show_address(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_address(struct device *dev, + struct device_attribute *attr, char *buf) { struct hci_dev *hdev = to_hci_dev(dev); return sprintf(buf, "%s\n", batostr(&hdev->bdaddr)); } -static ssize_t show_features(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_features(struct device *dev, + struct device_attribute *attr, char *buf) { struct hci_dev *hdev = to_hci_dev(dev); return sprintf(buf, "0x%02x%02x%02x%02x%02x%02x%02x%02x\n", - hdev->features[0], hdev->features[1], - hdev->features[2], hdev->features[3], - hdev->features[4], hdev->features[5], - hdev->features[6], hdev->features[7]); + hdev->features[0], hdev->features[1], + hdev->features[2], hdev->features[3], + hdev->features[4], hdev->features[5], + hdev->features[6], hdev->features[7]); } -static ssize_t show_manufacturer(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_manufacturer(struct device *dev, + struct device_attribute *attr, char *buf) { struct hci_dev *hdev = to_hci_dev(dev); return sprintf(buf, "%d\n", hdev->manufacturer); } -static ssize_t show_hci_version(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_hci_version(struct device *dev, + struct device_attribute *attr, char *buf) { struct hci_dev *hdev = to_hci_dev(dev); return sprintf(buf, "%d\n", hdev->hci_ver); } -static ssize_t show_hci_revision(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_hci_revision(struct device *dev, + struct device_attribute *attr, char *buf) { struct hci_dev *hdev = to_hci_dev(dev); return sprintf(buf, "%d\n", hdev->hci_rev); } -static ssize_t show_idle_timeout(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_idle_timeout(struct device *dev, + struct device_attribute *attr, char *buf) { struct hci_dev *hdev = to_hci_dev(dev); return sprintf(buf, "%d\n", hdev->idle_timeout); } -static ssize_t store_idle_timeout(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) +static ssize_t store_idle_timeout(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct hci_dev *hdev = to_hci_dev(dev); unsigned int val; @@ -276,13 +287,16 @@ static ssize_t store_idle_timeout(struct device *dev, struct device_attribute *a return count; } -static ssize_t show_sniff_max_interval(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_sniff_max_interval(struct device *dev, + struct device_attribute *attr, char *buf) { struct hci_dev *hdev = to_hci_dev(dev); return sprintf(buf, "%d\n", hdev->sniff_max_interval); } -static ssize_t store_sniff_max_interval(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) +static ssize_t store_sniff_max_interval(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct hci_dev *hdev = to_hci_dev(dev); u16 val; @@ -300,13 +314,16 @@ static ssize_t store_sniff_max_interval(struct device *dev, struct device_attrib return count; } -static ssize_t show_sniff_min_interval(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t show_sniff_min_interval(struct device *dev, + struct device_attribute *attr, char *buf) { struct hci_dev *hdev = to_hci_dev(dev); return sprintf(buf, "%d\n", hdev->sniff_min_interval); } -static ssize_t store_sniff_min_interval(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) +static ssize_t store_sniff_min_interval(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct hci_dev *hdev = to_hci_dev(dev); u16 val; @@ -335,11 +352,11 @@ static DEVICE_ATTR(hci_version, S_IRUGO, show_hci_version, NULL); static DEVICE_ATTR(hci_revision, S_IRUGO, show_hci_revision, NULL); static DEVICE_ATTR(idle_timeout, S_IRUGO | S_IWUSR, - show_idle_timeout, store_idle_timeout); + show_idle_timeout, store_idle_timeout); static DEVICE_ATTR(sniff_max_interval, S_IRUGO | S_IWUSR, - show_sniff_max_interval, store_sniff_max_interval); + show_sniff_max_interval, store_sniff_max_interval); static DEVICE_ATTR(sniff_min_interval, S_IRUGO | S_IWUSR, - show_sniff_min_interval, store_sniff_min_interval); + show_sniff_min_interval, store_sniff_min_interval); static struct attribute *bt_host_attrs[] = { &dev_attr_bus.attr, @@ -455,8 +472,8 @@ static void print_bt_uuid(struct seq_file *f, u8 *uuid) memcpy(&data5, &uuid[14], 2); seq_printf(f, "%.8x-%.4x-%.4x-%.4x-%.8x%.4x\n", - ntohl(data0), ntohs(data1), ntohs(data2), - ntohs(data3), ntohl(data4), ntohs(data5)); + ntohl(data0), ntohs(data1), ntohs(data2), ntohs(data3), + ntohl(data4), ntohs(data5)); } static int uuids_show(struct seq_file *f, void *p) @@ -513,7 +530,7 @@ static int auto_accept_delay_get(void *data, u64 *val) } DEFINE_SIMPLE_ATTRIBUTE(auto_accept_delay_fops, auto_accept_delay_get, - auto_accept_delay_set, "%llu\n"); + auto_accept_delay_set, "%llu\n"); void hci_init_sysfs(struct hci_dev *hdev) { @@ -547,15 +564,15 @@ int hci_add_sysfs(struct hci_dev *hdev) return 0; debugfs_create_file("inquiry_cache", 0444, hdev->debugfs, - hdev, &inquiry_cache_fops); + hdev, &inquiry_cache_fops); debugfs_create_file("blacklist", 0444, hdev->debugfs, - hdev, &blacklist_fops); + hdev, &blacklist_fops); debugfs_create_file("uuids", 0444, hdev->debugfs, hdev, &uuids_fops); debugfs_create_file("auto_accept_delay", 0444, hdev->debugfs, hdev, - &auto_accept_delay_fops); + &auto_accept_delay_fops); return 0; } diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 2c20d765b39..ccd985da651 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -21,27 +21,8 @@ */ #include <linux/module.h> - -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/poll.h> -#include <linux/freezer.h> -#include <linux/fcntl.h> -#include <linux/skbuff.h> -#include <linux/socket.h> -#include <linux/ioctl.h> #include <linux/file.h> -#include <linux/init.h> -#include <linux/wait.h> -#include <linux/mutex.h> #include <linux/kthread.h> -#include <net/sock.h> - -#include <linux/input.h> -#include <linux/hid.h> #include <linux/hidraw.h> #include <net/bluetooth/bluetooth.h> @@ -244,7 +225,8 @@ static void hidp_input_report(struct hidp_session *session, struct sk_buff *skb) } static int __hidp_send_ctrl_message(struct hidp_session *session, - unsigned char hdr, unsigned char *data, int size) + unsigned char hdr, unsigned char *data, + int size) { struct sk_buff *skb; @@ -268,7 +250,7 @@ static int __hidp_send_ctrl_message(struct hidp_session *session, return 0; } -static inline int hidp_send_ctrl_message(struct hidp_session *session, +static int hidp_send_ctrl_message(struct hidp_session *session, unsigned char hdr, unsigned char *data, int size) { int err; @@ -471,7 +453,7 @@ static void hidp_set_timer(struct hidp_session *session) mod_timer(&session->timer, jiffies + HZ * session->idle_to); } -static inline void hidp_del_timer(struct hidp_session *session) +static void hidp_del_timer(struct hidp_session *session) { if (session->idle_to > 0) del_timer(&session->timer); diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c index 73a32d705c1..18b3f6892a3 100644 --- a/net/bluetooth/hidp/sock.c +++ b/net/bluetooth/hidp/sock.c @@ -20,22 +20,8 @@ SOFTWARE IS DISCLAIMED. */ -#include <linux/module.h> - -#include <linux/types.h> -#include <linux/capability.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/poll.h> -#include <linux/fcntl.h> -#include <linux/skbuff.h> -#include <linux/socket.h> -#include <linux/ioctl.h> +#include <linux/export.h> #include <linux/file.h> -#include <linux/init.h> -#include <linux/compat.h> -#include <linux/gfp.h> -#include <net/sock.h> #include "hidp.h" diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 4554e80d16a..daa149b7003 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -30,32 +30,14 @@ #include <linux/module.h> -#include <linux/types.h> -#include <linux/capability.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/poll.h> -#include <linux/fcntl.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/socket.h> -#include <linux/skbuff.h> -#include <linux/list.h> -#include <linux/device.h> #include <linux/debugfs.h> -#include <linux/seq_file.h> -#include <linux/uaccess.h> #include <linux/crc16.h> -#include <net/sock.h> - -#include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> #include <net/bluetooth/smp.h> +#include <net/bluetooth/a2mp.h> bool disable_ertm; @@ -73,6 +55,9 @@ static int l2cap_build_conf_req(struct l2cap_chan *chan, void *data); static void l2cap_send_disconn_req(struct l2cap_conn *conn, struct l2cap_chan *chan, int err); +static void l2cap_tx(struct l2cap_chan *chan, struct l2cap_ctrl *control, + struct sk_buff_head *skbs, u8 event); + /* ---- L2CAP channels ---- */ static struct l2cap_chan *__l2cap_get_chan_by_dcid(struct l2cap_conn *conn, u16 cid) @@ -196,7 +181,7 @@ static void __l2cap_state_change(struct l2cap_chan *chan, int state) state_to_string(state)); chan->state = state; - chan->ops->state_change(chan->data, state); + chan->ops->state_change(chan, state); } static void l2cap_state_change(struct l2cap_chan *chan, int state) @@ -224,6 +209,37 @@ static inline void l2cap_chan_set_err(struct l2cap_chan *chan, int err) release_sock(sk); } +static void __set_retrans_timer(struct l2cap_chan *chan) +{ + if (!delayed_work_pending(&chan->monitor_timer) && + chan->retrans_timeout) { + l2cap_set_timer(chan, &chan->retrans_timer, + msecs_to_jiffies(chan->retrans_timeout)); + } +} + +static void __set_monitor_timer(struct l2cap_chan *chan) +{ + __clear_retrans_timer(chan); + if (chan->monitor_timeout) { + l2cap_set_timer(chan, &chan->monitor_timer, + msecs_to_jiffies(chan->monitor_timeout)); + } +} + +static struct sk_buff *l2cap_ertm_seq_in_queue(struct sk_buff_head *head, + u16 seq) +{ + struct sk_buff *skb; + + skb_queue_walk(head, skb) { + if (bt_cb(skb)->control.txseq == seq) + return skb; + } + + return NULL; +} + /* ---- L2CAP sequence number lists ---- */ /* For ERTM, ordered lists of sequence numbers must be tracked for @@ -366,7 +382,7 @@ static void l2cap_chan_timeout(struct work_struct *work) l2cap_chan_unlock(chan); - chan->ops->close(chan->data); + chan->ops->close(chan); mutex_unlock(&conn->chan_lock); l2cap_chan_put(chan); @@ -392,6 +408,9 @@ struct l2cap_chan *l2cap_chan_create(void) atomic_set(&chan->refcnt, 1); + /* This flag is cleared in l2cap_chan_ready() */ + set_bit(CONF_NOT_COMPLETE, &chan->conf_state); + BT_DBG("chan %p", chan); return chan; @@ -412,6 +431,7 @@ void l2cap_chan_set_defaults(struct l2cap_chan *chan) chan->max_tx = L2CAP_DEFAULT_MAX_TX; chan->tx_win = L2CAP_DEFAULT_TX_WINDOW; chan->tx_win_max = L2CAP_DEFAULT_TX_WINDOW; + chan->ack_win = L2CAP_DEFAULT_TX_WINDOW; chan->sec_level = BT_SECURITY_LOW; set_bit(FLAG_FORCE_ACTIVE, &chan->flags); @@ -430,7 +450,7 @@ static void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) case L2CAP_CHAN_CONN_ORIENTED: if (conn->hcon->type == LE_LINK) { /* LE connection */ - chan->omtu = L2CAP_LE_DEFAULT_MTU; + chan->omtu = L2CAP_DEFAULT_MTU; chan->scid = L2CAP_CID_LE_DATA; chan->dcid = L2CAP_CID_LE_DATA; } else { @@ -447,6 +467,13 @@ static void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) chan->omtu = L2CAP_DEFAULT_MTU; break; + case L2CAP_CHAN_CONN_FIX_A2MP: + chan->scid = L2CAP_CID_A2MP; + chan->dcid = L2CAP_CID_A2MP; + chan->omtu = L2CAP_A2MP_DEFAULT_MTU; + chan->imtu = L2CAP_A2MP_DEFAULT_MTU; + break; + default: /* Raw socket can send/recv signalling messages only */ chan->scid = L2CAP_CID_SIGNALING; @@ -466,18 +493,16 @@ static void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) list_add(&chan->list, &conn->chan_l); } -static void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) +void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) { mutex_lock(&conn->chan_lock); __l2cap_chan_add(conn, chan); mutex_unlock(&conn->chan_lock); } -static void l2cap_chan_del(struct l2cap_chan *chan, int err) +void l2cap_chan_del(struct l2cap_chan *chan, int err) { - struct sock *sk = chan->sk; struct l2cap_conn *conn = chan->conn; - struct sock *parent = bt_sk(sk)->parent; __clear_chan_timer(chan); @@ -490,34 +515,22 @@ static void l2cap_chan_del(struct l2cap_chan *chan, int err) l2cap_chan_put(chan); chan->conn = NULL; - hci_conn_put(conn->hcon); - } - - lock_sock(sk); - - __l2cap_state_change(chan, BT_CLOSED); - sock_set_flag(sk, SOCK_ZAPPED); - - if (err) - __l2cap_chan_set_err(chan, err); - if (parent) { - bt_accept_unlink(sk); - parent->sk_data_ready(parent, 0); - } else - sk->sk_state_change(sk); + if (chan->chan_type != L2CAP_CHAN_CONN_FIX_A2MP) + hci_conn_put(conn->hcon); + } - release_sock(sk); + if (chan->ops->teardown) + chan->ops->teardown(chan, err); - if (!(test_bit(CONF_OUTPUT_DONE, &chan->conf_state) && - test_bit(CONF_INPUT_DONE, &chan->conf_state))) + if (test_bit(CONF_NOT_COMPLETE, &chan->conf_state)) return; - skb_queue_purge(&chan->tx_q); - - if (chan->mode == L2CAP_MODE_ERTM) { - struct srej_list *l, *tmp; + switch(chan->mode) { + case L2CAP_MODE_BASIC: + break; + case L2CAP_MODE_ERTM: __clear_retrans_timer(chan); __clear_monitor_timer(chan); __clear_ack_timer(chan); @@ -526,30 +539,15 @@ static void l2cap_chan_del(struct l2cap_chan *chan, int err) l2cap_seq_list_free(&chan->srej_list); l2cap_seq_list_free(&chan->retrans_list); - list_for_each_entry_safe(l, tmp, &chan->srej_l, list) { - list_del(&l->list); - kfree(l); - } - } -} -static void l2cap_chan_cleanup_listen(struct sock *parent) -{ - struct sock *sk; - - BT_DBG("parent %p", parent); - - /* Close not yet accepted channels */ - while ((sk = bt_accept_dequeue(parent, NULL))) { - struct l2cap_chan *chan = l2cap_pi(sk)->chan; - - l2cap_chan_lock(chan); - __clear_chan_timer(chan); - l2cap_chan_close(chan, ECONNRESET); - l2cap_chan_unlock(chan); + /* fall through */ - chan->ops->close(chan->data); + case L2CAP_MODE_STREAMING: + skb_queue_purge(&chan->tx_q); + break; } + + return; } void l2cap_chan_close(struct l2cap_chan *chan, int reason) @@ -562,12 +560,8 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason) switch (chan->state) { case BT_LISTEN: - lock_sock(sk); - l2cap_chan_cleanup_listen(sk); - - __l2cap_state_change(chan, BT_CLOSED); - sock_set_flag(sk, SOCK_ZAPPED); - release_sock(sk); + if (chan->ops->teardown) + chan->ops->teardown(chan, 0); break; case BT_CONNECTED: @@ -595,7 +589,7 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason) rsp.scid = cpu_to_le16(chan->dcid); rsp.dcid = cpu_to_le16(chan->scid); rsp.result = cpu_to_le16(result); - rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); + rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, sizeof(rsp), &rsp); } @@ -609,9 +603,8 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason) break; default: - lock_sock(sk); - sock_set_flag(sk, SOCK_ZAPPED); - release_sock(sk); + if (chan->ops->teardown) + chan->ops->teardown(chan, 0); break; } } @@ -627,7 +620,7 @@ static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan) default: return HCI_AT_NO_BONDING; } - } else if (chan->psm == cpu_to_le16(0x0001)) { + } else if (chan->psm == __constant_cpu_to_le16(L2CAP_PSM_SDP)) { if (chan->sec_level == BT_SECURITY_LOW) chan->sec_level = BT_SECURITY_SDP; @@ -773,9 +766,11 @@ static inline void __unpack_control(struct l2cap_chan *chan, if (test_bit(FLAG_EXT_CTRL, &chan->flags)) { __unpack_extended_control(get_unaligned_le32(skb->data), &bt_cb(skb)->control); + skb_pull(skb, L2CAP_EXT_CTRL_SIZE); } else { __unpack_enhanced_control(get_unaligned_le16(skb->data), &bt_cb(skb)->control); + skb_pull(skb, L2CAP_ENH_CTRL_SIZE); } } @@ -830,66 +825,102 @@ static inline void __pack_control(struct l2cap_chan *chan, } } -static inline void l2cap_send_sframe(struct l2cap_chan *chan, u32 control) +static inline unsigned int __ertm_hdr_size(struct l2cap_chan *chan) { - struct sk_buff *skb; - struct l2cap_hdr *lh; - struct l2cap_conn *conn = chan->conn; - int count, hlen; - - if (chan->state != BT_CONNECTED) - return; - if (test_bit(FLAG_EXT_CTRL, &chan->flags)) - hlen = L2CAP_EXT_HDR_SIZE; + return L2CAP_EXT_HDR_SIZE; else - hlen = L2CAP_ENH_HDR_SIZE; + return L2CAP_ENH_HDR_SIZE; +} + +static struct sk_buff *l2cap_create_sframe_pdu(struct l2cap_chan *chan, + u32 control) +{ + struct sk_buff *skb; + struct l2cap_hdr *lh; + int hlen = __ertm_hdr_size(chan); if (chan->fcs == L2CAP_FCS_CRC16) hlen += L2CAP_FCS_SIZE; - BT_DBG("chan %p, control 0x%8.8x", chan, control); - - count = min_t(unsigned int, conn->mtu, hlen); + skb = bt_skb_alloc(hlen, GFP_KERNEL); - control |= __set_sframe(chan); - - if (test_and_clear_bit(CONN_SEND_FBIT, &chan->conn_state)) - control |= __set_ctrl_final(chan); - - if (test_and_clear_bit(CONN_SEND_PBIT, &chan->conn_state)) - control |= __set_ctrl_poll(chan); - - skb = bt_skb_alloc(count, GFP_ATOMIC); if (!skb) - return; + return ERR_PTR(-ENOMEM); lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); lh->len = cpu_to_le16(hlen - L2CAP_HDR_SIZE); lh->cid = cpu_to_le16(chan->dcid); - __put_control(chan, control, skb_put(skb, __ctrl_size(chan))); + if (test_bit(FLAG_EXT_CTRL, &chan->flags)) + put_unaligned_le32(control, skb_put(skb, L2CAP_EXT_CTRL_SIZE)); + else + put_unaligned_le16(control, skb_put(skb, L2CAP_ENH_CTRL_SIZE)); if (chan->fcs == L2CAP_FCS_CRC16) { - u16 fcs = crc16(0, (u8 *)lh, count - L2CAP_FCS_SIZE); + u16 fcs = crc16(0, (u8 *)skb->data, skb->len); put_unaligned_le16(fcs, skb_put(skb, L2CAP_FCS_SIZE)); } skb->priority = HCI_PRIO_MAX; - l2cap_do_send(chan, skb); + return skb; } -static inline void l2cap_send_rr_or_rnr(struct l2cap_chan *chan, u32 control) +static void l2cap_send_sframe(struct l2cap_chan *chan, + struct l2cap_ctrl *control) { - if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { - control |= __set_ctrl_super(chan, L2CAP_SUPER_RNR); + struct sk_buff *skb; + u32 control_field; + + BT_DBG("chan %p, control %p", chan, control); + + if (!control->sframe) + return; + + if (test_and_clear_bit(CONN_SEND_FBIT, &chan->conn_state) && + !control->poll) + control->final = 1; + + if (control->super == L2CAP_SUPER_RR) + clear_bit(CONN_RNR_SENT, &chan->conn_state); + else if (control->super == L2CAP_SUPER_RNR) set_bit(CONN_RNR_SENT, &chan->conn_state); - } else - control |= __set_ctrl_super(chan, L2CAP_SUPER_RR); - control |= __set_reqseq(chan, chan->buffer_seq); + if (control->super != L2CAP_SUPER_SREJ) { + chan->last_acked_seq = control->reqseq; + __clear_ack_timer(chan); + } - l2cap_send_sframe(chan, control); + BT_DBG("reqseq %d, final %d, poll %d, super %d", control->reqseq, + control->final, control->poll, control->super); + + if (test_bit(FLAG_EXT_CTRL, &chan->flags)) + control_field = __pack_extended_control(control); + else + control_field = __pack_enhanced_control(control); + + skb = l2cap_create_sframe_pdu(chan, control_field); + if (!IS_ERR(skb)) + l2cap_do_send(chan, skb); +} + +static void l2cap_send_rr_or_rnr(struct l2cap_chan *chan, bool poll) +{ + struct l2cap_ctrl control; + + BT_DBG("chan %p, poll %d", chan, poll); + + memset(&control, 0, sizeof(control)); + control.sframe = 1; + control.poll = poll; + + if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) + control.super = L2CAP_SUPER_RNR; + else + control.super = L2CAP_SUPER_RR; + + control.reqseq = chan->buffer_seq; + l2cap_send_sframe(chan, &control); } static inline int __l2cap_no_conn_pending(struct l2cap_chan *chan) @@ -914,25 +945,13 @@ static void l2cap_send_conn_req(struct l2cap_chan *chan) static void l2cap_chan_ready(struct l2cap_chan *chan) { - struct sock *sk = chan->sk; - struct sock *parent; - - lock_sock(sk); - - parent = bt_sk(sk)->parent; - - BT_DBG("sk %p, parent %p", sk, parent); - + /* This clears all conf flags, including CONF_NOT_COMPLETE */ chan->conf_state = 0; __clear_chan_timer(chan); - __l2cap_state_change(chan, BT_CONNECTED); - sk->sk_state_change(sk); - - if (parent) - parent->sk_data_ready(parent, 0); + chan->state = BT_CONNECTED; - release_sock(sk); + chan->ops->ready(chan); } static void l2cap_do_start(struct l2cap_chan *chan) @@ -953,7 +972,7 @@ static void l2cap_do_start(struct l2cap_chan *chan) l2cap_send_conn_req(chan); } else { struct l2cap_info_req req; - req.type = cpu_to_le16(L2CAP_IT_FEAT_MASK); + req.type = __constant_cpu_to_le16(L2CAP_IT_FEAT_MASK); conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_SENT; conn->info_ident = l2cap_get_ident(conn); @@ -995,6 +1014,11 @@ static void l2cap_send_disconn_req(struct l2cap_conn *conn, struct l2cap_chan *c __clear_ack_timer(chan); } + if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP) { + __l2cap_state_change(chan, BT_DISCONN); + return; + } + req.dcid = cpu_to_le16(chan->dcid); req.scid = cpu_to_le16(chan->scid); l2cap_send_cmd(conn, l2cap_get_ident(conn), @@ -1053,20 +1077,20 @@ static void l2cap_conn_start(struct l2cap_conn *conn) if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { struct sock *parent = bt_sk(sk)->parent; - rsp.result = cpu_to_le16(L2CAP_CR_PEND); - rsp.status = cpu_to_le16(L2CAP_CS_AUTHOR_PEND); + rsp.result = __constant_cpu_to_le16(L2CAP_CR_PEND); + rsp.status = __constant_cpu_to_le16(L2CAP_CS_AUTHOR_PEND); if (parent) parent->sk_data_ready(parent, 0); } else { __l2cap_state_change(chan, BT_CONFIG); - rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS); - rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); + rsp.result = __constant_cpu_to_le16(L2CAP_CR_SUCCESS); + rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); } release_sock(sk); } else { - rsp.result = cpu_to_le16(L2CAP_CR_PEND); - rsp.status = cpu_to_le16(L2CAP_CS_AUTHEN_PEND); + rsp.result = __constant_cpu_to_le16(L2CAP_CR_PEND); + rsp.status = __constant_cpu_to_le16(L2CAP_CS_AUTHEN_PEND); } l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, @@ -1150,19 +1174,14 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn) lock_sock(parent); - /* Check for backlog size */ - if (sk_acceptq_is_full(parent)) { - BT_DBG("backlog full %d", parent->sk_ack_backlog); - goto clean; - } - - chan = pchan->ops->new_connection(pchan->data); + chan = pchan->ops->new_connection(pchan); if (!chan) goto clean; sk = chan->sk; hci_conn_hold(conn->hcon); + conn->hcon->disc_timeout = HCI_DISCONN_TIMEOUT; bacpy(&bt_sk(sk)->src, conn->src); bacpy(&bt_sk(sk)->dst, conn->dst); @@ -1171,10 +1190,7 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn) l2cap_chan_add(conn, chan); - __set_chan_timer(chan, sk->sk_sndtimeo); - - __l2cap_state_change(chan, BT_CONNECTED); - parent->sk_data_ready(parent, 0); + l2cap_chan_ready(chan); clean: release_sock(parent); @@ -1198,6 +1214,11 @@ static void l2cap_conn_ready(struct l2cap_conn *conn) l2cap_chan_lock(chan); + if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP) { + l2cap_chan_unlock(chan); + continue; + } + if (conn->hcon->type == LE_LINK) { if (smp_conn_security(conn, chan->sec_level)) l2cap_chan_ready(chan); @@ -1270,7 +1291,7 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) l2cap_chan_unlock(chan); - chan->ops->close(chan->data); + chan->ops->close(chan); l2cap_chan_put(chan); } @@ -1444,21 +1465,17 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, goto done; } - lock_sock(sk); - - switch (sk->sk_state) { + switch (chan->state) { case BT_CONNECT: case BT_CONNECT2: case BT_CONFIG: /* Already connecting */ err = 0; - release_sock(sk); goto done; case BT_CONNECTED: /* Already connected */ err = -EISCONN; - release_sock(sk); goto done; case BT_OPEN: @@ -1468,13 +1485,12 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, default: err = -EBADFD; - release_sock(sk); goto done; } /* Set destination address and psm */ + lock_sock(sk); bacpy(&bt_sk(sk)->dst, dst); - release_sock(sk); chan->psm = psm; @@ -1576,23 +1592,20 @@ int __l2cap_wait_ack(struct sock *sk) static void l2cap_monitor_timeout(struct work_struct *work) { struct l2cap_chan *chan = container_of(work, struct l2cap_chan, - monitor_timer.work); + monitor_timer.work); BT_DBG("chan %p", chan); l2cap_chan_lock(chan); - if (chan->retry_count >= chan->remote_max_tx) { - l2cap_send_disconn_req(chan->conn, chan, ECONNABORTED); + if (!chan->conn) { l2cap_chan_unlock(chan); l2cap_chan_put(chan); return; } - chan->retry_count++; - __set_monitor_timer(chan); + l2cap_tx(chan, NULL, NULL, L2CAP_EV_MONITOR_TO); - l2cap_send_rr_or_rnr(chan, L2CAP_CTRL_POLL); l2cap_chan_unlock(chan); l2cap_chan_put(chan); } @@ -1600,234 +1613,293 @@ static void l2cap_monitor_timeout(struct work_struct *work) static void l2cap_retrans_timeout(struct work_struct *work) { struct l2cap_chan *chan = container_of(work, struct l2cap_chan, - retrans_timer.work); + retrans_timer.work); BT_DBG("chan %p", chan); l2cap_chan_lock(chan); - chan->retry_count = 1; - __set_monitor_timer(chan); - - set_bit(CONN_WAIT_F, &chan->conn_state); - - l2cap_send_rr_or_rnr(chan, L2CAP_CTRL_POLL); + if (!chan->conn) { + l2cap_chan_unlock(chan); + l2cap_chan_put(chan); + return; + } + l2cap_tx(chan, NULL, NULL, L2CAP_EV_RETRANS_TO); l2cap_chan_unlock(chan); l2cap_chan_put(chan); } -static void l2cap_drop_acked_frames(struct l2cap_chan *chan) +static void l2cap_streaming_send(struct l2cap_chan *chan, + struct sk_buff_head *skbs) { struct sk_buff *skb; + struct l2cap_ctrl *control; - while ((skb = skb_peek(&chan->tx_q)) && - chan->unacked_frames) { - if (bt_cb(skb)->control.txseq == chan->expected_ack_seq) - break; + BT_DBG("chan %p, skbs %p", chan, skbs); - skb = skb_dequeue(&chan->tx_q); - kfree_skb(skb); + skb_queue_splice_tail_init(skbs, &chan->tx_q); - chan->unacked_frames--; - } + while (!skb_queue_empty(&chan->tx_q)) { - if (!chan->unacked_frames) - __clear_retrans_timer(chan); -} + skb = skb_dequeue(&chan->tx_q); -static void l2cap_streaming_send(struct l2cap_chan *chan) -{ - struct sk_buff *skb; - u32 control; - u16 fcs; + bt_cb(skb)->control.retries = 1; + control = &bt_cb(skb)->control; + + control->reqseq = 0; + control->txseq = chan->next_tx_seq; - while ((skb = skb_dequeue(&chan->tx_q))) { - control = __get_control(chan, skb->data + L2CAP_HDR_SIZE); - control |= __set_txseq(chan, chan->next_tx_seq); - control |= __set_ctrl_sar(chan, bt_cb(skb)->control.sar); - __put_control(chan, control, skb->data + L2CAP_HDR_SIZE); + __pack_control(chan, control, skb); if (chan->fcs == L2CAP_FCS_CRC16) { - fcs = crc16(0, (u8 *)skb->data, - skb->len - L2CAP_FCS_SIZE); - put_unaligned_le16(fcs, - skb->data + skb->len - L2CAP_FCS_SIZE); + u16 fcs = crc16(0, (u8 *) skb->data, skb->len); + put_unaligned_le16(fcs, skb_put(skb, L2CAP_FCS_SIZE)); } l2cap_do_send(chan, skb); + BT_DBG("Sent txseq %u", control->txseq); + chan->next_tx_seq = __next_seq(chan, chan->next_tx_seq); + chan->frames_sent++; } } -static void l2cap_retransmit_one_frame(struct l2cap_chan *chan, u16 tx_seq) +static int l2cap_ertm_send(struct l2cap_chan *chan) { struct sk_buff *skb, *tx_skb; - u16 fcs; - u32 control; + struct l2cap_ctrl *control; + int sent = 0; - skb = skb_peek(&chan->tx_q); - if (!skb) - return; + BT_DBG("chan %p", chan); - while (bt_cb(skb)->control.txseq != tx_seq) { - if (skb_queue_is_last(&chan->tx_q, skb)) - return; + if (chan->state != BT_CONNECTED) + return -ENOTCONN; - skb = skb_queue_next(&chan->tx_q, skb); - } + if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state)) + return 0; - if (bt_cb(skb)->control.retries == chan->remote_max_tx && - chan->remote_max_tx) { - l2cap_send_disconn_req(chan->conn, chan, ECONNABORTED); - return; - } + while (chan->tx_send_head && + chan->unacked_frames < chan->remote_tx_win && + chan->tx_state == L2CAP_TX_STATE_XMIT) { + + skb = chan->tx_send_head; - tx_skb = skb_clone(skb, GFP_ATOMIC); - bt_cb(skb)->control.retries++; + bt_cb(skb)->control.retries = 1; + control = &bt_cb(skb)->control; - control = __get_control(chan, tx_skb->data + L2CAP_HDR_SIZE); - control &= __get_sar_mask(chan); + if (test_and_clear_bit(CONN_SEND_FBIT, &chan->conn_state)) + control->final = 1; + + control->reqseq = chan->buffer_seq; + chan->last_acked_seq = chan->buffer_seq; + control->txseq = chan->next_tx_seq; - if (test_and_clear_bit(CONN_SEND_FBIT, &chan->conn_state)) - control |= __set_ctrl_final(chan); + __pack_control(chan, control, skb); - control |= __set_reqseq(chan, chan->buffer_seq); - control |= __set_txseq(chan, tx_seq); + if (chan->fcs == L2CAP_FCS_CRC16) { + u16 fcs = crc16(0, (u8 *) skb->data, skb->len); + put_unaligned_le16(fcs, skb_put(skb, L2CAP_FCS_SIZE)); + } - __put_control(chan, control, tx_skb->data + L2CAP_HDR_SIZE); + /* Clone after data has been modified. Data is assumed to be + read-only (for locking purposes) on cloned sk_buffs. + */ + tx_skb = skb_clone(skb, GFP_KERNEL); - if (chan->fcs == L2CAP_FCS_CRC16) { - fcs = crc16(0, (u8 *)tx_skb->data, - tx_skb->len - L2CAP_FCS_SIZE); - put_unaligned_le16(fcs, - tx_skb->data + tx_skb->len - L2CAP_FCS_SIZE); + if (!tx_skb) + break; + + __set_retrans_timer(chan); + + chan->next_tx_seq = __next_seq(chan, chan->next_tx_seq); + chan->unacked_frames++; + chan->frames_sent++; + sent++; + + if (skb_queue_is_last(&chan->tx_q, skb)) + chan->tx_send_head = NULL; + else + chan->tx_send_head = skb_queue_next(&chan->tx_q, skb); + + l2cap_do_send(chan, tx_skb); + BT_DBG("Sent txseq %u", control->txseq); } - l2cap_do_send(chan, tx_skb); + BT_DBG("Sent %d, %u unacked, %u in ERTM queue", sent, + chan->unacked_frames, skb_queue_len(&chan->tx_q)); + + return sent; } -static int l2cap_ertm_send(struct l2cap_chan *chan) +static void l2cap_ertm_resend(struct l2cap_chan *chan) { - struct sk_buff *skb, *tx_skb; - u16 fcs; - u32 control; - int nsent = 0; + struct l2cap_ctrl control; + struct sk_buff *skb; + struct sk_buff *tx_skb; + u16 seq; - if (chan->state != BT_CONNECTED) - return -ENOTCONN; + BT_DBG("chan %p", chan); if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state)) - return 0; + return; - while ((skb = chan->tx_send_head) && (!l2cap_tx_window_full(chan))) { + while (chan->retrans_list.head != L2CAP_SEQ_LIST_CLEAR) { + seq = l2cap_seq_list_pop(&chan->retrans_list); - if (bt_cb(skb)->control.retries == chan->remote_max_tx && - chan->remote_max_tx) { - l2cap_send_disconn_req(chan->conn, chan, ECONNABORTED); - break; + skb = l2cap_ertm_seq_in_queue(&chan->tx_q, seq); + if (!skb) { + BT_DBG("Error: Can't retransmit seq %d, frame missing", + seq); + continue; } - tx_skb = skb_clone(skb, GFP_ATOMIC); - bt_cb(skb)->control.retries++; + control = bt_cb(skb)->control; - control = __get_control(chan, tx_skb->data + L2CAP_HDR_SIZE); - control &= __get_sar_mask(chan); + if (chan->max_tx != 0 && + bt_cb(skb)->control.retries > chan->max_tx) { + BT_DBG("Retry limit exceeded (%d)", chan->max_tx); + l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + l2cap_seq_list_clear(&chan->retrans_list); + break; + } + control.reqseq = chan->buffer_seq; if (test_and_clear_bit(CONN_SEND_FBIT, &chan->conn_state)) - control |= __set_ctrl_final(chan); + control.final = 1; + else + control.final = 0; - control |= __set_reqseq(chan, chan->buffer_seq); - control |= __set_txseq(chan, chan->next_tx_seq); - control |= __set_ctrl_sar(chan, bt_cb(skb)->control.sar); + if (skb_cloned(skb)) { + /* Cloned sk_buffs are read-only, so we need a + * writeable copy + */ + tx_skb = skb_copy(skb, GFP_ATOMIC); + } else { + tx_skb = skb_clone(skb, GFP_ATOMIC); + } - __put_control(chan, control, tx_skb->data + L2CAP_HDR_SIZE); + if (!tx_skb) { + l2cap_seq_list_clear(&chan->retrans_list); + break; + } + + /* Update skb contents */ + if (test_bit(FLAG_EXT_CTRL, &chan->flags)) { + put_unaligned_le32(__pack_extended_control(&control), + tx_skb->data + L2CAP_HDR_SIZE); + } else { + put_unaligned_le16(__pack_enhanced_control(&control), + tx_skb->data + L2CAP_HDR_SIZE); + } if (chan->fcs == L2CAP_FCS_CRC16) { - fcs = crc16(0, (u8 *)skb->data, - tx_skb->len - L2CAP_FCS_SIZE); - put_unaligned_le16(fcs, skb->data + - tx_skb->len - L2CAP_FCS_SIZE); + u16 fcs = crc16(0, (u8 *) tx_skb->data, tx_skb->len); + put_unaligned_le16(fcs, skb_put(tx_skb, + L2CAP_FCS_SIZE)); } l2cap_do_send(chan, tx_skb); - __set_retrans_timer(chan); - - bt_cb(skb)->control.txseq = chan->next_tx_seq; + BT_DBG("Resent txseq %d", control.txseq); - chan->next_tx_seq = __next_seq(chan, chan->next_tx_seq); - - if (bt_cb(skb)->control.retries == 1) { - chan->unacked_frames++; - - if (!nsent++) - __clear_ack_timer(chan); - } - - chan->frames_sent++; - - if (skb_queue_is_last(&chan->tx_q, skb)) - chan->tx_send_head = NULL; - else - chan->tx_send_head = skb_queue_next(&chan->tx_q, skb); + chan->last_acked_seq = chan->buffer_seq; } - - return nsent; } -static int l2cap_retransmit_frames(struct l2cap_chan *chan) +static void l2cap_retransmit(struct l2cap_chan *chan, + struct l2cap_ctrl *control) { - int ret; + BT_DBG("chan %p, control %p", chan, control); - if (!skb_queue_empty(&chan->tx_q)) - chan->tx_send_head = chan->tx_q.next; - - chan->next_tx_seq = chan->expected_ack_seq; - ret = l2cap_ertm_send(chan); - return ret; + l2cap_seq_list_append(&chan->retrans_list, control->reqseq); + l2cap_ertm_resend(chan); } -static void __l2cap_send_ack(struct l2cap_chan *chan) +static void l2cap_retransmit_all(struct l2cap_chan *chan, + struct l2cap_ctrl *control) { - u32 control = 0; + struct sk_buff *skb; - control |= __set_reqseq(chan, chan->buffer_seq); + BT_DBG("chan %p, control %p", chan, control); - if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { - control |= __set_ctrl_super(chan, L2CAP_SUPER_RNR); - set_bit(CONN_RNR_SENT, &chan->conn_state); - l2cap_send_sframe(chan, control); - return; - } + if (control->poll) + set_bit(CONN_SEND_FBIT, &chan->conn_state); + + l2cap_seq_list_clear(&chan->retrans_list); - if (l2cap_ertm_send(chan) > 0) + if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state)) return; - control |= __set_ctrl_super(chan, L2CAP_SUPER_RR); - l2cap_send_sframe(chan, control); + if (chan->unacked_frames) { + skb_queue_walk(&chan->tx_q, skb) { + if (bt_cb(skb)->control.txseq == control->reqseq || + skb == chan->tx_send_head) + break; + } + + skb_queue_walk_from(&chan->tx_q, skb) { + if (skb == chan->tx_send_head) + break; + + l2cap_seq_list_append(&chan->retrans_list, + bt_cb(skb)->control.txseq); + } + + l2cap_ertm_resend(chan); + } } static void l2cap_send_ack(struct l2cap_chan *chan) { - __clear_ack_timer(chan); - __l2cap_send_ack(chan); -} + struct l2cap_ctrl control; + u16 frames_to_ack = __seq_offset(chan, chan->buffer_seq, + chan->last_acked_seq); + int threshold; -static void l2cap_send_srejtail(struct l2cap_chan *chan) -{ - struct srej_list *tail; - u32 control; + BT_DBG("chan %p last_acked_seq %d buffer_seq %d", + chan, chan->last_acked_seq, chan->buffer_seq); - control = __set_ctrl_super(chan, L2CAP_SUPER_SREJ); - control |= __set_ctrl_final(chan); + memset(&control, 0, sizeof(control)); + control.sframe = 1; - tail = list_entry((&chan->srej_l)->prev, struct srej_list, list); - control |= __set_reqseq(chan, tail->tx_seq); + if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state) && + chan->rx_state == L2CAP_RX_STATE_RECV) { + __clear_ack_timer(chan); + control.super = L2CAP_SUPER_RNR; + control.reqseq = chan->buffer_seq; + l2cap_send_sframe(chan, &control); + } else { + if (!test_bit(CONN_REMOTE_BUSY, &chan->conn_state)) { + l2cap_ertm_send(chan); + /* If any i-frames were sent, they included an ack */ + if (chan->buffer_seq == chan->last_acked_seq) + frames_to_ack = 0; + } - l2cap_send_sframe(chan, control); + /* Ack now if the window is 3/4ths full. + * Calculate without mul or div + */ + threshold = chan->ack_win; + threshold += threshold << 1; + threshold >>= 2; + + BT_DBG("frames_to_ack %u, threshold %d", frames_to_ack, + threshold); + + if (frames_to_ack >= threshold) { + __clear_ack_timer(chan); + control.super = L2CAP_SUPER_RR; + control.reqseq = chan->buffer_seq; + l2cap_send_sframe(chan, &control); + frames_to_ack = 0; + } + + if (frames_to_ack) + __set_ack_timer(chan); + } } static inline int l2cap_skbuff_fromiovec(struct l2cap_chan *chan, @@ -1876,15 +1948,15 @@ static inline int l2cap_skbuff_fromiovec(struct l2cap_chan *chan, } static struct sk_buff *l2cap_create_connless_pdu(struct l2cap_chan *chan, - struct msghdr *msg, size_t len, - u32 priority) + struct msghdr *msg, size_t len, + u32 priority) { struct l2cap_conn *conn = chan->conn; struct sk_buff *skb; int err, count, hlen = L2CAP_HDR_SIZE + L2CAP_PSMLEN_SIZE; struct l2cap_hdr *lh; - BT_DBG("chan %p len %d priority %u", chan, (int)len, priority); + BT_DBG("chan %p len %zu priority %u", chan, len, priority); count = min_t(unsigned int, (conn->mtu - hlen), len); @@ -1910,15 +1982,15 @@ static struct sk_buff *l2cap_create_connless_pdu(struct l2cap_chan *chan, } static struct sk_buff *l2cap_create_basic_pdu(struct l2cap_chan *chan, - struct msghdr *msg, size_t len, - u32 priority) + struct msghdr *msg, size_t len, + u32 priority) { struct l2cap_conn *conn = chan->conn; struct sk_buff *skb; int err, count; struct l2cap_hdr *lh; - BT_DBG("chan %p len %d", chan, (int)len); + BT_DBG("chan %p len %zu", chan, len); count = min_t(unsigned int, (conn->mtu - L2CAP_HDR_SIZE), len); @@ -1943,23 +2015,20 @@ static struct sk_buff *l2cap_create_basic_pdu(struct l2cap_chan *chan, } static struct sk_buff *l2cap_create_iframe_pdu(struct l2cap_chan *chan, - struct msghdr *msg, size_t len, - u16 sdulen) + struct msghdr *msg, size_t len, + u16 sdulen) { struct l2cap_conn *conn = chan->conn; struct sk_buff *skb; int err, count, hlen; struct l2cap_hdr *lh; - BT_DBG("chan %p len %d", chan, (int)len); + BT_DBG("chan %p len %zu", chan, len); if (!conn) return ERR_PTR(-ENOTCONN); - if (test_bit(FLAG_EXT_CTRL, &chan->flags)) - hlen = L2CAP_EXT_HDR_SIZE; - else - hlen = L2CAP_ENH_HDR_SIZE; + hlen = __ertm_hdr_size(chan); if (sdulen) hlen += L2CAP_SDULEN_SIZE; @@ -1979,7 +2048,11 @@ static struct sk_buff *l2cap_create_iframe_pdu(struct l2cap_chan *chan, lh->cid = cpu_to_le16(chan->dcid); lh->len = cpu_to_le16(len + (hlen - L2CAP_HDR_SIZE)); - __put_control(chan, 0, skb_put(skb, __ctrl_size(chan))); + /* Control header is populated later */ + if (test_bit(FLAG_EXT_CTRL, &chan->flags)) + put_unaligned_le32(0, skb_put(skb, L2CAP_EXT_CTRL_SIZE)); + else + put_unaligned_le16(0, skb_put(skb, L2CAP_ENH_CTRL_SIZE)); if (sdulen) put_unaligned_le16(sdulen, skb_put(skb, L2CAP_SDULEN_SIZE)); @@ -1990,9 +2063,7 @@ static struct sk_buff *l2cap_create_iframe_pdu(struct l2cap_chan *chan, return ERR_PTR(err); } - if (chan->fcs == L2CAP_FCS_CRC16) - put_unaligned_le16(0, skb_put(skb, L2CAP_FCS_SIZE)); - + bt_cb(skb)->control.fcs = chan->fcs; bt_cb(skb)->control.retries = 0; return skb; } @@ -2004,10 +2075,9 @@ static int l2cap_segment_sdu(struct l2cap_chan *chan, struct sk_buff *skb; u16 sdu_len; size_t pdu_len; - int err = 0; u8 sar; - BT_DBG("chan %p, msg %p, len %d", chan, msg, (int)len); + BT_DBG("chan %p, msg %p, len %zu", chan, msg, len); /* It is critical that ERTM PDUs fit in a single HCI fragment, * so fragmented skbs are not used. The HCI layer's handling @@ -2020,7 +2090,10 @@ static int l2cap_segment_sdu(struct l2cap_chan *chan, pdu_len = min_t(size_t, pdu_len, L2CAP_BREDR_MAX_PAYLOAD); /* Adjust for largest possible L2CAP overhead. */ - pdu_len -= L2CAP_EXT_HDR_SIZE + L2CAP_FCS_SIZE; + if (chan->fcs) + pdu_len -= L2CAP_FCS_SIZE; + + pdu_len -= __ertm_hdr_size(chan); /* Remote device may have requested smaller PDUs */ pdu_len = min_t(size_t, pdu_len, chan->remote_mps); @@ -2060,7 +2133,7 @@ static int l2cap_segment_sdu(struct l2cap_chan *chan, } } - return err; + return 0; } int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, @@ -2122,17 +2195,12 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, if (err) break; - if (chan->mode == L2CAP_MODE_ERTM && chan->tx_send_head == NULL) - chan->tx_send_head = seg_queue.next; - skb_queue_splice_tail_init(&seg_queue, &chan->tx_q); - if (chan->mode == L2CAP_MODE_ERTM) - err = l2cap_ertm_send(chan); + l2cap_tx(chan, NULL, &seg_queue, L2CAP_EV_DATA_REQUEST); else - l2cap_streaming_send(chan); + l2cap_streaming_send(chan, &seg_queue); - if (err >= 0) - err = len; + err = len; /* If the skbs were not queued for sending, they'll still be in * seg_queue and need to be purged. @@ -2148,6 +2216,296 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, return err; } +static void l2cap_send_srej(struct l2cap_chan *chan, u16 txseq) +{ + struct l2cap_ctrl control; + u16 seq; + + BT_DBG("chan %p, txseq %u", chan, txseq); + + memset(&control, 0, sizeof(control)); + control.sframe = 1; + control.super = L2CAP_SUPER_SREJ; + + for (seq = chan->expected_tx_seq; seq != txseq; + seq = __next_seq(chan, seq)) { + if (!l2cap_ertm_seq_in_queue(&chan->srej_q, seq)) { + control.reqseq = seq; + l2cap_send_sframe(chan, &control); + l2cap_seq_list_append(&chan->srej_list, seq); + } + } + + chan->expected_tx_seq = __next_seq(chan, txseq); +} + +static void l2cap_send_srej_tail(struct l2cap_chan *chan) +{ + struct l2cap_ctrl control; + + BT_DBG("chan %p", chan); + + if (chan->srej_list.tail == L2CAP_SEQ_LIST_CLEAR) + return; + + memset(&control, 0, sizeof(control)); + control.sframe = 1; + control.super = L2CAP_SUPER_SREJ; + control.reqseq = chan->srej_list.tail; + l2cap_send_sframe(chan, &control); +} + +static void l2cap_send_srej_list(struct l2cap_chan *chan, u16 txseq) +{ + struct l2cap_ctrl control; + u16 initial_head; + u16 seq; + + BT_DBG("chan %p, txseq %u", chan, txseq); + + memset(&control, 0, sizeof(control)); + control.sframe = 1; + control.super = L2CAP_SUPER_SREJ; + + /* Capture initial list head to allow only one pass through the list. */ + initial_head = chan->srej_list.head; + + do { + seq = l2cap_seq_list_pop(&chan->srej_list); + if (seq == txseq || seq == L2CAP_SEQ_LIST_CLEAR) + break; + + control.reqseq = seq; + l2cap_send_sframe(chan, &control); + l2cap_seq_list_append(&chan->srej_list, seq); + } while (chan->srej_list.head != initial_head); +} + +static void l2cap_process_reqseq(struct l2cap_chan *chan, u16 reqseq) +{ + struct sk_buff *acked_skb; + u16 ackseq; + + BT_DBG("chan %p, reqseq %u", chan, reqseq); + + if (chan->unacked_frames == 0 || reqseq == chan->expected_ack_seq) + return; + + BT_DBG("expected_ack_seq %u, unacked_frames %u", + chan->expected_ack_seq, chan->unacked_frames); + + for (ackseq = chan->expected_ack_seq; ackseq != reqseq; + ackseq = __next_seq(chan, ackseq)) { + + acked_skb = l2cap_ertm_seq_in_queue(&chan->tx_q, ackseq); + if (acked_skb) { + skb_unlink(acked_skb, &chan->tx_q); + kfree_skb(acked_skb); + chan->unacked_frames--; + } + } + + chan->expected_ack_seq = reqseq; + + if (chan->unacked_frames == 0) + __clear_retrans_timer(chan); + + BT_DBG("unacked_frames %u", chan->unacked_frames); +} + +static void l2cap_abort_rx_srej_sent(struct l2cap_chan *chan) +{ + BT_DBG("chan %p", chan); + + chan->expected_tx_seq = chan->buffer_seq; + l2cap_seq_list_clear(&chan->srej_list); + skb_queue_purge(&chan->srej_q); + chan->rx_state = L2CAP_RX_STATE_RECV; +} + +static void l2cap_tx_state_xmit(struct l2cap_chan *chan, + struct l2cap_ctrl *control, + struct sk_buff_head *skbs, u8 event) +{ + BT_DBG("chan %p, control %p, skbs %p, event %d", chan, control, skbs, + event); + + switch (event) { + case L2CAP_EV_DATA_REQUEST: + if (chan->tx_send_head == NULL) + chan->tx_send_head = skb_peek(skbs); + + skb_queue_splice_tail_init(skbs, &chan->tx_q); + l2cap_ertm_send(chan); + break; + case L2CAP_EV_LOCAL_BUSY_DETECTED: + BT_DBG("Enter LOCAL_BUSY"); + set_bit(CONN_LOCAL_BUSY, &chan->conn_state); + + if (chan->rx_state == L2CAP_RX_STATE_SREJ_SENT) { + /* The SREJ_SENT state must be aborted if we are to + * enter the LOCAL_BUSY state. + */ + l2cap_abort_rx_srej_sent(chan); + } + + l2cap_send_ack(chan); + + break; + case L2CAP_EV_LOCAL_BUSY_CLEAR: + BT_DBG("Exit LOCAL_BUSY"); + clear_bit(CONN_LOCAL_BUSY, &chan->conn_state); + + if (test_bit(CONN_RNR_SENT, &chan->conn_state)) { + struct l2cap_ctrl local_control; + + memset(&local_control, 0, sizeof(local_control)); + local_control.sframe = 1; + local_control.super = L2CAP_SUPER_RR; + local_control.poll = 1; + local_control.reqseq = chan->buffer_seq; + l2cap_send_sframe(chan, &local_control); + + chan->retry_count = 1; + __set_monitor_timer(chan); + chan->tx_state = L2CAP_TX_STATE_WAIT_F; + } + break; + case L2CAP_EV_RECV_REQSEQ_AND_FBIT: + l2cap_process_reqseq(chan, control->reqseq); + break; + case L2CAP_EV_EXPLICIT_POLL: + l2cap_send_rr_or_rnr(chan, 1); + chan->retry_count = 1; + __set_monitor_timer(chan); + __clear_ack_timer(chan); + chan->tx_state = L2CAP_TX_STATE_WAIT_F; + break; + case L2CAP_EV_RETRANS_TO: + l2cap_send_rr_or_rnr(chan, 1); + chan->retry_count = 1; + __set_monitor_timer(chan); + chan->tx_state = L2CAP_TX_STATE_WAIT_F; + break; + case L2CAP_EV_RECV_FBIT: + /* Nothing to process */ + break; + default: + break; + } +} + +static void l2cap_tx_state_wait_f(struct l2cap_chan *chan, + struct l2cap_ctrl *control, + struct sk_buff_head *skbs, u8 event) +{ + BT_DBG("chan %p, control %p, skbs %p, event %d", chan, control, skbs, + event); + + switch (event) { + case L2CAP_EV_DATA_REQUEST: + if (chan->tx_send_head == NULL) + chan->tx_send_head = skb_peek(skbs); + /* Queue data, but don't send. */ + skb_queue_splice_tail_init(skbs, &chan->tx_q); + break; + case L2CAP_EV_LOCAL_BUSY_DETECTED: + BT_DBG("Enter LOCAL_BUSY"); + set_bit(CONN_LOCAL_BUSY, &chan->conn_state); + + if (chan->rx_state == L2CAP_RX_STATE_SREJ_SENT) { + /* The SREJ_SENT state must be aborted if we are to + * enter the LOCAL_BUSY state. + */ + l2cap_abort_rx_srej_sent(chan); + } + + l2cap_send_ack(chan); + + break; + case L2CAP_EV_LOCAL_BUSY_CLEAR: + BT_DBG("Exit LOCAL_BUSY"); + clear_bit(CONN_LOCAL_BUSY, &chan->conn_state); + + if (test_bit(CONN_RNR_SENT, &chan->conn_state)) { + struct l2cap_ctrl local_control; + memset(&local_control, 0, sizeof(local_control)); + local_control.sframe = 1; + local_control.super = L2CAP_SUPER_RR; + local_control.poll = 1; + local_control.reqseq = chan->buffer_seq; + l2cap_send_sframe(chan, &local_control); + + chan->retry_count = 1; + __set_monitor_timer(chan); + chan->tx_state = L2CAP_TX_STATE_WAIT_F; + } + break; + case L2CAP_EV_RECV_REQSEQ_AND_FBIT: + l2cap_process_reqseq(chan, control->reqseq); + + /* Fall through */ + + case L2CAP_EV_RECV_FBIT: + if (control && control->final) { + __clear_monitor_timer(chan); + if (chan->unacked_frames > 0) + __set_retrans_timer(chan); + chan->retry_count = 0; + chan->tx_state = L2CAP_TX_STATE_XMIT; + BT_DBG("recv fbit tx_state 0x2.2%x", chan->tx_state); + } + break; + case L2CAP_EV_EXPLICIT_POLL: + /* Ignore */ + break; + case L2CAP_EV_MONITOR_TO: + if (chan->max_tx == 0 || chan->retry_count < chan->max_tx) { + l2cap_send_rr_or_rnr(chan, 1); + __set_monitor_timer(chan); + chan->retry_count++; + } else { + l2cap_send_disconn_req(chan->conn, chan, ECONNABORTED); + } + break; + default: + break; + } +} + +static void l2cap_tx(struct l2cap_chan *chan, struct l2cap_ctrl *control, + struct sk_buff_head *skbs, u8 event) +{ + BT_DBG("chan %p, control %p, skbs %p, event %d, state %d", + chan, control, skbs, event, chan->tx_state); + + switch (chan->tx_state) { + case L2CAP_TX_STATE_XMIT: + l2cap_tx_state_xmit(chan, control, skbs, event); + break; + case L2CAP_TX_STATE_WAIT_F: + l2cap_tx_state_wait_f(chan, control, skbs, event); + break; + default: + /* Ignore event */ + break; + } +} + +static void l2cap_pass_to_tx(struct l2cap_chan *chan, + struct l2cap_ctrl *control) +{ + BT_DBG("chan %p, control %p", chan, control); + l2cap_tx(chan, control, NULL, L2CAP_EV_RECV_REQSEQ_AND_FBIT); +} + +static void l2cap_pass_to_tx_fbit(struct l2cap_chan *chan, + struct l2cap_ctrl *control) +{ + BT_DBG("chan %p, control %p", chan, control); + l2cap_tx(chan, control, NULL, L2CAP_EV_RECV_FBIT); +} + /* Copy frame to all raw sockets on that connection */ static void l2cap_raw_recv(struct l2cap_conn *conn, struct sk_buff *skb) { @@ -2170,7 +2528,7 @@ static void l2cap_raw_recv(struct l2cap_conn *conn, struct sk_buff *skb) if (!nskb) continue; - if (chan->ops->recv(chan->data, nskb)) + if (chan->ops->recv(chan, nskb)) kfree_skb(nskb); } @@ -2178,16 +2536,16 @@ static void l2cap_raw_recv(struct l2cap_conn *conn, struct sk_buff *skb) } /* ---- L2CAP signalling commands ---- */ -static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, - u8 code, u8 ident, u16 dlen, void *data) +static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, u8 code, + u8 ident, u16 dlen, void *data) { struct sk_buff *skb, **frag; struct l2cap_cmd_hdr *cmd; struct l2cap_hdr *lh; int len, count; - BT_DBG("conn %p, code 0x%2.2x, ident 0x%2.2x, len %d", - conn, code, ident, dlen); + BT_DBG("conn %p, code 0x%2.2x, ident 0x%2.2x, len %u", + conn, code, ident, dlen); len = L2CAP_HDR_SIZE + L2CAP_CMD_HDR_SIZE + dlen; count = min_t(unsigned int, conn->mtu, len); @@ -2200,9 +2558,9 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, lh->len = cpu_to_le16(L2CAP_CMD_HDR_SIZE + dlen); if (conn->hcon->type == LE_LINK) - lh->cid = cpu_to_le16(L2CAP_CID_LE_SIGNALING); + lh->cid = __constant_cpu_to_le16(L2CAP_CID_LE_SIGNALING); else - lh->cid = cpu_to_le16(L2CAP_CID_SIGNALING); + lh->cid = __constant_cpu_to_le16(L2CAP_CID_SIGNALING); cmd = (struct l2cap_cmd_hdr *) skb_put(skb, L2CAP_CMD_HDR_SIZE); cmd->code = code; @@ -2270,7 +2628,7 @@ static inline int l2cap_get_conf_opt(void **ptr, int *type, int *olen, unsigned break; } - BT_DBG("type 0x%2.2x len %d val 0x%lx", *type, opt->len, *val); + BT_DBG("type 0x%2.2x len %u val 0x%lx", *type, opt->len, *val); return len; } @@ -2278,7 +2636,7 @@ static void l2cap_add_conf_opt(void **ptr, u8 type, u8 len, unsigned long val) { struct l2cap_conf_opt *opt = *ptr; - BT_DBG("type 0x%2.2x len %d val 0x%lx", type, len, val); + BT_DBG("type 0x%2.2x len %u val 0x%lx", type, len, val); opt->type = type; opt->len = len; @@ -2314,8 +2672,8 @@ static void l2cap_add_opt_efs(void **ptr, struct l2cap_chan *chan) efs.stype = chan->local_stype; efs.msdu = cpu_to_le16(chan->local_msdu); efs.sdu_itime = cpu_to_le32(chan->local_sdu_itime); - efs.acc_lat = cpu_to_le32(L2CAP_DEFAULT_ACC_LAT); - efs.flush_to = cpu_to_le32(L2CAP_DEFAULT_FLUSH_TO); + efs.acc_lat = __constant_cpu_to_le32(L2CAP_DEFAULT_ACC_LAT); + efs.flush_to = __constant_cpu_to_le32(L2CAP_DEFAULT_FLUSH_TO); break; case L2CAP_MODE_STREAMING: @@ -2338,20 +2696,24 @@ static void l2cap_add_opt_efs(void **ptr, struct l2cap_chan *chan) static void l2cap_ack_timeout(struct work_struct *work) { struct l2cap_chan *chan = container_of(work, struct l2cap_chan, - ack_timer.work); + ack_timer.work); + u16 frames_to_ack; BT_DBG("chan %p", chan); l2cap_chan_lock(chan); - __l2cap_send_ack(chan); + frames_to_ack = __seq_offset(chan, chan->buffer_seq, + chan->last_acked_seq); - l2cap_chan_unlock(chan); + if (frames_to_ack) + l2cap_send_rr_or_rnr(chan, 0); + l2cap_chan_unlock(chan); l2cap_chan_put(chan); } -static inline int l2cap_ertm_init(struct l2cap_chan *chan) +int l2cap_ertm_init(struct l2cap_chan *chan) { int err; @@ -2360,7 +2722,6 @@ static inline int l2cap_ertm_init(struct l2cap_chan *chan) chan->expected_ack_seq = 0; chan->unacked_frames = 0; chan->buffer_seq = 0; - chan->num_acked = 0; chan->frames_sent = 0; chan->last_acked_seq = 0; chan->sdu = NULL; @@ -2381,12 +2742,15 @@ static inline int l2cap_ertm_init(struct l2cap_chan *chan) skb_queue_head_init(&chan->srej_q); - INIT_LIST_HEAD(&chan->srej_l); err = l2cap_seq_list_init(&chan->srej_list, chan->tx_win); if (err < 0) return err; - return l2cap_seq_list_init(&chan->retrans_list, chan->remote_tx_win); + err = l2cap_seq_list_init(&chan->retrans_list, chan->remote_tx_win); + if (err < 0) + l2cap_seq_list_free(&chan->srej_list); + + return err; } static inline __u8 l2cap_select_mode(__u8 mode, __u16 remote_feat_mask) @@ -2424,6 +2788,7 @@ static inline void l2cap_txwin_setup(struct l2cap_chan *chan) L2CAP_DEFAULT_TX_WINDOW); chan->tx_win_max = L2CAP_DEFAULT_TX_WINDOW; } + chan->ack_win = chan->tx_win; } static int l2cap_build_conf_req(struct l2cap_chan *chan, void *data) @@ -2512,6 +2877,7 @@ done: break; case L2CAP_MODE_STREAMING: + l2cap_txwin_setup(chan); rfc.mode = L2CAP_MODE_STREAMING; rfc.txwin_size = 0; rfc.max_transmit = 0; @@ -2542,7 +2908,7 @@ done: } req->dcid = cpu_to_le16(chan->dcid); - req->flags = cpu_to_le16(0); + req->flags = __constant_cpu_to_le16(0); return ptr - data; } @@ -2762,7 +3128,7 @@ done: } rsp->scid = cpu_to_le16(chan->dcid); rsp->result = cpu_to_le16(result); - rsp->flags = cpu_to_le16(0x0000); + rsp->flags = __constant_cpu_to_le16(0); return ptr - data; } @@ -2812,10 +3178,9 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, voi break; case L2CAP_CONF_EWS: - chan->tx_win = min_t(u16, val, - L2CAP_DEFAULT_EXT_WINDOW); + chan->ack_win = min_t(u16, val, chan->ack_win); l2cap_add_conf_opt(&ptr, L2CAP_CONF_EWS, 2, - chan->tx_win); + chan->tx_win); break; case L2CAP_CONF_EFS: @@ -2844,6 +3209,9 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, voi chan->retrans_timeout = le16_to_cpu(rfc.retrans_timeout); chan->monitor_timeout = le16_to_cpu(rfc.monitor_timeout); chan->mps = le16_to_cpu(rfc.max_pdu_size); + if (!test_bit(FLAG_EXT_CTRL, &chan->flags)) + chan->ack_win = min_t(u16, chan->ack_win, + rfc.txwin_size); if (test_bit(FLAG_EFS_ENABLE, &chan->flags)) { chan->local_msdu = le16_to_cpu(efs.msdu); @@ -2861,7 +3229,7 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, voi } req->dcid = cpu_to_le16(chan->dcid); - req->flags = cpu_to_le16(0x0000); + req->flags = __constant_cpu_to_le16(0); return ptr - data; } @@ -2888,8 +3256,8 @@ void __l2cap_connect_rsp_defer(struct l2cap_chan *chan) rsp.scid = cpu_to_le16(chan->dcid); rsp.dcid = cpu_to_le16(chan->scid); - rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS); - rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); + rsp.result = __constant_cpu_to_le16(L2CAP_CR_SUCCESS); + rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, sizeof(rsp), &rsp); @@ -2905,7 +3273,17 @@ static void l2cap_conf_rfc_get(struct l2cap_chan *chan, void *rsp, int len) { int type, olen; unsigned long val; - struct l2cap_conf_rfc rfc; + /* Use sane default values in case a misbehaving remote device + * did not send an RFC or extended window size option. + */ + u16 txwin_ext = chan->ack_win; + struct l2cap_conf_rfc rfc = { + .mode = chan->mode, + .retrans_timeout = __constant_cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO), + .monitor_timeout = __constant_cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO), + .max_pdu_size = cpu_to_le16(chan->imtu), + .txwin_size = min_t(u16, chan->ack_win, L2CAP_DEFAULT_TX_WINDOW), + }; BT_DBG("chan %p, rsp %p, len %d", chan, rsp, len); @@ -2915,32 +3293,27 @@ static void l2cap_conf_rfc_get(struct l2cap_chan *chan, void *rsp, int len) while (len >= L2CAP_CONF_OPT_SIZE) { len -= l2cap_get_conf_opt(&rsp, &type, &olen, &val); - if (type != L2CAP_CONF_RFC) - continue; - - if (olen != sizeof(rfc)) + switch (type) { + case L2CAP_CONF_RFC: + if (olen == sizeof(rfc)) + memcpy(&rfc, (void *)val, olen); break; - - memcpy(&rfc, (void *)val, olen); - goto done; + case L2CAP_CONF_EWS: + txwin_ext = val; + break; + } } - /* Use sane default values in case a misbehaving remote device - * did not send an RFC option. - */ - rfc.mode = chan->mode; - rfc.retrans_timeout = cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO); - rfc.monitor_timeout = cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO); - rfc.max_pdu_size = cpu_to_le16(chan->imtu); - - BT_ERR("Expected RFC option was not found, using defaults"); - -done: switch (rfc.mode) { case L2CAP_MODE_ERTM: chan->retrans_timeout = le16_to_cpu(rfc.retrans_timeout); chan->monitor_timeout = le16_to_cpu(rfc.monitor_timeout); - chan->mps = le16_to_cpu(rfc.max_pdu_size); + chan->mps = le16_to_cpu(rfc.max_pdu_size); + if (test_bit(FLAG_EXT_CTRL, &chan->flags)) + chan->ack_win = min_t(u16, chan->ack_win, txwin_ext); + else + chan->ack_win = min_t(u16, chan->ack_win, + rfc.txwin_size); break; case L2CAP_MODE_STREAMING: chan->mps = le16_to_cpu(rfc.max_pdu_size); @@ -2993,7 +3366,7 @@ static inline int l2cap_connect_req(struct l2cap_conn *conn, struct l2cap_cmd_hd lock_sock(parent); /* Check if the ACL is secure enough (if not SDP) */ - if (psm != cpu_to_le16(0x0001) && + if (psm != __constant_cpu_to_le16(L2CAP_PSM_SDP) && !hci_conn_check_link_mode(conn->hcon)) { conn->disc_reason = HCI_ERROR_AUTH_FAILURE; result = L2CAP_CR_SEC_BLOCK; @@ -3002,25 +3375,16 @@ static inline int l2cap_connect_req(struct l2cap_conn *conn, struct l2cap_cmd_hd result = L2CAP_CR_NO_MEM; - /* Check for backlog size */ - if (sk_acceptq_is_full(parent)) { - BT_DBG("backlog full %d", parent->sk_ack_backlog); + /* Check if we already have channel with that dcid */ + if (__l2cap_get_chan_by_dcid(conn, scid)) goto response; - } - chan = pchan->ops->new_connection(pchan->data); + chan = pchan->ops->new_connection(pchan); if (!chan) goto response; sk = chan->sk; - /* Check if we already have channel with that dcid */ - if (__l2cap_get_chan_by_dcid(conn, scid)) { - sock_set_flag(sk, SOCK_ZAPPED); - chan->ops->close(chan->data); - goto response; - } - hci_conn_hold(conn->hcon); bacpy(&bt_sk(sk)->src, conn->src); @@ -3074,7 +3438,7 @@ sendresp: if (result == L2CAP_CR_PEND && status == L2CAP_CS_NO_INFO) { struct l2cap_info_req info; - info.type = cpu_to_le16(L2CAP_IT_FEAT_MASK); + info.type = __constant_cpu_to_le16(L2CAP_IT_FEAT_MASK); conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_SENT; conn->info_ident = l2cap_get_ident(conn); @@ -3196,7 +3560,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr if (chan->state != BT_CONFIG && chan->state != BT_CONNECT2) { struct l2cap_cmd_rej_cid rej; - rej.reason = cpu_to_le16(L2CAP_REJ_INVALID_CID); + rej.reason = __constant_cpu_to_le16(L2CAP_REJ_INVALID_CID); rej.scid = cpu_to_le16(chan->scid); rej.dcid = cpu_to_le16(chan->dcid); @@ -3218,11 +3582,11 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr memcpy(chan->conf_req + chan->conf_len, req->data, len); chan->conf_len += len; - if (flags & 0x0001) { + if (flags & L2CAP_CONF_FLAG_CONTINUATION) { /* Incomplete config. Send empty response. */ l2cap_send_cmd(conn, cmd->ident, L2CAP_CONF_RSP, l2cap_build_conf_rsp(chan, rsp, - L2CAP_CONF_SUCCESS, 0x0001), rsp); + L2CAP_CONF_SUCCESS, flags), rsp); goto unlock; } @@ -3245,8 +3609,6 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr if (test_bit(CONF_INPUT_DONE, &chan->conf_state)) { set_default_fcs(chan); - l2cap_state_change(chan, BT_CONNECTED); - if (chan->mode == L2CAP_MODE_ERTM || chan->mode == L2CAP_MODE_STREAMING) err = l2cap_ertm_init(chan); @@ -3278,7 +3640,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr l2cap_send_cmd(conn, cmd->ident, L2CAP_CONF_RSP, l2cap_build_conf_rsp(chan, rsp, - L2CAP_CONF_SUCCESS, 0x0000), rsp); + L2CAP_CONF_SUCCESS, flags), rsp); } unlock: @@ -3369,7 +3731,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr goto done; } - if (flags & 0x01) + if (flags & L2CAP_CONF_FLAG_CONTINUATION) goto done; set_bit(CONF_INPUT_DONE, &chan->conf_state); @@ -3377,7 +3739,6 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr if (test_bit(CONF_OUTPUT_DONE, &chan->conf_state)) { set_default_fcs(chan); - l2cap_state_change(chan, BT_CONNECTED); if (chan->mode == L2CAP_MODE_ERTM || chan->mode == L2CAP_MODE_STREAMING) err = l2cap_ertm_init(chan); @@ -3431,7 +3792,7 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, struct l2cap_cmd l2cap_chan_unlock(chan); - chan->ops->close(chan->data); + chan->ops->close(chan); l2cap_chan_put(chan); mutex_unlock(&conn->chan_lock); @@ -3465,7 +3826,7 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, struct l2cap_cmd l2cap_chan_unlock(chan); - chan->ops->close(chan->data); + chan->ops->close(chan); l2cap_chan_put(chan); mutex_unlock(&conn->chan_lock); @@ -3486,8 +3847,8 @@ static inline int l2cap_information_req(struct l2cap_conn *conn, struct l2cap_cm u8 buf[8]; u32 feat_mask = l2cap_feat_mask; struct l2cap_info_rsp *rsp = (struct l2cap_info_rsp *) buf; - rsp->type = cpu_to_le16(L2CAP_IT_FEAT_MASK); - rsp->result = cpu_to_le16(L2CAP_IR_SUCCESS); + rsp->type = __constant_cpu_to_le16(L2CAP_IT_FEAT_MASK); + rsp->result = __constant_cpu_to_le16(L2CAP_IR_SUCCESS); if (!disable_ertm) feat_mask |= L2CAP_FEAT_ERTM | L2CAP_FEAT_STREAMING | L2CAP_FEAT_FCS; @@ -3507,15 +3868,15 @@ static inline int l2cap_information_req(struct l2cap_conn *conn, struct l2cap_cm else l2cap_fixed_chan[0] &= ~L2CAP_FC_A2MP; - rsp->type = cpu_to_le16(L2CAP_IT_FIXED_CHAN); - rsp->result = cpu_to_le16(L2CAP_IR_SUCCESS); + rsp->type = __constant_cpu_to_le16(L2CAP_IT_FIXED_CHAN); + rsp->result = __constant_cpu_to_le16(L2CAP_IR_SUCCESS); memcpy(rsp->data, l2cap_fixed_chan, sizeof(l2cap_fixed_chan)); l2cap_send_cmd(conn, cmd->ident, L2CAP_INFO_RSP, sizeof(buf), buf); } else { struct l2cap_info_rsp rsp; rsp.type = cpu_to_le16(type); - rsp.result = cpu_to_le16(L2CAP_IR_NOTSUPP); + rsp.result = __constant_cpu_to_le16(L2CAP_IR_NOTSUPP); l2cap_send_cmd(conn, cmd->ident, L2CAP_INFO_RSP, sizeof(rsp), &rsp); } @@ -3555,7 +3916,7 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn, struct l2cap_cm if (conn->feat_mask & L2CAP_FEAT_FIXED_CHAN) { struct l2cap_info_req req; - req.type = cpu_to_le16(L2CAP_IT_FIXED_CHAN); + req.type = __constant_cpu_to_le16(L2CAP_IT_FIXED_CHAN); conn->info_ident = l2cap_get_ident(conn); @@ -3598,7 +3959,7 @@ static inline int l2cap_create_channel_req(struct l2cap_conn *conn, psm = le16_to_cpu(req->psm); scid = le16_to_cpu(req->scid); - BT_DBG("psm %d, scid %d, amp_id %d", psm, scid, req->amp_id); + BT_DBG("psm 0x%2.2x, scid 0x%4.4x, amp_id %d", psm, scid, req->amp_id); /* Placeholder: Always reject */ rsp.dcid = 0; @@ -3621,11 +3982,11 @@ static inline int l2cap_create_channel_rsp(struct l2cap_conn *conn, } static void l2cap_send_move_chan_rsp(struct l2cap_conn *conn, u8 ident, - u16 icid, u16 result) + u16 icid, u16 result) { struct l2cap_move_chan_rsp rsp; - BT_DBG("icid %d, result %d", icid, result); + BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result); rsp.icid = cpu_to_le16(icid); rsp.result = cpu_to_le16(result); @@ -3634,12 +3995,13 @@ static void l2cap_send_move_chan_rsp(struct l2cap_conn *conn, u8 ident, } static void l2cap_send_move_chan_cfm(struct l2cap_conn *conn, - struct l2cap_chan *chan, u16 icid, u16 result) + struct l2cap_chan *chan, + u16 icid, u16 result) { struct l2cap_move_chan_cfm cfm; u8 ident; - BT_DBG("icid %d, result %d", icid, result); + BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result); ident = l2cap_get_ident(conn); if (chan) @@ -3652,18 +4014,19 @@ static void l2cap_send_move_chan_cfm(struct l2cap_conn *conn, } static void l2cap_send_move_chan_cfm_rsp(struct l2cap_conn *conn, u8 ident, - u16 icid) + u16 icid) { struct l2cap_move_chan_cfm_rsp rsp; - BT_DBG("icid %d", icid); + BT_DBG("icid 0x%4.4x", icid); rsp.icid = cpu_to_le16(icid); l2cap_send_cmd(conn, ident, L2CAP_MOVE_CHAN_CFM_RSP, sizeof(rsp), &rsp); } static inline int l2cap_move_channel_req(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, u16 cmd_len, void *data) + struct l2cap_cmd_hdr *cmd, + u16 cmd_len, void *data) { struct l2cap_move_chan_req *req = data; u16 icid = 0; @@ -3674,7 +4037,7 @@ static inline int l2cap_move_channel_req(struct l2cap_conn *conn, icid = le16_to_cpu(req->icid); - BT_DBG("icid %d, dest_amp_id %d", icid, req->dest_amp_id); + BT_DBG("icid 0x%4.4x, dest_amp_id %d", icid, req->dest_amp_id); if (!enable_hs) return -EINVAL; @@ -3686,7 +4049,8 @@ static inline int l2cap_move_channel_req(struct l2cap_conn *conn, } static inline int l2cap_move_channel_rsp(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, u16 cmd_len, void *data) + struct l2cap_cmd_hdr *cmd, + u16 cmd_len, void *data) { struct l2cap_move_chan_rsp *rsp = data; u16 icid, result; @@ -3697,7 +4061,7 @@ static inline int l2cap_move_channel_rsp(struct l2cap_conn *conn, icid = le16_to_cpu(rsp->icid); result = le16_to_cpu(rsp->result); - BT_DBG("icid %d, result %d", icid, result); + BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result); /* Placeholder: Always unconfirmed */ l2cap_send_move_chan_cfm(conn, NULL, icid, L2CAP_MC_UNCONFIRMED); @@ -3706,7 +4070,8 @@ static inline int l2cap_move_channel_rsp(struct l2cap_conn *conn, } static inline int l2cap_move_channel_confirm(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, u16 cmd_len, void *data) + struct l2cap_cmd_hdr *cmd, + u16 cmd_len, void *data) { struct l2cap_move_chan_cfm *cfm = data; u16 icid, result; @@ -3717,7 +4082,7 @@ static inline int l2cap_move_channel_confirm(struct l2cap_conn *conn, icid = le16_to_cpu(cfm->icid); result = le16_to_cpu(cfm->result); - BT_DBG("icid %d, result %d", icid, result); + BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result); l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid); @@ -3725,7 +4090,8 @@ static inline int l2cap_move_channel_confirm(struct l2cap_conn *conn, } static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, u16 cmd_len, void *data) + struct l2cap_cmd_hdr *cmd, + u16 cmd_len, void *data) { struct l2cap_move_chan_cfm_rsp *rsp = data; u16 icid; @@ -3735,7 +4101,7 @@ static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn, icid = le16_to_cpu(rsp->icid); - BT_DBG("icid %d", icid); + BT_DBG("icid 0x%4.4x", icid); return 0; } @@ -3790,9 +4156,9 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, err = l2cap_check_conn_param(min, max, latency, to_multiplier); if (err) - rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED); + rsp.result = __constant_cpu_to_le16(L2CAP_CONN_PARAM_REJECTED); else - rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_ACCEPTED); + rsp.result = __constant_cpu_to_le16(L2CAP_CONN_PARAM_ACCEPTED); l2cap_send_cmd(conn, cmd->ident, L2CAP_CONN_PARAM_UPDATE_RSP, sizeof(rsp), &rsp); @@ -3940,7 +4306,7 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn, BT_ERR("Wrong link type (%d)", err); /* FIXME: Map err to a valid reason */ - rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD); + rej.reason = __constant_cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD); l2cap_send_cmd(conn, cmd.ident, L2CAP_COMMAND_REJ, sizeof(rej), &rej); } @@ -3972,65 +4338,38 @@ static int l2cap_check_fcs(struct l2cap_chan *chan, struct sk_buff *skb) return 0; } -static inline void l2cap_send_i_or_rr_or_rnr(struct l2cap_chan *chan) +static void l2cap_send_i_or_rr_or_rnr(struct l2cap_chan *chan) { - u32 control = 0; + struct l2cap_ctrl control; - chan->frames_sent = 0; + BT_DBG("chan %p", chan); - control |= __set_reqseq(chan, chan->buffer_seq); + memset(&control, 0, sizeof(control)); + control.sframe = 1; + control.final = 1; + control.reqseq = chan->buffer_seq; + set_bit(CONN_SEND_FBIT, &chan->conn_state); if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { - control |= __set_ctrl_super(chan, L2CAP_SUPER_RNR); - l2cap_send_sframe(chan, control); - set_bit(CONN_RNR_SENT, &chan->conn_state); + control.super = L2CAP_SUPER_RNR; + l2cap_send_sframe(chan, &control); } - if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state)) - l2cap_retransmit_frames(chan); + if (test_and_clear_bit(CONN_REMOTE_BUSY, &chan->conn_state) && + chan->unacked_frames > 0) + __set_retrans_timer(chan); + /* Send pending iframes */ l2cap_ertm_send(chan); if (!test_bit(CONN_LOCAL_BUSY, &chan->conn_state) && - chan->frames_sent == 0) { - control |= __set_ctrl_super(chan, L2CAP_SUPER_RR); - l2cap_send_sframe(chan, control); - } -} - -static int l2cap_add_to_srej_queue(struct l2cap_chan *chan, struct sk_buff *skb, u16 tx_seq, u8 sar) -{ - struct sk_buff *next_skb; - int tx_seq_offset, next_tx_seq_offset; - - bt_cb(skb)->control.txseq = tx_seq; - bt_cb(skb)->control.sar = sar; - - next_skb = skb_peek(&chan->srej_q); - - tx_seq_offset = __seq_offset(chan, tx_seq, chan->buffer_seq); - - while (next_skb) { - if (bt_cb(next_skb)->control.txseq == tx_seq) - return -EINVAL; - - next_tx_seq_offset = __seq_offset(chan, - bt_cb(next_skb)->control.txseq, chan->buffer_seq); - - if (next_tx_seq_offset > tx_seq_offset) { - __skb_queue_before(&chan->srej_q, next_skb, skb); - return 0; - } - - if (skb_queue_is_last(&chan->srej_q, next_skb)) - next_skb = NULL; - else - next_skb = skb_queue_next(&chan->srej_q, next_skb); + test_bit(CONN_SEND_FBIT, &chan->conn_state)) { + /* F-bit wasn't sent in an s-frame or i-frame yet, so + * send it now. + */ + control.super = L2CAP_SUPER_RR; + l2cap_send_sframe(chan, &control); } - - __skb_queue_tail(&chan->srej_q, skb); - - return 0; } static void append_skb_frag(struct sk_buff *skb, @@ -4052,16 +4391,17 @@ static void append_skb_frag(struct sk_buff *skb, skb->truesize += new_frag->truesize; } -static int l2cap_reassemble_sdu(struct l2cap_chan *chan, struct sk_buff *skb, u32 control) +static int l2cap_reassemble_sdu(struct l2cap_chan *chan, struct sk_buff *skb, + struct l2cap_ctrl *control) { int err = -EINVAL; - switch (__get_ctrl_sar(chan, control)) { + switch (control->sar) { case L2CAP_SAR_UNSEGMENTED: if (chan->sdu) break; - err = chan->ops->recv(chan->data, skb); + err = chan->ops->recv(chan, skb); break; case L2CAP_SAR_START: @@ -4111,7 +4451,7 @@ static int l2cap_reassemble_sdu(struct l2cap_chan *chan, struct sk_buff *skb, u3 if (chan->sdu->len != chan->sdu_len) break; - err = chan->ops->recv(chan->data, chan->sdu); + err = chan->ops->recv(chan, chan->sdu); if (!err) { /* Reassembly complete */ @@ -4133,448 +4473,609 @@ static int l2cap_reassemble_sdu(struct l2cap_chan *chan, struct sk_buff *skb, u3 return err; } -static void l2cap_ertm_enter_local_busy(struct l2cap_chan *chan) +void l2cap_chan_busy(struct l2cap_chan *chan, int busy) { - BT_DBG("chan %p, Enter local busy", chan); + u8 event; - set_bit(CONN_LOCAL_BUSY, &chan->conn_state); - l2cap_seq_list_clear(&chan->srej_list); + if (chan->mode != L2CAP_MODE_ERTM) + return; - __set_ack_timer(chan); + event = busy ? L2CAP_EV_LOCAL_BUSY_DETECTED : L2CAP_EV_LOCAL_BUSY_CLEAR; + l2cap_tx(chan, NULL, NULL, event); } -static void l2cap_ertm_exit_local_busy(struct l2cap_chan *chan) +static int l2cap_rx_queued_iframes(struct l2cap_chan *chan) { - u32 control; - - if (!test_bit(CONN_RNR_SENT, &chan->conn_state)) - goto done; + int err = 0; + /* Pass sequential frames to l2cap_reassemble_sdu() + * until a gap is encountered. + */ - control = __set_reqseq(chan, chan->buffer_seq); - control |= __set_ctrl_poll(chan); - control |= __set_ctrl_super(chan, L2CAP_SUPER_RR); - l2cap_send_sframe(chan, control); - chan->retry_count = 1; + BT_DBG("chan %p", chan); - __clear_retrans_timer(chan); - __set_monitor_timer(chan); + while (!test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { + struct sk_buff *skb; + BT_DBG("Searching for skb with txseq %d (queue len %d)", + chan->buffer_seq, skb_queue_len(&chan->srej_q)); - set_bit(CONN_WAIT_F, &chan->conn_state); + skb = l2cap_ertm_seq_in_queue(&chan->srej_q, chan->buffer_seq); -done: - clear_bit(CONN_LOCAL_BUSY, &chan->conn_state); - clear_bit(CONN_RNR_SENT, &chan->conn_state); + if (!skb) + break; - BT_DBG("chan %p, Exit local busy", chan); -} + skb_unlink(skb, &chan->srej_q); + chan->buffer_seq = __next_seq(chan, chan->buffer_seq); + err = l2cap_reassemble_sdu(chan, skb, &bt_cb(skb)->control); + if (err) + break; + } -void l2cap_chan_busy(struct l2cap_chan *chan, int busy) -{ - if (chan->mode == L2CAP_MODE_ERTM) { - if (busy) - l2cap_ertm_enter_local_busy(chan); - else - l2cap_ertm_exit_local_busy(chan); + if (skb_queue_empty(&chan->srej_q)) { + chan->rx_state = L2CAP_RX_STATE_RECV; + l2cap_send_ack(chan); } + + return err; } -static void l2cap_check_srej_gap(struct l2cap_chan *chan, u16 tx_seq) +static void l2cap_handle_srej(struct l2cap_chan *chan, + struct l2cap_ctrl *control) { struct sk_buff *skb; - u32 control; - while ((skb = skb_peek(&chan->srej_q)) && - !test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { - int err; + BT_DBG("chan %p, control %p", chan, control); - if (bt_cb(skb)->control.txseq != tx_seq) - break; + if (control->reqseq == chan->next_tx_seq) { + BT_DBG("Invalid reqseq %d, disconnecting", control->reqseq); + l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + return; + } - skb = skb_dequeue(&chan->srej_q); - control = __set_ctrl_sar(chan, bt_cb(skb)->control.sar); - err = l2cap_reassemble_sdu(chan, skb, control); + skb = l2cap_ertm_seq_in_queue(&chan->tx_q, control->reqseq); - if (err < 0) { - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); - break; - } + if (skb == NULL) { + BT_DBG("Seq %d not available for retransmission", + control->reqseq); + return; + } - chan->buffer_seq_srej = __next_seq(chan, chan->buffer_seq_srej); - tx_seq = __next_seq(chan, tx_seq); + if (chan->max_tx != 0 && bt_cb(skb)->control.retries >= chan->max_tx) { + BT_DBG("Retry limit exceeded (%d)", chan->max_tx); + l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + return; } -} -static void l2cap_resend_srejframe(struct l2cap_chan *chan, u16 tx_seq) -{ - struct srej_list *l, *tmp; - u32 control; + clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); - list_for_each_entry_safe(l, tmp, &chan->srej_l, list) { - if (l->tx_seq == tx_seq) { - list_del(&l->list); - kfree(l); - return; + if (control->poll) { + l2cap_pass_to_tx(chan, control); + + set_bit(CONN_SEND_FBIT, &chan->conn_state); + l2cap_retransmit(chan, control); + l2cap_ertm_send(chan); + + if (chan->tx_state == L2CAP_TX_STATE_WAIT_F) { + set_bit(CONN_SREJ_ACT, &chan->conn_state); + chan->srej_save_reqseq = control->reqseq; + } + } else { + l2cap_pass_to_tx_fbit(chan, control); + + if (control->final) { + if (chan->srej_save_reqseq != control->reqseq || + !test_and_clear_bit(CONN_SREJ_ACT, + &chan->conn_state)) + l2cap_retransmit(chan, control); + } else { + l2cap_retransmit(chan, control); + if (chan->tx_state == L2CAP_TX_STATE_WAIT_F) { + set_bit(CONN_SREJ_ACT, &chan->conn_state); + chan->srej_save_reqseq = control->reqseq; + } } - control = __set_ctrl_super(chan, L2CAP_SUPER_SREJ); - control |= __set_reqseq(chan, l->tx_seq); - l2cap_send_sframe(chan, control); - list_del(&l->list); - list_add_tail(&l->list, &chan->srej_l); } } -static int l2cap_send_srejframe(struct l2cap_chan *chan, u16 tx_seq) +static void l2cap_handle_rej(struct l2cap_chan *chan, + struct l2cap_ctrl *control) { - struct srej_list *new; - u32 control; - - while (tx_seq != chan->expected_tx_seq) { - control = __set_ctrl_super(chan, L2CAP_SUPER_SREJ); - control |= __set_reqseq(chan, chan->expected_tx_seq); - l2cap_seq_list_append(&chan->srej_list, chan->expected_tx_seq); - l2cap_send_sframe(chan, control); + struct sk_buff *skb; - new = kzalloc(sizeof(struct srej_list), GFP_ATOMIC); - if (!new) - return -ENOMEM; + BT_DBG("chan %p, control %p", chan, control); - new->tx_seq = chan->expected_tx_seq; + if (control->reqseq == chan->next_tx_seq) { + BT_DBG("Invalid reqseq %d, disconnecting", control->reqseq); + l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + return; + } - chan->expected_tx_seq = __next_seq(chan, chan->expected_tx_seq); + skb = l2cap_ertm_seq_in_queue(&chan->tx_q, control->reqseq); - list_add_tail(&new->list, &chan->srej_l); + if (chan->max_tx && skb && + bt_cb(skb)->control.retries >= chan->max_tx) { + BT_DBG("Retry limit exceeded (%d)", chan->max_tx); + l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + return; } - chan->expected_tx_seq = __next_seq(chan, chan->expected_tx_seq); + clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); + + l2cap_pass_to_tx(chan, control); - return 0; + if (control->final) { + if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state)) + l2cap_retransmit_all(chan, control); + } else { + l2cap_retransmit_all(chan, control); + l2cap_ertm_send(chan); + if (chan->tx_state == L2CAP_TX_STATE_WAIT_F) + set_bit(CONN_REJ_ACT, &chan->conn_state); + } } -static inline int l2cap_data_channel_iframe(struct l2cap_chan *chan, u32 rx_control, struct sk_buff *skb) +static u8 l2cap_classify_txseq(struct l2cap_chan *chan, u16 txseq) { - u16 tx_seq = __get_txseq(chan, rx_control); - u16 req_seq = __get_reqseq(chan, rx_control); - u8 sar = __get_ctrl_sar(chan, rx_control); - int tx_seq_offset, expected_tx_seq_offset; - int num_to_ack = (chan->tx_win/6) + 1; - int err = 0; + BT_DBG("chan %p, txseq %d", chan, txseq); - BT_DBG("chan %p len %d tx_seq %d rx_control 0x%8.8x", chan, skb->len, - tx_seq, rx_control); + BT_DBG("last_acked_seq %d, expected_tx_seq %d", chan->last_acked_seq, + chan->expected_tx_seq); - if (__is_ctrl_final(chan, rx_control) && - test_bit(CONN_WAIT_F, &chan->conn_state)) { - __clear_monitor_timer(chan); - if (chan->unacked_frames > 0) - __set_retrans_timer(chan); - clear_bit(CONN_WAIT_F, &chan->conn_state); - } + if (chan->rx_state == L2CAP_RX_STATE_SREJ_SENT) { + if (__seq_offset(chan, txseq, chan->last_acked_seq) >= + chan->tx_win) { + /* See notes below regarding "double poll" and + * invalid packets. + */ + if (chan->tx_win <= ((chan->tx_win_max + 1) >> 1)) { + BT_DBG("Invalid/Ignore - after SREJ"); + return L2CAP_TXSEQ_INVALID_IGNORE; + } else { + BT_DBG("Invalid - in window after SREJ sent"); + return L2CAP_TXSEQ_INVALID; + } + } - chan->expected_ack_seq = req_seq; - l2cap_drop_acked_frames(chan); + if (chan->srej_list.head == txseq) { + BT_DBG("Expected SREJ"); + return L2CAP_TXSEQ_EXPECTED_SREJ; + } - tx_seq_offset = __seq_offset(chan, tx_seq, chan->buffer_seq); + if (l2cap_ertm_seq_in_queue(&chan->srej_q, txseq)) { + BT_DBG("Duplicate SREJ - txseq already stored"); + return L2CAP_TXSEQ_DUPLICATE_SREJ; + } - /* invalid tx_seq */ - if (tx_seq_offset >= chan->tx_win) { - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); - goto drop; + if (l2cap_seq_list_contains(&chan->srej_list, txseq)) { + BT_DBG("Unexpected SREJ - not requested"); + return L2CAP_TXSEQ_UNEXPECTED_SREJ; + } } - if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { - if (!test_bit(CONN_RNR_SENT, &chan->conn_state)) - l2cap_send_ack(chan); - goto drop; + if (chan->expected_tx_seq == txseq) { + if (__seq_offset(chan, txseq, chan->last_acked_seq) >= + chan->tx_win) { + BT_DBG("Invalid - txseq outside tx window"); + return L2CAP_TXSEQ_INVALID; + } else { + BT_DBG("Expected"); + return L2CAP_TXSEQ_EXPECTED; + } } - if (tx_seq == chan->expected_tx_seq) - goto expected; + if (__seq_offset(chan, txseq, chan->last_acked_seq) < + __seq_offset(chan, chan->expected_tx_seq, + chan->last_acked_seq)){ + BT_DBG("Duplicate - expected_tx_seq later than txseq"); + return L2CAP_TXSEQ_DUPLICATE; + } + + if (__seq_offset(chan, txseq, chan->last_acked_seq) >= chan->tx_win) { + /* A source of invalid packets is a "double poll" condition, + * where delays cause us to send multiple poll packets. If + * the remote stack receives and processes both polls, + * sequence numbers can wrap around in such a way that a + * resent frame has a sequence number that looks like new data + * with a sequence gap. This would trigger an erroneous SREJ + * request. + * + * Fortunately, this is impossible with a tx window that's + * less than half of the maximum sequence number, which allows + * invalid frames to be safely ignored. + * + * With tx window sizes greater than half of the tx window + * maximum, the frame is invalid and cannot be ignored. This + * causes a disconnect. + */ - if (test_bit(CONN_SREJ_SENT, &chan->conn_state)) { - struct srej_list *first; + if (chan->tx_win <= ((chan->tx_win_max + 1) >> 1)) { + BT_DBG("Invalid/Ignore - txseq outside tx window"); + return L2CAP_TXSEQ_INVALID_IGNORE; + } else { + BT_DBG("Invalid - txseq outside tx window"); + return L2CAP_TXSEQ_INVALID; + } + } else { + BT_DBG("Unexpected - txseq indicates missing frames"); + return L2CAP_TXSEQ_UNEXPECTED; + } +} - first = list_first_entry(&chan->srej_l, - struct srej_list, list); - if (tx_seq == first->tx_seq) { - l2cap_add_to_srej_queue(chan, skb, tx_seq, sar); - l2cap_check_srej_gap(chan, tx_seq); +static int l2cap_rx_state_recv(struct l2cap_chan *chan, + struct l2cap_ctrl *control, + struct sk_buff *skb, u8 event) +{ + int err = 0; + bool skb_in_use = 0; - list_del(&first->list); - kfree(first); + BT_DBG("chan %p, control %p, skb %p, event %d", chan, control, skb, + event); - if (list_empty(&chan->srej_l)) { - chan->buffer_seq = chan->buffer_seq_srej; - clear_bit(CONN_SREJ_SENT, &chan->conn_state); - l2cap_send_ack(chan); - BT_DBG("chan %p, Exit SREJ_SENT", chan); + switch (event) { + case L2CAP_EV_RECV_IFRAME: + switch (l2cap_classify_txseq(chan, control->txseq)) { + case L2CAP_TXSEQ_EXPECTED: + l2cap_pass_to_tx(chan, control); + + if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { + BT_DBG("Busy, discarding expected seq %d", + control->txseq); + break; } - } else { - struct srej_list *l; - /* duplicated tx_seq */ - if (l2cap_add_to_srej_queue(chan, skb, tx_seq, sar) < 0) - goto drop; + chan->expected_tx_seq = __next_seq(chan, + control->txseq); + + chan->buffer_seq = chan->expected_tx_seq; + skb_in_use = 1; + + err = l2cap_reassemble_sdu(chan, skb, control); + if (err) + break; - list_for_each_entry(l, &chan->srej_l, list) { - if (l->tx_seq == tx_seq) { - l2cap_resend_srejframe(chan, tx_seq); - return 0; + if (control->final) { + if (!test_and_clear_bit(CONN_REJ_ACT, + &chan->conn_state)) { + control->final = 0; + l2cap_retransmit_all(chan, control); + l2cap_ertm_send(chan); } } - err = l2cap_send_srejframe(chan, tx_seq); - if (err < 0) { - l2cap_send_disconn_req(chan->conn, chan, -err); - return err; + if (!test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) + l2cap_send_ack(chan); + break; + case L2CAP_TXSEQ_UNEXPECTED: + l2cap_pass_to_tx(chan, control); + + /* Can't issue SREJ frames in the local busy state. + * Drop this frame, it will be seen as missing + * when local busy is exited. + */ + if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { + BT_DBG("Busy, discarding unexpected seq %d", + control->txseq); + break; } - } - } else { - expected_tx_seq_offset = __seq_offset(chan, - chan->expected_tx_seq, chan->buffer_seq); - /* duplicated tx_seq */ - if (tx_seq_offset < expected_tx_seq_offset) - goto drop; - - set_bit(CONN_SREJ_SENT, &chan->conn_state); + /* There was a gap in the sequence, so an SREJ + * must be sent for each missing frame. The + * current frame is stored for later use. + */ + skb_queue_tail(&chan->srej_q, skb); + skb_in_use = 1; + BT_DBG("Queued %p (queue len %d)", skb, + skb_queue_len(&chan->srej_q)); - BT_DBG("chan %p, Enter SREJ", chan); + clear_bit(CONN_SREJ_ACT, &chan->conn_state); + l2cap_seq_list_clear(&chan->srej_list); + l2cap_send_srej(chan, control->txseq); - INIT_LIST_HEAD(&chan->srej_l); - chan->buffer_seq_srej = chan->buffer_seq; + chan->rx_state = L2CAP_RX_STATE_SREJ_SENT; + break; + case L2CAP_TXSEQ_DUPLICATE: + l2cap_pass_to_tx(chan, control); + break; + case L2CAP_TXSEQ_INVALID_IGNORE: + break; + case L2CAP_TXSEQ_INVALID: + default: + l2cap_send_disconn_req(chan->conn, chan, + ECONNRESET); + break; + } + break; + case L2CAP_EV_RECV_RR: + l2cap_pass_to_tx(chan, control); + if (control->final) { + clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); - __skb_queue_head_init(&chan->srej_q); - l2cap_add_to_srej_queue(chan, skb, tx_seq, sar); + if (!test_and_clear_bit(CONN_REJ_ACT, + &chan->conn_state)) { + control->final = 0; + l2cap_retransmit_all(chan, control); + } - /* Set P-bit only if there are some I-frames to ack. */ - if (__clear_ack_timer(chan)) - set_bit(CONN_SEND_PBIT, &chan->conn_state); + l2cap_ertm_send(chan); + } else if (control->poll) { + l2cap_send_i_or_rr_or_rnr(chan); + } else { + if (test_and_clear_bit(CONN_REMOTE_BUSY, + &chan->conn_state) && + chan->unacked_frames) + __set_retrans_timer(chan); - err = l2cap_send_srejframe(chan, tx_seq); - if (err < 0) { - l2cap_send_disconn_req(chan->conn, chan, -err); - return err; + l2cap_ertm_send(chan); } - } - return 0; - -expected: - chan->expected_tx_seq = __next_seq(chan, chan->expected_tx_seq); - - if (test_bit(CONN_SREJ_SENT, &chan->conn_state)) { - bt_cb(skb)->control.txseq = tx_seq; - bt_cb(skb)->control.sar = sar; - __skb_queue_tail(&chan->srej_q, skb); - return 0; + break; + case L2CAP_EV_RECV_RNR: + set_bit(CONN_REMOTE_BUSY, &chan->conn_state); + l2cap_pass_to_tx(chan, control); + if (control && control->poll) { + set_bit(CONN_SEND_FBIT, &chan->conn_state); + l2cap_send_rr_or_rnr(chan, 0); + } + __clear_retrans_timer(chan); + l2cap_seq_list_clear(&chan->retrans_list); + break; + case L2CAP_EV_RECV_REJ: + l2cap_handle_rej(chan, control); + break; + case L2CAP_EV_RECV_SREJ: + l2cap_handle_srej(chan, control); + break; + default: + break; } - err = l2cap_reassemble_sdu(chan, skb, rx_control); - chan->buffer_seq = __next_seq(chan, chan->buffer_seq); - - if (err < 0) { - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); - return err; + if (skb && !skb_in_use) { + BT_DBG("Freeing %p", skb); + kfree_skb(skb); } - if (__is_ctrl_final(chan, rx_control)) { - if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state)) - l2cap_retransmit_frames(chan); - } + return err; +} +static int l2cap_rx_state_srej_sent(struct l2cap_chan *chan, + struct l2cap_ctrl *control, + struct sk_buff *skb, u8 event) +{ + int err = 0; + u16 txseq = control->txseq; + bool skb_in_use = 0; + + BT_DBG("chan %p, control %p, skb %p, event %d", chan, control, skb, + event); + + switch (event) { + case L2CAP_EV_RECV_IFRAME: + switch (l2cap_classify_txseq(chan, txseq)) { + case L2CAP_TXSEQ_EXPECTED: + /* Keep frame for reassembly later */ + l2cap_pass_to_tx(chan, control); + skb_queue_tail(&chan->srej_q, skb); + skb_in_use = 1; + BT_DBG("Queued %p (queue len %d)", skb, + skb_queue_len(&chan->srej_q)); + + chan->expected_tx_seq = __next_seq(chan, txseq); + break; + case L2CAP_TXSEQ_EXPECTED_SREJ: + l2cap_seq_list_pop(&chan->srej_list); - chan->num_acked = (chan->num_acked + 1) % num_to_ack; - if (chan->num_acked == num_to_ack - 1) - l2cap_send_ack(chan); - else - __set_ack_timer(chan); + l2cap_pass_to_tx(chan, control); + skb_queue_tail(&chan->srej_q, skb); + skb_in_use = 1; + BT_DBG("Queued %p (queue len %d)", skb, + skb_queue_len(&chan->srej_q)); - return 0; + err = l2cap_rx_queued_iframes(chan); + if (err) + break; -drop: - kfree_skb(skb); - return 0; -} + break; + case L2CAP_TXSEQ_UNEXPECTED: + /* Got a frame that can't be reassembled yet. + * Save it for later, and send SREJs to cover + * the missing frames. + */ + skb_queue_tail(&chan->srej_q, skb); + skb_in_use = 1; + BT_DBG("Queued %p (queue len %d)", skb, + skb_queue_len(&chan->srej_q)); + + l2cap_pass_to_tx(chan, control); + l2cap_send_srej(chan, control->txseq); + break; + case L2CAP_TXSEQ_UNEXPECTED_SREJ: + /* This frame was requested with an SREJ, but + * some expected retransmitted frames are + * missing. Request retransmission of missing + * SREJ'd frames. + */ + skb_queue_tail(&chan->srej_q, skb); + skb_in_use = 1; + BT_DBG("Queued %p (queue len %d)", skb, + skb_queue_len(&chan->srej_q)); + + l2cap_pass_to_tx(chan, control); + l2cap_send_srej_list(chan, control->txseq); + break; + case L2CAP_TXSEQ_DUPLICATE_SREJ: + /* We've already queued this frame. Drop this copy. */ + l2cap_pass_to_tx(chan, control); + break; + case L2CAP_TXSEQ_DUPLICATE: + /* Expecting a later sequence number, so this frame + * was already received. Ignore it completely. + */ + break; + case L2CAP_TXSEQ_INVALID_IGNORE: + break; + case L2CAP_TXSEQ_INVALID: + default: + l2cap_send_disconn_req(chan->conn, chan, + ECONNRESET); + break; + } + break; + case L2CAP_EV_RECV_RR: + l2cap_pass_to_tx(chan, control); + if (control->final) { + clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); -static inline void l2cap_data_channel_rrframe(struct l2cap_chan *chan, u32 rx_control) -{ - BT_DBG("chan %p, req_seq %d ctrl 0x%8.8x", chan, - __get_reqseq(chan, rx_control), rx_control); + if (!test_and_clear_bit(CONN_REJ_ACT, + &chan->conn_state)) { + control->final = 0; + l2cap_retransmit_all(chan, control); + } - chan->expected_ack_seq = __get_reqseq(chan, rx_control); - l2cap_drop_acked_frames(chan); + l2cap_ertm_send(chan); + } else if (control->poll) { + if (test_and_clear_bit(CONN_REMOTE_BUSY, + &chan->conn_state) && + chan->unacked_frames) { + __set_retrans_timer(chan); + } - if (__is_ctrl_poll(chan, rx_control)) { - set_bit(CONN_SEND_FBIT, &chan->conn_state); - if (test_bit(CONN_SREJ_SENT, &chan->conn_state)) { - if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state) && - (chan->unacked_frames > 0)) + set_bit(CONN_SEND_FBIT, &chan->conn_state); + l2cap_send_srej_tail(chan); + } else { + if (test_and_clear_bit(CONN_REMOTE_BUSY, + &chan->conn_state) && + chan->unacked_frames) __set_retrans_timer(chan); - clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); - l2cap_send_srejtail(chan); + l2cap_send_ack(chan); + } + break; + case L2CAP_EV_RECV_RNR: + set_bit(CONN_REMOTE_BUSY, &chan->conn_state); + l2cap_pass_to_tx(chan, control); + if (control->poll) { + l2cap_send_srej_tail(chan); } else { - l2cap_send_i_or_rr_or_rnr(chan); + struct l2cap_ctrl rr_control; + memset(&rr_control, 0, sizeof(rr_control)); + rr_control.sframe = 1; + rr_control.super = L2CAP_SUPER_RR; + rr_control.reqseq = chan->buffer_seq; + l2cap_send_sframe(chan, &rr_control); } - } else if (__is_ctrl_final(chan, rx_control)) { - clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); - - if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state)) - l2cap_retransmit_frames(chan); - - } else { - if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state) && - (chan->unacked_frames > 0)) - __set_retrans_timer(chan); + break; + case L2CAP_EV_RECV_REJ: + l2cap_handle_rej(chan, control); + break; + case L2CAP_EV_RECV_SREJ: + l2cap_handle_srej(chan, control); + break; + } - clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); - if (test_bit(CONN_SREJ_SENT, &chan->conn_state)) - l2cap_send_ack(chan); - else - l2cap_ertm_send(chan); + if (skb && !skb_in_use) { + BT_DBG("Freeing %p", skb); + kfree_skb(skb); } + + return err; } -static inline void l2cap_data_channel_rejframe(struct l2cap_chan *chan, u32 rx_control) +static bool __valid_reqseq(struct l2cap_chan *chan, u16 reqseq) { - u16 tx_seq = __get_reqseq(chan, rx_control); - - BT_DBG("chan %p, req_seq %d ctrl 0x%8.8x", chan, tx_seq, rx_control); - - clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); - - chan->expected_ack_seq = tx_seq; - l2cap_drop_acked_frames(chan); + /* Make sure reqseq is for a packet that has been sent but not acked */ + u16 unacked; - if (__is_ctrl_final(chan, rx_control)) { - if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state)) - l2cap_retransmit_frames(chan); - } else { - l2cap_retransmit_frames(chan); - - if (test_bit(CONN_WAIT_F, &chan->conn_state)) - set_bit(CONN_REJ_ACT, &chan->conn_state); - } + unacked = __seq_offset(chan, chan->next_tx_seq, chan->expected_ack_seq); + return __seq_offset(chan, chan->next_tx_seq, reqseq) <= unacked; } -static inline void l2cap_data_channel_srejframe(struct l2cap_chan *chan, u32 rx_control) -{ - u16 tx_seq = __get_reqseq(chan, rx_control); - BT_DBG("chan %p, req_seq %d ctrl 0x%8.8x", chan, tx_seq, rx_control); - - clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); - - if (__is_ctrl_poll(chan, rx_control)) { - chan->expected_ack_seq = tx_seq; - l2cap_drop_acked_frames(chan); - - set_bit(CONN_SEND_FBIT, &chan->conn_state); - l2cap_retransmit_one_frame(chan, tx_seq); +static int l2cap_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, + struct sk_buff *skb, u8 event) +{ + int err = 0; - l2cap_ertm_send(chan); + BT_DBG("chan %p, control %p, skb %p, event %d, state %d", chan, + control, skb, event, chan->rx_state); - if (test_bit(CONN_WAIT_F, &chan->conn_state)) { - chan->srej_save_reqseq = tx_seq; - set_bit(CONN_SREJ_ACT, &chan->conn_state); + if (__valid_reqseq(chan, control->reqseq)) { + switch (chan->rx_state) { + case L2CAP_RX_STATE_RECV: + err = l2cap_rx_state_recv(chan, control, skb, event); + break; + case L2CAP_RX_STATE_SREJ_SENT: + err = l2cap_rx_state_srej_sent(chan, control, skb, + event); + break; + default: + /* shut it down */ + break; } - } else if (__is_ctrl_final(chan, rx_control)) { - if (test_bit(CONN_SREJ_ACT, &chan->conn_state) && - chan->srej_save_reqseq == tx_seq) - clear_bit(CONN_SREJ_ACT, &chan->conn_state); - else - l2cap_retransmit_one_frame(chan, tx_seq); } else { - l2cap_retransmit_one_frame(chan, tx_seq); - if (test_bit(CONN_WAIT_F, &chan->conn_state)) { - chan->srej_save_reqseq = tx_seq; - set_bit(CONN_SREJ_ACT, &chan->conn_state); - } + BT_DBG("Invalid reqseq %d (next_tx_seq %d, expected_ack_seq %d", + control->reqseq, chan->next_tx_seq, + chan->expected_ack_seq); + l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); } + + return err; } -static inline void l2cap_data_channel_rnrframe(struct l2cap_chan *chan, u32 rx_control) +static int l2cap_stream_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, + struct sk_buff *skb) { - u16 tx_seq = __get_reqseq(chan, rx_control); + int err = 0; - BT_DBG("chan %p, req_seq %d ctrl 0x%8.8x", chan, tx_seq, rx_control); + BT_DBG("chan %p, control %p, skb %p, state %d", chan, control, skb, + chan->rx_state); - set_bit(CONN_REMOTE_BUSY, &chan->conn_state); - chan->expected_ack_seq = tx_seq; - l2cap_drop_acked_frames(chan); + if (l2cap_classify_txseq(chan, control->txseq) == + L2CAP_TXSEQ_EXPECTED) { + l2cap_pass_to_tx(chan, control); - if (__is_ctrl_poll(chan, rx_control)) - set_bit(CONN_SEND_FBIT, &chan->conn_state); + BT_DBG("buffer_seq %d->%d", chan->buffer_seq, + __next_seq(chan, chan->buffer_seq)); - if (!test_bit(CONN_SREJ_SENT, &chan->conn_state)) { - __clear_retrans_timer(chan); - if (__is_ctrl_poll(chan, rx_control)) - l2cap_send_rr_or_rnr(chan, L2CAP_CTRL_FINAL); - return; - } + chan->buffer_seq = __next_seq(chan, chan->buffer_seq); - if (__is_ctrl_poll(chan, rx_control)) { - l2cap_send_srejtail(chan); + l2cap_reassemble_sdu(chan, skb, control); } else { - rx_control = __set_ctrl_super(chan, L2CAP_SUPER_RR); - l2cap_send_sframe(chan, rx_control); - } -} - -static inline int l2cap_data_channel_sframe(struct l2cap_chan *chan, u32 rx_control, struct sk_buff *skb) -{ - BT_DBG("chan %p rx_control 0x%8.8x len %d", chan, rx_control, skb->len); + if (chan->sdu) { + kfree_skb(chan->sdu); + chan->sdu = NULL; + } + chan->sdu_last_frag = NULL; + chan->sdu_len = 0; - if (__is_ctrl_final(chan, rx_control) && - test_bit(CONN_WAIT_F, &chan->conn_state)) { - __clear_monitor_timer(chan); - if (chan->unacked_frames > 0) - __set_retrans_timer(chan); - clear_bit(CONN_WAIT_F, &chan->conn_state); + if (skb) { + BT_DBG("Freeing %p", skb); + kfree_skb(skb); + } } - switch (__get_ctrl_super(chan, rx_control)) { - case L2CAP_SUPER_RR: - l2cap_data_channel_rrframe(chan, rx_control); - break; - - case L2CAP_SUPER_REJ: - l2cap_data_channel_rejframe(chan, rx_control); - break; - - case L2CAP_SUPER_SREJ: - l2cap_data_channel_srejframe(chan, rx_control); - break; - - case L2CAP_SUPER_RNR: - l2cap_data_channel_rnrframe(chan, rx_control); - break; - } + chan->last_acked_seq = control->txseq; + chan->expected_tx_seq = __next_seq(chan, control->txseq); - kfree_skb(skb); - return 0; + return err; } -static int l2cap_ertm_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) +static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) { - u32 control; - u16 req_seq; - int len, next_tx_seq_offset, req_seq_offset; + struct l2cap_ctrl *control = &bt_cb(skb)->control; + u16 len; + u8 event; __unpack_control(chan, skb); - control = __get_control(chan, skb->data); - skb_pull(skb, __ctrl_size(chan)); len = skb->len; /* * We can just drop the corrupted I-frame here. * Receiver will miss it and start proper recovery - * procedures and ask retransmission. + * procedures and ask for retransmission. */ if (l2cap_check_fcs(chan, skb)) goto drop; - if (__is_sar_start(chan, control) && !__is_sframe(chan, control)) + if (!control->sframe && control->sar == L2CAP_SAR_START) len -= L2CAP_SDULEN_SIZE; if (chan->fcs == L2CAP_FCS_CRC16) @@ -4585,34 +5086,57 @@ static int l2cap_ertm_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) goto drop; } - req_seq = __get_reqseq(chan, control); - - req_seq_offset = __seq_offset(chan, req_seq, chan->expected_ack_seq); + if (!control->sframe) { + int err; - next_tx_seq_offset = __seq_offset(chan, chan->next_tx_seq, - chan->expected_ack_seq); + BT_DBG("iframe sar %d, reqseq %d, final %d, txseq %d", + control->sar, control->reqseq, control->final, + control->txseq); - /* check for invalid req-seq */ - if (req_seq_offset > next_tx_seq_offset) { - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); - goto drop; - } - - if (!__is_sframe(chan, control)) { - if (len < 0) { - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + /* Validate F-bit - F=0 always valid, F=1 only + * valid in TX WAIT_F + */ + if (control->final && chan->tx_state != L2CAP_TX_STATE_WAIT_F) goto drop; + + if (chan->mode != L2CAP_MODE_STREAMING) { + event = L2CAP_EV_RECV_IFRAME; + err = l2cap_rx(chan, control, skb, event); + } else { + err = l2cap_stream_rx(chan, control, skb); } - l2cap_data_channel_iframe(chan, control, skb); + if (err) + l2cap_send_disconn_req(chan->conn, chan, + ECONNRESET); } else { + const u8 rx_func_to_event[4] = { + L2CAP_EV_RECV_RR, L2CAP_EV_RECV_REJ, + L2CAP_EV_RECV_RNR, L2CAP_EV_RECV_SREJ + }; + + /* Only I-frames are expected in streaming mode */ + if (chan->mode == L2CAP_MODE_STREAMING) + goto drop; + + BT_DBG("sframe reqseq %d, final %d, poll %d, super %d", + control->reqseq, control->final, control->poll, + control->super); + if (len != 0) { BT_ERR("%d", len); l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); goto drop; } - l2cap_data_channel_sframe(chan, control, skb); + /* Validate F and P bits */ + if (control->final && (control->poll || + chan->tx_state != L2CAP_TX_STATE_WAIT_F)) + goto drop; + + event = rx_func_to_event[control->super]; + if (l2cap_rx(chan, control, skb, event)) + l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); } return 0; @@ -4622,19 +5146,27 @@ drop: return 0; } -static inline int l2cap_data_channel(struct l2cap_conn *conn, u16 cid, struct sk_buff *skb) +static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid, + struct sk_buff *skb) { struct l2cap_chan *chan; - u32 control; - u16 tx_seq; - int len; chan = l2cap_get_chan_by_scid(conn, cid); if (!chan) { - BT_DBG("unknown cid 0x%4.4x", cid); - /* Drop packet and return */ - kfree_skb(skb); - return 0; + if (cid == L2CAP_CID_A2MP) { + chan = a2mp_channel_create(conn, skb); + if (!chan) { + kfree_skb(skb); + return; + } + + l2cap_chan_lock(chan); + } else { + BT_DBG("unknown cid 0x%4.4x", cid); + /* Drop packet and return */ + kfree_skb(skb); + return; + } } BT_DBG("chan %p, len %d", chan, skb->len); @@ -4652,49 +5184,13 @@ static inline int l2cap_data_channel(struct l2cap_conn *conn, u16 cid, struct sk if (chan->imtu < skb->len) goto drop; - if (!chan->ops->recv(chan->data, skb)) + if (!chan->ops->recv(chan, skb)) goto done; break; case L2CAP_MODE_ERTM: - l2cap_ertm_data_rcv(chan, skb); - - goto done; - case L2CAP_MODE_STREAMING: - control = __get_control(chan, skb->data); - skb_pull(skb, __ctrl_size(chan)); - len = skb->len; - - if (l2cap_check_fcs(chan, skb)) - goto drop; - - if (__is_sar_start(chan, control)) - len -= L2CAP_SDULEN_SIZE; - - if (chan->fcs == L2CAP_FCS_CRC16) - len -= L2CAP_FCS_SIZE; - - if (len > chan->mps || len < 0 || __is_sframe(chan, control)) - goto drop; - - tx_seq = __get_txseq(chan, control); - - if (chan->expected_tx_seq != tx_seq) { - /* Frame(s) missing - must discard partial SDU */ - kfree_skb(chan->sdu); - chan->sdu = NULL; - chan->sdu_last_frag = NULL; - chan->sdu_len = 0; - - /* TODO: Notify userland of missing data */ - } - - chan->expected_tx_seq = __next_seq(chan, tx_seq); - - if (l2cap_reassemble_sdu(chan, skb, control) == -EMSGSIZE) - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); - + l2cap_data_rcv(chan, skb); goto done; default: @@ -4707,11 +5203,10 @@ drop: done: l2cap_chan_unlock(chan); - - return 0; } -static inline int l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, struct sk_buff *skb) +static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, + struct sk_buff *skb) { struct l2cap_chan *chan; @@ -4727,17 +5222,15 @@ static inline int l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, str if (chan->imtu < skb->len) goto drop; - if (!chan->ops->recv(chan->data, skb)) - return 0; + if (!chan->ops->recv(chan, skb)) + return; drop: kfree_skb(skb); - - return 0; } -static inline int l2cap_att_channel(struct l2cap_conn *conn, u16 cid, - struct sk_buff *skb) +static void l2cap_att_channel(struct l2cap_conn *conn, u16 cid, + struct sk_buff *skb) { struct l2cap_chan *chan; @@ -4753,13 +5246,11 @@ static inline int l2cap_att_channel(struct l2cap_conn *conn, u16 cid, if (chan->imtu < skb->len) goto drop; - if (!chan->ops->recv(chan->data, skb)) - return 0; + if (!chan->ops->recv(chan, skb)) + return; drop: kfree_skb(skb); - - return 0; } static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb) @@ -4787,7 +5278,7 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb) case L2CAP_CID_CONN_LESS: psm = get_unaligned((__le16 *) skb->data); - skb_pull(skb, 2); + skb_pull(skb, L2CAP_PSMLEN_SIZE); l2cap_conless_channel(conn, psm, skb); break; @@ -4898,7 +5389,7 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) if (!conn) return 0; - BT_DBG("conn %p", conn); + BT_DBG("conn %p status 0x%2.2x encrypt %u", conn, status, encrypt); if (hcon->type == LE_LINK) { if (!status && encrypt) @@ -4911,7 +5402,8 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) list_for_each_entry(chan, &conn->chan_l, list) { l2cap_chan_lock(chan); - BT_DBG("chan->scid %d", chan->scid); + BT_DBG("chan %p scid 0x%4.4x state %s", chan, chan->scid, + state_to_string(chan->state)); if (chan->scid == L2CAP_CID_LE_DATA) { if (!status && encrypt) { @@ -4981,6 +5473,17 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) rsp.status = cpu_to_le16(stat); l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, sizeof(rsp), &rsp); + + if (!test_bit(CONF_REQ_SENT, &chan->conf_state) && + res == L2CAP_CR_SUCCESS) { + char buf[128]; + set_bit(CONF_REQ_SENT, &chan->conf_state); + l2cap_send_cmd(conn, l2cap_get_ident(conn), + L2CAP_CONF_REQ, + l2cap_build_conf_req(chan, buf), + buf); + chan->num_conf_req++; + } } l2cap_chan_unlock(chan); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 3bb1611b9d4..1497edd191a 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -27,7 +27,6 @@ /* Bluetooth L2CAP sockets. */ -#include <linux/security.h> #include <linux/export.h> #include <net/bluetooth/bluetooth.h> @@ -89,8 +88,8 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) if (err < 0) goto done; - if (__le16_to_cpu(la.l2_psm) == 0x0001 || - __le16_to_cpu(la.l2_psm) == 0x0003) + if (__le16_to_cpu(la.l2_psm) == L2CAP_PSM_SDP || + __le16_to_cpu(la.l2_psm) == L2CAP_PSM_RFCOMM) chan->sec_level = BT_SECURITY_SDP; bacpy(&bt_sk(sk)->src, &la.l2_bdaddr); @@ -246,6 +245,7 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *l BT_DBG("sock %p, sk %p", sock, sk); + memset(la, 0, sizeof(struct sockaddr_l2)); addr->sa_family = AF_BLUETOOTH; *len = sizeof(struct sockaddr_l2); @@ -446,6 +446,22 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, ch return err; } +static bool l2cap_valid_mtu(struct l2cap_chan *chan, u16 mtu) +{ + switch (chan->scid) { + case L2CAP_CID_LE_DATA: + if (mtu < L2CAP_LE_MIN_MTU) + return false; + break; + + default: + if (mtu < L2CAP_DEFAULT_MIN_MTU) + return false; + } + + return true; +} + static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; @@ -484,6 +500,11 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us break; } + if (!l2cap_valid_mtu(chan, opts.imtu)) { + err = -EINVAL; + break; + } + chan->mode = opts.mode; switch (chan->mode) { case L2CAP_MODE_BASIC: @@ -873,9 +894,34 @@ static int l2cap_sock_release(struct socket *sock) return err; } -static struct l2cap_chan *l2cap_sock_new_connection_cb(void *data) +static void l2cap_sock_cleanup_listen(struct sock *parent) { - struct sock *sk, *parent = data; + struct sock *sk; + + BT_DBG("parent %p", parent); + + /* Close not yet accepted channels */ + while ((sk = bt_accept_dequeue(parent, NULL))) { + struct l2cap_chan *chan = l2cap_pi(sk)->chan; + + l2cap_chan_lock(chan); + __clear_chan_timer(chan); + l2cap_chan_close(chan, ECONNRESET); + l2cap_chan_unlock(chan); + + l2cap_sock_kill(sk); + } +} + +static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) +{ + struct sock *sk, *parent = chan->data; + + /* Check for backlog size */ + if (sk_acceptq_is_full(parent)) { + BT_DBG("backlog full %d", parent->sk_ack_backlog); + return NULL; + } sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP, GFP_ATOMIC); @@ -889,10 +935,10 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(void *data) return l2cap_pi(sk)->chan; } -static int l2cap_sock_recv_cb(void *data, struct sk_buff *skb) +static int l2cap_sock_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) { int err; - struct sock *sk = data; + struct sock *sk = chan->data; struct l2cap_pinfo *pi = l2cap_pi(sk); lock_sock(sk); @@ -925,16 +971,57 @@ done: return err; } -static void l2cap_sock_close_cb(void *data) +static void l2cap_sock_close_cb(struct l2cap_chan *chan) { - struct sock *sk = data; + struct sock *sk = chan->data; l2cap_sock_kill(sk); } -static void l2cap_sock_state_change_cb(void *data, int state) +static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err) +{ + struct sock *sk = chan->data; + struct sock *parent; + + lock_sock(sk); + + parent = bt_sk(sk)->parent; + + sock_set_flag(sk, SOCK_ZAPPED); + + switch (chan->state) { + case BT_OPEN: + case BT_BOUND: + case BT_CLOSED: + break; + case BT_LISTEN: + l2cap_sock_cleanup_listen(sk); + sk->sk_state = BT_CLOSED; + chan->state = BT_CLOSED; + + break; + default: + sk->sk_state = BT_CLOSED; + chan->state = BT_CLOSED; + + sk->sk_err = err; + + if (parent) { + bt_accept_unlink(sk); + parent->sk_data_ready(parent, 0); + } else { + sk->sk_state_change(sk); + } + + break; + } + + release_sock(sk); +} + +static void l2cap_sock_state_change_cb(struct l2cap_chan *chan, int state) { - struct sock *sk = data; + struct sock *sk = chan->data; sk->sk_state = state; } @@ -955,12 +1042,34 @@ static struct sk_buff *l2cap_sock_alloc_skb_cb(struct l2cap_chan *chan, return skb; } +static void l2cap_sock_ready_cb(struct l2cap_chan *chan) +{ + struct sock *sk = chan->data; + struct sock *parent; + + lock_sock(sk); + + parent = bt_sk(sk)->parent; + + BT_DBG("sk %p, parent %p", sk, parent); + + sk->sk_state = BT_CONNECTED; + sk->sk_state_change(sk); + + if (parent) + parent->sk_data_ready(parent, 0); + + release_sock(sk); +} + static struct l2cap_ops l2cap_chan_ops = { .name = "L2CAP Socket Interface", .new_connection = l2cap_sock_new_connection_cb, .recv = l2cap_sock_recv_cb, .close = l2cap_sock_close_cb, + .teardown = l2cap_sock_teardown_cb, .state_change = l2cap_sock_state_change_cb, + .ready = l2cap_sock_ready_cb, .alloc_skb = l2cap_sock_alloc_skb_cb, }; @@ -1066,7 +1175,7 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int p chan = l2cap_chan_create(); if (!chan) { - l2cap_sock_kill(sk); + sk_free(sk); return NULL; } diff --git a/net/bluetooth/lib.c b/net/bluetooth/lib.c index 506628876f3..e1c97527e16 100644 --- a/net/bluetooth/lib.c +++ b/net/bluetooth/lib.c @@ -26,12 +26,7 @@ #define pr_fmt(fmt) "Bluetooth: " fmt -#include <linux/module.h> - -#include <linux/kernel.h> -#include <linux/stddef.h> -#include <linux/string.h> -#include <asm/errno.h> +#include <linux/export.h> #include <net/bluetooth/bluetooth.h> diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 3e5e3362ea0..ad6613d17ca 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -24,8 +24,6 @@ /* Bluetooth HCI Management interface */ -#include <linux/kernel.h> -#include <linux/uaccess.h> #include <linux/module.h> #include <asm/unaligned.h> @@ -212,7 +210,7 @@ static int cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status) BT_DBG("sock %p, index %u, cmd %u, status %u", sk, index, cmd, status); - skb = alloc_skb(sizeof(*hdr) + sizeof(*ev), GFP_ATOMIC); + skb = alloc_skb(sizeof(*hdr) + sizeof(*ev), GFP_KERNEL); if (!skb) return -ENOMEM; @@ -243,7 +241,7 @@ static int cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status, BT_DBG("sock %p", sk); - skb = alloc_skb(sizeof(*hdr) + sizeof(*ev) + rp_len, GFP_ATOMIC); + skb = alloc_skb(sizeof(*hdr) + sizeof(*ev) + rp_len, GFP_KERNEL); if (!skb) return -ENOMEM; @@ -689,14 +687,14 @@ static struct pending_cmd *mgmt_pending_add(struct sock *sk, u16 opcode, { struct pending_cmd *cmd; - cmd = kmalloc(sizeof(*cmd), GFP_ATOMIC); + cmd = kmalloc(sizeof(*cmd), GFP_KERNEL); if (!cmd) return NULL; cmd->opcode = opcode; cmd->index = hdev->id; - cmd->param = kmalloc(len, GFP_ATOMIC); + cmd->param = kmalloc(len, GFP_KERNEL); if (!cmd->param) { kfree(cmd); return NULL; @@ -714,7 +712,8 @@ static struct pending_cmd *mgmt_pending_add(struct sock *sk, u16 opcode, } static void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev, - void (*cb)(struct pending_cmd *cmd, void *data), + void (*cb)(struct pending_cmd *cmd, + void *data), void *data) { struct list_head *p, *n; @@ -813,7 +812,7 @@ static int mgmt_event(u16 event, struct hci_dev *hdev, void *data, u16 data_len, struct sk_buff *skb; struct mgmt_hdr *hdr; - skb = alloc_skb(sizeof(*hdr) + data_len, GFP_ATOMIC); + skb = alloc_skb(sizeof(*hdr) + data_len, GFP_KERNEL); if (!skb) return -ENOMEM; @@ -871,7 +870,7 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data, } if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, hdev) || - mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) { + mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) { err = cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE, MGMT_STATUS_BUSY); goto failed; @@ -978,7 +977,7 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data, } if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, hdev) || - mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) { + mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) { err = cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE, MGMT_STATUS_BUSY); goto failed; @@ -1001,7 +1000,7 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data, scan = 0; if (test_bit(HCI_ISCAN, &hdev->flags) && - hdev->discov_timeout > 0) + hdev->discov_timeout > 0) cancel_delayed_work(&hdev->discov_off); } @@ -1056,7 +1055,7 @@ static int set_link_security(struct sock *sk, struct hci_dev *hdev, void *data, bool changed = false; if (!!cp->val != test_bit(HCI_LINK_SECURITY, - &hdev->dev_flags)) { + &hdev->dev_flags)) { change_bit(HCI_LINK_SECURITY, &hdev->dev_flags); changed = true; } @@ -1269,7 +1268,7 @@ static int add_uuid(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) goto failed; } - uuid = kmalloc(sizeof(*uuid), GFP_ATOMIC); + uuid = kmalloc(sizeof(*uuid), GFP_KERNEL); if (!uuid) { err = -ENOMEM; goto failed; @@ -1317,7 +1316,7 @@ static bool enable_service_cache(struct hci_dev *hdev) } static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data, - u16 len) + u16 len) { struct mgmt_cp_remove_uuid *cp = data; struct pending_cmd *cmd; @@ -1442,7 +1441,7 @@ unlock: } static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, - u16 len) + u16 len) { struct mgmt_cp_load_link_keys *cp = data; u16 key_count, expected_len; @@ -1454,13 +1453,13 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, sizeof(struct mgmt_link_key_info); if (expected_len != len) { BT_ERR("load_link_keys: expected %u bytes, got %u bytes", - len, expected_len); + len, expected_len); return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, MGMT_STATUS_INVALID_PARAMS); } BT_DBG("%s debug_keys %u key_count %u", hdev->name, cp->debug_keys, - key_count); + key_count); hci_dev_lock(hdev); @@ -1535,10 +1534,10 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data, if (cp->disconnect) { if (cp->addr.type == BDADDR_BREDR) conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, - &cp->addr.bdaddr); + &cp->addr.bdaddr); else conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, - &cp->addr.bdaddr); + &cp->addr.bdaddr); } else { conn = NULL; } @@ -1594,7 +1593,8 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data, } if (cp->addr.type == BDADDR_BREDR) - conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->addr.bdaddr); + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, + &cp->addr.bdaddr); else conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &cp->addr.bdaddr); @@ -1611,7 +1611,7 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data, } dc.handle = cpu_to_le16(conn->handle); - dc.reason = 0x13; /* Remote User Terminated Connection */ + dc.reason = HCI_ERROR_REMOTE_USER_TERM; err = hci_send_cmd(hdev, HCI_OP_DISCONNECT, sizeof(dc), &dc); if (err < 0) @@ -1667,7 +1667,7 @@ static int get_connections(struct sock *sk, struct hci_dev *hdev, void *data, } rp_len = sizeof(*rp) + (i * sizeof(struct mgmt_addr_info)); - rp = kmalloc(rp_len, GFP_ATOMIC); + rp = kmalloc(rp_len, GFP_KERNEL); if (!rp) { err = -ENOMEM; goto unlock; @@ -1778,29 +1778,6 @@ failed: return err; } -static int pin_code_neg_reply(struct sock *sk, struct hci_dev *hdev, - void *data, u16 len) -{ - struct mgmt_cp_pin_code_neg_reply *cp = data; - int err; - - BT_DBG(""); - - hci_dev_lock(hdev); - - if (!hdev_is_powered(hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_PIN_CODE_NEG_REPLY, - MGMT_STATUS_NOT_POWERED); - goto failed; - } - - err = send_pin_code_neg_reply(sk, hdev, cp); - -failed: - hci_dev_unlock(hdev); - return err; -} - static int set_io_capability(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { @@ -1813,7 +1790,7 @@ static int set_io_capability(struct sock *sk, struct hci_dev *hdev, void *data, hdev->io_capability = cp->io_capability; BT_DBG("%s IO capability set to 0x%02x", hdev->name, - hdev->io_capability); + hdev->io_capability); hci_dev_unlock(hdev); @@ -1821,7 +1798,7 @@ static int set_io_capability(struct sock *sk, struct hci_dev *hdev, void *data, 0); } -static inline struct pending_cmd *find_pairing(struct hci_conn *conn) +static struct pending_cmd *find_pairing(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; struct pending_cmd *cmd; @@ -1927,8 +1904,15 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, rp.addr.type = cp->addr.type; if (IS_ERR(conn)) { + int status; + + if (PTR_ERR(conn) == -EBUSY) + status = MGMT_STATUS_BUSY; + else + status = MGMT_STATUS_CONNECT_FAILED; + err = cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE, - MGMT_STATUS_CONNECT_FAILED, &rp, + status, &rp, sizeof(rp)); goto unlock; } @@ -1959,7 +1943,7 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, cmd->user_data = conn; if (conn->state == BT_CONNECTED && - hci_conn_security(conn, sec_level, auth_type)) + hci_conn_security(conn, sec_level, auth_type)) pairing_complete(cmd, 0); err = 0; @@ -2076,6 +2060,18 @@ done: return err; } +static int pin_code_neg_reply(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_cp_pin_code_neg_reply *cp = data; + + BT_DBG(""); + + return user_pairing_resp(sk, hdev, &cp->addr.bdaddr, cp->addr.type, + MGMT_OP_PIN_CODE_NEG_REPLY, + HCI_OP_PIN_CODE_NEG_REPLY, 0); +} + static int user_confirm_reply(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { @@ -2256,7 +2252,7 @@ unlock: } static int remove_remote_oob_data(struct sock *sk, struct hci_dev *hdev, - void *data, u16 len) + void *data, u16 len) { struct mgmt_cp_remove_remote_oob_data *cp = data; u8 status; @@ -2425,7 +2421,7 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data, case DISCOVERY_RESOLVING: e = hci_inquiry_cache_lookup_resolve(hdev, BDADDR_ANY, - NAME_PENDING); + NAME_PENDING); if (!e) { mgmt_pending_remove(cmd); err = cmd_complete(sk, hdev->id, @@ -2600,8 +2596,8 @@ static int set_fast_connectable(struct sock *sk, struct hci_dev *hdev, if (cp->val) { type = PAGE_SCAN_TYPE_INTERLACED; - /* 22.5 msec page scan interval */ - acp.interval = __constant_cpu_to_le16(0x0024); + /* 160 msec page scan interval */ + acp.interval = __constant_cpu_to_le16(0x0100); } else { type = PAGE_SCAN_TYPE_STANDARD; /* default */ @@ -2647,7 +2643,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, sizeof(struct mgmt_ltk_info); if (expected_len != len) { BT_ERR("load_keys: expected %u bytes, got %u bytes", - len, expected_len); + len, expected_len); return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, EINVAL); } @@ -2772,7 +2768,7 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen) } if (opcode >= ARRAY_SIZE(mgmt_handlers) || - mgmt_handlers[opcode].func == NULL) { + mgmt_handlers[opcode].func == NULL) { BT_DBG("Unknown op %u", opcode); err = cmd_status(sk, index, opcode, MGMT_STATUS_UNKNOWN_COMMAND); @@ -2780,7 +2776,7 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen) } if ((hdev && opcode < MGMT_OP_READ_INFO) || - (!hdev && opcode >= MGMT_OP_READ_INFO)) { + (!hdev && opcode >= MGMT_OP_READ_INFO)) { err = cmd_status(sk, index, opcode, MGMT_STATUS_INVALID_INDEX); goto done; @@ -2789,7 +2785,7 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen) handler = &mgmt_handlers[opcode]; if ((handler->var_len && len < handler->data_len) || - (!handler->var_len && len != handler->data_len)) { + (!handler->var_len && len != handler->data_len)) { err = cmd_status(sk, index, opcode, MGMT_STATUS_INVALID_PARAMS); goto done; @@ -2973,7 +2969,7 @@ int mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, bacpy(&ev.key.addr.bdaddr, &key->bdaddr); ev.key.addr.type = BDADDR_BREDR; ev.key.type = key->type; - memcpy(ev.key.val, key->val, 16); + memcpy(ev.key.val, key->val, HCI_LINK_KEY_SIZE); ev.key.pin_len = key->pin_len; return mgmt_event(MGMT_EV_NEW_LINK_KEY, hdev, &ev, sizeof(ev), NULL); @@ -3108,7 +3104,7 @@ int mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, mgmt_pending_remove(cmd); mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, unpair_device_rsp, - hdev); + hdev); return err; } @@ -3198,7 +3194,7 @@ int mgmt_user_confirm_request(struct hci_dev *hdev, bdaddr_t *bdaddr, } int mgmt_user_passkey_request(struct hci_dev *hdev, bdaddr_t *bdaddr, - u8 link_type, u8 addr_type) + u8 link_type, u8 addr_type) { struct mgmt_ev_user_passkey_request ev; @@ -3212,8 +3208,8 @@ int mgmt_user_passkey_request(struct hci_dev *hdev, bdaddr_t *bdaddr, } static int user_pairing_resp_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, - u8 link_type, u8 addr_type, u8 status, - u8 opcode) + u8 link_type, u8 addr_type, u8 status, + u8 opcode) { struct pending_cmd *cmd; struct mgmt_rp_user_confirm_reply rp; @@ -3244,7 +3240,8 @@ int mgmt_user_confirm_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status) { return user_pairing_resp_complete(hdev, bdaddr, link_type, addr_type, - status, MGMT_OP_USER_CONFIRM_NEG_REPLY); + status, + MGMT_OP_USER_CONFIRM_NEG_REPLY); } int mgmt_user_passkey_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, @@ -3258,7 +3255,8 @@ int mgmt_user_passkey_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status) { return user_pairing_resp_complete(hdev, bdaddr, link_type, addr_type, - status, MGMT_OP_USER_PASSKEY_NEG_REPLY); + status, + MGMT_OP_USER_PASSKEY_NEG_REPLY); } int mgmt_auth_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, @@ -3537,9 +3535,9 @@ int mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, ev->addr.type = link_to_bdaddr(link_type, addr_type); ev->rssi = rssi; if (cfm_name) - ev->flags[0] |= MGMT_DEV_FOUND_CONFIRM_NAME; + ev->flags |= cpu_to_le32(MGMT_DEV_FOUND_CONFIRM_NAME); if (!ssp) - ev->flags[0] |= MGMT_DEV_FOUND_LEGACY_PAIRING; + ev->flags |= cpu_to_le32(MGMT_DEV_FOUND_LEGACY_PAIRING); if (eir_len > 0) memcpy(ev->eir, eir, eir_len); @@ -3549,7 +3547,6 @@ int mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, dev_class, 3); ev->eir_len = cpu_to_le16(eir_len); - ev_size = sizeof(*ev) + eir_len; return mgmt_event(MGMT_EV_DEVICE_FOUND, hdev, ev, ev_size, NULL); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 8a602388f1e..c75107ef892 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -26,22 +26,8 @@ */ #include <linux/module.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/signal.h> -#include <linux/init.h> -#include <linux/wait.h> -#include <linux/device.h> #include <linux/debugfs.h> -#include <linux/seq_file.h> -#include <linux/net.h> -#include <linux/mutex.h> #include <linux/kthread.h> -#include <linux/slab.h> - -#include <net/sock.h> -#include <linux/uaccess.h> #include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> @@ -115,14 +101,14 @@ static void rfcomm_session_del(struct rfcomm_session *s); #define __get_rpn_stop_bits(line) (((line) >> 2) & 0x1) #define __get_rpn_parity(line) (((line) >> 3) & 0x7) -static inline void rfcomm_schedule(void) +static void rfcomm_schedule(void) { if (!rfcomm_thread) return; wake_up_process(rfcomm_thread); } -static inline void rfcomm_session_put(struct rfcomm_session *s) +static void rfcomm_session_put(struct rfcomm_session *s) { if (atomic_dec_and_test(&s->refcnt)) rfcomm_session_del(s); @@ -227,7 +213,7 @@ static int rfcomm_l2sock_create(struct socket **sock) return err; } -static inline int rfcomm_check_security(struct rfcomm_dlc *d) +static int rfcomm_check_security(struct rfcomm_dlc *d) { struct sock *sk = d->session->sock->sk; struct l2cap_conn *conn = l2cap_pi(sk)->chan->conn; @@ -1750,7 +1736,7 @@ static void rfcomm_process_connect(struct rfcomm_session *s) /* Send data queued for the DLC. * Return number of frames left in the queue. */ -static inline int rfcomm_process_tx(struct rfcomm_dlc *d) +static int rfcomm_process_tx(struct rfcomm_dlc *d) { struct sk_buff *skb; int err; @@ -1798,7 +1784,7 @@ static inline int rfcomm_process_tx(struct rfcomm_dlc *d) return skb_queue_len(&d->tx_queue); } -static inline void rfcomm_process_dlcs(struct rfcomm_session *s) +static void rfcomm_process_dlcs(struct rfcomm_session *s) { struct rfcomm_dlc *d; struct list_head *p, *n; @@ -1858,7 +1844,7 @@ static inline void rfcomm_process_dlcs(struct rfcomm_session *s) } } -static inline void rfcomm_process_rx(struct rfcomm_session *s) +static void rfcomm_process_rx(struct rfcomm_session *s) { struct socket *sock = s->sock; struct sock *sk = sock->sk; @@ -1883,7 +1869,7 @@ static inline void rfcomm_process_rx(struct rfcomm_session *s) } } -static inline void rfcomm_accept_connection(struct rfcomm_session *s) +static void rfcomm_accept_connection(struct rfcomm_session *s) { struct socket *sock = s->sock, *nsock; int err; @@ -1917,7 +1903,7 @@ static inline void rfcomm_accept_connection(struct rfcomm_session *s) sock_release(nsock); } -static inline void rfcomm_check_connection(struct rfcomm_session *s) +static void rfcomm_check_connection(struct rfcomm_session *s) { struct sock *sk = s->sock->sk; @@ -1941,7 +1927,7 @@ static inline void rfcomm_check_connection(struct rfcomm_session *s) } } -static inline void rfcomm_process_sessions(void) +static void rfcomm_process_sessions(void) { struct list_head *p, *n; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index e8707debb86..1a17850d093 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -25,27 +25,8 @@ * RFCOMM sockets. */ -#include <linux/module.h> - -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/poll.h> -#include <linux/fcntl.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/socket.h> -#include <linux/skbuff.h> -#include <linux/list.h> -#include <linux/device.h> +#include <linux/export.h> #include <linux/debugfs.h> -#include <linux/seq_file.h> -#include <linux/security.h> -#include <net/sock.h> - -#include <linux/uaccess.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -547,6 +528,7 @@ static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int * BT_DBG("sock %p, sk %p", sock, sk); + memset(sa, 0, sizeof(*sa)); sa->rc_family = AF_BLUETOOTH; sa->rc_channel = rfcomm_pi(sk)->channel; if (peer) @@ -841,6 +823,7 @@ static int rfcomm_sock_getsockopt(struct socket *sock, int level, int optname, c } sec.level = rfcomm_pi(sk)->sec_level; + sec.key_size = 0; len = min_t(unsigned int, len, sizeof(sec)); if (copy_to_user(optval, (char *) &sec, len)) diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index d1820ff14ae..56f182393c4 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -31,11 +31,6 @@ #include <linux/tty_driver.h> #include <linux/tty_flip.h> -#include <linux/capability.h> -#include <linux/slab.h> -#include <linux/skbuff.h> -#include <linux/workqueue.h> - #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/rfcomm.h> @@ -132,7 +127,7 @@ static struct rfcomm_dev *__rfcomm_dev_get(int id) return NULL; } -static inline struct rfcomm_dev *rfcomm_dev_get(int id) +static struct rfcomm_dev *rfcomm_dev_get(int id) { struct rfcomm_dev *dev; @@ -345,7 +340,7 @@ static void rfcomm_wfree(struct sk_buff *skb) tty_port_put(&dev->port); } -static inline void rfcomm_set_owner_w(struct sk_buff *skb, struct rfcomm_dev *dev) +static void rfcomm_set_owner_w(struct sk_buff *skb, struct rfcomm_dev *dev) { tty_port_get(&dev->port); atomic_add(skb->truesize, &dev->wmem_alloc); @@ -461,7 +456,7 @@ static int rfcomm_get_dev_list(void __user *arg) size = sizeof(*dl) + dev_num * sizeof(*di); - dl = kmalloc(size, GFP_KERNEL); + dl = kzalloc(size, GFP_KERNEL); if (!dl) return -ENOMEM; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index cbdd313659a..3589e21edb0 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -25,26 +25,8 @@ /* Bluetooth SCO sockets. */ #include <linux/module.h> - -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/poll.h> -#include <linux/fcntl.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/socket.h> -#include <linux/skbuff.h> -#include <linux/device.h> #include <linux/debugfs.h> #include <linux/seq_file.h> -#include <linux/list.h> -#include <linux/security.h> -#include <net/sock.h> - -#include <linux/uaccess.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -123,7 +105,7 @@ static struct sco_conn *sco_conn_add(struct hci_conn *hcon) return conn; } -static inline struct sock *sco_chan_get(struct sco_conn *conn) +static struct sock *sco_chan_get(struct sco_conn *conn) { struct sock *sk = NULL; sco_conn_lock(conn); @@ -149,6 +131,15 @@ static int sco_conn_del(struct hci_conn *hcon, int err) sco_sock_clear_timer(sk); sco_chan_del(sk, err); bh_unlock_sock(sk); + + sco_conn_lock(conn); + conn->sk = NULL; + sco_pi(sk)->conn = NULL; + sco_conn_unlock(conn); + + if (conn->hcon) + hci_conn_put(conn->hcon); + sco_sock_kill(sk); } @@ -157,7 +148,8 @@ static int sco_conn_del(struct hci_conn *hcon, int err) return 0; } -static inline int sco_chan_add(struct sco_conn *conn, struct sock *sk, struct sock *parent) +static int sco_chan_add(struct sco_conn *conn, struct sock *sk, + struct sock *parent) { int err = 0; @@ -228,7 +220,7 @@ done: return err; } -static inline int sco_send_frame(struct sock *sk, struct msghdr *msg, int len) +static int sco_send_frame(struct sock *sk, struct msghdr *msg, int len) { struct sco_conn *conn = sco_pi(sk)->conn; struct sk_buff *skb; @@ -254,7 +246,7 @@ static inline int sco_send_frame(struct sock *sk, struct msghdr *msg, int len) return len; } -static inline void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb) +static void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb) { struct sock *sk = sco_chan_get(conn); @@ -523,7 +515,7 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen goto done; err = bt_sock_wait_state(sk, BT_CONNECTED, - sock_sndtimeo(sk, flags & O_NONBLOCK)); + sock_sndtimeo(sk, flags & O_NONBLOCK)); done: release_sock(sk); @@ -788,7 +780,7 @@ static int sco_sock_shutdown(struct socket *sock, int how) if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) err = bt_sock_wait_state(sk, BT_CLOSED, - sk->sk_lingertime); + sk->sk_lingertime); } release_sock(sk); return err; @@ -838,16 +830,6 @@ static void sco_chan_del(struct sock *sk, int err) BT_DBG("sk %p, conn %p, err %d", sk, conn, err); - if (conn) { - sco_conn_lock(conn); - conn->sk = NULL; - sco_pi(sk)->conn = NULL; - sco_conn_unlock(conn); - - if (conn->hcon) - hci_conn_put(conn->hcon); - } - sk->sk_state = BT_CLOSED; sk->sk_err = err; sk->sk_state_change(sk); @@ -878,7 +860,7 @@ static void sco_conn_ready(struct sco_conn *conn) bh_lock_sock(parent); sk = sco_sock_alloc(sock_net(parent), NULL, - BTPROTO_SCO, GFP_ATOMIC); + BTPROTO_SCO, GFP_ATOMIC); if (!sk) { bh_unlock_sock(parent); goto done; @@ -907,7 +889,7 @@ done: /* ----- SCO interface with lower layer (HCI) ----- */ int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr) { - register struct sock *sk; + struct sock *sk; struct hlist_node *node; int lm = 0; @@ -920,7 +902,7 @@ int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr) continue; if (!bacmp(&bt_sk(sk)->src, &hdev->bdaddr) || - !bacmp(&bt_sk(sk)->src, BDADDR_ANY)) { + !bacmp(&bt_sk(sk)->src, BDADDR_ANY)) { lm |= HCI_LM_ACCEPT; break; } @@ -981,7 +963,7 @@ static int sco_debugfs_show(struct seq_file *f, void *p) sk_for_each(sk, node, &sco_sk_list.head) { seq_printf(f, "%s %s %d\n", batostr(&bt_sk(sk)->src), - batostr(&bt_sk(sk)->dst), sk->sk_state); + batostr(&bt_sk(sk)->dst), sk->sk_state); } read_unlock(&sco_sk_list.lock); @@ -1044,8 +1026,8 @@ int __init sco_init(void) } if (bt_debugfs) { - sco_debugfs = debugfs_create_file("sco", 0444, - bt_debugfs, NULL, &sco_debugfs_fops); + sco_debugfs = debugfs_create_file("sco", 0444, bt_debugfs, + NULL, &sco_debugfs_fops); if (!sco_debugfs) BT_ERR("Failed to create SCO debug file"); } diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 37df4e9b389..901a616c808 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -20,14 +20,15 @@ SOFTWARE IS DISCLAIMED. */ +#include <linux/crypto.h> +#include <linux/scatterlist.h> +#include <crypto/b128ops.h> + #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> #include <net/bluetooth/mgmt.h> #include <net/bluetooth/smp.h> -#include <linux/crypto.h> -#include <linux/scatterlist.h> -#include <crypto/b128ops.h> #define SMP_TIMEOUT msecs_to_jiffies(30000) @@ -578,8 +579,11 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) if (!test_and_set_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags)) smp = smp_chan_create(conn); + else + smp = conn->smp_chan; - smp = conn->smp_chan; + if (!smp) + return SMP_UNSPECIFIED; smp->preq[0] = SMP_CMD_PAIRING_REQ; memcpy(&smp->preq[1], req, sizeof(*req)); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 929e48aed44..070e8a68cfc 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -31,9 +31,11 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct net_bridge_mdb_entry *mdst; struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats); + rcu_read_lock(); #ifdef CONFIG_BRIDGE_NETFILTER if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) { br_nf_pre_routing_finish_bridge_slow(skb); + rcu_read_unlock(); return NETDEV_TX_OK; } #endif @@ -48,7 +50,6 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) skb_reset_mac_header(skb); skb_pull(skb, ETH_HLEN); - rcu_read_lock(); if (is_broadcast_ether_addr(dest)) br_flood_deliver(br, skb); else if (is_multicast_ether_addr(dest)) { @@ -127,9 +128,9 @@ static struct rtnl_link_stats64 *br_get_stats64(struct net_device *dev, const struct br_cpu_netstats *bstats = per_cpu_ptr(br->stats, cpu); do { - start = u64_stats_fetch_begin(&bstats->syncp); + start = u64_stats_fetch_begin_bh(&bstats->syncp); memcpy(&tmp, bstats, sizeof(tmp)); - } while (u64_stats_fetch_retry(&bstats->syncp, start)); + } while (u64_stats_fetch_retry_bh(&bstats->syncp, start)); sum.tx_bytes += tmp.tx_bytes; sum.tx_packets += tmp.tx_packets; sum.rx_bytes += tmp.rx_bytes; @@ -206,24 +207,23 @@ static void br_poll_controller(struct net_device *br_dev) static void br_netpoll_cleanup(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); - struct net_bridge_port *p, *n; + struct net_bridge_port *p; - list_for_each_entry_safe(p, n, &br->port_list, list) { + list_for_each_entry(p, &br->port_list, list) br_netpoll_disable(p); - } } -static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) +static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, + gfp_t gfp) { struct net_bridge *br = netdev_priv(dev); - struct net_bridge_port *p, *n; + struct net_bridge_port *p; int err = 0; - list_for_each_entry_safe(p, n, &br->port_list, list) { + list_for_each_entry(p, &br->port_list, list) { if (!p->dev) continue; - - err = br_netpoll_enable(p); + err = br_netpoll_enable(p, gfp); if (err) goto fail; } @@ -236,20 +236,17 @@ fail: goto out; } -int br_netpoll_enable(struct net_bridge_port *p) +int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) { struct netpoll *np; int err = 0; - np = kzalloc(sizeof(*p->np), GFP_KERNEL); + np = kzalloc(sizeof(*p->np), gfp); err = -ENOMEM; if (!np) goto out; - np->dev = p->dev; - strlcpy(np->dev_name, p->dev->name, IFNAMSIZ); - - err = __netpoll_setup(np); + err = __netpoll_setup(np, p->dev, gfp); if (err) { kfree(np); goto out; @@ -270,11 +267,7 @@ void br_netpoll_disable(struct net_bridge_port *p) p->np = NULL; - /* Wait for transmitting packets to finish before freeing. */ - synchronize_rcu_bh(); - - __netpoll_cleanup(np); - kfree(np); + __netpoll_free_rcu(np); } #endif diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index e9466d41270..02015a505d2 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -65,7 +65,7 @@ static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) { skb->dev = to->dev; - if (unlikely(netpoll_tx_running(to->dev))) { + if (unlikely(netpoll_tx_running(to->br->dev))) { if (packet_length(skb) > skb->dev->mtu && !skb_is_gso(skb)) kfree_skb(skb); else { diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index e1144e1617b..1c8fdc3558c 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -361,7 +361,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (err) goto err2; - if (br_netpoll_info(br) && ((err = br_netpoll_enable(p)))) + if (br_netpoll_info(br) && ((err = br_netpoll_enable(p, GFP_KERNEL)))) goto err3; err = netdev_set_master(dev, br->dev); @@ -427,6 +427,10 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) if (!p || p->br != br) return -EINVAL; + /* Since more than one interface can be attached to a bridge, + * there still maybe an alternate path for netconsole to use; + * therefore there is no reason for a NETDEV_RELEASE event. + */ del_nbp(p); spin_lock_bh(&br->lock); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index b66581208cb..241743417f4 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -540,10 +540,11 @@ static struct net_bridge_mdb_entry *br_multicast_get_group( if (mdb->size >= max) { max *= 2; - if (unlikely(max >= br->hash_max)) { - br_warn(br, "Multicast hash table maximum " - "reached, disabling snooping: %s, %d\n", - port ? port->dev->name : br->dev->name, max); + if (unlikely(max > br->hash_max)) { + br_warn(br, "Multicast hash table maximum of %d " + "reached, disabling snooping: %s\n", + br->hash_max, + port ? port->dev->name : br->dev->name); err = -E2BIG; disable: br->multicast_disabled = 1; @@ -1160,7 +1161,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, goto out; } mld = (struct mld_msg *) icmp6_hdr(skb); - max_delay = msecs_to_jiffies(htons(mld->mld_maxdelay)); + max_delay = msecs_to_jiffies(ntohs(mld->mld_maxdelay)); if (max_delay) group = &mld->mld_mca; } else if (skb->len >= sizeof(*mld2q)) { diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index e41456bd3cc..68e8f364bbf 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -111,7 +111,13 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb) pppoe_proto(skb) == htons(PPP_IPV6) && \ brnf_filter_pppoe_tagged) -static void fake_update_pmtu(struct dst_entry *dst, u32 mtu) +static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) +{ +} + +static void fake_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) { } @@ -120,7 +126,9 @@ static u32 *fake_cow_metrics(struct dst_entry *dst, unsigned long old) return NULL; } -static struct neighbour *fake_neigh_lookup(const struct dst_entry *dst, const void *daddr) +static struct neighbour *fake_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) { return NULL; } @@ -134,6 +142,7 @@ static struct dst_ops fake_dst_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), .update_pmtu = fake_update_pmtu, + .redirect = fake_redirect, .cow_metrics = fake_cow_metrics, .neigh_lookup = fake_neigh_lookup, .mtu = fake_mtu, @@ -373,19 +382,29 @@ static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb) if (!skb->dev) goto free_skb; dst = skb_dst(skb); - neigh = dst_get_neighbour_noref(dst); - if (neigh->hh.hh_len) { - neigh_hh_bridge(&neigh->hh, skb); - skb->dev = nf_bridge->physindev; - return br_handle_frame_finish(skb); - } else { - /* the neighbour function below overwrites the complete - * MAC header, so we save the Ethernet source address and - * protocol number. */ - skb_copy_from_linear_data_offset(skb, -(ETH_HLEN-ETH_ALEN), skb->nf_bridge->data, ETH_HLEN-ETH_ALEN); - /* tell br_dev_xmit to continue with forwarding */ - nf_bridge->mask |= BRNF_BRIDGED_DNAT; - return neigh->output(neigh, skb); + neigh = dst_neigh_lookup_skb(dst, skb); + if (neigh) { + int ret; + + if (neigh->hh.hh_len) { + neigh_hh_bridge(&neigh->hh, skb); + skb->dev = nf_bridge->physindev; + ret = br_handle_frame_finish(skb); + } else { + /* the neighbour function below overwrites the complete + * MAC header, so we save the Ethernet source address and + * protocol number. + */ + skb_copy_from_linear_data_offset(skb, + -(ETH_HLEN-ETH_ALEN), + skb->nf_bridge->data, + ETH_HLEN-ETH_ALEN); + /* tell br_dev_xmit to continue with forwarding */ + nf_bridge->mask |= BRNF_BRIDGED_DNAT; + ret = neigh->output(neigh, skb); + } + neigh_release(neigh); + return ret; } free_skb: kfree_skb(skb); @@ -764,9 +783,9 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb, return NF_DROP; if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb)) - pf = PF_INET; + pf = NFPROTO_IPV4; else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) - pf = PF_INET6; + pf = NFPROTO_IPV6; else return NF_ACCEPT; @@ -778,13 +797,13 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb, nf_bridge->mask |= BRNF_PKT_TYPE; } - if (pf == PF_INET && br_parse_ip_options(skb)) + if (pf == NFPROTO_IPV4 && br_parse_ip_options(skb)) return NF_DROP; /* The physdev module checks on this */ nf_bridge->mask |= BRNF_BRIDGED; nf_bridge->physoutdev = skb->dev; - if (pf == PF_INET) + if (pf == NFPROTO_IPV4) skb->protocol = htons(ETH_P_IP); else skb->protocol = htons(ETH_P_IPV6); @@ -871,9 +890,9 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, return NF_DROP; if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb)) - pf = PF_INET; + pf = NFPROTO_IPV4; else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) - pf = PF_INET6; + pf = NFPROTO_IPV6; else return NF_ACCEPT; @@ -886,7 +905,7 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, nf_bridge_pull_encap_header(skb); nf_bridge_save_header(skb); - if (pf == PF_INET) + if (pf == NFPROTO_IPV4) skb->protocol = htons(ETH_P_IP); else skb->protocol = htons(ETH_P_IPV6); @@ -919,49 +938,49 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = { { .hook = br_nf_pre_routing, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_PRE_ROUTING, .priority = NF_BR_PRI_BRNF, }, { .hook = br_nf_local_in, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_IN, .priority = NF_BR_PRI_BRNF, }, { .hook = br_nf_forward_ip, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, .priority = NF_BR_PRI_BRNF - 1, }, { .hook = br_nf_forward_arp, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, .priority = NF_BR_PRI_BRNF, }, { .hook = br_nf_post_routing, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_POST_ROUTING, .priority = NF_BR_PRI_LAST, }, { .hook = ip_sabotage_in, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_FIRST, }, { .hook = ip_sabotage_in, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_FIRST, }, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index a768b2408ed..f507d2af964 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -316,7 +316,7 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p, netpoll_send_skb(np, skb); } -extern int br_netpoll_enable(struct net_bridge_port *p); +extern int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp); extern void br_netpoll_disable(struct net_bridge_port *p); #else static inline struct netpoll_info *br_netpoll_info(struct net_bridge *br) @@ -329,7 +329,7 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p, { } -static inline int br_netpoll_enable(struct net_bridge_port *p) +static inline int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) { return 0; } diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 6229b62749e..13b36bdc76a 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -27,7 +27,7 @@ struct brport_attribute { }; #define BRPORT_ATTR(_name,_mode,_show,_store) \ -struct brport_attribute brport_attr_##_name = { \ +const struct brport_attribute brport_attr_##_name = { \ .attr = {.name = __stringify(_name), \ .mode = _mode }, \ .show = _show, \ @@ -164,7 +164,7 @@ static BRPORT_ATTR(multicast_router, S_IRUGO | S_IWUSR, show_multicast_router, store_multicast_router); #endif -static struct brport_attribute *brport_attrs[] = { +static const struct brport_attribute *brport_attrs[] = { &brport_attr_path_cost, &brport_attr_priority, &brport_attr_port_id, @@ -241,7 +241,7 @@ const struct sysfs_ops brport_sysfs_ops = { int br_sysfs_addif(struct net_bridge_port *p) { struct net_bridge *br = p->br; - struct brport_attribute **a; + const struct brport_attribute **a; int err; err = sysfs_create_link(&p->kobj, &br->dev->dev.kobj, diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index 5449294bdd5..19063473c71 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -145,19 +145,24 @@ static void ebt_ulog_packet(unsigned int hooknr, const struct sk_buff *skb, if (!ub->skb) { if (!(ub->skb = ulog_alloc_skb(size))) - goto alloc_failure; + goto unlock; } else if (size > skb_tailroom(ub->skb)) { ulog_send(group); if (!(ub->skb = ulog_alloc_skb(size))) - goto alloc_failure; + goto unlock; } - nlh = NLMSG_PUT(ub->skb, 0, ub->qlen, 0, - size - NLMSG_ALIGN(sizeof(*nlh))); + nlh = nlmsg_put(ub->skb, 0, ub->qlen, 0, + size - NLMSG_ALIGN(sizeof(*nlh)), 0); + if (!nlh) { + kfree_skb(ub->skb); + ub->skb = NULL; + goto unlock; + } ub->qlen++; - pm = NLMSG_DATA(nlh); + pm = nlmsg_data(nlh); /* Fill in the ulog data */ pm->version = EBT_ULOG_VERSION; @@ -209,14 +214,6 @@ static void ebt_ulog_packet(unsigned int hooknr, const struct sk_buff *skb, unlock: spin_unlock_bh(lock); - - return; - -nlmsg_failure: - pr_debug("error during NLMSG_PUT. This should " - "not happen, please report to author.\n"); -alloc_failure: - goto unlock; } /* this function is registered with the netfilter core */ @@ -285,6 +282,9 @@ static int __init ebt_ulog_init(void) { int ret; int i; + struct netlink_kernel_cfg cfg = { + .groups = EBT_ULOG_MAXNLGROUPS, + }; if (nlbufsiz >= 128*1024) { pr_warning("Netlink buffer has to be <= 128kB," @@ -299,8 +299,7 @@ static int __init ebt_ulog_init(void) } ebtulognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, - EBT_ULOG_MAXNLGROUPS, NULL, NULL, - THIS_MODULE); + THIS_MODULE, &cfg); if (!ebtulognl) ret = -ENOMEM; else if ((ret = xt_register_target(&ebt_ulog_tg_reg)) != 0) diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 8c83c175b03..1ae1d9cb278 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -90,11 +90,8 @@ static int caifd_refcnt_read(struct caif_device_entry *e) /* Allocate new CAIF device. */ static struct caif_device_entry *caif_device_alloc(struct net_device *dev) { - struct caif_device_entry_list *caifdevs; struct caif_device_entry *caifd; - caifdevs = caif_device_list(dev_net(dev)); - caifd = kzalloc(sizeof(*caifd), GFP_KERNEL); if (!caifd) return NULL; @@ -131,6 +128,11 @@ void caif_flow_cb(struct sk_buff *skb) rcu_read_lock(); caifd = caif_get(skb->dev); + + WARN_ON(caifd == NULL); + if (caifd == NULL) + return; + caifd_hold(caifd); rcu_read_unlock(); diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 78f1cdad5b3..095259f8390 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -141,7 +141,7 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) err = sk_filter(sk, skb); if (err) return err; - if (!sk_rmem_schedule(sk, skb->truesize) && rx_flow_is_on(cf_sk)) { + if (!sk_rmem_schedule(sk, skb, skb->truesize) && rx_flow_is_on(cf_sk)) { set_rx_flow_off(cf_sk); net_dbg_ratelimited("sending flow OFF due to rmem_schedule\n"); caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_OFF_REQ); diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c index 047cd0eec02..44f270fc2d0 100644 --- a/net/caif/cfctrl.c +++ b/net/caif/cfctrl.c @@ -175,15 +175,17 @@ static void init_info(struct caif_payload_info *info, struct cfctrl *cfctrl) void cfctrl_enum_req(struct cflayer *layer, u8 physlinkid) { + struct cfpkt *pkt; struct cfctrl *cfctrl = container_obj(layer); - struct cfpkt *pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); struct cflayer *dn = cfctrl->serv.layer.dn; - if (!pkt) - return; + if (!dn) { pr_debug("not able to send enum request\n"); return; } + pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); + if (!pkt) + return; caif_assert(offsetof(struct cfctrl, serv.layer) == 0); init_info(cfpkt_info(pkt), cfctrl); cfpkt_info(pkt)->dev_info->id = physlinkid; @@ -302,18 +304,17 @@ int cfctrl_linkdown_req(struct cflayer *layer, u8 channelid, struct cflayer *client) { int ret; + struct cfpkt *pkt; struct cfctrl *cfctrl = container_obj(layer); - struct cfpkt *pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); struct cflayer *dn = cfctrl->serv.layer.dn; - if (!pkt) - return -ENOMEM; - if (!dn) { pr_debug("not able to send link-down request\n"); return -ENODEV; } - + pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); + if (!pkt) + return -ENOMEM; cfpkt_addbdy(pkt, CFCTRL_CMD_LINK_DESTROY); cfpkt_addbdy(pkt, channelid); init_info(cfpkt_info(pkt), cfctrl); diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 69771c04ba8..e597733affb 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -94,6 +94,10 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) /* check the version of IP */ ip_version = skb_header_pointer(skb, 0, 1, &buf); + if (!ip_version) { + kfree_skb(skb); + return -EINVAL; + } switch (*ip_version >> 4) { case 4: diff --git a/net/can/af_can.c b/net/can/af_can.c index 0ce2ad0696d..821022a7214 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -41,6 +41,7 @@ */ #include <linux/module.h> +#include <linux/stddef.h> #include <linux/init.h> #include <linux/kmod.h> #include <linux/slab.h> @@ -220,30 +221,46 @@ static int can_create(struct net *net, struct socket *sock, int protocol, * -ENOBUFS on full driver queue (see net_xmit_errno()) * -ENOMEM when local loopback failed at calling skb_clone() * -EPERM when trying to send on a non-CAN interface + * -EMSGSIZE CAN frame size is bigger than CAN interface MTU * -EINVAL when the skb->data does not contain a valid CAN frame */ int can_send(struct sk_buff *skb, int loop) { struct sk_buff *newskb = NULL; - struct can_frame *cf = (struct can_frame *)skb->data; - int err; + struct canfd_frame *cfd = (struct canfd_frame *)skb->data; + int err = -EINVAL; + + if (skb->len == CAN_MTU) { + skb->protocol = htons(ETH_P_CAN); + if (unlikely(cfd->len > CAN_MAX_DLEN)) + goto inval_skb; + } else if (skb->len == CANFD_MTU) { + skb->protocol = htons(ETH_P_CANFD); + if (unlikely(cfd->len > CANFD_MAX_DLEN)) + goto inval_skb; + } else + goto inval_skb; - if (skb->len != sizeof(struct can_frame) || cf->can_dlc > 8) { - kfree_skb(skb); - return -EINVAL; + /* + * Make sure the CAN frame can pass the selected CAN netdevice. + * As structs can_frame and canfd_frame are similar, we can provide + * CAN FD frames to legacy CAN drivers as long as the length is <= 8 + */ + if (unlikely(skb->len > skb->dev->mtu && cfd->len > CAN_MAX_DLEN)) { + err = -EMSGSIZE; + goto inval_skb; } - if (skb->dev->type != ARPHRD_CAN) { - kfree_skb(skb); - return -EPERM; + if (unlikely(skb->dev->type != ARPHRD_CAN)) { + err = -EPERM; + goto inval_skb; } - if (!(skb->dev->flags & IFF_UP)) { - kfree_skb(skb); - return -ENETDOWN; + if (unlikely(!(skb->dev->flags & IFF_UP))) { + err = -ENETDOWN; + goto inval_skb; } - skb->protocol = htons(ETH_P_CAN); skb_reset_network_header(skb); skb_reset_transport_header(skb); @@ -300,6 +317,10 @@ int can_send(struct sk_buff *skb, int loop) can_stats.tx_frames_delta++; return 0; + +inval_skb: + kfree_skb(skb); + return err; } EXPORT_SYMBOL(can_send); @@ -334,8 +355,8 @@ static struct dev_rcv_lists *find_dev_rcv_lists(struct net_device *dev) * relevant bits for the filter. * * The filter can be inverted (CAN_INV_FILTER bit set in can_id) or it can - * filter for error frames (CAN_ERR_FLAG bit set in mask). For error frames - * there is a special filterlist and a special rx path filter handling. + * filter for error messages (CAN_ERR_FLAG bit set in mask). For error msg + * frames there is a special filterlist and a special rx path filter handling. * * Return: * Pointer to optimal filterlist for the given can_id/mask pair. @@ -347,7 +368,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask, { canid_t inv = *can_id & CAN_INV_FILTER; /* save flag before masking */ - /* filter for error frames in extra filterlist */ + /* filter for error message frames in extra filterlist */ if (*mask & CAN_ERR_FLAG) { /* clear CAN_ERR_FLAG in filter entry */ *mask &= CAN_ERR_MASK; @@ -408,7 +429,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask, * <received_can_id> & mask == can_id & mask * * The filter can be inverted (CAN_INV_FILTER bit set in can_id) or it can - * filter for error frames (CAN_ERR_FLAG bit set in mask). + * filter for error message frames (CAN_ERR_FLAG bit set in mask). * * The provided pointer to the sk_buff is guaranteed to be valid as long as * the callback function is running. The callback function must *not* free @@ -578,7 +599,7 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) return 0; if (can_id & CAN_ERR_FLAG) { - /* check for error frame entries only */ + /* check for error message frame entries only */ hlist_for_each_entry_rcu(r, n, &d->rx[RX_ERR], list) { if (can_id & r->mask) { deliver(skb, r); @@ -632,24 +653,11 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) return matches; } -static int can_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) +static void can_receive(struct sk_buff *skb, struct net_device *dev) { struct dev_rcv_lists *d; - struct can_frame *cf = (struct can_frame *)skb->data; int matches; - if (!net_eq(dev_net(dev), &init_net)) - goto drop; - - if (WARN_ONCE(dev->type != ARPHRD_CAN || - skb->len != sizeof(struct can_frame) || - cf->can_dlc > 8, - "PF_CAN: dropped non conform skbuf: " - "dev type %d, len %d, can_dlc %d\n", - dev->type, skb->len, cf->can_dlc)) - goto drop; - /* update statistics */ can_stats.rx_frames++; can_stats.rx_frames_delta++; @@ -673,7 +681,49 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, can_stats.matches++; can_stats.matches_delta++; } +} +static int can_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + struct canfd_frame *cfd = (struct canfd_frame *)skb->data; + + if (unlikely(!net_eq(dev_net(dev), &init_net))) + goto drop; + + if (WARN_ONCE(dev->type != ARPHRD_CAN || + skb->len != CAN_MTU || + cfd->len > CAN_MAX_DLEN, + "PF_CAN: dropped non conform CAN skbuf: " + "dev type %d, len %d, datalen %d\n", + dev->type, skb->len, cfd->len)) + goto drop; + + can_receive(skb, dev); + return NET_RX_SUCCESS; + +drop: + kfree_skb(skb); + return NET_RX_DROP; +} + +static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + struct canfd_frame *cfd = (struct canfd_frame *)skb->data; + + if (unlikely(!net_eq(dev_net(dev), &init_net))) + goto drop; + + if (WARN_ONCE(dev->type != ARPHRD_CAN || + skb->len != CANFD_MTU || + cfd->len > CANFD_MAX_DLEN, + "PF_CAN: dropped non conform CAN FD skbuf: " + "dev type %d, len %d, datalen %d\n", + dev->type, skb->len, cfd->len)) + goto drop; + + can_receive(skb, dev); return NET_RX_SUCCESS; drop: @@ -807,10 +857,14 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg, static struct packet_type can_packet __read_mostly = { .type = cpu_to_be16(ETH_P_CAN), - .dev = NULL, .func = can_rcv, }; +static struct packet_type canfd_packet __read_mostly = { + .type = cpu_to_be16(ETH_P_CANFD), + .func = canfd_rcv, +}; + static const struct net_proto_family can_family_ops = { .family = PF_CAN, .create = can_create, @@ -824,6 +878,12 @@ static struct notifier_block can_netdev_notifier __read_mostly = { static __init int can_init(void) { + /* check for correct padding to be able to use the structs similarly */ + BUILD_BUG_ON(offsetof(struct can_frame, can_dlc) != + offsetof(struct canfd_frame, len) || + offsetof(struct can_frame, data) != + offsetof(struct canfd_frame, data)); + printk(banner); memset(&can_rx_alldev_list, 0, sizeof(can_rx_alldev_list)); @@ -846,6 +906,7 @@ static __init int can_init(void) sock_register(&can_family_ops); register_netdevice_notifier(&can_netdev_notifier); dev_add_pack(&can_packet); + dev_add_pack(&canfd_packet); return 0; } @@ -860,6 +921,7 @@ static __exit void can_exit(void) can_remove_proc(); /* protocol unregister */ + dev_remove_pack(&canfd_packet); dev_remove_pack(&can_packet); unregister_netdevice_notifier(&can_netdev_notifier); sock_unregister(PF_CAN); diff --git a/net/can/af_can.h b/net/can/af_can.h index fd882dbadad..1dccb4c3389 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -104,6 +104,9 @@ struct s_pstats { unsigned long rcv_entries_max; }; +/* receive filters subscribed for 'all' CAN devices */ +extern struct dev_rcv_lists can_rx_alldev_list; + /* function prototypes for the CAN networklayer procfs (proc.c) */ extern void can_init_proc(void); extern void can_remove_proc(void); diff --git a/net/can/gw.c b/net/can/gw.c index b41acf25668..b54d5e695b0 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -444,11 +444,14 @@ static int cgw_notifier(struct notifier_block *nb, return NOTIFY_DONE; } -static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj) +static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, + u32 pid, u32 seq, int flags) { struct cgw_frame_mod mb; struct rtcanmsg *rtcan; - struct nlmsghdr *nlh = nlmsg_put(skb, 0, 0, 0, sizeof(*rtcan), 0); + struct nlmsghdr *nlh; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtcan), flags); if (!nlh) return -EMSGSIZE; @@ -462,15 +465,11 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj) if (gwj->handled_frames) { if (nla_put_u32(skb, CGW_HANDLED, gwj->handled_frames) < 0) goto cancel; - else - nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(u32)); } if (gwj->dropped_frames) { if (nla_put_u32(skb, CGW_DROPPED, gwj->dropped_frames) < 0) goto cancel; - else - nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(u32)); } /* check non default settings of attributes */ @@ -480,8 +479,6 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj) mb.modtype = gwj->mod.modtype.and; if (nla_put(skb, CGW_MOD_AND, sizeof(mb), &mb) < 0) goto cancel; - else - nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(mb)); } if (gwj->mod.modtype.or) { @@ -489,8 +486,6 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj) mb.modtype = gwj->mod.modtype.or; if (nla_put(skb, CGW_MOD_OR, sizeof(mb), &mb) < 0) goto cancel; - else - nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(mb)); } if (gwj->mod.modtype.xor) { @@ -498,8 +493,6 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj) mb.modtype = gwj->mod.modtype.xor; if (nla_put(skb, CGW_MOD_XOR, sizeof(mb), &mb) < 0) goto cancel; - else - nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(mb)); } if (gwj->mod.modtype.set) { @@ -507,26 +500,18 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj) mb.modtype = gwj->mod.modtype.set; if (nla_put(skb, CGW_MOD_SET, sizeof(mb), &mb) < 0) goto cancel; - else - nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(mb)); } if (gwj->mod.csumfunc.crc8) { if (nla_put(skb, CGW_CS_CRC8, CGW_CS_CRC8_LEN, &gwj->mod.csum.crc8) < 0) goto cancel; - else - nlh->nlmsg_len += NLA_HDRLEN + \ - NLA_ALIGN(CGW_CS_CRC8_LEN); } if (gwj->mod.csumfunc.xor) { if (nla_put(skb, CGW_CS_XOR, CGW_CS_XOR_LEN, &gwj->mod.csum.xor) < 0) goto cancel; - else - nlh->nlmsg_len += NLA_HDRLEN + \ - NLA_ALIGN(CGW_CS_XOR_LEN); } if (gwj->gwtype == CGW_TYPE_CAN_CAN) { @@ -535,23 +520,16 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj) if (nla_put(skb, CGW_FILTER, sizeof(struct can_filter), &gwj->ccgw.filter) < 0) goto cancel; - else - nlh->nlmsg_len += NLA_HDRLEN + - NLA_ALIGN(sizeof(struct can_filter)); } if (nla_put_u32(skb, CGW_SRC_IF, gwj->ccgw.src_idx) < 0) goto cancel; - else - nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(u32)); if (nla_put_u32(skb, CGW_DST_IF, gwj->ccgw.dst_idx) < 0) goto cancel; - else - nlh->nlmsg_len += NLA_HDRLEN + NLA_ALIGN(sizeof(u32)); } - return skb->len; + return nlmsg_end(skb, nlh); cancel: nlmsg_cancel(skb, nlh); @@ -571,7 +549,8 @@ static int cgw_dump_jobs(struct sk_buff *skb, struct netlink_callback *cb) if (idx < s_idx) goto cont; - if (cgw_put_job(skb, gwj) < 0) + if (cgw_put_job(skb, gwj, RTM_NEWROUTE, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) break; cont: idx++; @@ -583,6 +562,18 @@ cont: return skb->len; } +static const struct nla_policy cgw_policy[CGW_MAX+1] = { + [CGW_MOD_AND] = { .len = sizeof(struct cgw_frame_mod) }, + [CGW_MOD_OR] = { .len = sizeof(struct cgw_frame_mod) }, + [CGW_MOD_XOR] = { .len = sizeof(struct cgw_frame_mod) }, + [CGW_MOD_SET] = { .len = sizeof(struct cgw_frame_mod) }, + [CGW_CS_XOR] = { .len = sizeof(struct cgw_csum_xor) }, + [CGW_CS_CRC8] = { .len = sizeof(struct cgw_csum_crc8) }, + [CGW_SRC_IF] = { .type = NLA_U32 }, + [CGW_DST_IF] = { .type = NLA_U32 }, + [CGW_FILTER] = { .len = sizeof(struct can_filter) }, +}; + /* check for common and gwtype specific attributes */ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, u8 gwtype, void *gwtypeattr) @@ -595,14 +586,14 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, /* initialize modification & checksum data space */ memset(mod, 0, sizeof(*mod)); - err = nlmsg_parse(nlh, sizeof(struct rtcanmsg), tb, CGW_MAX, NULL); + err = nlmsg_parse(nlh, sizeof(struct rtcanmsg), tb, CGW_MAX, + cgw_policy); if (err < 0) return err; /* check for AND/OR/XOR/SET modifications */ - if (tb[CGW_MOD_AND] && - nla_len(tb[CGW_MOD_AND]) == CGW_MODATTR_LEN) { + if (tb[CGW_MOD_AND]) { nla_memcpy(&mb, tb[CGW_MOD_AND], CGW_MODATTR_LEN); canframecpy(&mod->modframe.and, &mb.cf); @@ -618,8 +609,7 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, mod->modfunc[modidx++] = mod_and_data; } - if (tb[CGW_MOD_OR] && - nla_len(tb[CGW_MOD_OR]) == CGW_MODATTR_LEN) { + if (tb[CGW_MOD_OR]) { nla_memcpy(&mb, tb[CGW_MOD_OR], CGW_MODATTR_LEN); canframecpy(&mod->modframe.or, &mb.cf); @@ -635,8 +625,7 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, mod->modfunc[modidx++] = mod_or_data; } - if (tb[CGW_MOD_XOR] && - nla_len(tb[CGW_MOD_XOR]) == CGW_MODATTR_LEN) { + if (tb[CGW_MOD_XOR]) { nla_memcpy(&mb, tb[CGW_MOD_XOR], CGW_MODATTR_LEN); canframecpy(&mod->modframe.xor, &mb.cf); @@ -652,8 +641,7 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, mod->modfunc[modidx++] = mod_xor_data; } - if (tb[CGW_MOD_SET] && - nla_len(tb[CGW_MOD_SET]) == CGW_MODATTR_LEN) { + if (tb[CGW_MOD_SET]) { nla_memcpy(&mb, tb[CGW_MOD_SET], CGW_MODATTR_LEN); canframecpy(&mod->modframe.set, &mb.cf); @@ -672,11 +660,8 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, /* check for checksum operations after CAN frame modifications */ if (modidx) { - if (tb[CGW_CS_CRC8] && - nla_len(tb[CGW_CS_CRC8]) == CGW_CS_CRC8_LEN) { - - struct cgw_csum_crc8 *c = (struct cgw_csum_crc8 *)\ - nla_data(tb[CGW_CS_CRC8]); + if (tb[CGW_CS_CRC8]) { + struct cgw_csum_crc8 *c = nla_data(tb[CGW_CS_CRC8]); err = cgw_chk_csum_parms(c->from_idx, c->to_idx, c->result_idx); @@ -699,11 +684,8 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, mod->csumfunc.crc8 = cgw_csum_crc8_neg; } - if (tb[CGW_CS_XOR] && - nla_len(tb[CGW_CS_XOR]) == CGW_CS_XOR_LEN) { - - struct cgw_csum_xor *c = (struct cgw_csum_xor *)\ - nla_data(tb[CGW_CS_XOR]); + if (tb[CGW_CS_XOR]) { + struct cgw_csum_xor *c = nla_data(tb[CGW_CS_XOR]); err = cgw_chk_csum_parms(c->from_idx, c->to_idx, c->result_idx); @@ -735,8 +717,7 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, memset(ccgw, 0, sizeof(*ccgw)); /* check for can_filter in attributes */ - if (tb[CGW_FILTER] && - nla_len(tb[CGW_FILTER]) == sizeof(struct can_filter)) + if (tb[CGW_FILTER]) nla_memcpy(&ccgw->filter, tb[CGW_FILTER], sizeof(struct can_filter)); @@ -746,13 +727,8 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, if (!tb[CGW_SRC_IF] || !tb[CGW_DST_IF]) return err; - if (nla_len(tb[CGW_SRC_IF]) == sizeof(u32)) - nla_memcpy(&ccgw->src_idx, tb[CGW_SRC_IF], - sizeof(u32)); - - if (nla_len(tb[CGW_DST_IF]) == sizeof(u32)) - nla_memcpy(&ccgw->dst_idx, tb[CGW_DST_IF], - sizeof(u32)); + ccgw->src_idx = nla_get_u32(tb[CGW_SRC_IF]); + ccgw->dst_idx = nla_get_u32(tb[CGW_DST_IF]); /* both indices set to 0 for flushing all routing entries */ if (!ccgw->src_idx && !ccgw->dst_idx) diff --git a/net/can/proc.c b/net/can/proc.c index ba873c36d2f..3b6dd318049 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -83,9 +83,6 @@ static const char rx_list_name[][8] = { [RX_EFF] = "rx_eff", }; -/* receive filters subscribed for 'all' CAN devices */ -extern struct dev_rcv_lists can_rx_alldev_list; - /* * af_can statistics stuff */ diff --git a/net/can/raw.c b/net/can/raw.c index 46cca3a91d1..3e9c89356a9 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -82,6 +82,7 @@ struct raw_sock { struct notifier_block notifier; int loopback; int recv_own_msgs; + int fd_frames; int count; /* number of active filters */ struct can_filter dfilter; /* default/single filter */ struct can_filter *filter; /* pointer to filter(s) */ @@ -119,6 +120,14 @@ static void raw_rcv(struct sk_buff *oskb, void *data) if (!ro->recv_own_msgs && oskb->sk == sk) return; + /* do not pass frames with DLC > 8 to a legacy socket */ + if (!ro->fd_frames) { + struct canfd_frame *cfd = (struct canfd_frame *)oskb->data; + + if (unlikely(cfd->len > CAN_MAX_DLEN)) + return; + } + /* clone the given skb to be able to enqueue it into the rcv queue */ skb = skb_clone(oskb, GFP_ATOMIC); if (!skb) @@ -291,6 +300,7 @@ static int raw_init(struct sock *sk) /* set default loopback behaviour */ ro->loopback = 1; ro->recv_own_msgs = 0; + ro->fd_frames = 0; /* set notifier */ ro->notifier.notifier_call = raw_notifier; @@ -569,6 +579,15 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, break; + case CAN_RAW_FD_FRAMES: + if (optlen != sizeof(ro->fd_frames)) + return -EINVAL; + + if (copy_from_user(&ro->fd_frames, optval, optlen)) + return -EFAULT; + + break; + default: return -ENOPROTOOPT; } @@ -627,6 +646,12 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, val = &ro->recv_own_msgs; break; + case CAN_RAW_FD_FRAMES: + if (len > sizeof(int)) + len = sizeof(int); + val = &ro->fd_frames; + break; + default: return -ENOPROTOOPT; } @@ -662,8 +687,13 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock, } else ifindex = ro->ifindex; - if (size != sizeof(struct can_frame)) - return -EINVAL; + if (ro->fd_frames) { + if (unlikely(size != CANFD_MTU && size != CAN_MTU)) + return -EINVAL; + } else { + if (unlikely(size != CAN_MTU)) + return -EINVAL; + } dev = dev_get_by_index(&init_net, ifindex); if (!dev) @@ -705,7 +735,9 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; + struct raw_sock *ro = raw_sk(sk); struct sk_buff *skb; + int rxmtu; int err = 0; int noblock; @@ -716,10 +748,20 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) return err; - if (size < skb->len) + /* + * when serving a legacy socket the DLC <= 8 is already checked inside + * raw_rcv(). Now check if we need to pass a canfd_frame to a legacy + * socket and cut the possible CANFD_MTU/CAN_MTU length to CAN_MTU + */ + if (!ro->fd_frames) + rxmtu = CAN_MTU; + else + rxmtu = skb->len; + + if (size < rxmtu) msg->msg_flags |= MSG_TRUNC; else - size = skb->len; + size = rxmtu; err = memcpy_toiovec(msg->msg_iov, skb->data, size); if (err < 0) { diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index ba4323bce0e..a8020293f34 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -17,6 +17,7 @@ #include <linux/string.h> +#include <linux/ceph/ceph_features.h> #include <linux/ceph/libceph.h> #include <linux/ceph/debugfs.h> #include <linux/ceph/decode.h> @@ -83,7 +84,6 @@ int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid) return -1; } } else { - pr_info("client%lld fsid %pU\n", ceph_client_id(client), fsid); memcpy(&client->fsid, fsid, sizeof(*fsid)); } return 0; @@ -460,27 +460,23 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, client->auth_err = 0; client->extra_mon_dispatch = NULL; - client->supported_features = CEPH_FEATURE_SUPPORTED_DEFAULT | + client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT | supported_features; - client->required_features = CEPH_FEATURE_REQUIRED_DEFAULT | + client->required_features = CEPH_FEATURES_REQUIRED_DEFAULT | required_features; /* msgr */ if (ceph_test_opt(client, MYIP)) myaddr = &client->options->my_addr; - client->msgr = ceph_messenger_create(myaddr, - client->supported_features, - client->required_features); - if (IS_ERR(client->msgr)) { - err = PTR_ERR(client->msgr); - goto fail; - } - client->msgr->nocrc = ceph_test_opt(client, NOCRC); + ceph_messenger_init(&client->msgr, myaddr, + client->supported_features, + client->required_features, + ceph_test_opt(client, NOCRC)); /* subsystems */ err = ceph_monc_init(&client->monc, client); if (err < 0) - goto fail_msgr; + goto fail; err = ceph_osdc_init(&client->osdc, client); if (err < 0) goto fail_monc; @@ -489,8 +485,6 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, fail_monc: ceph_monc_stop(&client->monc); -fail_msgr: - ceph_messenger_destroy(client->msgr); fail: kfree(client); return ERR_PTR(err); @@ -501,6 +495,8 @@ void ceph_destroy_client(struct ceph_client *client) { dout("destroy_client %p\n", client); + atomic_set(&client->msgr.stopping, 1); + /* unmount */ ceph_osdc_stop(&client->osdc); @@ -508,8 +504,6 @@ void ceph_destroy_client(struct ceph_client *client) ceph_debugfs_client_cleanup(client); - ceph_messenger_destroy(client->msgr); - ceph_destroy_options(client->options); kfree(client); diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index d7edc24333b..35fce755ce1 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -306,7 +306,6 @@ static int crush_choose(const struct crush_map *map, int item = 0; int itemtype; int collide, reject; - const unsigned int orig_tries = 5; /* attempts before we fall back to search */ dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "", bucket->id, x, outpos, numrep); @@ -351,8 +350,9 @@ static int crush_choose(const struct crush_map *map, reject = 1; goto reject; } - if (flocal >= (in->size>>1) && - flocal > orig_tries) + if (map->choose_local_fallback_tries > 0 && + flocal >= (in->size>>1) && + flocal > map->choose_local_fallback_tries) item = bucket_perm_choose(in, x, r); else item = crush_bucket_choose(in, x, r); @@ -422,13 +422,14 @@ reject: ftotal++; flocal++; - if (collide && flocal < 3) + if (collide && flocal <= map->choose_local_tries) /* retry locally a few times */ retry_bucket = 1; - else if (flocal <= in->size + orig_tries) + else if (map->choose_local_fallback_tries > 0 && + flocal <= in->size + map->choose_local_fallback_tries) /* exhaustive bucket search */ retry_bucket = 1; - else if (ftotal < 20) + else if (ftotal <= map->choose_total_tries) /* then retry descent */ retry_descent = 1; else diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index b780cb7947d..9da7fdd3cd8 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -466,6 +466,7 @@ void ceph_key_destroy(struct key *key) { struct ceph_crypto_key *ckey = key->payload.data; ceph_crypto_key_destroy(ckey); + kfree(ckey); } struct key_type key_type_ceph = { diff --git a/net/ceph/crypto.h b/net/ceph/crypto.h index 1919d1550d7..3572dc518bc 100644 --- a/net/ceph/crypto.h +++ b/net/ceph/crypto.h @@ -16,7 +16,8 @@ struct ceph_crypto_key { static inline void ceph_crypto_key_destroy(struct ceph_crypto_key *key) { - kfree(key->key); + if (key) + kfree(key->key); } extern int ceph_crypto_key_clone(struct ceph_crypto_key *dst, diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c index 54b531a0112..38b5dc1823d 100644 --- a/net/ceph/debugfs.c +++ b/net/ceph/debugfs.c @@ -189,6 +189,9 @@ int ceph_debugfs_client_init(struct ceph_client *client) snprintf(name, sizeof(name), "%pU.client%lld", &client->fsid, client->monc.auth->global_id); + dout("ceph_debugfs_client_init %p %s\n", client, name); + + BUG_ON(client->debugfs_dir); client->debugfs_dir = debugfs_create_dir(name, ceph_debugfs_dir); if (!client->debugfs_dir) goto out; @@ -234,6 +237,7 @@ out: void ceph_debugfs_client_cleanup(struct ceph_client *client) { + dout("ceph_debugfs_client_cleanup %p\n", client); debugfs_remove(client->debugfs_osdmap); debugfs_remove(client->debugfs_monmap); debugfs_remove(client->osdc.debugfs_file); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 10255e81be7..24c5eea8c45 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -29,6 +29,74 @@ * the sender. */ +/* + * We track the state of the socket on a given connection using + * values defined below. The transition to a new socket state is + * handled by a function which verifies we aren't coming from an + * unexpected state. + * + * -------- + * | NEW* | transient initial state + * -------- + * | con_sock_state_init() + * v + * ---------- + * | CLOSED | initialized, but no socket (and no + * ---------- TCP connection) + * ^ \ + * | \ con_sock_state_connecting() + * | ---------------------- + * | \ + * + con_sock_state_closed() \ + * |+--------------------------- \ + * | \ \ \ + * | ----------- \ \ + * | | CLOSING | socket event; \ \ + * | ----------- await close \ \ + * | ^ \ | + * | | \ | + * | + con_sock_state_closing() \ | + * | / \ | | + * | / --------------- | | + * | / \ v v + * | / -------------- + * | / -----------------| CONNECTING | socket created, TCP + * | | / -------------- connect initiated + * | | | con_sock_state_connected() + * | | v + * ------------- + * | CONNECTED | TCP connection established + * ------------- + * + * State values for ceph_connection->sock_state; NEW is assumed to be 0. + */ + +#define CON_SOCK_STATE_NEW 0 /* -> CLOSED */ +#define CON_SOCK_STATE_CLOSED 1 /* -> CONNECTING */ +#define CON_SOCK_STATE_CONNECTING 2 /* -> CONNECTED or -> CLOSING */ +#define CON_SOCK_STATE_CONNECTED 3 /* -> CLOSING or -> CLOSED */ +#define CON_SOCK_STATE_CLOSING 4 /* -> CLOSED */ + +/* + * connection states + */ +#define CON_STATE_CLOSED 1 /* -> PREOPEN */ +#define CON_STATE_PREOPEN 2 /* -> CONNECTING, CLOSED */ +#define CON_STATE_CONNECTING 3 /* -> NEGOTIATING, CLOSED */ +#define CON_STATE_NEGOTIATING 4 /* -> OPEN, CLOSED */ +#define CON_STATE_OPEN 5 /* -> STANDBY, CLOSED */ +#define CON_STATE_STANDBY 6 /* -> PREOPEN, CLOSED */ + +/* + * ceph_connection flag bits + */ +#define CON_FLAG_LOSSYTX 0 /* we can close channel or drop + * messages on errors */ +#define CON_FLAG_KEEPALIVE_PENDING 1 /* we need to send a keepalive */ +#define CON_FLAG_WRITE_PENDING 2 /* we have data ready to send */ +#define CON_FLAG_SOCK_CLOSED 3 /* socket state changed to closed */ +#define CON_FLAG_BACKOFF 4 /* need to retry queuing delayed work */ + /* static tag bytes (protocol control messages) */ static char tag_msg = CEPH_MSGR_TAG_MSG; static char tag_ack = CEPH_MSGR_TAG_ACK; @@ -147,72 +215,130 @@ void ceph_msgr_flush(void) } EXPORT_SYMBOL(ceph_msgr_flush); +/* Connection socket state transition functions */ + +static void con_sock_state_init(struct ceph_connection *con) +{ + int old_state; + + old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CLOSED); + if (WARN_ON(old_state != CON_SOCK_STATE_NEW)) + printk("%s: unexpected old state %d\n", __func__, old_state); + dout("%s con %p sock %d -> %d\n", __func__, con, old_state, + CON_SOCK_STATE_CLOSED); +} + +static void con_sock_state_connecting(struct ceph_connection *con) +{ + int old_state; + + old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CONNECTING); + if (WARN_ON(old_state != CON_SOCK_STATE_CLOSED)) + printk("%s: unexpected old state %d\n", __func__, old_state); + dout("%s con %p sock %d -> %d\n", __func__, con, old_state, + CON_SOCK_STATE_CONNECTING); +} + +static void con_sock_state_connected(struct ceph_connection *con) +{ + int old_state; + + old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CONNECTED); + if (WARN_ON(old_state != CON_SOCK_STATE_CONNECTING)) + printk("%s: unexpected old state %d\n", __func__, old_state); + dout("%s con %p sock %d -> %d\n", __func__, con, old_state, + CON_SOCK_STATE_CONNECTED); +} + +static void con_sock_state_closing(struct ceph_connection *con) +{ + int old_state; + + old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CLOSING); + if (WARN_ON(old_state != CON_SOCK_STATE_CONNECTING && + old_state != CON_SOCK_STATE_CONNECTED && + old_state != CON_SOCK_STATE_CLOSING)) + printk("%s: unexpected old state %d\n", __func__, old_state); + dout("%s con %p sock %d -> %d\n", __func__, con, old_state, + CON_SOCK_STATE_CLOSING); +} + +static void con_sock_state_closed(struct ceph_connection *con) +{ + int old_state; + + old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CLOSED); + if (WARN_ON(old_state != CON_SOCK_STATE_CONNECTED && + old_state != CON_SOCK_STATE_CLOSING && + old_state != CON_SOCK_STATE_CONNECTING && + old_state != CON_SOCK_STATE_CLOSED)) + printk("%s: unexpected old state %d\n", __func__, old_state); + dout("%s con %p sock %d -> %d\n", __func__, con, old_state, + CON_SOCK_STATE_CLOSED); +} /* * socket callback functions */ /* data available on socket, or listen socket received a connect */ -static void ceph_data_ready(struct sock *sk, int count_unused) +static void ceph_sock_data_ready(struct sock *sk, int count_unused) { struct ceph_connection *con = sk->sk_user_data; + if (atomic_read(&con->msgr->stopping)) { + return; + } if (sk->sk_state != TCP_CLOSE_WAIT) { - dout("ceph_data_ready on %p state = %lu, queueing work\n", + dout("%s on %p state = %lu, queueing work\n", __func__, con, con->state); queue_con(con); } } /* socket has buffer space for writing */ -static void ceph_write_space(struct sock *sk) +static void ceph_sock_write_space(struct sock *sk) { struct ceph_connection *con = sk->sk_user_data; /* only queue to workqueue if there is data we want to write, * and there is sufficient space in the socket buffer to accept - * more data. clear SOCK_NOSPACE so that ceph_write_space() + * more data. clear SOCK_NOSPACE so that ceph_sock_write_space() * doesn't get called again until try_write() fills the socket * buffer. See net/ipv4/tcp_input.c:tcp_check_space() * and net/core/stream.c:sk_stream_write_space(). */ - if (test_bit(WRITE_PENDING, &con->state)) { + if (test_bit(CON_FLAG_WRITE_PENDING, &con->flags)) { if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) { - dout("ceph_write_space %p queueing write work\n", con); + dout("%s %p queueing write work\n", __func__, con); clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); queue_con(con); } } else { - dout("ceph_write_space %p nothing to write\n", con); + dout("%s %p nothing to write\n", __func__, con); } } /* socket's state has changed */ -static void ceph_state_change(struct sock *sk) +static void ceph_sock_state_change(struct sock *sk) { struct ceph_connection *con = sk->sk_user_data; - dout("ceph_state_change %p state = %lu sk_state = %u\n", + dout("%s %p state = %lu sk_state = %u\n", __func__, con, con->state, sk->sk_state); - if (test_bit(CLOSED, &con->state)) - return; - switch (sk->sk_state) { case TCP_CLOSE: - dout("ceph_state_change TCP_CLOSE\n"); + dout("%s TCP_CLOSE\n", __func__); case TCP_CLOSE_WAIT: - dout("ceph_state_change TCP_CLOSE_WAIT\n"); - if (test_and_set_bit(SOCK_CLOSED, &con->state) == 0) { - if (test_bit(CONNECTING, &con->state)) - con->error_msg = "connection failed"; - else - con->error_msg = "socket closed"; - queue_con(con); - } + dout("%s TCP_CLOSE_WAIT\n", __func__); + con_sock_state_closing(con); + set_bit(CON_FLAG_SOCK_CLOSED, &con->flags); + queue_con(con); break; case TCP_ESTABLISHED: - dout("ceph_state_change TCP_ESTABLISHED\n"); + dout("%s TCP_ESTABLISHED\n", __func__); + con_sock_state_connected(con); queue_con(con); break; default: /* Everything else is uninteresting */ @@ -228,9 +354,9 @@ static void set_sock_callbacks(struct socket *sock, { struct sock *sk = sock->sk; sk->sk_user_data = con; - sk->sk_data_ready = ceph_data_ready; - sk->sk_write_space = ceph_write_space; - sk->sk_state_change = ceph_state_change; + sk->sk_data_ready = ceph_sock_data_ready; + sk->sk_write_space = ceph_sock_write_space; + sk->sk_state_change = ceph_sock_state_change; } @@ -262,6 +388,7 @@ static int ceph_tcp_connect(struct ceph_connection *con) dout("connect %s\n", ceph_pr_addr(&con->peer_addr.in_addr)); + con_sock_state_connecting(con); ret = sock->ops->connect(sock, (struct sockaddr *)paddr, sizeof(*paddr), O_NONBLOCK); if (ret == -EINPROGRESS) { @@ -277,7 +404,6 @@ static int ceph_tcp_connect(struct ceph_connection *con) return ret; } con->sock = sock; - return 0; } @@ -333,16 +459,24 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page, */ static int con_close_socket(struct ceph_connection *con) { - int rc; + int rc = 0; dout("con_close_socket on %p sock %p\n", con, con->sock); - if (!con->sock) - return 0; - set_bit(SOCK_CLOSED, &con->state); - rc = con->sock->ops->shutdown(con->sock, SHUT_RDWR); - sock_release(con->sock); - con->sock = NULL; - clear_bit(SOCK_CLOSED, &con->state); + if (con->sock) { + rc = con->sock->ops->shutdown(con->sock, SHUT_RDWR); + sock_release(con->sock); + con->sock = NULL; + } + + /* + * Forcibly clear the SOCK_CLOSED flag. It gets set + * independent of the connection mutex, and we could have + * received a socket close event before we had the chance to + * shut the socket down. + */ + clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags); + + con_sock_state_closed(con); return rc; } @@ -353,6 +487,10 @@ static int con_close_socket(struct ceph_connection *con) static void ceph_msg_remove(struct ceph_msg *msg) { list_del_init(&msg->list_head); + BUG_ON(msg->con == NULL); + msg->con->ops->put(msg->con); + msg->con = NULL; + ceph_msg_put(msg); } static void ceph_msg_remove_list(struct list_head *head) @@ -372,8 +510,11 @@ static void reset_connection(struct ceph_connection *con) ceph_msg_remove_list(&con->out_sent); if (con->in_msg) { + BUG_ON(con->in_msg->con != con); + con->in_msg->con = NULL; ceph_msg_put(con->in_msg); con->in_msg = NULL; + con->ops->put(con); } con->connect_seq = 0; @@ -391,32 +532,44 @@ static void reset_connection(struct ceph_connection *con) */ void ceph_con_close(struct ceph_connection *con) { + mutex_lock(&con->mutex); dout("con_close %p peer %s\n", con, ceph_pr_addr(&con->peer_addr.in_addr)); - set_bit(CLOSED, &con->state); /* in case there's queued work */ - clear_bit(STANDBY, &con->state); /* avoid connect_seq bump */ - clear_bit(LOSSYTX, &con->state); /* so we retry next connect */ - clear_bit(KEEPALIVE_PENDING, &con->state); - clear_bit(WRITE_PENDING, &con->state); - mutex_lock(&con->mutex); + con->state = CON_STATE_CLOSED; + + clear_bit(CON_FLAG_LOSSYTX, &con->flags); /* so we retry next connect */ + clear_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags); + clear_bit(CON_FLAG_WRITE_PENDING, &con->flags); + clear_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags); + clear_bit(CON_FLAG_BACKOFF, &con->flags); + reset_connection(con); con->peer_global_seq = 0; cancel_delayed_work(&con->work); + con_close_socket(con); mutex_unlock(&con->mutex); - queue_con(con); } EXPORT_SYMBOL(ceph_con_close); /* * Reopen a closed connection, with a new peer address. */ -void ceph_con_open(struct ceph_connection *con, struct ceph_entity_addr *addr) +void ceph_con_open(struct ceph_connection *con, + __u8 entity_type, __u64 entity_num, + struct ceph_entity_addr *addr) { + mutex_lock(&con->mutex); dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr)); - set_bit(OPENING, &con->state); - clear_bit(CLOSED, &con->state); + + BUG_ON(con->state != CON_STATE_CLOSED); + con->state = CON_STATE_PREOPEN; + + con->peer_name.type = (__u8) entity_type; + con->peer_name.num = cpu_to_le64(entity_num); + memcpy(&con->peer_addr, addr, sizeof(*addr)); con->delay = 0; /* reset backoff memory */ + mutex_unlock(&con->mutex); queue_con(con); } EXPORT_SYMBOL(ceph_con_open); @@ -430,42 +583,26 @@ bool ceph_con_opened(struct ceph_connection *con) } /* - * generic get/put - */ -struct ceph_connection *ceph_con_get(struct ceph_connection *con) -{ - int nref = __atomic_add_unless(&con->nref, 1, 0); - - dout("con_get %p nref = %d -> %d\n", con, nref, nref + 1); - - return nref ? con : NULL; -} - -void ceph_con_put(struct ceph_connection *con) -{ - int nref = atomic_dec_return(&con->nref); - - BUG_ON(nref < 0); - if (nref == 0) { - BUG_ON(con->sock); - kfree(con); - } - dout("con_put %p nref = %d -> %d\n", con, nref + 1, nref); -} - -/* * initialize a new connection. */ -void ceph_con_init(struct ceph_messenger *msgr, struct ceph_connection *con) +void ceph_con_init(struct ceph_connection *con, void *private, + const struct ceph_connection_operations *ops, + struct ceph_messenger *msgr) { dout("con_init %p\n", con); memset(con, 0, sizeof(*con)); - atomic_set(&con->nref, 1); + con->private = private; + con->ops = ops; con->msgr = msgr; + + con_sock_state_init(con); + mutex_init(&con->mutex); INIT_LIST_HEAD(&con->out_queue); INIT_LIST_HEAD(&con->out_sent); INIT_DELAYED_WORK(&con->work, con_work); + + con->state = CON_STATE_CLOSED; } EXPORT_SYMBOL(ceph_con_init); @@ -486,14 +623,14 @@ static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt) return ret; } -static void ceph_con_out_kvec_reset(struct ceph_connection *con) +static void con_out_kvec_reset(struct ceph_connection *con) { con->out_kvec_left = 0; con->out_kvec_bytes = 0; con->out_kvec_cur = &con->out_kvec[0]; } -static void ceph_con_out_kvec_add(struct ceph_connection *con, +static void con_out_kvec_add(struct ceph_connection *con, size_t size, void *data) { int index; @@ -507,6 +644,53 @@ static void ceph_con_out_kvec_add(struct ceph_connection *con, con->out_kvec_bytes += size; } +#ifdef CONFIG_BLOCK +static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg) +{ + if (!bio) { + *iter = NULL; + *seg = 0; + return; + } + *iter = bio; + *seg = bio->bi_idx; +} + +static void iter_bio_next(struct bio **bio_iter, int *seg) +{ + if (*bio_iter == NULL) + return; + + BUG_ON(*seg >= (*bio_iter)->bi_vcnt); + + (*seg)++; + if (*seg == (*bio_iter)->bi_vcnt) + init_bio_iter((*bio_iter)->bi_next, bio_iter, seg); +} +#endif + +static void prepare_write_message_data(struct ceph_connection *con) +{ + struct ceph_msg *msg = con->out_msg; + + BUG_ON(!msg); + BUG_ON(!msg->hdr.data_len); + + /* initialize page iterator */ + con->out_msg_pos.page = 0; + if (msg->pages) + con->out_msg_pos.page_pos = msg->page_alignment; + else + con->out_msg_pos.page_pos = 0; +#ifdef CONFIG_BLOCK + if (msg->bio) + init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg); +#endif + con->out_msg_pos.data_pos = 0; + con->out_msg_pos.did_page_crc = false; + con->out_more = 1; /* data + footer will follow */ +} + /* * Prepare footer for currently outgoing message, and finish things * off. Assumes out_kvec* are already valid.. we just add on to the end. @@ -516,6 +700,8 @@ static void prepare_write_message_footer(struct ceph_connection *con) struct ceph_msg *m = con->out_msg; int v = con->out_kvec_left; + m->footer.flags |= CEPH_MSG_FOOTER_COMPLETE; + dout("prepare_write_message_footer %p\n", con); con->out_kvec_is_msg = true; con->out_kvec[v].iov_base = &m->footer; @@ -534,7 +720,7 @@ static void prepare_write_message(struct ceph_connection *con) struct ceph_msg *m; u32 crc; - ceph_con_out_kvec_reset(con); + con_out_kvec_reset(con); con->out_kvec_is_msg = true; con->out_msg_done = false; @@ -542,14 +728,16 @@ static void prepare_write_message(struct ceph_connection *con) * TCP packet that's a good thing. */ if (con->in_seq > con->in_seq_acked) { con->in_seq_acked = con->in_seq; - ceph_con_out_kvec_add(con, sizeof (tag_ack), &tag_ack); + con_out_kvec_add(con, sizeof (tag_ack), &tag_ack); con->out_temp_ack = cpu_to_le64(con->in_seq_acked); - ceph_con_out_kvec_add(con, sizeof (con->out_temp_ack), + con_out_kvec_add(con, sizeof (con->out_temp_ack), &con->out_temp_ack); } + BUG_ON(list_empty(&con->out_queue)); m = list_first_entry(&con->out_queue, struct ceph_msg, list_head); con->out_msg = m; + BUG_ON(m->con != con); /* put message on sent list */ ceph_msg_get(m); @@ -576,18 +764,18 @@ static void prepare_write_message(struct ceph_connection *con) BUG_ON(le32_to_cpu(m->hdr.front_len) != m->front.iov_len); /* tag + hdr + front + middle */ - ceph_con_out_kvec_add(con, sizeof (tag_msg), &tag_msg); - ceph_con_out_kvec_add(con, sizeof (m->hdr), &m->hdr); - ceph_con_out_kvec_add(con, m->front.iov_len, m->front.iov_base); + con_out_kvec_add(con, sizeof (tag_msg), &tag_msg); + con_out_kvec_add(con, sizeof (m->hdr), &m->hdr); + con_out_kvec_add(con, m->front.iov_len, m->front.iov_base); if (m->middle) - ceph_con_out_kvec_add(con, m->middle->vec.iov_len, + con_out_kvec_add(con, m->middle->vec.iov_len, m->middle->vec.iov_base); /* fill in crc (except data pages), footer */ crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc)); con->out_msg->hdr.crc = cpu_to_le32(crc); - con->out_msg->footer.flags = CEPH_MSG_FOOTER_COMPLETE; + con->out_msg->footer.flags = 0; crc = crc32c(0, m->front.iov_base, m->front.iov_len); con->out_msg->footer.front_crc = cpu_to_le32(crc); @@ -597,28 +785,19 @@ static void prepare_write_message(struct ceph_connection *con) con->out_msg->footer.middle_crc = cpu_to_le32(crc); } else con->out_msg->footer.middle_crc = 0; - con->out_msg->footer.data_crc = 0; - dout("prepare_write_message front_crc %u data_crc %u\n", + dout("%s front_crc %u middle_crc %u\n", __func__, le32_to_cpu(con->out_msg->footer.front_crc), le32_to_cpu(con->out_msg->footer.middle_crc)); /* is there a data payload? */ - if (le32_to_cpu(m->hdr.data_len) > 0) { - /* initialize page iterator */ - con->out_msg_pos.page = 0; - if (m->pages) - con->out_msg_pos.page_pos = m->page_alignment; - else - con->out_msg_pos.page_pos = 0; - con->out_msg_pos.data_pos = 0; - con->out_msg_pos.did_page_crc = false; - con->out_more = 1; /* data + footer will follow */ - } else { + con->out_msg->footer.data_crc = 0; + if (m->hdr.data_len) + prepare_write_message_data(con); + else /* no, queue up footer too and be done */ prepare_write_message_footer(con); - } - set_bit(WRITE_PENDING, &con->state); + set_bit(CON_FLAG_WRITE_PENDING, &con->flags); } /* @@ -630,16 +809,16 @@ static void prepare_write_ack(struct ceph_connection *con) con->in_seq_acked, con->in_seq); con->in_seq_acked = con->in_seq; - ceph_con_out_kvec_reset(con); + con_out_kvec_reset(con); - ceph_con_out_kvec_add(con, sizeof (tag_ack), &tag_ack); + con_out_kvec_add(con, sizeof (tag_ack), &tag_ack); con->out_temp_ack = cpu_to_le64(con->in_seq_acked); - ceph_con_out_kvec_add(con, sizeof (con->out_temp_ack), + con_out_kvec_add(con, sizeof (con->out_temp_ack), &con->out_temp_ack); con->out_more = 1; /* more will follow.. eventually.. */ - set_bit(WRITE_PENDING, &con->state); + set_bit(CON_FLAG_WRITE_PENDING, &con->flags); } /* @@ -648,9 +827,9 @@ static void prepare_write_ack(struct ceph_connection *con) static void prepare_write_keepalive(struct ceph_connection *con) { dout("prepare_write_keepalive %p\n", con); - ceph_con_out_kvec_reset(con); - ceph_con_out_kvec_add(con, sizeof (tag_keepalive), &tag_keepalive); - set_bit(WRITE_PENDING, &con->state); + con_out_kvec_reset(con); + con_out_kvec_add(con, sizeof (tag_keepalive), &tag_keepalive); + set_bit(CON_FLAG_WRITE_PENDING, &con->flags); } /* @@ -665,27 +844,21 @@ static struct ceph_auth_handshake *get_connect_authorizer(struct ceph_connection if (!con->ops->get_authorizer) { con->out_connect.authorizer_protocol = CEPH_AUTH_UNKNOWN; con->out_connect.authorizer_len = 0; - return NULL; } /* Can't hold the mutex while getting authorizer */ - mutex_unlock(&con->mutex); - auth = con->ops->get_authorizer(con, auth_proto, con->auth_retry); - mutex_lock(&con->mutex); if (IS_ERR(auth)) return auth; - if (test_bit(CLOSED, &con->state) || test_bit(OPENING, &con->state)) + if (con->state != CON_STATE_NEGOTIATING) return ERR_PTR(-EAGAIN); con->auth_reply_buf = auth->authorizer_reply_buf; con->auth_reply_buf_len = auth->authorizer_reply_buf_len; - - return auth; } @@ -694,12 +867,12 @@ static struct ceph_auth_handshake *get_connect_authorizer(struct ceph_connection */ static void prepare_write_banner(struct ceph_connection *con) { - ceph_con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER); - ceph_con_out_kvec_add(con, sizeof (con->msgr->my_enc_addr), + con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER); + con_out_kvec_add(con, sizeof (con->msgr->my_enc_addr), &con->msgr->my_enc_addr); con->out_more = 0; - set_bit(WRITE_PENDING, &con->state); + set_bit(CON_FLAG_WRITE_PENDING, &con->flags); } static int prepare_write_connect(struct ceph_connection *con) @@ -742,14 +915,14 @@ static int prepare_write_connect(struct ceph_connection *con) con->out_connect.authorizer_len = auth ? cpu_to_le32(auth->authorizer_buf_len) : 0; - ceph_con_out_kvec_add(con, sizeof (con->out_connect), + con_out_kvec_add(con, sizeof (con->out_connect), &con->out_connect); if (auth && auth->authorizer_buf_len) - ceph_con_out_kvec_add(con, auth->authorizer_buf_len, + con_out_kvec_add(con, auth->authorizer_buf_len, auth->authorizer_buf); con->out_more = 0; - set_bit(WRITE_PENDING, &con->state); + set_bit(CON_FLAG_WRITE_PENDING, &con->flags); return 0; } @@ -797,30 +970,34 @@ out: return ret; /* done! */ } -#ifdef CONFIG_BLOCK -static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg) +static void out_msg_pos_next(struct ceph_connection *con, struct page *page, + size_t len, size_t sent, bool in_trail) { - if (!bio) { - *iter = NULL; - *seg = 0; - return; - } - *iter = bio; - *seg = bio->bi_idx; -} + struct ceph_msg *msg = con->out_msg; -static void iter_bio_next(struct bio **bio_iter, int *seg) -{ - if (*bio_iter == NULL) - return; + BUG_ON(!msg); + BUG_ON(!sent); - BUG_ON(*seg >= (*bio_iter)->bi_vcnt); + con->out_msg_pos.data_pos += sent; + con->out_msg_pos.page_pos += sent; + if (sent < len) + return; - (*seg)++; - if (*seg == (*bio_iter)->bi_vcnt) - init_bio_iter((*bio_iter)->bi_next, bio_iter, seg); -} + BUG_ON(sent != len); + con->out_msg_pos.page_pos = 0; + con->out_msg_pos.page++; + con->out_msg_pos.did_page_crc = false; + if (in_trail) + list_move_tail(&page->lru, + &msg->trail->head); + else if (msg->pagelist) + list_move_tail(&page->lru, + &msg->pagelist->head); +#ifdef CONFIG_BLOCK + else if (msg->bio) + iter_bio_next(&msg->bio_iter, &msg->bio_seg); #endif +} /* * Write as much message data payload as we can. If we finish, queue @@ -837,41 +1014,36 @@ static int write_partial_msg_pages(struct ceph_connection *con) bool do_datacrc = !con->msgr->nocrc; int ret; int total_max_write; - int in_trail = 0; - size_t trail_len = (msg->trail ? msg->trail->length : 0); + bool in_trail = false; + const size_t trail_len = (msg->trail ? msg->trail->length : 0); + const size_t trail_off = data_len - trail_len; dout("write_partial_msg_pages %p msg %p page %d/%d offset %d\n", - con, con->out_msg, con->out_msg_pos.page, con->out_msg->nr_pages, + con, msg, con->out_msg_pos.page, msg->nr_pages, con->out_msg_pos.page_pos); -#ifdef CONFIG_BLOCK - if (msg->bio && !msg->bio_iter) - init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg); -#endif - + /* + * Iterate through each page that contains data to be + * written, and send as much as possible for each. + * + * If we are calculating the data crc (the default), we will + * need to map the page. If we have no pages, they have + * been revoked, so use the zero page. + */ while (data_len > con->out_msg_pos.data_pos) { struct page *page = NULL; int max_write = PAGE_SIZE; int bio_offset = 0; - total_max_write = data_len - trail_len - - con->out_msg_pos.data_pos; - - /* - * if we are calculating the data crc (the default), we need - * to map the page. if our pages[] has been revoked, use the - * zero page. - */ - - /* have we reached the trail part of the data? */ - if (con->out_msg_pos.data_pos >= data_len - trail_len) { - in_trail = 1; + in_trail = in_trail || con->out_msg_pos.data_pos >= trail_off; + if (!in_trail) + total_max_write = trail_off - con->out_msg_pos.data_pos; + if (in_trail) { total_max_write = data_len - con->out_msg_pos.data_pos; page = list_first_entry(&msg->trail->head, struct page, lru); - max_write = PAGE_SIZE; } else if (msg->pages) { page = msg->pages[con->out_msg_pos.page]; } else if (msg->pagelist) { @@ -894,15 +1066,14 @@ static int write_partial_msg_pages(struct ceph_connection *con) if (do_datacrc && !con->out_msg_pos.did_page_crc) { void *base; - u32 crc; - u32 tmpcrc = le32_to_cpu(con->out_msg->footer.data_crc); + u32 crc = le32_to_cpu(msg->footer.data_crc); char *kaddr; kaddr = kmap(page); BUG_ON(kaddr == NULL); base = kaddr + con->out_msg_pos.page_pos + bio_offset; - crc = crc32c(tmpcrc, base, len); - con->out_msg->footer.data_crc = cpu_to_le32(crc); + crc = crc32c(crc, base, len); + msg->footer.data_crc = cpu_to_le32(crc); con->out_msg_pos.did_page_crc = true; } ret = ceph_tcp_sendpage(con->sock, page, @@ -915,31 +1086,15 @@ static int write_partial_msg_pages(struct ceph_connection *con) if (ret <= 0) goto out; - con->out_msg_pos.data_pos += ret; - con->out_msg_pos.page_pos += ret; - if (ret == len) { - con->out_msg_pos.page_pos = 0; - con->out_msg_pos.page++; - con->out_msg_pos.did_page_crc = false; - if (in_trail) - list_move_tail(&page->lru, - &msg->trail->head); - else if (msg->pagelist) - list_move_tail(&page->lru, - &msg->pagelist->head); -#ifdef CONFIG_BLOCK - else if (msg->bio) - iter_bio_next(&msg->bio_iter, &msg->bio_seg); -#endif - } + out_msg_pos_next(con, page, len, (size_t) ret, in_trail); } dout("write_partial_msg_pages %p msg %p done\n", con, msg); /* prepare and queue up footer, too */ if (!do_datacrc) - con->out_msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC; - ceph_con_out_kvec_reset(con); + msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC; + con_out_kvec_reset(con); prepare_write_message_footer(con); ret = 1; out: @@ -1351,20 +1506,14 @@ static int process_banner(struct ceph_connection *con) ceph_pr_addr(&con->msgr->inst.addr.in_addr)); } - set_bit(NEGOTIATING, &con->state); - prepare_read_connect(con); return 0; } static void fail_protocol(struct ceph_connection *con) { reset_connection(con); - set_bit(CLOSED, &con->state); /* in case there's queued work */ - - mutex_unlock(&con->mutex); - if (con->ops->bad_proto) - con->ops->bad_proto(con); - mutex_lock(&con->mutex); + BUG_ON(con->state != CON_STATE_NEGOTIATING); + con->state = CON_STATE_CLOSED; } static int process_connect(struct ceph_connection *con) @@ -1407,7 +1556,7 @@ static int process_connect(struct ceph_connection *con) return -1; } con->auth_retry = 1; - ceph_con_out_kvec_reset(con); + con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) return ret; @@ -1428,7 +1577,7 @@ static int process_connect(struct ceph_connection *con) ENTITY_NAME(con->peer_name), ceph_pr_addr(&con->peer_addr.in_addr)); reset_connection(con); - ceph_con_out_kvec_reset(con); + con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) return ret; @@ -1440,8 +1589,7 @@ static int process_connect(struct ceph_connection *con) if (con->ops->peer_reset) con->ops->peer_reset(con); mutex_lock(&con->mutex); - if (test_bit(CLOSED, &con->state) || - test_bit(OPENING, &con->state)) + if (con->state != CON_STATE_NEGOTIATING) return -EAGAIN; break; @@ -1454,7 +1602,7 @@ static int process_connect(struct ceph_connection *con) le32_to_cpu(con->out_connect.connect_seq), le32_to_cpu(con->in_reply.connect_seq)); con->connect_seq = le32_to_cpu(con->in_reply.connect_seq); - ceph_con_out_kvec_reset(con); + con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) return ret; @@ -1471,7 +1619,7 @@ static int process_connect(struct ceph_connection *con) le32_to_cpu(con->in_reply.global_seq)); get_global_seq(con->msgr, le32_to_cpu(con->in_reply.global_seq)); - ceph_con_out_kvec_reset(con); + con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) return ret; @@ -1489,7 +1637,10 @@ static int process_connect(struct ceph_connection *con) fail_protocol(con); return -1; } - clear_bit(CONNECTING, &con->state); + + BUG_ON(con->state != CON_STATE_NEGOTIATING); + con->state = CON_STATE_OPEN; + con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq); con->connect_seq++; con->peer_features = server_feat; @@ -1501,7 +1652,9 @@ static int process_connect(struct ceph_connection *con) le32_to_cpu(con->in_reply.connect_seq)); if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY) - set_bit(LOSSYTX, &con->state); + set_bit(CON_FLAG_LOSSYTX, &con->flags); + + con->delay = 0; /* reset backoff memory */ prepare_read_tag(con); break; @@ -1587,10 +1740,7 @@ static int read_partial_message_section(struct ceph_connection *con, return 1; } -static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con, - struct ceph_msg_header *hdr, - int *skip); - +static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip); static int read_partial_message_pages(struct ceph_connection *con, struct page **pages, @@ -1633,9 +1783,6 @@ static int read_partial_message_bio(struct ceph_connection *con, void *p; int ret, left; - if (IS_ERR(bv)) - return PTR_ERR(bv); - left = min((int)(data_len - con->in_msg_pos.data_pos), (int)(bv->bv_len - con->in_msg_pos.page_pos)); @@ -1672,7 +1819,6 @@ static int read_partial_message(struct ceph_connection *con) int ret; unsigned int front_len, middle_len, data_len; bool do_datacrc = !con->msgr->nocrc; - int skip; u64 seq; u32 crc; @@ -1723,10 +1869,13 @@ static int read_partial_message(struct ceph_connection *con) /* allocate message? */ if (!con->in_msg) { + int skip = 0; + dout("got hdr type %d front %d data %d\n", con->in_hdr.type, con->in_hdr.front_len, con->in_hdr.data_len); - skip = 0; - con->in_msg = ceph_alloc_msg(con, &con->in_hdr, &skip); + ret = ceph_con_in_msg_alloc(con, &skip); + if (ret < 0) + return ret; if (skip) { /* skip this message */ dout("alloc_msg said skip message\n"); @@ -1737,11 +1886,9 @@ static int read_partial_message(struct ceph_connection *con) con->in_seq++; return 0; } - if (!con->in_msg) { - con->error_msg = - "error allocating memory for incoming message"; - return -ENOMEM; - } + + BUG_ON(!con->in_msg); + BUG_ON(con->in_msg->con != con); m = con->in_msg; m->front.iov_len = 0; /* haven't read it yet */ if (m->middle) @@ -1753,6 +1900,11 @@ static int read_partial_message(struct ceph_connection *con) else con->in_msg_pos.page_pos = 0; con->in_msg_pos.data_pos = 0; + +#ifdef CONFIG_BLOCK + if (m->bio) + init_bio_iter(m->bio, &m->bio_iter, &m->bio_seg); +#endif } /* front */ @@ -1769,10 +1921,6 @@ static int read_partial_message(struct ceph_connection *con) if (ret <= 0) return ret; } -#ifdef CONFIG_BLOCK - if (m->bio && !m->bio_iter) - init_bio_iter(m->bio, &m->bio_iter, &m->bio_seg); -#endif /* (page) data */ while (con->in_msg_pos.data_pos < data_len) { @@ -1783,7 +1931,7 @@ static int read_partial_message(struct ceph_connection *con) return ret; #ifdef CONFIG_BLOCK } else if (m->bio) { - + BUG_ON(!m->bio_iter); ret = read_partial_message_bio(con, &m->bio_iter, &m->bio_seg, data_len, do_datacrc); @@ -1837,8 +1985,11 @@ static void process_message(struct ceph_connection *con) { struct ceph_msg *msg; + BUG_ON(con->in_msg->con != con); + con->in_msg->con = NULL; msg = con->in_msg; con->in_msg = NULL; + con->ops->put(con); /* if first message, set peer_name */ if (con->peer_name.type == 0) @@ -1858,7 +2009,6 @@ static void process_message(struct ceph_connection *con) con->ops->dispatch(con, msg); mutex_lock(&con->mutex); - prepare_read_tag(con); } @@ -1870,22 +2020,19 @@ static int try_write(struct ceph_connection *con) { int ret = 1; - dout("try_write start %p state %lu nref %d\n", con, con->state, - atomic_read(&con->nref)); + dout("try_write start %p state %lu\n", con, con->state); more: dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes); /* open the socket first? */ - if (con->sock == NULL) { - ceph_con_out_kvec_reset(con); + if (con->state == CON_STATE_PREOPEN) { + BUG_ON(con->sock); + con->state = CON_STATE_CONNECTING; + + con_out_kvec_reset(con); prepare_write_banner(con); - ret = prepare_write_connect(con); - if (ret < 0) - goto out; prepare_read_banner(con); - set_bit(CONNECTING, &con->state); - clear_bit(NEGOTIATING, &con->state); BUG_ON(con->in_msg); con->in_tag = CEPH_MSGR_TAG_READY; @@ -1932,7 +2079,7 @@ more_kvec: } do_next: - if (!test_bit(CONNECTING, &con->state)) { + if (con->state == CON_STATE_OPEN) { /* is anything else pending? */ if (!list_empty(&con->out_queue)) { prepare_write_message(con); @@ -1942,14 +2089,15 @@ do_next: prepare_write_ack(con); goto more; } - if (test_and_clear_bit(KEEPALIVE_PENDING, &con->state)) { + if (test_and_clear_bit(CON_FLAG_KEEPALIVE_PENDING, + &con->flags)) { prepare_write_keepalive(con); goto more; } } /* Nothing to do! */ - clear_bit(WRITE_PENDING, &con->state); + clear_bit(CON_FLAG_WRITE_PENDING, &con->flags); dout("try_write nothing else to write.\n"); ret = 0; out: @@ -1966,38 +2114,46 @@ static int try_read(struct ceph_connection *con) { int ret = -1; - if (!con->sock) - return 0; - - if (test_bit(STANDBY, &con->state)) +more: + dout("try_read start on %p state %lu\n", con, con->state); + if (con->state != CON_STATE_CONNECTING && + con->state != CON_STATE_NEGOTIATING && + con->state != CON_STATE_OPEN) return 0; - dout("try_read start on %p\n", con); + BUG_ON(!con->sock); -more: dout("try_read tag %d in_base_pos %d\n", (int)con->in_tag, con->in_base_pos); - /* - * process_connect and process_message drop and re-take - * con->mutex. make sure we handle a racing close or reopen. - */ - if (test_bit(CLOSED, &con->state) || - test_bit(OPENING, &con->state)) { - ret = -EAGAIN; + if (con->state == CON_STATE_CONNECTING) { + dout("try_read connecting\n"); + ret = read_partial_banner(con); + if (ret <= 0) + goto out; + ret = process_banner(con); + if (ret < 0) + goto out; + + BUG_ON(con->state != CON_STATE_CONNECTING); + con->state = CON_STATE_NEGOTIATING; + + /* + * Received banner is good, exchange connection info. + * Do not reset out_kvec, as sending our banner raced + * with receiving peer banner after connect completed. + */ + ret = prepare_write_connect(con); + if (ret < 0) + goto out; + prepare_read_connect(con); + + /* Send connection info before awaiting response */ goto out; } - if (test_bit(CONNECTING, &con->state)) { - if (!test_bit(NEGOTIATING, &con->state)) { - dout("try_read connecting\n"); - ret = read_partial_banner(con); - if (ret <= 0) - goto out; - ret = process_banner(con); - if (ret < 0) - goto out; - } + if (con->state == CON_STATE_NEGOTIATING) { + dout("try_read negotiating\n"); ret = read_partial_connect(con); if (ret <= 0) goto out; @@ -2007,6 +2163,8 @@ more: goto more; } + BUG_ON(con->state != CON_STATE_OPEN); + if (con->in_base_pos < 0) { /* * skipping + discarding content. @@ -2040,7 +2198,8 @@ more: prepare_read_ack(con); break; case CEPH_MSGR_TAG_CLOSE: - set_bit(CLOSED, &con->state); /* fixme */ + con_close_socket(con); + con->state = CON_STATE_CLOSED; goto out; default: goto bad_tag; @@ -2063,6 +2222,8 @@ more: if (con->in_tag == CEPH_MSGR_TAG_READY) goto more; process_message(con); + if (con->state == CON_STATE_OPEN) + prepare_read_tag(con); goto more; } if (con->in_tag == CEPH_MSGR_TAG_ACK) { @@ -2091,12 +2252,6 @@ bad_tag: */ static void queue_con(struct ceph_connection *con) { - if (test_bit(DEAD, &con->state)) { - dout("queue_con %p ignoring: DEAD\n", - con); - return; - } - if (!con->ops->get(con)) { dout("queue_con %p ref count 0\n", con); return; @@ -2121,7 +2276,26 @@ static void con_work(struct work_struct *work) mutex_lock(&con->mutex); restart: - if (test_and_clear_bit(BACKOFF, &con->state)) { + if (test_and_clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags)) { + switch (con->state) { + case CON_STATE_CONNECTING: + con->error_msg = "connection failed"; + break; + case CON_STATE_NEGOTIATING: + con->error_msg = "negotiation failed"; + break; + case CON_STATE_OPEN: + con->error_msg = "socket closed"; + break; + default: + dout("unrecognized con state %d\n", (int)con->state); + con->error_msg = "unrecognized con state"; + BUG(); + } + goto fault; + } + + if (test_and_clear_bit(CON_FLAG_BACKOFF, &con->flags)) { dout("con_work %p backing off\n", con); if (queue_delayed_work(ceph_msgr_wq, &con->work, round_jiffies_relative(con->delay))) { @@ -2135,35 +2309,35 @@ restart: } } - if (test_bit(STANDBY, &con->state)) { + if (con->state == CON_STATE_STANDBY) { dout("con_work %p STANDBY\n", con); goto done; } - if (test_bit(CLOSED, &con->state)) { /* e.g. if we are replaced */ - dout("con_work CLOSED\n"); - con_close_socket(con); + if (con->state == CON_STATE_CLOSED) { + dout("con_work %p CLOSED\n", con); + BUG_ON(con->sock); goto done; } - if (test_and_clear_bit(OPENING, &con->state)) { - /* reopen w/ new peer */ + if (con->state == CON_STATE_PREOPEN) { dout("con_work OPENING\n"); - con_close_socket(con); + BUG_ON(con->sock); } - if (test_and_clear_bit(SOCK_CLOSED, &con->state)) - goto fault; - ret = try_read(con); if (ret == -EAGAIN) goto restart; - if (ret < 0) + if (ret < 0) { + con->error_msg = "socket error on read"; goto fault; + } ret = try_write(con); if (ret == -EAGAIN) goto restart; - if (ret < 0) + if (ret < 0) { + con->error_msg = "socket error on write"; goto fault; + } done: mutex_unlock(&con->mutex); @@ -2172,7 +2346,6 @@ done_unlocked: return; fault: - mutex_unlock(&con->mutex); ceph_fault(con); /* error/fault path */ goto done_unlocked; } @@ -2183,26 +2356,31 @@ fault: * exponential backoff */ static void ceph_fault(struct ceph_connection *con) + __releases(con->mutex) { pr_err("%s%lld %s %s\n", ENTITY_NAME(con->peer_name), ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg); dout("fault %p state %lu to peer %s\n", con, con->state, ceph_pr_addr(&con->peer_addr.in_addr)); - if (test_bit(LOSSYTX, &con->state)) { - dout("fault on LOSSYTX channel\n"); - goto out; - } - - mutex_lock(&con->mutex); - if (test_bit(CLOSED, &con->state)) - goto out_unlock; + BUG_ON(con->state != CON_STATE_CONNECTING && + con->state != CON_STATE_NEGOTIATING && + con->state != CON_STATE_OPEN); con_close_socket(con); + if (test_bit(CON_FLAG_LOSSYTX, &con->flags)) { + dout("fault on LOSSYTX channel, marking CLOSED\n"); + con->state = CON_STATE_CLOSED; + goto out_unlock; + } + if (con->in_msg) { + BUG_ON(con->in_msg->con != con); + con->in_msg->con = NULL; ceph_msg_put(con->in_msg); con->in_msg = NULL; + con->ops->put(con); } /* Requeue anything that hasn't been acked */ @@ -2211,12 +2389,13 @@ static void ceph_fault(struct ceph_connection *con) /* If there are no messages queued or keepalive pending, place * the connection in a STANDBY state */ if (list_empty(&con->out_queue) && - !test_bit(KEEPALIVE_PENDING, &con->state)) { + !test_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags)) { dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con); - clear_bit(WRITE_PENDING, &con->state); - set_bit(STANDBY, &con->state); + clear_bit(CON_FLAG_WRITE_PENDING, &con->flags); + con->state = CON_STATE_STANDBY; } else { /* retry after a delay. */ + con->state = CON_STATE_PREOPEN; if (con->delay == 0) con->delay = BASE_DELAY_INTERVAL; else if (con->delay < MAX_DELAY_INTERVAL) @@ -2237,13 +2416,12 @@ static void ceph_fault(struct ceph_connection *con) * that when con_work restarts we schedule the * delay then. */ - set_bit(BACKOFF, &con->state); + set_bit(CON_FLAG_BACKOFF, &con->flags); } } out_unlock: mutex_unlock(&con->mutex); -out: /* * in case we faulted due to authentication, invalidate our * current tickets so that we can get new ones. @@ -2260,18 +2438,14 @@ out: /* - * create a new messenger instance + * initialize a new messenger instance */ -struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr, - u32 supported_features, - u32 required_features) +void ceph_messenger_init(struct ceph_messenger *msgr, + struct ceph_entity_addr *myaddr, + u32 supported_features, + u32 required_features, + bool nocrc) { - struct ceph_messenger *msgr; - - msgr = kzalloc(sizeof(*msgr), GFP_KERNEL); - if (msgr == NULL) - return ERR_PTR(-ENOMEM); - msgr->supported_features = supported_features; msgr->required_features = required_features; @@ -2284,30 +2458,23 @@ struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr, msgr->inst.addr.type = 0; get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce)); encode_my_addr(msgr); + msgr->nocrc = nocrc; - dout("messenger_create %p\n", msgr); - return msgr; -} -EXPORT_SYMBOL(ceph_messenger_create); + atomic_set(&msgr->stopping, 0); -void ceph_messenger_destroy(struct ceph_messenger *msgr) -{ - dout("destroy %p\n", msgr); - kfree(msgr); - dout("destroyed messenger %p\n", msgr); + dout("%s %p\n", __func__, msgr); } -EXPORT_SYMBOL(ceph_messenger_destroy); +EXPORT_SYMBOL(ceph_messenger_init); static void clear_standby(struct ceph_connection *con) { /* come back from STANDBY? */ - if (test_and_clear_bit(STANDBY, &con->state)) { - mutex_lock(&con->mutex); + if (con->state == CON_STATE_STANDBY) { dout("clear_standby %p and ++connect_seq\n", con); + con->state = CON_STATE_PREOPEN; con->connect_seq++; - WARN_ON(test_bit(WRITE_PENDING, &con->state)); - WARN_ON(test_bit(KEEPALIVE_PENDING, &con->state)); - mutex_unlock(&con->mutex); + WARN_ON(test_bit(CON_FLAG_WRITE_PENDING, &con->flags)); + WARN_ON(test_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags)); } } @@ -2316,21 +2483,24 @@ static void clear_standby(struct ceph_connection *con) */ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg) { - if (test_bit(CLOSED, &con->state)) { - dout("con_send %p closed, dropping %p\n", con, msg); - ceph_msg_put(msg); - return; - } - /* set src+dst */ msg->hdr.src = con->msgr->inst.name; - BUG_ON(msg->front.iov_len != le32_to_cpu(msg->hdr.front_len)); - msg->needs_out_seq = true; - /* queue */ mutex_lock(&con->mutex); + + if (con->state == CON_STATE_CLOSED) { + dout("con_send %p closed, dropping %p\n", con, msg); + ceph_msg_put(msg); + mutex_unlock(&con->mutex); + return; + } + + BUG_ON(msg->con != NULL); + msg->con = con->ops->get(con); + BUG_ON(msg->con == NULL); + BUG_ON(!list_empty(&msg->list_head)); list_add_tail(&msg->list_head, &con->out_queue); dout("----- %p to %s%lld %d=%s len %d+%d+%d -----\n", msg, @@ -2339,12 +2509,13 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg) le32_to_cpu(msg->hdr.front_len), le32_to_cpu(msg->hdr.middle_len), le32_to_cpu(msg->hdr.data_len)); + + clear_standby(con); mutex_unlock(&con->mutex); /* if there wasn't anything waiting to send before, queue * new work */ - clear_standby(con); - if (test_and_set_bit(WRITE_PENDING, &con->state) == 0) + if (test_and_set_bit(CON_FLAG_WRITE_PENDING, &con->flags) == 0) queue_con(con); } EXPORT_SYMBOL(ceph_con_send); @@ -2352,24 +2523,34 @@ EXPORT_SYMBOL(ceph_con_send); /* * Revoke a message that was previously queued for send */ -void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg) +void ceph_msg_revoke(struct ceph_msg *msg) { + struct ceph_connection *con = msg->con; + + if (!con) + return; /* Message not in our possession */ + mutex_lock(&con->mutex); if (!list_empty(&msg->list_head)) { - dout("con_revoke %p msg %p - was on queue\n", con, msg); + dout("%s %p msg %p - was on queue\n", __func__, con, msg); list_del_init(&msg->list_head); - ceph_msg_put(msg); + BUG_ON(msg->con == NULL); + msg->con->ops->put(msg->con); + msg->con = NULL; msg->hdr.seq = 0; + + ceph_msg_put(msg); } if (con->out_msg == msg) { - dout("con_revoke %p msg %p - was sending\n", con, msg); + dout("%s %p msg %p - was sending\n", __func__, con, msg); con->out_msg = NULL; if (con->out_kvec_is_msg) { con->out_skip = con->out_kvec_bytes; con->out_kvec_is_msg = false; } - ceph_msg_put(msg); msg->hdr.seq = 0; + + ceph_msg_put(msg); } mutex_unlock(&con->mutex); } @@ -2377,17 +2558,27 @@ void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg) /* * Revoke a message that we may be reading data into */ -void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg) +void ceph_msg_revoke_incoming(struct ceph_msg *msg) { + struct ceph_connection *con; + + BUG_ON(msg == NULL); + if (!msg->con) { + dout("%s msg %p null con\n", __func__, msg); + + return; /* Message not in our possession */ + } + + con = msg->con; mutex_lock(&con->mutex); - if (con->in_msg && con->in_msg == msg) { + if (con->in_msg == msg) { unsigned int front_len = le32_to_cpu(con->in_hdr.front_len); unsigned int middle_len = le32_to_cpu(con->in_hdr.middle_len); unsigned int data_len = le32_to_cpu(con->in_hdr.data_len); /* skip rest of message */ - dout("con_revoke_pages %p msg %p revoked\n", con, msg); - con->in_base_pos = con->in_base_pos - + dout("%s %p msg %p revoked\n", __func__, con, msg); + con->in_base_pos = con->in_base_pos - sizeof(struct ceph_msg_header) - front_len - middle_len - @@ -2398,8 +2589,8 @@ void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg) con->in_tag = CEPH_MSGR_TAG_READY; con->in_seq++; } else { - dout("con_revoke_pages %p msg %p pages %p no-op\n", - con, con->in_msg, msg); + dout("%s %p in_msg %p msg %p no-op\n", + __func__, con, con->in_msg, msg); } mutex_unlock(&con->mutex); } @@ -2410,9 +2601,11 @@ void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg) void ceph_con_keepalive(struct ceph_connection *con) { dout("con_keepalive %p\n", con); + mutex_lock(&con->mutex); clear_standby(con); - if (test_and_set_bit(KEEPALIVE_PENDING, &con->state) == 0 && - test_and_set_bit(WRITE_PENDING, &con->state) == 0) + mutex_unlock(&con->mutex); + if (test_and_set_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags) == 0 && + test_and_set_bit(CON_FLAG_WRITE_PENDING, &con->flags) == 0) queue_con(con); } EXPORT_SYMBOL(ceph_con_keepalive); @@ -2431,6 +2624,8 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, if (m == NULL) goto out; kref_init(&m->kref); + + m->con = NULL; INIT_LIST_HEAD(&m->list_head); m->hdr.tid = 0; @@ -2526,46 +2721,77 @@ static int ceph_alloc_middle(struct ceph_connection *con, struct ceph_msg *msg) } /* - * Generic message allocator, for incoming messages. + * Allocate a message for receiving an incoming message on a + * connection, and save the result in con->in_msg. Uses the + * connection's private alloc_msg op if available. + * + * Returns 0 on success, or a negative error code. + * + * On success, if we set *skip = 1: + * - the next message should be skipped and ignored. + * - con->in_msg == NULL + * or if we set *skip = 0: + * - con->in_msg is non-null. + * On error (ENOMEM, EAGAIN, ...), + * - con->in_msg == NULL */ -static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con, - struct ceph_msg_header *hdr, - int *skip) +static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip) { + struct ceph_msg_header *hdr = &con->in_hdr; int type = le16_to_cpu(hdr->type); int front_len = le32_to_cpu(hdr->front_len); int middle_len = le32_to_cpu(hdr->middle_len); - struct ceph_msg *msg = NULL; - int ret; + int ret = 0; + + BUG_ON(con->in_msg != NULL); if (con->ops->alloc_msg) { + struct ceph_msg *msg; + mutex_unlock(&con->mutex); msg = con->ops->alloc_msg(con, hdr, skip); mutex_lock(&con->mutex); - if (!msg || *skip) - return NULL; + if (con->state != CON_STATE_OPEN) { + ceph_msg_put(msg); + return -EAGAIN; + } + con->in_msg = msg; + if (con->in_msg) { + con->in_msg->con = con->ops->get(con); + BUG_ON(con->in_msg->con == NULL); + } + if (*skip) { + con->in_msg = NULL; + return 0; + } + if (!con->in_msg) { + con->error_msg = + "error allocating memory for incoming message"; + return -ENOMEM; + } } - if (!msg) { - *skip = 0; - msg = ceph_msg_new(type, front_len, GFP_NOFS, false); - if (!msg) { + if (!con->in_msg) { + con->in_msg = ceph_msg_new(type, front_len, GFP_NOFS, false); + if (!con->in_msg) { pr_err("unable to allocate msg type %d len %d\n", type, front_len); - return NULL; + return -ENOMEM; } - msg->page_alignment = le16_to_cpu(hdr->data_off); + con->in_msg->con = con->ops->get(con); + BUG_ON(con->in_msg->con == NULL); + con->in_msg->page_alignment = le16_to_cpu(hdr->data_off); } - memcpy(&msg->hdr, &con->in_hdr, sizeof(con->in_hdr)); + memcpy(&con->in_msg->hdr, &con->in_hdr, sizeof(con->in_hdr)); - if (middle_len && !msg->middle) { - ret = ceph_alloc_middle(con, msg); + if (middle_len && !con->in_msg->middle) { + ret = ceph_alloc_middle(con, con->in_msg); if (ret < 0) { - ceph_msg_put(msg); - return NULL; + ceph_msg_put(con->in_msg); + con->in_msg = NULL; } } - return msg; + return ret; } diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index d0649a9655b..900ea0f043f 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -106,9 +106,9 @@ static void __send_prepared_auth_request(struct ceph_mon_client *monc, int len) monc->pending_auth = 1; monc->m_auth->front.iov_len = len; monc->m_auth->hdr.front_len = cpu_to_le32(len); - ceph_con_revoke(monc->con, monc->m_auth); + ceph_msg_revoke(monc->m_auth); ceph_msg_get(monc->m_auth); /* keep our ref */ - ceph_con_send(monc->con, monc->m_auth); + ceph_con_send(&monc->con, monc->m_auth); } /* @@ -117,8 +117,11 @@ static void __send_prepared_auth_request(struct ceph_mon_client *monc, int len) static void __close_session(struct ceph_mon_client *monc) { dout("__close_session closing mon%d\n", monc->cur_mon); - ceph_con_revoke(monc->con, monc->m_auth); - ceph_con_close(monc->con); + ceph_msg_revoke(monc->m_auth); + ceph_msg_revoke_incoming(monc->m_auth_reply); + ceph_msg_revoke(monc->m_subscribe); + ceph_msg_revoke_incoming(monc->m_subscribe_ack); + ceph_con_close(&monc->con); monc->cur_mon = -1; monc->pending_auth = 0; ceph_auth_reset(monc->auth); @@ -142,9 +145,8 @@ static int __open_session(struct ceph_mon_client *monc) monc->want_next_osdmap = !!monc->want_next_osdmap; dout("open_session mon%d opening\n", monc->cur_mon); - monc->con->peer_name.type = CEPH_ENTITY_TYPE_MON; - monc->con->peer_name.num = cpu_to_le64(monc->cur_mon); - ceph_con_open(monc->con, + ceph_con_open(&monc->con, + CEPH_ENTITY_TYPE_MON, monc->cur_mon, &monc->monmap->mon_inst[monc->cur_mon].addr); /* initiatiate authentication handshake */ @@ -226,8 +228,8 @@ static void __send_subscribe(struct ceph_mon_client *monc) msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); - ceph_con_revoke(monc->con, msg); - ceph_con_send(monc->con, ceph_msg_get(msg)); + ceph_msg_revoke(msg); + ceph_con_send(&monc->con, ceph_msg_get(msg)); monc->sub_sent = jiffies | 1; /* never 0 */ } @@ -247,7 +249,7 @@ static void handle_subscribe_ack(struct ceph_mon_client *monc, if (monc->hunting) { pr_info("mon%d %s session established\n", monc->cur_mon, - ceph_pr_addr(&monc->con->peer_addr.in_addr)); + ceph_pr_addr(&monc->con.peer_addr.in_addr)); monc->hunting = false; } dout("handle_subscribe_ack after %d seconds\n", seconds); @@ -309,6 +311,17 @@ int ceph_monc_open_session(struct ceph_mon_client *monc) EXPORT_SYMBOL(ceph_monc_open_session); /* + * We require the fsid and global_id in order to initialize our + * debugfs dir. + */ +static bool have_debugfs_info(struct ceph_mon_client *monc) +{ + dout("have_debugfs_info fsid %d globalid %lld\n", + (int)monc->client->have_fsid, monc->auth->global_id); + return monc->client->have_fsid && monc->auth->global_id > 0; +} + +/* * The monitor responds with mount ack indicate mount success. The * included client ticket allows the client to talk to MDSs and OSDs. */ @@ -318,9 +331,12 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc, struct ceph_client *client = monc->client; struct ceph_monmap *monmap = NULL, *old = monc->monmap; void *p, *end; + int had_debugfs_info, init_debugfs = 0; mutex_lock(&monc->mutex); + had_debugfs_info = have_debugfs_info(monc); + dout("handle_monmap\n"); p = msg->front.iov_base; end = p + msg->front.iov_len; @@ -342,12 +358,22 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc, if (!client->have_fsid) { client->have_fsid = true; + if (!had_debugfs_info && have_debugfs_info(monc)) { + pr_info("client%lld fsid %pU\n", + ceph_client_id(monc->client), + &monc->client->fsid); + init_debugfs = 1; + } mutex_unlock(&monc->mutex); - /* - * do debugfs initialization without mutex to avoid - * creating a locking dependency - */ - ceph_debugfs_client_init(client); + + if (init_debugfs) { + /* + * do debugfs initialization without mutex to avoid + * creating a locking dependency + */ + ceph_debugfs_client_init(monc->client); + } + goto out_unlocked; } out: @@ -439,6 +465,7 @@ static struct ceph_msg *get_generic_reply(struct ceph_connection *con, m = NULL; } else { dout("get_generic_reply %lld got %p\n", tid, req->reply); + *skip = 0; m = ceph_msg_get(req->reply); /* * we don't need to track the connection reading into @@ -461,7 +488,7 @@ static int do_generic_request(struct ceph_mon_client *monc, req->request->hdr.tid = cpu_to_le64(req->tid); __insert_generic_request(monc, req); monc->num_generic_requests++; - ceph_con_send(monc->con, ceph_msg_get(req->request)); + ceph_con_send(&monc->con, ceph_msg_get(req->request)); mutex_unlock(&monc->mutex); err = wait_for_completion_interruptible(&req->completion); @@ -684,8 +711,9 @@ static void __resend_generic_request(struct ceph_mon_client *monc) for (p = rb_first(&monc->generic_request_tree); p; p = rb_next(p)) { req = rb_entry(p, struct ceph_mon_generic_request, node); - ceph_con_revoke(monc->con, req->request); - ceph_con_send(monc->con, ceph_msg_get(req->request)); + ceph_msg_revoke(req->request); + ceph_msg_revoke_incoming(req->reply); + ceph_con_send(&monc->con, ceph_msg_get(req->request)); } } @@ -705,7 +733,7 @@ static void delayed_work(struct work_struct *work) __close_session(monc); __open_session(monc); /* continue hunting */ } else { - ceph_con_keepalive(monc->con); + ceph_con_keepalive(&monc->con); __validate_auth(monc); @@ -760,19 +788,12 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl) goto out; /* connection */ - monc->con = kmalloc(sizeof(*monc->con), GFP_KERNEL); - if (!monc->con) - goto out_monmap; - ceph_con_init(monc->client->msgr, monc->con); - monc->con->private = monc; - monc->con->ops = &mon_con_ops; - /* authentication */ monc->auth = ceph_auth_init(cl->options->name, cl->options->key); if (IS_ERR(monc->auth)) { err = PTR_ERR(monc->auth); - goto out_con; + goto out_monmap; } monc->auth->want_keys = CEPH_ENTITY_TYPE_AUTH | CEPH_ENTITY_TYPE_MON | @@ -801,6 +822,9 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl) if (!monc->m_auth) goto out_auth_reply; + ceph_con_init(&monc->con, monc, &mon_con_ops, + &monc->client->msgr); + monc->cur_mon = -1; monc->hunting = true; monc->sub_renew_after = jiffies; @@ -824,8 +848,6 @@ out_subscribe_ack: ceph_msg_put(monc->m_subscribe_ack); out_auth: ceph_auth_destroy(monc->auth); -out_con: - monc->con->ops->put(monc->con); out_monmap: kfree(monc->monmap); out: @@ -841,10 +863,6 @@ void ceph_monc_stop(struct ceph_mon_client *monc) mutex_lock(&monc->mutex); __close_session(monc); - monc->con->private = NULL; - monc->con->ops->put(monc->con); - monc->con = NULL; - mutex_unlock(&monc->mutex); /* @@ -871,8 +889,10 @@ static void handle_auth_reply(struct ceph_mon_client *monc, { int ret; int was_auth = 0; + int had_debugfs_info, init_debugfs = 0; mutex_lock(&monc->mutex); + had_debugfs_info = have_debugfs_info(monc); if (monc->auth->ops) was_auth = monc->auth->ops->is_authenticated(monc->auth); monc->pending_auth = 0; @@ -888,14 +908,29 @@ static void handle_auth_reply(struct ceph_mon_client *monc, } else if (!was_auth && monc->auth->ops->is_authenticated(monc->auth)) { dout("authenticated, starting session\n"); - monc->client->msgr->inst.name.type = CEPH_ENTITY_TYPE_CLIENT; - monc->client->msgr->inst.name.num = + monc->client->msgr.inst.name.type = CEPH_ENTITY_TYPE_CLIENT; + monc->client->msgr.inst.name.num = cpu_to_le64(monc->auth->global_id); __send_subscribe(monc); __resend_generic_request(monc); } + + if (!had_debugfs_info && have_debugfs_info(monc)) { + pr_info("client%lld fsid %pU\n", + ceph_client_id(monc->client), + &monc->client->fsid); + init_debugfs = 1; + } mutex_unlock(&monc->mutex); + + if (init_debugfs) { + /* + * do debugfs initialization without mutex to avoid + * creating a locking dependency + */ + ceph_debugfs_client_init(monc->client); + } } static int __validate_auth(struct ceph_mon_client *monc) @@ -1000,6 +1035,8 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con, case CEPH_MSG_MDS_MAP: case CEPH_MSG_OSD_MAP: m = ceph_msg_new(type, front_len, GFP_NOFS, false); + if (!m) + return NULL; /* ENOMEM--return skip == 0 */ break; } @@ -1029,7 +1066,7 @@ static void mon_fault(struct ceph_connection *con) if (!monc->hunting) pr_info("mon%d %s session lost, " "hunting for new mon\n", monc->cur_mon, - ceph_pr_addr(&monc->con->peer_addr.in_addr)); + ceph_pr_addr(&monc->con.peer_addr.in_addr)); __close_session(monc); if (!monc->hunting) { @@ -1044,9 +1081,23 @@ out: mutex_unlock(&monc->mutex); } +/* + * We can ignore refcounting on the connection struct, as all references + * will come from the messenger workqueue, which is drained prior to + * mon_client destruction. + */ +static struct ceph_connection *con_get(struct ceph_connection *con) +{ + return con; +} + +static void con_put(struct ceph_connection *con) +{ +} + static const struct ceph_connection_operations mon_con_ops = { - .get = ceph_con_get, - .put = ceph_con_put, + .get = con_get, + .put = con_put, .dispatch = dispatch, .fault = mon_fault, .alloc_msg = mon_alloc_msg, diff --git a/net/ceph/msgpool.c b/net/ceph/msgpool.c index 11d5f4196a7..ddec1c10ac8 100644 --- a/net/ceph/msgpool.c +++ b/net/ceph/msgpool.c @@ -12,7 +12,7 @@ static void *msgpool_alloc(gfp_t gfp_mask, void *arg) struct ceph_msgpool *pool = arg; struct ceph_msg *msg; - msg = ceph_msg_new(0, pool->front_len, gfp_mask, true); + msg = ceph_msg_new(pool->type, pool->front_len, gfp_mask, true); if (!msg) { dout("msgpool_alloc %s failed\n", pool->name); } else { @@ -32,10 +32,11 @@ static void msgpool_free(void *element, void *arg) ceph_msg_put(msg); } -int ceph_msgpool_init(struct ceph_msgpool *pool, +int ceph_msgpool_init(struct ceph_msgpool *pool, int type, int front_len, int size, bool blocking, const char *name) { dout("msgpool %s init\n", name); + pool->type = type; pool->front_len = front_len; pool->pool = mempool_create(size, msgpool_alloc, msgpool_free, pool); if (!pool->pool) @@ -61,7 +62,7 @@ struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, WARN_ON(1); /* try to alloc a fresh message */ - return ceph_msg_new(0, front_len, GFP_NOFS, false); + return ceph_msg_new(pool->type, front_len, GFP_NOFS, false); } msg = mempool_alloc(pool->pool, GFP_NOFS); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index ca59e66c978..42119c05e82 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -140,10 +140,9 @@ void ceph_osdc_release_request(struct kref *kref) if (req->r_request) ceph_msg_put(req->r_request); if (req->r_con_filling_msg) { - dout("release_request revoking pages %p from con %p\n", + dout("%s revoking pages %p from con %p\n", __func__, req->r_pages, req->r_con_filling_msg); - ceph_con_revoke_message(req->r_con_filling_msg, - req->r_reply); + ceph_msg_revoke_incoming(req->r_reply); req->r_con_filling_msg->ops->put(req->r_con_filling_msg); } if (req->r_reply) @@ -214,10 +213,13 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, kref_init(&req->r_kref); init_completion(&req->r_completion); init_completion(&req->r_safe_completion); + rb_init_node(&req->r_node); INIT_LIST_HEAD(&req->r_unsafe_item); INIT_LIST_HEAD(&req->r_linger_item); INIT_LIST_HEAD(&req->r_linger_osd); INIT_LIST_HEAD(&req->r_req_lru_item); + INIT_LIST_HEAD(&req->r_osd_item); + req->r_flags = flags; WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0); @@ -243,6 +245,7 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, } ceph_pagelist_init(req->r_trail); } + /* create request message; allow space for oid */ msg_size += MAX_OBJ_NAME_SIZE; if (snapc) @@ -256,7 +259,6 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, return NULL; } - msg->hdr.type = cpu_to_le16(CEPH_MSG_OSD_OP); memset(msg->front.iov_base, 0, msg->front.iov_len); req->r_request = msg; @@ -624,7 +626,7 @@ static void osd_reset(struct ceph_connection *con) /* * Track open sessions with osds. */ -static struct ceph_osd *create_osd(struct ceph_osd_client *osdc) +static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum) { struct ceph_osd *osd; @@ -634,15 +636,13 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc) atomic_set(&osd->o_ref, 1); osd->o_osdc = osdc; + osd->o_osd = onum; INIT_LIST_HEAD(&osd->o_requests); INIT_LIST_HEAD(&osd->o_linger_requests); INIT_LIST_HEAD(&osd->o_osd_lru); osd->o_incarnation = 1; - ceph_con_init(osdc->client->msgr, &osd->o_con); - osd->o_con.private = osd; - osd->o_con.ops = &osd_con_ops; - osd->o_con.peer_name.type = CEPH_ENTITY_TYPE_OSD; + ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr); INIT_LIST_HEAD(&osd->o_keepalive_item); return osd; @@ -688,7 +688,7 @@ static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) static void remove_all_osds(struct ceph_osd_client *osdc) { - dout("__remove_old_osds %p\n", osdc); + dout("%s %p\n", __func__, osdc); mutex_lock(&osdc->request_mutex); while (!RB_EMPTY_ROOT(&osdc->osds)) { struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds), @@ -752,7 +752,8 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) ret = -EAGAIN; } else { ceph_con_close(&osd->o_con); - ceph_con_open(&osd->o_con, &osdc->osdmap->osd_addr[osd->o_osd]); + ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd, + &osdc->osdmap->osd_addr[osd->o_osd]); osd->o_incarnation++; } return ret; @@ -853,7 +854,7 @@ static void __unregister_request(struct ceph_osd_client *osdc, if (req->r_osd) { /* make sure the original request isn't in flight. */ - ceph_con_revoke(&req->r_osd->o_con, req->r_request); + ceph_msg_revoke(req->r_request); list_del_init(&req->r_osd_item); if (list_empty(&req->r_osd->o_requests) && @@ -880,7 +881,7 @@ static void __unregister_request(struct ceph_osd_client *osdc, static void __cancel_request(struct ceph_osd_request *req) { if (req->r_sent && req->r_osd) { - ceph_con_revoke(&req->r_osd->o_con, req->r_request); + ceph_msg_revoke(req->r_request); req->r_sent = 0; } } @@ -890,7 +891,9 @@ static void __register_linger_request(struct ceph_osd_client *osdc, { dout("__register_linger_request %p\n", req); list_add_tail(&req->r_linger_item, &osdc->req_linger); - list_add_tail(&req->r_linger_osd, &req->r_osd->o_linger_requests); + if (req->r_osd) + list_add_tail(&req->r_linger_osd, + &req->r_osd->o_linger_requests); } static void __unregister_linger_request(struct ceph_osd_client *osdc, @@ -998,18 +1001,18 @@ static int __map_request(struct ceph_osd_client *osdc, req->r_osd = __lookup_osd(osdc, o); if (!req->r_osd && o >= 0) { err = -ENOMEM; - req->r_osd = create_osd(osdc); + req->r_osd = create_osd(osdc, o); if (!req->r_osd) { list_move(&req->r_req_lru_item, &osdc->req_notarget); goto out; } dout("map_request osd %p is osd%d\n", req->r_osd, o); - req->r_osd->o_osd = o; - req->r_osd->o_con.peer_name.num = cpu_to_le64(o); __insert_osd(osdc, req->r_osd); - ceph_con_open(&req->r_osd->o_con, &osdc->osdmap->osd_addr[o]); + ceph_con_open(&req->r_osd->o_con, + CEPH_ENTITY_TYPE_OSD, o, + &osdc->osdmap->osd_addr[o]); } if (req->r_osd) { @@ -1304,8 +1307,9 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) dout("kick_requests %s\n", force_resend ? " (force resend)" : ""); mutex_lock(&osdc->request_mutex); - for (p = rb_first(&osdc->requests); p; p = rb_next(p)) { + for (p = rb_first(&osdc->requests); p; ) { req = rb_entry(p, struct ceph_osd_request, r_node); + p = rb_next(p); err = __map_request(osdc, req, force_resend); if (err < 0) continue; /* error */ @@ -1313,10 +1317,23 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) dout("%p tid %llu maps to no osd\n", req, req->r_tid); needmap++; /* request a newer map */ } else if (err > 0) { - dout("%p tid %llu requeued on osd%d\n", req, req->r_tid, - req->r_osd ? req->r_osd->o_osd : -1); - if (!req->r_linger) + if (!req->r_linger) { + dout("%p tid %llu requeued on osd%d\n", req, + req->r_tid, + req->r_osd ? req->r_osd->o_osd : -1); req->r_flags |= CEPH_OSD_FLAG_RETRY; + } + } + if (req->r_linger && list_empty(&req->r_linger_item)) { + /* + * register as a linger so that we will + * re-submit below and get a new tid + */ + dout("%p tid %llu restart on osd%d\n", + req, req->r_tid, + req->r_osd ? req->r_osd->o_osd : -1); + __register_linger_request(osdc, req); + __unregister_request(osdc, req); } } @@ -1391,7 +1408,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) epoch, maplen); newmap = osdmap_apply_incremental(&p, next, osdc->osdmap, - osdc->client->msgr); + &osdc->client->msgr); if (IS_ERR(newmap)) { err = PTR_ERR(newmap); goto bad; @@ -1839,11 +1856,12 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) if (!osdc->req_mempool) goto out; - err = ceph_msgpool_init(&osdc->msgpool_op, OSD_OP_FRONT_LEN, 10, true, + err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP, + OSD_OP_FRONT_LEN, 10, true, "osd_op"); if (err < 0) goto out_mempool; - err = ceph_msgpool_init(&osdc->msgpool_op_reply, + err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY, OSD_OPREPLY_FRONT_LEN, 10, true, "osd_op_reply"); if (err < 0) @@ -2019,15 +2037,15 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, if (!req) { *skip = 1; m = NULL; - pr_info("get_reply unknown tid %llu from osd%d\n", tid, - osd->o_osd); + dout("get_reply unknown tid %llu from osd%d\n", tid, + osd->o_osd); goto out; } if (req->r_con_filling_msg) { - dout("get_reply revoking msg %p from old con %p\n", + dout("%s revoking msg %p from old con %p\n", __func__, req->r_reply, req->r_con_filling_msg); - ceph_con_revoke_message(req->r_con_filling_msg, req->r_reply); + ceph_msg_revoke_incoming(req->r_reply); req->r_con_filling_msg->ops->put(req->r_con_filling_msg); req->r_con_filling_msg = NULL; } @@ -2080,6 +2098,7 @@ static struct ceph_msg *alloc_msg(struct ceph_connection *con, int type = le16_to_cpu(hdr->type); int front = le32_to_cpu(hdr->front_len); + *skip = 0; switch (type) { case CEPH_MSG_OSD_MAP: case CEPH_MSG_WATCH_NOTIFY: diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 81e3b84a77e..3124b71a888 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -135,6 +135,21 @@ bad: return -EINVAL; } +static int skip_name_map(void **p, void *end) +{ + int len; + ceph_decode_32_safe(p, end, len ,bad); + while (len--) { + int strlen; + *p += sizeof(u32); + ceph_decode_32_safe(p, end, strlen, bad); + *p += strlen; +} + return 0; +bad: + return -EINVAL; +} + static struct crush_map *crush_decode(void *pbyval, void *end) { struct crush_map *c; @@ -143,6 +158,7 @@ static struct crush_map *crush_decode(void *pbyval, void *end) void **p = &pbyval; void *start = pbyval; u32 magic; + u32 num_name_maps; dout("crush_decode %p to %p len %d\n", *p, end, (int)(end - *p)); @@ -150,6 +166,11 @@ static struct crush_map *crush_decode(void *pbyval, void *end) if (c == NULL) return ERR_PTR(-ENOMEM); + /* set tunables to default values */ + c->choose_local_tries = 2; + c->choose_local_fallback_tries = 5; + c->choose_total_tries = 19; + ceph_decode_need(p, end, 4*sizeof(u32), bad); magic = ceph_decode_32(p); if (magic != CRUSH_MAGIC) { @@ -297,7 +318,25 @@ static struct crush_map *crush_decode(void *pbyval, void *end) } /* ignore trailing name maps. */ + for (num_name_maps = 0; num_name_maps < 3; num_name_maps++) { + err = skip_name_map(p, end); + if (err < 0) + goto done; + } + + /* tunables */ + ceph_decode_need(p, end, 3*sizeof(u32), done); + c->choose_local_tries = ceph_decode_32(p); + c->choose_local_fallback_tries = ceph_decode_32(p); + c->choose_total_tries = ceph_decode_32(p); + dout("crush decode tunable choose_local_tries = %d", + c->choose_local_tries); + dout("crush decode tunable choose_local_fallback_tries = %d", + c->choose_local_fallback_tries); + dout("crush decode tunable choose_total_tries = %d", + c->choose_total_tries); +done: dout("crush_decode success\n"); return c; @@ -488,15 +527,16 @@ static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map) ceph_decode_32_safe(p, end, pool, bad); ceph_decode_32_safe(p, end, len, bad); dout(" pool %d len %d\n", pool, len); + ceph_decode_need(p, end, len, bad); pi = __lookup_pg_pool(&map->pg_pools, pool); if (pi) { + char *name = kstrndup(*p, len, GFP_NOFS); + + if (!name) + return -ENOMEM; kfree(pi->name); - pi->name = kmalloc(len + 1, GFP_NOFS); - if (pi->name) { - memcpy(pi->name, *p, len); - pi->name[len] = '\0'; - dout(" name is %s\n", pi->name); - } + pi->name = name; + dout(" name is %s\n", pi->name); } *p += len; } @@ -666,6 +706,9 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) ceph_decode_need(p, end, sizeof(u32) + sizeof(u64), bad); ceph_decode_copy(p, &pgid, sizeof(pgid)); n = ceph_decode_32(p); + err = -EINVAL; + if (n > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) + goto bad; ceph_decode_need(p, end, n * sizeof(u32), bad); err = -ENOMEM; pg = kmalloc(sizeof(*pg) + n*sizeof(u32), GFP_NOFS); @@ -889,6 +932,10 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, (void) __remove_pg_mapping(&map->pg_temp, pgid); /* insert */ + if (pglen > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) { + err = -EINVAL; + goto bad; + } pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS); if (!pg) { err = -ENOMEM; diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c index 13cb409a7bb..665cd23020f 100644 --- a/net/ceph/pagelist.c +++ b/net/ceph/pagelist.c @@ -72,8 +72,7 @@ int ceph_pagelist_append(struct ceph_pagelist *pl, const void *buf, size_t len) } EXPORT_SYMBOL(ceph_pagelist_append); -/** - * Allocate enough pages for a pagelist to append the given amount +/* Allocate enough pages for a pagelist to append the given amount * of data without without allocating. * Returns: 0 on success, -ENOMEM on error. */ @@ -95,9 +94,7 @@ int ceph_pagelist_reserve(struct ceph_pagelist *pl, size_t space) } EXPORT_SYMBOL(ceph_pagelist_reserve); -/** - * Free any pages that have been preallocated. - */ +/* Free any pages that have been preallocated. */ int ceph_pagelist_free_reserve(struct ceph_pagelist *pl) { while (!list_empty(&pl->free_list)) { @@ -112,9 +109,7 @@ int ceph_pagelist_free_reserve(struct ceph_pagelist *pl) } EXPORT_SYMBOL(ceph_pagelist_free_reserve); -/** - * Create a truncation point. - */ +/* Create a truncation point. */ void ceph_pagelist_set_cursor(struct ceph_pagelist *pl, struct ceph_pagelist_cursor *c) { @@ -124,8 +119,7 @@ void ceph_pagelist_set_cursor(struct ceph_pagelist *pl, } EXPORT_SYMBOL(ceph_pagelist_set_cursor); -/** - * Truncate a pagelist to the given point. Move extra pages to reserve. +/* Truncate a pagelist to the given point. Move extra pages to reserve. * This won't sleep. * Returns: 0 on success, * -EINVAL if the pagelist doesn't match the trunc point pagelist diff --git a/net/compat.c b/net/compat.c index 1b96281892d..74ed1d7a84a 100644 --- a/net/compat.c +++ b/net/compat.c @@ -221,6 +221,8 @@ int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *dat { struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control; struct compat_cmsghdr cmhdr; + struct compat_timeval ctv; + struct compat_timespec cts[3]; int cmlen; if (cm == NULL || kmsg->msg_controllen < sizeof(*cm)) { @@ -229,8 +231,6 @@ int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *dat } if (!COMPAT_USE_64BIT_TIME) { - struct compat_timeval ctv; - struct compat_timespec cts[3]; if (level == SOL_SOCKET && type == SCM_TIMESTAMP) { struct timeval *tv = (struct timeval *)data; ctv.tv_sec = tv->tv_sec; diff --git a/net/core/datagram.c b/net/core/datagram.c index ae6acf6a3de..0337e2b7686 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -248,7 +248,6 @@ void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb) unlock_sock_fast(sk, slow); /* skb is now orphaned, can be freed outside of locked section */ - trace_kfree_skb(skb, skb_free_datagram_locked); __kfree_skb(skb); } EXPORT_SYMBOL(skb_free_datagram_locked); diff --git a/net/core/dev.c b/net/core/dev.c index 1cb0d8a6aa6..83988362805 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1055,6 +1055,8 @@ rollback: */ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) { + char *new_ifalias; + ASSERT_RTNL(); if (len >= IFALIASZ) @@ -1068,9 +1070,10 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) return 0; } - dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); - if (!dev->ifalias) + new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); + if (!new_ifalias) return -ENOMEM; + dev->ifalias = new_ifalias; strlcpy(dev->ifalias, alias, len+1); return len; @@ -1172,6 +1175,7 @@ static int __dev_open(struct net_device *dev) net_dmaengine_get(); dev_set_rx_mode(dev); dev_activate(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); } return ret; @@ -1632,10 +1636,25 @@ static inline int deliver_skb(struct sk_buff *skb, struct packet_type *pt_prev, struct net_device *orig_dev) { + if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + return -ENOMEM; atomic_inc(&skb->users); return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } +static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) +{ + if (ptype->af_packet_priv == NULL) + return false; + + if (ptype->id_match) + return ptype->id_match(ptype, skb->sk); + else if ((struct sock *)ptype->af_packet_priv == skb->sk) + return true; + + return false; +} + /* * Support routine. Sends outgoing frames to any network * taps currently in use. @@ -1653,8 +1672,7 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) * they originated from - MvS (miquels@drinkel.ow.org) */ if ((ptype->dev == dev || !ptype->dev) && - (ptype->af_packet_priv == NULL || - (struct sock *)ptype->af_packet_priv != skb->sk)) { + (!skb_loop_sk(ptype, skb))) { if (pt_prev) { deliver_skb(skb2, pt_prev, skb->dev); pt_prev = ptype; @@ -1691,7 +1709,8 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) rcu_read_unlock(); } -/* netif_setup_tc - Handle tc mappings on real_num_tx_queues change +/** + * netif_setup_tc - Handle tc mappings on real_num_tx_queues change * @dev: Network device * @txq: number of queues available * @@ -1793,6 +1812,18 @@ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) EXPORT_SYMBOL(netif_set_real_num_rx_queues); #endif +/** + * netif_get_num_default_rss_queues - default number of RSS queues + * + * This routine should set an upper limit on the number of RSS queues + * used by default by multiqueue devices. + */ +int netif_get_num_default_rss_queues(void) +{ + return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus()); +} +EXPORT_SYMBOL(netif_get_num_default_rss_queues); + static inline void __netif_reschedule(struct Qdisc *q) { struct softnet_data *sd; @@ -2118,6 +2149,9 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) __be16 protocol = skb->protocol; netdev_features_t features = skb->dev->features; + if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) + features &= ~NETIF_F_GSO_MASK; + if (protocol == htons(ETH_P_8021Q)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; @@ -2459,6 +2493,23 @@ static DEFINE_PER_CPU(int, xmit_recursion); #define RECURSION_LIMIT 10 /** + * dev_loopback_xmit - loop back @skb + * @skb: buffer to transmit + */ +int dev_loopback_xmit(struct sk_buff *skb) +{ + skb_reset_mac_header(skb); + __skb_pull(skb, skb_network_offset(skb)); + skb->pkt_type = PACKET_LOOPBACK; + skb->ip_summed = CHECKSUM_UNNECESSARY; + WARN_ON(!skb_dst(skb)); + skb_dst_force(skb); + netif_rx_ni(skb); + return 0; +} +EXPORT_SYMBOL(dev_loopback_xmit); + +/** * dev_queue_xmit - transmit a buffer * @skb: buffer to transmit * @@ -3123,6 +3174,23 @@ void netdev_rx_handler_unregister(struct net_device *dev) } EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); +/* + * Limit the use of PFMEMALLOC reserves to those protocols that implement + * the special handling of PFMEMALLOC skbs. + */ +static bool skb_pfmemalloc_protocol(struct sk_buff *skb) +{ + switch (skb->protocol) { + case __constant_htons(ETH_P_ARP): + case __constant_htons(ETH_P_IP): + case __constant_htons(ETH_P_IPV6): + case __constant_htons(ETH_P_8021Q): + return true; + default: + return false; + } +} + static int __netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; @@ -3132,17 +3200,28 @@ static int __netif_receive_skb(struct sk_buff *skb) bool deliver_exact = false; int ret = NET_RX_DROP; __be16 type; + unsigned long pflags = current->flags; net_timestamp_check(!netdev_tstamp_prequeue, skb); trace_netif_receive_skb(skb); + /* + * PFMEMALLOC skbs are special, they should + * - be delivered to SOCK_MEMALLOC sockets only + * - stay away from userspace + * - have bounded memory usage + * + * Use PF_MEMALLOC as this saves us from propagating the allocation + * context down to all allocation sites. + */ + if (sk_memalloc_socks() && skb_pfmemalloc(skb)) + current->flags |= PF_MEMALLOC; + /* if we've gotten here through NAPI, check netpoll */ if (netpoll_receive_skb(skb)) - return NET_RX_DROP; + goto out; - if (!skb->skb_iif) - skb->skb_iif = skb->dev->ifindex; orig_dev = skb->dev; skb_reset_network_header(skb); @@ -3154,13 +3233,14 @@ static int __netif_receive_skb(struct sk_buff *skb) rcu_read_lock(); another_round: + skb->skb_iif = skb->dev->ifindex; __this_cpu_inc(softnet_data.processed); if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { skb = vlan_untag(skb); if (unlikely(!skb)) - goto out; + goto unlock; } #ifdef CONFIG_NET_CLS_ACT @@ -3170,6 +3250,9 @@ another_round: } #endif + if (sk_memalloc_socks() && skb_pfmemalloc(skb)) + goto skip_taps; + list_for_each_entry_rcu(ptype, &ptype_all, list) { if (!ptype->dev || ptype->dev == skb->dev) { if (pt_prev) @@ -3178,13 +3261,18 @@ another_round: } } +skip_taps: #ifdef CONFIG_NET_CLS_ACT skb = handle_ing(skb, &pt_prev, &ret, orig_dev); if (!skb) - goto out; + goto unlock; ncls: #endif + if (sk_memalloc_socks() && skb_pfmemalloc(skb) + && !skb_pfmemalloc_protocol(skb)) + goto drop; + rx_handler = rcu_dereference(skb->dev->rx_handler); if (vlan_tx_tag_present(skb)) { if (pt_prev) { @@ -3194,7 +3282,7 @@ ncls: if (vlan_do_receive(&skb, !rx_handler)) goto another_round; else if (unlikely(!skb)) - goto out; + goto unlock; } if (rx_handler) { @@ -3204,7 +3292,7 @@ ncls: } switch (rx_handler(&skb)) { case RX_HANDLER_CONSUMED: - goto out; + goto unlock; case RX_HANDLER_ANOTHER: goto another_round; case RX_HANDLER_EXACT: @@ -3232,8 +3320,12 @@ ncls: } if (pt_prev) { - ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); + if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + ret = -ENOMEM; + else + ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } else { +drop: atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); /* Jamal, now you will not able to escape explaining @@ -3242,8 +3334,10 @@ ncls: ret = NET_RX_DROP; } -out: +unlock: rcu_read_unlock(); +out: + tsk_restore_flags(current, pflags, PF_MEMALLOC); return ret; } @@ -4767,6 +4861,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) err = ops->ndo_set_mac_address(dev, sa); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + add_device_randomness(dev->dev_addr, dev->addr_len); return err; } EXPORT_SYMBOL(dev_set_mac_address); @@ -5545,6 +5640,7 @@ int register_netdevice(struct net_device *dev) dev_init_scheduler(dev); dev_hold(dev); list_netdevice(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); /* Notify protocols, that a new device appeared. */ ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); @@ -5646,8 +5742,9 @@ int netdev_refcnt_read(const struct net_device *dev) } EXPORT_SYMBOL(netdev_refcnt_read); -/* +/** * netdev_wait_allrefs - wait until all references are gone. + * @dev: target net_device * * This is called when unregistering network devices. * @@ -5908,6 +6005,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); dev->gso_max_size = GSO_MAX_SIZE; + dev->gso_max_segs = GSO_MAX_SEGS; INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); diff --git a/net/core/dst.c b/net/core/dst.c index 43d94cedbf7..56d63612e1e 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -94,7 +94,7 @@ loop: * But we do not have state "obsoleted, but * referenced by parent", so it is right. */ - if (dst->obsolete > 1) + if (dst->obsolete > 0) continue; ___dst_free(dst); @@ -149,10 +149,18 @@ int dst_discard(struct sk_buff *skb) } EXPORT_SYMBOL(dst_discard); -const u32 dst_default_metrics[RTAX_MAX]; +const u32 dst_default_metrics[RTAX_MAX + 1] = { + /* This initializer is needed to force linker to place this variable + * into const section. Otherwise it might end into bss section. + * We really want to avoid false sharing on this variable, and catch + * any writes on it. + */ + [RTAX_MAX] = 0xdeadbeef, +}; + void *dst_alloc(struct dst_ops *ops, struct net_device *dev, - int initial_ref, int initial_obsolete, int flags) + int initial_ref, int initial_obsolete, unsigned short flags) { struct dst_entry *dst; @@ -171,7 +179,6 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, dst_init_metrics(dst, dst_default_metrics, true); dst->expires = 0UL; dst->path = dst; - RCU_INIT_POINTER(dst->_neighbour, NULL); #ifdef CONFIG_XFRM dst->xfrm = NULL; #endif @@ -188,6 +195,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, dst->__use = 0; dst->lastuse = jiffies; dst->flags = flags; + dst->pending_confirm = 0; dst->next = NULL; if (!(flags & DST_NOCOUNT)) dst_entries_add(ops, 1); @@ -202,7 +210,7 @@ static void ___dst_free(struct dst_entry *dst) */ if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) dst->input = dst->output = dst_discard; - dst->obsolete = 2; + dst->obsolete = DST_OBSOLETE_DEAD; } void __dst_free(struct dst_entry *dst) @@ -224,19 +232,12 @@ EXPORT_SYMBOL(__dst_free); struct dst_entry *dst_destroy(struct dst_entry * dst) { struct dst_entry *child; - struct neighbour *neigh; smp_rmb(); again: - neigh = rcu_dereference_protected(dst->_neighbour, 1); child = dst->child; - if (neigh) { - RCU_INIT_POINTER(dst->_neighbour, NULL); - neigh_release(neigh); - } - if (!(dst->flags & DST_NOCOUNT)) dst_entries_add(dst->ops, -1); @@ -360,19 +361,9 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, if (!unregister) { dst->input = dst->output = dst_discard; } else { - struct neighbour *neigh; - dst->dev = dev_net(dst->dev)->loopback_dev; dev_hold(dst->dev); dev_put(dev); - rcu_read_lock(); - neigh = dst_get_neighbour_noref(dst); - if (neigh && neigh->dev == dev) { - neigh->dev = dst->dev; - dev_hold(dst->dev); - dev_put(dev); - } - rcu_read_unlock(); } } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 9c2afb48027..cbf033dcaf1 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -729,6 +729,40 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) return dev->ethtool_ops->set_wol(dev, &wol); } +static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_eee edata; + int rc; + + if (!dev->ethtool_ops->get_eee) + return -EOPNOTSUPP; + + memset(&edata, 0, sizeof(struct ethtool_eee)); + edata.cmd = ETHTOOL_GEEE; + rc = dev->ethtool_ops->get_eee(dev, &edata); + + if (rc) + return rc; + + if (copy_to_user(useraddr, &edata, sizeof(edata))) + return -EFAULT; + + return 0; +} + +static int ethtool_set_eee(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_eee edata; + + if (!dev->ethtool_ops->set_eee) + return -EOPNOTSUPP; + + if (copy_from_user(&edata, useraddr, sizeof(edata))) + return -EFAULT; + + return dev->ethtool_ops->set_eee(dev, &edata); +} + static int ethtool_nway_reset(struct net_device *dev) { if (!dev->ethtool_ops->nway_reset) @@ -1409,6 +1443,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GSET: case ETHTOOL_GDRVINFO: case ETHTOOL_GMSGLVL: + case ETHTOOL_GLINK: case ETHTOOL_GCOALESCE: case ETHTOOL_GRINGPARAM: case ETHTOOL_GPAUSEPARAM: @@ -1417,6 +1452,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GSG: case ETHTOOL_GSSET_INFO: case ETHTOOL_GSTRINGS: + case ETHTOOL_GSTATS: case ETHTOOL_GTSO: case ETHTOOL_GPERMADDR: case ETHTOOL_GUFO: @@ -1429,8 +1465,11 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GRXCLSRLCNT: case ETHTOOL_GRXCLSRULE: case ETHTOOL_GRXCLSRLALL: + case ETHTOOL_GRXFHINDIR: case ETHTOOL_GFEATURES: + case ETHTOOL_GCHANNELS: case ETHTOOL_GET_TS_INFO: + case ETHTOOL_GEEE: break; default: if (!capable(CAP_NET_ADMIN)) @@ -1471,6 +1510,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) rc = ethtool_set_value_void(dev, useraddr, dev->ethtool_ops->set_msglevel); break; + case ETHTOOL_GEEE: + rc = ethtool_get_eee(dev, useraddr); + break; + case ETHTOOL_SEEE: + rc = ethtool_set_eee(dev, useraddr); + break; case ETHTOOL_NWAY_RST: rc = ethtool_nway_reset(dev); break; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 72cceb79d0d..ab7db83236c 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -151,6 +151,8 @@ static void fib_rules_cleanup_ops(struct fib_rules_ops *ops) list_for_each_entry_safe(rule, tmp, &ops->rules_list, list) { list_del_rcu(&rule->list); + if (ops->delete) + ops->delete(rule); fib_rule_put(rule); } } @@ -499,6 +501,8 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).pid); + if (ops->delete) + ops->delete(rule); fib_rule_put(rule); flush_route_cache(ops); rules_ops_put(ops); diff --git a/net/core/filter.c b/net/core/filter.c index d4ce2dc712e..907efd27ec7 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -83,6 +83,14 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) int err; struct sk_filter *filter; + /* + * If the skb was allocated from pfmemalloc reserves, only + * allow SOCK_MEMALLOC sockets to use it as this socket is + * helping free memory + */ + if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) + return -ENOMEM; + err = security_sock_rcv_skb(sk, skb); if (err) return err; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index a225089df5b..466820b6e34 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -4,6 +4,7 @@ #include <linux/ipv6.h> #include <linux/if_vlan.h> #include <net/ip.h> +#include <net/ipv6.h> #include <linux/if_tunnel.h> #include <linux/if_pppox.h> #include <linux/ppp_defs.h> @@ -55,8 +56,8 @@ ipv6: return false; ip_proto = iph->nexthdr; - flow->src = iph->saddr.s6_addr32[3]; - flow->dst = iph->daddr.s6_addr32[3]; + flow->src = (__force __be32)ipv6_addr_hash(&iph->saddr); + flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr); nhoff += sizeof(struct ipv6hdr); break; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index d81d026138f..117afaf5126 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -474,8 +474,8 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, } EXPORT_SYMBOL(neigh_lookup_nodev); -struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, - struct net_device *dev) +struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, + struct net_device *dev, bool want_ref) { u32 hash_val; int key_len = tbl->key_len; @@ -535,14 +535,16 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, n1 = rcu_dereference_protected(n1->next, lockdep_is_held(&tbl->lock))) { if (dev == n1->dev && !memcmp(n1->primary_key, pkey, key_len)) { - neigh_hold(n1); + if (want_ref) + neigh_hold(n1); rc = n1; goto out_tbl_unlock; } } n->dead = 0; - neigh_hold(n); + if (want_ref) + neigh_hold(n); rcu_assign_pointer(n->next, rcu_dereference_protected(nht->hash_buckets[hash_val], lockdep_is_held(&tbl->lock))); @@ -558,7 +560,7 @@ out_neigh_release: neigh_release(n); goto out; } -EXPORT_SYMBOL(neigh_create); +EXPORT_SYMBOL(__neigh_create); static u32 pneigh_hash(const void *pkey, int key_len) { @@ -1199,10 +1201,23 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, write_unlock_bh(&neigh->lock); rcu_read_lock(); - /* On shaper/eql skb->dst->neighbour != neigh :( */ - if (dst && (n2 = dst_get_neighbour_noref(dst)) != NULL) - n1 = n2; + + /* Why not just use 'neigh' as-is? The problem is that + * things such as shaper, eql, and sch_teql can end up + * using alternative, different, neigh objects to output + * the packet in the output path. So what we need to do + * here is re-lookup the top-level neigh in the path so + * we can reinject the packet there. + */ + n2 = NULL; + if (dst) { + n2 = dst_neigh_lookup_skb(dst, skb); + if (n2) + n1 = n2; + } n1->output(n1, skb); + if (n2) + neigh_release(n2); rcu_read_unlock(); write_lock_bh(&neigh->lock); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index fdf9e61d065..72607174ea5 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -417,72 +417,6 @@ static struct attribute_group netstat_group = { .name = "statistics", .attrs = netstat_attrs, }; - -#ifdef CONFIG_WIRELESS_EXT_SYSFS -/* helper function that does all the locking etc for wireless stats */ -static ssize_t wireless_show(struct device *d, char *buf, - ssize_t (*format)(const struct iw_statistics *, - char *)) -{ - struct net_device *dev = to_net_dev(d); - const struct iw_statistics *iw; - ssize_t ret = -EINVAL; - - if (!rtnl_trylock()) - return restart_syscall(); - if (dev_isalive(dev)) { - iw = get_wireless_stats(dev); - if (iw) - ret = (*format)(iw, buf); - } - rtnl_unlock(); - - return ret; -} - -/* show function template for wireless fields */ -#define WIRELESS_SHOW(name, field, format_string) \ -static ssize_t format_iw_##name(const struct iw_statistics *iw, char *buf) \ -{ \ - return sprintf(buf, format_string, iw->field); \ -} \ -static ssize_t show_iw_##name(struct device *d, \ - struct device_attribute *attr, char *buf) \ -{ \ - return wireless_show(d, buf, format_iw_##name); \ -} \ -static DEVICE_ATTR(name, S_IRUGO, show_iw_##name, NULL) - -WIRELESS_SHOW(status, status, fmt_hex); -WIRELESS_SHOW(link, qual.qual, fmt_dec); -WIRELESS_SHOW(level, qual.level, fmt_dec); -WIRELESS_SHOW(noise, qual.noise, fmt_dec); -WIRELESS_SHOW(nwid, discard.nwid, fmt_dec); -WIRELESS_SHOW(crypt, discard.code, fmt_dec); -WIRELESS_SHOW(fragment, discard.fragment, fmt_dec); -WIRELESS_SHOW(misc, discard.misc, fmt_dec); -WIRELESS_SHOW(retries, discard.retries, fmt_dec); -WIRELESS_SHOW(beacon, miss.beacon, fmt_dec); - -static struct attribute *wireless_attrs[] = { - &dev_attr_status.attr, - &dev_attr_link.attr, - &dev_attr_level.attr, - &dev_attr_noise.attr, - &dev_attr_nwid.attr, - &dev_attr_crypt.attr, - &dev_attr_fragment.attr, - &dev_attr_retries.attr, - &dev_attr_misc.attr, - &dev_attr_beacon.attr, - NULL -}; - -static struct attribute_group wireless_group = { - .name = "wireless", - .attrs = wireless_attrs, -}; -#endif #endif /* CONFIG_SYSFS */ #ifdef CONFIG_RPS @@ -1463,14 +1397,6 @@ int netdev_register_kobject(struct net_device *net) groups++; *groups++ = &netstat_group; -#ifdef CONFIG_WIRELESS_EXT_SYSFS - if (net->ieee80211_ptr) - *groups++ = &wireless_group; -#ifdef CONFIG_WIRELESS_EXT - else if (net->wireless_handlers) - *groups++ = &wireless_group; -#endif -#endif #endif /* CONFIG_SYSFS */ error = device_add(dev); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index f9f40b932e4..e4ba3e70c17 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -26,6 +26,7 @@ #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/if_vlan.h> #include <net/tcp.h> #include <net/udp.h> #include <asm/unaligned.h> @@ -54,7 +55,7 @@ static atomic_t trapped; MAX_UDP_CHUNK) static void zap_completion_queue(void); -static void arp_reply(struct sk_buff *skb); +static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo); static unsigned int carrier_timeout = 4; module_param(carrier_timeout, uint, 0644); @@ -170,7 +171,8 @@ static void poll_napi(struct net_device *dev) list_for_each_entry(napi, &dev->napi_list, dev_list) { if (napi->poll_owner != smp_processor_id() && spin_trylock(&napi->poll_lock)) { - budget = poll_one_napi(dev->npinfo, napi, budget); + budget = poll_one_napi(rcu_dereference_bh(dev->npinfo), + napi, budget); spin_unlock(&napi->poll_lock); if (!budget) @@ -185,13 +187,14 @@ static void service_arp_queue(struct netpoll_info *npi) struct sk_buff *skb; while ((skb = skb_dequeue(&npi->arp_tx))) - arp_reply(skb); + netpoll_arp_reply(skb, npi); } } static void netpoll_poll_dev(struct net_device *dev) { const struct net_device_ops *ops; + struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); if (!dev || !netif_running(dev)) return; @@ -206,17 +209,18 @@ static void netpoll_poll_dev(struct net_device *dev) poll_napi(dev); if (dev->flags & IFF_SLAVE) { - if (dev->npinfo) { + if (ni) { struct net_device *bond_dev = dev->master; struct sk_buff *skb; - while ((skb = skb_dequeue(&dev->npinfo->arp_tx))) { + struct netpoll_info *bond_ni = rcu_dereference_bh(bond_dev->npinfo); + while ((skb = skb_dequeue(&ni->arp_tx))) { skb->dev = bond_dev; - skb_queue_tail(&bond_dev->npinfo->arp_tx, skb); + skb_queue_tail(&bond_ni->arp_tx, skb); } } } - service_arp_queue(dev->npinfo); + service_arp_queue(ni); zap_completion_queue(); } @@ -302,6 +306,7 @@ static int netpoll_owner_active(struct net_device *dev) return 0; } +/* call with IRQ disabled */ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, struct net_device *dev) { @@ -309,8 +314,11 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, unsigned long tries; const struct net_device_ops *ops = dev->netdev_ops; /* It is up to the caller to keep npinfo alive. */ - struct netpoll_info *npinfo = np->dev->npinfo; + struct netpoll_info *npinfo; + + WARN_ON_ONCE(!irqs_disabled()); + npinfo = rcu_dereference_bh(np->dev->npinfo); if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) { __kfree_skb(skb); return; @@ -319,16 +327,22 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, /* don't get messages out of order, and no recursion */ if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) { struct netdev_queue *txq; - unsigned long flags; txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); - local_irq_save(flags); /* try until next clock tick */ for (tries = jiffies_to_usecs(1)/USEC_PER_POLL; tries > 0; --tries) { if (__netif_tx_trylock(txq)) { if (!netif_xmit_stopped(txq)) { + if (vlan_tx_tag_present(skb) && + !(netif_skb_features(skb) & NETIF_F_HW_VLAN_TX)) { + skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb)); + if (unlikely(!skb)) + break; + skb->vlan_tci = 0; + } + status = ops->ndo_start_xmit(skb, dev); if (status == NETDEV_TX_OK) txq_trans_update(txq); @@ -347,10 +361,9 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, } WARN_ONCE(!irqs_disabled(), - "netpoll_send_skb(): %s enabled interrupts in poll (%pF)\n", + "netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n", dev->name, ops->ndo_start_xmit); - local_irq_restore(flags); } if (status != NETDEV_TX_OK) { @@ -423,9 +436,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) } EXPORT_SYMBOL(netpoll_send_udp); -static void arp_reply(struct sk_buff *skb) +static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo) { - struct netpoll_info *npinfo = skb->dev->npinfo; struct arphdr *arp; unsigned char *arp_ptr; int size, type = ARPOP_REPLY, ptype = ETH_P_ARP; @@ -543,13 +555,12 @@ static void arp_reply(struct sk_buff *skb) spin_unlock_irqrestore(&npinfo->rx_lock, flags); } -int __netpoll_rx(struct sk_buff *skb) +int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) { int proto, len, ulen; int hits = 0; const struct iphdr *iph; struct udphdr *uh; - struct netpoll_info *npinfo = skb->dev->npinfo; struct netpoll *np, *tmp; if (list_empty(&npinfo->rx_np)) @@ -565,6 +576,12 @@ int __netpoll_rx(struct sk_buff *skb) return 1; } + if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { + skb = vlan_untag(skb); + if (unlikely(!skb)) + goto out; + } + proto = ntohs(eth_hdr(skb)->h_proto); if (proto != ETH_P_IP) goto out; @@ -715,14 +732,16 @@ int netpoll_parse_options(struct netpoll *np, char *opt) } EXPORT_SYMBOL(netpoll_parse_options); -int __netpoll_setup(struct netpoll *np) +int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) { - struct net_device *ndev = np->dev; struct netpoll_info *npinfo; const struct net_device_ops *ops; unsigned long flags; int err; + np->dev = ndev; + strlcpy(np->dev_name, ndev->name, IFNAMSIZ); + if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) || !ndev->netdev_ops->ndo_poll_controller) { np_err(np, "%s doesn't support polling, aborting\n", @@ -732,7 +751,7 @@ int __netpoll_setup(struct netpoll *np) } if (!ndev->npinfo) { - npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL); + npinfo = kmalloc(sizeof(*npinfo), gfp); if (!npinfo) { err = -ENOMEM; goto out; @@ -750,7 +769,7 @@ int __netpoll_setup(struct netpoll *np) ops = np->dev->netdev_ops; if (ops->ndo_netpoll_setup) { - err = ops->ndo_netpoll_setup(ndev, npinfo); + err = ops->ndo_netpoll_setup(ndev, npinfo, gfp); if (err) goto free_npinfo; } @@ -851,13 +870,11 @@ int netpoll_setup(struct netpoll *np) np_info(np, "local IP %pI4\n", &np->local_ip); } - np->dev = ndev; - /* fill up the skb queue */ refill_skbs(); rtnl_lock(); - err = __netpoll_setup(np); + err = __netpoll_setup(np, ndev, GFP_KERNEL); rtnl_unlock(); if (err) @@ -878,6 +895,24 @@ static int __init netpoll_init(void) } core_initcall(netpoll_init); +static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head) +{ + struct netpoll_info *npinfo = + container_of(rcu_head, struct netpoll_info, rcu); + + skb_queue_purge(&npinfo->arp_tx); + skb_queue_purge(&npinfo->txq); + + /* we can't call cancel_delayed_work_sync here, as we are in softirq */ + cancel_delayed_work(&npinfo->tx_work); + + /* clean after last, unfinished work */ + __skb_queue_purge(&npinfo->txq); + /* now cancel it again */ + cancel_delayed_work(&npinfo->tx_work); + kfree(npinfo); +} + void __netpoll_cleanup(struct netpoll *np) { struct netpoll_info *npinfo; @@ -903,20 +938,24 @@ void __netpoll_cleanup(struct netpoll *np) ops->ndo_netpoll_cleanup(np->dev); RCU_INIT_POINTER(np->dev->npinfo, NULL); + call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info); + } +} +EXPORT_SYMBOL_GPL(__netpoll_cleanup); - /* avoid racing with NAPI reading npinfo */ - synchronize_rcu_bh(); +static void rcu_cleanup_netpoll(struct rcu_head *rcu_head) +{ + struct netpoll *np = container_of(rcu_head, struct netpoll, rcu); - skb_queue_purge(&npinfo->arp_tx); - skb_queue_purge(&npinfo->txq); - cancel_delayed_work_sync(&npinfo->tx_work); + __netpoll_cleanup(np); + kfree(np); +} - /* clean after last, unfinished work */ - __skb_queue_purge(&npinfo->txq); - kfree(npinfo); - } +void __netpoll_free_rcu(struct netpoll *np) +{ + call_rcu_bh(&np->rcu, rcu_cleanup_netpoll); } -EXPORT_SYMBOL_GPL(__netpoll_cleanup); +EXPORT_SYMBOL_GPL(__netpoll_free_rcu); void netpoll_cleanup(struct netpoll *np) { diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index b2e9caa1ad1..c75e3f9d060 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -25,6 +25,8 @@ #include <net/sock.h> #include <net/netprio_cgroup.h> +#include <linux/fdtable.h> + #define PRIOIDX_SZ 128 static unsigned long prioidx_map[PRIOIDX_SZ]; @@ -99,12 +101,10 @@ static int write_update_netdev_table(struct net_device *dev) u32 max_len; struct netprio_map *map; - rtnl_lock(); max_len = atomic_read(&max_prioidx) + 1; map = rtnl_dereference(dev->priomap); if (!map || map->priomap_len < max_len) ret = extend_netdev_table(dev, max_len); - rtnl_unlock(); return ret; } @@ -232,7 +232,7 @@ static int write_priomap(struct cgroup *cgrp, struct cftype *cft, /* *Separate the devname from the associated priority - *and advance the priostr poitner to the priority value + *and advance the priostr pointer to the priority value */ *priostr = '\0'; priostr++; @@ -254,17 +254,17 @@ static int write_priomap(struct cgroup *cgrp, struct cftype *cft, if (!dev) goto out_free_devname; + rtnl_lock(); ret = write_update_netdev_table(dev); if (ret < 0) goto out_put_dev; - rcu_read_lock(); - map = rcu_dereference(dev->priomap); + map = rtnl_dereference(dev->priomap); if (map) map->priomap[prioidx] = priority; - rcu_read_unlock(); out_put_dev: + rtnl_unlock(); dev_put(dev); out_free_devname: @@ -272,6 +272,42 @@ out_free_devname: return ret; } +void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) +{ + struct task_struct *p; + + cgroup_taskset_for_each(p, cgrp, tset) { + unsigned int fd; + struct fdtable *fdt; + struct files_struct *files; + + task_lock(p); + files = p->files; + if (!files) { + task_unlock(p); + continue; + } + + spin_lock(&files->file_lock); + fdt = files_fdtable(files); + for (fd = 0; fd < fdt->max_fds; fd++) { + struct file *file; + struct socket *sock; + int err; + + file = fcheck_files(files, fd); + if (!file) + continue; + + sock = sock_from_file(file, &err); + if (sock) + sock_update_netprioidx(sock->sk, p); + } + spin_unlock(&files->file_lock); + task_unlock(p); + } +} + static struct cftype ss_files[] = { { .name = "prioidx", @@ -289,6 +325,7 @@ struct cgroup_subsys net_prio_subsys = { .name = "net_prio", .create = cgrp_create, .destroy = cgrp_destroy, + .attach = net_prio_attach, #ifdef CONFIG_NETPRIO_CGROUP .subsys_id = net_prio_subsys_id, #endif diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 21318d15bbc..2c5a0a06c4c 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -541,19 +541,6 @@ static const int rta_max[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWACTION)] = TCAA_MAX, }; -void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data) -{ - struct rtattr *rta; - int size = RTA_LENGTH(attrlen); - - rta = (struct rtattr *)skb_put(skb, RTA_ALIGN(size)); - rta->rta_type = attrtype; - rta->rta_len = size; - memcpy(RTA_DATA(rta), data, attrlen); - memset(RTA_DATA(rta) + attrlen, 0, RTA_ALIGN(size) - size); -} -EXPORT_SYMBOL(__rta_fill); - int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, int echo) { struct sock *rtnl = net->rtnl; @@ -628,7 +615,7 @@ nla_put_failure: EXPORT_SYMBOL(rtnetlink_put_metrics); int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, - u32 ts, u32 tsage, long expires, u32 error) + long expires, u32 error) { struct rta_cacheinfo ci = { .rta_lastuse = jiffies_to_clock_t(jiffies - dst->lastuse), @@ -636,13 +623,15 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, .rta_clntref = atomic_read(&(dst->__refcnt)), .rta_error = error, .rta_id = id, - .rta_ts = ts, - .rta_tsage = tsage, }; - if (expires) - ci.rta_expires = jiffies_to_clock_t(expires); + if (expires) { + unsigned long clock; + clock = jiffies_to_clock_t(abs(expires)); + clock = min_t(unsigned long, clock, INT_MAX); + ci.rta_expires = (expires > 0) ? clock : -clock; + } return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci); } EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo); @@ -674,6 +663,12 @@ static void set_operstate(struct net_device *dev, unsigned char transition) } } +static unsigned int rtnl_dev_get_flags(const struct net_device *dev) +{ + return (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI)) | + (dev->gflags & (IFF_PROMISC | IFF_ALLMULTI)); +} + static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, const struct ifinfomsg *ifm) { @@ -682,7 +677,7 @@ static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, /* bugwards compatibility: ifi_change == 0 is treated as ~0 */ if (ifm->ifi_change) flags = (flags & ifm->ifi_change) | - (dev->flags & ~ifm->ifi_change); + (rtnl_dev_get_flags(dev) & ~ifm->ifi_change); return flags; } @@ -786,6 +781,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(4) /* IFLA_MASTER */ + nla_total_size(4) /* IFLA_PROMISCUITY */ + + nla_total_size(4) /* IFLA_NUM_TX_QUEUES */ + + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ + nla_total_size(ext_filter_mask @@ -904,6 +901,10 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put_u32(skb, IFLA_MTU, dev->mtu) || nla_put_u32(skb, IFLA_GROUP, dev->group) || nla_put_u32(skb, IFLA_PROMISCUITY, dev->promiscuity) || + nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) || +#ifdef CONFIG_RPS + nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) || +#endif (dev->ifindex != dev->iflink && nla_put_u32(skb, IFLA_LINK, dev->iflink)) || (dev->master && @@ -1121,6 +1122,8 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_AF_SPEC] = { .type = NLA_NESTED }, [IFLA_EXT_MASK] = { .type = NLA_U32 }, [IFLA_PROMISCUITY] = { .type = NLA_U32 }, + [IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 }, + [IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 }, }; EXPORT_SYMBOL(ifla_policy); @@ -1378,6 +1381,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, goto errout; send_addr_notify = 1; modified = 1; + add_device_randomness(dev->dev_addr, dev->addr_len); } if (tb[IFLA_MTU]) { @@ -1639,17 +1643,22 @@ struct net_device *rtnl_create_link(struct net *src_net, struct net *net, { int err; struct net_device *dev; - unsigned int num_queues = 1; + unsigned int num_tx_queues = 1; + unsigned int num_rx_queues = 1; - if (ops->get_tx_queues) { - err = ops->get_tx_queues(src_net, tb); - if (err < 0) - goto err; - num_queues = err; - } + if (tb[IFLA_NUM_TX_QUEUES]) + num_tx_queues = nla_get_u32(tb[IFLA_NUM_TX_QUEUES]); + else if (ops->get_num_tx_queues) + num_tx_queues = ops->get_num_tx_queues(); + + if (tb[IFLA_NUM_RX_QUEUES]) + num_rx_queues = nla_get_u32(tb[IFLA_NUM_RX_QUEUES]); + else if (ops->get_num_rx_queues) + num_rx_queues = ops->get_num_rx_queues(); err = -ENOMEM; - dev = alloc_netdev_mq(ops->priv_size, ifname, ops->setup, num_queues); + dev = alloc_netdev_mqs(ops->priv_size, ifname, ops->setup, + num_tx_queues, num_rx_queues); if (!dev) goto err; @@ -2189,7 +2198,7 @@ skip: } /** - * ndo_dflt_fdb_dump: default netdevice operation to dump an FDB table. + * ndo_dflt_fdb_dump - default netdevice operation to dump an FDB table. * @nlh: netlink message header * @dev: netdevice * @@ -2366,8 +2375,13 @@ static struct notifier_block rtnetlink_dev_notifier = { static int __net_init rtnetlink_net_init(struct net *net) { struct sock *sk; - sk = netlink_kernel_create(net, NETLINK_ROUTE, RTNLGRP_MAX, - rtnetlink_rcv, &rtnl_mutex, THIS_MODULE); + struct netlink_kernel_cfg cfg = { + .groups = RTNLGRP_MAX, + .input = rtnetlink_rcv, + .cb_mutex = &rtnl_mutex, + }; + + sk = netlink_kernel_create(net, NETLINK_ROUTE, THIS_MODULE, &cfg); if (!sk) return -ENOMEM; net->rtnl = sk; diff --git a/net/core/scm.c b/net/core/scm.c index 611c5efd4cb..040cebeed45 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -109,25 +109,9 @@ void __scm_destroy(struct scm_cookie *scm) if (fpl) { scm->fp = NULL; - if (current->scm_work_list) { - list_add_tail(&fpl->list, current->scm_work_list); - } else { - LIST_HEAD(work_list); - - current->scm_work_list = &work_list; - - list_add(&fpl->list, &work_list); - while (!list_empty(&work_list)) { - fpl = list_first_entry(&work_list, struct scm_fp_list, list); - - list_del(&fpl->list); - for (i=fpl->count-1; i>=0; i--) - fput(fpl->fp[i]); - kfree(fpl); - } - - current->scm_work_list = NULL; - } + for (i=fpl->count-1; i>=0; i--) + fput(fpl->fp[i]); + kfree(fpl); } } EXPORT_SYMBOL(__scm_destroy); @@ -281,6 +265,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) for (i=0, cmfptr=(__force int __user *)CMSG_DATA(cm); i<fdmax; i++, cmfptr++) { + struct socket *sock; int new_fd; err = security_file_receive(fp[i]); if (err) @@ -297,6 +282,9 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) } /* Bump the usage count and install the file. */ get_file(fp[i]); + sock = sock_from_file(fp[i], &err); + if (sock) + sock_update_netprioidx(sock->sk, current); fd_install(new_fd, fp[i]); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d124306b81f..fe00d120816 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -145,6 +145,43 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here) BUG(); } + +/* + * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells + * the caller if emergency pfmemalloc reserves are being used. If it is and + * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves + * may be used. Otherwise, the packet data may be discarded until enough + * memory is free + */ +#define kmalloc_reserve(size, gfp, node, pfmemalloc) \ + __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc) +void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip, + bool *pfmemalloc) +{ + void *obj; + bool ret_pfmemalloc = false; + + /* + * Try a regular allocation, when that fails and we're not entitled + * to the reserves, fail. + */ + obj = kmalloc_node_track_caller(size, + flags | __GFP_NOMEMALLOC | __GFP_NOWARN, + node); + if (obj || !(gfp_pfmemalloc_allowed(flags))) + goto out; + + /* Try again but now we are using pfmemalloc reserves */ + ret_pfmemalloc = true; + obj = kmalloc_node_track_caller(size, flags, node); + +out: + if (pfmemalloc) + *pfmemalloc = ret_pfmemalloc; + + return obj; +} + /* Allocate a new skbuff. We do this ourselves so we can fill in a few * 'private' fields and also do memory statistics to find all the * [BEEP] leaks. @@ -155,26 +192,33 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here) * __alloc_skb - allocate a network buffer * @size: size to allocate * @gfp_mask: allocation mask - * @fclone: allocate from fclone cache instead of head cache - * and allocate a cloned (child) skb + * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache + * instead of head cache and allocate a cloned (child) skb. + * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for + * allocations in case the data is required for writeback * @node: numa node to allocate memory on * * Allocate a new &sk_buff. The returned buffer has no headroom and a - * tail room of size bytes. The object has a reference count of one. - * The return is the buffer. On a failure the return is %NULL. + * tail room of at least size bytes. The object has a reference count + * of one. The return is the buffer. On a failure the return is %NULL. * * Buffers may only be allocated from interrupts using a @gfp_mask of * %GFP_ATOMIC. */ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, - int fclone, int node) + int flags, int node) { struct kmem_cache *cache; struct skb_shared_info *shinfo; struct sk_buff *skb; u8 *data; + bool pfmemalloc; - cache = fclone ? skbuff_fclone_cache : skbuff_head_cache; + cache = (flags & SKB_ALLOC_FCLONE) + ? skbuff_fclone_cache : skbuff_head_cache; + + if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) + gfp_mask |= __GFP_MEMALLOC; /* Get the HEAD */ skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node); @@ -189,7 +233,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, */ size = SKB_DATA_ALIGN(size); size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - data = kmalloc_node_track_caller(size, gfp_mask, node); + data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc); if (!data) goto nodata; /* kmalloc(size) might give us more room than requested. @@ -207,6 +251,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, memset(skb, 0, offsetof(struct sk_buff, tail)); /* Account for allocated memory : skb + skb->head */ skb->truesize = SKB_TRUESIZE(size); + skb->pfmemalloc = pfmemalloc; atomic_set(&skb->users, 1); skb->head = data; skb->data = data; @@ -222,7 +267,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, atomic_set(&shinfo->dataref, 1); kmemcheck_annotate_variable(shinfo->destructor_arg); - if (fclone) { + if (flags & SKB_ALLOC_FCLONE) { struct sk_buff *child = skb + 1; atomic_t *fclone_ref = (atomic_t *) (child + 1); @@ -232,6 +277,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, atomic_set(fclone_ref, 1); child->fclone = SKB_FCLONE_UNAVAILABLE; + child->pfmemalloc = pfmemalloc; } out: return skb; @@ -296,17 +342,13 @@ EXPORT_SYMBOL(build_skb); struct netdev_alloc_cache { struct page *page; unsigned int offset; + unsigned int pagecnt_bias; }; static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache); -/** - * netdev_alloc_frag - allocate a page fragment - * @fragsz: fragment size - * - * Allocates a frag from a page for receive buffer. - * Uses GFP_ATOMIC allocations. - */ -void *netdev_alloc_frag(unsigned int fragsz) +#define NETDEV_PAGECNT_BIAS (PAGE_SIZE / SMP_CACHE_BYTES) + +static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { struct netdev_alloc_cache *nc; void *data = NULL; @@ -316,21 +358,42 @@ void *netdev_alloc_frag(unsigned int fragsz) nc = &__get_cpu_var(netdev_alloc_cache); if (unlikely(!nc->page)) { refill: - nc->page = alloc_page(GFP_ATOMIC | __GFP_COLD); + nc->page = alloc_page(gfp_mask); + if (unlikely(!nc->page)) + goto end; +recycle: + atomic_set(&nc->page->_count, NETDEV_PAGECNT_BIAS); + nc->pagecnt_bias = NETDEV_PAGECNT_BIAS; nc->offset = 0; } - if (likely(nc->page)) { - if (nc->offset + fragsz > PAGE_SIZE) { - put_page(nc->page); - goto refill; - } - data = page_address(nc->page) + nc->offset; - nc->offset += fragsz; - get_page(nc->page); + + if (nc->offset + fragsz > PAGE_SIZE) { + /* avoid unnecessary locked operations if possible */ + if ((atomic_read(&nc->page->_count) == nc->pagecnt_bias) || + atomic_sub_and_test(nc->pagecnt_bias, &nc->page->_count)) + goto recycle; + goto refill; } + + data = page_address(nc->page) + nc->offset; + nc->offset += fragsz; + nc->pagecnt_bias--; +end: local_irq_restore(flags); return data; } + +/** + * netdev_alloc_frag - allocate a page fragment + * @fragsz: fragment size + * + * Allocates a frag from a page for receive buffer. + * Uses GFP_ATOMIC allocations. + */ +void *netdev_alloc_frag(unsigned int fragsz) +{ + return __netdev_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD); +} EXPORT_SYMBOL(netdev_alloc_frag); /** @@ -354,7 +417,12 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) { - void *data = netdev_alloc_frag(fragsz); + void *data; + + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; + + data = __netdev_alloc_frag(fragsz, gfp_mask); if (likely(data)) { skb = build_skb(data, fragsz); @@ -362,7 +430,8 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, put_page(virt_to_head_page(data)); } } else { - skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE); + skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, + SKB_ALLOC_RX, NUMA_NO_NODE); } if (likely(skb)) { skb_reserve(skb, NET_SKB_PAD); @@ -644,6 +713,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #if IS_ENABLED(CONFIG_IP_VS) new->ipvs_property = old->ipvs_property; #endif + new->pfmemalloc = old->pfmemalloc; new->protocol = old->protocol; new->mark = old->mark; new->skb_iif = old->skb_iif; @@ -713,7 +783,8 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) } EXPORT_SYMBOL_GPL(skb_morph); -/* skb_copy_ubufs - copy userspace skb frags buffers to kernel +/** + * skb_copy_ubufs - copy userspace skb frags buffers to kernel * @skb: the skb to modify * @gfp_mask: allocation priority * @@ -738,7 +809,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) u8 *vaddr; skb_frag_t *f = &skb_shinfo(skb)->frags[i]; - page = alloc_page(GFP_ATOMIC); + page = alloc_page(gfp_mask); if (!page) { while (head) { struct page *next = (struct page *)head->private; @@ -756,22 +827,22 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) } /* skb frags release userspace buffers */ - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) + for (i = 0; i < num_frags; i++) skb_frag_unref(skb, i); uarg->callback(uarg); /* skb frags point to kernel buffers */ - for (i = skb_shinfo(skb)->nr_frags; i > 0; i--) { - __skb_fill_page_desc(skb, i-1, head, 0, - skb_shinfo(skb)->frags[i - 1].size); + for (i = num_frags - 1; i >= 0; i--) { + __skb_fill_page_desc(skb, i, head, 0, + skb_shinfo(skb)->frags[i].size); head = (struct page *)head->private; } skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; return 0; } - +EXPORT_SYMBOL_GPL(skb_copy_ubufs); /** * skb_clone - duplicate an sk_buff @@ -791,10 +862,8 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff *n; - if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { - if (skb_copy_ubufs(skb, gfp_mask)) - return NULL; - } + if (skb_orphan_frags(skb, gfp_mask)) + return NULL; n = skb + 1; if (skb->fclone == SKB_FCLONE_ORIG && @@ -803,6 +872,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) n->fclone = SKB_FCLONE_CLONE; atomic_inc(fclone_ref); } else { + if (skb_pfmemalloc(skb)) + gfp_mask |= __GFP_MEMALLOC; + n = kmem_cache_alloc(skbuff_head_cache, gfp_mask); if (!n) return NULL; @@ -839,6 +911,13 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type; } +static inline int skb_alloc_rx_flag(const struct sk_buff *skb) +{ + if (skb_pfmemalloc(skb)) + return SKB_ALLOC_RX; + return 0; +} + /** * skb_copy - create private copy of an sk_buff * @skb: buffer to copy @@ -860,7 +939,8 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { int headerlen = skb_headroom(skb); unsigned int size = skb_end_offset(skb) + skb->data_len; - struct sk_buff *n = alloc_skb(size, gfp_mask); + struct sk_buff *n = __alloc_skb(size, gfp_mask, + skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; @@ -895,7 +975,8 @@ EXPORT_SYMBOL(skb_copy); struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask) { unsigned int size = skb_headlen(skb) + headroom; - struct sk_buff *n = alloc_skb(size, gfp_mask); + struct sk_buff *n = __alloc_skb(size, gfp_mask, + skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) goto out; @@ -914,12 +995,10 @@ struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask) if (skb_shinfo(skb)->nr_frags) { int i; - if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { - if (skb_copy_ubufs(skb, gfp_mask)) { - kfree_skb(n); - n = NULL; - goto out; - } + if (skb_orphan_frags(skb, gfp_mask)) { + kfree_skb(n); + n = NULL; + goto out; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i]; @@ -970,8 +1049,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, size = SKB_DATA_ALIGN(size); - data = kmalloc(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), - gfp_mask); + if (skb_pfmemalloc(skb)) + gfp_mask |= __GFP_MEMALLOC; + data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), + gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; size = SKB_WITH_OVERHEAD(ksize(data)); @@ -992,10 +1073,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, */ if (skb_cloned(skb)) { /* copy this zero copy skb frags */ - if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { - if (skb_copy_ubufs(skb, gfp_mask)) - goto nofrags; - } + if (skb_orphan_frags(skb, gfp_mask)) + goto nofrags; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); @@ -1085,8 +1164,9 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, /* * Allocate the copy buffer */ - struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom, - gfp_mask); + struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom, + gfp_mask, skb_alloc_rx_flag(skb), + NUMA_NO_NODE); int oldheadroom = skb_headroom(skb); int head_copy_len, head_copy_off; int off; @@ -2614,7 +2694,7 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, EXPORT_SYMBOL(skb_find_text); /** - * skb_append_datato_frags: - append the user data to a skb + * skb_append_datato_frags - append the user data to a skb * @sk: sock structure * @skb: skb structure to be appened with user data. * @getfrag: call back function to be used for getting the user data @@ -2768,8 +2848,9 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) skb_release_head_state(nskb); __skb_push(nskb, doffset); } else { - nskb = alloc_skb(hsize + doffset + headroom, - GFP_ATOMIC); + nskb = __alloc_skb(hsize + doffset + headroom, + GFP_ATOMIC, skb_alloc_rx_flag(skb), + NUMA_NO_NODE); if (unlikely(!nskb)) goto err; diff --git a/net/core/sock.c b/net/core/sock.c index 9e5b71fda6e..8f67ced8d6a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -142,7 +142,7 @@ static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { struct proto *proto; @@ -271,6 +271,61 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); EXPORT_SYMBOL(sysctl_optmem_max); +struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE; +EXPORT_SYMBOL_GPL(memalloc_socks); + +/** + * sk_set_memalloc - sets %SOCK_MEMALLOC + * @sk: socket to set it on + * + * Set %SOCK_MEMALLOC on a socket for access to emergency reserves. + * It's the responsibility of the admin to adjust min_free_kbytes + * to meet the requirements + */ +void sk_set_memalloc(struct sock *sk) +{ + sock_set_flag(sk, SOCK_MEMALLOC); + sk->sk_allocation |= __GFP_MEMALLOC; + static_key_slow_inc(&memalloc_socks); +} +EXPORT_SYMBOL_GPL(sk_set_memalloc); + +void sk_clear_memalloc(struct sock *sk) +{ + sock_reset_flag(sk, SOCK_MEMALLOC); + sk->sk_allocation &= ~__GFP_MEMALLOC; + static_key_slow_dec(&memalloc_socks); + + /* + * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward + * progress of swapping. However, if SOCK_MEMALLOC is cleared while + * it has rmem allocations there is a risk that the user of the + * socket cannot make forward progress due to exceeding the rmem + * limits. By rights, sk_clear_memalloc() should only be called + * on sockets being torn down but warn and reset the accounting if + * that assumption breaks. + */ + if (WARN_ON(sk->sk_forward_alloc)) + sk_mem_reclaim(sk); +} +EXPORT_SYMBOL_GPL(sk_clear_memalloc); + +int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) +{ + int ret; + unsigned long pflags = current->flags; + + /* these should have been dropped before queueing */ + BUG_ON(!sock_flag(sk, SOCK_MEMALLOC)); + + current->flags |= PF_MEMALLOC; + ret = sk->sk_backlog_rcv(sk, skb); + tsk_restore_flags(current, pflags, PF_MEMALLOC); + + return ret; +} +EXPORT_SYMBOL(__sk_backlog_rcv); + #if defined(CONFIG_CGROUPS) #if !defined(CONFIG_NET_CLS_CGROUP) int net_cls_subsys_id = -1; @@ -353,7 +408,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (err) return err; - if (!sk_rmem_schedule(sk, skb->truesize)) { + if (!sk_rmem_schedule(sk, skb, skb->truesize)) { atomic_inc(&sk->sk_drops); return -ENOBUFS; } @@ -1180,12 +1235,12 @@ void sock_update_classid(struct sock *sk) } EXPORT_SYMBOL(sock_update_classid); -void sock_update_netprioidx(struct sock *sk) +void sock_update_netprioidx(struct sock *sk, struct task_struct *task) { if (in_interrupt()) return; - sk->sk_cgrp_prioidx = task_netprioidx(current); + sk->sk_cgrp_prioidx = task_netprioidx(task); } EXPORT_SYMBOL_GPL(sock_update_netprioidx); #endif @@ -1215,7 +1270,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, atomic_set(&sk->sk_wmem_alloc, 1); sock_update_classid(sk); - sock_update_netprioidx(sk); + sock_update_netprioidx(sk, current); } return sk; @@ -1403,6 +1458,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; sk->sk_gso_max_size = dst->dev->gso_max_size; + sk->sk_gso_max_segs = dst->dev->gso_max_segs; } } } @@ -1465,6 +1521,11 @@ void sock_rfree(struct sk_buff *skb) } EXPORT_SYMBOL(sock_rfree); +void sock_edemux(struct sk_buff *skb) +{ + sock_put(skb->sk); +} +EXPORT_SYMBOL(sock_edemux); int sock_i_uid(struct sock *sk) { @@ -2154,6 +2215,10 @@ void release_sock(struct sock *sk) spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_backlog.tail) __release_sock(sk); + + if (sk->sk_prot->release_cb) + sk->sk_prot->release_cb(sk); + sk->sk_lock.owned = 0; if (waitqueue_active(&sk->sk_lock.wq)) wake_up(&sk->sk_lock.wq); diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 5fd146720f3..9d8755e4a7a 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -4,7 +4,6 @@ #include <net/netlink.h> #include <net/net_namespace.h> #include <linux/module.h> -#include <linux/rtnetlink.h> #include <net/sock.h> #include <linux/inet_diag.h> @@ -35,9 +34,7 @@ EXPORT_SYMBOL_GPL(sock_diag_save_cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) { - __u32 *mem; - - mem = RTA_DATA(__RTA_PUT(skb, attrtype, SK_MEMINFO_VARS * sizeof(__u32))); + u32 mem[SK_MEMINFO_VARS]; mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk); mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf; @@ -46,11 +43,9 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); + mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; - return 0; - -rtattr_failure: - return -EMSGSIZE; + return nla_put(skb, attrtype, sizeof(mem), &mem); } EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); @@ -120,7 +115,7 @@ static inline void sock_diag_unlock_handler(const struct sock_diag_handler *h) static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { int err; - struct sock_diag_req *req = NLMSG_DATA(nlh); + struct sock_diag_req *req = nlmsg_data(nlh); const struct sock_diag_handler *hndl; if (nlmsg_len(nlh) < sizeof(*req)) @@ -171,19 +166,36 @@ static void sock_diag_rcv(struct sk_buff *skb) mutex_unlock(&sock_diag_mutex); } -struct sock *sock_diag_nlsk; -EXPORT_SYMBOL_GPL(sock_diag_nlsk); +static int __net_init diag_net_init(struct net *net) +{ + struct netlink_kernel_cfg cfg = { + .input = sock_diag_rcv, + }; + + net->diag_nlsk = netlink_kernel_create(net, NETLINK_SOCK_DIAG, + THIS_MODULE, &cfg); + return net->diag_nlsk == NULL ? -ENOMEM : 0; +} + +static void __net_exit diag_net_exit(struct net *net) +{ + netlink_kernel_release(net->diag_nlsk); + net->diag_nlsk = NULL; +} + +static struct pernet_operations diag_net_ops = { + .init = diag_net_init, + .exit = diag_net_exit, +}; static int __init sock_diag_init(void) { - sock_diag_nlsk = netlink_kernel_create(&init_net, NETLINK_SOCK_DIAG, 0, - sock_diag_rcv, NULL, THIS_MODULE); - return sock_diag_nlsk == NULL ? -ENOMEM : 0; + return register_pernet_subsys(&diag_net_ops); } static void __exit sock_diag_exit(void) { - netlink_kernel_release(sock_diag_nlsk); + unregister_pernet_subsys(&diag_net_ops); } module_init(sock_diag_init); diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 656c7c75b19..81f2bb62dea 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -28,8 +28,7 @@ #include <linux/module.h> #include <net/sock.h> -/** - * Data Center Bridging (DCB) is a collection of Ethernet enhancements +/* Data Center Bridging (DCB) is a collection of Ethernet enhancements * intended to allow network traffic with differing requirements * (highly reliable, no drops vs. best effort vs. low latency) to operate * and co-exist on Ethernet. Current DCB features are: @@ -196,92 +195,66 @@ static const struct nla_policy dcbnl_featcfg_nest[DCB_FEATCFG_ATTR_MAX + 1] = { static LIST_HEAD(dcb_app_list); static DEFINE_SPINLOCK(dcb_lock); -/* standard netlink reply call */ -static int dcbnl_reply(u8 value, u8 event, u8 cmd, u8 attr, u32 pid, - u32 seq, u16 flags) +static struct sk_buff *dcbnl_newmsg(int type, u8 cmd, u32 port, u32 seq, + u32 flags, struct nlmsghdr **nlhp) { - struct sk_buff *dcbnl_skb; + struct sk_buff *skb; struct dcbmsg *dcb; struct nlmsghdr *nlh; - int ret = -EINVAL; - dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!dcbnl_skb) - return ret; + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return NULL; - nlh = NLMSG_NEW(dcbnl_skb, pid, seq, event, sizeof(*dcb), flags); + nlh = nlmsg_put(skb, port, seq, type, sizeof(*dcb), flags); + BUG_ON(!nlh); - dcb = NLMSG_DATA(nlh); + dcb = nlmsg_data(nlh); dcb->dcb_family = AF_UNSPEC; dcb->cmd = cmd; dcb->dcb_pad = 0; - ret = nla_put_u8(dcbnl_skb, attr, value); - if (ret) - goto err; + if (nlhp) + *nlhp = nlh; - /* end the message, assign the nlmsg_len. */ - nlmsg_end(dcbnl_skb, nlh); - ret = rtnl_unicast(dcbnl_skb, &init_net, pid); - if (ret) - return -EINVAL; - - return 0; -nlmsg_failure: -err: - kfree_skb(dcbnl_skb); - return ret; + return skb; } -static int dcbnl_getstate(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_getstate(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - int ret = -EINVAL; - /* if (!tb[DCB_ATTR_STATE] || !netdev->dcbnl_ops->getstate) */ if (!netdev->dcbnl_ops->getstate) - return ret; - - ret = dcbnl_reply(netdev->dcbnl_ops->getstate(netdev), RTM_GETDCB, - DCB_CMD_GSTATE, DCB_ATTR_STATE, pid, seq, flags); + return -EOPNOTSUPP; - return ret; + return nla_put_u8(skb, DCB_ATTR_STATE, + netdev->dcbnl_ops->getstate(netdev)); } -static int dcbnl_getpfccfg(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_getpfccfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - struct sk_buff *dcbnl_skb; - struct nlmsghdr *nlh; - struct dcbmsg *dcb; struct nlattr *data[DCB_PFC_UP_ATTR_MAX + 1], *nest; u8 value; - int ret = -EINVAL; + int ret; int i; int getall = 0; - if (!tb[DCB_ATTR_PFC_CFG] || !netdev->dcbnl_ops->getpfccfg) - return ret; + if (!tb[DCB_ATTR_PFC_CFG]) + return -EINVAL; + + if (!netdev->dcbnl_ops->getpfccfg) + return -EOPNOTSUPP; ret = nla_parse_nested(data, DCB_PFC_UP_ATTR_MAX, tb[DCB_ATTR_PFC_CFG], dcbnl_pfc_up_nest); if (ret) - goto err_out; - - dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!dcbnl_skb) - goto err_out; - - nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); - - dcb = NLMSG_DATA(nlh); - dcb->dcb_family = AF_UNSPEC; - dcb->cmd = DCB_CMD_PFC_GCFG; + return ret; - nest = nla_nest_start(dcbnl_skb, DCB_ATTR_PFC_CFG); + nest = nla_nest_start(skb, DCB_ATTR_PFC_CFG); if (!nest) - goto err; + return -EMSGSIZE; if (data[DCB_PFC_UP_ATTR_ALL]) getall = 1; @@ -292,103 +265,53 @@ static int dcbnl_getpfccfg(struct net_device *netdev, struct nlattr **tb, netdev->dcbnl_ops->getpfccfg(netdev, i - DCB_PFC_UP_ATTR_0, &value); - ret = nla_put_u8(dcbnl_skb, i, value); - + ret = nla_put_u8(skb, i, value); if (ret) { - nla_nest_cancel(dcbnl_skb, nest); - goto err; + nla_nest_cancel(skb, nest); + return ret; } } - nla_nest_end(dcbnl_skb, nest); - - nlmsg_end(dcbnl_skb, nlh); - - ret = rtnl_unicast(dcbnl_skb, &init_net, pid); - if (ret) - goto err_out; + nla_nest_end(skb, nest); return 0; -nlmsg_failure: -err: - kfree_skb(dcbnl_skb); -err_out: - return -EINVAL; } -static int dcbnl_getperm_hwaddr(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_getperm_hwaddr(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - struct sk_buff *dcbnl_skb; - struct nlmsghdr *nlh; - struct dcbmsg *dcb; u8 perm_addr[MAX_ADDR_LEN]; - int ret = -EINVAL; if (!netdev->dcbnl_ops->getpermhwaddr) - return ret; - - dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!dcbnl_skb) - goto err_out; - - nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); - - dcb = NLMSG_DATA(nlh); - dcb->dcb_family = AF_UNSPEC; - dcb->cmd = DCB_CMD_GPERM_HWADDR; + return -EOPNOTSUPP; netdev->dcbnl_ops->getpermhwaddr(netdev, perm_addr); - ret = nla_put(dcbnl_skb, DCB_ATTR_PERM_HWADDR, sizeof(perm_addr), - perm_addr); - - nlmsg_end(dcbnl_skb, nlh); - - ret = rtnl_unicast(dcbnl_skb, &init_net, pid); - if (ret) - goto err_out; - - return 0; - -nlmsg_failure: - kfree_skb(dcbnl_skb); -err_out: - return -EINVAL; + return nla_put(skb, DCB_ATTR_PERM_HWADDR, sizeof(perm_addr), perm_addr); } -static int dcbnl_getcap(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_getcap(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - struct sk_buff *dcbnl_skb; - struct nlmsghdr *nlh; - struct dcbmsg *dcb; struct nlattr *data[DCB_CAP_ATTR_MAX + 1], *nest; u8 value; - int ret = -EINVAL; + int ret; int i; int getall = 0; - if (!tb[DCB_ATTR_CAP] || !netdev->dcbnl_ops->getcap) - return ret; + if (!tb[DCB_ATTR_CAP]) + return -EINVAL; + + if (!netdev->dcbnl_ops->getcap) + return -EOPNOTSUPP; ret = nla_parse_nested(data, DCB_CAP_ATTR_MAX, tb[DCB_ATTR_CAP], dcbnl_cap_nest); if (ret) - goto err_out; - - dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!dcbnl_skb) - goto err_out; - - nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); - - dcb = NLMSG_DATA(nlh); - dcb->dcb_family = AF_UNSPEC; - dcb->cmd = DCB_CMD_GCAP; + return ret; - nest = nla_nest_start(dcbnl_skb, DCB_ATTR_CAP); + nest = nla_nest_start(skb, DCB_ATTR_CAP); if (!nest) - goto err; + return -EMSGSIZE; if (data[DCB_CAP_ATTR_ALL]) getall = 1; @@ -398,69 +321,41 @@ static int dcbnl_getcap(struct net_device *netdev, struct nlattr **tb, continue; if (!netdev->dcbnl_ops->getcap(netdev, i, &value)) { - ret = nla_put_u8(dcbnl_skb, i, value); - + ret = nla_put_u8(skb, i, value); if (ret) { - nla_nest_cancel(dcbnl_skb, nest); - goto err; + nla_nest_cancel(skb, nest); + return ret; } } } - nla_nest_end(dcbnl_skb, nest); - - nlmsg_end(dcbnl_skb, nlh); - - ret = rtnl_unicast(dcbnl_skb, &init_net, pid); - if (ret) - goto err_out; + nla_nest_end(skb, nest); return 0; -nlmsg_failure: -err: - kfree_skb(dcbnl_skb); -err_out: - return -EINVAL; } -static int dcbnl_getnumtcs(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_getnumtcs(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - struct sk_buff *dcbnl_skb; - struct nlmsghdr *nlh; - struct dcbmsg *dcb; struct nlattr *data[DCB_NUMTCS_ATTR_MAX + 1], *nest; u8 value; - int ret = -EINVAL; + int ret; int i; int getall = 0; - if (!tb[DCB_ATTR_NUMTCS] || !netdev->dcbnl_ops->getnumtcs) - return ret; + if (!tb[DCB_ATTR_NUMTCS]) + return -EINVAL; + + if (!netdev->dcbnl_ops->getnumtcs) + return -EOPNOTSUPP; ret = nla_parse_nested(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS], dcbnl_numtcs_nest); - if (ret) { - ret = -EINVAL; - goto err_out; - } - - dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!dcbnl_skb) { - ret = -EINVAL; - goto err_out; - } - - nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); - - dcb = NLMSG_DATA(nlh); - dcb->dcb_family = AF_UNSPEC; - dcb->cmd = DCB_CMD_GNUMTCS; + if (ret) + return ret; - nest = nla_nest_start(dcbnl_skb, DCB_ATTR_NUMTCS); - if (!nest) { - ret = -EINVAL; - goto err; - } + nest = nla_nest_start(skb, DCB_ATTR_NUMTCS); + if (!nest) + return -EMSGSIZE; if (data[DCB_NUMTCS_ATTR_ALL]) getall = 1; @@ -471,53 +366,37 @@ static int dcbnl_getnumtcs(struct net_device *netdev, struct nlattr **tb, ret = netdev->dcbnl_ops->getnumtcs(netdev, i, &value); if (!ret) { - ret = nla_put_u8(dcbnl_skb, i, value); - + ret = nla_put_u8(skb, i, value); if (ret) { - nla_nest_cancel(dcbnl_skb, nest); - ret = -EINVAL; - goto err; + nla_nest_cancel(skb, nest); + return ret; } - } else { - goto err; - } - } - nla_nest_end(dcbnl_skb, nest); - - nlmsg_end(dcbnl_skb, nlh); - - ret = rtnl_unicast(dcbnl_skb, &init_net, pid); - if (ret) { - ret = -EINVAL; - goto err_out; + } else + return -EINVAL; } + nla_nest_end(skb, nest); return 0; -nlmsg_failure: -err: - kfree_skb(dcbnl_skb); -err_out: - return ret; } -static int dcbnl_setnumtcs(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_setnumtcs(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_NUMTCS_ATTR_MAX + 1]; - int ret = -EINVAL; + int ret; u8 value; int i; - if (!tb[DCB_ATTR_NUMTCS] || !netdev->dcbnl_ops->setnumtcs) - return ret; + if (!tb[DCB_ATTR_NUMTCS]) + return -EINVAL; + + if (!netdev->dcbnl_ops->setnumtcs) + return -EOPNOTSUPP; ret = nla_parse_nested(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS], dcbnl_numtcs_nest); - - if (ret) { - ret = -EINVAL; - goto err; - } + if (ret) + return ret; for (i = DCB_NUMTCS_ATTR_ALL+1; i <= DCB_NUMTCS_ATTR_MAX; i++) { if (data[i] == NULL) @@ -526,84 +405,68 @@ static int dcbnl_setnumtcs(struct net_device *netdev, struct nlattr **tb, value = nla_get_u8(data[i]); ret = netdev->dcbnl_ops->setnumtcs(netdev, i, value); - if (ret) - goto operr; + break; } -operr: - ret = dcbnl_reply(!!ret, RTM_SETDCB, DCB_CMD_SNUMTCS, - DCB_ATTR_NUMTCS, pid, seq, flags); - -err: - return ret; + return nla_put_u8(skb, DCB_ATTR_NUMTCS, !!ret); } -static int dcbnl_getpfcstate(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_getpfcstate(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - int ret = -EINVAL; - if (!netdev->dcbnl_ops->getpfcstate) - return ret; - - ret = dcbnl_reply(netdev->dcbnl_ops->getpfcstate(netdev), RTM_GETDCB, - DCB_CMD_PFC_GSTATE, DCB_ATTR_PFC_STATE, - pid, seq, flags); + return -EOPNOTSUPP; - return ret; + return nla_put_u8(skb, DCB_ATTR_PFC_STATE, + netdev->dcbnl_ops->getpfcstate(netdev)); } -static int dcbnl_setpfcstate(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_setpfcstate(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - int ret = -EINVAL; u8 value; - if (!tb[DCB_ATTR_PFC_STATE] || !netdev->dcbnl_ops->setpfcstate) - return ret; + if (!tb[DCB_ATTR_PFC_STATE]) + return -EINVAL; + + if (!netdev->dcbnl_ops->setpfcstate) + return -EOPNOTSUPP; value = nla_get_u8(tb[DCB_ATTR_PFC_STATE]); netdev->dcbnl_ops->setpfcstate(netdev, value); - ret = dcbnl_reply(0, RTM_SETDCB, DCB_CMD_PFC_SSTATE, DCB_ATTR_PFC_STATE, - pid, seq, flags); - - return ret; + return nla_put_u8(skb, DCB_ATTR_PFC_STATE, 0); } -static int dcbnl_getapp(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_getapp(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - struct sk_buff *dcbnl_skb; - struct nlmsghdr *nlh; - struct dcbmsg *dcb; struct nlattr *app_nest; struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1]; u16 id; u8 up, idtype; - int ret = -EINVAL; + int ret; if (!tb[DCB_ATTR_APP]) - goto out; + return -EINVAL; ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP], dcbnl_app_nest); if (ret) - goto out; + return ret; - ret = -EINVAL; /* all must be non-null */ if ((!app_tb[DCB_APP_ATTR_IDTYPE]) || (!app_tb[DCB_APP_ATTR_ID])) - goto out; + return -EINVAL; /* either by eth type or by socket number */ idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]); if ((idtype != DCB_APP_IDTYPE_ETHTYPE) && (idtype != DCB_APP_IDTYPE_PORTNUM)) - goto out; + return -EINVAL; id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]); @@ -617,138 +480,106 @@ static int dcbnl_getapp(struct net_device *netdev, struct nlattr **tb, up = dcb_getapp(netdev, &app); } - /* send this back */ - dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!dcbnl_skb) - goto out; - - nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); - dcb = NLMSG_DATA(nlh); - dcb->dcb_family = AF_UNSPEC; - dcb->cmd = DCB_CMD_GAPP; - - app_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_APP); + app_nest = nla_nest_start(skb, DCB_ATTR_APP); if (!app_nest) - goto out_cancel; + return -EMSGSIZE; - ret = nla_put_u8(dcbnl_skb, DCB_APP_ATTR_IDTYPE, idtype); + ret = nla_put_u8(skb, DCB_APP_ATTR_IDTYPE, idtype); if (ret) goto out_cancel; - ret = nla_put_u16(dcbnl_skb, DCB_APP_ATTR_ID, id); + ret = nla_put_u16(skb, DCB_APP_ATTR_ID, id); if (ret) goto out_cancel; - ret = nla_put_u8(dcbnl_skb, DCB_APP_ATTR_PRIORITY, up); + ret = nla_put_u8(skb, DCB_APP_ATTR_PRIORITY, up); if (ret) goto out_cancel; - nla_nest_end(dcbnl_skb, app_nest); - nlmsg_end(dcbnl_skb, nlh); - - ret = rtnl_unicast(dcbnl_skb, &init_net, pid); - if (ret) - goto nlmsg_failure; + nla_nest_end(skb, app_nest); - goto out; + return 0; out_cancel: - nla_nest_cancel(dcbnl_skb, app_nest); -nlmsg_failure: - kfree_skb(dcbnl_skb); -out: + nla_nest_cancel(skb, app_nest); return ret; } -static int dcbnl_setapp(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_setapp(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - int err, ret = -EINVAL; + int ret; u16 id; u8 up, idtype; struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1]; if (!tb[DCB_ATTR_APP]) - goto out; + return -EINVAL; ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP], dcbnl_app_nest); if (ret) - goto out; + return ret; - ret = -EINVAL; /* all must be non-null */ if ((!app_tb[DCB_APP_ATTR_IDTYPE]) || (!app_tb[DCB_APP_ATTR_ID]) || (!app_tb[DCB_APP_ATTR_PRIORITY])) - goto out; + return -EINVAL; /* either by eth type or by socket number */ idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]); if ((idtype != DCB_APP_IDTYPE_ETHTYPE) && (idtype != DCB_APP_IDTYPE_PORTNUM)) - goto out; + return -EINVAL; id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]); up = nla_get_u8(app_tb[DCB_APP_ATTR_PRIORITY]); if (netdev->dcbnl_ops->setapp) { - err = netdev->dcbnl_ops->setapp(netdev, idtype, id, up); + ret = netdev->dcbnl_ops->setapp(netdev, idtype, id, up); } else { struct dcb_app app; app.selector = idtype; app.protocol = id; app.priority = up; - err = dcb_setapp(netdev, &app); + ret = dcb_setapp(netdev, &app); } - ret = dcbnl_reply(err, RTM_SETDCB, DCB_CMD_SAPP, DCB_ATTR_APP, - pid, seq, flags); + ret = nla_put_u8(skb, DCB_ATTR_APP, ret); dcbnl_cee_notify(netdev, RTM_SETDCB, DCB_CMD_SAPP, seq, 0); -out: + return ret; } -static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags, int dir) +static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, + struct nlattr **tb, struct sk_buff *skb, int dir) { - struct sk_buff *dcbnl_skb; - struct nlmsghdr *nlh; - struct dcbmsg *dcb; struct nlattr *pg_nest, *param_nest, *data; struct nlattr *pg_tb[DCB_PG_ATTR_MAX + 1]; struct nlattr *param_tb[DCB_TC_ATTR_PARAM_MAX + 1]; u8 prio, pgid, tc_pct, up_map; - int ret = -EINVAL; + int ret; int getall = 0; int i; - if (!tb[DCB_ATTR_PG_CFG] || - !netdev->dcbnl_ops->getpgtccfgtx || + if (!tb[DCB_ATTR_PG_CFG]) + return -EINVAL; + + if (!netdev->dcbnl_ops->getpgtccfgtx || !netdev->dcbnl_ops->getpgtccfgrx || !netdev->dcbnl_ops->getpgbwgcfgtx || !netdev->dcbnl_ops->getpgbwgcfgrx) - return ret; + return -EOPNOTSUPP; ret = nla_parse_nested(pg_tb, DCB_PG_ATTR_MAX, tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest); - if (ret) - goto err_out; - - dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!dcbnl_skb) - goto err_out; - - nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); - - dcb = NLMSG_DATA(nlh); - dcb->dcb_family = AF_UNSPEC; - dcb->cmd = (dir) ? DCB_CMD_PGRX_GCFG : DCB_CMD_PGTX_GCFG; + return ret; - pg_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_PG_CFG); + pg_nest = nla_nest_start(skb, DCB_ATTR_PG_CFG); if (!pg_nest) - goto err; + return -EMSGSIZE; if (pg_tb[DCB_PG_ATTR_TC_ALL]) getall = 1; @@ -766,7 +597,7 @@ static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlattr **tb, if (ret) goto err_pg; - param_nest = nla_nest_start(dcbnl_skb, i); + param_nest = nla_nest_start(skb, i); if (!param_nest) goto err_pg; @@ -789,33 +620,33 @@ static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlattr **tb, if (param_tb[DCB_TC_ATTR_PARAM_PGID] || param_tb[DCB_TC_ATTR_PARAM_ALL]) { - ret = nla_put_u8(dcbnl_skb, + ret = nla_put_u8(skb, DCB_TC_ATTR_PARAM_PGID, pgid); if (ret) goto err_param; } if (param_tb[DCB_TC_ATTR_PARAM_UP_MAPPING] || param_tb[DCB_TC_ATTR_PARAM_ALL]) { - ret = nla_put_u8(dcbnl_skb, + ret = nla_put_u8(skb, DCB_TC_ATTR_PARAM_UP_MAPPING, up_map); if (ret) goto err_param; } if (param_tb[DCB_TC_ATTR_PARAM_STRICT_PRIO] || param_tb[DCB_TC_ATTR_PARAM_ALL]) { - ret = nla_put_u8(dcbnl_skb, + ret = nla_put_u8(skb, DCB_TC_ATTR_PARAM_STRICT_PRIO, prio); if (ret) goto err_param; } if (param_tb[DCB_TC_ATTR_PARAM_BW_PCT] || param_tb[DCB_TC_ATTR_PARAM_ALL]) { - ret = nla_put_u8(dcbnl_skb, DCB_TC_ATTR_PARAM_BW_PCT, + ret = nla_put_u8(skb, DCB_TC_ATTR_PARAM_BW_PCT, tc_pct); if (ret) goto err_param; } - nla_nest_end(dcbnl_skb, param_nest); + nla_nest_end(skb, param_nest); } if (pg_tb[DCB_PG_ATTR_BW_ID_ALL]) @@ -838,80 +669,71 @@ static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlattr **tb, netdev->dcbnl_ops->getpgbwgcfgtx(netdev, i - DCB_PG_ATTR_BW_ID_0, &tc_pct); } - ret = nla_put_u8(dcbnl_skb, i, tc_pct); - + ret = nla_put_u8(skb, i, tc_pct); if (ret) goto err_pg; } - nla_nest_end(dcbnl_skb, pg_nest); - - nlmsg_end(dcbnl_skb, nlh); - - ret = rtnl_unicast(dcbnl_skb, &init_net, pid); - if (ret) - goto err_out; + nla_nest_end(skb, pg_nest); return 0; err_param: - nla_nest_cancel(dcbnl_skb, param_nest); + nla_nest_cancel(skb, param_nest); err_pg: - nla_nest_cancel(dcbnl_skb, pg_nest); -nlmsg_failure: -err: - kfree_skb(dcbnl_skb); -err_out: - ret = -EINVAL; - return ret; + nla_nest_cancel(skb, pg_nest); + + return -EMSGSIZE; } -static int dcbnl_pgtx_getcfg(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_pgtx_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - return __dcbnl_pg_getcfg(netdev, tb, pid, seq, flags, 0); + return __dcbnl_pg_getcfg(netdev, nlh, tb, skb, 0); } -static int dcbnl_pgrx_getcfg(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_pgrx_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - return __dcbnl_pg_getcfg(netdev, tb, pid, seq, flags, 1); + return __dcbnl_pg_getcfg(netdev, nlh, tb, skb, 1); } -static int dcbnl_setstate(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_setstate(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - int ret = -EINVAL; u8 value; - if (!tb[DCB_ATTR_STATE] || !netdev->dcbnl_ops->setstate) - return ret; + if (!tb[DCB_ATTR_STATE]) + return -EINVAL; - value = nla_get_u8(tb[DCB_ATTR_STATE]); + if (!netdev->dcbnl_ops->setstate) + return -EOPNOTSUPP; - ret = dcbnl_reply(netdev->dcbnl_ops->setstate(netdev, value), - RTM_SETDCB, DCB_CMD_SSTATE, DCB_ATTR_STATE, - pid, seq, flags); + value = nla_get_u8(tb[DCB_ATTR_STATE]); - return ret; + return nla_put_u8(skb, DCB_ATTR_STATE, + netdev->dcbnl_ops->setstate(netdev, value)); } -static int dcbnl_setpfccfg(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_setpfccfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_PFC_UP_ATTR_MAX + 1]; int i; - int ret = -EINVAL; + int ret; u8 value; - if (!tb[DCB_ATTR_PFC_CFG] || !netdev->dcbnl_ops->setpfccfg) - return ret; + if (!tb[DCB_ATTR_PFC_CFG]) + return -EINVAL; + + if (!netdev->dcbnl_ops->setpfccfg) + return -EOPNOTSUPP; ret = nla_parse_nested(data, DCB_PFC_UP_ATTR_MAX, tb[DCB_ATTR_PFC_CFG], dcbnl_pfc_up_nest); if (ret) - goto err; + return ret; for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) { if (data[i] == NULL) @@ -921,50 +743,53 @@ static int dcbnl_setpfccfg(struct net_device *netdev, struct nlattr **tb, data[i]->nla_type - DCB_PFC_UP_ATTR_0, value); } - ret = dcbnl_reply(0, RTM_SETDCB, DCB_CMD_PFC_SCFG, DCB_ATTR_PFC_CFG, - pid, seq, flags); -err: - return ret; + return nla_put_u8(skb, DCB_ATTR_PFC_CFG, 0); } -static int dcbnl_setall(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_setall(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - int ret = -EINVAL; + int ret; - if (!tb[DCB_ATTR_SET_ALL] || !netdev->dcbnl_ops->setall) - return ret; + if (!tb[DCB_ATTR_SET_ALL]) + return -EINVAL; + + if (!netdev->dcbnl_ops->setall) + return -EOPNOTSUPP; - ret = dcbnl_reply(netdev->dcbnl_ops->setall(netdev), RTM_SETDCB, - DCB_CMD_SET_ALL, DCB_ATTR_SET_ALL, pid, seq, flags); + ret = nla_put_u8(skb, DCB_ATTR_SET_ALL, + netdev->dcbnl_ops->setall(netdev)); dcbnl_cee_notify(netdev, RTM_SETDCB, DCB_CMD_SET_ALL, seq, 0); return ret; } -static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags, int dir) +static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb, + int dir) { struct nlattr *pg_tb[DCB_PG_ATTR_MAX + 1]; struct nlattr *param_tb[DCB_TC_ATTR_PARAM_MAX + 1]; - int ret = -EINVAL; + int ret; int i; u8 pgid; u8 up_map; u8 prio; u8 tc_pct; - if (!tb[DCB_ATTR_PG_CFG] || - !netdev->dcbnl_ops->setpgtccfgtx || + if (!tb[DCB_ATTR_PG_CFG]) + return -EINVAL; + + if (!netdev->dcbnl_ops->setpgtccfgtx || !netdev->dcbnl_ops->setpgtccfgrx || !netdev->dcbnl_ops->setpgbwgcfgtx || !netdev->dcbnl_ops->setpgbwgcfgrx) - return ret; + return -EOPNOTSUPP; ret = nla_parse_nested(pg_tb, DCB_PG_ATTR_MAX, tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest); if (ret) - goto err; + return ret; for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) { if (!pg_tb[i]) @@ -973,7 +798,7 @@ static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlattr **tb, ret = nla_parse_nested(param_tb, DCB_TC_ATTR_PARAM_MAX, pg_tb[i], dcbnl_tc_param_nest); if (ret) - goto err; + return ret; pgid = DCB_ATTR_VALUE_UNDEFINED; prio = DCB_ATTR_VALUE_UNDEFINED; @@ -1026,63 +851,47 @@ static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlattr **tb, } } - ret = dcbnl_reply(0, RTM_SETDCB, - (dir ? DCB_CMD_PGRX_SCFG : DCB_CMD_PGTX_SCFG), - DCB_ATTR_PG_CFG, pid, seq, flags); - -err: - return ret; + return nla_put_u8(skb, DCB_ATTR_PG_CFG, 0); } -static int dcbnl_pgtx_setcfg(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_pgtx_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - return __dcbnl_pg_setcfg(netdev, tb, pid, seq, flags, 0); + return __dcbnl_pg_setcfg(netdev, nlh, seq, tb, skb, 0); } -static int dcbnl_pgrx_setcfg(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_pgrx_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - return __dcbnl_pg_setcfg(netdev, tb, pid, seq, flags, 1); + return __dcbnl_pg_setcfg(netdev, nlh, seq, tb, skb, 1); } -static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - struct sk_buff *dcbnl_skb; - struct nlmsghdr *nlh; - struct dcbmsg *dcb; struct nlattr *bcn_nest; struct nlattr *bcn_tb[DCB_BCN_ATTR_MAX + 1]; u8 value_byte; u32 value_integer; - int ret = -EINVAL; + int ret; bool getall = false; int i; - if (!tb[DCB_ATTR_BCN] || !netdev->dcbnl_ops->getbcnrp || + if (!tb[DCB_ATTR_BCN]) + return -EINVAL; + + if (!netdev->dcbnl_ops->getbcnrp || !netdev->dcbnl_ops->getbcncfg) - return ret; + return -EOPNOTSUPP; ret = nla_parse_nested(bcn_tb, DCB_BCN_ATTR_MAX, tb[DCB_ATTR_BCN], dcbnl_bcn_nest); - if (ret) - goto err_out; - - dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!dcbnl_skb) - goto err_out; - - nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); - - dcb = NLMSG_DATA(nlh); - dcb->dcb_family = AF_UNSPEC; - dcb->cmd = DCB_CMD_BCN_GCFG; + return ret; - bcn_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_BCN); + bcn_nest = nla_nest_start(skb, DCB_ATTR_BCN); if (!bcn_nest) - goto err; + return -EMSGSIZE; if (bcn_tb[DCB_BCN_ATTR_ALL]) getall = true; @@ -1093,7 +902,7 @@ static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlattr **tb, netdev->dcbnl_ops->getbcnrp(netdev, i - DCB_BCN_ATTR_RP_0, &value_byte); - ret = nla_put_u8(dcbnl_skb, i, value_byte); + ret = nla_put_u8(skb, i, value_byte); if (ret) goto err_bcn; } @@ -1104,49 +913,41 @@ static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlattr **tb, netdev->dcbnl_ops->getbcncfg(netdev, i, &value_integer); - ret = nla_put_u32(dcbnl_skb, i, value_integer); + ret = nla_put_u32(skb, i, value_integer); if (ret) goto err_bcn; } - nla_nest_end(dcbnl_skb, bcn_nest); - - nlmsg_end(dcbnl_skb, nlh); - - ret = rtnl_unicast(dcbnl_skb, &init_net, pid); - if (ret) - goto err_out; + nla_nest_end(skb, bcn_nest); return 0; err_bcn: - nla_nest_cancel(dcbnl_skb, bcn_nest); -nlmsg_failure: -err: - kfree_skb(dcbnl_skb); -err_out: - ret = -EINVAL; + nla_nest_cancel(skb, bcn_nest); return ret; } -static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_BCN_ATTR_MAX + 1]; int i; - int ret = -EINVAL; + int ret; u8 value_byte; u32 value_int; - if (!tb[DCB_ATTR_BCN] || !netdev->dcbnl_ops->setbcncfg || + if (!tb[DCB_ATTR_BCN]) + return -EINVAL; + + if (!netdev->dcbnl_ops->setbcncfg || !netdev->dcbnl_ops->setbcnrp) - return ret; + return -EOPNOTSUPP; ret = nla_parse_nested(data, DCB_BCN_ATTR_MAX, tb[DCB_ATTR_BCN], dcbnl_pfc_up_nest); if (ret) - goto err; + return ret; for (i = DCB_BCN_ATTR_RP_0; i <= DCB_BCN_ATTR_RP_7; i++) { if (data[i] == NULL) @@ -1164,10 +965,7 @@ static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlattr **tb, i, value_int); } - ret = dcbnl_reply(0, RTM_SETDCB, DCB_CMD_BCN_SCFG, DCB_ATTR_BCN, - pid, seq, flags); -err: - return ret; + return nla_put_u8(skb, DCB_ATTR_BCN, 0); } static int dcbnl_build_peer_app(struct net_device *netdev, struct sk_buff* skb, @@ -1233,20 +1031,21 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) struct dcb_app_type *itr; const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; int dcbx; - int err = -EMSGSIZE; + int err; if (nla_put_string(skb, DCB_ATTR_IFNAME, netdev->name)) - goto nla_put_failure; + return -EMSGSIZE; + ieee = nla_nest_start(skb, DCB_ATTR_IEEE); if (!ieee) - goto nla_put_failure; + return -EMSGSIZE; if (ops->ieee_getets) { struct ieee_ets ets; err = ops->ieee_getets(netdev, &ets); if (!err && nla_put(skb, DCB_ATTR_IEEE_ETS, sizeof(ets), &ets)) - goto nla_put_failure; + return -EMSGSIZE; } if (ops->ieee_getmaxrate) { @@ -1256,7 +1055,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) err = nla_put(skb, DCB_ATTR_IEEE_MAXRATE, sizeof(maxrate), &maxrate); if (err) - goto nla_put_failure; + return -EMSGSIZE; } } @@ -1265,12 +1064,12 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) err = ops->ieee_getpfc(netdev, &pfc); if (!err && nla_put(skb, DCB_ATTR_IEEE_PFC, sizeof(pfc), &pfc)) - goto nla_put_failure; + return -EMSGSIZE; } app = nla_nest_start(skb, DCB_ATTR_IEEE_APP_TABLE); if (!app) - goto nla_put_failure; + return -EMSGSIZE; spin_lock(&dcb_lock); list_for_each_entry(itr, &dcb_app_list, list) { @@ -1279,7 +1078,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) &itr->app); if (err) { spin_unlock(&dcb_lock); - goto nla_put_failure; + return -EMSGSIZE; } } } @@ -1298,7 +1097,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) err = ops->ieee_peer_getets(netdev, &ets); if (!err && nla_put(skb, DCB_ATTR_IEEE_PEER_ETS, sizeof(ets), &ets)) - goto nla_put_failure; + return -EMSGSIZE; } if (ops->ieee_peer_getpfc) { @@ -1306,7 +1105,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) err = ops->ieee_peer_getpfc(netdev, &pfc); if (!err && nla_put(skb, DCB_ATTR_IEEE_PEER_PFC, sizeof(pfc), &pfc)) - goto nla_put_failure; + return -EMSGSIZE; } if (ops->peer_getappinfo && ops->peer_getapptable) { @@ -1315,20 +1114,17 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) DCB_ATTR_IEEE_APP_UNSPEC, DCB_ATTR_IEEE_APP); if (err) - goto nla_put_failure; + return -EMSGSIZE; } nla_nest_end(skb, ieee); if (dcbx >= 0) { err = nla_put_u8(skb, DCB_ATTR_DCBX, dcbx); if (err) - goto nla_put_failure; + return -EMSGSIZE; } return 0; - -nla_put_failure: - return err; } static int dcbnl_cee_pg_fill(struct sk_buff *skb, struct net_device *dev, @@ -1340,13 +1136,13 @@ static int dcbnl_cee_pg_fill(struct sk_buff *skb, struct net_device *dev, struct nlattr *pg = nla_nest_start(skb, i); if (!pg) - goto nla_put_failure; + return -EMSGSIZE; for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) { struct nlattr *tc_nest = nla_nest_start(skb, i); if (!tc_nest) - goto nla_put_failure; + return -EMSGSIZE; pgid = DCB_ATTR_VALUE_UNDEFINED; prio = DCB_ATTR_VALUE_UNDEFINED; @@ -1364,7 +1160,7 @@ static int dcbnl_cee_pg_fill(struct sk_buff *skb, struct net_device *dev, nla_put_u8(skb, DCB_TC_ATTR_PARAM_UP_MAPPING, up_map) || nla_put_u8(skb, DCB_TC_ATTR_PARAM_STRICT_PRIO, prio) || nla_put_u8(skb, DCB_TC_ATTR_PARAM_BW_PCT, tc_pct)) - goto nla_put_failure; + return -EMSGSIZE; nla_nest_end(skb, tc_nest); } @@ -1378,13 +1174,10 @@ static int dcbnl_cee_pg_fill(struct sk_buff *skb, struct net_device *dev, ops->getpgbwgcfgtx(dev, i - DCB_PG_ATTR_BW_ID_0, &tc_pct); if (nla_put_u8(skb, i, tc_pct)) - goto nla_put_failure; + return -EMSGSIZE; } nla_nest_end(skb, pg); return 0; - -nla_put_failure: - return -EMSGSIZE; } static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) @@ -1531,27 +1324,16 @@ static int dcbnl_notify(struct net_device *dev, int event, int cmd, struct net *net = dev_net(dev); struct sk_buff *skb; struct nlmsghdr *nlh; - struct dcbmsg *dcb; const struct dcbnl_rtnl_ops *ops = dev->dcbnl_ops; int err; if (!ops) return -EOPNOTSUPP; - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + skb = dcbnl_newmsg(event, cmd, pid, seq, 0, &nlh); if (!skb) return -ENOBUFS; - nlh = nlmsg_put(skb, pid, 0, event, sizeof(*dcb), 0); - if (nlh == NULL) { - nlmsg_free(skb); - return -EMSGSIZE; - } - - dcb = NLMSG_DATA(nlh); - dcb->dcb_family = AF_UNSPEC; - dcb->cmd = cmd; - if (dcbx_ver == DCB_CAP_DCBX_VER_IEEE) err = dcbnl_ieee_fill(skb, dev); else @@ -1559,8 +1341,7 @@ static int dcbnl_notify(struct net_device *dev, int event, int cmd, if (err < 0) { /* Report error to broadcast listeners */ - nlmsg_cancel(skb, nlh); - kfree_skb(skb); + nlmsg_free(skb); rtnl_set_sk_err(net, RTNLGRP_DCB, err); } else { /* End nlmsg and notify broadcast listeners */ @@ -1590,15 +1371,15 @@ EXPORT_SYMBOL(dcbnl_cee_notify); * No attempt is made to reconcile the case where only part of the * cmd can be completed. */ -static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1]; - int err = -EOPNOTSUPP; + int err; if (!ops) - return err; + return -EOPNOTSUPP; if (!tb[DCB_ATTR_IEEE]) return -EINVAL; @@ -1649,58 +1430,28 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb, } err: - dcbnl_reply(err, RTM_SETDCB, DCB_CMD_IEEE_SET, DCB_ATTR_IEEE, - pid, seq, flags); + err = nla_put_u8(skb, DCB_ATTR_IEEE, err); dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_SET, seq, 0); return err; } -static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_ieee_get(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - struct net *net = dev_net(netdev); - struct sk_buff *skb; - struct nlmsghdr *nlh; - struct dcbmsg *dcb; const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; - int err; if (!ops) return -EOPNOTSUPP; - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!skb) - return -ENOBUFS; - - nlh = nlmsg_put(skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); - if (nlh == NULL) { - nlmsg_free(skb); - return -EMSGSIZE; - } - - dcb = NLMSG_DATA(nlh); - dcb->dcb_family = AF_UNSPEC; - dcb->cmd = DCB_CMD_IEEE_GET; - - err = dcbnl_ieee_fill(skb, netdev); - - if (err < 0) { - nlmsg_cancel(skb, nlh); - kfree_skb(skb); - } else { - nlmsg_end(skb, nlh); - err = rtnl_unicast(skb, net, pid); - } - - return err; + return dcbnl_ieee_fill(skb, netdev); } -static int dcbnl_ieee_del(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_ieee_del(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1]; - int err = -EOPNOTSUPP; + int err; if (!ops) return -EOPNOTSUPP; @@ -1733,32 +1484,26 @@ static int dcbnl_ieee_del(struct net_device *netdev, struct nlattr **tb, } err: - dcbnl_reply(err, RTM_SETDCB, DCB_CMD_IEEE_DEL, DCB_ATTR_IEEE, - pid, seq, flags); + err = nla_put_u8(skb, DCB_ATTR_IEEE, err); dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_DEL, seq, 0); return err; } /* DCBX configuration */ -static int dcbnl_getdcbx(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_getdcbx(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - int ret; - if (!netdev->dcbnl_ops->getdcbx) return -EOPNOTSUPP; - ret = dcbnl_reply(netdev->dcbnl_ops->getdcbx(netdev), RTM_GETDCB, - DCB_CMD_GDCBX, DCB_ATTR_DCBX, pid, seq, flags); - - return ret; + return nla_put_u8(skb, DCB_ATTR_DCBX, + netdev->dcbnl_ops->getdcbx(netdev)); } -static int dcbnl_setdcbx(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_setdcbx(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - int ret; u8 value; if (!netdev->dcbnl_ops->setdcbx) @@ -1769,19 +1514,13 @@ static int dcbnl_setdcbx(struct net_device *netdev, struct nlattr **tb, value = nla_get_u8(tb[DCB_ATTR_DCBX]); - ret = dcbnl_reply(netdev->dcbnl_ops->setdcbx(netdev, value), - RTM_SETDCB, DCB_CMD_SDCBX, DCB_ATTR_DCBX, - pid, seq, flags); - - return ret; + return nla_put_u8(skb, DCB_ATTR_DCBX, + netdev->dcbnl_ops->setdcbx(netdev, value)); } -static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - struct sk_buff *dcbnl_skb; - struct nlmsghdr *nlh; - struct dcbmsg *dcb; struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1], *nest; u8 value; int ret, i; @@ -1796,25 +1535,11 @@ static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlattr **tb, ret = nla_parse_nested(data, DCB_FEATCFG_ATTR_MAX, tb[DCB_ATTR_FEATCFG], dcbnl_featcfg_nest); if (ret) - goto err_out; - - dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!dcbnl_skb) { - ret = -ENOBUFS; - goto err_out; - } - - nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); - - dcb = NLMSG_DATA(nlh); - dcb->dcb_family = AF_UNSPEC; - dcb->cmd = DCB_CMD_GFEATCFG; + return ret; - nest = nla_nest_start(dcbnl_skb, DCB_ATTR_FEATCFG); - if (!nest) { - ret = -EMSGSIZE; - goto nla_put_failure; - } + nest = nla_nest_start(skb, DCB_ATTR_FEATCFG); + if (!nest) + return -EMSGSIZE; if (data[DCB_FEATCFG_ATTR_ALL]) getall = 1; @@ -1825,28 +1550,21 @@ static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlattr **tb, ret = netdev->dcbnl_ops->getfeatcfg(netdev, i, &value); if (!ret) - ret = nla_put_u8(dcbnl_skb, i, value); + ret = nla_put_u8(skb, i, value); if (ret) { - nla_nest_cancel(dcbnl_skb, nest); + nla_nest_cancel(skb, nest); goto nla_put_failure; } } - nla_nest_end(dcbnl_skb, nest); + nla_nest_end(skb, nest); - nlmsg_end(dcbnl_skb, nlh); - - return rtnl_unicast(dcbnl_skb, &init_net, pid); nla_put_failure: - nlmsg_cancel(dcbnl_skb, nlh); -nlmsg_failure: - kfree_skb(dcbnl_skb); -err_out: return ret; } -static int dcbnl_setfeatcfg(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_setfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1]; int ret, i; @@ -1876,60 +1594,73 @@ static int dcbnl_setfeatcfg(struct net_device *netdev, struct nlattr **tb, goto err; } err: - dcbnl_reply(ret, RTM_SETDCB, DCB_CMD_SFEATCFG, DCB_ATTR_FEATCFG, - pid, seq, flags); + ret = nla_put_u8(skb, DCB_ATTR_FEATCFG, ret); return ret; } /* Handle CEE DCBX GET commands. */ -static int dcbnl_cee_get(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_cee_get(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) { - struct net *net = dev_net(netdev); - struct sk_buff *skb; - struct nlmsghdr *nlh; - struct dcbmsg *dcb; const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; - int err; if (!ops) return -EOPNOTSUPP; - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!skb) - return -ENOBUFS; - - nlh = nlmsg_put(skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); - if (nlh == NULL) { - nlmsg_free(skb); - return -EMSGSIZE; - } + return dcbnl_cee_fill(skb, netdev); +} - dcb = NLMSG_DATA(nlh); - dcb->dcb_family = AF_UNSPEC; - dcb->cmd = DCB_CMD_CEE_GET; +struct reply_func { + /* reply netlink message type */ + int type; - err = dcbnl_cee_fill(skb, netdev); + /* function to fill message contents */ + int (*cb)(struct net_device *, struct nlmsghdr *, u32, + struct nlattr **, struct sk_buff *); +}; - if (err < 0) { - nlmsg_cancel(skb, nlh); - nlmsg_free(skb); - } else { - nlmsg_end(skb, nlh); - err = rtnl_unicast(skb, net, pid); - } - return err; -} +static const struct reply_func reply_funcs[DCB_CMD_MAX+1] = { + [DCB_CMD_GSTATE] = { RTM_GETDCB, dcbnl_getstate }, + [DCB_CMD_SSTATE] = { RTM_SETDCB, dcbnl_setstate }, + [DCB_CMD_PFC_GCFG] = { RTM_GETDCB, dcbnl_getpfccfg }, + [DCB_CMD_PFC_SCFG] = { RTM_SETDCB, dcbnl_setpfccfg }, + [DCB_CMD_GPERM_HWADDR] = { RTM_GETDCB, dcbnl_getperm_hwaddr }, + [DCB_CMD_GCAP] = { RTM_GETDCB, dcbnl_getcap }, + [DCB_CMD_GNUMTCS] = { RTM_GETDCB, dcbnl_getnumtcs }, + [DCB_CMD_SNUMTCS] = { RTM_SETDCB, dcbnl_setnumtcs }, + [DCB_CMD_PFC_GSTATE] = { RTM_GETDCB, dcbnl_getpfcstate }, + [DCB_CMD_PFC_SSTATE] = { RTM_SETDCB, dcbnl_setpfcstate }, + [DCB_CMD_GAPP] = { RTM_GETDCB, dcbnl_getapp }, + [DCB_CMD_SAPP] = { RTM_SETDCB, dcbnl_setapp }, + [DCB_CMD_PGTX_GCFG] = { RTM_GETDCB, dcbnl_pgtx_getcfg }, + [DCB_CMD_PGTX_SCFG] = { RTM_SETDCB, dcbnl_pgtx_setcfg }, + [DCB_CMD_PGRX_GCFG] = { RTM_GETDCB, dcbnl_pgrx_getcfg }, + [DCB_CMD_PGRX_SCFG] = { RTM_SETDCB, dcbnl_pgrx_setcfg }, + [DCB_CMD_SET_ALL] = { RTM_SETDCB, dcbnl_setall }, + [DCB_CMD_BCN_GCFG] = { RTM_GETDCB, dcbnl_bcn_getcfg }, + [DCB_CMD_BCN_SCFG] = { RTM_SETDCB, dcbnl_bcn_setcfg }, + [DCB_CMD_IEEE_GET] = { RTM_GETDCB, dcbnl_ieee_get }, + [DCB_CMD_IEEE_SET] = { RTM_SETDCB, dcbnl_ieee_set }, + [DCB_CMD_IEEE_DEL] = { RTM_SETDCB, dcbnl_ieee_del }, + [DCB_CMD_GDCBX] = { RTM_GETDCB, dcbnl_getdcbx }, + [DCB_CMD_SDCBX] = { RTM_SETDCB, dcbnl_setdcbx }, + [DCB_CMD_GFEATCFG] = { RTM_GETDCB, dcbnl_getfeatcfg }, + [DCB_CMD_SFEATCFG] = { RTM_SETDCB, dcbnl_setfeatcfg }, + [DCB_CMD_CEE_GET] = { RTM_GETDCB, dcbnl_cee_get }, +}; static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); struct net_device *netdev; - struct dcbmsg *dcb = (struct dcbmsg *)NLMSG_DATA(nlh); + struct dcbmsg *dcb = nlmsg_data(nlh); struct nlattr *tb[DCB_ATTR_MAX + 1]; u32 pid = skb ? NETLINK_CB(skb).pid : 0; int ret = -EINVAL; + struct sk_buff *reply_skb; + struct nlmsghdr *reply_nlh = NULL; + const struct reply_func *fn; if (!net_eq(net, &init_net)) return -EINVAL; @@ -1939,136 +1670,78 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (ret < 0) return ret; + if (dcb->cmd > DCB_CMD_MAX) + return -EINVAL; + + /* check if a reply function has been defined for the command */ + fn = &reply_funcs[dcb->cmd]; + if (!fn->cb) + return -EOPNOTSUPP; + if (!tb[DCB_ATTR_IFNAME]) return -EINVAL; netdev = dev_get_by_name(&init_net, nla_data(tb[DCB_ATTR_IFNAME])); if (!netdev) - return -EINVAL; + return -ENODEV; - if (!netdev->dcbnl_ops) - goto errout; - - switch (dcb->cmd) { - case DCB_CMD_GSTATE: - ret = dcbnl_getstate(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_PFC_GCFG: - ret = dcbnl_getpfccfg(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_GPERM_HWADDR: - ret = dcbnl_getperm_hwaddr(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_PGTX_GCFG: - ret = dcbnl_pgtx_getcfg(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_PGRX_GCFG: - ret = dcbnl_pgrx_getcfg(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_BCN_GCFG: - ret = dcbnl_bcn_getcfg(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_SSTATE: - ret = dcbnl_setstate(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_PFC_SCFG: - ret = dcbnl_setpfccfg(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); + if (!netdev->dcbnl_ops) { + ret = -EOPNOTSUPP; goto out; + } - case DCB_CMD_SET_ALL: - ret = dcbnl_setall(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_PGTX_SCFG: - ret = dcbnl_pgtx_setcfg(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_PGRX_SCFG: - ret = dcbnl_pgrx_setcfg(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_GCAP: - ret = dcbnl_getcap(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_GNUMTCS: - ret = dcbnl_getnumtcs(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_SNUMTCS: - ret = dcbnl_setnumtcs(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_PFC_GSTATE: - ret = dcbnl_getpfcstate(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_PFC_SSTATE: - ret = dcbnl_setpfcstate(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_BCN_SCFG: - ret = dcbnl_bcn_setcfg(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_GAPP: - ret = dcbnl_getapp(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_SAPP: - ret = dcbnl_setapp(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_IEEE_SET: - ret = dcbnl_ieee_set(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_IEEE_GET: - ret = dcbnl_ieee_get(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_IEEE_DEL: - ret = dcbnl_ieee_del(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_GDCBX: - ret = dcbnl_getdcbx(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_SDCBX: - ret = dcbnl_setdcbx(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_GFEATCFG: - ret = dcbnl_getfeatcfg(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); - goto out; - case DCB_CMD_SFEATCFG: - ret = dcbnl_setfeatcfg(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); + reply_skb = dcbnl_newmsg(fn->type, dcb->cmd, pid, nlh->nlmsg_seq, + nlh->nlmsg_flags, &reply_nlh); + if (!reply_skb) { + ret = -ENOBUFS; goto out; - case DCB_CMD_CEE_GET: - ret = dcbnl_cee_get(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); + } + + ret = fn->cb(netdev, nlh, nlh->nlmsg_seq, tb, reply_skb); + if (ret < 0) { + nlmsg_free(reply_skb); goto out; - default: - goto errout; } -errout: - ret = -EINVAL; + + nlmsg_end(reply_skb, reply_nlh); + + ret = rtnl_unicast(reply_skb, &init_net, pid); out: dev_put(netdev); return ret; } +static struct dcb_app_type *dcb_app_lookup(const struct dcb_app *app, + int ifindex, int prio) +{ + struct dcb_app_type *itr; + + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->app.selector == app->selector && + itr->app.protocol == app->protocol && + itr->ifindex == ifindex && + (!prio || itr->app.priority == prio)) + return itr; + } + + return NULL; +} + +static int dcb_app_add(const struct dcb_app *app, int ifindex) +{ + struct dcb_app_type *entry; + + entry = kmalloc(sizeof(*entry), GFP_ATOMIC); + if (!entry) + return -ENOMEM; + + memcpy(&entry->app, app, sizeof(*app)); + entry->ifindex = ifindex; + list_add(&entry->list, &dcb_app_list); + + return 0; +} + /** * dcb_getapp - retrieve the DCBX application user priority * @@ -2082,14 +1755,8 @@ u8 dcb_getapp(struct net_device *dev, struct dcb_app *app) u8 prio = 0; spin_lock(&dcb_lock); - list_for_each_entry(itr, &dcb_app_list, list) { - if (itr->app.selector == app->selector && - itr->app.protocol == app->protocol && - itr->ifindex == dev->ifindex) { - prio = itr->app.priority; - break; - } - } + if ((itr = dcb_app_lookup(app, dev->ifindex, 0))) + prio = itr->app.priority; spin_unlock(&dcb_lock); return prio; @@ -2107,6 +1774,7 @@ int dcb_setapp(struct net_device *dev, struct dcb_app *new) { struct dcb_app_type *itr; struct dcb_app_type event; + int err = 0; event.ifindex = dev->ifindex; memcpy(&event.app, new, sizeof(event.app)); @@ -2115,36 +1783,23 @@ int dcb_setapp(struct net_device *dev, struct dcb_app *new) spin_lock(&dcb_lock); /* Search for existing match and replace */ - list_for_each_entry(itr, &dcb_app_list, list) { - if (itr->app.selector == new->selector && - itr->app.protocol == new->protocol && - itr->ifindex == dev->ifindex) { - if (new->priority) - itr->app.priority = new->priority; - else { - list_del(&itr->list); - kfree(itr); - } - goto out; + if ((itr = dcb_app_lookup(new, dev->ifindex, 0))) { + if (new->priority) + itr->app.priority = new->priority; + else { + list_del(&itr->list); + kfree(itr); } + goto out; } /* App type does not exist add new application type */ - if (new->priority) { - struct dcb_app_type *entry; - entry = kmalloc(sizeof(struct dcb_app_type), GFP_ATOMIC); - if (!entry) { - spin_unlock(&dcb_lock); - return -ENOMEM; - } - - memcpy(&entry->app, new, sizeof(*new)); - entry->ifindex = dev->ifindex; - list_add(&entry->list, &dcb_app_list); - } + if (new->priority) + err = dcb_app_add(new, dev->ifindex); out: spin_unlock(&dcb_lock); - call_dcbevent_notifiers(DCB_APP_EVENT, &event); - return 0; + if (!err) + call_dcbevent_notifiers(DCB_APP_EVENT, &event); + return err; } EXPORT_SYMBOL(dcb_setapp); @@ -2161,13 +1816,8 @@ u8 dcb_ieee_getapp_mask(struct net_device *dev, struct dcb_app *app) u8 prio = 0; spin_lock(&dcb_lock); - list_for_each_entry(itr, &dcb_app_list, list) { - if (itr->app.selector == app->selector && - itr->app.protocol == app->protocol && - itr->ifindex == dev->ifindex) { - prio |= 1 << itr->app.priority; - } - } + if ((itr = dcb_app_lookup(app, dev->ifindex, 0))) + prio |= 1 << itr->app.priority; spin_unlock(&dcb_lock); return prio; @@ -2183,7 +1833,6 @@ EXPORT_SYMBOL(dcb_ieee_getapp_mask); */ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new) { - struct dcb_app_type *itr, *entry; struct dcb_app_type event; int err = 0; @@ -2194,26 +1843,12 @@ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new) spin_lock(&dcb_lock); /* Search for existing match and abort if found */ - list_for_each_entry(itr, &dcb_app_list, list) { - if (itr->app.selector == new->selector && - itr->app.protocol == new->protocol && - itr->app.priority == new->priority && - itr->ifindex == dev->ifindex) { - err = -EEXIST; - goto out; - } - } - - /* App entry does not exist add new entry */ - entry = kmalloc(sizeof(struct dcb_app_type), GFP_ATOMIC); - if (!entry) { - err = -ENOMEM; + if (dcb_app_lookup(new, dev->ifindex, new->priority)) { + err = -EEXIST; goto out; } - memcpy(&entry->app, new, sizeof(*new)); - entry->ifindex = dev->ifindex; - list_add(&entry->list, &dcb_app_list); + err = dcb_app_add(new, dev->ifindex); out: spin_unlock(&dcb_lock); if (!err) @@ -2240,19 +1875,12 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del) spin_lock(&dcb_lock); /* Search for existing match and remove it. */ - list_for_each_entry(itr, &dcb_app_list, list) { - if (itr->app.selector == del->selector && - itr->app.protocol == del->protocol && - itr->app.priority == del->priority && - itr->ifindex == dev->ifindex) { - list_del(&itr->list); - kfree(itr); - err = 0; - goto out; - } + if ((itr = dcb_app_lookup(del, dev->ifindex, del->priority))) { + list_del(&itr->list); + kfree(itr); + err = 0; } -out: spin_unlock(&dcb_lock); if (!err) call_dcbevent_notifiers(DCB_APP_EVENT, &event); diff --git a/net/dccp/ackvec.h b/net/dccp/ackvec.h index e2ab0627a5f..a269aa7f792 100644 --- a/net/dccp/ackvec.h +++ b/net/dccp/ackvec.h @@ -50,7 +50,8 @@ static inline u8 dccp_ackvec_state(const u8 *cell) return *cell & ~DCCPAV_MAX_RUNLEN; } -/** struct dccp_ackvec - Ack Vector main data structure +/** + * struct dccp_ackvec - Ack Vector main data structure * * This implements a fixed-size circular buffer within an array and is largely * based on Appendix A of RFC 4340. @@ -76,7 +77,8 @@ struct dccp_ackvec { struct list_head av_records; }; -/** struct dccp_ackvec_record - Records information about sent Ack Vectors +/** + * struct dccp_ackvec_record - Records information about sent Ack Vectors * * These list entries define the additional information which the HC-Receiver * keeps about recently-sent Ack Vectors; again refer to RFC 4340, Appendix A. @@ -121,6 +123,7 @@ static inline bool dccp_ackvec_is_empty(const struct dccp_ackvec *av) * @len: length of @vec * @nonce: whether @vec had an ECN nonce of 0 or 1 * @node: FIFO - arranged in descending order of ack_ackno + * * This structure is used by CCIDs to access Ack Vectors in a received skb. */ struct dccp_ackvec_parsed { diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c index 48b585a5cba..597557254dd 100644 --- a/net/dccp/ccid.c +++ b/net/dccp/ccid.c @@ -46,6 +46,7 @@ bool ccid_support_check(u8 const *ccid_array, u8 array_len) * ccid_get_builtin_ccids - Populate a list of built-in CCIDs * @ccid_array: pointer to copy into * @array_len: value to return length into + * * This function allocates memory - caller must see that it is freed after use. */ int ccid_get_builtin_ccids(u8 **ccid_array, u8 *array_len) diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 75c3582a767..fb85d371a8d 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -246,7 +246,7 @@ static inline int ccid_hc_rx_getsockopt(struct ccid *ccid, struct sock *sk, u32 __user *optval, int __user *optlen) { int rc = -ENOPROTOOPT; - if (ccid->ccid_ops->ccid_hc_rx_getsockopt != NULL) + if (ccid != NULL && ccid->ccid_ops->ccid_hc_rx_getsockopt != NULL) rc = ccid->ccid_ops->ccid_hc_rx_getsockopt(sk, optname, len, optval, optlen); return rc; @@ -257,7 +257,7 @@ static inline int ccid_hc_tx_getsockopt(struct ccid *ccid, struct sock *sk, u32 __user *optval, int __user *optlen) { int rc = -ENOPROTOOPT; - if (ccid->ccid_ops->ccid_hc_tx_getsockopt != NULL) + if (ccid != NULL && ccid->ccid_ops->ccid_hc_tx_getsockopt != NULL) rc = ccid->ccid_ops->ccid_hc_tx_getsockopt(sk, optname, len, optval, optlen); return rc; diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 8c67bedf85b..119c04317d4 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -113,6 +113,7 @@ static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hc, ktime_t now) /** * ccid3_hc_tx_update_x - Update allowed sending rate X * @stamp: most recent time if available - can be left NULL. + * * This function tracks draft rfc3448bis, check there for latest details. * * Note: X and X_recv are both stored in units of 64 * bytes/second, to support @@ -161,9 +162,11 @@ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp) } } -/* - * Track the mean packet size `s' (cf. RFC 4342, 5.3 and RFC 3448, 4.1) +/** + * ccid3_hc_tx_update_s - Track the mean packet size `s' * @len: DCCP packet payload size in bytes + * + * cf. RFC 4342, 5.3 and RFC 3448, 4.1 */ static inline void ccid3_hc_tx_update_s(struct ccid3_hc_tx_sock *hc, int len) { @@ -270,6 +273,7 @@ out: /** * ccid3_hc_tx_send_packet - Delay-based dequeueing of TX packets * @skb: next packet candidate to send on @sk + * * This function uses the convention of ccid_packet_dequeue_eval() and * returns a millisecond-delay value between 0 and t_mbi = 64000 msec. */ @@ -531,6 +535,7 @@ static int ccid3_hc_tx_getsockopt(struct sock *sk, const int optname, int len, case DCCP_SOCKOPT_CCID_TX_INFO: if (len < sizeof(tfrc)) return -EINVAL; + memset(&tfrc, 0, sizeof(tfrc)); tfrc.tfrctx_x = hc->tx_x; tfrc.tfrctx_x_recv = hc->tx_x_recv; tfrc.tfrctx_x_calc = hc->tx_x_calc; diff --git a/net/dccp/ccids/lib/loss_interval.c b/net/dccp/ccids/lib/loss_interval.c index 497723c4d4b..57f9fd78c4d 100644 --- a/net/dccp/ccids/lib/loss_interval.c +++ b/net/dccp/ccids/lib/loss_interval.c @@ -133,6 +133,7 @@ static inline u8 tfrc_lh_is_new_loss(struct tfrc_loss_interval *cur, * @rh: Receive history containing a fresh loss event * @calc_first_li: Caller-dependent routine to compute length of first interval * @sk: Used by @calc_first_li in caller-specific way (subtyping) + * * Updates I_mean and returns 1 if a new interval has in fact been added to @lh. */ int tfrc_lh_interval_add(struct tfrc_loss_hist *lh, struct tfrc_rx_hist *rh, diff --git a/net/dccp/ccids/lib/packet_history.c b/net/dccp/ccids/lib/packet_history.c index de8fe294bf0..08df7a3acb3 100644 --- a/net/dccp/ccids/lib/packet_history.c +++ b/net/dccp/ccids/lib/packet_history.c @@ -315,6 +315,7 @@ static void __three_after_loss(struct tfrc_rx_hist *h) * @ndp: The NDP count belonging to @skb * @calc_first_li: Caller-dependent computation of first loss interval in @lh * @sk: Used by @calc_first_li (see tfrc_lh_interval_add) + * * Chooses action according to pending loss, updates LI database when a new * loss was detected, and does required post-processing. Returns 1 when caller * should send feedback, 0 otherwise. @@ -387,7 +388,7 @@ static inline struct tfrc_rx_hist_entry * } /** - * tfrc_rx_hist_rtt_prev_s: previously suitable (wrt rtt_last_s) RTT-sampling entry + * tfrc_rx_hist_rtt_prev_s - previously suitable (wrt rtt_last_s) RTT-sampling entry */ static inline struct tfrc_rx_hist_entry * tfrc_rx_hist_rtt_prev_s(const struct tfrc_rx_hist *h) diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c index a052a4377e2..88ef98285be 100644 --- a/net/dccp/ccids/lib/tfrc_equation.c +++ b/net/dccp/ccids/lib/tfrc_equation.c @@ -611,6 +611,7 @@ static inline u32 tfrc_binsearch(u32 fval, u8 small) * @s: packet size in bytes * @R: RTT scaled by 1000000 (i.e., microseconds) * @p: loss ratio estimate scaled by 1000000 + * * Returns X_calc in bytes per second (not scaled). */ u32 tfrc_calc_x(u16 s, u32 R, u32 p) @@ -659,6 +660,7 @@ u32 tfrc_calc_x(u16 s, u32 R, u32 p) /** * tfrc_calc_x_reverse_lookup - try to find p given f(p) * @fvalue: function value to match, scaled by 1000000 + * * Returns closest match for p, also scaled by 1000000 */ u32 tfrc_calc_x_reverse_lookup(u32 fvalue) diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 9040be049d8..708e75bf623 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -352,6 +352,7 @@ static inline int dccp_bad_service_code(const struct sock *sk, * @dccpd_opt_len: total length of all options (5.8) in the packet * @dccpd_seq: sequence number * @dccpd_ack_seq: acknowledgment number subheader field value + * * This is used for transmission as well as for reception. */ struct dccp_skb_cb { diff --git a/net/dccp/feat.c b/net/dccp/feat.c index 78a2ad70e1b..9733ddbc96c 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -350,6 +350,7 @@ static int __dccp_feat_activate(struct sock *sk, const int idx, * @feat_num: feature to activate, one of %dccp_feature_numbers * @local: whether local (1) or remote (0) @feat_num is meant * @fval: the value (SP or NN) to activate, or NULL to use the default value + * * For general use this function is preferable over __dccp_feat_activate(). */ static int dccp_feat_activate(struct sock *sk, u8 feat_num, bool local, @@ -446,6 +447,7 @@ static struct dccp_feat_entry *dccp_feat_list_lookup(struct list_head *fn_list, * @head: list to add to * @feat: feature number * @local: whether the local (1) or remote feature with number @feat is meant + * * This is the only constructor and serves to ensure the above invariants. */ static struct dccp_feat_entry * @@ -504,6 +506,7 @@ static int dccp_feat_push_change(struct list_head *fn_list, u8 feat, u8 local, * @feat: one of %dccp_feature_numbers * @local: whether local (1) or remote (0) @feat_num is being confirmed * @fval: pointer to NN/SP value to be inserted or NULL + * * Returns 0 on success, a Reset code for further processing otherwise. */ static int dccp_feat_push_confirm(struct list_head *fn_list, u8 feat, u8 local, @@ -691,6 +694,7 @@ int dccp_feat_insert_opts(struct dccp_sock *dp, struct dccp_request_sock *dreq, * @feat: an NN feature from %dccp_feature_numbers * @mandatory: use Mandatory option if 1 * @nn_val: value to register (restricted to 4 bytes) + * * Note that NN features are local by definition (RFC 4340, 6.3.2). */ static int __feat_register_nn(struct list_head *fn, u8 feat, @@ -760,6 +764,7 @@ int dccp_feat_register_sp(struct sock *sk, u8 feat, u8 is_local, * dccp_feat_nn_get - Query current/pending value of NN feature * @sk: DCCP socket of an established connection * @feat: NN feature number from %dccp_feature_numbers + * * For a known NN feature, returns value currently being negotiated, or * current (confirmed) value if no negotiation is going on. */ @@ -790,6 +795,7 @@ EXPORT_SYMBOL_GPL(dccp_feat_nn_get); * @sk: DCCP socket of an established connection * @feat: NN feature number from %dccp_feature_numbers * @nn_val: the new value to use + * * This function is used to communicate NN updates out-of-band. */ int dccp_feat_signal_nn_change(struct sock *sk, u8 feat, u64 nn_val) @@ -930,6 +936,7 @@ static const struct ccid_dependency *dccp_feat_ccid_deps(u8 ccid, bool is_local) * @fn: feature-negotiation list to update * @id: CCID number to track * @is_local: whether TX CCID (1) or RX CCID (0) is meant + * * This function needs to be called after registering all other features. */ static int dccp_feat_propagate_ccid(struct list_head *fn, u8 id, bool is_local) @@ -953,6 +960,7 @@ static int dccp_feat_propagate_ccid(struct list_head *fn, u8 id, bool is_local) /** * dccp_feat_finalise_settings - Finalise settings before starting negotiation * @dp: client or listening socket (settings will be inherited) + * * This is called after all registrations (socket initialisation, sysctls, and * sockopt calls), and before sending the first packet containing Change options * (ie. client-Request or server-Response), to ensure internal consistency. @@ -1284,6 +1292,7 @@ confirmation_failed: * @feat: NN number, one of %dccp_feature_numbers * @val: NN value * @len: length of @val in bytes + * * This function combines the functionality of change_recv/confirm_recv, with * the following differences (reset codes are the same): * - cleanup after receiving the Confirm; @@ -1379,6 +1388,7 @@ fast_path_failed: * @feat: one of %dccp_feature_numbers * @val: value contents of @opt * @len: length of @val in bytes + * * Returns 0 on success, a Reset code for ending the connection otherwise. */ int dccp_feat_parse_options(struct sock *sk, struct dccp_request_sock *dreq, diff --git a/net/dccp/input.c b/net/dccp/input.c index bc93a333931..14cdafad7a9 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -710,6 +710,7 @@ EXPORT_SYMBOL_GPL(dccp_rcv_state_process); /** * dccp_sample_rtt - Validate and finalise computation of RTT sample * @delta: number of microseconds between packet and acknowledgment + * * The routine is kept generic to work in different contexts. It should be * called immediately when the ACK used for the RTT sample arrives. */ diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 07f5579ca75..176ecdba4a2 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -161,17 +161,10 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk, if (sk->sk_state == DCCP_LISTEN) return; - /* We don't check in the destentry if pmtu discovery is forbidden - * on this route. We just assume that no packet_to_big packets - * are send back when pmtu discovery is not active. - * There is a small race when the user changes this flag in the - * route, but I think that's acceptable. - */ - if ((dst = __sk_dst_check(sk, 0)) == NULL) + dst = inet_csk_update_pmtu(sk, mtu); + if (!dst) return; - dst->ops->update_pmtu(dst, mtu); - /* Something is about to be wrong... Remember soft error * for the case, if this connection will not able to recover. */ @@ -195,6 +188,14 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk, } /* else let the usual retransmit timer handle it */ } +static void dccp_do_redirect(struct sk_buff *skb, struct sock *sk) +{ + struct dst_entry *dst = __sk_dst_check(sk, 0); + + if (dst) + dst->ops->redirect(dst, sk, skb); +} + /* * This routine is called by the ICMP module when it gets some sort of error * condition. If err < 0 then the socket should be closed and the error @@ -259,6 +260,9 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) } switch (type) { + case ICMP_REDIRECT: + dccp_do_redirect(skb, sk); + goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ goto out; @@ -477,7 +481,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, struct rtable *rt; const struct iphdr *iph = ip_hdr(skb); struct flowi4 fl4 = { - .flowi4_oif = skb_rtable(skb)->rt_iif, + .flowi4_oif = inet_iif(skb), .daddr = iph->saddr, .saddr = iph->daddr, .flowi4_tos = RT_CONN_FLAGS(sk), diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index fa9512d86f3..56840b249f3 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -130,6 +130,13 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); + if (type == NDISC_REDIRECT) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); + + if (dst) + dst->ops->redirect(dst, sk, skb); + } + if (type == ICMPV6_PKT_TOOBIG) { struct dst_entry *dst = NULL; @@ -138,37 +145,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED)) goto out; - /* icmp should have updated the destination cache entry */ - dst = __sk_dst_check(sk, np->dst_cookie); - if (dst == NULL) { - struct inet_sock *inet = inet_sk(sk); - struct flowi6 fl6; - - /* BUGGG_FUTURE: Again, it is not clear how - to handle rthdr case. Ignore this complexity - for now. - */ - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_DCCP; - fl6.daddr = np->daddr; - fl6.saddr = np->saddr; - fl6.flowi6_oif = sk->sk_bound_dev_if; - fl6.fl6_dport = inet->inet_dport; - fl6.fl6_sport = inet->inet_sport; - security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - - dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false); - if (IS_ERR(dst)) { - sk->sk_err_soft = -PTR_ERR(dst); - goto out; - } - } else - dst_hold(dst); + dst = inet6_csk_update_pmtu(sk, ntohl(info)); + if (!dst) + goto out; - if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { + if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) dccp_sync_mss(sk, dst_mtu(dst)); - } /* else let the usual retransmit timer handle it */ - dst_release(dst); goto out; } @@ -237,7 +219,6 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, struct inet6_request_sock *ireq6 = inet6_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; - struct ipv6_txoptions *opt = NULL; struct in6_addr *final_p, final; struct flowi6 fl6; int err = -1; @@ -253,9 +234,8 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, fl6.fl6_sport = inet_rsk(req)->loc_port; security_req_classify_flow(req, flowi6_to_flowi(&fl6)); - opt = np->opt; - final_p = fl6_update_dst(&fl6, opt, &final); + final_p = fl6_update_dst(&fl6, np->opt, &final); dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); if (IS_ERR(dst)) { @@ -272,13 +252,11 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, &ireq6->loc_addr, &ireq6->rmt_addr); fl6.daddr = ireq6->rmt_addr; - err = ip6_xmit(sk, skb, &fl6, opt, np->tclass); + err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); err = net_xmit_eval(err); } done: - if (opt != NULL && opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); dst_release(dst); return err; } @@ -473,7 +451,6 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, struct inet_sock *newinet; struct dccp6_sock *newdp6; struct sock *newsk; - struct ipv6_txoptions *opt; if (skb->protocol == htons(ETH_P_IP)) { /* @@ -518,7 +495,6 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, return newsk; } - opt = np->opt; if (sk_acceptq_is_full(sk)) goto out_overflow; @@ -530,7 +506,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_DCCP; fl6.daddr = ireq6->rmt_addr; - final_p = fl6_update_dst(&fl6, opt, &final); + final_p = fl6_update_dst(&fl6, np->opt, &final); fl6.saddr = ireq6->loc_addr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.fl6_dport = inet_rsk(req)->rmt_port; @@ -595,11 +571,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, * Yes, keeping reference count would be much more clever, but we make * one more one thing there: reattach optmem to newsk. */ - if (opt != NULL) { - newnp->opt = ipv6_dup_options(newsk, opt); - if (opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); - } + if (np->opt != NULL) + newnp->opt = ipv6_dup_options(newsk, np->opt); inet_csk(newsk)->icsk_ext_hdr_len = 0; if (newnp->opt != NULL) @@ -625,8 +598,6 @@ out_nonewsk: dst_release(dst); out: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); - if (opt != NULL && opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); return NULL; } diff --git a/net/dccp/options.c b/net/dccp/options.c index 68fa6b7a3e0..a58e0b63405 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -527,6 +527,7 @@ int dccp_insert_option_mandatory(struct sk_buff *skb) * @val: NN value or SP array (preferred element first) to copy * @len: true length of @val in bytes (excluding first element repetition) * @repeat_first: whether to copy the first element of @val twice + * * The last argument is used to construct Confirm options, where the preferred * value and the preference list appear separately (RFC 4340, 6.3.1). Preference * lists are kept such that the preferred entry is always first, so we only need diff --git a/net/dccp/output.c b/net/dccp/output.c index 78736730879..d17fc90a74b 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -214,6 +214,7 @@ void dccp_write_space(struct sock *sk) * dccp_wait_for_ccid - Await CCID send permission * @sk: socket to wait for * @delay: timeout in jiffies + * * This is used by CCIDs which need to delay the send time in process context. */ static int dccp_wait_for_ccid(struct sock *sk, unsigned long delay) diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 7eaf9879972..102d6106a94 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -505,6 +505,14 @@ static int dn_fib_check_attr(struct rtmsg *r, struct rtattr **rta) return 0; } +static inline u32 rtm_get_table(struct rtattr **rta, u8 table) +{ + if (rta[RTA_TABLE - 1]) + table = nla_get_u32((struct nlattr *) rta[RTA_TABLE - 1]); + + return table; +} + static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index ac90f658586..3aede1b459f 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -202,7 +202,7 @@ static int dn_neigh_output_packet(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct dn_route *rt = (struct dn_route *)dst; - struct neighbour *neigh = dst_get_neighbour_noref(dst); + struct neighbour *neigh = rt->n; struct net_device *dev = neigh->dev; char mac_addr[ETH_ALEN]; unsigned int seq; @@ -240,7 +240,7 @@ static int dn_long_output(struct neighbour *neigh, struct sk_buff *skb) kfree_skb(skb); return -ENOBUFS; } - kfree_skb(skb); + consume_skb(skb); skb = skb2; net_info_ratelimited("dn_long_output: Increasing headroom\n"); } @@ -283,7 +283,7 @@ static int dn_short_output(struct neighbour *neigh, struct sk_buff *skb) kfree_skb(skb); return -ENOBUFS; } - kfree_skb(skb); + consume_skb(skb); skb = skb2; net_info_ratelimited("dn_short_output: Increasing headroom\n"); } @@ -322,7 +322,7 @@ static int dn_phase3_output(struct neighbour *neigh, struct sk_buff *skb) kfree_skb(skb); return -ENOBUFS; } - kfree_skb(skb); + consume_skb(skb); skb = skb2; net_info_ratelimited("dn_phase3_output: Increasing headroom\n"); } diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index 564a6ad13ce..8a96047c7c9 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -322,7 +322,7 @@ static __le16 *dn_mk_ack_header(struct sock *sk, struct sk_buff *skb, unsigned c /* Set "cross subchannel" bit in ackcrs */ ackcrs |= 0x2000; - ptr = (__le16 *)dn_mk_common_header(scp, skb, msgflag, hlen); + ptr = dn_mk_common_header(scp, skb, msgflag, hlen); *ptr++ = cpu_to_le16(acknum); *ptr++ = cpu_to_le16(ackcrs); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 586302e557a..85a3604c87c 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -114,10 +114,16 @@ static struct dst_entry *dn_dst_check(struct dst_entry *, __u32); static unsigned int dn_dst_default_advmss(const struct dst_entry *dst); static unsigned int dn_dst_mtu(const struct dst_entry *dst); static void dn_dst_destroy(struct dst_entry *); +static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); static void dn_dst_link_failure(struct sk_buff *); -static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu); -static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, const void *daddr); +static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb , u32 mtu); +static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb); +static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr); static int dn_route_input(struct sk_buff *); static void dn_run_flush(unsigned long dummy); @@ -138,17 +144,37 @@ static struct dst_ops dn_dst_ops = { .mtu = dn_dst_mtu, .cow_metrics = dst_cow_metrics_generic, .destroy = dn_dst_destroy, + .ifdown = dn_dst_ifdown, .negative_advice = dn_dst_negative_advice, .link_failure = dn_dst_link_failure, .update_pmtu = dn_dst_update_pmtu, + .redirect = dn_dst_redirect, .neigh_lookup = dn_dst_neigh_lookup, }; static void dn_dst_destroy(struct dst_entry *dst) { + struct dn_route *rt = (struct dn_route *) dst; + + if (rt->n) + neigh_release(rt->n); dst_destroy_metrics_generic(dst); } +static void dn_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int how) +{ + if (how) { + struct dn_route *rt = (struct dn_route *) dst; + struct neighbour *n = rt->n; + + if (n && n->dev == dev) { + n->dev = dev_net(dev)->loopback_dev; + dev_hold(n->dev); + dev_put(dev); + } + } +} + static __inline__ unsigned int dn_hash(__le16 src, __le16 dst) { __u16 tmp = (__u16 __force)(src ^ dst); @@ -242,9 +268,11 @@ static int dn_dst_gc(struct dst_ops *ops) * We update both the mtu and the advertised mss (i.e. the segment size we * advertise to the other end). */ -static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu) +static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { - struct neighbour *n = dst_get_neighbour_noref(dst); + struct dn_route *rt = (struct dn_route *) dst; + struct neighbour *n = rt->n; u32 min_mtu = 230; struct dn_dev *dn; @@ -269,6 +297,11 @@ static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu) } } +static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) +{ +} + /* * When a route has been marked obsolete. (e.g. routing cache flush) */ @@ -713,7 +746,8 @@ out: static int dn_to_neigh_output(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - struct neighbour *n = dst_get_neighbour_noref(dst); + struct dn_route *rt = (struct dn_route *) dst; + struct neighbour *n = rt->n; return n->output(n, skb); } @@ -727,7 +761,7 @@ static int dn_output(struct sk_buff *skb) int err = -EINVAL; - if (dst_get_neighbour_noref(dst) == NULL) + if (rt->n == NULL) goto error; skb->dev = dev; @@ -828,7 +862,9 @@ static unsigned int dn_dst_mtu(const struct dst_entry *dst) return mtu ? : dst->dev->mtu; } -static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, const void *daddr) +static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) { return __neigh_lookup_errno(&dn_neigh_table, daddr, dst->dev); } @@ -848,11 +884,11 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) } rt->rt_type = res->type; - if (dev != NULL && dst_get_neighbour_noref(&rt->dst) == NULL) { + if (dev != NULL && rt->n == NULL) { n = __neigh_lookup_errno(&dn_neigh_table, &rt->rt_gateway, dev); if (IS_ERR(n)) return PTR_ERR(n); - dst_set_neighbour(&rt->dst, n); + rt->n = n; } if (dst_metric(&rt->dst, RTAX_MTU) > rt->dst.dev->mtu) @@ -1140,7 +1176,7 @@ make_route: if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; - rt = dst_alloc(&dn_dst_ops, dev_out, 1, 0, DST_HOST); + rt = dst_alloc(&dn_dst_ops, dev_out, 1, DST_OBSOLETE_NONE, DST_HOST); if (rt == NULL) goto e_nobufs; @@ -1159,7 +1195,7 @@ make_route: rt->rt_dst_map = fld.daddr; rt->rt_src_map = fld.saddr; - dst_set_neighbour(&rt->dst, neigh); + rt->n = neigh; neigh = NULL; rt->dst.lastuse = jiffies; @@ -1388,7 +1424,6 @@ static int dn_route_input_slow(struct sk_buff *skb) /* Packet was intra-ethernet, so we know its on-link */ if (cb->rt_flags & DN_RT_F_IE) { gateway = cb->src; - flags |= RTCF_DIRECTSRC; goto make_route; } @@ -1401,14 +1436,13 @@ static int dn_route_input_slow(struct sk_buff *skb) /* Close eyes and pray */ gateway = cb->src; - flags |= RTCF_DIRECTSRC; goto make_route; default: goto e_inval; } make_route: - rt = dst_alloc(&dn_dst_ops, out_dev, 0, 0, DST_HOST); + rt = dst_alloc(&dn_dst_ops, out_dev, 0, DST_OBSOLETE_NONE, DST_HOST); if (rt == NULL) goto e_nobufs; @@ -1429,7 +1463,7 @@ make_route: rt->fld.flowidn_iif = in_dev->ifindex; rt->fld.flowidn_mark = fld.flowidn_mark; - dst_set_neighbour(&rt->dst, neigh); + rt->n = neigh; rt->dst.lastuse = jiffies; rt->dst.output = dn_rt_bug; switch (res.type) { @@ -1515,54 +1549,68 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, struct dn_route *rt = (struct dn_route *)skb_dst(skb); struct rtmsg *r; struct nlmsghdr *nlh; - unsigned char *b = skb_tail_pointer(skb); long expires; - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*r), flags); - r = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags); + if (!nlh) + return -EMSGSIZE; + + r = nlmsg_data(nlh); r->rtm_family = AF_DECnet; r->rtm_dst_len = 16; r->rtm_src_len = 0; r->rtm_tos = 0; r->rtm_table = RT_TABLE_MAIN; - RTA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN); r->rtm_type = rt->rt_type; r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; r->rtm_scope = RT_SCOPE_UNIVERSE; r->rtm_protocol = RTPROT_UNSPEC; + if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; - RTA_PUT(skb, RTA_DST, 2, &rt->rt_daddr); + + if (nla_put_u32(skb, RTA_TABLE, RT_TABLE_MAIN) < 0 || + nla_put_le16(skb, RTA_DST, rt->rt_daddr) < 0) + goto errout; + if (rt->fld.saddr) { r->rtm_src_len = 16; - RTA_PUT(skb, RTA_SRC, 2, &rt->fld.saddr); + if (nla_put_le16(skb, RTA_SRC, rt->fld.saddr) < 0) + goto errout; } - if (rt->dst.dev) - RTA_PUT(skb, RTA_OIF, sizeof(int), &rt->dst.dev->ifindex); + if (rt->dst.dev && + nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex) < 0) + goto errout; + /* * Note to self - change this if input routes reverse direction when * they deal only with inputs and not with replies like they do * currently. */ - RTA_PUT(skb, RTA_PREFSRC, 2, &rt->rt_local_src); - if (rt->rt_daddr != rt->rt_gateway) - RTA_PUT(skb, RTA_GATEWAY, 2, &rt->rt_gateway); + if (nla_put_le16(skb, RTA_PREFSRC, rt->rt_local_src) < 0) + goto errout; + + if (rt->rt_daddr != rt->rt_gateway && + nla_put_le16(skb, RTA_GATEWAY, rt->rt_gateway) < 0) + goto errout; + if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) - goto rtattr_failure; + goto errout; + expires = rt->dst.expires ? rt->dst.expires - jiffies : 0; - if (rtnl_put_cacheinfo(skb, &rt->dst, 0, 0, 0, expires, + if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0) - goto rtattr_failure; - if (dn_is_input_route(rt)) - RTA_PUT(skb, RTA_IIF, sizeof(int), &rt->fld.flowidn_iif); + goto errout; - nlh->nlmsg_len = skb_tail_pointer(skb) - b; - return skb->len; + if (dn_is_input_route(rt) && + nla_put_u32(skb, RTA_IIF, rt->fld.flowidn_iif) < 0) + goto errout; -nlmsg_failure: -rtattr_failure: - nlmsg_trim(skb, b); - return -1; + return nlmsg_end(skb, nlh); + +errout: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; } /* @@ -1572,7 +1620,7 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void { struct net *net = sock_net(in_skb->sk); struct rtattr **rta = arg; - struct rtmsg *rtm = NLMSG_DATA(nlh); + struct rtmsg *rtm = nlmsg_data(nlh); struct dn_route *rt = NULL; struct dn_skb_cb *cb; int err; @@ -1585,7 +1633,7 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void memset(&fld, 0, sizeof(fld)); fld.flowidn_proto = DNPROTO_NSP; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb == NULL) return -ENOBUFS; skb_reset_mac_header(skb); @@ -1663,13 +1711,16 @@ int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb) struct dn_route *rt; int h, s_h; int idx, s_idx; + struct rtmsg *rtm; if (!net_eq(net, &init_net)) return 0; - if (NLMSG_PAYLOAD(cb->nlh, 0) < sizeof(struct rtmsg)) + if (nlmsg_len(cb->nlh) < sizeof(struct rtmsg)) return -EINVAL; - if (!(((struct rtmsg *)NLMSG_DATA(cb->nlh))->rtm_flags&RTM_F_CLONED)) + + rtm = nlmsg_data(cb->nlh); + if (!(rtm->rtm_flags & RTM_F_CLONED)) return 0; s_h = cb->args[0]; @@ -1769,12 +1820,11 @@ static int dn_rt_cache_seq_show(struct seq_file *seq, void *v) char buf1[DN_ASCBUF_LEN], buf2[DN_ASCBUF_LEN]; seq_printf(seq, "%-8s %-7s %-7s %04d %04d %04d\n", - rt->dst.dev ? rt->dst.dev->name : "*", - dn_addr2asc(le16_to_cpu(rt->rt_daddr), buf1), - dn_addr2asc(le16_to_cpu(rt->rt_saddr), buf2), - atomic_read(&rt->dst.__refcnt), - rt->dst.__use, - (int) dst_metric(&rt->dst, RTAX_RTT)); + rt->dst.dev ? rt->dst.dev->name : "*", + dn_addr2asc(le16_to_cpu(rt->rt_daddr), buf1), + dn_addr2asc(le16_to_cpu(rt->rt_saddr), buf2), + atomic_read(&rt->dst.__refcnt), + rt->dst.__use, 0); return 0; } diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index 650f3380c98..16c986ab122 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -297,61 +297,75 @@ static int dn_fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, { struct rtmsg *rtm; struct nlmsghdr *nlh; - unsigned char *b = skb_tail_pointer(skb); - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*rtm), flags); - rtm = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*rtm), flags); + if (!nlh) + return -EMSGSIZE; + + rtm = nlmsg_data(nlh); rtm->rtm_family = AF_DECnet; rtm->rtm_dst_len = dst_len; rtm->rtm_src_len = 0; rtm->rtm_tos = 0; rtm->rtm_table = tb_id; - RTA_PUT_U32(skb, RTA_TABLE, tb_id); rtm->rtm_flags = fi->fib_flags; rtm->rtm_scope = scope; rtm->rtm_type = type; - if (rtm->rtm_dst_len) - RTA_PUT(skb, RTA_DST, 2, dst); rtm->rtm_protocol = fi->fib_protocol; - if (fi->fib_priority) - RTA_PUT(skb, RTA_PRIORITY, 4, &fi->fib_priority); + + if (nla_put_u32(skb, RTA_TABLE, tb_id) < 0) + goto errout; + + if (rtm->rtm_dst_len && + nla_put(skb, RTA_DST, 2, dst) < 0) + goto errout; + + if (fi->fib_priority && + nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority) < 0) + goto errout; + if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0) - goto rtattr_failure; + goto errout; + if (fi->fib_nhs == 1) { - if (fi->fib_nh->nh_gw) - RTA_PUT(skb, RTA_GATEWAY, 2, &fi->fib_nh->nh_gw); - if (fi->fib_nh->nh_oif) - RTA_PUT(skb, RTA_OIF, sizeof(int), &fi->fib_nh->nh_oif); + if (fi->fib_nh->nh_gw && + nla_put_le16(skb, RTA_GATEWAY, fi->fib_nh->nh_gw) < 0) + goto errout; + + if (fi->fib_nh->nh_oif && + nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif) < 0) + goto errout; } + if (fi->fib_nhs > 1) { struct rtnexthop *nhp; - struct rtattr *mp_head; - if (skb_tailroom(skb) <= RTA_SPACE(0)) - goto rtattr_failure; - mp_head = (struct rtattr *)skb_put(skb, RTA_SPACE(0)); + struct nlattr *mp_head; + + if (!(mp_head = nla_nest_start(skb, RTA_MULTIPATH))) + goto errout; for_nexthops(fi) { - if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4)) - goto rtattr_failure; - nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp))); + if (!(nhp = nla_reserve_nohdr(skb, sizeof(*nhp)))) + goto errout; + nhp->rtnh_flags = nh->nh_flags & 0xFF; nhp->rtnh_hops = nh->nh_weight - 1; nhp->rtnh_ifindex = nh->nh_oif; - if (nh->nh_gw) - RTA_PUT(skb, RTA_GATEWAY, 2, &nh->nh_gw); + + if (nh->nh_gw && + nla_put_le16(skb, RTA_GATEWAY, nh->nh_gw) < 0) + goto errout; + nhp->rtnh_len = skb_tail_pointer(skb) - (unsigned char *)nhp; } endfor_nexthops(fi); - mp_head->rta_type = RTA_MULTIPATH; - mp_head->rta_len = skb_tail_pointer(skb) - (u8 *)mp_head; - } - nlh->nlmsg_len = skb_tail_pointer(skb) - b; - return skb->len; + nla_nest_end(skb, mp_head); + } + return nlmsg_end(skb, nlh); -nlmsg_failure: -rtattr_failure: - nlmsg_trim(skb, b); +errout: + nlmsg_cancel(skb, nlh); return -EMSGSIZE; } @@ -476,7 +490,7 @@ int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb) return 0; if (NLMSG_PAYLOAD(cb->nlh, 0) >= sizeof(struct rtmsg) && - ((struct rtmsg *)NLMSG_DATA(cb->nlh))->rtm_flags&RTM_F_CLONED) + ((struct rtmsg *)nlmsg_data(cb->nlh))->rtm_flags&RTM_F_CLONED) return dn_cache_dump(skb, cb); s_h = cb->args[0]; diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index 44b890936fc..11db0ecf342 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -42,23 +42,23 @@ static struct sk_buff *dnrmg_build_message(struct sk_buff *rt_skb, int *errp) size = NLMSG_SPACE(rt_skb->len); size += NLMSG_ALIGN(sizeof(struct nf_dn_rtmsg)); skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) - goto nlmsg_failure; + if (!skb) { + *errp = -ENOMEM; + return NULL; + } old_tail = skb->tail; - nlh = NLMSG_PUT(skb, 0, 0, 0, size - sizeof(*nlh)); + nlh = nlmsg_put(skb, 0, 0, 0, size - sizeof(*nlh), 0); + if (!nlh) { + kfree_skb(skb); + *errp = -ENOMEM; + return NULL; + } rtm = (struct nf_dn_rtmsg *)NLMSG_DATA(nlh); rtm->nfdn_ifindex = rt_skb->dev->ifindex; ptr = NFDN_RTMSG(rtm); skb_copy_from_linear_data(rt_skb, ptr, rt_skb->len); nlh->nlmsg_len = skb->tail - old_tail; return skb; - -nlmsg_failure: - if (skb) - kfree_skb(skb); - *errp = -ENOMEM; - net_err_ratelimited("dn_rtmsg: error creating netlink message\n"); - return NULL; } static void dnrmg_send_peer(struct sk_buff *skb) @@ -117,7 +117,7 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb) static struct nf_hook_ops dnrmg_ops __read_mostly = { .hook = dnrmg_hook, - .pf = PF_DECnet, + .pf = NFPROTO_DECNET, .hooknum = NF_DN_ROUTE, .priority = NF_DN_PRI_DNRTMSG, }; @@ -125,11 +125,13 @@ static struct nf_hook_ops dnrmg_ops __read_mostly = { static int __init dn_rtmsg_init(void) { int rv = 0; + struct netlink_kernel_cfg cfg = { + .groups = DNRNG_NLGRP_MAX, + .input = dnrmg_receive_user_skb, + }; dnrmg = netlink_kernel_create(&init_net, - NETLINK_DNRTMSG, DNRNG_NLGRP_MAX, - dnrmg_receive_user_skb, - NULL, THIS_MODULE); + NETLINK_DNRTMSG, THIS_MODULE, &cfg); if (dnrmg == NULL) { printk(KERN_ERR "dn_rtmsg: Cannot create netlink socket"); return -ENOMEM; diff --git a/net/ethernet/Makefile b/net/ethernet/Makefile index 7cef1d8ace2..32317750540 100644 --- a/net/ethernet/Makefile +++ b/net/ethernet/Makefile @@ -3,5 +3,3 @@ # obj-y += eth.o -obj-$(subst m,y,$(CONFIG_IPX)) += pe2.o -obj-$(subst m,y,$(CONFIG_ATALK)) += pe2.o diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 36e58800a9e..4efad533e5f 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -232,6 +232,7 @@ EXPORT_SYMBOL(eth_header_parse); * @neigh: source neighbour * @hh: destination cache entry * @type: Ethernet type field + * * Create an Ethernet header template from the neighbour. */ int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type) @@ -274,6 +275,7 @@ EXPORT_SYMBOL(eth_header_cache_update); * eth_mac_addr - set new Ethernet hardware address * @dev: network device * @p: socket address + * * Change hardware address of device. * * This doesn't change hardware matching, so needs to be overridden @@ -283,7 +285,7 @@ int eth_mac_addr(struct net_device *dev, void *p) { struct sockaddr *addr = p; - if (netif_running(dev)) + if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev)) return -EBUSY; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; @@ -331,6 +333,7 @@ const struct header_ops eth_header_ops ____cacheline_aligned = { /** * ether_setup - setup Ethernet network device * @dev: network device + * * Fill in the fields of the device structure with Ethernet-generic values. */ void ether_setup(struct net_device *dev) diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index 32eb4179e8f..6a095225148 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -55,7 +55,6 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/netdevice.h> -#include <linux/etherdevice.h> #include <net/af_ieee802154.h> #include <net/ieee802154.h> #include <net/ieee802154_netdev.h> @@ -114,7 +113,6 @@ struct lowpan_dev_record { struct lowpan_fragment { struct sk_buff *skb; /* skb to be assembled */ - spinlock_t lock; /* concurency lock */ u16 length; /* length to be assemled */ u32 bytes_rcv; /* bytes received */ u16 tag; /* current fragment tag */ @@ -124,7 +122,7 @@ struct lowpan_fragment { static unsigned short fragment_tag; static LIST_HEAD(lowpan_fragments); -spinlock_t flist_lock; +static DEFINE_SPINLOCK(flist_lock); static inline struct lowpan_dev_info *lowpan_dev_info(const struct net_device *dev) @@ -240,8 +238,7 @@ lowpan_uncompress_addr(struct sk_buff *skb, struct in6_addr *ipaddr, lowpan_uip_ds6_set_addr_iid(ipaddr, lladdr); } - pr_debug("(%s): uncompressing %d + %d => ", __func__, prefcount, - postcount); + pr_debug("uncompressing %d + %d => ", prefcount, postcount); lowpan_raw_dump_inline(NULL, NULL, ipaddr->s6_addr, 16); return 0; @@ -252,13 +249,11 @@ lowpan_compress_udp_header(u8 **hc06_ptr, struct sk_buff *skb) { struct udphdr *uh = udp_hdr(skb); - pr_debug("(%s): UDP header compression\n", __func__); - if (((uh->source & LOWPAN_NHC_UDP_4BIT_MASK) == LOWPAN_NHC_UDP_4BIT_PORT) && ((uh->dest & LOWPAN_NHC_UDP_4BIT_MASK) == LOWPAN_NHC_UDP_4BIT_PORT)) { - pr_debug("(%s): both ports compression to 4 bits\n", __func__); + pr_debug("UDP header: both ports compression to 4 bits\n"); **hc06_ptr = LOWPAN_NHC_UDP_CS_P_11; **(hc06_ptr + 1) = /* subtraction is faster */ (u8)((uh->dest - LOWPAN_NHC_UDP_4BIT_PORT) + @@ -266,20 +261,20 @@ lowpan_compress_udp_header(u8 **hc06_ptr, struct sk_buff *skb) *hc06_ptr += 2; } else if ((uh->dest & LOWPAN_NHC_UDP_8BIT_MASK) == LOWPAN_NHC_UDP_8BIT_PORT) { - pr_debug("(%s): remove 8 bits of dest\n", __func__); + pr_debug("UDP header: remove 8 bits of dest\n"); **hc06_ptr = LOWPAN_NHC_UDP_CS_P_01; memcpy(*hc06_ptr + 1, &uh->source, 2); **(hc06_ptr + 3) = (u8)(uh->dest - LOWPAN_NHC_UDP_8BIT_PORT); *hc06_ptr += 4; } else if ((uh->source & LOWPAN_NHC_UDP_8BIT_MASK) == LOWPAN_NHC_UDP_8BIT_PORT) { - pr_debug("(%s): remove 8 bits of source\n", __func__); + pr_debug("UDP header: remove 8 bits of source\n"); **hc06_ptr = LOWPAN_NHC_UDP_CS_P_10; memcpy(*hc06_ptr + 1, &uh->dest, 2); **(hc06_ptr + 3) = (u8)(uh->source - LOWPAN_NHC_UDP_8BIT_PORT); *hc06_ptr += 4; } else { - pr_debug("(%s): can't compress header\n", __func__); + pr_debug("UDP header: can't compress\n"); **hc06_ptr = LOWPAN_NHC_UDP_CS_P_00; memcpy(*hc06_ptr + 1, &uh->source, 2); memcpy(*hc06_ptr + 3, &uh->dest, 2); @@ -291,25 +286,26 @@ lowpan_compress_udp_header(u8 **hc06_ptr, struct sk_buff *skb) *hc06_ptr += 2; } -static u8 lowpan_fetch_skb_u8(struct sk_buff *skb) +static inline int lowpan_fetch_skb_u8(struct sk_buff *skb, u8 *val) { - u8 ret; + if (unlikely(!pskb_may_pull(skb, 1))) + return -EINVAL; - ret = skb->data[0]; + *val = skb->data[0]; skb_pull(skb, 1); - return ret; + return 0; } -static u16 lowpan_fetch_skb_u16(struct sk_buff *skb) +static inline int lowpan_fetch_skb_u16(struct sk_buff *skb, u16 *val) { - u16 ret; - - BUG_ON(!pskb_may_pull(skb, 2)); + if (unlikely(!pskb_may_pull(skb, 2))) + return -EINVAL; - ret = skb->data[0] | (skb->data[1] << 8); + *val = (skb->data[0] << 8) | skb->data[1]; skb_pull(skb, 2); - return ret; + + return 0; } static int @@ -318,10 +314,14 @@ lowpan_uncompress_udp_header(struct sk_buff *skb) struct udphdr *uh = udp_hdr(skb); u8 tmp; - tmp = lowpan_fetch_skb_u8(skb); + if (!uh) + goto err; + + if (lowpan_fetch_skb_u8(skb, &tmp)) + goto err; if ((tmp & LOWPAN_NHC_UDP_MASK) == LOWPAN_NHC_UDP_ID) { - pr_debug("(%s): UDP header uncompression\n", __func__); + pr_debug("UDP header uncompression\n"); switch (tmp & LOWPAN_NHC_UDP_CS_P_11) { case LOWPAN_NHC_UDP_CS_P_00: memcpy(&uh->source, &skb->data[0], 2); @@ -347,19 +347,19 @@ lowpan_uncompress_udp_header(struct sk_buff *skb) skb_pull(skb, 1); break; default: - pr_debug("(%s) ERROR: unknown UDP format\n", __func__); + pr_debug("ERROR: unknown UDP format\n"); goto err; break; } - pr_debug("(%s): uncompressed UDP ports: src = %d, dst = %d\n", - __func__, uh->source, uh->dest); + pr_debug("uncompressed UDP ports: src = %d, dst = %d\n", + uh->source, uh->dest); /* copy checksum */ memcpy(&uh->check, &skb->data[0], 2); skb_pull(skb, 2); } else { - pr_debug("(%s): ERROR: unsupported NH format\n", __func__); + pr_debug("ERROR: unsupported NH format\n"); goto err; } @@ -392,10 +392,9 @@ static int lowpan_header_create(struct sk_buff *skb, hdr = ipv6_hdr(skb); hc06_ptr = head + 2; - pr_debug("(%s): IPv6 header dump:\n\tversion = %d\n\tlength = %d\n" - "\tnexthdr = 0x%02x\n\thop_lim = %d\n", __func__, - hdr->version, ntohs(hdr->payload_len), hdr->nexthdr, - hdr->hop_limit); + pr_debug("IPv6 header dump:\n\tversion = %d\n\tlength = %d\n" + "\tnexthdr = 0x%02x\n\thop_lim = %d\n", hdr->version, + ntohs(hdr->payload_len), hdr->nexthdr, hdr->hop_limit); lowpan_raw_dump_table(__func__, "raw skb network header dump", skb_network_header(skb), sizeof(struct ipv6hdr)); @@ -490,28 +489,28 @@ static int lowpan_header_create(struct sk_buff *skb, break; default: *hc06_ptr = hdr->hop_limit; + hc06_ptr += 1; break; } /* source address compression */ if (is_addr_unspecified(&hdr->saddr)) { - pr_debug("(%s): source address is unspecified, setting SAC\n", - __func__); + pr_debug("source address is unspecified, setting SAC\n"); iphc1 |= LOWPAN_IPHC_SAC; /* TODO: context lookup */ } else if (is_addr_link_local(&hdr->saddr)) { - pr_debug("(%s): source address is link-local\n", __func__); + pr_debug("source address is link-local\n"); iphc1 |= lowpan_compress_addr_64(&hc06_ptr, LOWPAN_IPHC_SAM_BIT, &hdr->saddr, saddr); } else { - pr_debug("(%s): send the full source address\n", __func__); + pr_debug("send the full source address\n"); memcpy(hc06_ptr, &hdr->saddr.s6_addr16[0], 16); hc06_ptr += 16; } /* destination address compression */ if (is_addr_mcast(&hdr->daddr)) { - pr_debug("(%s): destination address is multicast", __func__); + pr_debug("destination address is multicast: "); iphc1 |= LOWPAN_IPHC_M; if (lowpan_is_mcast_addr_compressable8(&hdr->daddr)) { pr_debug("compressed to 1 octet\n"); @@ -540,14 +539,13 @@ static int lowpan_header_create(struct sk_buff *skb, hc06_ptr += 16; } } else { - pr_debug("(%s): destination address is unicast: ", __func__); /* TODO: context lookup */ if (is_addr_link_local(&hdr->daddr)) { - pr_debug("destination address is link-local\n"); + pr_debug("dest address is unicast and link-local\n"); iphc1 |= lowpan_compress_addr_64(&hc06_ptr, LOWPAN_IPHC_DAM_BIT, &hdr->daddr, daddr); } else { - pr_debug("using full address\n"); + pr_debug("dest address is unicast: using full one\n"); memcpy(hc06_ptr, &hdr->daddr.s6_addr16[0], 16); hc06_ptr += 16; } @@ -639,19 +637,15 @@ static void lowpan_fragment_timer_expired(unsigned long entry_addr) { struct lowpan_fragment *entry = (struct lowpan_fragment *)entry_addr; - pr_debug("%s: timer expired for frame with tag %d\n", __func__, - entry->tag); + pr_debug("timer expired for frame with tag %d\n", entry->tag); - spin_lock(&flist_lock); list_del(&entry->list); - spin_unlock(&flist_lock); - dev_kfree_skb(entry->skb); kfree(entry); } static struct lowpan_fragment * -lowpan_alloc_new_frame(struct sk_buff *skb, u8 iphc0, u8 len, u8 tag) +lowpan_alloc_new_frame(struct sk_buff *skb, u8 len, u16 tag) { struct lowpan_fragment *frame; @@ -662,12 +656,12 @@ lowpan_alloc_new_frame(struct sk_buff *skb, u8 iphc0, u8 len, u8 tag) INIT_LIST_HEAD(&frame->list); - frame->length = (iphc0 & 7) | (len << 3); + frame->length = len; frame->tag = tag; /* allocate buffer for frame assembling */ - frame->skb = alloc_skb(frame->length + - sizeof(struct ipv6hdr), GFP_ATOMIC); + frame->skb = netdev_alloc_skb_ip_align(skb->dev, frame->length + + sizeof(struct ipv6hdr)); if (!frame->skb) goto skb_err; @@ -710,7 +704,9 @@ lowpan_process_data(struct sk_buff *skb) /* at least two bytes will be used for the encoding */ if (skb->len < 2) goto drop; - iphc0 = lowpan_fetch_skb_u8(skb); + + if (lowpan_fetch_skb_u8(skb, &iphc0)) + goto drop; /* fragments assembling */ switch (iphc0 & LOWPAN_DISPATCH_MASK) { @@ -718,18 +714,23 @@ lowpan_process_data(struct sk_buff *skb) case LOWPAN_DISPATCH_FRAGN: { struct lowpan_fragment *frame; - u8 len, offset; - u16 tag; + /* slen stores the rightmost 8 bits of the 11 bits length */ + u8 slen, offset; + u16 len, tag; bool found = false; - len = lowpan_fetch_skb_u8(skb); /* frame length */ - tag = lowpan_fetch_skb_u16(skb); + if (lowpan_fetch_skb_u8(skb, &slen) || /* frame length */ + lowpan_fetch_skb_u16(skb, &tag)) /* fragment tag */ + goto drop; + + /* adds the 3 MSB to the 8 LSB to retrieve the 11 bits length */ + len = ((iphc0 & 7) << 8) | slen; /* * check if frame assembling with the same tag is * already in progress */ - spin_lock(&flist_lock); + spin_lock_bh(&flist_lock); list_for_each_entry(frame, &lowpan_fragments, list) if (frame->tag == tag) { @@ -739,7 +740,7 @@ lowpan_process_data(struct sk_buff *skb) /* alloc new frame structure */ if (!found) { - frame = lowpan_alloc_new_frame(skb, iphc0, len, tag); + frame = lowpan_alloc_new_frame(skb, len, tag); if (!frame) goto unlock_and_drop; } @@ -747,7 +748,8 @@ lowpan_process_data(struct sk_buff *skb) if ((iphc0 & LOWPAN_DISPATCH_MASK) == LOWPAN_DISPATCH_FRAG1) goto unlock_and_drop; - offset = lowpan_fetch_skb_u8(skb); /* fetch offset */ + if (lowpan_fetch_skb_u8(skb, &offset)) /* fetch offset */ + goto unlock_and_drop; /* if payload fits buffer, copy it */ if (likely((offset * 8 + skb->len) <= frame->length)) @@ -762,17 +764,20 @@ lowpan_process_data(struct sk_buff *skb) if ((frame->bytes_rcv == frame->length) && frame->timer.expires > jiffies) { /* if timer haven't expired - first of all delete it */ - del_timer(&frame->timer); + del_timer_sync(&frame->timer); list_del(&frame->list); - spin_unlock(&flist_lock); + spin_unlock_bh(&flist_lock); dev_kfree_skb(skb); skb = frame->skb; kfree(frame); - iphc0 = lowpan_fetch_skb_u8(skb); + + if (lowpan_fetch_skb_u8(skb, &iphc0)) + goto drop; + break; } - spin_unlock(&flist_lock); + spin_unlock_bh(&flist_lock); return kfree_skb(skb), 0; } @@ -780,20 +785,19 @@ lowpan_process_data(struct sk_buff *skb) break; } - iphc1 = lowpan_fetch_skb_u8(skb); + if (lowpan_fetch_skb_u8(skb, &iphc1)) + goto drop; _saddr = mac_cb(skb)->sa.hwaddr; _daddr = mac_cb(skb)->da.hwaddr; - pr_debug("(%s): iphc0 = %02x, iphc1 = %02x\n", __func__, iphc0, iphc1); + pr_debug("iphc0 = %02x, iphc1 = %02x\n", iphc0, iphc1); /* another if the CID flag is set */ if (iphc1 & LOWPAN_IPHC_CID) { - pr_debug("(%s): CID flag is set, increase header with one\n", - __func__); - if (!skb->len) + pr_debug("CID flag is set, increase header with one\n"); + if (lowpan_fetch_skb_u8(skb, &num_context)) goto drop; - num_context = lowpan_fetch_skb_u8(skb); } hdr.version = 6; @@ -805,9 +809,9 @@ lowpan_process_data(struct sk_buff *skb) * ECN + DSCP + 4-bit Pad + Flow Label (4 bytes) */ case 0: /* 00b */ - if (!skb->len) + if (lowpan_fetch_skb_u8(skb, &tmp)) goto drop; - tmp = lowpan_fetch_skb_u8(skb); + memcpy(&hdr.flow_lbl, &skb->data[0], 3); skb_pull(skb, 3); hdr.priority = ((tmp >> 2) & 0x0f); @@ -819,9 +823,9 @@ lowpan_process_data(struct sk_buff *skb) * ECN + DSCP (1 byte), Flow Label is elided */ case 1: /* 10b */ - if (!skb->len) + if (lowpan_fetch_skb_u8(skb, &tmp)) goto drop; - tmp = lowpan_fetch_skb_u8(skb); + hdr.priority = ((tmp >> 2) & 0x0f); hdr.flow_lbl[0] = ((tmp << 6) & 0xC0) | ((tmp >> 2) & 0x30); hdr.flow_lbl[1] = 0; @@ -832,9 +836,9 @@ lowpan_process_data(struct sk_buff *skb) * ECN + 2-bit Pad + Flow Label (3 bytes), DSCP is elided */ case 2: /* 01b */ - if (!skb->len) + if (lowpan_fetch_skb_u8(skb, &tmp)) goto drop; - tmp = lowpan_fetch_skb_u8(skb); + hdr.flow_lbl[0] = (skb->data[0] & 0x0F) | ((tmp >> 2) & 0x30); memcpy(&hdr.flow_lbl[1], &skb->data[0], 2); skb_pull(skb, 2); @@ -853,27 +857,26 @@ lowpan_process_data(struct sk_buff *skb) /* Next Header */ if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) { /* Next header is carried inline */ - if (!skb->len) + if (lowpan_fetch_skb_u8(skb, &(hdr.nexthdr))) goto drop; - hdr.nexthdr = lowpan_fetch_skb_u8(skb); - pr_debug("(%s): NH flag is set, next header is carried " - "inline: %02x\n", __func__, hdr.nexthdr); + + pr_debug("NH flag is set, next header carried inline: %02x\n", + hdr.nexthdr); } /* Hop Limit */ if ((iphc0 & 0x03) != LOWPAN_IPHC_TTL_I) hdr.hop_limit = lowpan_ttl_values[iphc0 & 0x03]; else { - if (!skb->len) + if (lowpan_fetch_skb_u8(skb, &(hdr.hop_limit))) goto drop; - hdr.hop_limit = lowpan_fetch_skb_u8(skb); } /* Extract SAM to the tmp variable */ tmp = ((iphc1 & LOWPAN_IPHC_SAM) >> LOWPAN_IPHC_SAM_BIT) & 0x03; /* Source address uncompression */ - pr_debug("(%s): source address stateless compression\n", __func__); + pr_debug("source address stateless compression\n"); err = lowpan_uncompress_addr(skb, &hdr.saddr, lowpan_llprefix, lowpan_unc_llconf[tmp], skb->data); if (err) @@ -885,19 +888,15 @@ lowpan_process_data(struct sk_buff *skb) /* check for Multicast Compression */ if (iphc1 & LOWPAN_IPHC_M) { if (iphc1 & LOWPAN_IPHC_DAC) { - pr_debug("(%s): destination address context-based " - "multicast compression\n", __func__); + pr_debug("dest: context-based mcast compression\n"); /* TODO: implement this */ } else { u8 prefix[] = {0xff, 0x02}; - pr_debug("(%s): destination address non-context-based" - " multicast compression\n", __func__); + pr_debug("dest: non context-based mcast compression\n"); if (0 < tmp && tmp < 3) { - if (!skb->len) + if (lowpan_fetch_skb_u8(skb, &prefix[1])) goto drop; - else - prefix[1] = lowpan_fetch_skb_u8(skb); } err = lowpan_uncompress_addr(skb, &hdr.daddr, prefix, @@ -906,8 +905,7 @@ lowpan_process_data(struct sk_buff *skb) goto drop; } } else { - pr_debug("(%s): destination address stateless compression\n", - __func__); + pr_debug("dest: stateless compression\n"); err = lowpan_uncompress_addr(skb, &hdr.daddr, lowpan_llprefix, lowpan_unc_llconf[tmp], skb->data); if (err) @@ -922,11 +920,11 @@ lowpan_process_data(struct sk_buff *skb) /* Not fragmented package */ hdr.payload_len = htons(skb->len); - pr_debug("(%s): skb headroom size = %d, data length = %d\n", __func__, - skb_headroom(skb), skb->len); + pr_debug("skb headroom size = %d, data length = %d\n", + skb_headroom(skb), skb->len); - pr_debug("(%s): IPv6 header dump:\n\tversion = %d\n\tlength = %d\n\t" - "nexthdr = 0x%02x\n\thop_lim = %d\n", __func__, hdr.version, + pr_debug("IPv6 header dump:\n\tversion = %d\n\tlength = %d\n\t" + "nexthdr = 0x%02x\n\thop_lim = %d\n", hdr.version, ntohs(hdr.payload_len), hdr.nexthdr, hdr.hop_limit); lowpan_raw_dump_table(__func__, "raw header dump", (u8 *)&hdr, @@ -934,12 +932,25 @@ lowpan_process_data(struct sk_buff *skb) return lowpan_skb_deliver(skb, &hdr); unlock_and_drop: - spin_unlock(&flist_lock); + spin_unlock_bh(&flist_lock); drop: kfree_skb(skb); return -EINVAL; } +static int lowpan_set_address(struct net_device *dev, void *p) +{ + struct sockaddr *sa = p; + + if (netif_running(dev)) + return -EBUSY; + + /* TODO: validate addr */ + memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + + return 0; +} + static int lowpan_get_mac_header_length(struct sk_buff *skb) { /* @@ -997,10 +1008,10 @@ lowpan_skb_fragmentation(struct sk_buff *skb) tag = fragment_tag++; /* first fragment header */ - head[0] = LOWPAN_DISPATCH_FRAG1 | (payload_length & 0x7); - head[1] = (payload_length >> 3) & 0xff; - head[2] = tag & 0xff; - head[3] = tag >> 8; + head[0] = LOWPAN_DISPATCH_FRAG1 | ((payload_length >> 8) & 0x7); + head[1] = payload_length & 0xff; + head[2] = tag >> 8; + head[3] = tag & 0xff; err = lowpan_fragment_xmit(skb, head, header_length, 0, 0); @@ -1028,11 +1039,11 @@ static netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev) { int err = -1; - pr_debug("(%s): package xmit\n", __func__); + pr_debug("package xmit\n"); skb->dev = lowpan_dev_info(dev)->real_dev; if (skb->dev == NULL) { - pr_debug("(%s) ERROR: no real wpan device found\n", __func__); + pr_debug("ERROR: no real wpan device found\n"); goto error; } @@ -1041,14 +1052,13 @@ static netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev) goto out; } - pr_debug("(%s): frame is too big, fragmentation is needed\n", - __func__); + pr_debug("frame is too big, fragmentation is needed\n"); err = lowpan_skb_fragmentation(skb); error: dev_kfree_skb(skb); out: if (err < 0) - pr_debug("(%s): ERROR: xmit failed\n", __func__); + pr_debug("ERROR: xmit failed\n"); return (err < 0 ? NETDEV_TX_BUSY : NETDEV_TX_OK); } @@ -1083,7 +1093,7 @@ static struct header_ops lowpan_header_ops = { static const struct net_device_ops lowpan_netdev_ops = { .ndo_start_xmit = lowpan_xmit, - .ndo_set_mac_address = eth_mac_addr, + .ndo_set_mac_address = lowpan_set_address, }; static struct ieee802154_mlme_ops lowpan_mlme = { @@ -1094,8 +1104,6 @@ static struct ieee802154_mlme_ops lowpan_mlme = { static void lowpan_setup(struct net_device *dev) { - pr_debug("(%s)\n", __func__); - dev->addr_len = IEEE802154_ADDR_LEN; memset(dev->broadcast, 0xff, IEEE802154_ADDR_LEN); dev->type = ARPHRD_IEEE802154; @@ -1115,8 +1123,6 @@ static void lowpan_setup(struct net_device *dev) static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[]) { - pr_debug("(%s)\n", __func__); - if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != IEEE802154_ADDR_LEN) return -EINVAL; @@ -1157,7 +1163,7 @@ static int lowpan_newlink(struct net *src_net, struct net_device *dev, struct net_device *real_dev; struct lowpan_dev_record *entry; - pr_debug("(%s)\n", __func__); + pr_debug("adding new link\n"); if (!tb[IFLA_LINK]) return -EINVAL; @@ -1183,8 +1189,6 @@ static int lowpan_newlink(struct net *src_net, struct net_device *dev, list_add_tail(&entry->list, &lowpan_devices); mutex_unlock(&lowpan_dev_info(dev)->dev_list_mtx); - spin_lock_init(&flist_lock); - register_netdevice(dev); return 0; @@ -1195,19 +1199,9 @@ static void lowpan_dellink(struct net_device *dev, struct list_head *head) struct lowpan_dev_info *lowpan_dev = lowpan_dev_info(dev); struct net_device *real_dev = lowpan_dev->real_dev; struct lowpan_dev_record *entry, *tmp; - struct lowpan_fragment *frame, *tframe; ASSERT_RTNL(); - spin_lock(&flist_lock); - list_for_each_entry_safe(frame, tframe, &lowpan_fragments, list) { - del_timer(&frame->timer); - list_del(&frame->list); - dev_kfree_skb(frame->skb); - kfree(frame); - } - spin_unlock(&flist_lock); - mutex_lock(&lowpan_dev_info(dev)->dev_list_mtx); list_for_each_entry_safe(entry, tmp, &lowpan_devices, list) { if (entry->ldev == dev) { @@ -1252,8 +1246,6 @@ static int __init lowpan_init_module(void) { int err = 0; - pr_debug("(%s)\n", __func__); - err = lowpan_netlink_init(); if (err < 0) goto out; @@ -1265,11 +1257,24 @@ out: static void __exit lowpan_cleanup_module(void) { - pr_debug("(%s)\n", __func__); + struct lowpan_fragment *frame, *tframe; lowpan_netlink_fini(); dev_remove_pack(&lowpan_packet_type); + + /* Now 6lowpan packet_type is removed, so no new fragments are + * expected on RX, therefore that's the time to clean incomplete + * fragments. + */ + spin_lock_bh(&flist_lock); + list_for_each_entry_safe(frame, tframe, &lowpan_fragments, list) { + del_timer_sync(&frame->timer); + list_del(&frame->list); + dev_kfree_skb(frame->skb); + kfree(frame); + } + spin_unlock_bh(&flist_lock); } module_init(lowpan_init_module); diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index c8097ae2482..97351e1d07a 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -44,7 +44,7 @@ struct genl_family nl802154_family = { struct sk_buff *ieee802154_nl_create(int flags, u8 req) { void *hdr; - struct sk_buff *msg = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); + struct sk_buff *msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); unsigned long f; if (!msg) @@ -80,7 +80,7 @@ struct sk_buff *ieee802154_nl_new_reply(struct genl_info *info, int flags, u8 req) { void *hdr; - struct sk_buff *msg = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); + struct sk_buff *msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return NULL; diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index ca92587720f..1e9917124e7 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -530,7 +530,7 @@ static int ieee802154_list_iface(struct sk_buff *skb, if (!dev) return -ENODEV; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) goto out_dev; diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index eed291626da..d54be34cca9 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -101,7 +101,7 @@ static int ieee802154_list_phy(struct sk_buff *skb, if (!phy) return -ENODEV; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) goto out_dev; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 20f1cb5c8ab..5a19aeb8609 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -310,6 +310,17 @@ config SYN_COOKIES If unsure, say N. +config NET_IPVTI + tristate "Virtual (secure) IP: tunneling" + select INET_TUNNEL + depends on INET_XFRM_MODE_TUNNEL + ---help--- + Tunneling means encapsulating data of one protocol type within + another protocol and sending it over a channel that understands the + encapsulating protocol. This can be used with xfrm mode tunnel to give + the notion of a secure tunnel for IPSEC and then use routing protocol + on top. + config INET_AH tristate "IP: AH transformation" select XFRM_ALGO diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index ff75d3bbcd6..15ca63ec604 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -7,7 +7,7 @@ obj-y := route.o inetpeer.o protocol.o \ ip_output.o ip_sockglue.o inet_hashtables.o \ inet_timewait_sock.o inet_connection_sock.o \ tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \ - tcp_minisocks.o tcp_cong.o \ + tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \ datagram.o raw.o udp.o udplite.o \ arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o \ @@ -20,6 +20,7 @@ obj-$(CONFIG_IP_MROUTE) += ipmr.o obj-$(CONFIG_NET_IPIP) += ipip.o obj-$(CONFIG_NET_IPGRE_DEMUX) += gre.o obj-$(CONFIG_NET_IPGRE) += ip_gre.o +obj-$(CONFIG_NET_IPVTI) += ip_vti.o obj-$(CONFIG_SYN_COOKIES) += syncookies.o obj-$(CONFIG_INET_AH) += ah4.o obj-$(CONFIG_INET_ESP) += esp4.o @@ -48,7 +49,7 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o -obj-$(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) += tcp_memcontrol.o +obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index c8f7aee587d..fe4582ca969 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -157,6 +157,7 @@ void inet_sock_destruct(struct sock *sk) kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_check(sk->sk_dst_cache, 1)); + dst_release(sk->sk_rx_dst); sk_refcnt_debug_dec(sk); } EXPORT_SYMBOL(inet_sock_destruct); @@ -242,20 +243,18 @@ void build_ehash_secret(void) } EXPORT_SYMBOL(build_ehash_secret); -static inline int inet_netns_ok(struct net *net, int protocol) +static inline int inet_netns_ok(struct net *net, __u8 protocol) { - int hash; const struct net_protocol *ipprot; if (net_eq(net, &init_net)) return 1; - hash = protocol & (MAX_INET_PROTOS - 1); - ipprot = rcu_dereference(inet_protos[hash]); - - if (ipprot == NULL) + ipprot = rcu_dereference(inet_protos[protocol]); + if (ipprot == NULL) { /* raw IP is OK */ return 1; + } return ipprot->netns_ok; } @@ -553,15 +552,16 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; - return sk->sk_prot->connect(sk, (struct sockaddr *)uaddr, addr_len); + return sk->sk_prot->connect(sk, uaddr, addr_len); } EXPORT_SYMBOL(inet_dgram_connect); -static long inet_wait_for_connect(struct sock *sk, long timeo) +static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) { DEFINE_WAIT(wait); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + sk->sk_write_pending += writebias; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. @@ -577,6 +577,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo) prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } finish_wait(sk_sleep(sk), &wait); + sk->sk_write_pending -= writebias; return timeo; } @@ -584,8 +585,8 @@ static long inet_wait_for_connect(struct sock *sk, long timeo) * Connect to a remote host. There is regrettably still a little * TCP 'magic' in here. */ -int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, - int addr_len, int flags) +int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, + int addr_len, int flags) { struct sock *sk = sock->sk; int err; @@ -594,8 +595,6 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, if (addr_len < sizeof(uaddr->sa_family)) return -EINVAL; - lock_sock(sk); - if (uaddr->sa_family == AF_UNSPEC) { err = sk->sk_prot->disconnect(sk, flags); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; @@ -635,8 +634,12 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { + int writebias = (sk->sk_protocol == IPPROTO_TCP) && + tcp_sk(sk)->fastopen_req && + tcp_sk(sk)->fastopen_req->data ? 1 : 0; + /* Error code is set above */ - if (!timeo || !inet_wait_for_connect(sk, timeo)) + if (!timeo || !inet_wait_for_connect(sk, timeo, writebias)) goto out; err = sock_intr_errno(timeo); @@ -658,7 +661,6 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, sock->state = SS_CONNECTED; err = 0; out: - release_sock(sk); return err; sock_error: @@ -668,6 +670,18 @@ sock_error: sock->state = SS_DISCONNECTING; goto out; } +EXPORT_SYMBOL(__inet_stream_connect); + +int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, + int addr_len, int flags) +{ + int err; + + lock_sock(sock->sk); + err = __inet_stream_connect(sock, uaddr, addr_len, flags); + release_sock(sock->sk); + return err; +} EXPORT_SYMBOL(inet_stream_connect); /* @@ -1216,8 +1230,8 @@ EXPORT_SYMBOL(inet_sk_rebuild_header); static int inet_gso_send_check(struct sk_buff *skb) { - const struct iphdr *iph; const struct net_protocol *ops; + const struct iphdr *iph; int proto; int ihl; int err = -EINVAL; @@ -1236,7 +1250,7 @@ static int inet_gso_send_check(struct sk_buff *skb) __skb_pull(skb, ihl); skb_reset_transport_header(skb); iph = ip_hdr(skb); - proto = iph->protocol & (MAX_INET_PROTOS - 1); + proto = iph->protocol; err = -EPROTONOSUPPORT; rcu_read_lock(); @@ -1253,8 +1267,8 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); - struct iphdr *iph; const struct net_protocol *ops; + struct iphdr *iph; int proto; int ihl; int id; @@ -1286,7 +1300,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, skb_reset_transport_header(skb); iph = ip_hdr(skb); id = ntohs(iph->id); - proto = iph->protocol & (MAX_INET_PROTOS - 1); + proto = iph->protocol; segs = ERR_PTR(-EPROTONOSUPPORT); rcu_read_lock(); @@ -1340,7 +1354,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, goto out; } - proto = iph->protocol & (MAX_INET_PROTOS - 1); + proto = iph->protocol; rcu_read_lock(); ops = rcu_dereference(inet_protos[proto]); @@ -1398,11 +1412,11 @@ out: static int inet_gro_complete(struct sk_buff *skb) { - const struct net_protocol *ops; + __be16 newlen = htons(skb->len - skb_network_offset(skb)); struct iphdr *iph = ip_hdr(skb); - int proto = iph->protocol & (MAX_INET_PROTOS - 1); + const struct net_protocol *ops; + int proto = iph->protocol; int err = -ENOSYS; - __be16 newlen = htons(skb->len - skb_network_offset(skb)); csum_replace2(&iph->check, iph->tot_len, newlen); iph->tot_len = newlen; @@ -1520,14 +1534,15 @@ static const struct net_protocol igmp_protocol = { #endif static const struct net_protocol tcp_protocol = { - .handler = tcp_v4_rcv, - .err_handler = tcp_v4_err, - .gso_send_check = tcp_v4_gso_send_check, - .gso_segment = tcp_tso_segment, - .gro_receive = tcp4_gro_receive, - .gro_complete = tcp4_gro_complete, - .no_policy = 1, - .netns_ok = 1, + .early_demux = tcp_v4_early_demux, + .handler = tcp_v4_rcv, + .err_handler = tcp_v4_err, + .gso_send_check = tcp_v4_gso_send_check, + .gso_segment = tcp_tso_segment, + .gro_receive = tcp4_gro_receive, + .gro_complete = tcp4_gro_complete, + .no_policy = 1, + .netns_ok = 1, }; static const struct net_protocol udp_protocol = { diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index e8f2617ecd4..a0d8392491c 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -398,16 +398,25 @@ static void ah4_err(struct sk_buff *skb, u32 info) struct ip_auth_hdr *ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); struct xfrm_state *x; - if (icmp_hdr(skb)->type != ICMP_DEST_UNREACH || - icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + switch (icmp_hdr(skb)->type) { + case ICMP_DEST_UNREACH: + if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + return; + case ICMP_REDIRECT: + break; + default: return; + } x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET); if (!x) return; - pr_debug("pmtu discovery on SA AH/%08x/%08x\n", - ntohl(ah->spi), ntohl(iph->daddr)); + + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0); + else + ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0); xfrm_state_put(x); } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index cda37be02f8..77e87aff419 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -475,8 +475,7 @@ int arp_find(unsigned char *haddr, struct sk_buff *skb) return 1; } - paddr = skb_rtable(skb)->rt_gateway; - + paddr = rt_nexthop(skb_rtable(skb), ip_hdr(skb)->daddr); if (arp_set_predefined(inet_addr_type(dev_net(dev), paddr), haddr, paddr, dev)) return 0; @@ -790,7 +789,8 @@ static int arp_process(struct sk_buff *skb) * Check for bad requests for 127.x.x.x and requests for multicast * addresses. If this is one such, delete it. */ - if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) + if (ipv4_is_multicast(tip) || + (!IN_DEV_ROUTE_LOCALNET(in_dev) && ipv4_is_loopback(tip))) goto out; /* diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 10e15a144e9..44bf82e3aef 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1500,7 +1500,8 @@ static int devinet_conf_proc(ctl_table *ctl, int write, if (cnf == net->ipv4.devconf_dflt) devinet_copy_dflt_conf(net, i); - if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1) + if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1 || + i == IPV4_DEVCONF_ROUTE_LOCALNET - 1) if ((new_value == 0) && (old_value != 0)) rt_cache_flush(net, 0); } @@ -1617,6 +1618,8 @@ static struct devinet_sysctl_table { "force_igmp_version"), DEVINET_SYSCTL_FLUSHING_ENTRY(PROMOTE_SECONDARIES, "promote_secondaries"), + DEVINET_SYSCTL_FLUSHING_ENTRY(ROUTE_LOCALNET, + "route_localnet"), }, }; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index cb982a61536..b61e9deb7c7 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -484,16 +484,25 @@ static void esp4_err(struct sk_buff *skb, u32 info) struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); struct xfrm_state *x; - if (icmp_hdr(skb)->type != ICMP_DEST_UNREACH || - icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + switch (icmp_hdr(skb)->type) { + case ICMP_DEST_UNREACH: + if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + return; + case ICMP_REDIRECT: + break; + default: return; + } x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET); if (!x) return; - NETDEBUG(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%08x\n", - ntohl(esph->spi), ntohl(iph->daddr)); + + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0); + else + ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0); xfrm_state_put(x); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 3854411fa37..c43ae3fba79 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -31,6 +31,7 @@ #include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/skbuff.h> +#include <linux/cache.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> @@ -85,6 +86,24 @@ struct fib_table *fib_new_table(struct net *net, u32 id) tb = fib_trie_table(id); if (!tb) return NULL; + + switch (id) { + case RT_TABLE_LOCAL: + net->ipv4.fib_local = tb; + break; + + case RT_TABLE_MAIN: + net->ipv4.fib_main = tb; + break; + + case RT_TABLE_DEFAULT: + net->ipv4.fib_default = tb; + break; + + default: + break; + } + h = id & (FIB_TABLE_HASHSZ - 1); hlist_add_head_rcu(&tb->tb_hlist, &net->ipv4.fib_table_hash[h]); return tb; @@ -150,10 +169,6 @@ static inline unsigned int __inet_dev_addr_type(struct net *net, if (ipv4_is_multicast(addr)) return RTN_MULTICAST; -#ifdef CONFIG_IP_MULTIPLE_TABLES - res.r = NULL; -#endif - local_table = fib_get_table(net, RT_TABLE_LOCAL); if (local_table) { ret = RTN_UNICAST; @@ -180,6 +195,44 @@ unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, } EXPORT_SYMBOL(inet_dev_addr_type); +__be32 fib_compute_spec_dst(struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + struct in_device *in_dev; + struct fib_result res; + struct rtable *rt; + struct flowi4 fl4; + struct net *net; + int scope; + + rt = skb_rtable(skb); + if ((rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL)) == + RTCF_LOCAL) + return ip_hdr(skb)->daddr; + + in_dev = __in_dev_get_rcu(dev); + BUG_ON(!in_dev); + + net = dev_net(dev); + + scope = RT_SCOPE_UNIVERSE; + if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { + fl4.flowi4_oif = 0; + fl4.flowi4_iif = net->loopback_dev->ifindex; + fl4.daddr = ip_hdr(skb)->saddr; + fl4.saddr = 0; + fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); + fl4.flowi4_scope = scope; + fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0; + if (!fib_lookup(net, &fl4, &res)) + return FIB_RES_PREFSRC(net, res); + } else { + scope = RT_SCOPE_LINK; + } + + return inet_select_addr(dev, ip_hdr(skb)->saddr, scope); +} + /* Given (packet source, input interface) and optional (dst, oif, tos): * - (main) check, that source is valid i.e. not broadcast or our local * address. @@ -188,17 +241,15 @@ EXPORT_SYMBOL(inet_dev_addr_type); * - check, that packet arrived from expected physical interface. * called with rcu_read_lock() */ -int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, - int oif, struct net_device *dev, __be32 *spec_dst, - u32 *itag) +static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, + u8 tos, int oif, struct net_device *dev, + int rpf, struct in_device *idev, u32 *itag) { - struct in_device *in_dev; - struct flowi4 fl4; + int ret, no_addr, accept_local; struct fib_result res; - int no_addr, rpf, accept_local; - bool dev_match; - int ret; + struct flowi4 fl4; struct net *net; + bool dev_match; fl4.flowi4_oif = 0; fl4.flowi4_iif = oif; @@ -207,20 +258,10 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; - no_addr = rpf = accept_local = 0; - in_dev = __in_dev_get_rcu(dev); - if (in_dev) { - no_addr = in_dev->ifa_list == NULL; - - /* Ignore rp_filter for packets protected by IPsec. */ - rpf = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(in_dev); - - accept_local = IN_DEV_ACCEPT_LOCAL(in_dev); - fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0; - } + no_addr = idev->ifa_list == NULL; - if (in_dev == NULL) - goto e_inval; + accept_local = IN_DEV_ACCEPT_LOCAL(idev); + fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0; net = dev_net(dev); if (fib_lookup(net, &fl4, &res)) @@ -229,7 +270,6 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, if (res.type != RTN_LOCAL || !accept_local) goto e_inval; } - *spec_dst = FIB_RES_PREFSRC(net, res); fib_combine_itag(itag, &res); dev_match = false; @@ -258,17 +298,14 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, ret = 0; if (fib_lookup(net, &fl4, &res) == 0) { - if (res.type == RTN_UNICAST) { - *spec_dst = FIB_RES_PREFSRC(net, res); + if (res.type == RTN_UNICAST) ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST; - } } return ret; last_resort: if (rpf) goto e_rpf; - *spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE); *itag = 0; return 0; @@ -278,6 +315,20 @@ e_rpf: return -EXDEV; } +/* Ignore rp_filter for packets protected by IPsec. */ +int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, + u8 tos, int oif, struct net_device *dev, + struct in_device *idev, u32 *itag) +{ + int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev); + + if (!r && !fib_num_tclassid_users(dev_net(dev))) { + *itag = 0; + return 0; + } + return __fib_validate_source(skb, src, dst, tos, oif, dev, r, idev, itag); +} + static inline __be32 sk_extract_addr(struct sockaddr *addr) { return ((struct sockaddr_in *) addr)->sin_addr.s_addr; @@ -879,10 +930,6 @@ static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb) .flowi4_scope = frn->fl_scope, }; -#ifdef CONFIG_IP_MULTIPLE_TABLES - res.r = NULL; -#endif - frn->err = -ENOENT; if (tb) { local_bh_disable(); @@ -935,8 +982,11 @@ static void nl_fib_input(struct sk_buff *skb) static int __net_init nl_fib_lookup_init(struct net *net) { struct sock *sk; - sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, 0, - nl_fib_input, NULL, THIS_MODULE); + struct netlink_kernel_cfg cfg = { + .input = nl_fib_input, + }; + + sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, THIS_MODULE, &cfg); if (sk == NULL) return -EAFNOSUPPORT; net->ipv4.fibnl = sk; @@ -996,6 +1046,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo if (event == NETDEV_UNREGISTER) { fib_disable_ip(dev, 2, -1); + rt_flush_dev(dev); return NOTIFY_DONE; } @@ -1021,11 +1072,6 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo rt_cache_flush(dev_net(dev), 0); break; case NETDEV_UNREGISTER_BATCH: - /* The batch unregister is only called on the first - * device in the list of devices being unregistered. - * Therefore we should not pass dev_net(dev) in here. - */ - rt_cache_flush_batch(NULL); break; } return NOTIFY_DONE; @@ -1090,6 +1136,9 @@ static int __net_init fib_net_init(struct net *net) { int error; +#ifdef CONFIG_IP_ROUTE_CLASSID + net->ipv4.fib_num_tclassid_users = 0; +#endif error = ip_fib_net_init(net); if (error < 0) goto out; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 2d043f71ef7..a83d74e498d 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -47,14 +47,7 @@ struct fib4_rule { #endif }; -#ifdef CONFIG_IP_ROUTE_CLASSID -u32 fib_rules_tclass(const struct fib_result *res) -{ - return res->r ? ((struct fib4_rule *) res->r)->tclassid : 0; -} -#endif - -int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res) +int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res) { struct fib_lookup_arg arg = { .result = res, @@ -63,11 +56,15 @@ int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res) int err; err = fib_rules_lookup(net->ipv4.rules_ops, flowi4_to_flowi(flp), 0, &arg); - res->r = arg.rule; - +#ifdef CONFIG_IP_ROUTE_CLASSID + if (arg.rule) + res->tclassid = ((struct fib4_rule *)arg.rule)->tclassid; + else + res->tclassid = 0; +#endif return err; } -EXPORT_SYMBOL_GPL(fib_lookup); +EXPORT_SYMBOL_GPL(__fib_lookup); static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) @@ -169,8 +166,11 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, rule4->dst = nla_get_be32(tb[FRA_DST]); #ifdef CONFIG_IP_ROUTE_CLASSID - if (tb[FRA_FLOW]) + if (tb[FRA_FLOW]) { rule4->tclassid = nla_get_u32(tb[FRA_FLOW]); + if (rule4->tclassid) + net->ipv4.fib_num_tclassid_users++; + } #endif rule4->src_len = frh->src_len; @@ -179,11 +179,24 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, rule4->dstmask = inet_make_mask(rule4->dst_len); rule4->tos = frh->tos; + net->ipv4.fib_has_custom_rules = true; err = 0; errout: return err; } +static void fib4_rule_delete(struct fib_rule *rule) +{ + struct net *net = rule->fr_net; +#ifdef CONFIG_IP_ROUTE_CLASSID + struct fib4_rule *rule4 = (struct fib4_rule *) rule; + + if (rule4->tclassid) + net->ipv4.fib_num_tclassid_users--; +#endif + net->ipv4.fib_has_custom_rules = true; +} + static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, struct nlattr **tb) { @@ -256,6 +269,7 @@ static const struct fib_rules_ops __net_initdata fib4_rules_ops_template = { .action = fib4_rule_action, .match = fib4_rule_match, .configure = fib4_rule_configure, + .delete = fib4_rule_delete, .compare = fib4_rule_compare, .fill = fib4_rule_fill, .default_pref = fib_default_rule_pref, @@ -295,6 +309,7 @@ int __net_init fib4_rules_init(struct net *net) if (err < 0) goto fail; net->ipv4.rules_ops = ops; + net->ipv4.fib_has_custom_rules = false; return 0; fail: diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index e5b7182fa09..da80dc14cc7 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -140,6 +140,62 @@ const struct fib_prop fib_props[RTN_MAX + 1] = { }, }; +static void rt_fibinfo_free(struct rtable __rcu **rtp) +{ + struct rtable *rt = rcu_dereference_protected(*rtp, 1); + + if (!rt) + return; + + /* Not even needed : RCU_INIT_POINTER(*rtp, NULL); + * because we waited an RCU grace period before calling + * free_fib_info_rcu() + */ + + dst_free(&rt->dst); +} + +static void free_nh_exceptions(struct fib_nh *nh) +{ + struct fnhe_hash_bucket *hash = nh->nh_exceptions; + int i; + + for (i = 0; i < FNHE_HASH_SIZE; i++) { + struct fib_nh_exception *fnhe; + + fnhe = rcu_dereference_protected(hash[i].chain, 1); + while (fnhe) { + struct fib_nh_exception *next; + + next = rcu_dereference_protected(fnhe->fnhe_next, 1); + + rt_fibinfo_free(&fnhe->fnhe_rth); + + kfree(fnhe); + + fnhe = next; + } + } + kfree(hash); +} + +static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp) +{ + int cpu; + + if (!rtp) + return; + + for_each_possible_cpu(cpu) { + struct rtable *rt; + + rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1); + if (rt) + dst_free(&rt->dst); + } + free_percpu(rtp); +} + /* Release a nexthop info record */ static void free_fib_info_rcu(struct rcu_head *head) { @@ -148,6 +204,10 @@ static void free_fib_info_rcu(struct rcu_head *head) change_nexthops(fi) { if (nexthop_nh->nh_dev) dev_put(nexthop_nh->nh_dev); + if (nexthop_nh->nh_exceptions) + free_nh_exceptions(nexthop_nh); + rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output); + rt_fibinfo_free(&nexthop_nh->nh_rth_input); } endfor_nexthops(fi); release_net(fi->fib_net); @@ -163,6 +223,12 @@ void free_fib_info(struct fib_info *fi) return; } fib_info_cnt--; +#ifdef CONFIG_IP_ROUTE_CLASSID + change_nexthops(fi) { + if (nexthop_nh->nh_tclassid) + fi->fib_net->ipv4.fib_num_tclassid_users--; + } endfor_nexthops(fi); +#endif call_rcu(&fi->rcu, free_fib_info_rcu); } @@ -421,6 +487,8 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, #ifdef CONFIG_IP_ROUTE_CLASSID nla = nla_find(attrs, attrlen, RTA_FLOW); nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0; + if (nexthop_nh->nh_tclassid) + fi->fib_net->ipv4.fib_num_tclassid_users++; #endif } @@ -769,6 +837,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi->fib_nhs = nhs; change_nexthops(fi) { nexthop_nh->nh_parent = fi; + nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *); } endfor_nexthops(fi) if (cfg->fc_mx) { @@ -779,9 +848,16 @@ struct fib_info *fib_create_info(struct fib_config *cfg) int type = nla_type(nla); if (type) { + u32 val; + if (type > RTAX_MAX) goto err_inval; - fi->fib_metrics[type - 1] = nla_get_u32(nla); + val = nla_get_u32(nla); + if (type == RTAX_ADVMSS && val > 65535 - 40) + val = 65535 - 40; + if (type == RTAX_MTU && val > 65535 - 15) + val = 65535 - 15; + fi->fib_metrics[type - 1] = val; } } } @@ -810,6 +886,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg) nh->nh_flags = cfg->fc_flags; #ifdef CONFIG_IP_ROUTE_CLASSID nh->nh_tclassid = cfg->fc_flow; + if (nh->nh_tclassid) + fi->fib_net->ipv4.fib_num_tclassid_users++; #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH nh->nh_weight = 1; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 30b88d7b4bd..57bd978483e 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -159,7 +159,6 @@ struct trie { #endif }; -static void put_child(struct trie *t, struct tnode *tn, int i, struct rt_trie_node *n); static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node *n, int wasfull); static struct rt_trie_node *resize(struct trie *t, struct tnode *tn); @@ -368,7 +367,7 @@ static void __leaf_free_rcu(struct rcu_head *head) static inline void free_leaf(struct leaf *l) { - call_rcu_bh(&l->rcu, __leaf_free_rcu); + call_rcu(&l->rcu, __leaf_free_rcu); } static inline void free_leaf_info(struct leaf_info *leaf) @@ -473,7 +472,7 @@ static struct tnode *tnode_new(t_key key, int pos, int bits) } pr_debug("AT %p s=%zu %zu\n", tn, sizeof(struct tnode), - sizeof(struct rt_trie_node) << bits); + sizeof(struct rt_trie_node *) << bits); return tn; } @@ -490,7 +489,7 @@ static inline int tnode_full(const struct tnode *tn, const struct rt_trie_node * return ((struct tnode *) n)->pos == tn->pos + tn->bits; } -static inline void put_child(struct trie *t, struct tnode *tn, int i, +static inline void put_child(struct tnode *tn, int i, struct rt_trie_node *n) { tnode_put_child_reorg(tn, i, n, -1); @@ -754,8 +753,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) goto nomem; } - put_child(t, tn, 2*i, (struct rt_trie_node *) left); - put_child(t, tn, 2*i+1, (struct rt_trie_node *) right); + put_child(tn, 2*i, (struct rt_trie_node *) left); + put_child(tn, 2*i+1, (struct rt_trie_node *) right); } } @@ -776,9 +775,9 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) if (tkey_extract_bits(node->key, oldtnode->pos + oldtnode->bits, 1) == 0) - put_child(t, tn, 2*i, node); + put_child(tn, 2*i, node); else - put_child(t, tn, 2*i+1, node); + put_child(tn, 2*i+1, node); continue; } @@ -786,8 +785,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) inode = (struct tnode *) node; if (inode->bits == 1) { - put_child(t, tn, 2*i, rtnl_dereference(inode->child[0])); - put_child(t, tn, 2*i+1, rtnl_dereference(inode->child[1])); + put_child(tn, 2*i, rtnl_dereference(inode->child[0])); + put_child(tn, 2*i+1, rtnl_dereference(inode->child[1])); tnode_free_safe(inode); continue; @@ -817,22 +816,22 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) */ left = (struct tnode *) tnode_get_child(tn, 2*i); - put_child(t, tn, 2*i, NULL); + put_child(tn, 2*i, NULL); BUG_ON(!left); right = (struct tnode *) tnode_get_child(tn, 2*i+1); - put_child(t, tn, 2*i+1, NULL); + put_child(tn, 2*i+1, NULL); BUG_ON(!right); size = tnode_child_length(left); for (j = 0; j < size; j++) { - put_child(t, left, j, rtnl_dereference(inode->child[j])); - put_child(t, right, j, rtnl_dereference(inode->child[j + size])); + put_child(left, j, rtnl_dereference(inode->child[j])); + put_child(right, j, rtnl_dereference(inode->child[j + size])); } - put_child(t, tn, 2*i, resize(t, left)); - put_child(t, tn, 2*i+1, resize(t, right)); + put_child(tn, 2*i, resize(t, left)); + put_child(tn, 2*i+1, resize(t, right)); tnode_free_safe(inode); } @@ -877,7 +876,7 @@ static struct tnode *halve(struct trie *t, struct tnode *tn) if (!newn) goto nomem; - put_child(t, tn, i/2, (struct rt_trie_node *)newn); + put_child(tn, i/2, (struct rt_trie_node *)newn); } } @@ -892,21 +891,21 @@ static struct tnode *halve(struct trie *t, struct tnode *tn) if (left == NULL) { if (right == NULL) /* Both are empty */ continue; - put_child(t, tn, i/2, right); + put_child(tn, i/2, right); continue; } if (right == NULL) { - put_child(t, tn, i/2, left); + put_child(tn, i/2, left); continue; } /* Two nonempty children */ newBinNode = (struct tnode *) tnode_get_child(tn, i/2); - put_child(t, tn, i/2, NULL); - put_child(t, newBinNode, 0, left); - put_child(t, newBinNode, 1, right); - put_child(t, tn, i/2, resize(t, newBinNode)); + put_child(tn, i/2, NULL); + put_child(newBinNode, 0, left); + put_child(newBinNode, 1, right); + put_child(tn, i/2, resize(t, newBinNode)); } tnode_free_safe(oldtnode); return tn; @@ -1007,9 +1006,9 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) while (tn != NULL && (tp = node_parent((struct rt_trie_node *)tn)) != NULL) { cindex = tkey_extract_bits(key, tp->pos, tp->bits); wasfull = tnode_full(tp, tnode_get_child(tp, cindex)); - tn = (struct tnode *) resize(t, (struct tnode *)tn); + tn = (struct tnode *)resize(t, tn); - tnode_put_child_reorg((struct tnode *)tp, cindex, + tnode_put_child_reorg(tp, cindex, (struct rt_trie_node *)tn, wasfull); tp = node_parent((struct rt_trie_node *) tn); @@ -1024,7 +1023,7 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) /* Handle last (top) tnode */ if (IS_TNODE(tn)) - tn = (struct tnode *)resize(t, (struct tnode *)tn); + tn = (struct tnode *)resize(t, tn); rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tnode_free_flush(); @@ -1125,7 +1124,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) node_set_parent((struct rt_trie_node *)l, tp); cindex = tkey_extract_bits(key, tp->pos, tp->bits); - put_child(t, (struct tnode *)tp, cindex, (struct rt_trie_node *)l); + put_child(tp, cindex, (struct rt_trie_node *)l); } else { /* Case 3: n is a LEAF or a TNODE and the key doesn't match. */ /* @@ -1155,13 +1154,12 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) node_set_parent((struct rt_trie_node *)tn, tp); missbit = tkey_extract_bits(key, newpos, 1); - put_child(t, tn, missbit, (struct rt_trie_node *)l); - put_child(t, tn, 1-missbit, n); + put_child(tn, missbit, (struct rt_trie_node *)l); + put_child(tn, 1-missbit, n); if (tp) { cindex = tkey_extract_bits(key, tp->pos, tp->bits); - put_child(t, (struct tnode *)tp, cindex, - (struct rt_trie_node *)tn); + put_child(tp, cindex, (struct rt_trie_node *)tn); } else { rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tp = tn; @@ -1620,7 +1618,7 @@ static void trie_leaf_remove(struct trie *t, struct leaf *l) if (tp) { t_key cindex = tkey_extract_bits(l->key, tp->pos, tp->bits); - put_child(t, (struct tnode *)tp, cindex, NULL); + put_child(tp, cindex, NULL); trie_rebalance(t, tp); } else RCU_INIT_POINTER(t->trie, NULL); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index c75efbdc71c..f2eccd53174 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -95,6 +95,7 @@ #include <net/checksum.h> #include <net/xfrm.h> #include <net/inet_common.h> +#include <net/ip_fib.h> /* * Build xmit assembly blocks @@ -253,10 +254,10 @@ static inline bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, /* Limit if icmp type is enabled in ratemask. */ if ((1 << type) & net->ipv4.sysctl_icmp_ratemask) { - if (!rt->peer) - rt_bind_peer(rt, fl4->daddr, 1); - rc = inet_peer_xrlim_allow(rt->peer, + struct inet_peer *peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, 1); + rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit); + inet_putpeer(peer); } out: return rc; @@ -334,7 +335,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) struct flowi4 fl4; struct sock *sk; struct inet_sock *inet; - __be32 daddr; + __be32 daddr, saddr; if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb)) return; @@ -348,6 +349,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) inet->tos = ip_hdr(skb)->tos; daddr = ipc.addr = ip_hdr(skb)->saddr; + saddr = fib_compute_spec_dst(skb); ipc.opt = NULL; ipc.tx_flags = 0; if (icmp_param->replyopts.opt.opt.optlen) { @@ -357,7 +359,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) } memset(&fl4, 0, sizeof(fl4)); fl4.daddr = daddr; - fl4.saddr = rt->rt_spec_dst; + fl4.saddr = saddr; fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); fl4.flowi4_proto = IPPROTO_ICMP; security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); @@ -569,7 +571,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) rcu_read_lock(); if (rt_is_input_route(rt) && net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr) - dev = dev_get_by_index_rcu(net, rt->rt_iif); + dev = dev_get_by_index_rcu(net, inet_iif(skb_in)); if (dev) saddr = inet_select_addr(dev, 0, RT_SCOPE_LINK); @@ -632,6 +634,27 @@ out:; EXPORT_SYMBOL(icmp_send); +static void icmp_socket_deliver(struct sk_buff *skb, u32 info) +{ + const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct net_protocol *ipprot; + int protocol = iph->protocol; + + /* Checkin full IP header plus 8 bytes of protocol to + * avoid additional coding at protocol handlers. + */ + if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) + return; + + raw_icmp_error(skb, protocol, info); + + rcu_read_lock(); + ipprot = rcu_dereference(inet_protos[protocol]); + if (ipprot && ipprot->err_handler) + ipprot->err_handler(skb, info); + rcu_read_unlock(); +} + /* * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, and ICMP_QUENCH. */ @@ -640,10 +663,8 @@ static void icmp_unreach(struct sk_buff *skb) { const struct iphdr *iph; struct icmphdr *icmph; - int hash, protocol; - const struct net_protocol *ipprot; - u32 info = 0; struct net *net; + u32 info = 0; net = dev_net(skb_dst(skb)->dev); @@ -674,9 +695,7 @@ static void icmp_unreach(struct sk_buff *skb) LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: fragmentation needed and DF set\n"), &iph->daddr); } else { - info = ip_rt_frag_needed(net, iph, - ntohs(icmph->un.frag.mtu), - skb->dev); + info = ntohs(icmph->un.frag.mtu); if (!info) goto out; } @@ -720,26 +739,7 @@ static void icmp_unreach(struct sk_buff *skb) goto out; } - /* Checkin full IP header plus 8 bytes of protocol to - * avoid additional coding at protocol handlers. - */ - if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) - goto out; - - iph = (const struct iphdr *)skb->data; - protocol = iph->protocol; - - /* - * Deliver ICMP message to raw sockets. Pretty useless feature? - */ - raw_icmp_error(skb, protocol, info); - - hash = protocol & (MAX_INET_PROTOS - 1); - rcu_read_lock(); - ipprot = rcu_dereference(inet_protos[hash]); - if (ipprot && ipprot->err_handler) - ipprot->err_handler(skb, info); - rcu_read_unlock(); + icmp_socket_deliver(skb, info); out: return; @@ -755,46 +755,15 @@ out_err: static void icmp_redirect(struct sk_buff *skb) { - const struct iphdr *iph; - - if (skb->len < sizeof(struct iphdr)) - goto out_err; - - /* - * Get the copied header of the packet that caused the redirect - */ - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - goto out; - - iph = (const struct iphdr *)skb->data; - - switch (icmp_hdr(skb)->code & 7) { - case ICMP_REDIR_NET: - case ICMP_REDIR_NETTOS: - /* - * As per RFC recommendations now handle it as a host redirect. - */ - case ICMP_REDIR_HOST: - case ICMP_REDIR_HOSTTOS: - ip_rt_redirect(ip_hdr(skb)->saddr, iph->daddr, - icmp_hdr(skb)->un.gateway, - iph->saddr, skb->dev); - break; + if (skb->len < sizeof(struct iphdr)) { + ICMP_INC_STATS_BH(dev_net(skb->dev), ICMP_MIB_INERRORS); + return; } - /* Ping wants to see redirects. - * Let's pretend they are errors of sorts... */ - if (iph->protocol == IPPROTO_ICMP && - iph->ihl >= 5 && - pskb_may_pull(skb, (iph->ihl<<2)+8)) { - ping_err(skb, icmp_hdr(skb)->un.gateway); - } + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + return; -out: - return; -out_err: - ICMP_INC_STATS_BH(dev_net(skb->dev), ICMP_MIB_INERRORS); - goto out; + icmp_socket_deliver(skb, icmp_hdr(skb)->un.gateway); } /* @@ -868,86 +837,6 @@ out_err: goto out; } - -/* - * Handle ICMP_ADDRESS_MASK requests. (RFC950) - * - * RFC1122 (3.2.2.9). A host MUST only send replies to - * ADDRESS_MASK requests if it's been configured as an address mask - * agent. Receiving a request doesn't constitute implicit permission to - * act as one. Of course, implementing this correctly requires (SHOULD) - * a way to turn the functionality on and off. Another one for sysctl(), - * I guess. -- MS - * - * RFC1812 (4.3.3.9). A router MUST implement it. - * A router SHOULD have switch turning it on/off. - * This switch MUST be ON by default. - * - * Gratuitous replies, zero-source replies are not implemented, - * that complies with RFC. DO NOT implement them!!! All the idea - * of broadcast addrmask replies as specified in RFC950 is broken. - * The problem is that it is not uncommon to have several prefixes - * on one physical interface. Moreover, addrmask agent can even be - * not aware of existing another prefixes. - * If source is zero, addrmask agent cannot choose correct prefix. - * Gratuitous mask announcements suffer from the same problem. - * RFC1812 explains it, but still allows to use ADDRMASK, - * that is pretty silly. --ANK - * - * All these rules are so bizarre, that I removed kernel addrmask - * support at all. It is wrong, it is obsolete, nobody uses it in - * any case. --ANK - * - * Furthermore you can do it with a usermode address agent program - * anyway... - */ - -static void icmp_address(struct sk_buff *skb) -{ -#if 0 - net_dbg_ratelimited("a guy asks for address mask. Who is it?\n"); -#endif -} - -/* - * RFC1812 (4.3.3.9). A router SHOULD listen all replies, and complain - * loudly if an inconsistency is found. - * called with rcu_read_lock() - */ - -static void icmp_address_reply(struct sk_buff *skb) -{ - struct rtable *rt = skb_rtable(skb); - struct net_device *dev = skb->dev; - struct in_device *in_dev; - struct in_ifaddr *ifa; - - if (skb->len < 4 || !(rt->rt_flags&RTCF_DIRECTSRC)) - return; - - in_dev = __in_dev_get_rcu(dev); - if (!in_dev) - return; - - if (in_dev->ifa_list && - IN_DEV_LOG_MARTIANS(in_dev) && - IN_DEV_FORWARD(in_dev)) { - __be32 _mask, *mp; - - mp = skb_header_pointer(skb, 0, sizeof(_mask), &_mask); - BUG_ON(mp == NULL); - for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { - if (*mp == ifa->ifa_mask && - inet_ifa_match(ip_hdr(skb)->saddr, ifa)) - break; - } - if (!ifa) - net_info_ratelimited("Wrong address mask %pI4 from %s/%pI4\n", - mp, - dev->name, &ip_hdr(skb)->saddr); - } -} - static void icmp_discard(struct sk_buff *skb) { } @@ -1111,10 +1000,10 @@ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES + 1] = { .handler = icmp_discard, }, [ICMP_ADDRESS] = { - .handler = icmp_address, + .handler = icmp_discard, }, [ICMP_ADDRESSREPLY] = { - .handler = icmp_address_reply, + .handler = icmp_discard, }, }; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index f9ee7417f6a..7f75f21d7b8 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -374,18 +374,19 @@ struct dst_entry *inet_csk_route_req(struct sock *sk, const struct inet_request_sock *ireq = inet_rsk(req); struct ip_options_rcu *opt = inet_rsk(req)->opt; struct net *net = sock_net(sk); + int flags = inet_sk_flowi_flags(sk); flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, sk->sk_protocol, - inet_sk_flowi_flags(sk) & ~FLOWI_FLAG_PRECOW_METRICS, + flags, (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr, ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport); security_req_classify_flow(req, flowi4_to_flowi(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; - if (opt && opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway) + if (opt && opt->opt.is_strictroute && rt->rt_gateway) goto route_err; return &rt->dst; @@ -403,12 +404,15 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk, { const struct inet_request_sock *ireq = inet_rsk(req); struct inet_sock *newinet = inet_sk(newsk); - struct ip_options_rcu *opt = ireq->opt; + struct ip_options_rcu *opt; struct net *net = sock_net(sk); struct flowi4 *fl4; struct rtable *rt; fl4 = &newinet->cork.fl.u.ip4; + + rcu_read_lock(); + opt = rcu_dereference(newinet->inet_opt); flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, sk->sk_protocol, inet_sk_flowi_flags(sk), @@ -418,13 +422,15 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk, rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; - if (opt && opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway) + if (opt && opt->opt.is_strictroute && rt->rt_gateway) goto route_err; + rcu_read_unlock(); return &rt->dst; route_err: ip_rt_put(rt); no_route: + rcu_read_unlock(); IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } @@ -799,3 +805,49 @@ int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, } EXPORT_SYMBOL_GPL(inet_csk_compat_setsockopt); #endif + +static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *fl) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct ip_options_rcu *inet_opt; + __be32 daddr = inet->inet_daddr; + struct flowi4 *fl4; + struct rtable *rt; + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt && inet_opt->opt.srr) + daddr = inet_opt->opt.faddr; + fl4 = &fl->u.ip4; + rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, + inet->inet_saddr, inet->inet_dport, + inet->inet_sport, sk->sk_protocol, + RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); + if (IS_ERR(rt)) + rt = NULL; + if (rt) + sk_setup_caps(sk, &rt->dst); + rcu_read_unlock(); + + return &rt->dst; +} + +struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu) +{ + struct dst_entry *dst = __sk_dst_check(sk, 0); + struct inet_sock *inet = inet_sk(sk); + + if (!dst) { + dst = inet_csk_rebuild_route(sk, &inet->cork.fl); + if (!dst) + goto out; + } + dst->ops->update_pmtu(dst, sk, NULL, mtu); + + dst = __sk_dst_check(sk, 0); + if (!dst) + dst = inet_csk_rebuild_route(sk, &inet->cork.fl); +out: + return dst; +} +EXPORT_SYMBOL_GPL(inet_csk_update_pmtu); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 46d1e7199a8..570e61f9611 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -46,9 +46,6 @@ struct inet_diag_entry { u16 userlocks; }; -#define INET_DIAG_PUT(skb, attrtype, attrlen) \ - RTA_DATA(__RTA_PUT(skb, attrtype, attrlen)) - static DEFINE_MUTEX(inet_diag_table_mutex); static const struct inet_diag_handler *inet_diag_lock_handler(int proto) @@ -78,24 +75,22 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, const struct inet_sock *inet = inet_sk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; + struct nlattr *attr; void *info = NULL; - struct inet_diag_meminfo *minfo = NULL; - unsigned char *b = skb_tail_pointer(skb); const struct inet_diag_handler *handler; int ext = req->idiag_ext; handler = inet_diag_table[req->sdiag_protocol]; BUG_ON(handler == NULL); - nlh = NLMSG_PUT(skb, pid, seq, unlh->nlmsg_type, sizeof(*r)); - nlh->nlmsg_flags = nlmsg_flags; + nlh = nlmsg_put(skb, pid, seq, unlh->nlmsg_type, sizeof(*r), + nlmsg_flags); + if (!nlh) + return -EMSGSIZE; - r = NLMSG_DATA(nlh); + r = nlmsg_data(nlh); BUG_ON(sk->sk_state == TCP_TIME_WAIT); - if (ext & (1 << (INET_DIAG_MEMINFO - 1))) - minfo = INET_DIAG_PUT(skb, INET_DIAG_MEMINFO, sizeof(*minfo)); - r->idiag_family = sk->sk_family; r->idiag_state = sk->sk_state; r->idiag_timer = 0; @@ -113,7 +108,8 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, * hence this needs to be included regardless of socket family. */ if (ext & (1 << (INET_DIAG_TOS - 1))) - RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos); + if (nla_put_u8(skb, INET_DIAG_TOS, inet->tos) < 0) + goto errout; #if IS_ENABLED(CONFIG_IPV6) if (r->idiag_family == AF_INET6) { @@ -121,24 +117,31 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, *(struct in6_addr *)r->id.idiag_src = np->rcv_saddr; *(struct in6_addr *)r->id.idiag_dst = np->daddr; + if (ext & (1 << (INET_DIAG_TCLASS - 1))) - RTA_PUT_U8(skb, INET_DIAG_TCLASS, np->tclass); + if (nla_put_u8(skb, INET_DIAG_TCLASS, np->tclass) < 0) + goto errout; } #endif r->idiag_uid = sock_i_uid(sk); r->idiag_inode = sock_i_ino(sk); - if (minfo) { - minfo->idiag_rmem = sk_rmem_alloc_get(sk); - minfo->idiag_wmem = sk->sk_wmem_queued; - minfo->idiag_fmem = sk->sk_forward_alloc; - minfo->idiag_tmem = sk_wmem_alloc_get(sk); + if (ext & (1 << (INET_DIAG_MEMINFO - 1))) { + struct inet_diag_meminfo minfo = { + .idiag_rmem = sk_rmem_alloc_get(sk), + .idiag_wmem = sk->sk_wmem_queued, + .idiag_fmem = sk->sk_forward_alloc, + .idiag_tmem = sk_wmem_alloc_get(sk), + }; + + if (nla_put(skb, INET_DIAG_MEMINFO, sizeof(minfo), &minfo) < 0) + goto errout; } if (ext & (1 << (INET_DIAG_SKMEMINFO - 1))) if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO)) - goto rtattr_failure; + goto errout; if (icsk == NULL) { handler->idiag_get_info(sk, r, NULL); @@ -165,16 +168,20 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, } #undef EXPIRES_IN_MS - if (ext & (1 << (INET_DIAG_INFO - 1))) - info = INET_DIAG_PUT(skb, INET_DIAG_INFO, sizeof(struct tcp_info)); - - if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops) { - const size_t len = strlen(icsk->icsk_ca_ops->name); + if (ext & (1 << (INET_DIAG_INFO - 1))) { + attr = nla_reserve(skb, INET_DIAG_INFO, + sizeof(struct tcp_info)); + if (!attr) + goto errout; - strcpy(INET_DIAG_PUT(skb, INET_DIAG_CONG, len + 1), - icsk->icsk_ca_ops->name); + info = nla_data(attr); } + if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops) + if (nla_put_string(skb, INET_DIAG_CONG, + icsk->icsk_ca_ops->name) < 0) + goto errout; + handler->idiag_get_info(sk, r, info); if (sk->sk_state < TCP_TIME_WAIT && @@ -182,12 +189,10 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, icsk->icsk_ca_ops->get_info(sk, ext, skb); out: - nlh->nlmsg_len = skb_tail_pointer(skb) - b; - return skb->len; + return nlmsg_end(skb, nlh); -rtattr_failure: -nlmsg_failure: - nlmsg_trim(skb, b); +errout: + nlmsg_cancel(skb, nlh); return -EMSGSIZE; } EXPORT_SYMBOL_GPL(inet_sk_diag_fill); @@ -208,14 +213,15 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, { long tmo; struct inet_diag_msg *r; - const unsigned char *previous_tail = skb_tail_pointer(skb); - struct nlmsghdr *nlh = NLMSG_PUT(skb, pid, seq, - unlh->nlmsg_type, sizeof(*r)); + struct nlmsghdr *nlh; - r = NLMSG_DATA(nlh); - BUG_ON(tw->tw_state != TCP_TIME_WAIT); + nlh = nlmsg_put(skb, pid, seq, unlh->nlmsg_type, sizeof(*r), + nlmsg_flags); + if (!nlh) + return -EMSGSIZE; - nlh->nlmsg_flags = nlmsg_flags; + r = nlmsg_data(nlh); + BUG_ON(tw->tw_state != TCP_TIME_WAIT); tmo = tw->tw_ttd - jiffies; if (tmo < 0) @@ -245,11 +251,8 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, *(struct in6_addr *)r->id.idiag_dst = tw6->tw_v6_daddr; } #endif - nlh->nlmsg_len = skb_tail_pointer(skb) - previous_tail; - return skb->len; -nlmsg_failure: - nlmsg_trim(skb, previous_tail); - return -EMSGSIZE; + + return nlmsg_end(skb, nlh); } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, @@ -269,16 +272,17 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_s int err; struct sock *sk; struct sk_buff *rep; + struct net *net = sock_net(in_skb->sk); err = -EINVAL; if (req->sdiag_family == AF_INET) { - sk = inet_lookup(&init_net, hashinfo, req->id.idiag_dst[0], + sk = inet_lookup(net, hashinfo, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if); } #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) { - sk = inet6_lookup(&init_net, hashinfo, + sk = inet6_lookup(net, hashinfo, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, (struct in6_addr *)req->id.idiag_src, @@ -298,23 +302,23 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_s if (err) goto out; - err = -ENOMEM; - rep = alloc_skb(NLMSG_SPACE((sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + - sizeof(struct tcp_info) + 64)), - GFP_KERNEL); - if (!rep) + rep = nlmsg_new(sizeof(struct inet_diag_msg) + + sizeof(struct inet_diag_meminfo) + + sizeof(struct tcp_info) + 64, GFP_KERNEL); + if (!rep) { + err = -ENOMEM; goto out; + } err = sk_diag_fill(sk, rep, req, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, 0, nlh); if (err < 0) { WARN_ON(err == -EMSGSIZE); - kfree_skb(rep); + nlmsg_free(rep); goto out; } - err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid, + err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); if (err > 0) err = 0; @@ -592,15 +596,16 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, { const struct inet_request_sock *ireq = inet_rsk(req); struct inet_sock *inet = inet_sk(sk); - unsigned char *b = skb_tail_pointer(skb); struct inet_diag_msg *r; struct nlmsghdr *nlh; long tmo; - nlh = NLMSG_PUT(skb, pid, seq, unlh->nlmsg_type, sizeof(*r)); - nlh->nlmsg_flags = NLM_F_MULTI; - r = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, unlh->nlmsg_type, sizeof(*r), + NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + r = nlmsg_data(nlh); r->idiag_family = sk->sk_family; r->idiag_state = TCP_SYN_RECV; r->idiag_timer = 1; @@ -628,13 +633,8 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, *(struct in6_addr *)r->id.idiag_dst = inet6_rsk(req)->rmt_addr; } #endif - nlh->nlmsg_len = skb_tail_pointer(skb) - b; - - return skb->len; -nlmsg_failure: - nlmsg_trim(skb, b); - return -1; + return nlmsg_end(skb, nlh); } static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, @@ -725,6 +725,7 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, { int i, num; int s_i, s_num; + struct net *net = sock_net(skb->sk); s_i = cb->args[1]; s_num = num = cb->args[2]; @@ -744,6 +745,9 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, sk_nulls_for_each(sk, node, &ilb->head) { struct inet_sock *inet = inet_sk(sk); + if (!net_eq(sock_net(sk), net)) + continue; + if (num < s_num) { num++; continue; @@ -814,6 +818,8 @@ skip_listen_ht: sk_nulls_for_each(sk, node, &head->chain) { struct inet_sock *inet = inet_sk(sk); + if (!net_eq(sock_net(sk), net)) + continue; if (num < s_num) goto next_normal; if (!(r->idiag_states & (1 << sk->sk_state))) @@ -840,6 +846,8 @@ next_normal: inet_twsk_for_each(tw, node, &head->twchain) { + if (!net_eq(twsk_net(tw), net)) + continue; if (num < s_num) goto next_dying; @@ -892,7 +900,7 @@ static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) if (nlmsg_attrlen(cb->nlh, hdrlen)) bc = nlmsg_find_attr(cb->nlh, hdrlen, INET_DIAG_REQ_BYTECODE); - return __inet_diag_dump(skb, cb, (struct inet_diag_req_v2 *)NLMSG_DATA(cb->nlh), bc); + return __inet_diag_dump(skb, cb, nlmsg_data(cb->nlh), bc); } static inline int inet_diag_type2proto(int type) @@ -909,7 +917,7 @@ static inline int inet_diag_type2proto(int type) static int inet_diag_dump_compat(struct sk_buff *skb, struct netlink_callback *cb) { - struct inet_diag_req *rc = NLMSG_DATA(cb->nlh); + struct inet_diag_req *rc = nlmsg_data(cb->nlh); struct inet_diag_req_v2 req; struct nlattr *bc = NULL; int hdrlen = sizeof(struct inet_diag_req); @@ -929,7 +937,7 @@ static int inet_diag_dump_compat(struct sk_buff *skb, struct netlink_callback *c static int inet_diag_get_exact_compat(struct sk_buff *in_skb, const struct nlmsghdr *nlh) { - struct inet_diag_req *rc = NLMSG_DATA(nlh); + struct inet_diag_req *rc = nlmsg_data(nlh); struct inet_diag_req_v2 req; req.sdiag_family = rc->idiag_family; @@ -944,6 +952,7 @@ static int inet_diag_get_exact_compat(struct sk_buff *in_skb, static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) { int hdrlen = sizeof(struct inet_diag_req); + struct net *net = sock_net(skb->sk); if (nlh->nlmsg_type >= INET_DIAG_GETSOCK_MAX || nlmsg_len(nlh) < hdrlen) @@ -964,7 +973,7 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) struct netlink_dump_control c = { .dump = inet_diag_dump_compat, }; - return netlink_dump_start(sock_diag_nlsk, skb, nlh, &c); + return netlink_dump_start(net->diag_nlsk, skb, nlh, &c); } } @@ -974,6 +983,7 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) { int hdrlen = sizeof(struct inet_diag_req_v2); + struct net *net = sock_net(skb->sk); if (nlmsg_len(h) < hdrlen) return -EINVAL; @@ -992,11 +1002,11 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) struct netlink_dump_control c = { .dump = inet_diag_dump, }; - return netlink_dump_start(sock_diag_nlsk, skb, h, &c); + return netlink_dump_start(net->diag_nlsk, skb, h, &c); } } - return inet_diag_get_exact(skb, h, (struct inet_diag_req_v2 *)NLMSG_DATA(h)); + return inet_diag_get_exact(skb, h, nlmsg_data(h)); } static const struct sock_diag_handler inet_diag_handler = { diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 5ff2a51b6d0..85190e69297 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -243,12 +243,12 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, if (q == NULL) return NULL; + q->net = nf; f->constructor(q, arg); atomic_add(f->qsize, &nf->mem); setup_timer(&q->timer, f->frag_expire, (unsigned long)q); spin_lock_init(&q->lock); atomic_set(&q->refcnt, 1); - q->net = nf; return q; } diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index dfba343b250..e1e0a4e8fd3 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -82,23 +82,39 @@ static const struct inet_peer peer_fake_node = { .avl_height = 0 }; -struct inet_peer_base { - struct inet_peer __rcu *root; - seqlock_t lock; - int total; -}; +void inet_peer_base_init(struct inet_peer_base *bp) +{ + bp->root = peer_avl_empty_rcu; + seqlock_init(&bp->lock); + bp->flush_seq = ~0U; + bp->total = 0; +} +EXPORT_SYMBOL_GPL(inet_peer_base_init); -static struct inet_peer_base v4_peers = { - .root = peer_avl_empty_rcu, - .lock = __SEQLOCK_UNLOCKED(v4_peers.lock), - .total = 0, -}; +static atomic_t v4_seq = ATOMIC_INIT(0); +static atomic_t v6_seq = ATOMIC_INIT(0); -static struct inet_peer_base v6_peers = { - .root = peer_avl_empty_rcu, - .lock = __SEQLOCK_UNLOCKED(v6_peers.lock), - .total = 0, -}; +static atomic_t *inetpeer_seq_ptr(int family) +{ + return (family == AF_INET ? &v4_seq : &v6_seq); +} + +static inline void flush_check(struct inet_peer_base *base, int family) +{ + atomic_t *fp = inetpeer_seq_ptr(family); + + if (unlikely(base->flush_seq != atomic_read(fp))) { + inetpeer_invalidate_tree(base); + base->flush_seq = atomic_read(fp); + } +} + +void inetpeer_invalidate_family(int family) +{ + atomic_t *fp = inetpeer_seq_ptr(family); + + atomic_inc(fp); +} #define PEER_MAXDEPTH 40 /* sufficient for about 2^27 nodes */ @@ -110,7 +126,7 @@ int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min static void inetpeer_gc_worker(struct work_struct *work) { - struct inet_peer *p, *n; + struct inet_peer *p, *n, *c; LIST_HEAD(list); spin_lock_bh(&gc_lock); @@ -122,17 +138,19 @@ static void inetpeer_gc_worker(struct work_struct *work) list_for_each_entry_safe(p, n, &list, gc_list) { - if(need_resched()) + if (need_resched()) cond_resched(); - if (p->avl_left != peer_avl_empty) { - list_add_tail(&p->avl_left->gc_list, &list); - p->avl_left = peer_avl_empty; + c = rcu_dereference_protected(p->avl_left, 1); + if (c != peer_avl_empty) { + list_add_tail(&c->gc_list, &list); + p->avl_left = peer_avl_empty_rcu; } - if (p->avl_right != peer_avl_empty) { - list_add_tail(&p->avl_right->gc_list, &list); - p->avl_right = peer_avl_empty; + c = rcu_dereference_protected(p->avl_right, 1); + if (c != peer_avl_empty) { + list_add_tail(&c->gc_list, &list); + p->avl_right = peer_avl_empty_rcu; } n = list_entry(p->gc_list.next, struct inet_peer, gc_list); @@ -401,11 +419,6 @@ static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base, call_rcu(&p->rcu, inetpeer_free_rcu); } -static struct inet_peer_base *family_to_base(int family) -{ - return family == AF_INET ? &v4_peers : &v6_peers; -} - /* perform garbage collect on all items stacked during a lookup */ static int inet_peer_gc(struct inet_peer_base *base, struct inet_peer __rcu **stack[PEER_MAXDEPTH], @@ -443,14 +456,17 @@ static int inet_peer_gc(struct inet_peer_base *base, return cnt; } -struct inet_peer *inet_getpeer(const struct inetpeer_addr *daddr, int create) +struct inet_peer *inet_getpeer(struct inet_peer_base *base, + const struct inetpeer_addr *daddr, + int create) { struct inet_peer __rcu **stack[PEER_MAXDEPTH], ***stackptr; - struct inet_peer_base *base = family_to_base(daddr->family); struct inet_peer *p; unsigned int sequence; int invalidated, gccnt = 0; + flush_check(base, daddr->family); + /* Attempt a lockless lookup first. * Because of a concurrent writer, we might not find an existing entry. */ @@ -492,13 +508,9 @@ relookup: (daddr->family == AF_INET) ? secure_ip_id(daddr->addr.a4) : secure_ipv6_id(daddr->addr.a6)); - p->tcp_ts_stamp = 0; p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; p->rate_last = 0; - p->pmtu_expires = 0; - p->pmtu_orig = 0; - memset(&p->redirect_learned, 0, sizeof(p->redirect_learned)); INIT_LIST_HEAD(&p->gc_list); /* Link the node. */ @@ -571,26 +583,19 @@ static void inetpeer_inval_rcu(struct rcu_head *head) schedule_delayed_work(&gc_work, gc_delay); } -void inetpeer_invalidate_tree(int family) +void inetpeer_invalidate_tree(struct inet_peer_base *base) { - struct inet_peer *old, *new, *prev; - struct inet_peer_base *base = family_to_base(family); + struct inet_peer *root; write_seqlock_bh(&base->lock); - old = base->root; - if (old == peer_avl_empty_rcu) - goto out; - - new = peer_avl_empty_rcu; - - prev = cmpxchg(&base->root, old, new); - if (prev == old) { + root = rcu_deref_locked(base->root, base); + if (root != peer_avl_empty) { + base->root = peer_avl_empty_rcu; base->total = 0; - call_rcu(&prev->gc_rcu, inetpeer_inval_rcu); + call_rcu(&root->gc_rcu, inetpeer_inval_rcu); } -out: write_sequnlock_bh(&base->lock); } EXPORT_SYMBOL(inetpeer_invalidate_tree); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 9dbd3dd6022..8d07c973409 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -171,6 +171,10 @@ static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb) static void ip4_frag_init(struct inet_frag_queue *q, void *a) { struct ipq *qp = container_of(q, struct ipq, q); + struct netns_ipv4 *ipv4 = container_of(q->net, struct netns_ipv4, + frags); + struct net *net = container_of(ipv4, struct net, ipv4); + struct ip4_create_arg *arg = a; qp->protocol = arg->iph->protocol; @@ -180,7 +184,7 @@ static void ip4_frag_init(struct inet_frag_queue *q, void *a) qp->daddr = arg->iph->daddr; qp->user = arg->user; qp->peer = sysctl_ipfrag_max_dist ? - inet_getpeer_v4(arg->iph->saddr, 1) : NULL; + inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, 1) : NULL; } static __inline__ void ip4_frag_free(struct inet_frag_queue *q) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index f49047b7960..b062a98574f 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -516,9 +516,6 @@ static void ipgre_err(struct sk_buff *skb, u32 info) case ICMP_PORT_UNREACH: /* Impossible event. */ return; - case ICMP_FRAG_NEEDED: - /* Soft state for pmtu is maintained by IP core. */ - return; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, @@ -531,6 +528,9 @@ static void ipgre_err(struct sk_buff *skb, u32 info) if (code != ICMP_EXC_TTL) return; break; + + case ICMP_REDIRECT: + break; } rcu_read_lock(); @@ -538,7 +538,20 @@ static void ipgre_err(struct sk_buff *skb, u32 info) flags & GRE_KEY ? *(((__be32 *)p) + (grehlen / 4) - 1) : 0, p[1]); - if (t == NULL || t->parms.iph.daddr == 0 || + if (t == NULL) + goto out; + + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { + ipv4_update_pmtu(skb, dev_net(skb->dev), info, + t->parms.link, 0, IPPROTO_GRE, 0); + goto out; + } + if (type == ICMP_REDIRECT) { + ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0, + IPPROTO_GRE, 0); + goto out; + } + if (t->parms.iph.daddr == 0 || ipv4_is_multicast(t->parms.iph.daddr)) goto out; @@ -753,7 +766,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (skb->protocol == htons(ETH_P_IP)) { rt = skb_rtable(skb); - dst = rt->rt_gateway; + dst = rt_nexthop(rt, old_iph->daddr); } #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { @@ -820,7 +833,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { df |= (old_iph->frag_off&htons(IP_DF)); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 8590144ca33..f1395a6fb35 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -198,14 +198,13 @@ static int ip_local_deliver_finish(struct sk_buff *skb) rcu_read_lock(); { int protocol = ip_hdr(skb)->protocol; - int hash, raw; const struct net_protocol *ipprot; + int raw; resubmit: raw = raw_local_deliver(skb, protocol); - hash = protocol & (MAX_INET_PROTOS - 1); - ipprot = rcu_dereference(inet_protos[hash]); + ipprot = rcu_dereference(inet_protos[protocol]); if (ipprot != NULL) { int ret; @@ -314,26 +313,35 @@ drop: return true; } +int sysctl_ip_early_demux __read_mostly = 1; +EXPORT_SYMBOL(sysctl_ip_early_demux); + static int ip_rcv_finish(struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; + if (sysctl_ip_early_demux && !skb_dst(skb)) { + const struct net_protocol *ipprot; + int protocol = iph->protocol; + + ipprot = rcu_dereference(inet_protos[protocol]); + if (ipprot && ipprot->early_demux) { + ipprot->early_demux(skb); + /* must reload iph, skb->head might have changed */ + iph = ip_hdr(skb); + } + } + /* * Initialise the virtual path cache for the packet. It describes * how the packet travels inside Linux networking. */ - if (skb_dst(skb) == NULL) { + if (!skb_dst(skb)) { int err = ip_route_input_noref(skb, iph->daddr, iph->saddr, iph->tos, skb->dev); if (unlikely(err)) { - if (err == -EHOSTUNREACH) - IP_INC_STATS_BH(dev_net(skb->dev), - IPSTATS_MIB_INADDRERRORS); - else if (err == -ENETUNREACH) - IP_INC_STATS_BH(dev_net(skb->dev), - IPSTATS_MIB_INNOROUTES); - else if (err == -EXDEV) + if (err == -EXDEV) NET_INC_STATS_BH(dev_net(skb->dev), LINUX_MIB_IPRPFILTER); goto drop; diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 708b99494e2..1dc01f9793d 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -27,6 +27,7 @@ #include <net/icmp.h> #include <net/route.h> #include <net/cipso_ipv4.h> +#include <net/ip_fib.h> /* * Write options to IP header, record destination address to @@ -92,7 +93,6 @@ int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb) unsigned char *sptr, *dptr; int soffset, doffset; int optlen; - __be32 daddr; memset(dopt, 0, sizeof(struct ip_options)); @@ -104,8 +104,6 @@ int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb) sptr = skb_network_header(skb); dptr = dopt->__data; - daddr = skb_rtable(skb)->rt_spec_dst; - if (sopt->rr) { optlen = sptr[sopt->rr+1]; soffset = sptr[sopt->rr+2]; @@ -179,6 +177,8 @@ int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb) doffset -= 4; } if (doffset > 3) { + __be32 daddr = fib_compute_spec_dst(skb); + memcpy(&start[doffset-1], &daddr, 4); dopt->faddr = faddr; dptr[0] = start[0]; @@ -241,6 +241,15 @@ void ip_options_fragment(struct sk_buff *skb) opt->ts_needtime = 0; } +/* helper used by ip_options_compile() to call fib_compute_spec_dst() + * at most one time. + */ +static void spec_dst_fill(__be32 *spec_dst, struct sk_buff *skb) +{ + if (*spec_dst == htonl(INADDR_ANY)) + *spec_dst = fib_compute_spec_dst(skb); +} + /* * Verify options and fill pointers in struct options. * Caller should clear *opt, and set opt->data. @@ -250,12 +259,12 @@ void ip_options_fragment(struct sk_buff *skb) int ip_options_compile(struct net *net, struct ip_options *opt, struct sk_buff *skb) { - int l; - unsigned char *iph; - unsigned char *optptr; - int optlen; + __be32 spec_dst = htonl(INADDR_ANY); unsigned char *pp_ptr = NULL; struct rtable *rt = NULL; + unsigned char *optptr; + unsigned char *iph; + int optlen, l; if (skb != NULL) { rt = skb_rtable(skb); @@ -331,7 +340,8 @@ int ip_options_compile(struct net *net, goto error; } if (rt) { - memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4); + spec_dst_fill(&spec_dst, skb); + memcpy(&optptr[optptr[2]-1], &spec_dst, 4); opt->is_changed = 1; } optptr[2] += 4; @@ -373,7 +383,8 @@ int ip_options_compile(struct net *net, } opt->ts = optptr - iph; if (rt) { - memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4); + spec_dst_fill(&spec_dst, skb); + memcpy(&optptr[optptr[2]-1], &spec_dst, 4); timeptr = &optptr[optptr[2]+3]; } opt->ts_needaddr = 1; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 451f97c42eb..c196d749daf 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -113,19 +113,6 @@ int ip_local_out(struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ip_local_out); -/* dev_loopback_xmit for use with netfilter. */ -static int ip_dev_loopback_xmit(struct sk_buff *newskb) -{ - skb_reset_mac_header(newskb); - __skb_pull(newskb, skb_network_offset(newskb)); - newskb->pkt_type = PACKET_LOOPBACK; - newskb->ip_summed = CHECKSUM_UNNECESSARY; - WARN_ON(!skb_dst(newskb)); - skb_dst_force(newskb); - netif_rx_ni(newskb); - return 0; -} - static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) { int ttl = inet->uc_ttl; @@ -183,6 +170,7 @@ static inline int ip_finish_output2(struct sk_buff *skb) struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; + u32 nexthop; if (rt->rt_type == RTN_MULTICAST) { IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUTMCAST, skb->len); @@ -200,19 +188,22 @@ static inline int ip_finish_output2(struct sk_buff *skb) } if (skb->sk) skb_set_owner_w(skb2, skb->sk); - kfree_skb(skb); + consume_skb(skb); skb = skb2; } - rcu_read_lock(); - neigh = dst_get_neighbour_noref(dst); - if (neigh) { - int res = neigh_output(neigh, skb); + rcu_read_lock_bh(); + nexthop = rt->rt_gateway ? rt->rt_gateway : ip_hdr(skb)->daddr; + neigh = __ipv4_neigh_lookup_noref(dev, nexthop); + if (unlikely(!neigh)) + neigh = __neigh_create(&arp_tbl, &nexthop, dev, false); + if (!IS_ERR(neigh)) { + int res = dst_neigh_output(dst, neigh, skb); - rcu_read_unlock(); + rcu_read_unlock_bh(); return res; } - rcu_read_unlock(); + rcu_read_unlock_bh(); net_dbg_ratelimited("%s: No header cache and no neighbour!\n", __func__); @@ -281,7 +272,7 @@ int ip_mc_output(struct sk_buff *skb) if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, newskb, NULL, newskb->dev, - ip_dev_loopback_xmit); + dev_loopback_xmit); } /* Multicasts with ttl 0 must not go beyond the host */ @@ -296,7 +287,7 @@ int ip_mc_output(struct sk_buff *skb) struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, newskb, - NULL, newskb->dev, ip_dev_loopback_xmit); + NULL, newskb->dev, dev_loopback_xmit); } return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL, @@ -380,7 +371,7 @@ int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl) skb_dst_set_noref(skb, &rt->dst); packet_routed: - if (inet_opt && inet_opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway) + if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gateway) goto no_route; /* OK, we know where to send it, allocate and build IP header. */ @@ -709,7 +700,7 @@ slow_path: IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGCREATES); } - kfree_skb(skb); + consume_skb(skb); IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGOKS); return err; @@ -1347,10 +1338,10 @@ struct sk_buff *__ip_make_skb(struct sock *sk, iph->ihl = 5; iph->tos = inet->tos; iph->frag_off = df; - ip_select_ident(iph, &rt->dst, sk); iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); + ip_select_ident(iph, &rt->dst, sk); if (opt) { iph->ihl += opt->optlen>>2; @@ -1375,9 +1366,8 @@ out: return skb; } -int ip_send_skb(struct sk_buff *skb) +int ip_send_skb(struct net *net, struct sk_buff *skb) { - struct net *net = sock_net(skb->sk); int err; err = ip_local_out(skb); @@ -1400,7 +1390,7 @@ int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4) return 0; /* Netfilter gets whole the not fragmented skb. */ - return ip_send_skb(skb); + return ip_send_skb(sock_net(sk), skb); } /* @@ -1472,19 +1462,34 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset, /* * Generic function to send a packet as reply to another packet. - * Used to send TCP resets so far. ICMP should use this function too. + * Used to send some TCP resets/acks so far. * - * Should run single threaded per socket because it uses the sock - * structure to pass arguments. + * Use a fake percpu inet socket to avoid false sharing and contention. */ -void ip_send_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr, - const struct ip_reply_arg *arg, unsigned int len) +static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = { + .sk = { + .__sk_common = { + .skc_refcnt = ATOMIC_INIT(1), + }, + .sk_wmem_alloc = ATOMIC_INIT(1), + .sk_allocation = GFP_ATOMIC, + .sk_flags = (1UL << SOCK_USE_WRITE_QUEUE), + }, + .pmtudisc = IP_PMTUDISC_WANT, + .uc_ttl = -1, +}; + +void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, + __be32 saddr, const struct ip_reply_arg *arg, + unsigned int len) { - struct inet_sock *inet = inet_sk(sk); struct ip_options_data replyopts; struct ipcm_cookie ipc; struct flowi4 fl4; struct rtable *rt = skb_rtable(skb); + struct sk_buff *nskb; + struct sock *sk; + struct inet_sock *inet; if (ip_options_echo(&replyopts.opt.opt, skb)) return; @@ -1502,38 +1507,40 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr, flowi4_init_output(&fl4, arg->bound_dev_if, 0, RT_TOS(arg->tos), - RT_SCOPE_UNIVERSE, sk->sk_protocol, + RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol, ip_reply_arg_flowi_flags(arg), - daddr, rt->rt_spec_dst, + daddr, saddr, tcp_hdr(skb)->source, tcp_hdr(skb)->dest); security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); - rt = ip_route_output_key(sock_net(sk), &fl4); + rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) return; - /* And let IP do all the hard work. + inet = &get_cpu_var(unicast_sock); - This chunk is not reenterable, hence spinlock. - Note that it uses the fact, that this function is called - with locally disabled BH and that sk cannot be already spinlocked. - */ - bh_lock_sock(sk); inet->tos = arg->tos; + sk = &inet->sk; sk->sk_priority = skb->priority; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; + sock_net_set(sk, net); + __skb_queue_head_init(&sk->sk_write_queue); + sk->sk_sndbuf = sysctl_wmem_default; ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); - if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) { + nskb = skb_peek(&sk->sk_write_queue); + if (nskb) { if (arg->csumoffset >= 0) - *((__sum16 *)skb_transport_header(skb) + - arg->csumoffset) = csum_fold(csum_add(skb->csum, + *((__sum16 *)skb_transport_header(nskb) + + arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); - skb->ip_summed = CHECKSUM_NONE; + nskb->ip_summed = CHECKSUM_NONE; + skb_orphan(nskb); + skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb)); ip_push_pending_frames(sk, &fl4); } - bh_unlock_sock(sk); + put_cpu_var(unicast_sock); ip_rt_put(rt); } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 0d11f234d61..5eea4a81104 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -40,6 +40,7 @@ #if IS_ENABLED(CONFIG_IPV6) #include <net/transp_v6.h> #endif +#include <net/ip_fib.h> #include <linux/errqueue.h> #include <asm/uaccess.h> @@ -1019,18 +1020,17 @@ e_inval: * @sk: socket * @skb: buffer * - * To support IP_CMSG_PKTINFO option, we store rt_iif and rt_spec_dst - * in skb->cb[] before dst drop. + * To support IP_CMSG_PKTINFO option, we store rt_iif and specific + * destination in skb->cb[] before dst drop. * This way, receiver doesnt make cache line misses to read rtable. */ void ipv4_pktinfo_prepare(struct sk_buff *skb) { struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); - const struct rtable *rt = skb_rtable(skb); - if (rt) { - pktinfo->ipi_ifindex = rt->rt_iif; - pktinfo->ipi_spec_dst.s_addr = rt->rt_spec_dst; + if (skb_rtable(skb)) { + pktinfo->ipi_ifindex = inet_iif(skb); + pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb); } else { pktinfo->ipi_ifindex = 0; pktinfo->ipi_spec_dst.s_addr = 0; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c new file mode 100644 index 00000000000..3511ffba7bd --- /dev/null +++ b/net/ipv4/ip_vti.c @@ -0,0 +1,956 @@ +/* + * Linux NET3: IP/IP protocol decoder modified to support + * virtual tunnel interface + * + * Authors: + * Saurabh Mohan (saurabh.mohan@vyatta.com) 05/07/2012 + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +/* + This version of net/ipv4/ip_vti.c is cloned of net/ipv4/ipip.c + + For comments look at net/ipv4/ip_gre.c --ANK + */ + + +#include <linux/capability.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/uaccess.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/in.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/if_arp.h> +#include <linux/mroute.h> +#include <linux/init.h> +#include <linux/netfilter_ipv4.h> +#include <linux/if_ether.h> + +#include <net/sock.h> +#include <net/ip.h> +#include <net/icmp.h> +#include <net/ipip.h> +#include <net/inet_ecn.h> +#include <net/xfrm.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> + +#define HASH_SIZE 16 +#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&(HASH_SIZE-1)) + +static struct rtnl_link_ops vti_link_ops __read_mostly; + +static int vti_net_id __read_mostly; +struct vti_net { + struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_r[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_l[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_wc[1]; + struct ip_tunnel __rcu **tunnels[4]; + + struct net_device *fb_tunnel_dev; +}; + +static int vti_fb_tunnel_init(struct net_device *dev); +static int vti_tunnel_init(struct net_device *dev); +static void vti_tunnel_setup(struct net_device *dev); +static void vti_dev_free(struct net_device *dev); +static int vti_tunnel_bind_dev(struct net_device *dev); + +/* Locking : hash tables are protected by RCU and RTNL */ + +#define for_each_ip_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) + +/* often modified stats are per cpu, other are shared (netdev->stats) */ +struct pcpu_tstats { + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + struct u64_stats_sync syncp; +}; + +#define VTI_XMIT(stats1, stats2) do { \ + int err; \ + int pkt_len = skb->len; \ + err = dst_output(skb); \ + if (net_xmit_eval(err) == 0) { \ + u64_stats_update_begin(&(stats1)->syncp); \ + (stats1)->tx_bytes += pkt_len; \ + (stats1)->tx_packets++; \ + u64_stats_update_end(&(stats1)->syncp); \ + } else { \ + (stats2)->tx_errors++; \ + (stats2)->tx_aborted_errors++; \ + } \ +} while (0) + + +static struct rtnl_link_stats64 *vti_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *tot) +{ + int i; + + for_each_possible_cpu(i) { + const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + unsigned int start; + + do { + start = u64_stats_fetch_begin_bh(&tstats->syncp); + rx_packets = tstats->rx_packets; + tx_packets = tstats->tx_packets; + rx_bytes = tstats->rx_bytes; + tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); + + tot->rx_packets += rx_packets; + tot->tx_packets += tx_packets; + tot->rx_bytes += rx_bytes; + tot->tx_bytes += tx_bytes; + } + + tot->multicast = dev->stats.multicast; + tot->rx_crc_errors = dev->stats.rx_crc_errors; + tot->rx_fifo_errors = dev->stats.rx_fifo_errors; + tot->rx_length_errors = dev->stats.rx_length_errors; + tot->rx_errors = dev->stats.rx_errors; + tot->tx_fifo_errors = dev->stats.tx_fifo_errors; + tot->tx_carrier_errors = dev->stats.tx_carrier_errors; + tot->tx_dropped = dev->stats.tx_dropped; + tot->tx_aborted_errors = dev->stats.tx_aborted_errors; + tot->tx_errors = dev->stats.tx_errors; + + return tot; +} + +static struct ip_tunnel *vti_tunnel_lookup(struct net *net, + __be32 remote, __be32 local) +{ + unsigned h0 = HASH(remote); + unsigned h1 = HASH(local); + struct ip_tunnel *t; + struct vti_net *ipn = net_generic(net, vti_net_id); + + for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1]) + if (local == t->parms.iph.saddr && + remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) + return t; + for_each_ip_tunnel_rcu(ipn->tunnels_r[h0]) + if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) + return t; + + for_each_ip_tunnel_rcu(ipn->tunnels_l[h1]) + if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP)) + return t; + + for_each_ip_tunnel_rcu(ipn->tunnels_wc[0]) + if (t && (t->dev->flags&IFF_UP)) + return t; + return NULL; +} + +static struct ip_tunnel __rcu **__vti_bucket(struct vti_net *ipn, + struct ip_tunnel_parm *parms) +{ + __be32 remote = parms->iph.daddr; + __be32 local = parms->iph.saddr; + unsigned h = 0; + int prio = 0; + + if (remote) { + prio |= 2; + h ^= HASH(remote); + } + if (local) { + prio |= 1; + h ^= HASH(local); + } + return &ipn->tunnels[prio][h]; +} + +static inline struct ip_tunnel __rcu **vti_bucket(struct vti_net *ipn, + struct ip_tunnel *t) +{ + return __vti_bucket(ipn, &t->parms); +} + +static void vti_tunnel_unlink(struct vti_net *ipn, struct ip_tunnel *t) +{ + struct ip_tunnel __rcu **tp; + struct ip_tunnel *iter; + + for (tp = vti_bucket(ipn, t); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); + break; + } + } +} + +static void vti_tunnel_link(struct vti_net *ipn, struct ip_tunnel *t) +{ + struct ip_tunnel __rcu **tp = vti_bucket(ipn, t); + + rcu_assign_pointer(t->next, rtnl_dereference(*tp)); + rcu_assign_pointer(*tp, t); +} + +static struct ip_tunnel *vti_tunnel_locate(struct net *net, + struct ip_tunnel_parm *parms, + int create) +{ + __be32 remote = parms->iph.daddr; + __be32 local = parms->iph.saddr; + struct ip_tunnel *t, *nt; + struct ip_tunnel __rcu **tp; + struct net_device *dev; + char name[IFNAMSIZ]; + struct vti_net *ipn = net_generic(net, vti_net_id); + + for (tp = __vti_bucket(ipn, parms); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) { + if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr) + return t; + } + if (!create) + return NULL; + + if (parms->name[0]) + strlcpy(name, parms->name, IFNAMSIZ); + else + strcpy(name, "vti%d"); + + dev = alloc_netdev(sizeof(*t), name, vti_tunnel_setup); + if (dev == NULL) + return NULL; + + dev_net_set(dev, net); + + nt = netdev_priv(dev); + nt->parms = *parms; + dev->rtnl_link_ops = &vti_link_ops; + + vti_tunnel_bind_dev(dev); + + if (register_netdevice(dev) < 0) + goto failed_free; + + dev_hold(dev); + vti_tunnel_link(ipn, nt); + return nt; + +failed_free: + free_netdev(dev); + return NULL; +} + +static void vti_tunnel_uninit(struct net_device *dev) +{ + struct net *net = dev_net(dev); + struct vti_net *ipn = net_generic(net, vti_net_id); + + vti_tunnel_unlink(ipn, netdev_priv(dev)); + dev_put(dev); +} + +static int vti_err(struct sk_buff *skb, u32 info) +{ + + /* All the routers (except for Linux) return only + * 8 bytes of packet payload. It means, that precise relaying of + * ICMP in the real Internet is absolutely infeasible. + */ + struct iphdr *iph = (struct iphdr *)skb->data; + const int type = icmp_hdr(skb)->type; + const int code = icmp_hdr(skb)->code; + struct ip_tunnel *t; + int err; + + switch (type) { + default: + case ICMP_PARAMETERPROB: + return 0; + + case ICMP_DEST_UNREACH: + switch (code) { + case ICMP_SR_FAILED: + case ICMP_PORT_UNREACH: + /* Impossible event. */ + return 0; + default: + /* All others are translated to HOST_UNREACH. */ + break; + } + break; + case ICMP_TIME_EXCEEDED: + if (code != ICMP_EXC_TTL) + return 0; + break; + } + + err = -ENOENT; + + rcu_read_lock(); + t = vti_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr); + if (t == NULL) + goto out; + + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { + ipv4_update_pmtu(skb, dev_net(skb->dev), info, + t->parms.link, 0, IPPROTO_IPIP, 0); + err = 0; + goto out; + } + + err = 0; + if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) + goto out; + + if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) + t->err_count++; + else + t->err_count = 1; + t->err_time = jiffies; +out: + rcu_read_unlock(); + return err; +} + +/* We dont digest the packet therefore let the packet pass */ +static int vti_rcv(struct sk_buff *skb) +{ + struct ip_tunnel *tunnel; + const struct iphdr *iph = ip_hdr(skb); + + rcu_read_lock(); + tunnel = vti_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr); + if (tunnel != NULL) { + struct pcpu_tstats *tstats; + + tstats = this_cpu_ptr(tunnel->dev->tstats); + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + + skb->dev = tunnel->dev; + rcu_read_unlock(); + return 1; + } + rcu_read_unlock(); + + return -1; +} + +/* This function assumes it is being called from dev_queue_xmit() + * and that skb is filled properly by that function. + */ + +static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + struct pcpu_tstats *tstats; + struct iphdr *tiph = &tunnel->parms.iph; + u8 tos; + struct rtable *rt; /* Route to the other host */ + struct net_device *tdev; /* Device to other host */ + struct iphdr *old_iph = ip_hdr(skb); + __be32 dst = tiph->daddr; + struct flowi4 fl4; + + if (skb->protocol != htons(ETH_P_IP)) + goto tx_error; + + tos = old_iph->tos; + + memset(&fl4, 0, sizeof(fl4)); + flowi4_init_output(&fl4, tunnel->parms.link, + htonl(tunnel->parms.i_key), RT_TOS(tos), + RT_SCOPE_UNIVERSE, + IPPROTO_IPIP, 0, + dst, tiph->saddr, 0, 0); + rt = ip_route_output_key(dev_net(dev), &fl4); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } + /* if there is no transform then this tunnel is not functional. + * Or if the xfrm is not mode tunnel. + */ + if (!rt->dst.xfrm || + rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } + tdev = rt->dst.dev; + + if (tdev == dev) { + ip_rt_put(rt); + dev->stats.collisions++; + goto tx_error; + } + + if (tunnel->err_count > 0) { + if (time_before(jiffies, + tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { + tunnel->err_count--; + dst_link_failure(skb); + } else + tunnel->err_count = 0; + } + + IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | + IPSKB_REROUTED); + skb_dst_drop(skb); + skb_dst_set(skb, &rt->dst); + nf_reset(skb); + skb->dev = skb_dst(skb)->dev; + + tstats = this_cpu_ptr(dev->tstats); + VTI_XMIT(tstats, &dev->stats); + return NETDEV_TX_OK; + +tx_error_icmp: + dst_link_failure(skb); +tx_error: + dev->stats.tx_errors++; + dev_kfree_skb(skb); + return NETDEV_TX_OK; +} + +static int vti_tunnel_bind_dev(struct net_device *dev) +{ + struct net_device *tdev = NULL; + struct ip_tunnel *tunnel; + struct iphdr *iph; + + tunnel = netdev_priv(dev); + iph = &tunnel->parms.iph; + + if (iph->daddr) { + struct rtable *rt; + struct flowi4 fl4; + memset(&fl4, 0, sizeof(fl4)); + flowi4_init_output(&fl4, tunnel->parms.link, + htonl(tunnel->parms.i_key), + RT_TOS(iph->tos), RT_SCOPE_UNIVERSE, + IPPROTO_IPIP, 0, + iph->daddr, iph->saddr, 0, 0); + rt = ip_route_output_key(dev_net(dev), &fl4); + if (!IS_ERR(rt)) { + tdev = rt->dst.dev; + ip_rt_put(rt); + } + dev->flags |= IFF_POINTOPOINT; + } + + if (!tdev && tunnel->parms.link) + tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link); + + if (tdev) { + dev->hard_header_len = tdev->hard_header_len + + sizeof(struct iphdr); + dev->mtu = tdev->mtu; + } + dev->iflink = tunnel->parms.link; + return dev->mtu; +} + +static int +vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + int err = 0; + struct ip_tunnel_parm p; + struct ip_tunnel *t; + struct net *net = dev_net(dev); + struct vti_net *ipn = net_generic(net, vti_net_id); + + switch (cmd) { + case SIOCGETTUNNEL: + t = NULL; + if (dev == ipn->fb_tunnel_dev) { + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, + sizeof(p))) { + err = -EFAULT; + break; + } + t = vti_tunnel_locate(net, &p, 0); + } + if (t == NULL) + t = netdev_priv(dev); + memcpy(&p, &t->parms, sizeof(p)); + p.i_flags |= GRE_KEY | VTI_ISVTI; + p.o_flags |= GRE_KEY; + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + err = -EFAULT; + break; + + case SIOCADDTUNNEL: + case SIOCCHGTUNNEL: + err = -EPERM; + if (!capable(CAP_NET_ADMIN)) + goto done; + + err = -EFAULT; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + goto done; + + err = -EINVAL; + if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP || + p.iph.ihl != 5) + goto done; + + t = vti_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL); + + if (dev != ipn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { + if (t != NULL) { + if (t->dev != dev) { + err = -EEXIST; + break; + } + } else { + if (((dev->flags&IFF_POINTOPOINT) && + !p.iph.daddr) || + (!(dev->flags&IFF_POINTOPOINT) && + p.iph.daddr)) { + err = -EINVAL; + break; + } + t = netdev_priv(dev); + vti_tunnel_unlink(ipn, t); + synchronize_net(); + t->parms.iph.saddr = p.iph.saddr; + t->parms.iph.daddr = p.iph.daddr; + t->parms.i_key = p.i_key; + t->parms.o_key = p.o_key; + t->parms.iph.protocol = IPPROTO_IPIP; + memcpy(dev->dev_addr, &p.iph.saddr, 4); + memcpy(dev->broadcast, &p.iph.daddr, 4); + vti_tunnel_link(ipn, t); + netdev_state_change(dev); + } + } + + if (t) { + err = 0; + if (cmd == SIOCCHGTUNNEL) { + t->parms.i_key = p.i_key; + t->parms.o_key = p.o_key; + if (t->parms.link != p.link) { + t->parms.link = p.link; + vti_tunnel_bind_dev(dev); + netdev_state_change(dev); + } + } + p.i_flags |= GRE_KEY | VTI_ISVTI; + p.o_flags |= GRE_KEY; + if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, + sizeof(p))) + err = -EFAULT; + } else + err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); + break; + + case SIOCDELTUNNEL: + err = -EPERM; + if (!capable(CAP_NET_ADMIN)) + goto done; + + if (dev == ipn->fb_tunnel_dev) { + err = -EFAULT; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, + sizeof(p))) + goto done; + err = -ENOENT; + + t = vti_tunnel_locate(net, &p, 0); + if (t == NULL) + goto done; + err = -EPERM; + if (t->dev == ipn->fb_tunnel_dev) + goto done; + dev = t->dev; + } + unregister_netdevice(dev); + err = 0; + break; + + default: + err = -EINVAL; + } + +done: + return err; +} + +static int vti_tunnel_change_mtu(struct net_device *dev, int new_mtu) +{ + if (new_mtu < 68 || new_mtu > 0xFFF8) + return -EINVAL; + dev->mtu = new_mtu; + return 0; +} + +static const struct net_device_ops vti_netdev_ops = { + .ndo_init = vti_tunnel_init, + .ndo_uninit = vti_tunnel_uninit, + .ndo_start_xmit = vti_tunnel_xmit, + .ndo_do_ioctl = vti_tunnel_ioctl, + .ndo_change_mtu = vti_tunnel_change_mtu, + .ndo_get_stats64 = vti_get_stats64, +}; + +static void vti_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + +static void vti_tunnel_setup(struct net_device *dev) +{ + dev->netdev_ops = &vti_netdev_ops; + dev->destructor = vti_dev_free; + + dev->type = ARPHRD_TUNNEL; + dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); + dev->mtu = ETH_DATA_LEN; + dev->flags = IFF_NOARP; + dev->iflink = 0; + dev->addr_len = 4; + dev->features |= NETIF_F_NETNS_LOCAL; + dev->features |= NETIF_F_LLTX; + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; +} + +static int vti_tunnel_init(struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + + tunnel->dev = dev; + strcpy(tunnel->parms.name, dev->name); + + memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); + memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); + + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + + return 0; +} + +static int __net_init vti_fb_tunnel_init(struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + struct iphdr *iph = &tunnel->parms.iph; + struct vti_net *ipn = net_generic(dev_net(dev), vti_net_id); + + tunnel->dev = dev; + strcpy(tunnel->parms.name, dev->name); + + iph->version = 4; + iph->protocol = IPPROTO_IPIP; + iph->ihl = 5; + + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + + dev_hold(dev); + rcu_assign_pointer(ipn->tunnels_wc[0], tunnel); + return 0; +} + +static struct xfrm_tunnel vti_handler __read_mostly = { + .handler = vti_rcv, + .err_handler = vti_err, + .priority = 1, +}; + +static void vti_destroy_tunnels(struct vti_net *ipn, struct list_head *head) +{ + int prio; + + for (prio = 1; prio < 4; prio++) { + int h; + for (h = 0; h < HASH_SIZE; h++) { + struct ip_tunnel *t; + + t = rtnl_dereference(ipn->tunnels[prio][h]); + while (t != NULL) { + unregister_netdevice_queue(t->dev, head); + t = rtnl_dereference(t->next); + } + } + } +} + +static int __net_init vti_init_net(struct net *net) +{ + int err; + struct vti_net *ipn = net_generic(net, vti_net_id); + + ipn->tunnels[0] = ipn->tunnels_wc; + ipn->tunnels[1] = ipn->tunnels_l; + ipn->tunnels[2] = ipn->tunnels_r; + ipn->tunnels[3] = ipn->tunnels_r_l; + + ipn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), + "ip_vti0", + vti_tunnel_setup); + if (!ipn->fb_tunnel_dev) { + err = -ENOMEM; + goto err_alloc_dev; + } + dev_net_set(ipn->fb_tunnel_dev, net); + + err = vti_fb_tunnel_init(ipn->fb_tunnel_dev); + if (err) + goto err_reg_dev; + ipn->fb_tunnel_dev->rtnl_link_ops = &vti_link_ops; + + err = register_netdev(ipn->fb_tunnel_dev); + if (err) + goto err_reg_dev; + return 0; + +err_reg_dev: + vti_dev_free(ipn->fb_tunnel_dev); +err_alloc_dev: + /* nothing */ + return err; +} + +static void __net_exit vti_exit_net(struct net *net) +{ + struct vti_net *ipn = net_generic(net, vti_net_id); + LIST_HEAD(list); + + rtnl_lock(); + vti_destroy_tunnels(ipn, &list); + unregister_netdevice_many(&list); + rtnl_unlock(); +} + +static struct pernet_operations vti_net_ops = { + .init = vti_init_net, + .exit = vti_exit_net, + .id = &vti_net_id, + .size = sizeof(struct vti_net), +}; + +static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + return 0; +} + +static void vti_netlink_parms(struct nlattr *data[], + struct ip_tunnel_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + parms->iph.protocol = IPPROTO_IPIP; + + if (!data) + return; + + if (data[IFLA_VTI_LINK]) + parms->link = nla_get_u32(data[IFLA_VTI_LINK]); + + if (data[IFLA_VTI_IKEY]) + parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]); + + if (data[IFLA_VTI_OKEY]) + parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]); + + if (data[IFLA_VTI_LOCAL]) + parms->iph.saddr = nla_get_be32(data[IFLA_VTI_LOCAL]); + + if (data[IFLA_VTI_REMOTE]) + parms->iph.daddr = nla_get_be32(data[IFLA_VTI_REMOTE]); + +} + +static int vti_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct ip_tunnel *nt; + struct net *net = dev_net(dev); + struct vti_net *ipn = net_generic(net, vti_net_id); + int mtu; + int err; + + nt = netdev_priv(dev); + vti_netlink_parms(data, &nt->parms); + + if (vti_tunnel_locate(net, &nt->parms, 0)) + return -EEXIST; + + mtu = vti_tunnel_bind_dev(dev); + if (!tb[IFLA_MTU]) + dev->mtu = mtu; + + err = register_netdevice(dev); + if (err) + goto out; + + dev_hold(dev); + vti_tunnel_link(ipn, nt); + +out: + return err; +} + +static int vti_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip_tunnel *t, *nt; + struct net *net = dev_net(dev); + struct vti_net *ipn = net_generic(net, vti_net_id); + struct ip_tunnel_parm p; + int mtu; + + if (dev == ipn->fb_tunnel_dev) + return -EINVAL; + + nt = netdev_priv(dev); + vti_netlink_parms(data, &p); + + t = vti_tunnel_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else { + t = nt; + + vti_tunnel_unlink(ipn, t); + t->parms.iph.saddr = p.iph.saddr; + t->parms.iph.daddr = p.iph.daddr; + t->parms.i_key = p.i_key; + t->parms.o_key = p.o_key; + if (dev->type != ARPHRD_ETHER) { + memcpy(dev->dev_addr, &p.iph.saddr, 4); + memcpy(dev->broadcast, &p.iph.daddr, 4); + } + vti_tunnel_link(ipn, t); + netdev_state_change(dev); + } + + if (t->parms.link != p.link) { + t->parms.link = p.link; + mtu = vti_tunnel_bind_dev(dev); + if (!tb[IFLA_MTU]) + dev->mtu = mtu; + netdev_state_change(dev); + } + + return 0; +} + +static size_t vti_get_size(const struct net_device *dev) +{ + return + /* IFLA_VTI_LINK */ + nla_total_size(4) + + /* IFLA_VTI_IKEY */ + nla_total_size(4) + + /* IFLA_VTI_OKEY */ + nla_total_size(4) + + /* IFLA_VTI_LOCAL */ + nla_total_size(4) + + /* IFLA_VTI_REMOTE */ + nla_total_size(4) + + 0; +} + +static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm *p = &t->parms; + + nla_put_u32(skb, IFLA_VTI_LINK, p->link); + nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key); + nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key); + nla_put_be32(skb, IFLA_VTI_LOCAL, p->iph.saddr); + nla_put_be32(skb, IFLA_VTI_REMOTE, p->iph.daddr); + + return 0; +} + +static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = { + [IFLA_VTI_LINK] = { .type = NLA_U32 }, + [IFLA_VTI_IKEY] = { .type = NLA_U32 }, + [IFLA_VTI_OKEY] = { .type = NLA_U32 }, + [IFLA_VTI_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, + [IFLA_VTI_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, +}; + +static struct rtnl_link_ops vti_link_ops __read_mostly = { + .kind = "vti", + .maxtype = IFLA_VTI_MAX, + .policy = vti_policy, + .priv_size = sizeof(struct ip_tunnel), + .setup = vti_tunnel_setup, + .validate = vti_tunnel_validate, + .newlink = vti_newlink, + .changelink = vti_changelink, + .get_size = vti_get_size, + .fill_info = vti_fill_info, +}; + +static int __init vti_init(void) +{ + int err; + + pr_info("IPv4 over IPSec tunneling driver\n"); + + err = register_pernet_device(&vti_net_ops); + if (err < 0) + return err; + err = xfrm4_mode_tunnel_input_register(&vti_handler); + if (err < 0) { + unregister_pernet_device(&vti_net_ops); + pr_info(KERN_INFO "vti init: can't register tunnel\n"); + } + + err = rtnl_link_register(&vti_link_ops); + if (err < 0) + goto rtnl_link_failed; + + return err; + +rtnl_link_failed: + xfrm4_mode_tunnel_input_deregister(&vti_handler); + unregister_pernet_device(&vti_net_ops); + return err; +} + +static void __exit vti_fini(void) +{ + rtnl_link_unregister(&vti_link_ops); + if (xfrm4_mode_tunnel_input_deregister(&vti_handler)) + pr_info("vti close: can't deregister tunnel\n"); + + unregister_pernet_device(&vti_net_ops); +} + +module_init(vti_init); +module_exit(vti_fini); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("vti"); +MODULE_ALIAS_NETDEV("ip_vti0"); diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 63b64c45a82..d3ab47e19a8 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -31,17 +31,26 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) struct ip_comp_hdr *ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); struct xfrm_state *x; - if (icmp_hdr(skb)->type != ICMP_DEST_UNREACH || - icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + switch (icmp_hdr(skb)->type) { + case ICMP_DEST_UNREACH: + if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + return; + case ICMP_REDIRECT: + break; + default: return; + } spi = htonl(ntohs(ipch->cpi)); x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET); if (!x) return; - NETDEBUG(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/%pI4\n", - spi, &iph->daddr); + + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0); + else + ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0); xfrm_state_put(x); } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 2d0f99bf61b..99af1f0cc65 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -348,9 +348,6 @@ static int ipip_err(struct sk_buff *skb, u32 info) case ICMP_PORT_UNREACH: /* Impossible event. */ return 0; - case ICMP_FRAG_NEEDED: - /* Soft state for pmtu is maintained by IP core. */ - return 0; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, @@ -363,13 +360,32 @@ static int ipip_err(struct sk_buff *skb, u32 info) if (code != ICMP_EXC_TTL) return 0; break; + case ICMP_REDIRECT: + break; } err = -ENOENT; rcu_read_lock(); t = ipip_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr); - if (t == NULL || t->parms.iph.daddr == 0) + if (t == NULL) + goto out; + + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { + ipv4_update_pmtu(skb, dev_net(skb->dev), info, + t->dev->ifindex, 0, IPPROTO_IPIP, 0); + err = 0; + goto out; + } + + if (type == ICMP_REDIRECT) { + ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0, + IPPROTO_IPIP, 0); + err = 0; + goto out; + } + + if (t->parms.iph.daddr == 0) goto out; err = 0; @@ -471,7 +487,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_fifo_errors++; goto tx_error; } - dst = rt->rt_gateway; + dst = rt_nexthop(rt, old_iph->daddr); } rt = ip_route_output_ports(dev_net(dev), &fl4, NULL, @@ -503,7 +519,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) } if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if ((old_iph->frag_off & htons(IP_DF)) && mtu < ntohs(old_iph->tot_len)) { diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c94bbc6f2ba..ebdf06f938b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -124,6 +124,8 @@ static DEFINE_SPINLOCK(mfc_unres_lock); static struct kmem_cache *mrt_cachep __read_mostly; static struct mr_table *ipmr_new_table(struct net *net, u32 id); +static void ipmr_free_table(struct mr_table *mrt); + static int ip_mr_forward(struct net *net, struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *cache, int local); @@ -131,6 +133,7 @@ static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert); static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm); +static void mroute_clean_tables(struct mr_table *mrt); static void ipmr_expire_process(unsigned long arg); #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES @@ -271,7 +274,7 @@ static void __net_exit ipmr_rules_exit(struct net *net) list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) { list_del(&mrt->list); - kfree(mrt); + ipmr_free_table(mrt); } fib_rules_unregister(net->ipv4.mr_rules_ops); } @@ -299,7 +302,7 @@ static int __net_init ipmr_rules_init(struct net *net) static void __net_exit ipmr_rules_exit(struct net *net) { - kfree(net->ipv4.mrt); + ipmr_free_table(net->ipv4.mrt); } #endif @@ -336,6 +339,13 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id) return mrt; } +static void ipmr_free_table(struct mr_table *mrt) +{ + del_timer_sync(&mrt->ipmr_expire_timer); + mroute_clean_tables(mrt); + kfree(mrt); +} + /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */ static void ipmr_del_tunnel(struct net_device *dev, struct vifctl *v) @@ -524,8 +534,8 @@ failure: } #endif -/* - * Delete a VIF entry +/** + * vif_delete - Delete a VIF entry * @notify: Set to 1, if the caller is a notifier_call */ @@ -1795,9 +1805,12 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb) .daddr = iph->daddr, .saddr = iph->saddr, .flowi4_tos = RT_TOS(iph->tos), - .flowi4_oif = rt->rt_oif, - .flowi4_iif = rt->rt_iif, - .flowi4_mark = rt->rt_mark, + .flowi4_oif = (rt_is_output_route(rt) ? + skb->dev->ifindex : 0), + .flowi4_iif = (rt_is_output_route(rt) ? + net->loopback_dev->ifindex : + skb->dev->ifindex), + .flowi4_mark = skb->mark, }; struct mr_table *mrt; int err; @@ -2006,37 +2019,37 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, { int ct; struct rtnexthop *nhp; - u8 *b = skb_tail_pointer(skb); - struct rtattr *mp_head; + struct nlattr *mp_attr; /* If cache is unresolved, don't try to parse IIF and OIF */ if (c->mfc_parent >= MAXVIFS) return -ENOENT; - if (VIF_EXISTS(mrt, c->mfc_parent)) - RTA_PUT(skb, RTA_IIF, 4, &mrt->vif_table[c->mfc_parent].dev->ifindex); + if (VIF_EXISTS(mrt, c->mfc_parent) && + nla_put_u32(skb, RTA_IIF, mrt->vif_table[c->mfc_parent].dev->ifindex) < 0) + return -EMSGSIZE; - mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0)); + if (!(mp_attr = nla_nest_start(skb, RTA_MULTIPATH))) + return -EMSGSIZE; for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { - if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4)) - goto rtattr_failure; - nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp))); + if (!(nhp = nla_reserve_nohdr(skb, sizeof(*nhp)))) { + nla_nest_cancel(skb, mp_attr); + return -EMSGSIZE; + } + nhp->rtnh_flags = 0; nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; nhp->rtnh_ifindex = mrt->vif_table[ct].dev->ifindex; nhp->rtnh_len = sizeof(*nhp); } } - mp_head->rta_type = RTA_MULTIPATH; - mp_head->rta_len = skb_tail_pointer(skb) - (u8 *)mp_head; + + nla_nest_end(skb, mp_attr); + rtm->rtm_type = RTN_MULTICAST; return 1; - -rtattr_failure: - nlmsg_trim(skb, b); - return -EMSGSIZE; } int ipmr_get_route(struct net *net, struct sk_buff *skb, diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index 2f210c79dc8..cbb6a1a6f6f 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -52,7 +52,7 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par) struct nf_nat_ipv4_range newrange; const struct nf_nat_ipv4_multi_range_compat *mr; const struct rtable *rt; - __be32 newsrc; + __be32 newsrc, nh; NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING); @@ -70,7 +70,8 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par) mr = par->targinfo; rt = skb_rtable(skb); - newsrc = inet_select_addr(par->out, rt->rt_gateway, RT_SCOPE_UNIVERSE); + nh = rt_nexthop(rt, ip_hdr(skb)->daddr); + newsrc = inet_select_addr(par->out, nh, RT_SCOPE_UNIVERSE); if (!newsrc) { pr_info("%s ate my IP address\n", par->out->name); return NF_DROP; diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index ba5756d2016..1109f7f6c25 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -196,12 +196,15 @@ static void ipt_ulog_packet(unsigned int hooknum, pr_debug("qlen %d, qthreshold %Zu\n", ub->qlen, loginfo->qthreshold); - /* NLMSG_PUT contains a hidden goto nlmsg_failure !!! */ - nlh = NLMSG_PUT(ub->skb, 0, ub->qlen, ULOG_NL_EVENT, - sizeof(*pm)+copy_len); + nlh = nlmsg_put(ub->skb, 0, ub->qlen, ULOG_NL_EVENT, + sizeof(*pm)+copy_len, 0); + if (!nlh) { + pr_debug("error during nlmsg_put\n"); + goto out_unlock; + } ub->qlen++; - pm = NLMSG_DATA(nlh); + pm = nlmsg_data(nlh); /* We might not have a timestamp, get one */ if (skb->tstamp.tv64 == 0) @@ -261,13 +264,11 @@ static void ipt_ulog_packet(unsigned int hooknum, nlh->nlmsg_type = NLMSG_DONE; ulog_send(groupnum); } - +out_unlock: spin_unlock_bh(&ulog_lock); return; -nlmsg_failure: - pr_debug("error during NLMSG_PUT\n"); alloc_failure: pr_debug("Error building netlink message\n"); spin_unlock_bh(&ulog_lock); @@ -380,6 +381,9 @@ static struct nf_logger ipt_ulog_logger __read_mostly = { static int __init ulog_tg_init(void) { int ret, i; + struct netlink_kernel_cfg cfg = { + .groups = ULOG_MAXNLGROUPS, + }; pr_debug("init module\n"); @@ -392,9 +396,8 @@ static int __init ulog_tg_init(void) for (i = 0; i < ULOG_MAXNLGROUPS; i++) setup_timer(&ulog_buffers[i].timer, ulog_timer, i); - nflognl = netlink_kernel_create(&init_net, - NETLINK_NFLOG, ULOG_MAXNLGROUPS, NULL, - NULL, THIS_MODULE); + nflognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, + THIS_MODULE, &cfg); if (!nflognl) return -ENOMEM; diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 91747d4ebc2..e7ff2dcab6c 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -95,11 +95,11 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, return NF_ACCEPT; } -static unsigned int ipv4_confirm(unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static unsigned int ipv4_helper(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; @@ -110,24 +110,38 @@ static unsigned int ipv4_confirm(unsigned int hooknum, /* This is where we call the helper: as the packet goes out. */ ct = nf_ct_get(skb, &ctinfo); if (!ct || ctinfo == IP_CT_RELATED_REPLY) - goto out; + return NF_ACCEPT; help = nfct_help(ct); if (!help) - goto out; + return NF_ACCEPT; /* rcu_read_lock()ed by nf_hook_slow */ helper = rcu_dereference(help->helper); if (!helper) - goto out; + return NF_ACCEPT; ret = helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb), ct, ctinfo); - if (ret != NF_ACCEPT) { + if (ret != NF_ACCEPT && (ret & NF_VERDICT_MASK) != NF_QUEUE) { nf_log_packet(NFPROTO_IPV4, hooknum, skb, in, out, NULL, "nf_ct_%s: dropping packet", helper->name); - return ret; } + return ret; +} + +static unsigned int ipv4_confirm(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || ctinfo == IP_CT_RELATED_REPLY) + goto out; /* adjust seqs for loopback traffic only in outgoing direction */ if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && @@ -185,6 +199,13 @@ static struct nf_hook_ops ipv4_conntrack_ops[] __read_mostly = { .priority = NF_IP_PRI_CONNTRACK, }, { + .hook = ipv4_helper, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_HELPER, + }, + { .hook = ipv4_confirm, .owner = THIS_MODULE, .pf = NFPROTO_IPV4, @@ -192,6 +213,13 @@ static struct nf_hook_ops ipv4_conntrack_ops[] __read_mostly = { .priority = NF_IP_PRI_CONNTRACK_CONFIRM, }, { + .hook = ipv4_helper, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_HELPER, + }, + { .hook = ipv4_confirm, .owner = THIS_MODULE, .pf = NFPROTO_IPV4, @@ -207,35 +235,30 @@ static int log_invalid_proto_max = 255; static ctl_table ip_ct_sysctl_table[] = { { .procname = "ip_conntrack_max", - .data = &nf_conntrack_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "ip_conntrack_count", - .data = &init_net.ct.count, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, { .procname = "ip_conntrack_buckets", - .data = &init_net.ct.htable_size, .maxlen = sizeof(unsigned int), .mode = 0444, .proc_handler = proc_dointvec, }, { .procname = "ip_conntrack_checksum", - .data = &init_net.ct.sysctl_checksum, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "ip_conntrack_log_invalid", - .data = &init_net.ct.sysctl_log_invalid, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, @@ -351,6 +374,25 @@ static struct nf_sockopt_ops so_getorigdst = { .owner = THIS_MODULE, }; +static int ipv4_init_net(struct net *net) +{ +#if defined(CONFIG_SYSCTL) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) + struct nf_ip_net *in = &net->ct.nf_ct_proto; + in->ctl_table = kmemdup(ip_ct_sysctl_table, + sizeof(ip_ct_sysctl_table), + GFP_KERNEL); + if (!in->ctl_table) + return -ENOMEM; + + in->ctl_table[0].data = &nf_conntrack_max; + in->ctl_table[1].data = &net->ct.count; + in->ctl_table[2].data = &net->ct.htable_size; + in->ctl_table[3].data = &net->ct.sysctl_checksum; + in->ctl_table[4].data = &net->ct.sysctl_log_invalid; +#endif + return 0; +} + struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = { .l3proto = PF_INET, .name = "ipv4", @@ -366,8 +408,8 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = { #endif #if defined(CONFIG_SYSCTL) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) .ctl_table_path = "net/ipv4/netfilter", - .ctl_table = ip_ct_sysctl_table, #endif + .init_net = ipv4_init_net, .me = THIS_MODULE, }; @@ -378,6 +420,65 @@ MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET)); MODULE_ALIAS("ip_conntrack"); MODULE_LICENSE("GPL"); +static int ipv4_net_init(struct net *net) +{ + int ret = 0; + + ret = nf_conntrack_l4proto_register(net, + &nf_conntrack_l4proto_tcp4); + if (ret < 0) { + pr_err("nf_conntrack_l4proto_tcp4 :protocol register failed\n"); + goto out_tcp; + } + ret = nf_conntrack_l4proto_register(net, + &nf_conntrack_l4proto_udp4); + if (ret < 0) { + pr_err("nf_conntrack_l4proto_udp4 :protocol register failed\n"); + goto out_udp; + } + ret = nf_conntrack_l4proto_register(net, + &nf_conntrack_l4proto_icmp); + if (ret < 0) { + pr_err("nf_conntrack_l4proto_icmp4 :protocol register failed\n"); + goto out_icmp; + } + ret = nf_conntrack_l3proto_register(net, + &nf_conntrack_l3proto_ipv4); + if (ret < 0) { + pr_err("nf_conntrack_l3proto_ipv4 :protocol register failed\n"); + goto out_ipv4; + } + return 0; +out_ipv4: + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_icmp); +out_icmp: + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_udp4); +out_udp: + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_tcp4); +out_tcp: + return ret; +} + +static void ipv4_net_exit(struct net *net) +{ + nf_conntrack_l3proto_unregister(net, + &nf_conntrack_l3proto_ipv4); + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_icmp); + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_udp4); + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_tcp4); +} + +static struct pernet_operations ipv4_net_ops = { + .init = ipv4_net_init, + .exit = ipv4_net_exit, +}; + static int __init nf_conntrack_l3proto_ipv4_init(void) { int ret = 0; @@ -391,35 +492,17 @@ static int __init nf_conntrack_l3proto_ipv4_init(void) return ret; } - ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_tcp4); + ret = register_pernet_subsys(&ipv4_net_ops); if (ret < 0) { - pr_err("nf_conntrack_ipv4: can't register tcp.\n"); + pr_err("nf_conntrack_ipv4: can't register pernet ops\n"); goto cleanup_sockopt; } - ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_udp4); - if (ret < 0) { - pr_err("nf_conntrack_ipv4: can't register udp.\n"); - goto cleanup_tcp; - } - - ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_icmp); - if (ret < 0) { - pr_err("nf_conntrack_ipv4: can't register icmp.\n"); - goto cleanup_udp; - } - - ret = nf_conntrack_l3proto_register(&nf_conntrack_l3proto_ipv4); - if (ret < 0) { - pr_err("nf_conntrack_ipv4: can't register ipv4\n"); - goto cleanup_icmp; - } - ret = nf_register_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops)); if (ret < 0) { pr_err("nf_conntrack_ipv4: can't register hooks.\n"); - goto cleanup_ipv4; + goto cleanup_pernet; } #if defined(CONFIG_PROC_FS) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) ret = nf_conntrack_ipv4_compat_init(); @@ -431,14 +514,8 @@ static int __init nf_conntrack_l3proto_ipv4_init(void) cleanup_hooks: nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops)); #endif - cleanup_ipv4: - nf_conntrack_l3proto_unregister(&nf_conntrack_l3proto_ipv4); - cleanup_icmp: - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_icmp); - cleanup_udp: - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udp4); - cleanup_tcp: - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_tcp4); + cleanup_pernet: + unregister_pernet_subsys(&ipv4_net_ops); cleanup_sockopt: nf_unregister_sockopt(&so_getorigdst); return ret; @@ -451,10 +528,7 @@ static void __exit nf_conntrack_l3proto_ipv4_fini(void) nf_conntrack_ipv4_compat_fini(); #endif nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops)); - nf_conntrack_l3proto_unregister(&nf_conntrack_l3proto_ipv4); - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_icmp); - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udp4); - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_tcp4); + unregister_pernet_subsys(&ipv4_net_ops); nf_unregister_sockopt(&so_getorigdst); } diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 0847e373d33..5241d997ab7 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -23,6 +23,11 @@ static unsigned int nf_ct_icmp_timeout __read_mostly = 30*HZ; +static inline struct nf_icmp_net *icmp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.icmp; +} + static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct nf_conntrack_tuple *tuple) { @@ -77,7 +82,7 @@ static int icmp_print_tuple(struct seq_file *s, static unsigned int *icmp_get_timeouts(struct net *net) { - return &nf_ct_icmp_timeout; + return &icmp_pernet(net)->timeout; } /* Returns verdict for packet, or -1 for invalid. */ @@ -274,16 +279,18 @@ static int icmp_nlattr_tuple_size(void) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> -static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], + struct net *net, void *data) { unsigned int *timeout = data; + struct nf_icmp_net *in = icmp_pernet(net); if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { *timeout = ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ; } else { /* Set default ICMP timeout. */ - *timeout = nf_ct_icmp_timeout; + *timeout = in->timeout; } return 0; } @@ -308,11 +315,9 @@ icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL -static struct ctl_table_header *icmp_sysctl_header; static struct ctl_table icmp_sysctl_table[] = { { .procname = "nf_conntrack_icmp_timeout", - .data = &nf_ct_icmp_timeout, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -323,7 +328,6 @@ static struct ctl_table icmp_sysctl_table[] = { static struct ctl_table icmp_compat_sysctl_table[] = { { .procname = "ip_conntrack_icmp_timeout", - .data = &nf_ct_icmp_timeout, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -333,6 +337,62 @@ static struct ctl_table icmp_compat_sysctl_table[] = { #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ +static int icmp_kmemdup_sysctl_table(struct nf_proto_net *pn, + struct nf_icmp_net *in) +{ +#ifdef CONFIG_SYSCTL + pn->ctl_table = kmemdup(icmp_sysctl_table, + sizeof(icmp_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_table) + return -ENOMEM; + + pn->ctl_table[0].data = &in->timeout; +#endif + return 0; +} + +static int icmp_kmemdup_compat_sysctl_table(struct nf_proto_net *pn, + struct nf_icmp_net *in) +{ +#ifdef CONFIG_SYSCTL +#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT + pn->ctl_compat_table = kmemdup(icmp_compat_sysctl_table, + sizeof(icmp_compat_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_compat_table) + return -ENOMEM; + + pn->ctl_compat_table[0].data = &in->timeout; +#endif +#endif + return 0; +} + +static int icmp_init_net(struct net *net, u_int16_t proto) +{ + int ret; + struct nf_icmp_net *in = icmp_pernet(net); + struct nf_proto_net *pn = &in->pn; + + in->timeout = nf_ct_icmp_timeout; + + ret = icmp_kmemdup_compat_sysctl_table(pn, in); + if (ret < 0) + return ret; + + ret = icmp_kmemdup_sysctl_table(pn, in); + if (ret < 0) + nf_ct_kfree_compat_sysctl_table(pn); + + return ret; +} + +static struct nf_proto_net *icmp_get_net_proto(struct net *net) +{ + return &net->ct.nf_ct_proto.icmp.pn; +} + struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly = { .l3proto = PF_INET, @@ -362,11 +422,6 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly = .nla_policy = icmp_timeout_nla_policy, }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ -#ifdef CONFIG_SYSCTL - .ctl_table_header = &icmp_sysctl_header, - .ctl_table = icmp_sysctl_table, -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT - .ctl_compat_table = icmp_compat_sysctl_table, -#endif -#endif + .init_net = icmp_init_net, + .get_net_proto = icmp_get_net_proto, }; diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 9bb1b8a37a2..742815518b0 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -94,14 +94,14 @@ static struct nf_hook_ops ipv4_defrag_ops[] = { { .hook = ipv4_conntrack_defrag, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_CONNTRACK_DEFRAG, }, { .hook = ipv4_conntrack_defrag, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_CONNTRACK_DEFRAG, }, diff --git a/net/ipv4/netfilter/nf_nat_amanda.c b/net/ipv4/netfilter/nf_nat_amanda.c index 7b22382ff0e..3c04d24e297 100644 --- a/net/ipv4/netfilter/nf_nat_amanda.c +++ b/net/ipv4/netfilter/nf_nat_amanda.c @@ -13,10 +13,10 @@ #include <linux/skbuff.h> #include <linux/udp.h> -#include <net/netfilter/nf_nat_helper.h> -#include <net/netfilter/nf_nat_rule.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_expect.h> +#include <net/netfilter/nf_nat_helper.h> +#include <net/netfilter/nf_nat_rule.h> #include <linux/netfilter/nf_conntrack_amanda.h> MODULE_AUTHOR("Brian J. Murrell <netfilter@interlinx.bc.ca>"); diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index abb52adf5ac..44b082fd48a 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -691,6 +691,10 @@ static struct nf_ct_helper_expectfn follow_master_nat = { .expectfn = nf_nat_follow_master, }; +static struct nfq_ct_nat_hook nfq_ct_nat = { + .seq_adjust = nf_nat_tcp_seq_adjust, +}; + static int __init nf_nat_init(void) { size_t i; @@ -731,6 +735,7 @@ static int __init nf_nat_init(void) nfnetlink_parse_nat_setup); BUG_ON(nf_ct_nat_offset != NULL); RCU_INIT_POINTER(nf_ct_nat_offset, nf_nat_get_offset); + RCU_INIT_POINTER(nfq_ct_nat_hook, &nfq_ct_nat); return 0; cleanup_extend: @@ -747,6 +752,7 @@ static void __exit nf_nat_cleanup(void) RCU_INIT_POINTER(nf_nat_seq_adjust_hook, NULL); RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL); RCU_INIT_POINTER(nf_ct_nat_offset, NULL); + RCU_INIT_POINTER(nfq_ct_nat_hook, NULL); synchronize_net(); } diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index cad29c12131..c6784a18c1c 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -95,7 +95,7 @@ static int set_sig_addr(struct sk_buff *skb, struct nf_conn *ct, unsigned char **data, TransportAddress *taddr, int count) { - const struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + const struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); int i; __be16 port; @@ -178,7 +178,7 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, struct nf_conntrack_expect *rtp_exp, struct nf_conntrack_expect *rtcp_exp) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); int i; u_int16_t nated_port; @@ -330,7 +330,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); u_int16_t nated_port = ntohs(port); @@ -419,7 +419,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, unsigned char **data, TransportAddress *taddr, int idx, __be16 port, struct nf_conntrack_expect *exp) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); u_int16_t nated_port = ntohs(port); union nf_inet_addr addr; diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index af65958f630..2e59ad0b90c 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -153,6 +153,19 @@ void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo, } EXPORT_SYMBOL_GPL(nf_nat_set_seq_adjust); +void nf_nat_tcp_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, + u32 ctinfo, int off) +{ + const struct tcphdr *th; + + if (nf_ct_protonum(ct) != IPPROTO_TCP) + return; + + th = (struct tcphdr *)(skb_network_header(skb)+ ip_hdrlen(skb)); + nf_nat_set_seq_adjust(ct, ctinfo, th->seq, off); +} +EXPORT_SYMBOL_GPL(nf_nat_tcp_seq_adjust); + static void nf_nat_csum(struct sk_buff *skb, const struct iphdr *iph, void *data, int datalen, __sum16 *check, int oldlen) { diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index c273d58980a..388140881eb 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -49,7 +49,7 @@ static void pptp_nat_expected(struct nf_conn *ct, const struct nf_nat_pptp *nat_pptp_info; struct nf_nat_ipv4_range range; - ct_pptp_info = &nfct_help(master)->help.ct_pptp_info; + ct_pptp_info = nfct_help_data(master); nat_pptp_info = &nfct_nat(master)->help.nat_pptp_info; /* And here goes the grand finale of corrosion... */ @@ -123,7 +123,7 @@ pptp_outbound_pkt(struct sk_buff *skb, __be16 new_callid; unsigned int cid_off; - ct_pptp_info = &nfct_help(ct)->help.ct_pptp_info; + ct_pptp_info = nfct_help_data(ct); nat_pptp_info = &nfct_nat(ct)->help.nat_pptp_info; new_callid = ct_pptp_info->pns_call_id; @@ -192,7 +192,7 @@ pptp_exp_gre(struct nf_conntrack_expect *expect_orig, struct nf_ct_pptp_master *ct_pptp_info; struct nf_nat_pptp *nat_pptp_info; - ct_pptp_info = &nfct_help(ct)->help.ct_pptp_info; + ct_pptp_info = nfct_help_data(ct); nat_pptp_info = &nfct_nat(ct)->help.nat_pptp_info; /* save original PAC call ID in nat_info */ diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index ea4a23813d2..9c87cde28ff 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -148,7 +148,7 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, hdr, NULL, &matchoff, &matchlen, &addr, &port) > 0) { - unsigned int matchend, poff, plen, buflen, n; + unsigned int olen, matchend, poff, plen, buflen, n; char buffer[sizeof("nnn.nnn.nnn.nnn:nnnnn")]; /* We're only interested in headers related to this @@ -163,17 +163,18 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, goto next; } + olen = *datalen; if (!map_addr(skb, dataoff, dptr, datalen, matchoff, matchlen, &addr, port)) return NF_DROP; - matchend = matchoff + matchlen; + matchend = matchoff + matchlen + *datalen - olen; /* The maddr= parameter (RFC 2361) specifies where to send * the reply. */ if (ct_sip_parse_address_param(ct, *dptr, matchend, *datalen, "maddr=", &poff, &plen, - &addr) > 0 && + &addr, true) > 0 && addr.ip == ct->tuplehash[dir].tuple.src.u3.ip && addr.ip != ct->tuplehash[!dir].tuple.dst.u3.ip) { buflen = sprintf(buffer, "%pI4", @@ -187,7 +188,7 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, * from which the server received the request. */ if (ct_sip_parse_address_param(ct, *dptr, matchend, *datalen, "received=", &poff, &plen, - &addr) > 0 && + &addr, false) > 0 && addr.ip == ct->tuplehash[dir].tuple.dst.u3.ip && addr.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { buflen = sprintf(buffer, "%pI4", @@ -501,7 +502,10 @@ static unsigned int ip_nat_sdp_media(struct sk_buff *skb, unsigned int dataoff, ret = nf_ct_expect_related(rtcp_exp); if (ret == 0) break; - else if (ret != -EBUSY) { + else if (ret == -EBUSY) { + nf_ct_unexpect_related(rtp_exp); + continue; + } else if (ret < 0) { nf_ct_unexpect_related(rtp_exp); port = 0; break; diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 746edec8b86..bac712293fd 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -405,7 +405,7 @@ static unsigned char asn1_octets_decode(struct asn1_ctx *ctx, ptr = *octets; while (ctx->pointer < eoc) { - if (!asn1_octet_decode(ctx, (unsigned char *)ptr++)) { + if (!asn1_octet_decode(ctx, ptr++)) { kfree(*octets); *octets = NULL; return 0; @@ -759,7 +759,7 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, } break; case SNMP_OBJECTID: - if (!asn1_oid_decode(ctx, end, (unsigned long **)&lp, &len)) { + if (!asn1_oid_decode(ctx, end, &lp, &len)) { kfree(id); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_tftp.c b/net/ipv4/netfilter/nf_nat_tftp.c index a2901bf829c..9dbb8d284f9 100644 --- a/net/ipv4/netfilter/nf_nat_tftp.c +++ b/net/ipv4/netfilter/nf_nat_tftp.c @@ -8,10 +8,10 @@ #include <linux/module.h> #include <linux/udp.h> -#include <net/netfilter/nf_nat_helper.h> -#include <net/netfilter/nf_nat_rule.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_expect.h> +#include <net/netfilter/nf_nat_helper.h> +#include <net/netfilter/nf_nat_rule.h> #include <linux/netfilter/nf_conntrack_tftp.h> MODULE_AUTHOR("Magnus Boden <mb@ozaba.mine.nu>"); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 2c00e8bf684..6232d476f37 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -371,6 +371,7 @@ void ping_err(struct sk_buff *skb, u32 info) break; case ICMP_DEST_UNREACH: if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */ + ipv4_sk_update_pmtu(skb, sk, info); if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) { err = EMSGSIZE; harderr = 1; @@ -386,6 +387,7 @@ void ping_err(struct sk_buff *skb, u32 info) break; case ICMP_REDIRECT: /* See ICMP_SOURCE_QUENCH */ + ipv4_sk_redirect(skb, sk); err = EREMOTEIO; break; } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 8af0d44e4e2..957acd12250 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -232,7 +232,6 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPDSACKOfoSent", LINUX_MIB_TCPDSACKOFOSENT), SNMP_MIB_ITEM("TCPDSACKRecv", LINUX_MIB_TCPDSACKRECV), SNMP_MIB_ITEM("TCPDSACKOfoRecv", LINUX_MIB_TCPDSACKOFORECV), - SNMP_MIB_ITEM("TCPAbortOnSyn", LINUX_MIB_TCPABORTONSYN), SNMP_MIB_ITEM("TCPAbortOnData", LINUX_MIB_TCPABORTONDATA), SNMP_MIB_ITEM("TCPAbortOnClose", LINUX_MIB_TCPABORTONCLOSE), SNMP_MIB_ITEM("TCPAbortOnMemory", LINUX_MIB_TCPABORTONMEMORY), @@ -258,6 +257,12 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPReqQFullDrop", LINUX_MIB_TCPREQQFULLDROP), SNMP_MIB_ITEM("TCPRetransFail", LINUX_MIB_TCPRETRANSFAIL), SNMP_MIB_ITEM("TCPRcvCoalesce", LINUX_MIB_TCPRCVCOALESCE), + SNMP_MIB_ITEM("TCPOFOQueue", LINUX_MIB_TCPOFOQUEUE), + SNMP_MIB_ITEM("TCPOFODrop", LINUX_MIB_TCPOFODROP), + SNMP_MIB_ITEM("TCPOFOMerge", LINUX_MIB_TCPOFOMERGE), + SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK), + SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE), + SNMP_MIB_ITEM("TCPFastOpenActive", LINUX_MIB_TCPFASTOPENACTIVE), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c index 9ae5c01cd0b..8918eff1426 100644 --- a/net/ipv4/protocol.c +++ b/net/ipv4/protocol.c @@ -36,9 +36,7 @@ const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly; int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol) { - int hash = protocol & (MAX_INET_PROTOS - 1); - - return !cmpxchg((const struct net_protocol **)&inet_protos[hash], + return !cmpxchg((const struct net_protocol **)&inet_protos[protocol], NULL, prot) ? 0 : -1; } EXPORT_SYMBOL(inet_add_protocol); @@ -49,9 +47,9 @@ EXPORT_SYMBOL(inet_add_protocol); int inet_del_protocol(const struct net_protocol *prot, unsigned char protocol) { - int ret, hash = protocol & (MAX_INET_PROTOS - 1); + int ret; - ret = (cmpxchg((const struct net_protocol **)&inet_protos[hash], + ret = (cmpxchg((const struct net_protocol **)&inet_protos[protocol], prot, NULL) == prot) ? 0 : -1; synchronize_net(); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 4032b818f3e..ff0f071969e 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -216,6 +216,11 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) int err = 0; int harderr = 0; + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) + ipv4_sk_update_pmtu(skb, sk, info); + else if (type == ICMP_REDIRECT) + ipv4_sk_redirect(skb, sk); + /* Report error on raw socket, if: 1. User requested ip_recverr. 2. Socket is connected (otherwise the error indication diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 98b30d08efe..82cf2a722b2 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -70,7 +70,6 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/bootmem.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> @@ -80,7 +79,6 @@ #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/init.h> -#include <linux/workqueue.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> @@ -88,11 +86,9 @@ #include <linux/mroute.h> #include <linux/netfilter_ipv4.h> #include <linux/random.h> -#include <linux/jhash.h> #include <linux/rcupdate.h> #include <linux/times.h> #include <linux/slab.h> -#include <linux/prefetch.h> #include <net/dst.h> #include <net/net_namespace.h> #include <net/protocol.h> @@ -133,10 +129,6 @@ static int ip_rt_gc_elasticity __read_mostly = 8; static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; -static int rt_chain_length_max __read_mostly = 20; - -static struct delayed_work expires_work; -static unsigned long expires_ljiffies; /* * Interface to generic destination cache. @@ -145,11 +137,13 @@ static unsigned long expires_ljiffies; static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); static unsigned int ipv4_mtu(const struct dst_entry *dst); -static void ipv4_dst_destroy(struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); -static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu); -static int rt_garbage_collect(struct dst_ops *ops); +static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu); +static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb); +static void ipv4_dst_destroy(struct dst_entry *dst); static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int how) @@ -158,45 +152,17 @@ static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old) { - struct rtable *rt = (struct rtable *) dst; - struct inet_peer *peer; - u32 *p = NULL; - - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); - - peer = rt->peer; - if (peer) { - u32 *old_p = __DST_METRICS_PTR(old); - unsigned long prev, new; - - p = peer->metrics; - if (inet_metrics_new(peer)) - memcpy(p, old_p, sizeof(u32) * RTAX_MAX); - - new = (unsigned long) p; - prev = cmpxchg(&dst->_metrics, old, new); - - if (prev != old) { - p = __DST_METRICS_PTR(prev); - if (prev & DST_METRICS_READ_ONLY) - p = NULL; - } else { - if (rt->fi) { - fib_info_put(rt->fi); - rt->fi = NULL; - } - } - } - return p; + WARN_ON(1); + return NULL; } -static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr); +static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr); static struct dst_ops ipv4_dst_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), - .gc = rt_garbage_collect, .check = ipv4_dst_check, .default_advmss = ipv4_default_advmss, .mtu = ipv4_mtu, @@ -206,6 +172,7 @@ static struct dst_ops ipv4_dst_ops = { .negative_advice = ipv4_negative_advice, .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, + .redirect = ip_do_redirect, .local_out = __ip_local_out, .neigh_lookup = ipv4_neigh_lookup, }; @@ -232,184 +199,30 @@ const __u8 ip_tos2prio[16] = { }; EXPORT_SYMBOL(ip_tos2prio); -/* - * Route cache. - */ - -/* The locking scheme is rather straight forward: - * - * 1) Read-Copy Update protects the buckets of the central route hash. - * 2) Only writers remove entries, and they hold the lock - * as they look at rtable reference counts. - * 3) Only readers acquire references to rtable entries, - * they do so with atomic increments and with the - * lock held. - */ - -struct rt_hash_bucket { - struct rtable __rcu *chain; -}; - -#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \ - defined(CONFIG_PROVE_LOCKING) -/* - * Instead of using one spinlock for each rt_hash_bucket, we use a table of spinlocks - * The size of this table is a power of two and depends on the number of CPUS. - * (on lockdep we have a quite big spinlock_t, so keep the size down there) - */ -#ifdef CONFIG_LOCKDEP -# define RT_HASH_LOCK_SZ 256 -#else -# if NR_CPUS >= 32 -# define RT_HASH_LOCK_SZ 4096 -# elif NR_CPUS >= 16 -# define RT_HASH_LOCK_SZ 2048 -# elif NR_CPUS >= 8 -# define RT_HASH_LOCK_SZ 1024 -# elif NR_CPUS >= 4 -# define RT_HASH_LOCK_SZ 512 -# else -# define RT_HASH_LOCK_SZ 256 -# endif -#endif - -static spinlock_t *rt_hash_locks; -# define rt_hash_lock_addr(slot) &rt_hash_locks[(slot) & (RT_HASH_LOCK_SZ - 1)] - -static __init void rt_hash_lock_init(void) -{ - int i; - - rt_hash_locks = kmalloc(sizeof(spinlock_t) * RT_HASH_LOCK_SZ, - GFP_KERNEL); - if (!rt_hash_locks) - panic("IP: failed to allocate rt_hash_locks\n"); - - for (i = 0; i < RT_HASH_LOCK_SZ; i++) - spin_lock_init(&rt_hash_locks[i]); -} -#else -# define rt_hash_lock_addr(slot) NULL - -static inline void rt_hash_lock_init(void) -{ -} -#endif - -static struct rt_hash_bucket *rt_hash_table __read_mostly; -static unsigned int rt_hash_mask __read_mostly; -static unsigned int rt_hash_log __read_mostly; - static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); #define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field) -static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx, - int genid) -{ - return jhash_3words((__force u32)daddr, (__force u32)saddr, - idx, genid) - & rt_hash_mask; -} - static inline int rt_genid(struct net *net) { return atomic_read(&net->ipv4.rt_genid); } #ifdef CONFIG_PROC_FS -struct rt_cache_iter_state { - struct seq_net_private p; - int bucket; - int genid; -}; - -static struct rtable *rt_cache_get_first(struct seq_file *seq) -{ - struct rt_cache_iter_state *st = seq->private; - struct rtable *r = NULL; - - for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) { - if (!rcu_access_pointer(rt_hash_table[st->bucket].chain)) - continue; - rcu_read_lock_bh(); - r = rcu_dereference_bh(rt_hash_table[st->bucket].chain); - while (r) { - if (dev_net(r->dst.dev) == seq_file_net(seq) && - r->rt_genid == st->genid) - return r; - r = rcu_dereference_bh(r->dst.rt_next); - } - rcu_read_unlock_bh(); - } - return r; -} - -static struct rtable *__rt_cache_get_next(struct seq_file *seq, - struct rtable *r) -{ - struct rt_cache_iter_state *st = seq->private; - - r = rcu_dereference_bh(r->dst.rt_next); - while (!r) { - rcu_read_unlock_bh(); - do { - if (--st->bucket < 0) - return NULL; - } while (!rcu_access_pointer(rt_hash_table[st->bucket].chain)); - rcu_read_lock_bh(); - r = rcu_dereference_bh(rt_hash_table[st->bucket].chain); - } - return r; -} - -static struct rtable *rt_cache_get_next(struct seq_file *seq, - struct rtable *r) -{ - struct rt_cache_iter_state *st = seq->private; - while ((r = __rt_cache_get_next(seq, r)) != NULL) { - if (dev_net(r->dst.dev) != seq_file_net(seq)) - continue; - if (r->rt_genid == st->genid) - break; - } - return r; -} - -static struct rtable *rt_cache_get_idx(struct seq_file *seq, loff_t pos) -{ - struct rtable *r = rt_cache_get_first(seq); - - if (r) - while (pos && (r = rt_cache_get_next(seq, r))) - --pos; - return pos ? NULL : r; -} - static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos) { - struct rt_cache_iter_state *st = seq->private; if (*pos) - return rt_cache_get_idx(seq, *pos - 1); - st->genid = rt_genid(seq_file_net(seq)); + return NULL; return SEQ_START_TOKEN; } static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct rtable *r; - - if (v == SEQ_START_TOKEN) - r = rt_cache_get_first(seq); - else - r = rt_cache_get_next(seq, v); ++*pos; - return r; + return NULL; } static void rt_cache_seq_stop(struct seq_file *seq, void *v) { - if (v && v != SEQ_START_TOKEN) - rcu_read_unlock_bh(); } static int rt_cache_seq_show(struct seq_file *seq, void *v) @@ -419,34 +232,6 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) "Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t" "Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t" "HHUptod\tSpecDst"); - else { - struct rtable *r = v; - struct neighbour *n; - int len, HHUptod; - - rcu_read_lock(); - n = dst_get_neighbour_noref(&r->dst); - HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0; - rcu_read_unlock(); - - seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t" - "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n", - r->dst.dev ? r->dst.dev->name : "*", - (__force u32)r->rt_dst, - (__force u32)r->rt_gateway, - r->rt_flags, atomic_read(&r->dst.__refcnt), - r->dst.__use, 0, (__force u32)r->rt_src, - dst_metric_advmss(&r->dst) + 40, - dst_metric(&r->dst, RTAX_WINDOW), - (int)((dst_metric(&r->dst, RTAX_RTT) >> 3) + - dst_metric(&r->dst, RTAX_RTTVAR)), - r->rt_key_tos, - -1, - HHUptod, - r->rt_spec_dst, &len); - - seq_printf(seq, "%*s\n", 127 - len, ""); - } return 0; } @@ -459,8 +244,7 @@ static const struct seq_operations rt_cache_seq_ops = { static int rt_cache_seq_open(struct inode *inode, struct file *file) { - return seq_open_net(inode, file, &rt_cache_seq_ops, - sizeof(struct rt_cache_iter_state)); + return seq_open(file, &rt_cache_seq_ops); } static const struct file_operations rt_cache_seq_fops = { @@ -468,7 +252,7 @@ static const struct file_operations rt_cache_seq_fops = { .open = rt_cache_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_net, + .release = seq_release, }; @@ -658,275 +442,12 @@ static inline int ip_rt_proc_init(void) } #endif /* CONFIG_PROC_FS */ -static inline void rt_free(struct rtable *rt) -{ - call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free); -} - -static inline void rt_drop(struct rtable *rt) -{ - ip_rt_put(rt); - call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free); -} - -static inline int rt_fast_clean(struct rtable *rth) -{ - /* Kill broadcast/multicast entries very aggresively, if they - collide in hash table with more useful entries */ - return (rth->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) && - rt_is_input_route(rth) && rth->dst.rt_next; -} - -static inline int rt_valuable(struct rtable *rth) -{ - return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) || - (rth->peer && rth->peer->pmtu_expires); -} - -static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2) -{ - unsigned long age; - int ret = 0; - - if (atomic_read(&rth->dst.__refcnt)) - goto out; - - age = jiffies - rth->dst.lastuse; - if ((age <= tmo1 && !rt_fast_clean(rth)) || - (age <= tmo2 && rt_valuable(rth))) - goto out; - ret = 1; -out: return ret; -} - -/* Bits of score are: - * 31: very valuable - * 30: not quite useless - * 29..0: usage counter - */ -static inline u32 rt_score(struct rtable *rt) -{ - u32 score = jiffies - rt->dst.lastuse; - - score = ~score & ~(3<<30); - - if (rt_valuable(rt)) - score |= (1<<31); - - if (rt_is_output_route(rt) || - !(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL))) - score |= (1<<30); - - return score; -} - -static inline bool rt_caching(const struct net *net) -{ - return net->ipv4.current_rt_cache_rebuild_count <= - net->ipv4.sysctl_rt_cache_rebuild_count; -} - -static inline bool compare_hash_inputs(const struct rtable *rt1, - const struct rtable *rt2) -{ - return ((((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) | - ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) | - (rt1->rt_route_iif ^ rt2->rt_route_iif)) == 0); -} - -static inline int compare_keys(struct rtable *rt1, struct rtable *rt2) -{ - return (((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) | - ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) | - (rt1->rt_mark ^ rt2->rt_mark) | - (rt1->rt_key_tos ^ rt2->rt_key_tos) | - (rt1->rt_route_iif ^ rt2->rt_route_iif) | - (rt1->rt_oif ^ rt2->rt_oif)) == 0; -} - -static inline int compare_netns(struct rtable *rt1, struct rtable *rt2) -{ - return net_eq(dev_net(rt1->dst.dev), dev_net(rt2->dst.dev)); -} - -static inline int rt_is_expired(struct rtable *rth) +static inline bool rt_is_expired(const struct rtable *rth) { return rth->rt_genid != rt_genid(dev_net(rth->dst.dev)); } /* - * Perform a full scan of hash table and free all entries. - * Can be called by a softirq or a process. - * In the later case, we want to be reschedule if necessary - */ -static void rt_do_flush(struct net *net, int process_context) -{ - unsigned int i; - struct rtable *rth, *next; - - for (i = 0; i <= rt_hash_mask; i++) { - struct rtable __rcu **pprev; - struct rtable *list; - - if (process_context && need_resched()) - cond_resched(); - rth = rcu_access_pointer(rt_hash_table[i].chain); - if (!rth) - continue; - - spin_lock_bh(rt_hash_lock_addr(i)); - - list = NULL; - pprev = &rt_hash_table[i].chain; - rth = rcu_dereference_protected(*pprev, - lockdep_is_held(rt_hash_lock_addr(i))); - - while (rth) { - next = rcu_dereference_protected(rth->dst.rt_next, - lockdep_is_held(rt_hash_lock_addr(i))); - - if (!net || - net_eq(dev_net(rth->dst.dev), net)) { - rcu_assign_pointer(*pprev, next); - rcu_assign_pointer(rth->dst.rt_next, list); - list = rth; - } else { - pprev = &rth->dst.rt_next; - } - rth = next; - } - - spin_unlock_bh(rt_hash_lock_addr(i)); - - for (; list; list = next) { - next = rcu_dereference_protected(list->dst.rt_next, 1); - rt_free(list); - } - } -} - -/* - * While freeing expired entries, we compute average chain length - * and standard deviation, using fixed-point arithmetic. - * This to have an estimation of rt_chain_length_max - * rt_chain_length_max = max(elasticity, AVG + 4*SD) - * We use 3 bits for frational part, and 29 (or 61) for magnitude. - */ - -#define FRACT_BITS 3 -#define ONE (1UL << FRACT_BITS) - -/* - * Given a hash chain and an item in this hash chain, - * find if a previous entry has the same hash_inputs - * (but differs on tos, mark or oif) - * Returns 0 if an alias is found. - * Returns ONE if rth has no alias before itself. - */ -static int has_noalias(const struct rtable *head, const struct rtable *rth) -{ - const struct rtable *aux = head; - - while (aux != rth) { - if (compare_hash_inputs(aux, rth)) - return 0; - aux = rcu_dereference_protected(aux->dst.rt_next, 1); - } - return ONE; -} - -static void rt_check_expire(void) -{ - static unsigned int rover; - unsigned int i = rover, goal; - struct rtable *rth; - struct rtable __rcu **rthp; - unsigned long samples = 0; - unsigned long sum = 0, sum2 = 0; - unsigned long delta; - u64 mult; - - delta = jiffies - expires_ljiffies; - expires_ljiffies = jiffies; - mult = ((u64)delta) << rt_hash_log; - if (ip_rt_gc_timeout > 1) - do_div(mult, ip_rt_gc_timeout); - goal = (unsigned int)mult; - if (goal > rt_hash_mask) - goal = rt_hash_mask + 1; - for (; goal > 0; goal--) { - unsigned long tmo = ip_rt_gc_timeout; - unsigned long length; - - i = (i + 1) & rt_hash_mask; - rthp = &rt_hash_table[i].chain; - - if (need_resched()) - cond_resched(); - - samples++; - - if (rcu_dereference_raw(*rthp) == NULL) - continue; - length = 0; - spin_lock_bh(rt_hash_lock_addr(i)); - while ((rth = rcu_dereference_protected(*rthp, - lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) { - prefetch(rth->dst.rt_next); - if (rt_is_expired(rth)) { - *rthp = rth->dst.rt_next; - rt_free(rth); - continue; - } - if (rth->dst.expires) { - /* Entry is expired even if it is in use */ - if (time_before_eq(jiffies, rth->dst.expires)) { -nofree: - tmo >>= 1; - rthp = &rth->dst.rt_next; - /* - * We only count entries on - * a chain with equal hash inputs once - * so that entries for different QOS - * levels, and other non-hash input - * attributes don't unfairly skew - * the length computation - */ - length += has_noalias(rt_hash_table[i].chain, rth); - continue; - } - } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) - goto nofree; - - /* Cleanup aged off entries. */ - *rthp = rth->dst.rt_next; - rt_free(rth); - } - spin_unlock_bh(rt_hash_lock_addr(i)); - sum += length; - sum2 += length*length; - } - if (samples) { - unsigned long avg = sum / samples; - unsigned long sd = int_sqrt(sum2 / samples - avg*avg); - rt_chain_length_max = max_t(unsigned long, - ip_rt_gc_elasticity, - (avg + 4*sd) >> FRACT_BITS); - } - rover = i; -} - -/* - * rt_worker_func() is run in process context. - * we call rt_check_expire() to scan part of the hash table - */ -static void rt_worker_func(struct work_struct *work) -{ - rt_check_expire(); - schedule_delayed_work(&expires_work, ip_rt_gc_interval); -} - -/* * Perturbation of rt_genid by a small quantity [1..256] * Using 8 bits of shuffling ensure we can call rt_cache_invalidate() * many times (2^24) without giving recent rt_genid. @@ -938,7 +459,6 @@ static void rt_cache_invalidate(struct net *net) get_random_bytes(&shuffle, sizeof(shuffle)); atomic_add(shuffle + 1U, &net->ipv4.rt_genid); - inetpeer_invalidate_tree(AF_INET); } /* @@ -948,183 +468,22 @@ static void rt_cache_invalidate(struct net *net) void rt_cache_flush(struct net *net, int delay) { rt_cache_invalidate(net); - if (delay >= 0) - rt_do_flush(net, !in_softirq()); -} - -/* Flush previous cache invalidated entries from the cache */ -void rt_cache_flush_batch(struct net *net) -{ - rt_do_flush(net, !in_softirq()); -} - -static void rt_emergency_hash_rebuild(struct net *net) -{ - net_warn_ratelimited("Route hash chain too long!\n"); - rt_cache_invalidate(net); -} - -/* - Short description of GC goals. - - We want to build algorithm, which will keep routing cache - at some equilibrium point, when number of aged off entries - is kept approximately equal to newly generated ones. - - Current expiration strength is variable "expire". - We try to adjust it dynamically, so that if networking - is idle expires is large enough to keep enough of warm entries, - and when load increases it reduces to limit cache size. - */ - -static int rt_garbage_collect(struct dst_ops *ops) -{ - static unsigned long expire = RT_GC_TIMEOUT; - static unsigned long last_gc; - static int rover; - static int equilibrium; - struct rtable *rth; - struct rtable __rcu **rthp; - unsigned long now = jiffies; - int goal; - int entries = dst_entries_get_fast(&ipv4_dst_ops); - - /* - * Garbage collection is pretty expensive, - * do not make it too frequently. - */ - - RT_CACHE_STAT_INC(gc_total); - - if (now - last_gc < ip_rt_gc_min_interval && - entries < ip_rt_max_size) { - RT_CACHE_STAT_INC(gc_ignored); - goto out; - } - - entries = dst_entries_get_slow(&ipv4_dst_ops); - /* Calculate number of entries, which we want to expire now. */ - goal = entries - (ip_rt_gc_elasticity << rt_hash_log); - if (goal <= 0) { - if (equilibrium < ipv4_dst_ops.gc_thresh) - equilibrium = ipv4_dst_ops.gc_thresh; - goal = entries - equilibrium; - if (goal > 0) { - equilibrium += min_t(unsigned int, goal >> 1, rt_hash_mask + 1); - goal = entries - equilibrium; - } - } else { - /* We are in dangerous area. Try to reduce cache really - * aggressively. - */ - goal = max_t(unsigned int, goal >> 1, rt_hash_mask + 1); - equilibrium = entries - goal; - } - - if (now - last_gc >= ip_rt_gc_min_interval) - last_gc = now; - - if (goal <= 0) { - equilibrium += goal; - goto work_done; - } - - do { - int i, k; - - for (i = rt_hash_mask, k = rover; i >= 0; i--) { - unsigned long tmo = expire; - - k = (k + 1) & rt_hash_mask; - rthp = &rt_hash_table[k].chain; - spin_lock_bh(rt_hash_lock_addr(k)); - while ((rth = rcu_dereference_protected(*rthp, - lockdep_is_held(rt_hash_lock_addr(k)))) != NULL) { - if (!rt_is_expired(rth) && - !rt_may_expire(rth, tmo, expire)) { - tmo >>= 1; - rthp = &rth->dst.rt_next; - continue; - } - *rthp = rth->dst.rt_next; - rt_free(rth); - goal--; - } - spin_unlock_bh(rt_hash_lock_addr(k)); - if (goal <= 0) - break; - } - rover = k; - - if (goal <= 0) - goto work_done; - - /* Goal is not achieved. We stop process if: - - - if expire reduced to zero. Otherwise, expire is halfed. - - if table is not full. - - if we are called from interrupt. - - jiffies check is just fallback/debug loop breaker. - We will not spin here for long time in any case. - */ - - RT_CACHE_STAT_INC(gc_goal_miss); - - if (expire == 0) - break; - - expire >>= 1; - - if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size) - goto out; - } while (!in_softirq() && time_before_eq(jiffies, now)); - - if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size) - goto out; - if (dst_entries_get_slow(&ipv4_dst_ops) < ip_rt_max_size) - goto out; - net_warn_ratelimited("dst cache overflow\n"); - RT_CACHE_STAT_INC(gc_dst_overflow); - return 1; - -work_done: - expire += ip_rt_gc_min_interval; - if (expire > ip_rt_gc_timeout || - dst_entries_get_fast(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh || - dst_entries_get_slow(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh) - expire = ip_rt_gc_timeout; -out: return 0; -} - -/* - * Returns number of entries in a hash chain that have different hash_inputs - */ -static int slow_chain_length(const struct rtable *head) -{ - int length = 0; - const struct rtable *rth = head; - - while (rth) { - length += has_noalias(head, rth); - rth = rcu_dereference_protected(rth->dst.rt_next, 1); - } - return length >> FRACT_BITS; } -static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr) +static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) { - static const __be32 inaddr_any = 0; struct net_device *dev = dst->dev; const __be32 *pkey = daddr; const struct rtable *rt; struct neighbour *n; rt = (const struct rtable *) dst; - - if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) - pkey = &inaddr_any; - else if (rt->rt_gateway) + if (rt->rt_gateway) pkey = (const __be32 *) &rt->rt_gateway; + else if (skb) + pkey = &ip_hdr(skb)->daddr; n = __ipv4_neigh_lookup(dev, *(__force u32 *)pkey); if (n) @@ -1132,311 +491,221 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const vo return neigh_create(&arp_tbl, pkey, dev); } -static int rt_bind_neighbour(struct rtable *rt) +/* + * Peer allocation may fail only in serious out-of-memory conditions. However + * we still can generate some output. + * Random ID selection looks a bit dangerous because we have no chances to + * select ID being unique in a reasonable period of time. + * But broken packet identifier may be better than no packet at all. + */ +static void ip_select_fb_ident(struct iphdr *iph) { - struct neighbour *n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); - if (IS_ERR(n)) - return PTR_ERR(n); - dst_set_neighbour(&rt->dst, n); + static DEFINE_SPINLOCK(ip_fb_id_lock); + static u32 ip_fallback_id; + u32 salt; - return 0; + spin_lock_bh(&ip_fb_id_lock); + salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr); + iph->id = htons(salt & 0xFFFF); + ip_fallback_id = salt; + spin_unlock_bh(&ip_fb_id_lock); } -static struct rtable *rt_intern_hash(unsigned int hash, struct rtable *rt, - struct sk_buff *skb, int ifindex) +void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) { - struct rtable *rth, *cand; - struct rtable __rcu **rthp, **candp; - unsigned long now; - u32 min_score; - int chain_length; - int attempts = !in_softirq(); - -restart: - chain_length = 0; - min_score = ~(u32)0; - cand = NULL; - candp = NULL; - now = jiffies; - - if (!rt_caching(dev_net(rt->dst.dev))) { - /* - * If we're not caching, just tell the caller we - * were successful and don't touch the route. The - * caller hold the sole reference to the cache entry, and - * it will be released when the caller is done with it. - * If we drop it here, the callers have no way to resolve routes - * when we're not caching. Instead, just point *rp at rt, so - * the caller gets a single use out of the route - * Note that we do rt_free on this new route entry, so that - * once its refcount hits zero, we are still able to reap it - * (Thanks Alexey) - * Note: To avoid expensive rcu stuff for this uncached dst, - * we set DST_NOCACHE so that dst_release() can free dst without - * waiting a grace period. - */ - - rt->dst.flags |= DST_NOCACHE; - if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) { - int err = rt_bind_neighbour(rt); - if (err) { - net_warn_ratelimited("Neighbour table failure & not caching routes\n"); - ip_rt_put(rt); - return ERR_PTR(err); - } - } + struct net *net = dev_net(dst->dev); + struct inet_peer *peer; - goto skip_hashing; + peer = inet_getpeer_v4(net->ipv4.peers, iph->daddr, 1); + if (peer) { + iph->id = htons(inet_getid(peer, more)); + inet_putpeer(peer); + return; } - rthp = &rt_hash_table[hash].chain; - - spin_lock_bh(rt_hash_lock_addr(hash)); - while ((rth = rcu_dereference_protected(*rthp, - lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) { - if (rt_is_expired(rth)) { - *rthp = rth->dst.rt_next; - rt_free(rth); - continue; - } - if (compare_keys(rth, rt) && compare_netns(rth, rt)) { - /* Put it first */ - *rthp = rth->dst.rt_next; - /* - * Since lookup is lockfree, the deletion - * must be visible to another weakly ordered CPU before - * the insertion at the start of the hash chain. - */ - rcu_assign_pointer(rth->dst.rt_next, - rt_hash_table[hash].chain); - /* - * Since lookup is lockfree, the update writes - * must be ordered for consistency on SMP. - */ - rcu_assign_pointer(rt_hash_table[hash].chain, rth); - - dst_use(&rth->dst, now); - spin_unlock_bh(rt_hash_lock_addr(hash)); - - rt_drop(rt); - if (skb) - skb_dst_set(skb, &rth->dst); - return rth; - } - - if (!atomic_read(&rth->dst.__refcnt)) { - u32 score = rt_score(rth); - - if (score <= min_score) { - cand = rth; - candp = rthp; - min_score = score; - } - } - - chain_length++; - - rthp = &rth->dst.rt_next; - } + ip_select_fb_ident(iph); +} +EXPORT_SYMBOL(__ip_select_ident); - if (cand) { - /* ip_rt_gc_elasticity used to be average length of chain - * length, when exceeded gc becomes really aggressive. - * - * The second limit is less certain. At the moment it allows - * only 2 entries per bucket. We will see. - */ - if (chain_length > ip_rt_gc_elasticity) { - *candp = cand->dst.rt_next; - rt_free(cand); - } - } else { - if (chain_length > rt_chain_length_max && - slow_chain_length(rt_hash_table[hash].chain) > rt_chain_length_max) { - struct net *net = dev_net(rt->dst.dev); - int num = ++net->ipv4.current_rt_cache_rebuild_count; - if (!rt_caching(net)) { - pr_warn("%s: %d rebuilds is over limit, route caching disabled\n", - rt->dst.dev->name, num); - } - rt_emergency_hash_rebuild(net); - spin_unlock_bh(rt_hash_lock_addr(hash)); +static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk, + const struct iphdr *iph, + int oif, u8 tos, + u8 prot, u32 mark, int flow_flags) +{ + if (sk) { + const struct inet_sock *inet = inet_sk(sk); - hash = rt_hash(rt->rt_key_dst, rt->rt_key_src, - ifindex, rt_genid(net)); - goto restart; - } + oif = sk->sk_bound_dev_if; + mark = sk->sk_mark; + tos = RT_CONN_FLAGS(sk); + prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol; } + flowi4_init_output(fl4, oif, mark, tos, + RT_SCOPE_UNIVERSE, prot, + flow_flags, + iph->daddr, iph->saddr, 0, 0); +} - /* Try to bind route to arp only if it is output - route or unicast forwarding path. - */ - if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) { - int err = rt_bind_neighbour(rt); - if (err) { - spin_unlock_bh(rt_hash_lock_addr(hash)); - - if (err != -ENOBUFS) { - rt_drop(rt); - return ERR_PTR(err); - } - - /* Neighbour tables are full and nothing - can be released. Try to shrink route cache, - it is most likely it holds some neighbour records. - */ - if (attempts-- > 0) { - int saved_elasticity = ip_rt_gc_elasticity; - int saved_int = ip_rt_gc_min_interval; - ip_rt_gc_elasticity = 1; - ip_rt_gc_min_interval = 0; - rt_garbage_collect(&ipv4_dst_ops); - ip_rt_gc_min_interval = saved_int; - ip_rt_gc_elasticity = saved_elasticity; - goto restart; - } - - net_warn_ratelimited("Neighbour table overflow\n"); - rt_drop(rt); - return ERR_PTR(-ENOBUFS); - } - } +static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb, + const struct sock *sk) +{ + const struct iphdr *iph = ip_hdr(skb); + int oif = skb->dev->ifindex; + u8 tos = RT_TOS(iph->tos); + u8 prot = iph->protocol; + u32 mark = skb->mark; - rt->dst.rt_next = rt_hash_table[hash].chain; + __build_flow_key(fl4, sk, iph, oif, tos, prot, mark, 0); +} - /* - * Since lookup is lockfree, we must make sure - * previous writes to rt are committed to memory - * before making rt visible to other CPUS. - */ - rcu_assign_pointer(rt_hash_table[hash].chain, rt); +static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct ip_options_rcu *inet_opt; + __be32 daddr = inet->inet_daddr; - spin_unlock_bh(rt_hash_lock_addr(hash)); + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt && inet_opt->opt.srr) + daddr = inet_opt->opt.faddr; + flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, + RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, + inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, + inet_sk_flowi_flags(sk), + daddr, inet->inet_saddr, 0, 0); + rcu_read_unlock(); +} -skip_hashing: +static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk, + const struct sk_buff *skb) +{ if (skb) - skb_dst_set(skb, &rt->dst); - return rt; + build_skb_flow_key(fl4, skb, sk); + else + build_sk_flow_key(fl4, sk); } -static atomic_t __rt_peer_genid = ATOMIC_INIT(0); - -static u32 rt_peer_genid(void) +static inline void rt_free(struct rtable *rt) { - return atomic_read(&__rt_peer_genid); + call_rcu(&rt->dst.rcu_head, dst_rcu_free); } -void rt_bind_peer(struct rtable *rt, __be32 daddr, int create) -{ - struct inet_peer *peer; +static DEFINE_SPINLOCK(fnhe_lock); - peer = inet_getpeer_v4(daddr, create); +static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash) +{ + struct fib_nh_exception *fnhe, *oldest; + struct rtable *orig; - if (peer && cmpxchg(&rt->peer, NULL, peer) != NULL) - inet_putpeer(peer); - else - rt->rt_peer_genid = rt_peer_genid(); + oldest = rcu_dereference(hash->chain); + for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe; + fnhe = rcu_dereference(fnhe->fnhe_next)) { + if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) + oldest = fnhe; + } + orig = rcu_dereference(oldest->fnhe_rth); + if (orig) { + RCU_INIT_POINTER(oldest->fnhe_rth, NULL); + rt_free(orig); + } + return oldest; } -/* - * Peer allocation may fail only in serious out-of-memory conditions. However - * we still can generate some output. - * Random ID selection looks a bit dangerous because we have no chances to - * select ID being unique in a reasonable period of time. - * But broken packet identifier may be better than no packet at all. - */ -static void ip_select_fb_ident(struct iphdr *iph) +static inline u32 fnhe_hashfun(__be32 daddr) { - static DEFINE_SPINLOCK(ip_fb_id_lock); - static u32 ip_fallback_id; - u32 salt; + u32 hval; - spin_lock_bh(&ip_fb_id_lock); - salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr); - iph->id = htons(salt & 0xFFFF); - ip_fallback_id = salt; - spin_unlock_bh(&ip_fb_id_lock); + hval = (__force u32) daddr; + hval ^= (hval >> 11) ^ (hval >> 22); + + return hval & (FNHE_HASH_SIZE - 1); } -void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) +static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, + u32 pmtu, unsigned long expires) { - struct rtable *rt = (struct rtable *) dst; + struct fnhe_hash_bucket *hash; + struct fib_nh_exception *fnhe; + int depth; + u32 hval = fnhe_hashfun(daddr); - if (rt && !(rt->dst.flags & DST_NOPEER)) { - if (rt->peer == NULL) - rt_bind_peer(rt, rt->rt_dst, 1); + spin_lock_bh(&fnhe_lock); - /* If peer is attached to destination, it is never detached, - so that we need not to grab a lock to dereference it. - */ - if (rt->peer) { - iph->id = htons(inet_getid(rt->peer, more)); - return; - } - } else if (!rt) - pr_debug("rt_bind_peer(0) @%p\n", __builtin_return_address(0)); + hash = nh->nh_exceptions; + if (!hash) { + hash = kzalloc(FNHE_HASH_SIZE * sizeof(*hash), GFP_ATOMIC); + if (!hash) + goto out_unlock; + nh->nh_exceptions = hash; + } - ip_select_fb_ident(iph); -} -EXPORT_SYMBOL(__ip_select_ident); + hash += hval; -static void rt_del(unsigned int hash, struct rtable *rt) -{ - struct rtable __rcu **rthp; - struct rtable *aux; + depth = 0; + for (fnhe = rcu_dereference(hash->chain); fnhe; + fnhe = rcu_dereference(fnhe->fnhe_next)) { + if (fnhe->fnhe_daddr == daddr) + break; + depth++; + } - rthp = &rt_hash_table[hash].chain; - spin_lock_bh(rt_hash_lock_addr(hash)); - ip_rt_put(rt); - while ((aux = rcu_dereference_protected(*rthp, - lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) { - if (aux == rt || rt_is_expired(aux)) { - *rthp = aux->dst.rt_next; - rt_free(aux); - continue; + if (fnhe) { + if (gw) + fnhe->fnhe_gw = gw; + if (pmtu) { + fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_expires = expires; } - rthp = &aux->dst.rt_next; + } else { + if (depth > FNHE_RECLAIM_DEPTH) + fnhe = fnhe_oldest(hash); + else { + fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC); + if (!fnhe) + goto out_unlock; + + fnhe->fnhe_next = hash->chain; + rcu_assign_pointer(hash->chain, fnhe); + } + fnhe->fnhe_daddr = daddr; + fnhe->fnhe_gw = gw; + fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_expires = expires; } - spin_unlock_bh(rt_hash_lock_addr(hash)); + + fnhe->fnhe_stamp = jiffies; + +out_unlock: + spin_unlock_bh(&fnhe_lock); + return; } -static void check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) +static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4, + bool kill_route) { - struct rtable *rt = (struct rtable *) dst; - __be32 orig_gw = rt->rt_gateway; - struct neighbour *n, *old_n; - - dst_confirm(&rt->dst); + __be32 new_gw = icmp_hdr(skb)->un.gateway; + __be32 old_gw = ip_hdr(skb)->saddr; + struct net_device *dev = skb->dev; + struct in_device *in_dev; + struct fib_result res; + struct neighbour *n; + struct net *net; - rt->rt_gateway = peer->redirect_learned.a4; + switch (icmp_hdr(skb)->code & 7) { + case ICMP_REDIR_NET: + case ICMP_REDIR_NETTOS: + case ICMP_REDIR_HOST: + case ICMP_REDIR_HOSTTOS: + break; - n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); - if (IS_ERR(n)) { - rt->rt_gateway = orig_gw; + default: return; } - old_n = xchg(&rt->dst._neighbour, n); - if (old_n) - neigh_release(old_n); - if (!(n->nud_state & NUD_VALID)) { - neigh_event_send(n, NULL); - } else { - rt->rt_flags |= RTCF_REDIRECTED; - call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); - } -} -/* called in rcu_read_lock() section */ -void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, - __be32 saddr, struct net_device *dev) -{ - int s, i; - struct in_device *in_dev = __in_dev_get_rcu(dev); - __be32 skeys[2] = { saddr, 0 }; - int ikeys[2] = { dev->ifindex, 0 }; - struct inet_peer *peer; - struct net *net; + if (rt->rt_gateway != old_gw) + return; + in_dev = __in_dev_get_rcu(dev); if (!in_dev) return; @@ -1456,72 +725,50 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, goto reject_redirect; } - for (s = 0; s < 2; s++) { - for (i = 0; i < 2; i++) { - unsigned int hash; - struct rtable __rcu **rthp; - struct rtable *rt; - - hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net)); - - rthp = &rt_hash_table[hash].chain; - - while ((rt = rcu_dereference(*rthp)) != NULL) { - rthp = &rt->dst.rt_next; - - if (rt->rt_key_dst != daddr || - rt->rt_key_src != skeys[s] || - rt->rt_oif != ikeys[i] || - rt_is_input_route(rt) || - rt_is_expired(rt) || - !net_eq(dev_net(rt->dst.dev), net) || - rt->dst.error || - rt->dst.dev != dev || - rt->rt_gateway != old_gw) - continue; - - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); - - peer = rt->peer; - if (peer) { - if (peer->redirect_learned.a4 != new_gw) { - peer->redirect_learned.a4 = new_gw; - atomic_inc(&__rt_peer_genid); - } - check_peer_redir(&rt->dst, peer); - } + n = ipv4_neigh_lookup(&rt->dst, NULL, &new_gw); + if (n) { + if (!(n->nud_state & NUD_VALID)) { + neigh_event_send(n, NULL); + } else { + if (fib_lookup(net, fl4, &res) == 0) { + struct fib_nh *nh = &FIB_RES_NH(res); + + update_or_create_fnhe(nh, fl4->daddr, new_gw, + 0, 0); } + if (kill_route) + rt->dst.obsolete = DST_OBSOLETE_KILL; + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); } + neigh_release(n); } return; reject_redirect: #ifdef CONFIG_IP_ROUTE_VERBOSE - if (IN_DEV_LOG_MARTIANS(in_dev)) + if (IN_DEV_LOG_MARTIANS(in_dev)) { + const struct iphdr *iph = (const struct iphdr *) skb->data; + __be32 daddr = iph->daddr; + __be32 saddr = iph->saddr; + net_info_ratelimited("Redirect from %pI4 on %s about %pI4 ignored\n" " Advised path = %pI4 -> %pI4\n", &old_gw, dev->name, &new_gw, &saddr, &daddr); + } #endif ; } -static bool peer_pmtu_expired(struct inet_peer *peer) +static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { - unsigned long orig = ACCESS_ONCE(peer->pmtu_expires); - - return orig && - time_after_eq(jiffies, orig) && - cmpxchg(&peer->pmtu_expires, orig, 0) == orig; -} + struct rtable *rt; + struct flowi4 fl4; -static bool peer_pmtu_cleaned(struct inet_peer *peer) -{ - unsigned long orig = ACCESS_ONCE(peer->pmtu_expires); + rt = (struct rtable *) dst; - return orig && - cmpxchg(&peer->pmtu_expires, orig, 0) == orig; + ip_rt_build_flow_key(&fl4, sk, skb); + __ip_do_redirect(rt, skb, &fl4, true); } static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) @@ -1533,14 +780,10 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) if (dst->obsolete > 0) { ip_rt_put(rt); ret = NULL; - } else if (rt->rt_flags & RTCF_REDIRECTED) { - unsigned int hash = rt_hash(rt->rt_key_dst, rt->rt_key_src, - rt->rt_oif, - rt_genid(dev_net(dst->dev))); - rt_del(hash, rt); + } else if ((rt->rt_flags & RTCF_REDIRECTED) || + rt->dst.expires) { + ip_rt_put(rt); ret = NULL; - } else if (rt->peer && peer_pmtu_expired(rt->peer)) { - dst_metric_set(dst, RTAX_MTU, rt->peer->pmtu_orig); } } return ret; @@ -1567,6 +810,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) struct rtable *rt = skb_rtable(skb); struct in_device *in_dev; struct inet_peer *peer; + struct net *net; int log_martians; rcu_read_lock(); @@ -1578,9 +822,8 @@ void ip_rt_send_redirect(struct sk_buff *skb) log_martians = IN_DEV_LOG_MARTIANS(in_dev); rcu_read_unlock(); - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); - peer = rt->peer; + net = dev_net(rt->dst.dev); + peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1); if (!peer) { icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway); return; @@ -1597,7 +840,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) */ if (peer->rate_tokens >= ip_rt_redirect_number) { peer->rate_last = jiffies; - return; + goto out_put_peer; } /* Check for load limit; set rate_last to the latest sent @@ -1614,20 +857,38 @@ void ip_rt_send_redirect(struct sk_buff *skb) if (log_martians && peer->rate_tokens == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", - &ip_hdr(skb)->saddr, rt->rt_iif, - &rt->rt_dst, &rt->rt_gateway); + &ip_hdr(skb)->saddr, inet_iif(skb), + &ip_hdr(skb)->daddr, &rt->rt_gateway); #endif } +out_put_peer: + inet_putpeer(peer); } static int ip_error(struct sk_buff *skb) { + struct in_device *in_dev = __in_dev_get_rcu(skb->dev); struct rtable *rt = skb_rtable(skb); struct inet_peer *peer; unsigned long now; + struct net *net; bool send; int code; + net = dev_net(rt->dst.dev); + if (!IN_DEV_FORWARD(in_dev)) { + switch (rt->dst.error) { + case EHOSTUNREACH: + IP_INC_STATS_BH(net, IPSTATS_MIB_INADDRERRORS); + break; + + case ENETUNREACH: + IP_INC_STATS_BH(net, IPSTATS_MIB_INNOROUTES); + break; + } + goto out; + } + switch (rt->dst.error) { case EINVAL: default: @@ -1637,17 +898,14 @@ static int ip_error(struct sk_buff *skb) break; case ENETUNREACH: code = ICMP_NET_UNREACH; - IP_INC_STATS_BH(dev_net(rt->dst.dev), - IPSTATS_MIB_INNOROUTES); + IP_INC_STATS_BH(net, IPSTATS_MIB_INNOROUTES); break; case EACCES: code = ICMP_PKT_FILTERED; break; } - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); - peer = rt->peer; + peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1); send = true; if (peer) { @@ -1660,6 +918,7 @@ static int ip_error(struct sk_buff *skb) peer->rate_tokens -= ip_rt_error_cost; else send = false; + inet_putpeer(peer); } if (send) icmp_send(skb, ICMP_DEST_UNREACH, code, 0); @@ -1668,163 +927,122 @@ out: kfree_skb(skb); return 0; } -/* - * The last two values are not from the RFC but - * are needed for AMPRnet AX.25 paths. - */ +static u32 __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) +{ + struct fib_result res; -static const unsigned short mtu_plateau[] = -{32000, 17914, 8166, 4352, 2002, 1492, 576, 296, 216, 128 }; + if (mtu < ip_rt_min_pmtu) + mtu = ip_rt_min_pmtu; -static inline unsigned short guess_mtu(unsigned short old_mtu) -{ - int i; + rcu_read_lock(); + if (fib_lookup(dev_net(rt->dst.dev), fl4, &res) == 0) { + struct fib_nh *nh = &FIB_RES_NH(res); - for (i = 0; i < ARRAY_SIZE(mtu_plateau); i++) - if (old_mtu > mtu_plateau[i]) - return mtu_plateau[i]; - return 68; + update_or_create_fnhe(nh, fl4->daddr, 0, mtu, + jiffies + ip_rt_mtu_expires); + } + rcu_read_unlock(); + return mtu; } -unsigned short ip_rt_frag_needed(struct net *net, const struct iphdr *iph, - unsigned short new_mtu, - struct net_device *dev) +static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { - unsigned short old_mtu = ntohs(iph->tot_len); - unsigned short est_mtu = 0; - struct inet_peer *peer; - - peer = inet_getpeer_v4(iph->daddr, 1); - if (peer) { - unsigned short mtu = new_mtu; - - if (new_mtu < 68 || new_mtu >= old_mtu) { - /* BSD 4.2 derived systems incorrectly adjust - * tot_len by the IP header length, and report - * a zero MTU in the ICMP message. - */ - if (mtu == 0 && - old_mtu >= 68 + (iph->ihl << 2)) - old_mtu -= iph->ihl << 2; - mtu = guess_mtu(old_mtu); - } - - if (mtu < ip_rt_min_pmtu) - mtu = ip_rt_min_pmtu; - if (!peer->pmtu_expires || mtu < peer->pmtu_learned) { - unsigned long pmtu_expires; - - pmtu_expires = jiffies + ip_rt_mtu_expires; - if (!pmtu_expires) - pmtu_expires = 1UL; + struct rtable *rt = (struct rtable *) dst; + struct flowi4 fl4; - est_mtu = mtu; - peer->pmtu_learned = mtu; - peer->pmtu_expires = pmtu_expires; - atomic_inc(&__rt_peer_genid); - } + ip_rt_build_flow_key(&fl4, sk, skb); + mtu = __ip_rt_update_pmtu(rt, &fl4, mtu); - inet_putpeer(peer); + if (!rt->rt_pmtu) { + dst->obsolete = DST_OBSOLETE_KILL; + } else { + rt->rt_pmtu = mtu; + rt->dst.expires = max(1UL, jiffies + ip_rt_mtu_expires); } - return est_mtu ? : new_mtu; } -static void check_peer_pmtu(struct dst_entry *dst, struct inet_peer *peer) +void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, + int oif, u32 mark, u8 protocol, int flow_flags) { - unsigned long expires = ACCESS_ONCE(peer->pmtu_expires); + const struct iphdr *iph = (const struct iphdr *) skb->data; + struct flowi4 fl4; + struct rtable *rt; - if (!expires) - return; - if (time_before(jiffies, expires)) { - u32 orig_dst_mtu = dst_mtu(dst); - if (peer->pmtu_learned < orig_dst_mtu) { - if (!peer->pmtu_orig) - peer->pmtu_orig = dst_metric_raw(dst, RTAX_MTU); - dst_metric_set(dst, RTAX_MTU, peer->pmtu_learned); - } - } else if (cmpxchg(&peer->pmtu_expires, expires, 0) == expires) - dst_metric_set(dst, RTAX_MTU, peer->pmtu_orig); + __build_flow_key(&fl4, NULL, iph, oif, + RT_TOS(iph->tos), protocol, mark, flow_flags); + rt = __ip_route_output_key(net, &fl4); + if (!IS_ERR(rt)) { + __ip_rt_update_pmtu(rt, &fl4, mtu); + ip_rt_put(rt); + } } +EXPORT_SYMBOL_GPL(ipv4_update_pmtu); -static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) +void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { - struct rtable *rt = (struct rtable *) dst; - struct inet_peer *peer; - - dst_confirm(dst); - - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); - peer = rt->peer; - if (peer) { - unsigned long pmtu_expires = ACCESS_ONCE(peer->pmtu_expires); - - if (mtu < ip_rt_min_pmtu) - mtu = ip_rt_min_pmtu; - if (!pmtu_expires || mtu < peer->pmtu_learned) { - - pmtu_expires = jiffies + ip_rt_mtu_expires; - if (!pmtu_expires) - pmtu_expires = 1UL; - - peer->pmtu_learned = mtu; - peer->pmtu_expires = pmtu_expires; + const struct iphdr *iph = (const struct iphdr *) skb->data; + struct flowi4 fl4; + struct rtable *rt; - atomic_inc(&__rt_peer_genid); - rt->rt_peer_genid = rt_peer_genid(); - } - check_peer_pmtu(dst, peer); + __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0); + rt = __ip_route_output_key(sock_net(sk), &fl4); + if (!IS_ERR(rt)) { + __ip_rt_update_pmtu(rt, &fl4, mtu); + ip_rt_put(rt); } } +EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); - -static void ipv4_validate_peer(struct rtable *rt) +void ipv4_redirect(struct sk_buff *skb, struct net *net, + int oif, u32 mark, u8 protocol, int flow_flags) { - if (rt->rt_peer_genid != rt_peer_genid()) { - struct inet_peer *peer; - - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 0); + const struct iphdr *iph = (const struct iphdr *) skb->data; + struct flowi4 fl4; + struct rtable *rt; - peer = rt->peer; - if (peer) { - check_peer_pmtu(&rt->dst, peer); + __build_flow_key(&fl4, NULL, iph, oif, + RT_TOS(iph->tos), protocol, mark, flow_flags); + rt = __ip_route_output_key(net, &fl4); + if (!IS_ERR(rt)) { + __ip_do_redirect(rt, skb, &fl4, false); + ip_rt_put(rt); + } +} +EXPORT_SYMBOL_GPL(ipv4_redirect); - if (peer->redirect_learned.a4 && - peer->redirect_learned.a4 != rt->rt_gateway) - check_peer_redir(&rt->dst, peer); - } +void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk) +{ + const struct iphdr *iph = (const struct iphdr *) skb->data; + struct flowi4 fl4; + struct rtable *rt; - rt->rt_peer_genid = rt_peer_genid(); + __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0); + rt = __ip_route_output_key(sock_net(sk), &fl4); + if (!IS_ERR(rt)) { + __ip_do_redirect(rt, skb, &fl4, false); + ip_rt_put(rt); } } +EXPORT_SYMBOL_GPL(ipv4_sk_redirect); static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { struct rtable *rt = (struct rtable *) dst; - if (rt_is_expired(rt)) + /* All IPV4 dsts are created with ->obsolete set to the value + * DST_OBSOLETE_FORCE_CHK which forces validation calls down + * into this function always. + * + * When a PMTU/redirect information update invalidates a + * route, this is indicated by setting obsolete to + * DST_OBSOLETE_KILL. + */ + if (dst->obsolete == DST_OBSOLETE_KILL || rt_is_expired(rt)) return NULL; - ipv4_validate_peer(rt); return dst; } -static void ipv4_dst_destroy(struct dst_entry *dst) -{ - struct rtable *rt = (struct rtable *) dst; - struct inet_peer *peer = rt->peer; - - if (rt->fi) { - fib_info_put(rt->fi); - rt->fi = NULL; - } - if (peer) { - rt->peer = NULL; - inet_putpeer(peer); - } -} - - static void ipv4_link_failure(struct sk_buff *skb) { struct rtable *rt; @@ -1832,8 +1050,8 @@ static void ipv4_link_failure(struct sk_buff *skb) icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); rt = skb_rtable(skb); - if (rt && rt->peer && peer_pmtu_cleaned(rt->peer)) - dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig); + if (rt) + dst_set_expires(&rt->dst, 0); } static int ip_rt_bug(struct sk_buff *skb) @@ -1880,8 +1098,9 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res) == 0) src = FIB_RES_PREFSRC(dev_net(rt->dst.dev), res); else - src = inet_select_addr(rt->dst.dev, rt->rt_gateway, - RT_SCOPE_UNIVERSE); + src = inet_select_addr(rt->dst.dev, + rt_nexthop(rt, iph->daddr), + RT_SCOPE_UNIVERSE); rcu_read_unlock(); } memcpy(addr, &src, 4); @@ -1913,7 +1132,13 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst) static unsigned int ipv4_mtu(const struct dst_entry *dst) { const struct rtable *rt = (const struct rtable *) dst; - unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + unsigned int mtu = rt->rt_pmtu; + + if (mtu && time_after_eq(jiffies, rt->dst.expires)) + mtu = 0; + + if (!mtu) + mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu && rt_is_output_route(rt)) return mtu; @@ -1921,8 +1146,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = dst->dev->mtu; if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { - - if (rt->rt_gateway != rt->rt_dst && mtu > 576) + if (rt->rt_gateway && mtu > 576) mtu = 576; } @@ -1932,76 +1156,184 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) return mtu; } -static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4, - struct fib_info *fi) +static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) { - struct inet_peer *peer; - int create = 0; + struct fnhe_hash_bucket *hash = nh->nh_exceptions; + struct fib_nh_exception *fnhe; + u32 hval; - /* If a peer entry exists for this destination, we must hook - * it up in order to get at cached metrics. - */ - if (fl4 && (fl4->flowi4_flags & FLOWI_FLAG_PRECOW_METRICS)) - create = 1; + if (!hash) + return NULL; - rt->peer = peer = inet_getpeer_v4(rt->rt_dst, create); - if (peer) { - rt->rt_peer_genid = rt_peer_genid(); - if (inet_metrics_new(peer)) - memcpy(peer->metrics, fi->fib_metrics, - sizeof(u32) * RTAX_MAX); - dst_init_metrics(&rt->dst, peer->metrics, false); + hval = fnhe_hashfun(daddr); - check_peer_pmtu(&rt->dst, peer); + for (fnhe = rcu_dereference(hash[hval].chain); fnhe; + fnhe = rcu_dereference(fnhe->fnhe_next)) { + if (fnhe->fnhe_daddr == daddr) + return fnhe; + } + return NULL; +} + +static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, + __be32 daddr) +{ + bool ret = false; + + spin_lock_bh(&fnhe_lock); - if (peer->redirect_learned.a4 && - peer->redirect_learned.a4 != rt->rt_gateway) { - rt->rt_gateway = peer->redirect_learned.a4; + if (daddr == fnhe->fnhe_daddr) { + struct rtable *orig; + + if (fnhe->fnhe_pmtu) { + unsigned long expires = fnhe->fnhe_expires; + unsigned long diff = expires - jiffies; + + if (time_before(jiffies, expires)) { + rt->rt_pmtu = fnhe->fnhe_pmtu; + dst_set_expires(&rt->dst, diff); + } + } + if (fnhe->fnhe_gw) { rt->rt_flags |= RTCF_REDIRECTED; + rt->rt_gateway = fnhe->fnhe_gw; } + + orig = rcu_dereference(fnhe->fnhe_rth); + rcu_assign_pointer(fnhe->fnhe_rth, rt); + if (orig) + rt_free(orig); + + fnhe->fnhe_stamp = jiffies; + ret = true; + } else { + /* Routes we intend to cache in nexthop exception have + * the DST_NOCACHE bit clear. However, if we are + * unsuccessful at storing this route into the cache + * we really need to set it. + */ + rt->dst.flags |= DST_NOCACHE; + } + spin_unlock_bh(&fnhe_lock); + + return ret; +} + +static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt) +{ + struct rtable *orig, *prev, **p; + bool ret = true; + + if (rt_is_input_route(rt)) { + p = (struct rtable **)&nh->nh_rth_input; + } else { + if (!nh->nh_pcpu_rth_output) + goto nocache; + p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output); + } + orig = *p; + + prev = cmpxchg(p, orig, rt); + if (prev == orig) { + if (orig) + rt_free(orig); } else { - if (fi->fib_metrics != (u32 *) dst_default_metrics) { - rt->fi = fi; - atomic_inc(&fi->fib_clntref); + /* Routes we intend to cache in the FIB nexthop have + * the DST_NOCACHE bit clear. However, if we are + * unsuccessful at storing this route into the cache + * we really need to set it. + */ +nocache: + rt->dst.flags |= DST_NOCACHE; + ret = false; + } + + return ret; +} + +static DEFINE_SPINLOCK(rt_uncached_lock); +static LIST_HEAD(rt_uncached_list); + +static void rt_add_uncached_list(struct rtable *rt) +{ + spin_lock_bh(&rt_uncached_lock); + list_add_tail(&rt->rt_uncached, &rt_uncached_list); + spin_unlock_bh(&rt_uncached_lock); +} + +static void ipv4_dst_destroy(struct dst_entry *dst) +{ + struct rtable *rt = (struct rtable *) dst; + + if (!list_empty(&rt->rt_uncached)) { + spin_lock_bh(&rt_uncached_lock); + list_del(&rt->rt_uncached); + spin_unlock_bh(&rt_uncached_lock); + } +} + +void rt_flush_dev(struct net_device *dev) +{ + if (!list_empty(&rt_uncached_list)) { + struct net *net = dev_net(dev); + struct rtable *rt; + + spin_lock_bh(&rt_uncached_lock); + list_for_each_entry(rt, &rt_uncached_list, rt_uncached) { + if (rt->dst.dev != dev) + continue; + rt->dst.dev = net->loopback_dev; + dev_hold(rt->dst.dev); + dev_put(dev); } - dst_init_metrics(&rt->dst, fi->fib_metrics, true); + spin_unlock_bh(&rt_uncached_lock); } } -static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *fl4, +static bool rt_cache_valid(const struct rtable *rt) +{ + return rt && + rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && + !rt_is_expired(rt); +} + +static void rt_set_nexthop(struct rtable *rt, __be32 daddr, const struct fib_result *res, + struct fib_nh_exception *fnhe, struct fib_info *fi, u16 type, u32 itag) { - struct dst_entry *dst = &rt->dst; + bool cached = false; if (fi) { - if (FIB_RES_GW(*res) && - FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) - rt->rt_gateway = FIB_RES_GW(*res); - rt_init_metrics(rt, fl4, fi); + struct fib_nh *nh = &FIB_RES_NH(*res); + + if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK) + rt->rt_gateway = nh->nh_gw; + dst_init_metrics(&rt->dst, fi->fib_metrics, true); #ifdef CONFIG_IP_ROUTE_CLASSID - dst->tclassid = FIB_RES_NH(*res).nh_tclassid; + rt->dst.tclassid = nh->nh_tclassid; #endif + if (unlikely(fnhe)) + cached = rt_bind_exception(rt, fnhe, daddr); + else if (!(rt->dst.flags & DST_NOCACHE)) + cached = rt_cache_route(nh, rt); } - - if (dst_mtu(dst) > IP_MAX_MTU) - dst_metric_set(dst, RTAX_MTU, IP_MAX_MTU); - if (dst_metric_raw(dst, RTAX_ADVMSS) > 65535 - 40) - dst_metric_set(dst, RTAX_ADVMSS, 65535 - 40); + if (unlikely(!cached)) + rt_add_uncached_list(rt); #ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES - set_class_tag(rt, fib_rules_tclass(res)); + set_class_tag(rt, res->tclassid); #endif set_class_tag(rt, itag); #endif } static struct rtable *rt_dst_alloc(struct net_device *dev, - bool nopolicy, bool noxfrm) + bool nopolicy, bool noxfrm, bool will_cache) { - return dst_alloc(&ipv4_dst_ops, dev, 1, -1, - DST_HOST | + return dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, + (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) | (nopolicy ? DST_NOPOLICY : 0) | (noxfrm ? DST_NOXFRM : 0)); } @@ -2010,9 +1342,7 @@ static struct rtable *rt_dst_alloc(struct net_device *dev, static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, int our) { - unsigned int hash; struct rtable *rth; - __be32 spec_dst; struct in_device *in_dev = __in_dev_get_rcu(dev); u32 itag = 0; int err; @@ -2023,21 +1353,24 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, return -EINVAL; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || - ipv4_is_loopback(saddr) || skb->protocol != htons(ETH_P_IP)) + skb->protocol != htons(ETH_P_IP)) goto e_inval; + if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) + if (ipv4_is_loopback(saddr)) + goto e_inval; + if (ipv4_is_zeronet(saddr)) { if (!ipv4_is_local_multicast(daddr)) goto e_inval; - spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK); } else { - err = fib_validate_source(skb, saddr, 0, tos, 0, dev, &spec_dst, - &itag); + err = fib_validate_source(skb, saddr, 0, tos, 0, dev, + in_dev, &itag); if (err < 0) goto e_err; } rth = rt_dst_alloc(dev_net(dev)->loopback_dev, - IN_DEV_CONF_GET(in_dev, NOPOLICY), false); + IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false); if (!rth) goto e_nobufs; @@ -2046,23 +1379,14 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, #endif rth->dst.output = ip_rt_bug; - rth->rt_key_dst = daddr; - rth->rt_key_src = saddr; rth->rt_genid = rt_genid(dev_net(dev)); rth->rt_flags = RTCF_MULTICAST; rth->rt_type = RTN_MULTICAST; - rth->rt_key_tos = tos; - rth->rt_dst = daddr; - rth->rt_src = saddr; - rth->rt_route_iif = dev->ifindex; - rth->rt_iif = dev->ifindex; - rth->rt_oif = 0; - rth->rt_mark = skb->mark; - rth->rt_gateway = daddr; - rth->rt_spec_dst= spec_dst; - rth->rt_peer_genid = 0; - rth->peer = NULL; - rth->fi = NULL; + rth->rt_is_input= 1; + rth->rt_iif = 0; + rth->rt_pmtu = 0; + rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); if (our) { rth->dst.input= ip_local_deliver; rth->rt_flags |= RTCF_LOCAL; @@ -2074,9 +1398,8 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, #endif RT_CACHE_STAT_INC(in_slow_mc); - hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev))); - rth = rt_intern_hash(hash, rth, skb, dev->ifindex); - return IS_ERR(rth) ? PTR_ERR(rth) : 0; + skb_dst_set(skb, &rth->dst); + return 0; e_nobufs: return -ENOBUFS; @@ -2116,14 +1439,13 @@ static void ip_handle_martian_source(struct net_device *dev, static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, struct in_device *in_dev, - __be32 daddr, __be32 saddr, u32 tos, - struct rtable **result) + __be32 daddr, __be32 saddr, u32 tos) { struct rtable *rth; int err; struct in_device *out_dev; unsigned int flags = 0; - __be32 spec_dst; + bool do_cache; u32 itag; /* get a working reference to the output device */ @@ -2135,7 +1457,7 @@ static int __mkroute_input(struct sk_buff *skb, err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res), - in_dev->dev, &spec_dst, &itag); + in_dev->dev, in_dev, &itag); if (err < 0) { ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr, saddr); @@ -2143,9 +1465,6 @@ static int __mkroute_input(struct sk_buff *skb, goto cleanup; } - if (err) - flags |= RTCF_DIRECTSRC; - if (out_dev == in_dev && err && (IN_DEV_SHARED_MEDIA(out_dev) || inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) @@ -2166,38 +1485,41 @@ static int __mkroute_input(struct sk_buff *skb, } } + do_cache = false; + if (res->fi) { + if (!itag) { + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); + if (rt_cache_valid(rth)) { + skb_dst_set_noref(skb, &rth->dst); + goto out; + } + do_cache = true; + } + } + rth = rt_dst_alloc(out_dev->dev, IN_DEV_CONF_GET(in_dev, NOPOLICY), - IN_DEV_CONF_GET(out_dev, NOXFRM)); + IN_DEV_CONF_GET(out_dev, NOXFRM), do_cache); if (!rth) { err = -ENOBUFS; goto cleanup; } - rth->rt_key_dst = daddr; - rth->rt_key_src = saddr; rth->rt_genid = rt_genid(dev_net(rth->dst.dev)); rth->rt_flags = flags; rth->rt_type = res->type; - rth->rt_key_tos = tos; - rth->rt_dst = daddr; - rth->rt_src = saddr; - rth->rt_route_iif = in_dev->dev->ifindex; - rth->rt_iif = in_dev->dev->ifindex; - rth->rt_oif = 0; - rth->rt_mark = skb->mark; - rth->rt_gateway = daddr; - rth->rt_spec_dst= spec_dst; - rth->rt_peer_genid = 0; - rth->peer = NULL; - rth->fi = NULL; + rth->rt_is_input = 1; + rth->rt_iif = 0; + rth->rt_pmtu = 0; + rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); rth->dst.input = ip_forward; rth->dst.output = ip_output; - rt_set_nexthop(rth, NULL, res, res->fi, res->type, itag); - - *result = rth; + rt_set_nexthop(rth, daddr, res, NULL, res->fi, res->type, itag); + skb_dst_set(skb, &rth->dst); +out: err = 0; cleanup: return err; @@ -2209,27 +1531,13 @@ static int ip_mkroute_input(struct sk_buff *skb, struct in_device *in_dev, __be32 daddr, __be32 saddr, u32 tos) { - struct rtable *rth = NULL; - int err; - unsigned int hash; - #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && res->fi->fib_nhs > 1) fib_select_multipath(res); #endif /* create a routing cache entry */ - err = __mkroute_input(skb, res, in_dev, daddr, saddr, tos, &rth); - if (err) - return err; - - /* put it into the cache */ - hash = rt_hash(daddr, saddr, fl4->flowi4_iif, - rt_genid(dev_net(rth->dst.dev))); - rth = rt_intern_hash(hash, rth, skb, fl4->flowi4_iif); - if (IS_ERR(rth)) - return PTR_ERR(rth); - return 0; + return __mkroute_input(skb, res, in_dev, daddr, saddr, tos); } /* @@ -2252,10 +1560,9 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, unsigned int flags = 0; u32 itag = 0; struct rtable *rth; - unsigned int hash; - __be32 spec_dst; int err = -EINVAL; struct net *net = dev_net(dev); + bool do_cache; /* IP on this device is disabled. */ @@ -2266,10 +1573,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, by fib_lookup. */ - if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || - ipv4_is_loopback(saddr)) + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; + res.fi = NULL; if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) goto brd_input; @@ -2279,9 +1586,17 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (ipv4_is_zeronet(saddr)) goto martian_source; - if (ipv4_is_zeronet(daddr) || ipv4_is_loopback(daddr)) + if (ipv4_is_zeronet(daddr)) goto martian_destination; + if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) { + if (ipv4_is_loopback(daddr)) + goto martian_destination; + + if (ipv4_is_loopback(saddr)) + goto martian_source; + } + /* * Now we are ready to route packet. */ @@ -2293,11 +1608,8 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; err = fib_lookup(net, &fl4, &res); - if (err != 0) { - if (!IN_DEV_FORWARD(in_dev)) - goto e_hostunreach; + if (err != 0) goto no_route; - } RT_CACHE_STAT_INC(in_slow_tot); @@ -2307,17 +1619,14 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (res.type == RTN_LOCAL) { err = fib_validate_source(skb, saddr, daddr, tos, net->loopback_dev->ifindex, - dev, &spec_dst, &itag); + dev, in_dev, &itag); if (err < 0) goto martian_source_keep_err; - if (err) - flags |= RTCF_DIRECTSRC; - spec_dst = daddr; goto local_input; } if (!IN_DEV_FORWARD(in_dev)) - goto e_hostunreach; + goto no_route; if (res.type != RTN_UNICAST) goto martian_destination; @@ -2328,23 +1637,32 @@ brd_input: if (skb->protocol != htons(ETH_P_IP)) goto e_inval; - if (ipv4_is_zeronet(saddr)) - spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK); - else { - err = fib_validate_source(skb, saddr, 0, tos, 0, dev, &spec_dst, - &itag); + if (!ipv4_is_zeronet(saddr)) { + err = fib_validate_source(skb, saddr, 0, tos, 0, dev, + in_dev, &itag); if (err < 0) goto martian_source_keep_err; - if (err) - flags |= RTCF_DIRECTSRC; } flags |= RTCF_BROADCAST; res.type = RTN_BROADCAST; RT_CACHE_STAT_INC(in_brd); local_input: + do_cache = false; + if (res.fi) { + if (!itag) { + rth = rcu_dereference(FIB_RES_NH(res).nh_rth_input); + if (rt_cache_valid(rth)) { + skb_dst_set_noref(skb, &rth->dst); + err = 0; + goto out; + } + do_cache = true; + } + } + rth = rt_dst_alloc(net->loopback_dev, - IN_DEV_CONF_GET(in_dev, NOPOLICY), false); + IN_DEV_CONF_GET(in_dev, NOPOLICY), false, do_cache); if (!rth) goto e_nobufs; @@ -2354,41 +1672,27 @@ local_input: rth->dst.tclassid = itag; #endif - rth->rt_key_dst = daddr; - rth->rt_key_src = saddr; rth->rt_genid = rt_genid(net); rth->rt_flags = flags|RTCF_LOCAL; rth->rt_type = res.type; - rth->rt_key_tos = tos; - rth->rt_dst = daddr; - rth->rt_src = saddr; -#ifdef CONFIG_IP_ROUTE_CLASSID - rth->dst.tclassid = itag; -#endif - rth->rt_route_iif = dev->ifindex; - rth->rt_iif = dev->ifindex; - rth->rt_oif = 0; - rth->rt_mark = skb->mark; - rth->rt_gateway = daddr; - rth->rt_spec_dst= spec_dst; - rth->rt_peer_genid = 0; - rth->peer = NULL; - rth->fi = NULL; + rth->rt_is_input = 1; + rth->rt_iif = 0; + rth->rt_pmtu = 0; + rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } - hash = rt_hash(daddr, saddr, fl4.flowi4_iif, rt_genid(net)); - rth = rt_intern_hash(hash, rth, skb, fl4.flowi4_iif); + if (do_cache) + rt_cache_route(&FIB_RES_NH(res), rth); + skb_dst_set(skb, &rth->dst); err = 0; - if (IS_ERR(rth)) - err = PTR_ERR(rth); goto out; no_route: RT_CACHE_STAT_INC(in_no_route); - spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE); res.type = RTN_UNREACHABLE; if (err == -ESRCH) err = -ENETUNREACH; @@ -2405,10 +1709,6 @@ martian_destination: &daddr, &saddr, dev->name); #endif -e_hostunreach: - err = -EHOSTUNREACH; - goto out; - e_inval: err = -EINVAL; goto out; @@ -2424,50 +1724,13 @@ martian_source_keep_err: goto out; } -int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev, bool noref) +int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev) { - struct rtable *rth; - unsigned int hash; - int iif = dev->ifindex; - struct net *net; int res; - net = dev_net(dev); - rcu_read_lock(); - if (!rt_caching(net)) - goto skip_cache; - - tos &= IPTOS_RT_MASK; - hash = rt_hash(daddr, saddr, iif, rt_genid(net)); - - for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; - rth = rcu_dereference(rth->dst.rt_next)) { - if ((((__force u32)rth->rt_key_dst ^ (__force u32)daddr) | - ((__force u32)rth->rt_key_src ^ (__force u32)saddr) | - (rth->rt_route_iif ^ iif) | - (rth->rt_key_tos ^ tos)) == 0 && - rth->rt_mark == skb->mark && - net_eq(dev_net(rth->dst.dev), net) && - !rt_is_expired(rth)) { - ipv4_validate_peer(rth); - if (noref) { - dst_use_noref(&rth->dst, jiffies); - skb_dst_set_noref(skb, &rth->dst); - } else { - dst_use(&rth->dst, jiffies); - skb_dst_set(skb, &rth->dst); - } - RT_CACHE_STAT_INC(in_hit); - rcu_read_unlock(); - return 0; - } - RT_CACHE_STAT_INC(in_hlist_search); - } - -skip_cache: /* Multicast recognition logic is moved from route cache to here. The problem was that too many Ethernet cards have broken/missing hardware multicast filters :-( As result the host on multicasting @@ -2505,24 +1768,28 @@ skip_cache: rcu_read_unlock(); return res; } -EXPORT_SYMBOL(ip_route_input_common); +EXPORT_SYMBOL(ip_route_input_noref); /* called with rcu_read_lock() */ static struct rtable *__mkroute_output(const struct fib_result *res, - const struct flowi4 *fl4, - __be32 orig_daddr, __be32 orig_saddr, - int orig_oif, __u8 orig_rtos, + const struct flowi4 *fl4, int orig_oif, struct net_device *dev_out, unsigned int flags) { struct fib_info *fi = res->fi; + struct fib_nh_exception *fnhe; struct in_device *in_dev; u16 type = res->type; struct rtable *rth; - if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK)) + in_dev = __in_dev_get_rcu(dev_out); + if (!in_dev) return ERR_PTR(-EINVAL); + if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) + if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK)) + return ERR_PTR(-EINVAL); + if (ipv4_is_lbcast(fl4->daddr)) type = RTN_BROADCAST; else if (ipv4_is_multicast(fl4->daddr)) @@ -2533,10 +1800,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res, if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; - in_dev = __in_dev_get_rcu(dev_out); - if (!in_dev) - return ERR_PTR(-EINVAL); - if (type == RTN_BROADCAST) { flags |= RTCF_BROADCAST | RTCF_LOCAL; fi = NULL; @@ -2553,40 +1816,44 @@ static struct rtable *__mkroute_output(const struct fib_result *res, fi = NULL; } + fnhe = NULL; + if (fi) { + struct rtable __rcu **prth; + + fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr); + if (fnhe) + prth = &fnhe->fnhe_rth; + else + prth = __this_cpu_ptr(FIB_RES_NH(*res).nh_pcpu_rth_output); + rth = rcu_dereference(*prth); + if (rt_cache_valid(rth)) { + dst_hold(&rth->dst); + return rth; + } + } rth = rt_dst_alloc(dev_out, IN_DEV_CONF_GET(in_dev, NOPOLICY), - IN_DEV_CONF_GET(in_dev, NOXFRM)); + IN_DEV_CONF_GET(in_dev, NOXFRM), + fi); if (!rth) return ERR_PTR(-ENOBUFS); rth->dst.output = ip_output; - rth->rt_key_dst = orig_daddr; - rth->rt_key_src = orig_saddr; rth->rt_genid = rt_genid(dev_net(dev_out)); rth->rt_flags = flags; rth->rt_type = type; - rth->rt_key_tos = orig_rtos; - rth->rt_dst = fl4->daddr; - rth->rt_src = fl4->saddr; - rth->rt_route_iif = 0; - rth->rt_iif = orig_oif ? : dev_out->ifindex; - rth->rt_oif = orig_oif; - rth->rt_mark = fl4->flowi4_mark; - rth->rt_gateway = fl4->daddr; - rth->rt_spec_dst= fl4->saddr; - rth->rt_peer_genid = 0; - rth->peer = NULL; - rth->fi = NULL; + rth->rt_is_input = 0; + rth->rt_iif = orig_oif ? : 0; + rth->rt_pmtu = 0; + rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); RT_CACHE_STAT_INC(out_slow_tot); - if (flags & RTCF_LOCAL) { + if (flags & RTCF_LOCAL) rth->dst.input = ip_local_deliver; - rth->rt_spec_dst = fl4->daddr; - } if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) { - rth->rt_spec_dst = fl4->saddr; if (flags & RTCF_LOCAL && !(dev_out->flags & IFF_LOOPBACK)) { rth->dst.output = ip_mc_output; @@ -2603,34 +1870,28 @@ static struct rtable *__mkroute_output(const struct fib_result *res, #endif } - rt_set_nexthop(rth, fl4, res, fi, type, 0); + rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0); return rth; } /* * Major route resolver routine. - * called with rcu_read_lock(); */ -static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) +struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) { struct net_device *dev_out = NULL; __u8 tos = RT_FL_TOS(fl4); unsigned int flags = 0; struct fib_result res; struct rtable *rth; - __be32 orig_daddr; - __be32 orig_saddr; int orig_oif; + res.tclassid = 0; res.fi = NULL; -#ifdef CONFIG_IP_MULTIPLE_TABLES - res.r = NULL; -#endif + res.table = NULL; - orig_daddr = fl4->daddr; - orig_saddr = fl4->saddr; orig_oif = fl4->flowi4_oif; fl4->flowi4_iif = net->loopback_dev->ifindex; @@ -2730,6 +1991,7 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) if (fib_lookup(net, fl4, &res)) { res.fi = NULL; + res.table = NULL; if (fl4->flowi4_oif) { /* Apparently, routing tables are wrong. Assume, that the destination is on link. @@ -2768,7 +2030,6 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) } dev_out = net->loopback_dev; fl4->flowi4_oif = dev_out->ifindex; - res.fi = NULL; flags |= RTCF_LOCAL; goto make_route; } @@ -2791,60 +2052,12 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) make_route: - rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif, - tos, dev_out, flags); - if (!IS_ERR(rth)) { - unsigned int hash; - - hash = rt_hash(orig_daddr, orig_saddr, orig_oif, - rt_genid(dev_net(dev_out))); - rth = rt_intern_hash(hash, rth, NULL, orig_oif); - } + rth = __mkroute_output(&res, fl4, orig_oif, dev_out, flags); out: rcu_read_unlock(); return rth; } - -struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp4) -{ - struct rtable *rth; - unsigned int hash; - - if (!rt_caching(net)) - goto slow_output; - - hash = rt_hash(flp4->daddr, flp4->saddr, flp4->flowi4_oif, rt_genid(net)); - - rcu_read_lock_bh(); - for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth; - rth = rcu_dereference_bh(rth->dst.rt_next)) { - if (rth->rt_key_dst == flp4->daddr && - rth->rt_key_src == flp4->saddr && - rt_is_output_route(rth) && - rth->rt_oif == flp4->flowi4_oif && - rth->rt_mark == flp4->flowi4_mark && - !((rth->rt_key_tos ^ flp4->flowi4_tos) & - (IPTOS_RT_MASK | RTO_ONLINK)) && - net_eq(dev_net(rth->dst.dev), net) && - !rt_is_expired(rth)) { - ipv4_validate_peer(rth); - dst_use(&rth->dst, jiffies); - RT_CACHE_STAT_INC(out_hit); - rcu_read_unlock_bh(); - if (!flp4->saddr) - flp4->saddr = rth->rt_src; - if (!flp4->daddr) - flp4->daddr = rth->rt_dst; - return rth; - } - RT_CACHE_STAT_INC(out_hlist_search); - } - rcu_read_unlock_bh(); - -slow_output: - return ip_route_output_slow(net, flp4); -} EXPORT_SYMBOL_GPL(__ip_route_output_key); static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) @@ -2859,7 +2072,13 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) return mtu ? : dst->dev->mtu; } -static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) +static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) +{ +} + +static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) { } @@ -2872,53 +2091,42 @@ static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst, static struct dst_ops ipv4_dst_blackhole_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), - .destroy = ipv4_dst_destroy, .check = ipv4_blackhole_dst_check, .mtu = ipv4_blackhole_mtu, .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, + .redirect = ipv4_rt_blackhole_redirect, .cow_metrics = ipv4_rt_blackhole_cow_metrics, .neigh_lookup = ipv4_neigh_lookup, }; struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig) { - struct rtable *rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, 0, 0); struct rtable *ort = (struct rtable *) dst_orig; + struct rtable *rt; + rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, 0); if (rt) { struct dst_entry *new = &rt->dst; new->__use = 1; new->input = dst_discard; new->output = dst_discard; - dst_copy_metrics(new, &ort->dst); new->dev = ort->dst.dev; if (new->dev) dev_hold(new->dev); - rt->rt_key_dst = ort->rt_key_dst; - rt->rt_key_src = ort->rt_key_src; - rt->rt_key_tos = ort->rt_key_tos; - rt->rt_route_iif = ort->rt_route_iif; + rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; - rt->rt_oif = ort->rt_oif; - rt->rt_mark = ort->rt_mark; + rt->rt_pmtu = ort->rt_pmtu; rt->rt_genid = rt_genid(net); rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; - rt->rt_dst = ort->rt_dst; - rt->rt_src = ort->rt_src; rt->rt_gateway = ort->rt_gateway; - rt->rt_spec_dst = ort->rt_spec_dst; - rt->peer = ort->peer; - if (rt->peer) - atomic_inc(&rt->peer->refcnt); - rt->fi = ort->fi; - if (rt->fi) - atomic_inc(&rt->fi->fib_clntref); + + INIT_LIST_HEAD(&rt->rt_uncached); dst_free(new); } @@ -2945,16 +2153,16 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, } EXPORT_SYMBOL_GPL(ip_route_output_flow); -static int rt_fill_info(struct net *net, - struct sk_buff *skb, u32 pid, u32 seq, int event, - int nowait, unsigned int flags) +static int rt_fill_info(struct net *net, __be32 dst, __be32 src, + struct flowi4 *fl4, struct sk_buff *skb, u32 pid, + u32 seq, int event, int nowait, unsigned int flags) { struct rtable *rt = skb_rtable(skb); struct rtmsg *r; struct nlmsghdr *nlh; unsigned long expires = 0; - const struct inet_peer *peer = rt->peer; - u32 id = 0, ts = 0, tsage = 0, error; + u32 error; + u32 metrics[RTAX_MAX]; nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags); if (nlh == NULL) @@ -2964,7 +2172,7 @@ static int rt_fill_info(struct net *net, r->rtm_family = AF_INET; r->rtm_dst_len = 32; r->rtm_src_len = 0; - r->rtm_tos = rt->rt_key_tos; + r->rtm_tos = fl4->flowi4_tos; r->rtm_table = RT_TABLE_MAIN; if (nla_put_u32(skb, RTA_TABLE, RT_TABLE_MAIN)) goto nla_put_failure; @@ -2975,11 +2183,11 @@ static int rt_fill_info(struct net *net, if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; - if (nla_put_be32(skb, RTA_DST, rt->rt_dst)) + if (nla_put_be32(skb, RTA_DST, dst)) goto nla_put_failure; - if (rt->rt_key_src) { + if (src) { r->rtm_src_len = 32; - if (nla_put_be32(skb, RTA_SRC, rt->rt_key_src)) + if (nla_put_be32(skb, RTA_SRC, src)) goto nla_put_failure; } if (rt->dst.dev && @@ -2990,69 +2198,40 @@ static int rt_fill_info(struct net *net, nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid)) goto nla_put_failure; #endif - if (rt_is_input_route(rt)) { - if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_spec_dst)) - goto nla_put_failure; - } else if (rt->rt_src != rt->rt_key_src) { - if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_src)) + if (!rt_is_input_route(rt) && + fl4->saddr != src) { + if (nla_put_be32(skb, RTA_PREFSRC, fl4->saddr)) goto nla_put_failure; } - if (rt->rt_dst != rt->rt_gateway && + if (rt->rt_gateway && nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway)) goto nla_put_failure; - if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) + memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); + if (rt->rt_pmtu) + metrics[RTAX_MTU - 1] = rt->rt_pmtu; + if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; - if (rt->rt_mark && - nla_put_be32(skb, RTA_MARK, rt->rt_mark)) + if (fl4->flowi4_mark && + nla_put_be32(skb, RTA_MARK, fl4->flowi4_mark)) goto nla_put_failure; error = rt->dst.error; - if (peer) { - inet_peer_refcheck(rt->peer); - id = atomic_read(&peer->ip_id_count) & 0xffff; - if (peer->tcp_ts_stamp) { - ts = peer->tcp_ts; - tsage = get_seconds() - peer->tcp_ts_stamp; - } - expires = ACCESS_ONCE(peer->pmtu_expires); - if (expires) { - if (time_before(jiffies, expires)) - expires -= jiffies; - else - expires = 0; - } + expires = rt->dst.expires; + if (expires) { + if (time_before(jiffies, expires)) + expires -= jiffies; + else + expires = 0; } if (rt_is_input_route(rt)) { -#ifdef CONFIG_IP_MROUTE - __be32 dst = rt->rt_dst; - - if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) && - IPV4_DEVCONF_ALL(net, MC_FORWARDING)) { - int err = ipmr_get_route(net, skb, - rt->rt_src, rt->rt_dst, - r, nowait); - if (err <= 0) { - if (!nowait) { - if (err == 0) - return 0; - goto nla_put_failure; - } else { - if (err == -EMSGSIZE) - goto nla_put_failure; - error = err; - } - } - } else -#endif - if (nla_put_u32(skb, RTA_IIF, rt->rt_iif)) - goto nla_put_failure; + if (nla_put_u32(skb, RTA_IIF, rt->rt_iif)) + goto nla_put_failure; } - if (rtnl_put_cacheinfo(skb, &rt->dst, id, ts, tsage, - expires, error) < 0) + if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0) goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -3068,6 +2247,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; struct rtable *rt = NULL; + struct flowi4 fl4; __be32 dst = 0; __be32 src = 0; u32 iif; @@ -3102,6 +2282,13 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0; mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0; + memset(&fl4, 0, sizeof(fl4)); + fl4.daddr = dst; + fl4.saddr = src; + fl4.flowi4_tos = rtm->rtm_tos; + fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; + fl4.flowi4_mark = mark; + if (iif) { struct net_device *dev; @@ -3122,13 +2309,6 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void if (err == 0 && rt->dst.error) err = -rt->dst.error; } else { - struct flowi4 fl4 = { - .daddr = dst, - .saddr = src, - .flowi4_tos = rtm->rtm_tos, - .flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0, - .flowi4_mark = mark, - }; rt = ip_route_output_key(net, &fl4); err = 0; @@ -3143,7 +2323,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; - err = rt_fill_info(net, skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, + err = rt_fill_info(net, dst, src, &fl4, skb, + NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, RTM_NEWROUTE, 0, 0); if (err <= 0) goto errout_free; @@ -3159,43 +2340,6 @@ errout_free: int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) { - struct rtable *rt; - int h, s_h; - int idx, s_idx; - struct net *net; - - net = sock_net(skb->sk); - - s_h = cb->args[0]; - if (s_h < 0) - s_h = 0; - s_idx = idx = cb->args[1]; - for (h = s_h; h <= rt_hash_mask; h++, s_idx = 0) { - if (!rt_hash_table[h].chain) - continue; - rcu_read_lock_bh(); - for (rt = rcu_dereference_bh(rt_hash_table[h].chain), idx = 0; rt; - rt = rcu_dereference_bh(rt->dst.rt_next), idx++) { - if (!net_eq(dev_net(rt->dst.dev), net) || idx < s_idx) - continue; - if (rt_is_expired(rt)) - continue; - skb_dst_set_noref(skb, &rt->dst); - if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, RTM_NEWROUTE, - 1, NLM_F_MULTI) <= 0) { - skb_dst_drop(skb); - rcu_read_unlock_bh(); - goto done; - } - skb_dst_drop(skb); - } - rcu_read_unlock_bh(); - } - -done: - cb->args[0] = h; - cb->args[1] = idx; return skb->len; } @@ -3400,26 +2544,34 @@ static __net_initdata struct pernet_operations rt_genid_ops = { .init = rt_genid_init, }; +static int __net_init ipv4_inetpeer_init(struct net *net) +{ + struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL); -#ifdef CONFIG_IP_ROUTE_CLASSID -struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; -#endif /* CONFIG_IP_ROUTE_CLASSID */ + if (!bp) + return -ENOMEM; + inet_peer_base_init(bp); + net->ipv4.peers = bp; + return 0; +} -static __initdata unsigned long rhash_entries; -static int __init set_rhash_entries(char *str) +static void __net_exit ipv4_inetpeer_exit(struct net *net) { - ssize_t ret; + struct inet_peer_base *bp = net->ipv4.peers; - if (!str) - return 0; + net->ipv4.peers = NULL; + inetpeer_invalidate_tree(bp); + kfree(bp); +} - ret = kstrtoul(str, 0, &rhash_entries); - if (ret) - return 0; +static __net_initdata struct pernet_operations ipv4_inetpeer_ops = { + .init = ipv4_inetpeer_init, + .exit = ipv4_inetpeer_exit, +}; - return 1; -} -__setup("rhash_entries=", set_rhash_entries); +#ifdef CONFIG_IP_ROUTE_CLASSID +struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; +#endif /* CONFIG_IP_ROUTE_CLASSID */ int __init ip_rt_init(void) { @@ -3443,31 +2595,12 @@ int __init ip_rt_init(void) if (dst_entries_init(&ipv4_dst_blackhole_ops) < 0) panic("IP: failed to allocate ipv4_dst_blackhole_ops counter\n"); - rt_hash_table = (struct rt_hash_bucket *) - alloc_large_system_hash("IP route cache", - sizeof(struct rt_hash_bucket), - rhash_entries, - (totalram_pages >= 128 * 1024) ? - 15 : 17, - 0, - &rt_hash_log, - &rt_hash_mask, - 0, - rhash_entries ? 0 : 512 * 1024); - memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket)); - rt_hash_lock_init(); - - ipv4_dst_ops.gc_thresh = (rt_hash_mask + 1); - ip_rt_max_size = (rt_hash_mask + 1) * 16; + ipv4_dst_ops.gc_thresh = ~0; + ip_rt_max_size = INT_MAX; devinet_init(); ip_fib_init(); - INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func); - expires_ljiffies = jiffies; - schedule_delayed_work(&expires_work, - net_random() % ip_rt_gc_interval + ip_rt_gc_interval); - if (ip_rt_proc_init()) pr_err("Unable to create route proc files\n"); #ifdef CONFIG_XFRM @@ -3480,6 +2613,7 @@ int __init ip_rt_init(void) register_pernet_subsys(&sysctl_route_ops); #endif register_pernet_subsys(&rt_genid_ops); + register_pernet_subsys(&ipv4_inetpeer_ops); return rc; } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index eab2a7fb15d..650e1528e1e 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -293,7 +293,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, &hash_location, 0); + tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL); if (!cookie_check_timestamp(&tcp_opt, &ecn_ok)) goto out; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index ef32956ed65..1b5ce96707a 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -184,7 +184,7 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, int ret; unsigned long vec[3]; struct net *net = current->nsproxy->net_ns; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM struct mem_cgroup *memcg; #endif @@ -203,7 +203,7 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, if (ret) return ret; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM rcu_read_lock(); memcg = mem_cgroup_from_task(current); @@ -301,6 +301,13 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { + .procname = "ip_early_demux", + .data = &sysctl_ip_early_demux, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { .procname = "ip_dynaddr", .data = &sysctl_ip_dynaddr, .maxlen = sizeof(int), @@ -360,6 +367,13 @@ static struct ctl_table ipv4_table[] = { }, #endif { + .procname = "tcp_fastopen", + .data = &sysctl_tcp_fastopen, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "tcp_tw_recycle", .data = &tcp_death_row.sysctl_tw_recycle, .maxlen = sizeof(int), @@ -591,6 +605,20 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_limit_output_bytes", + .data = &sysctl_tcp_limit_output_bytes, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_challenge_ack_limit", + .data = &sysctl_tcp_challenge_ack_limit, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, #ifdef CONFIG_NET_DMA { .procname = "tcp_dma_copybreak", @@ -756,13 +784,6 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { - .procname = "rt_cache_rebuild_count", - .data = &init_net.ipv4.sysctl_rt_cache_rebuild_count, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "ping_group_range", .data = &init_net.ipv4.sysctl_ping_group_range, .maxlen = sizeof(init_net.ipv4.sysctl_ping_group_range), @@ -801,8 +822,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) table[5].data = &net->ipv4.sysctl_icmp_ratemask; table[6].data = - &net->ipv4.sysctl_rt_cache_rebuild_count; - table[7].data = &net->ipv4.sysctl_ping_group_range; } @@ -814,8 +833,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) net->ipv4.sysctl_ping_group_range[0] = 1; net->ipv4.sysctl_ping_group_range[1] = 0; - net->ipv4.sysctl_rt_cache_rebuild_count = 4; - tcp_init_mem(net); net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3ba605f60e4..2109ff4a1da 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -270,6 +270,7 @@ #include <linux/slab.h> #include <net/icmp.h> +#include <net/inet_common.h> #include <net/tcp.h> #include <net/xfrm.h> #include <net/ip.h> @@ -376,6 +377,7 @@ void tcp_init_sock(struct sock *sk) skb_queue_head_init(&tp->out_of_order_queue); tcp_init_xmit_timers(sk); tcp_prequeue_init(tp); + INIT_LIST_HEAD(&tp->tsq_node); icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->mdev = TCP_TIMEOUT_INIT; @@ -796,6 +798,10 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, inet_csk(sk)->icsk_ext_hdr_len - tp->tcp_header_len); + /* TSQ : try to have two TSO segments in flight */ + xmit_size_goal = min_t(u32, xmit_size_goal, + sysctl_tcp_limit_output_bytes >> 1); + xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal); /* We try hard to avoid divides here */ @@ -805,7 +811,9 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, old_size_goal + mss_now > xmit_size_goal)) { xmit_size_goal = old_size_goal; } else { - tp->xmit_size_goal_segs = xmit_size_goal / mss_now; + tp->xmit_size_goal_segs = + min_t(u16, xmit_size_goal / mss_now, + sk->sk_gso_max_segs); xmit_size_goal = tp->xmit_size_goal_segs * mss_now; } } @@ -977,26 +985,67 @@ static inline int select_size(const struct sock *sk, bool sg) return tmp; } +void tcp_free_fastopen_req(struct tcp_sock *tp) +{ + if (tp->fastopen_req != NULL) { + kfree(tp->fastopen_req); + tp->fastopen_req = NULL; + } +} + +static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) +{ + struct tcp_sock *tp = tcp_sk(sk); + int err, flags; + + if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE)) + return -EOPNOTSUPP; + if (tp->fastopen_req != NULL) + return -EALREADY; /* Another Fast Open is in progress */ + + tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request), + sk->sk_allocation); + if (unlikely(tp->fastopen_req == NULL)) + return -ENOBUFS; + tp->fastopen_req->data = msg; + + flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; + err = __inet_stream_connect(sk->sk_socket, msg->msg_name, + msg->msg_namelen, flags); + *size = tp->fastopen_req->copied; + tcp_free_fastopen_req(tp); + return err; +} + int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size) { struct iovec *iov; struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - int iovlen, flags, err, copied; - int mss_now = 0, size_goal; + int iovlen, flags, err, copied = 0; + int mss_now = 0, size_goal, copied_syn = 0, offset = 0; bool sg; long timeo; lock_sock(sk); flags = msg->msg_flags; + if (flags & MSG_FASTOPEN) { + err = tcp_sendmsg_fastopen(sk, msg, &copied_syn); + if (err == -EINPROGRESS && copied_syn > 0) + goto out; + else if (err) + goto out_err; + offset = copied_syn; + } + timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); /* Wait for a connection to finish. */ if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) - goto out_err; + goto do_error; if (unlikely(tp->repair)) { if (tp->repair_queue == TCP_RECV_QUEUE) { @@ -1032,6 +1081,15 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, unsigned char __user *from = iov->iov_base; iov++; + if (unlikely(offset > 0)) { /* Skip bytes copied in SYN */ + if (offset >= seglen) { + offset -= seglen; + continue; + } + seglen -= offset; + from += offset; + offset = 0; + } while (seglen > 0) { int copy = 0; @@ -1194,7 +1252,7 @@ out: if (copied && likely(!tp->repair)) tcp_push(sk, flags, mss_now, tp->nonagle); release_sock(sk); - return copied; + return copied + copied_syn; do_fault: if (!skb->len) { @@ -1207,7 +1265,7 @@ do_fault: } do_error: - if (copied) + if (copied + copied_syn) goto out; out_err: err = sk_stream_error(sk, flags, err); @@ -2625,7 +2683,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, /* Cap the max timeout in ms TCP will retry/retrans * before giving up and aborting (ETIMEDOUT) a connection. */ - icsk->icsk_user_timeout = msecs_to_jiffies(val); + if (val < 0) + err = -EINVAL; + else + icsk->icsk_user_timeout = msecs_to_jiffies(val); break; default: err = -ENOPROTOOPT; @@ -3310,8 +3371,7 @@ EXPORT_SYMBOL(tcp_md5_hash_key); #endif -/** - * Each Responder maintains up to two secret values concurrently for +/* Each Responder maintains up to two secret values concurrently for * efficient secret rollover. Each secret value has 4 states: * * Generating. (tcp_secret_generating != tcp_secret_primary) @@ -3563,6 +3623,8 @@ void __init tcp_init(void) pr_info("Hash tables configured (established %u bind %u)\n", tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size); + tcp_metrics_init(); + tcp_register_congestion_control(&tcp_reno); memset(&tcp_secret_one.secrets[0], 0, sizeof(tcp_secret_one.secrets)); @@ -3573,4 +3635,5 @@ void __init tcp_init(void) tcp_secret_primary = &tcp_secret_one; tcp_secret_retiring = &tcp_secret_two; tcp_secret_secondary = &tcp_secret_two; + tcp_tasklet_init(); } diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 04dbd7ae7c6..1432cdb0644 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -291,7 +291,8 @@ bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight) left = tp->snd_cwnd - in_flight; if (sk_can_gso(sk) && left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd && - left * tp->mss_cache < sk->sk_gso_max_size) + left * tp->mss_cache < sk->sk_gso_max_size && + left < sk->sk_gso_max_segs) return true; return left <= tcp_max_tso_deferred_mss(tp); } @@ -307,6 +308,7 @@ EXPORT_SYMBOL_GPL(tcp_is_cwnd_limited); void tcp_slow_start(struct tcp_sock *tp) { int cnt; /* increase in packets */ + unsigned int delta = 0; /* RFC3465: ABC Slow start * Increase only after a full MSS of bytes is acked @@ -333,9 +335,9 @@ void tcp_slow_start(struct tcp_sock *tp) tp->snd_cwnd_cnt += cnt; while (tp->snd_cwnd_cnt >= tp->snd_cwnd) { tp->snd_cwnd_cnt -= tp->snd_cwnd; - if (tp->snd_cwnd < tp->snd_cwnd_clamp) - tp->snd_cwnd++; + delta++; } + tp->snd_cwnd = min(tp->snd_cwnd + delta, tp->snd_cwnd_clamp); } EXPORT_SYMBOL_GPL(tcp_slow_start); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c new file mode 100644 index 00000000000..a7f729c409d --- /dev/null +++ b/net/ipv4/tcp_fastopen.c @@ -0,0 +1,11 @@ +#include <linux/init.h> +#include <linux/kernel.h> + +int sysctl_tcp_fastopen; + +static int __init tcp_fastopen_init(void) +{ + return 0; +} + +late_initcall(tcp_fastopen_init); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b224eb8bce8..6e38c6c23ca 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -88,12 +88,14 @@ int sysctl_tcp_app_win __read_mostly = 31; int sysctl_tcp_adv_win_scale __read_mostly = 1; EXPORT_SYMBOL(sysctl_tcp_adv_win_scale); +/* rfc5961 challenge ack rate limiting */ +int sysctl_tcp_challenge_ack_limit = 100; + int sysctl_tcp_stdurg __read_mostly; int sysctl_tcp_rfc1337 __read_mostly; int sysctl_tcp_max_orphans __read_mostly = NR_FILE; int sysctl_tcp_frto __read_mostly = 2; int sysctl_tcp_frto_response __read_mostly; -int sysctl_tcp_nometrics_save __read_mostly; int sysctl_tcp_thin_dupack __read_mostly; @@ -701,7 +703,7 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) /* Calculate rto without backoff. This is the second half of Van Jacobson's * routine referred to above. */ -static inline void tcp_set_rto(struct sock *sk) +void tcp_set_rto(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); /* Old crap is replaced with new one. 8) @@ -728,109 +730,6 @@ static inline void tcp_set_rto(struct sock *sk) tcp_bound_rto(sk); } -/* Save metrics learned by this TCP session. - This function is called only, when TCP finishes successfully - i.e. when it enters TIME-WAIT or goes from LAST-ACK to CLOSE. - */ -void tcp_update_metrics(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - struct dst_entry *dst = __sk_dst_get(sk); - - if (sysctl_tcp_nometrics_save) - return; - - dst_confirm(dst); - - if (dst && (dst->flags & DST_HOST)) { - const struct inet_connection_sock *icsk = inet_csk(sk); - int m; - unsigned long rtt; - - if (icsk->icsk_backoff || !tp->srtt) { - /* This session failed to estimate rtt. Why? - * Probably, no packets returned in time. - * Reset our results. - */ - if (!(dst_metric_locked(dst, RTAX_RTT))) - dst_metric_set(dst, RTAX_RTT, 0); - return; - } - - rtt = dst_metric_rtt(dst, RTAX_RTT); - m = rtt - tp->srtt; - - /* If newly calculated rtt larger than stored one, - * store new one. Otherwise, use EWMA. Remember, - * rtt overestimation is always better than underestimation. - */ - if (!(dst_metric_locked(dst, RTAX_RTT))) { - if (m <= 0) - set_dst_metric_rtt(dst, RTAX_RTT, tp->srtt); - else - set_dst_metric_rtt(dst, RTAX_RTT, rtt - (m >> 3)); - } - - if (!(dst_metric_locked(dst, RTAX_RTTVAR))) { - unsigned long var; - if (m < 0) - m = -m; - - /* Scale deviation to rttvar fixed point */ - m >>= 1; - if (m < tp->mdev) - m = tp->mdev; - - var = dst_metric_rtt(dst, RTAX_RTTVAR); - if (m >= var) - var = m; - else - var -= (var - m) >> 2; - - set_dst_metric_rtt(dst, RTAX_RTTVAR, var); - } - - if (tcp_in_initial_slowstart(tp)) { - /* Slow start still did not finish. */ - if (dst_metric(dst, RTAX_SSTHRESH) && - !dst_metric_locked(dst, RTAX_SSTHRESH) && - (tp->snd_cwnd >> 1) > dst_metric(dst, RTAX_SSTHRESH)) - dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_cwnd >> 1); - if (!dst_metric_locked(dst, RTAX_CWND) && - tp->snd_cwnd > dst_metric(dst, RTAX_CWND)) - dst_metric_set(dst, RTAX_CWND, tp->snd_cwnd); - } else if (tp->snd_cwnd > tp->snd_ssthresh && - icsk->icsk_ca_state == TCP_CA_Open) { - /* Cong. avoidance phase, cwnd is reliable. */ - if (!dst_metric_locked(dst, RTAX_SSTHRESH)) - dst_metric_set(dst, RTAX_SSTHRESH, - max(tp->snd_cwnd >> 1, tp->snd_ssthresh)); - if (!dst_metric_locked(dst, RTAX_CWND)) - dst_metric_set(dst, RTAX_CWND, - (dst_metric(dst, RTAX_CWND) + - tp->snd_cwnd) >> 1); - } else { - /* Else slow start did not finish, cwnd is non-sense, - ssthresh may be also invalid. - */ - if (!dst_metric_locked(dst, RTAX_CWND)) - dst_metric_set(dst, RTAX_CWND, - (dst_metric(dst, RTAX_CWND) + - tp->snd_ssthresh) >> 1); - if (dst_metric(dst, RTAX_SSTHRESH) && - !dst_metric_locked(dst, RTAX_SSTHRESH) && - tp->snd_ssthresh > dst_metric(dst, RTAX_SSTHRESH)) - dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_ssthresh); - } - - if (!dst_metric_locked(dst, RTAX_REORDERING)) { - if (dst_metric(dst, RTAX_REORDERING) < tp->reordering && - tp->reordering != sysctl_tcp_reordering) - dst_metric_set(dst, RTAX_REORDERING, tp->reordering); - } - } -} - __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst) { __u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0); @@ -867,7 +766,7 @@ void tcp_enter_cwr(struct sock *sk, const int set_ssthresh) * Packet counting of FACK is based on in-order assumptions, therefore TCP * disables it when reordering is detected */ -static void tcp_disable_fack(struct tcp_sock *tp) +void tcp_disable_fack(struct tcp_sock *tp) { /* RFC3517 uses different metric in lost marker => reset on change */ if (tcp_is_fack(tp)) @@ -881,86 +780,6 @@ static void tcp_dsack_seen(struct tcp_sock *tp) tp->rx_opt.sack_ok |= TCP_DSACK_SEEN; } -/* Initialize metrics on socket. */ - -static void tcp_init_metrics(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - struct dst_entry *dst = __sk_dst_get(sk); - - if (dst == NULL) - goto reset; - - dst_confirm(dst); - - if (dst_metric_locked(dst, RTAX_CWND)) - tp->snd_cwnd_clamp = dst_metric(dst, RTAX_CWND); - if (dst_metric(dst, RTAX_SSTHRESH)) { - tp->snd_ssthresh = dst_metric(dst, RTAX_SSTHRESH); - if (tp->snd_ssthresh > tp->snd_cwnd_clamp) - tp->snd_ssthresh = tp->snd_cwnd_clamp; - } else { - /* ssthresh may have been reduced unnecessarily during. - * 3WHS. Restore it back to its initial default. - */ - tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; - } - if (dst_metric(dst, RTAX_REORDERING) && - tp->reordering != dst_metric(dst, RTAX_REORDERING)) { - tcp_disable_fack(tp); - tcp_disable_early_retrans(tp); - tp->reordering = dst_metric(dst, RTAX_REORDERING); - } - - if (dst_metric(dst, RTAX_RTT) == 0 || tp->srtt == 0) - goto reset; - - /* Initial rtt is determined from SYN,SYN-ACK. - * The segment is small and rtt may appear much - * less than real one. Use per-dst memory - * to make it more realistic. - * - * A bit of theory. RTT is time passed after "normal" sized packet - * is sent until it is ACKed. In normal circumstances sending small - * packets force peer to delay ACKs and calculation is correct too. - * The algorithm is adaptive and, provided we follow specs, it - * NEVER underestimate RTT. BUT! If peer tries to make some clever - * tricks sort of "quick acks" for time long enough to decrease RTT - * to low value, and then abruptly stops to do it and starts to delay - * ACKs, wait for troubles. - */ - if (dst_metric_rtt(dst, RTAX_RTT) > tp->srtt) { - tp->srtt = dst_metric_rtt(dst, RTAX_RTT); - tp->rtt_seq = tp->snd_nxt; - } - if (dst_metric_rtt(dst, RTAX_RTTVAR) > tp->mdev) { - tp->mdev = dst_metric_rtt(dst, RTAX_RTTVAR); - tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk)); - } - tcp_set_rto(sk); -reset: - if (tp->srtt == 0) { - /* RFC6298: 5.7 We've failed to get a valid RTT sample from - * 3WHS. This is most likely due to retransmission, - * including spurious one. Reset the RTO back to 3secs - * from the more aggressive 1sec to avoid more spurious - * retransmission. - */ - tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK; - inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK; - } - /* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been - * retransmitted. In light of RFC6298 more aggressive 1sec - * initRTO, we only reset cwnd when more than 1 SYN/SYN-ACK - * retransmission has occurred. - */ - if (tp->total_retrans > 1) - tp->snd_cwnd = 1; - else - tp->snd_cwnd = tcp_init_cwnd(tp, dst); - tp->snd_cwnd_stamp = tcp_time_stamp; -} - static void tcp_update_reordering(struct sock *sk, const int metric, const int ts) { @@ -2702,7 +2521,7 @@ static void tcp_cwnd_down(struct sock *sk, int flag) /* Nothing was retransmitted or returned timestamp is less * than timestamp of the first retransmission. */ -static inline int tcp_packet_delayed(const struct tcp_sock *tp) +static inline bool tcp_packet_delayed(const struct tcp_sock *tp) { return !tp->retrans_stamp || (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && @@ -2763,7 +2582,7 @@ static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh) tp->snd_cwnd_stamp = tcp_time_stamp; } -static inline int tcp_may_undo(const struct tcp_sock *tp) +static inline bool tcp_may_undo(const struct tcp_sock *tp) { return tp->undo_marker && (!tp->undo_retrans || tcp_packet_delayed(tp)); } @@ -3107,13 +2926,14 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) * tcp_xmit_retransmit_queue(). */ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, - int newly_acked_sacked, bool is_dupack, + int prior_sacked, bool is_dupack, int flag) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && (tcp_fackets_out(tp) > tp->reordering)); + int newly_acked_sacked = 0; int fast_rexmit = 0; if (WARN_ON(!tp->packets_out && tp->sacked_out)) @@ -3173,6 +2993,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, tcp_add_reno_sack(sk); } else do_lost = tcp_try_undo_partial(sk, pkts_acked); + newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked; break; case TCP_CA_Loss: if (flag & FLAG_DATA_ACKED) @@ -3194,6 +3015,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, if (is_dupack) tcp_add_reno_sack(sk); } + newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked; if (icsk->icsk_ca_state <= TCP_CA_Disorder) tcp_try_undo_dsack(sk); @@ -3552,13 +3374,13 @@ static void tcp_ack_probe(struct sock *sk) } } -static inline int tcp_ack_is_dubious(const struct sock *sk, const int flag) +static inline bool tcp_ack_is_dubious(const struct sock *sk, const int flag) { return !(flag & FLAG_NOT_DUP) || (flag & FLAG_CA_ALERT) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open; } -static inline int tcp_may_raise_cwnd(const struct sock *sk, const int flag) +static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) { const struct tcp_sock *tp = tcp_sk(sk); return (!(flag & FLAG_ECE) || tp->snd_cwnd < tp->snd_ssthresh) && @@ -3568,7 +3390,7 @@ static inline int tcp_may_raise_cwnd(const struct sock *sk, const int flag) /* Check that window update is acceptable. * The function assumes that snd_una<=ack<=snd_next. */ -static inline int tcp_may_update_window(const struct tcp_sock *tp, +static inline bool tcp_may_update_window(const struct tcp_sock *tp, const u32 ack, const u32 ack_seq, const u32 nwin) { @@ -3771,7 +3593,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) int prior_packets; int prior_sacked = tp->sacked_out; int pkts_acked = 0; - int newly_acked_sacked = 0; bool frto_cwnd = false; /* If the ack is older than previous acks @@ -3847,8 +3668,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una); pkts_acked = prior_packets - tp->packets_out; - newly_acked_sacked = (prior_packets - prior_sacked) - - (tp->packets_out - tp->sacked_out); if (tp->frto_counter) frto_cwnd = tcp_process_frto(sk, flag); @@ -3862,22 +3681,24 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_may_raise_cwnd(sk, flag)) tcp_cong_avoid(sk, ack, prior_in_flight); is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); - tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked, + tcp_fastretrans_alert(sk, pkts_acked, prior_sacked, is_dupack, flag); } else { if ((flag & FLAG_DATA_ACKED) && !frto_cwnd) tcp_cong_avoid(sk, ack, prior_in_flight); } - if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) - dst_confirm(__sk_dst_get(sk)); - + if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) { + struct dst_entry *dst = __sk_dst_get(sk); + if (dst) + dst_confirm(dst); + } return 1; no_queue: /* If data was DSACKed, see if we can undo a cwnd reduction. */ if (flag & FLAG_DSACKING_ACK) - tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked, + tcp_fastretrans_alert(sk, pkts_acked, prior_sacked, is_dupack, flag); /* If this ack opens up a zero window, clear backoff. It was * being used to time the probes, and is probably far higher than @@ -3897,8 +3718,7 @@ old_ack: */ if (TCP_SKB_CB(skb)->sacked) { flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una); - newly_acked_sacked = tp->sacked_out - prior_sacked; - tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked, + tcp_fastretrans_alert(sk, pkts_acked, prior_sacked, is_dupack, flag); } @@ -3911,7 +3731,8 @@ old_ack: * the fast version below fails. */ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx, - const u8 **hvpp, int estab) + const u8 **hvpp, int estab, + struct tcp_fastopen_cookie *foc) { const unsigned char *ptr; const struct tcphdr *th = tcp_hdr(skb); @@ -4018,8 +3839,25 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o break; } break; - } + case TCPOPT_EXP: + /* Fast Open option shares code 254 using a + * 16 bits magic number. It's valid only in + * SYN or SYN-ACK with an even size. + */ + if (opsize < TCPOLEN_EXP_FASTOPEN_BASE || + get_unaligned_be16(ptr) != TCPOPT_FASTOPEN_MAGIC || + foc == NULL || !th->syn || (opsize & 1)) + break; + foc->len = opsize - TCPOLEN_EXP_FASTOPEN_BASE; + if (foc->len >= TCP_FASTOPEN_COOKIE_MIN && + foc->len <= TCP_FASTOPEN_COOKIE_MAX) + memcpy(foc->val, ptr + 2, foc->len); + else if (foc->len != 0) + foc->len = -1; + break; + + } ptr += opsize-2; length -= opsize; } @@ -4061,7 +3899,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb, if (tcp_parse_aligned_timestamp(tp, th)) return true; } - tcp_parse_options(skb, &tp->rx_opt, hvpp, 1); + tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL); return true; } @@ -4167,7 +4005,7 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb) (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (inet_csk(sk)->icsk_rto * 1024) / HZ); } -static inline int tcp_paws_discard(const struct sock *sk, +static inline bool tcp_paws_discard(const struct sock *sk, const struct sk_buff *skb) { const struct tcp_sock *tp = tcp_sk(sk); @@ -4189,7 +4027,7 @@ static inline int tcp_paws_discard(const struct sock *sk, * (borrowed from freebsd) */ -static inline int tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq) +static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq) { return !before(end_seq, tp->rcv_wup) && !after(seq, tp->rcv_nxt + tcp_receive_window(tp)); @@ -4512,19 +4350,20 @@ static void tcp_ofo_queue(struct sock *sk) static bool tcp_prune_ofo_queue(struct sock *sk); static int tcp_prune_queue(struct sock *sk); -static int tcp_try_rmem_schedule(struct sock *sk, unsigned int size) +static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, + unsigned int size) { if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || - !sk_rmem_schedule(sk, size)) { + !sk_rmem_schedule(sk, skb, size)) { if (tcp_prune_queue(sk) < 0) return -1; - if (!sk_rmem_schedule(sk, size)) { + if (!sk_rmem_schedule(sk, skb, size)) { if (!tcp_prune_ofo_queue(sk)) return -1; - if (!sk_rmem_schedule(sk, size)) + if (!sk_rmem_schedule(sk, skb, size)) return -1; } } @@ -4579,8 +4418,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) TCP_ECN_check_ce(tp, skb); - if (tcp_try_rmem_schedule(sk, skb->truesize)) { - /* TODO: should increment a counter */ + if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFODROP); __kfree_skb(skb); return; } @@ -4589,6 +4428,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) tp->pred_flags = 0; inet_csk_schedule_ack(sk); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOQUEUE); SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n", tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); @@ -4642,6 +4482,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) { if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { /* All the bits are present. Drop. */ + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOMERGE); __kfree_skb(skb); skb = NULL; tcp_dsack_set(sk, seq, end_seq); @@ -4680,6 +4521,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) __skb_unlink(skb1, &tp->out_of_order_queue); tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, TCP_SKB_CB(skb1)->end_seq); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOMERGE); __kfree_skb(skb1); } @@ -4710,17 +4552,17 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) { - struct sk_buff *skb; + struct sk_buff *skb = NULL; struct tcphdr *th; bool fragstolen; - if (tcp_try_rmem_schedule(sk, size + sizeof(*th))) - goto err; - skb = alloc_skb(size + sizeof(*th), sk->sk_allocation); if (!skb) goto err; + if (tcp_try_rmem_schedule(sk, skb, size + sizeof(*th))) + goto err_free; + th = (struct tcphdr *)skb_put(skb, sizeof(*th)); skb_reset_transport_header(skb); memset(th, 0, sizeof(*th)); @@ -4791,7 +4633,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) if (eaten <= 0) { queue_and_out: if (eaten < 0 && - tcp_try_rmem_schedule(sk, skb->truesize)) + tcp_try_rmem_schedule(sk, skb, skb->truesize)) goto drop; eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen); @@ -5372,7 +5214,7 @@ static __sum16 __tcp_checksum_complete_user(struct sock *sk, return result; } -static inline int tcp_checksum_complete_user(struct sock *sk, +static inline bool tcp_checksum_complete_user(struct sock *sk, struct sk_buff *skb) { return !skb_csum_unnecessary(skb) && @@ -5426,11 +5268,28 @@ out: } #endif /* CONFIG_NET_DMA */ +static void tcp_send_challenge_ack(struct sock *sk) +{ + /* unprotected vars, we dont care of overwrites */ + static u32 challenge_timestamp; + static unsigned int challenge_count; + u32 now = jiffies / HZ; + + if (now != challenge_timestamp) { + challenge_timestamp = now; + challenge_count = 0; + } + if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); + tcp_send_ack(sk); + } +} + /* Does PAWS and seqno based validation of an incoming segment, flags will * play significant role here. */ -static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th, int syn_inerr) +static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, + const struct tcphdr *th, int syn_inerr) { const u8 *hash_location; struct tcp_sock *tp = tcp_sk(sk); @@ -5455,14 +5314,26 @@ static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, * an acknowledgment should be sent in reply (unless the RST * bit is set, if so drop the segment and return)". */ - if (!th->rst) + if (!th->rst) { + if (th->syn) + goto syn_challenge; tcp_send_dupack(sk, skb); + } goto discard; } /* Step 2: check RST bit */ if (th->rst) { - tcp_reset(sk); + /* RFC 5961 3.2 : + * If sequence number exactly matches RCV.NXT, then + * RESET the connection + * else + * Send a challenge ACK + */ + if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) + tcp_reset(sk); + else + tcp_send_challenge_ack(sk); goto discard; } @@ -5473,20 +5344,23 @@ static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, /* step 3: check security and precedence [ignored] */ - /* step 4: Check for a SYN in window. */ - if (th->syn && !before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { + /* step 4: Check for a SYN + * RFC 5691 4.2 : Send a challenge ack + */ + if (th->syn) { +syn_challenge: if (syn_inerr) TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONSYN); - tcp_reset(sk); - return -1; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE); + tcp_send_challenge_ack(sk); + goto discard; } - return 1; + return true; discard: __kfree_skb(skb); - return 0; + return false; } /* @@ -5516,8 +5390,9 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len) { struct tcp_sock *tp = tcp_sk(sk); - int res; + if (unlikely(sk->sk_rx_dst == NULL)) + inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb); /* * Header prediction. * The code loosely follows the one in the famous @@ -5602,7 +5477,9 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, if (tp->copied_seq == tp->rcv_nxt && len - tcp_header_len <= tp->ucopy.len) { #ifdef CONFIG_NET_DMA - if (tcp_dma_try_early_copy(sk, skb, tcp_header_len)) { + if (tp->ucopy.task == current && + sock_owned_by_user(sk) && + tcp_dma_try_early_copy(sk, skb, tcp_header_len)) { copied_early = 1; eaten = 1; } @@ -5693,9 +5570,8 @@ slow_path: * Standard slow path. */ - res = tcp_validate_incoming(sk, skb, th, 1); - if (res <= 0) - return -res; + if (!tcp_validate_incoming(sk, skb, th, 1)) + return 0; step5: if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0) @@ -5729,8 +5605,10 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) tcp_set_state(sk, TCP_ESTABLISHED); - if (skb != NULL) + if (skb != NULL) { + icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); security_inet_conn_established(sk, skb); + } /* Make sure socket is routed, for correct metrics. */ icsk->icsk_af_ops->rebuild_header(sk); @@ -5760,6 +5638,45 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) } } +static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, + struct tcp_fastopen_cookie *cookie) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL; + u16 mss = tp->rx_opt.mss_clamp; + bool syn_drop; + + if (mss == tp->rx_opt.user_mss) { + struct tcp_options_received opt; + const u8 *hash_location; + + /* Get original SYNACK MSS value if user MSS sets mss_clamp */ + tcp_clear_options(&opt); + opt.user_mss = opt.mss_clamp = 0; + tcp_parse_options(synack, &opt, &hash_location, 0, NULL); + mss = opt.mss_clamp; + } + + if (!tp->syn_fastopen) /* Ignore an unsolicited cookie */ + cookie->len = -1; + + /* The SYN-ACK neither has cookie nor acknowledges the data. Presumably + * the remote receives only the retransmitted (regular) SYNs: either + * the original SYN-data or the corresponding SYN-ACK is lost. + */ + syn_drop = (cookie->len <= 0 && data && + inet_csk(sk)->icsk_retransmits); + + tcp_fastopen_cache_set(sk, mss, cookie, syn_drop); + + if (data) { /* Retransmit unacked data in SYN */ + tcp_retransmit_skb(sk, data); + tcp_rearm_rto(sk); + return true; + } + return false; +} + static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len) { @@ -5767,9 +5684,10 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct tcp_cookie_values *cvp = tp->cookie_values; + struct tcp_fastopen_cookie foc = { .len = -1 }; int saved_clamp = tp->rx_opt.mss_clamp; - tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0); + tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, &foc); if (th->ack) { /* rfc793: @@ -5779,11 +5697,9 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, * If SEG.ACK =< ISS, or SEG.ACK > SND.NXT, send * a reset (unless the RST bit is set, if so drop * the segment and return)" - * - * We do not send data with SYN, so that RFC-correct - * test reduces to: */ - if (TCP_SKB_CB(skb)->ack_seq != tp->snd_nxt) + if (!after(TCP_SKB_CB(skb)->ack_seq, tp->snd_una) || + after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) goto reset_and_undo; if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && @@ -5895,6 +5811,10 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tcp_finish_connect(sk, skb); + if ((tp->syn_fastopen || tp->syn_data) && + tcp_rcv_fastopen_synack(sk, skb, &foc)) + return -1; + if (sk->sk_write_pending || icsk->icsk_accept_queue.rskq_defer_accept || icsk->icsk_ack.pingpong) { @@ -6013,7 +5933,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); int queued = 0; - int res; tp->rx_opt.saw_tstamp = 0; @@ -6068,9 +5987,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, return 0; } - res = tcp_validate_incoming(sk, skb, th, 0); - if (res <= 0) - return -res; + if (!tcp_validate_incoming(sk, skb, th, 0)) + return 0; /* step 5: check the ACK field */ if (th->ack) { @@ -6126,9 +6044,14 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, case TCP_FIN_WAIT1: if (tp->snd_una == tp->write_seq) { + struct dst_entry *dst; + tcp_set_state(sk, TCP_FIN_WAIT2); sk->sk_shutdown |= SEND_SHUTDOWN; - dst_confirm(__sk_dst_get(sk)); + + dst = __sk_dst_get(sk); + if (dst) + dst_confirm(dst); if (!sock_flag(sk, SOCK_DEAD)) /* Wake up lingering close() */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c8d28c433b2..00a748d1406 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -209,22 +209,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) } if (tcp_death_row.sysctl_tw_recycle && - !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr) { - struct inet_peer *peer = rt_get_peer(rt, fl4->daddr); - /* - * VJ's idea. We save last timestamp seen from - * the destination in peer table, when entering state - * TIME-WAIT * and initialize rx_opt.ts_recent from it, - * when trying new connection. - */ - if (peer) { - inet_peer_refcheck(peer); - if ((u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) { - tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp; - tp->rx_opt.ts_recent = peer->tcp_ts; - } - } - } + !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr) + tcp_fetch_timewait_stamp(sk, &rt->dst); inet->inet_dport = usin->sin_port; inet->inet_daddr = daddr; @@ -289,12 +275,15 @@ failure: EXPORT_SYMBOL(tcp_v4_connect); /* - * This routine does path mtu discovery as defined in RFC1191. + * This routine reacts to ICMP_FRAG_NEEDED mtu indications as defined in RFC1191. + * It can be called through tcp_release_cb() if socket was owned by user + * at the time tcp_v4_err() was called to handle ICMP message. */ -static void do_pmtu_discovery(struct sock *sk, const struct iphdr *iph, u32 mtu) +static void tcp_v4_mtu_reduced(struct sock *sk) { struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); + u32 mtu = tcp_sk(sk)->mtu_info; /* We are not interested in TCP_LISTEN and open_requests (SYN-ACKs * send out by Linux are always <576bytes so they should go through @@ -303,17 +292,10 @@ static void do_pmtu_discovery(struct sock *sk, const struct iphdr *iph, u32 mtu) if (sk->sk_state == TCP_LISTEN) return; - /* We don't check in the destentry if pmtu discovery is forbidden - * on this route. We just assume that no packet_to_big packets - * are send back when pmtu discovery is not active. - * There is a small race when the user changes this flag in the - * route, but I think that's acceptable. - */ - if ((dst = __sk_dst_check(sk, 0)) == NULL) + dst = inet_csk_update_pmtu(sk, mtu); + if (!dst) return; - dst->ops->update_pmtu(dst, mtu); - /* Something is about to be wrong... Remember soft error * for the case, if this connection will not able to recover. */ @@ -335,6 +317,14 @@ static void do_pmtu_discovery(struct sock *sk, const struct iphdr *iph, u32 mtu) } /* else let the usual retransmit timer handle it */ } +static void do_redirect(struct sk_buff *skb, struct sock *sk) +{ + struct dst_entry *dst = __sk_dst_check(sk, 0); + + if (dst) + dst->ops->redirect(dst, sk, skb); +} + /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should @@ -386,8 +376,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) bh_lock_sock(sk); /* If too many ICMPs get dropped on busy * servers this needs to be solved differently. + * We do take care of PMTU discovery (RFC1191) special case : + * we can receive locally generated ICMP messages while socket is held. */ - if (sock_owned_by_user(sk)) + if (sock_owned_by_user(sk) && + type != ICMP_DEST_UNREACH && + code != ICMP_FRAG_NEEDED) NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == TCP_CLOSE) @@ -408,6 +402,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) } switch (type) { + case ICMP_REDIRECT: + do_redirect(icmp_skb, sk); + goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ goto out; @@ -419,8 +416,13 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) goto out; if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */ - if (!sock_owned_by_user(sk)) - do_pmtu_discovery(sk, iph, info); + tp->mtu_info = info; + if (!sock_owned_by_user(sk)) { + tcp_v4_mtu_reduced(sk); + } else { + if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags)) + sock_hold(sk); + } goto out; } @@ -698,8 +700,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) net = dev_net(skb_dst(skb)->dev); arg.tos = ip_hdr(skb)->tos; - ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr, - &arg, arg.iov[0].iov_len); + ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); @@ -781,8 +783,8 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, if (oif) arg.bound_dev_if = oif; arg.tos = tos; - ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr, - &arg, arg.iov[0].iov_len); + ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); } @@ -825,7 +827,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct request_values *rvp, - u16 queue_mapping) + u16 queue_mapping, + bool nocache) { const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; @@ -848,7 +851,6 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, err = net_xmit_eval(err); } - dst_release(dst); return err; } @@ -856,7 +858,7 @@ static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req, struct request_values *rvp) { TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - return tcp_v4_send_synack(sk, NULL, req, rvp, 0); + return tcp_v4_send_synack(sk, NULL, req, rvp, 0, false); } /* @@ -1317,7 +1319,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = TCP_MSS_DEFAULT; tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, &hash_location, 0); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL); if (tmp_opt.cookie_plus > 0 && tmp_opt.saw_tstamp && @@ -1375,7 +1377,6 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) isn = cookie_v4_init_sequence(sk, skb, &req->mss); req->cookie_ts = tmp_opt.tstamp_ok; } else if (!isn) { - struct inet_peer *peer = NULL; struct flowi4 fl4; /* VJ's idea. We save last timestamp seen @@ -1390,12 +1391,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle && (dst = inet_csk_route_req(sk, &fl4, req)) != NULL && - fl4.daddr == saddr && - (peer = rt_get_peer((struct rtable *)dst, fl4.daddr)) != NULL) { - inet_peer_refcheck(peer); - if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL && - (s32)(peer->tcp_ts - req->ts_recent) > - TCP_PAWS_WINDOW) { + fl4.daddr == saddr) { + if (!tcp_peer_is_proven(req, dst, true)) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); goto drop_and_release; } @@ -1404,8 +1401,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) else if (!sysctl_tcp_syncookies && (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < (sysctl_max_syn_backlog >> 2)) && - (!peer || !peer->tcp_ts_stamp) && - (!dst || !dst_metric(dst, RTAX_RTT))) { + !tcp_peer_is_proven(req, dst, false)) { /* Without syncookies last quarter of * backlog is filled with destinations, * proven to be alive. @@ -1425,7 +1421,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (tcp_v4_send_synack(sk, dst, req, (struct request_values *)&tmp_ext, - skb_get_queue_mapping(skb)) || + skb_get_queue_mapping(skb), + want_cookie) || want_cookie) goto drop_and_free; @@ -1467,6 +1464,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, goto exit_nonewsk; newsk->sk_gso_type = SKB_GSO_TCPV4; + inet_sk_rx_dst_set(newsk, skb); newtp = tcp_sk(newsk); newinet = inet_sk(newsk); @@ -1622,7 +1620,16 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) #endif if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ + struct dst_entry *dst = sk->sk_rx_dst; + sock_rps_save_rxhash(sk, skb); + if (dst) { + if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || + dst->ops->check(dst, 0) == NULL) { + dst_release(dst); + sk->sk_rx_dst = NULL; + } + } if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) { rsk = sk; goto reset; @@ -1672,6 +1679,44 @@ csum_err: } EXPORT_SYMBOL(tcp_v4_do_rcv); +void tcp_v4_early_demux(struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + const struct iphdr *iph; + const struct tcphdr *th; + struct sock *sk; + + if (skb->pkt_type != PACKET_HOST) + return; + + if (!pskb_may_pull(skb, ip_hdrlen(skb) + sizeof(struct tcphdr))) + return; + + iph = ip_hdr(skb); + th = (struct tcphdr *) ((char *)iph + ip_hdrlen(skb)); + + if (th->doff < sizeof(struct tcphdr) / 4) + return; + + sk = __inet_lookup_established(net, &tcp_hashinfo, + iph->saddr, th->source, + iph->daddr, ntohs(th->dest), + skb->skb_iif); + if (sk) { + skb->sk = sk; + skb->destructor = sock_edemux; + if (sk->sk_state != TCP_TIME_WAIT) { + struct dst_entry *dst = sk->sk_rx_dst; + + if (dst) + dst = dst_check(dst, 0); + if (dst && + inet_sk(sk)->rx_dst_ifindex == skb->skb_iif) + skb_dst_set_noref(skb, dst); + } + } +} + /* * From tcp_input.c */ @@ -1821,49 +1866,29 @@ do_time_wait: goto discard_it; } -struct inet_peer *tcp_v4_get_peer(struct sock *sk, bool *release_it) -{ - struct rtable *rt = (struct rtable *) __sk_dst_get(sk); - struct inet_sock *inet = inet_sk(sk); - struct inet_peer *peer; - - if (!rt || - inet->cork.fl.u.ip4.daddr != inet->inet_daddr) { - peer = inet_getpeer_v4(inet->inet_daddr, 1); - *release_it = true; - } else { - if (!rt->peer) - rt_bind_peer(rt, inet->inet_daddr, 1); - peer = rt->peer; - *release_it = false; - } - - return peer; -} -EXPORT_SYMBOL(tcp_v4_get_peer); - -void *tcp_v4_tw_get_peer(struct sock *sk) -{ - const struct inet_timewait_sock *tw = inet_twsk(sk); - - return inet_getpeer_v4(tw->tw_daddr, 1); -} -EXPORT_SYMBOL(tcp_v4_tw_get_peer); - static struct timewait_sock_ops tcp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp_timewait_sock), .twsk_unique = tcp_twsk_unique, .twsk_destructor= tcp_twsk_destructor, - .twsk_getpeer = tcp_v4_tw_get_peer, }; +void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + + dst_hold(dst); + sk->sk_rx_dst = dst; + inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; +} +EXPORT_SYMBOL(inet_sk_rx_dst_set); + const struct inet_connection_sock_af_ops ipv4_specific = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, + .sk_rx_dst_set = inet_sk_rx_dst_set, .conn_request = tcp_v4_conn_request, .syn_recv_sock = tcp_v4_syn_recv_sock, - .get_peer = tcp_v4_get_peer, .net_header_len = sizeof(struct iphdr), .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, @@ -1953,6 +1978,9 @@ void tcp_v4_destroy_sock(struct sock *sk) tp->cookie_values = NULL; } + /* If socket is aborted during connect operation */ + tcp_free_fastopen_req(tp); + sk_sockets_allocated_dec(sk); sock_release_memcg(sk); } @@ -2593,6 +2621,8 @@ struct proto tcp_prot = { .sendmsg = tcp_sendmsg, .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, + .release_cb = tcp_release_cb, + .mtu_reduced = tcp_v4_mtu_reduced, .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, @@ -2614,7 +2644,7 @@ struct proto tcp_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM .init_cgroup = tcp_init_cgroup, .destroy_cgroup = tcp_destroy_cgroup, .proto_cgroup = tcp_proto_cgroup, @@ -2624,13 +2654,11 @@ EXPORT_SYMBOL(tcp_prot); static int __net_init tcp_sk_init(struct net *net) { - return inet_ctl_sock_create(&net->ipv4.tcp_sock, - PF_INET, SOCK_RAW, IPPROTO_TCP, net); + return 0; } static void __net_exit tcp_sk_exit(struct net *net) { - inet_ctl_sock_destroy(net->ipv4.tcp_sock); } static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c new file mode 100644 index 00000000000..0abe67bb4d3 --- /dev/null +++ b/net/ipv4/tcp_metrics.c @@ -0,0 +1,757 @@ +#include <linux/rcupdate.h> +#include <linux/spinlock.h> +#include <linux/jiffies.h> +#include <linux/bootmem.h> +#include <linux/module.h> +#include <linux/cache.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/tcp.h> +#include <linux/hash.h> + +#include <net/inet_connection_sock.h> +#include <net/net_namespace.h> +#include <net/request_sock.h> +#include <net/inetpeer.h> +#include <net/sock.h> +#include <net/ipv6.h> +#include <net/dst.h> +#include <net/tcp.h> + +int sysctl_tcp_nometrics_save __read_mostly; + +enum tcp_metric_index { + TCP_METRIC_RTT, + TCP_METRIC_RTTVAR, + TCP_METRIC_SSTHRESH, + TCP_METRIC_CWND, + TCP_METRIC_REORDERING, + + /* Always last. */ + TCP_METRIC_MAX, +}; + +struct tcp_fastopen_metrics { + u16 mss; + u16 syn_loss:10; /* Recurring Fast Open SYN losses */ + unsigned long last_syn_loss; /* Last Fast Open SYN loss */ + struct tcp_fastopen_cookie cookie; +}; + +struct tcp_metrics_block { + struct tcp_metrics_block __rcu *tcpm_next; + struct inetpeer_addr tcpm_addr; + unsigned long tcpm_stamp; + u32 tcpm_ts; + u32 tcpm_ts_stamp; + u32 tcpm_lock; + u32 tcpm_vals[TCP_METRIC_MAX]; + struct tcp_fastopen_metrics tcpm_fastopen; +}; + +static bool tcp_metric_locked(struct tcp_metrics_block *tm, + enum tcp_metric_index idx) +{ + return tm->tcpm_lock & (1 << idx); +} + +static u32 tcp_metric_get(struct tcp_metrics_block *tm, + enum tcp_metric_index idx) +{ + return tm->tcpm_vals[idx]; +} + +static u32 tcp_metric_get_jiffies(struct tcp_metrics_block *tm, + enum tcp_metric_index idx) +{ + return msecs_to_jiffies(tm->tcpm_vals[idx]); +} + +static void tcp_metric_set(struct tcp_metrics_block *tm, + enum tcp_metric_index idx, + u32 val) +{ + tm->tcpm_vals[idx] = val; +} + +static void tcp_metric_set_msecs(struct tcp_metrics_block *tm, + enum tcp_metric_index idx, + u32 val) +{ + tm->tcpm_vals[idx] = jiffies_to_msecs(val); +} + +static bool addr_same(const struct inetpeer_addr *a, + const struct inetpeer_addr *b) +{ + const struct in6_addr *a6, *b6; + + if (a->family != b->family) + return false; + if (a->family == AF_INET) + return a->addr.a4 == b->addr.a4; + + a6 = (const struct in6_addr *) &a->addr.a6[0]; + b6 = (const struct in6_addr *) &b->addr.a6[0]; + + return ipv6_addr_equal(a6, b6); +} + +struct tcpm_hash_bucket { + struct tcp_metrics_block __rcu *chain; +}; + +static DEFINE_SPINLOCK(tcp_metrics_lock); + +static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst) +{ + u32 val; + + tm->tcpm_stamp = jiffies; + + val = 0; + if (dst_metric_locked(dst, RTAX_RTT)) + val |= 1 << TCP_METRIC_RTT; + if (dst_metric_locked(dst, RTAX_RTTVAR)) + val |= 1 << TCP_METRIC_RTTVAR; + if (dst_metric_locked(dst, RTAX_SSTHRESH)) + val |= 1 << TCP_METRIC_SSTHRESH; + if (dst_metric_locked(dst, RTAX_CWND)) + val |= 1 << TCP_METRIC_CWND; + if (dst_metric_locked(dst, RTAX_REORDERING)) + val |= 1 << TCP_METRIC_REORDERING; + tm->tcpm_lock = val; + + tm->tcpm_vals[TCP_METRIC_RTT] = dst_metric_raw(dst, RTAX_RTT); + tm->tcpm_vals[TCP_METRIC_RTTVAR] = dst_metric_raw(dst, RTAX_RTTVAR); + tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH); + tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND); + tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING); + tm->tcpm_ts = 0; + tm->tcpm_ts_stamp = 0; + tm->tcpm_fastopen.mss = 0; + tm->tcpm_fastopen.syn_loss = 0; + tm->tcpm_fastopen.cookie.len = 0; +} + +static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, + struct inetpeer_addr *addr, + unsigned int hash, + bool reclaim) +{ + struct tcp_metrics_block *tm; + struct net *net; + + spin_lock_bh(&tcp_metrics_lock); + net = dev_net(dst->dev); + if (unlikely(reclaim)) { + struct tcp_metrics_block *oldest; + + oldest = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); + for (tm = rcu_dereference(oldest->tcpm_next); tm; + tm = rcu_dereference(tm->tcpm_next)) { + if (time_before(tm->tcpm_stamp, oldest->tcpm_stamp)) + oldest = tm; + } + tm = oldest; + } else { + tm = kmalloc(sizeof(*tm), GFP_ATOMIC); + if (!tm) + goto out_unlock; + } + tm->tcpm_addr = *addr; + + tcpm_suck_dst(tm, dst); + + if (likely(!reclaim)) { + tm->tcpm_next = net->ipv4.tcp_metrics_hash[hash].chain; + rcu_assign_pointer(net->ipv4.tcp_metrics_hash[hash].chain, tm); + } + +out_unlock: + spin_unlock_bh(&tcp_metrics_lock); + return tm; +} + +#define TCP_METRICS_TIMEOUT (60 * 60 * HZ) + +static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst) +{ + if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT))) + tcpm_suck_dst(tm, dst); +} + +#define TCP_METRICS_RECLAIM_DEPTH 5 +#define TCP_METRICS_RECLAIM_PTR (struct tcp_metrics_block *) 0x1UL + +static struct tcp_metrics_block *tcp_get_encode(struct tcp_metrics_block *tm, int depth) +{ + if (tm) + return tm; + if (depth > TCP_METRICS_RECLAIM_DEPTH) + return TCP_METRICS_RECLAIM_PTR; + return NULL; +} + +static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *addr, + struct net *net, unsigned int hash) +{ + struct tcp_metrics_block *tm; + int depth = 0; + + for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm; + tm = rcu_dereference(tm->tcpm_next)) { + if (addr_same(&tm->tcpm_addr, addr)) + break; + depth++; + } + return tcp_get_encode(tm, depth); +} + +static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, + struct dst_entry *dst) +{ + struct tcp_metrics_block *tm; + struct inetpeer_addr addr; + unsigned int hash; + struct net *net; + + addr.family = req->rsk_ops->family; + switch (addr.family) { + case AF_INET: + addr.addr.a4 = inet_rsk(req)->rmt_addr; + hash = (__force unsigned int) addr.addr.a4; + break; + case AF_INET6: + *(struct in6_addr *)addr.addr.a6 = inet6_rsk(req)->rmt_addr; + hash = ipv6_addr_hash(&inet6_rsk(req)->rmt_addr); + break; + default: + return NULL; + } + + net = dev_net(dst->dev); + hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log); + + for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm; + tm = rcu_dereference(tm->tcpm_next)) { + if (addr_same(&tm->tcpm_addr, &addr)) + break; + } + tcpm_check_stamp(tm, dst); + return tm; +} + +static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw) +{ + struct inet6_timewait_sock *tw6; + struct tcp_metrics_block *tm; + struct inetpeer_addr addr; + unsigned int hash; + struct net *net; + + addr.family = tw->tw_family; + switch (addr.family) { + case AF_INET: + addr.addr.a4 = tw->tw_daddr; + hash = (__force unsigned int) addr.addr.a4; + break; + case AF_INET6: + tw6 = inet6_twsk((struct sock *)tw); + *(struct in6_addr *)addr.addr.a6 = tw6->tw_v6_daddr; + hash = ipv6_addr_hash(&tw6->tw_v6_daddr); + break; + default: + return NULL; + } + + net = twsk_net(tw); + hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log); + + for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm; + tm = rcu_dereference(tm->tcpm_next)) { + if (addr_same(&tm->tcpm_addr, &addr)) + break; + } + return tm; +} + +static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, + struct dst_entry *dst, + bool create) +{ + struct tcp_metrics_block *tm; + struct inetpeer_addr addr; + unsigned int hash; + struct net *net; + bool reclaim; + + addr.family = sk->sk_family; + switch (addr.family) { + case AF_INET: + addr.addr.a4 = inet_sk(sk)->inet_daddr; + hash = (__force unsigned int) addr.addr.a4; + break; + case AF_INET6: + *(struct in6_addr *)addr.addr.a6 = inet6_sk(sk)->daddr; + hash = ipv6_addr_hash(&inet6_sk(sk)->daddr); + break; + default: + return NULL; + } + + net = dev_net(dst->dev); + hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log); + + tm = __tcp_get_metrics(&addr, net, hash); + reclaim = false; + if (tm == TCP_METRICS_RECLAIM_PTR) { + reclaim = true; + tm = NULL; + } + if (!tm && create) + tm = tcpm_new(dst, &addr, hash, reclaim); + else + tcpm_check_stamp(tm, dst); + + return tm; +} + +/* Save metrics learned by this TCP session. This function is called + * only, when TCP finishes successfully i.e. when it enters TIME-WAIT + * or goes from LAST-ACK to CLOSE. + */ +void tcp_update_metrics(struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + struct dst_entry *dst = __sk_dst_get(sk); + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_metrics_block *tm; + unsigned long rtt; + u32 val; + int m; + + if (sysctl_tcp_nometrics_save || !dst) + return; + + if (dst->flags & DST_HOST) + dst_confirm(dst); + + rcu_read_lock(); + if (icsk->icsk_backoff || !tp->srtt) { + /* This session failed to estimate rtt. Why? + * Probably, no packets returned in time. Reset our + * results. + */ + tm = tcp_get_metrics(sk, dst, false); + if (tm && !tcp_metric_locked(tm, TCP_METRIC_RTT)) + tcp_metric_set(tm, TCP_METRIC_RTT, 0); + goto out_unlock; + } else + tm = tcp_get_metrics(sk, dst, true); + + if (!tm) + goto out_unlock; + + rtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT); + m = rtt - tp->srtt; + + /* If newly calculated rtt larger than stored one, store new + * one. Otherwise, use EWMA. Remember, rtt overestimation is + * always better than underestimation. + */ + if (!tcp_metric_locked(tm, TCP_METRIC_RTT)) { + if (m <= 0) + rtt = tp->srtt; + else + rtt -= (m >> 3); + tcp_metric_set_msecs(tm, TCP_METRIC_RTT, rtt); + } + + if (!tcp_metric_locked(tm, TCP_METRIC_RTTVAR)) { + unsigned long var; + + if (m < 0) + m = -m; + + /* Scale deviation to rttvar fixed point */ + m >>= 1; + if (m < tp->mdev) + m = tp->mdev; + + var = tcp_metric_get_jiffies(tm, TCP_METRIC_RTTVAR); + if (m >= var) + var = m; + else + var -= (var - m) >> 2; + + tcp_metric_set_msecs(tm, TCP_METRIC_RTTVAR, var); + } + + if (tcp_in_initial_slowstart(tp)) { + /* Slow start still did not finish. */ + if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) { + val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH); + if (val && (tp->snd_cwnd >> 1) > val) + tcp_metric_set(tm, TCP_METRIC_SSTHRESH, + tp->snd_cwnd >> 1); + } + if (!tcp_metric_locked(tm, TCP_METRIC_CWND)) { + val = tcp_metric_get(tm, TCP_METRIC_CWND); + if (tp->snd_cwnd > val) + tcp_metric_set(tm, TCP_METRIC_CWND, + tp->snd_cwnd); + } + } else if (tp->snd_cwnd > tp->snd_ssthresh && + icsk->icsk_ca_state == TCP_CA_Open) { + /* Cong. avoidance phase, cwnd is reliable. */ + if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) + tcp_metric_set(tm, TCP_METRIC_SSTHRESH, + max(tp->snd_cwnd >> 1, tp->snd_ssthresh)); + if (!tcp_metric_locked(tm, TCP_METRIC_CWND)) { + val = tcp_metric_get(tm, TCP_METRIC_CWND); + tcp_metric_set(tm, TCP_METRIC_CWND, (val + tp->snd_cwnd) >> 1); + } + } else { + /* Else slow start did not finish, cwnd is non-sense, + * ssthresh may be also invalid. + */ + if (!tcp_metric_locked(tm, TCP_METRIC_CWND)) { + val = tcp_metric_get(tm, TCP_METRIC_CWND); + tcp_metric_set(tm, TCP_METRIC_CWND, + (val + tp->snd_ssthresh) >> 1); + } + if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) { + val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH); + if (val && tp->snd_ssthresh > val) + tcp_metric_set(tm, TCP_METRIC_SSTHRESH, + tp->snd_ssthresh); + } + if (!tcp_metric_locked(tm, TCP_METRIC_REORDERING)) { + val = tcp_metric_get(tm, TCP_METRIC_REORDERING); + if (val < tp->reordering && + tp->reordering != sysctl_tcp_reordering) + tcp_metric_set(tm, TCP_METRIC_REORDERING, + tp->reordering); + } + } + tm->tcpm_stamp = jiffies; +out_unlock: + rcu_read_unlock(); +} + +/* Initialize metrics on socket. */ + +void tcp_init_metrics(struct sock *sk) +{ + struct dst_entry *dst = __sk_dst_get(sk); + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_metrics_block *tm; + u32 val; + + if (dst == NULL) + goto reset; + + dst_confirm(dst); + + rcu_read_lock(); + tm = tcp_get_metrics(sk, dst, true); + if (!tm) { + rcu_read_unlock(); + goto reset; + } + + if (tcp_metric_locked(tm, TCP_METRIC_CWND)) + tp->snd_cwnd_clamp = tcp_metric_get(tm, TCP_METRIC_CWND); + + val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH); + if (val) { + tp->snd_ssthresh = val; + if (tp->snd_ssthresh > tp->snd_cwnd_clamp) + tp->snd_ssthresh = tp->snd_cwnd_clamp; + } else { + /* ssthresh may have been reduced unnecessarily during. + * 3WHS. Restore it back to its initial default. + */ + tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; + } + val = tcp_metric_get(tm, TCP_METRIC_REORDERING); + if (val && tp->reordering != val) { + tcp_disable_fack(tp); + tcp_disable_early_retrans(tp); + tp->reordering = val; + } + + val = tcp_metric_get(tm, TCP_METRIC_RTT); + if (val == 0 || tp->srtt == 0) { + rcu_read_unlock(); + goto reset; + } + /* Initial rtt is determined from SYN,SYN-ACK. + * The segment is small and rtt may appear much + * less than real one. Use per-dst memory + * to make it more realistic. + * + * A bit of theory. RTT is time passed after "normal" sized packet + * is sent until it is ACKed. In normal circumstances sending small + * packets force peer to delay ACKs and calculation is correct too. + * The algorithm is adaptive and, provided we follow specs, it + * NEVER underestimate RTT. BUT! If peer tries to make some clever + * tricks sort of "quick acks" for time long enough to decrease RTT + * to low value, and then abruptly stops to do it and starts to delay + * ACKs, wait for troubles. + */ + val = msecs_to_jiffies(val); + if (val > tp->srtt) { + tp->srtt = val; + tp->rtt_seq = tp->snd_nxt; + } + val = tcp_metric_get_jiffies(tm, TCP_METRIC_RTTVAR); + if (val > tp->mdev) { + tp->mdev = val; + tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk)); + } + rcu_read_unlock(); + + tcp_set_rto(sk); +reset: + if (tp->srtt == 0) { + /* RFC6298: 5.7 We've failed to get a valid RTT sample from + * 3WHS. This is most likely due to retransmission, + * including spurious one. Reset the RTO back to 3secs + * from the more aggressive 1sec to avoid more spurious + * retransmission. + */ + tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK; + inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK; + } + /* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been + * retransmitted. In light of RFC6298 more aggressive 1sec + * initRTO, we only reset cwnd when more than 1 SYN/SYN-ACK + * retransmission has occurred. + */ + if (tp->total_retrans > 1) + tp->snd_cwnd = 1; + else + tp->snd_cwnd = tcp_init_cwnd(tp, dst); + tp->snd_cwnd_stamp = tcp_time_stamp; +} + +bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, bool paws_check) +{ + struct tcp_metrics_block *tm; + bool ret; + + if (!dst) + return false; + + rcu_read_lock(); + tm = __tcp_get_metrics_req(req, dst); + if (paws_check) { + if (tm && + (u32)get_seconds() - tm->tcpm_ts_stamp < TCP_PAWS_MSL && + (s32)(tm->tcpm_ts - req->ts_recent) > TCP_PAWS_WINDOW) + ret = false; + else + ret = true; + } else { + if (tm && tcp_metric_get(tm, TCP_METRIC_RTT) && tm->tcpm_ts_stamp) + ret = true; + else + ret = false; + } + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL_GPL(tcp_peer_is_proven); + +void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst) +{ + struct tcp_metrics_block *tm; + + rcu_read_lock(); + tm = tcp_get_metrics(sk, dst, true); + if (tm) { + struct tcp_sock *tp = tcp_sk(sk); + + if ((u32)get_seconds() - tm->tcpm_ts_stamp <= TCP_PAWS_MSL) { + tp->rx_opt.ts_recent_stamp = tm->tcpm_ts_stamp; + tp->rx_opt.ts_recent = tm->tcpm_ts; + } + } + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(tcp_fetch_timewait_stamp); + +/* VJ's idea. Save last timestamp seen from this destination and hold + * it at least for normal timewait interval to use for duplicate + * segment detection in subsequent connections, before they enter + * synchronized state. + */ +bool tcp_remember_stamp(struct sock *sk) +{ + struct dst_entry *dst = __sk_dst_get(sk); + bool ret = false; + + if (dst) { + struct tcp_metrics_block *tm; + + rcu_read_lock(); + tm = tcp_get_metrics(sk, dst, true); + if (tm) { + struct tcp_sock *tp = tcp_sk(sk); + + if ((s32)(tm->tcpm_ts - tp->rx_opt.ts_recent) <= 0 || + ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL && + tm->tcpm_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) { + tm->tcpm_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp; + tm->tcpm_ts = tp->rx_opt.ts_recent; + } + ret = true; + } + rcu_read_unlock(); + } + return ret; +} + +bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw) +{ + struct tcp_metrics_block *tm; + bool ret = false; + + rcu_read_lock(); + tm = __tcp_get_metrics_tw(tw); + if (tm) { + const struct tcp_timewait_sock *tcptw; + struct sock *sk = (struct sock *) tw; + + tcptw = tcp_twsk(sk); + if ((s32)(tm->tcpm_ts - tcptw->tw_ts_recent) <= 0 || + ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL && + tm->tcpm_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) { + tm->tcpm_ts_stamp = (u32)tcptw->tw_ts_recent_stamp; + tm->tcpm_ts = tcptw->tw_ts_recent; + } + ret = true; + } + rcu_read_unlock(); + + return ret; +} + +static DEFINE_SEQLOCK(fastopen_seqlock); + +void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, + struct tcp_fastopen_cookie *cookie, + int *syn_loss, unsigned long *last_syn_loss) +{ + struct tcp_metrics_block *tm; + + rcu_read_lock(); + tm = tcp_get_metrics(sk, __sk_dst_get(sk), false); + if (tm) { + struct tcp_fastopen_metrics *tfom = &tm->tcpm_fastopen; + unsigned int seq; + + do { + seq = read_seqbegin(&fastopen_seqlock); + if (tfom->mss) + *mss = tfom->mss; + *cookie = tfom->cookie; + *syn_loss = tfom->syn_loss; + *last_syn_loss = *syn_loss ? tfom->last_syn_loss : 0; + } while (read_seqretry(&fastopen_seqlock, seq)); + } + rcu_read_unlock(); +} + +void tcp_fastopen_cache_set(struct sock *sk, u16 mss, + struct tcp_fastopen_cookie *cookie, bool syn_lost) +{ + struct tcp_metrics_block *tm; + + rcu_read_lock(); + tm = tcp_get_metrics(sk, __sk_dst_get(sk), true); + if (tm) { + struct tcp_fastopen_metrics *tfom = &tm->tcpm_fastopen; + + write_seqlock_bh(&fastopen_seqlock); + tfom->mss = mss; + if (cookie->len > 0) + tfom->cookie = *cookie; + if (syn_lost) { + ++tfom->syn_loss; + tfom->last_syn_loss = jiffies; + } else + tfom->syn_loss = 0; + write_sequnlock_bh(&fastopen_seqlock); + } + rcu_read_unlock(); +} + +static unsigned int tcpmhash_entries; +static int __init set_tcpmhash_entries(char *str) +{ + ssize_t ret; + + if (!str) + return 0; + + ret = kstrtouint(str, 0, &tcpmhash_entries); + if (ret) + return 0; + + return 1; +} +__setup("tcpmhash_entries=", set_tcpmhash_entries); + +static int __net_init tcp_net_metrics_init(struct net *net) +{ + size_t size; + unsigned int slots; + + slots = tcpmhash_entries; + if (!slots) { + if (totalram_pages >= 128 * 1024) + slots = 16 * 1024; + else + slots = 8 * 1024; + } + + net->ipv4.tcp_metrics_hash_log = order_base_2(slots); + size = sizeof(struct tcpm_hash_bucket) << net->ipv4.tcp_metrics_hash_log; + + net->ipv4.tcp_metrics_hash = kzalloc(size, GFP_KERNEL); + if (!net->ipv4.tcp_metrics_hash) + return -ENOMEM; + + return 0; +} + +static void __net_exit tcp_net_metrics_exit(struct net *net) +{ + unsigned int i; + + for (i = 0; i < (1U << net->ipv4.tcp_metrics_hash_log) ; i++) { + struct tcp_metrics_block *tm, *next; + + tm = rcu_dereference_protected(net->ipv4.tcp_metrics_hash[i].chain, 1); + while (tm) { + next = rcu_dereference_protected(tm->tcpm_next, 1); + kfree(tm); + tm = next; + } + } + kfree(net->ipv4.tcp_metrics_hash); +} + +static __net_initdata struct pernet_operations tcp_net_metrics_ops = { + .init = tcp_net_metrics_init, + .exit = tcp_net_metrics_exit, +}; + +void __init tcp_metrics_init(void) +{ + register_pernet_subsys(&tcp_net_metrics_ops); +} diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index b85d9fe7d66..6ff7f10dce9 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -49,56 +49,6 @@ struct inet_timewait_death_row tcp_death_row = { }; EXPORT_SYMBOL_GPL(tcp_death_row); -/* VJ's idea. Save last timestamp seen from this destination - * and hold it at least for normal timewait interval to use for duplicate - * segment detection in subsequent connections, before they enter synchronized - * state. - */ - -static bool tcp_remember_stamp(struct sock *sk) -{ - const struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - struct inet_peer *peer; - bool release_it; - - peer = icsk->icsk_af_ops->get_peer(sk, &release_it); - if (peer) { - if ((s32)(peer->tcp_ts - tp->rx_opt.ts_recent) <= 0 || - ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL && - peer->tcp_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) { - peer->tcp_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp; - peer->tcp_ts = tp->rx_opt.ts_recent; - } - if (release_it) - inet_putpeer(peer); - return true; - } - - return false; -} - -static bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw) -{ - struct sock *sk = (struct sock *) tw; - struct inet_peer *peer; - - peer = twsk_getpeer(sk); - if (peer) { - const struct tcp_timewait_sock *tcptw = tcp_twsk(sk); - - if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 || - ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL && - peer->tcp_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) { - peer->tcp_ts_stamp = (u32)tcptw->tw_ts_recent_stamp; - peer->tcp_ts = tcptw->tw_ts_recent; - } - inet_putpeer(peer); - return true; - } - return false; -} - static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win) { if (seq == s_win) @@ -147,7 +97,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { - tcp_parse_options(skb, &tmp_opt, &hash_location, 0); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = tcptw->tw_ts_recent; @@ -327,8 +277,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) if (tw != NULL) { struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); + struct inet_sock *inet = inet_sk(sk); - tw->tw_transparent = inet_sk(sk)->transparent; + tw->tw_transparent = inet->transparent; tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; tcptw->tw_rcv_nxt = tp->rcv_nxt; tcptw->tw_snd_nxt = tp->snd_nxt; @@ -403,6 +354,7 @@ void tcp_twsk_destructor(struct sock *sk) { #ifdef CONFIG_TCP_MD5SIG struct tcp_timewait_sock *twsk = tcp_twsk(sk); + if (twsk->tw_md5_key) { tcp_free_md5sig_pool(); kfree_rcu(twsk->tw_md5_key, rcu); @@ -470,6 +422,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, treq->snt_isn + 1 + tcp_s_data_size(oldtp); tcp_prequeue_init(newtp); + INIT_LIST_HEAD(&newtp->tsq_node); tcp_init_wl(newtp, treq->rcv_isn); @@ -579,7 +532,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(struct tcphdr)>>2)) { - tcp_parse_options(skb, &tmp_opt, &hash_location, 0); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = req->ts_recent; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 803cbfe82fb..d04632673a9 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -50,6 +50,9 @@ int sysctl_tcp_retrans_collapse __read_mostly = 1; */ int sysctl_tcp_workaround_signed_windows __read_mostly = 0; +/* Default TSQ limit of two TSO segments */ +int sysctl_tcp_limit_output_bytes __read_mostly = 131072; + /* This limits the percentage of the congestion window which we * will allow a single TSO frame to consume. Building TSO frames * which are too large can cause TCP streams to be bursty. @@ -65,6 +68,8 @@ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; int sysctl_tcp_cookie_size __read_mostly = 0; /* TCP_COOKIE_MAX */ EXPORT_SYMBOL_GPL(sysctl_tcp_cookie_size); +static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, + int push_one, gfp_t gfp); /* Account for new data that has been sent to the network. */ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) @@ -380,15 +385,17 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp) #define OPTION_MD5 (1 << 2) #define OPTION_WSCALE (1 << 3) #define OPTION_COOKIE_EXTENSION (1 << 4) +#define OPTION_FAST_OPEN_COOKIE (1 << 8) struct tcp_out_options { - u8 options; /* bit field of OPTION_* */ + u16 options; /* bit field of OPTION_* */ + u16 mss; /* 0 to disable */ u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ u8 hash_size; /* bytes in hash_location */ - u16 mss; /* 0 to disable */ - __u32 tsval, tsecr; /* need to include OPTION_TS */ __u8 *hash_location; /* temporary pointer, overloaded */ + __u32 tsval, tsecr; /* need to include OPTION_TS */ + struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */ }; /* The sysctl int routines are generic, so check consistency here. @@ -437,7 +444,7 @@ static u8 tcp_cookie_size_check(u8 desired) static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, struct tcp_out_options *opts) { - u8 options = opts->options; /* mungable copy */ + u16 options = opts->options; /* mungable copy */ /* Having both authentication and cookies for security is redundant, * and there's certainly not enough room. Instead, the cookie-less @@ -559,6 +566,21 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, tp->rx_opt.dsack = 0; } + + if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) { + struct tcp_fastopen_cookie *foc = opts->fastopen_cookie; + + *ptr++ = htonl((TCPOPT_EXP << 24) | + ((TCPOLEN_EXP_FASTOPEN_BASE + foc->len) << 16) | + TCPOPT_FASTOPEN_MAGIC); + + memcpy(ptr, foc->val, foc->len); + if ((foc->len & 3) == 2) { + u8 *align = ((u8 *)ptr) + foc->len; + align[0] = align[1] = TCPOPT_NOP; + } + ptr += (foc->len + 3) >> 2; + } } /* Compute TCP options for SYN packets. This is not the final @@ -574,6 +596,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ? tcp_cookie_size_check(cvp->cookie_desired) : 0; + struct tcp_fastopen_request *fastopen = tp->fastopen_req; #ifdef CONFIG_TCP_MD5SIG *md5 = tp->af_specific->md5_lookup(sk, sk); @@ -614,6 +637,16 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, remaining -= TCPOLEN_SACKPERM_ALIGNED; } + if (fastopen && fastopen->cookie.len >= 0) { + u32 need = TCPOLEN_EXP_FASTOPEN_BASE + fastopen->cookie.len; + need = (need + 3) & ~3U; /* Align to 32 bits */ + if (remaining >= need) { + opts->options |= OPTION_FAST_OPEN_COOKIE; + opts->fastopen_cookie = &fastopen->cookie; + remaining -= need; + tp->syn_fastopen = 1; + } + } /* Note that timestamps are required by the specification. * * Odd numbers of bytes are prohibited by the specification, ensuring @@ -783,6 +816,160 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb return size; } + +/* TCP SMALL QUEUES (TSQ) + * + * TSQ goal is to keep small amount of skbs per tcp flow in tx queues (qdisc+dev) + * to reduce RTT and bufferbloat. + * We do this using a special skb destructor (tcp_wfree). + * + * Its important tcp_wfree() can be replaced by sock_wfree() in the event skb + * needs to be reallocated in a driver. + * The invariant being skb->truesize substracted from sk->sk_wmem_alloc + * + * Since transmit from skb destructor is forbidden, we use a tasklet + * to process all sockets that eventually need to send more skbs. + * We use one tasklet per cpu, with its own queue of sockets. + */ +struct tsq_tasklet { + struct tasklet_struct tasklet; + struct list_head head; /* queue of tcp sockets */ +}; +static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); + +static void tcp_tsq_handler(struct sock *sk) +{ + if ((1 << sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING | + TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) + tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC); +} +/* + * One tasklest per cpu tries to send more skbs. + * We run in tasklet context but need to disable irqs when + * transfering tsq->head because tcp_wfree() might + * interrupt us (non NAPI drivers) + */ +static void tcp_tasklet_func(unsigned long data) +{ + struct tsq_tasklet *tsq = (struct tsq_tasklet *)data; + LIST_HEAD(list); + unsigned long flags; + struct list_head *q, *n; + struct tcp_sock *tp; + struct sock *sk; + + local_irq_save(flags); + list_splice_init(&tsq->head, &list); + local_irq_restore(flags); + + list_for_each_safe(q, n, &list) { + tp = list_entry(q, struct tcp_sock, tsq_node); + list_del(&tp->tsq_node); + + sk = (struct sock *)tp; + bh_lock_sock(sk); + + if (!sock_owned_by_user(sk)) { + tcp_tsq_handler(sk); + } else { + /* defer the work to tcp_release_cb() */ + set_bit(TCP_TSQ_DEFERRED, &tp->tsq_flags); + } + bh_unlock_sock(sk); + + clear_bit(TSQ_QUEUED, &tp->tsq_flags); + sk_free(sk); + } +} + +#define TCP_DEFERRED_ALL ((1UL << TCP_TSQ_DEFERRED) | \ + (1UL << TCP_WRITE_TIMER_DEFERRED) | \ + (1UL << TCP_DELACK_TIMER_DEFERRED) | \ + (1UL << TCP_MTU_REDUCED_DEFERRED)) +/** + * tcp_release_cb - tcp release_sock() callback + * @sk: socket + * + * called from release_sock() to perform protocol dependent + * actions before socket release. + */ +void tcp_release_cb(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + unsigned long flags, nflags; + + /* perform an atomic operation only if at least one flag is set */ + do { + flags = tp->tsq_flags; + if (!(flags & TCP_DEFERRED_ALL)) + return; + nflags = flags & ~TCP_DEFERRED_ALL; + } while (cmpxchg(&tp->tsq_flags, flags, nflags) != flags); + + if (flags & (1UL << TCP_TSQ_DEFERRED)) + tcp_tsq_handler(sk); + + if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) { + tcp_write_timer_handler(sk); + __sock_put(sk); + } + if (flags & (1UL << TCP_DELACK_TIMER_DEFERRED)) { + tcp_delack_timer_handler(sk); + __sock_put(sk); + } + if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) { + sk->sk_prot->mtu_reduced(sk); + __sock_put(sk); + } +} +EXPORT_SYMBOL(tcp_release_cb); + +void __init tcp_tasklet_init(void) +{ + int i; + + for_each_possible_cpu(i) { + struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i); + + INIT_LIST_HEAD(&tsq->head); + tasklet_init(&tsq->tasklet, + tcp_tasklet_func, + (unsigned long)tsq); + } +} + +/* + * Write buffer destructor automatically called from kfree_skb. + * We cant xmit new skbs from this context, as we might already + * hold qdisc lock. + */ +static void tcp_wfree(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + struct tcp_sock *tp = tcp_sk(sk); + + if (test_and_clear_bit(TSQ_THROTTLED, &tp->tsq_flags) && + !test_and_set_bit(TSQ_QUEUED, &tp->tsq_flags)) { + unsigned long flags; + struct tsq_tasklet *tsq; + + /* Keep a ref on socket. + * This last ref will be released in tcp_tasklet_func() + */ + atomic_sub(skb->truesize - 1, &sk->sk_wmem_alloc); + + /* queue this socket to tasklet queue */ + local_irq_save(flags); + tsq = &__get_cpu_var(tsq_tasklet); + list_add(&tp->tsq_node, &tsq->head); + tasklet_schedule(&tsq->tasklet); + local_irq_restore(flags); + } else { + sock_wfree(skb); + } +} + /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. @@ -844,7 +1031,12 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); - skb_set_owner_w(skb, sk); + + skb_orphan(skb); + skb->sk = sk; + skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ? + tcp_wfree : sock_wfree; + atomic_add(skb->truesize, &sk->sk_wmem_alloc); /* Build TCP header and checksum it. */ th = tcp_hdr(skb); @@ -1334,21 +1526,21 @@ static void tcp_cwnd_validate(struct sock *sk) * when we would be allowed to send the split-due-to-Nagle skb fully. */ static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_buff *skb, - unsigned int mss_now, unsigned int cwnd) + unsigned int mss_now, unsigned int max_segs) { const struct tcp_sock *tp = tcp_sk(sk); - u32 needed, window, cwnd_len; + u32 needed, window, max_len; window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; - cwnd_len = mss_now * cwnd; + max_len = mss_now * max_segs; - if (likely(cwnd_len <= window && skb != tcp_write_queue_tail(sk))) - return cwnd_len; + if (likely(max_len <= window && skb != tcp_write_queue_tail(sk))) + return max_len; needed = min(skb->len, window); - if (cwnd_len <= needed) - return cwnd_len; + if (max_len <= needed) + return max_len; return needed - needed % mss_now; } @@ -1577,7 +1769,8 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) limit = min(send_win, cong_win); /* If a full-sized TSO skb can be sent, do it. */ - if (limit >= sk->sk_gso_max_size) + if (limit >= min_t(unsigned int, sk->sk_gso_max_size, + sk->sk_gso_max_segs * tp->mss_cache)) goto send_now; /* Middle in queue won't get any more data, full sendable already? */ @@ -1780,6 +1973,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, while ((skb = tcp_send_head(sk))) { unsigned int limit; + tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); @@ -1800,10 +1994,19 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, break; } + /* TSQ : sk_wmem_alloc accounts skb truesize, + * including skb overhead. But thats OK. + */ + if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) { + set_bit(TSQ_THROTTLED, &tp->tsq_flags); + break; + } limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, - cwnd_quota); + min_t(unsigned int, + cwnd_quota, + sk->sk_gso_max_segs)); if (skb->len > limit && unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) @@ -1849,7 +2052,8 @@ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, if (unlikely(sk->sk_state == TCP_CLOSE)) return; - if (tcp_write_xmit(sk, cur_mss, nonagle, 0, GFP_ATOMIC)) + if (tcp_write_xmit(sk, cur_mss, nonagle, 0, + sk_gfp_atomic(sk, GFP_ATOMIC))) tcp_check_probe_timer(sk); } @@ -2442,7 +2646,16 @@ int tcp_send_synack(struct sock *sk) return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } -/* Prepare a SYN-ACK. */ +/** + * tcp_make_synack - Prepare a SYN-ACK. + * sk: listener socket + * dst: dst entry attached to the SYNACK + * req: request_sock pointer + * rvp: request_values pointer + * + * Allocate one skb and build a SYNACK packet. + * @dst is consumed : Caller should not use it again. + */ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct request_values *rvp) @@ -2461,14 +2674,16 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, if (cvp != NULL && cvp->s_data_constant && cvp->s_data_desired) s_data_desired = cvp->s_data_desired; - skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15 + s_data_desired, 1, GFP_ATOMIC); - if (skb == NULL) + skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired, + sk_gfp_atomic(sk, GFP_ATOMIC)); + if (unlikely(!skb)) { + dst_release(dst); return NULL; - + } /* Reserve space for headers. */ skb_reserve(skb, MAX_TCP_HEADER); - skb_dst_set(skb, dst_clone(dst)); + skb_dst_set(skb, dst); mss = dst_metric_advmss(dst); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) @@ -2645,6 +2860,109 @@ void tcp_connect_init(struct sock *sk) tcp_clear_retrans(tp); } +static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); + + tcb->end_seq += skb->len; + skb_header_release(skb); + __tcp_add_write_queue_tail(sk, skb); + sk->sk_wmem_queued += skb->truesize; + sk_mem_charge(sk, skb->truesize); + tp->write_seq = tcb->end_seq; + tp->packets_out += tcp_skb_pcount(skb); +} + +/* Build and send a SYN with data and (cached) Fast Open cookie. However, + * queue a data-only packet after the regular SYN, such that regular SYNs + * are retransmitted on timeouts. Also if the remote SYN-ACK acknowledges + * only the SYN sequence, the data are retransmitted in the first ACK. + * If cookie is not cached or other error occurs, falls back to send a + * regular SYN with Fast Open cookie request option. + */ +static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_fastopen_request *fo = tp->fastopen_req; + int syn_loss = 0, space, i, err = 0, iovlen = fo->data->msg_iovlen; + struct sk_buff *syn_data = NULL, *data; + unsigned long last_syn_loss = 0; + + tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */ + tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie, + &syn_loss, &last_syn_loss); + /* Recurring FO SYN losses: revert to regular handshake temporarily */ + if (syn_loss > 1 && + time_before(jiffies, last_syn_loss + (60*HZ << syn_loss))) { + fo->cookie.len = -1; + goto fallback; + } + + if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) + fo->cookie.len = -1; + else if (fo->cookie.len <= 0) + goto fallback; + + /* MSS for SYN-data is based on cached MSS and bounded by PMTU and + * user-MSS. Reserve maximum option space for middleboxes that add + * private TCP options. The cost is reduced data space in SYN :( + */ + if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->rx_opt.mss_clamp) + tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; + space = tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - + MAX_TCP_OPTION_SPACE; + + syn_data = skb_copy_expand(syn, skb_headroom(syn), space, + sk->sk_allocation); + if (syn_data == NULL) + goto fallback; + + for (i = 0; i < iovlen && syn_data->len < space; ++i) { + struct iovec *iov = &fo->data->msg_iov[i]; + unsigned char __user *from = iov->iov_base; + int len = iov->iov_len; + + if (syn_data->len + len > space) + len = space - syn_data->len; + else if (i + 1 == iovlen) + /* No more data pending in inet_wait_for_connect() */ + fo->data = NULL; + + if (skb_add_data(syn_data, from, len)) + goto fallback; + } + + /* Queue a data-only packet after the regular SYN for retransmission */ + data = pskb_copy(syn_data, sk->sk_allocation); + if (data == NULL) + goto fallback; + TCP_SKB_CB(data)->seq++; + TCP_SKB_CB(data)->tcp_flags &= ~TCPHDR_SYN; + TCP_SKB_CB(data)->tcp_flags = (TCPHDR_ACK|TCPHDR_PSH); + tcp_connect_queue_skb(sk, data); + fo->copied = data->len; + + if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) { + tp->syn_data = (fo->copied > 0); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); + goto done; + } + syn_data = NULL; + +fallback: + /* Send a regular SYN with Fast Open cookie request option */ + if (fo->cookie.len > 0) + fo->cookie.len = 0; + err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation); + if (err) + tp->syn_fastopen = 0; + kfree_skb(syn_data); +done: + fo->cookie.len = -1; /* Exclude Fast Open option for SYN retries */ + return err; +} + /* Build a SYN and send it off. */ int tcp_connect(struct sock *sk) { @@ -2662,17 +2980,13 @@ int tcp_connect(struct sock *sk) skb_reserve(buff, MAX_TCP_HEADER); tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); + tp->retrans_stamp = TCP_SKB_CB(buff)->when = tcp_time_stamp; + tcp_connect_queue_skb(sk, buff); TCP_ECN_send_syn(sk, buff); - /* Send it off. */ - TCP_SKB_CB(buff)->when = tcp_time_stamp; - tp->retrans_stamp = TCP_SKB_CB(buff)->when; - skb_header_release(buff); - __tcp_add_write_queue_tail(sk, buff); - sk->sk_wmem_queued += buff->truesize; - sk_mem_charge(sk, buff->truesize); - tp->packets_out += tcp_skb_pcount(buff); - err = tcp_transmit_skb(sk, buff, 1, sk->sk_allocation); + /* Send off SYN; include data in Fast Open. */ + err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) : + tcp_transmit_skb(sk, buff, 1, sk->sk_allocation); if (err == -ECONNREFUSED) return err; @@ -2759,7 +3073,7 @@ void tcp_send_ack(struct sock *sk) * tcp_transmit_skb() will set the ownership to this * sock. */ - buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); + buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); if (buff == NULL) { inet_csk_schedule_ack(sk); inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN; @@ -2774,7 +3088,7 @@ void tcp_send_ack(struct sock *sk) /* Send it off, this clears delayed acks for us. */ TCP_SKB_CB(buff)->when = tcp_time_stamp; - tcp_transmit_skb(sk, buff, 0, GFP_ATOMIC); + tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC)); } /* This routine sends a packet with an out of date sequence @@ -2794,7 +3108,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) struct sk_buff *skb; /* We don't queue it, tcp_transmit_skb() sets ownership. */ - skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); + skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); if (skb == NULL) return -1; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index e911e6c523e..b774a03bd1d 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -32,17 +32,6 @@ int sysctl_tcp_retries2 __read_mostly = TCP_RETR2; int sysctl_tcp_orphan_retries __read_mostly; int sysctl_tcp_thin_linear_timeouts __read_mostly; -static void tcp_write_timer(unsigned long); -static void tcp_delack_timer(unsigned long); -static void tcp_keepalive_timer (unsigned long data); - -void tcp_init_xmit_timers(struct sock *sk) -{ - inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, - &tcp_keepalive_timer); -} -EXPORT_SYMBOL(tcp_init_xmit_timers); - static void tcp_write_err(struct sock *sk) { sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; @@ -205,21 +194,11 @@ static int tcp_write_timeout(struct sock *sk) return 0; } -static void tcp_delack_timer(unsigned long data) +void tcp_delack_timer_handler(struct sock *sk) { - struct sock *sk = (struct sock *)data; struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); - bh_lock_sock(sk); - if (sock_owned_by_user(sk)) { - /* Try again later. */ - icsk->icsk_ack.blocked = 1; - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); - sk_reset_timer(sk, &icsk->icsk_delack_timer, jiffies + TCP_DELACK_MIN); - goto out_unlock; - } - sk_mem_reclaim_partial(sk); if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) @@ -260,7 +239,22 @@ static void tcp_delack_timer(unsigned long data) out: if (sk_under_memory_pressure(sk)) sk_mem_reclaim(sk); -out_unlock: +} + +static void tcp_delack_timer(unsigned long data) +{ + struct sock *sk = (struct sock *)data; + + bh_lock_sock(sk); + if (!sock_owned_by_user(sk)) { + tcp_delack_timer_handler(sk); + } else { + inet_csk(sk)->icsk_ack.blocked = 1; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); + /* deleguate our work to tcp_release_cb() */ + if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags)) + sock_hold(sk); + } bh_unlock_sock(sk); sock_put(sk); } @@ -450,19 +444,11 @@ out_reset_timer: out:; } -static void tcp_write_timer(unsigned long data) +void tcp_write_timer_handler(struct sock *sk) { - struct sock *sk = (struct sock *)data; struct inet_connection_sock *icsk = inet_csk(sk); int event; - bh_lock_sock(sk); - if (sock_owned_by_user(sk)) { - /* Try again later */ - sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + (HZ / 20)); - goto out_unlock; - } - if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending) goto out; @@ -485,7 +471,20 @@ static void tcp_write_timer(unsigned long data) out: sk_mem_reclaim(sk); -out_unlock: +} + +static void tcp_write_timer(unsigned long data) +{ + struct sock *sk = (struct sock *)data; + + bh_lock_sock(sk); + if (!sock_owned_by_user(sk)) { + tcp_write_timer_handler(sk); + } else { + /* deleguate our work to tcp_release_cb() */ + if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags)) + sock_hold(sk); + } bh_unlock_sock(sk); sock_put(sk); } @@ -602,3 +601,10 @@ out: bh_unlock_sock(sk); sock_put(sk); } + +void tcp_init_xmit_timers(struct sock *sk) +{ + inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, + &tcp_keepalive_timer); +} +EXPORT_SYMBOL(tcp_init_xmit_timers); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index eaca73644e7..6f6d1aca3c3 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -108,6 +108,7 @@ #include <net/xfrm.h> #include <trace/events/udp.h> #include <linux/static_key.h> +#include <trace/events/skb.h> #include "udp_impl.h" struct udp_table udp_table __read_mostly; @@ -615,6 +616,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) break; case ICMP_DEST_UNREACH: if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */ + ipv4_sk_update_pmtu(skb, sk, info); if (inet->pmtudisc != IP_PMTUDISC_DONT) { err = EMSGSIZE; harderr = 1; @@ -628,6 +630,9 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) err = icmp_err_convert[code].errno; } break; + case ICMP_REDIRECT: + ipv4_sk_redirect(skb, sk); + break; } /* @@ -753,7 +758,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) uh->check = CSUM_MANGLED_0; send: - err = ip_send_skb(skb); + err = ip_send_skb(sock_net(sk), skb); if (err) { if (err == -ENOBUFS && !inet->recverr) { UDP_INC_STATS_USER(sock_net(sk), @@ -1219,8 +1224,10 @@ try_again: goto csum_copy_err; } - if (err) + if (unlikely(err)) { + trace_kfree_skb(skb, udp_recvmsg); goto out_free; + } if (!peeked) UDP_INC_STATS_USER(sock_net(sk), diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index a7f86a3cd50..16d0960062b 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -34,15 +34,16 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, int err = -EINVAL; struct sock *sk; struct sk_buff *rep; + struct net *net = sock_net(in_skb->sk); if (req->sdiag_family == AF_INET) - sk = __udp4_lib_lookup(&init_net, + sk = __udp4_lib_lookup(net, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_if, tbl); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) - sk = __udp6_lib_lookup(&init_net, + sk = __udp6_lib_lookup(net, (struct in6_addr *)req->id.idiag_src, req->id.idiag_sport, (struct in6_addr *)req->id.idiag_dst, @@ -75,7 +76,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, kfree_skb(rep); goto out; } - err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid, + err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); if (err > 0) err = 0; @@ -90,6 +91,7 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlin struct inet_diag_req_v2 *r, struct nlattr *bc) { int num, s_num, slot, s_slot; + struct net *net = sock_net(skb->sk); s_slot = cb->args[0]; num = s_num = cb->args[1]; @@ -106,6 +108,8 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlin sk_nulls_for_each(sk, node, &hslot->head) { struct inet_sock *inet = inet_sk(sk); + if (!net_eq(sock_net(sk), net)) + continue; if (num < s_num) goto next; if (!(r->idiag_states & (1 << sk->sk_state))) diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index ed4bf11ef9f..ddee0a099a2 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -15,6 +15,65 @@ #include <net/ip.h> #include <net/xfrm.h> +/* Informational hook. The decap is still done here. */ +static struct xfrm_tunnel __rcu *rcv_notify_handlers __read_mostly; +static DEFINE_MUTEX(xfrm4_mode_tunnel_input_mutex); + +int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel *handler) +{ + struct xfrm_tunnel __rcu **pprev; + struct xfrm_tunnel *t; + int ret = -EEXIST; + int priority = handler->priority; + + mutex_lock(&xfrm4_mode_tunnel_input_mutex); + + for (pprev = &rcv_notify_handlers; + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm4_mode_tunnel_input_mutex))) != NULL; + pprev = &t->next) { + if (t->priority > priority) + break; + if (t->priority == priority) + goto err; + + } + + handler->next = *pprev; + rcu_assign_pointer(*pprev, handler); + + ret = 0; + +err: + mutex_unlock(&xfrm4_mode_tunnel_input_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_register); + +int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel *handler) +{ + struct xfrm_tunnel __rcu **pprev; + struct xfrm_tunnel *t; + int ret = -ENOENT; + + mutex_lock(&xfrm4_mode_tunnel_input_mutex); + for (pprev = &rcv_notify_handlers; + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm4_mode_tunnel_input_mutex))) != NULL; + pprev = &t->next) { + if (t == handler) { + *pprev = handler->next; + ret = 0; + break; + } + } + mutex_unlock(&xfrm4_mode_tunnel_input_mutex); + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_deregister); + static inline void ipip_ecn_decapsulate(struct sk_buff *skb) { struct iphdr *inner_iph = ipip_hdr(skb); @@ -64,8 +123,14 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) return 0; } +#define for_each_input_rcu(head, handler) \ + for (handler = rcu_dereference(head); \ + handler != NULL; \ + handler = rcu_dereference(handler->next)) + static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { + struct xfrm_tunnel *handler; int err = -EINVAL; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP) @@ -74,6 +139,9 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out; + for_each_input_rcu(rcv_notify_handlers, handler) + handler->handler(skb); + if (skb_cloned(skb) && (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) goto out; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 0d3426cb5c4..681ea2f413e 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -79,30 +79,20 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, struct rtable *rt = (struct rtable *)xdst->route; const struct flowi4 *fl4 = &fl->u.ip4; - xdst->u.rt.rt_key_dst = fl4->daddr; - xdst->u.rt.rt_key_src = fl4->saddr; - xdst->u.rt.rt_key_tos = fl4->flowi4_tos; - xdst->u.rt.rt_route_iif = fl4->flowi4_iif; xdst->u.rt.rt_iif = fl4->flowi4_iif; - xdst->u.rt.rt_oif = fl4->flowi4_oif; - xdst->u.rt.rt_mark = fl4->flowi4_mark; xdst->u.dst.dev = dev; dev_hold(dev); - xdst->u.rt.peer = rt->peer; - if (rt->peer) - atomic_inc(&rt->peer->refcnt); - /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ + xdst->u.rt.rt_is_input = rt->rt_is_input; xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL); xdst->u.rt.rt_type = rt->rt_type; - xdst->u.rt.rt_src = rt->rt_src; - xdst->u.rt.rt_dst = rt->rt_dst; xdst->u.rt.rt_gateway = rt->rt_gateway; - xdst->u.rt.rt_spec_dst = rt->rt_spec_dst; + xdst->u.rt.rt_pmtu = rt->rt_pmtu; + INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); return 0; } @@ -198,12 +188,22 @@ static inline int xfrm4_garbage_collect(struct dst_ops *ops) return (dst_entries_get_slow(ops) > ops->gc_thresh * 2); } -static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu) +static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) +{ + struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + struct dst_entry *path = xdst->route; + + path->ops->update_pmtu(path, sk, skb, mtu); +} + +static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, mtu); + path->ops->redirect(path, sk, skb); } static void xfrm4_dst_destroy(struct dst_entry *dst) @@ -212,9 +212,6 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) dst_destroy_metrics_generic(dst); - if (likely(xdst->u.rt.peer)) - inet_putpeer(xdst->u.rt.peer); - xfrm_dst_destroy(xdst); } @@ -232,6 +229,7 @@ static struct dst_ops xfrm4_dst_ops = { .protocol = cpu_to_be16(ETH_P_IP), .gc = xfrm4_garbage_collect, .update_pmtu = xfrm4_update_pmtu, + .redirect = xfrm4_redirect, .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm4_dst_destroy, .ifdown = xfrm4_dst_ifdown, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 8f6411c9718..6bc85f7c31e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -63,6 +63,7 @@ #include <linux/delay.h> #include <linux/notifier.h> #include <linux/string.h> +#include <linux/hash.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -493,8 +494,7 @@ static void addrconf_forward_change(struct net *net, __s32 newf) struct net_device *dev; struct inet6_dev *idev; - rcu_read_lock(); - for_each_netdev_rcu(net, dev) { + for_each_netdev(net, dev) { idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.forwarding) ^ (!newf); @@ -503,7 +503,6 @@ static void addrconf_forward_change(struct net *net, __s32 newf) dev_forward_change(idev); } } - rcu_read_unlock(); } static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) @@ -579,15 +578,9 @@ ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) list_add_tail(&ifp->if_list, p); } -static u32 ipv6_addr_hash(const struct in6_addr *addr) +static u32 inet6_addr_hash(const struct in6_addr *addr) { - /* - * We perform the hash function over the last 64 bits of the address - * This will include the IEEE address token on links that support it. - */ - return jhash_2words((__force u32)addr->s6_addr32[2], - (__force u32)addr->s6_addr32[3], 0) - & (IN6_ADDR_HSIZE - 1); + return hash_32(ipv6_addr_hash(addr), IN6_ADDR_HSIZE_SHIFT); } /* On success it returns ifp with increased reference count */ @@ -662,7 +655,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, in6_ifa_hold(ifa); /* Add to big hash table */ - hash = ipv6_addr_hash(addr); + hash = inet6_addr_hash(addr); hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]); spin_unlock(&addrconf_hash_lock); @@ -1270,7 +1263,7 @@ int ipv6_chk_addr(struct net *net, const struct in6_addr *addr, { struct inet6_ifaddr *ifp; struct hlist_node *node; - unsigned int hash = ipv6_addr_hash(addr); + unsigned int hash = inet6_addr_hash(addr); rcu_read_lock_bh(); hlist_for_each_entry_rcu(ifp, node, &inet6_addr_lst[hash], addr_lst) { @@ -1293,7 +1286,7 @@ EXPORT_SYMBOL(ipv6_chk_addr); static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, struct net_device *dev) { - unsigned int hash = ipv6_addr_hash(addr); + unsigned int hash = inet6_addr_hash(addr); struct inet6_ifaddr *ifp; struct hlist_node *node; @@ -1336,7 +1329,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add struct net_device *dev, int strict) { struct inet6_ifaddr *ifp, *result = NULL; - unsigned int hash = ipv6_addr_hash(addr); + unsigned int hash = inet6_addr_hash(addr); struct hlist_node *node; rcu_read_lock_bh(); @@ -3223,7 +3216,7 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) int ret = 0; struct inet6_ifaddr *ifp = NULL; struct hlist_node *n; - unsigned int hash = ipv6_addr_hash(addr); + unsigned int hash = inet6_addr_hash(addr); rcu_read_lock_bh(); hlist_for_each_entry_rcu_bh(ifp, n, &inet6_addr_lst[hash], addr_lst) { diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index f1a4a2c28ed..7e6139508ee 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -35,6 +35,7 @@ #include <linux/pfkeyv2.h> #include <linux/string.h> #include <linux/scatterlist.h> +#include <net/ip6_route.h> #include <net/icmp.h> #include <net/ipv6.h> #include <net/protocol.h> @@ -612,16 +613,18 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct xfrm_state *x; if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG) + type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) return; x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6); if (!x) return; - NETDEBUG(KERN_DEBUG "pmtu discovery on SA AH/%08x/%pI6\n", - ntohl(ah->spi), &iph->daddr); - + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, 0, 0); + else + ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index db1521fcda5..282f3723ee1 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -39,6 +39,7 @@ #include <linux/random.h> #include <linux/slab.h> #include <linux/spinlock.h> +#include <net/ip6_route.h> #include <net/icmp.h> #include <net/ipv6.h> #include <net/protocol.h> @@ -166,8 +167,6 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) struct esp_data *esp = x->data; /* skb is pure payload to encrypt */ - err = -ENOMEM; - aead = esp->aead; alen = crypto_aead_authsize(aead); @@ -202,8 +201,10 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) } tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen); - if (!tmp) + if (!tmp) { + err = -ENOMEM; goto error; + } seqhi = esp_tmp_seqhi(tmp); iv = esp_tmp_iv(aead, tmp, seqhilen); @@ -433,15 +434,19 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct xfrm_state *x; if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG) + type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) return; x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6); if (!x) return; - pr_debug("pmtu discovery on SA ESP/%08x/%pI6\n", - ntohl(esph->spi), &iph->daddr); + + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, 0, 0); + else + ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 6447dc49429..fa3d9c32809 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -791,14 +791,14 @@ static int ipv6_renew_option(void *ohdr, if (ohdr) { memcpy(*p, ohdr, ipv6_optlen((struct ipv6_opt_hdr *)ohdr)); *hdr = (struct ipv6_opt_hdr *)*p; - *p += CMSG_ALIGN(ipv6_optlen(*(struct ipv6_opt_hdr **)hdr)); + *p += CMSG_ALIGN(ipv6_optlen(*hdr)); } } else { if (newopt) { if (copy_from_user(*p, newopt, newoptlen)) return -EFAULT; *hdr = (struct ipv6_opt_hdr *)*p; - if (ipv6_optlen(*(struct ipv6_opt_hdr **)hdr) > newoptlen) + if (ipv6_optlen(*hdr) > newoptlen) return -EINVAL; *p += CMSG_ALIGN(newoptlen); } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 091a2971c7b..24d69dbca4d 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -188,14 +188,16 @@ static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type, } else { struct rt6_info *rt = (struct rt6_info *)dst; int tmo = net->ipv6.sysctl.icmpv6_time; + struct inet_peer *peer; /* Give more bandwidth to wider prefixes. */ if (rt->rt6i_dst.plen < 128) tmo >>= ((128 - rt->rt6i_dst.plen)>>5); - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); - res = inet_peer_xrlim_allow(rt->rt6i_peer, tmo); + peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + res = inet_peer_xrlim_allow(peer, tmo); + if (peer) + inet_putpeer(peer); } dst_release(dst); return res; @@ -596,13 +598,12 @@ out: icmpv6_xmit_unlock(sk); } -static void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) +void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) { const struct inet6_protocol *ipprot; int inner_offset; - int hash; - u8 nexthdr; __be16 frag_off; + u8 nexthdr; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) return; @@ -629,10 +630,8 @@ static void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) --ANK (980726) */ - hash = nexthdr & (MAX_INET_PROTOS - 1); - rcu_read_lock(); - ipprot = rcu_dereference(inet6_protos[hash]); + ipprot = rcu_dereference(inet6_protos[nexthdr]); if (ipprot && ipprot->err_handler) ipprot->err_handler(skb, NULL, type, code, inner_offset, info); rcu_read_unlock(); @@ -649,7 +648,6 @@ static int icmpv6_rcv(struct sk_buff *skb) struct net_device *dev = skb->dev; struct inet6_dev *idev = __in6_dev_get(dev); const struct in6_addr *saddr, *daddr; - const struct ipv6hdr *orig_hdr; struct icmp6hdr *hdr; u8 type; @@ -661,7 +659,7 @@ static int icmpv6_rcv(struct sk_buff *skb) XFRM_STATE_ICMP)) goto drop_no_count; - if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(*orig_hdr))) + if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr))) goto drop_no_count; nh = skb_network_offset(skb); @@ -722,9 +720,6 @@ static int icmpv6_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto discard_it; hdr = icmp6_hdr(skb); - orig_hdr = (struct ipv6hdr *) (hdr + 1); - rt6_pmtu_discovery(&orig_hdr->daddr, &orig_hdr->saddr, dev, - ntohl(hdr->icmp6_mtu)); /* * Drop through to notify diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index e6cee5292a0..0251a6005be 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -55,26 +55,26 @@ int inet6_csk_bind_conflict(const struct sock *sk, EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict); struct dst_entry *inet6_csk_route_req(struct sock *sk, + struct flowi6 *fl6, const struct request_sock *req) { struct inet6_request_sock *treq = inet6_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *final_p, final; struct dst_entry *dst; - struct flowi6 fl6; - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_TCP; - fl6.daddr = treq->rmt_addr; - final_p = fl6_update_dst(&fl6, np->opt, &final); - fl6.saddr = treq->loc_addr; - fl6.flowi6_oif = sk->sk_bound_dev_if; - fl6.flowi6_mark = sk->sk_mark; - fl6.fl6_dport = inet_rsk(req)->rmt_port; - fl6.fl6_sport = inet_rsk(req)->loc_port; - security_req_classify_flow(req, flowi6_to_flowi(&fl6)); - - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); + memset(fl6, 0, sizeof(*fl6)); + fl6->flowi6_proto = IPPROTO_TCP; + fl6->daddr = treq->rmt_addr; + final_p = fl6_update_dst(fl6, np->opt, &final); + fl6->saddr = treq->loc_addr; + fl6->flowi6_oif = treq->iif; + fl6->flowi6_mark = sk->sk_mark; + fl6->fl6_dport = inet_rsk(req)->rmt_port; + fl6->fl6_sport = inet_rsk(req)->loc_port; + security_req_classify_flow(req, flowi6_to_flowi(fl6)); + + dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); if (IS_ERR(dst)) return NULL; @@ -171,7 +171,8 @@ EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr); static inline void __inet6_csk_dst_store(struct sock *sk, struct dst_entry *dst, - struct in6_addr *daddr, struct in6_addr *saddr) + const struct in6_addr *daddr, + const struct in6_addr *saddr) { __ip6_dst_store(sk, dst, daddr, saddr); @@ -203,43 +204,52 @@ struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie) return dst; } -int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) +static struct dst_entry *inet6_csk_route_socket(struct sock *sk, + struct flowi6 *fl6) { - struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct flowi6 fl6; - struct dst_entry *dst; struct in6_addr *final_p, final; - int res; + struct dst_entry *dst; - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_proto = sk->sk_protocol; - fl6.daddr = np->daddr; - fl6.saddr = np->saddr; - fl6.flowlabel = np->flow_label; - IP6_ECN_flow_xmit(sk, fl6.flowlabel); - fl6.flowi6_oif = sk->sk_bound_dev_if; - fl6.flowi6_mark = sk->sk_mark; - fl6.fl6_sport = inet->inet_sport; - fl6.fl6_dport = inet->inet_dport; - security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + memset(fl6, 0, sizeof(*fl6)); + fl6->flowi6_proto = sk->sk_protocol; + fl6->daddr = np->daddr; + fl6->saddr = np->saddr; + fl6->flowlabel = np->flow_label; + IP6_ECN_flow_xmit(sk, fl6->flowlabel); + fl6->flowi6_oif = sk->sk_bound_dev_if; + fl6->flowi6_mark = sk->sk_mark; + fl6->fl6_sport = inet->inet_sport; + fl6->fl6_dport = inet->inet_dport; + security_sk_classify_flow(sk, flowi6_to_flowi(fl6)); - final_p = fl6_update_dst(&fl6, np->opt, &final); + final_p = fl6_update_dst(fl6, np->opt, &final); dst = __inet6_csk_dst_check(sk, np->dst_cookie); + if (!dst) { + dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); - if (dst == NULL) { - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); + if (!IS_ERR(dst)) + __inet6_csk_dst_store(sk, dst, NULL, NULL); + } + return dst; +} - if (IS_ERR(dst)) { - sk->sk_err_soft = -PTR_ERR(dst); - sk->sk_route_caps = 0; - kfree_skb(skb); - return PTR_ERR(dst); - } +int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) +{ + struct sock *sk = skb->sk; + struct ipv6_pinfo *np = inet6_sk(sk); + struct flowi6 fl6; + struct dst_entry *dst; + int res; - __inet6_csk_dst_store(sk, dst, NULL, NULL); + dst = inet6_csk_route_socket(sk, &fl6); + if (IS_ERR(dst)) { + sk->sk_err_soft = -PTR_ERR(dst); + sk->sk_route_caps = 0; + kfree_skb(skb); + return PTR_ERR(dst); } rcu_read_lock(); @@ -253,3 +263,16 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) return res; } EXPORT_SYMBOL_GPL(inet6_csk_xmit); + +struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu) +{ + struct flowi6 fl6; + struct dst_entry *dst = inet6_csk_route_socket(sk, &fl6); + + if (IS_ERR(dst)) + return NULL; + dst->ops->update_pmtu(dst, sk, NULL, mtu); + + return inet6_csk_route_socket(sk, &fl6); +} +EXPORT_SYMBOL_GPL(inet6_csk_update_pmtu); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 60832766196..13690d650c3 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -197,6 +197,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) table->tb6_id = id; table->tb6_root.leaf = net->ipv6.ip6_null_entry; table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; + inet_peer_base_init(&table->tb6_peers); } return table; @@ -1633,6 +1634,7 @@ static int __net_init fib6_net_init(struct net *net) net->ipv6.fib6_main_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; + inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl), @@ -1643,6 +1645,7 @@ static int __net_init fib6_net_init(struct net *net) net->ipv6.fib6_local_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; + inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); #endif fib6_tables_init(net); @@ -1666,8 +1669,10 @@ static void fib6_net_exit(struct net *net) del_timer_sync(&net->ipv6.ip6_fib_timer); #ifdef CONFIG_IPV6_MULTIPLE_TABLES + inetpeer_invalidate_tree(&net->ipv6.fib6_local_tbl->tb6_peers); kfree(net->ipv6.fib6_local_tbl); #endif + inetpeer_invalidate_tree(&net->ipv6.fib6_main_tbl->tb6_peers); kfree(net->ipv6.fib6_main_tbl); kfree(net->ipv6.fib_table_hash); kfree(net->ipv6.rt6_stats); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 21a15dfe4a9..a52d864d562 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -47,9 +47,16 @@ -inline int ip6_rcv_finish( struct sk_buff *skb) +int ip6_rcv_finish(struct sk_buff *skb) { - if (skb_dst(skb) == NULL) + if (sysctl_ip_early_demux && !skb_dst(skb)) { + const struct inet6_protocol *ipprot; + + ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]); + if (ipprot && ipprot->early_demux) + ipprot->early_demux(skb); + } + if (!skb_dst(skb)) ip6_route_input(skb); return dst_input(skb); @@ -168,13 +175,12 @@ drop: static int ip6_input_finish(struct sk_buff *skb) { + struct net *net = dev_net(skb_dst(skb)->dev); const struct inet6_protocol *ipprot; + struct inet6_dev *idev; unsigned int nhoff; int nexthdr; bool raw; - u8 hash; - struct inet6_dev *idev; - struct net *net = dev_net(skb_dst(skb)->dev); /* * Parse extension headers @@ -189,9 +195,7 @@ resubmit: nexthdr = skb_network_header(skb)[nhoff]; raw = raw6_local_deliver(skb, nexthdr); - - hash = nexthdr & (MAX_INET_PROTOS - 1); - if ((ipprot = rcu_dereference(inet6_protos[hash])) != NULL) { + if ((ipprot = rcu_dereference(inet6_protos[nexthdr])) != NULL) { int ret; if (ipprot->flags & INET6_PROTO_FINAL) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index decc21d19c5..5b2d63ed793 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -83,24 +83,12 @@ int ip6_local_out(struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ip6_local_out); -/* dev_loopback_xmit for use with netfilter. */ -static int ip6_dev_loopback_xmit(struct sk_buff *newskb) -{ - skb_reset_mac_header(newskb); - __skb_pull(newskb, skb_network_offset(newskb)); - newskb->pkt_type = PACKET_LOOPBACK; - newskb->ip_summed = CHECKSUM_UNNECESSARY; - WARN_ON(!skb_dst(newskb)); - - netif_rx_ni(newskb); - return 0; -} - static int ip6_finish_output2(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; struct neighbour *neigh; + struct rt6_info *rt; skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; @@ -121,7 +109,7 @@ static int ip6_finish_output2(struct sk_buff *skb) if (newskb) NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, newskb, NULL, newskb->dev, - ip6_dev_loopback_xmit); + dev_loopback_xmit); if (ipv6_hdr(skb)->hop_limit == 0) { IP6_INC_STATS(dev_net(dev), idev, @@ -136,9 +124,10 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_lock(); - neigh = dst_get_neighbour_noref(dst); + rt = (struct rt6_info *) dst; + neigh = rt->n; if (neigh) { - int res = neigh_output(neigh, skb); + int res = dst_neigh_output(dst, neigh, skb); rcu_read_unlock(); return res; @@ -463,6 +452,7 @@ int ip6_forward(struct sk_buff *skb) */ if (skb->dev == dst->dev && opt->srcrt == 0 && !skb_sec_path(skb)) { struct in6_addr *target = NULL; + struct inet_peer *peer; struct rt6_info *rt; /* @@ -476,14 +466,15 @@ int ip6_forward(struct sk_buff *skb) else target = &hdr->daddr; - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); + peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); /* Limit redirects both by destination (here) and by source (inside ndisc_send_redirect) */ - if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) + if (inet_peer_xrlim_allow(peer, 1*HZ)) ndisc_send_redirect(skb, target); + if (peer) + inet_putpeer(peer); } else { int addrtype = ipv6_addr_type(&hdr->saddr); @@ -604,12 +595,13 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) if (rt && !(rt->dst.flags & DST_NOPEER)) { struct inet_peer *peer; + struct net *net; - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); - peer = rt->rt6i_peer; + net = dev_net(rt->dst.dev); + peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); if (peer) { fhdr->identification = htonl(inet_getid(peer, 0)); + inet_putpeer(peer); return; } } @@ -960,6 +952,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, struct net *net = sock_net(sk); #ifdef CONFIG_IPV6_OPTIMISTIC_DAD struct neighbour *n; + struct rt6_info *rt; #endif int err; @@ -988,7 +981,8 @@ static int ip6_dst_lookup_tail(struct sock *sk, * dst entry of the nexthop router */ rcu_read_lock(); - n = dst_get_neighbour_noref(*dst); + rt = (struct rt6_info *) *dst; + n = rt->n; if (n && !(n->nud_state & NUD_VALID)) { struct inet6_ifaddr *ifp; struct flowi6 fl_gw6; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index c9015fad8d6..9a1d5fe6aef 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -40,6 +40,7 @@ #include <linux/rtnetlink.h> #include <linux/netfilter_ipv6.h> #include <linux/slab.h> +#include <linux/hash.h> #include <asm/uaccess.h> #include <linux/atomic.h> @@ -70,11 +71,15 @@ MODULE_ALIAS_NETDEV("ip6tnl0"); #define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK) #define IPV6_TCLASS_SHIFT 20 -#define HASH_SIZE 32 +#define HASH_SIZE_SHIFT 5 +#define HASH_SIZE (1 << HASH_SIZE_SHIFT) -#define HASH(addr) ((__force u32)((addr)->s6_addr32[0] ^ (addr)->s6_addr32[1] ^ \ - (addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \ - (HASH_SIZE - 1)) +static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) +{ + u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2); + + return hash_32(hash, HASH_SIZE_SHIFT); +} static int ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); @@ -166,12 +171,11 @@ static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) static struct ip6_tnl * ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_addr *local) { - unsigned int h0 = HASH(remote); - unsigned int h1 = HASH(local); + unsigned int hash = HASH(remote, local); struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[h0 ^ h1]) { + for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr) && (t->dev->flags & IFF_UP)) @@ -205,7 +209,7 @@ ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct ip6_tnl_parm *p) if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) { prio = 1; - h = HASH(remote) ^ HASH(local); + h = HASH(remote, local); } return &ip6n->tnls[prio][h]; } @@ -252,7 +256,7 @@ static void ip6_dev_free(struct net_device *dev) } /** - * ip6_tnl_create() - create a new tunnel + * ip6_tnl_create - create a new tunnel * @p: tunnel parameters * @pt: pointer to new tunnel * @@ -550,6 +554,9 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_FRAG_NEEDED; break; + case NDISC_REDIRECT: + rel_type = ICMP_REDIRECT; + rel_code = ICMP_REDIR_HOST; default: return 0; } @@ -606,8 +613,10 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rel_info > dst_mtu(skb_dst(skb2))) goto out; - skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), rel_info); + skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2, rel_info); } + if (rel_type == ICMP_REDIRECT) + skb_dst(skb2)->ops->redirect(skb_dst(skb2), NULL, skb2); icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); @@ -684,24 +693,50 @@ static void ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, IP6_ECN_set_ce(ipv6_hdr(skb)); } +static __u32 ip6_tnl_get_cap(struct ip6_tnl *t, + const struct in6_addr *laddr, + const struct in6_addr *raddr) +{ + struct ip6_tnl_parm *p = &t->parms; + int ltype = ipv6_addr_type(laddr); + int rtype = ipv6_addr_type(raddr); + __u32 flags = 0; + + if (ltype == IPV6_ADDR_ANY || rtype == IPV6_ADDR_ANY) { + flags = IP6_TNL_F_CAP_PER_PACKET; + } else if (ltype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && + rtype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && + !((ltype|rtype) & IPV6_ADDR_LOOPBACK) && + (!((ltype|rtype) & IPV6_ADDR_LINKLOCAL) || p->link)) { + if (ltype&IPV6_ADDR_UNICAST) + flags |= IP6_TNL_F_CAP_XMIT; + if (rtype&IPV6_ADDR_UNICAST) + flags |= IP6_TNL_F_CAP_RCV; + } + return flags; +} + /* called with rcu_read_lock() */ -static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t) +static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t, + const struct in6_addr *laddr, + const struct in6_addr *raddr) { struct ip6_tnl_parm *p = &t->parms; int ret = 0; struct net *net = dev_net(t->dev); - if (p->flags & IP6_TNL_F_CAP_RCV) { + if ((p->flags & IP6_TNL_F_CAP_RCV) || + ((p->flags & IP6_TNL_F_CAP_PER_PACKET) && + (ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_RCV))) { struct net_device *ldev = NULL; if (p->link) ldev = dev_get_by_index_rcu(net, p->link); - if ((ipv6_addr_is_multicast(&p->laddr) || - likely(ipv6_chk_addr(net, &p->laddr, ldev, 0))) && - likely(!ipv6_chk_addr(net, &p->raddr, NULL, 0))) + if ((ipv6_addr_is_multicast(laddr) || + likely(ipv6_chk_addr(net, laddr, ldev, 0))) && + likely(!ipv6_chk_addr(net, raddr, NULL, 0))) ret = 1; - } return ret; } @@ -740,7 +775,7 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, goto discard; } - if (!ip6_tnl_rcv_ctl(t)) { + if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) { t->dev->stats.rx_dropped++; rcu_read_unlock(); goto discard; @@ -921,7 +956,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (skb->len > mtu) { *pmtu = mtu; err = -EMSGSIZE; @@ -1114,25 +1149,6 @@ tx_err: return NETDEV_TX_OK; } -static void ip6_tnl_set_cap(struct ip6_tnl *t) -{ - struct ip6_tnl_parm *p = &t->parms; - int ltype = ipv6_addr_type(&p->laddr); - int rtype = ipv6_addr_type(&p->raddr); - - p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV); - - if (ltype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && - rtype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && - !((ltype|rtype) & IPV6_ADDR_LOOPBACK) && - (!((ltype|rtype) & IPV6_ADDR_LINKLOCAL) || p->link)) { - if (ltype&IPV6_ADDR_UNICAST) - p->flags |= IP6_TNL_F_CAP_XMIT; - if (rtype&IPV6_ADDR_UNICAST) - p->flags |= IP6_TNL_F_CAP_RCV; - } -} - static void ip6_tnl_link_config(struct ip6_tnl *t) { struct net_device *dev = t->dev; @@ -1153,7 +1169,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL)) fl6->flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo; - ip6_tnl_set_cap(t); + p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV|IP6_TNL_F_CAP_PER_PACKET); + p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); if (p->flags&IP6_TNL_F_CAP_XMIT && p->flags&IP6_TNL_F_CAP_RCV) dev->flags |= IFF_POINTOPOINT; @@ -1438,6 +1455,9 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) t->parms.proto = IPPROTO_IPV6; dev_hold(dev); + + ip6_tnl_link_config(t); + rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 461e47c8e95..4532973f0dd 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2104,8 +2104,9 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, if (c->mf6c_parent >= MAXMIFS) return -ENOENT; - if (MIF_EXISTS(mrt, c->mf6c_parent)) - RTA_PUT(skb, RTA_IIF, 4, &mrt->vif6_table[c->mf6c_parent].dev->ifindex); + if (MIF_EXISTS(mrt, c->mf6c_parent) && + nla_put_u32(skb, RTA_IIF, mrt->vif6_table[c->mf6c_parent].dev->ifindex) < 0) + return -EMSGSIZE; mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0)); diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 5cb75bfe45b..7af5aee75d9 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -46,6 +46,7 @@ #include <linux/list.h> #include <linux/vmalloc.h> #include <linux/rtnetlink.h> +#include <net/ip6_route.h> #include <net/icmp.h> #include <net/ipv6.h> #include <net/protocol.h> @@ -63,7 +64,9 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, (struct ip_comp_hdr *)(skb->data + offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && type != ICMPV6_PKT_TOOBIG) + if (type != ICMPV6_DEST_UNREACH && + type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) return; spi = htonl(ntohs(ipcomph->cpi)); @@ -72,8 +75,10 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!x) return; - pr_debug("pmtu discovery on SA IPCOMP/%08x/%pI6\n", - spi, &iph->daddr); + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, 0, 0); + else + ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 6d0f5dc8e3a..92f8e48e4ba 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -211,6 +211,9 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) struct ipv6_mc_socklist __rcu **lnk; struct net *net = sock_net(sk); + if (!ipv6_addr_is_multicast(addr)) + return -EINVAL; + spin_lock(&ipv6_sk_mc_lock); for (lnk = &np->ipv6_mc_list; (mc_lst = rcu_dereference_protected(*lnk, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 54f62d3b8dd..ff36194a71a 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -143,40 +143,6 @@ struct neigh_table nd_tbl = { .gc_thresh3 = 1024, }; -/* ND options */ -struct ndisc_options { - struct nd_opt_hdr *nd_opt_array[__ND_OPT_ARRAY_MAX]; -#ifdef CONFIG_IPV6_ROUTE_INFO - struct nd_opt_hdr *nd_opts_ri; - struct nd_opt_hdr *nd_opts_ri_end; -#endif - struct nd_opt_hdr *nd_useropts; - struct nd_opt_hdr *nd_useropts_end; -}; - -#define nd_opts_src_lladdr nd_opt_array[ND_OPT_SOURCE_LL_ADDR] -#define nd_opts_tgt_lladdr nd_opt_array[ND_OPT_TARGET_LL_ADDR] -#define nd_opts_pi nd_opt_array[ND_OPT_PREFIX_INFO] -#define nd_opts_pi_end nd_opt_array[__ND_OPT_PREFIX_INFO_END] -#define nd_opts_rh nd_opt_array[ND_OPT_REDIRECT_HDR] -#define nd_opts_mtu nd_opt_array[ND_OPT_MTU] - -#define NDISC_OPT_SPACE(len) (((len)+2+7)&~7) - -/* - * Return the padding between the option length and the start of the - * link addr. Currently only IP-over-InfiniBand needs this, although - * if RFC 3831 IPv6-over-Fibre Channel is ever implemented it may - * also need a pad of 2. - */ -static int ndisc_addr_option_pad(unsigned short type) -{ - switch (type) { - case ARPHRD_INFINIBAND: return 2; - default: return 0; - } -} - static inline int ndisc_opt_addr_space(struct net_device *dev) { return NDISC_OPT_SPACE(dev->addr_len + ndisc_addr_option_pad(dev->type)); @@ -233,8 +199,8 @@ static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur, return cur <= end && ndisc_is_useropt(cur) ? cur : NULL; } -static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, - struct ndisc_options *ndopts) +struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, + struct ndisc_options *ndopts) { struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt; @@ -297,17 +263,6 @@ static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, return ndopts; } -static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, - struct net_device *dev) -{ - u8 *lladdr = (u8 *)(p + 1); - int lladdrlen = p->nd_opt_len << 3; - int prepad = ndisc_addr_option_pad(dev->type); - if (lladdrlen != NDISC_OPT_SPACE(dev->addr_len + prepad)) - return NULL; - return lladdr + prepad; -} - int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir) { switch (dev->type) { @@ -1379,16 +1334,6 @@ out: static void ndisc_redirect_rcv(struct sk_buff *skb) { - struct inet6_dev *in6_dev; - struct icmp6hdr *icmph; - const struct in6_addr *dest; - const struct in6_addr *target; /* new first hop to destination */ - struct neighbour *neigh; - int on_link = 0; - struct ndisc_options ndopts; - int optlen; - u8 *lladdr = NULL; - #ifdef CONFIG_IPV6_NDISC_NODETYPE switch (skb->ndisc_nodetype) { case NDISC_NODETYPE_HOST: @@ -1405,65 +1350,7 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) return; } - optlen = skb->tail - skb->transport_header; - optlen -= sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); - - if (optlen < 0) { - ND_PRINTK(2, warn, "Redirect: packet too short\n"); - return; - } - - icmph = icmp6_hdr(skb); - target = (const struct in6_addr *) (icmph + 1); - dest = target + 1; - - if (ipv6_addr_is_multicast(dest)) { - ND_PRINTK(2, warn, - "Redirect: destination address is multicast\n"); - return; - } - - if (ipv6_addr_equal(dest, target)) { - on_link = 1; - } else if (ipv6_addr_type(target) != - (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { - ND_PRINTK(2, warn, - "Redirect: target address is not link-local unicast\n"); - return; - } - - in6_dev = __in6_dev_get(skb->dev); - if (!in6_dev) - return; - if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_redirects) - return; - - /* RFC2461 8.1: - * The IP source address of the Redirect MUST be the same as the current - * first-hop router for the specified ICMP Destination Address. - */ - - if (!ndisc_parse_options((u8*)(dest + 1), optlen, &ndopts)) { - ND_PRINTK(2, warn, "Redirect: invalid ND options\n"); - return; - } - if (ndopts.nd_opts_tgt_lladdr) { - lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, - skb->dev); - if (!lladdr) { - ND_PRINTK(2, warn, - "Redirect: invalid link-layer address length\n"); - return; - } - } - - neigh = __neigh_lookup(&nd_tbl, target, skb->dev, 1); - if (neigh) { - rt6_redirect(dest, &ipv6_hdr(skb)->daddr, - &ipv6_hdr(skb)->saddr, neigh, lladdr, - on_link); - neigh_release(neigh); - } + icmpv6_notify(skb, NDISC_REDIRECT, 0, 0); } void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) @@ -1472,6 +1359,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; int len = sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); + struct inet_peer *peer; struct sk_buff *buff; struct icmp6hdr *icmph; struct in6_addr saddr_buf; @@ -1485,6 +1373,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) int rd_len; int err; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL; + bool ret; if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) { ND_PRINTK(2, warn, "Redirect: no link-local address on %s\n", @@ -1518,9 +1407,11 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) "Redirect: destination is not a neighbour\n"); goto release; } - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); - if (!inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) + peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + ret = inet_peer_xrlim_allow(peer, 1*HZ); + if (peer) + inet_putpeer(peer); + if (!ret) goto release; if (dev->addr_len) { diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 3224ef90a21..4794f96cf2e 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -143,11 +143,11 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, return NF_ACCEPT; } -static unsigned int ipv6_confirm(unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static unsigned int ipv6_helper(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { struct nf_conn *ct; const struct nf_conn_help *help; @@ -161,15 +161,15 @@ static unsigned int ipv6_confirm(unsigned int hooknum, /* This is where we call the helper: as the packet goes out. */ ct = nf_ct_get(skb, &ctinfo); if (!ct || ctinfo == IP_CT_RELATED_REPLY) - goto out; + return NF_ACCEPT; help = nfct_help(ct); if (!help) - goto out; + return NF_ACCEPT; /* rcu_read_lock()ed by nf_hook_slow */ helper = rcu_dereference(help->helper); if (!helper) - goto out; + return NF_ACCEPT; protoff = nf_ct_ipv6_skip_exthdr(skb, extoff, &pnum, skb->len - extoff); @@ -179,12 +179,19 @@ static unsigned int ipv6_confirm(unsigned int hooknum, } ret = helper->help(skb, protoff, ct, ctinfo); - if (ret != NF_ACCEPT) { + if (ret != NF_ACCEPT && (ret & NF_VERDICT_MASK) != NF_QUEUE) { nf_log_packet(NFPROTO_IPV6, hooknum, skb, in, out, NULL, "nf_ct_%s: dropping packet", helper->name); - return ret; } -out: + return ret; +} + +static unsigned int ipv6_confirm(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ /* We've seen it coming out the other side: confirm it */ return nf_conntrack_confirm(skb); } @@ -254,6 +261,13 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { .priority = NF_IP6_PRI_CONNTRACK, }, { + .hook = ipv6_helper, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_CONNTRACK_HELPER, + }, + { .hook = ipv6_confirm, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, @@ -261,6 +275,13 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { .priority = NF_IP6_PRI_LAST, }, { + .hook = ipv6_helper, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP6_PRI_CONNTRACK_HELPER, + }, + { .hook = ipv6_confirm, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, @@ -333,37 +354,75 @@ MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6)); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>"); -static int __init nf_conntrack_l3proto_ipv6_init(void) +static int ipv6_net_init(struct net *net) { int ret = 0; - need_conntrack(); - nf_defrag_ipv6_enable(); - - ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_tcp6); + ret = nf_conntrack_l4proto_register(net, + &nf_conntrack_l4proto_tcp6); if (ret < 0) { - pr_err("nf_conntrack_ipv6: can't register tcp.\n"); - return ret; + printk(KERN_ERR "nf_conntrack_l4proto_tcp6: protocol register failed\n"); + goto out; } - - ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_udp6); + ret = nf_conntrack_l4proto_register(net, + &nf_conntrack_l4proto_udp6); if (ret < 0) { - pr_err("nf_conntrack_ipv6: can't register udp.\n"); - goto cleanup_tcp; + printk(KERN_ERR "nf_conntrack_l4proto_udp6: protocol register failed\n"); + goto cleanup_tcp6; } - - ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_icmpv6); + ret = nf_conntrack_l4proto_register(net, + &nf_conntrack_l4proto_icmpv6); if (ret < 0) { - pr_err("nf_conntrack_ipv6: can't register icmpv6.\n"); - goto cleanup_udp; + printk(KERN_ERR "nf_conntrack_l4proto_icmp6: protocol register failed\n"); + goto cleanup_udp6; } - - ret = nf_conntrack_l3proto_register(&nf_conntrack_l3proto_ipv6); + ret = nf_conntrack_l3proto_register(net, + &nf_conntrack_l3proto_ipv6); if (ret < 0) { - pr_err("nf_conntrack_ipv6: can't register ipv6\n"); + printk(KERN_ERR "nf_conntrack_l3proto_ipv6: protocol register failed\n"); goto cleanup_icmpv6; } + return 0; + cleanup_icmpv6: + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_icmpv6); + cleanup_udp6: + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_udp6); + cleanup_tcp6: + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_tcp6); + out: + return ret; +} +static void ipv6_net_exit(struct net *net) +{ + nf_conntrack_l3proto_unregister(net, + &nf_conntrack_l3proto_ipv6); + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_icmpv6); + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_udp6); + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_tcp6); +} + +static struct pernet_operations ipv6_net_ops = { + .init = ipv6_net_init, + .exit = ipv6_net_exit, +}; + +static int __init nf_conntrack_l3proto_ipv6_init(void) +{ + int ret = 0; + + need_conntrack(); + nf_defrag_ipv6_enable(); + + ret = register_pernet_subsys(&ipv6_net_ops); + if (ret < 0) + goto cleanup_pernet; ret = nf_register_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); if (ret < 0) { @@ -374,13 +433,8 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) return ret; cleanup_ipv6: - nf_conntrack_l3proto_unregister(&nf_conntrack_l3proto_ipv6); - cleanup_icmpv6: - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_icmpv6); - cleanup_udp: - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udp6); - cleanup_tcp: - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_tcp6); + unregister_pernet_subsys(&ipv6_net_ops); + cleanup_pernet: return ret; } @@ -388,10 +442,7 @@ static void __exit nf_conntrack_l3proto_ipv6_fini(void) { synchronize_net(); nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); - nf_conntrack_l3proto_unregister(&nf_conntrack_l3proto_ipv6); - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_icmpv6); - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udp6); - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_tcp6); + unregister_pernet_subsys(&ipv6_net_ops); } module_init(nf_conntrack_l3proto_ipv6_init); diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 3e81904fbbc..2d54b2061d6 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -29,6 +29,11 @@ static unsigned int nf_ct_icmpv6_timeout __read_mostly = 30*HZ; +static inline struct nf_icmp_net *icmpv6_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.icmpv6; +} + static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct nf_conntrack_tuple *tuple) @@ -90,7 +95,7 @@ static int icmpv6_print_tuple(struct seq_file *s, static unsigned int *icmpv6_get_timeouts(struct net *net) { - return &nf_ct_icmpv6_timeout; + return &icmpv6_pernet(net)->timeout; } /* Returns verdict for packet, or -1 for invalid. */ @@ -281,16 +286,18 @@ static int icmpv6_nlattr_tuple_size(void) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> -static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], + struct net *net, void *data) { unsigned int *timeout = data; + struct nf_icmp_net *in = icmpv6_pernet(net); if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) { *timeout = ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ; } else { /* Set default ICMPv6 timeout. */ - *timeout = nf_ct_icmpv6_timeout; + *timeout = in->timeout; } return 0; } @@ -315,11 +322,9 @@ icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL -static struct ctl_table_header *icmpv6_sysctl_header; static struct ctl_table icmpv6_sysctl_table[] = { { .procname = "nf_conntrack_icmpv6_timeout", - .data = &nf_ct_icmpv6_timeout, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -328,6 +333,36 @@ static struct ctl_table icmpv6_sysctl_table[] = { }; #endif /* CONFIG_SYSCTL */ +static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn, + struct nf_icmp_net *in) +{ +#ifdef CONFIG_SYSCTL + pn->ctl_table = kmemdup(icmpv6_sysctl_table, + sizeof(icmpv6_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_table) + return -ENOMEM; + + pn->ctl_table[0].data = &in->timeout; +#endif + return 0; +} + +static int icmpv6_init_net(struct net *net, u_int16_t proto) +{ + struct nf_icmp_net *in = icmpv6_pernet(net); + struct nf_proto_net *pn = &in->pn; + + in->timeout = nf_ct_icmpv6_timeout; + + return icmpv6_kmemdup_sysctl_table(pn, in); +} + +static struct nf_proto_net *icmpv6_get_net_proto(struct net *net) +{ + return &net->ct.nf_ct_proto.icmpv6.pn; +} + struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly = { .l3proto = PF_INET6, @@ -355,8 +390,6 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly = .nla_policy = icmpv6_timeout_nla_policy, }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ -#ifdef CONFIG_SYSCTL - .ctl_table_header = &icmpv6_sysctl_header, - .ctl_table = icmpv6_sysctl_table, -#endif + .init_net = icmpv6_init_net, + .get_net_proto = icmpv6_get_net_proto, }; diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index da2e92d05c1..745a3204295 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -307,10 +307,10 @@ static int __net_init ipv6_proc_init_net(struct net *net) goto proc_dev_snmp6_fail; return 0; +proc_dev_snmp6_fail: + proc_net_remove(net, "snmp6"); proc_snmp6_fail: proc_net_remove(net, "sockstat6"); -proc_dev_snmp6_fail: - proc_net_remove(net, "dev_snmp6"); return -ENOMEM; } diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c index 9a7978fdc02..053082dfc93 100644 --- a/net/ipv6/protocol.c +++ b/net/ipv6/protocol.c @@ -29,9 +29,7 @@ const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly; int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol) { - int hash = protocol & (MAX_INET_PROTOS - 1); - - return !cmpxchg((const struct inet6_protocol **)&inet6_protos[hash], + return !cmpxchg((const struct inet6_protocol **)&inet6_protos[protocol], NULL, prot) ? 0 : -1; } EXPORT_SYMBOL(inet6_add_protocol); @@ -42,9 +40,9 @@ EXPORT_SYMBOL(inet6_add_protocol); int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char protocol) { - int ret, hash = protocol & (MAX_INET_PROTOS - 1); + int ret; - ret = (cmpxchg((const struct inet6_protocol **)&inet6_protos[hash], + ret = (cmpxchg((const struct inet6_protocol **)&inet6_protos[protocol], prot, NULL) == prot) ? 0 : -1; synchronize_net(); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 93d69836fde..ef0579d5bca 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -165,7 +165,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) saddr = &ipv6_hdr(skb)->saddr; daddr = saddr + 1; - hash = nexthdr & (MAX_INET_PROTOS - 1); + hash = nexthdr & (RAW_HTABLE_SIZE - 1); read_lock(&raw_v6_hashinfo.lock); sk = sk_head(&raw_v6_hashinfo.ht[hash]); @@ -229,7 +229,7 @@ bool raw6_local_deliver(struct sk_buff *skb, int nexthdr) { struct sock *raw_sk; - raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (MAX_INET_PROTOS - 1)]); + raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (RAW_HTABLE_SIZE - 1)]); if (raw_sk && !ipv6_raw_deliver(skb, nexthdr)) raw_sk = NULL; @@ -328,9 +328,12 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, return; harderr = icmpv6_err_convert(type, code, &err); - if (type == ICMPV6_PKT_TOOBIG) + if (type == ICMPV6_PKT_TOOBIG) { + ip6_sk_update_pmtu(skb, sk, info); harderr = (np->pmtudisc == IPV6_PMTUDISC_DO); - + } + if (type == NDISC_REDIRECT) + ip6_sk_redirect(skb, sk); if (np->recverr) { u8 *payload = skb->data; if (!inet->hdrincl) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index becb048d18d..8e80fd27910 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -78,7 +78,10 @@ static int ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); -static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu); +static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu); +static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb); #ifdef CONFIG_IPV6_ROUTE_INFO static struct rt6_info *rt6_add_route_info(struct net *net, @@ -99,10 +102,7 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) if (!(rt->dst.flags & DST_HOST)) return NULL; - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); - - peer = rt->rt6i_peer; + peer = rt6_get_peer_create(rt); if (peer) { u32 *old_p = __DST_METRICS_PTR(old); unsigned long prev, new; @@ -123,21 +123,27 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) return p; } -static inline const void *choose_neigh_daddr(struct rt6_info *rt, const void *daddr) +static inline const void *choose_neigh_daddr(struct rt6_info *rt, + struct sk_buff *skb, + const void *daddr) { struct in6_addr *p = &rt->rt6i_gateway; if (!ipv6_addr_any(p)) return (const void *) p; + else if (skb) + return &ipv6_hdr(skb)->daddr; return daddr; } -static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, const void *daddr) +static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) { struct rt6_info *rt = (struct rt6_info *) dst; struct neighbour *n; - daddr = choose_neigh_daddr(rt, daddr); + daddr = choose_neigh_daddr(rt, skb, daddr); n = __ipv6_neigh_lookup(&nd_tbl, dst->dev, daddr); if (n) return n; @@ -152,7 +158,7 @@ static int rt6_bind_neighbour(struct rt6_info *rt, struct net_device *dev) if (IS_ERR(n)) return PTR_ERR(n); } - dst_set_neighbour(&rt->dst, n); + rt->n = n; return 0; } @@ -171,6 +177,7 @@ static struct dst_ops ip6_dst_ops_template = { .negative_advice = ip6_negative_advice, .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, + .redirect = rt6_do_redirect, .local_out = __ip6_local_out, .neigh_lookup = ip6_neigh_lookup, }; @@ -182,7 +189,13 @@ static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) return mtu ? : dst->dev->mtu; } -static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) +static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) +{ +} + +static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) { } @@ -200,6 +213,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { .mtu = ip6_blackhole_mtu, .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, + .redirect = ip6_rt_blackhole_redirect, .cow_metrics = ip6_rt_blackhole_cow_metrics, .neigh_lookup = ip6_neigh_lookup, }; @@ -261,16 +275,20 @@ static struct rt6_info ip6_blk_hole_entry_template = { #endif /* allocate dst with ip6_dst_ops */ -static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops, +static inline struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, - int flags) + int flags, + struct fib6_table *table) { - struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, flags); + struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, + 0, DST_OBSOLETE_NONE, flags); - if (rt) - memset(&rt->rt6i_table, 0, - sizeof(*rt) - sizeof(struct dst_entry)); + if (rt) { + struct dst_entry *dst = &rt->dst; + memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); + rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); + } return rt; } @@ -278,7 +296,9 @@ static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *)dst; struct inet6_dev *idev = rt->rt6i_idev; - struct inet_peer *peer = rt->rt6i_peer; + + if (rt->n) + neigh_release(rt->n); if (!(rt->dst.flags & DST_HOST)) dst_destroy_metrics_generic(dst); @@ -291,8 +311,8 @@ static void ip6_dst_destroy(struct dst_entry *dst) if (!(rt->rt6i_flags & RTF_EXPIRES) && dst->from) dst_release(dst->from); - if (peer) { - rt->rt6i_peer = NULL; + if (rt6_has_peer(rt)) { + struct inet_peer *peer = rt6_peer_ptr(rt); inet_putpeer(peer); } } @@ -306,13 +326,20 @@ static u32 rt6_peer_genid(void) void rt6_bind_peer(struct rt6_info *rt, int create) { + struct inet_peer_base *base; struct inet_peer *peer; - peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create); - if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL) - inet_putpeer(peer); - else - rt->rt6i_peer_genid = rt6_peer_genid(); + base = inetpeer_base_ptr(rt->_rt6i_peer); + if (!base) + return; + + peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create); + if (peer) { + if (!rt6_set_peer(rt, peer)) + inet_putpeer(peer); + else + rt->rt6i_peer_genid = rt6_peer_genid(); + } } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -323,12 +350,19 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, struct net_device *loopback_dev = dev_net(dev)->loopback_dev; - if (dev != loopback_dev && idev && idev->dev == dev) { - struct inet6_dev *loopback_idev = - in6_dev_get(loopback_dev); - if (loopback_idev) { - rt->rt6i_idev = loopback_idev; - in6_dev_put(idev); + if (dev != loopback_dev) { + if (idev && idev->dev == dev) { + struct inet6_dev *loopback_idev = + in6_dev_get(loopback_dev); + if (loopback_idev) { + rt->rt6i_idev = loopback_idev; + in6_dev_put(idev); + } + } + if (rt->n && rt->n->dev == dev) { + rt->n->dev = loopback_dev; + dev_hold(loopback_dev); + dev_put(dev); } } } @@ -418,7 +452,7 @@ static void rt6_probe(struct rt6_info *rt) * to no more than one per minute. */ rcu_read_lock(); - neigh = rt ? dst_get_neighbour_noref(&rt->dst) : NULL; + neigh = rt ? rt->n : NULL; if (!neigh || (neigh->nud_state & NUD_VALID)) goto out; read_lock_bh(&neigh->lock); @@ -465,7 +499,7 @@ static inline int rt6_check_neigh(struct rt6_info *rt) int m; rcu_read_lock(); - neigh = dst_get_neighbour_noref(&rt->dst); + neigh = rt->n; if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) m = 1; @@ -812,7 +846,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, if (rt) { rt->rt6i_flags |= RTF_CACHE; - dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_noref_raw(&ort->dst))); + rt->n = neigh_clone(ort->n); } return rt; } @@ -846,7 +880,7 @@ restart: dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); - if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!rt->n && !(rt->rt6i_flags & RTF_NONEXTHOP)) nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); else if (!(rt->dst.flags & DST_HOST)) nrt = rt6_alloc_clone(rt, &fl6->daddr); @@ -931,6 +965,8 @@ struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk, { int flags = 0; + fl6->flowi6_iif = net->loopback_dev->ifindex; + if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr)) flags |= RT6_LOOKUP_F_IFACE; @@ -949,12 +985,13 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig; struct dst_entry *new = NULL; - rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, 0, 0); + rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, DST_OBSOLETE_NONE, 0); if (rt) { - memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry)); - new = &rt->dst; + memset(new + 1, 0, sizeof(*rt) - sizeof(*new)); + rt6_init_peer(rt, net->ipv6.peers); + new->__use = 1; new->input = dst_discard; new->output = dst_discard; @@ -996,7 +1033,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) { if (rt->rt6i_peer_genid != rt6_peer_genid()) { - if (!rt->rt6i_peer) + if (!rt6_has_peer(rt)) rt6_bind_peer(rt, 0); rt->rt6i_peer_genid = rt6_peer_genid(); } @@ -1038,11 +1075,15 @@ static void ip6_link_failure(struct sk_buff *skb) } } -static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu) +static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { struct rt6_info *rt6 = (struct rt6_info*)dst; + dst_confirm(dst); if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) { + struct net *net = dev_net(dst->dev); + rt6->rt6i_flags |= RTF_MODIFIED; if (mtu < IPV6_MIN_MTU) { u32 features = dst_metric(dst, RTAX_FEATURES); @@ -1051,9 +1092,66 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu) dst_metric_set(dst, RTAX_FEATURES, features); } dst_metric_set(dst, RTAX_MTU, mtu); + rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires); } } +void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, + int oif, u32 mark) +{ + const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; + struct dst_entry *dst; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = oif; + fl6.flowi6_mark = mark; + fl6.flowi6_flags = 0; + fl6.daddr = iph->daddr; + fl6.saddr = iph->saddr; + fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK; + + dst = ip6_route_output(net, NULL, &fl6); + if (!dst->error) + ip6_rt_update_pmtu(dst, NULL, skb, ntohl(mtu)); + dst_release(dst); +} +EXPORT_SYMBOL_GPL(ip6_update_pmtu); + +void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) +{ + ip6_update_pmtu(skb, sock_net(sk), mtu, + sk->sk_bound_dev_if, sk->sk_mark); +} +EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu); + +void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark) +{ + const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; + struct dst_entry *dst; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = oif; + fl6.flowi6_mark = mark; + fl6.flowi6_flags = 0; + fl6.daddr = iph->daddr; + fl6.saddr = iph->saddr; + fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK; + + dst = ip6_route_output(net, NULL, &fl6); + if (!dst->error) + rt6_do_redirect(dst, NULL, skb); + dst_release(dst); +} +EXPORT_SYMBOL_GPL(ip6_redirect); + +void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) +{ + ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark); +} +EXPORT_SYMBOL_GPL(ip6_sk_redirect); + static unsigned int ip6_default_advmss(const struct dst_entry *dst) { struct net_device *dev = dst->dev; @@ -1110,7 +1208,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, if (unlikely(!idev)) return ERR_PTR(-ENODEV); - rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0); + rt = ip6_dst_alloc(net, dev, 0, NULL); if (unlikely(!rt)) { in6_dev_put(idev); dst = ERR_PTR(-ENOMEM); @@ -1120,7 +1218,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, if (neigh) neigh_hold(neigh); else { - neigh = ip6_neigh_lookup(&rt->dst, &fl6->daddr); + neigh = ip6_neigh_lookup(&rt->dst, NULL, &fl6->daddr); if (IS_ERR(neigh)) { in6_dev_put(idev); dst_free(&rt->dst); @@ -1130,7 +1228,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->dst.flags |= DST_HOST; rt->dst.output = ip6_output; - dst_set_neighbour(&rt->dst, neigh); + rt->n = neigh; atomic_set(&rt->dst.__refcnt, 1); rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; @@ -1292,7 +1390,7 @@ int ip6_route_add(struct fib6_config *cfg) if (!table) goto out; - rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, DST_NOCOUNT); + rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table); if (!rt) { err = -ENOMEM; @@ -1546,107 +1644,94 @@ static int ip6_route_del(struct fib6_config *cfg) return err; } -/* - * Handle redirects - */ -struct ip6rd_flowi { - struct flowi6 fl6; - struct in6_addr gateway; -}; - -static struct rt6_info *__ip6_route_redirect(struct net *net, - struct fib6_table *table, - struct flowi6 *fl6, - int flags) +static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { - struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; - struct rt6_info *rt; - struct fib6_node *fn; + struct net *net = dev_net(skb->dev); + struct netevent_redirect netevent; + struct rt6_info *rt, *nrt = NULL; + const struct in6_addr *target; + struct ndisc_options ndopts; + const struct in6_addr *dest; + struct neighbour *old_neigh; + struct inet6_dev *in6_dev; + struct neighbour *neigh; + struct icmp6hdr *icmph; + int optlen, on_link; + u8 *lladdr; - /* - * Get the "current" route for this destination and - * check if the redirect has come from approriate router. - * - * RFC 2461 specifies that redirects should only be - * accepted if they come from the nexthop to the target. - * Due to the way the routes are chosen, this notion - * is a bit fuzzy and one might need to check all possible - * routes. - */ + optlen = skb->tail - skb->transport_header; + optlen -= sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); - read_lock_bh(&table->tb6_lock); - fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); -restart: - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { - /* - * Current route is on-link; redirect is always invalid. - * - * Seems, previous statement is not true. It could - * be node, which looks for us as on-link (f.e. proxy ndisc) - * But then router serving it might decide, that we should - * know truth 8)8) --ANK (980726). - */ - if (rt6_check_expired(rt)) - continue; - if (!(rt->rt6i_flags & RTF_GATEWAY)) - continue; - if (fl6->flowi6_oif != rt->dst.dev->ifindex) - continue; - if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) - continue; - break; + if (optlen < 0) { + net_dbg_ratelimited("rt6_do_redirect: packet too short\n"); + return; } - if (!rt) - rt = net->ipv6.ip6_null_entry; - BACKTRACK(net, &fl6->saddr); -out: - dst_hold(&rt->dst); - - read_unlock_bh(&table->tb6_lock); - - return rt; -}; + icmph = icmp6_hdr(skb); + target = (const struct in6_addr *) (icmph + 1); + dest = target + 1; -static struct rt6_info *ip6_route_redirect(const struct in6_addr *dest, - const struct in6_addr *src, - const struct in6_addr *gateway, - struct net_device *dev) -{ - int flags = RT6_LOOKUP_F_HAS_SADDR; - struct net *net = dev_net(dev); - struct ip6rd_flowi rdfl = { - .fl6 = { - .flowi6_oif = dev->ifindex, - .daddr = *dest, - .saddr = *src, - }, - }; + if (ipv6_addr_is_multicast(dest)) { + net_dbg_ratelimited("rt6_do_redirect: destination address is multicast\n"); + return; + } - rdfl.gateway = *gateway; + on_link = 0; + if (ipv6_addr_equal(dest, target)) { + on_link = 1; + } else if (ipv6_addr_type(target) != + (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { + net_dbg_ratelimited("rt6_do_redirect: target address is not link-local unicast\n"); + return; + } - if (rt6_need_strict(dest)) - flags |= RT6_LOOKUP_F_IFACE; + in6_dev = __in6_dev_get(skb->dev); + if (!in6_dev) + return; + if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_redirects) + return; - return (struct rt6_info *)fib6_rule_lookup(net, &rdfl.fl6, - flags, __ip6_route_redirect); -} + /* RFC2461 8.1: + * The IP source address of the Redirect MUST be the same as the current + * first-hop router for the specified ICMP Destination Address. + */ -void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, - const struct in6_addr *saddr, - struct neighbour *neigh, u8 *lladdr, int on_link) -{ - struct rt6_info *rt, *nrt = NULL; - struct netevent_redirect netevent; - struct net *net = dev_net(neigh->dev); + if (!ndisc_parse_options((u8*)(dest + 1), optlen, &ndopts)) { + net_dbg_ratelimited("rt6_redirect: invalid ND options\n"); + return; + } - rt = ip6_route_redirect(dest, src, saddr, neigh->dev); + lladdr = NULL; + if (ndopts.nd_opts_tgt_lladdr) { + lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, + skb->dev); + if (!lladdr) { + net_dbg_ratelimited("rt6_redirect: invalid link-layer address length\n"); + return; + } + } + rt = (struct rt6_info *) dst; if (rt == net->ipv6.ip6_null_entry) { net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n"); - goto out; + return; } + /* Redirect received -> path was valid. + * Look, redirects are sent only in response to data packets, + * so that this nexthop apparently is reachable. --ANK + */ + dst_confirm(&rt->dst); + + neigh = __neigh_lookup(&nd_tbl, target, skb->dev, 1); + if (!neigh) + return; + + /* Duplicate redirect: silently ignore. */ + old_neigh = rt->n; + if (neigh == old_neigh) + goto out; + /* * We have finally decided to accept it. */ @@ -1658,17 +1743,6 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, NEIGH_UPDATE_F_ISROUTER)) ); - /* - * Redirect received -> path was valid. - * Look, redirects are sent only in response to data packets, - * so that this nexthop apparently is reachable. --ANK - */ - dst_confirm(&rt->dst); - - /* Duplicate redirect: silently ignore. */ - if (neigh == dst_get_neighbour_noref_raw(&rt->dst)) - goto out; - nrt = ip6_rt_copy(rt, dest); if (!nrt) goto out; @@ -1678,132 +1752,25 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, nrt->rt6i_flags &= ~RTF_GATEWAY; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; - dst_set_neighbour(&nrt->dst, neigh_clone(neigh)); + nrt->n = neigh_clone(neigh); if (ip6_ins_rt(nrt)) goto out; netevent.old = &rt->dst; + netevent.old_neigh = old_neigh; netevent.new = &nrt->dst; + netevent.new_neigh = neigh; + netevent.daddr = dest; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); if (rt->rt6i_flags & RTF_CACHE) { + rt = (struct rt6_info *) dst_clone(&rt->dst); ip6_del_rt(rt); - return; } out: - dst_release(&rt->dst); -} - -/* - * Handle ICMP "packet too big" messages - * i.e. Path MTU discovery - */ - -static void rt6_do_pmtu_disc(const struct in6_addr *daddr, const struct in6_addr *saddr, - struct net *net, u32 pmtu, int ifindex) -{ - struct rt6_info *rt, *nrt; - int allfrag = 0; -again: - rt = rt6_lookup(net, daddr, saddr, ifindex, 0); - if (!rt) - return; - - if (rt6_check_expired(rt)) { - ip6_del_rt(rt); - goto again; - } - - if (pmtu >= dst_mtu(&rt->dst)) - goto out; - - if (pmtu < IPV6_MIN_MTU) { - /* - * According to RFC2460, PMTU is set to the IPv6 Minimum Link - * MTU (1280) and a fragment header should always be included - * after a node receiving Too Big message reporting PMTU is - * less than the IPv6 Minimum Link MTU. - */ - pmtu = IPV6_MIN_MTU; - allfrag = 1; - } - - /* New mtu received -> path was valid. - They are sent only in response to data packets, - so that this nexthop apparently is reachable. --ANK - */ - dst_confirm(&rt->dst); - - /* Host route. If it is static, it would be better - not to override it, but add new one, so that - when cache entry will expire old pmtu - would return automatically. - */ - if (rt->rt6i_flags & RTF_CACHE) { - dst_metric_set(&rt->dst, RTAX_MTU, pmtu); - if (allfrag) { - u32 features = dst_metric(&rt->dst, RTAX_FEATURES); - features |= RTAX_FEATURE_ALLFRAG; - dst_metric_set(&rt->dst, RTAX_FEATURES, features); - } - rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires); - rt->rt6i_flags |= RTF_MODIFIED; - goto out; - } - - /* Network route. - Two cases are possible: - 1. It is connected route. Action: COW - 2. It is gatewayed route or NONEXTHOP route. Action: clone it. - */ - if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) - nrt = rt6_alloc_cow(rt, daddr, saddr); - else - nrt = rt6_alloc_clone(rt, daddr); - - if (nrt) { - dst_metric_set(&nrt->dst, RTAX_MTU, pmtu); - if (allfrag) { - u32 features = dst_metric(&nrt->dst, RTAX_FEATURES); - features |= RTAX_FEATURE_ALLFRAG; - dst_metric_set(&nrt->dst, RTAX_FEATURES, features); - } - - /* According to RFC 1981, detecting PMTU increase shouldn't be - * happened within 5 mins, the recommended timer is 10 mins. - * Here this route expiration time is set to ip6_rt_mtu_expires - * which is 10 mins. After 10 mins the decreased pmtu is expired - * and detecting PMTU increase will be automatically happened. - */ - rt6_update_expires(nrt, net->ipv6.sysctl.ip6_rt_mtu_expires); - nrt->rt6i_flags |= RTF_DYNAMIC; - ip6_ins_rt(nrt); - } -out: - dst_release(&rt->dst); -} - -void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *saddr, - struct net_device *dev, u32 pmtu) -{ - struct net *net = dev_net(dev); - - /* - * RFC 1981 states that a node "MUST reduce the size of the packets it - * is sending along the path" that caused the Packet Too Big message. - * Since it's not possible in the general case to determine which - * interface was used to send the original packet, we update the MTU - * on the interface that will be used to send future packets. We also - * update the MTU on the interface that received the Packet Too Big in - * case the original packet was forced out that interface with - * SO_BINDTODEVICE or similar. This is the next best thing to the - * correct behaviour, which would be to update the MTU on all - * interfaces. - */ - rt6_do_pmtu_disc(daddr, saddr, net, pmtu, 0); - rt6_do_pmtu_disc(daddr, saddr, net, pmtu, dev->ifindex); + neigh_release(neigh); } /* @@ -1814,8 +1781,8 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, const struct in6_addr *dest) { struct net *net = dev_net(ort->dst.dev); - struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, - ort->dst.dev, 0); + struct rt6_info *rt = ip6_dst_alloc(net, ort->dst.dev, 0, + ort->rt6i_table); if (rt) { rt->dst.input = ort->dst.input; @@ -2099,8 +2066,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, bool anycast) { struct net *net = dev_net(idev->dev); - struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, - net->loopback_dev, 0); + struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL); int err; if (!rt) { @@ -2396,13 +2362,11 @@ static int rt6_fill_node(struct net *net, int iif, int type, u32 pid, u32 seq, int prefix, int nowait, unsigned int flags) { - const struct inet_peer *peer; struct rtmsg *rtm; struct nlmsghdr *nlh; long expires; u32 table; struct neighbour *n; - u32 ts, tsage; if (prefix) { /* user wants prefix routes only */ if (!(rt->rt6i_flags & RTF_PREFIX_RT)) { @@ -2440,10 +2404,12 @@ static int rt6_fill_node(struct net *net, rtm->rtm_protocol = rt->rt6i_protocol; if (rt->rt6i_flags & RTF_DYNAMIC) rtm->rtm_protocol = RTPROT_REDIRECT; - else if (rt->rt6i_flags & RTF_ADDRCONF) - rtm->rtm_protocol = RTPROT_KERNEL; - else if (rt->rt6i_flags & RTF_DEFAULT) - rtm->rtm_protocol = RTPROT_RA; + else if (rt->rt6i_flags & RTF_ADDRCONF) { + if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ROUTEINFO)) + rtm->rtm_protocol = RTPROT_RA; + else + rtm->rtm_protocol = RTPROT_KERNEL; + } if (rt->rt6i_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; @@ -2500,7 +2466,7 @@ static int rt6_fill_node(struct net *net, goto nla_put_failure; rcu_read_lock(); - n = dst_get_neighbour_noref(&rt->dst); + n = rt->n; if (n) { if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0) { rcu_read_unlock(); @@ -2514,22 +2480,10 @@ static int rt6_fill_node(struct net *net, goto nla_put_failure; if (nla_put_u32(skb, RTA_PRIORITY, rt->rt6i_metric)) goto nla_put_failure; - if (!(rt->rt6i_flags & RTF_EXPIRES)) - expires = 0; - else if (rt->dst.expires - jiffies < INT_MAX) - expires = rt->dst.expires - jiffies; - else - expires = INT_MAX; - peer = rt->rt6i_peer; - ts = tsage = 0; - if (peer && peer->tcp_ts_stamp) { - ts = peer->tcp_ts; - tsage = get_seconds() - peer->tcp_ts_stamp; - } + expires = (rt->rt6i_flags & RTF_EXPIRES) ? rt->dst.expires - jiffies : 0; - if (rtnl_put_cacheinfo(skb, &rt->dst, 0, ts, tsage, - expires, rt->dst.error) < 0) + if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0) goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -2722,7 +2676,7 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg) seq_puts(m, "00000000000000000000000000000000 00 "); #endif rcu_read_lock(); - n = dst_get_neighbour_noref(&rt->dst); + n = rt->n; if (n) { seq_printf(m, "%pi6", n->primary_key); } else { @@ -3007,6 +2961,31 @@ static struct pernet_operations ip6_route_net_ops = { .exit = ip6_route_net_exit, }; +static int __net_init ipv6_inetpeer_init(struct net *net) +{ + struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL); + + if (!bp) + return -ENOMEM; + inet_peer_base_init(bp); + net->ipv6.peers = bp; + return 0; +} + +static void __net_exit ipv6_inetpeer_exit(struct net *net) +{ + struct inet_peer_base *bp = net->ipv6.peers; + + net->ipv6.peers = NULL; + inetpeer_invalidate_tree(bp); + kfree(bp); +} + +static struct pernet_operations ipv6_inetpeer_ops = { + .init = ipv6_inetpeer_init, + .exit = ipv6_inetpeer_exit, +}; + static struct pernet_operations ip6_route_net_late_ops = { .init = ip6_route_net_init_late, .exit = ip6_route_net_exit_late, @@ -3032,10 +3011,14 @@ int __init ip6_route_init(void) if (ret) goto out_kmem_cache; - ret = register_pernet_subsys(&ip6_route_net_ops); + ret = register_pernet_subsys(&ipv6_inetpeer_ops); if (ret) goto out_dst_entries; + ret = register_pernet_subsys(&ip6_route_net_ops); + if (ret) + goto out_register_inetpeer; + ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep; /* Registering of the loopback is done before this portion of code, @@ -3088,6 +3071,8 @@ out_fib6_init: fib6_gc_cleanup(); out_register_subsys: unregister_pernet_subsys(&ip6_route_net_ops); +out_register_inetpeer: + unregister_pernet_subsys(&ipv6_inetpeer_ops); out_dst_entries: dst_entries_destroy(&ip6_dst_blackhole_ops); out_kmem_cache: @@ -3102,6 +3087,7 @@ void ip6_route_cleanup(void) fib6_rules_cleanup(); xfrm6_fini(); fib6_gc_cleanup(); + unregister_pernet_subsys(&ipv6_inetpeer_ops); unregister_pernet_subsys(&ip6_route_net_ops); dst_entries_destroy(&ip6_dst_blackhole_ops); kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 60415711563..3bd1bfc01f8 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -527,9 +527,6 @@ static int ipip6_err(struct sk_buff *skb, u32 info) case ICMP_PORT_UNREACH: /* Impossible event. */ return 0; - case ICMP_FRAG_NEEDED: - /* Soft state for pmtu is maintained by IP core. */ - return 0; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, @@ -542,6 +539,8 @@ static int ipip6_err(struct sk_buff *skb, u32 info) if (code != ICMP_EXC_TTL) return 0; break; + case ICMP_REDIRECT: + break; } err = -ENOENT; @@ -551,7 +550,23 @@ static int ipip6_err(struct sk_buff *skb, u32 info) skb->dev, iph->daddr, iph->saddr); - if (t == NULL || t->parms.iph.daddr == 0) + if (t == NULL) + goto out; + + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { + ipv4_update_pmtu(skb, dev_net(skb->dev), info, + t->dev->ifindex, 0, IPPROTO_IPV6, 0); + err = 0; + goto out; + } + if (type == ICMP_REDIRECT) { + ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0, + IPPROTO_IPV6, 0); + err = 0; + goto out; + } + + if (t->parms.iph.daddr == 0) goto out; err = 0; @@ -792,7 +807,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } if (tunnel->parms.iph.daddr && skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (skb->len > mtu) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 8e951d8d3b8..bb46061c813 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -21,9 +21,6 @@ #include <net/ipv6.h> #include <net/tcp.h> -extern int sysctl_tcp_syncookies; -extern __u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS]; - #define COOKIEBITS 24 /* Upper bits store count */ #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1) @@ -180,7 +177,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, &hash_location, 0); + tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL); if (!cookie_check_timestamp(&tcp_opt, &ecn_ok)) goto out; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 9df64a50b07..a3e60cc04a8 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -94,6 +94,18 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, } #endif +static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + const struct rt6_info *rt = (const struct rt6_info *)dst; + + dst_hold(dst); + sk->sk_rx_dst = dst; + inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; + if (rt->rt6i_node) + inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum; +} + static void tcp_v6_hash(struct sock *sk) { if (sk->sk_state != TCP_CLOSE) { @@ -277,22 +289,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, rt = (struct rt6_info *) dst; if (tcp_death_row.sysctl_tw_recycle && !tp->rx_opt.ts_recent_stamp && - ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr)) { - struct inet_peer *peer = rt6_get_peer(rt); - /* - * VJ's idea. We save last timestamp seen from - * the destination in peer table, when entering state - * TIME-WAIT * and initialize rx_opt.ts_recent from it, - * when trying new connection. - */ - if (peer) { - inet_peer_refcheck(peer); - if ((u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) { - tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp; - tp->rx_opt.ts_recent = peer->tcp_ts; - } - } - } + ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr)) + tcp_fetch_timewait_stamp(sk, dst); icsk->icsk_ext_hdr_len = 0; if (np->opt) @@ -329,6 +327,23 @@ failure: return err; } +static void tcp_v6_mtu_reduced(struct sock *sk) +{ + struct dst_entry *dst; + + if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) + return; + + dst = inet6_csk_update_pmtu(sk, tcp_sk(sk)->mtu_info); + if (!dst) + return; + + if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { + tcp_sync_mss(sk, dst_mtu(dst)); + tcp_simple_retransmit(sk); + } +} + static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { @@ -356,7 +371,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } bh_lock_sock(sk); - if (sock_owned_by_user(sk)) + if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == TCP_CLOSE) @@ -377,49 +392,19 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); - if (type == ICMPV6_PKT_TOOBIG) { - struct dst_entry *dst; + if (type == NDISC_REDIRECT) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); - if (sock_owned_by_user(sk)) - goto out; - if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) - goto out; - - /* icmp should have updated the destination cache entry */ - dst = __sk_dst_check(sk, np->dst_cookie); - - if (dst == NULL) { - struct inet_sock *inet = inet_sk(sk); - struct flowi6 fl6; - - /* BUGGG_FUTURE: Again, it is not clear how - to handle rthdr case. Ignore this complexity - for now. - */ - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_TCP; - fl6.daddr = np->daddr; - fl6.saddr = np->saddr; - fl6.flowi6_oif = sk->sk_bound_dev_if; - fl6.flowi6_mark = sk->sk_mark; - fl6.fl6_dport = inet->inet_dport; - fl6.fl6_sport = inet->inet_sport; - security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); - - dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false); - if (IS_ERR(dst)) { - sk->sk_err_soft = -PTR_ERR(dst); - goto out; - } - - } else - dst_hold(dst); + if (dst) + dst->ops->redirect(dst, sk, skb); + } - if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { - tcp_sync_mss(sk, dst_mtu(dst)); - tcp_simple_retransmit(sk); - } /* else let the usual retransmit timer handle it */ - dst_release(dst); + if (type == ICMPV6_PKT_TOOBIG) { + tp->mtu_info = ntohl(info); + if (!sock_owned_by_user(sk)) + tcp_v6_mtu_reduced(sk); + else + set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags); goto out; } @@ -475,62 +460,43 @@ out: } -static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, +static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, + struct flowi6 *fl6, + struct request_sock *req, struct request_values *rvp, u16 queue_mapping) { struct inet6_request_sock *treq = inet6_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff * skb; - struct ipv6_txoptions *opt = NULL; - struct in6_addr * final_p, final; - struct flowi6 fl6; - struct dst_entry *dst; - int err; - - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_TCP; - fl6.daddr = treq->rmt_addr; - fl6.saddr = treq->loc_addr; - fl6.flowlabel = 0; - fl6.flowi6_oif = treq->iif; - fl6.flowi6_mark = sk->sk_mark; - fl6.fl6_dport = inet_rsk(req)->rmt_port; - fl6.fl6_sport = inet_rsk(req)->loc_port; - security_req_classify_flow(req, flowi6_to_flowi(&fl6)); - - opt = np->opt; - final_p = fl6_update_dst(&fl6, opt, &final); + int err = -ENOMEM; - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); - if (IS_ERR(dst)) { - err = PTR_ERR(dst); - dst = NULL; + /* First, grab a route. */ + if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL) goto done; - } + skb = tcp_make_synack(sk, dst, req, rvp); - err = -ENOMEM; + if (skb) { __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); - fl6.daddr = treq->rmt_addr; + fl6->daddr = treq->rmt_addr; skb_set_queue_mapping(skb, queue_mapping); - err = ip6_xmit(sk, skb, &fl6, opt, np->tclass); + err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass); err = net_xmit_eval(err); } done: - if (opt && opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); - dst_release(dst); return err; } static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req, struct request_values *rvp) { + struct flowi6 fl6; + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - return tcp_v6_send_synack(sk, req, rvp, 0); + return tcp_v6_send_synack(sk, NULL, &fl6, req, rvp, 0); } static void tcp_v6_reqsk_destructor(struct request_sock *req) @@ -1057,6 +1023,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); __u32 isn = TCP_SKB_CB(skb)->when; struct dst_entry *dst = NULL; + struct flowi6 fl6; bool want_cookie = false; if (skb->protocol == htons(ETH_P_IP)) @@ -1085,7 +1052,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, &hash_location, 0); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL); if (tmp_opt.cookie_plus > 0 && tmp_opt.saw_tstamp && @@ -1150,8 +1117,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) treq->iif = inet6_iif(skb); if (!isn) { - struct inet_peer *peer = NULL; - if (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { @@ -1176,14 +1141,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) */ if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle && - (dst = inet6_csk_route_req(sk, req)) != NULL && - (peer = rt6_get_peer((struct rt6_info *)dst)) != NULL && - ipv6_addr_equal((struct in6_addr *)peer->daddr.addr.a6, - &treq->rmt_addr)) { - inet_peer_refcheck(peer); - if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL && - (s32)(peer->tcp_ts - req->ts_recent) > - TCP_PAWS_WINDOW) { + (dst = inet6_csk_route_req(sk, &fl6, req)) != NULL) { + if (!tcp_peer_is_proven(req, dst, true)) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); goto drop_and_release; } @@ -1192,8 +1151,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) else if (!sysctl_tcp_syncookies && (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < (sysctl_max_syn_backlog >> 2)) && - (!peer || !peer->tcp_ts_stamp) && - (!dst || !dst_metric(dst, RTAX_RTT))) { + !tcp_peer_is_proven(req, dst, false)) { /* Without syncookies last quarter of * backlog is filled with destinations, * proven to be alive. @@ -1215,7 +1173,7 @@ have_isn: if (security_inet_conn_request(sk, skb, req)) goto drop_and_release; - if (tcp_v6_send_synack(sk, req, + if (tcp_v6_send_synack(sk, dst, &fl6, req, (struct request_values *)&tmp_ext, skb_get_queue_mapping(skb)) || want_cookie) @@ -1242,10 +1200,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; - struct ipv6_txoptions *opt; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key; #endif + struct flowi6 fl6; if (skb->protocol == htons(ETH_P_IP)) { /* @@ -1302,13 +1260,12 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } treq = inet6_rsk(req); - opt = np->opt; if (sk_acceptq_is_full(sk)) goto out_overflow; if (!dst) { - dst = inet6_csk_route_req(sk, req); + dst = inet6_csk_route_req(sk, &fl6, req); if (!dst) goto out; } @@ -1325,6 +1282,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newsk->sk_gso_type = SKB_GSO_TCPV6; __ip6_dst_store(newsk, dst, NULL, NULL); + inet6_sk_rx_dst_set(newsk, skb); newtcp6sk = (struct tcp6_sock *)newsk; inet_sk(newsk)->pinet6 = &newtcp6sk->inet6; @@ -1354,7 +1312,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, /* Clone pktoptions received with SYN */ newnp->pktoptions = NULL; if (treq->pktopts != NULL) { - newnp->pktoptions = skb_clone(treq->pktopts, GFP_ATOMIC); + newnp->pktoptions = skb_clone(treq->pktopts, + sk_gfp_atomic(sk, GFP_ATOMIC)); consume_skb(treq->pktopts); treq->pktopts = NULL; if (newnp->pktoptions) @@ -1371,11 +1330,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, but we make one more one thing there: reattach optmem to newsk. */ - if (opt) { - newnp->opt = ipv6_dup_options(newsk, opt); - if (opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); - } + if (np->opt) + newnp->opt = ipv6_dup_options(newsk, np->opt); inet_csk(newsk)->icsk_ext_hdr_len = 0; if (newnp->opt) @@ -1407,7 +1363,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, * across. Shucks. */ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newnp->daddr, - AF_INET6, key->key, key->keylen, GFP_ATOMIC); + AF_INET6, key->key, key->keylen, + sk_gfp_atomic(sk, GFP_ATOMIC)); } #endif @@ -1422,8 +1379,6 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, out_overflow: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); out_nonewsk: - if (opt && opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); dst_release(dst); out: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); @@ -1502,10 +1457,20 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, GFP_ATOMIC); + opt_skb = skb_clone(skb, sk_gfp_atomic(sk, GFP_ATOMIC)); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ + struct dst_entry *dst = sk->sk_rx_dst; + sock_rps_save_rxhash(sk, skb); + if (dst) { + if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || + dst->ops->check(dst, np->rx_dst_cookie) == NULL) { + dst_release(dst); + sk->sk_rx_dst = NULL; + } + } + if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) goto reset; if (opt_skb) @@ -1734,51 +1699,56 @@ do_time_wait: goto discard_it; } -static struct inet_peer *tcp_v6_get_peer(struct sock *sk, bool *release_it) +static void tcp_v6_early_demux(struct sk_buff *skb) { - struct rt6_info *rt = (struct rt6_info *) __sk_dst_get(sk); - struct ipv6_pinfo *np = inet6_sk(sk); - struct inet_peer *peer; + const struct ipv6hdr *hdr; + const struct tcphdr *th; + struct sock *sk; - if (!rt || - !ipv6_addr_equal(&np->daddr, &rt->rt6i_dst.addr)) { - peer = inet_getpeer_v6(&np->daddr, 1); - *release_it = true; - } else { - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); - peer = rt->rt6i_peer; - *release_it = false; - } + if (skb->pkt_type != PACKET_HOST) + return; - return peer; -} + if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) + return; -static void *tcp_v6_tw_get_peer(struct sock *sk) -{ - const struct inet6_timewait_sock *tw6 = inet6_twsk(sk); - const struct inet_timewait_sock *tw = inet_twsk(sk); + hdr = ipv6_hdr(skb); + th = tcp_hdr(skb); - if (tw->tw_family == AF_INET) - return tcp_v4_tw_get_peer(sk); + if (th->doff < sizeof(struct tcphdr) / 4) + return; - return inet_getpeer_v6(&tw6->tw_v6_daddr, 1); + sk = __inet6_lookup_established(dev_net(skb->dev), &tcp_hashinfo, + &hdr->saddr, th->source, + &hdr->daddr, ntohs(th->dest), + inet6_iif(skb)); + if (sk) { + skb->sk = sk; + skb->destructor = sock_edemux; + if (sk->sk_state != TCP_TIME_WAIT) { + struct dst_entry *dst = sk->sk_rx_dst; + struct inet_sock *icsk = inet_sk(sk); + if (dst) + dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); + if (dst && + icsk->rx_dst_ifindex == skb->skb_iif) + skb_dst_set_noref(skb, dst); + } + } } static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp6_timewait_sock), .twsk_unique = tcp_twsk_unique, .twsk_destructor= tcp_twsk_destructor, - .twsk_getpeer = tcp_v6_tw_get_peer, }; static const struct inet_connection_sock_af_ops ipv6_specific = { .queue_xmit = inet6_csk_xmit, .send_check = tcp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, + .sk_rx_dst_set = inet6_sk_rx_dst_set, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, - .get_peer = tcp_v6_get_peer, .net_header_len = sizeof(struct ipv6hdr), .net_frag_header_len = sizeof(struct frag_hdr), .setsockopt = ipv6_setsockopt, @@ -1808,9 +1778,9 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, + .sk_rx_dst_set = inet_sk_rx_dst_set, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, - .get_peer = tcp_v4_get_peer, .net_header_len = sizeof(struct iphdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, @@ -2049,6 +2019,8 @@ struct proto tcpv6_prot = { .sendmsg = tcp_sendmsg, .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, + .release_cb = tcp_release_cb, + .mtu_reduced = tcp_v6_mtu_reduced, .hash = tcp_v6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, @@ -2070,12 +2042,13 @@ struct proto tcpv6_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM .proto_cgroup = tcp_proto_cgroup, #endif }; static const struct inet6_protocol tcpv6_protocol = { + .early_demux = tcp_v6_early_demux, .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, .gso_send_check = tcp_v6_gso_send_check, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index f05099fc590..99d0077b56b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -48,6 +48,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <trace/events/skb.h> #include "udp_impl.h" int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) @@ -385,15 +386,16 @@ try_again: if (skb_csum_unnecessary(skb)) err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov, copied ); + msg->msg_iov, copied); else { err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); if (err == -EINVAL) goto csum_copy_err; } - if (err) + if (unlikely(err)) { + trace_kfree_skb(skb, udpv6_recvmsg); goto out_free; - + } if (!peeked) { if (is_udp4) UDP_INC_STATS_USER(sock_net(sk), @@ -479,6 +481,11 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (sk == NULL) return; + if (type == ICMPV6_PKT_TOOBIG) + ip6_sk_update_pmtu(skb, sk, info); + if (type == NDISC_REDIRECT) + ip6_sk_redirect(skb, sk); + np = inet6_sk(sk); if (!icmpv6_err_convert(type, code, &err) && !np->recverr) diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 8625fba96db..f8c4c08ffb6 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -73,6 +73,13 @@ static int xfrm6_get_tos(const struct flowi *fl) return 0; } +static void xfrm6_init_dst(struct net *net, struct xfrm_dst *xdst) +{ + struct rt6_info *rt = (struct rt6_info *)xdst; + + rt6_init_peer(rt, net->ipv6.peers); +} + static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len) { @@ -99,12 +106,11 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, if (!xdst->u.rt6.rt6i_idev) return -ENODEV; - xdst->u.rt6.rt6i_peer = rt->rt6i_peer; - if (rt->rt6i_peer) - atomic_inc(&rt->rt6i_peer->refcnt); + rt6_transfer_peer(&xdst->u.rt6, rt); /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ + xdst->u.rt6.n = neigh_clone(rt->n); xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST | RTF_LOCAL); xdst->u.rt6.rt6i_metric = rt->rt6i_metric; @@ -208,12 +214,22 @@ static inline int xfrm6_garbage_collect(struct dst_ops *ops) return dst_entries_get_fast(ops) > ops->gc_thresh * 2; } -static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu) +static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, mtu); + path->ops->update_pmtu(path, sk, skb, mtu); +} + +static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) +{ + struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + struct dst_entry *path = xdst->route; + + path->ops->redirect(path, sk, skb); } static void xfrm6_dst_destroy(struct dst_entry *dst) @@ -223,8 +239,10 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); - if (likely(xdst->u.rt6.rt6i_peer)) - inet_putpeer(xdst->u.rt6.rt6i_peer); + if (rt6_has_peer(&xdst->u.rt6)) { + struct inet_peer *peer = rt6_peer_ptr(&xdst->u.rt6); + inet_putpeer(peer); + } xfrm_dst_destroy(xdst); } @@ -260,6 +278,7 @@ static struct dst_ops xfrm6_dst_ops = { .protocol = cpu_to_be16(ETH_P_IPV6), .gc = xfrm6_garbage_collect, .update_pmtu = xfrm6_update_pmtu, + .redirect = xfrm6_redirect, .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm6_dst_destroy, .ifdown = xfrm6_dst_ifdown, @@ -274,6 +293,7 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { .get_saddr = xfrm6_get_saddr, .decode_session = _decode_session6, .get_tos = xfrm6_get_tos, + .init_dst = xfrm6_init_dst, .init_path = xfrm6_init_path, .fill_dst = xfrm6_fill_dst, .blackhole_route = ip6_blackhole_route, diff --git a/net/ipx/Makefile b/net/ipx/Makefile index 4b95e3ea0f8..440fafa9fd0 100644 --- a/net/ipx/Makefile +++ b/net/ipx/Makefile @@ -4,5 +4,5 @@ obj-$(CONFIG_IPX) += ipx.o -ipx-y := af_ipx.o ipx_route.o ipx_proc.o +ipx-y := af_ipx.o ipx_route.o ipx_proc.o pe2.o ipx-$(CONFIG_SYSCTL) += sysctl_net_ipx.o diff --git a/net/ethernet/pe2.c b/net/ipx/pe2.c index 85d574addbc..32dcd601ab3 100644 --- a/net/ethernet/pe2.c +++ b/net/ipx/pe2.c @@ -28,10 +28,8 @@ struct datalink_proto *make_EII_client(void) return proto; } -EXPORT_SYMBOL(make_EII_client); void destroy_EII_client(struct datalink_proto *dl) { kfree(dl); } -EXPORT_SYMBOL(destroy_EII_client); diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index bb14c347768..bb738c9f914 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -955,7 +955,7 @@ out: * The main difference with a "standard" connect is that with IrDA we need * to resolve the service name into a TSAP selector (in TCP, port number * doesn't have to be resolved). - * Because of this service name resoltion, we can offer "auto-connect", + * Because of this service name resolution, we can offer "auto-connect", * where we connect to a service without specifying a destination address. * * Note : by consulting "errno", the user space caller may learn the cause diff --git a/net/irda/irlan/irlan_provider.c b/net/irda/irlan/irlan_provider.c index 32dcaac70b0..4664855222f 100644 --- a/net/irda/irlan/irlan_provider.c +++ b/net/irda/irlan/irlan_provider.c @@ -296,7 +296,7 @@ void irlan_provider_send_reply(struct irlan_cb *self, int command, skb = alloc_skb(IRLAN_MAX_HEADER + IRLAN_CMD_HEADER + /* Bigger param length comes from CMD_GET_MEDIA_CHAR */ IRLAN_STRING_PARAMETER_LEN("FILTER_TYPE", "DIRECTED") + - IRLAN_STRING_PARAMETER_LEN("FILTER_TYPE", "BORADCAST") + + IRLAN_STRING_PARAMETER_LEN("FILTER_TYPE", "BROADCAST") + IRLAN_STRING_PARAMETER_LEN("FILTER_TYPE", "MULTICAST") + IRLAN_STRING_PARAMETER_LEN("ACCESS_TYPE", "HOSTED"), GFP_ATOMIC); diff --git a/net/irda/irqueue.c b/net/irda/irqueue.c index f06947c4fa8..7152624ed5f 100644 --- a/net/irda/irqueue.c +++ b/net/irda/irqueue.c @@ -523,7 +523,7 @@ void *hashbin_remove_first( hashbin_t *hashbin) * Dequeue the entry... */ dequeue_general( (irda_queue_t**) &hashbin->hb_queue[ bin ], - (irda_queue_t*) entry ); + entry); hashbin->hb_size--; entry->q_next = NULL; entry->q_prev = NULL; @@ -615,7 +615,7 @@ void* hashbin_remove( hashbin_t* hashbin, long hashv, const char* name) */ if ( found ) { dequeue_general( (irda_queue_t**) &hashbin->hb_queue[ bin ], - (irda_queue_t*) entry ); + entry); hashbin->hb_size--; /* @@ -685,7 +685,7 @@ void* hashbin_remove_this( hashbin_t* hashbin, irda_queue_t* entry) * Dequeue the entry... */ dequeue_general( (irda_queue_t**) &hashbin->hb_queue[ bin ], - (irda_queue_t*) entry ); + entry); hashbin->hb_size--; entry->q_next = NULL; entry->q_prev = NULL; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 32b2155e7ab..513cab08a98 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1128,6 +1128,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len int headroom; int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; int udp_len; + int ret = NET_XMIT_SUCCESS; /* Check that there's enough headroom in the skb to insert IP, * UDP and L2TP headers. If not enough, expand it to @@ -1137,8 +1138,8 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len uhlen + hdr_len; old_headroom = skb_headroom(skb); if (skb_cow_head(skb, headroom)) { - dev_kfree_skb(skb); - goto abort; + kfree_skb(skb); + return NET_XMIT_DROP; } new_headroom = skb_headroom(skb); @@ -1156,7 +1157,8 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len bh_lock_sock(sk); if (sock_owned_by_user(sk)) { - dev_kfree_skb(skb); + kfree_skb(skb); + ret = NET_XMIT_DROP; goto out_unlock; } @@ -1215,8 +1217,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len out_unlock: bh_unlock_sock(sk); -abort: - return 0; + return ret; } EXPORT_SYMBOL_GPL(l2tp_xmit_skb); @@ -1346,11 +1347,10 @@ static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) /* Remove from tunnel list */ spin_lock_bh(&pn->l2tp_tunnel_list_lock); list_del_rcu(&tunnel->list); + kfree_rcu(tunnel, rcu); spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - synchronize_rcu(); atomic_dec(&l2tp_tunnel_count); - kfree(tunnel); } /* Create a socket for the tunnel, if one isn't set up by diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index a38ec6cdeee..56d583e083a 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -163,6 +163,7 @@ struct l2tp_tunnel_cfg { struct l2tp_tunnel { int magic; /* Should be L2TP_TUNNEL_MAGIC */ + struct rcu_head rcu; rwlock_t hlist_lock; /* protect session_hlist */ struct hlist_head session_hlist[L2TP_HASH_SIZE]; /* hashed list of sessions, diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 47b259fccd2..f9ee74deeac 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -44,6 +44,7 @@ struct l2tp_eth { struct list_head list; atomic_long_t tx_bytes; atomic_long_t tx_packets; + atomic_long_t tx_dropped; atomic_long_t rx_bytes; atomic_long_t rx_packets; atomic_long_t rx_errors; @@ -92,12 +93,15 @@ static int l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct l2tp_eth *priv = netdev_priv(dev); struct l2tp_session *session = priv->session; + unsigned int len = skb->len; + int ret = l2tp_xmit_skb(session, skb, session->hdr_len); - atomic_long_add(skb->len, &priv->tx_bytes); - atomic_long_inc(&priv->tx_packets); - - l2tp_xmit_skb(session, skb, session->hdr_len); - + if (likely(ret == NET_XMIT_SUCCESS)) { + atomic_long_add(len, &priv->tx_bytes); + atomic_long_inc(&priv->tx_packets); + } else { + atomic_long_inc(&priv->tx_dropped); + } return NETDEV_TX_OK; } @@ -108,6 +112,7 @@ static struct rtnl_link_stats64 *l2tp_eth_get_stats64(struct net_device *dev, stats->tx_bytes = atomic_long_read(&priv->tx_bytes); stats->tx_packets = atomic_long_read(&priv->tx_packets); + stats->tx_dropped = atomic_long_read(&priv->tx_dropped); stats->rx_bytes = atomic_long_read(&priv->rx_bytes); stats->rx_packets = atomic_long_read(&priv->rx_packets); stats->rx_errors = atomic_long_read(&priv->rx_errors); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 35e1e4bde58..927547171bc 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -410,6 +410,7 @@ static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr, lsa->l2tp_family = AF_INET6; lsa->l2tp_flowinfo = 0; lsa->l2tp_scope_id = 0; + lsa->l2tp_unused = 0; if (peer) { if (!lsk->peer_conn_id) return -ENOTCONN; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index ddc553e7667..d71cd9229a4 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -72,7 +72,7 @@ static int l2tp_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info) void *hdr; int ret = -ENOBUFS; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; goto out; @@ -353,7 +353,7 @@ static int l2tp_nl_cmd_tunnel_get(struct sk_buff *skb, struct genl_info *info) goto out; } - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; goto out; @@ -699,7 +699,7 @@ static int l2tp_nl_cmd_session_get(struct sk_buff *skb, struct genl_info *info) goto out; } - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; goto out; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 8ef6b9416cb..286366ef893 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1522,8 +1522,8 @@ static int pppol2tp_session_getsockopt(struct sock *sk, * handler, according to whether the PPPoX socket is a for a regular session * or the special tunnel type. */ -static int pppol2tp_getsockopt(struct socket *sock, int level, - int optname, char __user *optval, int __user *optlen) +static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct l2tp_session *session; @@ -1535,7 +1535,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, if (level != SOL_PPPOL2TP) return udp_prot.getsockopt(sk, level, optname, optval, optlen); - if (get_user(len, (int __user *) optlen)) + if (get_user(len, optlen)) return -EFAULT; len = min_t(unsigned int, len, sizeof(int)); @@ -1568,7 +1568,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, err = pppol2tp_session_getsockopt(sk, session, optname, &val); err = -EFAULT; - if (put_user(len, (int __user *) optlen)) + if (put_user(len, optlen)) goto end_put_sess; if (copy_to_user((void __user *) optval, &val, len)) diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index fe5453c3e71..c2190005a11 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -969,14 +969,13 @@ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr, struct sockaddr_llc sllc; struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); - int rc = 0; + int rc = -EBADF; memset(&sllc, 0, sizeof(sllc)); lock_sock(sk); if (sock_flag(sk, SOCK_ZAPPED)) goto out; *uaddrlen = sizeof(sllc); - memset(uaddr, 0, *uaddrlen); if (peer) { rc = -ENOTCONN; if (sk->sk_state != TCP_ESTABLISHED) @@ -1024,7 +1023,7 @@ static int llc_ui_ioctl(struct socket *sock, unsigned int cmd, * @sock: Socket to set options on. * @level: Socket level user is requesting operations on. * @optname: Operation name. - * @optval User provided operation data. + * @optval: User provided operation data. * @optlen: Length of optval. * * Set various connection specific parameters. @@ -1206,7 +1205,7 @@ static int __init llc2_init(void) rc = llc_proc_init(); if (rc != 0) { printk(llc_proc_err_msg); - goto out_unregister_llc_proto; + goto out_station; } rc = llc_sysctl_init(); if (rc) { @@ -1226,7 +1225,8 @@ out_sysctl: llc_sysctl_exit(); out_proc: llc_proc_exit(); -out_unregister_llc_proto: +out_station: + llc_station_exit(); proto_unregister(&llc_proto); goto out; } diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index e32cab44ea9..dd3e83328ad 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -42,6 +42,7 @@ static void (*llc_type_handlers[2])(struct llc_sap *sap, void llc_add_pack(int type, void (*handler)(struct llc_sap *sap, struct sk_buff *skb)) { + smp_wmb(); /* ensure initialisation is complete before it's called */ if (type == LLC_DEST_SAP || type == LLC_DEST_CONN) llc_type_handlers[type - 1] = handler; } @@ -50,11 +51,19 @@ void llc_remove_pack(int type) { if (type == LLC_DEST_SAP || type == LLC_DEST_CONN) llc_type_handlers[type - 1] = NULL; + synchronize_net(); } void llc_set_station_handler(void (*handler)(struct sk_buff *skb)) { + /* Ensure initialisation is complete before it's called */ + if (handler) + smp_wmb(); + llc_station_handler = handler; + + if (!handler) + synchronize_net(); } /** @@ -150,6 +159,8 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev, int dest; int (*rcv)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); + void (*sta_handler)(struct sk_buff *skb); + void (*sap_handler)(struct llc_sap *sap, struct sk_buff *skb); if (!net_eq(dev_net(dev), &init_net)) goto drop; @@ -182,7 +193,8 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev, */ rcv = rcu_dereference(sap->rcv_func); dest = llc_pdu_type(skb); - if (unlikely(!dest || !llc_type_handlers[dest - 1])) { + sap_handler = dest ? ACCESS_ONCE(llc_type_handlers[dest - 1]) : NULL; + if (unlikely(!sap_handler)) { if (rcv) rcv(skb, dev, pt, orig_dev); else @@ -193,7 +205,7 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev, if (cskb) rcv(cskb, dev, pt, orig_dev); } - llc_type_handlers[dest - 1](sap, skb); + sap_handler(sap, skb); } llc_sap_put(sap); out: @@ -202,9 +214,10 @@ drop: kfree_skb(skb); goto out; handle_station: - if (!llc_station_handler) + sta_handler = ACCESS_ONCE(llc_station_handler); + if (!sta_handler) goto drop; - llc_station_handler(skb); + sta_handler(skb); goto out; } diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c index cf4aea3ba30..b2f2bac2c2a 100644 --- a/net/llc/llc_station.c +++ b/net/llc/llc_station.c @@ -30,12 +30,12 @@ * * SAP and connection resource manager, one per adapter. * - * @state - state of station - * @xid_r_count - XID response PDU counter - * @mac_sa - MAC source address - * @sap_list - list of related SAPs - * @ev_q - events entering state mach. - * @mac_pdu_q - PDUs ready to send to MAC + * @state: state of station + * @xid_r_count: XID response PDU counter + * @mac_sa: MAC source address + * @sap_list: list of related SAPs + * @ev_q: events entering state mach. + * @mac_pdu_q: PDUs ready to send to MAC */ struct llc_station { u8 state; @@ -268,7 +268,7 @@ static int llc_station_ac_send_null_dsap_xid_c(struct sk_buff *skb) out: return rc; free: - kfree_skb(skb); + kfree_skb(nskb); goto out; } @@ -293,7 +293,7 @@ static int llc_station_ac_send_xid_r(struct sk_buff *skb) out: return rc; free: - kfree_skb(skb); + kfree_skb(nskb); goto out; } @@ -322,7 +322,7 @@ static int llc_station_ac_send_test_r(struct sk_buff *skb) out: return rc; free: - kfree_skb(skb); + kfree_skb(nskb); goto out; } @@ -646,7 +646,7 @@ static void llc_station_service_events(void) } /** - * llc_station_state_process: queue event and try to process queue. + * llc_station_state_process - queue event and try to process queue. * @skb: Address of the event * * Queues an event (on the station event queue) for handling by the @@ -672,7 +672,7 @@ static void llc_station_ack_tmr_cb(unsigned long timeout_data) } } -/* +/** * llc_station_rcv - send received pdu to the station state machine * @skb: received frame. * @@ -687,12 +687,8 @@ static void llc_station_rcv(struct sk_buff *skb) llc_station_state_process(skb); } -int __init llc_station_init(void) +void __init llc_station_init(void) { - int rc = -ENOBUFS; - struct sk_buff *skb; - struct llc_station_state_ev *ev; - skb_queue_head_init(&llc_main_station.mac_pdu_q); skb_queue_head_init(&llc_main_station.ev_q.list); spin_lock_init(&llc_main_station.ev_q.lock); @@ -700,23 +696,12 @@ int __init llc_station_init(void) (unsigned long)&llc_main_station); llc_main_station.ack_timer.expires = jiffies + sysctl_llc_station_ack_timeout; - skb = alloc_skb(0, GFP_ATOMIC); - if (!skb) - goto out; - rc = 0; - llc_set_station_handler(llc_station_rcv); - ev = llc_station_ev(skb); - memset(ev, 0, sizeof(*ev)); llc_main_station.maximum_retry = 1; - llc_main_station.state = LLC_STATION_STATE_DOWN; - ev->type = LLC_STATION_EV_TYPE_SIMPLE; - ev->prim_type = LLC_STATION_EV_ENABLE_WITHOUT_DUP_ADDR_CHECK; - rc = llc_station_next_state(skb); -out: - return rc; + llc_main_station.state = LLC_STATION_STATE_UP; + llc_set_station_handler(llc_station_rcv); } -void __exit llc_station_exit(void) +void llc_station_exit(void) { llc_set_station_handler(NULL); } diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 8d249d70598..63af25458fd 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -107,6 +107,19 @@ config MAC80211_DEBUGFS Say N unless you know you need this. +config MAC80211_MESSAGE_TRACING + bool "Trace all mac80211 debug messages" + depends on MAC80211 + ---help--- + Select this option to have mac80211 register the + mac80211_msg trace subsystem with tracepoints to + collect all debugging messages, independent of + printing them into the kernel log. + + The overhead in this option is that all the messages + need to be present in the binary and formatted at + runtime for tracing. + menuconfig MAC80211_DEBUG_MENU bool "Select mac80211 debugging features" depends on MAC80211 @@ -140,26 +153,35 @@ config MAC80211_VERBOSE_DEBUG Do not select this option. -config MAC80211_HT_DEBUG - bool "Verbose HT debugging" +config MAC80211_MLME_DEBUG + bool "Verbose managed MLME output" depends on MAC80211_DEBUG_MENU ---help--- - This option enables 802.11n High Throughput features - debug tracing output. - - It should not be selected on production systems as some + Selecting this option causes mac80211 to print out + debugging messages for the managed-mode MLME. It + should not be selected on production systems as some of the messages are remotely triggerable. Do not select this option. -config MAC80211_TKIP_DEBUG - bool "Verbose TKIP debugging" +config MAC80211_STA_DEBUG + bool "Verbose station debugging" depends on MAC80211_DEBUG_MENU ---help--- Selecting this option causes mac80211 to print out - very verbose TKIP debugging messages. It should not - be selected on production systems as those messages - are remotely triggerable. + debugging messages for station addition/removal. + + Do not select this option. + +config MAC80211_HT_DEBUG + bool "Verbose HT debugging" + depends on MAC80211_DEBUG_MENU + ---help--- + This option enables 802.11n High Throughput features + debug tracing output. + + It should not be selected on production systems as some + of the messages are remotely triggerable. Do not select this option. @@ -174,7 +196,7 @@ config MAC80211_IBSS_DEBUG Do not select this option. -config MAC80211_VERBOSE_PS_DEBUG +config MAC80211_PS_DEBUG bool "Verbose powersave mode debugging" depends on MAC80211_DEBUG_MENU ---help--- @@ -186,7 +208,7 @@ config MAC80211_VERBOSE_PS_DEBUG Do not select this option. -config MAC80211_VERBOSE_MPL_DEBUG +config MAC80211_MPL_DEBUG bool "Verbose mesh peer link debugging" depends on MAC80211_DEBUG_MENU depends on MAC80211_MESH @@ -199,7 +221,7 @@ config MAC80211_VERBOSE_MPL_DEBUG Do not select this option. -config MAC80211_VERBOSE_MPATH_DEBUG +config MAC80211_MPATH_DEBUG bool "Verbose mesh path debugging" depends on MAC80211_DEBUG_MENU depends on MAC80211_MESH @@ -212,7 +234,7 @@ config MAC80211_VERBOSE_MPATH_DEBUG Do not select this option. -config MAC80211_VERBOSE_MHWMP_DEBUG +config MAC80211_MHWMP_DEBUG bool "Verbose mesh HWMP routing debugging" depends on MAC80211_DEBUG_MENU depends on MAC80211_MESH @@ -225,7 +247,7 @@ config MAC80211_VERBOSE_MHWMP_DEBUG Do not select this option. -config MAC80211_VERBOSE_MESH_SYNC_DEBUG +config MAC80211_MESH_SYNC_DEBUG bool "Verbose mesh mesh synchronization debugging" depends on MAC80211_DEBUG_MENU depends on MAC80211_MESH @@ -236,7 +258,7 @@ config MAC80211_VERBOSE_MESH_SYNC_DEBUG Do not select this option. -config MAC80211_VERBOSE_TDLS_DEBUG +config MAC80211_TDLS_DEBUG bool "Verbose TDLS debugging" depends on MAC80211_DEBUG_MENU ---help--- diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index 3e9d931bba3..a7dd110faaf 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -9,7 +9,6 @@ mac80211-y := \ scan.o offchannel.o \ ht.o agg-tx.o agg-rx.o \ ibss.o \ - work.o \ iface.o \ rate.o \ michael.o \ @@ -25,7 +24,7 @@ mac80211-y := \ wme.o \ event.o \ chan.o \ - driver-trace.o mlme.o + trace.o mlme.o mac80211-$(CONFIG_MAC80211_LEDS) += led.o mac80211-$(CONFIG_MAC80211_DEBUGFS) += \ @@ -43,7 +42,7 @@ mac80211-$(CONFIG_MAC80211_MESH) += \ mac80211-$(CONFIG_PM) += pm.o -CFLAGS_driver-trace.o := -I$(src) +CFLAGS_trace.o := -I$(src) # objects for PID algorithm rc80211_pid-y := rc80211_pid_algo.o @@ -59,4 +58,4 @@ mac80211-$(CONFIG_MAC80211_RC_PID) += $(rc80211_pid-y) mac80211-$(CONFIG_MAC80211_RC_MINSTREL) += $(rc80211_minstrel-y) mac80211-$(CONFIG_MAC80211_RC_MINSTREL_HT) += $(rc80211_minstrel_ht-y) -ccflags-y += -D__CHECK_ENDIAN__ +ccflags-y += -D__CHECK_ENDIAN__ -DDEBUG diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index c649188314c..186d9919b04 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -74,18 +74,17 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, RCU_INIT_POINTER(sta->ampdu_mlme.tid_rx[tid], NULL); -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG + ht_dbg(sta->sdata, "Rx BA session stop requested for %pM tid %u %s reason: %d\n", sta->sta.addr, tid, initiator == WLAN_BACK_RECIPIENT ? "recipient" : "inititator", (int)reason); -#endif /* CONFIG_MAC80211_HT_DEBUG */ if (drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_STOP, &sta->sta, tid, NULL, 0)) - printk(KERN_DEBUG "HW problem - can not stop rx " - "aggregation for tid %d\n", tid); + sdata_info(sta->sdata, + "HW problem - can not stop rx aggregation for tid %d\n", + tid); /* check if this is a self generated aggregation halt */ if (initiator == WLAN_BACK_RECIPIENT && tx) @@ -160,9 +159,8 @@ static void sta_rx_agg_session_timer_expired(unsigned long data) } rcu_read_unlock(); -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "rx session timer expired on tid %d\n", (u16)*ptid); -#endif + ht_dbg(sta->sdata, "rx session timer expired on tid %d\n", (u16)*ptid); + set_bit(*ptid, sta->ampdu_mlme.tid_rx_timer_expired); ieee80211_queue_work(&sta->local->hw, &sta->ampdu_mlme.work); } @@ -249,10 +247,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, status = WLAN_STATUS_REQUEST_DECLINED; if (test_sta_flag(sta, WLAN_STA_BLOCK_BA)) { -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "Suspend in progress. " - "Denying ADDBA request\n"); -#endif + ht_dbg(sta->sdata, "Suspend in progress - Denying ADDBA request\n"); goto end_no_lock; } @@ -264,10 +259,9 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, (!(sta->sta.ht_cap.cap & IEEE80211_HT_CAP_DELAY_BA))) || (buf_size > IEEE80211_MAX_AMPDU_BUF)) { status = WLAN_STATUS_INVALID_QOS_PARAM; -#ifdef CONFIG_MAC80211_HT_DEBUG - net_dbg_ratelimited("AddBA Req with bad params from %pM on tid %u. policy %d, buffer size %d\n", - mgmt->sa, tid, ba_policy, buf_size); -#endif /* CONFIG_MAC80211_HT_DEBUG */ + ht_dbg_ratelimited(sta->sdata, + "AddBA Req with bad params from %pM on tid %u. policy %d, buffer size %d\n", + mgmt->sa, tid, ba_policy, buf_size); goto end_no_lock; } /* determine default buffer size */ @@ -282,10 +276,9 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, mutex_lock(&sta->ampdu_mlme.mtx); if (sta->ampdu_mlme.tid_rx[tid]) { -#ifdef CONFIG_MAC80211_HT_DEBUG - net_dbg_ratelimited("unexpected AddBA Req from %pM on tid %u\n", - mgmt->sa, tid); -#endif /* CONFIG_MAC80211_HT_DEBUG */ + ht_dbg_ratelimited(sta->sdata, + "unexpected AddBA Req from %pM on tid %u\n", + mgmt->sa, tid); /* delete existing Rx BA session on the same tid */ ___ieee80211_stop_rx_ba_session(sta, tid, WLAN_BACK_RECIPIENT, @@ -324,10 +317,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, ret = drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_START, &sta->sta, tid, &start_seq_num, 0); -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "Rx A-MPDU request on tid %d result %d\n", tid, ret); -#endif /* CONFIG_MAC80211_HT_DEBUG */ - + ht_dbg(sta->sdata, "Rx A-MPDU request on tid %d result %d\n", tid, ret); if (ret) { kfree(tid_agg_rx->reorder_buf); kfree(tid_agg_rx->reorder_time); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 7cf07158805..d0deb3edae2 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -135,7 +135,8 @@ void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn) bar->control = cpu_to_le16(bar_control); bar->start_seq_num = cpu_to_le16(ssn); - IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; + IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | + IEEE80211_TX_CTL_REQ_TX_STATUS; ieee80211_tx_skb_tid(sdata, skb, tid); } EXPORT_SYMBOL(ieee80211_send_bar); @@ -184,10 +185,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, spin_unlock_bh(&sta->lock); -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "Tx BA session stop requested for %pM tid %u\n", + ht_dbg(sta->sdata, "Tx BA session stop requested for %pM tid %u\n", sta->sta.addr, tid); -#endif /* CONFIG_MAC80211_HT_DEBUG */ del_timer_sync(&tid_tx->addba_resp_timer); del_timer_sync(&tid_tx->session_timer); @@ -253,17 +252,13 @@ static void sta_addba_resp_timer_expired(unsigned long data) if (!tid_tx || test_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state)) { rcu_read_unlock(); -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "timer expired on tid %d but we are not " - "(or no longer) expecting addBA response there\n", - tid); -#endif + ht_dbg(sta->sdata, + "timer expired on tid %d but we are not (or no longer) expecting addBA response there\n", + tid); return; } -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "addBA response timer expired on tid %d\n", tid); -#endif + ht_dbg(sta->sdata, "addBA response timer expired on tid %d\n", tid); ieee80211_stop_tx_ba_session(&sta->sta, tid); rcu_read_unlock(); @@ -323,8 +318,9 @@ ieee80211_agg_splice_packets(struct ieee80211_sub_if_data *sdata, ieee80211_stop_queue_agg(sdata, tid); - if (WARN(!tid_tx, "TID %d gone but expected when splicing aggregates" - " from the pending queue\n", tid)) + if (WARN(!tid_tx, + "TID %d gone but expected when splicing aggregates from the pending queue\n", + tid)) return; if (!skb_queue_empty(&tid_tx->pending)) { @@ -372,10 +368,8 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) ret = drv_ampdu_action(local, sdata, IEEE80211_AMPDU_TX_START, &sta->sta, tid, &start_seq_num, 0); if (ret) { -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "BA request denied - HW unavailable for" - " tid %d\n", tid); -#endif + ht_dbg(sdata, + "BA request denied - HW unavailable for tid %d\n", tid); spin_lock_bh(&sta->lock); ieee80211_agg_splice_packets(sdata, tid_tx, tid); ieee80211_assign_tid_tx(sta, tid, NULL); @@ -388,9 +382,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) /* activate the timer for the recipient's addBA response */ mod_timer(&tid_tx->addba_resp_timer, jiffies + ADDBA_RESP_INTERVAL); -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "activated addBA response timer on tid %d\n", tid); -#endif + ht_dbg(sdata, "activated addBA response timer on tid %d\n", tid); spin_lock_bh(&sta->lock); sta->ampdu_mlme.last_addba_req_time[tid] = jiffies; @@ -437,9 +429,7 @@ static void sta_tx_agg_session_timer_expired(unsigned long data) rcu_read_unlock(); -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "tx session timer expired on tid %d\n", (u16)*ptid); -#endif + ht_dbg(sta->sdata, "tx session timer expired on tid %d\n", (u16)*ptid); ieee80211_stop_tx_ba_session(&sta->sta, *ptid); } @@ -463,10 +453,8 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, (local->hw.flags & IEEE80211_HW_TX_AMPDU_SETUP_IN_HW)) return -EINVAL; -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "Open BA session requested for %pM tid %u\n", + ht_dbg(sdata, "Open BA session requested for %pM tid %u\n", pubsta->addr, tid); -#endif /* CONFIG_MAC80211_HT_DEBUG */ if (sdata->vif.type != NL80211_IFTYPE_STATION && sdata->vif.type != NL80211_IFTYPE_MESH_POINT && @@ -476,10 +464,8 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, return -EINVAL; if (test_sta_flag(sta, WLAN_STA_BLOCK_BA)) { -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "BA sessions blocked. " - "Denying BA session request\n"); -#endif + ht_dbg(sdata, + "BA sessions blocked - Denying BA session request\n"); return -EINVAL; } @@ -497,10 +483,9 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, */ if (sta->sdata->vif.type == NL80211_IFTYPE_ADHOC && !sta->sta.ht_cap.ht_supported) { -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "BA request denied - IBSS STA %pM" - "does not advertise HT support\n", pubsta->addr); -#endif /* CONFIG_MAC80211_HT_DEBUG */ + ht_dbg(sdata, + "BA request denied - IBSS STA %pM does not advertise HT support\n", + pubsta->addr); return -EINVAL; } @@ -520,12 +505,9 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, if (sta->ampdu_mlme.addba_req_num[tid] > HT_AGG_BURST_RETRIES && time_before(jiffies, sta->ampdu_mlme.last_addba_req_time[tid] + HT_AGG_RETRIES_PERIOD)) { -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "BA request denied - " - "waiting a grace period after %d failed requests " - "on tid %u\n", + ht_dbg(sdata, + "BA request denied - waiting a grace period after %d failed requests on tid %u\n", sta->ampdu_mlme.addba_req_num[tid], tid); -#endif /* CONFIG_MAC80211_HT_DEBUG */ ret = -EBUSY; goto err_unlock_sta; } @@ -533,10 +515,9 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, tid_tx = rcu_dereference_protected_tid_tx(sta, tid); /* check if the TID is not in aggregation flow already */ if (tid_tx || sta->ampdu_mlme.tid_start_tx[tid]) { -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "BA request denied - session is not " - "idle on tid %u\n", tid); -#endif /* CONFIG_MAC80211_HT_DEBUG */ + ht_dbg(sdata, + "BA request denied - session is not idle on tid %u\n", + tid); ret = -EAGAIN; goto err_unlock_sta; } @@ -591,9 +572,7 @@ static void ieee80211_agg_tx_operational(struct ieee80211_local *local, tid_tx = rcu_dereference_protected_tid_tx(sta, tid); -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "Aggregation is on for tid %d\n", tid); -#endif + ht_dbg(sta->sdata, "Aggregation is on for tid %d\n", tid); drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_TX_OPERATIONAL, @@ -627,10 +606,8 @@ void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid) trace_api_start_tx_ba_cb(sdata, ra, tid); if (tid >= STA_TID_NUM) { -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "Bad TID value: tid = %d (>= %d)\n", - tid, STA_TID_NUM); -#endif + ht_dbg(sdata, "Bad TID value: tid = %d (>= %d)\n", + tid, STA_TID_NUM); return; } @@ -638,9 +615,7 @@ void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid) sta = sta_info_get_bss(sdata, ra); if (!sta) { mutex_unlock(&local->sta_mtx); -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "Could not find station: %pM\n", ra); -#endif + ht_dbg(sdata, "Could not find station: %pM\n", ra); return; } @@ -648,9 +623,7 @@ void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid) tid_tx = rcu_dereference_protected_tid_tx(sta, tid); if (WARN_ON(!tid_tx)) { -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "addBA was not requested!\n"); -#endif + ht_dbg(sdata, "addBA was not requested!\n"); goto unlock; } @@ -750,25 +723,18 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid) trace_api_stop_tx_ba_cb(sdata, ra, tid); if (tid >= STA_TID_NUM) { -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "Bad TID value: tid = %d (>= %d)\n", - tid, STA_TID_NUM); -#endif + ht_dbg(sdata, "Bad TID value: tid = %d (>= %d)\n", + tid, STA_TID_NUM); return; } -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "Stopping Tx BA session for %pM tid %d\n", - ra, tid); -#endif /* CONFIG_MAC80211_HT_DEBUG */ + ht_dbg(sdata, "Stopping Tx BA session for %pM tid %d\n", ra, tid); mutex_lock(&local->sta_mtx); sta = sta_info_get_bss(sdata, ra); if (!sta) { -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "Could not find station: %pM\n", ra); -#endif + ht_dbg(sdata, "Could not find station: %pM\n", ra); goto unlock; } @@ -777,9 +743,7 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid) tid_tx = rcu_dereference_protected_tid_tx(sta, tid); if (!tid_tx || !test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "unexpected callback to A-MPDU stop\n"); -#endif + ht_dbg(sdata, "unexpected callback to A-MPDU stop\n"); goto unlock_sta; } @@ -855,17 +819,13 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, goto out; if (mgmt->u.action.u.addba_resp.dialog_token != tid_tx->dialog_token) { -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "wrong addBA response token, tid %d\n", tid); -#endif + ht_dbg(sta->sdata, "wrong addBA response token, tid %d\n", tid); goto out; } del_timer_sync(&tid_tx->addba_resp_timer); -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "switched off addBA timer for tid %d\n", tid); -#endif + ht_dbg(sta->sdata, "switched off addBA timer for tid %d\n", tid); /* * addba_resp_timer may have fired before we got here, and @@ -874,11 +834,9 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, */ if (test_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state) || test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG + ht_dbg(sta->sdata, "got addBA resp for tid %d but we already gave up\n", tid); -#endif goto out; } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 7d5108a867a..d41974aacf5 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -20,31 +20,31 @@ #include "rate.h" #include "mesh.h" -static struct net_device *ieee80211_add_iface(struct wiphy *wiphy, char *name, - enum nl80211_iftype type, - u32 *flags, - struct vif_params *params) +static struct wireless_dev *ieee80211_add_iface(struct wiphy *wiphy, char *name, + enum nl80211_iftype type, + u32 *flags, + struct vif_params *params) { struct ieee80211_local *local = wiphy_priv(wiphy); - struct net_device *dev; + struct wireless_dev *wdev; struct ieee80211_sub_if_data *sdata; int err; - err = ieee80211_if_add(local, name, &dev, type, params); + err = ieee80211_if_add(local, name, &wdev, type, params); if (err) return ERR_PTR(err); if (type == NL80211_IFTYPE_MONITOR && flags) { - sdata = IEEE80211_DEV_TO_SUB_IF(dev); + sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); sdata->u.mntr_flags = *flags; } - return dev; + return wdev; } -static int ieee80211_del_iface(struct wiphy *wiphy, struct net_device *dev) +static int ieee80211_del_iface(struct wiphy *wiphy, struct wireless_dev *wdev) { - ieee80211_if_remove(IEEE80211_DEV_TO_SUB_IF(dev)); + ieee80211_if_remove(IEEE80211_WDEV_TO_SUB_IF(wdev)); return 0; } @@ -353,6 +353,7 @@ void sta_set_rate_info_tx(struct sta_info *sta, static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) { struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ieee80211_local *local = sdata->local; struct timespec uptime; sinfo->generation = sdata->local->sta_generation; @@ -388,7 +389,9 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) if ((sta->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) || (sta->local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC)) { sinfo->filled |= STATION_INFO_SIGNAL | STATION_INFO_SIGNAL_AVG; - sinfo->signal = (s8)sta->last_signal; + if (!local->ops->get_rssi || + drv_get_rssi(local, sdata, &sta->sta, &sinfo->signal)) + sinfo->signal = (s8)sta->last_signal; sinfo->signal_avg = (s8) -ewma_read(&sta->avg_signal); } @@ -517,7 +520,7 @@ static void ieee80211_get_et_stats(struct wiphy *wiphy, * network device. */ - rcu_read_lock(); + mutex_lock(&local->sta_mtx); if (sdata->vif.type == NL80211_IFTYPE_STATION) { sta = sta_info_get_bss(sdata, sdata->u.mgd.bssid); @@ -546,7 +549,7 @@ static void ieee80211_get_et_stats(struct wiphy *wiphy, data[i] = (u8)sinfo.signal_avg; i++; } else { - list_for_each_entry_rcu(sta, &local->sta_list, list) { + list_for_each_entry(sta, &local->sta_list, list) { /* Make sure this station belongs to the proper dev */ if (sta->sdata->dev != dev) continue; @@ -603,7 +606,7 @@ do_survey: else data[i++] = -1LL; - rcu_read_unlock(); + mutex_unlock(&local->sta_mtx); if (WARN_ON(i != STA_STATS_LEN)) return; @@ -629,10 +632,11 @@ static int ieee80211_dump_station(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *mac, struct station_info *sinfo) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; struct sta_info *sta; int ret = -ENOENT; - rcu_read_lock(); + mutex_lock(&local->sta_mtx); sta = sta_info_get_by_idx(sdata, idx); if (sta) { @@ -641,7 +645,7 @@ static int ieee80211_dump_station(struct wiphy *wiphy, struct net_device *dev, sta_set_sinfo(sta, sinfo); } - rcu_read_unlock(); + mutex_unlock(&local->sta_mtx); return ret; } @@ -658,10 +662,11 @@ static int ieee80211_get_station(struct wiphy *wiphy, struct net_device *dev, u8 *mac, struct station_info *sinfo) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; struct sta_info *sta; int ret = -ENOENT; - rcu_read_lock(); + mutex_lock(&local->sta_mtx); sta = sta_info_get_bss(sdata, mac); if (sta) { @@ -669,11 +674,54 @@ static int ieee80211_get_station(struct wiphy *wiphy, struct net_device *dev, sta_set_sinfo(sta, sinfo); } - rcu_read_unlock(); + mutex_unlock(&local->sta_mtx); return ret; } +static int ieee80211_set_channel(struct wiphy *wiphy, + struct net_device *netdev, + struct ieee80211_channel *chan, + enum nl80211_channel_type channel_type) +{ + struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata = NULL; + + if (netdev) + sdata = IEEE80211_DEV_TO_SUB_IF(netdev); + + switch (ieee80211_get_channel_mode(local, NULL)) { + case CHAN_MODE_HOPPING: + return -EBUSY; + case CHAN_MODE_FIXED: + if (local->oper_channel != chan || + (!sdata && local->_oper_channel_type != channel_type)) + return -EBUSY; + if (!sdata && local->_oper_channel_type == channel_type) + return 0; + break; + case CHAN_MODE_UNDEFINED: + break; + } + + if (!ieee80211_set_channel_type(local, sdata, channel_type)) + return -EBUSY; + + local->oper_channel = chan; + + /* auto-detects changes */ + ieee80211_hw_config(local, 0); + + return 0; +} + +static int ieee80211_set_monitor_channel(struct wiphy *wiphy, + struct ieee80211_channel *chan, + enum nl80211_channel_type channel_type) +{ + return ieee80211_set_channel(wiphy, NULL, chan, channel_type); +} + static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, const u8 *resp, size_t resp_len) { @@ -788,6 +836,11 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, if (old) return -EALREADY; + err = ieee80211_set_channel(wiphy, dev, params->channel, + params->channel_type); + if (err) + return err; + /* * Apply control port protocol, this allows us to * not encrypt dynamic WEP control frames. @@ -864,6 +917,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) kfree_rcu(old, rcu_head); + sta_info_flush(sdata->local, sdata); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED); return 0; @@ -1482,7 +1536,7 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy, if (_chg_mesh_attr(NL80211_MESHCONF_TTL, mask)) conf->dot11MeshTTL = nconf->dot11MeshTTL; if (_chg_mesh_attr(NL80211_MESHCONF_ELEMENT_TTL, mask)) - conf->dot11MeshTTL = nconf->element_ttl; + conf->element_ttl = nconf->element_ttl; if (_chg_mesh_attr(NL80211_MESHCONF_AUTO_OPEN_PLINKS, mask)) conf->auto_open_plinks = nconf->auto_open_plinks; if (_chg_mesh_attr(NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR, mask)) @@ -1517,17 +1571,16 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy, * announcements, so require this ifmsh to also be a root node * */ if (nconf->dot11MeshGateAnnouncementProtocol && - !conf->dot11MeshHWMPRootMode) { - conf->dot11MeshHWMPRootMode = 1; + !(conf->dot11MeshHWMPRootMode > IEEE80211_ROOTMODE_ROOT)) { + conf->dot11MeshHWMPRootMode = IEEE80211_PROACTIVE_RANN; ieee80211_mesh_root_setup(ifmsh); } conf->dot11MeshGateAnnouncementProtocol = nconf->dot11MeshGateAnnouncementProtocol; } - if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_RANN_INTERVAL, mask)) { + if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_RANN_INTERVAL, mask)) conf->dot11MeshHWMPRannInterval = nconf->dot11MeshHWMPRannInterval; - } if (_chg_mesh_attr(NL80211_MESHCONF_FORWARDING, mask)) conf->dot11MeshForwarding = nconf->dot11MeshForwarding; if (_chg_mesh_attr(NL80211_MESHCONF_RSSI_THRESHOLD, mask)) { @@ -1543,6 +1596,15 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy, sdata->vif.bss_conf.ht_operation_mode = nconf->ht_opmode; ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_HT); } + if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT, mask)) + conf->dot11MeshHWMPactivePathToRootTimeout = + nconf->dot11MeshHWMPactivePathToRootTimeout; + if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_ROOT_INTERVAL, mask)) + conf->dot11MeshHWMProotInterval = + nconf->dot11MeshHWMProotInterval; + if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL, mask)) + conf->dot11MeshHWMPconfirmationInterval = + nconf->dot11MeshHWMPconfirmationInterval; return 0; } @@ -1558,6 +1620,12 @@ static int ieee80211_join_mesh(struct wiphy *wiphy, struct net_device *dev, err = copy_mesh_setup(ifmsh, setup); if (err) return err; + + err = ieee80211_set_channel(wiphy, dev, setup->channel, + setup->channel_type); + if (err) + return err; + ieee80211_start_mesh(sdata); return 0; @@ -1674,54 +1742,7 @@ static int ieee80211_set_txq_params(struct wiphy *wiphy, return -EINVAL; } - return 0; -} - -static int ieee80211_set_channel(struct wiphy *wiphy, - struct net_device *netdev, - struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type) -{ - struct ieee80211_local *local = wiphy_priv(wiphy); - struct ieee80211_sub_if_data *sdata = NULL; - struct ieee80211_channel *old_oper; - enum nl80211_channel_type old_oper_type; - enum nl80211_channel_type old_vif_oper_type= NL80211_CHAN_NO_HT; - - if (netdev) - sdata = IEEE80211_DEV_TO_SUB_IF(netdev); - - switch (ieee80211_get_channel_mode(local, NULL)) { - case CHAN_MODE_HOPPING: - return -EBUSY; - case CHAN_MODE_FIXED: - if (local->oper_channel != chan) - return -EBUSY; - if (!sdata && local->_oper_channel_type == channel_type) - return 0; - break; - case CHAN_MODE_UNDEFINED: - break; - } - - if (sdata) - old_vif_oper_type = sdata->vif.bss_conf.channel_type; - old_oper_type = local->_oper_channel_type; - - if (!ieee80211_set_channel_type(local, sdata, channel_type)) - return -EBUSY; - - old_oper = local->oper_channel; - local->oper_channel = chan; - - /* Update driver if changes were actually made. */ - if ((old_oper != local->oper_channel) || - (old_oper_type != local->_oper_channel_type)) - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); - - if (sdata && sdata->vif.type != NL80211_IFTYPE_MONITOR && - old_vif_oper_type != sdata->vif.bss_conf.channel_type) - ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_HT); + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_QOS); return 0; } @@ -1743,10 +1764,11 @@ static int ieee80211_resume(struct wiphy *wiphy) #endif static int ieee80211_scan(struct wiphy *wiphy, - struct net_device *dev, struct cfg80211_scan_request *req) { - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_sub_if_data *sdata; + + sdata = IEEE80211_WDEV_TO_SUB_IF(req->wdev); switch (ieee80211_vif_type_p2p(&sdata->vif)) { case NL80211_IFTYPE_STATION: @@ -2111,143 +2133,291 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, return 0; } -static int ieee80211_remain_on_channel_hw(struct ieee80211_local *local, - struct net_device *dev, - struct ieee80211_channel *chan, - enum nl80211_channel_type chantype, - unsigned int duration, u64 *cookie) +static int ieee80211_start_roc_work(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_channel *channel, + enum nl80211_channel_type channel_type, + unsigned int duration, u64 *cookie, + struct sk_buff *txskb) { + struct ieee80211_roc_work *roc, *tmp; + bool queued = false; int ret; - u32 random_cookie; lockdep_assert_held(&local->mtx); - if (local->hw_roc_cookie) - return -EBUSY; - /* must be nonzero */ - random_cookie = random32() | 1; - - *cookie = random_cookie; - local->hw_roc_dev = dev; - local->hw_roc_cookie = random_cookie; - local->hw_roc_channel = chan; - local->hw_roc_channel_type = chantype; - local->hw_roc_duration = duration; - ret = drv_remain_on_channel(local, chan, chantype, duration); + roc = kzalloc(sizeof(*roc), GFP_KERNEL); + if (!roc) + return -ENOMEM; + + roc->chan = channel; + roc->chan_type = channel_type; + roc->duration = duration; + roc->req_duration = duration; + roc->frame = txskb; + roc->mgmt_tx_cookie = (unsigned long)txskb; + roc->sdata = sdata; + INIT_DELAYED_WORK(&roc->work, ieee80211_sw_roc_work); + INIT_LIST_HEAD(&roc->dependents); + + /* if there's one pending or we're scanning, queue this one */ + if (!list_empty(&local->roc_list) || local->scanning) + goto out_check_combine; + + /* if not HW assist, just queue & schedule work */ + if (!local->ops->remain_on_channel) { + ieee80211_queue_delayed_work(&local->hw, &roc->work, 0); + goto out_queue; + } + + /* otherwise actually kick it off here (for error handling) */ + + /* + * If the duration is zero, then the driver + * wouldn't actually do anything. Set it to + * 10 for now. + * + * TODO: cancel the off-channel operation + * when we get the SKB's TX status and + * the wait time was zero before. + */ + if (!duration) + duration = 10; + + ret = drv_remain_on_channel(local, channel, channel_type, duration); if (ret) { - local->hw_roc_channel = NULL; - local->hw_roc_cookie = 0; + kfree(roc); + return ret; } - return ret; + roc->started = true; + goto out_queue; + + out_check_combine: + list_for_each_entry(tmp, &local->roc_list, list) { + if (tmp->chan != channel || tmp->chan_type != channel_type) + continue; + + /* + * Extend this ROC if possible: + * + * If it hasn't started yet, just increase the duration + * and add the new one to the list of dependents. + */ + if (!tmp->started) { + list_add_tail(&roc->list, &tmp->dependents); + tmp->duration = max(tmp->duration, roc->duration); + queued = true; + break; + } + + /* If it has already started, it's more difficult ... */ + if (local->ops->remain_on_channel) { + unsigned long j = jiffies; + + /* + * In the offloaded ROC case, if it hasn't begun, add + * this new one to the dependent list to be handled + * when the the master one begins. If it has begun, + * check that there's still a minimum time left and + * if so, start this one, transmitting the frame, but + * add it to the list directly after this one with a + * a reduced time so we'll ask the driver to execute + * it right after finishing the previous one, in the + * hope that it'll also be executed right afterwards, + * effectively extending the old one. + * If there's no minimum time left, just add it to the + * normal list. + */ + if (!tmp->hw_begun) { + list_add_tail(&roc->list, &tmp->dependents); + queued = true; + break; + } + + if (time_before(j + IEEE80211_ROC_MIN_LEFT, + tmp->hw_start_time + + msecs_to_jiffies(tmp->duration))) { + int new_dur; + + ieee80211_handle_roc_started(roc); + + new_dur = roc->duration - + jiffies_to_msecs(tmp->hw_start_time + + msecs_to_jiffies( + tmp->duration) - + j); + + if (new_dur > 0) { + /* add right after tmp */ + list_add(&roc->list, &tmp->list); + } else { + list_add_tail(&roc->list, + &tmp->dependents); + } + queued = true; + } + } else if (del_timer_sync(&tmp->work.timer)) { + unsigned long new_end; + + /* + * In the software ROC case, cancel the timer, if + * that fails then the finish work is already + * queued/pending and thus we queue the new ROC + * normally, if that succeeds then we can extend + * the timer duration and TX the frame (if any.) + */ + + list_add_tail(&roc->list, &tmp->dependents); + queued = true; + + new_end = jiffies + msecs_to_jiffies(roc->duration); + + /* ok, it was started & we canceled timer */ + if (time_after(new_end, tmp->work.timer.expires)) + mod_timer(&tmp->work.timer, new_end); + else + add_timer(&tmp->work.timer); + + ieee80211_handle_roc_started(roc); + } + break; + } + + out_queue: + if (!queued) + list_add_tail(&roc->list, &local->roc_list); + + /* + * cookie is either the roc (for normal roc) + * or the SKB (for mgmt TX) + */ + if (txskb) + *cookie = (unsigned long)txskb; + else + *cookie = (unsigned long)roc; + + return 0; } static int ieee80211_remain_on_channel(struct wiphy *wiphy, - struct net_device *dev, + struct wireless_dev *wdev, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type, unsigned int duration, u64 *cookie) { - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct ieee80211_local *local = sdata->local; + int ret; - if (local->ops->remain_on_channel) { - int ret; - - mutex_lock(&local->mtx); - ret = ieee80211_remain_on_channel_hw(local, dev, - chan, channel_type, - duration, cookie); - local->hw_roc_for_tx = false; - mutex_unlock(&local->mtx); - - return ret; - } + mutex_lock(&local->mtx); + ret = ieee80211_start_roc_work(local, sdata, chan, channel_type, + duration, cookie, NULL); + mutex_unlock(&local->mtx); - return ieee80211_wk_remain_on_channel(sdata, chan, channel_type, - duration, cookie); + return ret; } -static int ieee80211_cancel_remain_on_channel_hw(struct ieee80211_local *local, - u64 cookie) +static int ieee80211_cancel_roc(struct ieee80211_local *local, + u64 cookie, bool mgmt_tx) { + struct ieee80211_roc_work *roc, *tmp, *found = NULL; int ret; - lockdep_assert_held(&local->mtx); + mutex_lock(&local->mtx); + list_for_each_entry_safe(roc, tmp, &local->roc_list, list) { + struct ieee80211_roc_work *dep, *tmp2; - if (local->hw_roc_cookie != cookie) - return -ENOENT; + list_for_each_entry_safe(dep, tmp2, &roc->dependents, list) { + if (!mgmt_tx && (unsigned long)dep != cookie) + continue; + else if (mgmt_tx && dep->mgmt_tx_cookie != cookie) + continue; + /* found dependent item -- just remove it */ + list_del(&dep->list); + mutex_unlock(&local->mtx); - ret = drv_cancel_remain_on_channel(local); - if (ret) - return ret; + ieee80211_roc_notify_destroy(dep); + return 0; + } - local->hw_roc_cookie = 0; - local->hw_roc_channel = NULL; + if (!mgmt_tx && (unsigned long)roc != cookie) + continue; + else if (mgmt_tx && roc->mgmt_tx_cookie != cookie) + continue; + + found = roc; + break; + } - ieee80211_recalc_idle(local); + if (!found) { + mutex_unlock(&local->mtx); + return -ENOENT; + } - return 0; -} + /* + * We found the item to cancel, so do that. Note that it + * may have dependents, which we also cancel (and send + * the expired signal for.) Not doing so would be quite + * tricky here, but we may need to fix it later. + */ -static int ieee80211_cancel_remain_on_channel(struct wiphy *wiphy, - struct net_device *dev, - u64 cookie) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - struct ieee80211_local *local = sdata->local; + if (local->ops->remain_on_channel) { + if (found->started) { + ret = drv_cancel_remain_on_channel(local); + if (WARN_ON_ONCE(ret)) { + mutex_unlock(&local->mtx); + return ret; + } + } - if (local->ops->cancel_remain_on_channel) { - int ret; + list_del(&found->list); - mutex_lock(&local->mtx); - ret = ieee80211_cancel_remain_on_channel_hw(local, cookie); + if (found->started) + ieee80211_start_next_roc(local); mutex_unlock(&local->mtx); - return ret; + ieee80211_roc_notify_destroy(found); + } else { + /* work may be pending so use it all the time */ + found->abort = true; + ieee80211_queue_delayed_work(&local->hw, &found->work, 0); + + mutex_unlock(&local->mtx); + + /* work will clean up etc */ + flush_delayed_work(&found->work); } - return ieee80211_wk_cancel_remain_on_channel(sdata, cookie); + return 0; } -static enum work_done_result -ieee80211_offchan_tx_done(struct ieee80211_work *wk, struct sk_buff *skb) +static int ieee80211_cancel_remain_on_channel(struct wiphy *wiphy, + struct wireless_dev *wdev, + u64 cookie) { - /* - * Use the data embedded in the work struct for reporting - * here so if the driver mangled the SKB before dropping - * it (which is the only way we really should get here) - * then we don't report mangled data. - * - * If there was no wait time, then by the time we get here - * the driver will likely not have reported the status yet, - * so in that case userspace will have to deal with it. - */ - - if (wk->offchan_tx.wait && !wk->offchan_tx.status) - cfg80211_mgmt_tx_status(wk->sdata->dev, - (unsigned long) wk->offchan_tx.frame, - wk->data, wk->data_len, false, GFP_KERNEL); + struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); + struct ieee80211_local *local = sdata->local; - return WORK_DONE_DESTROY; + return ieee80211_cancel_roc(local, cookie, false); } -static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev, +static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, struct ieee80211_channel *chan, bool offchan, enum nl80211_channel_type channel_type, bool channel_type_valid, unsigned int wait, const u8 *buf, size_t len, bool no_cck, bool dont_wait_for_ack, u64 *cookie) { - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct sta_info *sta; - struct ieee80211_work *wk; const struct ieee80211_mgmt *mgmt = (void *)buf; + bool need_offchan = false; u32 flags; - bool is_offchan = false; + int ret; if (dont_wait_for_ack) flags = IEEE80211_TX_CTL_NO_ACK; @@ -2255,33 +2425,28 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev, flags = IEEE80211_TX_INTFL_NL80211_FRAME_TX | IEEE80211_TX_CTL_REQ_TX_STATUS; - /* Check that we are on the requested channel for transmission */ - if (chan != local->tmp_channel && - chan != local->oper_channel) - is_offchan = true; - if (channel_type_valid && - (channel_type != local->tmp_channel_type && - channel_type != local->_oper_channel_type)) - is_offchan = true; - - if (chan == local->hw_roc_channel) { - /* TODO: check channel type? */ - is_offchan = false; - flags |= IEEE80211_TX_CTL_TX_OFFCHAN; - } - if (no_cck) flags |= IEEE80211_TX_CTL_NO_CCK_RATE; - if (is_offchan && !offchan) - return -EBUSY; - switch (sdata->vif.type) { case NL80211_IFTYPE_ADHOC: + if (!sdata->vif.bss_conf.ibss_joined) + need_offchan = true; + /* fall through */ +#ifdef CONFIG_MAC80211_MESH + case NL80211_IFTYPE_MESH_POINT: + if (ieee80211_vif_is_mesh(&sdata->vif) && + !sdata->u.mesh.mesh_id_len) + need_offchan = true; + /* fall through */ +#endif case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_P2P_GO: - case NL80211_IFTYPE_MESH_POINT: + if (sdata->vif.type != NL80211_IFTYPE_ADHOC && + !ieee80211_vif_is_mesh(&sdata->vif) && + !rcu_access_pointer(sdata->bss->beacon)) + need_offchan = true; if (!ieee80211_is_action(mgmt->frame_control) || mgmt->u.action.category == WLAN_CATEGORY_PUBLIC) break; @@ -2293,167 +2458,101 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev, break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: + if (!sdata->u.mgd.associated) + need_offchan = true; break; default: return -EOPNOTSUPP; } + mutex_lock(&local->mtx); + + /* Check if the operating channel is the requested channel */ + if (!need_offchan) { + need_offchan = chan != local->oper_channel; + if (channel_type_valid && + channel_type != local->_oper_channel_type) + need_offchan = true; + } + + if (need_offchan && !offchan) { + ret = -EBUSY; + goto out_unlock; + } + skb = dev_alloc_skb(local->hw.extra_tx_headroom + len); - if (!skb) - return -ENOMEM; + if (!skb) { + ret = -ENOMEM; + goto out_unlock; + } skb_reserve(skb, local->hw.extra_tx_headroom); memcpy(skb_put(skb, len), buf, len); IEEE80211_SKB_CB(skb)->flags = flags; - if (flags & IEEE80211_TX_CTL_TX_OFFCHAN) - IEEE80211_SKB_CB(skb)->hw_queue = - local->hw.offchannel_tx_hw_queue; - skb->dev = sdata->dev; - *cookie = (unsigned long) skb; - - if (is_offchan && local->ops->remain_on_channel) { - unsigned int duration; - int ret; - - mutex_lock(&local->mtx); - /* - * If the duration is zero, then the driver - * wouldn't actually do anything. Set it to - * 100 for now. - * - * TODO: cancel the off-channel operation - * when we get the SKB's TX status and - * the wait time was zero before. - */ - duration = 100; - if (wait) - duration = wait; - ret = ieee80211_remain_on_channel_hw(local, dev, chan, - channel_type, - duration, cookie); - if (ret) { - kfree_skb(skb); - mutex_unlock(&local->mtx); - return ret; - } - - local->hw_roc_for_tx = true; - local->hw_roc_duration = wait; - - /* - * queue up frame for transmission after - * ieee80211_ready_on_channel call - */ + if (!need_offchan) { + *cookie = (unsigned long) skb; + ieee80211_tx_skb(sdata, skb); + ret = 0; + goto out_unlock; + } - /* modify cookie to prevent API mismatches */ - *cookie ^= 2; - IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_TX_OFFCHAN; + IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_TX_OFFCHAN; + if (local->hw.flags & IEEE80211_HW_QUEUE_CONTROL) IEEE80211_SKB_CB(skb)->hw_queue = local->hw.offchannel_tx_hw_queue; - local->hw_roc_skb = skb; - local->hw_roc_skb_for_status = skb; - mutex_unlock(&local->mtx); - - return 0; - } - - /* - * Can transmit right away if the channel was the - * right one and there's no wait involved... If a - * wait is involved, we might otherwise not be on - * the right channel for long enough! - */ - if (!is_offchan && !wait && !sdata->vif.bss_conf.idle) { - ieee80211_tx_skb(sdata, skb); - return 0; - } - wk = kzalloc(sizeof(*wk) + len, GFP_KERNEL); - if (!wk) { + /* This will handle all kinds of coalescing and immediate TX */ + ret = ieee80211_start_roc_work(local, sdata, chan, channel_type, + wait, cookie, skb); + if (ret) kfree_skb(skb); - return -ENOMEM; - } - - wk->type = IEEE80211_WORK_OFFCHANNEL_TX; - wk->chan = chan; - wk->chan_type = channel_type; - wk->sdata = sdata; - wk->done = ieee80211_offchan_tx_done; - wk->offchan_tx.frame = skb; - wk->offchan_tx.wait = wait; - wk->data_len = len; - memcpy(wk->data, buf, len); - - ieee80211_add_work(wk); - return 0; + out_unlock: + mutex_unlock(&local->mtx); + return ret; } static int ieee80211_mgmt_tx_cancel_wait(struct wiphy *wiphy, - struct net_device *dev, + struct wireless_dev *wdev, u64 cookie) { - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - struct ieee80211_local *local = sdata->local; - struct ieee80211_work *wk; - int ret = -ENOENT; - - mutex_lock(&local->mtx); - - if (local->ops->cancel_remain_on_channel) { - cookie ^= 2; - ret = ieee80211_cancel_remain_on_channel_hw(local, cookie); - - if (ret == 0) { - kfree_skb(local->hw_roc_skb); - local->hw_roc_skb = NULL; - local->hw_roc_skb_for_status = NULL; - } - - mutex_unlock(&local->mtx); - - return ret; - } - - list_for_each_entry(wk, &local->work_list, list) { - if (wk->sdata != sdata) - continue; - - if (wk->type != IEEE80211_WORK_OFFCHANNEL_TX) - continue; - - if (cookie != (unsigned long) wk->offchan_tx.frame) - continue; - - wk->timeout = jiffies; - - ieee80211_queue_work(&local->hw, &local->work_work); - ret = 0; - break; - } - mutex_unlock(&local->mtx); + struct ieee80211_local *local = wiphy_priv(wiphy); - return ret; + return ieee80211_cancel_roc(local, cookie, true); } static void ieee80211_mgmt_frame_register(struct wiphy *wiphy, - struct net_device *dev, + struct wireless_dev *wdev, u16 frame_type, bool reg) { struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); - if (frame_type != (IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_REQ)) - return; + switch (frame_type) { + case IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_AUTH: + if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { + struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; - if (reg) - local->probe_req_reg++; - else - local->probe_req_reg--; + if (reg) + ifibss->auth_frame_registrations++; + else + ifibss->auth_frame_registrations--; + } + break; + case IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_REQ: + if (reg) + local->probe_req_reg++; + else + local->probe_req_reg--; - ieee80211_queue_work(&local->hw, &local->reconfig_filter); + ieee80211_queue_work(&local->hw, &local->reconfig_filter); + break; + default: + break; + } } static int ieee80211_set_antenna(struct wiphy *wiphy, u32 tx_ant, u32 rx_ant) @@ -2573,8 +2672,8 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev, tf->u.setup_req.capability = cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); - ieee80211_add_srates_ie(&sdata->vif, skb, false); - ieee80211_add_ext_srates_ie(&sdata->vif, skb, false); + ieee80211_add_srates_ie(sdata, skb, false); + ieee80211_add_ext_srates_ie(sdata, skb, false); ieee80211_tdls_add_ext_capab(skb); break; case WLAN_TDLS_SETUP_RESPONSE: @@ -2587,8 +2686,8 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev, tf->u.setup_resp.capability = cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); - ieee80211_add_srates_ie(&sdata->vif, skb, false); - ieee80211_add_ext_srates_ie(&sdata->vif, skb, false); + ieee80211_add_srates_ie(sdata, skb, false); + ieee80211_add_ext_srates_ie(sdata, skb, false); ieee80211_tdls_add_ext_capab(skb); break; case WLAN_TDLS_SETUP_CONFIRM: @@ -2648,8 +2747,8 @@ ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev, mgmt->u.action.u.tdls_discover_resp.capability = cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); - ieee80211_add_srates_ie(&sdata->vif, skb, false); - ieee80211_add_ext_srates_ie(&sdata->vif, skb, false); + ieee80211_add_srates_ie(sdata, skb, false); + ieee80211_add_ext_srates_ie(sdata, skb, false); ieee80211_tdls_add_ext_capab(skb); break; default: @@ -2679,9 +2778,8 @@ static int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, !sdata->u.mgd.associated) return -EINVAL; -#ifdef CONFIG_MAC80211_VERBOSE_TDLS_DEBUG - printk(KERN_DEBUG "TDLS mgmt action %d peer %pM\n", action_code, peer); -#endif + tdls_dbg(sdata, "TDLS mgmt action %d peer %pM\n", + action_code, peer); skb = dev_alloc_skb(local->hw.extra_tx_headroom + max(sizeof(struct ieee80211_mgmt), @@ -2790,9 +2888,7 @@ static int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EINVAL; -#ifdef CONFIG_MAC80211_VERBOSE_TDLS_DEBUG - printk(KERN_DEBUG "TDLS oper %d peer %pM\n", oper, peer); -#endif + tdls_dbg(sdata, "TDLS oper %d peer %pM\n", oper, peer); switch (oper) { case NL80211_TDLS_ENABLE_LINK: @@ -2889,8 +2985,8 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, } static struct ieee80211_channel * -ieee80211_wiphy_get_channel(struct wiphy *wiphy, - enum nl80211_channel_type *type) +ieee80211_cfg_get_channel(struct wiphy *wiphy, struct wireless_dev *wdev, + enum nl80211_channel_type *type) { struct ieee80211_local *local = wiphy_priv(wiphy); @@ -2936,7 +3032,7 @@ struct cfg80211_ops mac80211_config_ops = { #endif .change_bss = ieee80211_change_bss, .set_txq_params = ieee80211_set_txq_params, - .set_channel = ieee80211_set_channel, + .set_monitor_channel = ieee80211_set_monitor_channel, .suspend = ieee80211_suspend, .resume = ieee80211_resume, .scan = ieee80211_scan, @@ -2971,7 +3067,6 @@ struct cfg80211_ops mac80211_config_ops = { .tdls_oper = ieee80211_tdls_oper, .tdls_mgmt = ieee80211_tdls_mgmt, .probe_client = ieee80211_probe_client, - .get_channel = ieee80211_wiphy_get_channel, .set_noack_map = ieee80211_set_noack_map, #ifdef CONFIG_PM .set_wakeup = ieee80211_set_wakeup, @@ -2979,4 +3074,5 @@ struct cfg80211_ops mac80211_config_ops = { .get_et_sset_count = ieee80211_get_et_sset_count, .get_et_stats = ieee80211_get_et_stats, .get_et_strings = ieee80211_get_et_strings, + .get_channel = ieee80211_cfg_get_channel, }; diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index c76cf7230c7..f0f87e5a1d3 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -41,6 +41,10 @@ __ieee80211_get_channel_mode(struct ieee80211_local *local, if (!sdata->u.ap.beacon) continue; break; + case NL80211_IFTYPE_MESH_POINT: + if (!sdata->wdev.mesh_id_len) + continue; + break; default: break; } diff --git a/net/mac80211/debug.h b/net/mac80211/debug.h new file mode 100644 index 00000000000..8f383a57601 --- /dev/null +++ b/net/mac80211/debug.h @@ -0,0 +1,170 @@ +#ifndef __MAC80211_DEBUG_H +#define __MAC80211_DEBUG_H +#include <net/cfg80211.h> + +#ifdef CONFIG_MAC80211_IBSS_DEBUG +#define MAC80211_IBSS_DEBUG 1 +#else +#define MAC80211_IBSS_DEBUG 0 +#endif + +#ifdef CONFIG_MAC80211_PS_DEBUG +#define MAC80211_PS_DEBUG 1 +#else +#define MAC80211_PS_DEBUG 0 +#endif + +#ifdef CONFIG_MAC80211_HT_DEBUG +#define MAC80211_HT_DEBUG 1 +#else +#define MAC80211_HT_DEBUG 0 +#endif + +#ifdef CONFIG_MAC80211_MPL_DEBUG +#define MAC80211_MPL_DEBUG 1 +#else +#define MAC80211_MPL_DEBUG 0 +#endif + +#ifdef CONFIG_MAC80211_MPATH_DEBUG +#define MAC80211_MPATH_DEBUG 1 +#else +#define MAC80211_MPATH_DEBUG 0 +#endif + +#ifdef CONFIG_MAC80211_MHWMP_DEBUG +#define MAC80211_MHWMP_DEBUG 1 +#else +#define MAC80211_MHWMP_DEBUG 0 +#endif + +#ifdef CONFIG_MAC80211_MESH_SYNC_DEBUG +#define MAC80211_MESH_SYNC_DEBUG 1 +#else +#define MAC80211_MESH_SYNC_DEBUG 0 +#endif + +#ifdef CONFIG_MAC80211_TDLS_DEBUG +#define MAC80211_TDLS_DEBUG 1 +#else +#define MAC80211_TDLS_DEBUG 0 +#endif + +#ifdef CONFIG_MAC80211_STA_DEBUG +#define MAC80211_STA_DEBUG 1 +#else +#define MAC80211_STA_DEBUG 0 +#endif + +#ifdef CONFIG_MAC80211_MLME_DEBUG +#define MAC80211_MLME_DEBUG 1 +#else +#define MAC80211_MLME_DEBUG 0 +#endif + +#ifdef CONFIG_MAC80211_MESSAGE_TRACING +void __sdata_info(const char *fmt, ...) __printf(1, 2); +void __sdata_dbg(bool print, const char *fmt, ...) __printf(2, 3); +void __sdata_err(const char *fmt, ...) __printf(1, 2); +void __wiphy_dbg(struct wiphy *wiphy, bool print, const char *fmt, ...) + __printf(3, 4); + +#define _sdata_info(sdata, fmt, ...) \ + __sdata_info("%s: " fmt, (sdata)->name, ##__VA_ARGS__) +#define _sdata_dbg(print, sdata, fmt, ...) \ + __sdata_dbg(print, "%s: " fmt, (sdata)->name, ##__VA_ARGS__) +#define _sdata_err(sdata, fmt, ...) \ + __sdata_err("%s: " fmt, (sdata)->name, ##__VA_ARGS__) +#define _wiphy_dbg(print, wiphy, fmt, ...) \ + __wiphy_dbg(wiphy, print, fmt, ##__VA_ARGS__) +#else +#define _sdata_info(sdata, fmt, ...) \ +do { \ + pr_info("%s: " fmt, \ + (sdata)->name, ##__VA_ARGS__); \ +} while (0) + +#define _sdata_dbg(print, sdata, fmt, ...) \ +do { \ + if (print) \ + pr_debug("%s: " fmt, \ + (sdata)->name, ##__VA_ARGS__); \ +} while (0) + +#define _sdata_err(sdata, fmt, ...) \ +do { \ + pr_err("%s: " fmt, \ + (sdata)->name, ##__VA_ARGS__); \ +} while (0) + +#define _wiphy_dbg(print, wiphy, fmt, ...) \ +do { \ + if (print) \ + wiphy_dbg((wiphy), fmt, ##__VA_ARGS__); \ +} while (0) +#endif + +#define sdata_info(sdata, fmt, ...) \ + _sdata_info(sdata, fmt, ##__VA_ARGS__) +#define sdata_err(sdata, fmt, ...) \ + _sdata_err(sdata, fmt, ##__VA_ARGS__) +#define sdata_dbg(sdata, fmt, ...) \ + _sdata_dbg(1, sdata, fmt, ##__VA_ARGS__) + +#define ht_dbg(sdata, fmt, ...) \ + _sdata_dbg(MAC80211_HT_DEBUG, \ + sdata, fmt, ##__VA_ARGS__) + +#define ht_dbg_ratelimited(sdata, fmt, ...) \ + _sdata_dbg(MAC80211_HT_DEBUG && net_ratelimit(), \ + sdata, fmt, ##__VA_ARGS__) + +#define ibss_dbg(sdata, fmt, ...) \ + _sdata_dbg(MAC80211_IBSS_DEBUG, \ + sdata, fmt, ##__VA_ARGS__) + +#define ps_dbg(sdata, fmt, ...) \ + _sdata_dbg(MAC80211_PS_DEBUG, \ + sdata, fmt, ##__VA_ARGS__) + +#define ps_dbg_hw(hw, fmt, ...) \ + _wiphy_dbg(MAC80211_PS_DEBUG, \ + (hw)->wiphy, fmt, ##__VA_ARGS__) + +#define ps_dbg_ratelimited(sdata, fmt, ...) \ + _sdata_dbg(MAC80211_PS_DEBUG && net_ratelimit(), \ + sdata, fmt, ##__VA_ARGS__) + +#define mpl_dbg(sdata, fmt, ...) \ + _sdata_dbg(MAC80211_MPL_DEBUG, \ + sdata, fmt, ##__VA_ARGS__) + +#define mpath_dbg(sdata, fmt, ...) \ + _sdata_dbg(MAC80211_MPATH_DEBUG, \ + sdata, fmt, ##__VA_ARGS__) + +#define mhwmp_dbg(sdata, fmt, ...) \ + _sdata_dbg(MAC80211_MHWMP_DEBUG, \ + sdata, fmt, ##__VA_ARGS__) + +#define msync_dbg(sdata, fmt, ...) \ + _sdata_dbg(MAC80211_MESH_SYNC_DEBUG, \ + sdata, fmt, ##__VA_ARGS__) + +#define tdls_dbg(sdata, fmt, ...) \ + _sdata_dbg(MAC80211_TDLS_DEBUG, \ + sdata, fmt, ##__VA_ARGS__) + +#define sta_dbg(sdata, fmt, ...) \ + _sdata_dbg(MAC80211_STA_DEBUG, \ + sdata, fmt, ##__VA_ARGS__) + +#define mlme_dbg(sdata, fmt, ...) \ + _sdata_dbg(MAC80211_MLME_DEBUG, \ + sdata, fmt, ##__VA_ARGS__) + +#define mlme_dbg_ratelimited(sdata, fmt, ...) \ + _sdata_dbg(MAC80211_MLME_DEBUG && net_ratelimit(), \ + sdata, fmt, ##__VA_ARGS__) + +#endif /* __MAC80211_DEBUG_H */ diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 778e5916d7c..b8dfb440c8e 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -325,8 +325,6 @@ void debugfs_hw_add(struct ieee80211_local *local) local->rx_handlers_drop_defrag); DEBUGFS_STATS_ADD(rx_handlers_drop_short, local->rx_handlers_drop_short); - DEBUGFS_STATS_ADD(rx_handlers_drop_passive_scan, - local->rx_handlers_drop_passive_scan); DEBUGFS_STATS_ADD(tx_expand_skb_head, local->tx_expand_skb_head); DEBUGFS_STATS_ADD(tx_expand_skb_head_cloned, diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c index 7932767bb48..090d08ff22c 100644 --- a/net/mac80211/debugfs_key.c +++ b/net/mac80211/debugfs_key.c @@ -283,6 +283,11 @@ void ieee80211_debugfs_key_update_default(struct ieee80211_sub_if_data *sdata) lockdep_assert_held(&sdata->local->key_mtx); + if (sdata->debugfs.default_unicast_key) { + debugfs_remove(sdata->debugfs.default_unicast_key); + sdata->debugfs.default_unicast_key = NULL; + } + if (sdata->default_unicast_key) { key = key_mtx_dereference(sdata->local, sdata->default_unicast_key); @@ -290,9 +295,11 @@ void ieee80211_debugfs_key_update_default(struct ieee80211_sub_if_data *sdata) sdata->debugfs.default_unicast_key = debugfs_create_symlink("default_unicast_key", sdata->debugfs.dir, buf); - } else { - debugfs_remove(sdata->debugfs.default_unicast_key); - sdata->debugfs.default_unicast_key = NULL; + } + + if (sdata->debugfs.default_multicast_key) { + debugfs_remove(sdata->debugfs.default_multicast_key); + sdata->debugfs.default_multicast_key = NULL; } if (sdata->default_multicast_key) { @@ -302,9 +309,6 @@ void ieee80211_debugfs_key_update_default(struct ieee80211_sub_if_data *sdata) sdata->debugfs.default_multicast_key = debugfs_create_symlink("default_multicast_key", sdata->debugfs.dir, buf); - } else { - debugfs_remove(sdata->debugfs.default_multicast_key); - sdata->debugfs.default_multicast_key = NULL; } } diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 7ed433c66d6..6d5aec9418e 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -468,48 +468,54 @@ IEEE80211_IF_FILE(fwded_unicast, u.mesh.mshstats.fwded_unicast, DEC); IEEE80211_IF_FILE(fwded_frames, u.mesh.mshstats.fwded_frames, DEC); IEEE80211_IF_FILE(dropped_frames_ttl, u.mesh.mshstats.dropped_frames_ttl, DEC); IEEE80211_IF_FILE(dropped_frames_congestion, - u.mesh.mshstats.dropped_frames_congestion, DEC); + u.mesh.mshstats.dropped_frames_congestion, DEC); IEEE80211_IF_FILE(dropped_frames_no_route, - u.mesh.mshstats.dropped_frames_no_route, DEC); + u.mesh.mshstats.dropped_frames_no_route, DEC); IEEE80211_IF_FILE(estab_plinks, u.mesh.mshstats.estab_plinks, ATOMIC); /* Mesh parameters */ IEEE80211_IF_FILE(dot11MeshMaxRetries, - u.mesh.mshcfg.dot11MeshMaxRetries, DEC); + u.mesh.mshcfg.dot11MeshMaxRetries, DEC); IEEE80211_IF_FILE(dot11MeshRetryTimeout, - u.mesh.mshcfg.dot11MeshRetryTimeout, DEC); + u.mesh.mshcfg.dot11MeshRetryTimeout, DEC); IEEE80211_IF_FILE(dot11MeshConfirmTimeout, - u.mesh.mshcfg.dot11MeshConfirmTimeout, DEC); + u.mesh.mshcfg.dot11MeshConfirmTimeout, DEC); IEEE80211_IF_FILE(dot11MeshHoldingTimeout, - u.mesh.mshcfg.dot11MeshHoldingTimeout, DEC); + u.mesh.mshcfg.dot11MeshHoldingTimeout, DEC); IEEE80211_IF_FILE(dot11MeshTTL, u.mesh.mshcfg.dot11MeshTTL, DEC); IEEE80211_IF_FILE(element_ttl, u.mesh.mshcfg.element_ttl, DEC); IEEE80211_IF_FILE(auto_open_plinks, u.mesh.mshcfg.auto_open_plinks, DEC); IEEE80211_IF_FILE(dot11MeshMaxPeerLinks, - u.mesh.mshcfg.dot11MeshMaxPeerLinks, DEC); + u.mesh.mshcfg.dot11MeshMaxPeerLinks, DEC); IEEE80211_IF_FILE(dot11MeshHWMPactivePathTimeout, - u.mesh.mshcfg.dot11MeshHWMPactivePathTimeout, DEC); + u.mesh.mshcfg.dot11MeshHWMPactivePathTimeout, DEC); IEEE80211_IF_FILE(dot11MeshHWMPpreqMinInterval, - u.mesh.mshcfg.dot11MeshHWMPpreqMinInterval, DEC); + u.mesh.mshcfg.dot11MeshHWMPpreqMinInterval, DEC); IEEE80211_IF_FILE(dot11MeshHWMPperrMinInterval, - u.mesh.mshcfg.dot11MeshHWMPperrMinInterval, DEC); + u.mesh.mshcfg.dot11MeshHWMPperrMinInterval, DEC); IEEE80211_IF_FILE(dot11MeshHWMPnetDiameterTraversalTime, - u.mesh.mshcfg.dot11MeshHWMPnetDiameterTraversalTime, DEC); + u.mesh.mshcfg.dot11MeshHWMPnetDiameterTraversalTime, DEC); IEEE80211_IF_FILE(dot11MeshHWMPmaxPREQretries, - u.mesh.mshcfg.dot11MeshHWMPmaxPREQretries, DEC); + u.mesh.mshcfg.dot11MeshHWMPmaxPREQretries, DEC); IEEE80211_IF_FILE(path_refresh_time, - u.mesh.mshcfg.path_refresh_time, DEC); + u.mesh.mshcfg.path_refresh_time, DEC); IEEE80211_IF_FILE(min_discovery_timeout, - u.mesh.mshcfg.min_discovery_timeout, DEC); + u.mesh.mshcfg.min_discovery_timeout, DEC); IEEE80211_IF_FILE(dot11MeshHWMPRootMode, - u.mesh.mshcfg.dot11MeshHWMPRootMode, DEC); + u.mesh.mshcfg.dot11MeshHWMPRootMode, DEC); IEEE80211_IF_FILE(dot11MeshGateAnnouncementProtocol, - u.mesh.mshcfg.dot11MeshGateAnnouncementProtocol, DEC); + u.mesh.mshcfg.dot11MeshGateAnnouncementProtocol, DEC); IEEE80211_IF_FILE(dot11MeshHWMPRannInterval, - u.mesh.mshcfg.dot11MeshHWMPRannInterval, DEC); + u.mesh.mshcfg.dot11MeshHWMPRannInterval, DEC); IEEE80211_IF_FILE(dot11MeshForwarding, u.mesh.mshcfg.dot11MeshForwarding, DEC); IEEE80211_IF_FILE(rssi_threshold, u.mesh.mshcfg.rssi_threshold, DEC); IEEE80211_IF_FILE(ht_opmode, u.mesh.mshcfg.ht_opmode, DEC); +IEEE80211_IF_FILE(dot11MeshHWMPactivePathToRootTimeout, + u.mesh.mshcfg.dot11MeshHWMPactivePathToRootTimeout, DEC); +IEEE80211_IF_FILE(dot11MeshHWMProotInterval, + u.mesh.mshcfg.dot11MeshHWMProotInterval, DEC); +IEEE80211_IF_FILE(dot11MeshHWMPconfirmationInterval, + u.mesh.mshcfg.dot11MeshHWMPconfirmationInterval, DEC); #endif #define DEBUGFS_ADD_MODE(name, mode) \ @@ -607,9 +613,13 @@ static void add_mesh_config(struct ieee80211_sub_if_data *sdata) MESHPARAMS_ADD(min_discovery_timeout); MESHPARAMS_ADD(dot11MeshHWMPRootMode); MESHPARAMS_ADD(dot11MeshHWMPRannInterval); + MESHPARAMS_ADD(dot11MeshForwarding); MESHPARAMS_ADD(dot11MeshGateAnnouncementProtocol); MESHPARAMS_ADD(rssi_threshold); MESHPARAMS_ADD(ht_opmode); + MESHPARAMS_ADD(dot11MeshHWMPactivePathToRootTimeout); + MESHPARAMS_ADD(dot11MeshHWMProotInterval); + MESHPARAMS_ADD(dot11MeshHWMPconfirmationInterval); #undef MESHPARAMS_ADD } #endif @@ -685,6 +695,7 @@ void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata) sprintf(buf, "netdev:%s", sdata->name); if (!debugfs_rename(dir->d_parent, dir, dir->d_parent, buf)) - printk(KERN_ERR "mac80211: debugfs: failed to rename debugfs " - "dir to %s\n", buf); + sdata_err(sdata, + "debugfs: failed to rename debugfs dir to %s\n", + buf); } diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 6d33a0c743a..df920319910 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -3,7 +3,7 @@ #include <net/mac80211.h> #include "ieee80211_i.h" -#include "driver-trace.h" +#include "trace.h" static inline void check_sdata_in_driver(struct ieee80211_sub_if_data *sdata) { @@ -27,14 +27,6 @@ static inline void drv_tx(struct ieee80211_local *local, struct sk_buff *skb) local->ops->tx(&local->hw, skb); } -static inline void drv_tx_frags(struct ieee80211_local *local, - struct ieee80211_vif *vif, - struct ieee80211_sta *sta, - struct sk_buff_head *skbs) -{ - local->ops->tx_frags(&local->hw, vif, sta, skbs); -} - static inline void drv_get_et_strings(struct ieee80211_sub_if_data *sdata, u32 sset, u8 *data) { @@ -845,4 +837,33 @@ drv_allow_buffered_frames(struct ieee80211_local *local, more_data); trace_drv_return_void(local); } + +static inline int drv_get_rssi(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, + s8 *rssi_dbm) +{ + int ret; + + might_sleep(); + + ret = local->ops->get_rssi(&local->hw, &sdata->vif, sta, rssi_dbm); + trace_drv_get_rssi(local, sta, *rssi_dbm, ret); + + return ret; +} + +static inline void drv_mgd_prepare_tx(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + might_sleep(); + + check_sdata_in_driver(sdata); + WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION); + + trace_drv_mgd_prepare_tx(local, sdata); + if (local->ops->mgd_prepare_tx) + local->ops->mgd_prepare_tx(&local->hw, &sdata->vif); + trace_drv_return_void(local); +} #endif /* __MAC80211_DRIVER_OPS */ diff --git a/net/mac80211/driver-trace.c b/net/mac80211/driver-trace.c deleted file mode 100644 index 8ed8711b1a6..00000000000 --- a/net/mac80211/driver-trace.c +++ /dev/null @@ -1,9 +0,0 @@ -/* bug in tracepoint.h, it should include this */ -#include <linux/module.h> - -/* sparse isn't too happy with all macros... */ -#ifndef __CHECKER__ -#include "driver-ops.h" -#define CREATE_TRACE_POINTS -#include "driver-trace.h" -#endif diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 6f8615c54b2..4b4538d6392 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -305,12 +305,10 @@ void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, tid = (params & IEEE80211_DELBA_PARAM_TID_MASK) >> 12; initiator = (params & IEEE80211_DELBA_PARAM_INITIATOR_MASK) >> 11; -#ifdef CONFIG_MAC80211_HT_DEBUG - net_dbg_ratelimited("delba from %pM (%s) tid %d reason code %d\n", - mgmt->sa, initiator ? "initiator" : "recipient", - tid, - le16_to_cpu(mgmt->u.action.u.delba.reason_code)); -#endif /* CONFIG_MAC80211_HT_DEBUG */ + ht_dbg_ratelimited(sdata, "delba from %pM (%s) tid %d reason code %d\n", + mgmt->sa, initiator ? "initiator" : "recipient", + tid, + le16_to_cpu(mgmt->u.action.u.delba.reason_code)); if (initiator == WLAN_BACK_INITIATOR) __ieee80211_stop_rx_ba_session(sta, tid, WLAN_BACK_INITIATOR, 0, diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 33d9d0c3e3d..5746d62faba 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -82,8 +82,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, local->oper_channel = chan; channel_type = ifibss->channel_type; - if (channel_type > NL80211_CHAN_HT20 && - !cfg80211_can_beacon_sec_chan(local->hw.wiphy, chan, channel_type)) + if (!cfg80211_can_beacon_sec_chan(local->hw.wiphy, chan, channel_type)) channel_type = NL80211_CHAN_HT20; if (!ieee80211_set_channel_type(local, sdata, channel_type)) { /* can only fail due to HT40+/- mismatch */ @@ -262,11 +261,7 @@ static struct sta_info *ieee80211_ibss_finish_sta(struct sta_info *sta, memcpy(addr, sta->sta.addr, ETH_ALEN); -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - wiphy_debug(sdata->local->hw.wiphy, - "Adding new IBSS station %pM (dev=%s)\n", - addr, sdata->name); -#endif + ibss_dbg(sdata, "Adding new IBSS station %pM\n", addr); sta_info_pre_move_state(sta, IEEE80211_STA_AUTH); sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC); @@ -280,12 +275,10 @@ static struct sta_info *ieee80211_ibss_finish_sta(struct sta_info *sta, /* If it fails, maybe we raced another insertion? */ if (sta_info_insert_rcu(sta)) return sta_info_get(sdata, addr); - if (auth) { -#ifdef CONFIG_MAC80211_IBSS_DEBUG - printk(KERN_DEBUG "TX Auth SA=%pM DA=%pM BSSID=%pM" - "(auth_transaction=1)\n", sdata->vif.addr, - sdata->u.ibss.bssid, addr); -#endif + if (auth && !sdata->u.ibss.auth_frame_registrations) { + ibss_dbg(sdata, + "TX Auth SA=%pM DA=%pM BSSID=%pM (auth_transaction=1)\n", + sdata->vif.addr, sdata->u.ibss.bssid, addr); ieee80211_send_auth(sdata, 1, WLAN_AUTH_OPEN, NULL, 0, addr, sdata->u.ibss.bssid, NULL, 0, 0); } @@ -308,7 +301,7 @@ ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata, * allow new one to be added. */ if (local->num_sta >= IEEE80211_IBSS_MAX_STA_ENTRIES) { - net_dbg_ratelimited("%s: No room for a new IBSS STA entry %pM\n", + net_info_ratelimited("%s: No room for a new IBSS STA entry %pM\n", sdata->name, addr); rcu_read_lock(); return NULL; @@ -355,11 +348,9 @@ static void ieee80211_rx_mgmt_auth_ibss(struct ieee80211_sub_if_data *sdata, if (auth_alg != WLAN_AUTH_OPEN || auth_transaction != 1) return; -#ifdef CONFIG_MAC80211_IBSS_DEBUG - printk(KERN_DEBUG "%s: RX Auth SA=%pM DA=%pM BSSID=%pM." - "(auth_transaction=%d)\n", - sdata->name, mgmt->sa, mgmt->da, mgmt->bssid, auth_transaction); -#endif + ibss_dbg(sdata, + "RX Auth SA=%pM DA=%pM BSSID=%pM (auth_transaction=%d)\n", + mgmt->sa, mgmt->da, mgmt->bssid, auth_transaction); sta_info_destroy_addr(sdata, mgmt->sa); ieee80211_ibss_add_sta(sdata, mgmt->bssid, mgmt->sa, 0, false); rcu_read_unlock(); @@ -422,15 +413,10 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, ieee80211_mandatory_rates(local, band); if (sta->sta.supp_rates[band] != prev_rates) { -#ifdef CONFIG_MAC80211_IBSS_DEBUG - printk(KERN_DEBUG - "%s: updated supp_rates set " - "for %pM based on beacon" - "/probe_resp (0x%x -> 0x%x)\n", - sdata->name, sta->sta.addr, - prev_rates, - sta->sta.supp_rates[band]); -#endif + ibss_dbg(sdata, + "updated supp_rates set for %pM based on beacon/probe_resp (0x%x -> 0x%x)\n", + sta->sta.addr, prev_rates, + sta->sta.supp_rates[band]); rates_updated = true; } } else { @@ -545,22 +531,18 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, rx_timestamp = drv_get_tsf(local, sdata); } -#ifdef CONFIG_MAC80211_IBSS_DEBUG - printk(KERN_DEBUG "RX beacon SA=%pM BSSID=" - "%pM TSF=0x%llx BCN=0x%llx diff=%lld @%lu\n", - mgmt->sa, mgmt->bssid, - (unsigned long long)rx_timestamp, - (unsigned long long)beacon_timestamp, - (unsigned long long)(rx_timestamp - beacon_timestamp), - jiffies); -#endif + ibss_dbg(sdata, + "RX beacon SA=%pM BSSID=%pM TSF=0x%llx BCN=0x%llx diff=%lld @%lu\n", + mgmt->sa, mgmt->bssid, + (unsigned long long)rx_timestamp, + (unsigned long long)beacon_timestamp, + (unsigned long long)(rx_timestamp - beacon_timestamp), + jiffies); if (beacon_timestamp > rx_timestamp) { -#ifdef CONFIG_MAC80211_IBSS_DEBUG - printk(KERN_DEBUG "%s: beacon TSF higher than " - "local TSF - IBSS merge with BSSID %pM\n", - sdata->name, mgmt->bssid); -#endif + ibss_dbg(sdata, + "beacon TSF higher than local TSF - IBSS merge with BSSID %pM\n", + mgmt->bssid); ieee80211_sta_join_ibss(sdata, bss); supp_rates = ieee80211_sta_get_rates(local, elems, band, NULL); ieee80211_ibss_add_sta(sdata, mgmt->bssid, mgmt->sa, @@ -586,7 +568,7 @@ void ieee80211_ibss_rx_no_sta(struct ieee80211_sub_if_data *sdata, * allow new one to be added. */ if (local->num_sta >= IEEE80211_IBSS_MAX_STA_ENTRIES) { - net_dbg_ratelimited("%s: No room for a new IBSS STA entry %pM\n", + net_info_ratelimited("%s: No room for a new IBSS STA entry %pM\n", sdata->name, addr); return; } @@ -662,8 +644,8 @@ static void ieee80211_sta_merge_ibss(struct ieee80211_sub_if_data *sdata) if (ifibss->fixed_channel) return; - printk(KERN_DEBUG "%s: No active IBSS STAs - trying to scan for other " - "IBSS networks with same SSID (merge)\n", sdata->name); + sdata_info(sdata, + "No active IBSS STAs - trying to scan for other IBSS networks with same SSID (merge)\n"); ieee80211_request_internal_scan(sdata, ifibss->ssid, ifibss->ssid_len, NULL); @@ -691,8 +673,7 @@ static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata) bssid[0] |= 0x02; } - printk(KERN_DEBUG "%s: Creating new IBSS network, BSSID %pM\n", - sdata->name, bssid); + sdata_info(sdata, "Creating new IBSS network, BSSID %pM\n", bssid); capability = WLAN_CAPABILITY_IBSS; @@ -723,10 +704,7 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) lockdep_assert_held(&ifibss->mtx); active_ibss = ieee80211_sta_active_ibss(sdata); -#ifdef CONFIG_MAC80211_IBSS_DEBUG - printk(KERN_DEBUG "%s: sta_find_ibss (active_ibss=%d)\n", - sdata->name, active_ibss); -#endif /* CONFIG_MAC80211_IBSS_DEBUG */ + ibss_dbg(sdata, "sta_find_ibss (active_ibss=%d)\n", active_ibss); if (active_ibss) return; @@ -749,29 +727,24 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) struct ieee80211_bss *bss; bss = (void *)cbss->priv; -#ifdef CONFIG_MAC80211_IBSS_DEBUG - printk(KERN_DEBUG " sta_find_ibss: selected %pM current " - "%pM\n", cbss->bssid, ifibss->bssid); -#endif /* CONFIG_MAC80211_IBSS_DEBUG */ - - printk(KERN_DEBUG "%s: Selected IBSS BSSID %pM" - " based on configured SSID\n", - sdata->name, cbss->bssid); + ibss_dbg(sdata, + "sta_find_ibss: selected %pM current %pM\n", + cbss->bssid, ifibss->bssid); + sdata_info(sdata, + "Selected IBSS BSSID %pM based on configured SSID\n", + cbss->bssid); ieee80211_sta_join_ibss(sdata, bss); ieee80211_rx_bss_put(local, bss); return; } -#ifdef CONFIG_MAC80211_IBSS_DEBUG - printk(KERN_DEBUG " did not try to join ibss\n"); -#endif /* CONFIG_MAC80211_IBSS_DEBUG */ + ibss_dbg(sdata, "sta_find_ibss: did not try to join ibss\n"); /* Selected IBSS not found in current scan results - try to scan */ if (time_after(jiffies, ifibss->last_scan_completed + IEEE80211_SCAN_INTERVAL)) { - printk(KERN_DEBUG "%s: Trigger new scan to find an IBSS to " - "join\n", sdata->name); + sdata_info(sdata, "Trigger new scan to find an IBSS to join\n"); ieee80211_request_internal_scan(sdata, ifibss->ssid, ifibss->ssid_len, @@ -785,9 +758,8 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) ieee80211_sta_create_ibss(sdata); return; } - printk(KERN_DEBUG "%s: IBSS not allowed on" - " %d MHz\n", sdata->name, - local->hw.conf.channel->center_freq); + sdata_info(sdata, "IBSS not allowed on %d MHz\n", + local->hw.conf.channel->center_freq); /* No IBSS found - decrease scan interval and continue * scanning. */ @@ -822,12 +794,9 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata, tx_last_beacon = drv_tx_last_beacon(local); -#ifdef CONFIG_MAC80211_IBSS_DEBUG - printk(KERN_DEBUG "%s: RX ProbeReq SA=%pM DA=%pM BSSID=%pM" - " (tx_last_beacon=%d)\n", - sdata->name, mgmt->sa, mgmt->da, - mgmt->bssid, tx_last_beacon); -#endif /* CONFIG_MAC80211_IBSS_DEBUG */ + ibss_dbg(sdata, + "RX ProbeReq SA=%pM DA=%pM BSSID=%pM (tx_last_beacon=%d)\n", + mgmt->sa, mgmt->da, mgmt->bssid, tx_last_beacon); if (!tx_last_beacon && is_multicast_ether_addr(mgmt->da)) return; @@ -840,11 +809,8 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata, pos = mgmt->u.probe_req.variable; if (pos[0] != WLAN_EID_SSID || pos + 2 + pos[1] > end) { -#ifdef CONFIG_MAC80211_IBSS_DEBUG - printk(KERN_DEBUG "%s: Invalid SSID IE in ProbeReq " - "from %pM\n", - sdata->name, mgmt->sa); -#endif + ibss_dbg(sdata, "Invalid SSID IE in ProbeReq from %pM\n", + mgmt->sa); return; } if (pos[1] != 0 && @@ -861,10 +827,7 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata, resp = (struct ieee80211_mgmt *) skb->data; memcpy(resp->da, mgmt->sa, ETH_ALEN); -#ifdef CONFIG_MAC80211_IBSS_DEBUG - printk(KERN_DEBUG "%s: Sending ProbeResp to %pM\n", - sdata->name, resp->da); -#endif /* CONFIG_MAC80211_IBSS_DEBUG */ + ibss_dbg(sdata, "Sending ProbeResp to %pM\n", resp->da); IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; ieee80211_tx_skb(sdata, skb); } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 3f3cd50fff1..bb61f7718c4 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -30,6 +30,7 @@ #include <net/mac80211.h> #include "key.h" #include "sta_info.h" +#include "debug.h" struct ieee80211_local; @@ -55,11 +56,14 @@ struct ieee80211_local; #define TU_TO_JIFFIES(x) (usecs_to_jiffies((x) * 1024)) #define TU_TO_EXP_TIME(x) (jiffies + TU_TO_JIFFIES(x)) +/* + * Some APs experience problems when working with U-APSD. Decrease the + * probability of that happening by using legacy mode for all ACs but VO. + * The AP that caused us trouble was a Cisco 4410N. It ignores our + * setting, and always treats non-VO ACs as legacy. + */ #define IEEE80211_DEFAULT_UAPSD_QUEUES \ - (IEEE80211_WMM_IE_STA_QOSINFO_AC_BK | \ - IEEE80211_WMM_IE_STA_QOSINFO_AC_BE | \ - IEEE80211_WMM_IE_STA_QOSINFO_AC_VI | \ - IEEE80211_WMM_IE_STA_QOSINFO_AC_VO) + IEEE80211_WMM_IE_STA_QOSINFO_AC_VO #define IEEE80211_DEFAULT_MAX_SP_LEN \ IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL @@ -81,6 +85,8 @@ struct ieee80211_bss { size_t ssid_len; u8 ssid[IEEE80211_MAX_SSID_LEN]; + u32 device_ts; + u8 dtim_period; bool wmm_used; @@ -203,7 +209,6 @@ typedef unsigned __bitwise__ ieee80211_rx_result; * enum ieee80211_packet_rx_flags - packet RX flags * @IEEE80211_RX_RA_MATCH: frame is destined to interface currently processed * (incl. multicast frames) - * @IEEE80211_RX_IN_SCAN: received while scanning * @IEEE80211_RX_FRAGMENTED: fragmented frame * @IEEE80211_RX_AMSDU: a-MSDU packet * @IEEE80211_RX_MALFORMED_ACTION_FRM: action frame is malformed @@ -213,7 +218,6 @@ typedef unsigned __bitwise__ ieee80211_rx_result; * @rx_flags field of &struct ieee80211_rx_status. */ enum ieee80211_packet_rx_flags { - IEEE80211_RX_IN_SCAN = BIT(0), IEEE80211_RX_RA_MATCH = BIT(1), IEEE80211_RX_FRAGMENTED = BIT(2), IEEE80211_RX_AMSDU = BIT(3), @@ -317,55 +321,30 @@ struct mesh_preq_queue { u8 flags; }; -enum ieee80211_work_type { - IEEE80211_WORK_ABORT, - IEEE80211_WORK_REMAIN_ON_CHANNEL, - IEEE80211_WORK_OFFCHANNEL_TX, -}; - -/** - * enum work_done_result - indicates what to do after work was done - * - * @WORK_DONE_DESTROY: This work item is no longer needed, destroy. - * @WORK_DONE_REQUEUE: This work item was reset to be reused, and - * should be requeued. - */ -enum work_done_result { - WORK_DONE_DESTROY, - WORK_DONE_REQUEUE, -}; +#if HZ/100 == 0 +#define IEEE80211_ROC_MIN_LEFT 1 +#else +#define IEEE80211_ROC_MIN_LEFT (HZ/100) +#endif -struct ieee80211_work { +struct ieee80211_roc_work { struct list_head list; + struct list_head dependents; - struct rcu_head rcu_head; + struct delayed_work work; struct ieee80211_sub_if_data *sdata; - enum work_done_result (*done)(struct ieee80211_work *wk, - struct sk_buff *skb); - struct ieee80211_channel *chan; enum nl80211_channel_type chan_type; - unsigned long timeout; - enum ieee80211_work_type type; + bool started, abort, hw_begun, notified; - bool started; + unsigned long hw_start_time; - union { - struct { - u32 duration; - } remain; - struct { - struct sk_buff *frame; - u32 wait; - bool status; - } offchan_tx; - }; - - size_t data_len; - u8 data[]; + u32 duration, req_duration; + struct sk_buff *frame; + u64 mgmt_tx_cookie; }; /* flags used in struct ieee80211_if_managed.flags */ @@ -399,7 +378,6 @@ struct ieee80211_mgd_auth_data { struct ieee80211_mgd_assoc_data { struct cfg80211_bss *bss; const u8 *supp_rates; - const u8 *ht_operation_ie; unsigned long timeout; int tries; @@ -414,6 +392,8 @@ struct ieee80211_mgd_assoc_data { bool sent_assoc; bool synced; + u8 ap_ht_param; + size_t ie_len; u8 ie[]; }; @@ -532,6 +512,7 @@ struct ieee80211_if_ibss { bool privacy; bool control_port; + unsigned int auth_frame_registrations; u8 bssid[ETH_ALEN] __aligned(2); u8 ssid[IEEE80211_MAX_SSID_LEN]; @@ -701,6 +682,9 @@ struct ieee80211_sub_if_data { /* TID bitmap for NoAck policy */ u16 noack_map; + /* bit field of ACM bits (BIT(802.1D tag)) */ + u8 wmm_acm; + struct ieee80211_key __rcu *keys[NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS]; struct ieee80211_key __rcu *default_unicast_key; struct ieee80211_key __rcu *default_multicast_key; @@ -847,13 +831,6 @@ struct ieee80211_local { const struct ieee80211_ops *ops; /* - * work stuff, potentially off-channel (in the future) - */ - struct list_head work_list; - struct timer_list work_timer; - struct work_struct work_work; - - /* * private workqueue to mac80211. mac80211 makes this accessible * via ieee80211_queue_work() */ @@ -912,6 +889,9 @@ struct ieee80211_local { /* device is started */ bool started; + /* device is during a HW reconfig */ + bool in_reconfig; + /* wowlan is enabled -- don't reconfig on resume */ bool wowlan; @@ -985,14 +965,14 @@ struct ieee80211_local { int scan_channel_idx; int scan_ies_len; - bool sched_scanning; struct ieee80211_sched_scan_ies sched_scan_ies; struct work_struct sched_scan_stopped_work; + struct ieee80211_sub_if_data __rcu *sched_scan_sdata; unsigned long leave_oper_channel_time; enum mac80211_scan_state next_scan_state; struct delayed_work scan_work; - struct ieee80211_sub_if_data *scan_sdata; + struct ieee80211_sub_if_data __rcu *scan_sdata; enum nl80211_channel_type _oper_channel_type; struct ieee80211_channel *oper_channel, *csa_channel; @@ -1034,7 +1014,6 @@ struct ieee80211_local { unsigned int rx_handlers_drop_nullfunc; unsigned int rx_handlers_drop_defrag; unsigned int rx_handlers_drop_short; - unsigned int rx_handlers_drop_passive_scan; unsigned int tx_expand_skb_head; unsigned int tx_expand_skb_head_cloned; unsigned int rx_expand_skb_head; @@ -1050,7 +1029,6 @@ struct ieee80211_local { int total_ps_buffered; /* total number of all buffered unicast and * multicast packets for power saving stations */ - unsigned int wmm_acm; /* bit field of ACM bits (BIT(802.1D tag)) */ bool pspolling; bool offchannel_ps_enabled; @@ -1087,14 +1065,12 @@ struct ieee80211_local { } debugfs; #endif - struct ieee80211_channel *hw_roc_channel; - struct net_device *hw_roc_dev; - struct sk_buff *hw_roc_skb, *hw_roc_skb_for_status; + /* + * Remain-on-channel support + */ + struct list_head roc_list; struct work_struct hw_roc_start, hw_roc_done; - enum nl80211_channel_type hw_roc_channel_type; - unsigned int hw_roc_duration; - u32 hw_roc_cookie; - bool hw_roc_for_tx; + unsigned long hw_roc_start_time; struct idr ack_status_frames; spinlock_t ack_status_lock; @@ -1114,6 +1090,12 @@ IEEE80211_DEV_TO_SUB_IF(struct net_device *dev) return netdev_priv(dev); } +static inline struct ieee80211_sub_if_data * +IEEE80211_WDEV_TO_SUB_IF(struct wireless_dev *wdev) +{ + return container_of(wdev, struct ieee80211_sub_if_data, wdev); +} + /* this struct represents 802.11n's RA/TID combination */ struct ieee80211_ra_tid { u8 ra[ETH_ALEN]; @@ -1264,8 +1246,7 @@ int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req); void ieee80211_scan_cancel(struct ieee80211_local *local); void ieee80211_run_deferred_scan(struct ieee80211_local *local); -ieee80211_rx_result -ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); +void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb); void ieee80211_mlme_notify_scan_completed(struct ieee80211_local *local); struct ieee80211_bss * @@ -1290,19 +1271,23 @@ void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local, bool offchannel_ps_enable); void ieee80211_offchannel_return(struct ieee80211_local *local, bool offchannel_ps_disable); -void ieee80211_hw_roc_setup(struct ieee80211_local *local); +void ieee80211_roc_setup(struct ieee80211_local *local); +void ieee80211_start_next_roc(struct ieee80211_local *local); +void ieee80211_roc_purge(struct ieee80211_sub_if_data *sdata); +void ieee80211_roc_notify_destroy(struct ieee80211_roc_work *roc); +void ieee80211_sw_roc_work(struct work_struct *work); +void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc); /* interface handling */ int ieee80211_iface_init(void); void ieee80211_iface_exit(void); int ieee80211_if_add(struct ieee80211_local *local, const char *name, - struct net_device **new_dev, enum nl80211_iftype type, + struct wireless_dev **new_wdev, enum nl80211_iftype type, struct vif_params *params); int ieee80211_if_change_type(struct ieee80211_sub_if_data *sdata, enum nl80211_iftype type); void ieee80211_if_remove(struct ieee80211_sub_if_data *sdata); void ieee80211_remove_interfaces(struct ieee80211_local *local); -u32 __ieee80211_recalc_idle(struct ieee80211_local *local); void ieee80211_recalc_idle(struct ieee80211_local *local); void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata, const int offset); @@ -1499,18 +1484,12 @@ u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, struct ieee80211_channel *channel, enum nl80211_channel_type channel_type, u16 prot_mode); - -/* internal work items */ -void ieee80211_work_init(struct ieee80211_local *local); -void ieee80211_add_work(struct ieee80211_work *wk); -void free_work(struct ieee80211_work *wk); -void ieee80211_work_purge(struct ieee80211_sub_if_data *sdata); -int ieee80211_wk_remain_on_channel(struct ieee80211_sub_if_data *sdata, - struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type, - unsigned int duration, u64 *cookie); -int ieee80211_wk_cancel_remain_on_channel( - struct ieee80211_sub_if_data *sdata, u64 cookie); +u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, + u32 cap); +int ieee80211_add_srates_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, bool need_basic); +int ieee80211_add_ext_srates_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, bool need_basic); /* channel management */ enum ieee80211_chan_mode { diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 8664111d056..bfb57dcc153 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -43,6 +43,128 @@ */ +static u32 ieee80211_idle_off(struct ieee80211_local *local, + const char *reason) +{ + if (!(local->hw.conf.flags & IEEE80211_CONF_IDLE)) + return 0; + + local->hw.conf.flags &= ~IEEE80211_CONF_IDLE; + return IEEE80211_CONF_CHANGE_IDLE; +} + +static u32 ieee80211_idle_on(struct ieee80211_local *local) +{ + if (local->hw.conf.flags & IEEE80211_CONF_IDLE) + return 0; + + drv_flush(local, false); + + local->hw.conf.flags |= IEEE80211_CONF_IDLE; + return IEEE80211_CONF_CHANGE_IDLE; +} + +static u32 __ieee80211_recalc_idle(struct ieee80211_local *local) +{ + struct ieee80211_sub_if_data *sdata; + int count = 0; + bool working = false, scanning = false; + unsigned int led_trig_start = 0, led_trig_stop = 0; + struct ieee80211_roc_work *roc; + +#ifdef CONFIG_PROVE_LOCKING + WARN_ON(debug_locks && !lockdep_rtnl_is_held() && + !lockdep_is_held(&local->iflist_mtx)); +#endif + lockdep_assert_held(&local->mtx); + + list_for_each_entry(sdata, &local->interfaces, list) { + if (!ieee80211_sdata_running(sdata)) { + sdata->vif.bss_conf.idle = true; + continue; + } + + sdata->old_idle = sdata->vif.bss_conf.idle; + + /* do not count disabled managed interfaces */ + if (sdata->vif.type == NL80211_IFTYPE_STATION && + !sdata->u.mgd.associated && + !sdata->u.mgd.auth_data && + !sdata->u.mgd.assoc_data) { + sdata->vif.bss_conf.idle = true; + continue; + } + /* do not count unused IBSS interfaces */ + if (sdata->vif.type == NL80211_IFTYPE_ADHOC && + !sdata->u.ibss.ssid_len) { + sdata->vif.bss_conf.idle = true; + continue; + } + /* count everything else */ + sdata->vif.bss_conf.idle = false; + count++; + } + + if (!local->ops->remain_on_channel) { + list_for_each_entry(roc, &local->roc_list, list) { + working = true; + roc->sdata->vif.bss_conf.idle = false; + } + } + + sdata = rcu_dereference_protected(local->scan_sdata, + lockdep_is_held(&local->mtx)); + if (sdata && !(local->hw.flags & IEEE80211_HW_SCAN_WHILE_IDLE)) { + scanning = true; + sdata->vif.bss_conf.idle = false; + } + + list_for_each_entry(sdata, &local->interfaces, list) { + if (sdata->vif.type == NL80211_IFTYPE_MONITOR || + sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + continue; + if (sdata->old_idle == sdata->vif.bss_conf.idle) + continue; + if (!ieee80211_sdata_running(sdata)) + continue; + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_IDLE); + } + + if (working || scanning) + led_trig_start |= IEEE80211_TPT_LEDTRIG_FL_WORK; + else + led_trig_stop |= IEEE80211_TPT_LEDTRIG_FL_WORK; + + if (count) + led_trig_start |= IEEE80211_TPT_LEDTRIG_FL_CONNECTED; + else + led_trig_stop |= IEEE80211_TPT_LEDTRIG_FL_CONNECTED; + + ieee80211_mod_tpt_led_trig(local, led_trig_start, led_trig_stop); + + if (working) + return ieee80211_idle_off(local, "working"); + if (scanning) + return ieee80211_idle_off(local, "scanning"); + if (!count) + return ieee80211_idle_on(local); + else + return ieee80211_idle_off(local, "in use"); + + return 0; +} + +void ieee80211_recalc_idle(struct ieee80211_local *local) +{ + u32 chg; + + mutex_lock(&local->iflist_mtx); + chg = __ieee80211_recalc_idle(local); + mutex_unlock(&local->iflist_mtx); + if (chg) + ieee80211_hw_config(local, chg); +} + static int ieee80211_change_mtu(struct net_device *dev, int new_mtu) { int meshhdrlen; @@ -57,9 +179,6 @@ static int ieee80211_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; } -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - printk(KERN_DEBUG "%s: setting MTU %d\n", dev->name, new_mtu); -#endif /* CONFIG_MAC80211_VERBOSE_DEBUG */ dev->mtu = new_mtu; return 0; } @@ -100,15 +219,12 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *nsdata; - struct net_device *dev = sdata->dev; ASSERT_RTNL(); /* we hold the RTNL here so can safely walk the list */ list_for_each_entry(nsdata, &local->interfaces, list) { - struct net_device *ndev = nsdata->dev; - - if (ndev != dev && ieee80211_sdata_running(nsdata)) { + if (nsdata != sdata && ieee80211_sdata_running(nsdata)) { /* * Allow only a single IBSS interface to be up at any * time. This is restricted because beacon distribution @@ -127,7 +243,8 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata, * The remaining checks are only performed for interfaces * with the same MAC address. */ - if (!ether_addr_equal(dev->dev_addr, ndev->dev_addr)) + if (!ether_addr_equal(sdata->vif.addr, + nsdata->vif.addr)) continue; /* @@ -217,17 +334,21 @@ static void ieee80211_set_default_queues(struct ieee80211_sub_if_data *sdata) static int ieee80211_add_virtual_monitor(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; - int ret; + int ret = 0; if (!(local->hw.flags & IEEE80211_HW_WANT_MONITOR_VIF)) return 0; + mutex_lock(&local->iflist_mtx); + if (local->monitor_sdata) - return 0; + goto out_unlock; sdata = kzalloc(sizeof(*sdata) + local->hw.vif_data_size, GFP_KERNEL); - if (!sdata) - return -ENOMEM; + if (!sdata) { + ret = -ENOMEM; + goto out_unlock; + } /* set up data */ sdata->local = local; @@ -241,18 +362,19 @@ static int ieee80211_add_virtual_monitor(struct ieee80211_local *local) if (WARN_ON(ret)) { /* ok .. stupid driver, it asked for this! */ kfree(sdata); - return ret; + goto out_unlock; } ret = ieee80211_check_queues(sdata); if (ret) { kfree(sdata); - return ret; + goto out_unlock; } rcu_assign_pointer(local->monitor_sdata, sdata); - - return 0; + out_unlock: + mutex_unlock(&local->iflist_mtx); + return ret; } static void ieee80211_del_virtual_monitor(struct ieee80211_local *local) @@ -262,10 +384,12 @@ static void ieee80211_del_virtual_monitor(struct ieee80211_local *local) if (!(local->hw.flags & IEEE80211_HW_WANT_MONITOR_VIF)) return; - sdata = rtnl_dereference(local->monitor_sdata); + mutex_lock(&local->iflist_mtx); + sdata = rcu_dereference_protected(local->monitor_sdata, + lockdep_is_held(&local->iflist_mtx)); if (!sdata) - return; + goto out_unlock; rcu_assign_pointer(local->monitor_sdata, NULL); synchronize_net(); @@ -273,6 +397,8 @@ static void ieee80211_del_virtual_monitor(struct ieee80211_local *local) drv_remove_interface(local, sdata); kfree(sdata); + out_unlock: + mutex_unlock(&local->iflist_mtx); } /* @@ -520,7 +646,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, clear_bit(SDATA_STATE_RUNNING, &sdata->state); - if (local->scan_sdata == sdata) + if (rcu_access_pointer(local->scan_sdata) == sdata) ieee80211_scan_cancel(local); /* @@ -528,10 +654,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, */ netif_tx_stop_all_queues(sdata->dev); - /* - * Purge work for this interface. - */ - ieee80211_work_purge(sdata); + ieee80211_roc_purge(sdata); /* * Remove all stations associated with this interface. @@ -637,18 +760,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, ieee80211_configure_filter(local); break; default: - mutex_lock(&local->mtx); - if (local->hw_roc_dev == sdata->dev && - local->hw_roc_channel) { - /* ignore return value since this is racy */ - drv_cancel_remain_on_channel(local); - ieee80211_queue_work(&local->hw, &local->hw_roc_done); - } - mutex_unlock(&local->mtx); - - flush_work(&local->hw_roc_start); - flush_work(&local->hw_roc_done); - flush_work(&sdata->work); /* * When we get here, the interface is marked down. @@ -823,7 +934,7 @@ static u16 ieee80211_monitor_select_queue(struct net_device *dev, hdr = (void *)((u8 *)skb->data + le16_to_cpu(rtap->it_len)); - return ieee80211_select_queue_80211(local, skb, hdr); + return ieee80211_select_queue_80211(sdata, skb, hdr); } static const struct net_device_ops ieee80211_monitorif_ops = { @@ -1238,7 +1349,7 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local, if (__ffs64(mask) + hweight64(mask) != fls64(mask)) { /* not a contiguous mask ... not handled now! */ - printk(KERN_DEBUG "not contiguous\n"); + pr_info("not contiguous\n"); break; } @@ -1284,7 +1395,7 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local, } int ieee80211_if_add(struct ieee80211_local *local, const char *name, - struct net_device **new_dev, enum nl80211_iftype type, + struct wireless_dev **new_wdev, enum nl80211_iftype type, struct vif_params *params) { struct net_device *ndev; @@ -1364,6 +1475,8 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sdata->u.mgd.use_4addr = params->use_4addr; } + ndev->features |= local->hw.netdev_features; + ret = register_netdevice(ndev); if (ret) goto fail; @@ -1372,8 +1485,8 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, list_add_tail_rcu(&sdata->list, &local->interfaces); mutex_unlock(&local->iflist_mtx); - if (new_dev) - *new_dev = ndev; + if (new_wdev) + *new_wdev = &sdata->wdev; return 0; @@ -1421,138 +1534,6 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) list_del(&unreg_list); } -static u32 ieee80211_idle_off(struct ieee80211_local *local, - const char *reason) -{ - if (!(local->hw.conf.flags & IEEE80211_CONF_IDLE)) - return 0; - -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - wiphy_debug(local->hw.wiphy, "device no longer idle - %s\n", reason); -#endif - - local->hw.conf.flags &= ~IEEE80211_CONF_IDLE; - return IEEE80211_CONF_CHANGE_IDLE; -} - -static u32 ieee80211_idle_on(struct ieee80211_local *local) -{ - if (local->hw.conf.flags & IEEE80211_CONF_IDLE) - return 0; - -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - wiphy_debug(local->hw.wiphy, "device now idle\n"); -#endif - - drv_flush(local, false); - - local->hw.conf.flags |= IEEE80211_CONF_IDLE; - return IEEE80211_CONF_CHANGE_IDLE; -} - -u32 __ieee80211_recalc_idle(struct ieee80211_local *local) -{ - struct ieee80211_sub_if_data *sdata; - int count = 0; - bool working = false, scanning = false, hw_roc = false; - struct ieee80211_work *wk; - unsigned int led_trig_start = 0, led_trig_stop = 0; - -#ifdef CONFIG_PROVE_LOCKING - WARN_ON(debug_locks && !lockdep_rtnl_is_held() && - !lockdep_is_held(&local->iflist_mtx)); -#endif - lockdep_assert_held(&local->mtx); - - list_for_each_entry(sdata, &local->interfaces, list) { - if (!ieee80211_sdata_running(sdata)) { - sdata->vif.bss_conf.idle = true; - continue; - } - - sdata->old_idle = sdata->vif.bss_conf.idle; - - /* do not count disabled managed interfaces */ - if (sdata->vif.type == NL80211_IFTYPE_STATION && - !sdata->u.mgd.associated && - !sdata->u.mgd.auth_data && - !sdata->u.mgd.assoc_data) { - sdata->vif.bss_conf.idle = true; - continue; - } - /* do not count unused IBSS interfaces */ - if (sdata->vif.type == NL80211_IFTYPE_ADHOC && - !sdata->u.ibss.ssid_len) { - sdata->vif.bss_conf.idle = true; - continue; - } - /* count everything else */ - sdata->vif.bss_conf.idle = false; - count++; - } - - list_for_each_entry(wk, &local->work_list, list) { - working = true; - wk->sdata->vif.bss_conf.idle = false; - } - - if (local->scan_sdata && - !(local->hw.flags & IEEE80211_HW_SCAN_WHILE_IDLE)) { - scanning = true; - local->scan_sdata->vif.bss_conf.idle = false; - } - - if (local->hw_roc_channel) - hw_roc = true; - - list_for_each_entry(sdata, &local->interfaces, list) { - if (sdata->vif.type == NL80211_IFTYPE_MONITOR || - sdata->vif.type == NL80211_IFTYPE_AP_VLAN) - continue; - if (sdata->old_idle == sdata->vif.bss_conf.idle) - continue; - if (!ieee80211_sdata_running(sdata)) - continue; - ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_IDLE); - } - - if (working || scanning || hw_roc) - led_trig_start |= IEEE80211_TPT_LEDTRIG_FL_WORK; - else - led_trig_stop |= IEEE80211_TPT_LEDTRIG_FL_WORK; - - if (count) - led_trig_start |= IEEE80211_TPT_LEDTRIG_FL_CONNECTED; - else - led_trig_stop |= IEEE80211_TPT_LEDTRIG_FL_CONNECTED; - - ieee80211_mod_tpt_led_trig(local, led_trig_start, led_trig_stop); - - if (hw_roc) - return ieee80211_idle_off(local, "hw remain-on-channel"); - if (working) - return ieee80211_idle_off(local, "working"); - if (scanning) - return ieee80211_idle_off(local, "scanning"); - if (!count) - return ieee80211_idle_on(local); - else - return ieee80211_idle_off(local, "in use"); - - return 0; -} - -void ieee80211_recalc_idle(struct ieee80211_local *local) -{ - u32 chg; - - mutex_lock(&local->iflist_mtx); - chg = __ieee80211_recalc_idle(local); - mutex_unlock(&local->iflist_mtx); - if (chg) - ieee80211_hw_config(local, chg); -} - static int netdev_notify(struct notifier_block *nb, unsigned long state, void *ndev) diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 5bb600d93d7..7ae678ba5d6 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -139,7 +139,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) } if (ret != -ENOSPC && ret != -EOPNOTSUPP) - wiphy_err(key->local->hw.wiphy, + sdata_err(sdata, "failed to set key (%d, %pM) to hardware (%d)\n", key->conf.keyidx, sta ? sta->sta.addr : bcast_addr, ret); @@ -186,7 +186,7 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) sta ? &sta->sta : NULL, &key->conf); if (ret) - wiphy_err(key->local->hw.wiphy, + sdata_err(sdata, "failed to remove key (%d, %pM) from hardware (%d)\n", key->conf.keyidx, sta ? sta->sta.addr : bcast_addr, ret); @@ -194,26 +194,6 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; } -void ieee80211_key_removed(struct ieee80211_key_conf *key_conf) -{ - struct ieee80211_key *key; - - key = container_of(key_conf, struct ieee80211_key, conf); - - might_sleep(); - assert_key_lock(key->local); - - key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; - - /* - * Flush TX path to avoid attempts to use this key - * after this function returns. Until then, drivers - * must be prepared to handle the key. - */ - synchronize_rcu(); -} -EXPORT_SYMBOL_GPL(ieee80211_key_removed); - static void __ieee80211_set_default_key(struct ieee80211_sub_if_data *sdata, int idx, bool uni, bool multi) { diff --git a/net/mac80211/led.c b/net/mac80211/led.c index 1bf7903496f..bcffa690312 100644 --- a/net/mac80211/led.c +++ b/net/mac80211/led.c @@ -276,7 +276,7 @@ static void ieee80211_stop_tpt_led_trig(struct ieee80211_local *local) read_lock(&tpt_trig->trig.leddev_list_lock); list_for_each_entry(led_cdev, &tpt_trig->trig.led_cdevs, trig_list) - led_brightness_set(led_cdev, LED_OFF); + led_set_brightness(led_cdev, LED_OFF); read_unlock(&tpt_trig->trig.leddev_list_lock); } diff --git a/net/mac80211/main.c b/net/mac80211/main.c index f5548e95325..c26e231c733 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -322,7 +322,8 @@ static void ieee80211_restart_work(struct work_struct *work) mutex_lock(&local->mtx); WARN(test_bit(SCAN_HW_SCANNING, &local->scanning) || - local->sched_scanning, + rcu_dereference_protected(local->sched_scan_sdata, + lockdep_is_held(&local->mtx)), "%s called with hardware scan in progress\n", __func__); mutex_unlock(&local->mtx); @@ -345,6 +346,13 @@ void ieee80211_restart_hw(struct ieee80211_hw *hw) ieee80211_stop_queues_by_reason(hw, IEEE80211_QUEUE_STOP_REASON_SUSPEND); + /* + * Stop all Rx during the reconfig. We don't want state changes + * or driver callbacks while this is in progress. + */ + local->in_reconfig = true; + barrier(); + schedule_work(&local->restart_work); } EXPORT_SYMBOL(ieee80211_restart_hw); @@ -455,7 +463,9 @@ static const struct ieee80211_txrx_stypes ieee80211_default_mgmt_stypes[NUM_NL80211_IFTYPES] = { [NL80211_IFTYPE_ADHOC] = { .tx = 0xffff, - .rx = BIT(IEEE80211_STYPE_ACTION >> 4), + .rx = BIT(IEEE80211_STYPE_ACTION >> 4) | + BIT(IEEE80211_STYPE_AUTH >> 4) | + BIT(IEEE80211_STYPE_DEAUTH >> 4), }, [NL80211_IFTYPE_STATION] = { .tx = 0xffff, @@ -578,7 +588,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, local->hw.priv = (char *)local + ALIGN(sizeof(*local), NETDEV_ALIGN); - BUG_ON(!ops->tx && !ops->tx_frags); + BUG_ON(!ops->tx); BUG_ON(!ops->start); BUG_ON(!ops->stop); BUG_ON(!ops->config); @@ -625,8 +635,6 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, INIT_DELAYED_WORK(&local->scan_work, ieee80211_scan_work); - ieee80211_work_init(local); - INIT_WORK(&local->restart_work, ieee80211_restart_work); INIT_WORK(&local->reconfig_filter, ieee80211_reconfig_filter); @@ -669,7 +677,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, ieee80211_led_names(local); - ieee80211_hw_roc_setup(local); + ieee80211_roc_setup(local); return &local->hw; } @@ -681,7 +689,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) int result, i; enum ieee80211_band band; int channels, max_bitrates; - bool supp_ht; + bool supp_ht, supp_vht; + netdev_features_t feature_whitelist; static const u32 cipher_suites[] = { /* keep WEP first, it may be removed below */ WLAN_CIPHER_SUITE_WEP40, @@ -698,16 +707,21 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->hw.offchannel_tx_hw_queue >= local->hw.queues)) return -EINVAL; - if ((hw->wiphy->wowlan.flags || hw->wiphy->wowlan.n_patterns) #ifdef CONFIG_PM - && (!local->ops->suspend || !local->ops->resume) -#endif - ) + if ((hw->wiphy->wowlan.flags || hw->wiphy->wowlan.n_patterns) && + (!local->ops->suspend || !local->ops->resume)) return -EINVAL; +#endif if ((hw->flags & IEEE80211_HW_SCAN_WHILE_IDLE) && !local->ops->hw_scan) return -EINVAL; + /* Only HW csum features are currently compatible with mac80211 */ + feature_whitelist = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_HW_CSUM; + if (WARN_ON(hw->netdev_features & ~feature_whitelist)) + return -EINVAL; + if (hw->max_report_rates == 0) hw->max_report_rates = hw->max_rates; @@ -719,6 +733,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) channels = 0; max_bitrates = 0; supp_ht = false; + supp_vht = false; for (band = 0; band < IEEE80211_NUM_BANDS; band++) { struct ieee80211_supported_band *sband; @@ -736,6 +751,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (max_bitrates < sband->n_bitrates) max_bitrates = sband->n_bitrates; supp_ht = supp_ht || sband->ht_cap.ht_supported; + supp_vht = supp_vht || sband->vht_cap.vht_supported; } local->int_scan_req = kzalloc(sizeof(*local->int_scan_req) + @@ -811,6 +827,10 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (supp_ht) local->scan_ies_len += 2 + sizeof(struct ieee80211_ht_cap); + if (supp_vht) + local->scan_ies_len += + 2 + sizeof(struct ieee80211_vht_capabilities); + if (!local->ops->hw_scan) { /* For hw_scan, driver needs to set these up. */ local->hw.wiphy->max_scan_ssids = 4; @@ -1009,12 +1029,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) rtnl_unlock(); - /* - * Now all work items will be gone, but the - * timer might still be armed, so delete it - */ - del_timer_sync(&local->work_timer); - cancel_work_sync(&local->restart_work); cancel_work_sync(&local->reconfig_filter); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 2913113c583..85572353a7e 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -133,7 +133,7 @@ bool mesh_peer_accepts_plinks(struct ieee802_11_elems *ie) } /** - * mesh_accept_plinks_update: update accepting_plink in local mesh beacons + * mesh_accept_plinks_update - update accepting_plink in local mesh beacons * * @sdata: mesh interface in which mesh beacons are going to be updated */ @@ -443,7 +443,7 @@ static void ieee80211_mesh_path_root_timer(unsigned long data) void ieee80211_mesh_root_setup(struct ieee80211_if_mesh *ifmsh) { - if (ifmsh->mshcfg.dot11MeshHWMPRootMode) + if (ifmsh->mshcfg.dot11MeshHWMPRootMode > IEEE80211_ROOTMODE_ROOT) set_bit(MESH_WORK_ROOT, &ifmsh->wrkq_flags); else { clear_bit(MESH_WORK_ROOT, &ifmsh->wrkq_flags); @@ -523,11 +523,6 @@ static void ieee80211_mesh_housekeeping(struct ieee80211_sub_if_data *sdata, { bool free_plinks; -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - printk(KERN_DEBUG "%s: running mesh housekeeping\n", - sdata->name); -#endif - ieee80211_sta_expire(sdata, IEEE80211_MESH_PEER_INACTIVITY_LIMIT); mesh_path_expire(sdata); @@ -542,11 +537,17 @@ static void ieee80211_mesh_housekeeping(struct ieee80211_sub_if_data *sdata, static void ieee80211_mesh_rootpath(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + u32 interval; mesh_path_tx_root_frame(sdata); + + if (ifmsh->mshcfg.dot11MeshHWMPRootMode == IEEE80211_PROACTIVE_RANN) + interval = ifmsh->mshcfg.dot11MeshHWMPRannInterval; + else + interval = ifmsh->mshcfg.dot11MeshHWMProotInterval; + mod_timer(&ifmsh->mesh_path_root_timer, - round_jiffies(TU_TO_EXP_TIME( - ifmsh->mshcfg.dot11MeshHWMPRannInterval))); + round_jiffies(TU_TO_EXP_TIME(interval))); } #ifdef CONFIG_PM @@ -621,6 +622,7 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) del_timer_sync(&sdata->u.mesh.housekeeping_timer); del_timer_sync(&sdata->u.mesh.mesh_path_root_timer); + del_timer_sync(&sdata->u.mesh.mesh_path_timer); /* * If the timer fired while we waited for it, it will have * requeued the work. Now the work will be running again @@ -633,6 +635,8 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) local->fif_other_bss--; atomic_dec(&local->iff_allmultis); ieee80211_configure_filter(local); + + sdata->u.mesh.timers_running = 0; } static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index e3642756f8f..faaa39bcfd1 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -104,6 +104,7 @@ enum mesh_deferred_task_flags { * an mpath to a hash bucket on a path table. * @rann_snd_addr: the RANN sender address * @rann_metric: the aggregated path metric towards the root node + * @last_preq_to_root: Timestamp of last PREQ sent to root * @is_root: the destination station of this path is a root node * @is_gate: the destination station of this path is a mesh gate * @@ -131,6 +132,7 @@ struct mesh_path { spinlock_t state_lock; u8 rann_snd_addr[ETH_ALEN]; u32 rann_metric; + unsigned long last_preq_to_root; bool is_root; bool is_gate; }; @@ -245,7 +247,7 @@ void mesh_rmc_free(struct ieee80211_sub_if_data *sdata); int mesh_rmc_init(struct ieee80211_sub_if_data *sdata); void ieee80211s_init(void); void ieee80211s_update_metric(struct ieee80211_local *local, - struct sta_info *stainfo, struct sk_buff *skb); + struct sta_info *sta, struct sk_buff *skb); void ieee80211s_stop(void); void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata); void ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata); diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 9b59658e865..494bc39f61a 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -13,13 +13,6 @@ #include "wme.h" #include "mesh.h" -#ifdef CONFIG_MAC80211_VERBOSE_MHWMP_DEBUG -#define mhwmp_dbg(fmt, args...) \ - printk(KERN_DEBUG "Mesh HWMP (%s): " fmt "\n", sdata->name, ##args) -#else -#define mhwmp_dbg(fmt, args...) do { (void)(0); } while (0) -#endif - #define TEST_FRAME_LEN 8192 #define MAX_METRIC 0xffffffff #define ARITH_SHIFT 8 @@ -98,6 +91,8 @@ static inline u32 u16_field_get(u8 *preq_elem, int offset, bool ae) #define max_preq_retries(s) (s->u.mesh.mshcfg.dot11MeshHWMPmaxPREQretries) #define disc_timeout_jiff(s) \ msecs_to_jiffies(sdata->u.mesh.mshcfg.min_discovery_timeout) +#define root_path_confirmation_jiffies(s) \ + msecs_to_jiffies(sdata->u.mesh.mshcfg.dot11MeshHWMPconfirmationInterval) enum mpath_frame_type { MPATH_PREQ = 0, @@ -142,19 +137,19 @@ static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags, switch (action) { case MPATH_PREQ: - mhwmp_dbg("sending PREQ to %pM", target); + mhwmp_dbg(sdata, "sending PREQ to %pM\n", target); ie_len = 37; pos = skb_put(skb, 2 + ie_len); *pos++ = WLAN_EID_PREQ; break; case MPATH_PREP: - mhwmp_dbg("sending PREP to %pM", target); + mhwmp_dbg(sdata, "sending PREP to %pM\n", target); ie_len = 31; pos = skb_put(skb, 2 + ie_len); *pos++ = WLAN_EID_PREP; break; case MPATH_RANN: - mhwmp_dbg("sending RANN from %pM", orig_addr); + mhwmp_dbg(sdata, "sending RANN from %pM\n", orig_addr); ie_len = sizeof(struct ieee80211_rann_ie); pos = skb_put(skb, 2 + ie_len); *pos++ = WLAN_EID_RANN; @@ -303,7 +298,7 @@ int mesh_path_error_tx(u8 ttl, u8 *target, __le32 target_sn, } void ieee80211s_update_metric(struct ieee80211_local *local, - struct sta_info *stainfo, struct sk_buff *skb) + struct sta_info *sta, struct sk_buff *skb) { struct ieee80211_tx_info *txinfo = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; @@ -315,15 +310,14 @@ void ieee80211s_update_metric(struct ieee80211_local *local, failed = !(txinfo->flags & IEEE80211_TX_STAT_ACK); /* moving average, scaled to 100 */ - stainfo->fail_avg = ((80 * stainfo->fail_avg + 5) / 100 + 20 * failed); - if (stainfo->fail_avg > 95) - mesh_plink_broken(stainfo); + sta->fail_avg = ((80 * sta->fail_avg + 5) / 100 + 20 * failed); + if (sta->fail_avg > 95) + mesh_plink_broken(sta); } static u32 airtime_link_metric_get(struct ieee80211_local *local, struct sta_info *sta) { - struct ieee80211_supported_band *sband; struct rate_info rinfo; /* This should be adjusted for each device */ int device_constant = 1 << ARITH_SHIFT; @@ -333,8 +327,6 @@ static u32 airtime_link_metric_get(struct ieee80211_local *local, u32 tx_time, estimated_retx; u64 result; - sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; - if (sta->fail_avg >= 100) return MAX_METRIC; @@ -519,10 +511,11 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, struct mesh_path *mpath = NULL; u8 *target_addr, *orig_addr; const u8 *da; - u8 target_flags, ttl; - u32 orig_sn, target_sn, lifetime; + u8 target_flags, ttl, flags; + u32 orig_sn, target_sn, lifetime, orig_metric; bool reply = false; bool forward = true; + bool root_is_gate; /* Update target SN, if present */ target_addr = PREQ_IE_TARGET_ADDR(preq_elem); @@ -530,11 +523,15 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, target_sn = PREQ_IE_TARGET_SN(preq_elem); orig_sn = PREQ_IE_ORIG_SN(preq_elem); target_flags = PREQ_IE_TARGET_F(preq_elem); + orig_metric = metric; + /* Proactive PREQ gate announcements */ + flags = PREQ_IE_FLAGS(preq_elem); + root_is_gate = !!(flags & RANN_FLAG_IS_GATE); - mhwmp_dbg("received PREQ from %pM", orig_addr); + mhwmp_dbg(sdata, "received PREQ from %pM\n", orig_addr); if (ether_addr_equal(target_addr, sdata->vif.addr)) { - mhwmp_dbg("PREQ is for us"); + mhwmp_dbg(sdata, "PREQ is for us\n"); forward = false; reply = true; metric = 0; @@ -544,6 +541,22 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, target_sn = ++ifmsh->sn; ifmsh->last_sn_update = jiffies; } + } else if (is_broadcast_ether_addr(target_addr) && + (target_flags & IEEE80211_PREQ_TO_FLAG)) { + rcu_read_lock(); + mpath = mesh_path_lookup(orig_addr, sdata); + if (mpath) { + if (flags & IEEE80211_PREQ_PROACTIVE_PREP_FLAG) { + reply = true; + target_addr = sdata->vif.addr; + target_sn = ++ifmsh->sn; + metric = 0; + ifmsh->last_sn_update = jiffies; + } + if (root_is_gate) + mesh_path_add_gate(mpath); + } + rcu_read_unlock(); } else { rcu_read_lock(); mpath = mesh_path_lookup(target_addr, sdata); @@ -570,19 +583,20 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, lifetime = PREQ_IE_LIFETIME(preq_elem); ttl = ifmsh->mshcfg.element_ttl; if (ttl != 0) { - mhwmp_dbg("replying to the PREQ"); + mhwmp_dbg(sdata, "replying to the PREQ\n"); mesh_path_sel_frame_tx(MPATH_PREP, 0, orig_addr, cpu_to_le32(orig_sn), 0, target_addr, cpu_to_le32(target_sn), mgmt->sa, 0, ttl, cpu_to_le32(lifetime), cpu_to_le32(metric), 0, sdata); - } else + } else { ifmsh->mshstats.dropped_frames_ttl++; + } } if (forward && ifmsh->mshcfg.dot11MeshForwarding) { u32 preq_id; - u8 hopcount, flags; + u8 hopcount; ttl = PREQ_IE_TTL(preq_elem); lifetime = PREQ_IE_LIFETIME(preq_elem); @@ -590,13 +604,19 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, ifmsh->mshstats.dropped_frames_ttl++; return; } - mhwmp_dbg("forwarding the PREQ from %pM", orig_addr); + mhwmp_dbg(sdata, "forwarding the PREQ from %pM\n", orig_addr); --ttl; - flags = PREQ_IE_FLAGS(preq_elem); preq_id = PREQ_IE_PREQ_ID(preq_elem); hopcount = PREQ_IE_HOPCOUNT(preq_elem) + 1; da = (mpath && mpath->is_root) ? mpath->rann_snd_addr : broadcast_addr; + + if (flags & IEEE80211_PREQ_PROACTIVE_PREP_FLAG) { + target_addr = PREQ_IE_TARGET_ADDR(preq_elem); + target_sn = PREQ_IE_TARGET_SN(preq_elem); + metric = orig_metric; + } + mesh_path_sel_frame_tx(MPATH_PREQ, flags, orig_addr, cpu_to_le32(orig_sn), target_flags, target_addr, cpu_to_le32(target_sn), da, @@ -631,7 +651,8 @@ static void hwmp_prep_frame_process(struct ieee80211_sub_if_data *sdata, u8 next_hop[ETH_ALEN]; u32 target_sn, orig_sn, lifetime; - mhwmp_dbg("received PREP from %pM", PREP_IE_ORIG_ADDR(prep_elem)); + mhwmp_dbg(sdata, "received PREP from %pM\n", + PREP_IE_ORIG_ADDR(prep_elem)); orig_addr = PREP_IE_ORIG_ADDR(prep_elem); if (ether_addr_equal(orig_addr, sdata->vif.addr)) @@ -744,11 +765,6 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, bool root_is_gate; ttl = rann->rann_ttl; - if (ttl <= 1) { - ifmsh->mshstats.dropped_frames_ttl++; - return; - } - ttl--; flags = rann->rann_flags; root_is_gate = !!(flags & RANN_FLAG_IS_GATE); orig_addr = rann->rann_addr; @@ -762,8 +778,9 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, if (ether_addr_equal(orig_addr, sdata->vif.addr)) return; - mhwmp_dbg("received RANN from %pM via neighbour %pM (is_gate=%d)", - orig_addr, mgmt->sa, root_is_gate); + mhwmp_dbg(sdata, + "received RANN from %pM via neighbour %pM (is_gate=%d)\n", + orig_addr, mgmt->sa, root_is_gate); rcu_read_lock(); sta = sta_info_get(sdata, mgmt->sa); @@ -785,34 +802,50 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, } } + if (!(SN_LT(mpath->sn, orig_sn)) && + !(mpath->sn == orig_sn && metric < mpath->rann_metric)) { + rcu_read_unlock(); + return; + } + if ((!(mpath->flags & (MESH_PATH_ACTIVE | MESH_PATH_RESOLVING)) || - time_after(jiffies, mpath->exp_time - 1*HZ)) && - !(mpath->flags & MESH_PATH_FIXED)) { - mhwmp_dbg("%s time to refresh root mpath %pM", sdata->name, - orig_addr); + (time_after(jiffies, mpath->last_preq_to_root + + root_path_confirmation_jiffies(sdata)) || + time_before(jiffies, mpath->last_preq_to_root))) && + !(mpath->flags & MESH_PATH_FIXED) && (ttl != 0)) { + mhwmp_dbg(sdata, + "time to refresh root mpath %pM\n", + orig_addr); mesh_queue_preq(mpath, PREQ_Q_F_START | PREQ_Q_F_REFRESH); + mpath->last_preq_to_root = jiffies; } - if ((SN_LT(mpath->sn, orig_sn) || (mpath->sn == orig_sn && - metric < mpath->rann_metric)) && ifmsh->mshcfg.dot11MeshForwarding) { + mpath->sn = orig_sn; + mpath->rann_metric = metric + metric_txsta; + mpath->is_root = true; + /* Recording RANNs sender address to send individually + * addressed PREQs destined for root mesh STA */ + memcpy(mpath->rann_snd_addr, mgmt->sa, ETH_ALEN); + + if (root_is_gate) + mesh_path_add_gate(mpath); + + if (ttl <= 1) { + ifmsh->mshstats.dropped_frames_ttl++; + rcu_read_unlock(); + return; + } + ttl--; + + if (ifmsh->mshcfg.dot11MeshForwarding) { mesh_path_sel_frame_tx(MPATH_RANN, flags, orig_addr, cpu_to_le32(orig_sn), 0, NULL, 0, broadcast_addr, hopcount, ttl, cpu_to_le32(interval), cpu_to_le32(metric + metric_txsta), 0, sdata); - mpath->sn = orig_sn; - mpath->rann_metric = metric + metric_txsta; - /* Recording RANNs sender address to send individually - * addressed PREQs destined for root mesh STA */ - memcpy(mpath->rann_snd_addr, mgmt->sa, ETH_ALEN); } - mpath->is_root = true; - - if (root_is_gate) - mesh_path_add_gate(mpath); - rcu_read_unlock(); } @@ -889,7 +922,7 @@ static void mesh_queue_preq(struct mesh_path *mpath, u8 flags) preq_node = kmalloc(sizeof(struct mesh_preq_queue), GFP_ATOMIC); if (!preq_node) { - mhwmp_dbg("could not allocate PREQ node"); + mhwmp_dbg(sdata, "could not allocate PREQ node\n"); return; } @@ -898,7 +931,7 @@ static void mesh_queue_preq(struct mesh_path *mpath, u8 flags) spin_unlock_bh(&ifmsh->mesh_preq_queue_lock); kfree(preq_node); if (printk_ratelimit()) - mhwmp_dbg("PREQ node queue full"); + mhwmp_dbg(sdata, "PREQ node queue full\n"); return; } @@ -1021,12 +1054,15 @@ enddiscovery: kfree(preq_node); } -/* mesh_nexthop_resolve - lookup next hop for given skb and start path - * discovery if no forwarding information is found. +/** + * mesh_nexthop_resolve - lookup next hop; conditionally start path discovery * * @skb: 802.11 frame to be sent * @sdata: network subif the frame will be sent through * + * Lookup next hop for given skb and start path discovery if no + * forwarding information is found. + * * Returns: 0 if the next hop was found and -ENOENT if the frame was queued. * skb is freeed here if no mpath could be allocated. */ @@ -1146,7 +1182,7 @@ void mesh_path_timer(unsigned long data) if (!mpath->is_gate && mesh_gate_num(sdata) > 0) { ret = mesh_path_send_to_gates(mpath); if (ret) - mhwmp_dbg("no gate was reachable"); + mhwmp_dbg(sdata, "no gate was reachable\n"); } else mesh_path_flush_pending(mpath); } @@ -1157,13 +1193,34 @@ mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; u32 interval = ifmsh->mshcfg.dot11MeshHWMPRannInterval; - u8 flags; + u8 flags, target_flags = 0; flags = (ifmsh->mshcfg.dot11MeshGateAnnouncementProtocol) ? RANN_FLAG_IS_GATE : 0; - mesh_path_sel_frame_tx(MPATH_RANN, flags, sdata->vif.addr, + + switch (ifmsh->mshcfg.dot11MeshHWMPRootMode) { + case IEEE80211_PROACTIVE_RANN: + mesh_path_sel_frame_tx(MPATH_RANN, flags, sdata->vif.addr, cpu_to_le32(++ifmsh->sn), 0, NULL, 0, broadcast_addr, - 0, sdata->u.mesh.mshcfg.element_ttl, + 0, ifmsh->mshcfg.element_ttl, cpu_to_le32(interval), 0, 0, sdata); + break; + case IEEE80211_PROACTIVE_PREQ_WITH_PREP: + flags |= IEEE80211_PREQ_PROACTIVE_PREP_FLAG; + case IEEE80211_PROACTIVE_PREQ_NO_PREP: + interval = ifmsh->mshcfg.dot11MeshHWMPactivePathToRootTimeout; + target_flags |= IEEE80211_PREQ_TO_FLAG | + IEEE80211_PREQ_USN_FLAG; + mesh_path_sel_frame_tx(MPATH_PREQ, flags, sdata->vif.addr, + cpu_to_le32(++ifmsh->sn), target_flags, + (u8 *) broadcast_addr, 0, broadcast_addr, + 0, ifmsh->mshcfg.element_ttl, + cpu_to_le32(interval), + 0, cpu_to_le32(ifmsh->preq_id++), sdata); + break; + default: + mhwmp_dbg(sdata, "Proactive mechanism not supported\n"); + return; + } } diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index b39224d8255..075bc535c60 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -18,12 +18,6 @@ #include "ieee80211_i.h" #include "mesh.h" -#ifdef CONFIG_MAC80211_VERBOSE_MPATH_DEBUG -#define mpath_dbg(fmt, args...) printk(KERN_DEBUG fmt, ##args) -#else -#define mpath_dbg(fmt, args...) do { (void)(0); } while (0) -#endif - /* There will be initially 2^INIT_PATHS_SIZE_ORDER buckets */ #define INIT_PATHS_SIZE_ORDER 2 @@ -322,9 +316,8 @@ static void mesh_path_move_to_queue(struct mesh_path *gate_mpath, spin_lock_irqsave(&gate_mpath->frame_queue.lock, flags); skb_queue_splice(&gateq, &gate_mpath->frame_queue); - mpath_dbg("Mpath queue for gate %pM has %d frames\n", - gate_mpath->dst, - skb_queue_len(&gate_mpath->frame_queue)); + mpath_dbg(gate_mpath->sdata, "Mpath queue for gate %pM has %d frames\n", + gate_mpath->dst, skb_queue_len(&gate_mpath->frame_queue)); spin_unlock_irqrestore(&gate_mpath->frame_queue.lock, flags); if (!copy) @@ -446,9 +439,9 @@ int mesh_path_add_gate(struct mesh_path *mpath) hlist_add_head_rcu(&new_gate->list, tbl->known_gates); spin_unlock_bh(&tbl->gates_lock); rcu_read_unlock(); - mpath_dbg("Mesh path (%s): Recorded new gate: %pM. %d known gates\n", - mpath->sdata->name, mpath->dst, - mpath->sdata->u.mesh.num_gates); + mpath_dbg(mpath->sdata, + "Mesh path: Recorded new gate: %pM. %d known gates\n", + mpath->dst, mpath->sdata->u.mesh.num_gates); return 0; err_rcu: rcu_read_unlock(); @@ -477,8 +470,8 @@ static int mesh_gate_del(struct mesh_table *tbl, struct mesh_path *mpath) spin_unlock_bh(&tbl->gates_lock); mpath->sdata->u.mesh.num_gates--; mpath->is_gate = false; - mpath_dbg("Mesh path (%s): Deleted gate: %pM. " - "%d known gates\n", mpath->sdata->name, + mpath_dbg(mpath->sdata, + "Mesh path: Deleted gate: %pM. %d known gates\n", mpath->dst, mpath->sdata->u.mesh.num_gates); break; } @@ -785,7 +778,7 @@ static void __mesh_path_del(struct mesh_table *tbl, struct mpath_node *node) /** * mesh_path_flush_by_nexthop - Deletes mesh paths if their next hop matches * - * @sta - mesh peer to match + * @sta: mesh peer to match * * RCU notes: this function is called when a mesh plink transitions from * PLINK_ESTAB to any other state, since PLINK_ESTAB state is the only one that @@ -840,7 +833,7 @@ static void table_flush_by_iface(struct mesh_table *tbl, * * This function deletes both mesh paths as well as mesh portal paths. * - * @sdata - interface data to match + * @sdata: interface data to match * */ void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) @@ -946,19 +939,20 @@ int mesh_path_send_to_gates(struct mesh_path *mpath) continue; if (gate->mpath->flags & MESH_PATH_ACTIVE) { - mpath_dbg("Forwarding to %pM\n", gate->mpath->dst); + mpath_dbg(sdata, "Forwarding to %pM\n", gate->mpath->dst); mesh_path_move_to_queue(gate->mpath, from_mpath, copy); from_mpath = gate->mpath; copy = true; } else { - mpath_dbg("Not forwarding %p\n", gate->mpath); - mpath_dbg("flags %x\n", gate->mpath->flags); + mpath_dbg(sdata, + "Not forwarding %p (flags %#x)\n", + gate->mpath, gate->mpath->flags); } } hlist_for_each_entry_rcu(gate, n, known_gates, list) if (gate->mpath->sdata == sdata) { - mpath_dbg("Sending to %pM\n", gate->mpath->dst); + mpath_dbg(sdata, "Sending to %pM\n", gate->mpath->dst); mesh_path_tx_pending(gate->mpath); } diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 60ef235c9d9..af671b984df 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -13,12 +13,6 @@ #include "rate.h" #include "mesh.h" -#ifdef CONFIG_MAC80211_VERBOSE_MPL_DEBUG -#define mpl_dbg(fmt, args...) printk(KERN_DEBUG fmt, ##args) -#else -#define mpl_dbg(fmt, args...) do { (void)(0); } while (0) -#endif - #define PLINK_GET_LLID(p) (p + 2) #define PLINK_GET_PLID(p) (p + 4) @@ -105,7 +99,7 @@ static struct sta_info *mesh_plink_alloc(struct ieee80211_sub_if_data *sdata, return sta; } -/* +/** * mesh_set_ht_prot_mode - set correct HT protection mode * * Section 9.23.3.5 of IEEE 80211-2012 describes the protection rules for HT @@ -134,12 +128,14 @@ static u32 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata) switch (sta->ch_type) { case NL80211_CHAN_NO_HT: - mpl_dbg("mesh_plink %pM: nonHT sta (%pM) is present", + mpl_dbg(sdata, + "mesh_plink %pM: nonHT sta (%pM) is present\n", sdata->vif.addr, sta->sta.addr); non_ht_sta = true; goto out; case NL80211_CHAN_HT20: - mpl_dbg("mesh_plink %pM: HT20 sta (%pM) is present", + mpl_dbg(sdata, + "mesh_plink %pM: HT20 sta (%pM) is present\n", sdata->vif.addr, sta->sta.addr); ht20_sta = true; default: @@ -160,7 +156,8 @@ out: sdata->vif.bss_conf.ht_operation_mode = ht_opmode; sdata->u.mesh.mshcfg.ht_opmode = ht_opmode; changed = BSS_CHANGED_HT; - mpl_dbg("mesh_plink %pM: protection mode changed to %d", + mpl_dbg(sdata, + "mesh_plink %pM: protection mode changed to %d\n", sdata->vif.addr, ht_opmode); } @@ -261,8 +258,8 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, pos = skb_put(skb, 2); memcpy(pos + 2, &plid, 2); } - if (ieee80211_add_srates_ie(&sdata->vif, skb, true) || - ieee80211_add_ext_srates_ie(&sdata->vif, skb, true) || + if (ieee80211_add_srates_ie(sdata, skb, true) || + ieee80211_add_ext_srates_ie(sdata, skb, true) || mesh_add_rsn_ie(skb, sdata) || mesh_add_meshid_ie(skb, sdata) || mesh_add_meshconf_ie(skb, sdata)) @@ -323,7 +320,8 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, return 0; } -/* mesh_peer_init - initialize new mesh peer and return resulting sta_info +/** + * mesh_peer_init - initialize new mesh peer and return resulting sta_info * * @sdata: local meshif * @addr: peer's address @@ -437,7 +435,8 @@ static void mesh_plink_timer(unsigned long data) spin_unlock_bh(&sta->lock); return; } - mpl_dbg("Mesh plink timer for %pM fired on state %d\n", + mpl_dbg(sta->sdata, + "Mesh plink timer for %pM fired on state %d\n", sta->sta.addr, sta->plink_state); reason = 0; llid = sta->llid; @@ -450,7 +449,8 @@ static void mesh_plink_timer(unsigned long data) /* retry timer */ if (sta->plink_retries < dot11MeshMaxRetries(sdata)) { u32 rand; - mpl_dbg("Mesh plink for %pM (retry, timeout): %d %d\n", + mpl_dbg(sta->sdata, + "Mesh plink for %pM (retry, timeout): %d %d\n", sta->sta.addr, sta->plink_retries, sta->plink_timeout); get_random_bytes(&rand, sizeof(u32)); @@ -530,7 +530,8 @@ int mesh_plink_open(struct sta_info *sta) sta->plink_state = NL80211_PLINK_OPN_SNT; mesh_plink_timer_set(sta, dot11MeshRetryTimeout(sdata)); spin_unlock_bh(&sta->lock); - mpl_dbg("Mesh plink: starting establishment with %pM\n", + mpl_dbg(sdata, + "Mesh plink: starting establishment with %pM\n", sta->sta.addr); return mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_OPEN, @@ -565,7 +566,6 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m u8 *baseaddr; u32 changed = 0; __le16 plid, llid, reason; -#ifdef CONFIG_MAC80211_VERBOSE_MPL_DEBUG static const char *mplstates[] = { [NL80211_PLINK_LISTEN] = "LISTEN", [NL80211_PLINK_OPN_SNT] = "OPN-SNT", @@ -575,14 +575,14 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m [NL80211_PLINK_HOLDING] = "HOLDING", [NL80211_PLINK_BLOCKED] = "BLOCKED" }; -#endif /* need action_code, aux */ if (len < IEEE80211_MIN_ACTION_SIZE + 3) return; if (is_multicast_ether_addr(mgmt->da)) { - mpl_dbg("Mesh plink: ignore frame from multicast address"); + mpl_dbg(sdata, + "Mesh plink: ignore frame from multicast address\n"); return; } @@ -595,12 +595,14 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m } ieee802_11_parse_elems(baseaddr, len - baselen, &elems); if (!elems.peering) { - mpl_dbg("Mesh plink: missing necessary peer link ie\n"); + mpl_dbg(sdata, + "Mesh plink: missing necessary peer link ie\n"); return; } if (elems.rsn_len && sdata->u.mesh.security == IEEE80211_MESH_SEC_NONE) { - mpl_dbg("Mesh plink: can't establish link with secure peer\n"); + mpl_dbg(sdata, + "Mesh plink: can't establish link with secure peer\n"); return; } @@ -610,14 +612,15 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m (ftype == WLAN_SP_MESH_PEERING_CONFIRM && ie_len != 6) || (ftype == WLAN_SP_MESH_PEERING_CLOSE && ie_len != 6 && ie_len != 8)) { - mpl_dbg("Mesh plink: incorrect plink ie length %d %d\n", - ftype, ie_len); + mpl_dbg(sdata, + "Mesh plink: incorrect plink ie length %d %d\n", + ftype, ie_len); return; } if (ftype != WLAN_SP_MESH_PEERING_CLOSE && (!elems.mesh_id || !elems.mesh_config)) { - mpl_dbg("Mesh plink: missing necessary ie\n"); + mpl_dbg(sdata, "Mesh plink: missing necessary ie\n"); return; } /* Note the lines below are correct, the llid in the frame is the plid @@ -632,21 +635,21 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m sta = sta_info_get(sdata, mgmt->sa); if (!sta && ftype != WLAN_SP_MESH_PEERING_OPEN) { - mpl_dbg("Mesh plink: cls or cnf from unknown peer\n"); + mpl_dbg(sdata, "Mesh plink: cls or cnf from unknown peer\n"); rcu_read_unlock(); return; } if (ftype == WLAN_SP_MESH_PEERING_OPEN && !rssi_threshold_check(sta, sdata)) { - mpl_dbg("Mesh plink: %pM does not meet rssi threshold\n", + mpl_dbg(sdata, "Mesh plink: %pM does not meet rssi threshold\n", mgmt->sa); rcu_read_unlock(); return; } if (sta && !test_sta_flag(sta, WLAN_STA_AUTH)) { - mpl_dbg("Mesh plink: Action frame from non-authed peer\n"); + mpl_dbg(sdata, "Mesh plink: Action frame from non-authed peer\n"); rcu_read_unlock(); return; } @@ -683,7 +686,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m } else if (!sta) { /* ftype == WLAN_SP_MESH_PEERING_OPEN */ if (!mesh_plink_free_count(sdata)) { - mpl_dbg("Mesh plink error: no more free plinks\n"); + mpl_dbg(sdata, "Mesh plink error: no more free plinks\n"); rcu_read_unlock(); return; } @@ -724,7 +727,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m event = CLS_ACPT; break; default: - mpl_dbg("Mesh plink: unknown frame subtype\n"); + mpl_dbg(sdata, "Mesh plink: unknown frame subtype\n"); rcu_read_unlock(); return; } @@ -734,13 +737,14 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m /* allocate sta entry if necessary and update info */ sta = mesh_peer_init(sdata, mgmt->sa, &elems); if (!sta) { - mpl_dbg("Mesh plink: failed to init peer!\n"); + mpl_dbg(sdata, "Mesh plink: failed to init peer!\n"); rcu_read_unlock(); return; } } - mpl_dbg("Mesh plink (peer, state, llid, plid, event): %pM %s %d %d %d\n", + mpl_dbg(sdata, + "Mesh plink (peer, state, llid, plid, event): %pM %s %d %d %d\n", mgmt->sa, mplstates[sta->plink_state], le16_to_cpu(sta->llid), le16_to_cpu(sta->plid), event); @@ -851,7 +855,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m mesh_plink_inc_estab_count(sdata); changed |= mesh_set_ht_prot_mode(sdata); changed |= BSS_CHANGED_BEACON; - mpl_dbg("Mesh plink with %pM ESTABLISHED\n", + mpl_dbg(sdata, "Mesh plink with %pM ESTABLISHED\n", sta->sta.addr); break; default: @@ -887,7 +891,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m mesh_plink_inc_estab_count(sdata); changed |= mesh_set_ht_prot_mode(sdata); changed |= BSS_CHANGED_BEACON; - mpl_dbg("Mesh plink with %pM ESTABLISHED\n", + mpl_dbg(sdata, "Mesh plink with %pM ESTABLISHED\n", sta->sta.addr); mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CONFIRM, diff --git a/net/mac80211/mesh_sync.c b/net/mac80211/mesh_sync.c index 38d30e8ce6d..accfa00ffcd 100644 --- a/net/mac80211/mesh_sync.c +++ b/net/mac80211/mesh_sync.c @@ -12,13 +12,6 @@ #include "mesh.h" #include "driver-ops.h" -#ifdef CONFIG_MAC80211_VERBOSE_MESH_SYNC_DEBUG -#define msync_dbg(fmt, args...) \ - printk(KERN_DEBUG "Mesh sync (%s): " fmt "\n", sdata->name, ##args) -#else -#define msync_dbg(fmt, args...) do { (void)(0); } while (0) -#endif - /* This is not in the standard. It represents a tolerable tbtt drift below * which we do no TSF adjustment. */ @@ -65,14 +58,14 @@ void mesh_sync_adjust_tbtt(struct ieee80211_sub_if_data *sdata) spin_lock_bh(&ifmsh->sync_offset_lock); if (ifmsh->sync_offset_clockdrift_max < beacon_int_fraction) { - msync_dbg("TBTT : max clockdrift=%lld; adjusting", - (long long) ifmsh->sync_offset_clockdrift_max); + msync_dbg(sdata, "TBTT : max clockdrift=%lld; adjusting\n", + (long long) ifmsh->sync_offset_clockdrift_max); tsfdelta = -ifmsh->sync_offset_clockdrift_max; ifmsh->sync_offset_clockdrift_max = 0; } else { - msync_dbg("TBTT : max clockdrift=%lld; adjusting by %llu", - (long long) ifmsh->sync_offset_clockdrift_max, - (unsigned long long) beacon_int_fraction); + msync_dbg(sdata, "TBTT : max clockdrift=%lld; adjusting by %llu\n", + (long long) ifmsh->sync_offset_clockdrift_max, + (unsigned long long) beacon_int_fraction); tsfdelta = -beacon_int_fraction; ifmsh->sync_offset_clockdrift_max -= beacon_int_fraction; } @@ -120,7 +113,7 @@ static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, if (elems->mesh_config && mesh_peer_tbtt_adjusting(elems)) { clear_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN); - msync_dbg("STA %pM : is adjusting TBTT", sta->sta.addr); + msync_dbg(sdata, "STA %pM : is adjusting TBTT\n", sta->sta.addr); goto no_sync; } @@ -169,7 +162,8 @@ static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) { s64 t_clockdrift = sta->t_offset_setpoint - sta->t_offset; - msync_dbg("STA %pM : sta->t_offset=%lld, sta->t_offset_setpoint=%lld, t_clockdrift=%lld", + msync_dbg(sdata, + "STA %pM : sta->t_offset=%lld, sta->t_offset_setpoint=%lld, t_clockdrift=%lld\n", sta->sta.addr, (long long) sta->t_offset, (long long) @@ -178,7 +172,8 @@ static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, if (t_clockdrift > TOFFSET_MAXIMUM_ADJUSTMENT || t_clockdrift < -TOFFSET_MAXIMUM_ADJUSTMENT) { - msync_dbg("STA %pM : t_clockdrift=%lld too large, setpoint reset", + msync_dbg(sdata, + "STA %pM : t_clockdrift=%lld too large, setpoint reset\n", sta->sta.addr, (long long) t_clockdrift); clear_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN); @@ -197,8 +192,8 @@ static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, } else { sta->t_offset_setpoint = sta->t_offset - TOFFSET_SET_MARGIN; set_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN); - msync_dbg("STA %pM : offset was invalid, " - " sta->t_offset=%lld", + msync_dbg(sdata, + "STA %pM : offset was invalid, sta->t_offset=%lld\n", sta->sta.addr, (long long) sta->t_offset); rcu_read_unlock(); @@ -226,17 +221,15 @@ static void mesh_sync_offset_adjust_tbtt(struct ieee80211_sub_if_data *sdata) * to the driver tsf setter, we punt * the tsf adjustment to the mesh tasklet */ - msync_dbg("TBTT : kicking off TBTT " - "adjustment with " - "clockdrift_max=%lld", - ifmsh->sync_offset_clockdrift_max); + msync_dbg(sdata, + "TBTT : kicking off TBTT adjustment with clockdrift_max=%lld\n", + ifmsh->sync_offset_clockdrift_max); set_bit(MESH_WORK_DRIFT_ADJUST, &ifmsh->wrkq_flags); } else { - msync_dbg("TBTT : max clockdrift=%lld; " - "too small to adjust", - (long long) - ifmsh->sync_offset_clockdrift_max); + msync_dbg(sdata, + "TBTT : max clockdrift=%lld; too small to adjust\n", + (long long)ifmsh->sync_offset_clockdrift_max); ifmsh->sync_offset_clockdrift_max = 0; } spin_unlock_bh(&ifmsh->sync_offset_lock); @@ -268,7 +261,7 @@ static void mesh_sync_vendor_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, const u8 *oui; WARN_ON(sdata->u.mesh.mesh_sp_id != IEEE80211_SYNC_METHOD_VENDOR); - msync_dbg("called mesh_sync_vendor_rx_bcn_presp"); + msync_dbg(sdata, "called mesh_sync_vendor_rx_bcn_presp\n"); oui = mesh_get_vendor_oui(sdata); /* here you would implement the vendor offset tracking for this oui */ } @@ -278,7 +271,7 @@ static void mesh_sync_vendor_adjust_tbtt(struct ieee80211_sub_if_data *sdata) const u8 *oui; WARN_ON(sdata->u.mesh.mesh_sp_id != IEEE80211_SYNC_METHOD_VENDOR); - msync_dbg("called mesh_sync_vendor_adjust_tbtt"); + msync_dbg(sdata, "called mesh_sync_vendor_adjust_tbtt\n"); oui = mesh_get_vendor_oui(sdata); /* here you would implement the vendor tsf adjustment for this oui */ } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 0db5d34a06b..a4a5acdbaa4 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -258,12 +258,11 @@ static int ieee80211_compatible_rates(const u8 *supp_rates, int supp_rates_len, } static void ieee80211_add_ht_ie(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, const u8 *ht_oper_ie, + struct sk_buff *skb, u8 ap_ht_param, struct ieee80211_supported_band *sband, struct ieee80211_channel *channel, enum ieee80211_smps_mode smps) { - struct ieee80211_ht_operation *ht_oper; u8 *pos; u32 flags = channel->flags; u16 cap; @@ -271,21 +270,13 @@ static void ieee80211_add_ht_ie(struct ieee80211_sub_if_data *sdata, BUILD_BUG_ON(sizeof(ht_cap) != sizeof(sband->ht_cap)); - if (!ht_oper_ie) - return; - - if (ht_oper_ie[1] < sizeof(struct ieee80211_ht_operation)) - return; - memcpy(&ht_cap, &sband->ht_cap, sizeof(ht_cap)); ieee80211_apply_htcap_overrides(sdata, &ht_cap); - ht_oper = (struct ieee80211_ht_operation *)(ht_oper_ie + 2); - /* determine capability flags */ cap = ht_cap.cap; - switch (ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { + switch (ap_ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: if (flags & IEEE80211_CHAN_NO_HT40PLUS) { cap &= ~IEEE80211_HT_CAP_SUP_WIDTH_20_40; @@ -509,7 +500,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) } if (!(ifmgd->flags & IEEE80211_STA_DISABLE_11N)) - ieee80211_add_ht_ie(sdata, skb, assoc_data->ht_operation_ie, + ieee80211_add_ht_ie(sdata, skb, assoc_data->ap_ht_param, sband, local->oper_channel, ifmgd->ap_smps); /* if present, add any custom non-vendor IEs that go after HT */ @@ -550,6 +541,8 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) memcpy(pos, assoc_data->ie + offset, noffset - offset); } + drv_mgd_prepare_tx(local, sdata); + IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; ieee80211_tx_skb(sdata, skb); } @@ -589,6 +582,9 @@ static void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, if (!(ifmgd->flags & IEEE80211_STA_MFP_ENABLED)) IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; + + drv_mgd_prepare_tx(local, sdata); + ieee80211_tx_skb(sdata, skb); } } @@ -911,9 +907,6 @@ static bool ieee80211_powersave_allowed(struct ieee80211_sub_if_data *sdata) if (!mgd->associated) return false; - if (!mgd->associated->beacon_ies) - return false; - if (mgd->flags & (IEEE80211_STA_BEACON_POLL | IEEE80211_STA_CONNECTION_POLL)) return false; @@ -939,11 +932,6 @@ void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency) return; } - if (!list_empty(&local->work_list)) { - local->ps_sdata = NULL; - goto change; - } - list_for_each_entry(sdata, &local->interfaces, list) { if (!ieee80211_sdata_running(sdata)) continue; @@ -1016,7 +1004,6 @@ void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency) local->ps_sdata = NULL; } - change: ieee80211_change_ps(local); } @@ -1121,7 +1108,7 @@ void ieee80211_dynamic_ps_timer(unsigned long data) } /* MLME */ -static void ieee80211_sta_wmm_params(struct ieee80211_local *local, +static bool ieee80211_sta_wmm_params(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, u8 *wmm_param, size_t wmm_param_len) { @@ -1132,23 +1119,23 @@ static void ieee80211_sta_wmm_params(struct ieee80211_local *local, u8 *pos, uapsd_queues = 0; if (!local->ops->conf_tx) - return; + return false; if (local->hw.queues < IEEE80211_NUM_ACS) - return; + return false; if (!wmm_param) - return; + return false; if (wmm_param_len < 8 || wmm_param[5] /* version */ != 1) - return; + return false; if (ifmgd->flags & IEEE80211_STA_UAPSD_ENABLED) uapsd_queues = ifmgd->uapsd_queues; count = wmm_param[6] & 0x0f; if (count == ifmgd->wmm_last_param_set) - return; + return false; ifmgd->wmm_last_param_set = count; pos = wmm_param + 8; @@ -1156,7 +1143,7 @@ static void ieee80211_sta_wmm_params(struct ieee80211_local *local, memset(¶ms, 0, sizeof(params)); - local->wmm_acm = 0; + sdata->wmm_acm = 0; for (; left >= 4; left -= 4, pos += 4) { int aci = (pos[0] >> 5) & 0x03; int acm = (pos[0] >> 4) & 0x01; @@ -1167,21 +1154,21 @@ static void ieee80211_sta_wmm_params(struct ieee80211_local *local, case 1: /* AC_BK */ queue = 3; if (acm) - local->wmm_acm |= BIT(1) | BIT(2); /* BK/- */ + sdata->wmm_acm |= BIT(1) | BIT(2); /* BK/- */ if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BK) uapsd = true; break; case 2: /* AC_VI */ queue = 1; if (acm) - local->wmm_acm |= BIT(4) | BIT(5); /* CL/VI */ + sdata->wmm_acm |= BIT(4) | BIT(5); /* CL/VI */ if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VI) uapsd = true; break; case 3: /* AC_VO */ queue = 0; if (acm) - local->wmm_acm |= BIT(6) | BIT(7); /* VO/NC */ + sdata->wmm_acm |= BIT(6) | BIT(7); /* VO/NC */ if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VO) uapsd = true; break; @@ -1189,7 +1176,7 @@ static void ieee80211_sta_wmm_params(struct ieee80211_local *local, default: queue = 2; if (acm) - local->wmm_acm |= BIT(0) | BIT(3); /* BE/EE */ + sdata->wmm_acm |= BIT(0) | BIT(3); /* BE/EE */ if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BE) uapsd = true; break; @@ -1201,23 +1188,21 @@ static void ieee80211_sta_wmm_params(struct ieee80211_local *local, params.txop = get_unaligned_le16(pos + 2); params.uapsd = uapsd; -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - wiphy_debug(local->hw.wiphy, - "WMM queue=%d aci=%d acm=%d aifs=%d " - "cWmin=%d cWmax=%d txop=%d uapsd=%d\n", - queue, aci, acm, - params.aifs, params.cw_min, params.cw_max, - params.txop, params.uapsd); -#endif + mlme_dbg(sdata, + "WMM queue=%d aci=%d acm=%d aifs=%d cWmin=%d cWmax=%d txop=%d uapsd=%d\n", + queue, aci, acm, + params.aifs, params.cw_min, params.cw_max, + params.txop, params.uapsd); sdata->tx_conf[queue] = params; if (drv_conf_tx(local, sdata, queue, ¶ms)) - wiphy_debug(local->hw.wiphy, - "failed to set TX queue parameters for queue %d\n", - queue); + sdata_err(sdata, + "failed to set TX queue parameters for queue %d\n", + queue); } /* enable WMM or activate new settings */ sdata->vif.bss_conf.qos = true; + return true; } static void __ieee80211_stop_poll(struct ieee80211_sub_if_data *sdata) @@ -1284,13 +1269,8 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; bss_info_changed |= BSS_CHANGED_ASSOC; - /* set timing information */ - bss_conf->beacon_int = cbss->beacon_interval; - bss_conf->last_tsf = cbss->tsf; - - bss_info_changed |= BSS_CHANGED_BEACON_INT; bss_info_changed |= ieee80211_handle_bss_capability(sdata, - cbss->capability, bss->has_erp_value, bss->erp_value); + bss_conf->assoc_capability, bss->has_erp_value, bss->erp_value); sdata->u.mgd.beacon_timeout = usecs_to_jiffies(ieee80211_tu_to_usec( IEEE80211_BEACON_LOSS_COUNT * bss_conf->beacon_int)); @@ -1380,6 +1360,21 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, } mutex_unlock(&local->sta_mtx); + /* + * if we want to get out of ps before disassoc (why?) we have + * to do it before sending disassoc, as otherwise the null-packet + * won't be valid. + */ + if (local->hw.conf.flags & IEEE80211_CONF_PS) { + local->hw.conf.flags &= ~IEEE80211_CONF_PS; + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); + } + local->ps_sdata = NULL; + + /* flush out any pending frame (e.g. DELBA) before deauth/disassoc */ + if (tx) + drv_flush(local, false); + /* deauthenticate/disassociate now */ if (tx || frame_buf) ieee80211_send_deauth_disassoc(sdata, ifmgd->bssid, stype, @@ -1411,12 +1406,6 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, del_timer_sync(&local->dynamic_ps_timer); cancel_work_sync(&local->dynamic_ps_enable_work); - if (local->hw.conf.flags & IEEE80211_CONF_PS) { - local->hw.conf.flags &= ~IEEE80211_CONF_PS; - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); - } - local->ps_sdata = NULL; - /* Disable ARP filtering */ if (sdata->vif.bss_conf.arp_filter_enabled) { sdata->vif.bss_conf.arp_filter_enabled = false; @@ -1441,6 +1430,8 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, del_timer_sync(&sdata->u.mgd.bcn_mon_timer); del_timer_sync(&sdata->u.mgd.timer); del_timer_sync(&sdata->u.mgd.chswitch_timer); + + sdata->u.mgd.timers_running = 0; } void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata, @@ -1581,11 +1572,12 @@ static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata, goto out; } -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG if (beacon) - net_dbg_ratelimited("%s: detected beacon loss from AP - sending probe request\n", - sdata->name); -#endif + mlme_dbg_ratelimited(sdata, + "detected beacon loss from AP - sending probe request\n"); + + ieee80211_cqm_rssi_notify(&sdata->vif, + NL80211_CQM_RSSI_BEACON_LOSS_EVENT, GFP_KERNEL); /* * The driver/our work has already reported this event or the @@ -1627,6 +1619,7 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + struct cfg80211_bss *cbss; struct sk_buff *skb; const u8 *ssid; int ssid_len; @@ -1636,16 +1629,22 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, ASSERT_MGD_MTX(ifmgd); - if (!ifmgd->associated) + if (ifmgd->associated) + cbss = ifmgd->associated; + else if (ifmgd->auth_data) + cbss = ifmgd->auth_data->bss; + else if (ifmgd->assoc_data) + cbss = ifmgd->assoc_data->bss; + else return NULL; - ssid = ieee80211_bss_get_ie(ifmgd->associated, WLAN_EID_SSID); + ssid = ieee80211_bss_get_ie(cbss, WLAN_EID_SSID); if (WARN_ON_ONCE(ssid == NULL)) ssid_len = 0; else ssid_len = ssid[1]; - skb = ieee80211_build_probe_req(sdata, ifmgd->associated->bssid, + skb = ieee80211_build_probe_req(sdata, cbss->bssid, (u32) -1, ssid + 2, ssid_len, NULL, 0, true); @@ -1668,8 +1667,7 @@ static void __ieee80211_connection_loss(struct ieee80211_sub_if_data *sdata) memcpy(bssid, ifmgd->associated->bssid, ETH_ALEN); - printk(KERN_DEBUG "%s: Connection to AP %pM lost.\n", - sdata->name, bssid); + sdata_info(sdata, "Connection to AP %pM lost\n", bssid); ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY, @@ -1765,6 +1763,7 @@ static void ieee80211_auth_challenge(struct ieee80211_sub_if_data *sdata, if (!elems.challenge) return; auth_data->expected_transaction = 4; + drv_mgd_prepare_tx(sdata->local, sdata); ieee80211_send_auth(sdata, 3, auth_data->algorithm, elems.challenge - 2, elems.challenge_len + 2, auth_data->bss->bssid, auth_data->bss->bssid, @@ -1803,9 +1802,10 @@ ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, return RX_MGMT_NONE; if (status_code != WLAN_STATUS_SUCCESS) { - printk(KERN_DEBUG "%s: %pM denied authentication (status %d)\n", - sdata->name, mgmt->sa, status_code); - goto out; + sdata_info(sdata, "%pM denied authentication (status %d)\n", + mgmt->sa, status_code); + ieee80211_destroy_auth_data(sdata, false); + return RX_MGMT_CFG80211_RX_AUTH; } switch (ifmgd->auth_data->algorithm) { @@ -1826,8 +1826,7 @@ ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, return RX_MGMT_NONE; } - printk(KERN_DEBUG "%s: authenticated\n", sdata->name); - out: + sdata_info(sdata, "authenticated\n"); ifmgd->auth_data->done = true; ifmgd->auth_data->timeout = jiffies + IEEE80211_AUTH_WAIT_ASSOC; run_again(ifmgd, ifmgd->auth_data->timeout); @@ -1840,8 +1839,7 @@ ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, goto out_err; } if (sta_info_move_state(sta, IEEE80211_STA_AUTH)) { - printk(KERN_DEBUG "%s: failed moving %pM to auth\n", - sdata->name, bssid); + sdata_info(sdata, "failed moving %pM to auth\n", bssid); goto out_err; } mutex_unlock(&sdata->local->sta_mtx); @@ -1875,8 +1873,8 @@ ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, reason_code = le16_to_cpu(mgmt->u.deauth.reason_code); - printk(KERN_DEBUG "%s: deauthenticated from %pM (Reason: %u)\n", - sdata->name, bssid, reason_code); + sdata_info(sdata, "deauthenticated from %pM (Reason: %u)\n", + bssid, reason_code); ieee80211_set_disassoc(sdata, 0, 0, false, NULL); @@ -1906,8 +1904,8 @@ ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata, reason_code = le16_to_cpu(mgmt->u.disassoc.reason_code); - printk(KERN_DEBUG "%s: disassociated from %pM (Reason: %u)\n", - sdata->name, mgmt->sa, reason_code); + sdata_info(sdata, "disassociated from %pM (Reason: %u)\n", + mgmt->sa, reason_code); ieee80211_set_disassoc(sdata, 0, 0, false, NULL); @@ -1999,17 +1997,15 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info); if ((aid & (BIT(15) | BIT(14))) != (BIT(15) | BIT(14))) - printk(KERN_DEBUG - "%s: invalid AID value 0x%x; bits 15:14 not set\n", - sdata->name, aid); + sdata_info(sdata, "invalid AID value 0x%x; bits 15:14 not set\n", + aid); aid &= ~(BIT(15) | BIT(14)); ifmgd->broken_ap = false; if (aid == 0 || aid > IEEE80211_MAX_AID) { - printk(KERN_DEBUG - "%s: invalid AID value %d (out of range), turn off PS\n", - sdata->name, aid); + sdata_info(sdata, "invalid AID value %d (out of range), turn off PS\n", + aid); aid = 0; ifmgd->broken_ap = true; } @@ -2018,8 +2014,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, ieee802_11_parse_elems(pos, len - (pos - (u8 *) mgmt), &elems); if (!elems.supp_rates) { - printk(KERN_DEBUG "%s: no SuppRates element in AssocResp\n", - sdata->name); + sdata_info(sdata, "no SuppRates element in AssocResp\n"); return false; } @@ -2059,9 +2054,9 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, if (!err && !(ifmgd->flags & IEEE80211_STA_CONTROL_PORT)) err = sta_info_move_state(sta, IEEE80211_STA_AUTHORIZED); if (err) { - printk(KERN_DEBUG - "%s: failed to move station %pM to desired state\n", - sdata->name, sta->sta.addr); + sdata_info(sdata, + "failed to move station %pM to desired state\n", + sta->sta.addr); WARN_ON(__sta_info_destroy(sta)); mutex_unlock(&sdata->local->sta_mtx); return false; @@ -2144,10 +2139,10 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, status_code = le16_to_cpu(mgmt->u.assoc_resp.status_code); aid = le16_to_cpu(mgmt->u.assoc_resp.aid); - printk(KERN_DEBUG "%s: RX %sssocResp from %pM (capab=0x%x " - "status=%d aid=%d)\n", - sdata->name, reassoc ? "Rea" : "A", mgmt->sa, - capab_info, status_code, (u16)(aid & ~(BIT(15) | BIT(14)))); + sdata_info(sdata, + "RX %sssocResp from %pM (capab=0x%x status=%d aid=%d)\n", + reassoc ? "Rea" : "A", mgmt->sa, + capab_info, status_code, (u16)(aid & ~(BIT(15) | BIT(14)))); pos = mgmt->u.assoc_resp.variable; ieee802_11_parse_elems(pos, len - (pos - (u8 *) mgmt), &elems); @@ -2158,9 +2153,9 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, u32 tu, ms; tu = get_unaligned_le32(elems.timeout_int + 1); ms = tu * 1024 / 1000; - printk(KERN_DEBUG "%s: %pM rejected association temporarily; " - "comeback duration %u TU (%u ms)\n", - sdata->name, mgmt->sa, tu, ms); + sdata_info(sdata, + "%pM rejected association temporarily; comeback duration %u TU (%u ms)\n", + mgmt->sa, tu, ms); assoc_data->timeout = jiffies + msecs_to_jiffies(ms); if (ms > IEEE80211_ASSOC_TIMEOUT) run_again(ifmgd, assoc_data->timeout); @@ -2170,8 +2165,8 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, *bss = assoc_data->bss; if (status_code != WLAN_STATUS_SUCCESS) { - printk(KERN_DEBUG "%s: %pM denied association (code=%d)\n", - sdata->name, mgmt->sa, status_code); + sdata_info(sdata, "%pM denied association (code=%d)\n", + mgmt->sa, status_code); ieee80211_destroy_assoc_data(sdata, false); } else { if (!ieee80211_assoc_success(sdata, *bss, mgmt, len)) { @@ -2180,7 +2175,7 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, cfg80211_put_bss(*bss); return RX_MGMT_CFG80211_ASSOC_TIMEOUT; } - printk(KERN_DEBUG "%s: associated\n", sdata->name); + sdata_info(sdata, "associated\n"); /* * destroy assoc_data afterwards, as otherwise an idle @@ -2280,7 +2275,7 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata, if (ifmgd->auth_data && !ifmgd->auth_data->bss->proberesp_ies && ether_addr_equal(mgmt->bssid, ifmgd->auth_data->bss->bssid)) { /* got probe response, continue with auth */ - printk(KERN_DEBUG "%s: direct probe responded\n", sdata->name); + sdata_info(sdata, "direct probe responded\n"); ifmgd->auth_data->tries = 0; ifmgd->auth_data->timeout = jiffies; run_again(ifmgd, ifmgd->auth_data->timeout); @@ -2416,10 +2411,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, } if (ifmgd->flags & IEEE80211_STA_BEACON_POLL) { -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - net_dbg_ratelimited("%s: cancelling probereq poll due to a received beacon\n", - sdata->name); -#endif + mlme_dbg_ratelimited(sdata, + "cancelling probereq poll due to a received beacon\n"); mutex_lock(&local->mtx); ifmgd->flags &= ~IEEE80211_STA_BEACON_POLL; ieee80211_run_deferred_scan(local); @@ -2445,14 +2438,6 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, directed_tim = ieee80211_check_tim(elems.tim, elems.tim_len, ifmgd->aid); - if (ncrc != ifmgd->beacon_crc || !ifmgd->beacon_crc_valid) { - ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems, - true); - - ieee80211_sta_wmm_params(local, sdata, elems.wmm_param, - elems.wmm_param_len); - } - if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) { if (directed_tim) { if (local->hw.conf.dynamic_ps_timeout > 0) { @@ -2483,6 +2468,13 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, ifmgd->beacon_crc = ncrc; ifmgd->beacon_crc_valid = true; + ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems, + true); + + if (ieee80211_sta_wmm_params(local, sdata, elems.wmm_param, + elems.wmm_param_len)) + changed |= BSS_CHANGED_QOS; + if (elems.erp_info && elems.erp_info_len >= 1) { erp_valid = true; erp_value = elems.erp_info[0]; @@ -2642,8 +2634,8 @@ static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata) auth_data->tries++; if (auth_data->tries > IEEE80211_AUTH_MAX_TRIES) { - printk(KERN_DEBUG "%s: authentication with %pM timed out\n", - sdata->name, auth_data->bss->bssid); + sdata_info(sdata, "authentication with %pM timed out\n", + auth_data->bss->bssid); /* * Most likely AP is not in the range so remove the @@ -2654,10 +2646,12 @@ static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata) return -ETIMEDOUT; } + drv_mgd_prepare_tx(local, sdata); + if (auth_data->bss->proberesp_ies) { - printk(KERN_DEBUG "%s: send auth to %pM (try %d/%d)\n", - sdata->name, auth_data->bss->bssid, auth_data->tries, - IEEE80211_AUTH_MAX_TRIES); + sdata_info(sdata, "send auth to %pM (try %d/%d)\n", + auth_data->bss->bssid, auth_data->tries, + IEEE80211_AUTH_MAX_TRIES); auth_data->expected_transaction = 2; ieee80211_send_auth(sdata, 1, auth_data->algorithm, @@ -2667,9 +2661,9 @@ static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata) } else { const u8 *ssidie; - printk(KERN_DEBUG "%s: direct probe to %pM (try %d/%i)\n", - sdata->name, auth_data->bss->bssid, auth_data->tries, - IEEE80211_AUTH_MAX_TRIES); + sdata_info(sdata, "direct probe to %pM (try %d/%i)\n", + auth_data->bss->bssid, auth_data->tries, + IEEE80211_AUTH_MAX_TRIES); ssidie = ieee80211_bss_get_ie(auth_data->bss, WLAN_EID_SSID); if (!ssidie) @@ -2697,8 +2691,8 @@ static int ieee80211_do_assoc(struct ieee80211_sub_if_data *sdata) assoc_data->tries++; if (assoc_data->tries > IEEE80211_ASSOC_MAX_TRIES) { - printk(KERN_DEBUG "%s: association with %pM timed out\n", - sdata->name, assoc_data->bss->bssid); + sdata_info(sdata, "association with %pM timed out\n", + assoc_data->bss->bssid); /* * Most likely AP is not in the range so remove the @@ -2709,9 +2703,9 @@ static int ieee80211_do_assoc(struct ieee80211_sub_if_data *sdata) return -ETIMEDOUT; } - printk(KERN_DEBUG "%s: associate with %pM (try %d/%d)\n", - sdata->name, assoc_data->bss->bssid, assoc_data->tries, - IEEE80211_ASSOC_MAX_TRIES); + sdata_info(sdata, "associate with %pM (try %d/%d)\n", + assoc_data->bss->bssid, assoc_data->tries, + IEEE80211_ASSOC_MAX_TRIES); ieee80211_send_assoc(sdata); assoc_data->timeout = jiffies + IEEE80211_ASSOC_TIMEOUT; @@ -2784,45 +2778,31 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) ieee80211_reset_ap_probe(sdata); else if (ifmgd->nullfunc_failed) { if (ifmgd->probe_send_count < max_tries) { -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - wiphy_debug(local->hw.wiphy, - "%s: No ack for nullfunc frame to" - " AP %pM, try %d/%i\n", - sdata->name, bssid, - ifmgd->probe_send_count, max_tries); -#endif + mlme_dbg(sdata, + "No ack for nullfunc frame to AP %pM, try %d/%i\n", + bssid, ifmgd->probe_send_count, + max_tries); ieee80211_mgd_probe_ap_send(sdata); } else { -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - wiphy_debug(local->hw.wiphy, - "%s: No ack for nullfunc frame to" - " AP %pM, disconnecting.\n", - sdata->name, bssid); -#endif + mlme_dbg(sdata, + "No ack for nullfunc frame to AP %pM, disconnecting.\n", + bssid); ieee80211_sta_connection_lost(sdata, bssid, WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY); } } else if (time_is_after_jiffies(ifmgd->probe_timeout)) run_again(ifmgd, ifmgd->probe_timeout); else if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) { -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - wiphy_debug(local->hw.wiphy, - "%s: Failed to send nullfunc to AP %pM" - " after %dms, disconnecting.\n", - sdata->name, - bssid, probe_wait_ms); -#endif + mlme_dbg(sdata, + "Failed to send nullfunc to AP %pM after %dms, disconnecting\n", + bssid, probe_wait_ms); ieee80211_sta_connection_lost(sdata, bssid, WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY); } else if (ifmgd->probe_send_count < max_tries) { -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - wiphy_debug(local->hw.wiphy, - "%s: No probe response from AP %pM" - " after %dms, try %d/%i\n", - sdata->name, - bssid, probe_wait_ms, - ifmgd->probe_send_count, max_tries); -#endif + mlme_dbg(sdata, + "No probe response from AP %pM after %dms, try %d/%i\n", + bssid, probe_wait_ms, + ifmgd->probe_send_count, max_tries); ieee80211_mgd_probe_ap_send(sdata); } else { /* @@ -2937,11 +2917,8 @@ void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) sdata->flags &= ~IEEE80211_SDATA_DISCONNECT_RESUME; mutex_lock(&ifmgd->mtx); if (ifmgd->associated) { -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - wiphy_debug(sdata->local->hw.wiphy, - "%s: driver requested disconnect after resume.\n", - sdata->name); -#endif + mlme_dbg(sdata, + "driver requested disconnect after resume\n"); ieee80211_sta_connection_lost(sdata, ifmgd->associated->bssid, WLAN_REASON_UNSPECIFIED); @@ -2999,7 +2976,7 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) /* scan finished notification */ void ieee80211_mlme_notify_scan_completed(struct ieee80211_local *local) { - struct ieee80211_sub_if_data *sdata = local->scan_sdata; + struct ieee80211_sub_if_data *sdata; /* Restart STA timers */ rcu_read_lock(); @@ -3029,7 +3006,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_bss *bss = (void *)cbss->priv; - struct sta_info *sta; + struct sta_info *sta = NULL; bool have_sta = false; int err; int ht_cfreq; @@ -3082,13 +3059,11 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, * since we look at probe response/beacon data here * it should be OK. */ - printk(KERN_DEBUG - "%s: Wrong control channel: center-freq: %d" - " ht-cfreq: %d ht->primary_chan: %d" - " band: %d. Disabling HT.\n", - sdata->name, cbss->channel->center_freq, - ht_cfreq, ht_oper->primary_chan, - cbss->channel->band); + sdata_info(sdata, + "Wrong control channel: center-freq: %d ht-cfreq: %d ht->primary_chan: %d band: %d - Disabling HT\n", + cbss->channel->center_freq, + ht_cfreq, ht_oper->primary_chan, + cbss->channel->band); ht_oper = NULL; } } @@ -3112,9 +3087,8 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, if (!ieee80211_set_channel_type(local, sdata, channel_type)) { /* can only fail due to HT40+/- mismatch */ channel_type = NL80211_CHAN_HT20; - printk(KERN_DEBUG - "%s: disabling 40 MHz due to multi-vif mismatch\n", - sdata->name); + sdata_info(sdata, + "disabling 40 MHz due to multi-vif mismatch\n"); ifmgd->flags |= IEEE80211_STA_DISABLE_40MHZ; WARN_ON(!ieee80211_set_channel_type(local, sdata, channel_type)); @@ -3123,7 +3097,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, local->oper_channel = cbss->channel; ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); - if (!have_sta) { + if (sta) { u32 rates = 0, basic_rates = 0; bool have_higher_than_11mbit; int min_rate = INT_MAX, min_rate_index = -1; @@ -3143,9 +3117,8 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, * we can connect -- with a warning. */ if (!basic_rates && min_rate_index >= 0) { - printk(KERN_DEBUG - "%s: No basic rates, using min rate instead.\n", - sdata->name); + sdata_info(sdata, + "No basic rates, using min rate instead\n"); basic_rates = BIT(min_rate_index); } @@ -3161,9 +3134,15 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, memcpy(ifmgd->bssid, cbss->bssid, ETH_ALEN); - /* tell driver about BSSID and basic rates */ + /* set timing information */ + sdata->vif.bss_conf.beacon_int = cbss->beacon_interval; + sdata->vif.bss_conf.sync_tsf = cbss->tsf; + sdata->vif.bss_conf.sync_device_ts = bss->device_ts; + + /* tell driver about BSSID, basic rates and timing */ ieee80211_bss_info_change_notify(sdata, - BSS_CHANGED_BSSID | BSS_CHANGED_BASIC_RATES); + BSS_CHANGED_BSSID | BSS_CHANGED_BASIC_RATES | + BSS_CHANGED_BEACON_INT); if (assoc) sta_info_pre_move_state(sta, IEEE80211_STA_AUTH); @@ -3171,9 +3150,9 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, err = sta_info_insert(sta); sta = NULL; if (err) { - printk(KERN_DEBUG - "%s: failed to insert STA entry for the AP (error %d)\n", - sdata->name, err); + sdata_info(sdata, + "failed to insert STA entry for the AP (error %d)\n", + err); return err; } } else @@ -3251,8 +3230,7 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, if (ifmgd->associated) ieee80211_set_disassoc(sdata, 0, 0, false, NULL); - printk(KERN_DEBUG "%s: authenticate with %pM\n", - sdata->name, req->bss->bssid); + sdata_info(sdata, "authenticate with %pM\n", req->bss->bssid); err = ieee80211_prep_connection(sdata, req->bss, false); if (err) @@ -3287,7 +3265,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, struct ieee80211_bss *bss = (void *)req->bss->priv; struct ieee80211_mgd_assoc_data *assoc_data; struct ieee80211_supported_band *sband; - const u8 *ssidie; + const u8 *ssidie, *ht_ie; int i, err; ssidie = ieee80211_bss_get_ie(req->bss, WLAN_EID_SSID); @@ -3335,11 +3313,15 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, * We can set this to true for non-11n hardware, that'll be checked * separately along with the peer capabilities. */ - for (i = 0; i < req->crypto.n_ciphers_pairwise; i++) + for (i = 0; i < req->crypto.n_ciphers_pairwise; i++) { if (req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP40 || req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_TKIP || - req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP104) + req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP104) { ifmgd->flags |= IEEE80211_STA_DISABLE_11N; + netdev_info(sdata->dev, + "disabling HT due to WEP/TKIP use\n"); + } + } if (req->flags & ASSOC_REQ_DISABLE_HT) ifmgd->flags |= IEEE80211_STA_DISABLE_11N; @@ -3347,8 +3329,11 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, /* Also disable HT if we don't support it or the AP doesn't use WMM */ sband = local->hw.wiphy->bands[req->bss->channel->band]; if (!sband->ht_cap.ht_supported || - local->hw.queues < IEEE80211_NUM_ACS || !bss->wmm_used) + local->hw.queues < IEEE80211_NUM_ACS || !bss->wmm_used) { ifmgd->flags |= IEEE80211_STA_DISABLE_11N; + netdev_info(sdata->dev, + "disabling HT as WMM/QoS is not supported\n"); + } memcpy(&ifmgd->ht_capa, &req->ht_capa, sizeof(ifmgd->ht_capa)); memcpy(&ifmgd->ht_capa_mask, &req->ht_capa_mask, @@ -3374,8 +3359,13 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, (local->hw.queues >= IEEE80211_NUM_ACS); assoc_data->supp_rates = bss->supp_rates; assoc_data->supp_rates_len = bss->supp_rates_len; - assoc_data->ht_operation_ie = - ieee80211_bss_get_ie(req->bss, WLAN_EID_HT_OPERATION); + + ht_ie = ieee80211_bss_get_ie(req->bss, WLAN_EID_HT_OPERATION); + if (ht_ie && ht_ie[1] >= sizeof(struct ieee80211_ht_operation)) + assoc_data->ap_ht_param = + ((struct ieee80211_ht_operation *)(ht_ie + 2))->ht_param; + else + ifmgd->flags |= IEEE80211_STA_DISABLE_11N; if (bss->wmm_used && bss->uapsd_supported && (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)) { @@ -3422,8 +3412,8 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, * Wait up to one beacon interval ... * should this be more if we miss one? */ - printk(KERN_DEBUG "%s: waiting for beacon from %pM\n", - sdata->name, ifmgd->bssid); + sdata_info(sdata, "waiting for beacon from %pM\n", + ifmgd->bssid); assoc_data->timeout = TU_TO_EXP_TIME(req->bss->beacon_interval); } else { assoc_data->have_beacon = true; @@ -3442,8 +3432,8 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, corrupt_type = "beacon"; } else if (bss->corrupt_data & IEEE80211_BSS_CORRUPT_PROBE_RESP) corrupt_type = "probe response"; - printk(KERN_DEBUG "%s: associating with AP with corrupt %s\n", - sdata->name, corrupt_type); + sdata_info(sdata, "associating with AP with corrupt %s\n", + corrupt_type); } err = 0; @@ -3472,9 +3462,9 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, return 0; } - printk(KERN_DEBUG - "%s: deauthenticating from %pM by local choice (reason=%d)\n", - sdata->name, req->bssid, req->reason_code); + sdata_info(sdata, + "deauthenticating from %pM by local choice (reason=%d)\n", + req->bssid, req->reason_code); if (ifmgd->associated && ether_addr_equal(ifmgd->associated->bssid, req->bssid)) @@ -3516,8 +3506,9 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, return -ENOLINK; } - printk(KERN_DEBUG "%s: disassociating from %pM by local choice (reason=%d)\n", - sdata->name, req->bss->bssid, req->reason_code); + sdata_info(sdata, + "disassociating from %pM by local choice (reason=%d)\n", + req->bss->bssid, req->reason_code); memcpy(bssid, req->bss->bssid, ETH_ALEN); ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DISASSOC, @@ -3558,10 +3549,3 @@ void ieee80211_cqm_rssi_notify(struct ieee80211_vif *vif, cfg80211_cqm_rssi_notify(sdata->dev, rssi_event, gfp); } EXPORT_SYMBOL(ieee80211_cqm_rssi_notify); - -unsigned char ieee80211_get_operstate(struct ieee80211_vif *vif) -{ - struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); - return sdata->dev->operstate; -} -EXPORT_SYMBOL(ieee80211_get_operstate); diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 935aa4b6dee..635c3250c66 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -15,7 +15,7 @@ #include <linux/export.h> #include <net/mac80211.h> #include "ieee80211_i.h" -#include "driver-trace.h" +#include "driver-ops.h" /* * Tell our hardware to disable PS. @@ -24,8 +24,7 @@ * because we *may* be doing work on-operating channel, and want our * hardware unconditionally awake, but still let the AP send us normal frames. */ -static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata, - bool tell_ap) +static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -46,8 +45,8 @@ static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata, ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); } - if (tell_ap && (!local->offchannel_ps_enabled || - !(local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK))) + if (!local->offchannel_ps_enabled || + !(local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK)) /* * If power save was enabled, no need to send a nullfunc * frame because AP knows that we are sleeping. But if the @@ -132,7 +131,7 @@ void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local, if (offchannel_ps_enable && (sdata->vif.type == NL80211_IFTYPE_STATION) && sdata->u.mgd.associated) - ieee80211_offchannel_ps_enable(sdata, true); + ieee80211_offchannel_ps_enable(sdata); } } mutex_unlock(&local->iflist_mtx); @@ -181,34 +180,58 @@ void ieee80211_offchannel_return(struct ieee80211_local *local, mutex_unlock(&local->iflist_mtx); } +void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc) +{ + if (roc->notified) + return; + + if (roc->mgmt_tx_cookie) { + if (!WARN_ON(!roc->frame)) { + ieee80211_tx_skb(roc->sdata, roc->frame); + roc->frame = NULL; + } + } else { + cfg80211_ready_on_channel(&roc->sdata->wdev, (unsigned long)roc, + roc->chan, roc->chan_type, + roc->req_duration, GFP_KERNEL); + } + + roc->notified = true; +} + static void ieee80211_hw_roc_start(struct work_struct *work) { struct ieee80211_local *local = container_of(work, struct ieee80211_local, hw_roc_start); - struct ieee80211_sub_if_data *sdata; + struct ieee80211_roc_work *roc, *dep, *tmp; mutex_lock(&local->mtx); - if (!local->hw_roc_channel) { - mutex_unlock(&local->mtx); - return; - } + if (list_empty(&local->roc_list)) + goto out_unlock; - if (local->hw_roc_skb) { - sdata = IEEE80211_DEV_TO_SUB_IF(local->hw_roc_dev); - ieee80211_tx_skb(sdata, local->hw_roc_skb); - local->hw_roc_skb = NULL; - } else { - cfg80211_ready_on_channel(local->hw_roc_dev, - local->hw_roc_cookie, - local->hw_roc_channel, - local->hw_roc_channel_type, - local->hw_roc_duration, - GFP_KERNEL); - } + roc = list_first_entry(&local->roc_list, struct ieee80211_roc_work, + list); + + if (!roc->started) + goto out_unlock; - ieee80211_recalc_idle(local); + roc->hw_begun = true; + roc->hw_start_time = local->hw_roc_start_time; + ieee80211_handle_roc_started(roc); + list_for_each_entry_safe(dep, tmp, &roc->dependents, list) { + ieee80211_handle_roc_started(dep); + + if (dep->duration > roc->duration) { + u32 dur = dep->duration; + dep->duration = dur - roc->duration; + roc->duration = dur; + list_del(&dep->list); + list_add(&dep->list, &roc->list); + } + } + out_unlock: mutex_unlock(&local->mtx); } @@ -216,52 +239,181 @@ void ieee80211_ready_on_channel(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); + local->hw_roc_start_time = jiffies; + trace_api_ready_on_channel(local); ieee80211_queue_work(hw, &local->hw_roc_start); } EXPORT_SYMBOL_GPL(ieee80211_ready_on_channel); -static void ieee80211_hw_roc_done(struct work_struct *work) +void ieee80211_start_next_roc(struct ieee80211_local *local) { - struct ieee80211_local *local = - container_of(work, struct ieee80211_local, hw_roc_done); + struct ieee80211_roc_work *roc; - mutex_lock(&local->mtx); + lockdep_assert_held(&local->mtx); - if (!local->hw_roc_channel) { - mutex_unlock(&local->mtx); + if (list_empty(&local->roc_list)) { + ieee80211_run_deferred_scan(local); return; } - /* was never transmitted */ - if (local->hw_roc_skb) { - u64 cookie; + roc = list_first_entry(&local->roc_list, struct ieee80211_roc_work, + list); - cookie = local->hw_roc_cookie ^ 2; + if (WARN_ON_ONCE(roc->started)) + return; + + if (local->ops->remain_on_channel) { + int ret, duration = roc->duration; + + /* XXX: duplicated, see ieee80211_start_roc_work() */ + if (!duration) + duration = 10; + + ret = drv_remain_on_channel(local, roc->chan, + roc->chan_type, + duration); + + roc->started = true; + + if (ret) { + wiphy_warn(local->hw.wiphy, + "failed to start next HW ROC (%d)\n", ret); + /* + * queue the work struct again to avoid recursion + * when multiple failures occur + */ + ieee80211_remain_on_channel_expired(&local->hw); + } + } else { + /* delay it a bit */ + ieee80211_queue_delayed_work(&local->hw, &roc->work, + round_jiffies_relative(HZ/2)); + } +} - cfg80211_mgmt_tx_status(local->hw_roc_dev, cookie, - local->hw_roc_skb->data, - local->hw_roc_skb->len, false, - GFP_KERNEL); +void ieee80211_roc_notify_destroy(struct ieee80211_roc_work *roc) +{ + struct ieee80211_roc_work *dep, *tmp; - kfree_skb(local->hw_roc_skb); - local->hw_roc_skb = NULL; - local->hw_roc_skb_for_status = NULL; + /* was never transmitted */ + if (roc->frame) { + cfg80211_mgmt_tx_status(&roc->sdata->wdev, + (unsigned long)roc->frame, + roc->frame->data, roc->frame->len, + false, GFP_KERNEL); + kfree_skb(roc->frame); } - if (!local->hw_roc_for_tx) - cfg80211_remain_on_channel_expired(local->hw_roc_dev, - local->hw_roc_cookie, - local->hw_roc_channel, - local->hw_roc_channel_type, + if (!roc->mgmt_tx_cookie) + cfg80211_remain_on_channel_expired(&roc->sdata->wdev, + (unsigned long)roc, + roc->chan, roc->chan_type, GFP_KERNEL); - local->hw_roc_channel = NULL; - local->hw_roc_cookie = 0; + list_for_each_entry_safe(dep, tmp, &roc->dependents, list) + ieee80211_roc_notify_destroy(dep); + + kfree(roc); +} + +void ieee80211_sw_roc_work(struct work_struct *work) +{ + struct ieee80211_roc_work *roc = + container_of(work, struct ieee80211_roc_work, work.work); + struct ieee80211_sub_if_data *sdata = roc->sdata; + struct ieee80211_local *local = sdata->local; + bool started; + + mutex_lock(&local->mtx); + + if (roc->abort) + goto finish; + + if (WARN_ON(list_empty(&local->roc_list))) + goto out_unlock; + + if (WARN_ON(roc != list_first_entry(&local->roc_list, + struct ieee80211_roc_work, + list))) + goto out_unlock; - ieee80211_recalc_idle(local); + if (!roc->started) { + struct ieee80211_roc_work *dep; + /* start this ROC */ + + /* switch channel etc */ + ieee80211_recalc_idle(local); + + local->tmp_channel = roc->chan; + local->tmp_channel_type = roc->chan_type; + ieee80211_hw_config(local, 0); + + /* tell userspace or send frame */ + ieee80211_handle_roc_started(roc); + list_for_each_entry(dep, &roc->dependents, list) + ieee80211_handle_roc_started(dep); + + /* if it was pure TX, just finish right away */ + if (!roc->duration) + goto finish; + + roc->started = true; + ieee80211_queue_delayed_work(&local->hw, &roc->work, + msecs_to_jiffies(roc->duration)); + } else { + /* finish this ROC */ + finish: + list_del(&roc->list); + started = roc->started; + ieee80211_roc_notify_destroy(roc); + + if (started) { + drv_flush(local, false); + + local->tmp_channel = NULL; + ieee80211_hw_config(local, 0); + + ieee80211_offchannel_return(local, true); + } + + ieee80211_recalc_idle(local); + + if (started) + ieee80211_start_next_roc(local); + } + + out_unlock: + mutex_unlock(&local->mtx); +} + +static void ieee80211_hw_roc_done(struct work_struct *work) +{ + struct ieee80211_local *local = + container_of(work, struct ieee80211_local, hw_roc_done); + struct ieee80211_roc_work *roc; + + mutex_lock(&local->mtx); + + if (list_empty(&local->roc_list)) + goto out_unlock; + + roc = list_first_entry(&local->roc_list, struct ieee80211_roc_work, + list); + + if (!roc->started) + goto out_unlock; + + list_del(&roc->list); + + ieee80211_roc_notify_destroy(roc); + + /* if there's another roc, start it now */ + ieee80211_start_next_roc(local); + + out_unlock: mutex_unlock(&local->mtx); } @@ -275,8 +427,47 @@ void ieee80211_remain_on_channel_expired(struct ieee80211_hw *hw) } EXPORT_SYMBOL_GPL(ieee80211_remain_on_channel_expired); -void ieee80211_hw_roc_setup(struct ieee80211_local *local) +void ieee80211_roc_setup(struct ieee80211_local *local) { INIT_WORK(&local->hw_roc_start, ieee80211_hw_roc_start); INIT_WORK(&local->hw_roc_done, ieee80211_hw_roc_done); + INIT_LIST_HEAD(&local->roc_list); +} + +void ieee80211_roc_purge(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_roc_work *roc, *tmp; + LIST_HEAD(tmp_list); + + mutex_lock(&local->mtx); + list_for_each_entry_safe(roc, tmp, &local->roc_list, list) { + if (roc->sdata != sdata) + continue; + + if (roc->started && local->ops->remain_on_channel) { + /* can race, so ignore return value */ + drv_cancel_remain_on_channel(local); + } + + list_move_tail(&roc->list, &tmp_list); + roc->abort = true; + } + + ieee80211_start_next_roc(local); + mutex_unlock(&local->mtx); + + list_for_each_entry_safe(roc, tmp, &tmp_list, list) { + if (local->ops->remain_on_channel) { + list_del(&roc->list); + ieee80211_roc_notify_destroy(roc); + } else { + ieee80211_queue_delayed_work(&local->hw, &roc->work, 0); + + /* work will clean up etc */ + flush_delayed_work(&roc->work); + } + } + + WARN_ON_ONCE(!list_empty(&tmp_list)); } diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index af1c4e26e96..5c572e7a1a7 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -77,6 +77,17 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) int err = drv_suspend(local, wowlan); if (err < 0) { local->quiescing = false; + local->wowlan = false; + if (hw->flags & IEEE80211_HW_AMPDU_AGGREGATION) { + mutex_lock(&local->sta_mtx); + list_for_each_entry(sta, + &local->sta_list, list) { + clear_sta_flag(sta, WLAN_STA_BLOCK_BA); + } + mutex_unlock(&local->sta_mtx); + } + ieee80211_wake_queues_by_reason(hw, + IEEE80211_QUEUE_STOP_REASON_SUSPEND); return err; } else if (err > 0) { WARN_ON(err != 1); diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index f9e51ef8dfa..fb1d4aa65e8 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -626,8 +626,12 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, #ifdef CONFIG_MAC80211_DEBUGFS /* use fixed index if set */ - if (mp->fixed_rate_idx != -1) - sample_idx = mp->fixed_rate_idx; + if (mp->fixed_rate_idx != -1) { + mi->max_tp_rate = mp->fixed_rate_idx; + mi->max_tp_rate2 = mp->fixed_rate_idx; + mi->max_prob_rate = mp->fixed_rate_idx; + sample_idx = -1; + } #endif if (sample_idx >= 0) { diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 965e6ec0adb..0cb4edee6af 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -94,7 +94,7 @@ ieee80211_rx_radiotap_len(struct ieee80211_local *local, return len; } -/* +/** * ieee80211_add_rx_radiotap_header - add radiotap header * * add a radiotap header containing all the fields which the hardware provided. @@ -413,29 +413,6 @@ static void ieee80211_verify_alignment(struct ieee80211_rx_data *rx) /* rx handlers */ -static ieee80211_rx_result debug_noinline -ieee80211_rx_h_passive_scan(struct ieee80211_rx_data *rx) -{ - struct ieee80211_local *local = rx->local; - struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); - struct sk_buff *skb = rx->skb; - - if (likely(!(status->rx_flags & IEEE80211_RX_IN_SCAN) && - !local->sched_scanning)) - return RX_CONTINUE; - - if (test_bit(SCAN_HW_SCANNING, &local->scanning) || - test_bit(SCAN_SW_SCANNING, &local->scanning) || - test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning) || - local->sched_scanning) - return ieee80211_scan_rx(rx->sdata, skb); - - /* scanning finished during invoking of handlers */ - I802_DEBUG_INC(local->rx_handlers_drop_passive_scan); - return RX_DROP_UNUSABLE; -} - - static int ieee80211_is_unicast_robust_mgmt_frame(struct sk_buff *skb) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; @@ -554,11 +531,11 @@ static inline u16 seq_sub(u16 sq1, u16 sq2) } -static void ieee80211_release_reorder_frame(struct ieee80211_hw *hw, +static void ieee80211_release_reorder_frame(struct ieee80211_sub_if_data *sdata, struct tid_ampdu_rx *tid_agg_rx, int index) { - struct ieee80211_local *local = hw_to_local(hw); + struct ieee80211_local *local = sdata->local; struct sk_buff *skb = tid_agg_rx->reorder_buf[index]; struct ieee80211_rx_status *status; @@ -578,7 +555,7 @@ no_frame: tid_agg_rx->head_seq_num = seq_inc(tid_agg_rx->head_seq_num); } -static void ieee80211_release_reorder_frames(struct ieee80211_hw *hw, +static void ieee80211_release_reorder_frames(struct ieee80211_sub_if_data *sdata, struct tid_ampdu_rx *tid_agg_rx, u16 head_seq_num) { @@ -589,7 +566,7 @@ static void ieee80211_release_reorder_frames(struct ieee80211_hw *hw, while (seq_less(tid_agg_rx->head_seq_num, head_seq_num)) { index = seq_sub(tid_agg_rx->head_seq_num, tid_agg_rx->ssn) % tid_agg_rx->buf_size; - ieee80211_release_reorder_frame(hw, tid_agg_rx, index); + ieee80211_release_reorder_frame(sdata, tid_agg_rx, index); } } @@ -604,7 +581,7 @@ static void ieee80211_release_reorder_frames(struct ieee80211_hw *hw, */ #define HT_RX_REORDER_BUF_TIMEOUT (HZ / 10) -static void ieee80211_sta_reorder_release(struct ieee80211_hw *hw, +static void ieee80211_sta_reorder_release(struct ieee80211_sub_if_data *sdata, struct tid_ampdu_rx *tid_agg_rx) { int index, j; @@ -632,12 +609,9 @@ static void ieee80211_sta_reorder_release(struct ieee80211_hw *hw, HT_RX_REORDER_BUF_TIMEOUT)) goto set_release_timer; -#ifdef CONFIG_MAC80211_HT_DEBUG - if (net_ratelimit()) - wiphy_debug(hw->wiphy, - "release an RX reorder frame due to timeout on earlier frames\n"); -#endif - ieee80211_release_reorder_frame(hw, tid_agg_rx, j); + ht_dbg_ratelimited(sdata, + "release an RX reorder frame due to timeout on earlier frames\n"); + ieee80211_release_reorder_frame(sdata, tid_agg_rx, j); /* * Increment the head seq# also for the skipped slots. @@ -647,7 +621,7 @@ static void ieee80211_sta_reorder_release(struct ieee80211_hw *hw, skipped = 0; } } else while (tid_agg_rx->reorder_buf[index]) { - ieee80211_release_reorder_frame(hw, tid_agg_rx, index); + ieee80211_release_reorder_frame(sdata, tid_agg_rx, index); index = seq_sub(tid_agg_rx->head_seq_num, tid_agg_rx->ssn) % tid_agg_rx->buf_size; } @@ -677,7 +651,7 @@ static void ieee80211_sta_reorder_release(struct ieee80211_hw *hw, * rcu_read_lock protection. It returns false if the frame * can be processed immediately, true if it was consumed. */ -static bool ieee80211_sta_manage_reorder_buf(struct ieee80211_hw *hw, +static bool ieee80211_sta_manage_reorder_buf(struct ieee80211_sub_if_data *sdata, struct tid_ampdu_rx *tid_agg_rx, struct sk_buff *skb) { @@ -706,7 +680,8 @@ static bool ieee80211_sta_manage_reorder_buf(struct ieee80211_hw *hw, if (!seq_less(mpdu_seq_num, head_seq_num + buf_size)) { head_seq_num = seq_inc(seq_sub(mpdu_seq_num, buf_size)); /* release stored frames up to new head to stack */ - ieee80211_release_reorder_frames(hw, tid_agg_rx, head_seq_num); + ieee80211_release_reorder_frames(sdata, tid_agg_rx, + head_seq_num); } /* Now the new frame is always in the range of the reordering buffer */ @@ -736,7 +711,7 @@ static bool ieee80211_sta_manage_reorder_buf(struct ieee80211_hw *hw, tid_agg_rx->reorder_buf[index] = skb; tid_agg_rx->reorder_time[index] = jiffies; tid_agg_rx->stored_mpdu_num++; - ieee80211_sta_reorder_release(hw, tid_agg_rx); + ieee80211_sta_reorder_release(sdata, tid_agg_rx); out: spin_unlock(&tid_agg_rx->reorder_lock); @@ -751,7 +726,6 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx) { struct sk_buff *skb = rx->skb; struct ieee80211_local *local = rx->local; - struct ieee80211_hw *hw = &local->hw; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct sta_info *sta = rx->sta; @@ -813,7 +787,7 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx) * sure that we cannot get to it any more before doing * anything with it. */ - if (ieee80211_sta_manage_reorder_buf(hw, tid_agg_rx, skb)) + if (ieee80211_sta_manage_reorder_buf(rx->sdata, tid_agg_rx, skb)) return; dont_reorder: @@ -1136,24 +1110,18 @@ static void ap_sta_ps_start(struct sta_info *sta) set_sta_flag(sta, WLAN_STA_PS_STA); if (!(local->hw.flags & IEEE80211_HW_AP_LINK_PS)) drv_sta_notify(local, sdata, STA_NOTIFY_SLEEP, &sta->sta); -#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - printk(KERN_DEBUG "%s: STA %pM aid %d enters power save mode\n", - sdata->name, sta->sta.addr, sta->sta.aid); -#endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ + ps_dbg(sdata, "STA %pM aid %d enters power save mode\n", + sta->sta.addr, sta->sta.aid); } static void ap_sta_ps_end(struct sta_info *sta) { -#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - printk(KERN_DEBUG "%s: STA %pM aid %d exits power save mode\n", - sta->sdata->name, sta->sta.addr, sta->sta.aid); -#endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ + ps_dbg(sta->sdata, "STA %pM aid %d exits power save mode\n", + sta->sta.addr, sta->sta.aid); if (test_sta_flag(sta, WLAN_STA_PS_DRIVER)) { -#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - printk(KERN_DEBUG "%s: STA %pM aid %d driver-ps-blocked\n", - sta->sdata->name, sta->sta.addr, sta->sta.aid); -#endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ + ps_dbg(sta->sdata, "STA %pM aid %d driver-ps-blocked\n", + sta->sta.addr, sta->sta.aid); return; } @@ -1383,19 +1351,8 @@ ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, if (sdata->fragment_next >= IEEE80211_FRAGMENT_MAX) sdata->fragment_next = 0; - if (!skb_queue_empty(&entry->skb_list)) { -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - struct ieee80211_hdr *hdr = - (struct ieee80211_hdr *) entry->skb_list.next->data; - printk(KERN_DEBUG "%s: RX reassembly removed oldest " - "fragment entry (idx=%d age=%lu seq=%d last_frag=%d " - "addr1=%pM addr2=%pM\n", - sdata->name, idx, - jiffies - entry->first_frag_time, entry->seq, - entry->last_frag, hdr->addr1, hdr->addr2); -#endif + if (!skb_queue_empty(&entry->skb_list)) __skb_queue_purge(&entry->skb_list); - } __skb_queue_tail(&entry->skb_list, *skb); /* no need for locking */ *skb = NULL; @@ -1753,7 +1710,7 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) */ xmit_skb = skb_copy(skb, GFP_ATOMIC); if (!xmit_skb) - net_dbg_ratelimited("%s: failed to clone multicast frame\n", + net_info_ratelimited("%s: failed to clone multicast frame\n", dev->name); } else { dsta = sta_info_get(sdata, skb->data); @@ -1937,7 +1894,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) ether_addr_equal(sdata->vif.addr, hdr->addr3)) return RX_CONTINUE; - q = ieee80211_select_queue_80211(local, skb, hdr); + q = ieee80211_select_queue_80211(sdata, skb, hdr); if (ieee80211_queue_stopped(&local->hw, q)) { IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_congestion); return RX_DROP_MONITOR; @@ -1957,7 +1914,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) fwd_skb = skb_copy(skb, GFP_ATOMIC); if (!fwd_skb) { - net_dbg_ratelimited("%s: failed to clone mesh frame\n", + net_info_ratelimited("%s: failed to clone mesh frame\n", sdata->name); goto out; } @@ -2060,8 +2017,6 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx) static ieee80211_rx_result debug_noinline ieee80211_rx_h_ctrl(struct ieee80211_rx_data *rx) { - struct ieee80211_local *local = rx->local; - struct ieee80211_hw *hw = &local->hw; struct sk_buff *skb = rx->skb; struct ieee80211_bar *bar = (struct ieee80211_bar *)skb->data; struct tid_ampdu_rx *tid_agg_rx; @@ -2098,7 +2053,8 @@ ieee80211_rx_h_ctrl(struct ieee80211_rx_data *rx) spin_lock(&tid_agg_rx->reorder_lock); /* release stored frames up to start of BAR */ - ieee80211_release_reorder_frames(hw, tid_agg_rx, start_seq_num); + ieee80211_release_reorder_frames(rx->sdata, tid_agg_rx, + start_seq_num); spin_unlock(&tid_agg_rx->reorder_lock); kfree_skb(skb); @@ -2425,7 +2381,7 @@ ieee80211_rx_h_userspace_mgmt(struct ieee80211_rx_data *rx) if (rx->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) sig = status->signal; - if (cfg80211_rx_mgmt(rx->sdata->dev, status->freq, sig, + if (cfg80211_rx_mgmt(&rx->sdata->wdev, status->freq, sig, rx->skb->data, rx->skb->len, GFP_ATOMIC)) { if (rx->sta) @@ -2716,7 +2672,6 @@ static void ieee80211_invoke_rx_handlers(struct ieee80211_rx_data *rx) goto rxh_next; \ } while (0); - CALL_RXH(ieee80211_rx_h_passive_scan) CALL_RXH(ieee80211_rx_h_check) ieee80211_rx_reorder_ampdu(rx); @@ -2752,7 +2707,7 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) return; spin_lock(&tid_agg_rx->reorder_lock); - ieee80211_sta_reorder_release(&sta->local->hw, tid_agg_rx); + ieee80211_sta_reorder_release(sta->sdata, tid_agg_rx); spin_unlock(&tid_agg_rx->reorder_lock); ieee80211_rx_handlers(&rx); @@ -2786,11 +2741,8 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, return 0; if (ieee80211_is_beacon(hdr->frame_control)) { return 1; - } - else if (!ieee80211_bssid_match(bssid, sdata->u.ibss.bssid)) { - if (!(status->rx_flags & IEEE80211_RX_IN_SCAN)) - return 0; - status->rx_flags &= ~IEEE80211_RX_RA_MATCH; + } else if (!ieee80211_bssid_match(bssid, sdata->u.ibss.bssid)) { + return 0; } else if (!multicast && !ether_addr_equal(sdata->vif.addr, hdr->addr1)) { if (!(sdata->dev->flags & IFF_PROMISC)) @@ -2828,11 +2780,9 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, * and location updates. Note that mac80211 * itself never looks at these frames. */ - if (!(status->rx_flags & IEEE80211_RX_IN_SCAN) && - ieee80211_is_public_action(hdr, skb->len)) + if (ieee80211_is_public_action(hdr, skb->len)) return 1; - if (!(status->rx_flags & IEEE80211_RX_IN_SCAN) && - !ieee80211_is_beacon(hdr->frame_control)) + if (!ieee80211_is_beacon(hdr->frame_control)) return 0; status->rx_flags &= ~IEEE80211_RX_RA_MATCH; } @@ -2898,7 +2848,6 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, struct sk_buff *skb) { - struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_sub_if_data *sdata; struct ieee80211_hdr *hdr; @@ -2916,11 +2865,6 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, if (ieee80211_is_data(fc) || ieee80211_is_mgmt(fc)) local->dot11ReceivedFragmentCount++; - if (unlikely(test_bit(SCAN_HW_SCANNING, &local->scanning) || - test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning) || - test_bit(SCAN_SW_SCANNING, &local->scanning))) - status->rx_flags |= IEEE80211_RX_IN_SCAN; - if (ieee80211_is_mgmt(fc)) err = skb_linearize(skb); else @@ -2935,6 +2879,10 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, ieee80211_parse_qos(&rx); ieee80211_verify_alignment(&rx); + if (unlikely(ieee80211_is_probe_resp(hdr->frame_control) || + ieee80211_is_beacon(hdr->frame_control))) + ieee80211_scan_rx(local, skb); + if (ieee80211_is_data(fc)) { prev_sta = NULL; @@ -3032,6 +2980,10 @@ void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) if (unlikely(local->quiescing || local->suspended)) goto drop; + /* We might be during a HW reconfig, prevent Rx for the same reason */ + if (unlikely(local->in_reconfig)) + goto drop; + /* * The same happens when we're not even started, * but that's worth a warning. diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 169da0742c8..839dd973798 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -83,13 +83,14 @@ ieee80211_bss_info_update(struct ieee80211_local *local, cbss = cfg80211_inform_bss_frame(local->hw.wiphy, channel, mgmt, len, signal, GFP_ATOMIC); - if (!cbss) return NULL; cbss->free_priv = ieee80211_rx_bss_free; bss = (void *)cbss->priv; + bss->device_ts = rx_status->device_timestamp; + if (elems->parse_error) { if (beacon) bss->corrupt_data |= IEEE80211_BSS_CORRUPT_BEACON; @@ -114,8 +115,7 @@ ieee80211_bss_info_update(struct ieee80211_local *local, if (elems->tim && (!elems->parse_error || !(bss->valid_data & IEEE80211_BSS_VALID_DTIM))) { - struct ieee80211_tim_ie *tim_ie = - (struct ieee80211_tim_ie *)elems->tim; + struct ieee80211_tim_ie *tim_ie = elems->tim; bss->dtim_period = tim_ie->dtim_period; if (!elems->parse_error) bss->valid_data |= IEEE80211_BSS_VALID_DTIM; @@ -165,52 +165,47 @@ ieee80211_bss_info_update(struct ieee80211_local *local, return bss; } -ieee80211_rx_result -ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) +void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) { struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); - struct ieee80211_mgmt *mgmt; + struct ieee80211_sub_if_data *sdata1, *sdata2; + struct ieee80211_mgmt *mgmt = (void *)skb->data; struct ieee80211_bss *bss; u8 *elements; struct ieee80211_channel *channel; size_t baselen; int freq; - __le16 fc; - bool presp, beacon = false; + bool beacon; struct ieee802_11_elems elems; - if (skb->len < 2) - return RX_DROP_UNUSABLE; - - mgmt = (struct ieee80211_mgmt *) skb->data; - fc = mgmt->frame_control; + if (skb->len < 24 || + (!ieee80211_is_probe_resp(mgmt->frame_control) && + !ieee80211_is_beacon(mgmt->frame_control))) + return; - if (ieee80211_is_ctl(fc)) - return RX_CONTINUE; + sdata1 = rcu_dereference(local->scan_sdata); + sdata2 = rcu_dereference(local->sched_scan_sdata); - if (skb->len < 24) - return RX_CONTINUE; + if (likely(!sdata1 && !sdata2)) + return; - presp = ieee80211_is_probe_resp(fc); - if (presp) { + if (ieee80211_is_probe_resp(mgmt->frame_control)) { /* ignore ProbeResp to foreign address */ - if (!ether_addr_equal(mgmt->da, sdata->vif.addr)) - return RX_DROP_MONITOR; + if ((!sdata1 || !ether_addr_equal(mgmt->da, sdata1->vif.addr)) && + (!sdata2 || !ether_addr_equal(mgmt->da, sdata2->vif.addr))) + return; - presp = true; elements = mgmt->u.probe_resp.variable; baselen = offsetof(struct ieee80211_mgmt, u.probe_resp.variable); + beacon = false; } else { - beacon = ieee80211_is_beacon(fc); baselen = offsetof(struct ieee80211_mgmt, u.beacon.variable); elements = mgmt->u.beacon.variable; + beacon = true; } - if (!presp && !beacon) - return RX_CONTINUE; - if (baselen > skb->len) - return RX_DROP_MONITOR; + return; ieee802_11_parse_elems(elements, skb->len - baselen, &elems); @@ -220,22 +215,16 @@ ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) else freq = rx_status->freq; - channel = ieee80211_get_channel(sdata->local->hw.wiphy, freq); + channel = ieee80211_get_channel(local->hw.wiphy, freq); if (!channel || channel->flags & IEEE80211_CHAN_DISABLED) - return RX_DROP_MONITOR; + return; - bss = ieee80211_bss_info_update(sdata->local, rx_status, + bss = ieee80211_bss_info_update(local, rx_status, mgmt, skb->len, &elems, channel, beacon); if (bss) - ieee80211_rx_bss_put(sdata->local, bss); - - if (channel == sdata->local->oper_channel) - return RX_CONTINUE; - - dev_kfree_skb(skb); - return RX_QUEUED; + ieee80211_rx_bss_put(local, bss); } /* return false if no more work */ @@ -293,7 +282,13 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted, return; if (was_hw_scan && !aborted && ieee80211_prep_hw_scan(local)) { - int rc = drv_hw_scan(local, local->scan_sdata, local->hw_scan_req); + int rc; + + rc = drv_hw_scan(local, + rcu_dereference_protected(local->scan_sdata, + lockdep_is_held(&local->mtx)), + local->hw_scan_req); + if (rc == 0) return; } @@ -304,7 +299,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted, if (local->scan_req != local->int_scan_req) cfg80211_scan_done(local->scan_req, aborted); local->scan_req = NULL; - local->scan_sdata = NULL; + rcu_assign_pointer(local->scan_sdata, NULL); local->scanning = 0; local->scan_channel = NULL; @@ -323,7 +318,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted, ieee80211_mlme_notify_scan_completed(local); ieee80211_ibss_notify_scan_completed(local); ieee80211_mesh_notify_scan_completed(local); - ieee80211_queue_work(&local->hw, &local->work_work); + ieee80211_start_next_roc(local); } void ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) @@ -376,7 +371,7 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local) static bool ieee80211_can_scan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { - if (!list_empty(&local->work_list)) + if (!list_empty(&local->roc_list)) return false; if (sdata->vif.type == NL80211_IFTYPE_STATION && @@ -394,7 +389,10 @@ void ieee80211_run_deferred_scan(struct ieee80211_local *local) if (!local->scan_req || local->scanning) return; - if (!ieee80211_can_scan(local, local->scan_sdata)) + if (!ieee80211_can_scan(local, + rcu_dereference_protected( + local->scan_sdata, + lockdep_is_held(&local->mtx)))) return; ieee80211_queue_delayed_work(&local->hw, &local->scan_work, @@ -405,9 +403,12 @@ static void ieee80211_scan_state_send_probe(struct ieee80211_local *local, unsigned long *next_delay) { int i; - struct ieee80211_sub_if_data *sdata = local->scan_sdata; + struct ieee80211_sub_if_data *sdata; enum ieee80211_band band = local->hw.conf.channel->band; + sdata = rcu_dereference_protected(local->scan_sdata, + lockdep_is_held(&local->mtx));; + for (i = 0; i < local->scan_req->n_ssids; i++) ieee80211_send_probe_req( sdata, NULL, @@ -439,7 +440,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, if (!ieee80211_can_scan(local, sdata)) { /* wait for the work to finish/time out */ local->scan_req = req; - local->scan_sdata = sdata; + rcu_assign_pointer(local->scan_sdata, sdata); return 0; } @@ -473,7 +474,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, } local->scan_req = req; - local->scan_sdata = sdata; + rcu_assign_pointer(local->scan_sdata, sdata); if (local->ops->hw_scan) { __set_bit(SCAN_HW_SCANNING, &local->scanning); @@ -533,7 +534,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, ieee80211_recalc_idle(local); local->scan_req = NULL; - local->scan_sdata = NULL; + rcu_assign_pointer(local->scan_sdata, NULL); } return rc; @@ -720,7 +721,8 @@ void ieee80211_scan_work(struct work_struct *work) mutex_lock(&local->mtx); - sdata = local->scan_sdata; + sdata = rcu_dereference_protected(local->scan_sdata, + lockdep_is_held(&local->mtx)); /* When scanning on-channel, the first-callback means completed. */ if (test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning)) { @@ -741,7 +743,7 @@ void ieee80211_scan_work(struct work_struct *work) int rc; local->scan_req = NULL; - local->scan_sdata = NULL; + rcu_assign_pointer(local->scan_sdata, NULL); rc = __ieee80211_start_scan(sdata, req); if (rc) { @@ -893,7 +895,9 @@ void ieee80211_scan_cancel(struct ieee80211_local *local) if (test_bit(SCAN_HW_SCANNING, &local->scanning)) { if (local->ops->cancel_hw_scan) - drv_cancel_hw_scan(local, local->scan_sdata); + drv_cancel_hw_scan(local, + rcu_dereference_protected(local->scan_sdata, + lockdep_is_held(&local->mtx))); goto out; } @@ -915,9 +919,9 @@ int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; int ret, i; - mutex_lock(&sdata->local->mtx); + mutex_lock(&local->mtx); - if (local->sched_scanning) { + if (rcu_access_pointer(local->sched_scan_sdata)) { ret = -EBUSY; goto out; } @@ -928,6 +932,9 @@ int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, } for (i = 0; i < IEEE80211_NUM_BANDS; i++) { + if (!local->hw.wiphy->bands[i]) + continue; + local->sched_scan_ies.ie[i] = kzalloc(2 + IEEE80211_MAX_SSID_LEN + local->scan_ies_len + @@ -948,7 +955,7 @@ int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, ret = drv_sched_scan_start(local, sdata, req, &local->sched_scan_ies); if (ret == 0) { - local->sched_scanning = true; + rcu_assign_pointer(local->sched_scan_sdata, sdata); goto out; } @@ -956,7 +963,7 @@ out_free: while (i > 0) kfree(local->sched_scan_ies.ie[--i]); out: - mutex_unlock(&sdata->local->mtx); + mutex_unlock(&local->mtx); return ret; } @@ -965,22 +972,21 @@ int ieee80211_request_sched_scan_stop(struct ieee80211_sub_if_data *sdata) struct ieee80211_local *local = sdata->local; int ret = 0, i; - mutex_lock(&sdata->local->mtx); + mutex_lock(&local->mtx); if (!local->ops->sched_scan_stop) { ret = -ENOTSUPP; goto out; } - if (local->sched_scanning) { + if (rcu_access_pointer(local->sched_scan_sdata)) { for (i = 0; i < IEEE80211_NUM_BANDS; i++) kfree(local->sched_scan_ies.ie[i]); drv_sched_scan_stop(local, sdata); - local->sched_scanning = false; } out: - mutex_unlock(&sdata->local->mtx); + mutex_unlock(&local->mtx); return ret; } @@ -1004,7 +1010,7 @@ void ieee80211_sched_scan_stopped_work(struct work_struct *work) mutex_lock(&local->mtx); - if (!local->sched_scanning) { + if (!rcu_access_pointer(local->sched_scan_sdata)) { mutex_unlock(&local->mtx); return; } @@ -1012,7 +1018,7 @@ void ieee80211_sched_scan_stopped_work(struct work_struct *work) for (i = 0; i < IEEE80211_NUM_BANDS; i++) kfree(local->sched_scan_ies.ie[i]); - local->sched_scanning = false; + rcu_assign_pointer(local->sched_scan_sdata, NULL); mutex_unlock(&local->mtx); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index de455f8bbb9..06fa75ceb02 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -169,9 +169,7 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) if (sta->rate_ctrl) rate_control_free_sta(sta); -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - wiphy_debug(local->hw.wiphy, "Destroyed STA %pM\n", sta->sta.addr); -#endif /* CONFIG_MAC80211_VERBOSE_DEBUG */ + sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr); kfree(sta); } @@ -278,9 +276,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, for (i = 0; i < NUM_RX_DATA_QUEUES; i++) sta->last_seq_ctrl[i] = cpu_to_le16(USHRT_MAX); -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - wiphy_debug(local->hw.wiphy, "Allocated STA %pM\n", sta->sta.addr); -#endif /* CONFIG_MAC80211_VERBOSE_DEBUG */ + sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr); #ifdef CONFIG_MAC80211_MESH sta->plink_state = NL80211_PLINK_LISTEN; @@ -333,9 +329,9 @@ static int sta_info_insert_drv_state(struct ieee80211_local *local, } if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { - printk(KERN_DEBUG - "%s: failed to move IBSS STA %pM to state %d (%d) - keeping it anyway.\n", - sdata->name, sta->sta.addr, state + 1, err); + sdata_info(sdata, + "failed to move IBSS STA %pM to state %d (%d) - keeping it anyway\n", + sta->sta.addr, state + 1, err); err = 0; } @@ -390,9 +386,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) sinfo.generation = local->sta_generation; cfg80211_new_sta(sdata->dev, sta->sta.addr, &sinfo, GFP_KERNEL); -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - wiphy_debug(local->hw.wiphy, "Inserted STA %pM\n", sta->sta.addr); -#endif /* CONFIG_MAC80211_VERBOSE_DEBUG */ + sta_dbg(sdata, "Inserted STA %pM\n", sta->sta.addr); /* move reference to rcu-protected */ rcu_read_lock(); @@ -618,10 +612,8 @@ static bool sta_info_cleanup_expire_buffered_ac(struct ieee80211_local *local, break; local->total_ps_buffered--; -#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - printk(KERN_DEBUG "Buffered frame expired (STA %pM)\n", + ps_dbg(sta->sdata, "Buffered frame expired (STA %pM)\n", sta->sta.addr); -#endif dev_kfree_skb(skb); } @@ -747,9 +739,8 @@ int __must_check __sta_info_destroy(struct sta_info *sta) mesh_accept_plinks_update(sdata); #endif -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - wiphy_debug(local->hw.wiphy, "Removed STA %pM\n", sta->sta.addr); -#endif /* CONFIG_MAC80211_VERBOSE_DEBUG */ + sta_dbg(sdata, "Removed STA %pM\n", sta->sta.addr); + cancel_work_sync(&sta->drv_unblock_wk); cfg80211_del_sta(sdata->dev, sta->sta.addr, GFP_KERNEL); @@ -889,10 +880,8 @@ void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata, continue; if (time_after(jiffies, sta->last_rx + exp_time)) { -#ifdef CONFIG_MAC80211_IBSS_DEBUG - printk(KERN_DEBUG "%s: expiring inactive STA %pM\n", - sdata->name, sta->sta.addr); -#endif + ibss_dbg(sdata, "expiring inactive STA %pM\n", + sta->sta.addr); WARN_ON(__sta_info_destroy(sta)); } } @@ -990,11 +979,9 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) sta_info_recalc_tim(sta); -#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - printk(KERN_DEBUG "%s: STA %pM aid %d sending %d filtered/%d PS frames " - "since STA not sleeping anymore\n", sdata->name, + ps_dbg(sdata, + "STA %pM aid %d sending %d filtered/%d PS frames since STA not sleeping anymore\n", sta->sta.addr, sta->sta.aid, filtered, buffered); -#endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ } static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata, @@ -1384,10 +1371,8 @@ int sta_info_move_state(struct sta_info *sta, return -EINVAL; } -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - printk(KERN_DEBUG "%s: moving STA %pM to state %d\n", - sta->sdata->name, sta->sta.addr, new_state); -#endif + sta_dbg(sta->sdata, "moving STA %pM to state %d\n", + sta->sta.addr, new_state); /* * notify the driver before the actual changes so it can diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 28cfa981cfb..8cd72914cda 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -155,13 +155,10 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, return; } -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - if (net_ratelimit()) - wiphy_debug(local->hw.wiphy, - "dropped TX filtered frame, queue_len=%d PS=%d @%lu\n", - skb_queue_len(&sta->tx_filtered[ac]), - !!test_sta_flag(sta, WLAN_STA_PS_STA), jiffies); -#endif + ps_dbg_ratelimited(sta->sdata, + "dropped TX filtered frame, queue_len=%d PS=%d @%lu\n", + skb_queue_len(&sta->tx_filtered[ac]), + !!test_sta_flag(sta, WLAN_STA_PS_STA), jiffies); dev_kfree_skb(skb); } @@ -520,36 +517,21 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) if (info->flags & IEEE80211_TX_INTFL_NL80211_FRAME_TX) { u64 cookie = (unsigned long)skb; + acked = info->flags & IEEE80211_TX_STAT_ACK; - if (ieee80211_is_nullfunc(hdr->frame_control) || - ieee80211_is_qos_nullfunc(hdr->frame_control)) { - acked = info->flags & IEEE80211_TX_STAT_ACK; + /* + * TODO: When we have non-netdev frame TX, + * we cannot use skb->dev->ieee80211_ptr + */ + if (ieee80211_is_nullfunc(hdr->frame_control) || + ieee80211_is_qos_nullfunc(hdr->frame_control)) cfg80211_probe_status(skb->dev, hdr->addr1, cookie, acked, GFP_ATOMIC); - } else { - struct ieee80211_work *wk; - - rcu_read_lock(); - list_for_each_entry_rcu(wk, &local->work_list, list) { - if (wk->type != IEEE80211_WORK_OFFCHANNEL_TX) - continue; - if (wk->offchan_tx.frame != skb) - continue; - wk->offchan_tx.status = true; - break; - } - rcu_read_unlock(); - if (local->hw_roc_skb_for_status == skb) { - cookie = local->hw_roc_cookie ^ 2; - local->hw_roc_skb_for_status = NULL; - } - + else cfg80211_mgmt_tx_status( - skb->dev, cookie, skb->data, skb->len, - !!(info->flags & IEEE80211_TX_STAT_ACK), - GFP_ATOMIC); - } + skb->dev->ieee80211_ptr, cookie, skb->data, + skb->len, acked, GFP_ATOMIC); } if (unlikely(info->ack_frame_id)) { @@ -589,7 +571,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) /* send frame to monitor interfaces now */ rtap_len = ieee80211_tx_radiotap_len(info); if (WARN_ON_ONCE(skb_headroom(skb) < rtap_len)) { - printk(KERN_ERR "ieee80211_tx_status: headroom too small\n"); + pr_err("ieee80211_tx_status: headroom too small\n"); dev_kfree_skb(skb); return; } diff --git a/net/mac80211/tkip.c b/net/mac80211/tkip.c index 51077a956a8..57e14d59e12 100644 --- a/net/mac80211/tkip.c +++ b/net/mac80211/tkip.c @@ -260,17 +260,6 @@ int ieee80211_tkip_decrypt_data(struct crypto_cipher *tfm, keyid = pos[3]; iv32 = get_unaligned_le32(pos + 4); pos += 8; -#ifdef CONFIG_MAC80211_TKIP_DEBUG - { - int i; - printk(KERN_DEBUG "TKIP decrypt: data(len=%zd)", payload_len); - for (i = 0; i < payload_len; i++) - printk(" %02x", payload[i]); - printk("\n"); - printk(KERN_DEBUG "TKIP decrypt: iv16=%04x iv32=%08x\n", - iv16, iv32); - } -#endif if (!(keyid & (1 << 5))) return TKIP_DECRYPT_NO_EXT_IV; @@ -281,16 +270,8 @@ int ieee80211_tkip_decrypt_data(struct crypto_cipher *tfm, if (key->u.tkip.rx[queue].state != TKIP_STATE_NOT_INIT && (iv32 < key->u.tkip.rx[queue].iv32 || (iv32 == key->u.tkip.rx[queue].iv32 && - iv16 <= key->u.tkip.rx[queue].iv16))) { -#ifdef CONFIG_MAC80211_TKIP_DEBUG - printk(KERN_DEBUG "TKIP replay detected for RX frame from " - "%pM (RX IV (%04x,%02x) <= prev. IV (%04x,%02x)\n", - ta, - iv32, iv16, key->u.tkip.rx[queue].iv32, - key->u.tkip.rx[queue].iv16); -#endif + iv16 <= key->u.tkip.rx[queue].iv16))) return TKIP_DECRYPT_REPLAY; - } if (only_iv) { res = TKIP_DECRYPT_OK; @@ -302,22 +283,6 @@ int ieee80211_tkip_decrypt_data(struct crypto_cipher *tfm, key->u.tkip.rx[queue].iv32 != iv32) { /* IV16 wrapped around - perform TKIP phase 1 */ tkip_mixing_phase1(tk, &key->u.tkip.rx[queue], ta, iv32); -#ifdef CONFIG_MAC80211_TKIP_DEBUG - { - int i; - u8 key_offset = NL80211_TKIP_DATA_OFFSET_ENCR_KEY; - printk(KERN_DEBUG "TKIP decrypt: Phase1 TA=%pM" - " TK=", ta); - for (i = 0; i < 16; i++) - printk("%02x ", - key->conf.key[key_offset + i]); - printk("\n"); - printk(KERN_DEBUG "TKIP decrypt: P1K="); - for (i = 0; i < 5; i++) - printk("%04x ", key->u.tkip.rx[queue].p1k[i]); - printk("\n"); - } -#endif } if (key->local->ops->update_tkip_key && key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && @@ -333,15 +298,6 @@ int ieee80211_tkip_decrypt_data(struct crypto_cipher *tfm, } tkip_mixing_phase2(tk, &key->u.tkip.rx[queue], iv16, rc4key); -#ifdef CONFIG_MAC80211_TKIP_DEBUG - { - int i; - printk(KERN_DEBUG "TKIP decrypt: Phase2 rc4key="); - for (i = 0; i < 16; i++) - printk("%02x ", rc4key[i]); - printk("\n"); - } -#endif res = ieee80211_wep_decrypt_data(tfm, rc4key, 16, pos, payload_len - 12); done: diff --git a/net/mac80211/trace.c b/net/mac80211/trace.c new file mode 100644 index 00000000000..386e45d8a95 --- /dev/null +++ b/net/mac80211/trace.c @@ -0,0 +1,75 @@ +/* bug in tracepoint.h, it should include this */ +#include <linux/module.h> + +/* sparse isn't too happy with all macros... */ +#ifndef __CHECKER__ +#include <net/cfg80211.h> +#include "driver-ops.h" +#include "debug.h" +#define CREATE_TRACE_POINTS +#include "trace.h" + +#ifdef CONFIG_MAC80211_MESSAGE_TRACING +void __sdata_info(const char *fmt, ...) +{ + struct va_format vaf = { + .fmt = fmt, + }; + va_list args; + + va_start(args, fmt); + vaf.va = &args; + + pr_info("%pV", &vaf); + trace_mac80211_info(&vaf); + va_end(args); +} + +void __sdata_dbg(bool print, const char *fmt, ...) +{ + struct va_format vaf = { + .fmt = fmt, + }; + va_list args; + + va_start(args, fmt); + vaf.va = &args; + + if (print) + pr_debug("%pV", &vaf); + trace_mac80211_dbg(&vaf); + va_end(args); +} + +void __sdata_err(const char *fmt, ...) +{ + struct va_format vaf = { + .fmt = fmt, + }; + va_list args; + + va_start(args, fmt); + vaf.va = &args; + + pr_err("%pV", &vaf); + trace_mac80211_err(&vaf); + va_end(args); +} + +void __wiphy_dbg(struct wiphy *wiphy, bool print, const char *fmt, ...) +{ + struct va_format vaf = { + .fmt = fmt, + }; + va_list args; + + va_start(args, fmt); + vaf.va = &args; + + if (print) + wiphy_dbg(wiphy, "%pV", &vaf); + trace_mac80211_dbg(&vaf); + va_end(args); +} +#endif +#endif diff --git a/net/mac80211/driver-trace.h b/net/mac80211/trace.h index 6de00b2c268..c6d33b55b2d 100644 --- a/net/mac80211/driver-trace.h +++ b/net/mac80211/trace.h @@ -306,7 +306,8 @@ TRACE_EVENT(drv_bss_info_changed, __field(u8, dtimper) __field(u16, bcnint) __field(u16, assoc_cap) - __field(u64, timestamp) + __field(u64, sync_tsf) + __field(u32, sync_device_ts) __field(u32, basic_rates) __field(u32, changed) __field(bool, enable_beacon) @@ -325,7 +326,8 @@ TRACE_EVENT(drv_bss_info_changed, __entry->dtimper = info->dtim_period; __entry->bcnint = info->beacon_int; __entry->assoc_cap = info->assoc_capability; - __entry->timestamp = info->last_tsf; + __entry->sync_tsf = info->sync_tsf; + __entry->sync_device_ts = info->sync_device_ts; __entry->basic_rates = info->basic_rates; __entry->enable_beacon = info->enable_beacon; __entry->ht_operation_mode = info->ht_operation_mode; @@ -1218,6 +1220,39 @@ DEFINE_EVENT(release_evt, drv_allow_buffered_frames, TP_ARGS(local, sta, tids, num_frames, reason, more_data) ); +TRACE_EVENT(drv_get_rssi, + TP_PROTO(struct ieee80211_local *local, struct ieee80211_sta *sta, + s8 rssi, int ret), + + TP_ARGS(local, sta, rssi, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + STA_ENTRY + __field(s8, rssi) + __field(int, ret) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + STA_ASSIGN; + __entry->rssi = rssi; + __entry->ret = ret; + ), + + TP_printk( + LOCAL_PR_FMT STA_PR_FMT " rssi:%d ret:%d", + LOCAL_PR_ARG, STA_PR_ARG, __entry->rssi, __entry->ret + ) +); + +DEFINE_EVENT(local_sdata_evt, drv_mgd_prepare_tx, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata), + + TP_ARGS(local, sdata) +); + /* * Tracing for API calls that drivers call. */ @@ -1606,10 +1641,49 @@ TRACE_EVENT(stop_queue, LOCAL_PR_ARG, __entry->queue, __entry->reason ) ); + +#ifdef CONFIG_MAC80211_MESSAGE_TRACING +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mac80211_msg + +#define MAX_MSG_LEN 100 + +DECLARE_EVENT_CLASS(mac80211_msg_event, + TP_PROTO(struct va_format *vaf), + + TP_ARGS(vaf), + + TP_STRUCT__entry( + __dynamic_array(char, msg, MAX_MSG_LEN) + ), + + TP_fast_assign( + WARN_ON_ONCE(vsnprintf(__get_dynamic_array(msg), + MAX_MSG_LEN, vaf->fmt, + *vaf->va) >= MAX_MSG_LEN); + ), + + TP_printk("%s", __get_str(msg)) +); + +DEFINE_EVENT(mac80211_msg_event, mac80211_info, + TP_PROTO(struct va_format *vaf), + TP_ARGS(vaf) +); +DEFINE_EVENT(mac80211_msg_event, mac80211_dbg, + TP_PROTO(struct va_format *vaf), + TP_ARGS(vaf) +); +DEFINE_EVENT(mac80211_msg_event, mac80211_err, + TP_PROTO(struct va_format *vaf), + TP_ARGS(vaf) +); +#endif + #endif /* !__MAC80211_DRIVER_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE -#define TRACE_INCLUDE_FILE driver-trace +#define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index e453212fa17..c5e8c9c31f7 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -140,6 +140,8 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx, if (r->flags & IEEE80211_RATE_MANDATORY_A) mrate = r->bitrate; break; + case IEEE80211_BAND_60GHZ: + /* TODO, for now fall through */ case IEEE80211_NUM_BANDS: WARN_ON(1); break; @@ -175,12 +177,6 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx, return cpu_to_le16(dur); } -static inline int is_ieee80211_device(struct ieee80211_local *local, - struct net_device *dev) -{ - return local == wdev_priv(dev->ieee80211_ptr); -} - /* tx handlers */ static ieee80211_tx_result debug_noinline ieee80211_tx_h_dynamic_ps(struct ieee80211_tx_data *tx) @@ -297,10 +293,10 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx) if (unlikely(!assoc && ieee80211_is_data(hdr->frame_control))) { #ifdef CONFIG_MAC80211_VERBOSE_DEBUG - printk(KERN_DEBUG "%s: dropped data frame to not " - "associated station %pM\n", - tx->sdata->name, hdr->addr1); -#endif /* CONFIG_MAC80211_VERBOSE_DEBUG */ + sdata_info(tx->sdata, + "dropped data frame to not associated station %pM\n", + hdr->addr1); +#endif I802_DEBUG_INC(tx->local->tx_handlers_drop_not_assoc); return TX_DROP; } @@ -367,10 +363,7 @@ static void purge_old_ps_buffers(struct ieee80211_local *local) rcu_read_unlock(); local->total_ps_buffered = total; -#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - wiphy_debug(local->hw.wiphy, "PS buffers full - purged %d frames\n", - purged); -#endif + ps_dbg_hw(&local->hw, "PS buffers full - purged %d frames\n", purged); } static ieee80211_tx_result @@ -412,10 +405,8 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) purge_old_ps_buffers(tx->local); if (skb_queue_len(&tx->sdata->bss->ps_bc_buf) >= AP_MAX_BC_BUFFER) { -#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - net_dbg_ratelimited("%s: BC TX buffer full - dropping the oldest frame\n", - tx->sdata->name); -#endif + ps_dbg(tx->sdata, + "BC TX buffer full - dropping the oldest frame\n"); dev_kfree_skb(skb_dequeue(&tx->sdata->bss->ps_bc_buf)); } else tx->local->total_ps_buffered++; @@ -466,18 +457,15 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) return TX_CONTINUE; } -#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - printk(KERN_DEBUG "STA %pM aid %d: PS buffer for AC %d\n", + ps_dbg(sta->sdata, "STA %pM aid %d: PS buffer for AC %d\n", sta->sta.addr, sta->sta.aid, ac); -#endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER) purge_old_ps_buffers(tx->local); if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) { struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]); -#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - net_dbg_ratelimited("%s: STA %pM TX buffer for AC %d full - dropping oldest frame\n", - tx->sdata->name, sta->sta.addr, ac); -#endif + ps_dbg(tx->sdata, + "STA %pM TX buffer for AC %d full - dropping oldest frame\n", + sta->sta.addr, ac); dev_kfree_skb(old); } else tx->local->total_ps_buffered++; @@ -499,14 +487,11 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) sta_info_recalc_tim(sta); return TX_QUEUED; + } else if (unlikely(test_sta_flag(sta, WLAN_STA_PS_STA))) { + ps_dbg(tx->sdata, + "STA %pM in PS mode, but polling/in SP -> send frame\n", + sta->sta.addr); } -#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - else if (unlikely(test_sta_flag(sta, WLAN_STA_PS_STA))) { - printk(KERN_DEBUG - "%s: STA %pM in PS mode, but polling/in SP -> send frame\n", - tx->sdata->name, sta->sta.addr); - } -#endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ return TX_CONTINUE; } @@ -538,7 +523,7 @@ ieee80211_tx_h_check_control_port_protocol(struct ieee80211_tx_data *tx) static ieee80211_tx_result debug_noinline ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) { - struct ieee80211_key *key = NULL; + struct ieee80211_key *key; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; @@ -557,16 +542,23 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) else if (!is_multicast_ether_addr(hdr->addr1) && (key = rcu_dereference(tx->sdata->default_unicast_key))) tx->key = key; - else if (tx->sdata->drop_unencrypted && - (tx->skb->protocol != tx->sdata->control_port_protocol) && - !(info->flags & IEEE80211_TX_CTL_INJECTED) && - (!ieee80211_is_robust_mgmt_frame(hdr) || - (ieee80211_is_action(hdr->frame_control) && - tx->sta && test_sta_flag(tx->sta, WLAN_STA_MFP)))) { + else if (info->flags & IEEE80211_TX_CTL_INJECTED) + tx->key = NULL; + else if (!tx->sdata->drop_unencrypted) + tx->key = NULL; + else if (tx->skb->protocol == tx->sdata->control_port_protocol) + tx->key = NULL; + else if (ieee80211_is_robust_mgmt_frame(hdr) && + !(ieee80211_is_action(hdr->frame_control) && + tx->sta && test_sta_flag(tx->sta, WLAN_STA_MFP))) + tx->key = NULL; + else if (ieee80211_is_mgmt(hdr->frame_control) && + !ieee80211_is_robust_mgmt_frame(hdr)) + tx->key = NULL; + else { I802_DEBUG_INC(tx->local->tx_handlers_drop_unencrypted); return TX_DROP; - } else - tx->key = NULL; + } if (tx->key) { bool skip_hw = false; @@ -974,8 +966,7 @@ ieee80211_tx_h_fragment(struct ieee80211_tx_data *tx) info->control.rates[1].idx = -1; info->control.rates[2].idx = -1; info->control.rates[3].idx = -1; - info->control.rates[4].idx = -1; - BUILD_BUG_ON(IEEE80211_TX_MAX_RATES != 5); + BUILD_BUG_ON(IEEE80211_TX_MAX_RATES != 4); info->flags &= ~IEEE80211_TX_CTL_RATE_CTRL_PROBE; } else { hdr->frame_control &= ~morefrags; @@ -1310,11 +1301,8 @@ static bool __ieee80211_tx(struct ieee80211_local *local, break; } - if (local->ops->tx_frags) - drv_tx_frags(local, vif, pubsta, skbs); - else - result = ieee80211_tx_frags(local, vif, pubsta, skbs, - txpending); + result = ieee80211_tx_frags(local, vif, pubsta, skbs, + txpending); ieee80211_tpt_led_trig_tx(local, fc, led_len); ieee80211_led_tx(local, 1); @@ -1823,34 +1811,31 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, meshhdrlen = ieee80211_new_mesh_header(&mesh_hdr, sdata, NULL, NULL); } else { - int is_mesh_mcast = 1; - const u8 *mesh_da; + /* DS -> MBSS (802.11-2012 13.11.3.3). + * For unicast with unknown forwarding information, + * destination might be in the MBSS or if that fails + * forwarded to another mesh gate. In either case + * resolution will be handled in ieee80211_xmit(), so + * leave the original DA. This also works for mcast */ + const u8 *mesh_da = skb->data; + + if (mppath) + mesh_da = mppath->mpp; + else if (mpath) + mesh_da = mpath->dst; + rcu_read_unlock(); - if (is_multicast_ether_addr(skb->data)) - /* DA TA mSA AE:SA */ - mesh_da = skb->data; - else { - static const u8 bcast[ETH_ALEN] = - { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; - if (mppath) { - /* RA TA mDA mSA AE:DA SA */ - mesh_da = mppath->mpp; - is_mesh_mcast = 0; - } else { - /* DA TA mSA AE:SA */ - mesh_da = bcast; - } - } hdrlen = ieee80211_fill_mesh_addresses(&hdr, &fc, mesh_da, sdata->vif.addr); - rcu_read_unlock(); - if (is_mesh_mcast) + if (is_multicast_ether_addr(mesh_da)) + /* DA TA mSA AE:SA */ meshhdrlen = ieee80211_new_mesh_header(&mesh_hdr, sdata, skb->data + ETH_ALEN, NULL); else + /* RA TA mDA mSA AE:DA SA */ meshhdrlen = ieee80211_new_mesh_header(&mesh_hdr, sdata, @@ -1965,7 +1950,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, (cpu_to_be16(ethertype) != sdata->control_port_protocol || !ether_addr_equal(sdata->vif.addr, skb->data + ETH_ALEN)))) { #ifdef CONFIG_MAC80211_VERBOSE_DEBUG - net_dbg_ratelimited("%s: dropped frame to %pM (unauthorized port)\n", + net_info_ratelimited("%s: dropped frame to %pM (unauthorized port)\n", dev->name, hdr.addr1); #endif @@ -2437,9 +2422,9 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, *pos++ = WLAN_EID_SSID; *pos++ = 0x0; - if (ieee80211_add_srates_ie(&sdata->vif, skb, true) || + if (ieee80211_add_srates_ie(sdata, skb, true) || mesh_add_ds_params_ie(skb, sdata) || - ieee80211_add_ext_srates_ie(&sdata->vif, skb, true) || + ieee80211_add_ext_srates_ie(sdata, skb, true) || mesh_add_rsn_ie(skb, sdata) || mesh_add_ht_cap_ie(skb, sdata) || mesh_add_ht_oper_ie(skb, sdata) || @@ -2733,7 +2718,7 @@ EXPORT_SYMBOL(ieee80211_get_buffered_bc); void ieee80211_tx_skb_tid(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int tid) { - int ac = ieee802_1d_to_ac[tid]; + int ac = ieee802_1d_to_ac[tid & 7]; skb_set_mac_header(skb, 0); skb_set_network_header(skb, 0); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 8dd4712620f..39b82fee490 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -268,6 +268,10 @@ EXPORT_SYMBOL(ieee80211_ctstoself_duration); void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue) { struct ieee80211_sub_if_data *sdata; + int n_acs = IEEE80211_NUM_ACS; + + if (local->hw.queues < IEEE80211_NUM_ACS) + n_acs = 1; list_for_each_entry_rcu(sdata, &local->interfaces, list) { int ac; @@ -279,7 +283,7 @@ void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue) local->queue_stop_reasons[sdata->vif.cab_queue] != 0) continue; - for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + for (ac = 0; ac < n_acs; ac++) { int ac_queue = sdata->vif.hw_queue[ac]; if (ac_queue == queue || @@ -341,6 +345,7 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_sub_if_data *sdata; + int n_acs = IEEE80211_NUM_ACS; trace_stop_queue(local, queue, reason); @@ -352,11 +357,14 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, __set_bit(reason, &local->queue_stop_reasons[queue]); + if (local->hw.queues < IEEE80211_NUM_ACS) + n_acs = 1; + rcu_read_lock(); list_for_each_entry_rcu(sdata, &local->interfaces, list) { int ac; - for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + for (ac = 0; ac < n_acs; ac++) { if (sdata->vif.hw_queue[ac] == queue || sdata->vif.cab_queue == queue) netif_stop_subqueue(sdata->dev, ac); @@ -521,6 +529,11 @@ void ieee80211_iterate_active_interfaces( &sdata->vif); } + sdata = rcu_dereference_protected(local->monitor_sdata, + lockdep_is_held(&local->iflist_mtx)); + if (sdata) + iterator(data, sdata->vif.addr, &sdata->vif); + mutex_unlock(&local->iflist_mtx); } EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces); @@ -549,6 +562,10 @@ void ieee80211_iterate_active_interfaces_atomic( &sdata->vif); } + sdata = rcu_dereference(local->monitor_sdata); + if (sdata) + iterator(data, sdata->vif.addr, &sdata->vif); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_atomic); @@ -804,7 +821,7 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct ieee80211_tx_queue_params qparam; int ac; - bool use_11b; + bool use_11b, enable_qos; int aCWmin, aCWmax; if (!local->ops->conf_tx) @@ -818,6 +835,13 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata, use_11b = (local->hw.conf.channel->band == IEEE80211_BAND_2GHZ) && !(sdata->flags & IEEE80211_SDATA_OPERATING_GMODE); + /* + * By default disable QoS in STA mode for old access points, which do + * not support 802.11e. New APs will provide proper queue parameters, + * that we will configure later. + */ + enable_qos = (sdata->vif.type != NL80211_IFTYPE_STATION); + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { /* Set defaults according to 802.11-2007 Table 7-37 */ aCWmax = 1023; @@ -826,38 +850,47 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata, else aCWmin = 15; - switch (ac) { - case IEEE80211_AC_BK: - qparam.cw_max = aCWmax; - qparam.cw_min = aCWmin; - qparam.txop = 0; - qparam.aifs = 7; - break; - default: /* never happens but let's not leave undefined */ - case IEEE80211_AC_BE: + if (enable_qos) { + switch (ac) { + case IEEE80211_AC_BK: + qparam.cw_max = aCWmax; + qparam.cw_min = aCWmin; + qparam.txop = 0; + qparam.aifs = 7; + break; + /* never happens but let's not leave undefined */ + default: + case IEEE80211_AC_BE: + qparam.cw_max = aCWmax; + qparam.cw_min = aCWmin; + qparam.txop = 0; + qparam.aifs = 3; + break; + case IEEE80211_AC_VI: + qparam.cw_max = aCWmin; + qparam.cw_min = (aCWmin + 1) / 2 - 1; + if (use_11b) + qparam.txop = 6016/32; + else + qparam.txop = 3008/32; + qparam.aifs = 2; + break; + case IEEE80211_AC_VO: + qparam.cw_max = (aCWmin + 1) / 2 - 1; + qparam.cw_min = (aCWmin + 1) / 4 - 1; + if (use_11b) + qparam.txop = 3264/32; + else + qparam.txop = 1504/32; + qparam.aifs = 2; + break; + } + } else { + /* Confiure old 802.11b/g medium access rules. */ qparam.cw_max = aCWmax; qparam.cw_min = aCWmin; qparam.txop = 0; - qparam.aifs = 3; - break; - case IEEE80211_AC_VI: - qparam.cw_max = aCWmin; - qparam.cw_min = (aCWmin + 1) / 2 - 1; - if (use_11b) - qparam.txop = 6016/32; - else - qparam.txop = 3008/32; - qparam.aifs = 2; - break; - case IEEE80211_AC_VO: - qparam.cw_max = (aCWmin + 1) / 2 - 1; - qparam.cw_min = (aCWmin + 1) / 4 - 1; - if (use_11b) - qparam.txop = 3264/32; - else - qparam.txop = 1504/32; qparam.aifs = 2; - break; } qparam.uapsd = false; @@ -866,12 +899,8 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata, drv_conf_tx(local, sdata, ac, &qparam); } - /* after reinitialize QoS TX queues setting to default, - * disable QoS at all */ - if (sdata->vif.type != NL80211_IFTYPE_MONITOR) { - sdata->vif.bss_conf.qos = - sdata->vif.type != NL80211_IFTYPE_STATION; + sdata->vif.bss_conf.qos = enable_qos; if (bss_notify) ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_QOS); @@ -979,6 +1008,8 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, int ext_rates_len; sband = local->hw.wiphy->bands[band]; + if (WARN_ON_ONCE(!sband)) + return 0; pos = buffer; @@ -1060,6 +1091,10 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, pos += noffset - offset; } + if (sband->vht_cap.vht_supported) + pos = ieee80211_ie_build_vht_cap(pos, &sband->vht_cap, + sband->vht_cap.cap); + return pos - buffer; } @@ -1267,14 +1302,19 @@ int ieee80211_reconfig(struct ieee80211_local *local) /* add STAs back */ mutex_lock(&local->sta_mtx); list_for_each_entry(sta, &local->sta_list, list) { - if (sta->uploaded) { - enum ieee80211_sta_state state; + enum ieee80211_sta_state state; - for (state = IEEE80211_STA_NOTEXIST; - state < sta->sta_state; state++) - WARN_ON(drv_sta_state(local, sta->sdata, sta, - state, state + 1)); - } + if (!sta->uploaded) + continue; + + /* AP-mode stations will be added later */ + if (sta->sdata->vif.type == NL80211_IFTYPE_AP) + continue; + + for (state = IEEE80211_STA_NOTEXIST; + state < sta->sta_state; state++) + WARN_ON(drv_sta_state(local, sta->sdata, sta, state, + state + 1)); } mutex_unlock(&local->sta_mtx); @@ -1371,12 +1411,33 @@ int ieee80211_reconfig(struct ieee80211_local *local) } } + /* APs are now beaconing, add back stations */ + mutex_lock(&local->sta_mtx); + list_for_each_entry(sta, &local->sta_list, list) { + enum ieee80211_sta_state state; + + if (!sta->uploaded) + continue; + + if (sta->sdata->vif.type != NL80211_IFTYPE_AP) + continue; + + for (state = IEEE80211_STA_NOTEXIST; + state < sta->sta_state; state++) + WARN_ON(drv_sta_state(local, sta->sdata, sta, state, + state + 1)); + } + mutex_unlock(&local->sta_mtx); + /* add back keys */ list_for_each_entry(sdata, &local->interfaces, list) if (ieee80211_sdata_running(sdata)) ieee80211_enable_keys(sdata); wake_up: + local->in_reconfig = false; + barrier(); + /* * Clear the WLAN_STA_BLOCK_BA flag so new aggregation * sessions can be established after a resume. @@ -1661,6 +1722,27 @@ u8 *ieee80211_ie_build_ht_cap(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, return pos; } +u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, + u32 cap) +{ + __le32 tmp; + + *pos++ = WLAN_EID_VHT_CAPABILITY; + *pos++ = sizeof(struct ieee80211_vht_capabilities); + memset(pos, 0, sizeof(struct ieee80211_vht_capabilities)); + + /* capability flags */ + tmp = cpu_to_le32(cap); + memcpy(pos, &tmp, sizeof(u32)); + pos += sizeof(u32); + + /* VHT MCS set */ + memcpy(pos, &vht_cap->vht_mcs, sizeof(vht_cap->vht_mcs)); + pos += sizeof(vht_cap->vht_mcs); + + return pos; +} + u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, struct ieee80211_channel *channel, enum nl80211_channel_type channel_type, @@ -1726,15 +1808,14 @@ ieee80211_ht_oper_to_channel_type(struct ieee80211_ht_operation *ht_oper) return channel_type; } -int ieee80211_add_srates_ie(struct ieee80211_vif *vif, +int ieee80211_add_srates_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, bool need_basic) { - struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; int rate; u8 i, rates, *pos; - u32 basic_rates = vif->bss_conf.basic_rates; + u32 basic_rates = sdata->vif.bss_conf.basic_rates; sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; rates = sband->n_bitrates; @@ -1758,15 +1839,14 @@ int ieee80211_add_srates_ie(struct ieee80211_vif *vif, return 0; } -int ieee80211_add_ext_srates_ie(struct ieee80211_vif *vif, +int ieee80211_add_ext_srates_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, bool need_basic) { - struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; int rate; u8 i, exrates, *pos; - u32 basic_rates = vif->bss_conf.basic_rates; + u32 basic_rates = sdata->vif.bss_conf.basic_rates; sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; exrates = sband->n_bitrates; diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index c3d643a6536..cea06e9f26f 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -52,11 +52,11 @@ static int wme_downgrade_ac(struct sk_buff *skb) } } -static u16 ieee80211_downgrade_queue(struct ieee80211_local *local, +static u16 ieee80211_downgrade_queue(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { /* in case we are a client verify acm is not set for this ac */ - while (unlikely(local->wmm_acm & BIT(skb->priority))) { + while (unlikely(sdata->wmm_acm & BIT(skb->priority))) { if (wme_downgrade_ac(skb)) { /* * This should not really happen. The AP has marked all @@ -73,10 +73,11 @@ static u16 ieee80211_downgrade_queue(struct ieee80211_local *local, } /* Indicate which queue to use for this fully formed 802.11 frame */ -u16 ieee80211_select_queue_80211(struct ieee80211_local *local, +u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, struct ieee80211_hdr *hdr) { + struct ieee80211_local *local = sdata->local; u8 *p; if (local->hw.queues < IEEE80211_NUM_ACS) @@ -94,7 +95,7 @@ u16 ieee80211_select_queue_80211(struct ieee80211_local *local, p = ieee80211_get_qos_ctl(hdr); skb->priority = *p & IEEE80211_QOS_CTL_TAG1D_MASK; - return ieee80211_downgrade_queue(local, skb); + return ieee80211_downgrade_queue(sdata, skb); } /* Indicate which queue to use. */ @@ -156,7 +157,7 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, * data frame has */ skb->priority = cfg80211_classify8021d(skb); - return ieee80211_downgrade_queue(local, skb); + return ieee80211_downgrade_queue(sdata, skb); } void ieee80211_set_qos_hdr(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/wme.h b/net/mac80211/wme.h index ca80818b7b6..7fea4bb8acb 100644 --- a/net/mac80211/wme.h +++ b/net/mac80211/wme.h @@ -15,7 +15,7 @@ extern const int ieee802_1d_to_ac[8]; -u16 ieee80211_select_queue_80211(struct ieee80211_local *local, +u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, struct ieee80211_hdr *hdr); u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/work.c b/net/mac80211/work.c deleted file mode 100644 index b2650a9d45f..00000000000 --- a/net/mac80211/work.c +++ /dev/null @@ -1,370 +0,0 @@ -/* - * mac80211 work implementation - * - * Copyright 2003-2008, Jouni Malinen <j@w1.fi> - * Copyright 2004, Instant802 Networks, Inc. - * Copyright 2005, Devicescape Software, Inc. - * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> - * Copyright 2007, Michael Wu <flamingice@sourmilk.net> - * Copyright 2009, Johannes Berg <johannes@sipsolutions.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/delay.h> -#include <linux/if_ether.h> -#include <linux/skbuff.h> -#include <linux/if_arp.h> -#include <linux/etherdevice.h> -#include <linux/crc32.h> -#include <linux/slab.h> -#include <net/mac80211.h> -#include <asm/unaligned.h> - -#include "ieee80211_i.h" -#include "rate.h" -#include "driver-ops.h" - -enum work_action { - WORK_ACT_NONE, - WORK_ACT_TIMEOUT, -}; - - -/* utils */ -static inline void ASSERT_WORK_MTX(struct ieee80211_local *local) -{ - lockdep_assert_held(&local->mtx); -} - -/* - * We can have multiple work items (and connection probing) - * scheduling this timer, but we need to take care to only - * reschedule it when it should fire _earlier_ than it was - * asked for before, or if it's not pending right now. This - * function ensures that. Note that it then is required to - * run this function for all timeouts after the first one - * has happened -- the work that runs from this timer will - * do that. - */ -static void run_again(struct ieee80211_local *local, - unsigned long timeout) -{ - ASSERT_WORK_MTX(local); - - if (!timer_pending(&local->work_timer) || - time_before(timeout, local->work_timer.expires)) - mod_timer(&local->work_timer, timeout); -} - -void free_work(struct ieee80211_work *wk) -{ - kfree_rcu(wk, rcu_head); -} - -static enum work_action __must_check -ieee80211_remain_on_channel_timeout(struct ieee80211_work *wk) -{ - /* - * First time we run, do nothing -- the generic code will - * have switched to the right channel etc. - */ - if (!wk->started) { - wk->timeout = jiffies + msecs_to_jiffies(wk->remain.duration); - - cfg80211_ready_on_channel(wk->sdata->dev, (unsigned long) wk, - wk->chan, wk->chan_type, - wk->remain.duration, GFP_KERNEL); - - return WORK_ACT_NONE; - } - - return WORK_ACT_TIMEOUT; -} - -static enum work_action __must_check -ieee80211_offchannel_tx(struct ieee80211_work *wk) -{ - if (!wk->started) { - wk->timeout = jiffies + msecs_to_jiffies(wk->offchan_tx.wait); - - /* - * After this, offchan_tx.frame remains but now is no - * longer a valid pointer -- we still need it as the - * cookie for canceling this work/status matching. - */ - ieee80211_tx_skb(wk->sdata, wk->offchan_tx.frame); - - return WORK_ACT_NONE; - } - - return WORK_ACT_TIMEOUT; -} - -static void ieee80211_work_timer(unsigned long data) -{ - struct ieee80211_local *local = (void *) data; - - if (local->quiescing) - return; - - ieee80211_queue_work(&local->hw, &local->work_work); -} - -static void ieee80211_work_work(struct work_struct *work) -{ - struct ieee80211_local *local = - container_of(work, struct ieee80211_local, work_work); - struct ieee80211_work *wk, *tmp; - LIST_HEAD(free_work); - enum work_action rma; - bool remain_off_channel = false; - - /* - * ieee80211_queue_work() should have picked up most cases, - * here we'll pick the rest. - */ - if (WARN(local->suspended, "work scheduled while going to suspend\n")) - return; - - mutex_lock(&local->mtx); - - if (local->scanning) { - mutex_unlock(&local->mtx); - return; - } - - ieee80211_recalc_idle(local); - - list_for_each_entry_safe(wk, tmp, &local->work_list, list) { - bool started = wk->started; - - /* mark work as started if it's on the current off-channel */ - if (!started && local->tmp_channel && - wk->chan == local->tmp_channel && - wk->chan_type == local->tmp_channel_type) { - started = true; - wk->timeout = jiffies; - } - - if (!started && !local->tmp_channel) { - ieee80211_offchannel_stop_vifs(local, true); - - local->tmp_channel = wk->chan; - local->tmp_channel_type = wk->chan_type; - - ieee80211_hw_config(local, 0); - - started = true; - wk->timeout = jiffies; - } - - /* don't try to work with items that aren't started */ - if (!started) - continue; - - if (time_is_after_jiffies(wk->timeout)) { - /* - * This work item isn't supposed to be worked on - * right now, but take care to adjust the timer - * properly. - */ - run_again(local, wk->timeout); - continue; - } - - switch (wk->type) { - default: - WARN_ON(1); - /* nothing */ - rma = WORK_ACT_NONE; - break; - case IEEE80211_WORK_ABORT: - rma = WORK_ACT_TIMEOUT; - break; - case IEEE80211_WORK_REMAIN_ON_CHANNEL: - rma = ieee80211_remain_on_channel_timeout(wk); - break; - case IEEE80211_WORK_OFFCHANNEL_TX: - rma = ieee80211_offchannel_tx(wk); - break; - } - - wk->started = started; - - switch (rma) { - case WORK_ACT_NONE: - /* might have changed the timeout */ - run_again(local, wk->timeout); - break; - case WORK_ACT_TIMEOUT: - list_del_rcu(&wk->list); - synchronize_rcu(); - list_add(&wk->list, &free_work); - break; - default: - WARN(1, "unexpected: %d", rma); - } - } - - list_for_each_entry(wk, &local->work_list, list) { - if (!wk->started) - continue; - if (wk->chan != local->tmp_channel || - wk->chan_type != local->tmp_channel_type) - continue; - remain_off_channel = true; - } - - if (!remain_off_channel && local->tmp_channel) { - local->tmp_channel = NULL; - ieee80211_hw_config(local, 0); - - ieee80211_offchannel_return(local, true); - - /* give connection some time to breathe */ - run_again(local, jiffies + HZ/2); - } - - ieee80211_recalc_idle(local); - ieee80211_run_deferred_scan(local); - - mutex_unlock(&local->mtx); - - list_for_each_entry_safe(wk, tmp, &free_work, list) { - wk->done(wk, NULL); - list_del(&wk->list); - kfree(wk); - } -} - -void ieee80211_add_work(struct ieee80211_work *wk) -{ - struct ieee80211_local *local; - - if (WARN_ON(!wk->chan)) - return; - - if (WARN_ON(!wk->sdata)) - return; - - if (WARN_ON(!wk->done)) - return; - - if (WARN_ON(!ieee80211_sdata_running(wk->sdata))) - return; - - wk->started = false; - - local = wk->sdata->local; - mutex_lock(&local->mtx); - list_add_tail(&wk->list, &local->work_list); - mutex_unlock(&local->mtx); - - ieee80211_queue_work(&local->hw, &local->work_work); -} - -void ieee80211_work_init(struct ieee80211_local *local) -{ - INIT_LIST_HEAD(&local->work_list); - setup_timer(&local->work_timer, ieee80211_work_timer, - (unsigned long)local); - INIT_WORK(&local->work_work, ieee80211_work_work); -} - -void ieee80211_work_purge(struct ieee80211_sub_if_data *sdata) -{ - struct ieee80211_local *local = sdata->local; - struct ieee80211_work *wk; - bool cleanup = false; - - mutex_lock(&local->mtx); - list_for_each_entry(wk, &local->work_list, list) { - if (wk->sdata != sdata) - continue; - cleanup = true; - wk->type = IEEE80211_WORK_ABORT; - wk->started = true; - wk->timeout = jiffies; - } - mutex_unlock(&local->mtx); - - /* run cleanups etc. */ - if (cleanup) - ieee80211_work_work(&local->work_work); - - mutex_lock(&local->mtx); - list_for_each_entry(wk, &local->work_list, list) { - if (wk->sdata != sdata) - continue; - WARN_ON(1); - break; - } - mutex_unlock(&local->mtx); -} - -static enum work_done_result ieee80211_remain_done(struct ieee80211_work *wk, - struct sk_buff *skb) -{ - /* - * We are done serving the remain-on-channel command. - */ - cfg80211_remain_on_channel_expired(wk->sdata->dev, (unsigned long) wk, - wk->chan, wk->chan_type, - GFP_KERNEL); - - return WORK_DONE_DESTROY; -} - -int ieee80211_wk_remain_on_channel(struct ieee80211_sub_if_data *sdata, - struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type, - unsigned int duration, u64 *cookie) -{ - struct ieee80211_work *wk; - - wk = kzalloc(sizeof(*wk), GFP_KERNEL); - if (!wk) - return -ENOMEM; - - wk->type = IEEE80211_WORK_REMAIN_ON_CHANNEL; - wk->chan = chan; - wk->chan_type = channel_type; - wk->sdata = sdata; - wk->done = ieee80211_remain_done; - - wk->remain.duration = duration; - - *cookie = (unsigned long) wk; - - ieee80211_add_work(wk); - - return 0; -} - -int ieee80211_wk_cancel_remain_on_channel(struct ieee80211_sub_if_data *sdata, - u64 cookie) -{ - struct ieee80211_local *local = sdata->local; - struct ieee80211_work *wk, *tmp; - bool found = false; - - mutex_lock(&local->mtx); - list_for_each_entry_safe(wk, tmp, &local->work_list, list) { - if ((unsigned long) wk == cookie) { - wk->timeout = jiffies; - found = true; - break; - } - } - mutex_unlock(&local->mtx); - - if (!found) - return -ENOENT; - - ieee80211_queue_work(&local->hw, &local->work_work); - - return 0; -} diff --git a/net/mac802154/Makefile b/net/mac802154/Makefile index ec1bd3fc127..57cf5d1a2e4 100644 --- a/net/mac802154/Makefile +++ b/net/mac802154/Makefile @@ -1,2 +1,2 @@ obj-$(CONFIG_MAC802154) += mac802154.o -mac802154-objs := ieee802154_dev.o rx.o tx.o mac_cmd.o mib.o monitor.o +mac802154-objs := ieee802154_dev.o rx.o tx.o mac_cmd.o mib.o monitor.o wpan.o diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c index e3edfb0661b..e748aed290a 100644 --- a/net/mac802154/ieee802154_dev.c +++ b/net/mac802154/ieee802154_dev.c @@ -140,6 +140,10 @@ mac802154_add_iface(struct wpan_phy *phy, const char *name, int type) dev = alloc_netdev(sizeof(struct mac802154_sub_if_data), name, mac802154_monitor_setup); break; + case IEEE802154_DEV_WPAN: + dev = alloc_netdev(sizeof(struct mac802154_sub_if_data), + name, mac802154_wpan_setup); + break; default: dev = NULL; err = -EINVAL; diff --git a/net/mac802154/mac802154.h b/net/mac802154/mac802154.h index 789d9c948ae..a4dcaf1dd4b 100644 --- a/net/mac802154/mac802154.h +++ b/net/mac802154/mac802154.h @@ -93,6 +93,7 @@ struct mac802154_sub_if_data { #define MAC802154_CHAN_NONE (~(u8)0) /* No channel is assigned */ extern struct ieee802154_reduced_mlme_ops mac802154_mlme_reduced; +extern struct ieee802154_mlme_ops mac802154_mlme_wpan; int mac802154_slave_open(struct net_device *dev); int mac802154_slave_close(struct net_device *dev); @@ -100,10 +101,18 @@ int mac802154_slave_close(struct net_device *dev); void mac802154_monitors_rx(struct mac802154_priv *priv, struct sk_buff *skb); void mac802154_monitor_setup(struct net_device *dev); +void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb); +void mac802154_wpan_setup(struct net_device *dev); + netdev_tx_t mac802154_tx(struct mac802154_priv *priv, struct sk_buff *skb, u8 page, u8 chan); /* MIB callbacks */ +void mac802154_dev_set_short_addr(struct net_device *dev, u16 val); +u16 mac802154_dev_get_short_addr(const struct net_device *dev); void mac802154_dev_set_ieee_addr(struct net_device *dev); +u16 mac802154_dev_get_pan_id(const struct net_device *dev); +void mac802154_dev_set_pan_id(struct net_device *dev, u16 val); +void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan); #endif /* MAC802154_H */ diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c index 7a5d0e052cd..d8d27700608 100644 --- a/net/mac802154/mac_cmd.c +++ b/net/mac802154/mac_cmd.c @@ -25,13 +25,37 @@ #include <linux/skbuff.h> #include <linux/if_arp.h> +#include <net/ieee802154.h> #include <net/ieee802154_netdev.h> #include <net/wpan-phy.h> #include <net/mac802154.h> +#include <net/nl802154.h> #include "mac802154.h" -struct wpan_phy *mac802154_get_phy(const struct net_device *dev) +static int mac802154_mlme_start_req(struct net_device *dev, + struct ieee802154_addr *addr, + u8 channel, u8 page, + u8 bcn_ord, u8 sf_ord, + u8 pan_coord, u8 blx, + u8 coord_realign) +{ + BUG_ON(addr->addr_type != IEEE802154_ADDR_SHORT); + + mac802154_dev_set_pan_id(dev, addr->pan_id); + mac802154_dev_set_short_addr(dev, addr->short_addr); + mac802154_dev_set_ieee_addr(dev); + mac802154_dev_set_page_channel(dev, page, channel); + + /* FIXME: add validation for unused parameters to be sane + * for SoftMAC + */ + ieee802154_nl_start_confirm(dev, IEEE802154_SUCCESS); + + return 0; +} + +static struct wpan_phy *mac802154_get_phy(const struct net_device *dev) { struct mac802154_sub_if_data *priv = netdev_priv(dev); @@ -43,3 +67,10 @@ struct wpan_phy *mac802154_get_phy(const struct net_device *dev) struct ieee802154_reduced_mlme_ops mac802154_mlme_reduced = { .get_phy = mac802154_get_phy, }; + +struct ieee802154_mlme_ops mac802154_mlme_wpan = { + .get_phy = mac802154_get_phy, + .start_req = mac802154_mlme_start_req, + .get_pan_id = mac802154_dev_get_pan_id, + .get_short_addr = mac802154_dev_get_short_addr, +}; diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c index ab59821ec72..f47781ab0cc 100644 --- a/net/mac802154/mib.c +++ b/net/mac802154/mib.c @@ -28,13 +28,18 @@ #include "mac802154.h" +struct phy_chan_notify_work { + struct work_struct work; + struct net_device *dev; +}; + struct hw_addr_filt_notify_work { struct work_struct work; struct net_device *dev; unsigned long changed; }; -struct mac802154_priv *mac802154_slave_get_priv(struct net_device *dev) +static struct mac802154_priv *mac802154_slave_get_priv(struct net_device *dev) { struct mac802154_sub_if_data *priv = netdev_priv(dev); @@ -78,6 +83,37 @@ static void set_hw_addr_filt(struct net_device *dev, unsigned long changed) return; } +void mac802154_dev_set_short_addr(struct net_device *dev, u16 val) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + spin_lock_bh(&priv->mib_lock); + priv->short_addr = val; + spin_unlock_bh(&priv->mib_lock); + + if ((priv->hw->ops->set_hw_addr_filt) && + (priv->hw->hw.hw_filt.short_addr != priv->short_addr)) { + priv->hw->hw.hw_filt.short_addr = priv->short_addr; + set_hw_addr_filt(dev, IEEE802515_AFILT_SADDR_CHANGED); + } +} + +u16 mac802154_dev_get_short_addr(const struct net_device *dev) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + u16 ret; + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + spin_lock_bh(&priv->mib_lock); + ret = priv->short_addr; + spin_unlock_bh(&priv->mib_lock); + + return ret; +} + void mac802154_dev_set_ieee_addr(struct net_device *dev) { struct mac802154_sub_if_data *priv = netdev_priv(dev); @@ -91,3 +127,73 @@ void mac802154_dev_set_ieee_addr(struct net_device *dev) set_hw_addr_filt(dev, IEEE802515_AFILT_IEEEADDR_CHANGED); } } + +u16 mac802154_dev_get_pan_id(const struct net_device *dev) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + u16 ret; + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + spin_lock_bh(&priv->mib_lock); + ret = priv->pan_id; + spin_unlock_bh(&priv->mib_lock); + + return ret; +} + +void mac802154_dev_set_pan_id(struct net_device *dev, u16 val) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + spin_lock_bh(&priv->mib_lock); + priv->pan_id = val; + spin_unlock_bh(&priv->mib_lock); + + if ((priv->hw->ops->set_hw_addr_filt) && + (priv->hw->hw.hw_filt.pan_id != priv->pan_id)) { + priv->hw->hw.hw_filt.pan_id = priv->pan_id; + set_hw_addr_filt(dev, IEEE802515_AFILT_PANID_CHANGED); + } +} + +static void phy_chan_notify(struct work_struct *work) +{ + struct phy_chan_notify_work *nw = container_of(work, + struct phy_chan_notify_work, work); + struct mac802154_priv *hw = mac802154_slave_get_priv(nw->dev); + struct mac802154_sub_if_data *priv = netdev_priv(nw->dev); + int res; + + res = hw->ops->set_channel(&hw->hw, priv->page, priv->chan); + if (res) + pr_debug("set_channel failed\n"); + + kfree(nw); +} + +void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + struct phy_chan_notify_work *work; + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + spin_lock_bh(&priv->mib_lock); + priv->page = page; + priv->chan = chan; + spin_unlock_bh(&priv->mib_lock); + + if (priv->hw->phy->current_channel != priv->chan || + priv->hw->phy->current_page != priv->page) { + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return; + + INIT_WORK(&work->work, phy_chan_notify); + work->dev = dev; + queue_work(priv->hw->dev_workqueue, &work->work); + } +} diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index 4a7d76d4f8b..38548ec2098 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -77,6 +77,7 @@ mac802154_subif_rx(struct ieee802154_dev *hw, struct sk_buff *skb, u8 lqi) } mac802154_monitors_rx(priv, skb); + mac802154_wpans_rx(priv, skb); out: dev_kfree_skb(skb); return; diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index 434b6873b35..1a4df39c722 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -88,6 +88,8 @@ netdev_tx_t mac802154_tx(struct mac802154_priv *priv, struct sk_buff *skb, return NETDEV_TX_OK; } + mac802154_monitors_rx(mac802154_to_priv(&priv->hw), skb); + if (!(priv->hw.flags & IEEE802154_HW_OMIT_CKSUM)) { u16 crc = crc_ccitt(0, skb->data, skb->len); u8 *data = skb_put(skb, 2); diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c new file mode 100644 index 00000000000..f30f6d4beea --- /dev/null +++ b/net/mac802154/wpan.c @@ -0,0 +1,559 @@ +/* + * Copyright 2007-2012 Siemens AG + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * + * Written by: + * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + * Sergey Lapin <slapin@ossfans.org> + * Maxim Gorbachyov <maxim.gorbachev@siemens.com> + * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> + */ + +#include <linux/netdevice.h> +#include <linux/module.h> +#include <linux/if_arp.h> + +#include <net/rtnetlink.h> +#include <linux/nl802154.h> +#include <net/af_ieee802154.h> +#include <net/mac802154.h> +#include <net/ieee802154_netdev.h> +#include <net/ieee802154.h> +#include <net/wpan-phy.h> + +#include "mac802154.h" + +static inline int mac802154_fetch_skb_u8(struct sk_buff *skb, u8 *val) +{ + if (unlikely(!pskb_may_pull(skb, 1))) + return -EINVAL; + + *val = skb->data[0]; + skb_pull(skb, 1); + + return 0; +} + +static inline int mac802154_fetch_skb_u16(struct sk_buff *skb, u16 *val) +{ + if (unlikely(!pskb_may_pull(skb, 2))) + return -EINVAL; + + *val = skb->data[0] | (skb->data[1] << 8); + skb_pull(skb, 2); + + return 0; +} + +static inline void mac802154_haddr_copy_swap(u8 *dest, const u8 *src) +{ + int i; + for (i = 0; i < IEEE802154_ADDR_LEN; i++) + dest[IEEE802154_ADDR_LEN - i - 1] = src[i]; +} + +static int +mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + struct sockaddr_ieee802154 *sa = + (struct sockaddr_ieee802154 *)&ifr->ifr_addr; + int err = -ENOIOCTLCMD; + + spin_lock_bh(&priv->mib_lock); + + switch (cmd) { + case SIOCGIFADDR: + if (priv->pan_id == IEEE802154_PANID_BROADCAST || + priv->short_addr == IEEE802154_ADDR_BROADCAST) { + err = -EADDRNOTAVAIL; + break; + } + + sa->family = AF_IEEE802154; + sa->addr.addr_type = IEEE802154_ADDR_SHORT; + sa->addr.pan_id = priv->pan_id; + sa->addr.short_addr = priv->short_addr; + + err = 0; + break; + case SIOCSIFADDR: + dev_warn(&dev->dev, + "Using DEBUGing ioctl SIOCSIFADDR isn't recommened!\n"); + if (sa->family != AF_IEEE802154 || + sa->addr.addr_type != IEEE802154_ADDR_SHORT || + sa->addr.pan_id == IEEE802154_PANID_BROADCAST || + sa->addr.short_addr == IEEE802154_ADDR_BROADCAST || + sa->addr.short_addr == IEEE802154_ADDR_UNDEF) { + err = -EINVAL; + break; + } + + priv->pan_id = sa->addr.pan_id; + priv->short_addr = sa->addr.short_addr; + + err = 0; + break; + } + + spin_unlock_bh(&priv->mib_lock); + return err; +} + +static int mac802154_wpan_mac_addr(struct net_device *dev, void *p) +{ + struct sockaddr *addr = p; + + if (netif_running(dev)) + return -EBUSY; + + /* FIXME: validate addr */ + memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); + mac802154_dev_set_ieee_addr(dev); + return 0; +} + +static int mac802154_header_create(struct sk_buff *skb, + struct net_device *dev, + unsigned short type, + const void *_daddr, + const void *_saddr, + unsigned len) +{ + const struct ieee802154_addr *saddr = _saddr; + const struct ieee802154_addr *daddr = _daddr; + struct ieee802154_addr dev_addr; + struct mac802154_sub_if_data *priv = netdev_priv(dev); + int pos = 2; + u8 *head; + u16 fc; + + if (!daddr) + return -EINVAL; + + head = kzalloc(MAC802154_FRAME_HARD_HEADER_LEN, GFP_KERNEL); + if (head == NULL) + return -ENOMEM; + + head[pos++] = mac_cb(skb)->seq; /* DSN/BSN */ + fc = mac_cb_type(skb); + + if (!saddr) { + spin_lock_bh(&priv->mib_lock); + + if (priv->short_addr == IEEE802154_ADDR_BROADCAST || + priv->short_addr == IEEE802154_ADDR_UNDEF || + priv->pan_id == IEEE802154_PANID_BROADCAST) { + dev_addr.addr_type = IEEE802154_ADDR_LONG; + memcpy(dev_addr.hwaddr, dev->dev_addr, + IEEE802154_ADDR_LEN); + } else { + dev_addr.addr_type = IEEE802154_ADDR_SHORT; + dev_addr.short_addr = priv->short_addr; + } + + dev_addr.pan_id = priv->pan_id; + saddr = &dev_addr; + + spin_unlock_bh(&priv->mib_lock); + } + + if (daddr->addr_type != IEEE802154_ADDR_NONE) { + fc |= (daddr->addr_type << IEEE802154_FC_DAMODE_SHIFT); + + head[pos++] = daddr->pan_id & 0xff; + head[pos++] = daddr->pan_id >> 8; + + if (daddr->addr_type == IEEE802154_ADDR_SHORT) { + head[pos++] = daddr->short_addr & 0xff; + head[pos++] = daddr->short_addr >> 8; + } else { + mac802154_haddr_copy_swap(head + pos, daddr->hwaddr); + pos += IEEE802154_ADDR_LEN; + } + } + + if (saddr->addr_type != IEEE802154_ADDR_NONE) { + fc |= (saddr->addr_type << IEEE802154_FC_SAMODE_SHIFT); + + if ((saddr->pan_id == daddr->pan_id) && + (saddr->pan_id != IEEE802154_PANID_BROADCAST)) { + /* PANID compression/intra PAN */ + fc |= IEEE802154_FC_INTRA_PAN; + } else { + head[pos++] = saddr->pan_id & 0xff; + head[pos++] = saddr->pan_id >> 8; + } + + if (saddr->addr_type == IEEE802154_ADDR_SHORT) { + head[pos++] = saddr->short_addr & 0xff; + head[pos++] = saddr->short_addr >> 8; + } else { + mac802154_haddr_copy_swap(head + pos, saddr->hwaddr); + pos += IEEE802154_ADDR_LEN; + } + } + + head[0] = fc; + head[1] = fc >> 8; + + memcpy(skb_push(skb, pos), head, pos); + kfree(head); + + return pos; +} + +static int +mac802154_header_parse(const struct sk_buff *skb, unsigned char *haddr) +{ + const u8 *hdr = skb_mac_header(skb); + const u8 *tail = skb_tail_pointer(skb); + struct ieee802154_addr *addr = (struct ieee802154_addr *)haddr; + u16 fc; + int da_type; + + if (hdr + 3 > tail) + goto malformed; + + fc = hdr[0] | (hdr[1] << 8); + + hdr += 3; + + da_type = IEEE802154_FC_DAMODE(fc); + addr->addr_type = IEEE802154_FC_SAMODE(fc); + + switch (da_type) { + case IEEE802154_ADDR_NONE: + if (fc & IEEE802154_FC_INTRA_PAN) + goto malformed; + break; + case IEEE802154_ADDR_LONG: + if (fc & IEEE802154_FC_INTRA_PAN) { + if (hdr + 2 > tail) + goto malformed; + addr->pan_id = hdr[0] | (hdr[1] << 8); + hdr += 2; + } + + if (hdr + IEEE802154_ADDR_LEN > tail) + goto malformed; + + hdr += IEEE802154_ADDR_LEN; + break; + case IEEE802154_ADDR_SHORT: + if (fc & IEEE802154_FC_INTRA_PAN) { + if (hdr + 2 > tail) + goto malformed; + addr->pan_id = hdr[0] | (hdr[1] << 8); + hdr += 2; + } + + if (hdr + 2 > tail) + goto malformed; + + hdr += 2; + break; + default: + goto malformed; + + } + + switch (addr->addr_type) { + case IEEE802154_ADDR_NONE: + break; + case IEEE802154_ADDR_LONG: + if (!(fc & IEEE802154_FC_INTRA_PAN)) { + if (hdr + 2 > tail) + goto malformed; + addr->pan_id = hdr[0] | (hdr[1] << 8); + hdr += 2; + } + + if (hdr + IEEE802154_ADDR_LEN > tail) + goto malformed; + + mac802154_haddr_copy_swap(addr->hwaddr, hdr); + hdr += IEEE802154_ADDR_LEN; + break; + case IEEE802154_ADDR_SHORT: + if (!(fc & IEEE802154_FC_INTRA_PAN)) { + if (hdr + 2 > tail) + goto malformed; + addr->pan_id = hdr[0] | (hdr[1] << 8); + hdr += 2; + } + + if (hdr + 2 > tail) + goto malformed; + + addr->short_addr = hdr[0] | (hdr[1] << 8); + hdr += 2; + break; + default: + goto malformed; + } + + return sizeof(struct ieee802154_addr); + +malformed: + pr_debug("malformed packet\n"); + return 0; +} + +static netdev_tx_t +mac802154_wpan_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct mac802154_sub_if_data *priv; + u8 chan, page; + + priv = netdev_priv(dev); + + spin_lock_bh(&priv->mib_lock); + chan = priv->chan; + page = priv->page; + spin_unlock_bh(&priv->mib_lock); + + if (chan == MAC802154_CHAN_NONE || + page >= WPAN_NUM_PAGES || + chan >= WPAN_NUM_CHANNELS) + return NETDEV_TX_OK; + + skb->skb_iif = dev->ifindex; + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; + + return mac802154_tx(priv->hw, skb, page, chan); +} + +static struct header_ops mac802154_header_ops = { + .create = mac802154_header_create, + .parse = mac802154_header_parse, +}; + +static const struct net_device_ops mac802154_wpan_ops = { + .ndo_open = mac802154_slave_open, + .ndo_stop = mac802154_slave_close, + .ndo_start_xmit = mac802154_wpan_xmit, + .ndo_do_ioctl = mac802154_wpan_ioctl, + .ndo_set_mac_address = mac802154_wpan_mac_addr, +}; + +void mac802154_wpan_setup(struct net_device *dev) +{ + struct mac802154_sub_if_data *priv; + + dev->addr_len = IEEE802154_ADDR_LEN; + memset(dev->broadcast, 0xff, IEEE802154_ADDR_LEN); + + dev->hard_header_len = MAC802154_FRAME_HARD_HEADER_LEN; + dev->header_ops = &mac802154_header_ops; + dev->needed_tailroom = 2; /* FCS */ + dev->mtu = IEEE802154_MTU; + dev->tx_queue_len = 10; + dev->type = ARPHRD_IEEE802154; + dev->flags = IFF_NOARP | IFF_BROADCAST; + dev->watchdog_timeo = 0; + + dev->destructor = free_netdev; + dev->netdev_ops = &mac802154_wpan_ops; + dev->ml_priv = &mac802154_mlme_wpan; + + priv = netdev_priv(dev); + priv->type = IEEE802154_DEV_WPAN; + + priv->chan = MAC802154_CHAN_NONE; + priv->page = 0; + + spin_lock_init(&priv->mib_lock); + + get_random_bytes(&priv->bsn, 1); + get_random_bytes(&priv->dsn, 1); + + priv->pan_id = IEEE802154_PANID_BROADCAST; + priv->short_addr = IEEE802154_ADDR_BROADCAST; +} + +static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb) +{ + return netif_rx(skb); +} + +static int +mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb) +{ + pr_debug("getting packet via slave interface %s\n", sdata->dev->name); + + spin_lock_bh(&sdata->mib_lock); + + switch (mac_cb(skb)->da.addr_type) { + case IEEE802154_ADDR_NONE: + if (mac_cb(skb)->sa.addr_type != IEEE802154_ADDR_NONE) + /* FIXME: check if we are PAN coordinator */ + skb->pkt_type = PACKET_OTHERHOST; + else + /* ACK comes with both addresses empty */ + skb->pkt_type = PACKET_HOST; + break; + case IEEE802154_ADDR_LONG: + if (mac_cb(skb)->da.pan_id != sdata->pan_id && + mac_cb(skb)->da.pan_id != IEEE802154_PANID_BROADCAST) + skb->pkt_type = PACKET_OTHERHOST; + else if (!memcmp(mac_cb(skb)->da.hwaddr, sdata->dev->dev_addr, + IEEE802154_ADDR_LEN)) + skb->pkt_type = PACKET_HOST; + else + skb->pkt_type = PACKET_OTHERHOST; + break; + case IEEE802154_ADDR_SHORT: + if (mac_cb(skb)->da.pan_id != sdata->pan_id && + mac_cb(skb)->da.pan_id != IEEE802154_PANID_BROADCAST) + skb->pkt_type = PACKET_OTHERHOST; + else if (mac_cb(skb)->da.short_addr == sdata->short_addr) + skb->pkt_type = PACKET_HOST; + else if (mac_cb(skb)->da.short_addr == + IEEE802154_ADDR_BROADCAST) + skb->pkt_type = PACKET_BROADCAST; + else + skb->pkt_type = PACKET_OTHERHOST; + break; + default: + break; + } + + spin_unlock_bh(&sdata->mib_lock); + + skb->dev = sdata->dev; + + sdata->dev->stats.rx_packets++; + sdata->dev->stats.rx_bytes += skb->len; + + switch (mac_cb_type(skb)) { + case IEEE802154_FC_TYPE_DATA: + return mac802154_process_data(sdata->dev, skb); + default: + pr_warning("ieee802154: bad frame received (type = %d)\n", + mac_cb_type(skb)); + kfree_skb(skb); + return NET_RX_DROP; + } +} + +static int mac802154_parse_frame_start(struct sk_buff *skb) +{ + u8 *head = skb->data; + u16 fc; + + if (mac802154_fetch_skb_u16(skb, &fc) || + mac802154_fetch_skb_u8(skb, &(mac_cb(skb)->seq))) + goto err; + + pr_debug("fc: %04x dsn: %02x\n", fc, head[2]); + + mac_cb(skb)->flags = IEEE802154_FC_TYPE(fc); + mac_cb(skb)->sa.addr_type = IEEE802154_FC_SAMODE(fc); + mac_cb(skb)->da.addr_type = IEEE802154_FC_DAMODE(fc); + + if (fc & IEEE802154_FC_INTRA_PAN) + mac_cb(skb)->flags |= MAC_CB_FLAG_INTRAPAN; + + if (mac_cb(skb)->da.addr_type != IEEE802154_ADDR_NONE) { + if (mac802154_fetch_skb_u16(skb, &(mac_cb(skb)->da.pan_id))) + goto err; + + /* source PAN id compression */ + if (mac_cb_is_intrapan(skb)) + mac_cb(skb)->sa.pan_id = mac_cb(skb)->da.pan_id; + + pr_debug("dest PAN addr: %04x\n", mac_cb(skb)->da.pan_id); + + if (mac_cb(skb)->da.addr_type == IEEE802154_ADDR_SHORT) { + u16 *da = &(mac_cb(skb)->da.short_addr); + + if (mac802154_fetch_skb_u16(skb, da)) + goto err; + + pr_debug("destination address is short: %04x\n", + mac_cb(skb)->da.short_addr); + } else { + if (!pskb_may_pull(skb, IEEE802154_ADDR_LEN)) + goto err; + + mac802154_haddr_copy_swap(mac_cb(skb)->da.hwaddr, + skb->data); + skb_pull(skb, IEEE802154_ADDR_LEN); + + pr_debug("destination address is hardware\n"); + } + } + + if (mac_cb(skb)->sa.addr_type != IEEE802154_ADDR_NONE) { + /* non PAN-compression, fetch source address id */ + if (!(mac_cb_is_intrapan(skb))) { + u16 *sa_pan = &(mac_cb(skb)->sa.pan_id); + + if (mac802154_fetch_skb_u16(skb, sa_pan)) + goto err; + } + + pr_debug("source PAN addr: %04x\n", mac_cb(skb)->da.pan_id); + + if (mac_cb(skb)->sa.addr_type == IEEE802154_ADDR_SHORT) { + u16 *sa = &(mac_cb(skb)->sa.short_addr); + + if (mac802154_fetch_skb_u16(skb, sa)) + goto err; + + pr_debug("source address is short: %04x\n", + mac_cb(skb)->sa.short_addr); + } else { + if (!pskb_may_pull(skb, IEEE802154_ADDR_LEN)) + goto err; + + mac802154_haddr_copy_swap(mac_cb(skb)->sa.hwaddr, + skb->data); + skb_pull(skb, IEEE802154_ADDR_LEN); + + pr_debug("source address is hardware\n"); + } + } + + return 0; +err: + return -EINVAL; +} + +void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb) +{ + int ret; + struct sk_buff *sskb; + struct mac802154_sub_if_data *sdata; + + ret = mac802154_parse_frame_start(skb); + if (ret) { + pr_debug("got invalid frame\n"); + return; + } + + rcu_read_lock(); + list_for_each_entry_rcu(sdata, &priv->slaves, list) { + if (sdata->type != IEEE802154_DEV_WPAN) + continue; + + sskb = skb_clone(skb, GFP_ATOMIC); + if (sskb) + mac802154_subif_frame(sdata, sskb); + } + rcu_read_unlock(); +} diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 209c1ed4336..c19b214ffd5 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -335,6 +335,27 @@ config NF_CT_NETLINK_TIMEOUT If unsure, say `N'. +config NF_CT_NETLINK_HELPER + tristate 'Connection tracking helpers in user-space via Netlink' + select NETFILTER_NETLINK + depends on NF_CT_NETLINK + depends on NETFILTER_NETLINK_QUEUE + depends on NETFILTER_NETLINK_QUEUE_CT + depends on NETFILTER_ADVANCED + help + This option enables the user-space connection tracking helpers + infrastructure. + + If unsure, say `N'. + +config NETFILTER_NETLINK_QUEUE_CT + bool "NFQUEUE integration with Connection Tracking" + default n + depends on NETFILTER_NETLINK_QUEUE + help + If this option is enabled, NFQUEUE can include Connection Tracking + information together with the packet is the enqueued via NFNETLINK. + endif # NF_CONNTRACK # transparent proxy support diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 4e7960cc7b9..1c5160f2278 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -9,6 +9,8 @@ obj-$(CONFIG_NETFILTER) = netfilter.o obj-$(CONFIG_NETFILTER_NETLINK) += nfnetlink.o obj-$(CONFIG_NETFILTER_NETLINK_ACCT) += nfnetlink_acct.o +nfnetlink_queue-y := nfnetlink_queue_core.o +nfnetlink_queue-$(CONFIG_NETFILTER_NETLINK_QUEUE_CT) += nfnetlink_queue_ct.o obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += nfnetlink_queue.o obj-$(CONFIG_NETFILTER_NETLINK_LOG) += nfnetlink_log.o @@ -24,6 +26,7 @@ obj-$(CONFIG_NF_CT_PROTO_UDPLITE) += nf_conntrack_proto_udplite.o # netlink interface for nf_conntrack obj-$(CONFIG_NF_CT_NETLINK) += nf_conntrack_netlink.o obj-$(CONFIG_NF_CT_NETLINK_TIMEOUT) += nfnetlink_cttimeout.o +obj-$(CONFIG_NF_CT_NETLINK_HELPER) += nfnetlink_cthelper.o # connection tracking helpers nf_conntrack_h323-objs := nf_conntrack_h323_main.o nf_conntrack_h323_asn1.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index e19f3653db2..0bc6b60db4d 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -264,6 +264,13 @@ void nf_conntrack_destroy(struct nf_conntrack *nfct) rcu_read_unlock(); } EXPORT_SYMBOL(nf_conntrack_destroy); + +struct nfq_ct_hook __rcu *nfq_ct_hook __read_mostly; +EXPORT_SYMBOL_GPL(nfq_ct_hook); + +struct nfq_ct_nat_hook __rcu *nfq_ct_nat_hook __read_mostly; +EXPORT_SYMBOL_GPL(nfq_ct_nat_hook); + #endif /* CONFIG_NF_CONNTRACK */ #ifdef CONFIG_PROC_FS diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index a54b018c6ee..b54eccef40b 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1742,7 +1742,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_reply4, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 2, }, @@ -1752,7 +1752,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_remote_request4, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 1, }, @@ -1760,7 +1760,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_local_reply4, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 1, }, @@ -1768,7 +1768,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_local_request4, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 2, }, @@ -1777,7 +1777,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_forward_icmp, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 99, }, @@ -1785,7 +1785,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_reply4, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 100, }, @@ -1794,7 +1794,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_reply6, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 2, }, @@ -1804,7 +1804,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_remote_request6, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 1, }, @@ -1812,7 +1812,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_local_reply6, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 1, }, @@ -1820,7 +1820,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_local_request6, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 2, }, @@ -1829,7 +1829,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_forward_icmp_v6, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 99, }, @@ -1837,7 +1837,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_reply6, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 100, }, diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 84444dda194..f51013c07b9 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1171,8 +1171,10 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, goto out_err; } svc->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); - if (!svc->stats.cpustats) + if (!svc->stats.cpustats) { + ret = -ENOMEM; goto out_err; + } /* I'm the first user of the service */ atomic_set(&svc->usecnt, 0); @@ -2759,6 +2761,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { struct ip_vs_timeout_user t; + memset(&t, 0, sizeof(t)); __ip_vs_get_timeouts(net, &t); if (copy_to_user(user, &t, sizeof(t)) != 0) ret = -EFAULT; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 7fd66dec859..65b616ae171 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -797,7 +797,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_put; } if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); df |= (old_iph->frag_off & htons(IP_DF)); @@ -823,7 +823,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_ERR_RL("%s(): no memory\n", __func__); return NF_STOLEN; } - kfree_skb(skb); + consume_skb(skb); skb = new_skb; old_iph = ip_hdr(skb); } @@ -913,7 +913,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_put; } if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) && !skb_is_gso(skb)) { @@ -942,7 +942,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_ERR_RL("%s(): no memory\n", __func__); return NF_STOLEN; } - kfree_skb(skb); + consume_skb(skb); skb = new_skb; old_iph = ipv6_hdr(skb); } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index ac3af97cc46..2ceec64b19f 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -249,12 +249,15 @@ static void death_by_event(unsigned long ul_conntrack) { struct nf_conn *ct = (void *)ul_conntrack; struct net *net = nf_ct_net(ct); + struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct); + + BUG_ON(ecache == NULL); if (nf_conntrack_event(IPCT_DESTROY, ct) < 0) { /* bad luck, let's retry again */ - ct->timeout.expires = jiffies + + ecache->timeout.expires = jiffies + (random32() % net->ct.sysctl_events_retry_timeout); - add_timer(&ct->timeout); + add_timer(&ecache->timeout); return; } /* we've got the event delivered, now it's dying */ @@ -268,6 +271,9 @@ static void death_by_event(unsigned long ul_conntrack) void nf_ct_insert_dying_list(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); + struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct); + + BUG_ON(ecache == NULL); /* add this conntrack to the dying list */ spin_lock_bh(&nf_conntrack_lock); @@ -275,10 +281,10 @@ void nf_ct_insert_dying_list(struct nf_conn *ct) &net->ct.dying); spin_unlock_bh(&nf_conntrack_lock); /* set a new timer to retry event delivery */ - setup_timer(&ct->timeout, death_by_event, (unsigned long)ct); - ct->timeout.expires = jiffies + + setup_timer(&ecache->timeout, death_by_event, (unsigned long)ct); + ecache->timeout.expires = jiffies + (random32() % net->ct.sysctl_events_retry_timeout); - add_timer(&ct->timeout); + add_timer(&ecache->timeout); } EXPORT_SYMBOL_GPL(nf_ct_insert_dying_list); @@ -531,7 +537,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) tstamp = nf_conn_tstamp_find(ct); if (tstamp) { if (skb->tstamp.tv64 == 0) - __net_timestamp((struct sk_buff *)skb); + __net_timestamp(skb); tstamp->start = ktime_to_ns(skb->tstamp); } @@ -819,7 +825,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, __set_bit(IPS_EXPECTED_BIT, &ct->status); ct->master = exp->master; if (exp->helper) { - help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); + help = nf_ct_helper_ext_add(ct, exp->helper, + GFP_ATOMIC); if (help) rcu_assign_pointer(help->helper, exp->helper); } @@ -1333,7 +1340,6 @@ static void nf_conntrack_cleanup_init_net(void) while (untrack_refs() > 0) schedule(); - nf_conntrack_proto_fini(); #ifdef CONFIG_NF_CONNTRACK_ZONES nf_ct_extend_unregister(&nf_ct_zone_extend); #endif @@ -1372,7 +1378,7 @@ void nf_conntrack_cleanup(struct net *net) netfilter framework. Roll on, two-stage module delete... */ synchronize_net(); - + nf_conntrack_proto_fini(net); nf_conntrack_cleanup_net(net); if (net_eq(net, &init_net)) { @@ -1496,11 +1502,6 @@ static int nf_conntrack_init_init_net(void) printk(KERN_INFO "nf_conntrack version %s (%u buckets, %d max)\n", NF_CONNTRACK_VERSION, nf_conntrack_htable_size, nf_conntrack_max); - - ret = nf_conntrack_proto_init(); - if (ret < 0) - goto err_proto; - #ifdef CONFIG_NF_CONNTRACK_ZONES ret = nf_ct_extend_register(&nf_ct_zone_extend); if (ret < 0) @@ -1518,9 +1519,7 @@ static int nf_conntrack_init_init_net(void) #ifdef CONFIG_NF_CONNTRACK_ZONES err_extend: - nf_conntrack_proto_fini(); #endif -err_proto: return ret; } @@ -1583,9 +1582,7 @@ static int nf_conntrack_init_net(struct net *net) ret = nf_conntrack_helper_init(net); if (ret < 0) goto err_helper; - return 0; - err_helper: nf_conntrack_timeout_fini(net); err_timeout: @@ -1622,6 +1619,9 @@ int nf_conntrack_init(struct net *net) if (ret < 0) goto out_init_net; } + ret = nf_conntrack_proto_init(net); + if (ret < 0) + goto out_proto; ret = nf_conntrack_init_net(net); if (ret < 0) goto out_net; @@ -1637,6 +1637,8 @@ int nf_conntrack_init(struct net *net) return 0; out_net: + nf_conntrack_proto_fini(net); +out_proto: if (net_eq(net, &init_net)) nf_conntrack_cleanup_init_net(); out_init_net: diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 45cf602a76b..527651a53a4 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -361,23 +361,6 @@ static void evict_oldest_expect(struct nf_conn *master, } } -static inline int refresh_timer(struct nf_conntrack_expect *i) -{ - struct nf_conn_help *master_help = nfct_help(i->master); - const struct nf_conntrack_expect_policy *p; - - if (!del_timer(&i->timeout)) - return 0; - - p = &rcu_dereference_protected( - master_help->helper, - lockdep_is_held(&nf_conntrack_lock) - )->expect_policy[i->class]; - i->timeout.expires = jiffies + p->timeout * HZ; - add_timer(&i->timeout); - return 1; -} - static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) { const struct nf_conntrack_expect_policy *p; @@ -386,7 +369,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) struct nf_conn_help *master_help = nfct_help(master); struct nf_conntrack_helper *helper; struct net *net = nf_ct_exp_net(expect); - struct hlist_node *n; + struct hlist_node *n, *next; unsigned int h; int ret = 1; @@ -395,12 +378,12 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) goto out; } h = nf_ct_expect_dst_hash(&expect->tuple); - hlist_for_each_entry(i, n, &net->ct.expect_hash[h], hnode) { + hlist_for_each_entry_safe(i, n, next, &net->ct.expect_hash[h], hnode) { if (expect_matches(i, expect)) { - /* Refresh timer: if it's dying, ignore.. */ - if (refresh_timer(i)) { - ret = 0; - goto out; + if (del_timer(&i->timeout)) { + nf_ct_unlink_expect(i); + nf_ct_expect_put(i); + break; } } else if (expect_clash(i, expect)) { ret = -EBUSY; diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 641ff5f9671..1a9545965c0 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -44,7 +44,8 @@ void __nf_ct_ext_destroy(struct nf_conn *ct) EXPORT_SYMBOL(__nf_ct_ext_destroy); static void * -nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp) +nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, + size_t var_alloc_len, gfp_t gfp) { unsigned int off, len; struct nf_ct_ext_type *t; @@ -54,8 +55,8 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp) t = rcu_dereference(nf_ct_ext_types[id]); BUG_ON(t == NULL); off = ALIGN(sizeof(struct nf_ct_ext), t->align); - len = off + t->len; - alloc_size = t->alloc_size; + len = off + t->len + var_alloc_len; + alloc_size = t->alloc_size + var_alloc_len; rcu_read_unlock(); *ext = kzalloc(alloc_size, gfp); @@ -68,7 +69,8 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp) return (void *)(*ext) + off; } -void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) +void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id, + size_t var_alloc_len, gfp_t gfp) { struct nf_ct_ext *old, *new; int i, newlen, newoff; @@ -79,7 +81,7 @@ void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) old = ct->ext; if (!old) - return nf_ct_ext_create(&ct->ext, id, gfp); + return nf_ct_ext_create(&ct->ext, id, var_alloc_len, gfp); if (__nf_ct_ext_exist(old, id)) return NULL; @@ -89,7 +91,7 @@ void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) BUG_ON(t == NULL); newoff = ALIGN(old->len, t->align); - newlen = newoff + t->len; + newlen = newoff + t->len + var_alloc_len; rcu_read_unlock(); new = __krealloc(old, newlen, gfp); @@ -117,7 +119,7 @@ void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) memset((void *)new + newoff, 0, newlen - newoff); return (void *)new + newoff; } -EXPORT_SYMBOL(__nf_ct_ext_add); +EXPORT_SYMBOL(__nf_ct_ext_add_length); static void update_alloc_size(struct nf_ct_ext_type *type) { diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 8c5c95c6d34..4bb771d1f57 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -358,7 +358,7 @@ static int help(struct sk_buff *skb, u32 seq; int dir = CTINFO2DIR(ctinfo); unsigned int uninitialized_var(matchlen), uninitialized_var(matchoff); - struct nf_ct_ftp_master *ct_ftp_info = &nfct_help(ct)->help.ct_ftp_info; + struct nf_ct_ftp_master *ct_ftp_info = nfct_help_data(ct); struct nf_conntrack_expect *exp; union nf_inet_addr *daddr; struct nf_conntrack_man cmd = {}; @@ -512,7 +512,6 @@ out_update_nl: } static struct nf_conntrack_helper ftp[MAX_PORTS][2] __read_mostly; -static char ftp_names[MAX_PORTS][2][sizeof("ftp-65535")] __read_mostly; static const struct nf_conntrack_expect_policy ftp_exp_policy = { .max_expected = 1, @@ -541,7 +540,6 @@ static void nf_conntrack_ftp_fini(void) static int __init nf_conntrack_ftp_init(void) { int i, j = -1, ret = 0; - char *tmpname; ftp_buffer = kmalloc(65536, GFP_KERNEL); if (!ftp_buffer) @@ -556,17 +554,16 @@ static int __init nf_conntrack_ftp_init(void) ftp[i][0].tuple.src.l3num = PF_INET; ftp[i][1].tuple.src.l3num = PF_INET6; for (j = 0; j < 2; j++) { + ftp[i][j].data_len = sizeof(struct nf_ct_ftp_master); ftp[i][j].tuple.src.u.tcp.port = htons(ports[i]); ftp[i][j].tuple.dst.protonum = IPPROTO_TCP; ftp[i][j].expect_policy = &ftp_exp_policy; ftp[i][j].me = THIS_MODULE; ftp[i][j].help = help; - tmpname = &ftp_names[i][j][0]; if (ports[i] == FTP_PORT) - sprintf(tmpname, "ftp"); + sprintf(ftp[i][j].name, "ftp"); else - sprintf(tmpname, "ftp-%d", ports[i]); - ftp[i][j].name = tmpname; + sprintf(ftp[i][j].name, "ftp-%d", ports[i]); pr_debug("nf_ct_ftp: registering helper for pf: %d " "port: %d\n", diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 31f50bc3a31..4283b207e63 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -114,7 +114,7 @@ static int get_tpkt_data(struct sk_buff *skb, unsigned int protoff, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, int *datalen, int *dataoff) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); const struct tcphdr *th; struct tcphdr _tcph; @@ -617,6 +617,7 @@ static const struct nf_conntrack_expect_policy h245_exp_policy = { static struct nf_conntrack_helper nf_conntrack_helper_h245 __read_mostly = { .name = "H.245", .me = THIS_MODULE, + .data_len = sizeof(struct nf_ct_h323_master), .tuple.src.l3num = AF_UNSPEC, .tuple.dst.protonum = IPPROTO_UDP, .help = h245_help, @@ -1169,6 +1170,7 @@ static struct nf_conntrack_helper nf_conntrack_helper_q931[] __read_mostly = { { .name = "Q.931", .me = THIS_MODULE, + .data_len = sizeof(struct nf_ct_h323_master), .tuple.src.l3num = AF_INET, .tuple.src.u.tcp.port = cpu_to_be16(Q931_PORT), .tuple.dst.protonum = IPPROTO_TCP, @@ -1244,7 +1246,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, unsigned char **data, TransportAddress *taddr, int count) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); int ret = 0; int i; @@ -1359,7 +1361,7 @@ static int process_rrq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, RegistrationRequest *rrq) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int ret; typeof(set_ras_addr_hook) set_ras_addr; @@ -1394,7 +1396,7 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, RegistrationConfirm *rcf) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); int ret; struct nf_conntrack_expect *exp; @@ -1443,7 +1445,7 @@ static int process_urq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, UnregistrationRequest *urq) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); int ret; typeof(set_sig_addr_hook) set_sig_addr; @@ -1475,7 +1477,7 @@ static int process_arq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, AdmissionRequest *arq) { - const struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + const struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); __be16 port; union nf_inet_addr addr; @@ -1742,6 +1744,7 @@ static struct nf_conntrack_helper nf_conntrack_helper_ras[] __read_mostly = { { .name = "RAS", .me = THIS_MODULE, + .data_len = sizeof(struct nf_ct_h323_master), .tuple.src.l3num = AF_INET, .tuple.src.u.udp.port = cpu_to_be16(RAS_PORT), .tuple.dst.protonum = IPPROTO_UDP, @@ -1751,6 +1754,7 @@ static struct nf_conntrack_helper nf_conntrack_helper_ras[] __read_mostly = { { .name = "RAS", .me = THIS_MODULE, + .data_len = sizeof(struct nf_ct_h323_master), .tuple.src.l3num = AF_INET6, .tuple.src.u.udp.port = cpu_to_be16(RAS_PORT), .tuple.dst.protonum = IPPROTO_UDP, diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 4fa2ff961f5..c4bc637feb7 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -30,8 +30,10 @@ #include <net/netfilter/nf_conntrack_extend.h> static DEFINE_MUTEX(nf_ct_helper_mutex); -static struct hlist_head *nf_ct_helper_hash __read_mostly; -static unsigned int nf_ct_helper_hsize __read_mostly; +struct hlist_head *nf_ct_helper_hash __read_mostly; +EXPORT_SYMBOL_GPL(nf_ct_helper_hash); +unsigned int nf_ct_helper_hsize __read_mostly; +EXPORT_SYMBOL_GPL(nf_ct_helper_hsize); static unsigned int nf_ct_helper_count __read_mostly; static bool nf_ct_auto_assign_helper __read_mostly = true; @@ -161,11 +163,14 @@ nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum) } EXPORT_SYMBOL_GPL(nf_conntrack_helper_try_module_get); -struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp) +struct nf_conn_help * +nf_ct_helper_ext_add(struct nf_conn *ct, + struct nf_conntrack_helper *helper, gfp_t gfp) { struct nf_conn_help *help; - help = nf_ct_ext_add(ct, NF_CT_EXT_HELPER, gfp); + help = nf_ct_ext_add_length(ct, NF_CT_EXT_HELPER, + helper->data_len, gfp); if (help) INIT_HLIST_HEAD(&help->expectations); else @@ -218,13 +223,19 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, } if (help == NULL) { - help = nf_ct_helper_ext_add(ct, flags); + help = nf_ct_helper_ext_add(ct, helper, flags); if (help == NULL) { ret = -ENOMEM; goto out; } } else { - memset(&help->help, 0, sizeof(help->help)); + /* We only allow helper re-assignment of the same sort since + * we cannot reallocate the helper extension area. + */ + if (help->helper != helper) { + RCU_INIT_POINTER(help->helper, NULL); + goto out; + } } rcu_assign_pointer(help->helper, helper); @@ -319,6 +330,9 @@ EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_symbol); int nf_conntrack_helper_register(struct nf_conntrack_helper *me) { + int ret = 0; + struct nf_conntrack_helper *cur; + struct hlist_node *n; unsigned int h = helper_hash(&me->tuple); BUG_ON(me->expect_policy == NULL); @@ -326,11 +340,19 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1); mutex_lock(&nf_ct_helper_mutex); + hlist_for_each_entry(cur, n, &nf_ct_helper_hash[h], hnode) { + if (strncmp(cur->name, me->name, NF_CT_HELPER_NAME_LEN) == 0 && + cur->tuple.src.l3num == me->tuple.src.l3num && + cur->tuple.dst.protonum == me->tuple.dst.protonum) { + ret = -EEXIST; + goto out; + } + } hlist_add_head_rcu(&me->hnode, &nf_ct_helper_hash[h]); nf_ct_helper_count++; +out: mutex_unlock(&nf_ct_helper_mutex); - - return 0; + return ret; } EXPORT_SYMBOL_GPL(nf_conntrack_helper_register); diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 81366c11827..009c52cfd1e 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -221,7 +221,6 @@ static int help(struct sk_buff *skb, unsigned int protoff, } static struct nf_conntrack_helper irc[MAX_PORTS] __read_mostly; -static char irc_names[MAX_PORTS][sizeof("irc-65535")] __read_mostly; static struct nf_conntrack_expect_policy irc_exp_policy; static void nf_conntrack_irc_fini(void); @@ -229,7 +228,6 @@ static void nf_conntrack_irc_fini(void); static int __init nf_conntrack_irc_init(void) { int i, ret; - char *tmpname; if (max_dcc_channels < 1) { printk(KERN_ERR "nf_ct_irc: max_dcc_channels must not be zero\n"); @@ -255,12 +253,10 @@ static int __init nf_conntrack_irc_init(void) irc[i].me = THIS_MODULE; irc[i].help = help; - tmpname = &irc_names[i][0]; if (ports[i] == IRC_PORT) - sprintf(tmpname, "irc"); + sprintf(irc[i].name, "irc"); else - sprintf(tmpname, "irc-%u", i); - irc[i].name = tmpname; + sprintf(irc[i].name, "irc-%u", i); ret = nf_conntrack_helper_register(&irc[i]); if (ret) { diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 6f4b00a8fc7..9807f3278fc 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -4,7 +4,7 @@ * (C) 2001 by Jay Schulist <jschlst@samba.org> * (C) 2002-2006 by Harald Welte <laforge@gnumonks.org> * (C) 2003 by Patrick Mchardy <kaber@trash.net> - * (C) 2005-2011 by Pablo Neira Ayuso <pablo@netfilter.org> + * (C) 2005-2012 by Pablo Neira Ayuso <pablo@netfilter.org> * * Initial connection tracking via netlink development funded and * generally made possible by Network Robots, Inc. (www.networkrobots.com) @@ -46,6 +46,7 @@ #ifdef CONFIG_NF_NAT_NEEDED #include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_protocol.h> +#include <net/netfilter/nf_nat_helper.h> #endif #include <linux/netfilter/nfnetlink.h> @@ -477,7 +478,6 @@ nla_put_failure: return -1; } -#ifdef CONFIG_NF_CONNTRACK_EVENTS static inline size_t ctnetlink_proto_size(const struct nf_conn *ct) { @@ -564,6 +564,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct) ; } +#ifdef CONFIG_NF_CONNTRACK_EVENTS static int ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) { @@ -901,7 +902,8 @@ static const struct nla_policy help_nla_policy[CTA_HELP_MAX+1] = { }; static inline int -ctnetlink_parse_help(const struct nlattr *attr, char **helper_name) +ctnetlink_parse_help(const struct nlattr *attr, char **helper_name, + struct nlattr **helpinfo) { struct nlattr *tb[CTA_HELP_MAX+1]; @@ -912,6 +914,9 @@ ctnetlink_parse_help(const struct nlattr *attr, char **helper_name) *helper_name = nla_data(tb[CTA_HELP_NAME]); + if (tb[CTA_HELP_INFO]) + *helpinfo = tb[CTA_HELP_INFO]; + return 0; } @@ -1172,13 +1177,14 @@ ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) struct nf_conntrack_helper *helper; struct nf_conn_help *help = nfct_help(ct); char *helpname = NULL; + struct nlattr *helpinfo = NULL; int err; /* don't change helper of sibling connections */ if (ct->master) return -EBUSY; - err = ctnetlink_parse_help(cda[CTA_HELP], &helpname); + err = ctnetlink_parse_help(cda[CTA_HELP], &helpname, &helpinfo); if (err < 0) return err; @@ -1213,20 +1219,17 @@ ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) } if (help) { - if (help->helper == helper) + if (help->helper == helper) { + /* update private helper data if allowed. */ + if (helper->from_nlattr && helpinfo) + helper->from_nlattr(helpinfo, ct); return 0; - if (help->helper) + } else return -EBUSY; - /* need to zero data of old helper */ - memset(&help->help, 0, sizeof(help->help)); - } else { - /* we cannot set a helper for an existing conntrack */ - return -EOPNOTSUPP; } - rcu_assign_pointer(help->helper, helper); - - return 0; + /* we cannot set a helper for an existing conntrack */ + return -EOPNOTSUPP; } static inline int @@ -1410,8 +1413,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, rcu_read_lock(); if (cda[CTA_HELP]) { char *helpname = NULL; - - err = ctnetlink_parse_help(cda[CTA_HELP], &helpname); + struct nlattr *helpinfo = NULL; + + err = ctnetlink_parse_help(cda[CTA_HELP], &helpname, &helpinfo); if (err < 0) goto err2; @@ -1440,11 +1444,14 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, } else { struct nf_conn_help *help; - help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); + help = nf_ct_helper_ext_add(ct, helper, GFP_ATOMIC); if (help == NULL) { err = -ENOMEM; goto err2; } + /* set private helper data if allowed. */ + if (helper->from_nlattr && helpinfo) + helper->from_nlattr(helpinfo, ct); /* not in hash table yet so not strictly necessary */ RCU_INIT_POINTER(help->helper, helper); @@ -1620,6 +1627,293 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, return err; } +static int +ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 pid, u32 seq, + __u16 cpu, const struct ip_conntrack_stat *st) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + unsigned int flags = pid ? NLM_F_MULTI : 0, event; + + event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_CT_GET_STATS_CPU); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + if (nlh == NULL) + goto nlmsg_failure; + + nfmsg = nlmsg_data(nlh); + nfmsg->nfgen_family = AF_UNSPEC; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = htons(cpu); + + if (nla_put_be32(skb, CTA_STATS_SEARCHED, htonl(st->searched)) || + nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) || + nla_put_be32(skb, CTA_STATS_NEW, htonl(st->new)) || + nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) || + nla_put_be32(skb, CTA_STATS_IGNORE, htonl(st->ignore)) || + nla_put_be32(skb, CTA_STATS_DELETE, htonl(st->delete)) || + nla_put_be32(skb, CTA_STATS_DELETE_LIST, htonl(st->delete_list)) || + nla_put_be32(skb, CTA_STATS_INSERT, htonl(st->insert)) || + nla_put_be32(skb, CTA_STATS_INSERT_FAILED, + htonl(st->insert_failed)) || + nla_put_be32(skb, CTA_STATS_DROP, htonl(st->drop)) || + nla_put_be32(skb, CTA_STATS_EARLY_DROP, htonl(st->early_drop)) || + nla_put_be32(skb, CTA_STATS_ERROR, htonl(st->error)) || + nla_put_be32(skb, CTA_STATS_SEARCH_RESTART, + htonl(st->search_restart))) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + return skb->len; + +nla_put_failure: +nlmsg_failure: + nlmsg_cancel(skb, nlh); + return -1; +} + +static int +ctnetlink_ct_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + int cpu; + struct net *net = sock_net(skb->sk); + + if (cb->args[0] == nr_cpu_ids) + return 0; + + for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { + const struct ip_conntrack_stat *st; + + if (!cpu_possible(cpu)) + continue; + + st = per_cpu_ptr(net->ct.stat, cpu); + if (ctnetlink_ct_stat_cpu_fill_info(skb, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + cpu, st) < 0) + break; + } + cb->args[0] = cpu; + + return skb->len; +} + +static int +ctnetlink_stat_ct_cpu(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) +{ + if (nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = ctnetlink_ct_stat_cpu_dump, + }; + return netlink_dump_start(ctnl, skb, nlh, &c); + } + + return 0; +} + +static int +ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, + struct net *net) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + unsigned int flags = pid ? NLM_F_MULTI : 0, event; + unsigned int nr_conntracks = atomic_read(&net->ct.count); + + event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_CT_GET_STATS); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + if (nlh == NULL) + goto nlmsg_failure; + + nfmsg = nlmsg_data(nlh); + nfmsg->nfgen_family = AF_UNSPEC; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = 0; + + if (nla_put_be32(skb, CTA_STATS_GLOBAL_ENTRIES, htonl(nr_conntracks))) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + return skb->len; + +nla_put_failure: +nlmsg_failure: + nlmsg_cancel(skb, nlh); + return -1; +} + +static int +ctnetlink_stat_ct(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) +{ + struct sk_buff *skb2; + int err; + + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb2 == NULL) + return -ENOMEM; + + err = ctnetlink_stat_ct_fill_info(skb2, NETLINK_CB(skb).pid, + nlh->nlmsg_seq, + NFNL_MSG_TYPE(nlh->nlmsg_type), + sock_net(skb->sk)); + if (err <= 0) + goto free; + + err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + if (err < 0) + goto out; + + return 0; + +free: + kfree_skb(skb2); +out: + /* this avoids a loop in nfnetlink. */ + return err == -EAGAIN ? -ENOBUFS : err; +} + +#ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT +static size_t +ctnetlink_nfqueue_build_size(const struct nf_conn *ct) +{ + return 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */ + + 3 * nla_total_size(0) /* CTA_TUPLE_IP */ + + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */ + + 3 * nla_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */ + + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */ + + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */ + + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */ + + nla_total_size(0) /* CTA_PROTOINFO */ + + nla_total_size(0) /* CTA_HELP */ + + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ + + ctnetlink_secctx_size(ct) +#ifdef CONFIG_NF_NAT_NEEDED + + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ + + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */ +#endif +#ifdef CONFIG_NF_CONNTRACK_MARK + + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ +#endif + + ctnetlink_proto_size(ct) + ; +} + +static int +ctnetlink_nfqueue_build(struct sk_buff *skb, struct nf_conn *ct) +{ + struct nlattr *nest_parms; + + rcu_read_lock(); + nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED); + if (!nest_parms) + goto nla_put_failure; + if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) + goto nla_put_failure; + nla_nest_end(skb, nest_parms); + + nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED); + if (!nest_parms) + goto nla_put_failure; + if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) + goto nla_put_failure; + nla_nest_end(skb, nest_parms); + + if (nf_ct_zone(ct)) { + if (nla_put_be16(skb, CTA_ZONE, htons(nf_ct_zone(ct)))) + goto nla_put_failure; + } + + if (ctnetlink_dump_id(skb, ct) < 0) + goto nla_put_failure; + + if (ctnetlink_dump_status(skb, ct) < 0) + goto nla_put_failure; + + if (ctnetlink_dump_timeout(skb, ct) < 0) + goto nla_put_failure; + + if (ctnetlink_dump_protoinfo(skb, ct) < 0) + goto nla_put_failure; + + if (ctnetlink_dump_helpinfo(skb, ct) < 0) + goto nla_put_failure; + +#ifdef CONFIG_NF_CONNTRACK_SECMARK + if (ct->secmark && ctnetlink_dump_secctx(skb, ct) < 0) + goto nla_put_failure; +#endif + if (ct->master && ctnetlink_dump_master(skb, ct) < 0) + goto nla_put_failure; + + if ((ct->status & IPS_SEQ_ADJUST) && + ctnetlink_dump_nat_seq_adj(skb, ct) < 0) + goto nla_put_failure; + +#ifdef CONFIG_NF_CONNTRACK_MARK + if (ct->mark && ctnetlink_dump_mark(skb, ct) < 0) + goto nla_put_failure; +#endif + rcu_read_unlock(); + return 0; + +nla_put_failure: + rcu_read_unlock(); + return -ENOSPC; +} + +static int +ctnetlink_nfqueue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct) +{ + int err; + + if (cda[CTA_TIMEOUT]) { + err = ctnetlink_change_timeout(ct, cda); + if (err < 0) + return err; + } + if (cda[CTA_STATUS]) { + err = ctnetlink_change_status(ct, cda); + if (err < 0) + return err; + } + if (cda[CTA_HELP]) { + err = ctnetlink_change_helper(ct, cda); + if (err < 0) + return err; + } +#if defined(CONFIG_NF_CONNTRACK_MARK) + if (cda[CTA_MARK]) + ct->mark = ntohl(nla_get_be32(cda[CTA_MARK])); +#endif + return 0; +} + +static int +ctnetlink_nfqueue_parse(const struct nlattr *attr, struct nf_conn *ct) +{ + struct nlattr *cda[CTA_MAX+1]; + int ret; + + nla_parse_nested(cda, CTA_MAX, attr, ct_nla_policy); + + spin_lock_bh(&nf_conntrack_lock); + ret = ctnetlink_nfqueue_parse_ct((const struct nlattr **)cda, ct); + spin_unlock_bh(&nf_conntrack_lock); + + return ret; +} + +static struct nfq_ct_hook ctnetlink_nfqueue_hook = { + .build_size = ctnetlink_nfqueue_build_size, + .build = ctnetlink_nfqueue_build, + .parse = ctnetlink_nfqueue_parse, +}; +#endif /* CONFIG_NETFILTER_NETLINK_QUEUE_CT */ + /*********************************************************************** * EXPECT ***********************************************************************/ @@ -2300,6 +2594,79 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, return err; } +static int +ctnetlink_exp_stat_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int cpu, + const struct ip_conntrack_stat *st) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + unsigned int flags = pid ? NLM_F_MULTI : 0, event; + + event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_EXP_GET_STATS_CPU); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + if (nlh == NULL) + goto nlmsg_failure; + + nfmsg = nlmsg_data(nlh); + nfmsg->nfgen_family = AF_UNSPEC; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = htons(cpu); + + if (nla_put_be32(skb, CTA_STATS_EXP_NEW, htonl(st->expect_new)) || + nla_put_be32(skb, CTA_STATS_EXP_CREATE, htonl(st->expect_create)) || + nla_put_be32(skb, CTA_STATS_EXP_DELETE, htonl(st->expect_delete))) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + return skb->len; + +nla_put_failure: +nlmsg_failure: + nlmsg_cancel(skb, nlh); + return -1; +} + +static int +ctnetlink_exp_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + int cpu; + struct net *net = sock_net(skb->sk); + + if (cb->args[0] == nr_cpu_ids) + return 0; + + for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { + const struct ip_conntrack_stat *st; + + if (!cpu_possible(cpu)) + continue; + + st = per_cpu_ptr(net->ct.stat, cpu); + if (ctnetlink_exp_stat_fill_info(skb, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + cpu, st) < 0) + break; + } + cb->args[0] = cpu; + + return skb->len; +} + +static int +ctnetlink_stat_exp_cpu(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) +{ + if (nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = ctnetlink_exp_stat_cpu_dump, + }; + return netlink_dump_start(ctnl, skb, nlh, &c); + } + + return 0; +} + #ifdef CONFIG_NF_CONNTRACK_EVENTS static struct nf_ct_event_notifier ctnl_notifier = { .fcn = ctnetlink_conntrack_event, @@ -2323,6 +2690,8 @@ static const struct nfnl_callback ctnl_cb[IPCTNL_MSG_MAX] = { [IPCTNL_MSG_CT_GET_CTRZERO] = { .call = ctnetlink_get_conntrack, .attr_count = CTA_MAX, .policy = ct_nla_policy }, + [IPCTNL_MSG_CT_GET_STATS_CPU] = { .call = ctnetlink_stat_ct_cpu }, + [IPCTNL_MSG_CT_GET_STATS] = { .call = ctnetlink_stat_ct }, }; static const struct nfnl_callback ctnl_exp_cb[IPCTNL_MSG_EXP_MAX] = { @@ -2335,6 +2704,7 @@ static const struct nfnl_callback ctnl_exp_cb[IPCTNL_MSG_EXP_MAX] = { [IPCTNL_MSG_EXP_DELETE] = { .call = ctnetlink_del_expect, .attr_count = CTA_EXPECT_MAX, .policy = exp_nla_policy }, + [IPCTNL_MSG_EXP_GET_STATS_CPU] = { .call = ctnetlink_stat_exp_cpu }, }; static const struct nfnetlink_subsystem ctnl_subsys = { @@ -2420,11 +2790,15 @@ static int __init ctnetlink_init(void) goto err_unreg_subsys; } - if (register_pernet_subsys(&ctnetlink_net_ops)) { + ret = register_pernet_subsys(&ctnetlink_net_ops); + if (ret < 0) { pr_err("ctnetlink_init: cannot register pernet operations\n"); goto err_unreg_exp_subsys; } - +#ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT + /* setup interaction between nf_queue and nf_conntrack_netlink. */ + RCU_INIT_POINTER(nfq_ct_hook, &ctnetlink_nfqueue_hook); +#endif return 0; err_unreg_exp_subsys: @@ -2442,6 +2816,9 @@ static void __exit ctnetlink_exit(void) unregister_pernet_subsys(&ctnetlink_net_ops); nfnetlink_subsys_unregister(&ctnl_exp_subsys); nfnetlink_subsys_unregister(&ctnl_subsys); +#ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT + RCU_INIT_POINTER(nfq_ct_hook, NULL); +#endif } module_init(ctnetlink_init); diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 31d56b23b9e..6fed9ec3524 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -174,7 +174,7 @@ static int destroy_sibling_or_exp(struct net *net, struct nf_conn *ct, static void pptp_destroy_siblings(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); - const struct nf_conn_help *help = nfct_help(ct); + const struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct); struct nf_conntrack_tuple t; nf_ct_gre_keymap_destroy(ct); @@ -182,16 +182,16 @@ static void pptp_destroy_siblings(struct nf_conn *ct) /* try original (pns->pac) tuple */ memcpy(&t, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, sizeof(t)); t.dst.protonum = IPPROTO_GRE; - t.src.u.gre.key = help->help.ct_pptp_info.pns_call_id; - t.dst.u.gre.key = help->help.ct_pptp_info.pac_call_id; + t.src.u.gre.key = ct_pptp_info->pns_call_id; + t.dst.u.gre.key = ct_pptp_info->pac_call_id; if (!destroy_sibling_or_exp(net, ct, &t)) pr_debug("failed to timeout original pns->pac ct/exp\n"); /* try reply (pac->pns) tuple */ memcpy(&t, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, sizeof(t)); t.dst.protonum = IPPROTO_GRE; - t.src.u.gre.key = help->help.ct_pptp_info.pac_call_id; - t.dst.u.gre.key = help->help.ct_pptp_info.pns_call_id; + t.src.u.gre.key = ct_pptp_info->pac_call_id; + t.dst.u.gre.key = ct_pptp_info->pns_call_id; if (!destroy_sibling_or_exp(net, ct, &t)) pr_debug("failed to timeout reply pac->pns ct/exp\n"); } @@ -269,7 +269,7 @@ pptp_inbound_pkt(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - struct nf_ct_pptp_master *info = &nfct_help(ct)->help.ct_pptp_info; + struct nf_ct_pptp_master *info = nfct_help_data(ct); u_int16_t msg; __be16 cid = 0, pcid = 0; typeof(nf_nat_pptp_hook_inbound) nf_nat_pptp_inbound; @@ -396,7 +396,7 @@ pptp_outbound_pkt(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - struct nf_ct_pptp_master *info = &nfct_help(ct)->help.ct_pptp_info; + struct nf_ct_pptp_master *info = nfct_help_data(ct); u_int16_t msg; __be16 cid = 0, pcid = 0; typeof(nf_nat_pptp_hook_outbound) nf_nat_pptp_outbound; @@ -506,7 +506,7 @@ conntrack_pptp_help(struct sk_buff *skb, unsigned int protoff, { int dir = CTINFO2DIR(ctinfo); - const struct nf_ct_pptp_master *info = &nfct_help(ct)->help.ct_pptp_info; + const struct nf_ct_pptp_master *info = nfct_help_data(ct); const struct tcphdr *tcph; struct tcphdr _tcph; const struct pptp_pkt_hdr *pptph; @@ -592,6 +592,7 @@ static const struct nf_conntrack_expect_policy pptp_exp_policy = { static struct nf_conntrack_helper pptp __read_mostly = { .name = "pptp", .me = THIS_MODULE, + .data_len = sizeof(struct nf_ct_pptp_master), .tuple.src.l3num = AF_INET, .tuple.src.u.tcp.port = cpu_to_be16(PPTP_CONTROL_PORT), .tuple.dst.protonum = IPPROTO_TCP, diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 8b631b07a64..0dc63854390 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -36,28 +36,32 @@ static DEFINE_MUTEX(nf_ct_proto_mutex); #ifdef CONFIG_SYSCTL static int -nf_ct_register_sysctl(struct ctl_table_header **header, const char *path, - struct ctl_table *table, unsigned int *users) +nf_ct_register_sysctl(struct net *net, + struct ctl_table_header **header, + const char *path, + struct ctl_table *table) { if (*header == NULL) { - *header = register_net_sysctl(&init_net, path, table); + *header = register_net_sysctl(net, path, table); if (*header == NULL) return -ENOMEM; } - if (users != NULL) - (*users)++; + return 0; } static void nf_ct_unregister_sysctl(struct ctl_table_header **header, - struct ctl_table *table, unsigned int *users) + struct ctl_table **table, + unsigned int users) { - if (users != NULL && --*users > 0) + if (users > 0) return; unregister_net_sysctl_table(*header); + kfree(*table); *header = NULL; + *table = NULL; } #endif @@ -161,30 +165,56 @@ static int kill_l4proto(struct nf_conn *i, void *data) nf_ct_l3num(i) == l4proto->l3proto; } -static int nf_ct_l3proto_register_sysctl(struct nf_conntrack_l3proto *l3proto) +static struct nf_ip_net *nf_ct_l3proto_net(struct net *net, + struct nf_conntrack_l3proto *l3proto) { - int err = 0; + if (l3proto->l3proto == PF_INET) + return &net->ct.nf_ct_proto; + else + return NULL; +} -#ifdef CONFIG_SYSCTL - if (l3proto->ctl_table != NULL) { - err = nf_ct_register_sysctl(&l3proto->ctl_table_header, +static int nf_ct_l3proto_register_sysctl(struct net *net, + struct nf_conntrack_l3proto *l3proto) +{ + int err = 0; + struct nf_ip_net *in = nf_ct_l3proto_net(net, l3proto); + /* nf_conntrack_l3proto_ipv6 doesn't support sysctl */ + if (in == NULL) + return 0; + +#if defined(CONFIG_SYSCTL) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) + if (in->ctl_table != NULL) { + err = nf_ct_register_sysctl(net, + &in->ctl_table_header, l3proto->ctl_table_path, - l3proto->ctl_table, NULL); + in->ctl_table); + if (err < 0) { + kfree(in->ctl_table); + in->ctl_table = NULL; + } } #endif return err; } -static void nf_ct_l3proto_unregister_sysctl(struct nf_conntrack_l3proto *l3proto) +static void nf_ct_l3proto_unregister_sysctl(struct net *net, + struct nf_conntrack_l3proto *l3proto) { -#ifdef CONFIG_SYSCTL - if (l3proto->ctl_table_header != NULL) - nf_ct_unregister_sysctl(&l3proto->ctl_table_header, - l3proto->ctl_table, NULL); + struct nf_ip_net *in = nf_ct_l3proto_net(net, l3proto); + + if (in == NULL) + return; +#if defined(CONFIG_SYSCTL) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) + if (in->ctl_table_header != NULL) + nf_ct_unregister_sysctl(&in->ctl_table_header, + &in->ctl_table, + 0); #endif } -int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto) +static int +nf_conntrack_l3proto_register_net(struct nf_conntrack_l3proto *proto) { int ret = 0; struct nf_conntrack_l3proto *old; @@ -203,10 +233,6 @@ int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto) goto out_unlock; } - ret = nf_ct_l3proto_register_sysctl(proto); - if (ret < 0) - goto out_unlock; - if (proto->nlattr_tuple_size) proto->nla_size = 3 * proto->nlattr_tuple_size(); @@ -215,13 +241,37 @@ int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto) out_unlock: mutex_unlock(&nf_ct_proto_mutex); return ret; + } -EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_register); -void nf_conntrack_l3proto_unregister(struct nf_conntrack_l3proto *proto) +int nf_conntrack_l3proto_register(struct net *net, + struct nf_conntrack_l3proto *proto) { - struct net *net; + int ret = 0; + + if (proto->init_net) { + ret = proto->init_net(net); + if (ret < 0) + return ret; + } + + ret = nf_ct_l3proto_register_sysctl(net, proto); + if (ret < 0) + return ret; + if (net == &init_net) { + ret = nf_conntrack_l3proto_register_net(proto); + if (ret < 0) + nf_ct_l3proto_unregister_sysctl(net, proto); + } + + return ret; +} +EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_register); + +static void +nf_conntrack_l3proto_unregister_net(struct nf_conntrack_l3proto *proto) +{ BUG_ON(proto->l3proto >= AF_MAX); mutex_lock(&nf_ct_proto_mutex); @@ -230,68 +280,107 @@ void nf_conntrack_l3proto_unregister(struct nf_conntrack_l3proto *proto) ) != proto); rcu_assign_pointer(nf_ct_l3protos[proto->l3proto], &nf_conntrack_l3proto_generic); - nf_ct_l3proto_unregister_sysctl(proto); mutex_unlock(&nf_ct_proto_mutex); synchronize_rcu(); +} + +void nf_conntrack_l3proto_unregister(struct net *net, + struct nf_conntrack_l3proto *proto) +{ + if (net == &init_net) + nf_conntrack_l3proto_unregister_net(proto); + + nf_ct_l3proto_unregister_sysctl(net, proto); /* Remove all contrack entries for this protocol */ rtnl_lock(); - for_each_net(net) - nf_ct_iterate_cleanup(net, kill_l3proto, proto); + nf_ct_iterate_cleanup(net, kill_l3proto, proto); rtnl_unlock(); } EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_unregister); -static int nf_ct_l4proto_register_sysctl(struct nf_conntrack_l4proto *l4proto) +static struct nf_proto_net *nf_ct_l4proto_net(struct net *net, + struct nf_conntrack_l4proto *l4proto) +{ + if (l4proto->get_net_proto) { + /* statically built-in protocols use static per-net */ + return l4proto->get_net_proto(net); + } else if (l4proto->net_id) { + /* ... and loadable protocols use dynamic per-net */ + return net_generic(net, *l4proto->net_id); + } + return NULL; +} + +static +int nf_ct_l4proto_register_sysctl(struct net *net, + struct nf_proto_net *pn, + struct nf_conntrack_l4proto *l4proto) { int err = 0; #ifdef CONFIG_SYSCTL - if (l4proto->ctl_table != NULL) { - err = nf_ct_register_sysctl(l4proto->ctl_table_header, + if (pn->ctl_table != NULL) { + err = nf_ct_register_sysctl(net, + &pn->ctl_table_header, "net/netfilter", - l4proto->ctl_table, - l4proto->ctl_table_users); - if (err < 0) - goto out; + pn->ctl_table); + if (err < 0) { + if (!pn->users) { + kfree(pn->ctl_table); + pn->ctl_table = NULL; + } + } } #ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT - if (l4proto->ctl_compat_table != NULL) { - err = nf_ct_register_sysctl(&l4proto->ctl_compat_table_header, + if (l4proto->l3proto != AF_INET6 && pn->ctl_compat_table != NULL) { + if (err < 0) { + nf_ct_kfree_compat_sysctl_table(pn); + goto out; + } + err = nf_ct_register_sysctl(net, + &pn->ctl_compat_header, "net/ipv4/netfilter", - l4proto->ctl_compat_table, NULL); + pn->ctl_compat_table); if (err == 0) goto out; - nf_ct_unregister_sysctl(l4proto->ctl_table_header, - l4proto->ctl_table, - l4proto->ctl_table_users); + + nf_ct_kfree_compat_sysctl_table(pn); + nf_ct_unregister_sysctl(&pn->ctl_table_header, + &pn->ctl_table, + pn->users); } -#endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ out: +#endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ return err; } -static void nf_ct_l4proto_unregister_sysctl(struct nf_conntrack_l4proto *l4proto) +static +void nf_ct_l4proto_unregister_sysctl(struct net *net, + struct nf_proto_net *pn, + struct nf_conntrack_l4proto *l4proto) { #ifdef CONFIG_SYSCTL - if (l4proto->ctl_table_header != NULL && - *l4proto->ctl_table_header != NULL) - nf_ct_unregister_sysctl(l4proto->ctl_table_header, - l4proto->ctl_table, - l4proto->ctl_table_users); + if (pn->ctl_table_header != NULL) + nf_ct_unregister_sysctl(&pn->ctl_table_header, + &pn->ctl_table, + pn->users); + #ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT - if (l4proto->ctl_compat_table_header != NULL) - nf_ct_unregister_sysctl(&l4proto->ctl_compat_table_header, - l4proto->ctl_compat_table, NULL); + if (l4proto->l3proto != AF_INET6 && pn->ctl_compat_header != NULL) + nf_ct_unregister_sysctl(&pn->ctl_compat_header, + &pn->ctl_compat_table, + 0); #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ } /* FIXME: Allow NULL functions and sub in pointers to generic for them. --RR */ -int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto) +static int +nf_conntrack_l4proto_register_net(struct nf_conntrack_l4proto *l4proto) { int ret = 0; @@ -333,10 +422,6 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto) goto out_unlock; } - ret = nf_ct_l4proto_register_sysctl(l4proto); - if (ret < 0) - goto out_unlock; - l4proto->nla_size = 0; if (l4proto->nlattr_size) l4proto->nla_size += l4proto->nlattr_size(); @@ -345,17 +430,48 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto) rcu_assign_pointer(nf_ct_protos[l4proto->l3proto][l4proto->l4proto], l4proto); - out_unlock: mutex_unlock(&nf_ct_proto_mutex); return ret; } -EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_register); -void nf_conntrack_l4proto_unregister(struct nf_conntrack_l4proto *l4proto) +int nf_conntrack_l4proto_register(struct net *net, + struct nf_conntrack_l4proto *l4proto) { - struct net *net; + int ret = 0; + struct nf_proto_net *pn = NULL; + if (l4proto->init_net) { + ret = l4proto->init_net(net, l4proto->l3proto); + if (ret < 0) + goto out; + } + + pn = nf_ct_l4proto_net(net, l4proto); + if (pn == NULL) + goto out; + + ret = nf_ct_l4proto_register_sysctl(net, pn, l4proto); + if (ret < 0) + goto out; + + if (net == &init_net) { + ret = nf_conntrack_l4proto_register_net(l4proto); + if (ret < 0) { + nf_ct_l4proto_unregister_sysctl(net, pn, l4proto); + goto out; + } + } + + pn->users++; +out: + return ret; +} +EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_register); + +static void +nf_conntrack_l4proto_unregister_net(struct nf_conntrack_l4proto *l4proto) +{ BUG_ON(l4proto->l3proto >= PF_MAX); mutex_lock(&nf_ct_proto_mutex); @@ -365,41 +481,73 @@ void nf_conntrack_l4proto_unregister(struct nf_conntrack_l4proto *l4proto) ) != l4proto); rcu_assign_pointer(nf_ct_protos[l4proto->l3proto][l4proto->l4proto], &nf_conntrack_l4proto_generic); - nf_ct_l4proto_unregister_sysctl(l4proto); mutex_unlock(&nf_ct_proto_mutex); synchronize_rcu(); +} + +void nf_conntrack_l4proto_unregister(struct net *net, + struct nf_conntrack_l4proto *l4proto) +{ + struct nf_proto_net *pn = NULL; + + if (net == &init_net) + nf_conntrack_l4proto_unregister_net(l4proto); + + pn = nf_ct_l4proto_net(net, l4proto); + if (pn == NULL) + return; + + pn->users--; + nf_ct_l4proto_unregister_sysctl(net, pn, l4proto); /* Remove all contrack entries for this protocol */ rtnl_lock(); - for_each_net(net) - nf_ct_iterate_cleanup(net, kill_l4proto, l4proto); + nf_ct_iterate_cleanup(net, kill_l4proto, l4proto); rtnl_unlock(); } EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_unregister); -int nf_conntrack_proto_init(void) +int nf_conntrack_proto_init(struct net *net) { unsigned int i; int err; + struct nf_proto_net *pn = nf_ct_l4proto_net(net, + &nf_conntrack_l4proto_generic); - err = nf_ct_l4proto_register_sysctl(&nf_conntrack_l4proto_generic); + err = nf_conntrack_l4proto_generic.init_net(net, + nf_conntrack_l4proto_generic.l3proto); + if (err < 0) + return err; + err = nf_ct_l4proto_register_sysctl(net, + pn, + &nf_conntrack_l4proto_generic); if (err < 0) return err; - for (i = 0; i < AF_MAX; i++) - rcu_assign_pointer(nf_ct_l3protos[i], - &nf_conntrack_l3proto_generic); + if (net == &init_net) { + for (i = 0; i < AF_MAX; i++) + rcu_assign_pointer(nf_ct_l3protos[i], + &nf_conntrack_l3proto_generic); + } + + pn->users++; return 0; } -void nf_conntrack_proto_fini(void) +void nf_conntrack_proto_fini(struct net *net) { unsigned int i; - - nf_ct_l4proto_unregister_sysctl(&nf_conntrack_l4proto_generic); - - /* free l3proto protocol tables */ - for (i = 0; i < PF_MAX; i++) - kfree(nf_ct_protos[i]); + struct nf_proto_net *pn = nf_ct_l4proto_net(net, + &nf_conntrack_l4proto_generic); + + pn->users--; + nf_ct_l4proto_unregister_sysctl(net, + pn, + &nf_conntrack_l4proto_generic); + if (net == &init_net) { + /* free l3proto protocol tables */ + for (i = 0; i < PF_MAX; i++) + kfree(nf_ct_protos[i]); + } } diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index ef706a485be..6535326cf07 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -387,12 +387,9 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = /* this module per-net specifics */ static int dccp_net_id __read_mostly; struct dccp_net { + struct nf_proto_net pn; int dccp_loose; unsigned int dccp_timeout[CT_DCCP_MAX + 1]; -#ifdef CONFIG_SYSCTL - struct ctl_table_header *sysctl_header; - struct ctl_table *sysctl_table; -#endif }; static inline struct dccp_net *dccp_pernet(struct net *net) @@ -715,9 +712,10 @@ static int dccp_nlattr_size(void) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> -static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], + struct net *net, void *data) { - struct dccp_net *dn = dccp_pernet(&init_net); + struct dccp_net *dn = dccp_pernet(net); unsigned int *timeouts = data; int i; @@ -817,6 +815,51 @@ static struct ctl_table dccp_sysctl_table[] = { }; #endif /* CONFIG_SYSCTL */ +static int dccp_kmemdup_sysctl_table(struct nf_proto_net *pn, + struct dccp_net *dn) +{ +#ifdef CONFIG_SYSCTL + if (pn->ctl_table) + return 0; + + pn->ctl_table = kmemdup(dccp_sysctl_table, + sizeof(dccp_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_table) + return -ENOMEM; + + pn->ctl_table[0].data = &dn->dccp_timeout[CT_DCCP_REQUEST]; + pn->ctl_table[1].data = &dn->dccp_timeout[CT_DCCP_RESPOND]; + pn->ctl_table[2].data = &dn->dccp_timeout[CT_DCCP_PARTOPEN]; + pn->ctl_table[3].data = &dn->dccp_timeout[CT_DCCP_OPEN]; + pn->ctl_table[4].data = &dn->dccp_timeout[CT_DCCP_CLOSEREQ]; + pn->ctl_table[5].data = &dn->dccp_timeout[CT_DCCP_CLOSING]; + pn->ctl_table[6].data = &dn->dccp_timeout[CT_DCCP_TIMEWAIT]; + pn->ctl_table[7].data = &dn->dccp_loose; +#endif + return 0; +} + +static int dccp_init_net(struct net *net, u_int16_t proto) +{ + struct dccp_net *dn = dccp_pernet(net); + struct nf_proto_net *pn = &dn->pn; + + if (!pn->users) { + /* default values */ + dn->dccp_loose = 1; + dn->dccp_timeout[CT_DCCP_REQUEST] = 2 * DCCP_MSL; + dn->dccp_timeout[CT_DCCP_RESPOND] = 4 * DCCP_MSL; + dn->dccp_timeout[CT_DCCP_PARTOPEN] = 4 * DCCP_MSL; + dn->dccp_timeout[CT_DCCP_OPEN] = 12 * 3600 * HZ; + dn->dccp_timeout[CT_DCCP_CLOSEREQ] = 64 * HZ; + dn->dccp_timeout[CT_DCCP_CLOSING] = 64 * HZ; + dn->dccp_timeout[CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL; + } + + return dccp_kmemdup_sysctl_table(pn, dn); +} + static struct nf_conntrack_l4proto dccp_proto4 __read_mostly = { .l3proto = AF_INET, .l4proto = IPPROTO_DCCP, @@ -847,6 +890,8 @@ static struct nf_conntrack_l4proto dccp_proto4 __read_mostly = { .nla_policy = dccp_timeout_nla_policy, }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + .net_id = &dccp_net_id, + .init_net = dccp_init_net, }; static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = { @@ -879,55 +924,39 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = { .nla_policy = dccp_timeout_nla_policy, }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + .net_id = &dccp_net_id, + .init_net = dccp_init_net, }; static __net_init int dccp_net_init(struct net *net) { - struct dccp_net *dn = dccp_pernet(net); - - /* default values */ - dn->dccp_loose = 1; - dn->dccp_timeout[CT_DCCP_REQUEST] = 2 * DCCP_MSL; - dn->dccp_timeout[CT_DCCP_RESPOND] = 4 * DCCP_MSL; - dn->dccp_timeout[CT_DCCP_PARTOPEN] = 4 * DCCP_MSL; - dn->dccp_timeout[CT_DCCP_OPEN] = 12 * 3600 * HZ; - dn->dccp_timeout[CT_DCCP_CLOSEREQ] = 64 * HZ; - dn->dccp_timeout[CT_DCCP_CLOSING] = 64 * HZ; - dn->dccp_timeout[CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL; - -#ifdef CONFIG_SYSCTL - dn->sysctl_table = kmemdup(dccp_sysctl_table, - sizeof(dccp_sysctl_table), GFP_KERNEL); - if (!dn->sysctl_table) - return -ENOMEM; - - dn->sysctl_table[0].data = &dn->dccp_timeout[CT_DCCP_REQUEST]; - dn->sysctl_table[1].data = &dn->dccp_timeout[CT_DCCP_RESPOND]; - dn->sysctl_table[2].data = &dn->dccp_timeout[CT_DCCP_PARTOPEN]; - dn->sysctl_table[3].data = &dn->dccp_timeout[CT_DCCP_OPEN]; - dn->sysctl_table[4].data = &dn->dccp_timeout[CT_DCCP_CLOSEREQ]; - dn->sysctl_table[5].data = &dn->dccp_timeout[CT_DCCP_CLOSING]; - dn->sysctl_table[6].data = &dn->dccp_timeout[CT_DCCP_TIMEWAIT]; - dn->sysctl_table[7].data = &dn->dccp_loose; - - dn->sysctl_header = register_net_sysctl(net, "net/netfilter", - dn->sysctl_table); - if (!dn->sysctl_header) { - kfree(dn->sysctl_table); - return -ENOMEM; + int ret = 0; + ret = nf_conntrack_l4proto_register(net, + &dccp_proto4); + if (ret < 0) { + pr_err("nf_conntrack_l4proto_dccp4 :protocol register failed.\n"); + goto out; + } + ret = nf_conntrack_l4proto_register(net, + &dccp_proto6); + if (ret < 0) { + pr_err("nf_conntrack_l4proto_dccp6 :protocol register failed.\n"); + goto cleanup_dccp4; } -#endif - return 0; +cleanup_dccp4: + nf_conntrack_l4proto_unregister(net, + &dccp_proto4); +out: + return ret; } static __net_exit void dccp_net_exit(struct net *net) { - struct dccp_net *dn = dccp_pernet(net); -#ifdef CONFIG_SYSCTL - unregister_net_sysctl_table(dn->sysctl_header); - kfree(dn->sysctl_table); -#endif + nf_conntrack_l4proto_unregister(net, + &dccp_proto6); + nf_conntrack_l4proto_unregister(net, + &dccp_proto4); } static struct pernet_operations dccp_net_ops = { @@ -939,34 +968,12 @@ static struct pernet_operations dccp_net_ops = { static int __init nf_conntrack_proto_dccp_init(void) { - int err; - - err = register_pernet_subsys(&dccp_net_ops); - if (err < 0) - goto err1; - - err = nf_conntrack_l4proto_register(&dccp_proto4); - if (err < 0) - goto err2; - - err = nf_conntrack_l4proto_register(&dccp_proto6); - if (err < 0) - goto err3; - return 0; - -err3: - nf_conntrack_l4proto_unregister(&dccp_proto4); -err2: - unregister_pernet_subsys(&dccp_net_ops); -err1: - return err; + return register_pernet_subsys(&dccp_net_ops); } static void __exit nf_conntrack_proto_dccp_fini(void) { unregister_pernet_subsys(&dccp_net_ops); - nf_conntrack_l4proto_unregister(&dccp_proto6); - nf_conntrack_l4proto_unregister(&dccp_proto4); } module_init(nf_conntrack_proto_dccp_init); diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index d8923d54b35..d25f2937764 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -14,6 +14,11 @@ static unsigned int nf_ct_generic_timeout __read_mostly = 600*HZ; +static inline struct nf_generic_net *generic_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.generic; +} + static bool generic_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct nf_conntrack_tuple *tuple) @@ -42,7 +47,7 @@ static int generic_print_tuple(struct seq_file *s, static unsigned int *generic_get_timeouts(struct net *net) { - return &nf_ct_generic_timeout; + return &(generic_pernet(net)->timeout); } /* Returns verdict for packet, or -1 for invalid. */ @@ -70,16 +75,18 @@ static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb, #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> -static int generic_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +static int generic_timeout_nlattr_to_obj(struct nlattr *tb[], + struct net *net, void *data) { unsigned int *timeout = data; + struct nf_generic_net *gn = generic_pernet(net); if (tb[CTA_TIMEOUT_GENERIC_TIMEOUT]) *timeout = ntohl(nla_get_be32(tb[CTA_TIMEOUT_GENERIC_TIMEOUT])) * HZ; else { /* Set default generic timeout. */ - *timeout = nf_ct_generic_timeout; + *timeout = gn->timeout; } return 0; @@ -106,11 +113,9 @@ generic_timeout_nla_policy[CTA_TIMEOUT_GENERIC_MAX+1] = { #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL -static struct ctl_table_header *generic_sysctl_header; static struct ctl_table generic_sysctl_table[] = { { .procname = "nf_conntrack_generic_timeout", - .data = &nf_ct_generic_timeout, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -121,7 +126,6 @@ static struct ctl_table generic_sysctl_table[] = { static struct ctl_table generic_compat_sysctl_table[] = { { .procname = "ip_conntrack_generic_timeout", - .data = &nf_ct_generic_timeout, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -131,6 +135,62 @@ static struct ctl_table generic_compat_sysctl_table[] = { #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ +static int generic_kmemdup_sysctl_table(struct nf_proto_net *pn, + struct nf_generic_net *gn) +{ +#ifdef CONFIG_SYSCTL + pn->ctl_table = kmemdup(generic_sysctl_table, + sizeof(generic_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_table) + return -ENOMEM; + + pn->ctl_table[0].data = &gn->timeout; +#endif + return 0; +} + +static int generic_kmemdup_compat_sysctl_table(struct nf_proto_net *pn, + struct nf_generic_net *gn) +{ +#ifdef CONFIG_SYSCTL +#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT + pn->ctl_compat_table = kmemdup(generic_compat_sysctl_table, + sizeof(generic_compat_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_compat_table) + return -ENOMEM; + + pn->ctl_compat_table[0].data = &gn->timeout; +#endif +#endif + return 0; +} + +static int generic_init_net(struct net *net, u_int16_t proto) +{ + int ret; + struct nf_generic_net *gn = generic_pernet(net); + struct nf_proto_net *pn = &gn->pn; + + gn->timeout = nf_ct_generic_timeout; + + ret = generic_kmemdup_compat_sysctl_table(pn, gn); + if (ret < 0) + return ret; + + ret = generic_kmemdup_sysctl_table(pn, gn); + if (ret < 0) + nf_ct_kfree_compat_sysctl_table(pn); + + return ret; +} + +static struct nf_proto_net *generic_get_net_proto(struct net *net) +{ + return &net->ct.nf_ct_proto.generic.pn; +} + struct nf_conntrack_l4proto nf_conntrack_l4proto_generic __read_mostly = { .l3proto = PF_UNSPEC, @@ -151,11 +211,6 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_generic __read_mostly = .nla_policy = generic_timeout_nla_policy, }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ -#ifdef CONFIG_SYSCTL - .ctl_table_header = &generic_sysctl_header, - .ctl_table = generic_sysctl_table, -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT - .ctl_compat_table = generic_compat_sysctl_table, -#endif -#endif + .init_net = generic_init_net, + .get_net_proto = generic_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 4bf6b4e4b77..b09b7af7f6f 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -54,13 +54,20 @@ static unsigned int gre_timeouts[GRE_CT_MAX] = { static int proto_gre_net_id __read_mostly; struct netns_proto_gre { + struct nf_proto_net nf; rwlock_t keymap_lock; struct list_head keymap_list; + unsigned int gre_timeouts[GRE_CT_MAX]; }; +static inline struct netns_proto_gre *gre_pernet(struct net *net) +{ + return net_generic(net, proto_gre_net_id); +} + void nf_ct_gre_keymap_flush(struct net *net) { - struct netns_proto_gre *net_gre = net_generic(net, proto_gre_net_id); + struct netns_proto_gre *net_gre = gre_pernet(net); struct nf_ct_gre_keymap *km, *tmp; write_lock_bh(&net_gre->keymap_lock); @@ -85,7 +92,7 @@ static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km, /* look up the source key for a given tuple */ static __be16 gre_keymap_lookup(struct net *net, struct nf_conntrack_tuple *t) { - struct netns_proto_gre *net_gre = net_generic(net, proto_gre_net_id); + struct netns_proto_gre *net_gre = gre_pernet(net); struct nf_ct_gre_keymap *km; __be16 key = 0; @@ -109,11 +116,11 @@ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, struct nf_conntrack_tuple *t) { struct net *net = nf_ct_net(ct); - struct netns_proto_gre *net_gre = net_generic(net, proto_gre_net_id); - struct nf_conn_help *help = nfct_help(ct); + struct netns_proto_gre *net_gre = gre_pernet(net); + struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct); struct nf_ct_gre_keymap **kmp, *km; - kmp = &help->help.ct_pptp_info.keymap[dir]; + kmp = &ct_pptp_info->keymap[dir]; if (*kmp) { /* check whether it's a retransmission */ read_lock_bh(&net_gre->keymap_lock); @@ -150,20 +157,20 @@ EXPORT_SYMBOL_GPL(nf_ct_gre_keymap_add); void nf_ct_gre_keymap_destroy(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); - struct netns_proto_gre *net_gre = net_generic(net, proto_gre_net_id); - struct nf_conn_help *help = nfct_help(ct); + struct netns_proto_gre *net_gre = gre_pernet(net); + struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct); enum ip_conntrack_dir dir; pr_debug("entering for ct %p\n", ct); write_lock_bh(&net_gre->keymap_lock); for (dir = IP_CT_DIR_ORIGINAL; dir < IP_CT_DIR_MAX; dir++) { - if (help->help.ct_pptp_info.keymap[dir]) { + if (ct_pptp_info->keymap[dir]) { pr_debug("removing %p from list\n", - help->help.ct_pptp_info.keymap[dir]); - list_del(&help->help.ct_pptp_info.keymap[dir]->list); - kfree(help->help.ct_pptp_info.keymap[dir]); - help->help.ct_pptp_info.keymap[dir] = NULL; + ct_pptp_info->keymap[dir]); + list_del(&ct_pptp_info->keymap[dir]->list); + kfree(ct_pptp_info->keymap[dir]); + ct_pptp_info->keymap[dir] = NULL; } } write_unlock_bh(&net_gre->keymap_lock); @@ -237,7 +244,7 @@ static int gre_print_conntrack(struct seq_file *s, struct nf_conn *ct) static unsigned int *gre_get_timeouts(struct net *net) { - return gre_timeouts; + return gre_pernet(net)->gre_timeouts; } /* Returns verdict for packet, and may modify conntrack */ @@ -297,13 +304,15 @@ static void gre_destroy(struct nf_conn *ct) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> -static int gre_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +static int gre_timeout_nlattr_to_obj(struct nlattr *tb[], + struct net *net, void *data) { unsigned int *timeouts = data; + struct netns_proto_gre *net_gre = gre_pernet(net); /* set default timeouts for GRE. */ - timeouts[GRE_CT_UNREPLIED] = gre_timeouts[GRE_CT_UNREPLIED]; - timeouts[GRE_CT_REPLIED] = gre_timeouts[GRE_CT_REPLIED]; + timeouts[GRE_CT_UNREPLIED] = net_gre->gre_timeouts[GRE_CT_UNREPLIED]; + timeouts[GRE_CT_REPLIED] = net_gre->gre_timeouts[GRE_CT_REPLIED]; if (tb[CTA_TIMEOUT_GRE_UNREPLIED]) { timeouts[GRE_CT_UNREPLIED] = @@ -339,6 +348,19 @@ gre_timeout_nla_policy[CTA_TIMEOUT_GRE_MAX+1] = { }; #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +static int gre_init_net(struct net *net, u_int16_t proto) +{ + struct netns_proto_gre *net_gre = gre_pernet(net); + int i; + + rwlock_init(&net_gre->keymap_lock); + INIT_LIST_HEAD(&net_gre->keymap_list); + for (i = 0; i < GRE_CT_MAX; i++) + net_gre->gre_timeouts[i] = gre_timeouts[i]; + + return 0; +} + /* protocol helper struct */ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = { .l3proto = AF_INET, @@ -368,20 +390,22 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = { .nla_policy = gre_timeout_nla_policy, }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + .net_id = &proto_gre_net_id, + .init_net = gre_init_net, }; static int proto_gre_net_init(struct net *net) { - struct netns_proto_gre *net_gre = net_generic(net, proto_gre_net_id); - - rwlock_init(&net_gre->keymap_lock); - INIT_LIST_HEAD(&net_gre->keymap_list); - - return 0; + int ret = 0; + ret = nf_conntrack_l4proto_register(net, &nf_conntrack_l4proto_gre4); + if (ret < 0) + pr_err("nf_conntrack_l4proto_gre4 :protocol register failed.\n"); + return ret; } static void proto_gre_net_exit(struct net *net) { + nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_gre4); nf_ct_gre_keymap_flush(net); } @@ -394,20 +418,11 @@ static struct pernet_operations proto_gre_net_ops = { static int __init nf_ct_proto_gre_init(void) { - int rv; - - rv = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_gre4); - if (rv < 0) - return rv; - rv = register_pernet_subsys(&proto_gre_net_ops); - if (rv < 0) - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_gre4); - return rv; + return register_pernet_subsys(&proto_gre_net_ops); } static void __exit nf_ct_proto_gre_fini(void) { - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_gre4); unregister_pernet_subsys(&proto_gre_net_ops); } diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 996db2fa21f..c746d61f83e 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -127,6 +127,17 @@ static const u8 sctp_conntracks[2][9][SCTP_CONNTRACK_MAX] = { } }; +static int sctp_net_id __read_mostly; +struct sctp_net { + struct nf_proto_net pn; + unsigned int timeouts[SCTP_CONNTRACK_MAX]; +}; + +static inline struct sctp_net *sctp_pernet(struct net *net) +{ + return net_generic(net, sctp_net_id); +} + static bool sctp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct nf_conntrack_tuple *tuple) { @@ -281,7 +292,7 @@ static int sctp_new_state(enum ip_conntrack_dir dir, static unsigned int *sctp_get_timeouts(struct net *net) { - return sctp_timeouts; + return sctp_pernet(net)->timeouts; } /* Returns verdict for packet, or -NF_ACCEPT for invalid. */ @@ -551,14 +562,16 @@ static int sctp_nlattr_size(void) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> -static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], + struct net *net, void *data) { unsigned int *timeouts = data; + struct sctp_net *sn = sctp_pernet(net); int i; /* set default SCTP timeouts. */ for (i=0; i<SCTP_CONNTRACK_MAX; i++) - timeouts[i] = sctp_timeouts[i]; + timeouts[i] = sn->timeouts[i]; /* there's a 1:1 mapping between attributes and protocol states. */ for (i=CTA_TIMEOUT_SCTP_UNSPEC+1; i<CTA_TIMEOUT_SCTP_MAX+1; i++) { @@ -599,54 +612,45 @@ sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { #ifdef CONFIG_SYSCTL -static unsigned int sctp_sysctl_table_users; -static struct ctl_table_header *sctp_sysctl_header; static struct ctl_table sctp_sysctl_table[] = { { .procname = "nf_conntrack_sctp_timeout_closed", - .data = &sctp_timeouts[SCTP_CONNTRACK_CLOSED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_sctp_timeout_cookie_wait", - .data = &sctp_timeouts[SCTP_CONNTRACK_COOKIE_WAIT], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_sctp_timeout_cookie_echoed", - .data = &sctp_timeouts[SCTP_CONNTRACK_COOKIE_ECHOED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_sctp_timeout_established", - .data = &sctp_timeouts[SCTP_CONNTRACK_ESTABLISHED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_sctp_timeout_shutdown_sent", - .data = &sctp_timeouts[SCTP_CONNTRACK_SHUTDOWN_SENT], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_sctp_timeout_shutdown_recd", - .data = &sctp_timeouts[SCTP_CONNTRACK_SHUTDOWN_RECD], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_sctp_timeout_shutdown_ack_sent", - .data = &sctp_timeouts[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -658,49 +662,42 @@ static struct ctl_table sctp_sysctl_table[] = { static struct ctl_table sctp_compat_sysctl_table[] = { { .procname = "ip_conntrack_sctp_timeout_closed", - .data = &sctp_timeouts[SCTP_CONNTRACK_CLOSED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_sctp_timeout_cookie_wait", - .data = &sctp_timeouts[SCTP_CONNTRACK_COOKIE_WAIT], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_sctp_timeout_cookie_echoed", - .data = &sctp_timeouts[SCTP_CONNTRACK_COOKIE_ECHOED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_sctp_timeout_established", - .data = &sctp_timeouts[SCTP_CONNTRACK_ESTABLISHED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_sctp_timeout_shutdown_sent", - .data = &sctp_timeouts[SCTP_CONNTRACK_SHUTDOWN_SENT], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_sctp_timeout_shutdown_recd", - .data = &sctp_timeouts[SCTP_CONNTRACK_SHUTDOWN_RECD], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_sctp_timeout_shutdown_ack_sent", - .data = &sctp_timeouts[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -710,6 +707,80 @@ static struct ctl_table sctp_compat_sysctl_table[] = { #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif +static int sctp_kmemdup_sysctl_table(struct nf_proto_net *pn, + struct sctp_net *sn) +{ +#ifdef CONFIG_SYSCTL + if (pn->ctl_table) + return 0; + + pn->ctl_table = kmemdup(sctp_sysctl_table, + sizeof(sctp_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_table) + return -ENOMEM; + + pn->ctl_table[0].data = &sn->timeouts[SCTP_CONNTRACK_CLOSED]; + pn->ctl_table[1].data = &sn->timeouts[SCTP_CONNTRACK_COOKIE_WAIT]; + pn->ctl_table[2].data = &sn->timeouts[SCTP_CONNTRACK_COOKIE_ECHOED]; + pn->ctl_table[3].data = &sn->timeouts[SCTP_CONNTRACK_ESTABLISHED]; + pn->ctl_table[4].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_SENT]; + pn->ctl_table[5].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_RECD]; + pn->ctl_table[6].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT]; +#endif + return 0; +} + +static int sctp_kmemdup_compat_sysctl_table(struct nf_proto_net *pn, + struct sctp_net *sn) +{ +#ifdef CONFIG_SYSCTL +#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT + pn->ctl_compat_table = kmemdup(sctp_compat_sysctl_table, + sizeof(sctp_compat_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_compat_table) + return -ENOMEM; + + pn->ctl_compat_table[0].data = &sn->timeouts[SCTP_CONNTRACK_CLOSED]; + pn->ctl_compat_table[1].data = &sn->timeouts[SCTP_CONNTRACK_COOKIE_WAIT]; + pn->ctl_compat_table[2].data = &sn->timeouts[SCTP_CONNTRACK_COOKIE_ECHOED]; + pn->ctl_compat_table[3].data = &sn->timeouts[SCTP_CONNTRACK_ESTABLISHED]; + pn->ctl_compat_table[4].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_SENT]; + pn->ctl_compat_table[5].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_RECD]; + pn->ctl_compat_table[6].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT]; +#endif +#endif + return 0; +} + +static int sctp_init_net(struct net *net, u_int16_t proto) +{ + int ret; + struct sctp_net *sn = sctp_pernet(net); + struct nf_proto_net *pn = &sn->pn; + + if (!pn->users) { + int i; + + for (i = 0; i < SCTP_CONNTRACK_MAX; i++) + sn->timeouts[i] = sctp_timeouts[i]; + } + + if (proto == AF_INET) { + ret = sctp_kmemdup_compat_sysctl_table(pn, sn); + if (ret < 0) + return ret; + + ret = sctp_kmemdup_sysctl_table(pn, sn); + if (ret < 0) + nf_ct_kfree_compat_sysctl_table(pn); + } else + ret = sctp_kmemdup_sysctl_table(pn, sn); + + return ret; +} + static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = { .l3proto = PF_INET, .l4proto = IPPROTO_SCTP, @@ -740,14 +811,8 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = { .nla_policy = sctp_timeout_nla_policy, }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ -#ifdef CONFIG_SYSCTL - .ctl_table_users = &sctp_sysctl_table_users, - .ctl_table_header = &sctp_sysctl_header, - .ctl_table = sctp_sysctl_table, -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT - .ctl_compat_table = sctp_compat_sysctl_table, -#endif -#endif + .net_id = &sctp_net_id, + .init_net = sctp_init_net, }; static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = { @@ -780,40 +845,58 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = { }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #endif -#ifdef CONFIG_SYSCTL - .ctl_table_users = &sctp_sysctl_table_users, - .ctl_table_header = &sctp_sysctl_header, - .ctl_table = sctp_sysctl_table, -#endif + .net_id = &sctp_net_id, + .init_net = sctp_init_net, }; -static int __init nf_conntrack_proto_sctp_init(void) +static int sctp_net_init(struct net *net) { - int ret; + int ret = 0; - ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_sctp4); - if (ret) { - pr_err("nf_conntrack_l4proto_sctp4: protocol register failed\n"); + ret = nf_conntrack_l4proto_register(net, + &nf_conntrack_l4proto_sctp4); + if (ret < 0) { + pr_err("nf_conntrack_l4proto_sctp4 :protocol register failed.\n"); goto out; } - ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_sctp6); - if (ret) { - pr_err("nf_conntrack_l4proto_sctp6: protocol register failed\n"); + ret = nf_conntrack_l4proto_register(net, + &nf_conntrack_l4proto_sctp6); + if (ret < 0) { + pr_err("nf_conntrack_l4proto_sctp6 :protocol register failed.\n"); goto cleanup_sctp4; } + return 0; +cleanup_sctp4: + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_sctp4); +out: return ret; +} - cleanup_sctp4: - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_sctp4); - out: - return ret; +static void sctp_net_exit(struct net *net) +{ + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_sctp6); + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_sctp4); +} + +static struct pernet_operations sctp_net_ops = { + .init = sctp_net_init, + .exit = sctp_net_exit, + .id = &sctp_net_id, + .size = sizeof(struct sctp_net), +}; + +static int __init nf_conntrack_proto_sctp_init(void) +{ + return register_pernet_subsys(&sctp_net_ops); } static void __exit nf_conntrack_proto_sctp_fini(void) { - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_sctp6); - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_sctp4); + unregister_pernet_subsys(&sctp_net_ops); } module_init(nf_conntrack_proto_sctp_init); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 21ff1a99f53..a5ac11ebef3 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -270,6 +270,11 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { } }; +static inline struct nf_tcp_net *tcp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.tcp; +} + static bool tcp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct nf_conntrack_tuple *tuple) { @@ -516,6 +521,7 @@ static bool tcp_in_window(const struct nf_conn *ct, u_int8_t pf) { struct net *net = nf_ct_net(ct); + struct nf_tcp_net *tn = tcp_pernet(net); struct ip_ct_tcp_state *sender = &state->seen[dir]; struct ip_ct_tcp_state *receiver = &state->seen[!dir]; const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; @@ -720,7 +726,7 @@ static bool tcp_in_window(const struct nf_conn *ct, } else { res = false; if (sender->flags & IP_CT_TCP_FLAG_BE_LIBERAL || - nf_ct_tcp_be_liberal) + tn->tcp_be_liberal) res = true; if (!res && LOG_INVALID(net, IPPROTO_TCP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, @@ -815,7 +821,7 @@ static int tcp_error(struct net *net, struct nf_conn *tmpl, static unsigned int *tcp_get_timeouts(struct net *net) { - return tcp_timeouts; + return tcp_pernet(net)->timeouts; } /* Returns verdict for packet, or -1 for invalid. */ @@ -828,6 +834,7 @@ static int tcp_packet(struct nf_conn *ct, unsigned int *timeouts) { struct net *net = nf_ct_net(ct); + struct nf_tcp_net *tn = tcp_pernet(net); struct nf_conntrack_tuple *tuple; enum tcp_conntrack new_state, old_state; enum ip_conntrack_dir dir; @@ -1020,7 +1027,7 @@ static int tcp_packet(struct nf_conn *ct, && new_state == TCP_CONNTRACK_FIN_WAIT) ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT; - if (ct->proto.tcp.retrans >= nf_ct_tcp_max_retrans && + if (ct->proto.tcp.retrans >= tn->tcp_max_retrans && timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS]) timeout = timeouts[TCP_CONNTRACK_RETRANS]; else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) & @@ -1065,6 +1072,8 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, enum tcp_conntrack new_state; const struct tcphdr *th; struct tcphdr _tcph; + struct net *net = nf_ct_net(ct); + struct nf_tcp_net *tn = tcp_pernet(net); const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[0]; const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[1]; @@ -1093,7 +1102,7 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.tcp.seen[0].td_end; tcp_options(skb, dataoff, th, &ct->proto.tcp.seen[0]); - } else if (nf_ct_tcp_loose == 0) { + } else if (tn->tcp_loose == 0) { /* Don't try to pick up connections. */ return false; } else { @@ -1251,14 +1260,16 @@ static int tcp_nlattr_tuple_size(void) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> -static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], + struct net *net, void *data) { unsigned int *timeouts = data; + struct nf_tcp_net *tn = tcp_pernet(net); int i; /* set default TCP timeouts. */ for (i=0; i<TCP_CONNTRACK_TIMEOUT_MAX; i++) - timeouts[i] = tcp_timeouts[i]; + timeouts[i] = tn->timeouts[i]; if (tb[CTA_TIMEOUT_TCP_SYN_SENT]) { timeouts[TCP_CONNTRACK_SYN_SENT] = @@ -1355,96 +1366,81 @@ static const struct nla_policy tcp_timeout_nla_policy[CTA_TIMEOUT_TCP_MAX+1] = { #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL -static unsigned int tcp_sysctl_table_users; -static struct ctl_table_header *tcp_sysctl_header; static struct ctl_table tcp_sysctl_table[] = { { .procname = "nf_conntrack_tcp_timeout_syn_sent", - .data = &tcp_timeouts[TCP_CONNTRACK_SYN_SENT], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_tcp_timeout_syn_recv", - .data = &tcp_timeouts[TCP_CONNTRACK_SYN_RECV], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_tcp_timeout_established", - .data = &tcp_timeouts[TCP_CONNTRACK_ESTABLISHED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_tcp_timeout_fin_wait", - .data = &tcp_timeouts[TCP_CONNTRACK_FIN_WAIT], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_tcp_timeout_close_wait", - .data = &tcp_timeouts[TCP_CONNTRACK_CLOSE_WAIT], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_tcp_timeout_last_ack", - .data = &tcp_timeouts[TCP_CONNTRACK_LAST_ACK], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_tcp_timeout_time_wait", - .data = &tcp_timeouts[TCP_CONNTRACK_TIME_WAIT], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_tcp_timeout_close", - .data = &tcp_timeouts[TCP_CONNTRACK_CLOSE], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_tcp_timeout_max_retrans", - .data = &tcp_timeouts[TCP_CONNTRACK_RETRANS], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_tcp_timeout_unacknowledged", - .data = &tcp_timeouts[TCP_CONNTRACK_UNACK], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_tcp_loose", - .data = &nf_ct_tcp_loose, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "nf_conntrack_tcp_be_liberal", - .data = &nf_ct_tcp_be_liberal, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "nf_conntrack_tcp_max_retrans", - .data = &nf_ct_tcp_max_retrans, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec, @@ -1456,91 +1452,78 @@ static struct ctl_table tcp_sysctl_table[] = { static struct ctl_table tcp_compat_sysctl_table[] = { { .procname = "ip_conntrack_tcp_timeout_syn_sent", - .data = &tcp_timeouts[TCP_CONNTRACK_SYN_SENT], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_tcp_timeout_syn_sent2", - .data = &tcp_timeouts[TCP_CONNTRACK_SYN_SENT2], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_tcp_timeout_syn_recv", - .data = &tcp_timeouts[TCP_CONNTRACK_SYN_RECV], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_tcp_timeout_established", - .data = &tcp_timeouts[TCP_CONNTRACK_ESTABLISHED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_tcp_timeout_fin_wait", - .data = &tcp_timeouts[TCP_CONNTRACK_FIN_WAIT], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_tcp_timeout_close_wait", - .data = &tcp_timeouts[TCP_CONNTRACK_CLOSE_WAIT], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_tcp_timeout_last_ack", - .data = &tcp_timeouts[TCP_CONNTRACK_LAST_ACK], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_tcp_timeout_time_wait", - .data = &tcp_timeouts[TCP_CONNTRACK_TIME_WAIT], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_tcp_timeout_close", - .data = &tcp_timeouts[TCP_CONNTRACK_CLOSE], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_tcp_timeout_max_retrans", - .data = &tcp_timeouts[TCP_CONNTRACK_RETRANS], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_tcp_loose", - .data = &nf_ct_tcp_loose, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "ip_conntrack_tcp_be_liberal", - .data = &nf_ct_tcp_be_liberal, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "ip_conntrack_tcp_max_retrans", - .data = &nf_ct_tcp_max_retrans, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec, @@ -1550,6 +1533,101 @@ static struct ctl_table tcp_compat_sysctl_table[] = { #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ +static int tcp_kmemdup_sysctl_table(struct nf_proto_net *pn, + struct nf_tcp_net *tn) +{ +#ifdef CONFIG_SYSCTL + if (pn->ctl_table) + return 0; + + pn->ctl_table = kmemdup(tcp_sysctl_table, + sizeof(tcp_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_table) + return -ENOMEM; + + pn->ctl_table[0].data = &tn->timeouts[TCP_CONNTRACK_SYN_SENT]; + pn->ctl_table[1].data = &tn->timeouts[TCP_CONNTRACK_SYN_RECV]; + pn->ctl_table[2].data = &tn->timeouts[TCP_CONNTRACK_ESTABLISHED]; + pn->ctl_table[3].data = &tn->timeouts[TCP_CONNTRACK_FIN_WAIT]; + pn->ctl_table[4].data = &tn->timeouts[TCP_CONNTRACK_CLOSE_WAIT]; + pn->ctl_table[5].data = &tn->timeouts[TCP_CONNTRACK_LAST_ACK]; + pn->ctl_table[6].data = &tn->timeouts[TCP_CONNTRACK_TIME_WAIT]; + pn->ctl_table[7].data = &tn->timeouts[TCP_CONNTRACK_CLOSE]; + pn->ctl_table[8].data = &tn->timeouts[TCP_CONNTRACK_RETRANS]; + pn->ctl_table[9].data = &tn->timeouts[TCP_CONNTRACK_UNACK]; + pn->ctl_table[10].data = &tn->tcp_loose; + pn->ctl_table[11].data = &tn->tcp_be_liberal; + pn->ctl_table[12].data = &tn->tcp_max_retrans; +#endif + return 0; +} + +static int tcp_kmemdup_compat_sysctl_table(struct nf_proto_net *pn, + struct nf_tcp_net *tn) +{ +#ifdef CONFIG_SYSCTL +#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT + pn->ctl_compat_table = kmemdup(tcp_compat_sysctl_table, + sizeof(tcp_compat_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_compat_table) + return -ENOMEM; + + pn->ctl_compat_table[0].data = &tn->timeouts[TCP_CONNTRACK_SYN_SENT]; + pn->ctl_compat_table[1].data = &tn->timeouts[TCP_CONNTRACK_SYN_SENT2]; + pn->ctl_compat_table[2].data = &tn->timeouts[TCP_CONNTRACK_SYN_RECV]; + pn->ctl_compat_table[3].data = &tn->timeouts[TCP_CONNTRACK_ESTABLISHED]; + pn->ctl_compat_table[4].data = &tn->timeouts[TCP_CONNTRACK_FIN_WAIT]; + pn->ctl_compat_table[5].data = &tn->timeouts[TCP_CONNTRACK_CLOSE_WAIT]; + pn->ctl_compat_table[6].data = &tn->timeouts[TCP_CONNTRACK_LAST_ACK]; + pn->ctl_compat_table[7].data = &tn->timeouts[TCP_CONNTRACK_TIME_WAIT]; + pn->ctl_compat_table[8].data = &tn->timeouts[TCP_CONNTRACK_CLOSE]; + pn->ctl_compat_table[9].data = &tn->timeouts[TCP_CONNTRACK_RETRANS]; + pn->ctl_compat_table[10].data = &tn->tcp_loose; + pn->ctl_compat_table[11].data = &tn->tcp_be_liberal; + pn->ctl_compat_table[12].data = &tn->tcp_max_retrans; +#endif +#endif + return 0; +} + +static int tcp_init_net(struct net *net, u_int16_t proto) +{ + int ret; + struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_proto_net *pn = &tn->pn; + + if (!pn->users) { + int i; + + for (i = 0; i < TCP_CONNTRACK_TIMEOUT_MAX; i++) + tn->timeouts[i] = tcp_timeouts[i]; + + tn->tcp_loose = nf_ct_tcp_loose; + tn->tcp_be_liberal = nf_ct_tcp_be_liberal; + tn->tcp_max_retrans = nf_ct_tcp_max_retrans; + } + + if (proto == AF_INET) { + ret = tcp_kmemdup_compat_sysctl_table(pn, tn); + if (ret < 0) + return ret; + + ret = tcp_kmemdup_sysctl_table(pn, tn); + if (ret < 0) + nf_ct_kfree_compat_sysctl_table(pn); + } else + ret = tcp_kmemdup_sysctl_table(pn, tn); + + return ret; +} + +static struct nf_proto_net *tcp_get_net_proto(struct net *net) +{ + return &net->ct.nf_ct_proto.tcp.pn; +} + struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly = { .l3proto = PF_INET, @@ -1582,14 +1660,8 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly = .nla_policy = tcp_timeout_nla_policy, }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ -#ifdef CONFIG_SYSCTL - .ctl_table_users = &tcp_sysctl_table_users, - .ctl_table_header = &tcp_sysctl_header, - .ctl_table = tcp_sysctl_table, -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT - .ctl_compat_table = tcp_compat_sysctl_table, -#endif -#endif + .init_net = tcp_init_net, + .get_net_proto = tcp_get_net_proto, }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_tcp4); @@ -1625,10 +1697,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 __read_mostly = .nla_policy = tcp_timeout_nla_policy, }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ -#ifdef CONFIG_SYSCTL - .ctl_table_users = &tcp_sysctl_table_users, - .ctl_table_header = &tcp_sysctl_header, - .ctl_table = tcp_sysctl_table, -#endif + .init_net = tcp_init_net, + .get_net_proto = tcp_get_net_proto, }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_tcp6); diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 7259a6bdeb4..59623cc56e8 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -25,17 +25,16 @@ #include <net/netfilter/ipv4/nf_conntrack_ipv4.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> -enum udp_conntrack { - UDP_CT_UNREPLIED, - UDP_CT_REPLIED, - UDP_CT_MAX -}; - static unsigned int udp_timeouts[UDP_CT_MAX] = { [UDP_CT_UNREPLIED] = 30*HZ, [UDP_CT_REPLIED] = 180*HZ, }; +static inline struct nf_udp_net *udp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.udp; +} + static bool udp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct nf_conntrack_tuple *tuple) @@ -73,7 +72,7 @@ static int udp_print_tuple(struct seq_file *s, static unsigned int *udp_get_timeouts(struct net *net) { - return udp_timeouts; + return udp_pernet(net)->timeouts; } /* Returns verdict for packet, and may modify conntracktype */ @@ -157,13 +156,15 @@ static int udp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> -static int udp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +static int udp_timeout_nlattr_to_obj(struct nlattr *tb[], + struct net *net, void *data) { unsigned int *timeouts = data; + struct nf_udp_net *un = udp_pernet(net); /* set default timeouts for UDP. */ - timeouts[UDP_CT_UNREPLIED] = udp_timeouts[UDP_CT_UNREPLIED]; - timeouts[UDP_CT_REPLIED] = udp_timeouts[UDP_CT_REPLIED]; + timeouts[UDP_CT_UNREPLIED] = un->timeouts[UDP_CT_UNREPLIED]; + timeouts[UDP_CT_REPLIED] = un->timeouts[UDP_CT_REPLIED]; if (tb[CTA_TIMEOUT_UDP_UNREPLIED]) { timeouts[UDP_CT_UNREPLIED] = @@ -200,19 +201,15 @@ udp_timeout_nla_policy[CTA_TIMEOUT_UDP_MAX+1] = { #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL -static unsigned int udp_sysctl_table_users; -static struct ctl_table_header *udp_sysctl_header; static struct ctl_table udp_sysctl_table[] = { { .procname = "nf_conntrack_udp_timeout", - .data = &udp_timeouts[UDP_CT_UNREPLIED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_udp_timeout_stream", - .data = &udp_timeouts[UDP_CT_REPLIED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -223,14 +220,12 @@ static struct ctl_table udp_sysctl_table[] = { static struct ctl_table udp_compat_sysctl_table[] = { { .procname = "ip_conntrack_udp_timeout", - .data = &udp_timeouts[UDP_CT_UNREPLIED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_udp_timeout_stream", - .data = &udp_timeouts[UDP_CT_REPLIED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -240,6 +235,73 @@ static struct ctl_table udp_compat_sysctl_table[] = { #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ +static int udp_kmemdup_sysctl_table(struct nf_proto_net *pn, + struct nf_udp_net *un) +{ +#ifdef CONFIG_SYSCTL + if (pn->ctl_table) + return 0; + pn->ctl_table = kmemdup(udp_sysctl_table, + sizeof(udp_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_table) + return -ENOMEM; + pn->ctl_table[0].data = &un->timeouts[UDP_CT_UNREPLIED]; + pn->ctl_table[1].data = &un->timeouts[UDP_CT_REPLIED]; +#endif + return 0; +} + +static int udp_kmemdup_compat_sysctl_table(struct nf_proto_net *pn, + struct nf_udp_net *un) +{ +#ifdef CONFIG_SYSCTL +#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT + pn->ctl_compat_table = kmemdup(udp_compat_sysctl_table, + sizeof(udp_compat_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_compat_table) + return -ENOMEM; + + pn->ctl_compat_table[0].data = &un->timeouts[UDP_CT_UNREPLIED]; + pn->ctl_compat_table[1].data = &un->timeouts[UDP_CT_REPLIED]; +#endif +#endif + return 0; +} + +static int udp_init_net(struct net *net, u_int16_t proto) +{ + int ret; + struct nf_udp_net *un = udp_pernet(net); + struct nf_proto_net *pn = &un->pn; + + if (!pn->users) { + int i; + + for (i = 0; i < UDP_CT_MAX; i++) + un->timeouts[i] = udp_timeouts[i]; + } + + if (proto == AF_INET) { + ret = udp_kmemdup_compat_sysctl_table(pn, un); + if (ret < 0) + return ret; + + ret = udp_kmemdup_sysctl_table(pn, un); + if (ret < 0) + nf_ct_kfree_compat_sysctl_table(pn); + } else + ret = udp_kmemdup_sysctl_table(pn, un); + + return ret; +} + +static struct nf_proto_net *udp_get_net_proto(struct net *net) +{ + return &net->ct.nf_ct_proto.udp.pn; +} + struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 __read_mostly = { .l3proto = PF_INET, @@ -267,14 +329,8 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 __read_mostly = .nla_policy = udp_timeout_nla_policy, }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ -#ifdef CONFIG_SYSCTL - .ctl_table_users = &udp_sysctl_table_users, - .ctl_table_header = &udp_sysctl_header, - .ctl_table = udp_sysctl_table, -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT - .ctl_compat_table = udp_compat_sysctl_table, -#endif -#endif + .init_net = udp_init_net, + .get_net_proto = udp_get_net_proto, }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udp4); @@ -305,10 +361,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 __read_mostly = .nla_policy = udp_timeout_nla_policy, }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ -#ifdef CONFIG_SYSCTL - .ctl_table_users = &udp_sysctl_table_users, - .ctl_table_header = &udp_sysctl_header, - .ctl_table = udp_sysctl_table, -#endif + .init_net = udp_init_net, + .get_net_proto = udp_get_net_proto, }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udp6); diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index 4d60a5376aa..4b66df20928 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -35,6 +35,17 @@ static unsigned int udplite_timeouts[UDPLITE_CT_MAX] = { [UDPLITE_CT_REPLIED] = 180*HZ, }; +static int udplite_net_id __read_mostly; +struct udplite_net { + struct nf_proto_net pn; + unsigned int timeouts[UDPLITE_CT_MAX]; +}; + +static inline struct udplite_net *udplite_pernet(struct net *net) +{ + return net_generic(net, udplite_net_id); +} + static bool udplite_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct nf_conntrack_tuple *tuple) @@ -70,7 +81,7 @@ static int udplite_print_tuple(struct seq_file *s, static unsigned int *udplite_get_timeouts(struct net *net) { - return udplite_timeouts; + return udplite_pernet(net)->timeouts; } /* Returns verdict for packet, and may modify conntracktype */ @@ -161,13 +172,15 @@ static int udplite_error(struct net *net, struct nf_conn *tmpl, #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> -static int udplite_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +static int udplite_timeout_nlattr_to_obj(struct nlattr *tb[], + struct net *net, void *data) { unsigned int *timeouts = data; + struct udplite_net *un = udplite_pernet(net); /* set default timeouts for UDPlite. */ - timeouts[UDPLITE_CT_UNREPLIED] = udplite_timeouts[UDPLITE_CT_UNREPLIED]; - timeouts[UDPLITE_CT_REPLIED] = udplite_timeouts[UDPLITE_CT_REPLIED]; + timeouts[UDPLITE_CT_UNREPLIED] = un->timeouts[UDPLITE_CT_UNREPLIED]; + timeouts[UDPLITE_CT_REPLIED] = un->timeouts[UDPLITE_CT_REPLIED]; if (tb[CTA_TIMEOUT_UDPLITE_UNREPLIED]) { timeouts[UDPLITE_CT_UNREPLIED] = @@ -204,19 +217,15 @@ udplite_timeout_nla_policy[CTA_TIMEOUT_UDPLITE_MAX+1] = { #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL -static unsigned int udplite_sysctl_table_users; -static struct ctl_table_header *udplite_sysctl_header; static struct ctl_table udplite_sysctl_table[] = { { .procname = "nf_conntrack_udplite_timeout", - .data = &udplite_timeouts[UDPLITE_CT_UNREPLIED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_udplite_timeout_stream", - .data = &udplite_timeouts[UDPLITE_CT_REPLIED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -225,6 +234,40 @@ static struct ctl_table udplite_sysctl_table[] = { }; #endif /* CONFIG_SYSCTL */ +static int udplite_kmemdup_sysctl_table(struct nf_proto_net *pn, + struct udplite_net *un) +{ +#ifdef CONFIG_SYSCTL + if (pn->ctl_table) + return 0; + + pn->ctl_table = kmemdup(udplite_sysctl_table, + sizeof(udplite_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_table) + return -ENOMEM; + + pn->ctl_table[0].data = &un->timeouts[UDPLITE_CT_UNREPLIED]; + pn->ctl_table[1].data = &un->timeouts[UDPLITE_CT_REPLIED]; +#endif + return 0; +} + +static int udplite_init_net(struct net *net, u_int16_t proto) +{ + struct udplite_net *un = udplite_pernet(net); + struct nf_proto_net *pn = &un->pn; + + if (!pn->users) { + int i; + + for (i = 0 ; i < UDPLITE_CT_MAX; i++) + un->timeouts[i] = udplite_timeouts[i]; + } + + return udplite_kmemdup_sysctl_table(pn, un); +} + static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 __read_mostly = { .l3proto = PF_INET, @@ -253,11 +296,8 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 __read_mostly = .nla_policy = udplite_timeout_nla_policy, }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ -#ifdef CONFIG_SYSCTL - .ctl_table_users = &udplite_sysctl_table_users, - .ctl_table_header = &udplite_sysctl_header, - .ctl_table = udplite_sysctl_table, -#endif + .net_id = &udplite_net_id, + .init_net = udplite_init_net, }; static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly = @@ -288,34 +328,55 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly = .nla_policy = udplite_timeout_nla_policy, }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ -#ifdef CONFIG_SYSCTL - .ctl_table_users = &udplite_sysctl_table_users, - .ctl_table_header = &udplite_sysctl_header, - .ctl_table = udplite_sysctl_table, -#endif + .net_id = &udplite_net_id, + .init_net = udplite_init_net, }; -static int __init nf_conntrack_proto_udplite_init(void) +static int udplite_net_init(struct net *net) { - int err; - - err = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_udplite4); - if (err < 0) - goto err1; - err = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_udplite6); - if (err < 0) - goto err2; + int ret = 0; + + ret = nf_conntrack_l4proto_register(net, + &nf_conntrack_l4proto_udplite4); + if (ret < 0) { + pr_err("nf_conntrack_l4proto_udplite4 :protocol register failed.\n"); + goto out; + } + ret = nf_conntrack_l4proto_register(net, + &nf_conntrack_l4proto_udplite6); + if (ret < 0) { + pr_err("nf_conntrack_l4proto_udplite4 :protocol register failed.\n"); + goto cleanup_udplite4; + } return 0; -err2: - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udplite4); -err1: - return err; + +cleanup_udplite4: + nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_udplite4); +out: + return ret; +} + +static void udplite_net_exit(struct net *net) +{ + nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_udplite6); + nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_udplite4); +} + +static struct pernet_operations udplite_net_ops = { + .init = udplite_net_init, + .exit = udplite_net_exit, + .id = &udplite_net_id, + .size = sizeof(struct udplite_net), +}; + +static int __init nf_conntrack_proto_udplite_init(void) +{ + return register_pernet_subsys(&udplite_net_ops); } static void __exit nf_conntrack_proto_udplite_exit(void) { - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udplite6); - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udplite4); + unregister_pernet_subsys(&udplite_net_ops); } module_init(nf_conntrack_proto_udplite_init); diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c index 8501823b3f9..295429f3908 100644 --- a/net/netfilter/nf_conntrack_sane.c +++ b/net/netfilter/nf_conntrack_sane.c @@ -69,13 +69,12 @@ static int help(struct sk_buff *skb, void *sb_ptr; int ret = NF_ACCEPT; int dir = CTINFO2DIR(ctinfo); - struct nf_ct_sane_master *ct_sane_info; + struct nf_ct_sane_master *ct_sane_info = nfct_help_data(ct); struct nf_conntrack_expect *exp; struct nf_conntrack_tuple *tuple; struct sane_request *req; struct sane_reply_net_start *reply; - ct_sane_info = &nfct_help(ct)->help.ct_sane_info; /* Until there's been traffic both ways, don't look in packets. */ if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) @@ -163,7 +162,6 @@ out: } static struct nf_conntrack_helper sane[MAX_PORTS][2] __read_mostly; -static char sane_names[MAX_PORTS][2][sizeof("sane-65535")] __read_mostly; static const struct nf_conntrack_expect_policy sane_exp_policy = { .max_expected = 1, @@ -190,7 +188,6 @@ static void nf_conntrack_sane_fini(void) static int __init nf_conntrack_sane_init(void) { int i, j = -1, ret = 0; - char *tmpname; sane_buffer = kmalloc(65536, GFP_KERNEL); if (!sane_buffer) @@ -205,17 +202,16 @@ static int __init nf_conntrack_sane_init(void) sane[i][0].tuple.src.l3num = PF_INET; sane[i][1].tuple.src.l3num = PF_INET6; for (j = 0; j < 2; j++) { + sane[i][j].data_len = sizeof(struct nf_ct_sane_master); sane[i][j].tuple.src.u.tcp.port = htons(ports[i]); sane[i][j].tuple.dst.protonum = IPPROTO_TCP; sane[i][j].expect_policy = &sane_exp_policy; sane[i][j].me = THIS_MODULE; sane[i][j].help = help; - tmpname = &sane_names[i][j][0]; if (ports[i] == SANE_PORT) - sprintf(tmpname, "sane"); + sprintf(sane[i][j].name, "sane"); else - sprintf(tmpname, "sane-%d", ports[i]); - sane[i][j].name = tmpname; + sprintf(sane[i][j].name, "sane-%d", ports[i]); pr_debug("nf_ct_sane: registering helper for pf: %d " "port: %d\n", diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 93faf6a3a63..5c0a112aeee 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -183,12 +183,12 @@ static int media_len(const struct nf_conn *ct, const char *dptr, return len + digits_len(ct, dptr, limit, shift); } -static int parse_addr(const struct nf_conn *ct, const char *cp, - const char **endp, union nf_inet_addr *addr, - const char *limit) +static int sip_parse_addr(const struct nf_conn *ct, const char *cp, + const char **endp, union nf_inet_addr *addr, + const char *limit, bool delim) { const char *end; - int ret = 0; + int ret; if (!ct) return 0; @@ -197,16 +197,28 @@ static int parse_addr(const struct nf_conn *ct, const char *cp, switch (nf_ct_l3num(ct)) { case AF_INET: ret = in4_pton(cp, limit - cp, (u8 *)&addr->ip, -1, &end); + if (ret == 0) + return 0; break; case AF_INET6: + if (cp < limit && *cp == '[') + cp++; + else if (delim) + return 0; + ret = in6_pton(cp, limit - cp, (u8 *)&addr->ip6, -1, &end); + if (ret == 0) + return 0; + + if (end < limit && *end == ']') + end++; + else if (delim) + return 0; break; default: BUG(); } - if (ret == 0 || end == cp) - return 0; if (endp) *endp = end; return 1; @@ -219,7 +231,7 @@ static int epaddr_len(const struct nf_conn *ct, const char *dptr, union nf_inet_addr addr; const char *aux = dptr; - if (!parse_addr(ct, dptr, &dptr, &addr, limit)) { + if (!sip_parse_addr(ct, dptr, &dptr, &addr, limit, true)) { pr_debug("ip: %s parse failed.!\n", dptr); return 0; } @@ -296,7 +308,7 @@ int ct_sip_parse_request(const struct nf_conn *ct, return 0; dptr += shift; - if (!parse_addr(ct, dptr, &end, addr, limit)) + if (!sip_parse_addr(ct, dptr, &end, addr, limit, true)) return -1; if (end < limit && *end == ':') { end++; @@ -550,7 +562,7 @@ int ct_sip_parse_header_uri(const struct nf_conn *ct, const char *dptr, if (ret == 0) return ret; - if (!parse_addr(ct, dptr + *matchoff, &c, addr, limit)) + if (!sip_parse_addr(ct, dptr + *matchoff, &c, addr, limit, true)) return -1; if (*c == ':') { c++; @@ -599,7 +611,7 @@ int ct_sip_parse_address_param(const struct nf_conn *ct, const char *dptr, unsigned int dataoff, unsigned int datalen, const char *name, unsigned int *matchoff, unsigned int *matchlen, - union nf_inet_addr *addr) + union nf_inet_addr *addr, bool delim) { const char *limit = dptr + datalen; const char *start, *end; @@ -613,7 +625,7 @@ int ct_sip_parse_address_param(const struct nf_conn *ct, const char *dptr, return 0; start += strlen(name); - if (!parse_addr(ct, start, &end, addr, limit)) + if (!sip_parse_addr(ct, start, &end, addr, limit, delim)) return 0; *matchoff = start - dptr; *matchlen = end - start; @@ -675,6 +687,47 @@ static int ct_sip_parse_transport(struct nf_conn *ct, const char *dptr, return 1; } +static int sdp_parse_addr(const struct nf_conn *ct, const char *cp, + const char **endp, union nf_inet_addr *addr, + const char *limit) +{ + const char *end; + int ret; + + memset(addr, 0, sizeof(*addr)); + switch (nf_ct_l3num(ct)) { + case AF_INET: + ret = in4_pton(cp, limit - cp, (u8 *)&addr->ip, -1, &end); + break; + case AF_INET6: + ret = in6_pton(cp, limit - cp, (u8 *)&addr->ip6, -1, &end); + break; + default: + BUG(); + } + + if (ret == 0) + return 0; + if (endp) + *endp = end; + return 1; +} + +/* skip ip address. returns its length. */ +static int sdp_addr_len(const struct nf_conn *ct, const char *dptr, + const char *limit, int *shift) +{ + union nf_inet_addr addr; + const char *aux = dptr; + + if (!sdp_parse_addr(ct, dptr, &dptr, &addr, limit)) { + pr_debug("ip: %s parse failed.!\n", dptr); + return 0; + } + + return dptr - aux; +} + /* SDP header parsing: a SDP session description contains an ordered set of * headers, starting with a section containing general session parameters, * optionally followed by multiple media descriptions. @@ -686,10 +739,10 @@ static int ct_sip_parse_transport(struct nf_conn *ct, const char *dptr, */ static const struct sip_header ct_sdp_hdrs[] = { [SDP_HDR_VERSION] = SDP_HDR("v=", NULL, digits_len), - [SDP_HDR_OWNER_IP4] = SDP_HDR("o=", "IN IP4 ", epaddr_len), - [SDP_HDR_CONNECTION_IP4] = SDP_HDR("c=", "IN IP4 ", epaddr_len), - [SDP_HDR_OWNER_IP6] = SDP_HDR("o=", "IN IP6 ", epaddr_len), - [SDP_HDR_CONNECTION_IP6] = SDP_HDR("c=", "IN IP6 ", epaddr_len), + [SDP_HDR_OWNER_IP4] = SDP_HDR("o=", "IN IP4 ", sdp_addr_len), + [SDP_HDR_CONNECTION_IP4] = SDP_HDR("c=", "IN IP4 ", sdp_addr_len), + [SDP_HDR_OWNER_IP6] = SDP_HDR("o=", "IN IP6 ", sdp_addr_len), + [SDP_HDR_CONNECTION_IP6] = SDP_HDR("c=", "IN IP6 ", sdp_addr_len), [SDP_HDR_MEDIA] = SDP_HDR("m=", NULL, media_len), }; @@ -775,8 +828,8 @@ static int ct_sip_parse_sdp_addr(const struct nf_conn *ct, const char *dptr, if (ret <= 0) return ret; - if (!parse_addr(ct, dptr + *matchoff, NULL, addr, - dptr + *matchoff + *matchlen)) + if (!sdp_parse_addr(ct, dptr + *matchoff, NULL, addr, + dptr + *matchoff + *matchlen)) return -1; return 1; } @@ -1075,12 +1128,12 @@ static int process_invite_response(struct sk_buff *skb, unsigned int dataoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - struct nf_conn_help *help = nfct_help(ct); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); if ((code >= 100 && code <= 199) || (code >= 200 && code <= 299)) return process_sdp(skb, dataoff, dptr, datalen, cseq); - else if (help->help.ct_sip_info.invite_cseq == cseq) + else if (ct_sip_info->invite_cseq == cseq) flush_expectations(ct, true); return NF_ACCEPT; } @@ -1091,12 +1144,12 @@ static int process_update_response(struct sk_buff *skb, unsigned int dataoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - struct nf_conn_help *help = nfct_help(ct); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); if ((code >= 100 && code <= 199) || (code >= 200 && code <= 299)) return process_sdp(skb, dataoff, dptr, datalen, cseq); - else if (help->help.ct_sip_info.invite_cseq == cseq) + else if (ct_sip_info->invite_cseq == cseq) flush_expectations(ct, true); return NF_ACCEPT; } @@ -1107,12 +1160,12 @@ static int process_prack_response(struct sk_buff *skb, unsigned int dataoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - struct nf_conn_help *help = nfct_help(ct); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); if ((code >= 100 && code <= 199) || (code >= 200 && code <= 299)) return process_sdp(skb, dataoff, dptr, datalen, cseq); - else if (help->help.ct_sip_info.invite_cseq == cseq) + else if (ct_sip_info->invite_cseq == cseq) flush_expectations(ct, true); return NF_ACCEPT; } @@ -1123,13 +1176,13 @@ static int process_invite_request(struct sk_buff *skb, unsigned int dataoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - struct nf_conn_help *help = nfct_help(ct); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); unsigned int ret; flush_expectations(ct, true); ret = process_sdp(skb, dataoff, dptr, datalen, cseq); if (ret == NF_ACCEPT) - help->help.ct_sip_info.invite_cseq = cseq; + ct_sip_info->invite_cseq = cseq; return ret; } @@ -1154,7 +1207,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int dataoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - struct nf_conn_help *help = nfct_help(ct); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); unsigned int matchoff, matchlen; struct nf_conntrack_expect *exp; @@ -1235,7 +1288,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int dataoff, store_cseq: if (ret == NF_ACCEPT) - help->help.ct_sip_info.register_cseq = cseq; + ct_sip_info->register_cseq = cseq; return ret; } @@ -1245,7 +1298,7 @@ static int process_register_response(struct sk_buff *skb, unsigned int dataoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - struct nf_conn_help *help = nfct_help(ct); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); union nf_inet_addr addr; __be16 port; @@ -1262,7 +1315,7 @@ static int process_register_response(struct sk_buff *skb, unsigned int dataoff, * responses, so we store the sequence number of the last valid * request and compare it here. */ - if (help->help.ct_sip_info.register_cseq != cseq) + if (ct_sip_info->register_cseq != cseq) return NF_ACCEPT; if (code >= 100 && code <= 199) @@ -1515,7 +1568,6 @@ static int sip_help_udp(struct sk_buff *skb, unsigned int protoff, } static struct nf_conntrack_helper sip[MAX_PORTS][4] __read_mostly; -static char sip_names[MAX_PORTS][4][sizeof("sip-65535")] __read_mostly; static const struct nf_conntrack_expect_policy sip_exp_policy[SIP_EXPECT_MAX + 1] = { [SIP_EXPECT_SIGNALLING] = { @@ -1556,7 +1608,6 @@ static void nf_conntrack_sip_fini(void) static int __init nf_conntrack_sip_init(void) { int i, j, ret; - char *tmpname; if (ports_c == 0) ports[ports_c++] = SIP_PORT; @@ -1579,17 +1630,16 @@ static int __init nf_conntrack_sip_init(void) sip[i][3].help = sip_help_tcp; for (j = 0; j < ARRAY_SIZE(sip[i]); j++) { + sip[i][j].data_len = sizeof(struct nf_ct_sip_master); sip[i][j].tuple.src.u.udp.port = htons(ports[i]); sip[i][j].expect_policy = sip_exp_policy; sip[i][j].expect_class_max = SIP_EXPECT_MAX; sip[i][j].me = THIS_MODULE; - tmpname = &sip_names[i][j][0]; if (ports[i] == SIP_PORT) - sprintf(tmpname, "sip"); + sprintf(sip[i][j].name, "sip"); else - sprintf(tmpname, "sip-%u", i); - sip[i][j].name = tmpname; + sprintf(sip[i][j].name, "sip-%u", i); pr_debug("port #%u: %u\n", i, ports[i]); diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c index 75466fd72f4..81fc61c0526 100644 --- a/net/netfilter/nf_conntrack_tftp.c +++ b/net/netfilter/nf_conntrack_tftp.c @@ -92,7 +92,6 @@ static int tftp_help(struct sk_buff *skb, } static struct nf_conntrack_helper tftp[MAX_PORTS][2] __read_mostly; -static char tftp_names[MAX_PORTS][2][sizeof("tftp-65535")] __read_mostly; static const struct nf_conntrack_expect_policy tftp_exp_policy = { .max_expected = 1, @@ -112,7 +111,6 @@ static void nf_conntrack_tftp_fini(void) static int __init nf_conntrack_tftp_init(void) { int i, j, ret; - char *tmpname; if (ports_c == 0) ports[ports_c++] = TFTP_PORT; @@ -129,12 +127,10 @@ static int __init nf_conntrack_tftp_init(void) tftp[i][j].me = THIS_MODULE; tftp[i][j].help = tftp_help; - tmpname = &tftp_names[i][j][0]; if (ports[i] == TFTP_PORT) - sprintf(tmpname, "tftp"); + sprintf(tftp[i][j].name, "tftp"); else - sprintf(tmpname, "tftp-%u", i); - tftp[i][j].name = tmpname; + sprintf(tftp[i][j].name, "tftp-%u", i); ret = nf_conntrack_helper_register(&tftp[i][j]); if (ret) { diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 791d56bbd74..a26503342e7 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -39,6 +39,15 @@ static char __initdata nfversion[] = "0.30"; static const struct nfnetlink_subsystem __rcu *subsys_table[NFNL_SUBSYS_COUNT]; static DEFINE_MUTEX(nfnl_mutex); +static const int nfnl_group2type[NFNLGRP_MAX+1] = { + [NFNLGRP_CONNTRACK_NEW] = NFNL_SUBSYS_CTNETLINK, + [NFNLGRP_CONNTRACK_UPDATE] = NFNL_SUBSYS_CTNETLINK, + [NFNLGRP_CONNTRACK_DESTROY] = NFNL_SUBSYS_CTNETLINK, + [NFNLGRP_CONNTRACK_EXP_NEW] = NFNL_SUBSYS_CTNETLINK_EXP, + [NFNLGRP_CONNTRACK_EXP_UPDATE] = NFNL_SUBSYS_CTNETLINK_EXP, + [NFNLGRP_CONNTRACK_EXP_DESTROY] = NFNL_SUBSYS_CTNETLINK_EXP, +}; + void nfnl_lock(void) { mutex_lock(&nfnl_mutex); @@ -186,9 +195,11 @@ replay: lockdep_is_held(&nfnl_mutex)) != ss || nfnetlink_find_client(type, ss) != nc) err = -EAGAIN; - else + else if (nc->call) err = nc->call(net->nfnl, skb, nlh, (const struct nlattr **)cda); + else + err = -EINVAL; nfnl_unlock(); } if (err == -EAGAIN) @@ -202,12 +213,35 @@ static void nfnetlink_rcv(struct sk_buff *skb) netlink_rcv_skb(skb, &nfnetlink_rcv_msg); } +#ifdef CONFIG_MODULES +static void nfnetlink_bind(int group) +{ + const struct nfnetlink_subsystem *ss; + int type = nfnl_group2type[group]; + + rcu_read_lock(); + ss = nfnetlink_get_subsys(type); + if (!ss) { + rcu_read_unlock(); + request_module("nfnetlink-subsys-%d", type); + return; + } + rcu_read_unlock(); +} +#endif + static int __net_init nfnetlink_net_init(struct net *net) { struct sock *nfnl; + struct netlink_kernel_cfg cfg = { + .groups = NFNLGRP_MAX, + .input = nfnetlink_rcv, +#ifdef CONFIG_MODULES + .bind = nfnetlink_bind, +#endif + }; - nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, NFNLGRP_MAX, - nfnetlink_rcv, NULL, THIS_MODULE); + nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, THIS_MODULE, &cfg); if (!nfnl) return -ENOMEM; net->nfnl_stash = nfnl; diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c new file mode 100644 index 00000000000..d6836193d47 --- /dev/null +++ b/net/netfilter/nfnetlink_cthelper.c @@ -0,0 +1,672 @@ +/* + * (C) 2012 Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation (or any later at your option). + * + * This software has been sponsored by Vyatta Inc. <http://www.vyatta.com> + */ +#include <linux/init.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/skbuff.h> +#include <linux/netlink.h> +#include <linux/rculist.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/list.h> +#include <linux/errno.h> +#include <net/netlink.h> +#include <net/sock.h> + +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_expect.h> +#include <net/netfilter/nf_conntrack_ecache.h> + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_conntrack.h> +#include <linux/netfilter/nfnetlink_cthelper.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_DESCRIPTION("nfnl_cthelper: User-space connection tracking helpers"); + +static int +nfnl_userspace_cthelper(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, enum ip_conntrack_info ctinfo) +{ + const struct nf_conn_help *help; + struct nf_conntrack_helper *helper; + + help = nfct_help(ct); + if (help == NULL) + return NF_DROP; + + /* rcu_read_lock()ed by nf_hook_slow */ + helper = rcu_dereference(help->helper); + if (helper == NULL) + return NF_DROP; + + /* This is an user-space helper not yet configured, skip. */ + if ((helper->flags & + (NF_CT_HELPER_F_USERSPACE | NF_CT_HELPER_F_CONFIGURED)) == + NF_CT_HELPER_F_USERSPACE) + return NF_ACCEPT; + + /* If the user-space helper is not available, don't block traffic. */ + return NF_QUEUE_NR(helper->queue_num) | NF_VERDICT_FLAG_QUEUE_BYPASS; +} + +static const struct nla_policy nfnl_cthelper_tuple_pol[NFCTH_TUPLE_MAX+1] = { + [NFCTH_TUPLE_L3PROTONUM] = { .type = NLA_U16, }, + [NFCTH_TUPLE_L4PROTONUM] = { .type = NLA_U8, }, +}; + +static int +nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple, + const struct nlattr *attr) +{ + struct nlattr *tb[NFCTH_TUPLE_MAX+1]; + + nla_parse_nested(tb, NFCTH_TUPLE_MAX, attr, nfnl_cthelper_tuple_pol); + + if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM]) + return -EINVAL; + + tuple->src.l3num = ntohs(nla_get_u16(tb[NFCTH_TUPLE_L3PROTONUM])); + tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]); + + return 0; +} + +static int +nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct) +{ + const struct nf_conn_help *help = nfct_help(ct); + + if (help->helper->data_len == 0) + return -EINVAL; + + memcpy(&help->data, nla_data(attr), help->helper->data_len); + return 0; +} + +static int +nfnl_cthelper_to_nlattr(struct sk_buff *skb, const struct nf_conn *ct) +{ + const struct nf_conn_help *help = nfct_help(ct); + + if (help->helper->data_len && + nla_put(skb, CTA_HELP_INFO, help->helper->data_len, &help->data)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy nfnl_cthelper_expect_pol[NFCTH_POLICY_MAX+1] = { + [NFCTH_POLICY_NAME] = { .type = NLA_NUL_STRING, + .len = NF_CT_HELPER_NAME_LEN-1 }, + [NFCTH_POLICY_EXPECT_MAX] = { .type = NLA_U32, }, + [NFCTH_POLICY_EXPECT_TIMEOUT] = { .type = NLA_U32, }, +}; + +static int +nfnl_cthelper_expect_policy(struct nf_conntrack_expect_policy *expect_policy, + const struct nlattr *attr) +{ + struct nlattr *tb[NFCTH_POLICY_MAX+1]; + + nla_parse_nested(tb, NFCTH_POLICY_MAX, attr, nfnl_cthelper_expect_pol); + + if (!tb[NFCTH_POLICY_NAME] || + !tb[NFCTH_POLICY_EXPECT_MAX] || + !tb[NFCTH_POLICY_EXPECT_TIMEOUT]) + return -EINVAL; + + strncpy(expect_policy->name, + nla_data(tb[NFCTH_POLICY_NAME]), NF_CT_HELPER_NAME_LEN); + expect_policy->max_expected = + ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX])); + expect_policy->timeout = + ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_TIMEOUT])); + + return 0; +} + +static const struct nla_policy +nfnl_cthelper_expect_policy_set[NFCTH_POLICY_SET_MAX+1] = { + [NFCTH_POLICY_SET_NUM] = { .type = NLA_U32, }, +}; + +static int +nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper, + const struct nlattr *attr) +{ + int i, ret; + struct nf_conntrack_expect_policy *expect_policy; + struct nlattr *tb[NFCTH_POLICY_SET_MAX+1]; + + nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr, + nfnl_cthelper_expect_policy_set); + + if (!tb[NFCTH_POLICY_SET_NUM]) + return -EINVAL; + + helper->expect_class_max = + ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM])); + + if (helper->expect_class_max != 0 && + helper->expect_class_max > NF_CT_MAX_EXPECT_CLASSES) + return -EOVERFLOW; + + expect_policy = kzalloc(sizeof(struct nf_conntrack_expect_policy) * + helper->expect_class_max, GFP_KERNEL); + if (expect_policy == NULL) + return -ENOMEM; + + for (i=0; i<helper->expect_class_max; i++) { + if (!tb[NFCTH_POLICY_SET+i]) + goto err; + + ret = nfnl_cthelper_expect_policy(&expect_policy[i], + tb[NFCTH_POLICY_SET+i]); + if (ret < 0) + goto err; + } + helper->expect_policy = expect_policy; + return 0; +err: + kfree(expect_policy); + return -EINVAL; +} + +static int +nfnl_cthelper_create(const struct nlattr * const tb[], + struct nf_conntrack_tuple *tuple) +{ + struct nf_conntrack_helper *helper; + int ret; + + if (!tb[NFCTH_TUPLE] || !tb[NFCTH_POLICY] || !tb[NFCTH_PRIV_DATA_LEN]) + return -EINVAL; + + helper = kzalloc(sizeof(struct nf_conntrack_helper), GFP_KERNEL); + if (helper == NULL) + return -ENOMEM; + + ret = nfnl_cthelper_parse_expect_policy(helper, tb[NFCTH_POLICY]); + if (ret < 0) + goto err; + + strncpy(helper->name, nla_data(tb[NFCTH_NAME]), NF_CT_HELPER_NAME_LEN); + helper->data_len = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN])); + helper->flags |= NF_CT_HELPER_F_USERSPACE; + memcpy(&helper->tuple, tuple, sizeof(struct nf_conntrack_tuple)); + + helper->me = THIS_MODULE; + helper->help = nfnl_userspace_cthelper; + helper->from_nlattr = nfnl_cthelper_from_nlattr; + helper->to_nlattr = nfnl_cthelper_to_nlattr; + + /* Default to queue number zero, this can be updated at any time. */ + if (tb[NFCTH_QUEUE_NUM]) + helper->queue_num = ntohl(nla_get_be32(tb[NFCTH_QUEUE_NUM])); + + if (tb[NFCTH_STATUS]) { + int status = ntohl(nla_get_be32(tb[NFCTH_STATUS])); + + switch(status) { + case NFCT_HELPER_STATUS_ENABLED: + helper->flags |= NF_CT_HELPER_F_CONFIGURED; + break; + case NFCT_HELPER_STATUS_DISABLED: + helper->flags &= ~NF_CT_HELPER_F_CONFIGURED; + break; + } + } + + ret = nf_conntrack_helper_register(helper); + if (ret < 0) + goto err; + + return 0; +err: + kfree(helper); + return ret; +} + +static int +nfnl_cthelper_update(const struct nlattr * const tb[], + struct nf_conntrack_helper *helper) +{ + int ret; + + if (tb[NFCTH_PRIV_DATA_LEN]) + return -EBUSY; + + if (tb[NFCTH_POLICY]) { + ret = nfnl_cthelper_parse_expect_policy(helper, + tb[NFCTH_POLICY]); + if (ret < 0) + return ret; + } + if (tb[NFCTH_QUEUE_NUM]) + helper->queue_num = ntohl(nla_get_be32(tb[NFCTH_QUEUE_NUM])); + + if (tb[NFCTH_STATUS]) { + int status = ntohl(nla_get_be32(tb[NFCTH_STATUS])); + + switch(status) { + case NFCT_HELPER_STATUS_ENABLED: + helper->flags |= NF_CT_HELPER_F_CONFIGURED; + break; + case NFCT_HELPER_STATUS_DISABLED: + helper->flags &= ~NF_CT_HELPER_F_CONFIGURED; + break; + } + } + return 0; +} + +static int +nfnl_cthelper_new(struct sock *nfnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, const struct nlattr * const tb[]) +{ + const char *helper_name; + struct nf_conntrack_helper *cur, *helper = NULL; + struct nf_conntrack_tuple tuple; + struct hlist_node *n; + int ret = 0, i; + + if (!tb[NFCTH_NAME] || !tb[NFCTH_TUPLE]) + return -EINVAL; + + helper_name = nla_data(tb[NFCTH_NAME]); + + ret = nfnl_cthelper_parse_tuple(&tuple, tb[NFCTH_TUPLE]); + if (ret < 0) + return ret; + + rcu_read_lock(); + for (i = 0; i < nf_ct_helper_hsize && !helper; i++) { + hlist_for_each_entry_rcu(cur, n, &nf_ct_helper_hash[i], hnode) { + + /* skip non-userspace conntrack helpers. */ + if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) + continue; + + if (strncmp(cur->name, helper_name, + NF_CT_HELPER_NAME_LEN) != 0) + continue; + + if ((tuple.src.l3num != cur->tuple.src.l3num || + tuple.dst.protonum != cur->tuple.dst.protonum)) + continue; + + if (nlh->nlmsg_flags & NLM_F_EXCL) { + ret = -EEXIST; + goto err; + } + helper = cur; + break; + } + } + rcu_read_unlock(); + + if (helper == NULL) + ret = nfnl_cthelper_create(tb, &tuple); + else + ret = nfnl_cthelper_update(tb, helper); + + return ret; +err: + rcu_read_unlock(); + return ret; +} + +static int +nfnl_cthelper_dump_tuple(struct sk_buff *skb, + struct nf_conntrack_helper *helper) +{ + struct nlattr *nest_parms; + + nest_parms = nla_nest_start(skb, NFCTH_TUPLE | NLA_F_NESTED); + if (nest_parms == NULL) + goto nla_put_failure; + + if (nla_put_be16(skb, NFCTH_TUPLE_L3PROTONUM, + htons(helper->tuple.src.l3num))) + goto nla_put_failure; + + if (nla_put_u8(skb, NFCTH_TUPLE_L4PROTONUM, helper->tuple.dst.protonum)) + goto nla_put_failure; + + nla_nest_end(skb, nest_parms); + return 0; + +nla_put_failure: + return -1; +} + +static int +nfnl_cthelper_dump_policy(struct sk_buff *skb, + struct nf_conntrack_helper *helper) +{ + int i; + struct nlattr *nest_parms1, *nest_parms2; + + nest_parms1 = nla_nest_start(skb, NFCTH_POLICY | NLA_F_NESTED); + if (nest_parms1 == NULL) + goto nla_put_failure; + + if (nla_put_be32(skb, NFCTH_POLICY_SET_NUM, + htonl(helper->expect_class_max))) + goto nla_put_failure; + + for (i=0; i<helper->expect_class_max; i++) { + nest_parms2 = nla_nest_start(skb, + (NFCTH_POLICY_SET+i) | NLA_F_NESTED); + if (nest_parms2 == NULL) + goto nla_put_failure; + + if (nla_put_string(skb, NFCTH_POLICY_NAME, + helper->expect_policy[i].name)) + goto nla_put_failure; + + if (nla_put_be32(skb, NFCTH_POLICY_EXPECT_MAX, + htonl(helper->expect_policy[i].max_expected))) + goto nla_put_failure; + + if (nla_put_be32(skb, NFCTH_POLICY_EXPECT_TIMEOUT, + htonl(helper->expect_policy[i].timeout))) + goto nla_put_failure; + + nla_nest_end(skb, nest_parms2); + } + nla_nest_end(skb, nest_parms1); + return 0; + +nla_put_failure: + return -1; +} + +static int +nfnl_cthelper_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, + int event, struct nf_conntrack_helper *helper) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + unsigned int flags = pid ? NLM_F_MULTI : 0; + int status; + + event |= NFNL_SUBSYS_CTHELPER << 8; + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + if (nlh == NULL) + goto nlmsg_failure; + + nfmsg = nlmsg_data(nlh); + nfmsg->nfgen_family = AF_UNSPEC; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = 0; + + if (nla_put_string(skb, NFCTH_NAME, helper->name)) + goto nla_put_failure; + + if (nla_put_be32(skb, NFCTH_QUEUE_NUM, htonl(helper->queue_num))) + goto nla_put_failure; + + if (nfnl_cthelper_dump_tuple(skb, helper) < 0) + goto nla_put_failure; + + if (nfnl_cthelper_dump_policy(skb, helper) < 0) + goto nla_put_failure; + + if (nla_put_be32(skb, NFCTH_PRIV_DATA_LEN, htonl(helper->data_len))) + goto nla_put_failure; + + if (helper->flags & NF_CT_HELPER_F_CONFIGURED) + status = NFCT_HELPER_STATUS_ENABLED; + else + status = NFCT_HELPER_STATUS_DISABLED; + + if (nla_put_be32(skb, NFCTH_STATUS, htonl(status))) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + return skb->len; + +nlmsg_failure: +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -1; +} + +static int +nfnl_cthelper_dump_table(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct nf_conntrack_helper *cur, *last; + struct hlist_node *n; + + rcu_read_lock(); + last = (struct nf_conntrack_helper *)cb->args[1]; + for (; cb->args[0] < nf_ct_helper_hsize; cb->args[0]++) { +restart: + hlist_for_each_entry_rcu(cur, n, + &nf_ct_helper_hash[cb->args[0]], hnode) { + + /* skip non-userspace conntrack helpers. */ + if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) + continue; + + if (cb->args[1]) { + if (cur != last) + continue; + cb->args[1] = 0; + } + if (nfnl_cthelper_fill_info(skb, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + NFNL_MSG_TYPE(cb->nlh->nlmsg_type), + NFNL_MSG_CTHELPER_NEW, cur) < 0) { + cb->args[1] = (unsigned long)cur; + goto out; + } + } + } + if (cb->args[1]) { + cb->args[1] = 0; + goto restart; + } +out: + rcu_read_unlock(); + return skb->len; +} + +static int +nfnl_cthelper_get(struct sock *nfnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, const struct nlattr * const tb[]) +{ + int ret = -ENOENT, i; + struct nf_conntrack_helper *cur; + struct hlist_node *n; + struct sk_buff *skb2; + char *helper_name = NULL; + struct nf_conntrack_tuple tuple; + bool tuple_set = false; + + if (nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = nfnl_cthelper_dump_table, + }; + return netlink_dump_start(nfnl, skb, nlh, &c); + } + + if (tb[NFCTH_NAME]) + helper_name = nla_data(tb[NFCTH_NAME]); + + if (tb[NFCTH_TUPLE]) { + ret = nfnl_cthelper_parse_tuple(&tuple, tb[NFCTH_TUPLE]); + if (ret < 0) + return ret; + + tuple_set = true; + } + + for (i = 0; i < nf_ct_helper_hsize; i++) { + hlist_for_each_entry_rcu(cur, n, &nf_ct_helper_hash[i], hnode) { + + /* skip non-userspace conntrack helpers. */ + if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) + continue; + + if (helper_name && strncmp(cur->name, helper_name, + NF_CT_HELPER_NAME_LEN) != 0) { + continue; + } + if (tuple_set && + (tuple.src.l3num != cur->tuple.src.l3num || + tuple.dst.protonum != cur->tuple.dst.protonum)) + continue; + + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb2 == NULL) { + ret = -ENOMEM; + break; + } + + ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).pid, + nlh->nlmsg_seq, + NFNL_MSG_TYPE(nlh->nlmsg_type), + NFNL_MSG_CTHELPER_NEW, cur); + if (ret <= 0) { + kfree_skb(skb2); + break; + } + + ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).pid, + MSG_DONTWAIT); + if (ret > 0) + ret = 0; + + /* this avoids a loop in nfnetlink. */ + return ret == -EAGAIN ? -ENOBUFS : ret; + } + } + return ret; +} + +static int +nfnl_cthelper_del(struct sock *nfnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, const struct nlattr * const tb[]) +{ + char *helper_name = NULL; + struct nf_conntrack_helper *cur; + struct hlist_node *n, *tmp; + struct nf_conntrack_tuple tuple; + bool tuple_set = false, found = false; + int i, j = 0, ret; + + if (tb[NFCTH_NAME]) + helper_name = nla_data(tb[NFCTH_NAME]); + + if (tb[NFCTH_TUPLE]) { + ret = nfnl_cthelper_parse_tuple(&tuple, tb[NFCTH_TUPLE]); + if (ret < 0) + return ret; + + tuple_set = true; + } + + for (i = 0; i < nf_ct_helper_hsize; i++) { + hlist_for_each_entry_safe(cur, n, tmp, &nf_ct_helper_hash[i], + hnode) { + /* skip non-userspace conntrack helpers. */ + if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) + continue; + + j++; + + if (helper_name && strncmp(cur->name, helper_name, + NF_CT_HELPER_NAME_LEN) != 0) { + continue; + } + if (tuple_set && + (tuple.src.l3num != cur->tuple.src.l3num || + tuple.dst.protonum != cur->tuple.dst.protonum)) + continue; + + found = true; + nf_conntrack_helper_unregister(cur); + } + } + /* Make sure we return success if we flush and there is no helpers */ + return (found || j == 0) ? 0 : -ENOENT; +} + +static const struct nla_policy nfnl_cthelper_policy[NFCTH_MAX+1] = { + [NFCTH_NAME] = { .type = NLA_NUL_STRING, + .len = NF_CT_HELPER_NAME_LEN-1 }, + [NFCTH_QUEUE_NUM] = { .type = NLA_U32, }, +}; + +static const struct nfnl_callback nfnl_cthelper_cb[NFNL_MSG_CTHELPER_MAX] = { + [NFNL_MSG_CTHELPER_NEW] = { .call = nfnl_cthelper_new, + .attr_count = NFCTH_MAX, + .policy = nfnl_cthelper_policy }, + [NFNL_MSG_CTHELPER_GET] = { .call = nfnl_cthelper_get, + .attr_count = NFCTH_MAX, + .policy = nfnl_cthelper_policy }, + [NFNL_MSG_CTHELPER_DEL] = { .call = nfnl_cthelper_del, + .attr_count = NFCTH_MAX, + .policy = nfnl_cthelper_policy }, +}; + +static const struct nfnetlink_subsystem nfnl_cthelper_subsys = { + .name = "cthelper", + .subsys_id = NFNL_SUBSYS_CTHELPER, + .cb_count = NFNL_MSG_CTHELPER_MAX, + .cb = nfnl_cthelper_cb, +}; + +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTHELPER); + +static int __init nfnl_cthelper_init(void) +{ + int ret; + + ret = nfnetlink_subsys_register(&nfnl_cthelper_subsys); + if (ret < 0) { + pr_err("nfnl_cthelper: cannot register with nfnetlink.\n"); + goto err_out; + } + return 0; +err_out: + return ret; +} + +static void __exit nfnl_cthelper_exit(void) +{ + struct nf_conntrack_helper *cur; + struct hlist_node *n, *tmp; + int i; + + nfnetlink_subsys_unregister(&nfnl_cthelper_subsys); + + for (i=0; i<nf_ct_helper_hsize; i++) { + hlist_for_each_entry_safe(cur, n, tmp, &nf_ct_helper_hash[i], + hnode) { + /* skip non-userspace conntrack helpers. */ + if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) + continue; + + nf_conntrack_helper_unregister(cur); + } + } +} + +module_init(nfnl_cthelper_init); +module_exit(nfnl_cthelper_exit); diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 3e655288d1d..cdecbc8fe96 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -49,8 +49,9 @@ static const struct nla_policy cttimeout_nla_policy[CTA_TIMEOUT_MAX+1] = { static int ctnl_timeout_parse_policy(struct ctnl_timeout *timeout, - struct nf_conntrack_l4proto *l4proto, - const struct nlattr *attr) + struct nf_conntrack_l4proto *l4proto, + struct net *net, + const struct nlattr *attr) { int ret = 0; @@ -60,7 +61,8 @@ ctnl_timeout_parse_policy(struct ctnl_timeout *timeout, nla_parse_nested(tb, l4proto->ctnl_timeout.nlattr_max, attr, l4proto->ctnl_timeout.nla_policy); - ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, &timeout->data); + ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, net, + &timeout->data); } return ret; } @@ -74,6 +76,7 @@ cttimeout_new_timeout(struct sock *ctnl, struct sk_buff *skb, __u8 l4num; struct nf_conntrack_l4proto *l4proto; struct ctnl_timeout *timeout, *matching = NULL; + struct net *net = sock_net(skb->sk); char *name; int ret; @@ -117,7 +120,7 @@ cttimeout_new_timeout(struct sock *ctnl, struct sk_buff *skb, goto err_proto_put; } - ret = ctnl_timeout_parse_policy(matching, l4proto, + ret = ctnl_timeout_parse_policy(matching, l4proto, net, cda[CTA_TIMEOUT_DATA]); return ret; } @@ -132,7 +135,7 @@ cttimeout_new_timeout(struct sock *ctnl, struct sk_buff *skb, goto err_proto_put; } - ret = ctnl_timeout_parse_policy(timeout, l4proto, + ret = ctnl_timeout_parse_policy(timeout, l4proto, net, cda[CTA_TIMEOUT_DATA]); if (ret < 0) goto err; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 3c3cfc0cc9b..14e2f390314 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -326,18 +326,20 @@ __nfulnl_send(struct nfulnl_instance *inst) { int status = -1; - if (inst->qlen > 1) - NLMSG_PUT(inst->skb, 0, 0, - NLMSG_DONE, - sizeof(struct nfgenmsg)); - + if (inst->qlen > 1) { + struct nlmsghdr *nlh = nlmsg_put(inst->skb, 0, 0, + NLMSG_DONE, + sizeof(struct nfgenmsg), + 0); + if (!nlh) + goto out; + } status = nfnetlink_unicast(inst->skb, &init_net, inst->peer_pid, MSG_DONTWAIT); inst->qlen = 0; inst->skb = NULL; - -nlmsg_failure: +out: return status; } @@ -380,10 +382,12 @@ __build_packet_message(struct nfulnl_instance *inst, struct nfgenmsg *nfmsg; sk_buff_data_t old_tail = inst->skb->tail; - nlh = NLMSG_PUT(inst->skb, 0, 0, + nlh = nlmsg_put(inst->skb, 0, 0, NFNL_SUBSYS_ULOG << 8 | NFULNL_MSG_PACKET, - sizeof(struct nfgenmsg)); - nfmsg = NLMSG_DATA(nlh); + sizeof(struct nfgenmsg), 0); + if (!nlh) + return -1; + nfmsg = nlmsg_data(nlh); nfmsg->nfgen_family = pf; nfmsg->version = NFNETLINK_V0; nfmsg->res_id = htons(inst->group_num); @@ -476,7 +480,7 @@ __build_packet_message(struct nfulnl_instance *inst, } if (indev && skb_mac_header_was_set(skb)) { - if (nla_put_be32(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)) || + if (nla_put_be16(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)) || nla_put_be16(inst->skb, NFULA_HWLEN, htons(skb->dev->hard_header_len)) || nla_put(inst->skb, NFULA_HWHEADER, skb->dev->hard_header_len, @@ -526,7 +530,7 @@ __build_packet_message(struct nfulnl_instance *inst, if (skb_tailroom(inst->skb) < nla_total_size(data_len)) { printk(KERN_WARNING "nfnetlink_log: no tailroom!\n"); - goto nlmsg_failure; + return -1; } nla = (struct nlattr *)skb_put(inst->skb, nla_total_size(data_len)); @@ -540,7 +544,6 @@ __build_packet_message(struct nfulnl_instance *inst, nlh->nlmsg_len = inst->skb->tail - old_tail; return 0; -nlmsg_failure: nla_put_failure: PRINTR(KERN_ERR "nfnetlink_log: error creating log nlmsg\n"); return -1; @@ -745,7 +748,7 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nfula[]) { - struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int16_t group_num = ntohs(nfmsg->res_id); struct nfulnl_instance *inst; struct nfulnl_msg_config_cmd *cmd = NULL; @@ -993,8 +996,10 @@ static int __init nfnetlink_log_init(void) #ifdef CONFIG_PROC_FS if (!proc_create("nfnetlink_log", 0440, - proc_net_netfilter, &nful_file_ops)) + proc_net_netfilter, &nful_file_ops)) { + status = -ENOMEM; goto cleanup_logger; + } #endif return status; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue_core.c index 4162437b836..c0496a55ad0 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -30,6 +30,7 @@ #include <linux/list.h> #include <net/sock.h> #include <net/netfilter/nf_queue.h> +#include <net/netfilter/nfnetlink_queue.h> #include <linux/atomic.h> @@ -52,6 +53,7 @@ struct nfqnl_instance { u_int16_t queue_num; /* number of this queue */ u_int8_t copy_mode; + u_int32_t flags; /* Set using NFQA_CFG_FLAGS */ /* * Following fields are dirtied for each queued packet, * keep them in same cache line if possible. @@ -232,6 +234,8 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, struct sk_buff *entskb = entry->skb; struct net_device *indev; struct net_device *outdev; + struct nf_conn *ct = NULL; + enum ip_conntrack_info uninitialized_var(ctinfo); size = NLMSG_SPACE(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfqnl_msg_packet_hdr)) @@ -265,16 +269,22 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, break; } + if (queue->flags & NFQA_CFG_F_CONNTRACK) + ct = nfqnl_ct_get(entskb, &size, &ctinfo); skb = alloc_skb(size, GFP_ATOMIC); if (!skb) - goto nlmsg_failure; + return NULL; old_tail = skb->tail; - nlh = NLMSG_PUT(skb, 0, 0, + nlh = nlmsg_put(skb, 0, 0, NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET, - sizeof(struct nfgenmsg)); - nfmsg = NLMSG_DATA(nlh); + sizeof(struct nfgenmsg), 0); + if (!nlh) { + kfree_skb(skb); + return NULL; + } + nfmsg = nlmsg_data(nlh); nfmsg->nfgen_family = entry->pf; nfmsg->version = NFNETLINK_V0; nfmsg->res_id = htons(queue->queue_num); @@ -377,7 +387,8 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, if (skb_tailroom(skb) < nla_total_size(data_len)) { printk(KERN_WARNING "nf_queue: no tailroom!\n"); - goto nlmsg_failure; + kfree_skb(skb); + return NULL; } nla = (struct nlattr *)skb_put(skb, nla_total_size(data_len)); @@ -388,10 +399,12 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, BUG(); } + if (ct && nfqnl_ct_put(skb, ct, ctinfo) < 0) + goto nla_put_failure; + nlh->nlmsg_len = skb->tail - old_tail; return skb; -nlmsg_failure: nla_put_failure: if (skb) kfree_skb(skb); @@ -406,6 +419,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) struct nfqnl_instance *queue; int err = -ENOBUFS; __be32 *packet_id_ptr; + int failopen = 0; /* rcu_read_lock()ed by nf_hook_slow() */ queue = instance_lookup(queuenum); @@ -431,9 +445,14 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) goto err_out_free_nskb; } if (queue->queue_total >= queue->queue_maxlen) { - queue->queue_dropped++; - net_warn_ratelimited("nf_queue: full at %d entries, dropping packets(s)\n", - queue->queue_total); + if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { + failopen = 1; + err = 0; + } else { + queue->queue_dropped++; + net_warn_ratelimited("nf_queue: full at %d entries, dropping packets(s)\n", + queue->queue_total); + } goto err_out_free_nskb; } entry->id = ++queue->id_sequence; @@ -455,17 +474,17 @@ err_out_free_nskb: kfree_skb(nskb); err_out_unlock: spin_unlock_bh(&queue->lock); + if (failopen) + nf_reinject(entry, NF_ACCEPT); err_out: return err; } static int -nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e) +nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e, int diff) { struct sk_buff *nskb; - int diff; - diff = data_len - e->skb->len; if (diff < 0) { if (pskb_trim(e->skb, data_len)) return -ENOMEM; @@ -623,6 +642,7 @@ static const struct nla_policy nfqa_verdict_policy[NFQA_MAX+1] = { [NFQA_VERDICT_HDR] = { .len = sizeof(struct nfqnl_msg_verdict_hdr) }, [NFQA_MARK] = { .type = NLA_U32 }, [NFQA_PAYLOAD] = { .type = NLA_UNSPEC }, + [NFQA_CT] = { .type = NLA_UNSPEC }, }; static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = { @@ -670,7 +690,7 @@ nfqnl_recv_verdict_batch(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nfqa[]) { - struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nf_queue_entry *entry, *tmp; unsigned int verdict, maxid; struct nfqnl_msg_verdict_hdr *vhdr; @@ -716,13 +736,15 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nfqa[]) { - struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int16_t queue_num = ntohs(nfmsg->res_id); struct nfqnl_msg_verdict_hdr *vhdr; struct nfqnl_instance *queue; unsigned int verdict; struct nf_queue_entry *entry; + enum ip_conntrack_info uninitialized_var(ctinfo); + struct nf_conn *ct = NULL; queue = instance_lookup(queue_num); if (!queue) @@ -741,11 +763,22 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, if (entry == NULL) return -ENOENT; + rcu_read_lock(); + if (nfqa[NFQA_CT] && (queue->flags & NFQA_CFG_F_CONNTRACK)) + ct = nfqnl_ct_parse(entry->skb, nfqa[NFQA_CT], &ctinfo); + if (nfqa[NFQA_PAYLOAD]) { + u16 payload_len = nla_len(nfqa[NFQA_PAYLOAD]); + int diff = payload_len - entry->skb->len; + if (nfqnl_mangle(nla_data(nfqa[NFQA_PAYLOAD]), - nla_len(nfqa[NFQA_PAYLOAD]), entry) < 0) + payload_len, entry, diff) < 0) verdict = NF_DROP; + + if (ct) + nfqnl_ct_seq_adjust(skb, ct, ctinfo, diff); } + rcu_read_unlock(); if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK])); @@ -777,7 +810,7 @@ nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nfqa[]) { - struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int16_t queue_num = ntohs(nfmsg->res_id); struct nfqnl_instance *queue; struct nfqnl_msg_config_cmd *cmd = NULL; @@ -858,6 +891,36 @@ nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb, spin_unlock_bh(&queue->lock); } + if (nfqa[NFQA_CFG_FLAGS]) { + __u32 flags, mask; + + if (!queue) { + ret = -ENODEV; + goto err_out_unlock; + } + + if (!nfqa[NFQA_CFG_MASK]) { + /* A mask is needed to specify which flags are being + * changed. + */ + ret = -EINVAL; + goto err_out_unlock; + } + + flags = ntohl(nla_get_be32(nfqa[NFQA_CFG_FLAGS])); + mask = ntohl(nla_get_be32(nfqa[NFQA_CFG_MASK])); + + if (flags >= NFQA_CFG_F_MAX) { + ret = -EOPNOTSUPP; + goto err_out_unlock; + } + + spin_lock_bh(&queue->lock); + queue->flags &= ~mask; + queue->flags |= flags & mask; + spin_unlock_bh(&queue->lock); + } + err_out_unlock: rcu_read_unlock(); return ret; diff --git a/net/netfilter/nfnetlink_queue_ct.c b/net/netfilter/nfnetlink_queue_ct.c new file mode 100644 index 00000000000..ab61d66bc0b --- /dev/null +++ b/net/netfilter/nfnetlink_queue_ct.c @@ -0,0 +1,98 @@ +/* + * (C) 2012 by Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/skbuff.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_queue.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nfnetlink_queue.h> + +struct nf_conn *nfqnl_ct_get(struct sk_buff *entskb, size_t *size, + enum ip_conntrack_info *ctinfo) +{ + struct nfq_ct_hook *nfq_ct; + struct nf_conn *ct; + + /* rcu_read_lock()ed by __nf_queue already. */ + nfq_ct = rcu_dereference(nfq_ct_hook); + if (nfq_ct == NULL) + return NULL; + + ct = nf_ct_get(entskb, ctinfo); + if (ct) { + if (!nf_ct_is_untracked(ct)) + *size += nfq_ct->build_size(ct); + else + ct = NULL; + } + return ct; +} + +struct nf_conn * +nfqnl_ct_parse(const struct sk_buff *skb, const struct nlattr *attr, + enum ip_conntrack_info *ctinfo) +{ + struct nfq_ct_hook *nfq_ct; + struct nf_conn *ct; + + /* rcu_read_lock()ed by __nf_queue already. */ + nfq_ct = rcu_dereference(nfq_ct_hook); + if (nfq_ct == NULL) + return NULL; + + ct = nf_ct_get(skb, ctinfo); + if (ct && !nf_ct_is_untracked(ct)) + nfq_ct->parse(attr, ct); + + return ct; +} + +int nfqnl_ct_put(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ + struct nfq_ct_hook *nfq_ct; + struct nlattr *nest_parms; + u_int32_t tmp; + + nfq_ct = rcu_dereference(nfq_ct_hook); + if (nfq_ct == NULL) + return 0; + + nest_parms = nla_nest_start(skb, NFQA_CT | NLA_F_NESTED); + if (!nest_parms) + goto nla_put_failure; + + if (nfq_ct->build(skb, ct) < 0) + goto nla_put_failure; + + nla_nest_end(skb, nest_parms); + + tmp = ctinfo; + if (nla_put_be32(skb, NFQA_CT_INFO, htonl(tmp))) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, int diff) +{ + struct nfq_ct_nat_hook *nfq_nat_ct; + + nfq_nat_ct = rcu_dereference(nfq_ct_nat_hook); + if (nfq_nat_ct == NULL) + return; + + if ((ct->status & IPS_NAT_MASK) && diff) + nfq_nat_ct->seq_adjust(skb, ct, ctinfo, diff); +} diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index a51de9b052b..116018560c6 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -112,6 +112,8 @@ static int xt_ct_tg_check_v0(const struct xt_tgchk_param *par) goto err3; if (info->helper[0]) { + struct nf_conntrack_helper *helper; + ret = -ENOENT; proto = xt_ct_find_proto(par); if (!proto) { @@ -120,19 +122,21 @@ static int xt_ct_tg_check_v0(const struct xt_tgchk_param *par) goto err3; } - ret = -ENOMEM; - help = nf_ct_helper_ext_add(ct, GFP_KERNEL); - if (help == NULL) - goto err3; - ret = -ENOENT; - help->helper = nf_conntrack_helper_try_module_get(info->helper, - par->family, - proto); - if (help->helper == NULL) { + helper = nf_conntrack_helper_try_module_get(info->helper, + par->family, + proto); + if (helper == NULL) { pr_info("No such helper \"%s\"\n", info->helper); goto err3; } + + ret = -ENOMEM; + help = nf_ct_helper_ext_add(ct, helper, GFP_KERNEL); + if (help == NULL) + goto err3; + + help->helper = helper; } __set_bit(IPS_TEMPLATE_BIT, &ct->status); @@ -202,6 +206,8 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) goto err3; if (info->helper[0]) { + struct nf_conntrack_helper *helper; + ret = -ENOENT; proto = xt_ct_find_proto(par); if (!proto) { @@ -210,19 +216,21 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) goto err3; } - ret = -ENOMEM; - help = nf_ct_helper_ext_add(ct, GFP_KERNEL); - if (help == NULL) - goto err3; - ret = -ENOENT; - help->helper = nf_conntrack_helper_try_module_get(info->helper, - par->family, - proto); - if (help->helper == NULL) { + helper = nf_conntrack_helper_try_module_get(info->helper, + par->family, + proto); + if (helper == NULL) { pr_info("No such helper \"%s\"\n", info->helper); goto err3; } + + ret = -ENOMEM; + help = nf_ct_helper_ext_add(ct, helper, GFP_KERNEL); + if (help == NULL) + goto err3; + + help->helper = helper; } #ifdef CONFIG_NF_CONNTRACK_TIMEOUT diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index 95237c89607..7babe7d6871 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -41,26 +41,36 @@ nfqueue_tg(struct sk_buff *skb, const struct xt_action_param *par) static u32 hash_v4(const struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); - __be32 ipaddr; /* packets in either direction go into same queue */ - ipaddr = iph->saddr ^ iph->daddr; + if (iph->saddr < iph->daddr) + return jhash_3words((__force u32)iph->saddr, + (__force u32)iph->daddr, iph->protocol, jhash_initval); - return jhash_2words((__force u32)ipaddr, iph->protocol, jhash_initval); + return jhash_3words((__force u32)iph->daddr, + (__force u32)iph->saddr, iph->protocol, jhash_initval); } #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) static u32 hash_v6(const struct sk_buff *skb) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); - __be32 addr[4]; + u32 a, b, c; + + if (ip6h->saddr.s6_addr32[3] < ip6h->daddr.s6_addr32[3]) { + a = (__force u32) ip6h->saddr.s6_addr32[3]; + b = (__force u32) ip6h->daddr.s6_addr32[3]; + } else { + b = (__force u32) ip6h->saddr.s6_addr32[3]; + a = (__force u32) ip6h->daddr.s6_addr32[3]; + } - addr[0] = ip6h->saddr.s6_addr32[0] ^ ip6h->daddr.s6_addr32[0]; - addr[1] = ip6h->saddr.s6_addr32[1] ^ ip6h->daddr.s6_addr32[1]; - addr[2] = ip6h->saddr.s6_addr32[2] ^ ip6h->daddr.s6_addr32[2]; - addr[3] = ip6h->saddr.s6_addr32[3] ^ ip6h->daddr.s6_addr32[3]; + if (ip6h->saddr.s6_addr32[1] < ip6h->daddr.s6_addr32[1]) + c = (__force u32) ip6h->saddr.s6_addr32[1]; + else + c = (__force u32) ip6h->daddr.s6_addr32[1]; - return jhash2((__force u32 *)addr, ARRAY_SIZE(addr), jhash_initval); + return jhash_3words(a, b, c, jhash_initval); } #endif diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 146033a86de..d7f195388f6 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -69,7 +69,7 @@ tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) } /** - * tproxy_handle_time_wait4() - handle IPv4 TCP TIME_WAIT reopen redirections + * tproxy_handle_time_wait4 - handle IPv4 TCP TIME_WAIT reopen redirections * @skb: The skb being processed. * @laddr: IPv4 address to redirect to or zero. * @lport: TCP port to redirect to or zero. @@ -220,7 +220,7 @@ tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr, } /** - * tproxy_handle_time_wait6() - handle IPv6 TCP TIME_WAIT reopen redirections + * tproxy_handle_time_wait6 - handle IPv6 TCP TIME_WAIT reopen redirections * @skb: The skb being processed. * @tproto: Transport protocol. * @thoff: Transport protocol header offset. diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index c6d5a83450c..70b5591a258 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -274,38 +274,25 @@ static void connlimit_mt_destroy(const struct xt_mtdtor_param *par) kfree(info->data); } -static struct xt_match connlimit_mt_reg[] __read_mostly = { - { - .name = "connlimit", - .revision = 0, - .family = NFPROTO_UNSPEC, - .checkentry = connlimit_mt_check, - .match = connlimit_mt, - .matchsize = sizeof(struct xt_connlimit_info), - .destroy = connlimit_mt_destroy, - .me = THIS_MODULE, - }, - { - .name = "connlimit", - .revision = 1, - .family = NFPROTO_UNSPEC, - .checkentry = connlimit_mt_check, - .match = connlimit_mt, - .matchsize = sizeof(struct xt_connlimit_info), - .destroy = connlimit_mt_destroy, - .me = THIS_MODULE, - }, +static struct xt_match connlimit_mt_reg __read_mostly = { + .name = "connlimit", + .revision = 1, + .family = NFPROTO_UNSPEC, + .checkentry = connlimit_mt_check, + .match = connlimit_mt, + .matchsize = sizeof(struct xt_connlimit_info), + .destroy = connlimit_mt_destroy, + .me = THIS_MODULE, }; static int __init connlimit_mt_init(void) { - return xt_register_matches(connlimit_mt_reg, - ARRAY_SIZE(connlimit_mt_reg)); + return xt_register_match(&connlimit_mt_reg); } static void __exit connlimit_mt_exit(void) { - xt_unregister_matches(connlimit_mt_reg, ARRAY_SIZE(connlimit_mt_reg)); + xt_unregister_match(&connlimit_mt_reg); } module_init(connlimit_mt_init); diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index fc0d6dbe5d1..ae2ad1eec8d 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -75,6 +75,7 @@ struct recent_entry { struct recent_table { struct list_head list; char name[XT_RECENT_NAME_LEN]; + union nf_inet_addr mask; unsigned int refcnt; unsigned int entries; struct list_head lru_list; @@ -228,10 +229,10 @@ recent_mt(const struct sk_buff *skb, struct xt_action_param *par) { struct net *net = dev_net(par->in ? par->in : par->out); struct recent_net *recent_net = recent_pernet(net); - const struct xt_recent_mtinfo *info = par->matchinfo; + const struct xt_recent_mtinfo_v1 *info = par->matchinfo; struct recent_table *t; struct recent_entry *e; - union nf_inet_addr addr = {}; + union nf_inet_addr addr = {}, addr_mask; u_int8_t ttl; bool ret = info->invert; @@ -261,12 +262,15 @@ recent_mt(const struct sk_buff *skb, struct xt_action_param *par) spin_lock_bh(&recent_lock); t = recent_table_lookup(recent_net, info->name); - e = recent_entry_lookup(t, &addr, par->family, + + nf_inet_addr_mask(&addr, &addr_mask, &t->mask); + + e = recent_entry_lookup(t, &addr_mask, par->family, (info->check_set & XT_RECENT_TTL) ? ttl : 0); if (e == NULL) { if (!(info->check_set & XT_RECENT_SET)) goto out; - e = recent_entry_init(t, &addr, par->family, ttl); + e = recent_entry_init(t, &addr_mask, par->family, ttl); if (e == NULL) par->hotdrop = true; ret = !ret; @@ -306,10 +310,10 @@ out: return ret; } -static int recent_mt_check(const struct xt_mtchk_param *par) +static int recent_mt_check(const struct xt_mtchk_param *par, + const struct xt_recent_mtinfo_v1 *info) { struct recent_net *recent_net = recent_pernet(par->net); - const struct xt_recent_mtinfo *info = par->matchinfo; struct recent_table *t; #ifdef CONFIG_PROC_FS struct proc_dir_entry *pde; @@ -361,6 +365,8 @@ static int recent_mt_check(const struct xt_mtchk_param *par) goto out; } t->refcnt = 1; + + memcpy(&t->mask, &info->mask, sizeof(t->mask)); strcpy(t->name, info->name); INIT_LIST_HEAD(&t->lru_list); for (i = 0; i < ip_list_hash_size; i++) @@ -385,10 +391,28 @@ out: return ret; } +static int recent_mt_check_v0(const struct xt_mtchk_param *par) +{ + const struct xt_recent_mtinfo_v0 *info_v0 = par->matchinfo; + struct xt_recent_mtinfo_v1 info_v1; + + /* Copy revision 0 structure to revision 1 */ + memcpy(&info_v1, info_v0, sizeof(struct xt_recent_mtinfo)); + /* Set default mask to ensure backward compatible behaviour */ + memset(info_v1.mask.all, 0xFF, sizeof(info_v1.mask.all)); + + return recent_mt_check(par, &info_v1); +} + +static int recent_mt_check_v1(const struct xt_mtchk_param *par) +{ + return recent_mt_check(par, par->matchinfo); +} + static void recent_mt_destroy(const struct xt_mtdtor_param *par) { struct recent_net *recent_net = recent_pernet(par->net); - const struct xt_recent_mtinfo *info = par->matchinfo; + const struct xt_recent_mtinfo_v1 *info = par->matchinfo; struct recent_table *t; mutex_lock(&recent_mutex); @@ -625,7 +649,7 @@ static struct xt_match recent_mt_reg[] __read_mostly = { .family = NFPROTO_IPV4, .match = recent_mt, .matchsize = sizeof(struct xt_recent_mtinfo), - .checkentry = recent_mt_check, + .checkentry = recent_mt_check_v0, .destroy = recent_mt_destroy, .me = THIS_MODULE, }, @@ -635,10 +659,30 @@ static struct xt_match recent_mt_reg[] __read_mostly = { .family = NFPROTO_IPV6, .match = recent_mt, .matchsize = sizeof(struct xt_recent_mtinfo), - .checkentry = recent_mt_check, + .checkentry = recent_mt_check_v0, + .destroy = recent_mt_destroy, + .me = THIS_MODULE, + }, + { + .name = "recent", + .revision = 1, + .family = NFPROTO_IPV4, + .match = recent_mt, + .matchsize = sizeof(struct xt_recent_mtinfo_v1), + .checkentry = recent_mt_check_v1, .destroy = recent_mt_destroy, .me = THIS_MODULE, }, + { + .name = "recent", + .revision = 1, + .family = NFPROTO_IPV6, + .match = recent_mt, + .matchsize = sizeof(struct xt_recent_mtinfo_v1), + .checkentry = recent_mt_check_v1, + .destroy = recent_mt_destroy, + .me = THIS_MODULE, + } }; static int __init recent_mt_init(void) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index b3025a603d5..527023823b5 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -80,6 +80,7 @@ struct netlink_sock { struct mutex *cb_mutex; struct mutex cb_def_mutex; void (*netlink_rcv)(struct sk_buff *skb); + void (*netlink_bind)(int group); struct module *module; }; @@ -124,6 +125,7 @@ struct netlink_table { unsigned int groups; struct mutex *cb_mutex; struct module *module; + void (*bind)(int group); int registered; }; @@ -444,6 +446,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, struct module *module = NULL; struct mutex *cb_mutex; struct netlink_sock *nlk; + void (*bind)(int group); int err = 0; sock->state = SS_UNCONNECTED; @@ -468,6 +471,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, else err = -EPROTONOSUPPORT; cb_mutex = nl_table[protocol].cb_mutex; + bind = nl_table[protocol].bind; netlink_unlock_table(); if (err < 0) @@ -483,6 +487,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, nlk = nlk_sk(sock->sk); nlk->module = module; + nlk->netlink_bind = bind; out: return err; @@ -683,6 +688,15 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, netlink_update_listeners(sk); netlink_table_ungrab(); + if (nlk->netlink_bind && nlk->groups[0]) { + int i; + + for (i=0; i<nlk->ngroups; i++) { + if (test_bit(i, nlk->groups)) + nlk->netlink_bind(i); + } + } + return 0; } @@ -1239,6 +1253,10 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, netlink_update_socket_mc(nlk, val, optname == NETLINK_ADD_MEMBERSHIP); netlink_table_ungrab(); + + if (nlk->netlink_bind) + nlk->netlink_bind(val); + err = 0; break; } @@ -1344,7 +1362,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, if (NULL == siocb->scm) siocb->scm = &scm; - err = scm_send(sock, msg, siocb->scm); + err = scm_send(sock, msg, siocb->scm, true); if (err < 0) return err; @@ -1355,7 +1373,8 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, dst_pid = addr->nl_pid; dst_group = ffs(addr->nl_groups); err = -EPERM; - if (dst_group && !netlink_capable(sock, NL_NONROOT_SEND)) + if ((dst_group || dst_pid) && + !netlink_capable(sock, NL_NONROOT_SEND)) goto out; } else { dst_pid = nlk->dst_pid; @@ -1503,14 +1522,16 @@ static void netlink_data_ready(struct sock *sk, int len) */ struct sock * -netlink_kernel_create(struct net *net, int unit, unsigned int groups, - void (*input)(struct sk_buff *skb), - struct mutex *cb_mutex, struct module *module) +netlink_kernel_create(struct net *net, int unit, + struct module *module, + struct netlink_kernel_cfg *cfg) { struct socket *sock; struct sock *sk; struct netlink_sock *nlk; struct listeners *listeners = NULL; + struct mutex *cb_mutex = cfg ? cfg->cb_mutex : NULL; + unsigned int groups; BUG_ON(!nl_table); @@ -1532,16 +1553,18 @@ netlink_kernel_create(struct net *net, int unit, unsigned int groups, sk = sock->sk; sk_change_net(sk, net); - if (groups < 32) + if (!cfg || cfg->groups < 32) groups = 32; + else + groups = cfg->groups; listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); if (!listeners) goto out_sock_release; sk->sk_data_ready = netlink_data_ready; - if (input) - nlk_sk(sk)->netlink_rcv = input; + if (cfg && cfg->input) + nlk_sk(sk)->netlink_rcv = cfg->input; if (netlink_insert(sk, net, 0)) goto out_sock_release; @@ -1555,6 +1578,7 @@ netlink_kernel_create(struct net *net, int unit, unsigned int groups, rcu_assign_pointer(nl_table[unit].listeners, listeners); nl_table[unit].cb_mutex = cb_mutex; nl_table[unit].module = module; + nl_table[unit].bind = cfg ? cfg->bind : NULL; nl_table[unit].registered = 1; } else { kfree(listeners); @@ -2124,6 +2148,7 @@ static void __init netlink_add_usersock_entry(void) rcu_assign_pointer(nl_table[NETLINK_USERSOCK].listeners, listeners); nl_table[NETLINK_USERSOCK].module = THIS_MODULE; nl_table[NETLINK_USERSOCK].registered = 1; + nl_table[NETLINK_USERSOCK].nl_nonroot = NL_NONROOT_SEND; netlink_table_ungrab(); } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 2cc7c1ee769..fda497412fc 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -33,7 +33,7 @@ void genl_unlock(void) } EXPORT_SYMBOL(genl_unlock); -#ifdef CONFIG_PROVE_LOCKING +#ifdef CONFIG_LOCKDEP int lockdep_genl_is_held(void) { return lockdep_is_held(&genl_mutex); @@ -504,7 +504,7 @@ EXPORT_SYMBOL(genl_unregister_family); * @pid: netlink pid the message is addressed to * @seq: sequence number (usually the one of the sender) * @family: generic netlink family - * @flags netlink message flags + * @flags: netlink message flags * @cmd: generic netlink command * * Returns pointer to user specific header @@ -915,10 +915,14 @@ static struct genl_multicast_group notify_grp = { static int __net_init genl_pernet_init(struct net *net) { + struct netlink_kernel_cfg cfg = { + .input = genl_rcv, + .cb_mutex = &genl_mutex, + }; + /* we'll bump the group number right afterwards */ - net->genl_sock = netlink_kernel_create(net, NETLINK_GENERIC, 0, - genl_rcv, &genl_mutex, - THIS_MODULE); + net->genl_sock = netlink_kernel_create(net, NETLINK_GENERIC, + THIS_MODULE, &cfg); if (!net->genl_sock && net_eq(net, &init_net)) panic("GENL: Cannot initialize generic netlink\n"); diff --git a/net/nfc/core.c b/net/nfc/core.c index 9f6ce011d35..ff749794bc5 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -29,6 +29,8 @@ #include <linux/slab.h> #include <linux/nfc.h> +#include <net/genetlink.h> + #include "nfc.h" #define VERSION "0.1" @@ -121,14 +123,14 @@ error: * The device remains polling for targets until a target is found or * the nfc_stop_poll function is called. */ -int nfc_start_poll(struct nfc_dev *dev, u32 protocols) +int nfc_start_poll(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols) { int rc; - pr_debug("dev_name=%s protocols=0x%x\n", - dev_name(&dev->dev), protocols); + pr_debug("dev_name %s initiator protocols 0x%x target protocols 0x%x\n", + dev_name(&dev->dev), im_protocols, tm_protocols); - if (!protocols) + if (!im_protocols && !tm_protocols) return -EINVAL; device_lock(&dev->dev); @@ -143,9 +145,11 @@ int nfc_start_poll(struct nfc_dev *dev, u32 protocols) goto error; } - rc = dev->ops->start_poll(dev, protocols); - if (!rc) + rc = dev->ops->start_poll(dev, im_protocols, tm_protocols); + if (!rc) { dev->polling = true; + dev->rf_mode = NFC_RF_NONE; + } error: device_unlock(&dev->dev); @@ -235,8 +239,10 @@ int nfc_dep_link_up(struct nfc_dev *dev, int target_index, u8 comm_mode) } rc = dev->ops->dep_link_up(dev, target, comm_mode, gb, gb_len); - if (!rc) + if (!rc) { dev->active_target = target; + dev->rf_mode = NFC_RF_INITIATOR; + } error: device_unlock(&dev->dev); @@ -264,11 +270,6 @@ int nfc_dep_link_down(struct nfc_dev *dev) goto error; } - if (dev->dep_rf_mode == NFC_RF_TARGET) { - rc = -EOPNOTSUPP; - goto error; - } - rc = dev->ops->dep_link_down(dev); if (!rc) { dev->dep_link_up = false; @@ -286,7 +287,6 @@ int nfc_dep_link_is_up(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode) { dev->dep_link_up = true; - dev->dep_rf_mode = rf_mode; nfc_llcp_mac_is_up(dev, target_idx, comm_mode, rf_mode); @@ -330,6 +330,7 @@ int nfc_activate_target(struct nfc_dev *dev, u32 target_idx, u32 protocol) rc = dev->ops->activate_target(dev, target, protocol); if (!rc) { dev->active_target = target; + dev->rf_mode = NFC_RF_INITIATOR; if (dev->ops->check_presence) mod_timer(&dev->check_pres_timer, jiffies + @@ -409,27 +410,30 @@ int nfc_data_exchange(struct nfc_dev *dev, u32 target_idx, struct sk_buff *skb, goto error; } - if (dev->active_target == NULL) { - rc = -ENOTCONN; - kfree_skb(skb); - goto error; - } + if (dev->rf_mode == NFC_RF_INITIATOR && dev->active_target != NULL) { + if (dev->active_target->idx != target_idx) { + rc = -EADDRNOTAVAIL; + kfree_skb(skb); + goto error; + } - if (dev->active_target->idx != target_idx) { - rc = -EADDRNOTAVAIL; + if (dev->ops->check_presence) + del_timer_sync(&dev->check_pres_timer); + + rc = dev->ops->im_transceive(dev, dev->active_target, skb, cb, + cb_context); + + if (!rc && dev->ops->check_presence) + mod_timer(&dev->check_pres_timer, jiffies + + msecs_to_jiffies(NFC_CHECK_PRES_FREQ_MS)); + } else if (dev->rf_mode == NFC_RF_TARGET && dev->ops->tm_send != NULL) { + rc = dev->ops->tm_send(dev, skb); + } else { + rc = -ENOTCONN; kfree_skb(skb); goto error; } - if (dev->ops->check_presence) - del_timer_sync(&dev->check_pres_timer); - - rc = dev->ops->data_exchange(dev, dev->active_target, skb, cb, - cb_context); - - if (!rc && dev->ops->check_presence) - mod_timer(&dev->check_pres_timer, jiffies + - msecs_to_jiffies(NFC_CHECK_PRES_FREQ_MS)); error: device_unlock(&dev->dev); @@ -447,6 +451,63 @@ int nfc_set_remote_general_bytes(struct nfc_dev *dev, u8 *gb, u8 gb_len) } EXPORT_SYMBOL(nfc_set_remote_general_bytes); +u8 *nfc_get_local_general_bytes(struct nfc_dev *dev, size_t *gb_len) +{ + pr_debug("dev_name=%s\n", dev_name(&dev->dev)); + + return nfc_llcp_general_bytes(dev, gb_len); +} +EXPORT_SYMBOL(nfc_get_local_general_bytes); + +int nfc_tm_data_received(struct nfc_dev *dev, struct sk_buff *skb) +{ + /* Only LLCP target mode for now */ + if (dev->dep_link_up == false) { + kfree_skb(skb); + return -ENOLINK; + } + + return nfc_llcp_data_received(dev, skb); +} +EXPORT_SYMBOL(nfc_tm_data_received); + +int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode, + u8 *gb, size_t gb_len) +{ + int rc; + + device_lock(&dev->dev); + + dev->polling = false; + + if (gb != NULL) { + rc = nfc_set_remote_general_bytes(dev, gb, gb_len); + if (rc < 0) + goto out; + } + + dev->rf_mode = NFC_RF_TARGET; + + if (protocol == NFC_PROTO_NFC_DEP_MASK) + nfc_dep_link_is_up(dev, 0, comm_mode, NFC_RF_TARGET); + + rc = nfc_genl_tm_activated(dev, protocol); + +out: + device_unlock(&dev->dev); + + return rc; +} +EXPORT_SYMBOL(nfc_tm_activated); + +int nfc_tm_deactivated(struct nfc_dev *dev) +{ + dev->dep_link_up = false; + + return nfc_genl_tm_deactivated(dev); +} +EXPORT_SYMBOL(nfc_tm_deactivated); + /** * nfc_alloc_send_skb - allocate a skb for data exchange responses * @@ -501,6 +562,8 @@ EXPORT_SYMBOL(nfc_alloc_recv_skb); * The device driver must call this function when one or many nfc targets * are found. After calling this function, the device driver must stop * polling for targets. + * NOTE: This function can be called with targets=NULL and n_targets=0 to + * notify a driver error, meaning that the polling operation cannot complete. * IMPORTANT: this function must not be called from an atomic context. * In addition, it must also not be called from a context that would prevent * the NFC Core to call other nfc ops entry point concurrently. @@ -512,23 +575,33 @@ int nfc_targets_found(struct nfc_dev *dev, pr_debug("dev_name=%s n_targets=%d\n", dev_name(&dev->dev), n_targets); - dev->polling = false; - for (i = 0; i < n_targets; i++) targets[i].idx = dev->target_next_idx++; device_lock(&dev->dev); + if (dev->polling == false) { + device_unlock(&dev->dev); + return 0; + } + + dev->polling = false; + dev->targets_generation++; kfree(dev->targets); - dev->targets = kmemdup(targets, n_targets * sizeof(struct nfc_target), - GFP_ATOMIC); + dev->targets = NULL; - if (!dev->targets) { - dev->n_targets = 0; - device_unlock(&dev->dev); - return -ENOMEM; + if (targets) { + dev->targets = kmemdup(targets, + n_targets * sizeof(struct nfc_target), + GFP_ATOMIC); + + if (!dev->targets) { + dev->n_targets = 0; + device_unlock(&dev->dev); + return -ENOMEM; + } } dev->n_targets = n_targets; @@ -592,6 +665,12 @@ int nfc_target_lost(struct nfc_dev *dev, u32 target_idx) } EXPORT_SYMBOL(nfc_target_lost); +inline void nfc_driver_failure(struct nfc_dev *dev, int err) +{ + nfc_targets_found(dev, NULL, 0); +} +EXPORT_SYMBOL(nfc_driver_failure); + static void nfc_release(struct device *d) { struct nfc_dev *dev = to_nfc_dev(d); @@ -678,7 +757,7 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, struct nfc_dev *dev; if (!ops->start_poll || !ops->stop_poll || !ops->activate_target || - !ops->deactivate_target || !ops->data_exchange) + !ops->deactivate_target || !ops->im_transceive) return NULL; if (!supported_protocols) @@ -847,3 +926,5 @@ MODULE_AUTHOR("Lauro Ramos Venancio <lauro.venancio@openbossa.org>"); MODULE_DESCRIPTION("NFC Core ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); +MODULE_ALIAS_NETPROTO(PF_NFC); +MODULE_ALIAS_GENL_FAMILY(NFC_GENL_NAME); diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c index 8729abf5f18..46362ef979d 100644 --- a/net/nfc/hci/command.c +++ b/net/nfc/hci/command.c @@ -28,26 +28,14 @@ #include "hci.h" -static int nfc_hci_result_to_errno(u8 result) -{ - switch (result) { - case NFC_HCI_ANY_OK: - return 0; - case NFC_HCI_ANY_E_TIMEOUT: - return -ETIMEDOUT; - default: - return -1; - } -} - -static void nfc_hci_execute_cb(struct nfc_hci_dev *hdev, u8 result, +static void nfc_hci_execute_cb(struct nfc_hci_dev *hdev, int err, struct sk_buff *skb, void *cb_data) { struct hcp_exec_waiter *hcp_ew = (struct hcp_exec_waiter *)cb_data; - pr_debug("HCI Cmd completed with HCI result=%d\n", result); + pr_debug("HCI Cmd completed with result=%d\n", err); - hcp_ew->exec_result = nfc_hci_result_to_errno(result); + hcp_ew->exec_result = err; if (hcp_ew->exec_result == 0) hcp_ew->result_skb = skb; else @@ -311,9 +299,9 @@ int nfc_hci_disconnect_all_gates(struct nfc_hci_dev *hdev) } EXPORT_SYMBOL(nfc_hci_disconnect_all_gates); -int nfc_hci_connect_gate(struct nfc_hci_dev *hdev, u8 dest_host, u8 dest_gate) +int nfc_hci_connect_gate(struct nfc_hci_dev *hdev, u8 dest_host, u8 dest_gate, + u8 pipe) { - u8 pipe = NFC_HCI_INVALID_PIPE; bool pipe_created = false; int r; @@ -322,6 +310,9 @@ int nfc_hci_connect_gate(struct nfc_hci_dev *hdev, u8 dest_host, u8 dest_gate) if (hdev->gate2pipe[dest_gate] != NFC_HCI_INVALID_PIPE) return -EADDRINUSE; + if (pipe != NFC_HCI_INVALID_PIPE) + goto pipe_is_open; + switch (dest_gate) { case NFC_HCI_LINK_MGMT_GATE: pipe = NFC_HCI_LINK_MGMT_PIPE; @@ -347,6 +338,7 @@ int nfc_hci_connect_gate(struct nfc_hci_dev *hdev, u8 dest_host, u8 dest_gate) return r; } +pipe_is_open: hdev->gate2pipe[dest_gate] = pipe; return 0; diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index e1a640d2b58..1ac7b3fac6c 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -32,6 +32,18 @@ /* Largest headroom needed for outgoing HCI commands */ #define HCI_CMDS_HEADROOM 1 +static int nfc_hci_result_to_errno(u8 result) +{ + switch (result) { + case NFC_HCI_ANY_OK: + return 0; + case NFC_HCI_ANY_E_TIMEOUT: + return -ETIME; + default: + return -1; + } +} + static void nfc_hci_msg_tx_work(struct work_struct *work) { struct nfc_hci_dev *hdev = container_of(work, struct nfc_hci_dev, @@ -46,7 +58,7 @@ static void nfc_hci_msg_tx_work(struct work_struct *work) if (timer_pending(&hdev->cmd_timer) == 0) { if (hdev->cmd_pending_msg->cb) hdev->cmd_pending_msg->cb(hdev, - NFC_HCI_ANY_E_TIMEOUT, + -ETIME, NULL, hdev-> cmd_pending_msg-> @@ -71,8 +83,7 @@ next_msg: kfree_skb(skb); skb_queue_purge(&msg->msg_frags); if (msg->cb) - msg->cb(hdev, NFC_HCI_ANY_E_NOK, NULL, - msg->cb_context); + msg->cb(hdev, r, NULL, msg->cb_context); kfree(msg); break; } @@ -116,20 +127,13 @@ static void nfc_hci_msg_rx_work(struct work_struct *work) } } -void nfc_hci_resp_received(struct nfc_hci_dev *hdev, u8 result, - struct sk_buff *skb) +static void __nfc_hci_cmd_completion(struct nfc_hci_dev *hdev, int err, + struct sk_buff *skb) { - mutex_lock(&hdev->msg_tx_mutex); - - if (hdev->cmd_pending_msg == NULL) { - kfree_skb(skb); - goto exit; - } - del_timer_sync(&hdev->cmd_timer); if (hdev->cmd_pending_msg->cb) - hdev->cmd_pending_msg->cb(hdev, result, skb, + hdev->cmd_pending_msg->cb(hdev, err, skb, hdev->cmd_pending_msg->cb_context); else kfree_skb(skb); @@ -138,6 +142,19 @@ void nfc_hci_resp_received(struct nfc_hci_dev *hdev, u8 result, hdev->cmd_pending_msg = NULL; queue_work(hdev->msg_tx_wq, &hdev->msg_tx_work); +} + +void nfc_hci_resp_received(struct nfc_hci_dev *hdev, u8 result, + struct sk_buff *skb) +{ + mutex_lock(&hdev->msg_tx_mutex); + + if (hdev->cmd_pending_msg == NULL) { + kfree_skb(skb); + goto exit; + } + + __nfc_hci_cmd_completion(hdev, nfc_hci_result_to_errno(result), skb); exit: mutex_unlock(&hdev->msg_tx_mutex); @@ -170,6 +187,7 @@ static int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate) struct nfc_target *targets; struct sk_buff *atqa_skb = NULL; struct sk_buff *sak_skb = NULL; + struct sk_buff *uid_skb = NULL; int r; pr_debug("from gate %d\n", gate); @@ -205,6 +223,19 @@ static int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate) targets->sens_res = be16_to_cpu(*(u16 *)atqa_skb->data); targets->sel_res = sak_skb->data[0]; + r = nfc_hci_get_param(hdev, NFC_HCI_RF_READER_A_GATE, + NFC_HCI_RF_READER_A_UID, &uid_skb); + if (r < 0) + goto exit; + + if (uid_skb->len == 0 || uid_skb->len > NFC_NFCID1_MAXSIZE) { + r = -EPROTO; + goto exit; + } + + memcpy(targets->nfcid1, uid_skb->data, uid_skb->len); + targets->nfcid1_len = uid_skb->len; + if (hdev->ops->complete_target_discovered) { r = hdev->ops->complete_target_discovered(hdev, gate, targets); @@ -213,7 +244,7 @@ static int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate) } break; case NFC_HCI_RF_READER_B_GATE: - targets->supported_protocols = NFC_PROTO_ISO14443_MASK; + targets->supported_protocols = NFC_PROTO_ISO14443_B_MASK; break; default: if (hdev->ops->target_from_gate) @@ -240,6 +271,7 @@ exit: kfree(targets); kfree_skb(atqa_skb); kfree_skb(sak_skb); + kfree_skb(uid_skb); return r; } @@ -298,15 +330,15 @@ static void nfc_hci_cmd_timeout(unsigned long data) } static int hci_dev_connect_gates(struct nfc_hci_dev *hdev, u8 gate_count, - u8 gates[]) + struct nfc_hci_gate *gates) { int r; - u8 *p = gates; while (gate_count--) { - r = nfc_hci_connect_gate(hdev, NFC_HCI_HOST_CONTROLLER_ID, *p); + r = nfc_hci_connect_gate(hdev, NFC_HCI_HOST_CONTROLLER_ID, + gates->gate, gates->pipe); if (r < 0) return r; - p++; + gates++; } return 0; @@ -316,14 +348,13 @@ static int hci_dev_session_init(struct nfc_hci_dev *hdev) { struct sk_buff *skb = NULL; int r; - u8 hci_gates[] = { /* NFC_HCI_ADMIN_GATE MUST be first */ - NFC_HCI_ADMIN_GATE, NFC_HCI_LOOPBACK_GATE, - NFC_HCI_ID_MGMT_GATE, NFC_HCI_LINK_MGMT_GATE, - NFC_HCI_RF_READER_B_GATE, NFC_HCI_RF_READER_A_GATE - }; + + if (hdev->init_data.gates[0].gate != NFC_HCI_ADMIN_GATE) + return -EPROTO; r = nfc_hci_connect_gate(hdev, NFC_HCI_HOST_CONTROLLER_ID, - NFC_HCI_ADMIN_GATE); + hdev->init_data.gates[0].gate, + hdev->init_data.gates[0].pipe); if (r < 0) goto exit; @@ -351,10 +382,6 @@ static int hci_dev_session_init(struct nfc_hci_dev *hdev) if (r < 0) goto exit; - r = hci_dev_connect_gates(hdev, sizeof(hci_gates), hci_gates); - if (r < 0) - goto disconnect_all; - r = hci_dev_connect_gates(hdev, hdev->init_data.gate_count, hdev->init_data.gates); if (r < 0) @@ -481,12 +508,13 @@ static int hci_dev_down(struct nfc_dev *nfc_dev) return 0; } -static int hci_start_poll(struct nfc_dev *nfc_dev, u32 protocols) +static int hci_start_poll(struct nfc_dev *nfc_dev, + u32 im_protocols, u32 tm_protocols) { struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev); if (hdev->ops->start_poll) - return hdev->ops->start_poll(hdev, protocols); + return hdev->ops->start_poll(hdev, im_protocols, tm_protocols); else return nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE, NFC_HCI_EVT_READER_REQUESTED, NULL, 0); @@ -511,9 +539,9 @@ static void hci_deactivate_target(struct nfc_dev *nfc_dev, { } -static int hci_data_exchange(struct nfc_dev *nfc_dev, struct nfc_target *target, - struct sk_buff *skb, data_exchange_cb_t cb, - void *cb_context) +static int hci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target, + struct sk_buff *skb, data_exchange_cb_t cb, + void *cb_context) { struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev); int r; @@ -579,7 +607,7 @@ static struct nfc_ops hci_nfc_ops = { .stop_poll = hci_stop_poll, .activate_target = hci_activate_target, .deactivate_target = hci_deactivate_target, - .data_exchange = hci_data_exchange, + .im_transceive = hci_transceive, .check_presence = hci_check_presence, }; @@ -682,13 +710,12 @@ EXPORT_SYMBOL(nfc_hci_register_device); void nfc_hci_unregister_device(struct nfc_hci_dev *hdev) { - struct hci_msg *msg; + struct hci_msg *msg, *n; skb_queue_purge(&hdev->rx_hcp_frags); skb_queue_purge(&hdev->msg_rx_queue); - while ((msg = list_first_entry(&hdev->msg_tx_queue, struct hci_msg, - msg_l)) != NULL) { + list_for_each_entry_safe(msg, n, &hdev->msg_tx_queue, msg_l) { list_del(&msg->msg_l); skb_queue_purge(&msg->msg_frags); kfree(msg); @@ -716,6 +743,27 @@ void *nfc_hci_get_clientdata(struct nfc_hci_dev *hdev) } EXPORT_SYMBOL(nfc_hci_get_clientdata); +static void nfc_hci_failure(struct nfc_hci_dev *hdev, int err) +{ + mutex_lock(&hdev->msg_tx_mutex); + + if (hdev->cmd_pending_msg == NULL) { + nfc_driver_failure(hdev->ndev, err); + goto exit; + } + + __nfc_hci_cmd_completion(hdev, err, NULL); + +exit: + mutex_unlock(&hdev->msg_tx_mutex); +} + +void nfc_hci_driver_failure(struct nfc_hci_dev *hdev, int err) +{ + nfc_hci_failure(hdev, err); +} +EXPORT_SYMBOL(nfc_hci_driver_failure); + void nfc_hci_recv_frame(struct nfc_hci_dev *hdev, struct sk_buff *skb) { struct hcp_packet *packet; @@ -726,16 +774,6 @@ void nfc_hci_recv_frame(struct nfc_hci_dev *hdev, struct sk_buff *skb) struct sk_buff *frag_skb; int msg_len; - if (skb == NULL) { - /* TODO ELa: lower layer had permanent failure, need to - * propagate that up - */ - - skb_queue_purge(&hdev->rx_hcp_frags); - - return; - } - packet = (struct hcp_packet *)skb->data; if ((packet->header & ~NFC_HCI_FRAGMENT) == 0) { skb_queue_tail(&hdev->rx_hcp_frags, skb); @@ -756,9 +794,8 @@ void nfc_hci_recv_frame(struct nfc_hci_dev *hdev, struct sk_buff *skb) hcp_skb = nfc_alloc_recv_skb(NFC_HCI_HCP_PACKET_HEADER_LEN + msg_len, GFP_KERNEL); if (hcp_skb == NULL) { - /* TODO ELa: cannot deliver HCP message. How to - * propagate error up? - */ + nfc_hci_failure(hdev, -ENOMEM); + return; } *skb_put(hcp_skb, NFC_HCI_HCP_PACKET_HEADER_LEN) = pipe; diff --git a/net/nfc/hci/hci.h b/net/nfc/hci/hci.h index 45f2fe4fd48..fa9a21e9223 100644 --- a/net/nfc/hci/hci.h +++ b/net/nfc/hci/hci.h @@ -37,10 +37,11 @@ struct hcp_packet { /* * HCI command execution completion callback. - * result will be one of the HCI response codes. - * skb contains the response data and must be disposed. + * result will be a standard linux error (may be converted from HCI response) + * skb contains the response data and must be disposed, or may be NULL if + * an error occured */ -typedef void (*hci_cmd_cb_t) (struct nfc_hci_dev *hdev, u8 result, +typedef void (*hci_cmd_cb_t) (struct nfc_hci_dev *hdev, int result, struct sk_buff *skb, void *cb_data); struct hcp_exec_waiter { @@ -131,9 +132,4 @@ void nfc_hci_hcp_message_rx(struct nfc_hci_dev *hdev, u8 pipe, u8 type, #define NFC_HCI_ANY_E_REG_ACCESS_DENIED 0x0a #define NFC_HCI_ANY_E_PIPE_ACCESS_DENIED 0x0b -/* Pipes */ -#define NFC_HCI_INVALID_PIPE 0x80 -#define NFC_HCI_LINK_MGMT_PIPE 0x00 -#define NFC_HCI_ADMIN_PIPE 0x01 - #endif /* __LOCAL_HCI_H */ diff --git a/net/nfc/hci/hcp.c b/net/nfc/hci/hcp.c index 7212cf2c578..f4dad1a8974 100644 --- a/net/nfc/hci/hcp.c +++ b/net/nfc/hci/hcp.c @@ -105,7 +105,7 @@ int nfc_hci_hcp_message_tx(struct nfc_hci_dev *hdev, u8 pipe, } mutex_lock(&hdev->msg_tx_mutex); - list_add_tail(&hdev->msg_tx_queue, &cmd->msg_l); + list_add_tail(&cmd->msg_l, &hdev->msg_tx_queue); mutex_unlock(&hdev->msg_tx_mutex); queue_work(hdev->msg_tx_wq, &hdev->msg_tx_work); diff --git a/net/nfc/hci/shdlc.c b/net/nfc/hci/shdlc.c index 5665dc6d893..6f840c18c89 100644 --- a/net/nfc/hci/shdlc.c +++ b/net/nfc/hci/shdlc.c @@ -340,15 +340,6 @@ static void nfc_shdlc_connect_complete(struct nfc_shdlc *shdlc, int r) shdlc->state = SHDLC_CONNECTED; } else { shdlc->state = SHDLC_DISCONNECTED; - - /* - * TODO: Could it be possible that there are pending - * executing commands that are waiting for connect to complete - * before they can be carried? As connect is a blocking - * operation, it would require that the userspace process can - * send commands on the same device from a second thread before - * the device is up. I don't think that is possible, is it? - */ } shdlc->connect_result = r; @@ -413,12 +404,12 @@ static void nfc_shdlc_rcv_u_frame(struct nfc_shdlc *shdlc, r = nfc_shdlc_connect_send_ua(shdlc); nfc_shdlc_connect_complete(shdlc, r); } - } else if (shdlc->state > SHDLC_NEGOCIATING) { + } else if (shdlc->state == SHDLC_CONNECTED) { /* - * TODO: Chip wants to reset link - * send ua, empty skb lists, reset counters - * propagate info to HCI layer + * Chip wants to reset link. This is unexpected and + * unsupported. */ + shdlc->hard_fault = -ECONNRESET; } break; case U_FRAME_UA: @@ -523,10 +514,6 @@ static void nfc_shdlc_handle_send_queue(struct nfc_shdlc *shdlc) r = shdlc->ops->xmit(shdlc, skb); if (r < 0) { - /* - * TODO: Cannot send, shdlc machine is dead, we - * must propagate the information up to HCI. - */ shdlc->hard_fault = r; break; } @@ -590,6 +577,11 @@ static void nfc_shdlc_sm_work(struct work_struct *work) skb_queue_purge(&shdlc->ack_pending_q); break; case SHDLC_CONNECTING: + if (shdlc->hard_fault) { + nfc_shdlc_connect_complete(shdlc, shdlc->hard_fault); + break; + } + if (shdlc->connect_tries++ < 5) r = nfc_shdlc_connect_initiate(shdlc); else @@ -610,6 +602,11 @@ static void nfc_shdlc_sm_work(struct work_struct *work) } nfc_shdlc_handle_rcv_queue(shdlc); + + if (shdlc->hard_fault) { + nfc_shdlc_connect_complete(shdlc, shdlc->hard_fault); + break; + } break; case SHDLC_CONNECTED: nfc_shdlc_handle_rcv_queue(shdlc); @@ -637,10 +634,7 @@ static void nfc_shdlc_sm_work(struct work_struct *work) } if (shdlc->hard_fault) { - /* - * TODO: Handle hard_fault that occured during - * this invocation of the shdlc worker - */ + nfc_hci_driver_failure(shdlc->hdev, shdlc->hard_fault); } break; default: @@ -765,14 +759,16 @@ static int nfc_shdlc_xmit(struct nfc_hci_dev *hdev, struct sk_buff *skb) return 0; } -static int nfc_shdlc_start_poll(struct nfc_hci_dev *hdev, u32 protocols) +static int nfc_shdlc_start_poll(struct nfc_hci_dev *hdev, + u32 im_protocols, u32 tm_protocols) { struct nfc_shdlc *shdlc = nfc_hci_get_clientdata(hdev); pr_debug("\n"); if (shdlc->ops->start_poll) - return shdlc->ops->start_poll(shdlc, protocols); + return shdlc->ops->start_poll(shdlc, + im_protocols, tm_protocols); return 0; } @@ -921,8 +917,6 @@ void nfc_shdlc_free(struct nfc_shdlc *shdlc) { pr_debug("\n"); - /* TODO: Check that this cannot be called while still in use */ - nfc_hci_unregister_device(shdlc->hdev); nfc_hci_free_device(shdlc->hdev); diff --git a/net/nfc/llcp/commands.c b/net/nfc/llcp/commands.c index bf8ae4f0b90..b982b5b890d 100644 --- a/net/nfc/llcp/commands.c +++ b/net/nfc/llcp/commands.c @@ -51,7 +51,7 @@ static u8 llcp_tlv8(u8 *tlv, u8 type) return tlv[2]; } -static u8 llcp_tlv16(u8 *tlv, u8 type) +static u16 llcp_tlv16(u8 *tlv, u8 type) { if (tlv[0] != type || tlv[1] != llcp_tlv_length[tlv[0]]) return 0; @@ -67,7 +67,7 @@ static u8 llcp_tlv_version(u8 *tlv) static u16 llcp_tlv_miux(u8 *tlv) { - return llcp_tlv16(tlv, LLCP_TLV_MIUX) & 0x7f; + return llcp_tlv16(tlv, LLCP_TLV_MIUX) & 0x7ff; } static u16 llcp_tlv_wks(u8 *tlv) @@ -117,8 +117,8 @@ u8 *nfc_llcp_build_tlv(u8 type, u8 *value, u8 value_length, u8 *tlv_length) return tlv; } -int nfc_llcp_parse_tlv(struct nfc_llcp_local *local, - u8 *tlv_array, u16 tlv_array_len) +int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local, + u8 *tlv_array, u16 tlv_array_len) { u8 *tlv = tlv_array, type, length, offset = 0; @@ -149,8 +149,45 @@ int nfc_llcp_parse_tlv(struct nfc_llcp_local *local, case LLCP_TLV_OPT: local->remote_opt = llcp_tlv_opt(tlv); break; + default: + pr_err("Invalid gt tlv value 0x%x\n", type); + break; + } + + offset += length + 2; + tlv += length + 2; + } + + pr_debug("version 0x%x miu %d lto %d opt 0x%x wks 0x%x\n", + local->remote_version, local->remote_miu, + local->remote_lto, local->remote_opt, + local->remote_wks); + + return 0; +} + +int nfc_llcp_parse_connection_tlv(struct nfc_llcp_sock *sock, + u8 *tlv_array, u16 tlv_array_len) +{ + u8 *tlv = tlv_array, type, length, offset = 0; + + pr_debug("TLV array length %d\n", tlv_array_len); + + if (sock == NULL) + return -ENOTCONN; + + while (offset < tlv_array_len) { + type = tlv[0]; + length = tlv[1]; + + pr_debug("type 0x%x length %d\n", type, length); + + switch (type) { + case LLCP_TLV_MIUX: + sock->miu = llcp_tlv_miux(tlv) + 128; + break; case LLCP_TLV_RW: - local->remote_rw = llcp_tlv_rw(tlv); + sock->rw = llcp_tlv_rw(tlv); break; case LLCP_TLV_SN: break; @@ -163,10 +200,7 @@ int nfc_llcp_parse_tlv(struct nfc_llcp_local *local, tlv += length + 2; } - pr_debug("version 0x%x miu %d lto %d opt 0x%x wks 0x%x rw %d\n", - local->remote_version, local->remote_miu, - local->remote_lto, local->remote_opt, - local->remote_wks, local->remote_rw); + pr_debug("sock %p rw %d miu %d\n", sock, sock->rw, sock->miu); return 0; } @@ -474,7 +508,7 @@ int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock, while (remaining_len > 0) { - frag_len = min_t(size_t, local->remote_miu, remaining_len); + frag_len = min_t(size_t, sock->miu, remaining_len); pr_debug("Fragment %zd bytes remaining %zd", frag_len, remaining_len); diff --git a/net/nfc/llcp/llcp.c b/net/nfc/llcp/llcp.c index 42994fac26d..82f0f7588b4 100644 --- a/net/nfc/llcp/llcp.c +++ b/net/nfc/llcp/llcp.c @@ -31,47 +31,41 @@ static u8 llcp_magic[3] = {0x46, 0x66, 0x6d}; static struct list_head llcp_devices; -static void nfc_llcp_socket_release(struct nfc_llcp_local *local) +void nfc_llcp_sock_link(struct llcp_sock_list *l, struct sock *sk) { - struct nfc_llcp_sock *parent, *s, *n; - struct sock *sk, *parent_sk; - int i; - - mutex_lock(&local->socket_lock); - - for (i = 0; i < LLCP_MAX_SAP; i++) { - parent = local->sockets[i]; - if (parent == NULL) - continue; - - /* Release all child sockets */ - list_for_each_entry_safe(s, n, &parent->list, list) { - list_del_init(&s->list); - sk = &s->sk; - - lock_sock(sk); - - if (sk->sk_state == LLCP_CONNECTED) - nfc_put_device(s->dev); + write_lock(&l->lock); + sk_add_node(sk, &l->head); + write_unlock(&l->lock); +} - sk->sk_state = LLCP_CLOSED; +void nfc_llcp_sock_unlink(struct llcp_sock_list *l, struct sock *sk) +{ + write_lock(&l->lock); + sk_del_node_init(sk); + write_unlock(&l->lock); +} - release_sock(sk); +static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool listen) +{ + struct sock *sk; + struct hlist_node *node, *tmp; + struct nfc_llcp_sock *llcp_sock; - sock_orphan(sk); + write_lock(&local->sockets.lock); - s->local = NULL; - } + sk_for_each_safe(sk, node, tmp, &local->sockets.head) { + llcp_sock = nfc_llcp_sock(sk); - parent_sk = &parent->sk; + lock_sock(sk); - lock_sock(parent_sk); + if (sk->sk_state == LLCP_CONNECTED) + nfc_put_device(llcp_sock->dev); - if (parent_sk->sk_state == LLCP_LISTEN) { + if (sk->sk_state == LLCP_LISTEN) { struct nfc_llcp_sock *lsk, *n; struct sock *accept_sk; - list_for_each_entry_safe(lsk, n, &parent->accept_queue, + list_for_each_entry_safe(lsk, n, &llcp_sock->accept_queue, accept_queue) { accept_sk = &lsk->sk; lock_sock(accept_sk); @@ -83,35 +77,94 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local) release_sock(accept_sk); sock_orphan(accept_sk); + } - lsk->local = NULL; + if (listen == true) { + release_sock(sk); + continue; } } - if (parent_sk->sk_state == LLCP_CONNECTED) - nfc_put_device(parent->dev); - - parent_sk->sk_state = LLCP_CLOSED; + sk->sk_state = LLCP_CLOSED; - release_sock(parent_sk); + release_sock(sk); - sock_orphan(parent_sk); + sock_orphan(sk); - parent->local = NULL; + sk_del_node_init(sk); } - mutex_unlock(&local->socket_lock); + write_unlock(&local->sockets.lock); } -static void nfc_llcp_clear_sdp(struct nfc_llcp_local *local) +struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) { - mutex_lock(&local->sdp_lock); + kref_get(&local->ref); - local->local_wks = 0; - local->local_sdp = 0; - local->local_sap = 0; + return local; +} - mutex_unlock(&local->sdp_lock); +static void local_release(struct kref *ref) +{ + struct nfc_llcp_local *local; + + local = container_of(ref, struct nfc_llcp_local, ref); + + list_del(&local->list); + nfc_llcp_socket_release(local, false); + del_timer_sync(&local->link_timer); + skb_queue_purge(&local->tx_queue); + destroy_workqueue(local->tx_wq); + destroy_workqueue(local->rx_wq); + destroy_workqueue(local->timeout_wq); + kfree_skb(local->rx_pending); + kfree(local); +} + +int nfc_llcp_local_put(struct nfc_llcp_local *local) +{ + if (local == NULL) + return 0; + + return kref_put(&local->ref, local_release); +} + +static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, + u8 ssap, u8 dsap) +{ + struct sock *sk; + struct hlist_node *node; + struct nfc_llcp_sock *llcp_sock; + + pr_debug("ssap dsap %d %d\n", ssap, dsap); + + if (ssap == 0 && dsap == 0) + return NULL; + + read_lock(&local->sockets.lock); + + llcp_sock = NULL; + + sk_for_each(sk, node, &local->sockets.head) { + llcp_sock = nfc_llcp_sock(sk); + + if (llcp_sock->ssap == ssap && llcp_sock->dsap == dsap) + break; + } + + read_unlock(&local->sockets.lock); + + if (llcp_sock == NULL) + return NULL; + + sock_hold(&llcp_sock->sk); + + return llcp_sock; +} + +static void nfc_llcp_sock_put(struct nfc_llcp_sock *sock) +{ + sock_put(&sock->sk); } static void nfc_llcp_timeout_work(struct work_struct *work) @@ -174,6 +227,51 @@ static int nfc_llcp_wks_sap(char *service_name, size_t service_name_len) return -EINVAL; } +static +struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local, + u8 *sn, size_t sn_len) +{ + struct sock *sk; + struct hlist_node *node; + struct nfc_llcp_sock *llcp_sock, *tmp_sock; + + pr_debug("sn %zd %p\n", sn_len, sn); + + if (sn == NULL || sn_len == 0) + return NULL; + + read_lock(&local->sockets.lock); + + llcp_sock = NULL; + + sk_for_each(sk, node, &local->sockets.head) { + tmp_sock = nfc_llcp_sock(sk); + + pr_debug("llcp sock %p\n", tmp_sock); + + if (tmp_sock->sk.sk_state != LLCP_LISTEN) + continue; + + if (tmp_sock->service_name == NULL || + tmp_sock->service_name_len == 0) + continue; + + if (tmp_sock->service_name_len != sn_len) + continue; + + if (memcmp(sn, tmp_sock->service_name, sn_len) == 0) { + llcp_sock = tmp_sock; + break; + } + } + + read_unlock(&local->sockets.lock); + + pr_debug("Found llcp sock %p\n", llcp_sock); + + return llcp_sock; +} + u8 nfc_llcp_get_sdp_ssap(struct nfc_llcp_local *local, struct nfc_llcp_sock *sock) { @@ -200,41 +298,26 @@ u8 nfc_llcp_get_sdp_ssap(struct nfc_llcp_local *local, } /* - * This is not a well known service, - * we should try to find a local SDP free spot + * Check if there already is a non WKS socket bound + * to this service name. */ - ssap = find_first_zero_bit(&local->local_sdp, LLCP_SDP_NUM_SAP); - if (ssap == LLCP_SDP_NUM_SAP) { + if (nfc_llcp_sock_from_sn(local, sock->service_name, + sock->service_name_len) != NULL) { mutex_unlock(&local->sdp_lock); return LLCP_SAP_MAX; } - pr_debug("SDP ssap %d\n", LLCP_WKS_NUM_SAP + ssap); - - set_bit(ssap, &local->local_sdp); mutex_unlock(&local->sdp_lock); - return LLCP_WKS_NUM_SAP + ssap; + return LLCP_SDP_UNBOUND; - } else if (sock->ssap != 0) { - if (sock->ssap < LLCP_WKS_NUM_SAP) { - if (!test_bit(sock->ssap, &local->local_wks)) { - set_bit(sock->ssap, &local->local_wks); - mutex_unlock(&local->sdp_lock); - - return sock->ssap; - } - - } else if (sock->ssap < LLCP_SDP_NUM_SAP) { - if (!test_bit(sock->ssap - LLCP_WKS_NUM_SAP, - &local->local_sdp)) { - set_bit(sock->ssap - LLCP_WKS_NUM_SAP, - &local->local_sdp); - mutex_unlock(&local->sdp_lock); + } else if (sock->ssap != 0 && sock->ssap < LLCP_WKS_NUM_SAP) { + if (!test_bit(sock->ssap, &local->local_wks)) { + set_bit(sock->ssap, &local->local_wks); + mutex_unlock(&local->sdp_lock); - return sock->ssap; - } + return sock->ssap; } } @@ -271,8 +354,34 @@ void nfc_llcp_put_ssap(struct nfc_llcp_local *local, u8 ssap) local_ssap = ssap; sdp = &local->local_wks; } else if (ssap < LLCP_LOCAL_NUM_SAP) { + atomic_t *client_cnt; + local_ssap = ssap - LLCP_WKS_NUM_SAP; sdp = &local->local_sdp; + client_cnt = &local->local_sdp_cnt[local_ssap]; + + pr_debug("%d clients\n", atomic_read(client_cnt)); + + mutex_lock(&local->sdp_lock); + + if (atomic_dec_and_test(client_cnt)) { + struct nfc_llcp_sock *l_sock; + + pr_debug("No more clients for SAP %d\n", ssap); + + clear_bit(local_ssap, sdp); + + /* Find the listening sock and set it back to UNBOUND */ + l_sock = nfc_llcp_sock_get(local, ssap, LLCP_SAP_SDP); + if (l_sock) { + l_sock->ssap = LLCP_SDP_UNBOUND; + nfc_llcp_sock_put(l_sock); + } + } + + mutex_unlock(&local->sdp_lock); + + return; } else if (ssap < LLCP_MAX_SAP) { local_ssap = ssap - LLCP_LOCAL_NUM_SAP; sdp = &local->local_sap; @@ -287,19 +396,26 @@ void nfc_llcp_put_ssap(struct nfc_llcp_local *local, u8 ssap) mutex_unlock(&local->sdp_lock); } -u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len) +static u8 nfc_llcp_reserve_sdp_ssap(struct nfc_llcp_local *local) { - struct nfc_llcp_local *local; + u8 ssap; - local = nfc_llcp_find_local(dev); - if (local == NULL) { - *general_bytes_len = 0; - return NULL; + mutex_lock(&local->sdp_lock); + + ssap = find_first_zero_bit(&local->local_sdp, LLCP_SDP_NUM_SAP); + if (ssap == LLCP_SDP_NUM_SAP) { + mutex_unlock(&local->sdp_lock); + + return LLCP_SAP_MAX; } - *general_bytes_len = local->gb_len; + pr_debug("SDP ssap %d\n", LLCP_WKS_NUM_SAP + ssap); - return local->gb; + set_bit(ssap, &local->local_sdp); + + mutex_unlock(&local->sdp_lock); + + return LLCP_WKS_NUM_SAP + ssap; } static int nfc_llcp_build_gb(struct nfc_llcp_local *local) @@ -363,6 +479,23 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local) return 0; } +u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len) +{ + struct nfc_llcp_local *local; + + local = nfc_llcp_find_local(dev); + if (local == NULL) { + *general_bytes_len = 0; + return NULL; + } + + nfc_llcp_build_gb(local); + + *general_bytes_len = local->gb_len; + + return local->gb; +} + int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len) { struct nfc_llcp_local *local = nfc_llcp_find_local(dev); @@ -384,31 +517,9 @@ int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len) return -EINVAL; } - return nfc_llcp_parse_tlv(local, - &local->remote_gb[3], - local->remote_gb_len - 3); -} - -static void nfc_llcp_tx_work(struct work_struct *work) -{ - struct nfc_llcp_local *local = container_of(work, struct nfc_llcp_local, - tx_work); - struct sk_buff *skb; - - skb = skb_dequeue(&local->tx_queue); - if (skb != NULL) { - pr_debug("Sending pending skb\n"); - print_hex_dump(KERN_DEBUG, "LLCP Tx: ", DUMP_PREFIX_OFFSET, - 16, 1, skb->data, skb->len, true); - - nfc_data_exchange(local->dev, local->target_idx, - skb, nfc_llcp_recv, local); - } else { - nfc_llcp_send_symm(local->dev); - } - - mod_timer(&local->link_timer, - jiffies + msecs_to_jiffies(local->remote_lto)); + return nfc_llcp_parse_gb_tlv(local, + &local->remote_gb[3], + local->remote_gb_len - 3); } static u8 nfc_llcp_dsap(struct sk_buff *pdu) @@ -443,51 +554,84 @@ static void nfc_llcp_set_nrns(struct nfc_llcp_sock *sock, struct sk_buff *pdu) sock->recv_ack_n = (sock->recv_n - 1) % 16; } -static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, - u8 ssap, u8 dsap) +static void nfc_llcp_tx_work(struct work_struct *work) { - struct nfc_llcp_sock *sock, *llcp_sock, *n; + struct nfc_llcp_local *local = container_of(work, struct nfc_llcp_local, + tx_work); + struct sk_buff *skb; + struct sock *sk; + struct nfc_llcp_sock *llcp_sock; - pr_debug("ssap dsap %d %d\n", ssap, dsap); + skb = skb_dequeue(&local->tx_queue); + if (skb != NULL) { + sk = skb->sk; + llcp_sock = nfc_llcp_sock(sk); + if (llcp_sock != NULL) { + int ret; + + pr_debug("Sending pending skb\n"); + print_hex_dump(KERN_DEBUG, "LLCP Tx: ", + DUMP_PREFIX_OFFSET, 16, 1, + skb->data, skb->len, true); + + ret = nfc_data_exchange(local->dev, local->target_idx, + skb, nfc_llcp_recv, local); + + if (!ret && nfc_llcp_ptype(skb) == LLCP_PDU_I) { + skb = skb_get(skb); + skb_queue_tail(&llcp_sock->tx_pending_queue, + skb); + } + } else { + nfc_llcp_send_symm(local->dev); + } + } else { + nfc_llcp_send_symm(local->dev); + } - if (ssap == 0 && dsap == 0) - return NULL; + mod_timer(&local->link_timer, + jiffies + msecs_to_jiffies(2 * local->remote_lto)); +} - mutex_lock(&local->socket_lock); - sock = local->sockets[ssap]; - if (sock == NULL) { - mutex_unlock(&local->socket_lock); - return NULL; - } +static struct nfc_llcp_sock *nfc_llcp_connecting_sock_get(struct nfc_llcp_local *local, + u8 ssap) +{ + struct sock *sk; + struct nfc_llcp_sock *llcp_sock; + struct hlist_node *node; - pr_debug("root dsap %d (%d)\n", sock->dsap, dsap); + read_lock(&local->connecting_sockets.lock); - if (sock->dsap == dsap) { - sock_hold(&sock->sk); - mutex_unlock(&local->socket_lock); - return sock; - } + sk_for_each(sk, node, &local->connecting_sockets.head) { + llcp_sock = nfc_llcp_sock(sk); - list_for_each_entry_safe(llcp_sock, n, &sock->list, list) { - pr_debug("llcp_sock %p sk %p dsap %d\n", llcp_sock, - &llcp_sock->sk, llcp_sock->dsap); - if (llcp_sock->dsap == dsap) { + if (llcp_sock->ssap == ssap) { sock_hold(&llcp_sock->sk); - mutex_unlock(&local->socket_lock); - return llcp_sock; + goto out; } } - pr_err("Could not find socket for %d %d\n", ssap, dsap); + llcp_sock = NULL; - mutex_unlock(&local->socket_lock); +out: + read_unlock(&local->connecting_sockets.lock); - return NULL; + return llcp_sock; } -static void nfc_llcp_sock_put(struct nfc_llcp_sock *sock) +static struct nfc_llcp_sock *nfc_llcp_sock_get_sn(struct nfc_llcp_local *local, + u8 *sn, size_t sn_len) { - sock_put(&sock->sk); + struct nfc_llcp_sock *llcp_sock; + + llcp_sock = nfc_llcp_sock_from_sn(local, sn, sn_len); + + if (llcp_sock == NULL) + return NULL; + + sock_hold(&llcp_sock->sk); + + return llcp_sock; } static u8 *nfc_llcp_connect_sn(struct sk_buff *skb, size_t *sn_len) @@ -518,35 +662,19 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, { struct sock *new_sk, *parent; struct nfc_llcp_sock *sock, *new_sock; - u8 dsap, ssap, bound_sap, reason; + u8 dsap, ssap, reason; dsap = nfc_llcp_dsap(skb); ssap = nfc_llcp_ssap(skb); pr_debug("%d %d\n", dsap, ssap); - nfc_llcp_parse_tlv(local, &skb->data[LLCP_HEADER_SIZE], - skb->len - LLCP_HEADER_SIZE); - if (dsap != LLCP_SAP_SDP) { - bound_sap = dsap; - - mutex_lock(&local->socket_lock); - sock = local->sockets[dsap]; - if (sock == NULL) { - mutex_unlock(&local->socket_lock); + sock = nfc_llcp_sock_get(local, dsap, LLCP_SAP_SDP); + if (sock == NULL || sock->sk.sk_state != LLCP_LISTEN) { reason = LLCP_DM_NOBOUND; goto fail; } - - sock_hold(&sock->sk); - mutex_unlock(&local->socket_lock); - - lock_sock(&sock->sk); - - if (sock->dsap == LLCP_SAP_SDP && - sock->sk.sk_state == LLCP_LISTEN) - goto enqueue; } else { u8 *sn; size_t sn_len; @@ -559,40 +687,15 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, pr_debug("Service name length %zu\n", sn_len); - mutex_lock(&local->socket_lock); - for (bound_sap = 0; bound_sap < LLCP_LOCAL_SAP_OFFSET; - bound_sap++) { - sock = local->sockets[bound_sap]; - if (sock == NULL) - continue; - - if (sock->service_name == NULL || - sock->service_name_len == 0) - continue; - - if (sock->service_name_len != sn_len) - continue; - - if (sock->dsap == LLCP_SAP_SDP && - sock->sk.sk_state == LLCP_LISTEN && - !memcmp(sn, sock->service_name, sn_len)) { - pr_debug("Found service name at SAP %d\n", - bound_sap); - sock_hold(&sock->sk); - mutex_unlock(&local->socket_lock); - - lock_sock(&sock->sk); - - goto enqueue; - } + sock = nfc_llcp_sock_get_sn(local, sn, sn_len); + if (sock == NULL) { + reason = LLCP_DM_NOBOUND; + goto fail; } - mutex_unlock(&local->socket_lock); } - reason = LLCP_DM_NOBOUND; - goto fail; + lock_sock(&sock->sk); -enqueue: parent = &sock->sk; if (sk_acceptq_is_full(parent)) { @@ -602,6 +705,21 @@ enqueue: goto fail; } + if (sock->ssap == LLCP_SDP_UNBOUND) { + u8 ssap = nfc_llcp_reserve_sdp_ssap(local); + + pr_debug("First client, reserving %d\n", ssap); + + if (ssap == LLCP_SAP_MAX) { + reason = LLCP_DM_REJ; + release_sock(&sock->sk); + sock_put(&sock->sk); + goto fail; + } + + sock->ssap = ssap; + } + new_sk = nfc_llcp_sock_alloc(NULL, parent->sk_type, GFP_ATOMIC); if (new_sk == NULL) { reason = LLCP_DM_REJ; @@ -612,15 +730,31 @@ enqueue: new_sock = nfc_llcp_sock(new_sk); new_sock->dev = local->dev; - new_sock->local = local; + new_sock->local = nfc_llcp_local_get(local); + new_sock->miu = local->remote_miu; new_sock->nfc_protocol = sock->nfc_protocol; - new_sock->ssap = bound_sap; new_sock->dsap = ssap; + new_sock->target_idx = local->target_idx; new_sock->parent = parent; + new_sock->ssap = sock->ssap; + if (sock->ssap < LLCP_LOCAL_NUM_SAP && sock->ssap >= LLCP_WKS_NUM_SAP) { + atomic_t *client_count; + + pr_debug("reserved_ssap %d for %p\n", sock->ssap, new_sock); + + client_count = + &local->local_sdp_cnt[sock->ssap - LLCP_WKS_NUM_SAP]; + + atomic_inc(client_count); + new_sock->reserved_ssap = sock->ssap; + } + + nfc_llcp_parse_connection_tlv(new_sock, &skb->data[LLCP_HEADER_SIZE], + skb->len - LLCP_HEADER_SIZE); pr_debug("new sock %p sk %p\n", new_sock, &new_sock->sk); - list_add_tail(&new_sock->list, &sock->list); + nfc_llcp_sock_link(&local->sockets, new_sk); nfc_llcp_accept_enqueue(&sock->sk, new_sk); @@ -654,12 +788,12 @@ int nfc_llcp_queue_i_frames(struct nfc_llcp_sock *sock) pr_debug("Remote ready %d tx queue len %d remote rw %d", sock->remote_ready, skb_queue_len(&sock->tx_pending_queue), - local->remote_rw); + sock->rw); /* Try to queue some I frames for transmission */ while (sock->remote_ready && - skb_queue_len(&sock->tx_pending_queue) < local->remote_rw) { - struct sk_buff *pdu, *pending_pdu; + skb_queue_len(&sock->tx_pending_queue) < sock->rw) { + struct sk_buff *pdu; pdu = skb_dequeue(&sock->tx_queue); if (pdu == NULL) @@ -668,10 +802,7 @@ int nfc_llcp_queue_i_frames(struct nfc_llcp_sock *sock) /* Update N(S)/N(R) */ nfc_llcp_set_nrns(sock, pdu); - pending_pdu = skb_clone(pdu, GFP_KERNEL); - skb_queue_tail(&local->tx_queue, pdu); - skb_queue_tail(&sock->tx_pending_queue, pending_pdu); nr_frames++; } @@ -728,11 +859,21 @@ static void nfc_llcp_recv_hdlc(struct nfc_llcp_local *local, llcp_sock->send_ack_n = nr; - skb_queue_walk_safe(&llcp_sock->tx_pending_queue, s, tmp) - if (nfc_llcp_ns(s) <= nr) { - skb_unlink(s, &llcp_sock->tx_pending_queue); - kfree_skb(s); - } + /* Remove and free all skbs until ns == nr */ + skb_queue_walk_safe(&llcp_sock->tx_pending_queue, s, tmp) { + skb_unlink(s, &llcp_sock->tx_pending_queue); + kfree_skb(s); + + if (nfc_llcp_ns(s) == nr) + break; + } + + /* Re-queue the remaining skbs for transmission */ + skb_queue_reverse_walk_safe(&llcp_sock->tx_pending_queue, + s, tmp) { + skb_unlink(s, &llcp_sock->tx_pending_queue); + skb_queue_head(&local->tx_queue, s); + } } if (ptype == LLCP_PDU_RR) @@ -740,7 +881,7 @@ static void nfc_llcp_recv_hdlc(struct nfc_llcp_local *local, else if (ptype == LLCP_PDU_RNR) llcp_sock->remote_ready = false; - if (nfc_llcp_queue_i_frames(llcp_sock) == 0) + if (nfc_llcp_queue_i_frames(llcp_sock) == 0 && ptype == LLCP_PDU_I) nfc_llcp_send_rr(llcp_sock); release_sock(sk); @@ -791,11 +932,7 @@ static void nfc_llcp_recv_cc(struct nfc_llcp_local *local, struct sk_buff *skb) dsap = nfc_llcp_dsap(skb); ssap = nfc_llcp_ssap(skb); - llcp_sock = nfc_llcp_sock_get(local, dsap, ssap); - - if (llcp_sock == NULL) - llcp_sock = nfc_llcp_sock_get(local, dsap, LLCP_SAP_SDP); - + llcp_sock = nfc_llcp_connecting_sock_get(local, dsap); if (llcp_sock == NULL) { pr_err("Invalid CC\n"); nfc_llcp_send_dm(local, dsap, ssap, LLCP_DM_NOCONN); @@ -803,11 +940,15 @@ static void nfc_llcp_recv_cc(struct nfc_llcp_local *local, struct sk_buff *skb) return; } - llcp_sock->dsap = ssap; sk = &llcp_sock->sk; - nfc_llcp_parse_tlv(local, &skb->data[LLCP_HEADER_SIZE], - skb->len - LLCP_HEADER_SIZE); + /* Unlink from connecting and link to the client array */ + nfc_llcp_sock_unlink(&local->connecting_sockets, sk); + nfc_llcp_sock_link(&local->sockets, sk); + llcp_sock->dsap = ssap; + + nfc_llcp_parse_connection_tlv(llcp_sock, &skb->data[LLCP_HEADER_SIZE], + skb->len - LLCP_HEADER_SIZE); sk->sk_state = LLCP_CONNECTED; sk->sk_state_change(sk); @@ -815,6 +956,45 @@ static void nfc_llcp_recv_cc(struct nfc_llcp_local *local, struct sk_buff *skb) nfc_llcp_sock_put(llcp_sock); } +static void nfc_llcp_recv_dm(struct nfc_llcp_local *local, struct sk_buff *skb) +{ + struct nfc_llcp_sock *llcp_sock; + struct sock *sk; + u8 dsap, ssap, reason; + + dsap = nfc_llcp_dsap(skb); + ssap = nfc_llcp_ssap(skb); + reason = skb->data[2]; + + pr_debug("%d %d reason %d\n", ssap, dsap, reason); + + switch (reason) { + case LLCP_DM_NOBOUND: + case LLCP_DM_REJ: + llcp_sock = nfc_llcp_connecting_sock_get(local, dsap); + break; + + default: + llcp_sock = nfc_llcp_sock_get(local, dsap, ssap); + break; + } + + if (llcp_sock == NULL) { + pr_err("Invalid DM\n"); + return; + } + + sk = &llcp_sock->sk; + + sk->sk_err = ENXIO; + sk->sk_state = LLCP_CLOSED; + sk->sk_state_change(sk); + + nfc_llcp_sock_put(llcp_sock); + + return; +} + static void nfc_llcp_rx_work(struct work_struct *work) { struct nfc_llcp_local *local = container_of(work, struct nfc_llcp_local, @@ -858,6 +1038,11 @@ static void nfc_llcp_rx_work(struct work_struct *work) nfc_llcp_recv_cc(local, skb); break; + case LLCP_PDU_DM: + pr_debug("DM\n"); + nfc_llcp_recv_dm(local, skb); + break; + case LLCP_PDU_I: case LLCP_PDU_RR: case LLCP_PDU_RNR: @@ -891,6 +1076,21 @@ void nfc_llcp_recv(void *data, struct sk_buff *skb, int err) return; } +int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb) +{ + struct nfc_llcp_local *local; + + local = nfc_llcp_find_local(dev); + if (local == NULL) + return -ENODEV; + + local->rx_pending = skb_get(skb); + del_timer(&local->link_timer); + queue_work(local->rx_wq, &local->rx_work); + + return 0; +} + void nfc_llcp_mac_is_down(struct nfc_dev *dev) { struct nfc_llcp_local *local; @@ -899,10 +1099,8 @@ void nfc_llcp_mac_is_down(struct nfc_dev *dev) if (local == NULL) return; - nfc_llcp_clear_sdp(local); - /* Close and purge all existing sockets */ - nfc_llcp_socket_release(local); + nfc_llcp_socket_release(local, true); } void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx, @@ -943,8 +1141,8 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) local->dev = ndev; INIT_LIST_HEAD(&local->list); + kref_init(&local->ref); mutex_init(&local->sdp_lock); - mutex_init(&local->socket_lock); init_timer(&local->link_timer); local->link_timer.data = (unsigned long) local; local->link_timer.function = nfc_llcp_symm_timer; @@ -984,11 +1182,13 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) goto err_rx_wq; } + local->sockets.lock = __RW_LOCK_UNLOCKED(local->sockets.lock); + local->connecting_sockets.lock = __RW_LOCK_UNLOCKED(local->connecting_sockets.lock); + nfc_llcp_build_gb(local); local->remote_miu = LLCP_DEFAULT_MIU; local->remote_lto = LLCP_DEFAULT_LTO; - local->remote_rw = LLCP_DEFAULT_RW; list_add(&llcp_devices, &local->list); @@ -1015,14 +1215,7 @@ void nfc_llcp_unregister_device(struct nfc_dev *dev) return; } - list_del(&local->list); - nfc_llcp_socket_release(local); - del_timer_sync(&local->link_timer); - skb_queue_purge(&local->tx_queue); - destroy_workqueue(local->tx_wq); - destroy_workqueue(local->rx_wq); - kfree_skb(local->rx_pending); - kfree(local); + nfc_llcp_local_put(local); } int __init nfc_llcp_init(void) diff --git a/net/nfc/llcp/llcp.h b/net/nfc/llcp/llcp.h index 50680ce5ae4..83b8bba5a28 100644 --- a/net/nfc/llcp/llcp.h +++ b/net/nfc/llcp/llcp.h @@ -37,15 +37,22 @@ enum llcp_state { #define LLCP_LOCAL_NUM_SAP 32 #define LLCP_LOCAL_SAP_OFFSET (LLCP_WKS_NUM_SAP + LLCP_SDP_NUM_SAP) #define LLCP_MAX_SAP (LLCP_WKS_NUM_SAP + LLCP_SDP_NUM_SAP + LLCP_LOCAL_NUM_SAP) +#define LLCP_SDP_UNBOUND (LLCP_MAX_SAP + 1) struct nfc_llcp_sock; +struct llcp_sock_list { + struct hlist_head head; + rwlock_t lock; +}; + struct nfc_llcp_local { struct list_head list; struct nfc_dev *dev; + struct kref ref; + struct mutex sdp_lock; - struct mutex socket_lock; struct timer_list link_timer; struct sk_buff_head tx_queue; @@ -63,6 +70,7 @@ struct nfc_llcp_local { unsigned long local_wks; /* Well known services */ unsigned long local_sdp; /* Local services */ unsigned long local_sap; /* Local SAPs, not available for discovery */ + atomic_t local_sdp_cnt[LLCP_SDP_NUM_SAP]; /* local */ u8 gb[NFC_MAX_GT_LEN]; @@ -77,24 +85,26 @@ struct nfc_llcp_local { u16 remote_lto; u8 remote_opt; u16 remote_wks; - u8 remote_rw; /* sockets array */ - struct nfc_llcp_sock *sockets[LLCP_MAX_SAP]; + struct llcp_sock_list sockets; + struct llcp_sock_list connecting_sockets; }; struct nfc_llcp_sock { struct sock sk; - struct list_head list; struct nfc_dev *dev; struct nfc_llcp_local *local; u32 target_idx; u32 nfc_protocol; + /* Link parameters */ u8 ssap; u8 dsap; char *service_name; size_t service_name_len; + u8 rw; + u16 miu; /* Link variables */ u8 send_n; @@ -105,6 +115,9 @@ struct nfc_llcp_sock { /* Is the remote peer ready to receive */ u8 remote_ready; + /* Reserved source SAP */ + u8 reserved_ssap; + struct sk_buff_head tx_queue; struct sk_buff_head tx_pending_queue; struct sk_buff_head tx_backlog_queue; @@ -164,7 +177,11 @@ struct nfc_llcp_sock { #define LLCP_DM_REJ 0x03 +void nfc_llcp_sock_link(struct llcp_sock_list *l, struct sock *s); +void nfc_llcp_sock_unlink(struct llcp_sock_list *l, struct sock *s); struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev); +struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local); +int nfc_llcp_local_put(struct nfc_llcp_local *local); u8 nfc_llcp_get_sdp_ssap(struct nfc_llcp_local *local, struct nfc_llcp_sock *sock); u8 nfc_llcp_get_local_ssap(struct nfc_llcp_local *local); @@ -179,8 +196,10 @@ void nfc_llcp_accept_enqueue(struct sock *parent, struct sock *sk); struct sock *nfc_llcp_accept_dequeue(struct sock *sk, struct socket *newsock); /* TLV API */ -int nfc_llcp_parse_tlv(struct nfc_llcp_local *local, - u8 *tlv_array, u16 tlv_array_len); +int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local, + u8 *tlv_array, u16 tlv_array_len); +int nfc_llcp_parse_connection_tlv(struct nfc_llcp_sock *sock, + u8 *tlv_array, u16 tlv_array_len); /* Commands API */ void nfc_llcp_recv(void *data, struct sk_buff *skb, int err); diff --git a/net/nfc/llcp/sock.c b/net/nfc/llcp/sock.c index e06d458fc71..ddeb9aa398f 100644 --- a/net/nfc/llcp/sock.c +++ b/net/nfc/llcp/sock.c @@ -78,11 +78,11 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) struct sockaddr_nfc_llcp llcp_addr; int len, ret = 0; - pr_debug("sk %p addr %p family %d\n", sk, addr, addr->sa_family); - if (!addr || addr->sa_family != AF_NFC) return -EINVAL; + pr_debug("sk %p addr %p family %d\n", sk, addr, addr->sa_family); + memset(&llcp_addr, 0, sizeof(llcp_addr)); len = min_t(unsigned int, sizeof(llcp_addr), alen); memcpy(&llcp_addr, addr, len); @@ -111,7 +111,7 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) } llcp_sock->dev = dev; - llcp_sock->local = local; + llcp_sock->local = nfc_llcp_local_get(local); llcp_sock->nfc_protocol = llcp_addr.nfc_protocol; llcp_sock->service_name_len = min_t(unsigned int, llcp_addr.service_name_len, @@ -121,10 +121,14 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) GFP_KERNEL); llcp_sock->ssap = nfc_llcp_get_sdp_ssap(local, llcp_sock); - if (llcp_sock->ssap == LLCP_MAX_SAP) + if (llcp_sock->ssap == LLCP_SAP_MAX) { + ret = -EADDRINUSE; goto put_dev; + } + + llcp_sock->reserved_ssap = llcp_sock->ssap; - local->sockets[llcp_sock->ssap] = llcp_sock; + nfc_llcp_sock_link(&local->sockets, sk); pr_debug("Socket bound to SAP %d\n", llcp_sock->ssap); @@ -283,22 +287,28 @@ error: return ret; } -static int llcp_sock_getname(struct socket *sock, struct sockaddr *addr, +static int llcp_sock_getname(struct socket *sock, struct sockaddr *uaddr, int *len, int peer) { - struct sockaddr_nfc_llcp *llcp_addr = (struct sockaddr_nfc_llcp *)addr; struct sock *sk = sock->sk; struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); + DECLARE_SOCKADDR(struct sockaddr_nfc_llcp *, llcp_addr, uaddr); - pr_debug("%p\n", sk); + if (llcp_sock == NULL || llcp_sock->dev == NULL) + return -EBADFD; + + pr_debug("%p %d %d %d\n", sk, llcp_sock->target_idx, + llcp_sock->dsap, llcp_sock->ssap); if (llcp_sock == NULL || llcp_sock->dev == NULL) return -EBADFD; - addr->sa_family = AF_NFC; + uaddr->sa_family = AF_NFC; + *len = sizeof(struct sockaddr_nfc_llcp); llcp_addr->dev_idx = llcp_sock->dev->idx; + llcp_addr->target_idx = llcp_sock->target_idx; llcp_addr->dsap = llcp_sock->dsap; llcp_addr->ssap = llcp_sock->ssap; llcp_addr->service_name_len = llcp_sock->service_name_len; @@ -382,15 +392,6 @@ static int llcp_sock_release(struct socket *sock) goto out; } - mutex_lock(&local->socket_lock); - - if (llcp_sock == local->sockets[llcp_sock->ssap]) - local->sockets[llcp_sock->ssap] = NULL; - else - list_del_init(&llcp_sock->list); - - mutex_unlock(&local->socket_lock); - lock_sock(sk); /* Send a DISC */ @@ -415,14 +416,13 @@ static int llcp_sock_release(struct socket *sock) } } - /* Freeing the SAP */ - if ((sk->sk_state == LLCP_CONNECTED - && llcp_sock->ssap > LLCP_LOCAL_SAP_OFFSET) || - sk->sk_state == LLCP_BOUND || sk->sk_state == LLCP_LISTEN) + if (llcp_sock->reserved_ssap < LLCP_SAP_MAX) nfc_llcp_put_ssap(llcp_sock->local, llcp_sock->ssap); release_sock(sk); + nfc_llcp_sock_unlink(&local->sockets, sk); + out: sock_orphan(sk); sock_put(sk); @@ -490,12 +490,16 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, } llcp_sock->dev = dev; - llcp_sock->local = local; + llcp_sock->local = nfc_llcp_local_get(local); + llcp_sock->miu = llcp_sock->local->remote_miu; llcp_sock->ssap = nfc_llcp_get_local_ssap(local); if (llcp_sock->ssap == LLCP_SAP_MAX) { ret = -ENOMEM; goto put_dev; } + + llcp_sock->reserved_ssap = llcp_sock->ssap; + if (addr->service_name_len == 0) llcp_sock->dsap = addr->dsap; else @@ -508,21 +512,26 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, llcp_sock->service_name_len, GFP_KERNEL); - local->sockets[llcp_sock->ssap] = llcp_sock; + nfc_llcp_sock_link(&local->connecting_sockets, sk); ret = nfc_llcp_send_connect(llcp_sock); if (ret) - goto put_dev; + goto sock_unlink; ret = sock_wait_state(sk, LLCP_CONNECTED, sock_sndtimeo(sk, flags & O_NONBLOCK)); if (ret) - goto put_dev; + goto sock_unlink; release_sock(sk); return 0; +sock_unlink: + nfc_llcp_put_ssap(local, llcp_sock->ssap); + + nfc_llcp_sock_unlink(&local->connecting_sockets, sk); + put_dev: nfc_put_device(dev); @@ -687,13 +696,15 @@ struct sock *nfc_llcp_sock_alloc(struct socket *sock, int type, gfp_t gfp) llcp_sock->ssap = 0; llcp_sock->dsap = LLCP_SAP_SDP; + llcp_sock->rw = LLCP_DEFAULT_RW; + llcp_sock->miu = LLCP_DEFAULT_MIU; llcp_sock->send_n = llcp_sock->send_ack_n = 0; llcp_sock->recv_n = llcp_sock->recv_ack_n = 0; llcp_sock->remote_ready = 1; + llcp_sock->reserved_ssap = LLCP_SAP_MAX; skb_queue_head_init(&llcp_sock->tx_queue); skb_queue_head_init(&llcp_sock->tx_pending_queue); skb_queue_head_init(&llcp_sock->tx_backlog_queue); - INIT_LIST_HEAD(&llcp_sock->list); INIT_LIST_HEAD(&llcp_sock->accept_queue); if (sock != NULL) @@ -704,8 +715,6 @@ struct sock *nfc_llcp_sock_alloc(struct socket *sock, int type, gfp_t gfp) void nfc_llcp_sock_free(struct nfc_llcp_sock *sock) { - struct nfc_llcp_local *local = sock->local; - kfree(sock->service_name); skb_queue_purge(&sock->tx_queue); @@ -714,12 +723,9 @@ void nfc_llcp_sock_free(struct nfc_llcp_sock *sock) list_del_init(&sock->accept_queue); - if (local != NULL && sock == local->sockets[sock->ssap]) - local->sockets[sock->ssap] = NULL; - else - list_del_init(&sock->list); - sock->parent = NULL; + + nfc_llcp_local_put(sock->local); } static int llcp_sock_create(struct net *net, struct socket *sock, diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index d560e6f1307..f81efe13985 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -27,6 +27,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__ +#include <linux/module.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/completion.h> @@ -194,7 +195,7 @@ static void nci_rf_discover_req(struct nci_dev *ndev, unsigned long opt) } if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) && - (protocols & NFC_PROTO_ISO14443_MASK)) { + (protocols & NFC_PROTO_ISO14443_B_MASK)) { cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode = NCI_NFC_B_PASSIVE_POLL_MODE; cmd.disc_configs[cmd.num_disc_configs].frequency = 1; @@ -387,7 +388,8 @@ static int nci_dev_down(struct nfc_dev *nfc_dev) return nci_close_device(ndev); } -static int nci_start_poll(struct nfc_dev *nfc_dev, __u32 protocols) +static int nci_start_poll(struct nfc_dev *nfc_dev, + __u32 im_protocols, __u32 tm_protocols) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); int rc; @@ -413,11 +415,11 @@ static int nci_start_poll(struct nfc_dev *nfc_dev, __u32 protocols) return -EBUSY; } - rc = nci_request(ndev, nci_rf_discover_req, protocols, + rc = nci_request(ndev, nci_rf_discover_req, im_protocols, msecs_to_jiffies(NCI_RF_DISC_TIMEOUT)); if (!rc) - ndev->poll_prots = protocols; + ndev->poll_prots = im_protocols; return rc; } @@ -485,7 +487,8 @@ static int nci_activate_target(struct nfc_dev *nfc_dev, param.rf_protocol = NCI_RF_PROTOCOL_T2T; else if (protocol == NFC_PROTO_FELICA) param.rf_protocol = NCI_RF_PROTOCOL_T3T; - else if (protocol == NFC_PROTO_ISO14443) + else if (protocol == NFC_PROTO_ISO14443 || + protocol == NFC_PROTO_ISO14443_B) param.rf_protocol = NCI_RF_PROTOCOL_ISO_DEP; else param.rf_protocol = NCI_RF_PROTOCOL_NFC_DEP; @@ -521,9 +524,9 @@ static void nci_deactivate_target(struct nfc_dev *nfc_dev, } } -static int nci_data_exchange(struct nfc_dev *nfc_dev, struct nfc_target *target, - struct sk_buff *skb, - data_exchange_cb_t cb, void *cb_context) +static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target, + struct sk_buff *skb, + data_exchange_cb_t cb, void *cb_context) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); int rc; @@ -556,7 +559,7 @@ static struct nfc_ops nci_nfc_ops = { .stop_poll = nci_stop_poll, .activate_target = nci_activate_target, .deactivate_target = nci_deactivate_target, - .data_exchange = nci_data_exchange, + .im_transceive = nci_transceive, }; /* ---- Interface to NCI drivers ---- */ @@ -878,3 +881,5 @@ static void nci_cmd_work(struct work_struct *work) jiffies + msecs_to_jiffies(NCI_CMD_TIMEOUT)); } } + +MODULE_LICENSE("GPL"); diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index 2ab196a9f22..af7a93b0439 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -170,7 +170,10 @@ static int nci_add_new_protocol(struct nci_dev *ndev, if (rf_protocol == NCI_RF_PROTOCOL_T2T) protocol = NFC_PROTO_MIFARE_MASK; else if (rf_protocol == NCI_RF_PROTOCOL_ISO_DEP) - protocol = NFC_PROTO_ISO14443_MASK; + if (rf_tech_and_mode == NCI_NFC_A_PASSIVE_POLL_MODE) + protocol = NFC_PROTO_ISO14443_MASK; + else + protocol = NFC_PROTO_ISO14443_B_MASK; else if (rf_protocol == NCI_RF_PROTOCOL_T3T) protocol = NFC_PROTO_FELICA_MASK; else diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 581d419083a..4c51714ee74 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -49,6 +49,8 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = { [NFC_ATTR_COMM_MODE] = { .type = NLA_U8 }, [NFC_ATTR_RF_MODE] = { .type = NLA_U8 }, [NFC_ATTR_DEVICE_POWERED] = { .type = NLA_U8 }, + [NFC_ATTR_IM_PROTOCOLS] = { .type = NLA_U32 }, + [NFC_ATTR_TM_PROTOCOLS] = { .type = NLA_U32 }, }; static int nfc_genl_send_target(struct sk_buff *msg, struct nfc_target *target, @@ -165,7 +167,7 @@ int nfc_genl_targets_found(struct nfc_dev *dev) dev->genl_data.poll_req_pid = 0; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; @@ -193,7 +195,7 @@ int nfc_genl_target_lost(struct nfc_dev *dev, u32 target_idx) struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; @@ -219,12 +221,74 @@ free_msg: return -EMSGSIZE; } +int nfc_genl_tm_activated(struct nfc_dev *dev, u32 protocol) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, + NFC_EVENT_TM_ACTIVATED); + if (!hdr) + goto free_msg; + + if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) + goto nla_put_failure; + if (nla_put_u32(msg, NFC_ATTR_TM_PROTOCOLS, protocol)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -EMSGSIZE; +} + +int nfc_genl_tm_deactivated(struct nfc_dev *dev) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, + NFC_EVENT_TM_DEACTIVATED); + if (!hdr) + goto free_msg; + + if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -EMSGSIZE; +} + int nfc_genl_device_added(struct nfc_dev *dev) { struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; @@ -257,7 +321,7 @@ int nfc_genl_device_removed(struct nfc_dev *dev) struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; @@ -370,7 +434,7 @@ int nfc_genl_dep_link_up_event(struct nfc_dev *dev, u32 target_idx, pr_debug("DEP link is up\n"); - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; @@ -409,7 +473,7 @@ int nfc_genl_dep_link_down_event(struct nfc_dev *dev) pr_debug("DEP link is down\n"); - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; @@ -450,7 +514,7 @@ static int nfc_genl_get_device(struct sk_buff *skb, struct genl_info *info) if (!dev) return -ENODEV; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { rc = -ENOMEM; goto out_putdev; @@ -519,16 +583,25 @@ static int nfc_genl_start_poll(struct sk_buff *skb, struct genl_info *info) struct nfc_dev *dev; int rc; u32 idx; - u32 protocols; + u32 im_protocols = 0, tm_protocols = 0; pr_debug("Poll start\n"); if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || - !info->attrs[NFC_ATTR_PROTOCOLS]) + ((!info->attrs[NFC_ATTR_IM_PROTOCOLS] && + !info->attrs[NFC_ATTR_PROTOCOLS]) && + !info->attrs[NFC_ATTR_TM_PROTOCOLS])) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); - protocols = nla_get_u32(info->attrs[NFC_ATTR_PROTOCOLS]); + + if (info->attrs[NFC_ATTR_TM_PROTOCOLS]) + tm_protocols = nla_get_u32(info->attrs[NFC_ATTR_TM_PROTOCOLS]); + + if (info->attrs[NFC_ATTR_IM_PROTOCOLS]) + im_protocols = nla_get_u32(info->attrs[NFC_ATTR_IM_PROTOCOLS]); + else if (info->attrs[NFC_ATTR_PROTOCOLS]) + im_protocols = nla_get_u32(info->attrs[NFC_ATTR_PROTOCOLS]); dev = nfc_get_device(idx); if (!dev) @@ -536,7 +609,7 @@ static int nfc_genl_start_poll(struct sk_buff *skb, struct genl_info *info) mutex_lock(&dev->genl_data.genl_data_mutex); - rc = nfc_start_poll(dev, protocols); + rc = nfc_start_poll(dev, im_protocols, tm_protocols); if (!rc) dev->genl_data.poll_req_pid = info->snd_pid; @@ -561,6 +634,15 @@ static int nfc_genl_stop_poll(struct sk_buff *skb, struct genl_info *info) if (!dev) return -ENODEV; + device_lock(&dev->dev); + + if (!dev->polling) { + device_unlock(&dev->dev); + return -EINVAL; + } + + device_unlock(&dev->dev); + mutex_lock(&dev->genl_data.genl_data_mutex); if (dev->genl_data.poll_req_pid != info->snd_pid) { diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index 3dd4232ae66..c5e42b79a41 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -55,6 +55,7 @@ int nfc_llcp_register_device(struct nfc_dev *dev); void nfc_llcp_unregister_device(struct nfc_dev *dev); int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len); u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len); +int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb); int __init nfc_llcp_init(void); void nfc_llcp_exit(void); @@ -90,6 +91,12 @@ static inline u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *gb_len) return NULL; } +static inline int nfc_llcp_data_received(struct nfc_dev *dev, + struct sk_buff *skb) +{ + return 0; +} + static inline int nfc_llcp_init(void) { return 0; @@ -128,6 +135,9 @@ int nfc_genl_dep_link_up_event(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode); int nfc_genl_dep_link_down_event(struct nfc_dev *dev); +int nfc_genl_tm_activated(struct nfc_dev *dev, u32 protocol); +int nfc_genl_tm_deactivated(struct nfc_dev *dev); + struct nfc_dev *nfc_get_device(unsigned int idx); static inline void nfc_put_device(struct nfc_dev *dev) @@ -158,7 +168,7 @@ int nfc_dev_up(struct nfc_dev *dev); int nfc_dev_down(struct nfc_dev *dev); -int nfc_start_poll(struct nfc_dev *dev, u32 protocols); +int nfc_start_poll(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols); int nfc_stop_poll(struct nfc_dev *dev); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 48badffaafc..f3f96badf5a 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2012 Nicira Networks. + * Copyright (c) 2007-2012 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 2c74daa5aca..d8277d29e71 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2012 Nicira Networks. + * Copyright (c) 2007-2012 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -263,14 +263,15 @@ err: static int queue_gso_packets(int dp_ifindex, struct sk_buff *skb, const struct dp_upcall_info *upcall_info) { + unsigned short gso_type = skb_shinfo(skb)->gso_type; struct dp_upcall_info later_info; struct sw_flow_key later_key; struct sk_buff *segs, *nskb; int err; segs = skb_gso_segment(skb, NETIF_F_SG | NETIF_F_HW_CSUM); - if (IS_ERR(skb)) - return PTR_ERR(skb); + if (IS_ERR(segs)) + return PTR_ERR(segs); /* Queue all of the segments. */ skb = segs; @@ -279,7 +280,7 @@ static int queue_gso_packets(int dp_ifindex, struct sk_buff *skb, if (err) break; - if (skb == segs && skb_shinfo(skb)->gso_type & SKB_GSO_UDP) { + if (skb == segs && gso_type & SKB_GSO_UDP) { /* The initial flow key extracted by ovs_flow_extract() * in this case is for a first fragment, so we need to * properly mark later fragments. @@ -1649,7 +1650,9 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) if (!err && a[OVS_VPORT_ATTR_OPTIONS]) err = ovs_vport_set_options(vport, a[OVS_VPORT_ATTR_OPTIONS]); - if (!err && a[OVS_VPORT_ATTR_UPCALL_PID]) + if (err) + goto exit_unlock; + if (a[OVS_VPORT_ATTR_UPCALL_PID]) vport->upcall_pid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]); reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq, diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index c73370cc1f0..c1105c14753 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2011 Nicira Networks. + * Copyright (c) 2007-2012 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c index 46736518c45..36dcee8fc84 100644 --- a/net/openvswitch/dp_notify.c +++ b/net/openvswitch/dp_notify.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2011 Nicira Networks. + * Copyright (c) 2007-2012 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 6d4d8097cf9..b7f38b16190 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2011 Nicira Networks. + * Copyright (c) 2007-2011 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -182,7 +182,8 @@ void ovs_flow_used(struct sw_flow *flow, struct sk_buff *skb) { u8 tcp_flags = 0; - if (flow->key.eth.type == htons(ETH_P_IP) && + if ((flow->key.eth.type == htons(ETH_P_IP) || + flow->key.eth.type == htons(ETH_P_IPV6)) && flow->key.ip.proto == IPPROTO_TCP && likely(skb->len >= skb_transport_offset(skb) + sizeof(struct tcphdr))) { u8 *tcp = (u8 *)tcp_hdr(skb); diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 2747dc2c4ac..9b75617ca4e 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2011 Nicira Networks. + * Copyright (c) 2007-2011 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index b6b1d7daa3c..4061b9ee07f 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2011 Nicira Networks. + * Copyright (c) 2007-2012 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -24,6 +24,9 @@ #include <linux/ethtool.h> #include <linux/skbuff.h> +#include <net/dst.h> +#include <net/xfrm.h> + #include "datapath.h" #include "vport-internal_dev.h" #include "vport-netdev.h" @@ -209,6 +212,11 @@ static int internal_dev_recv(struct vport *vport, struct sk_buff *skb) int len; len = skb->len; + + skb_dst_drop(skb); + nf_reset(skb); + secpath_reset(skb); + skb->dev = netdev; skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, netdev); diff --git a/net/openvswitch/vport-internal_dev.h b/net/openvswitch/vport-internal_dev.h index 3454447c5f1..9a7d30ecc6a 100644 --- a/net/openvswitch/vport-internal_dev.h +++ b/net/openvswitch/vport-internal_dev.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2011 Nicira Networks. + * Copyright (c) 2007-2011 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 3fd6c0d88e1..6ea3551cc78 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2011 Nicira Networks. + * Copyright (c) 2007-2012 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public diff --git a/net/openvswitch/vport-netdev.h b/net/openvswitch/vport-netdev.h index fd9b008a0e6..f7072a25c60 100644 --- a/net/openvswitch/vport-netdev.h +++ b/net/openvswitch/vport-netdev.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2011 Nicira Networks. + * Copyright (c) 2007-2011 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 6c066ba25dc..6140336e79d 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2011 Nicira Networks. + * Copyright (c) 2007-2012 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index 19609629dab..aac680ca2b0 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2011 Nicira Networks. + * Copyright (c) 2007-2012 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 0f661745df0..c5c9e2a5421 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -531,6 +531,7 @@ static int prb_calc_retire_blk_tmo(struct packet_sock *po, unsigned int mbits = 0, msec = 0, div = 0, tmo = 0; struct ethtool_cmd ecmd; int err; + u32 speed; rtnl_lock(); dev = __dev_get_by_index(sock_net(&po->sk), po->ifindex); @@ -539,25 +540,18 @@ static int prb_calc_retire_blk_tmo(struct packet_sock *po, return DEFAULT_PRB_RETIRE_TOV; } err = __ethtool_get_settings(dev, &ecmd); + speed = ethtool_cmd_speed(&ecmd); rtnl_unlock(); if (!err) { - switch (ecmd.speed) { - case SPEED_10000: - msec = 1; - div = 10000/1000; - break; - case SPEED_1000: - msec = 1; - div = 1000/1000; - break; /* * If the link speed is so slow you don't really * need to worry about perf anyways */ - case SPEED_100: - case SPEED_10: - default: + if (speed < SPEED_1000 || speed == SPEED_UNKNOWN) { return DEFAULT_PRB_RETIRE_TOV; + } else { + msec = 1; + div = speed / 1000; } } @@ -592,7 +586,7 @@ static void init_prb_bdqc(struct packet_sock *po, p1->knxt_seq_num = 1; p1->pkbdq = pg_vec; pbd = (struct tpacket_block_desc *)pg_vec[0].buffer; - p1->pkblk_start = (char *)pg_vec[0].buffer; + p1->pkblk_start = pg_vec[0].buffer; p1->kblk_size = req_u->req3.tp_block_size; p1->knum_blocks = req_u->req3.tp_block_nr; p1->hdrlen = po->tp_hdrlen; @@ -824,8 +818,7 @@ static void prb_open_block(struct tpacket_kbdq_core *pkc1, h1->ts_first_pkt.ts_sec = ts.tv_sec; h1->ts_first_pkt.ts_nsec = ts.tv_nsec; pkc1->pkblk_start = (char *)pbd1; - pkc1->nxt_offset = (char *)(pkc1->pkblk_start + - BLK_PLUS_PRIV(pkc1->blk_sizeof_priv)); + pkc1->nxt_offset = pkc1->pkblk_start + BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN; pbd1->version = pkc1->version; @@ -1018,7 +1011,7 @@ static void *__packet_lookup_frame_in_block(struct packet_sock *po, struct tpacket_block_desc *pbd; char *curr, *end; - pkc = GET_PBDQC_FROM_RB(((struct packet_ring_buffer *)&po->rx_ring)); + pkc = GET_PBDQC_FROM_RB(&po->rx_ring); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* Queue is frozen when user space is lagging behind */ @@ -1044,7 +1037,7 @@ static void *__packet_lookup_frame_in_block(struct packet_sock *po, smp_mb(); curr = pkc->nxt_offset; pkc->skb = skb; - end = (char *) ((char *)pbd + pkc->kblk_size); + end = (char *)pbd + pkc->kblk_size; /* first try the current block */ if (curr+TOTAL_PKT_LEN_INCL_ALIGN(len) < end) { @@ -1086,7 +1079,7 @@ static void *packet_current_rx_frame(struct packet_sock *po, default: WARN(1, "TPACKET version not supported\n"); BUG(); - return 0; + return NULL; } } @@ -1280,6 +1273,14 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po) spin_unlock(&f->lock); } +static bool match_fanout_group(struct packet_type *ptype, struct sock * sk) +{ + if (ptype->af_packet_priv == (void*)((struct packet_sock *)sk)->fanout) + return true; + + return false; +} + static int fanout_add(struct sock *sk, u16 id, u16 type_flags) { struct packet_sock *po = pkt_sk(sk); @@ -1332,6 +1333,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) match->prot_hook.dev = po->prot_hook.dev; match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; + match->prot_hook.id_match = match_fanout_group; dev_add_pack(&match->prot_hook); list_add(&match->list, &fanout_list); } @@ -1476,7 +1478,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, * Find the device first to size check it */ - saddr->spkt_device[13] = 0; + saddr->spkt_device[sizeof(saddr->spkt_device) - 1] = 0; retry: rcu_read_lock(); dev = dev_get_by_name_rcu(sock_net(sk), saddr->spkt_device); @@ -1943,7 +1945,6 @@ static void tpacket_destruct_skb(struct sk_buff *skb) if (likely(po->tx_ring.pg_vec)) { ph = skb_shinfo(skb)->destructor_arg; - BUG_ON(__packet_get_status(po, ph) != TP_STATUS_SENDING); BUG_ON(atomic_read(&po->tx_ring.pending) == 0); atomic_dec(&po->tx_ring.pending); __packet_set_status(po, ph, TP_STATUS_AVAILABLE); diff --git a/net/rds/page.c b/net/rds/page.c index 2499cd10842..9005a2c920e 100644 --- a/net/rds/page.c +++ b/net/rds/page.c @@ -74,11 +74,12 @@ int rds_page_copy_user(struct page *page, unsigned long offset, } EXPORT_SYMBOL_GPL(rds_page_copy_user); -/* - * Message allocation uses this to build up regions of a message. +/** + * rds_page_remainder_alloc - build up regions of a message. * - * @bytes - the number of bytes needed. - * @gfp - the waiting behaviour of the allocation + * @scat: Scatter list for message + * @bytes: the number of bytes needed. + * @gfp: the waiting behaviour of the allocation * * @gfp is always ored with __GFP_HIGHMEM. Callers must be prepared to * kmap the pages, etc. diff --git a/net/rds/recv.c b/net/rds/recv.c index 5c6e9f13202..9f0f17cf6bf 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -410,6 +410,8 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, rdsdebug("size %zu flags 0x%x timeo %ld\n", size, msg_flags, timeo); + msg->msg_namelen = 0; + if (msg_flags & MSG_OOB) goto out; @@ -485,6 +487,7 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, sin->sin_port = inc->i_hdr.h_sport; sin->sin_addr.s_addr = inc->i_saddr; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + msg->msg_namelen = sizeof(*sin); } break; } diff --git a/net/rfkill/core.c b/net/rfkill/core.c index f974961754c..752b72360eb 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -325,7 +325,7 @@ static void __rfkill_switch_all(const enum rfkill_type type, bool blocked) rfkill_global_states[type].cur = blocked; list_for_each_entry(rfkill, &rfkill_list, node) { - if (rfkill->type != type) + if (rfkill->type != type && type != RFKILL_TYPE_ALL) continue; rfkill_set_block(rfkill, blocked); diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c index 5d6b572a670..a9206087b4d 100644 --- a/net/rxrpc/ar-error.c +++ b/net/rxrpc/ar-error.c @@ -81,10 +81,6 @@ void rxrpc_UDP_error_report(struct sock *sk) _net("I/F MTU %u", mtu); } - /* ip_rt_frag_needed() may have eaten the info */ - if (mtu == 0) - mtu = ntohs(icmp_hdr(skb)->un.frag.mtu); - if (mtu == 0) { /* they didn't give us a size, estimate one */ if (mtu > 1500) { diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c index 16ae88762d0..e1ac183d50b 100644 --- a/net/rxrpc/ar-output.c +++ b/net/rxrpc/ar-output.c @@ -242,7 +242,7 @@ int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg, EXPORT_SYMBOL(rxrpc_kernel_send_data); -/* +/** * rxrpc_kernel_abort_call - Allow a kernel service to abort a call * @call: The call to be aborted * @abort_code: The abort code to stick into the ABORT packet diff --git a/net/sched/Kconfig b/net/sched/Kconfig index e7a8976bf25..62fb51face8 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -507,6 +507,26 @@ config NET_EMATCH_TEXT To compile this code as a module, choose M here: the module will be called em_text. +config NET_EMATCH_CANID + tristate "CAN Identifier" + depends on NET_EMATCH && CAN + ---help--- + Say Y here if you want to be able to classify CAN frames based + on CAN Identifier. + + To compile this code as a module, choose M here: the + module will be called em_canid. + +config NET_EMATCH_IPSET + tristate "IPset" + depends on NET_EMATCH && IP_SET + ---help--- + Say Y here if you want to be able to classify packets based on + ipset membership. + + To compile this code as a module, choose M here: the + module will be called em_ipset. + config NET_CLS_ACT bool "Actions" ---help--- diff --git a/net/sched/Makefile b/net/sched/Makefile index 5940a1992f0..978cbf004e8 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -55,3 +55,5 @@ obj-$(CONFIG_NET_EMATCH_NBYTE) += em_nbyte.o obj-$(CONFIG_NET_EMATCH_U32) += em_u32.o obj-$(CONFIG_NET_EMATCH_META) += em_meta.o obj-$(CONFIG_NET_EMATCH_TEXT) += em_text.o +obj-$(CONFIG_NET_EMATCH_CANID) += em_canid.o +obj-$(CONFIG_NET_EMATCH_IPSET) += em_ipset.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 5cfb160df06..e3d2c78cb52 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -652,27 +652,27 @@ tca_get_fill(struct sk_buff *skb, struct tc_action *a, u32 pid, u32 seq, unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*t), flags); - - t = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*t), flags); + if (!nlh) + goto out_nlmsg_trim; + t = nlmsg_data(nlh); t->tca_family = AF_UNSPEC; t->tca__pad1 = 0; t->tca__pad2 = 0; nest = nla_nest_start(skb, TCA_ACT_TAB); if (nest == NULL) - goto nla_put_failure; + goto out_nlmsg_trim; if (tcf_action_dump(skb, a, bind, ref) < 0) - goto nla_put_failure; + goto out_nlmsg_trim; nla_nest_end(skb, nest); nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; -nla_put_failure: -nlmsg_failure: +out_nlmsg_trim: nlmsg_trim(skb, b); return -1; } @@ -799,19 +799,21 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, if (a->ops == NULL) goto err_out; - nlh = NLMSG_PUT(skb, pid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t)); - t = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0); + if (!nlh) + goto out_module_put; + t = nlmsg_data(nlh); t->tca_family = AF_UNSPEC; t->tca__pad1 = 0; t->tca__pad2 = 0; nest = nla_nest_start(skb, TCA_ACT_TAB); if (nest == NULL) - goto nla_put_failure; + goto out_module_put; err = a->ops->walk(skb, &dcb, RTM_DELACTION, a); if (err < 0) - goto nla_put_failure; + goto out_module_put; if (err == 0) goto noflush_out; @@ -828,8 +830,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, return err; -nla_put_failure: -nlmsg_failure: +out_module_put: module_put(a->ops->owner); err_out: noflush_out: @@ -919,18 +920,20 @@ static int tcf_add_notify(struct net *net, struct tc_action *a, b = skb_tail_pointer(skb); - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*t), flags); - t = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*t), flags); + if (!nlh) + goto out_kfree_skb; + t = nlmsg_data(nlh); t->tca_family = AF_UNSPEC; t->tca__pad1 = 0; t->tca__pad2 = 0; nest = nla_nest_start(skb, TCA_ACT_TAB); if (nest == NULL) - goto nla_put_failure; + goto out_kfree_skb; if (tcf_action_dump(skb, a, 0, 0) < 0) - goto nla_put_failure; + goto out_kfree_skb; nla_nest_end(skb, nest); @@ -942,8 +945,7 @@ static int tcf_add_notify(struct net *net, struct tc_action *a, err = 0; return err; -nla_put_failure: -nlmsg_failure: +out_kfree_skb: kfree_skb(skb); return -1; } @@ -1062,7 +1064,7 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) struct tc_action_ops *a_o; struct tc_action a; int ret = 0; - struct tcamsg *t = (struct tcamsg *) NLMSG_DATA(cb->nlh); + struct tcamsg *t = (struct tcamsg *) nlmsg_data(cb->nlh); struct nlattr *kind = find_dump_kind(cb->nlh); if (kind == NULL) { @@ -1080,23 +1082,25 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) if (a_o->walk == NULL) { WARN(1, "tc_dump_action: %s !capable of dumping table\n", a_o->kind); - goto nla_put_failure; + goto out_module_put; } - nlh = NLMSG_PUT(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, - cb->nlh->nlmsg_type, sizeof(*t)); - t = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + cb->nlh->nlmsg_type, sizeof(*t), 0); + if (!nlh) + goto out_module_put; + t = nlmsg_data(nlh); t->tca_family = AF_UNSPEC; t->tca__pad1 = 0; t->tca__pad2 = 0; nest = nla_nest_start(skb, TCA_ACT_TAB); if (nest == NULL) - goto nla_put_failure; + goto out_module_put; ret = a_o->walk(skb, cb, RTM_GETACTION, &a); if (ret < 0) - goto nla_put_failure; + goto out_module_put; if (ret > 0) { nla_nest_end(skb, nest); @@ -1110,8 +1114,7 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) module_put(a_o->owner); return skb->len; -nla_put_failure: -nlmsg_failure: +out_module_put: module_put(a_o->owner); nlmsg_trim(skb, b); return skb->len; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index f10fb825644..05d60859d8e 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -67,6 +67,9 @@ static int tcf_gact_init(struct nlattr *nla, struct nlattr *est, struct tcf_common *pc; int ret = 0; int err; +#ifdef CONFIG_GACT_PROB + struct tc_gact_p *p_parm = NULL; +#endif if (nla == NULL) return -EINVAL; @@ -82,6 +85,12 @@ static int tcf_gact_init(struct nlattr *nla, struct nlattr *est, #ifndef CONFIG_GACT_PROB if (tb[TCA_GACT_PROB] != NULL) return -EOPNOTSUPP; +#else + if (tb[TCA_GACT_PROB]) { + p_parm = nla_data(tb[TCA_GACT_PROB]); + if (p_parm->ptype >= MAX_RAND) + return -EINVAL; + } #endif pc = tcf_hash_check(parm->index, a, bind, &gact_hash_info); @@ -103,8 +112,7 @@ static int tcf_gact_init(struct nlattr *nla, struct nlattr *est, spin_lock_bh(&gact->tcf_lock); gact->tcf_action = parm->action; #ifdef CONFIG_GACT_PROB - if (tb[TCA_GACT_PROB] != NULL) { - struct tc_gact_p *p_parm = nla_data(tb[TCA_GACT_PROB]); + if (p_parm) { gact->tcfg_paction = p_parm->paction; gact->tcfg_pval = p_parm->pval; gact->tcfg_ptype = p_parm->ptype; @@ -133,7 +141,7 @@ static int tcf_gact(struct sk_buff *skb, const struct tc_action *a, spin_lock(&gact->tcf_lock); #ifdef CONFIG_GACT_PROB - if (gact->tcfg_ptype && gact_rand[gact->tcfg_ptype] != NULL) + if (gact->tcfg_ptype) action = gact_rand[gact->tcfg_ptype](gact); else action = gact->tcf_action; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 60e281ad0f0..58fb3c7aab9 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -185,7 +185,12 @@ err3: err2: kfree(tname); err1: - kfree(pc); + if (ret == ACT_P_CREATED) { + if (est) + gen_kill_estimator(&pc->tcfc_bstats, + &pc->tcfc_rate_est); + kfree_rcu(pc, tcfc_rcu); + } return err; } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index fe81cc18e9e..9c0fd0c7881 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -200,13 +200,12 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, out: if (err) { m->tcf_qstats.overlimits++; - /* should we be asking for packet to be dropped? - * may make sense for redirect case only - */ - retval = TC_ACT_SHOT; - } else { + if (m->tcfm_eaction != TCA_EGRESS_MIRROR) + retval = TC_ACT_SHOT; + else + retval = m->tcf_action; + } else retval = m->tcf_action; - } spin_unlock(&m->tcf_lock); return retval; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 26aa2f6ce25..45c53ab067a 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -74,7 +74,10 @@ static int tcf_pedit_init(struct nlattr *nla, struct nlattr *est, p = to_pedit(pc); keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) { - kfree(pc); + if (est) + gen_kill_estimator(&pc->tcfc_bstats, + &pc->tcfc_rate_est); + kfree_rcu(pc, tcfc_rcu); return -ENOMEM; } ret = ACT_P_CREATED; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 3922f2a2821..3714f60f0b3 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -131,7 +131,10 @@ static int tcf_simp_init(struct nlattr *nla, struct nlattr *est, d = to_defact(pc); ret = alloc_defdata(d, defdata); if (ret < 0) { - kfree(pc); + if (est) + gen_kill_estimator(&pc->tcfc_bstats, + &pc->tcfc_rate_est); + kfree_rcu(pc, tcfc_rcu); return ret; } d->tcf_action = parm->action; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index f452f696b4b..6dd1131f2ec 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -140,7 +140,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, void *arg) int tp_created = 0; replay: - t = NLMSG_DATA(n); + t = nlmsg_data(n); protocol = TC_H_MIN(t->tcm_info); prio = TC_H_MAJ(t->tcm_info); nprio = prio; @@ -349,8 +349,10 @@ static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp, struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags); - tcm = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*tcm), flags); + if (!nlh) + goto out_nlmsg_trim; + tcm = nlmsg_data(nlh); tcm->tcm_family = AF_UNSPEC; tcm->tcm__pad1 = 0; tcm->tcm__pad2 = 0; @@ -368,7 +370,7 @@ static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp, nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; -nlmsg_failure: +out_nlmsg_trim: nla_put_failure: nlmsg_trim(skb, b); return -1; @@ -418,7 +420,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) struct net_device *dev; struct Qdisc *q; struct tcf_proto *tp, **chain; - struct tcmsg *tcm = (struct tcmsg *)NLMSG_DATA(cb->nlh); + struct tcmsg *tcm = nlmsg_data(cb->nlh); unsigned long cl = 0; const struct Qdisc_class_ops *cops; struct tcf_dump_args arg; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 36fec422740..44f405cb9aa 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -143,7 +143,7 @@ static int route4_classify(struct sk_buff *skb, const struct tcf_proto *tp, if (head == NULL) goto old_method; - iif = ((struct rtable *)dst)->rt_iif; + iif = inet_iif(skb); h = route4_fastmap_hash(id, iif); if (id == head->fastmap[h].id && diff --git a/net/sched/em_canid.c b/net/sched/em_canid.c new file mode 100644 index 00000000000..bfd34e4c1af --- /dev/null +++ b/net/sched/em_canid.c @@ -0,0 +1,240 @@ +/* + * em_canid.c Ematch rule to match CAN frames according to their CAN IDs + * + * This program is free software; you can distribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Idea: Oliver Hartkopp <oliver.hartkopp@volkswagen.de> + * Copyright: (c) 2011 Czech Technical University in Prague + * (c) 2011 Volkswagen Group Research + * Authors: Michal Sojka <sojkam1@fel.cvut.cz> + * Pavel Pisa <pisa@cmp.felk.cvut.cz> + * Rostislav Lisovy <lisovy@gmail.cz> + * Funded by: Volkswagen Group Research + */ + +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/skbuff.h> +#include <net/pkt_cls.h> +#include <linux/can.h> + +#define EM_CAN_RULES_MAX 500 + +struct canid_match { + /* For each SFF CAN ID (11 bit) there is one record in this bitfield */ + DECLARE_BITMAP(match_sff, (1 << CAN_SFF_ID_BITS)); + + int rules_count; + int sff_rules_count; + int eff_rules_count; + + /* + * Raw rules copied from netlink message; Used for sending + * information to userspace (when 'tc filter show' is invoked) + * AND when matching EFF frames + */ + struct can_filter rules_raw[]; +}; + +/** + * em_canid_get_id() - Extracts Can ID out of the sk_buff structure. + */ +static canid_t em_canid_get_id(struct sk_buff *skb) +{ + /* CAN ID is stored within the data field */ + struct can_frame *cf = (struct can_frame *)skb->data; + + return cf->can_id; +} + +static void em_canid_sff_match_add(struct canid_match *cm, u32 can_id, + u32 can_mask) +{ + int i; + + /* + * Limit can_mask and can_id to SFF range to + * protect against write after end of array + */ + can_mask &= CAN_SFF_MASK; + can_id &= can_mask; + + /* Single frame */ + if (can_mask == CAN_SFF_MASK) { + set_bit(can_id, cm->match_sff); + return; + } + + /* All frames */ + if (can_mask == 0) { + bitmap_fill(cm->match_sff, (1 << CAN_SFF_ID_BITS)); + return; + } + + /* + * Individual frame filter. + * Add record (set bit to 1) for each ID that + * conforms particular rule + */ + for (i = 0; i < (1 << CAN_SFF_ID_BITS); i++) { + if ((i & can_mask) == can_id) + set_bit(i, cm->match_sff); + } +} + +static inline struct canid_match *em_canid_priv(struct tcf_ematch *m) +{ + return (struct canid_match *)m->data; +} + +static int em_canid_match(struct sk_buff *skb, struct tcf_ematch *m, + struct tcf_pkt_info *info) +{ + struct canid_match *cm = em_canid_priv(m); + canid_t can_id; + int match = 0; + int i; + const struct can_filter *lp; + + can_id = em_canid_get_id(skb); + + if (can_id & CAN_EFF_FLAG) { + for (i = 0, lp = cm->rules_raw; + i < cm->eff_rules_count; i++, lp++) { + if (!(((lp->can_id ^ can_id) & lp->can_mask))) { + match = 1; + break; + } + } + } else { /* SFF */ + can_id &= CAN_SFF_MASK; + match = (test_bit(can_id, cm->match_sff) ? 1 : 0); + } + + return match; +} + +static int em_canid_change(struct tcf_proto *tp, void *data, int len, + struct tcf_ematch *m) +{ + struct can_filter *conf = data; /* Array with rules */ + struct canid_match *cm; + struct canid_match *cm_old = (struct canid_match *)m->data; + int i; + + if (!len) + return -EINVAL; + + if (len % sizeof(struct can_filter)) + return -EINVAL; + + if (len > sizeof(struct can_filter) * EM_CAN_RULES_MAX) + return -EINVAL; + + cm = kzalloc(sizeof(struct canid_match) + len, GFP_KERNEL); + if (!cm) + return -ENOMEM; + + cm->rules_count = len / sizeof(struct can_filter); + + /* + * We need two for() loops for copying rules into two contiguous + * areas in rules_raw to process all eff rules with a simple loop. + * NB: The configuration interface supports sff and eff rules. + * We do not support filters here that match for the same can_id + * provided in a SFF and EFF frame (e.g. 0x123 / 0x80000123). + * For this (unusual case) two filters have to be specified. The + * SFF/EFF separation is done with the CAN_EFF_FLAG in the can_id. + */ + + /* Fill rules_raw with EFF rules first */ + for (i = 0; i < cm->rules_count; i++) { + if (conf[i].can_id & CAN_EFF_FLAG) { + memcpy(cm->rules_raw + cm->eff_rules_count, + &conf[i], + sizeof(struct can_filter)); + + cm->eff_rules_count++; + } + } + + /* append SFF frame rules */ + for (i = 0; i < cm->rules_count; i++) { + if (!(conf[i].can_id & CAN_EFF_FLAG)) { + memcpy(cm->rules_raw + + cm->eff_rules_count + + cm->sff_rules_count, + &conf[i], sizeof(struct can_filter)); + + cm->sff_rules_count++; + + em_canid_sff_match_add(cm, + conf[i].can_id, conf[i].can_mask); + } + } + + m->datalen = sizeof(struct canid_match) + len; + m->data = (unsigned long)cm; + + if (cm_old != NULL) { + pr_err("canid: Configuring an existing ematch!\n"); + kfree(cm_old); + } + + return 0; +} + +static void em_canid_destroy(struct tcf_proto *tp, struct tcf_ematch *m) +{ + struct canid_match *cm = em_canid_priv(m); + + kfree(cm); +} + +static int em_canid_dump(struct sk_buff *skb, struct tcf_ematch *m) +{ + struct canid_match *cm = em_canid_priv(m); + + /* + * When configuring this ematch 'rules_count' is set not to exceed + * 'rules_raw' array size + */ + if (nla_put_nohdr(skb, sizeof(struct can_filter) * cm->rules_count, + &cm->rules_raw) < 0) + return -EMSGSIZE; + + return 0; +} + +static struct tcf_ematch_ops em_canid_ops = { + .kind = TCF_EM_CANID, + .change = em_canid_change, + .match = em_canid_match, + .destroy = em_canid_destroy, + .dump = em_canid_dump, + .owner = THIS_MODULE, + .link = LIST_HEAD_INIT(em_canid_ops.link) +}; + +static int __init init_em_canid(void) +{ + return tcf_em_register(&em_canid_ops); +} + +static void __exit exit_em_canid(void) +{ + tcf_em_unregister(&em_canid_ops); +} + +MODULE_LICENSE("GPL"); + +module_init(init_em_canid); +module_exit(exit_em_canid); + +MODULE_ALIAS_TCF_EMATCH(TCF_EM_CANID); diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c new file mode 100644 index 00000000000..3130320997e --- /dev/null +++ b/net/sched/em_ipset.c @@ -0,0 +1,135 @@ +/* + * net/sched/em_ipset.c ipset ematch + * + * Copyright (c) 2012 Florian Westphal <fw@strlen.de> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ + +#include <linux/gfp.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/skbuff.h> +#include <linux/netfilter/xt_set.h> +#include <linux/ipv6.h> +#include <net/ip.h> +#include <net/pkt_cls.h> + +static int em_ipset_change(struct tcf_proto *tp, void *data, int data_len, + struct tcf_ematch *em) +{ + struct xt_set_info *set = data; + ip_set_id_t index; + + if (data_len != sizeof(*set)) + return -EINVAL; + + index = ip_set_nfnl_get_byindex(set->index); + if (index == IPSET_INVALID_ID) + return -ENOENT; + + em->datalen = sizeof(*set); + em->data = (unsigned long)kmemdup(data, em->datalen, GFP_KERNEL); + if (em->data) + return 0; + + ip_set_nfnl_put(index); + return -ENOMEM; +} + +static void em_ipset_destroy(struct tcf_proto *p, struct tcf_ematch *em) +{ + const struct xt_set_info *set = (const void *) em->data; + if (set) { + ip_set_nfnl_put(set->index); + kfree((void *) em->data); + } +} + +static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em, + struct tcf_pkt_info *info) +{ + struct ip_set_adt_opt opt; + struct xt_action_param acpar; + const struct xt_set_info *set = (const void *) em->data; + struct net_device *dev, *indev = NULL; + int ret, network_offset; + + switch (skb->protocol) { + case htons(ETH_P_IP): + acpar.family = NFPROTO_IPV4; + if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) + return 0; + acpar.thoff = ip_hdrlen(skb); + break; + case htons(ETH_P_IPV6): + acpar.family = NFPROTO_IPV6; + if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) + return 0; + /* doesn't call ipv6_find_hdr() because ipset doesn't use thoff, yet */ + acpar.thoff = sizeof(struct ipv6hdr); + break; + default: + return 0; + } + + acpar.hooknum = 0; + + opt.family = acpar.family; + opt.dim = set->dim; + opt.flags = set->flags; + opt.cmdflags = 0; + opt.timeout = ~0u; + + network_offset = skb_network_offset(skb); + skb_pull(skb, network_offset); + + dev = skb->dev; + + rcu_read_lock(); + + if (dev && skb->skb_iif) + indev = dev_get_by_index_rcu(dev_net(dev), skb->skb_iif); + + acpar.in = indev ? indev : dev; + acpar.out = dev; + + ret = ip_set_test(set->index, skb, &acpar, &opt); + + rcu_read_unlock(); + + skb_push(skb, network_offset); + return ret; +} + +static struct tcf_ematch_ops em_ipset_ops = { + .kind = TCF_EM_IPSET, + .change = em_ipset_change, + .destroy = em_ipset_destroy, + .match = em_ipset_match, + .owner = THIS_MODULE, + .link = LIST_HEAD_INIT(em_ipset_ops.link) +}; + +static int __init init_em_ipset(void) +{ + return tcf_em_register(&em_ipset_ops); +} + +static void __exit exit_em_ipset(void) +{ + tcf_em_unregister(&em_ipset_ops); +} + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); +MODULE_DESCRIPTION("TC extended match for IP sets"); + +module_init(init_em_ipset); +module_exit(exit_em_ipset); + +MODULE_ALIAS_TCF_EMATCH(TCF_EM_IPSET); diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 4790c696cbc..4ab6e332557 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -264,7 +264,7 @@ META_COLLECTOR(int_rtiif) if (unlikely(skb_rtable(skb) == NULL)) *err = -1; else - dst->value = skb_rtable(skb)->rt_iif; + dst->value = inet_iif(skb); } /************************************************************************** diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 085ce53d570..a08b4ab3e42 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -973,7 +973,7 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) { struct net *net = sock_net(skb->sk); - struct tcmsg *tcm = NLMSG_DATA(n); + struct tcmsg *tcm = nlmsg_data(n); struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; u32 clid = tcm->tcm_parent; @@ -1046,7 +1046,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) replay: /* Reinit, just in case something touches this. */ - tcm = NLMSG_DATA(n); + tcm = nlmsg_data(n); clid = tcm->tcm_parent; q = p = NULL; @@ -1193,8 +1193,10 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, struct gnet_dump d; struct qdisc_size_table *stab; - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags); - tcm = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*tcm), flags); + if (!nlh) + goto out_nlmsg_trim; + tcm = nlmsg_data(nlh); tcm->tcm_family = AF_UNSPEC; tcm->tcm__pad1 = 0; tcm->tcm__pad2 = 0; @@ -1230,7 +1232,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; -nlmsg_failure: +out_nlmsg_trim: nla_put_failure: nlmsg_trim(skb, b); return -1; @@ -1366,7 +1368,7 @@ done: static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) { struct net *net = sock_net(skb->sk); - struct tcmsg *tcm = NLMSG_DATA(n); + struct tcmsg *tcm = nlmsg_data(n); struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; struct Qdisc *q = NULL; @@ -1498,8 +1500,10 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, struct gnet_dump d; const struct Qdisc_class_ops *cl_ops = q->ops->cl_ops; - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags); - tcm = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*tcm), flags); + if (!nlh) + goto out_nlmsg_trim; + tcm = nlmsg_data(nlh); tcm->tcm_family = AF_UNSPEC; tcm->tcm__pad1 = 0; tcm->tcm__pad2 = 0; @@ -1525,7 +1529,7 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; -nlmsg_failure: +out_nlmsg_trim: nla_put_failure: nlmsg_trim(skb, b); return -1; @@ -1616,7 +1620,7 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) { - struct tcmsg *tcm = (struct tcmsg *)NLMSG_DATA(cb->nlh); + struct tcmsg *tcm = nlmsg_data(cb->nlh); struct net *net = sock_net(skb->sk); struct netdev_queue *dev_queue; struct net_device *dev; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index c412ad0d030..298c0ddfb57 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -380,7 +380,14 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; } - skb_orphan(skb); + /* If a delay is expected, orphan the skb. (orphaning usually takes + * place at TX completion time, so _before_ the link transit delay) + * Ideally, this orphaning should be done after the rate limiting + * module, because this breaks TCP Small Queue, and other mechanisms + * based on socket sk_wmem_alloc. + */ + if (q->latency || q->jitter) + skb_orphan(skb); /* * If we need to duplicate packet, then re-insert at top of the diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 9af01f3df18..e4723d31fdd 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -203,6 +203,34 @@ out: return index; } +/* Length of the next packet (0 if the queue is empty). */ +static unsigned int qdisc_peek_len(struct Qdisc *sch) +{ + struct sk_buff *skb; + + skb = sch->ops->peek(sch); + return skb ? qdisc_pkt_len(skb) : 0; +} + +static void qfq_deactivate_class(struct qfq_sched *, struct qfq_class *); +static void qfq_activate_class(struct qfq_sched *q, struct qfq_class *cl, + unsigned int len); + +static void qfq_update_class_params(struct qfq_sched *q, struct qfq_class *cl, + u32 lmax, u32 inv_w, int delta_w) +{ + int i; + + /* update qfq-specific data */ + cl->lmax = lmax; + cl->inv_w = inv_w; + i = qfq_calc_index(cl->inv_w, cl->lmax); + + cl->grp = &q->groups[i]; + + q->wsum += delta_w; +} + static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, unsigned long *arg) { @@ -250,6 +278,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, lmax = 1UL << QFQ_MTU_SHIFT; if (cl != NULL) { + bool need_reactivation = false; + if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, &cl->rate_est, qdisc_root_sleeping_lock(sch), @@ -258,12 +288,29 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, return err; } - if (inv_w != cl->inv_w) { - sch_tree_lock(sch); - q->wsum += delta_w; - cl->inv_w = inv_w; - sch_tree_unlock(sch); + if (lmax == cl->lmax && inv_w == cl->inv_w) + return 0; /* nothing to update */ + + i = qfq_calc_index(inv_w, lmax); + sch_tree_lock(sch); + if (&q->groups[i] != cl->grp && cl->qdisc->q.qlen > 0) { + /* + * shift cl->F back, to not charge the + * class for the not-yet-served head + * packet + */ + cl->F = cl->S; + /* remove class from its slot in the old group */ + qfq_deactivate_class(q, cl); + need_reactivation = true; } + + qfq_update_class_params(q, cl, lmax, inv_w, delta_w); + + if (need_reactivation) /* activate in new group */ + qfq_activate_class(q, cl, qdisc_peek_len(cl->qdisc)); + sch_tree_unlock(sch); + return 0; } @@ -273,11 +320,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cl->refcnt = 1; cl->common.classid = classid; - cl->lmax = lmax; - cl->inv_w = inv_w; - i = qfq_calc_index(cl->inv_w, cl->lmax); - cl->grp = &q->groups[i]; + qfq_update_class_params(q, cl, lmax, inv_w, delta_w); cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); @@ -294,7 +338,6 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, return err; } } - q->wsum += weight; sch_tree_lock(sch); qdisc_class_hash_insert(&q->clhash, &cl->common); @@ -711,15 +754,6 @@ static void qfq_update_eligible(struct qfq_sched *q, u64 old_V) } } -/* What is length of next packet in queue (0 if queue is empty) */ -static unsigned int qdisc_peek_len(struct Qdisc *sch) -{ - struct sk_buff *skb; - - skb = sch->ops->peek(sch); - return skb ? qdisc_pkt_len(skb) : 0; -} - /* * Updates the class, returns true if also the group needs to be updated. */ @@ -843,11 +877,8 @@ static void qfq_update_start(struct qfq_sched *q, struct qfq_class *cl) static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct qfq_sched *q = qdisc_priv(sch); - struct qfq_group *grp; struct qfq_class *cl; int err; - u64 roundedS; - int s; cl = qfq_classify(skb, sch, &err); if (cl == NULL) { @@ -876,11 +907,25 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) return err; /* If reach this point, queue q was idle */ - grp = cl->grp; + qfq_activate_class(q, cl, qdisc_pkt_len(skb)); + + return err; +} + +/* + * Handle class switch from idle to backlogged. + */ +static void qfq_activate_class(struct qfq_sched *q, struct qfq_class *cl, + unsigned int pkt_len) +{ + struct qfq_group *grp = cl->grp; + u64 roundedS; + int s; + qfq_update_start(q, cl); /* compute new finish time and rounded start. */ - cl->F = cl->S + (u64)qdisc_pkt_len(skb) * cl->inv_w; + cl->F = cl->S + (u64)pkt_len * cl->inv_w; roundedS = qfq_round_down(cl->S, grp->slot_shift); /* @@ -917,8 +962,6 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) skip_update: qfq_slot_insert(grp, cl, roundedS); - - return err; } diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index ca0c29695d5..47416716294 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -67,7 +67,6 @@ struct teql_master { struct teql_sched_data { struct Qdisc *next; struct teql_master *m; - struct neighbour *ncache; struct sk_buff_head q; }; @@ -134,7 +133,6 @@ teql_reset(struct Qdisc *sch) skb_queue_purge(&dat->q); sch->q.qlen = 0; - teql_neigh_release(xchg(&dat->ncache, NULL)); } static void @@ -166,7 +164,6 @@ teql_destroy(struct Qdisc *sch) } } skb_queue_purge(&dat->q); - teql_neigh_release(xchg(&dat->ncache, NULL)); break; } @@ -225,21 +222,25 @@ static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt) static int __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device *dev, struct netdev_queue *txq, - struct neighbour *mn) + struct dst_entry *dst) { - struct teql_sched_data *q = qdisc_priv(txq->qdisc); - struct neighbour *n = q->ncache; + struct neighbour *n; + int err = 0; - if (mn->tbl == NULL) - return -EINVAL; - if (n && n->tbl == mn->tbl && - memcmp(n->primary_key, mn->primary_key, mn->tbl->key_len) == 0) { - atomic_inc(&n->refcnt); - } else { - n = __neigh_lookup_errno(mn->tbl, mn->primary_key, dev); - if (IS_ERR(n)) - return PTR_ERR(n); + n = dst_neigh_lookup_skb(dst, skb); + if (!n) + return -ENOENT; + + if (dst->dev != dev) { + struct neighbour *mn; + + mn = __neigh_lookup_errno(n->tbl, n->primary_key, dev); + neigh_release(n); + if (IS_ERR(mn)) + return PTR_ERR(mn); + n = mn; } + if (neigh_event_send(n, skb_res) == 0) { int err; char haddr[MAX_ADDR_LEN]; @@ -248,15 +249,13 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, err = dev_hard_header(skb, dev, ntohs(skb->protocol), haddr, NULL, skb->len); - if (err < 0) { - neigh_release(n); - return -EINVAL; - } - teql_neigh_release(xchg(&q->ncache, n)); - return 0; + if (err < 0) + err = -EINVAL; + } else { + err = (skb_res == NULL) ? -EAGAIN : 1; } neigh_release(n); - return (skb_res == NULL) ? -EAGAIN : 1; + return err; } static inline int teql_resolve(struct sk_buff *skb, @@ -265,7 +264,6 @@ static inline int teql_resolve(struct sk_buff *skb, struct netdev_queue *txq) { struct dst_entry *dst = skb_dst(skb); - struct neighbour *mn; int res; if (txq->qdisc == &noop_qdisc) @@ -275,8 +273,7 @@ static inline int teql_resolve(struct sk_buff *skb, return 0; rcu_read_lock(); - mn = dst_get_neighbour_noref(dst); - res = mn ? __teql_resolve(skb, skb_res, dev, txq, mn) : 0; + res = __teql_resolve(skb, skb_res, dev, txq, dst); rcu_read_unlock(); return res; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index b16517ee1aa..ebaef3ed606 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -124,6 +124,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a * socket values. */ asoc->max_retrans = sp->assocparams.sasoc_asocmaxrxt; + asoc->pf_retrans = sctp_pf_retrans; + asoc->rto_initial = msecs_to_jiffies(sp->rtoinfo.srto_initial); asoc->rto_max = msecs_to_jiffies(sp->rtoinfo.srto_max); asoc->rto_min = msecs_to_jiffies(sp->rtoinfo.srto_min); @@ -686,6 +688,9 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, /* Set the path max_retrans. */ peer->pathmaxrxt = asoc->pathmaxrxt; + /* And the partial failure retrnas threshold */ + peer->pf_retrans = asoc->pf_retrans; + /* Initialize the peer's SACK delay timeout based on the * association configured value. */ @@ -841,6 +846,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, struct sctp_ulpevent *event; struct sockaddr_storage addr; int spc_state = 0; + bool ulp_notify = true; /* Record the transition on the transport. */ switch (command) { @@ -854,6 +860,14 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, spc_state = SCTP_ADDR_CONFIRMED; else spc_state = SCTP_ADDR_AVAILABLE; + /* Don't inform ULP about transition from PF to + * active state and set cwnd to 1, see SCTP + * Quick failover draft section 5.1, point 5 + */ + if (transport->state == SCTP_PF) { + ulp_notify = false; + transport->cwnd = 1; + } transport->state = SCTP_ACTIVE; break; @@ -872,6 +886,11 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, spc_state = SCTP_ADDR_UNREACHABLE; break; + case SCTP_TRANSPORT_PF: + transport->state = SCTP_PF; + ulp_notify = false; + break; + default: return; } @@ -879,12 +898,15 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, /* Generate and send a SCTP_PEER_ADDR_CHANGE notification to the * user. */ - memset(&addr, 0, sizeof(struct sockaddr_storage)); - memcpy(&addr, &transport->ipaddr, transport->af_specific->sockaddr_len); - event = sctp_ulpevent_make_peer_addr_change(asoc, &addr, - 0, spc_state, error, GFP_ATOMIC); - if (event) - sctp_ulpq_tail_event(&asoc->ulpq, event); + if (ulp_notify) { + memset(&addr, 0, sizeof(struct sockaddr_storage)); + memcpy(&addr, &transport->ipaddr, + transport->af_specific->sockaddr_len); + event = sctp_ulpevent_make_peer_addr_change(asoc, &addr, + 0, spc_state, error, GFP_ATOMIC); + if (event) + sctp_ulpq_tail_event(&asoc->ulpq, event); + } /* Select new active and retran paths. */ @@ -900,7 +922,8 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, transports) { if ((t->state == SCTP_INACTIVE) || - (t->state == SCTP_UNCONFIRMED)) + (t->state == SCTP_UNCONFIRMED) || + (t->state == SCTP_PF)) continue; if (!first || t->last_time_heard > first->last_time_heard) { second = first; @@ -1360,7 +1383,7 @@ struct sctp_transport *sctp_assoc_choose_alter_transport( /* Update the association's pmtu and frag_point by going through all the * transports. This routine is called when a transport's PMTU has changed. */ -void sctp_assoc_sync_pmtu(struct sctp_association *asoc) +void sctp_assoc_sync_pmtu(struct sock *sk, struct sctp_association *asoc) { struct sctp_transport *t; __u32 pmtu = 0; @@ -1372,7 +1395,7 @@ void sctp_assoc_sync_pmtu(struct sctp_association *asoc) list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { if (t->pmtu_pending && t->dst) { - sctp_transport_update_pmtu(t, dst_mtu(t->dst)); + sctp_transport_update_pmtu(sk, t, dst_mtu(t->dst)); t->pmtu_pending = 0; } if (!pmtu || (t->pathmtu < pmtu)) diff --git a/net/sctp/input.c b/net/sctp/input.c index 8b9b6790a3d..e64d5210ed1 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -408,10 +408,10 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, if (t->param_flags & SPP_PMTUD_ENABLE) { /* Update transports view of the MTU */ - sctp_transport_update_pmtu(t, pmtu); + sctp_transport_update_pmtu(sk, t, pmtu); /* Update association pmtu. */ - sctp_assoc_sync_pmtu(asoc); + sctp_assoc_sync_pmtu(sk, asoc); } /* Retransmit with the new pmtu setting. @@ -423,6 +423,18 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, sctp_retransmit(&asoc->outqueue, t, SCTP_RTXR_PMTUD); } +void sctp_icmp_redirect(struct sock *sk, struct sctp_transport *t, + struct sk_buff *skb) +{ + struct dst_entry *dst; + + if (!t) + return; + dst = sctp_transport_dst_check(t); + if (dst) + dst->ops->redirect(dst, sk, skb); +} + /* * SCTP Implementer's Guide, 2.37 ICMP handling procedures * @@ -628,6 +640,10 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info) err = EHOSTUNREACH; break; + case ICMP_REDIRECT: + sctp_icmp_redirect(sk, transport, skb); + err = 0; + break; default: goto out_unlock; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 91f479121c5..ed7139ea797 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -185,6 +185,9 @@ SCTP_STATIC void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, goto out_unlock; } break; + case NDISC_REDIRECT: + sctp_icmp_redirect(sk, transport, skb); + break; default: break; } diff --git a/net/sctp/output.c b/net/sctp/output.c index 6ae47acaaec..838e18b4d7e 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -64,6 +64,8 @@ #include <net/sctp/checksum.h> /* Forward declarations for private helpers. */ +static sctp_xmit_t __sctp_packet_append_chunk(struct sctp_packet *packet, + struct sctp_chunk *chunk); static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, struct sctp_chunk *chunk); static void sctp_packet_append_data(struct sctp_packet *packet, @@ -224,7 +226,10 @@ static sctp_xmit_t sctp_packet_bundle_auth(struct sctp_packet *pkt, if (!auth) return retval; - retval = sctp_packet_append_chunk(pkt, auth); + retval = __sctp_packet_append_chunk(pkt, auth); + + if (retval != SCTP_XMIT_OK) + sctp_chunk_free(auth); return retval; } @@ -256,48 +261,31 @@ static sctp_xmit_t sctp_packet_bundle_sack(struct sctp_packet *pkt, asoc->a_rwnd = asoc->rwnd; sack = sctp_make_sack(asoc); if (sack) { - retval = sctp_packet_append_chunk(pkt, sack); + retval = __sctp_packet_append_chunk(pkt, sack); + if (retval != SCTP_XMIT_OK) { + sctp_chunk_free(sack); + goto out; + } asoc->peer.sack_needed = 0; if (del_timer(timer)) sctp_association_put(asoc); } } } +out: return retval; } + /* Append a chunk to the offered packet reporting back any inability to do * so. */ -sctp_xmit_t sctp_packet_append_chunk(struct sctp_packet *packet, - struct sctp_chunk *chunk) +static sctp_xmit_t __sctp_packet_append_chunk(struct sctp_packet *packet, + struct sctp_chunk *chunk) { sctp_xmit_t retval = SCTP_XMIT_OK; __u16 chunk_len = WORD_ROUND(ntohs(chunk->chunk_hdr->length)); - SCTP_DEBUG_PRINTK("%s: packet:%p chunk:%p\n", __func__, packet, - chunk); - - /* Data chunks are special. Before seeing what else we can - * bundle into this packet, check to see if we are allowed to - * send this DATA. - */ - if (sctp_chunk_is_data(chunk)) { - retval = sctp_packet_can_append_data(packet, chunk); - if (retval != SCTP_XMIT_OK) - goto finish; - } - - /* Try to bundle AUTH chunk */ - retval = sctp_packet_bundle_auth(packet, chunk); - if (retval != SCTP_XMIT_OK) - goto finish; - - /* Try to bundle SACK chunk */ - retval = sctp_packet_bundle_sack(packet, chunk); - if (retval != SCTP_XMIT_OK) - goto finish; - /* Check to see if this chunk will fit into the packet */ retval = sctp_packet_will_fit(packet, chunk, chunk_len); if (retval != SCTP_XMIT_OK) @@ -339,6 +327,43 @@ finish: return retval; } +/* Append a chunk to the offered packet reporting back any inability to do + * so. + */ +sctp_xmit_t sctp_packet_append_chunk(struct sctp_packet *packet, + struct sctp_chunk *chunk) +{ + sctp_xmit_t retval = SCTP_XMIT_OK; + + SCTP_DEBUG_PRINTK("%s: packet:%p chunk:%p\n", __func__, packet, + chunk); + + /* Data chunks are special. Before seeing what else we can + * bundle into this packet, check to see if we are allowed to + * send this DATA. + */ + if (sctp_chunk_is_data(chunk)) { + retval = sctp_packet_can_append_data(packet, chunk); + if (retval != SCTP_XMIT_OK) + goto finish; + } + + /* Try to bundle AUTH chunk */ + retval = sctp_packet_bundle_auth(packet, chunk); + if (retval != SCTP_XMIT_OK) + goto finish; + + /* Try to bundle SACK chunk */ + retval = sctp_packet_bundle_sack(packet, chunk); + if (retval != SCTP_XMIT_OK) + goto finish; + + retval = __sctp_packet_append_chunk(packet, chunk); + +finish: + return retval; +} + /* All packets are sent to the network through this function from * sctp_outq_tail(). * @@ -385,7 +410,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) if (!sctp_transport_dst_check(tp)) { sctp_transport_route(tp, NULL, sctp_sk(sk)); if (asoc && (asoc->param_flags & SPP_PMTUD_ENABLE)) { - sctp_assoc_sync_pmtu(asoc); + sctp_assoc_sync_pmtu(sk, asoc); } } dst = dst_clone(tp->dst); diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index a0fa19f5650..e7aa177c952 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -792,7 +792,8 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) if (!new_transport) new_transport = asoc->peer.active_path; } else if ((new_transport->state == SCTP_INACTIVE) || - (new_transport->state == SCTP_UNCONFIRMED)) { + (new_transport->state == SCTP_UNCONFIRMED) || + (new_transport->state == SCTP_PF)) { /* If the chunk is Heartbeat or Heartbeat Ack, * send it to chunk->transport, even if it's * inactive. @@ -987,7 +988,8 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) new_transport = chunk->transport; if (!new_transport || ((new_transport->state == SCTP_INACTIVE) || - (new_transport->state == SCTP_UNCONFIRMED))) + (new_transport->state == SCTP_UNCONFIRMED) || + (new_transport->state == SCTP_PF))) new_transport = asoc->peer.active_path; if (new_transport->state == SCTP_UNCONFIRMED) continue; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 9c90811d113..1f89c4e6964 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -568,7 +568,7 @@ static void sctp_v4_get_saddr(struct sctp_sock *sk, /* What interface did this skb arrive on? */ static int sctp_v4_skb_iif(const struct sk_buff *skb) { - return skb_rtable(skb)->rt_iif; + return inet_iif(skb); } /* Was this packet marked by Explicit Congestion Notification? */ diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index b6de71efb14..479a70ef6ff 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -132,7 +132,7 @@ void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code, * abort chunk. Differs from sctp_init_cause in that it won't oops * if there isn't enough space in the op error chunk */ -int sctp_init_cause_fixed(struct sctp_chunk *chunk, __be16 cause_code, +static int sctp_init_cause_fixed(struct sctp_chunk *chunk, __be16 cause_code, size_t paylen) { sctp_errhdr_t err; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 8716da1a859..fe99628e125 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -76,6 +76,8 @@ static int sctp_side_effects(sctp_event_t event_type, sctp_subtype_t subtype, sctp_cmd_seq_t *commands, gfp_t gfp); +static void sctp_cmd_hb_timer_update(sctp_cmd_seq_t *cmds, + struct sctp_transport *t); /******************************************************************** * Helper functions ********************************************************************/ @@ -470,7 +472,8 @@ sctp_timer_event_t *sctp_timer_events[SCTP_NUM_TIMEOUT_TYPES] = { * notification SHOULD be sent to the upper layer. * */ -static void sctp_do_8_2_transport_strike(struct sctp_association *asoc, +static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands, + struct sctp_association *asoc, struct sctp_transport *transport, int is_hb) { @@ -495,6 +498,23 @@ static void sctp_do_8_2_transport_strike(struct sctp_association *asoc, transport->error_count++; } + /* If the transport error count is greater than the pf_retrans + * threshold, and less than pathmaxrtx, then mark this transport + * as Partially Failed, ee SCTP Quick Failover Draft, secon 5.1, + * point 1 + */ + if ((transport->state != SCTP_PF) && + (asoc->pf_retrans < transport->pathmaxrxt) && + (transport->error_count > asoc->pf_retrans)) { + + sctp_assoc_control_transport(asoc, transport, + SCTP_TRANSPORT_PF, + 0); + + /* Update the hb timer to resend a heartbeat every rto */ + sctp_cmd_hb_timer_update(commands, transport); + } + if (transport->state != SCTP_INACTIVE && (transport->error_count > transport->pathmaxrxt)) { SCTP_DEBUG_PRINTK_IPADDR("transport_strike:association %p", @@ -699,6 +719,10 @@ static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds, SCTP_HEARTBEAT_SUCCESS); } + if (t->state == SCTP_PF) + sctp_assoc_control_transport(asoc, t, SCTP_TRANSPORT_UP, + SCTP_HEARTBEAT_SUCCESS); + /* The receiver of the HEARTBEAT ACK should also perform an * RTT measurement for that destination transport address * using the time value carried in the HEARTBEAT ACK chunk. @@ -1565,8 +1589,8 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_STRIKE: /* Mark one strike against a transport. */ - sctp_do_8_2_transport_strike(asoc, cmd->obj.transport, - 0); + sctp_do_8_2_transport_strike(commands, asoc, + cmd->obj.transport, 0); break; case SCTP_CMD_TRANSPORT_IDLE: @@ -1576,7 +1600,8 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_TRANSPORT_HB_SENT: t = cmd->obj.transport; - sctp_do_8_2_transport_strike(asoc, t, 1); + sctp_do_8_2_transport_strike(commands, asoc, + t, 1); t->hb_sent = 1; break; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 31c7bfcd9b5..5e259817a7f 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1859,7 +1859,7 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, } if (asoc->pmtu_pending) - sctp_assoc_pending_pmtu(asoc); + sctp_assoc_pending_pmtu(sk, asoc); /* If fragmentation is disabled and the message length exceeds the * association fragmentation point, return EMSGSIZE. The I-D @@ -2373,7 +2373,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, if ((params->spp_flags & SPP_PMTUD_DISABLE) && params->spp_pathmtu) { if (trans) { trans->pathmtu = params->spp_pathmtu; - sctp_assoc_sync_pmtu(asoc); + sctp_assoc_sync_pmtu(sctp_opt2sk(sp), asoc); } else if (asoc) { asoc->pathmtu = params->spp_pathmtu; sctp_frag_point(asoc, params->spp_pathmtu); @@ -2390,7 +2390,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, (trans->param_flags & ~SPP_PMTUD) | pmtud_change; if (update) { sctp_transport_pmtu(trans, sctp_opt2sk(sp)); - sctp_assoc_sync_pmtu(asoc); + sctp_assoc_sync_pmtu(sctp_opt2sk(sp), asoc); } } else if (asoc) { asoc->param_flags = @@ -3478,6 +3478,56 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval, } +/* + * SCTP_PEER_ADDR_THLDS + * + * This option allows us to alter the partially failed threshold for one or all + * transports in an association. See Section 6.1 of: + * http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt + */ +static int sctp_setsockopt_paddr_thresholds(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_paddrthlds val; + struct sctp_transport *trans; + struct sctp_association *asoc; + + if (optlen < sizeof(struct sctp_paddrthlds)) + return -EINVAL; + if (copy_from_user(&val, (struct sctp_paddrthlds __user *)optval, + sizeof(struct sctp_paddrthlds))) + return -EFAULT; + + + if (sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { + asoc = sctp_id2assoc(sk, val.spt_assoc_id); + if (!asoc) + return -ENOENT; + list_for_each_entry(trans, &asoc->peer.transport_addr_list, + transports) { + if (val.spt_pathmaxrxt) + trans->pathmaxrxt = val.spt_pathmaxrxt; + trans->pf_retrans = val.spt_pathpfthld; + } + + if (val.spt_pathmaxrxt) + asoc->pathmaxrxt = val.spt_pathmaxrxt; + asoc->pf_retrans = val.spt_pathpfthld; + } else { + trans = sctp_addr_id2transport(sk, &val.spt_address, + val.spt_assoc_id); + if (!trans) + return -ENOENT; + + if (val.spt_pathmaxrxt) + trans->pathmaxrxt = val.spt_pathmaxrxt; + trans->pf_retrans = val.spt_pathpfthld; + } + + return 0; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -3627,6 +3677,9 @@ SCTP_STATIC int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_AUTO_ASCONF: retval = sctp_setsockopt_auto_asconf(sk, optval, optlen); break; + case SCTP_PEER_ADDR_THLDS: + retval = sctp_setsockopt_paddr_thresholds(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -5498,6 +5551,51 @@ static int sctp_getsockopt_assoc_ids(struct sock *sk, int len, return 0; } +/* + * SCTP_PEER_ADDR_THLDS + * + * This option allows us to fetch the partially failed threshold for one or all + * transports in an association. See Section 6.1 of: + * http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt + */ +static int sctp_getsockopt_paddr_thresholds(struct sock *sk, + char __user *optval, + int len, + int __user *optlen) +{ + struct sctp_paddrthlds val; + struct sctp_transport *trans; + struct sctp_association *asoc; + + if (len < sizeof(struct sctp_paddrthlds)) + return -EINVAL; + len = sizeof(struct sctp_paddrthlds); + if (copy_from_user(&val, (struct sctp_paddrthlds __user *)optval, len)) + return -EFAULT; + + if (sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { + asoc = sctp_id2assoc(sk, val.spt_assoc_id); + if (!asoc) + return -ENOENT; + + val.spt_pathpfthld = asoc->pf_retrans; + val.spt_pathmaxrxt = asoc->pathmaxrxt; + } else { + trans = sctp_addr_id2transport(sk, &val.spt_address, + val.spt_assoc_id); + if (!trans) + return -ENOENT; + + val.spt_pathmaxrxt = trans->pathmaxrxt; + val.spt_pathpfthld = trans->pf_retrans; + } + + if (put_user(len, optlen) || copy_to_user(optval, &val, len)) + return -EFAULT; + + return 0; +} + SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -5636,6 +5734,9 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname, case SCTP_AUTO_ASCONF: retval = sctp_getsockopt_auto_asconf(sk, len, optval, optlen); break; + case SCTP_PEER_ADDR_THLDS: + retval = sctp_getsockopt_paddr_thresholds(sk, optval, len, optlen); + break; default: retval = -ENOPROTOOPT; break; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index e5fe639c89e..2b2bfe933ff 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -141,6 +141,15 @@ static ctl_table sctp_table[] = { .extra2 = &int_max }, { + .procname = "pf_retrans", + .data = &sctp_pf_retrans, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &int_max + }, + { .procname = "max_init_retransmits", .data = &sctp_max_retrans_init, .maxlen = sizeof(int), diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 1dcceb6e0ce..c97472b248a 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -87,6 +87,7 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, /* Initialize the default path max_retrans. */ peer->pathmaxrxt = sctp_max_retrans_path; + peer->pf_retrans = sctp_pf_retrans; INIT_LIST_HEAD(&peer->transmitted); INIT_LIST_HEAD(&peer->send_ready); @@ -216,7 +217,7 @@ void sctp_transport_set_owner(struct sctp_transport *transport, void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) { /* If we don't have a fresh route, look one up */ - if (!transport->dst || transport->dst->obsolete > 1) { + if (!transport->dst || transport->dst->obsolete) { dst_release(transport->dst); transport->af_specific->get_dst(transport, &transport->saddr, &transport->fl, sk); @@ -228,7 +229,7 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; } -void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) +void sctp_transport_update_pmtu(struct sock *sk, struct sctp_transport *t, u32 pmtu) { struct dst_entry *dst; @@ -245,8 +246,16 @@ void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) } dst = sctp_transport_dst_check(t); - if (dst) - dst->ops->update_pmtu(dst, pmtu); + if (!dst) + t->af_specific->get_dst(t, &t->saddr, &t->fl, sk); + + if (dst) { + dst->ops->update_pmtu(dst, sk, NULL, pmtu); + + dst = sctp_transport_dst_check(t); + if (!dst) + t->af_specific->get_dst(t, &t->saddr, &t->fl, sk); + } } /* Caches the dst entry and source address for a transport's destination @@ -587,7 +596,8 @@ unsigned long sctp_transport_timeout(struct sctp_transport *t) { unsigned long timeout; timeout = t->rto + sctp_jitter(t->rto); - if (t->state != SCTP_UNCONFIRMED) + if ((t->state != SCTP_UNCONFIRMED) && + (t->state != SCTP_PF)) timeout += t->hbinterval; timeout += jiffies; return timeout; diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 33d89477619..10c018a5b9f 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -702,7 +702,8 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, if (rx_count >= asoc->base.sk->sk_rcvbuf) { if ((asoc->base.sk->sk_userlocks & SOCK_RCVBUF_LOCK) || - (!sk_rmem_schedule(asoc->base.sk, chunk->skb->truesize))) + (!sk_rmem_schedule(asoc->base.sk, chunk->skb, + chunk->skb->truesize))) goto fail; } diff --git a/net/socket.c b/net/socket.c index 6e0ccc09b31..edc3c4af908 100644 --- a/net/socket.c +++ b/net/socket.c @@ -398,7 +398,7 @@ int sock_map_fd(struct socket *sock, int flags) } EXPORT_SYMBOL(sock_map_fd); -static struct socket *sock_from_file(struct file *file, int *err) +struct socket *sock_from_file(struct file *file, int *err) { if (file->f_op == &socket_file_ops) return file->private_data; /* set in sock_map_fd */ @@ -406,6 +406,7 @@ static struct socket *sock_from_file(struct file *file, int *err) *err = -ENOTSOCK; return NULL; } +EXPORT_SYMBOL(sock_from_file); /** * sockfd_lookup - Go from a file number to its socket slot @@ -522,6 +523,9 @@ void sock_release(struct socket *sock) if (rcu_dereference_protected(sock->wq, 1)->fasync_list) printk(KERN_ERR "sock_release: fasync list not empty!\n"); + if (test_bit(SOCK_EXTERNALLY_ALLOCATED, &sock->flags)) + return; + this_cpu_sub(sockets_in_use, 1); if (!sock->file) { iput(SOCK_INODE(sock)); @@ -551,8 +555,6 @@ static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock, sock_update_classid(sock->sk); - sock_update_netprioidx(sock->sk); - si->sock = sock; si->scm = NULL; si->msg = msg; @@ -2602,7 +2604,7 @@ static int do_siocgstamp(struct net *net, struct socket *sock, err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv); set_fs(old_fs); if (!err) - err = compat_put_timeval(up, &ktv); + err = compat_put_timeval(&ktv, up); return err; } @@ -2618,7 +2620,7 @@ static int do_siocgstampns(struct net *net, struct socket *sock, err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts); set_fs(old_fs); if (!err) - err = compat_put_timespec(up, &kts); + err = compat_put_timespec(&kts, up); return err; } @@ -2655,6 +2657,7 @@ static int dev_ifconf(struct net *net, struct compat_ifconf __user *uifc32) if (copy_from_user(&ifc32, uifc32, sizeof(struct compat_ifconf))) return -EFAULT; + memset(&ifc, 0, sizeof(ifc)); if (ifc32.ifcbuf == 0) { ifc32.ifc_len = 0; ifc.ifc_len = 0; diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 9fe8857d8d5..03d03e37a7d 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -21,6 +21,11 @@ config SUNRPC_XPRT_RDMA If unsure, say N. +config SUNRPC_SWAP + bool + depends on SUNRPC + select NETVM + config RPCSEC_GSS_KRB5 tristate "Secure RPC: Kerberos V mechanism" depends on SUNRPC && CRYPTO diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 727e506cacd..b5c067bccc4 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -13,6 +13,7 @@ #include <linux/errno.h> #include <linux/hash.h> #include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/gss_api.h> #include <linux/spinlock.h> #ifdef RPC_DEBUG @@ -122,6 +123,59 @@ rpcauth_unregister(const struct rpc_authops *ops) } EXPORT_SYMBOL_GPL(rpcauth_unregister); +/** + * rpcauth_list_flavors - discover registered flavors and pseudoflavors + * @array: array to fill in + * @size: size of "array" + * + * Returns the number of array items filled in, or a negative errno. + * + * The returned array is not sorted by any policy. Callers should not + * rely on the order of the items in the returned array. + */ +int +rpcauth_list_flavors(rpc_authflavor_t *array, int size) +{ + rpc_authflavor_t flavor; + int result = 0; + + spin_lock(&rpc_authflavor_lock); + for (flavor = 0; flavor < RPC_AUTH_MAXFLAVOR; flavor++) { + const struct rpc_authops *ops = auth_flavors[flavor]; + rpc_authflavor_t pseudos[4]; + int i, len; + + if (result >= size) { + result = -ENOMEM; + break; + } + + if (ops == NULL) + continue; + if (ops->list_pseudoflavors == NULL) { + array[result++] = ops->au_flavor; + continue; + } + len = ops->list_pseudoflavors(pseudos, ARRAY_SIZE(pseudos)); + if (len < 0) { + result = len; + break; + } + for (i = 0; i < len; i++) { + if (result >= size) { + result = -ENOMEM; + break; + } + array[result++] = pseudos[i]; + } + } + spin_unlock(&rpc_authflavor_lock); + + dprintk("RPC: %s returns %d\n", __func__, result); + return result; +} +EXPORT_SYMBOL_GPL(rpcauth_list_flavors); + struct rpc_auth * rpcauth_create(rpc_authflavor_t pseudoflavor, struct rpc_clnt *clnt) { diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index d3ad81f8da5..34c52202100 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1619,6 +1619,7 @@ static const struct rpc_authops authgss_ops = { .crcreate = gss_create_cred, .pipes_create = gss_pipes_dentries_create, .pipes_destroy = gss_pipes_dentries_destroy, + .list_pseudoflavors = gss_mech_list_pseudoflavors, }; static const struct rpc_credops gss_credops = { diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 782bfe1b646..b174fcd9ff4 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -239,14 +239,28 @@ gss_mech_get_by_pseudoflavor(u32 pseudoflavor) EXPORT_SYMBOL_GPL(gss_mech_get_by_pseudoflavor); -int gss_mech_list_pseudoflavors(rpc_authflavor_t *array_ptr) +/** + * gss_mech_list_pseudoflavors - Discover registered GSS pseudoflavors + * @array: array to fill in + * @size: size of "array" + * + * Returns the number of array items filled in, or a negative errno. + * + * The returned array is not sorted by any policy. Callers should not + * rely on the order of the items in the returned array. + */ +int gss_mech_list_pseudoflavors(rpc_authflavor_t *array_ptr, int size) { struct gss_api_mech *pos = NULL; int j, i = 0; spin_lock(®istered_mechs_lock); list_for_each_entry(pos, ®istered_mechs, gm_list) { - for (j=0; j < pos->gm_pf_num; j++) { + for (j = 0; j < pos->gm_pf_num; j++) { + if (i >= size) { + spin_unlock(®istered_mechs_lock); + return -ENOMEM; + } array_ptr[i++] = pos->gm_pfs[j].pseudoflavor; } } @@ -254,8 +268,6 @@ int gss_mech_list_pseudoflavors(rpc_authflavor_t *array_ptr) return i; } -EXPORT_SYMBOL_GPL(gss_mech_list_pseudoflavors); - u32 gss_svc_to_pseudoflavor(struct gss_api_mech *gm, u32 service) { diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 31def68a0f6..5a3d675d2f2 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -176,13 +176,14 @@ out_free: } EXPORT_SYMBOL_GPL(xprt_setup_backchannel); -/* - * Destroys the backchannel preallocated structures. +/** + * xprt_destroy_backchannel - Destroys the backchannel preallocated structures. + * @xprt: the transport holding the preallocated strucures + * @max_reqs the maximum number of preallocated structures to destroy + * * Since these structures may have been allocated by multiple calls * to xprt_setup_backchannel, we only destroy up to the maximum number * of reqs specified by the caller. - * @xprt: the transport holding the preallocated strucures - * @max_reqs the maximum number of preallocated structures to destroy */ void xprt_destroy_backchannel(struct rpc_xprt *xprt, unsigned int max_reqs) { diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 47ad2666fdf..2afd2a84dc3 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1349,8 +1349,11 @@ static int c_show(struct seq_file *m, void *p) if (cache_check(cd, cp, NULL)) /* cache_check does a cache_put on failure */ seq_printf(m, "# "); - else + else { + if (cache_is_expired(cd, cp)) + seq_printf(m, "# "); cache_put(cp, cd); + } return cd->cache_show(m, cd, cp); } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index f56f045778a..fa48c60aef2 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -385,7 +385,7 @@ out_no_rpciod: return ERR_PTR(err); } -/* +/** * rpc_create - create an RPC client and transport with one call * @args: rpc_clnt create argument structure * @@ -717,6 +717,15 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) atomic_inc(&clnt->cl_count); if (clnt->cl_softrtry) task->tk_flags |= RPC_TASK_SOFT; + if (sk_memalloc_socks()) { + struct rpc_xprt *xprt; + + rcu_read_lock(); + xprt = rcu_dereference(clnt->cl_xprt); + if (xprt->swapper) + task->tk_flags |= RPC_TASK_SWAPPER; + rcu_read_unlock(); + } /* Add to the client's list of all tasks */ spin_lock(&clnt->cl_lock); list_add_tail(&task->tk_task, &clnt->cl_tasks); @@ -1844,12 +1853,13 @@ call_timeout(struct rpc_task *task) return; } if (RPC_IS_SOFT(task)) { - if (clnt->cl_chatty) + if (clnt->cl_chatty) { rcu_read_lock(); printk(KERN_NOTICE "%s: server %s not responding, timed out\n", clnt->cl_protname, rcu_dereference(clnt->cl_xprt)->servername); rcu_read_unlock(); + } if (task->tk_flags & RPC_TASK_TIMEOUT) rpc_exit(task, -ETIMEDOUT); else diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 92509ffe15f..a70acae496e 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -251,7 +251,7 @@ static int rpcb_create_local_unix(struct net *net) if (IS_ERR(clnt)) { dprintk("RPC: failed to create AF_LOCAL rpcbind " "client (errno %ld).\n", PTR_ERR(clnt)); - result = -PTR_ERR(clnt); + result = PTR_ERR(clnt); goto out; } @@ -298,7 +298,7 @@ static int rpcb_create_local_net(struct net *net) if (IS_ERR(clnt)) { dprintk("RPC: failed to create local rpcbind " "client (errno %ld).\n", PTR_ERR(clnt)); - result = -PTR_ERR(clnt); + result = PTR_ERR(clnt); goto out; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 994cfea2bad..128494ec9a6 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -300,8 +300,9 @@ EXPORT_SYMBOL_GPL(__rpc_wait_for_completion_task); /* * Make an RPC task runnable. * - * Note: If the task is ASYNC, this must be called with - * the spinlock held to protect the wait queue operation. + * Note: If the task is ASYNC, and is being made runnable after sitting on an + * rpc_wait_queue, this must be called with the queue spinlock held to protect + * the wait queue operation. */ static void rpc_make_runnable(struct rpc_task *task) { @@ -790,7 +791,9 @@ void rpc_execute(struct rpc_task *task) static void rpc_async_schedule(struct work_struct *work) { + current->flags |= PF_FSTRANS; __rpc_execute(container_of(work, struct rpc_task, u.tk_work)); + current->flags &= ~PF_FSTRANS; } /** @@ -812,7 +815,10 @@ static void rpc_async_schedule(struct work_struct *work) void *rpc_malloc(struct rpc_task *task, size_t size) { struct rpc_buffer *buf; - gfp_t gfp = RPC_IS_SWAPPER(task) ? GFP_ATOMIC : GFP_NOWAIT; + gfp_t gfp = GFP_NOWAIT; + + if (RPC_IS_SWAPPER(task)) + gfp |= __GFP_MEMALLOC; size += sizeof(struct rpc_buffer); if (size <= RPC_BUFFER_MAXSIZE) @@ -886,7 +892,7 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta static struct rpc_task * rpc_alloc_task(void) { - return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOFS); + return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOIO); } /* diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 88f2bf67196..bac973a3136 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -316,7 +316,6 @@ static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt) */ void svc_xprt_enqueue(struct svc_xprt *xprt) { - struct svc_serv *serv = xprt->xpt_server; struct svc_pool *pool; struct svc_rqst *rqstp; int cpu; @@ -362,8 +361,6 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) rqstp, rqstp->rq_xprt); rqstp->rq_xprt = xprt; svc_xprt_get(xprt); - rqstp->rq_reserved = serv->sv_max_mesg; - atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); pool->sp_stats.threads_woken++; wake_up(&rqstp->rq_wait); } else { @@ -640,8 +637,6 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) if (xprt) { rqstp->rq_xprt = xprt; svc_xprt_get(xprt); - rqstp->rq_reserved = serv->sv_max_mesg; - atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); /* As there is a shortage of threads and this request * had to be queued, don't allow the thread to wait so @@ -738,6 +733,8 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) else len = xprt->xpt_ops->xpo_recvfrom(rqstp); dprintk("svc: got len=%d\n", len); + rqstp->rq_reserved = serv->sv_max_mesg; + atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); } svc_xprt_received(xprt); @@ -794,7 +791,8 @@ int svc_send(struct svc_rqst *rqstp) /* Grab mutex to serialize outgoing data. */ mutex_lock(&xprt->xpt_mutex); - if (test_bit(XPT_DEAD, &xprt->xpt_flags)) + if (test_bit(XPT_DEAD, &xprt->xpt_flags) + || test_bit(XPT_CLOSE, &xprt->xpt_flags)) len = -ENOTCONN; else len = xprt->xpt_ops->xpo_sendto(rqstp); diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 2777fa89664..4d012920373 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -104,23 +104,9 @@ static void ip_map_put(struct kref *kref) kfree(im); } -#if IP_HASHBITS == 8 -/* hash_long on a 64 bit machine is currently REALLY BAD for - * IP addresses in reverse-endian (i.e. on a little-endian machine). - * So use a trivial but reliable hash instead - */ -static inline int hash_ip(__be32 ip) -{ - int hash = (__force u32)ip ^ ((__force u32)ip>>16); - return (hash ^ (hash>>8)) & 0xff; -} -#endif -static inline int hash_ip6(struct in6_addr ip) +static inline int hash_ip6(const struct in6_addr *ip) { - return (hash_ip(ip.s6_addr32[0]) ^ - hash_ip(ip.s6_addr32[1]) ^ - hash_ip(ip.s6_addr32[2]) ^ - hash_ip(ip.s6_addr32[3])); + return hash_32(ipv6_addr_hash(ip), IP_HASHBITS); } static int ip_map_match(struct cache_head *corig, struct cache_head *cnew) { @@ -301,7 +287,7 @@ static struct ip_map *__ip_map_lookup(struct cache_detail *cd, char *class, ip.m_addr = *addr; ch = sunrpc_cache_lookup(cd, &ip.h, hash_str(class, IP_HASHBITS) ^ - hash_ip6(*addr)); + hash_ip6(addr)); if (ch) return container_of(ch, struct ip_map, h); @@ -331,7 +317,7 @@ static int __ip_map_update(struct cache_detail *cd, struct ip_map *ipm, ip.h.expiry_time = expiry; ch = sunrpc_cache_update(cd, &ip.h, &ipm->h, hash_str(ipm->m_class, IP_HASHBITS) ^ - hash_ip6(ipm->m_addr)); + hash_ip6(&ipm->m_addr)); if (!ch) return -ENOMEM; cache_put(ch, cd); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index a6de09de5d2..998aa8c1807 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -43,6 +43,7 @@ #include <net/tcp_states.h> #include <asm/uaccess.h> #include <asm/ioctls.h> +#include <trace/events/skb.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/clnt.h> @@ -619,6 +620,8 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) if (!svc_udp_get_dest_address(rqstp, cmh)) { net_warn_ratelimited("svc: received unknown control message %d/%d; dropping RPC reply datagram\n", cmh->cmsg_level, cmh->cmsg_type); +out_free: + trace_kfree_skb(skb, svc_udp_recvfrom); skb_free_datagram_locked(svsk->sk_sk, skb); return 0; } @@ -630,8 +633,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) if (csum_partial_copy_to_xdr(&rqstp->rq_arg, skb)) { local_bh_enable(); /* checksum error */ - skb_free_datagram_locked(svsk->sk_sk, skb); - return 0; + goto out_free; } local_bh_enable(); skb_free_datagram_locked(svsk->sk_sk, skb); @@ -640,10 +642,8 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) rqstp->rq_arg.head[0].iov_base = skb->data + sizeof(struct udphdr); rqstp->rq_arg.head[0].iov_len = len; - if (skb_checksum_complete(skb)) { - skb_free_datagram_locked(svsk->sk_sk, skb); - return 0; - } + if (skb_checksum_complete(skb)) + goto out_free; rqstp->rq_xprt_ctxt = skb; } @@ -1129,9 +1129,9 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) if (len >= 0) svsk->sk_tcplen += len; if (len != want) { + svc_tcp_save_pages(svsk, rqstp); if (len < 0 && len != -EAGAIN) goto err_other; - svc_tcp_save_pages(svsk, rqstp); dprintk("svc: incomplete TCP record (%d of %d)\n", svsk->sk_tcplen, svsk->sk_reclen); goto err_noclose; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index fddcccfcdf7..0afba1b4b65 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -129,34 +129,6 @@ xdr_terminate_string(struct xdr_buf *buf, const u32 len) EXPORT_SYMBOL_GPL(xdr_terminate_string); void -xdr_encode_pages(struct xdr_buf *xdr, struct page **pages, unsigned int base, - unsigned int len) -{ - struct kvec *tail = xdr->tail; - u32 *p; - - xdr->pages = pages; - xdr->page_base = base; - xdr->page_len = len; - - p = (u32 *)xdr->head[0].iov_base + XDR_QUADLEN(xdr->head[0].iov_len); - tail->iov_base = p; - tail->iov_len = 0; - - if (len & 3) { - unsigned int pad = 4 - (len & 3); - - *p = 0; - tail->iov_base = (char *)p + (len & 3); - tail->iov_len = pad; - len += pad; - } - xdr->buflen += len; - xdr->len += len; -} -EXPORT_SYMBOL_GPL(xdr_encode_pages); - -void xdr_inline_pages(struct xdr_buf *xdr, unsigned int offset, struct page **pages, unsigned int base, unsigned int len) { @@ -180,7 +152,9 @@ EXPORT_SYMBOL_GPL(xdr_inline_pages); /* * Helper routines for doing 'memmove' like operations on a struct xdr_buf - * + */ + +/** * _shift_data_right_pages * @pages: vector of pages containing both the source and dest memory area. * @pgto_base: page vector address of destination @@ -242,7 +216,7 @@ _shift_data_right_pages(struct page **pages, size_t pgto_base, } while ((len -= copy) != 0); } -/* +/** * _copy_to_pages * @pages: array of pages * @pgbase: page vector address of destination @@ -286,7 +260,7 @@ _copy_to_pages(struct page **pages, size_t pgbase, const char *p, size_t len) flush_dcache_page(*pgto); } -/* +/** * _copy_from_pages * @p: pointer to destination * @pages: array of pages @@ -326,7 +300,7 @@ _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len) } EXPORT_SYMBOL_GPL(_copy_from_pages); -/* +/** * xdr_shrink_bufhead * @buf: xdr_buf * @len: bytes to remove from buf->head[0] @@ -399,7 +373,7 @@ xdr_shrink_bufhead(struct xdr_buf *buf, size_t len) buf->len = buf->buflen; } -/* +/** * xdr_shrink_pagelen * @buf: xdr_buf * @len: bytes to remove from buf->pages @@ -455,6 +429,16 @@ xdr_shift_buf(struct xdr_buf *buf, size_t len) EXPORT_SYMBOL_GPL(xdr_shift_buf); /** + * xdr_stream_pos - Return the current offset from the start of the xdr_stream + * @xdr: pointer to struct xdr_stream + */ +unsigned int xdr_stream_pos(const struct xdr_stream *xdr) +{ + return (unsigned int)(XDR_QUADLEN(xdr->buf->len) - xdr->nwords) << 2; +} +EXPORT_SYMBOL_GPL(xdr_stream_pos); + +/** * xdr_init_encode - Initialize a struct xdr_stream for sending data. * @xdr: pointer to xdr_stream struct * @buf: pointer to XDR buffer in which to encode data @@ -554,13 +538,11 @@ void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int b EXPORT_SYMBOL_GPL(xdr_write_pages); static void xdr_set_iov(struct xdr_stream *xdr, struct kvec *iov, - __be32 *p, unsigned int len) + unsigned int len) { if (len > iov->iov_len) len = iov->iov_len; - if (p == NULL) - p = (__be32*)iov->iov_base; - xdr->p = p; + xdr->p = (__be32*)iov->iov_base; xdr->end = (__be32*)(iov->iov_base + len); xdr->iov = iov; xdr->page_ptr = NULL; @@ -607,7 +589,7 @@ static void xdr_set_next_page(struct xdr_stream *xdr) newbase -= xdr->buf->page_base; if (xdr_set_page_base(xdr, newbase, PAGE_SIZE) < 0) - xdr_set_iov(xdr, xdr->buf->tail, NULL, xdr->buf->len); + xdr_set_iov(xdr, xdr->buf->tail, xdr->buf->len); } static bool xdr_set_next_buffer(struct xdr_stream *xdr) @@ -616,7 +598,7 @@ static bool xdr_set_next_buffer(struct xdr_stream *xdr) xdr_set_next_page(xdr); else if (xdr->iov == xdr->buf->head) { if (xdr_set_page_base(xdr, 0, PAGE_SIZE) < 0) - xdr_set_iov(xdr, xdr->buf->tail, NULL, xdr->buf->len); + xdr_set_iov(xdr, xdr->buf->tail, xdr->buf->len); } return xdr->p != xdr->end; } @@ -632,10 +614,15 @@ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p) xdr->buf = buf; xdr->scratch.iov_base = NULL; xdr->scratch.iov_len = 0; + xdr->nwords = XDR_QUADLEN(buf->len); if (buf->head[0].iov_len != 0) - xdr_set_iov(xdr, buf->head, p, buf->len); + xdr_set_iov(xdr, buf->head, buf->len); else if (buf->page_len != 0) xdr_set_page_base(xdr, 0, buf->len); + if (p != NULL && p > xdr->p && xdr->end >= p) { + xdr->nwords -= p - xdr->p; + xdr->p = p; + } } EXPORT_SYMBOL_GPL(xdr_init_decode); @@ -660,12 +647,14 @@ EXPORT_SYMBOL_GPL(xdr_init_decode_pages); static __be32 * __xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes) { + unsigned int nwords = XDR_QUADLEN(nbytes); __be32 *p = xdr->p; - __be32 *q = p + XDR_QUADLEN(nbytes); + __be32 *q = p + nwords; - if (unlikely(q > xdr->end || q < p)) + if (unlikely(nwords > xdr->nwords || q > xdr->end || q < p)) return NULL; xdr->p = q; + xdr->nwords -= nwords; return p; } @@ -732,6 +721,31 @@ __be32 * xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes) } EXPORT_SYMBOL_GPL(xdr_inline_decode); +static unsigned int xdr_align_pages(struct xdr_stream *xdr, unsigned int len) +{ + struct xdr_buf *buf = xdr->buf; + struct kvec *iov; + unsigned int nwords = XDR_QUADLEN(len); + unsigned int cur = xdr_stream_pos(xdr); + + if (xdr->nwords == 0) + return 0; + if (nwords > xdr->nwords) { + nwords = xdr->nwords; + len = nwords << 2; + } + /* Realign pages to current pointer position */ + iov = buf->head; + if (iov->iov_len > cur) + xdr_shrink_bufhead(buf, iov->iov_len - cur); + + /* Truncate page data and move it into the tail */ + if (buf->page_len > len) + xdr_shrink_pagelen(buf, buf->page_len - len); + xdr->nwords = XDR_QUADLEN(buf->len - cur); + return len; +} + /** * xdr_read_pages - Ensure page-based XDR data to decode is aligned at current pointer position * @xdr: pointer to xdr_stream struct @@ -740,39 +754,37 @@ EXPORT_SYMBOL_GPL(xdr_inline_decode); * Moves data beyond the current pointer position from the XDR head[] buffer * into the page list. Any data that lies beyond current position + "len" * bytes is moved into the XDR tail[]. + * + * Returns the number of XDR encoded bytes now contained in the pages */ -void xdr_read_pages(struct xdr_stream *xdr, unsigned int len) +unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len) { struct xdr_buf *buf = xdr->buf; struct kvec *iov; - ssize_t shift; + unsigned int nwords; unsigned int end; - int padding; - - /* Realign pages to current pointer position */ - iov = buf->head; - shift = iov->iov_len + (char *)iov->iov_base - (char *)xdr->p; - if (shift > 0) - xdr_shrink_bufhead(buf, shift); + unsigned int padding; - /* Truncate page data and move it into the tail */ - if (buf->page_len > len) - xdr_shrink_pagelen(buf, buf->page_len - len); - padding = (XDR_QUADLEN(len) << 2) - len; + len = xdr_align_pages(xdr, len); + if (len == 0) + return 0; + nwords = XDR_QUADLEN(len); + padding = (nwords << 2) - len; xdr->iov = iov = buf->tail; /* Compute remaining message length. */ - end = iov->iov_len; - shift = buf->buflen - buf->len; - if (shift < end) - end -= shift; - else if (shift > 0) - end = 0; + end = ((xdr->nwords - nwords) << 2) + padding; + if (end > iov->iov_len) + end = iov->iov_len; + /* * Position current pointer at beginning of tail, and * set remaining message length. */ xdr->p = (__be32 *)((char *)iov->iov_base + padding); xdr->end = (__be32 *)((char *)iov->iov_base + end); + xdr->page_ptr = NULL; + xdr->nwords = XDR_QUADLEN(end - padding); + return len; } EXPORT_SYMBOL_GPL(xdr_read_pages); @@ -788,12 +800,13 @@ EXPORT_SYMBOL_GPL(xdr_read_pages); */ void xdr_enter_page(struct xdr_stream *xdr, unsigned int len) { - xdr_read_pages(xdr, len); + len = xdr_align_pages(xdr, len); /* * Position current pointer at beginning of tail, and * set remaining message length. */ - xdr_set_page_base(xdr, 0, len); + if (len != 0) + xdr_set_page_base(xdr, 0, len); } EXPORT_SYMBOL_GPL(xdr_enter_page); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 3c83035cdaa..a5a402a7d21 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -531,7 +531,7 @@ void xprt_set_retrans_timeout_def(struct rpc_task *task) } EXPORT_SYMBOL_GPL(xprt_set_retrans_timeout_def); -/* +/** * xprt_set_retrans_timeout_rtt - set a request's retransmit timeout * @task: task whose timeout is to be set * diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index b446e100286..06cdbff79e4 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -200,6 +200,7 @@ xprt_rdma_connect_worker(struct work_struct *work) int rc = 0; if (!xprt->shutdown) { + current->flags |= PF_FSTRANS; xprt_clear_connected(xprt); dprintk("RPC: %s: %sconnect\n", __func__, @@ -212,10 +213,10 @@ xprt_rdma_connect_worker(struct work_struct *work) out: xprt_wake_pending_tasks(xprt, rc); - out_clear: dprintk("RPC: %s: exit\n", __func__); xprt_clear_connecting(xprt); + current->flags &= ~PF_FSTRANS; } /* diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 890b03f8d87..400567243f8 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1014,9 +1014,6 @@ static void xs_udp_data_ready(struct sock *sk, int len) UDPX_INC_STATS_BH(sk, UDP_MIB_INDATAGRAMS); - /* Something worked... */ - dst_confirm(skb_dst(skb)); - xprt_adjust_cwnd(task, copied); xprt_complete_rqst(task, copied); @@ -1895,6 +1892,8 @@ static void xs_local_setup_socket(struct work_struct *work) if (xprt->shutdown) goto out; + current->flags |= PF_FSTRANS; + clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); status = __sock_create(xprt->xprt_net, AF_LOCAL, SOCK_STREAM, 0, &sock, 1); @@ -1928,8 +1927,48 @@ static void xs_local_setup_socket(struct work_struct *work) out: xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); + current->flags &= ~PF_FSTRANS; +} + +#ifdef CONFIG_SUNRPC_SWAP +static void xs_set_memalloc(struct rpc_xprt *xprt) +{ + struct sock_xprt *transport = container_of(xprt, struct sock_xprt, + xprt); + + if (xprt->swapper) + sk_set_memalloc(transport->inet); } +/** + * xs_swapper - Tag this transport as being used for swap. + * @xprt: transport to tag + * @enable: enable/disable + * + */ +int xs_swapper(struct rpc_xprt *xprt, int enable) +{ + struct sock_xprt *transport = container_of(xprt, struct sock_xprt, + xprt); + int err = 0; + + if (enable) { + xprt->swapper++; + xs_set_memalloc(xprt); + } else if (xprt->swapper) { + xprt->swapper--; + sk_clear_memalloc(transport->inet); + } + + return err; +} +EXPORT_SYMBOL_GPL(xs_swapper); +#else +static void xs_set_memalloc(struct rpc_xprt *xprt) +{ +} +#endif + static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -1954,6 +1993,8 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) transport->sock = sock; transport->inet = sk; + xs_set_memalloc(xprt); + write_unlock_bh(&sk->sk_callback_lock); } xs_udp_do_set_buffer_size(xprt); @@ -1970,6 +2011,8 @@ static void xs_udp_setup_socket(struct work_struct *work) if (xprt->shutdown) goto out; + current->flags |= PF_FSTRANS; + /* Start by resetting any existing state */ xs_reset_transport(transport); sock = xs_create_sock(xprt, transport, @@ -1988,6 +2031,7 @@ static void xs_udp_setup_socket(struct work_struct *work) out: xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); + current->flags &= ~PF_FSTRANS; } /* @@ -2078,6 +2122,8 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) if (!xprt_bound(xprt)) goto out; + xs_set_memalloc(xprt); + /* Tell the socket layer to start connecting... */ xprt->stat.connect_count++; xprt->stat.connect_start = jiffies; @@ -2113,6 +2159,8 @@ static void xs_tcp_setup_socket(struct work_struct *work) if (xprt->shutdown) goto out; + current->flags |= PF_FSTRANS; + if (!sock) { clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); sock = xs_create_sock(xprt, transport, @@ -2162,6 +2210,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -EINPROGRESS: case -EALREADY: xprt_clear_connecting(xprt); + current->flags &= ~PF_FSTRANS; return; case -EINVAL: /* Happens, for instance, if the user specified a link @@ -2174,6 +2223,7 @@ out_eagain: out: xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); + current->flags &= ~PF_FSTRANS; } /** diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig index 2c5954b8593..585460180ff 100644 --- a/net/tipc/Kconfig +++ b/net/tipc/Kconfig @@ -41,29 +41,4 @@ config TIPC_PORTS Setting this to a smaller value saves some memory, setting it to higher allows for more ports. -config TIPC_LOG - int "Size of log buffer" - depends on TIPC_ADVANCED - range 0 32768 - default "0" - help - Size (in bytes) of TIPC's internal log buffer, which records the - occurrence of significant events. Can range from 0 to 32768 bytes; - default is 0. - - There is no need to enable the log buffer unless the node will be - managed remotely via TIPC. - -config TIPC_DEBUG - bool "Enable debugging support" - default n - help - Saying Y here enables TIPC debugging capabilities used by developers. - Most users do not need to bother; if unsure, just say N. - - Enabling debugging support causes TIPC to display data about its - internal state when certain abnormal conditions occur. It also - makes it easy for developers to capture additional information of - interest using the dbg() or msg_dbg() macros. - endif # TIPC diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 2625f5ebe3e..e4e6d8cd47e 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -162,7 +162,7 @@ static void bclink_update_last_sent(struct tipc_node *node, u32 seqno) } -/* +/** * tipc_bclink_retransmit_to - get most recent node to request retransmission * * Called with bc_lock locked @@ -270,7 +270,7 @@ exit: spin_unlock_bh(&bc_lock); } -/* +/** * tipc_bclink_update_link_state - update broadcast link state * * tipc_net_lock and node lock set @@ -330,7 +330,7 @@ void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent) } } -/* +/** * bclink_peek_nack - monitor retransmission requests sent by other nodes * * Delay any upcoming NACK by this node if another node has already @@ -381,7 +381,7 @@ exit: return res; } -/* +/** * bclink_accept_pkt - accept an incoming, in-sequence broadcast packet * * Called with both sending node's lock and bc_lock taken. @@ -406,7 +406,7 @@ static void bclink_accept_pkt(struct tipc_node *node, u32 seqno) } } -/* +/** * tipc_bclink_recv_pkt - receive a broadcast packet, and deliver upwards * * tipc_net_lock is read_locked, no other locks set @@ -701,48 +701,43 @@ void tipc_bcbearer_sort(void) int tipc_bclink_stats(char *buf, const u32 buf_size) { - struct print_buf pb; + int ret; + struct tipc_stats *s; if (!bcl) return 0; - tipc_printbuf_init(&pb, buf, buf_size); - spin_lock_bh(&bc_lock); - tipc_printf(&pb, "Link <%s>\n" - " Window:%u packets\n", - bcl->name, bcl->queue_limit[0]); - tipc_printf(&pb, " RX packets:%u fragments:%u/%u bundles:%u/%u\n", - bcl->stats.recv_info, - bcl->stats.recv_fragments, - bcl->stats.recv_fragmented, - bcl->stats.recv_bundles, - bcl->stats.recv_bundled); - tipc_printf(&pb, " TX packets:%u fragments:%u/%u bundles:%u/%u\n", - bcl->stats.sent_info, - bcl->stats.sent_fragments, - bcl->stats.sent_fragmented, - bcl->stats.sent_bundles, - bcl->stats.sent_bundled); - tipc_printf(&pb, " RX naks:%u defs:%u dups:%u\n", - bcl->stats.recv_nacks, - bcl->stats.deferred_recv, - bcl->stats.duplicates); - tipc_printf(&pb, " TX naks:%u acks:%u dups:%u\n", - bcl->stats.sent_nacks, - bcl->stats.sent_acks, - bcl->stats.retransmitted); - tipc_printf(&pb, " Congestion bearer:%u link:%u Send queue max:%u avg:%u\n", - bcl->stats.bearer_congs, - bcl->stats.link_congs, - bcl->stats.max_queue_sz, - bcl->stats.queue_sz_counts - ? (bcl->stats.accu_queue_sz / bcl->stats.queue_sz_counts) - : 0); + s = &bcl->stats; + + ret = tipc_snprintf(buf, buf_size, "Link <%s>\n" + " Window:%u packets\n", + bcl->name, bcl->queue_limit[0]); + ret += tipc_snprintf(buf + ret, buf_size - ret, + " RX packets:%u fragments:%u/%u bundles:%u/%u\n", + s->recv_info, s->recv_fragments, + s->recv_fragmented, s->recv_bundles, + s->recv_bundled); + ret += tipc_snprintf(buf + ret, buf_size - ret, + " TX packets:%u fragments:%u/%u bundles:%u/%u\n", + s->sent_info, s->sent_fragments, + s->sent_fragmented, s->sent_bundles, + s->sent_bundled); + ret += tipc_snprintf(buf + ret, buf_size - ret, + " RX naks:%u defs:%u dups:%u\n", + s->recv_nacks, s->deferred_recv, s->duplicates); + ret += tipc_snprintf(buf + ret, buf_size - ret, + " TX naks:%u acks:%u dups:%u\n", + s->sent_nacks, s->sent_acks, s->retransmitted); + ret += tipc_snprintf(buf + ret, buf_size - ret, + " Congestion bearer:%u link:%u Send queue max:%u avg:%u\n", + s->bearer_congs, s->link_congs, s->max_queue_sz, + s->queue_sz_counts ? + (s->accu_queue_sz / s->queue_sz_counts) : 0); spin_unlock_bh(&bc_lock); - return tipc_printbuf_validate(&pb); + return ret; } int tipc_bclink_reset_stats(void) @@ -880,7 +875,7 @@ void tipc_port_list_add(struct tipc_port_list *pl_ptr, u32 port) if (!item->next) { item->next = kmalloc(sizeof(*item), GFP_ATOMIC); if (!item->next) { - warn("Incomplete multicast delivery, no memory\n"); + pr_warn("Incomplete multicast delivery, no memory\n"); return; } item->next->next = NULL; diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index a297e3a2e3e..09e71241265 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -123,28 +123,30 @@ int tipc_register_media(struct tipc_media *m_ptr) exit: write_unlock_bh(&tipc_net_lock); if (res) - warn("Media <%s> registration error\n", m_ptr->name); + pr_warn("Media <%s> registration error\n", m_ptr->name); return res; } /** * tipc_media_addr_printf - record media address in print buffer */ -void tipc_media_addr_printf(struct print_buf *pb, struct tipc_media_addr *a) +void tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a) { char addr_str[MAX_ADDR_STR]; struct tipc_media *m_ptr; + int ret; m_ptr = media_find_id(a->media_id); if (m_ptr && !m_ptr->addr2str(a, addr_str, sizeof(addr_str))) - tipc_printf(pb, "%s(%s)", m_ptr->name, addr_str); + ret = tipc_snprintf(buf, len, "%s(%s)", m_ptr->name, addr_str); else { u32 i; - tipc_printf(pb, "UNKNOWN(%u)", a->media_id); + ret = tipc_snprintf(buf, len, "UNKNOWN(%u)", a->media_id); for (i = 0; i < sizeof(a->value); i++) - tipc_printf(pb, "-%02x", a->value[i]); + ret += tipc_snprintf(buf - ret, len + ret, + "-%02x", a->value[i]); } } @@ -172,8 +174,8 @@ struct sk_buff *tipc_media_get_names(void) /** * bearer_name_validate - validate & (optionally) deconstruct bearer name - * @name - ptr to bearer name string - * @name_parts - ptr to area for bearer name components (or NULL if not needed) + * @name: ptr to bearer name string + * @name_parts: ptr to area for bearer name components (or NULL if not needed) * * Returns 1 if bearer name is valid, otherwise 0. */ @@ -418,12 +420,12 @@ int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority) int res = -EINVAL; if (!tipc_own_addr) { - warn("Bearer <%s> rejected, not supported in standalone mode\n", - name); + pr_warn("Bearer <%s> rejected, not supported in standalone mode\n", + name); return -ENOPROTOOPT; } if (!bearer_name_validate(name, &b_names)) { - warn("Bearer <%s> rejected, illegal name\n", name); + pr_warn("Bearer <%s> rejected, illegal name\n", name); return -EINVAL; } if (tipc_addr_domain_valid(disc_domain) && @@ -435,12 +437,13 @@ int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority) res = 0; /* accept specified node in own cluster */ } if (res) { - warn("Bearer <%s> rejected, illegal discovery domain\n", name); + pr_warn("Bearer <%s> rejected, illegal discovery domain\n", + name); return -EINVAL; } if ((priority > TIPC_MAX_LINK_PRI) && (priority != TIPC_MEDIA_LINK_PRI)) { - warn("Bearer <%s> rejected, illegal priority\n", name); + pr_warn("Bearer <%s> rejected, illegal priority\n", name); return -EINVAL; } @@ -448,8 +451,8 @@ int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority) m_ptr = tipc_media_find(b_names.media_name); if (!m_ptr) { - warn("Bearer <%s> rejected, media <%s> not registered\n", name, - b_names.media_name); + pr_warn("Bearer <%s> rejected, media <%s> not registered\n", + name, b_names.media_name); goto exit; } @@ -465,24 +468,25 @@ restart: continue; } if (!strcmp(name, tipc_bearers[i].name)) { - warn("Bearer <%s> rejected, already enabled\n", name); + pr_warn("Bearer <%s> rejected, already enabled\n", + name); goto exit; } if ((tipc_bearers[i].priority == priority) && (++with_this_prio > 2)) { if (priority-- == 0) { - warn("Bearer <%s> rejected, duplicate priority\n", - name); + pr_warn("Bearer <%s> rejected, duplicate priority\n", + name); goto exit; } - warn("Bearer <%s> priority adjustment required %u->%u\n", - name, priority + 1, priority); + pr_warn("Bearer <%s> priority adjustment required %u->%u\n", + name, priority + 1, priority); goto restart; } } if (bearer_id >= MAX_BEARERS) { - warn("Bearer <%s> rejected, bearer limit reached (%u)\n", - name, MAX_BEARERS); + pr_warn("Bearer <%s> rejected, bearer limit reached (%u)\n", + name, MAX_BEARERS); goto exit; } @@ -490,7 +494,8 @@ restart: strcpy(b_ptr->name, name); res = m_ptr->enable_bearer(b_ptr); if (res) { - warn("Bearer <%s> rejected, enable failure (%d)\n", name, -res); + pr_warn("Bearer <%s> rejected, enable failure (%d)\n", + name, -res); goto exit; } @@ -508,20 +513,20 @@ restart: res = tipc_disc_create(b_ptr, &m_ptr->bcast_addr, disc_domain); if (res) { bearer_disable(b_ptr); - warn("Bearer <%s> rejected, discovery object creation failed\n", - name); + pr_warn("Bearer <%s> rejected, discovery object creation failed\n", + name); goto exit; } - info("Enabled bearer <%s>, discovery domain %s, priority %u\n", - name, tipc_addr_string_fill(addr_string, disc_domain), priority); + pr_info("Enabled bearer <%s>, discovery domain %s, priority %u\n", + name, + tipc_addr_string_fill(addr_string, disc_domain), priority); exit: write_unlock_bh(&tipc_net_lock); return res; } /** - * tipc_block_bearer(): Block the bearer with the given name, - * and reset all its links + * tipc_block_bearer - Block the bearer with the given name, and reset all its links */ int tipc_block_bearer(const char *name) { @@ -532,12 +537,12 @@ int tipc_block_bearer(const char *name) read_lock_bh(&tipc_net_lock); b_ptr = tipc_bearer_find(name); if (!b_ptr) { - warn("Attempt to block unknown bearer <%s>\n", name); + pr_warn("Attempt to block unknown bearer <%s>\n", name); read_unlock_bh(&tipc_net_lock); return -EINVAL; } - info("Blocking bearer <%s>\n", name); + pr_info("Blocking bearer <%s>\n", name); spin_lock_bh(&b_ptr->lock); b_ptr->blocked = 1; list_splice_init(&b_ptr->cong_links, &b_ptr->links); @@ -563,7 +568,7 @@ static void bearer_disable(struct tipc_bearer *b_ptr) struct tipc_link *l_ptr; struct tipc_link *temp_l_ptr; - info("Disabling bearer <%s>\n", b_ptr->name); + pr_info("Disabling bearer <%s>\n", b_ptr->name); spin_lock_bh(&b_ptr->lock); b_ptr->blocked = 1; b_ptr->media->disable_bearer(b_ptr); @@ -585,7 +590,7 @@ int tipc_disable_bearer(const char *name) write_lock_bh(&tipc_net_lock); b_ptr = tipc_bearer_find(name); if (b_ptr == NULL) { - warn("Attempt to disable unknown bearer <%s>\n", name); + pr_warn("Attempt to disable unknown bearer <%s>\n", name); res = -EINVAL; } else { bearer_disable(b_ptr); diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index e3b2be37fb3..dd4c2abf08e 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -57,7 +57,7 @@ */ #define TIPC_MEDIA_TYPE_ETH 1 -/* +/** * struct tipc_media_addr - destination address used by TIPC bearers * @value: address info (format defined by media) * @media_id: TIPC media type identifier @@ -179,7 +179,7 @@ void tipc_eth_media_stop(void); int tipc_media_set_priority(const char *name, u32 new_value); int tipc_media_set_window(const char *name, u32 new_value); -void tipc_media_addr_printf(struct print_buf *pb, struct tipc_media_addr *a); +void tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a); struct sk_buff *tipc_media_get_names(void); struct sk_buff *tipc_bearer_get_names(void); diff --git a/net/tipc/config.c b/net/tipc/config.c index c5712a34381..a056a3852f7 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -39,6 +39,8 @@ #include "name_table.h" #include "config.h" +#define REPLY_TRUNCATED "<truncated>\n" + static u32 config_port_ref; static DEFINE_SPINLOCK(config_lock); @@ -104,13 +106,12 @@ struct sk_buff *tipc_cfg_reply_string_type(u16 tlv_type, char *string) return buf; } -#define MAX_STATS_INFO 2000 - static struct sk_buff *tipc_show_stats(void) { struct sk_buff *buf; struct tlv_desc *rep_tlv; - struct print_buf pb; + char *pb; + int pb_len; int str_len; u32 value; @@ -121,17 +122,16 @@ static struct sk_buff *tipc_show_stats(void) if (value != 0) return tipc_cfg_reply_error_string("unsupported argument"); - buf = tipc_cfg_reply_alloc(TLV_SPACE(MAX_STATS_INFO)); + buf = tipc_cfg_reply_alloc(TLV_SPACE(ULTRA_STRING_MAX_LEN)); if (buf == NULL) return NULL; rep_tlv = (struct tlv_desc *)buf->data; - tipc_printbuf_init(&pb, (char *)TLV_DATA(rep_tlv), MAX_STATS_INFO); - - tipc_printf(&pb, "TIPC version " TIPC_MOD_VER "\n"); + pb = TLV_DATA(rep_tlv); + pb_len = ULTRA_STRING_MAX_LEN; - /* Use additional tipc_printf()'s to return more info ... */ - str_len = tipc_printbuf_validate(&pb); + str_len = tipc_snprintf(pb, pb_len, "TIPC version " TIPC_MOD_VER "\n"); + str_len += 1; /* for "\0" */ skb_put(buf, TLV_SPACE(str_len)); TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); @@ -334,12 +334,6 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_SHOW_PORTS: rep_tlv_buf = tipc_port_get_ports(); break; - case TIPC_CMD_SET_LOG_SIZE: - rep_tlv_buf = tipc_log_resize_cmd(req_tlv_area, req_tlv_space); - break; - case TIPC_CMD_DUMP_LOG: - rep_tlv_buf = tipc_log_dump(); - break; case TIPC_CMD_SHOW_STATS: rep_tlv_buf = tipc_show_stats(); break; @@ -399,6 +393,8 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_GET_MAX_CLUSTERS: case TIPC_CMD_SET_MAX_NODES: case TIPC_CMD_GET_MAX_NODES: + case TIPC_CMD_SET_LOG_SIZE: + case TIPC_CMD_DUMP_LOG: rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (obsolete command)"); break; @@ -408,6 +404,15 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area break; } + WARN_ON(rep_tlv_buf->len > TLV_SPACE(ULTRA_STRING_MAX_LEN)); + + /* Append an error message if we cannot return all requested data */ + if (rep_tlv_buf->len == TLV_SPACE(ULTRA_STRING_MAX_LEN)) { + if (*(rep_tlv_buf->data + ULTRA_STRING_MAX_LEN) != '\0') + sprintf(rep_tlv_buf->data + rep_tlv_buf->len - + sizeof(REPLY_TRUNCATED) - 1, REPLY_TRUNCATED); + } + /* Return reply buffer */ exit: spin_unlock_bh(&config_lock); @@ -432,7 +437,7 @@ static void cfg_named_msg_event(void *userdata, if ((size < sizeof(*req_hdr)) || (size != TCM_ALIGN(ntohl(req_hdr->tcm_len))) || (ntohs(req_hdr->tcm_flags) != TCM_F_REQUEST)) { - warn("Invalid configuration message discarded\n"); + pr_warn("Invalid configuration message discarded\n"); return; } @@ -478,7 +483,7 @@ int tipc_cfg_init(void) return 0; failed: - err("Unable to create configuration service\n"); + pr_err("Unable to create configuration service\n"); return res; } @@ -494,7 +499,7 @@ void tipc_cfg_reinit(void) seq.lower = seq.upper = tipc_own_addr; res = tipc_publish(config_port_ref, TIPC_ZONE_SCOPE, &seq); if (res) - err("Unable to reinitialize configuration service\n"); + pr_err("Unable to reinitialize configuration service\n"); } void tipc_cfg_stop(void) diff --git a/net/tipc/core.c b/net/tipc/core.c index f7b95239ebd..6586eac6a50 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -34,22 +34,18 @@ * POSSIBILITY OF SUCH DAMAGE. */ -#include <linux/module.h> - #include "core.h" #include "ref.h" #include "name_table.h" #include "subscr.h" #include "config.h" +#include <linux/module.h> #ifndef CONFIG_TIPC_PORTS #define CONFIG_TIPC_PORTS 8191 #endif -#ifndef CONFIG_TIPC_LOG -#define CONFIG_TIPC_LOG 0 -#endif /* global variables used by multiple sub-systems within TIPC */ int tipc_random; @@ -125,7 +121,6 @@ static void tipc_core_stop(void) tipc_nametbl_stop(); tipc_ref_table_stop(); tipc_socket_stop(); - tipc_log_resize(0); } /** @@ -161,10 +156,7 @@ static int __init tipc_init(void) { int res; - if (tipc_log_resize(CONFIG_TIPC_LOG) != 0) - warn("Unable to create log buffer\n"); - - info("Activated (version " TIPC_MOD_VER ")\n"); + pr_info("Activated (version " TIPC_MOD_VER ")\n"); tipc_own_addr = 0; tipc_remote_management = 1; @@ -175,9 +167,9 @@ static int __init tipc_init(void) res = tipc_core_start(); if (res) - err("Unable to start in single node mode\n"); + pr_err("Unable to start in single node mode\n"); else - info("Started in single node mode\n"); + pr_info("Started in single node mode\n"); return res; } @@ -185,7 +177,7 @@ static void __exit tipc_exit(void) { tipc_core_stop_net(); tipc_core_stop(); - info("Deactivated\n"); + pr_info("Deactivated\n"); } module_init(tipc_init); diff --git a/net/tipc/core.h b/net/tipc/core.h index 2a9bb99537b..fd42e106c18 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -37,6 +37,8 @@ #ifndef _TIPC_CORE_H #define _TIPC_CORE_H +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/tipc.h> #include <linux/tipc_config.h> #include <linux/types.h> @@ -58,68 +60,11 @@ #define TIPC_MOD_VER "2.0.0" -struct tipc_msg; /* msg.h */ -struct print_buf; /* log.h */ - -/* - * TIPC system monitoring code - */ - -/* - * TIPC's print buffer subsystem supports the following print buffers: - * - * TIPC_NULL : null buffer (i.e. print nowhere) - * TIPC_CONS : system console - * TIPC_LOG : TIPC log buffer - * &buf : user-defined buffer (struct print_buf *) - * - * Note: TIPC_LOG is configured to echo its output to the system console; - * user-defined buffers can be configured to do the same thing. - */ -extern struct print_buf *const TIPC_NULL; -extern struct print_buf *const TIPC_CONS; -extern struct print_buf *const TIPC_LOG; - -void tipc_printf(struct print_buf *, const char *fmt, ...); - -/* - * TIPC_OUTPUT is the destination print buffer for system messages. - */ -#ifndef TIPC_OUTPUT -#define TIPC_OUTPUT TIPC_LOG -#endif +#define ULTRA_STRING_MAX_LEN 32768 -#define err(fmt, arg...) tipc_printf(TIPC_OUTPUT, \ - KERN_ERR "TIPC: " fmt, ## arg) -#define warn(fmt, arg...) tipc_printf(TIPC_OUTPUT, \ - KERN_WARNING "TIPC: " fmt, ## arg) -#define info(fmt, arg...) tipc_printf(TIPC_OUTPUT, \ - KERN_NOTICE "TIPC: " fmt, ## arg) - -#ifdef CONFIG_TIPC_DEBUG - -/* - * DBG_OUTPUT is the destination print buffer for debug messages. - */ -#ifndef DBG_OUTPUT -#define DBG_OUTPUT TIPC_LOG -#endif - -#define dbg(fmt, arg...) tipc_printf(DBG_OUTPUT, KERN_DEBUG fmt, ## arg); - -#define msg_dbg(msg, txt) tipc_msg_dbg(DBG_OUTPUT, msg, txt); - -void tipc_msg_dbg(struct print_buf *, struct tipc_msg *, const char *); - -#else - -#define dbg(fmt, arg...) do {} while (0) -#define msg_dbg(msg, txt) do {} while (0) - -#define tipc_msg_dbg(buf, msg, txt) do {} while (0) - -#endif +struct tipc_msg; /* msg.h */ +int tipc_snprintf(char *buf, int len, const char *fmt, ...); /* * TIPC-specific error codes diff --git a/net/tipc/discover.c b/net/tipc/discover.c index ae054cfe179..50eaa403eb6 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -100,14 +100,12 @@ static void disc_dupl_alert(struct tipc_bearer *b_ptr, u32 node_addr, { char node_addr_str[16]; char media_addr_str[64]; - struct print_buf pb; tipc_addr_string_fill(node_addr_str, node_addr); - tipc_printbuf_init(&pb, media_addr_str, sizeof(media_addr_str)); - tipc_media_addr_printf(&pb, media_addr); - tipc_printbuf_validate(&pb); - warn("Duplicate %s using %s seen on <%s>\n", - node_addr_str, media_addr_str, b_ptr->name); + tipc_media_addr_printf(media_addr_str, sizeof(media_addr_str), + media_addr); + pr_warn("Duplicate %s using %s seen on <%s>\n", node_addr_str, + media_addr_str, b_ptr->name); } /** diff --git a/net/tipc/handler.c b/net/tipc/handler.c index 9c6f22ff1c6..7a52d3922f3 100644 --- a/net/tipc/handler.c +++ b/net/tipc/handler.c @@ -57,14 +57,14 @@ unsigned int tipc_k_signal(Handler routine, unsigned long argument) struct queue_item *item; if (!handler_enabled) { - err("Signal request ignored by handler\n"); + pr_err("Signal request ignored by handler\n"); return -ENOPROTOOPT; } spin_lock_bh(&qitem_lock); item = kmem_cache_alloc(tipc_queue_item_cache, GFP_ATOMIC); if (!item) { - err("Signal queue out of memory\n"); + pr_err("Signal queue out of memory\n"); spin_unlock_bh(&qitem_lock); return -ENOMEM; } diff --git a/net/tipc/link.c b/net/tipc/link.c index 7a614f43549..1c1e6151875 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -41,6 +41,12 @@ #include "discover.h" #include "config.h" +/* + * Error message prefixes + */ +static const char *link_co_err = "Link changeover error, "; +static const char *link_rst_msg = "Resetting link "; +static const char *link_unk_evt = "Unknown link event "; /* * Out-of-range value for link session numbers @@ -153,8 +159,8 @@ int tipc_link_is_active(struct tipc_link *l_ptr) /** * link_name_validate - validate & (optionally) deconstruct tipc_link name - * @name - ptr to link name string - * @name_parts - ptr to area for link name components (or NULL if not needed) + * @name: ptr to link name string + * @name_parts: ptr to area for link name components (or NULL if not needed) * * Returns 1 if link name is valid, otherwise 0. */ @@ -300,20 +306,20 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, if (n_ptr->link_cnt >= 2) { tipc_addr_string_fill(addr_string, n_ptr->addr); - err("Attempt to establish third link to %s\n", addr_string); + pr_err("Attempt to establish third link to %s\n", addr_string); return NULL; } if (n_ptr->links[b_ptr->identity]) { tipc_addr_string_fill(addr_string, n_ptr->addr); - err("Attempt to establish second link on <%s> to %s\n", - b_ptr->name, addr_string); + pr_err("Attempt to establish second link on <%s> to %s\n", + b_ptr->name, addr_string); return NULL; } l_ptr = kzalloc(sizeof(*l_ptr), GFP_ATOMIC); if (!l_ptr) { - warn("Link creation failed, no memory\n"); + pr_warn("Link creation failed, no memory\n"); return NULL; } @@ -371,7 +377,7 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, void tipc_link_delete(struct tipc_link *l_ptr) { if (!l_ptr) { - err("Attempt to delete non-existent link\n"); + pr_err("Attempt to delete non-existent link\n"); return; } @@ -632,8 +638,8 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) link_set_timer(l_ptr, cont_intv / 4); break; case RESET_MSG: - info("Resetting link <%s>, requested by peer\n", - l_ptr->name); + pr_info("%s<%s>, requested by peer\n", link_rst_msg, + l_ptr->name); tipc_link_reset(l_ptr); l_ptr->state = RESET_RESET; l_ptr->fsm_msg_cnt = 0; @@ -642,7 +648,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) link_set_timer(l_ptr, cont_intv); break; default: - err("Unknown link event %u in WW state\n", event); + pr_err("%s%u in WW state\n", link_unk_evt, event); } break; case WORKING_UNKNOWN: @@ -654,8 +660,8 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) link_set_timer(l_ptr, cont_intv); break; case RESET_MSG: - info("Resetting link <%s>, requested by peer " - "while probing\n", l_ptr->name); + pr_info("%s<%s>, requested by peer while probing\n", + link_rst_msg, l_ptr->name); tipc_link_reset(l_ptr); l_ptr->state = RESET_RESET; l_ptr->fsm_msg_cnt = 0; @@ -680,8 +686,8 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv / 4); } else { /* Link has failed */ - warn("Resetting link <%s>, peer not responding\n", - l_ptr->name); + pr_warn("%s<%s>, peer not responding\n", + link_rst_msg, l_ptr->name); tipc_link_reset(l_ptr); l_ptr->state = RESET_UNKNOWN; l_ptr->fsm_msg_cnt = 0; @@ -692,7 +698,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) } break; default: - err("Unknown link event %u in WU state\n", event); + pr_err("%s%u in WU state\n", link_unk_evt, event); } break; case RESET_UNKNOWN: @@ -726,7 +732,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) link_set_timer(l_ptr, cont_intv); break; default: - err("Unknown link event %u in RU state\n", event); + pr_err("%s%u in RU state\n", link_unk_evt, event); } break; case RESET_RESET: @@ -751,11 +757,11 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) link_set_timer(l_ptr, cont_intv); break; default: - err("Unknown link event %u in RR state\n", event); + pr_err("%s%u in RR state\n", link_unk_evt, event); } break; default: - err("Unknown link state %u/%u\n", l_ptr->state, event); + pr_err("Unknown link state %u/%u\n", l_ptr->state, event); } } @@ -856,7 +862,8 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) } kfree_skb(buf); if (imp > CONN_MANAGER) { - warn("Resetting link <%s>, send queue full", l_ptr->name); + pr_warn("%s<%s>, send queue full", link_rst_msg, + l_ptr->name); tipc_link_reset(l_ptr); } return dsz; @@ -944,7 +951,7 @@ int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector) return res; } -/* +/** * tipc_link_send_names - send name table entries to new neighbor * * Send routine for bulk delivery of name table messages when contact @@ -1409,8 +1416,8 @@ static void link_reset_all(unsigned long addr) tipc_node_lock(n_ptr); - warn("Resetting all links to %s\n", - tipc_addr_string_fill(addr_string, n_ptr->addr)); + pr_warn("Resetting all links to %s\n", + tipc_addr_string_fill(addr_string, n_ptr->addr)); for (i = 0; i < MAX_BEARERS; i++) { if (n_ptr->links[i]) { @@ -1428,7 +1435,7 @@ static void link_retransmit_failure(struct tipc_link *l_ptr, { struct tipc_msg *msg = buf_msg(buf); - warn("Retransmission failure on link <%s>\n", l_ptr->name); + pr_warn("Retransmission failure on link <%s>\n", l_ptr->name); if (l_ptr->addr) { /* Handle failure on standard link */ @@ -1440,21 +1447,23 @@ static void link_retransmit_failure(struct tipc_link *l_ptr, struct tipc_node *n_ptr; char addr_string[16]; - info("Msg seq number: %u, ", msg_seqno(msg)); - info("Outstanding acks: %lu\n", - (unsigned long) TIPC_SKB_CB(buf)->handle); + pr_info("Msg seq number: %u, ", msg_seqno(msg)); + pr_cont("Outstanding acks: %lu\n", + (unsigned long) TIPC_SKB_CB(buf)->handle); n_ptr = tipc_bclink_retransmit_to(); tipc_node_lock(n_ptr); tipc_addr_string_fill(addr_string, n_ptr->addr); - info("Broadcast link info for %s\n", addr_string); - info("Supportable: %d, ", n_ptr->bclink.supportable); - info("Supported: %d, ", n_ptr->bclink.supported); - info("Acked: %u\n", n_ptr->bclink.acked); - info("Last in: %u, ", n_ptr->bclink.last_in); - info("Oos state: %u, ", n_ptr->bclink.oos_state); - info("Last sent: %u\n", n_ptr->bclink.last_sent); + pr_info("Broadcast link info for %s\n", addr_string); + pr_info("Supportable: %d, Supported: %d, Acked: %u\n", + n_ptr->bclink.supportable, + n_ptr->bclink.supported, + n_ptr->bclink.acked); + pr_info("Last in: %u, Oos state: %u, Last sent: %u\n", + n_ptr->bclink.last_in, + n_ptr->bclink.oos_state, + n_ptr->bclink.last_sent); tipc_k_signal((Handler)link_reset_all, (unsigned long)n_ptr->addr); @@ -1479,8 +1488,8 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *buf, l_ptr->retransm_queue_head = msg_seqno(msg); l_ptr->retransm_queue_size = retransmits; } else { - err("Unexpected retransmit on link %s (qsize=%d)\n", - l_ptr->name, l_ptr->retransm_queue_size); + pr_err("Unexpected retransmit on link %s (qsize=%d)\n", + l_ptr->name, l_ptr->retransm_queue_size); } return; } else { @@ -1787,7 +1796,7 @@ cont: read_unlock_bh(&tipc_net_lock); } -/* +/** * tipc_link_defer_pkt - Add out-of-sequence message to deferred reception queue * * Returns increase in queue length (i.e. 0 or 1) @@ -2074,8 +2083,9 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) if (msg_linkprio(msg) && (msg_linkprio(msg) != l_ptr->priority)) { - warn("Resetting link <%s>, priority change %u->%u\n", - l_ptr->name, l_ptr->priority, msg_linkprio(msg)); + pr_warn("%s<%s>, priority change %u->%u\n", + link_rst_msg, l_ptr->name, l_ptr->priority, + msg_linkprio(msg)); l_ptr->priority = msg_linkprio(msg); tipc_link_reset(l_ptr); /* Enforce change to take effect */ break; @@ -2139,15 +2149,13 @@ static void tipc_link_tunnel(struct tipc_link *l_ptr, tunnel = l_ptr->owner->active_links[selector & 1]; if (!tipc_link_is_up(tunnel)) { - warn("Link changeover error, " - "tunnel link no longer available\n"); + pr_warn("%stunnel link no longer available\n", link_co_err); return; } msg_set_size(tunnel_hdr, length + INT_H_SIZE); buf = tipc_buf_acquire(length + INT_H_SIZE); if (!buf) { - warn("Link changeover error, " - "unable to send tunnel msg\n"); + pr_warn("%sunable to send tunnel msg\n", link_co_err); return; } skb_copy_to_linear_data(buf, tunnel_hdr, INT_H_SIZE); @@ -2173,8 +2181,7 @@ void tipc_link_changeover(struct tipc_link *l_ptr) return; if (!l_ptr->owner->permit_changeover) { - warn("Link changeover error, " - "peer did not permit changeover\n"); + pr_warn("%speer did not permit changeover\n", link_co_err); return; } @@ -2192,8 +2199,8 @@ void tipc_link_changeover(struct tipc_link *l_ptr) msg_set_size(&tunnel_hdr, INT_H_SIZE); tipc_link_send_buf(tunnel, buf); } else { - warn("Link changeover error, " - "unable to send changeover msg\n"); + pr_warn("%sunable to send changeover msg\n", + link_co_err); } return; } @@ -2246,8 +2253,8 @@ void tipc_link_send_duplicate(struct tipc_link *l_ptr, struct tipc_link *tunnel) msg_set_size(&tunnel_hdr, length + INT_H_SIZE); outbuf = tipc_buf_acquire(length + INT_H_SIZE); if (outbuf == NULL) { - warn("Link changeover error, " - "unable to send duplicate msg\n"); + pr_warn("%sunable to send duplicate msg\n", + link_co_err); return; } skb_copy_to_linear_data(outbuf, &tunnel_hdr, INT_H_SIZE); @@ -2298,8 +2305,8 @@ static int link_recv_changeover_msg(struct tipc_link **l_ptr, if (!dest_link) goto exit; if (dest_link == *l_ptr) { - err("Unexpected changeover message on link <%s>\n", - (*l_ptr)->name); + pr_err("Unexpected changeover message on link <%s>\n", + (*l_ptr)->name); goto exit; } *l_ptr = dest_link; @@ -2310,7 +2317,7 @@ static int link_recv_changeover_msg(struct tipc_link **l_ptr, goto exit; *buf = buf_extract(tunnel_buf, INT_H_SIZE); if (*buf == NULL) { - warn("Link changeover error, duplicate msg dropped\n"); + pr_warn("%sduplicate msg dropped\n", link_co_err); goto exit; } kfree_skb(tunnel_buf); @@ -2319,8 +2326,8 @@ static int link_recv_changeover_msg(struct tipc_link **l_ptr, /* First original message ?: */ if (tipc_link_is_up(dest_link)) { - info("Resetting link <%s>, changeover initiated by peer\n", - dest_link->name); + pr_info("%s<%s>, changeover initiated by peer\n", link_rst_msg, + dest_link->name); tipc_link_reset(dest_link); dest_link->exp_msg_count = msg_count; if (!msg_count) @@ -2333,8 +2340,7 @@ static int link_recv_changeover_msg(struct tipc_link **l_ptr, /* Receive original message */ if (dest_link->exp_msg_count == 0) { - warn("Link switchover error, " - "got too many tunnelled messages\n"); + pr_warn("%sgot too many tunnelled messages\n", link_co_err); goto exit; } dest_link->exp_msg_count--; @@ -2346,7 +2352,7 @@ static int link_recv_changeover_msg(struct tipc_link **l_ptr, kfree_skb(tunnel_buf); return 1; } else { - warn("Link changeover error, original msg dropped\n"); + pr_warn("%soriginal msg dropped\n", link_co_err); } } exit: @@ -2367,7 +2373,7 @@ void tipc_link_recv_bundle(struct sk_buff *buf) while (msgcount--) { obuf = buf_extract(buf, pos); if (obuf == NULL) { - warn("Link unable to unbundle message(s)\n"); + pr_warn("Link unable to unbundle message(s)\n"); break; } pos += align(msg_size(buf_msg(obuf))); @@ -2538,7 +2544,7 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, set_fragm_size(pbuf, fragm_sz); set_expected_frags(pbuf, exp_fragm_cnt - 1); } else { - dbg("Link unable to reassemble fragmented message\n"); + pr_debug("Link unable to reassemble fragmented message\n"); kfree_skb(fbuf); return -1; } @@ -2635,8 +2641,8 @@ void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window) /** * link_find_link - locate link by name - * @name - ptr to link name string - * @node - ptr to area to be filled with ptr to associated node + * @name: ptr to link name string + * @node: ptr to area to be filled with ptr to associated node * * Caller must hold 'tipc_net_lock' to ensure node and bearer are not deleted; * this also prevents link deletion. @@ -2671,8 +2677,8 @@ static struct tipc_link *link_find_link(const char *name, /** * link_value_is_valid -- validate proposed link tolerance/priority/window * - * @cmd - value type (TIPC_CMD_SET_LINK_*) - * @new_value - the new value + * @cmd: value type (TIPC_CMD_SET_LINK_*) + * @new_value: the new value * * Returns 1 if value is within range, 0 if not. */ @@ -2693,9 +2699,9 @@ static int link_value_is_valid(u16 cmd, u32 new_value) /** * link_cmd_set_value - change priority/tolerance/window for link/bearer/media - * @name - ptr to link, bearer, or media name - * @new_value - new value of link, bearer, or media setting - * @cmd - which link, bearer, or media attribute to set (TIPC_CMD_SET_LINK_*) + * @name: ptr to link, bearer, or media name + * @new_value: new value of link, bearer, or media setting + * @cmd: which link, bearer, or media attribute to set (TIPC_CMD_SET_LINK_*) * * Caller must hold 'tipc_net_lock' to ensure link/bearer/media is not deleted. * @@ -2860,112 +2866,114 @@ static u32 percent(u32 count, u32 total) */ static int tipc_link_stats(const char *name, char *buf, const u32 buf_size) { - struct print_buf pb; - struct tipc_link *l_ptr; + struct tipc_link *l; + struct tipc_stats *s; struct tipc_node *node; char *status; u32 profile_total = 0; + int ret; if (!strcmp(name, tipc_bclink_name)) return tipc_bclink_stats(buf, buf_size); - tipc_printbuf_init(&pb, buf, buf_size); - read_lock_bh(&tipc_net_lock); - l_ptr = link_find_link(name, &node); - if (!l_ptr) { + l = link_find_link(name, &node); + if (!l) { read_unlock_bh(&tipc_net_lock); return 0; } tipc_node_lock(node); + s = &l->stats; - if (tipc_link_is_active(l_ptr)) + if (tipc_link_is_active(l)) status = "ACTIVE"; - else if (tipc_link_is_up(l_ptr)) + else if (tipc_link_is_up(l)) status = "STANDBY"; else status = "DEFUNCT"; - tipc_printf(&pb, "Link <%s>\n" - " %s MTU:%u Priority:%u Tolerance:%u ms" - " Window:%u packets\n", - l_ptr->name, status, l_ptr->max_pkt, - l_ptr->priority, l_ptr->tolerance, l_ptr->queue_limit[0]); - tipc_printf(&pb, " RX packets:%u fragments:%u/%u bundles:%u/%u\n", - l_ptr->next_in_no - l_ptr->stats.recv_info, - l_ptr->stats.recv_fragments, - l_ptr->stats.recv_fragmented, - l_ptr->stats.recv_bundles, - l_ptr->stats.recv_bundled); - tipc_printf(&pb, " TX packets:%u fragments:%u/%u bundles:%u/%u\n", - l_ptr->next_out_no - l_ptr->stats.sent_info, - l_ptr->stats.sent_fragments, - l_ptr->stats.sent_fragmented, - l_ptr->stats.sent_bundles, - l_ptr->stats.sent_bundled); - profile_total = l_ptr->stats.msg_length_counts; + + ret = tipc_snprintf(buf, buf_size, "Link <%s>\n" + " %s MTU:%u Priority:%u Tolerance:%u ms" + " Window:%u packets\n", + l->name, status, l->max_pkt, l->priority, + l->tolerance, l->queue_limit[0]); + + ret += tipc_snprintf(buf + ret, buf_size - ret, + " RX packets:%u fragments:%u/%u bundles:%u/%u\n", + l->next_in_no - s->recv_info, s->recv_fragments, + s->recv_fragmented, s->recv_bundles, + s->recv_bundled); + + ret += tipc_snprintf(buf + ret, buf_size - ret, + " TX packets:%u fragments:%u/%u bundles:%u/%u\n", + l->next_out_no - s->sent_info, s->sent_fragments, + s->sent_fragmented, s->sent_bundles, + s->sent_bundled); + + profile_total = s->msg_length_counts; if (!profile_total) profile_total = 1; - tipc_printf(&pb, " TX profile sample:%u packets average:%u octets\n" - " 0-64:%u%% -256:%u%% -1024:%u%% -4096:%u%% " - "-16384:%u%% -32768:%u%% -66000:%u%%\n", - l_ptr->stats.msg_length_counts, - l_ptr->stats.msg_lengths_total / profile_total, - percent(l_ptr->stats.msg_length_profile[0], profile_total), - percent(l_ptr->stats.msg_length_profile[1], profile_total), - percent(l_ptr->stats.msg_length_profile[2], profile_total), - percent(l_ptr->stats.msg_length_profile[3], profile_total), - percent(l_ptr->stats.msg_length_profile[4], profile_total), - percent(l_ptr->stats.msg_length_profile[5], profile_total), - percent(l_ptr->stats.msg_length_profile[6], profile_total)); - tipc_printf(&pb, " RX states:%u probes:%u naks:%u defs:%u dups:%u\n", - l_ptr->stats.recv_states, - l_ptr->stats.recv_probes, - l_ptr->stats.recv_nacks, - l_ptr->stats.deferred_recv, - l_ptr->stats.duplicates); - tipc_printf(&pb, " TX states:%u probes:%u naks:%u acks:%u dups:%u\n", - l_ptr->stats.sent_states, - l_ptr->stats.sent_probes, - l_ptr->stats.sent_nacks, - l_ptr->stats.sent_acks, - l_ptr->stats.retransmitted); - tipc_printf(&pb, " Congestion bearer:%u link:%u Send queue max:%u avg:%u\n", - l_ptr->stats.bearer_congs, - l_ptr->stats.link_congs, - l_ptr->stats.max_queue_sz, - l_ptr->stats.queue_sz_counts - ? (l_ptr->stats.accu_queue_sz / l_ptr->stats.queue_sz_counts) - : 0); + + ret += tipc_snprintf(buf + ret, buf_size - ret, + " TX profile sample:%u packets average:%u octets\n" + " 0-64:%u%% -256:%u%% -1024:%u%% -4096:%u%% " + "-16384:%u%% -32768:%u%% -66000:%u%%\n", + s->msg_length_counts, + s->msg_lengths_total / profile_total, + percent(s->msg_length_profile[0], profile_total), + percent(s->msg_length_profile[1], profile_total), + percent(s->msg_length_profile[2], profile_total), + percent(s->msg_length_profile[3], profile_total), + percent(s->msg_length_profile[4], profile_total), + percent(s->msg_length_profile[5], profile_total), + percent(s->msg_length_profile[6], profile_total)); + + ret += tipc_snprintf(buf + ret, buf_size - ret, + " RX states:%u probes:%u naks:%u defs:%u" + " dups:%u\n", s->recv_states, s->recv_probes, + s->recv_nacks, s->deferred_recv, s->duplicates); + + ret += tipc_snprintf(buf + ret, buf_size - ret, + " TX states:%u probes:%u naks:%u acks:%u" + " dups:%u\n", s->sent_states, s->sent_probes, + s->sent_nacks, s->sent_acks, s->retransmitted); + + ret += tipc_snprintf(buf + ret, buf_size - ret, + " Congestion bearer:%u link:%u Send queue" + " max:%u avg:%u\n", s->bearer_congs, s->link_congs, + s->max_queue_sz, s->queue_sz_counts ? + (s->accu_queue_sz / s->queue_sz_counts) : 0); tipc_node_unlock(node); read_unlock_bh(&tipc_net_lock); - return tipc_printbuf_validate(&pb); + return ret; } -#define MAX_LINK_STATS_INFO 2000 - struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, int req_tlv_space) { struct sk_buff *buf; struct tlv_desc *rep_tlv; int str_len; + int pb_len; + char *pb; if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_LINK_NAME)) return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); - buf = tipc_cfg_reply_alloc(TLV_SPACE(MAX_LINK_STATS_INFO)); + buf = tipc_cfg_reply_alloc(TLV_SPACE(ULTRA_STRING_MAX_LEN)); if (!buf) return NULL; rep_tlv = (struct tlv_desc *)buf->data; - + pb = TLV_DATA(rep_tlv); + pb_len = ULTRA_STRING_MAX_LEN; str_len = tipc_link_stats((char *)TLV_DATA(req_tlv_area), - (char *)TLV_DATA(rep_tlv), MAX_LINK_STATS_INFO); + pb, pb_len); if (!str_len) { kfree_skb(buf); return tipc_cfg_reply_error_string("link not found"); } - + str_len += 1; /* for "\0" */ skb_put(buf, TLV_SPACE(str_len)); TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); @@ -3003,62 +3011,16 @@ u32 tipc_link_get_max_pkt(u32 dest, u32 selector) static void link_print(struct tipc_link *l_ptr, const char *str) { - char print_area[256]; - struct print_buf pb; - struct print_buf *buf = &pb; - - tipc_printbuf_init(buf, print_area, sizeof(print_area)); - - tipc_printf(buf, str); - tipc_printf(buf, "Link %x<%s>:", - l_ptr->addr, l_ptr->b_ptr->name); - -#ifdef CONFIG_TIPC_DEBUG - if (link_reset_reset(l_ptr) || link_reset_unknown(l_ptr)) - goto print_state; - - tipc_printf(buf, ": NXO(%u):", mod(l_ptr->next_out_no)); - tipc_printf(buf, "NXI(%u):", mod(l_ptr->next_in_no)); - tipc_printf(buf, "SQUE"); - if (l_ptr->first_out) { - tipc_printf(buf, "[%u..", buf_seqno(l_ptr->first_out)); - if (l_ptr->next_out) - tipc_printf(buf, "%u..", buf_seqno(l_ptr->next_out)); - tipc_printf(buf, "%u]", buf_seqno(l_ptr->last_out)); - if ((mod(buf_seqno(l_ptr->last_out) - - buf_seqno(l_ptr->first_out)) - != (l_ptr->out_queue_size - 1)) || - (l_ptr->last_out->next != NULL)) { - tipc_printf(buf, "\nSend queue inconsistency\n"); - tipc_printf(buf, "first_out= %p ", l_ptr->first_out); - tipc_printf(buf, "next_out= %p ", l_ptr->next_out); - tipc_printf(buf, "last_out= %p ", l_ptr->last_out); - } - } else - tipc_printf(buf, "[]"); - tipc_printf(buf, "SQSIZ(%u)", l_ptr->out_queue_size); - if (l_ptr->oldest_deferred_in) { - u32 o = buf_seqno(l_ptr->oldest_deferred_in); - u32 n = buf_seqno(l_ptr->newest_deferred_in); - tipc_printf(buf, ":RQUE[%u..%u]", o, n); - if (l_ptr->deferred_inqueue_sz != mod((n + 1) - o)) { - tipc_printf(buf, ":RQSIZ(%u)", - l_ptr->deferred_inqueue_sz); - } - } -print_state: -#endif + pr_info("%s Link %x<%s>:", str, l_ptr->addr, l_ptr->b_ptr->name); if (link_working_unknown(l_ptr)) - tipc_printf(buf, ":WU"); + pr_cont(":WU\n"); else if (link_reset_reset(l_ptr)) - tipc_printf(buf, ":RR"); + pr_cont(":RR\n"); else if (link_reset_unknown(l_ptr)) - tipc_printf(buf, ":RU"); + pr_cont(":RU\n"); else if (link_working_working(l_ptr)) - tipc_printf(buf, ":WW"); - tipc_printf(buf, "\n"); - - tipc_printbuf_validate(buf); - info("%s", print_area); + pr_cont(":WW\n"); + else + pr_cont("\n"); } diff --git a/net/tipc/link.h b/net/tipc/link.h index d6a60a963ce..6e921121be0 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -37,7 +37,6 @@ #ifndef _TIPC_LINK_H #define _TIPC_LINK_H -#include "log.h" #include "msg.h" #include "node.h" @@ -63,6 +62,37 @@ */ #define MAX_PKT_DEFAULT 1500 +struct tipc_stats { + u32 sent_info; /* used in counting # sent packets */ + u32 recv_info; /* used in counting # recv'd packets */ + u32 sent_states; + u32 recv_states; + u32 sent_probes; + u32 recv_probes; + u32 sent_nacks; + u32 recv_nacks; + u32 sent_acks; + u32 sent_bundled; + u32 sent_bundles; + u32 recv_bundled; + u32 recv_bundles; + u32 retransmitted; + u32 sent_fragmented; + u32 sent_fragments; + u32 recv_fragmented; + u32 recv_fragments; + u32 link_congs; /* # port sends blocked by congestion */ + u32 bearer_congs; + u32 deferred_recv; + u32 duplicates; + u32 max_queue_sz; /* send queue size high water mark */ + u32 accu_queue_sz; /* used for send queue size profiling */ + u32 queue_sz_counts; /* used for send queue size profiling */ + u32 msg_length_counts; /* used for message length profiling */ + u32 msg_lengths_total; /* used for message length profiling */ + u32 msg_length_profile[7]; /* used for msg. length profiling */ +}; + /** * struct tipc_link - TIPC link data structure * @addr: network address of link's peer node @@ -175,36 +205,7 @@ struct tipc_link { struct sk_buff *defragm_buf; /* Statistics */ - struct { - u32 sent_info; /* used in counting # sent packets */ - u32 recv_info; /* used in counting # recv'd packets */ - u32 sent_states; - u32 recv_states; - u32 sent_probes; - u32 recv_probes; - u32 sent_nacks; - u32 recv_nacks; - u32 sent_acks; - u32 sent_bundled; - u32 sent_bundles; - u32 recv_bundled; - u32 recv_bundles; - u32 retransmitted; - u32 sent_fragmented; - u32 sent_fragments; - u32 recv_fragmented; - u32 recv_fragments; - u32 link_congs; /* # port sends blocked by congestion */ - u32 bearer_congs; - u32 deferred_recv; - u32 duplicates; - u32 max_queue_sz; /* send queue size high water mark */ - u32 accu_queue_sz; /* used for send queue size profiling */ - u32 queue_sz_counts; /* used for send queue size profiling */ - u32 msg_length_counts; /* used for message length profiling */ - u32 msg_lengths_total; /* used for message length profiling */ - u32 msg_length_profile[7]; /* used for msg. length profiling */ - } stats; + struct tipc_stats stats; }; struct tipc_port; diff --git a/net/tipc/log.c b/net/tipc/log.c index 026733f2491..abef644f27d 100644 --- a/net/tipc/log.c +++ b/net/tipc/log.c @@ -36,302 +36,20 @@ #include "core.h" #include "config.h" -#include "log.h" - -/* - * TIPC pre-defines the following print buffers: - * - * TIPC_NULL : null buffer (i.e. print nowhere) - * TIPC_CONS : system console - * TIPC_LOG : TIPC log buffer - * - * Additional user-defined print buffers are also permitted. - */ -static struct print_buf null_buf = { NULL, 0, NULL, 0 }; -struct print_buf *const TIPC_NULL = &null_buf; - -static struct print_buf cons_buf = { NULL, 0, NULL, 1 }; -struct print_buf *const TIPC_CONS = &cons_buf; - -static struct print_buf log_buf = { NULL, 0, NULL, 1 }; -struct print_buf *const TIPC_LOG = &log_buf; - -/* - * Locking policy when using print buffers. - * - * 1) tipc_printf() uses 'print_lock' to protect against concurrent access to - * 'print_string' when writing to a print buffer. This also protects against - * concurrent writes to the print buffer being written to. - * - * 2) tipc_log_XXX() leverages the aforementioned use of 'print_lock' to - * protect against all types of concurrent operations on their associated - * print buffer (not just write operations). - * - * Note: All routines of the form tipc_printbuf_XXX() are lock-free, and rely - * on the caller to prevent simultaneous use of the print buffer(s) being - * manipulated. - */ -static char print_string[TIPC_PB_MAX_STR]; -static DEFINE_SPINLOCK(print_lock); - -static void tipc_printbuf_move(struct print_buf *pb_to, - struct print_buf *pb_from); - -#define FORMAT(PTR, LEN, FMT) \ -{\ - va_list args;\ - va_start(args, FMT);\ - LEN = vsprintf(PTR, FMT, args);\ - va_end(args);\ - *(PTR + LEN) = '\0';\ -} - -/** - * tipc_printbuf_init - initialize print buffer to empty - * @pb: pointer to print buffer structure - * @raw: pointer to character array used by print buffer - * @size: size of character array - * - * Note: If the character array is too small (or absent), the print buffer - * becomes a null device that discards anything written to it. - */ -void tipc_printbuf_init(struct print_buf *pb, char *raw, u32 size) -{ - pb->buf = raw; - pb->crs = raw; - pb->size = size; - pb->echo = 0; - - if (size < TIPC_PB_MIN_SIZE) { - pb->buf = NULL; - } else if (raw) { - pb->buf[0] = 0; - pb->buf[size - 1] = ~0; - } -} - -/** - * tipc_printbuf_reset - reinitialize print buffer to empty state - * @pb: pointer to print buffer structure - */ -static void tipc_printbuf_reset(struct print_buf *pb) -{ - if (pb->buf) { - pb->crs = pb->buf; - pb->buf[0] = 0; - pb->buf[pb->size - 1] = ~0; - } -} - -/** - * tipc_printbuf_empty - test if print buffer is in empty state - * @pb: pointer to print buffer structure - * - * Returns non-zero if print buffer is empty. - */ -static int tipc_printbuf_empty(struct print_buf *pb) -{ - return !pb->buf || (pb->crs == pb->buf); -} - -/** - * tipc_printbuf_validate - check for print buffer overflow - * @pb: pointer to print buffer structure - * - * Verifies that a print buffer has captured all data written to it. - * If data has been lost, linearize buffer and prepend an error message - * - * Returns length of print buffer data string (including trailing NUL) - */ -int tipc_printbuf_validate(struct print_buf *pb) -{ - char *err = "\n\n*** PRINT BUFFER OVERFLOW ***\n\n"; - char *cp_buf; - struct print_buf cb; - - if (!pb->buf) - return 0; - - if (pb->buf[pb->size - 1] == 0) { - cp_buf = kmalloc(pb->size, GFP_ATOMIC); - if (cp_buf) { - tipc_printbuf_init(&cb, cp_buf, pb->size); - tipc_printbuf_move(&cb, pb); - tipc_printbuf_move(pb, &cb); - kfree(cp_buf); - memcpy(pb->buf, err, strlen(err)); - } else { - tipc_printbuf_reset(pb); - tipc_printf(pb, err); - } - } - return pb->crs - pb->buf + 1; -} - -/** - * tipc_printbuf_move - move print buffer contents to another print buffer - * @pb_to: pointer to destination print buffer structure - * @pb_from: pointer to source print buffer structure - * - * Current contents of destination print buffer (if any) are discarded. - * Source print buffer becomes empty if a successful move occurs. - */ -static void tipc_printbuf_move(struct print_buf *pb_to, - struct print_buf *pb_from) -{ - int len; - - /* Handle the cases where contents can't be moved */ - if (!pb_to->buf) - return; - - if (!pb_from->buf) { - tipc_printbuf_reset(pb_to); - return; - } - - if (pb_to->size < pb_from->size) { - strcpy(pb_to->buf, "*** PRINT BUFFER MOVE ERROR ***"); - pb_to->buf[pb_to->size - 1] = ~0; - pb_to->crs = strchr(pb_to->buf, 0); - return; - } - - /* Copy data from char after cursor to end (if used) */ - len = pb_from->buf + pb_from->size - pb_from->crs - 2; - if ((pb_from->buf[pb_from->size - 1] == 0) && (len > 0)) { - strcpy(pb_to->buf, pb_from->crs + 1); - pb_to->crs = pb_to->buf + len; - } else - pb_to->crs = pb_to->buf; - - /* Copy data from start to cursor (always) */ - len = pb_from->crs - pb_from->buf; - strcpy(pb_to->crs, pb_from->buf); - pb_to->crs += len; - - tipc_printbuf_reset(pb_from); -} /** - * tipc_printf - append formatted output to print buffer - * @pb: pointer to print buffer + * tipc_snprintf - append formatted output to print buffer + * @buf: pointer to print buffer + * @len: buffer length * @fmt: formatted info to be printed */ -void tipc_printf(struct print_buf *pb, const char *fmt, ...) -{ - int chars_to_add; - int chars_left; - char save_char; - - spin_lock_bh(&print_lock); - - FORMAT(print_string, chars_to_add, fmt); - if (chars_to_add >= TIPC_PB_MAX_STR) - strcpy(print_string, "*** PRINT BUFFER STRING TOO LONG ***"); - - if (pb->buf) { - chars_left = pb->buf + pb->size - pb->crs - 1; - if (chars_to_add <= chars_left) { - strcpy(pb->crs, print_string); - pb->crs += chars_to_add; - } else if (chars_to_add >= (pb->size - 1)) { - strcpy(pb->buf, print_string + chars_to_add + 1 - - pb->size); - pb->crs = pb->buf + pb->size - 1; - } else { - strcpy(pb->buf, print_string + chars_left); - save_char = print_string[chars_left]; - print_string[chars_left] = 0; - strcpy(pb->crs, print_string); - print_string[chars_left] = save_char; - pb->crs = pb->buf + chars_to_add - chars_left; - } - } - - if (pb->echo) - printk("%s", print_string); - - spin_unlock_bh(&print_lock); -} - -/** - * tipc_log_resize - change the size of the TIPC log buffer - * @log_size: print buffer size to use - */ -int tipc_log_resize(int log_size) -{ - int res = 0; - - spin_lock_bh(&print_lock); - kfree(TIPC_LOG->buf); - TIPC_LOG->buf = NULL; - if (log_size) { - if (log_size < TIPC_PB_MIN_SIZE) - log_size = TIPC_PB_MIN_SIZE; - res = TIPC_LOG->echo; - tipc_printbuf_init(TIPC_LOG, kmalloc(log_size, GFP_ATOMIC), - log_size); - TIPC_LOG->echo = res; - res = !TIPC_LOG->buf; - } - spin_unlock_bh(&print_lock); - - return res; -} - -/** - * tipc_log_resize_cmd - reconfigure size of TIPC log buffer - */ -struct sk_buff *tipc_log_resize_cmd(const void *req_tlv_area, int req_tlv_space) -{ - u32 value; - - if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) - return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); - - value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area)); - if (value > 32768) - return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE - " (log size must be 0-32768)"); - if (tipc_log_resize(value)) - return tipc_cfg_reply_error_string( - "unable to create specified log (log size is now 0)"); - return tipc_cfg_reply_none(); -} - -/** - * tipc_log_dump - capture TIPC log buffer contents in configuration message - */ -struct sk_buff *tipc_log_dump(void) +int tipc_snprintf(char *buf, int len, const char *fmt, ...) { - struct sk_buff *reply; - - spin_lock_bh(&print_lock); - if (!TIPC_LOG->buf) { - spin_unlock_bh(&print_lock); - reply = tipc_cfg_reply_ultra_string("log not activated\n"); - } else if (tipc_printbuf_empty(TIPC_LOG)) { - spin_unlock_bh(&print_lock); - reply = tipc_cfg_reply_ultra_string("log is empty\n"); - } else { - struct tlv_desc *rep_tlv; - struct print_buf pb; - int str_len; + int i; + va_list args; - str_len = min(TIPC_LOG->size, 32768u); - spin_unlock_bh(&print_lock); - reply = tipc_cfg_reply_alloc(TLV_SPACE(str_len)); - if (reply) { - rep_tlv = (struct tlv_desc *)reply->data; - tipc_printbuf_init(&pb, TLV_DATA(rep_tlv), str_len); - spin_lock_bh(&print_lock); - tipc_printbuf_move(&pb, TIPC_LOG); - spin_unlock_bh(&print_lock); - str_len = strlen(TLV_DATA(rep_tlv)) + 1; - skb_put(reply, TLV_SPACE(str_len)); - TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); - } - } - return reply; + va_start(args, fmt); + i = vscnprintf(buf, len, fmt, args); + va_end(args); + return i; } diff --git a/net/tipc/log.h b/net/tipc/log.h deleted file mode 100644 index d1f5eb967fd..00000000000 --- a/net/tipc/log.h +++ /dev/null @@ -1,66 +0,0 @@ -/* - * net/tipc/log.h: Include file for TIPC print buffer routines - * - * Copyright (c) 1997-2006, Ericsson AB - * Copyright (c) 2005-2007, Wind River Systems - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#ifndef _TIPC_LOG_H -#define _TIPC_LOG_H - -/** - * struct print_buf - TIPC print buffer structure - * @buf: pointer to character array containing print buffer contents - * @size: size of character array - * @crs: pointer to first unused space in character array (i.e. final NUL) - * @echo: echo output to system console if non-zero - */ -struct print_buf { - char *buf; - u32 size; - char *crs; - int echo; -}; - -#define TIPC_PB_MIN_SIZE 64 /* minimum size for a print buffer's array */ -#define TIPC_PB_MAX_STR 512 /* max printable string (with trailing NUL) */ - -void tipc_printbuf_init(struct print_buf *pb, char *buf, u32 size); -int tipc_printbuf_validate(struct print_buf *pb); - -int tipc_log_resize(int log_size); - -struct sk_buff *tipc_log_resize_cmd(const void *req_tlv_area, - int req_tlv_space); -struct sk_buff *tipc_log_dump(void); - -#endif diff --git a/net/tipc/msg.c b/net/tipc/msg.c index deea0d232dc..f2db8a87d9c 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -109,245 +109,3 @@ int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect, *buf = NULL; return -EFAULT; } - -#ifdef CONFIG_TIPC_DEBUG -void tipc_msg_dbg(struct print_buf *buf, struct tipc_msg *msg, const char *str) -{ - u32 usr = msg_user(msg); - tipc_printf(buf, KERN_DEBUG); - tipc_printf(buf, str); - - switch (usr) { - case MSG_BUNDLER: - tipc_printf(buf, "BNDL::"); - tipc_printf(buf, "MSGS(%u):", msg_msgcnt(msg)); - break; - case BCAST_PROTOCOL: - tipc_printf(buf, "BCASTP::"); - break; - case MSG_FRAGMENTER: - tipc_printf(buf, "FRAGM::"); - switch (msg_type(msg)) { - case FIRST_FRAGMENT: - tipc_printf(buf, "FIRST:"); - break; - case FRAGMENT: - tipc_printf(buf, "BODY:"); - break; - case LAST_FRAGMENT: - tipc_printf(buf, "LAST:"); - break; - default: - tipc_printf(buf, "UNKNOWN:%x", msg_type(msg)); - - } - tipc_printf(buf, "NO(%u/%u):", msg_long_msgno(msg), - msg_fragm_no(msg)); - break; - case TIPC_LOW_IMPORTANCE: - case TIPC_MEDIUM_IMPORTANCE: - case TIPC_HIGH_IMPORTANCE: - case TIPC_CRITICAL_IMPORTANCE: - tipc_printf(buf, "DAT%u:", msg_user(msg)); - if (msg_short(msg)) { - tipc_printf(buf, "CON:"); - break; - } - switch (msg_type(msg)) { - case TIPC_CONN_MSG: - tipc_printf(buf, "CON:"); - break; - case TIPC_MCAST_MSG: - tipc_printf(buf, "MCST:"); - break; - case TIPC_NAMED_MSG: - tipc_printf(buf, "NAM:"); - break; - case TIPC_DIRECT_MSG: - tipc_printf(buf, "DIR:"); - break; - default: - tipc_printf(buf, "UNKNOWN TYPE %u", msg_type(msg)); - } - if (msg_reroute_cnt(msg)) - tipc_printf(buf, "REROUTED(%u):", - msg_reroute_cnt(msg)); - break; - case NAME_DISTRIBUTOR: - tipc_printf(buf, "NMD::"); - switch (msg_type(msg)) { - case PUBLICATION: - tipc_printf(buf, "PUBL(%u):", (msg_size(msg) - msg_hdr_sz(msg)) / 20); /* Items */ - break; - case WITHDRAWAL: - tipc_printf(buf, "WDRW:"); - break; - default: - tipc_printf(buf, "UNKNOWN:%x", msg_type(msg)); - } - if (msg_reroute_cnt(msg)) - tipc_printf(buf, "REROUTED(%u):", - msg_reroute_cnt(msg)); - break; - case CONN_MANAGER: - tipc_printf(buf, "CONN_MNG:"); - switch (msg_type(msg)) { - case CONN_PROBE: - tipc_printf(buf, "PROBE:"); - break; - case CONN_PROBE_REPLY: - tipc_printf(buf, "PROBE_REPLY:"); - break; - case CONN_ACK: - tipc_printf(buf, "CONN_ACK:"); - tipc_printf(buf, "ACK(%u):", msg_msgcnt(msg)); - break; - default: - tipc_printf(buf, "UNKNOWN TYPE:%x", msg_type(msg)); - } - if (msg_reroute_cnt(msg)) - tipc_printf(buf, "REROUTED(%u):", msg_reroute_cnt(msg)); - break; - case LINK_PROTOCOL: - switch (msg_type(msg)) { - case STATE_MSG: - tipc_printf(buf, "STATE:"); - tipc_printf(buf, "%s:", msg_probe(msg) ? "PRB" : ""); - tipc_printf(buf, "NXS(%u):", msg_next_sent(msg)); - tipc_printf(buf, "GAP(%u):", msg_seq_gap(msg)); - tipc_printf(buf, "LSTBC(%u):", msg_last_bcast(msg)); - break; - case RESET_MSG: - tipc_printf(buf, "RESET:"); - if (msg_size(msg) != msg_hdr_sz(msg)) - tipc_printf(buf, "BEAR:%s:", msg_data(msg)); - break; - case ACTIVATE_MSG: - tipc_printf(buf, "ACTIVATE:"); - break; - default: - tipc_printf(buf, "UNKNOWN TYPE:%x", msg_type(msg)); - } - tipc_printf(buf, "PLANE(%c):", msg_net_plane(msg)); - tipc_printf(buf, "SESS(%u):", msg_session(msg)); - break; - case CHANGEOVER_PROTOCOL: - tipc_printf(buf, "TUNL:"); - switch (msg_type(msg)) { - case DUPLICATE_MSG: - tipc_printf(buf, "DUPL:"); - break; - case ORIGINAL_MSG: - tipc_printf(buf, "ORIG:"); - tipc_printf(buf, "EXP(%u)", msg_msgcnt(msg)); - break; - default: - tipc_printf(buf, "UNKNOWN TYPE:%x", msg_type(msg)); - } - break; - case LINK_CONFIG: - tipc_printf(buf, "CFG:"); - switch (msg_type(msg)) { - case DSC_REQ_MSG: - tipc_printf(buf, "DSC_REQ:"); - break; - case DSC_RESP_MSG: - tipc_printf(buf, "DSC_RESP:"); - break; - default: - tipc_printf(buf, "UNKNOWN TYPE:%x:", msg_type(msg)); - break; - } - break; - default: - tipc_printf(buf, "UNKNOWN USER:"); - } - - switch (usr) { - case CONN_MANAGER: - case TIPC_LOW_IMPORTANCE: - case TIPC_MEDIUM_IMPORTANCE: - case TIPC_HIGH_IMPORTANCE: - case TIPC_CRITICAL_IMPORTANCE: - switch (msg_errcode(msg)) { - case TIPC_OK: - break; - case TIPC_ERR_NO_NAME: - tipc_printf(buf, "NO_NAME:"); - break; - case TIPC_ERR_NO_PORT: - tipc_printf(buf, "NO_PORT:"); - break; - case TIPC_ERR_NO_NODE: - tipc_printf(buf, "NO_PROC:"); - break; - case TIPC_ERR_OVERLOAD: - tipc_printf(buf, "OVERLOAD:"); - break; - case TIPC_CONN_SHUTDOWN: - tipc_printf(buf, "SHUTDOWN:"); - break; - default: - tipc_printf(buf, "UNKNOWN ERROR(%x):", - msg_errcode(msg)); - } - default: - break; - } - - tipc_printf(buf, "HZ(%u):", msg_hdr_sz(msg)); - tipc_printf(buf, "SZ(%u):", msg_size(msg)); - tipc_printf(buf, "SQNO(%u):", msg_seqno(msg)); - - if (msg_non_seq(msg)) - tipc_printf(buf, "NOSEQ:"); - else - tipc_printf(buf, "ACK(%u):", msg_ack(msg)); - tipc_printf(buf, "BACK(%u):", msg_bcast_ack(msg)); - tipc_printf(buf, "PRND(%x)", msg_prevnode(msg)); - - if (msg_isdata(msg)) { - if (msg_named(msg)) { - tipc_printf(buf, "NTYP(%u):", msg_nametype(msg)); - tipc_printf(buf, "NINST(%u)", msg_nameinst(msg)); - } - } - - if ((usr != LINK_PROTOCOL) && (usr != LINK_CONFIG) && - (usr != MSG_BUNDLER)) { - if (!msg_short(msg)) { - tipc_printf(buf, ":ORIG(%x:%u):", - msg_orignode(msg), msg_origport(msg)); - tipc_printf(buf, ":DEST(%x:%u):", - msg_destnode(msg), msg_destport(msg)); - } else { - tipc_printf(buf, ":OPRT(%u):", msg_origport(msg)); - tipc_printf(buf, ":DPRT(%u):", msg_destport(msg)); - } - } - if (msg_user(msg) == NAME_DISTRIBUTOR) { - tipc_printf(buf, ":ONOD(%x):", msg_orignode(msg)); - tipc_printf(buf, ":DNOD(%x):", msg_destnode(msg)); - } - - if (msg_user(msg) == LINK_CONFIG) { - struct tipc_media_addr orig; - - tipc_printf(buf, ":DDOM(%x):", msg_dest_domain(msg)); - tipc_printf(buf, ":NETID(%u):", msg_bc_netid(msg)); - memcpy(orig.value, msg_media_addr(msg), sizeof(orig.value)); - orig.media_id = 0; - orig.broadcast = 0; - tipc_media_addr_printf(buf, &orig); - } - if (msg_user(msg) == BCAST_PROTOCOL) { - tipc_printf(buf, "BCNACK:AFTER(%u):", msg_bcgap_after(msg)); - tipc_printf(buf, "TO(%u):", msg_bcgap_to(msg)); - } - tipc_printf(buf, "\n"); - if ((usr == CHANGEOVER_PROTOCOL) && (msg_msgcnt(msg))) - tipc_msg_dbg(buf, msg_get_wrapped(msg), " /"); - if ((usr == MSG_FRAGMENTER) && (msg_type(msg) == FIRST_FRAGMENT)) - tipc_msg_dbg(buf, msg_get_wrapped(msg), " /"); -} -#endif diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 158318e67b0..55d3928dfd6 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -161,7 +161,7 @@ void tipc_named_publish(struct publication *publ) buf = named_prepare_buf(PUBLICATION, ITEM_SIZE, 0); if (!buf) { - warn("Publication distribution failure\n"); + pr_warn("Publication distribution failure\n"); return; } @@ -186,7 +186,7 @@ void tipc_named_withdraw(struct publication *publ) buf = named_prepare_buf(WITHDRAWAL, ITEM_SIZE, 0); if (!buf) { - warn("Withdrawal distribution failure\n"); + pr_warn("Withdrawal distribution failure\n"); return; } @@ -213,7 +213,7 @@ static void named_distribute(struct list_head *message_list, u32 node, rest -= left; buf = named_prepare_buf(PUBLICATION, left, node); if (!buf) { - warn("Bulk publication failure\n"); + pr_warn("Bulk publication failure\n"); return; } item = (struct distr_item *)msg_data(buf_msg(buf)); @@ -283,9 +283,10 @@ static void named_purge_publ(struct publication *publ) write_unlock_bh(&tipc_nametbl_lock); if (p != publ) { - err("Unable to remove publication from failed node\n" - "(type=%u, lower=%u, node=0x%x, ref=%u, key=%u)\n", - publ->type, publ->lower, publ->node, publ->ref, publ->key); + pr_err("Unable to remove publication from failed node\n" + " (type=%u, lower=%u, node=0x%x, ref=%u, key=%u)\n", + publ->type, publ->lower, publ->node, publ->ref, + publ->key); } kfree(p); @@ -329,14 +330,14 @@ void tipc_named_recv(struct sk_buff *buf) tipc_nodesub_unsubscribe(&publ->subscr); kfree(publ); } else { - err("Unable to remove publication by node 0x%x\n" - "(type=%u, lower=%u, ref=%u, key=%u)\n", - msg_orignode(msg), - ntohl(item->type), ntohl(item->lower), - ntohl(item->ref), ntohl(item->key)); + pr_err("Unable to remove publication by node 0x%x\n" + " (type=%u, lower=%u, ref=%u, key=%u)\n", + msg_orignode(msg), ntohl(item->type), + ntohl(item->lower), ntohl(item->ref), + ntohl(item->key)); } } else { - warn("Unrecognized name table message received\n"); + pr_warn("Unrecognized name table message received\n"); } item++; } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 010f24a59da..360c478b0b5 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -126,7 +126,7 @@ static struct publication *publ_create(u32 type, u32 lower, u32 upper, { struct publication *publ = kzalloc(sizeof(*publ), GFP_ATOMIC); if (publ == NULL) { - warn("Publication creation failure, no memory\n"); + pr_warn("Publication creation failure, no memory\n"); return NULL; } @@ -163,7 +163,7 @@ static struct name_seq *tipc_nameseq_create(u32 type, struct hlist_head *seq_hea struct sub_seq *sseq = tipc_subseq_alloc(1); if (!nseq || !sseq) { - warn("Name sequence creation failed, no memory\n"); + pr_warn("Name sequence creation failed, no memory\n"); kfree(nseq); kfree(sseq); return NULL; @@ -191,7 +191,7 @@ static void nameseq_delete_empty(struct name_seq *seq) } } -/* +/** * nameseq_find_subseq - find sub-sequence (if any) matching a name instance * * Very time-critical, so binary searches through sub-sequence array. @@ -263,8 +263,8 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, /* Lower end overlaps existing entry => need an exact match */ if ((sseq->lower != lower) || (sseq->upper != upper)) { - warn("Cannot publish {%u,%u,%u}, overlap error\n", - type, lower, upper); + pr_warn("Cannot publish {%u,%u,%u}, overlap error\n", + type, lower, upper); return NULL; } @@ -286,8 +286,8 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, /* Fail if upper end overlaps into an existing entry */ if ((inspos < nseq->first_free) && (upper >= nseq->sseqs[inspos].lower)) { - warn("Cannot publish {%u,%u,%u}, overlap error\n", - type, lower, upper); + pr_warn("Cannot publish {%u,%u,%u}, overlap error\n", + type, lower, upper); return NULL; } @@ -296,8 +296,8 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, struct sub_seq *sseqs = tipc_subseq_alloc(nseq->alloc * 2); if (!sseqs) { - warn("Cannot publish {%u,%u,%u}, no memory\n", - type, lower, upper); + pr_warn("Cannot publish {%u,%u,%u}, no memory\n", + type, lower, upper); return NULL; } memcpy(sseqs, nseq->sseqs, @@ -309,8 +309,8 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, info = kzalloc(sizeof(*info), GFP_ATOMIC); if (!info) { - warn("Cannot publish {%u,%u,%u}, no memory\n", - type, lower, upper); + pr_warn("Cannot publish {%u,%u,%u}, no memory\n", + type, lower, upper); return NULL; } @@ -435,7 +435,7 @@ found: } /** - * tipc_nameseq_subscribe: attach a subscription, and issue + * tipc_nameseq_subscribe - attach a subscription, and issue * the prescribed number of events if there is any sub- * sequence overlapping with the requested sequence */ @@ -492,8 +492,8 @@ struct publication *tipc_nametbl_insert_publ(u32 type, u32 lower, u32 upper, if ((scope < TIPC_ZONE_SCOPE) || (scope > TIPC_NODE_SCOPE) || (lower > upper)) { - dbg("Failed to publish illegal {%u,%u,%u} with scope %u\n", - type, lower, upper, scope); + pr_debug("Failed to publish illegal {%u,%u,%u} with scope %u\n", + type, lower, upper, scope); return NULL; } @@ -520,7 +520,7 @@ struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower, return publ; } -/* +/** * tipc_nametbl_translate - perform name translation * * On entry, 'destnode' is the search domain used during translation. @@ -668,8 +668,8 @@ struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper, struct publication *publ; if (table.local_publ_count >= tipc_max_publications) { - warn("Publication failed, local publication limit reached (%u)\n", - tipc_max_publications); + pr_warn("Publication failed, local publication limit reached (%u)\n", + tipc_max_publications); return NULL; } @@ -702,9 +702,9 @@ int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key) return 1; } write_unlock_bh(&tipc_nametbl_lock); - err("Unable to remove local publication\n" - "(type=%u, lower=%u, ref=%u, key=%u)\n", - type, lower, ref, key); + pr_err("Unable to remove local publication\n" + "(type=%u, lower=%u, ref=%u, key=%u)\n", + type, lower, ref, key); return 0; } @@ -725,8 +725,8 @@ void tipc_nametbl_subscribe(struct tipc_subscription *s) tipc_nameseq_subscribe(seq, s); spin_unlock_bh(&seq->lock); } else { - warn("Failed to create subscription for {%u,%u,%u}\n", - s->seq.type, s->seq.lower, s->seq.upper); + pr_warn("Failed to create subscription for {%u,%u,%u}\n", + s->seq.type, s->seq.lower, s->seq.upper); } write_unlock_bh(&tipc_nametbl_lock); } @@ -751,21 +751,22 @@ void tipc_nametbl_unsubscribe(struct tipc_subscription *s) /** - * subseq_list: print specified sub-sequence contents into the given buffer + * subseq_list - print specified sub-sequence contents into the given buffer */ -static void subseq_list(struct sub_seq *sseq, struct print_buf *buf, u32 depth, +static int subseq_list(struct sub_seq *sseq, char *buf, int len, u32 depth, u32 index) { char portIdStr[27]; const char *scope_str[] = {"", " zone", " cluster", " node"}; struct publication *publ; struct name_info *info; + int ret; - tipc_printf(buf, "%-10u %-10u ", sseq->lower, sseq->upper); + ret = tipc_snprintf(buf, len, "%-10u %-10u ", sseq->lower, sseq->upper); if (depth == 2) { - tipc_printf(buf, "\n"); - return; + ret += tipc_snprintf(buf - ret, len + ret, "\n"); + return ret; } info = sseq->info; @@ -774,52 +775,58 @@ static void subseq_list(struct sub_seq *sseq, struct print_buf *buf, u32 depth, sprintf(portIdStr, "<%u.%u.%u:%u>", tipc_zone(publ->node), tipc_cluster(publ->node), tipc_node(publ->node), publ->ref); - tipc_printf(buf, "%-26s ", portIdStr); + ret += tipc_snprintf(buf + ret, len - ret, "%-26s ", portIdStr); if (depth > 3) { - tipc_printf(buf, "%-10u %s", publ->key, - scope_str[publ->scope]); + ret += tipc_snprintf(buf + ret, len - ret, "%-10u %s", + publ->key, scope_str[publ->scope]); } if (!list_is_last(&publ->zone_list, &info->zone_list)) - tipc_printf(buf, "\n%33s", " "); + ret += tipc_snprintf(buf + ret, len - ret, + "\n%33s", " "); }; - tipc_printf(buf, "\n"); + ret += tipc_snprintf(buf + ret, len - ret, "\n"); + return ret; } /** - * nameseq_list: print specified name sequence contents into the given buffer + * nameseq_list - print specified name sequence contents into the given buffer */ -static void nameseq_list(struct name_seq *seq, struct print_buf *buf, u32 depth, +static int nameseq_list(struct name_seq *seq, char *buf, int len, u32 depth, u32 type, u32 lowbound, u32 upbound, u32 index) { struct sub_seq *sseq; char typearea[11]; + int ret = 0; if (seq->first_free == 0) - return; + return 0; sprintf(typearea, "%-10u", seq->type); if (depth == 1) { - tipc_printf(buf, "%s\n", typearea); - return; + ret += tipc_snprintf(buf, len, "%s\n", typearea); + return ret; } for (sseq = seq->sseqs; sseq != &seq->sseqs[seq->first_free]; sseq++) { if ((lowbound <= sseq->upper) && (upbound >= sseq->lower)) { - tipc_printf(buf, "%s ", typearea); + ret += tipc_snprintf(buf + ret, len - ret, "%s ", + typearea); spin_lock_bh(&seq->lock); - subseq_list(sseq, buf, depth, index); + ret += subseq_list(sseq, buf + ret, len - ret, + depth, index); spin_unlock_bh(&seq->lock); sprintf(typearea, "%10s", " "); } } + return ret; } /** * nametbl_header - print name table header into the given buffer */ -static void nametbl_header(struct print_buf *buf, u32 depth) +static int nametbl_header(char *buf, int len, u32 depth) { const char *header[] = { "Type ", @@ -829,24 +836,27 @@ static void nametbl_header(struct print_buf *buf, u32 depth) }; int i; + int ret = 0; if (depth > 4) depth = 4; for (i = 0; i < depth; i++) - tipc_printf(buf, header[i]); - tipc_printf(buf, "\n"); + ret += tipc_snprintf(buf + ret, len - ret, header[i]); + ret += tipc_snprintf(buf + ret, len - ret, "\n"); + return ret; } /** * nametbl_list - print specified name table contents into the given buffer */ -static void nametbl_list(struct print_buf *buf, u32 depth_info, +static int nametbl_list(char *buf, int len, u32 depth_info, u32 type, u32 lowbound, u32 upbound) { struct hlist_head *seq_head; struct hlist_node *seq_node; struct name_seq *seq; int all_types; + int ret = 0; u32 depth; u32 i; @@ -854,65 +864,69 @@ static void nametbl_list(struct print_buf *buf, u32 depth_info, depth = (depth_info & ~TIPC_NTQ_ALLTYPES); if (depth == 0) - return; + return 0; if (all_types) { /* display all entries in name table to specified depth */ - nametbl_header(buf, depth); + ret += nametbl_header(buf, len, depth); lowbound = 0; upbound = ~0; for (i = 0; i < tipc_nametbl_size; i++) { seq_head = &table.types[i]; hlist_for_each_entry(seq, seq_node, seq_head, ns_list) { - nameseq_list(seq, buf, depth, seq->type, - lowbound, upbound, i); + ret += nameseq_list(seq, buf + ret, len - ret, + depth, seq->type, + lowbound, upbound, i); } } } else { /* display only the sequence that matches the specified type */ if (upbound < lowbound) { - tipc_printf(buf, "invalid name sequence specified\n"); - return; + ret += tipc_snprintf(buf + ret, len - ret, + "invalid name sequence specified\n"); + return ret; } - nametbl_header(buf, depth); + ret += nametbl_header(buf + ret, len - ret, depth); i = hash(type); seq_head = &table.types[i]; hlist_for_each_entry(seq, seq_node, seq_head, ns_list) { if (seq->type == type) { - nameseq_list(seq, buf, depth, type, - lowbound, upbound, i); + ret += nameseq_list(seq, buf + ret, len - ret, + depth, type, + lowbound, upbound, i); break; } } } + return ret; } -#define MAX_NAME_TBL_QUERY 32768 - struct sk_buff *tipc_nametbl_get(const void *req_tlv_area, int req_tlv_space) { struct sk_buff *buf; struct tipc_name_table_query *argv; struct tlv_desc *rep_tlv; - struct print_buf b; + char *pb; + int pb_len; int str_len; if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_NAME_TBL_QUERY)) return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); - buf = tipc_cfg_reply_alloc(TLV_SPACE(MAX_NAME_TBL_QUERY)); + buf = tipc_cfg_reply_alloc(TLV_SPACE(ULTRA_STRING_MAX_LEN)); if (!buf) return NULL; rep_tlv = (struct tlv_desc *)buf->data; - tipc_printbuf_init(&b, TLV_DATA(rep_tlv), MAX_NAME_TBL_QUERY); + pb = TLV_DATA(rep_tlv); + pb_len = ULTRA_STRING_MAX_LEN; argv = (struct tipc_name_table_query *)TLV_DATA(req_tlv_area); read_lock_bh(&tipc_nametbl_lock); - nametbl_list(&b, ntohl(argv->depth), ntohl(argv->type), - ntohl(argv->lowbound), ntohl(argv->upbound)); + str_len = nametbl_list(pb, pb_len, ntohl(argv->depth), + ntohl(argv->type), + ntohl(argv->lowbound), ntohl(argv->upbound)); read_unlock_bh(&tipc_nametbl_lock); - str_len = tipc_printbuf_validate(&b); - + str_len += 1; /* for "\0" */ skb_put(buf, TLV_SPACE(str_len)); TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); @@ -940,8 +954,10 @@ void tipc_nametbl_stop(void) /* Verify name table is empty, then release it */ write_lock_bh(&tipc_nametbl_lock); for (i = 0; i < tipc_nametbl_size; i++) { - if (!hlist_empty(&table.types[i])) - err("tipc_nametbl_stop(): hash chain %u is non-null\n", i); + if (hlist_empty(&table.types[i])) + continue; + pr_err("nametbl_stop(): orphaned hash chain detected\n"); + break; } kfree(table.types); table.types = NULL; diff --git a/net/tipc/net.c b/net/tipc/net.c index 7c236c89cf5..5b5cea259ca 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -184,9 +184,9 @@ int tipc_net_start(u32 addr) tipc_cfg_reinit(); - info("Started in network mode\n"); - info("Own node address %s, network identity %u\n", - tipc_addr_string_fill(addr_string, tipc_own_addr), tipc_net_id); + pr_info("Started in network mode\n"); + pr_info("Own node address %s, network identity %u\n", + tipc_addr_string_fill(addr_string, tipc_own_addr), tipc_net_id); return 0; } @@ -202,5 +202,5 @@ void tipc_net_stop(void) list_for_each_entry_safe(node, t_node, &tipc_node_list, list) tipc_node_delete(node); write_unlock_bh(&tipc_net_lock); - info("Left network mode\n"); + pr_info("Left network mode\n"); } diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 7bda8e3d139..47a839df27d 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -90,7 +90,7 @@ int tipc_netlink_start(void) res = genl_register_family_with_ops(&tipc_genl_family, &tipc_genl_ops, 1); if (res) { - err("Failed to register netlink interface\n"); + pr_err("Failed to register netlink interface\n"); return res; } diff --git a/net/tipc/node.c b/net/tipc/node.c index d4fd341e6e0..d21db204e25 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -105,7 +105,7 @@ struct tipc_node *tipc_node_create(u32 addr) n_ptr = kzalloc(sizeof(*n_ptr), GFP_ATOMIC); if (!n_ptr) { spin_unlock_bh(&node_create_lock); - warn("Node creation failed, no memory\n"); + pr_warn("Node creation failed, no memory\n"); return NULL; } @@ -151,8 +151,8 @@ void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr) n_ptr->working_links++; - info("Established link <%s> on network plane %c\n", - l_ptr->name, l_ptr->b_ptr->net_plane); + pr_info("Established link <%s> on network plane %c\n", + l_ptr->name, l_ptr->b_ptr->net_plane); if (!active[0]) { active[0] = active[1] = l_ptr; @@ -160,7 +160,7 @@ void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr) return; } if (l_ptr->priority < active[0]->priority) { - info("New link <%s> becomes standby\n", l_ptr->name); + pr_info("New link <%s> becomes standby\n", l_ptr->name); return; } tipc_link_send_duplicate(active[0], l_ptr); @@ -168,9 +168,9 @@ void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr) active[0] = l_ptr; return; } - info("Old link <%s> becomes standby\n", active[0]->name); + pr_info("Old link <%s> becomes standby\n", active[0]->name); if (active[1] != active[0]) - info("Old link <%s> becomes standby\n", active[1]->name); + pr_info("Old link <%s> becomes standby\n", active[1]->name); active[0] = active[1] = l_ptr; } @@ -211,11 +211,11 @@ void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr) n_ptr->working_links--; if (!tipc_link_is_active(l_ptr)) { - info("Lost standby link <%s> on network plane %c\n", - l_ptr->name, l_ptr->b_ptr->net_plane); + pr_info("Lost standby link <%s> on network plane %c\n", + l_ptr->name, l_ptr->b_ptr->net_plane); return; } - info("Lost link <%s> on network plane %c\n", + pr_info("Lost link <%s> on network plane %c\n", l_ptr->name, l_ptr->b_ptr->net_plane); active = &n_ptr->active_links[0]; @@ -290,8 +290,8 @@ static void node_lost_contact(struct tipc_node *n_ptr) char addr_string[16]; u32 i; - info("Lost contact with %s\n", - tipc_addr_string_fill(addr_string, n_ptr->addr)); + pr_info("Lost contact with %s\n", + tipc_addr_string_fill(addr_string, n_ptr->addr)); /* Flush broadcast link info associated with lost node */ if (n_ptr->bclink.supported) { diff --git a/net/tipc/node_subscr.c b/net/tipc/node_subscr.c index 7a27344108f..5e34b015da4 100644 --- a/net/tipc/node_subscr.c +++ b/net/tipc/node_subscr.c @@ -51,7 +51,8 @@ void tipc_nodesub_subscribe(struct tipc_node_subscr *node_sub, u32 addr, node_sub->node = tipc_node_find(addr); if (!node_sub->node) { - warn("Node subscription rejected, unknown node 0x%x\n", addr); + pr_warn("Node subscription rejected, unknown node 0x%x\n", + addr); return; } node_sub->handle_node_down = handle_down; diff --git a/net/tipc/port.c b/net/tipc/port.c index 2ad37a4db37..07c42fba672 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -69,7 +69,7 @@ static u32 port_peerport(struct tipc_port *p_ptr) return msg_destport(&p_ptr->phdr); } -/* +/** * tipc_port_peer_msg - verify message was sent by connected port's peer * * Handles cases where the node's network address has changed from @@ -191,7 +191,7 @@ void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp) struct sk_buff *b = skb_clone(buf, GFP_ATOMIC); if (b == NULL) { - warn("Unable to deliver multicast message(s)\n"); + pr_warn("Unable to deliver multicast message(s)\n"); goto exit; } if ((index == 0) && (cnt != 0)) @@ -221,12 +221,12 @@ struct tipc_port *tipc_createport_raw(void *usr_handle, p_ptr = kzalloc(sizeof(*p_ptr), GFP_ATOMIC); if (!p_ptr) { - warn("Port creation failed, no memory\n"); + pr_warn("Port creation failed, no memory\n"); return NULL; } ref = tipc_ref_acquire(p_ptr, &p_ptr->lock); if (!ref) { - warn("Port creation failed, reference table exhausted\n"); + pr_warn("Port creation failed, ref. table exhausted\n"); kfree(p_ptr); return NULL; } @@ -581,67 +581,73 @@ exit: kfree_skb(buf); } -static void port_print(struct tipc_port *p_ptr, struct print_buf *buf, int full_id) +static int port_print(struct tipc_port *p_ptr, char *buf, int len, int full_id) { struct publication *publ; + int ret; if (full_id) - tipc_printf(buf, "<%u.%u.%u:%u>:", - tipc_zone(tipc_own_addr), tipc_cluster(tipc_own_addr), - tipc_node(tipc_own_addr), p_ptr->ref); + ret = tipc_snprintf(buf, len, "<%u.%u.%u:%u>:", + tipc_zone(tipc_own_addr), + tipc_cluster(tipc_own_addr), + tipc_node(tipc_own_addr), p_ptr->ref); else - tipc_printf(buf, "%-10u:", p_ptr->ref); + ret = tipc_snprintf(buf, len, "%-10u:", p_ptr->ref); if (p_ptr->connected) { u32 dport = port_peerport(p_ptr); u32 destnode = port_peernode(p_ptr); - tipc_printf(buf, " connected to <%u.%u.%u:%u>", - tipc_zone(destnode), tipc_cluster(destnode), - tipc_node(destnode), dport); + ret += tipc_snprintf(buf + ret, len - ret, + " connected to <%u.%u.%u:%u>", + tipc_zone(destnode), + tipc_cluster(destnode), + tipc_node(destnode), dport); if (p_ptr->conn_type != 0) - tipc_printf(buf, " via {%u,%u}", - p_ptr->conn_type, - p_ptr->conn_instance); + ret += tipc_snprintf(buf + ret, len - ret, + " via {%u,%u}", p_ptr->conn_type, + p_ptr->conn_instance); } else if (p_ptr->published) { - tipc_printf(buf, " bound to"); + ret += tipc_snprintf(buf + ret, len - ret, " bound to"); list_for_each_entry(publ, &p_ptr->publications, pport_list) { if (publ->lower == publ->upper) - tipc_printf(buf, " {%u,%u}", publ->type, - publ->lower); + ret += tipc_snprintf(buf + ret, len - ret, + " {%u,%u}", publ->type, + publ->lower); else - tipc_printf(buf, " {%u,%u,%u}", publ->type, - publ->lower, publ->upper); + ret += tipc_snprintf(buf + ret, len - ret, + " {%u,%u,%u}", publ->type, + publ->lower, publ->upper); } } - tipc_printf(buf, "\n"); + ret += tipc_snprintf(buf + ret, len - ret, "\n"); + return ret; } -#define MAX_PORT_QUERY 32768 - struct sk_buff *tipc_port_get_ports(void) { struct sk_buff *buf; struct tlv_desc *rep_tlv; - struct print_buf pb; + char *pb; + int pb_len; struct tipc_port *p_ptr; - int str_len; + int str_len = 0; - buf = tipc_cfg_reply_alloc(TLV_SPACE(MAX_PORT_QUERY)); + buf = tipc_cfg_reply_alloc(TLV_SPACE(ULTRA_STRING_MAX_LEN)); if (!buf) return NULL; rep_tlv = (struct tlv_desc *)buf->data; + pb = TLV_DATA(rep_tlv); + pb_len = ULTRA_STRING_MAX_LEN; - tipc_printbuf_init(&pb, TLV_DATA(rep_tlv), MAX_PORT_QUERY); spin_lock_bh(&tipc_port_list_lock); list_for_each_entry(p_ptr, &ports, port_list) { spin_lock_bh(p_ptr->lock); - port_print(p_ptr, &pb, 0); + str_len += port_print(p_ptr, pb, pb_len, 0); spin_unlock_bh(p_ptr->lock); } spin_unlock_bh(&tipc_port_list_lock); - str_len = tipc_printbuf_validate(&pb); - + str_len += 1; /* for "\0" */ skb_put(buf, TLV_SPACE(str_len)); TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); @@ -906,11 +912,11 @@ int tipc_createport(void *usr_handle, up_ptr = kmalloc(sizeof(*up_ptr), GFP_ATOMIC); if (!up_ptr) { - warn("Port creation failed, no memory\n"); + pr_warn("Port creation failed, no memory\n"); return -ENOMEM; } - p_ptr = (struct tipc_port *)tipc_createport_raw(NULL, port_dispatcher, - port_wakeup, importance); + p_ptr = tipc_createport_raw(NULL, port_dispatcher, port_wakeup, + importance); if (!p_ptr) { kfree(up_ptr); return -ENOMEM; @@ -1078,8 +1084,7 @@ int tipc_disconnect_port(struct tipc_port *tp_ptr) if (tp_ptr->connected) { tp_ptr->connected = 0; /* let timer expire on it's own to avoid deadlock! */ - tipc_nodesub_unsubscribe( - &((struct tipc_port *)tp_ptr)->subscription); + tipc_nodesub_unsubscribe(&tp_ptr->subscription); res = 0; } else { res = -ENOTCONN; @@ -1099,7 +1104,7 @@ int tipc_disconnect(u32 ref) p_ptr = tipc_port_lock(ref); if (!p_ptr) return -EINVAL; - res = tipc_disconnect_port((struct tipc_port *)p_ptr); + res = tipc_disconnect_port(p_ptr); tipc_port_unlock(p_ptr); return res; } diff --git a/net/tipc/port.h b/net/tipc/port.h index 98cbec9c453..4660e306579 100644 --- a/net/tipc/port.h +++ b/net/tipc/port.h @@ -79,6 +79,7 @@ typedef void (*tipc_continue_event) (void *usr_handle, u32 portref); * struct user_port - TIPC user port (used with native API) * @usr_handle: user-specified field * @ref: object reference to associated TIPC port + * * <various callback routines> */ struct user_port { diff --git a/net/tipc/ref.c b/net/tipc/ref.c index 5cada0e38e0..2a2a938dc22 100644 --- a/net/tipc/ref.c +++ b/net/tipc/ref.c @@ -153,11 +153,11 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock) struct reference *entry = NULL; if (!object) { - err("Attempt to acquire reference to non-existent object\n"); + pr_err("Attempt to acquire ref. to non-existent obj\n"); return 0; } if (!tipc_ref_table.entries) { - err("Reference table not found during acquisition attempt\n"); + pr_err("Ref. table not found in acquisition attempt\n"); return 0; } @@ -211,7 +211,7 @@ void tipc_ref_discard(u32 ref) u32 index_mask; if (!tipc_ref_table.entries) { - err("Reference table not found during discard attempt\n"); + pr_err("Ref. table not found during discard attempt\n"); return; } @@ -222,11 +222,11 @@ void tipc_ref_discard(u32 ref) write_lock_bh(&ref_table_lock); if (!entry->object) { - err("Attempt to discard reference to non-existent object\n"); + pr_err("Attempt to discard ref. to non-existent obj\n"); goto exit; } if (entry->ref != ref) { - err("Attempt to discard non-existent reference\n"); + pr_err("Attempt to discard non-existent reference\n"); goto exit; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 5577a447f53..09dc5b97e07 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -34,12 +34,12 @@ * POSSIBILITY OF SUCH DAMAGE. */ -#include <linux/export.h> -#include <net/sock.h> - #include "core.h" #include "port.h" +#include <linux/export.h> +#include <net/sock.h> + #define SS_LISTENING -1 /* socket is listening */ #define SS_READY -2 /* socket is connectionless */ @@ -54,7 +54,7 @@ struct tipc_sock { }; #define tipc_sk(sk) ((struct tipc_sock *)(sk)) -#define tipc_sk_port(sk) ((struct tipc_port *)(tipc_sk(sk)->p)) +#define tipc_sk_port(sk) (tipc_sk(sk)->p) #define tipc_rx_ready(sock) (!skb_queue_empty(&sock->sk->sk_receive_queue) || \ (sock->state == SS_DISCONNECTING)) @@ -1699,9 +1699,8 @@ static int getsockopt(struct socket *sock, return put_user(sizeof(value), ol); } -/** - * Protocol switches for the various types of TIPC sockets - */ +/* Protocol switches for the various types of TIPC sockets */ + static const struct proto_ops msg_ops = { .owner = THIS_MODULE, .family = AF_TIPC, @@ -1788,13 +1787,13 @@ int tipc_socket_init(void) res = proto_register(&tipc_proto, 1); if (res) { - err("Failed to register TIPC protocol type\n"); + pr_err("Failed to register TIPC protocol type\n"); goto out; } res = sock_register(&tipc_family_ops); if (res) { - err("Failed to register TIPC socket type\n"); + pr_err("Failed to register TIPC socket type\n"); proto_unregister(&tipc_proto); goto out; } diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index f976e9cd6a7..5ed5965eb0b 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -305,8 +305,8 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, /* Refuse subscription if global limit exceeded */ if (atomic_read(&topsrv.subscription_count) >= tipc_max_subscriptions) { - warn("Subscription rejected, subscription limit reached (%u)\n", - tipc_max_subscriptions); + pr_warn("Subscription rejected, limit reached (%u)\n", + tipc_max_subscriptions); subscr_terminate(subscriber); return NULL; } @@ -314,7 +314,7 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, /* Allocate subscription object */ sub = kmalloc(sizeof(*sub), GFP_ATOMIC); if (!sub) { - warn("Subscription rejected, no memory\n"); + pr_warn("Subscription rejected, no memory\n"); subscr_terminate(subscriber); return NULL; } @@ -328,7 +328,7 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, if ((!(sub->filter & TIPC_SUB_PORTS) == !(sub->filter & TIPC_SUB_SERVICE)) || (sub->seq.lower > sub->seq.upper)) { - warn("Subscription rejected, illegal request\n"); + pr_warn("Subscription rejected, illegal request\n"); kfree(sub); subscr_terminate(subscriber); return NULL; @@ -440,7 +440,7 @@ static void subscr_named_msg_event(void *usr_handle, /* Create subscriber object */ subscriber = kzalloc(sizeof(struct tipc_subscriber), GFP_ATOMIC); if (subscriber == NULL) { - warn("Subscriber rejected, no memory\n"); + pr_warn("Subscriber rejected, no memory\n"); return; } INIT_LIST_HEAD(&subscriber->subscription_list); @@ -458,7 +458,7 @@ static void subscr_named_msg_event(void *usr_handle, NULL, &subscriber->port_ref); if (subscriber->port_ref == 0) { - warn("Subscriber rejected, unable to create port\n"); + pr_warn("Subscriber rejected, unable to create port\n"); kfree(subscriber); return; } @@ -517,7 +517,7 @@ int tipc_subscr_start(void) return 0; failed: - err("Failed to create subscription service\n"); + pr_err("Failed to create subscription service\n"); return res; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 641f2e47f16..c5ee4ff6136 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -115,15 +115,24 @@ #include <net/checksum.h> #include <linux/security.h> -struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1]; +struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE]; EXPORT_SYMBOL_GPL(unix_socket_table); DEFINE_SPINLOCK(unix_table_lock); EXPORT_SYMBOL_GPL(unix_table_lock); static atomic_long_t unix_nr_socks; -#define unix_sockets_unbound (&unix_socket_table[UNIX_HASH_SIZE]) -#define UNIX_ABSTRACT(sk) (unix_sk(sk)->addr->hash != UNIX_HASH_SIZE) +static struct hlist_head *unix_sockets_unbound(void *addr) +{ + unsigned long hash = (unsigned long)addr; + + hash ^= hash >> 16; + hash ^= hash >> 8; + hash %= UNIX_HASH_SIZE; + return &unix_socket_table[UNIX_HASH_SIZE + hash]; +} + +#define UNIX_ABSTRACT(sk) (unix_sk(sk)->addr->hash < UNIX_HASH_SIZE) #ifdef CONFIG_SECURITY_NETWORK static void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb) @@ -645,7 +654,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock) INIT_LIST_HEAD(&u->link); mutex_init(&u->readlock); /* single task reading lock */ init_waitqueue_head(&u->peer_wait); - unix_insert_socket(unix_sockets_unbound, sk); + unix_insert_socket(unix_sockets_unbound(sk), sk); out: if (sk == NULL) atomic_long_dec(&unix_nr_socks); @@ -814,6 +823,34 @@ fail: return NULL; } +static int unix_mknod(const char *sun_path, umode_t mode, struct path *res) +{ + struct dentry *dentry; + struct path path; + int err = 0; + /* + * Get the parent directory, calculate the hash for last + * component. + */ + dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); + err = PTR_ERR(dentry); + if (IS_ERR(dentry)) + return err; + + /* + * All right, let's create it. + */ + err = security_path_mknod(&path, dentry, mode, 0); + if (!err) { + err = vfs_mknod(path.dentry->d_inode, dentry, mode, 0); + if (!err) { + res->mnt = mntget(path.mnt); + res->dentry = dget(dentry); + } + } + done_path_create(&path, dentry); + return err; +} static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { @@ -822,8 +859,6 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct unix_sock *u = unix_sk(sk); struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; char *sun_path = sunaddr->sun_path; - struct dentry *dentry = NULL; - struct path path; int err; unsigned int hash; struct unix_address *addr; @@ -860,43 +895,23 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) atomic_set(&addr->refcnt, 1); if (sun_path[0]) { - umode_t mode; - err = 0; - /* - * Get the parent directory, calculate the hash for last - * component. - */ - dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); - err = PTR_ERR(dentry); - if (IS_ERR(dentry)) - goto out_mknod_parent; - - /* - * All right, let's create it. - */ - mode = S_IFSOCK | + struct path path; + umode_t mode = S_IFSOCK | (SOCK_INODE(sock)->i_mode & ~current_umask()); - err = mnt_want_write(path.mnt); - if (err) - goto out_mknod_dput; - err = security_path_mknod(&path, dentry, mode, 0); - if (err) - goto out_mknod_drop_write; - err = vfs_mknod(path.dentry->d_inode, dentry, mode, 0); -out_mknod_drop_write: - mnt_drop_write(path.mnt); - if (err) - goto out_mknod_dput; - mutex_unlock(&path.dentry->d_inode->i_mutex); - dput(path.dentry); - path.dentry = dentry; - + err = unix_mknod(sun_path, mode, &path); + if (err) { + if (err == -EEXIST) + err = -EADDRINUSE; + unix_release_addr(addr); + goto out_up; + } addr->hash = UNIX_HASH_SIZE; - } - - spin_lock(&unix_table_lock); - - if (!sun_path[0]) { + hash = path.dentry->d_inode->i_ino & (UNIX_HASH_SIZE-1); + spin_lock(&unix_table_lock); + u->path = path; + list = &unix_socket_table[hash]; + } else { + spin_lock(&unix_table_lock); err = -EADDRINUSE; if (__unix_find_socket_byname(net, sunaddr, addr_len, sk->sk_type, hash)) { @@ -905,9 +920,6 @@ out_mknod_drop_write: } list = &unix_socket_table[addr->hash]; - } else { - list = &unix_socket_table[dentry->d_inode->i_ino & (UNIX_HASH_SIZE-1)]; - u->path = path; } err = 0; @@ -921,16 +933,6 @@ out_up: mutex_unlock(&u->readlock); out: return err; - -out_mknod_dput: - dput(dentry); - mutex_unlock(&path.dentry->d_inode->i_mutex); - path_put(&path); -out_mknod_parent: - if (err == -EEXIST) - err = -EADDRINUSE; - unix_release_addr(addr); - goto out_up; } static void unix_state_double_lock(struct sock *sk1, struct sock *sk2) @@ -1448,7 +1450,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, if (NULL == siocb->scm) siocb->scm = &tmp_scm; wait_for_unix_gc(); - err = scm_send(sock, msg, siocb->scm); + err = scm_send(sock, msg, siocb->scm, false); if (err < 0) return err; @@ -1617,7 +1619,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, if (NULL == siocb->scm) siocb->scm = &tmp_scm; wait_for_unix_gc(); - err = scm_send(sock, msg, siocb->scm); + err = scm_send(sock, msg, siocb->scm, false); if (err < 0) return err; @@ -2239,47 +2241,54 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, } #ifdef CONFIG_PROC_FS -static struct sock *first_unix_socket(int *i) + +#define BUCKET_SPACE (BITS_PER_LONG - (UNIX_HASH_BITS + 1) - 1) + +#define get_bucket(x) ((x) >> BUCKET_SPACE) +#define get_offset(x) ((x) & ((1L << BUCKET_SPACE) - 1)) +#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o)) + +static struct sock *unix_from_bucket(struct seq_file *seq, loff_t *pos) { - for (*i = 0; *i <= UNIX_HASH_SIZE; (*i)++) { - if (!hlist_empty(&unix_socket_table[*i])) - return __sk_head(&unix_socket_table[*i]); + unsigned long offset = get_offset(*pos); + unsigned long bucket = get_bucket(*pos); + struct sock *sk; + unsigned long count = 0; + + for (sk = sk_head(&unix_socket_table[bucket]); sk; sk = sk_next(sk)) { + if (sock_net(sk) != seq_file_net(seq)) + continue; + if (++count == offset) + break; } - return NULL; + + return sk; } -static struct sock *next_unix_socket(int *i, struct sock *s) +static struct sock *unix_next_socket(struct seq_file *seq, + struct sock *sk, + loff_t *pos) { - struct sock *next = sk_next(s); - /* More in this chain? */ - if (next) - return next; - /* Look for next non-empty chain. */ - for ((*i)++; *i <= UNIX_HASH_SIZE; (*i)++) { - if (!hlist_empty(&unix_socket_table[*i])) - return __sk_head(&unix_socket_table[*i]); + unsigned long bucket; + + while (sk > (struct sock *)SEQ_START_TOKEN) { + sk = sk_next(sk); + if (!sk) + goto next_bucket; + if (sock_net(sk) == seq_file_net(seq)) + return sk; } - return NULL; -} -struct unix_iter_state { - struct seq_net_private p; - int i; -}; + do { + sk = unix_from_bucket(seq, pos); + if (sk) + return sk; -static struct sock *unix_seq_idx(struct seq_file *seq, loff_t pos) -{ - struct unix_iter_state *iter = seq->private; - loff_t off = 0; - struct sock *s; +next_bucket: + bucket = get_bucket(*pos) + 1; + *pos = set_bucket_offset(bucket, 1); + } while (bucket < ARRAY_SIZE(unix_socket_table)); - for (s = first_unix_socket(&iter->i); s; s = next_unix_socket(&iter->i, s)) { - if (sock_net(s) != seq_file_net(seq)) - continue; - if (off == pos) - return s; - ++off; - } return NULL; } @@ -2287,22 +2296,20 @@ static void *unix_seq_start(struct seq_file *seq, loff_t *pos) __acquires(unix_table_lock) { spin_lock(&unix_table_lock); - return *pos ? unix_seq_idx(seq, *pos - 1) : SEQ_START_TOKEN; + + if (!*pos) + return SEQ_START_TOKEN; + + if (get_bucket(*pos) >= ARRAY_SIZE(unix_socket_table)) + return NULL; + + return unix_next_socket(seq, NULL, pos); } static void *unix_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct unix_iter_state *iter = seq->private; - struct sock *sk = v; ++*pos; - - if (v == SEQ_START_TOKEN) - sk = first_unix_socket(&iter->i); - else - sk = next_unix_socket(&iter->i, sk); - while (sk && (sock_net(sk) != seq_file_net(seq))) - sk = next_unix_socket(&iter->i, sk); - return sk; + return unix_next_socket(seq, v, pos); } static void unix_seq_stop(struct seq_file *seq, void *v) @@ -2365,7 +2372,7 @@ static const struct seq_operations unix_seq_ops = { static int unix_seq_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &unix_seq_ops, - sizeof(struct unix_iter_state)); + sizeof(struct seq_net_private)); } static const struct file_operations unix_seq_fops = { diff --git a/net/unix/diag.c b/net/unix/diag.c index 47d3002737f..750b1340844 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -8,40 +8,31 @@ #include <net/af_unix.h> #include <net/tcp_states.h> -#define UNIX_DIAG_PUT(skb, attrtype, attrlen) \ - RTA_DATA(__RTA_PUT(skb, attrtype, attrlen)) - static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb) { struct unix_address *addr = unix_sk(sk)->addr; - char *s; - - if (addr) { - s = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_NAME, addr->len - sizeof(short)); - memcpy(s, addr->name->sun_path, addr->len - sizeof(short)); - } - return 0; + if (!addr) + return 0; -rtattr_failure: - return -EMSGSIZE; + return nla_put(nlskb, UNIX_DIAG_NAME, addr->len - sizeof(short), + addr->name->sun_path); } static int sk_diag_dump_vfs(struct sock *sk, struct sk_buff *nlskb) { struct dentry *dentry = unix_sk(sk)->path.dentry; - struct unix_diag_vfs *uv; if (dentry) { - uv = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_VFS, sizeof(*uv)); - uv->udiag_vfs_ino = dentry->d_inode->i_ino; - uv->udiag_vfs_dev = dentry->d_sb->s_dev; + struct unix_diag_vfs uv = { + .udiag_vfs_ino = dentry->d_inode->i_ino, + .udiag_vfs_dev = dentry->d_sb->s_dev, + }; + + return nla_put(nlskb, UNIX_DIAG_VFS, sizeof(uv), &uv); } return 0; - -rtattr_failure: - return -EMSGSIZE; } static int sk_diag_dump_peer(struct sock *sk, struct sk_buff *nlskb) @@ -56,24 +47,28 @@ static int sk_diag_dump_peer(struct sock *sk, struct sk_buff *nlskb) unix_state_unlock(peer); sock_put(peer); - RTA_PUT_U32(nlskb, UNIX_DIAG_PEER, ino); + return nla_put_u32(nlskb, UNIX_DIAG_PEER, ino); } return 0; -rtattr_failure: - return -EMSGSIZE; } static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb) { struct sk_buff *skb; + struct nlattr *attr; u32 *buf; int i; if (sk->sk_state == TCP_LISTEN) { spin_lock(&sk->sk_receive_queue.lock); - buf = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_ICONS, - sk->sk_receive_queue.qlen * sizeof(u32)); + + attr = nla_reserve(nlskb, UNIX_DIAG_ICONS, + sk->sk_receive_queue.qlen * sizeof(u32)); + if (!attr) + goto errout; + + buf = nla_data(attr); i = 0; skb_queue_walk(&sk->sk_receive_queue, skb) { struct sock *req, *peer; @@ -94,43 +89,38 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb) return 0; -rtattr_failure: +errout: spin_unlock(&sk->sk_receive_queue.lock); return -EMSGSIZE; } static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb) { - struct unix_diag_rqlen *rql; - - rql = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_RQLEN, sizeof(*rql)); + struct unix_diag_rqlen rql; if (sk->sk_state == TCP_LISTEN) { - rql->udiag_rqueue = sk->sk_receive_queue.qlen; - rql->udiag_wqueue = sk->sk_max_ack_backlog; + rql.udiag_rqueue = sk->sk_receive_queue.qlen; + rql.udiag_wqueue = sk->sk_max_ack_backlog; } else { - rql->udiag_rqueue = (__u32)unix_inq_len(sk); - rql->udiag_wqueue = (__u32)unix_outq_len(sk); + rql.udiag_rqueue = (u32) unix_inq_len(sk); + rql.udiag_wqueue = (u32) unix_outq_len(sk); } - return 0; - -rtattr_failure: - return -EMSGSIZE; + return nla_put(nlskb, UNIX_DIAG_RQLEN, sizeof(rql), &rql); } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, u32 pid, u32 seq, u32 flags, int sk_ino) { - unsigned char *b = skb_tail_pointer(skb); struct nlmsghdr *nlh; struct unix_diag_msg *rep; - nlh = NLMSG_PUT(skb, pid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep)); - nlh->nlmsg_flags = flags; - - rep = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep), + flags); + if (!nlh) + return -EMSGSIZE; + rep = nlmsg_data(nlh); rep->udiag_family = AF_UNIX; rep->udiag_type = sk->sk_type; rep->udiag_state = sk->sk_state; @@ -139,33 +129,32 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r if ((req->udiag_show & UDIAG_SHOW_NAME) && sk_diag_dump_name(sk, skb)) - goto nlmsg_failure; + goto out_nlmsg_trim; if ((req->udiag_show & UDIAG_SHOW_VFS) && sk_diag_dump_vfs(sk, skb)) - goto nlmsg_failure; + goto out_nlmsg_trim; if ((req->udiag_show & UDIAG_SHOW_PEER) && sk_diag_dump_peer(sk, skb)) - goto nlmsg_failure; + goto out_nlmsg_trim; if ((req->udiag_show & UDIAG_SHOW_ICONS) && sk_diag_dump_icons(sk, skb)) - goto nlmsg_failure; + goto out_nlmsg_trim; if ((req->udiag_show & UDIAG_SHOW_RQLEN) && sk_diag_show_rqlen(sk, skb)) - goto nlmsg_failure; + goto out_nlmsg_trim; if ((req->udiag_show & UDIAG_SHOW_MEMINFO) && sock_diag_put_meminfo(sk, skb, UNIX_DIAG_MEMINFO)) - goto nlmsg_failure; + goto out_nlmsg_trim; - nlh->nlmsg_len = skb_tail_pointer(skb) - b; - return skb->len; + return nlmsg_end(skb, nlh); -nlmsg_failure: - nlmsg_trim(skb, b); +out_nlmsg_trim: + nlmsg_cancel(skb, nlh); return -EMSGSIZE; } @@ -188,19 +177,24 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct unix_diag_req *req; int num, s_num, slot, s_slot; + struct net *net = sock_net(skb->sk); - req = NLMSG_DATA(cb->nlh); + req = nlmsg_data(cb->nlh); s_slot = cb->args[0]; num = s_num = cb->args[1]; spin_lock(&unix_table_lock); - for (slot = s_slot; slot <= UNIX_HASH_SIZE; s_num = 0, slot++) { + for (slot = s_slot; + slot < ARRAY_SIZE(unix_socket_table); + s_num = 0, slot++) { struct sock *sk; struct hlist_node *node; num = 0; sk_for_each(sk, node, &unix_socket_table[slot]) { + if (!net_eq(sock_net(sk), net)) + continue; if (num < s_num) goto next; if (!(req->udiag_states & (1 << sk->sk_state))) @@ -228,7 +222,7 @@ static struct sock *unix_lookup_by_ino(int ino) struct sock *sk; spin_lock(&unix_table_lock); - for (i = 0; i <= UNIX_HASH_SIZE; i++) { + for (i = 0; i < ARRAY_SIZE(unix_socket_table); i++) { struct hlist_node *node; sk_for_each(sk, node, &unix_socket_table[i]) @@ -252,6 +246,7 @@ static int unix_diag_get_exact(struct sk_buff *in_skb, struct sock *sk; struct sk_buff *rep; unsigned int extra_len; + struct net *net = sock_net(in_skb->sk); if (req->udiag_ino == 0) goto out_nosk; @@ -268,22 +263,21 @@ static int unix_diag_get_exact(struct sk_buff *in_skb, extra_len = 256; again: err = -ENOMEM; - rep = alloc_skb(NLMSG_SPACE((sizeof(struct unix_diag_msg) + extra_len)), - GFP_KERNEL); + rep = nlmsg_new(sizeof(struct unix_diag_msg) + extra_len, GFP_KERNEL); if (!rep) goto out; err = sk_diag_fill(sk, rep, req, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, 0, req->udiag_ino); if (err < 0) { - kfree_skb(rep); + nlmsg_free(rep); extra_len += 256; if (extra_len >= PAGE_SIZE) goto out; goto again; } - err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid, + err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); if (err > 0) err = 0; @@ -297,6 +291,7 @@ out_nosk: static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) { int hdrlen = sizeof(struct unix_diag_req); + struct net *net = sock_net(skb->sk); if (nlmsg_len(h) < hdrlen) return -EINVAL; @@ -305,9 +300,9 @@ static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) struct netlink_dump_control c = { .dump = unix_diag_dump, }; - return netlink_dump_start(sock_diag_nlsk, skb, h, &c); + return netlink_dump_start(net->diag_nlsk, skb, h, &c); } else - return unix_diag_get_exact(skb, h, (struct unix_diag_req *)NLMSG_DATA(h)); + return unix_diag_get_exact(skb, h, nlmsg_data(h)); } static const struct sock_diag_handler unix_diag_handler = { diff --git a/net/wanrouter/wanmain.c b/net/wanrouter/wanmain.c index 788a12c1eb5..2ab785064b7 100644 --- a/net/wanrouter/wanmain.c +++ b/net/wanrouter/wanmain.c @@ -602,36 +602,31 @@ static int wanrouter_device_new_if(struct wan_device *wandev, * successfully, add it to the interface list. */ - if (dev->name == NULL) { - err = -EINVAL; - } else { +#ifdef WANDEBUG + printk(KERN_INFO "%s: registering interface %s...\n", + wanrouter_modname, dev->name); +#endif - #ifdef WANDEBUG - printk(KERN_INFO "%s: registering interface %s...\n", - wanrouter_modname, dev->name); - #endif - - err = register_netdev(dev); - if (!err) { - struct net_device *slave = NULL; - unsigned long smp_flags=0; - - lock_adapter_irq(&wandev->lock, &smp_flags); - - if (wandev->dev == NULL) { - wandev->dev = dev; - } else { - for (slave=wandev->dev; - DEV_TO_SLAVE(slave); - slave = DEV_TO_SLAVE(slave)) - DEV_TO_SLAVE(slave) = dev; - } - ++wandev->ndev; - - unlock_adapter_irq(&wandev->lock, &smp_flags); - err = 0; /* done !!! */ - goto out; + err = register_netdev(dev); + if (!err) { + struct net_device *slave = NULL; + unsigned long smp_flags=0; + + lock_adapter_irq(&wandev->lock, &smp_flags); + + if (wandev->dev == NULL) { + wandev->dev = dev; + } else { + for (slave=wandev->dev; + DEV_TO_SLAVE(slave); + slave = DEV_TO_SLAVE(slave)) + DEV_TO_SLAVE(slave) = dev; } + ++wandev->ndev; + + unlock_adapter_irq(&wandev->lock, &smp_flags); + err = 0; /* done !!! */ + goto out; } if (wandev->del_if) wandev->del_if(wandev, dev); diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 2e4444fedbe..fe4adb12b3e 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -74,6 +74,27 @@ config CFG80211_REG_DEBUG If unsure, say N. +config CFG80211_CERTIFICATION_ONUS + bool "cfg80211 certification onus" + depends on CFG80211 && EXPERT + default n + ---help--- + You should disable this option unless you are both capable + and willing to ensure your system will remain regulatory + compliant with the features available under this option. + Some options may still be under heavy development and + for whatever reason regulatory compliance has not or + cannot yet be verified. Regulatory verification may at + times only be possible until you have the final system + in place. + + This option should only be enabled by system integrators + or distributions that have done work necessary to ensure + regulatory certification on the system with the enabled + features. Alternatively you can enable this option if + you are a wireless researcher and are working in a controlled + and approved environment by your local regulatory agency. + config CFG80211_DEFAULT_PS bool "enable powersave by default" depends on CFG80211 @@ -114,24 +135,10 @@ config CFG80211_WEXT bool "cfg80211 wireless extensions compatibility" depends on CFG80211 select WEXT_CORE - default y help Enable this option if you need old userspace for wireless extensions with cfg80211-based drivers. -config WIRELESS_EXT_SYSFS - bool "Wireless extensions sysfs files" - depends on WEXT_CORE && SYSFS - help - This option enables the deprecated wireless statistics - files in /sys/class/net/*/wireless/. The same information - is available via the ioctls as well. - - Say N. If you know you have ancient tools requiring it, - like very old versions of hal (prior to 0.5.12 release), - say Y and update the tools as soon as possible as this - option will be removed soon. - config LIB80211 tristate "Common routines for IEEE802.11 drivers" default n diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 55a28ab21db..0f7e0d621ab 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_WEXT_SPY) += wext-spy.o obj-$(CONFIG_WEXT_PRIV) += wext-priv.o cfg80211-y += core.o sysfs.o radiotap.o util.o reg.o scan.o nl80211.o -cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o mesh.o +cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o mesh.o ap.o cfg80211-$(CONFIG_CFG80211_DEBUGFS) += debugfs.o cfg80211-$(CONFIG_CFG80211_WEXT) += wext-compat.o wext-sme.o cfg80211-$(CONFIG_CFG80211_INTERNAL_REGDB) += regdb.o diff --git a/net/wireless/ap.c b/net/wireless/ap.c new file mode 100644 index 00000000000..fcc60d8dbef --- /dev/null +++ b/net/wireless/ap.c @@ -0,0 +1,46 @@ +#include <linux/ieee80211.h> +#include <linux/export.h> +#include <net/cfg80211.h> +#include "nl80211.h" +#include "core.h" + + +static int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, + struct net_device *dev) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + int err; + + ASSERT_WDEV_LOCK(wdev); + + if (!rdev->ops->stop_ap) + return -EOPNOTSUPP; + + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + return -EOPNOTSUPP; + + if (!wdev->beacon_interval) + return -ENOENT; + + err = rdev->ops->stop_ap(&rdev->wiphy, dev); + if (!err) { + wdev->beacon_interval = 0; + wdev->channel = NULL; + } + + return err; +} + +int cfg80211_stop_ap(struct cfg80211_registered_device *rdev, + struct net_device *dev) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + int err; + + wdev_lock(wdev); + err = __cfg80211_stop_ap(rdev, dev); + wdev_unlock(wdev); + + return err; +} diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 884801ac4dd..d355f67d0cd 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -60,7 +60,7 @@ bool cfg80211_can_beacon_sec_chan(struct wiphy *wiphy, diff = -20; break; default: - return false; + return true; } sec_chan = ieee80211_get_channel(wiphy, chan->center_freq + diff); @@ -78,60 +78,75 @@ bool cfg80211_can_beacon_sec_chan(struct wiphy *wiphy, } EXPORT_SYMBOL(cfg80211_can_beacon_sec_chan); -int cfg80211_set_freq(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev, int freq, - enum nl80211_channel_type channel_type) +int cfg80211_set_monitor_channel(struct cfg80211_registered_device *rdev, + int freq, enum nl80211_channel_type chantype) { struct ieee80211_channel *chan; - int result; - - if (wdev && wdev->iftype == NL80211_IFTYPE_MONITOR) - wdev = NULL; - if (wdev) { - ASSERT_WDEV_LOCK(wdev); - - if (!netif_running(wdev->netdev)) - return -ENETDOWN; - } - - if (!rdev->ops->set_channel) + if (!rdev->ops->set_monitor_channel) return -EOPNOTSUPP; + if (!cfg80211_has_monitors_only(rdev)) + return -EBUSY; - chan = rdev_freq_to_chan(rdev, freq, channel_type); + chan = rdev_freq_to_chan(rdev, freq, chantype); if (!chan) return -EINVAL; - /* Both channels should be able to initiate communication */ - if (wdev && (wdev->iftype == NL80211_IFTYPE_ADHOC || - wdev->iftype == NL80211_IFTYPE_AP || - wdev->iftype == NL80211_IFTYPE_AP_VLAN || - wdev->iftype == NL80211_IFTYPE_MESH_POINT || - wdev->iftype == NL80211_IFTYPE_P2P_GO)) { - switch (channel_type) { - case NL80211_CHAN_HT40PLUS: - case NL80211_CHAN_HT40MINUS: - if (!cfg80211_can_beacon_sec_chan(&rdev->wiphy, chan, - channel_type)) { - printk(KERN_DEBUG - "cfg80211: Secondary channel not " - "allowed to initiate communication\n"); - return -EINVAL; - } - break; - default: - break; + return rdev->ops->set_monitor_channel(&rdev->wiphy, chan, chantype); +} + +void +cfg80211_get_chan_state(struct wireless_dev *wdev, + struct ieee80211_channel **chan, + enum cfg80211_chan_mode *chanmode) +{ + *chan = NULL; + *chanmode = CHAN_MODE_UNDEFINED; + + ASSERT_WDEV_LOCK(wdev); + + if (!netif_running(wdev->netdev)) + return; + + switch (wdev->iftype) { + case NL80211_IFTYPE_ADHOC: + if (wdev->current_bss) { + *chan = wdev->current_bss->pub.channel; + *chanmode = wdev->ibss_fixed + ? CHAN_MODE_SHARED + : CHAN_MODE_EXCLUSIVE; + return; + } + case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_P2P_CLIENT: + if (wdev->current_bss) { + *chan = wdev->current_bss->pub.channel; + *chanmode = CHAN_MODE_SHARED; + return; + } + break; + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: + if (wdev->beacon_interval) { + *chan = wdev->channel; + *chanmode = CHAN_MODE_SHARED; } + return; + case NL80211_IFTYPE_MESH_POINT: + if (wdev->mesh_id_len) { + *chan = wdev->channel; + *chanmode = CHAN_MODE_SHARED; + } + return; + case NL80211_IFTYPE_MONITOR: + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_WDS: + /* these interface types don't really have a channel */ + return; + case NL80211_IFTYPE_UNSPECIFIED: + case NUM_NL80211_IFTYPES: + WARN_ON(1); } - result = rdev->ops->set_channel(&rdev->wiphy, - wdev ? wdev->netdev : NULL, - chan, channel_type); - if (result) - return result; - - if (wdev) - wdev->channel = chan; - - return 0; + return; } diff --git a/net/wireless/core.c b/net/wireless/core.c index a87d4355297..dcd64d5b07a 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -96,69 +96,6 @@ struct wiphy *wiphy_idx_to_wiphy(int wiphy_idx) return &rdev->wiphy; } -/* requires cfg80211_mutex to be held! */ -struct cfg80211_registered_device * -__cfg80211_rdev_from_info(struct genl_info *info) -{ - int ifindex; - struct cfg80211_registered_device *bywiphyidx = NULL, *byifidx = NULL; - struct net_device *dev; - int err = -EINVAL; - - assert_cfg80211_lock(); - - if (info->attrs[NL80211_ATTR_WIPHY]) { - bywiphyidx = cfg80211_rdev_by_wiphy_idx( - nla_get_u32(info->attrs[NL80211_ATTR_WIPHY])); - err = -ENODEV; - } - - if (info->attrs[NL80211_ATTR_IFINDEX]) { - ifindex = nla_get_u32(info->attrs[NL80211_ATTR_IFINDEX]); - dev = dev_get_by_index(genl_info_net(info), ifindex); - if (dev) { - if (dev->ieee80211_ptr) - byifidx = - wiphy_to_dev(dev->ieee80211_ptr->wiphy); - dev_put(dev); - } - err = -ENODEV; - } - - if (bywiphyidx && byifidx) { - if (bywiphyidx != byifidx) - return ERR_PTR(-EINVAL); - else - return bywiphyidx; /* == byifidx */ - } - if (bywiphyidx) - return bywiphyidx; - - if (byifidx) - return byifidx; - - return ERR_PTR(err); -} - -struct cfg80211_registered_device * -cfg80211_get_dev_from_info(struct genl_info *info) -{ - struct cfg80211_registered_device *rdev; - - mutex_lock(&cfg80211_mutex); - rdev = __cfg80211_rdev_from_info(info); - - /* if it is not an error we grab the lock on - * it to assure it won't be going away while - * we operate on it */ - if (!IS_ERR(rdev)) - mutex_lock(&rdev->mtx); - - mutex_unlock(&cfg80211_mutex); - - return rdev; -} - struct cfg80211_registered_device * cfg80211_get_dev_from_ifindex(struct net *net, int ifindex) { @@ -239,7 +176,9 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev, if (!(rdev->wiphy.flags & WIPHY_FLAG_NETNS_OK)) return -EOPNOTSUPP; - list_for_each_entry(wdev, &rdev->netdev_list, list) { + list_for_each_entry(wdev, &rdev->wdev_list, list) { + if (!wdev->netdev) + continue; wdev->netdev->features &= ~NETIF_F_NETNS_LOCAL; err = dev_change_net_namespace(wdev->netdev, net, "wlan%d"); if (err) @@ -251,8 +190,10 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev, /* failed -- clean up to old netns */ net = wiphy_net(&rdev->wiphy); - list_for_each_entry_continue_reverse(wdev, &rdev->netdev_list, + list_for_each_entry_continue_reverse(wdev, &rdev->wdev_list, list) { + if (!wdev->netdev) + continue; wdev->netdev->features &= ~NETIF_F_NETNS_LOCAL; err = dev_change_net_namespace(wdev->netdev, net, "wlan%d"); @@ -289,8 +230,9 @@ static int cfg80211_rfkill_set_block(void *data, bool blocked) rtnl_lock(); mutex_lock(&rdev->devlist_mtx); - list_for_each_entry(wdev, &rdev->netdev_list, list) - dev_close(wdev->netdev); + list_for_each_entry(wdev, &rdev->wdev_list, list) + if (wdev->netdev) + dev_close(wdev->netdev); mutex_unlock(&rdev->devlist_mtx); rtnl_unlock(); @@ -367,7 +309,7 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) mutex_init(&rdev->mtx); mutex_init(&rdev->devlist_mtx); mutex_init(&rdev->sched_scan_mtx); - INIT_LIST_HEAD(&rdev->netdev_list); + INIT_LIST_HEAD(&rdev->wdev_list); spin_lock_init(&rdev->bss_lock); INIT_LIST_HEAD(&rdev->bss_list); INIT_WORK(&rdev->scan_done_wk, __cfg80211_scan_done); @@ -436,6 +378,14 @@ static int wiphy_verify_combinations(struct wiphy *wiphy) if (WARN_ON(!c->num_different_channels)) return -EINVAL; + /* + * Put a sane limit on maximum number of different + * channels to simplify channel accounting code. + */ + if (WARN_ON(c->num_different_channels > + CFG80211_MAX_NUM_DIFFERENT_CHANNELS)) + return -EINVAL; + if (WARN_ON(!c->n_limits)) return -EINVAL; @@ -484,9 +434,11 @@ int wiphy_register(struct wiphy *wiphy) int i; u16 ifmodes = wiphy->interface_modes; +#ifdef CONFIG_PM if (WARN_ON((wiphy->wowlan.flags & WIPHY_WOWLAN_GTK_REKEY_FAILURE) && !(wiphy->wowlan.flags & WIPHY_WOWLAN_SUPPORTS_GTK_REKEY))) return -EINVAL; +#endif if (WARN_ON(wiphy->ap_sme_capa && !(wiphy->flags & WIPHY_FLAG_HAVE_AP_SME))) @@ -521,8 +473,14 @@ int wiphy_register(struct wiphy *wiphy) continue; sband->band = band; - - if (WARN_ON(!sband->n_channels || !sband->n_bitrates)) + if (WARN_ON(!sband->n_channels)) + return -EINVAL; + /* + * on 60gHz band, there are no legacy rates, so + * n_bitrates is 0 + */ + if (WARN_ON(band != IEEE80211_BAND_60GHZ && + !sband->n_bitrates)) return -EINVAL; /* @@ -563,12 +521,14 @@ int wiphy_register(struct wiphy *wiphy) return -EINVAL; } +#ifdef CONFIG_PM if (rdev->wiphy.wowlan.n_patterns) { if (WARN_ON(!rdev->wiphy.wowlan.pattern_min_len || rdev->wiphy.wowlan.pattern_min_len > rdev->wiphy.wowlan.pattern_max_len)) return -EINVAL; } +#endif /* check and set up bitrates */ ieee80211_set_bitrate_flags(wiphy); @@ -582,7 +542,7 @@ int wiphy_register(struct wiphy *wiphy) } /* set up regulatory info */ - regulatory_update(wiphy, NL80211_REGDOM_SET_BY_CORE); + wiphy_regulatory_register(wiphy); list_add_rcu(&rdev->list, &cfg80211_rdev_list); cfg80211_rdev_list_generation++; @@ -667,7 +627,7 @@ void wiphy_unregister(struct wiphy *wiphy) __count == 0; })); mutex_lock(&rdev->devlist_mtx); - BUG_ON(!list_empty(&rdev->netdev_list)); + BUG_ON(!list_empty(&rdev->wdev_list)); mutex_unlock(&rdev->devlist_mtx); /* @@ -692,9 +652,11 @@ void wiphy_unregister(struct wiphy *wiphy) /* nothing */ cfg80211_unlock_rdev(rdev); - /* If this device got a regulatory hint tell core its - * free to listen now to a new shiny device regulatory hint */ - reg_device_remove(wiphy); + /* + * If this device got a regulatory hint tell core its + * free to listen now to a new shiny device regulatory hint + */ + wiphy_regulatory_deregister(wiphy); cfg80211_rdev_list_generation++; device_del(&rdev->wiphy.dev); @@ -748,7 +710,7 @@ static void wdev_cleanup_work(struct work_struct *work) cfg80211_lock_rdev(rdev); - if (WARN_ON(rdev->scan_req && rdev->scan_req->dev == wdev->netdev)) { + if (WARN_ON(rdev->scan_req && rdev->scan_req->wdev == wdev)) { rdev->scan_req->aborted = true; ___cfg80211_scan_done(rdev, true); } @@ -776,6 +738,16 @@ static struct device_type wiphy_type = { .name = "wlan", }; +void cfg80211_update_iface_num(struct cfg80211_registered_device *rdev, + enum nl80211_iftype iftype, int num) +{ + ASSERT_RTNL(); + + rdev->num_running_ifaces += num; + if (iftype == NL80211_IFTYPE_MONITOR) + rdev->num_running_monitor_ifaces += num; +} + static int cfg80211_netdev_notifier_call(struct notifier_block *nb, unsigned long state, void *ndev) @@ -810,7 +782,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, spin_lock_init(&wdev->mgmt_registrations_lock); mutex_lock(&rdev->devlist_mtx); - list_add_rcu(&wdev->list, &rdev->netdev_list); + wdev->identifier = ++rdev->wdev_id; + list_add_rcu(&wdev->list, &rdev->wdev_list); rdev->devlist_generation++; /* can only change netns with wiphy */ dev->features |= NETIF_F_NETNS_LOCAL; @@ -869,12 +842,16 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, case NL80211_IFTYPE_MESH_POINT: cfg80211_leave_mesh(rdev, dev); break; + case NL80211_IFTYPE_AP: + cfg80211_stop_ap(rdev, dev); + break; default: break; } wdev->beacon_interval = 0; break; case NETDEV_DOWN: + cfg80211_update_iface_num(rdev, wdev->iftype, -1); dev_hold(dev); queue_work(cfg80211_wq, &wdev->cleanup_work); break; @@ -891,6 +868,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, mutex_unlock(&rdev->devlist_mtx); dev_put(dev); } + cfg80211_update_iface_num(rdev, wdev->iftype, 1); cfg80211_lock_rdev(rdev); mutex_lock(&rdev->devlist_mtx); wdev_lock(wdev); @@ -974,13 +952,20 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, */ synchronize_rcu(); INIT_LIST_HEAD(&wdev->list); + /* + * Ensure that all events have been processed and + * freed. + */ + cfg80211_process_wdev_events(wdev); break; case NETDEV_PRE_UP: if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype))) return notifier_from_errno(-EOPNOTSUPP); if (rfkill_blocked(rdev->rfkill)) return notifier_from_errno(-ERFKILL); + mutex_lock(&rdev->devlist_mtx); ret = cfg80211_can_add_interface(rdev, wdev->iftype); + mutex_unlock(&rdev->devlist_mtx); if (ret) return notifier_from_errno(ret); break; diff --git a/net/wireless/core.h b/net/wireless/core.h index 8523f387867..bc7430b5477 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -13,6 +13,7 @@ #include <linux/debugfs.h> #include <linux/rfkill.h> #include <linux/workqueue.h> +#include <linux/rtnetlink.h> #include <net/genetlink.h> #include <net/cfg80211.h> #include "reg.h" @@ -46,16 +47,20 @@ struct cfg80211_registered_device { /* wiphy index, internal only */ int wiphy_idx; - /* associate netdev list */ + /* associated wireless interfaces */ struct mutex devlist_mtx; /* protected by devlist_mtx or RCU */ - struct list_head netdev_list; - int devlist_generation; + struct list_head wdev_list; + int devlist_generation, wdev_id; int opencount; /* also protected by devlist_mtx */ wait_queue_head_t dev_wait; u32 ap_beacons_nlpid; + /* protected by RTNL only */ + int num_running_ifaces; + int num_running_monitor_ifaces; + /* BSSes/scanning */ spinlock_t bss_lock; struct list_head bss_list; @@ -159,32 +164,6 @@ static inline void cfg80211_unhold_bss(struct cfg80211_internal_bss *bss) struct cfg80211_registered_device *cfg80211_rdev_by_wiphy_idx(int wiphy_idx); int get_wiphy_idx(struct wiphy *wiphy); -struct cfg80211_registered_device * -__cfg80211_rdev_from_info(struct genl_info *info); - -/* - * This function returns a pointer to the driver - * that the genl_info item that is passed refers to. - * If successful, it returns non-NULL and also locks - * the driver's mutex! - * - * This means that you need to call cfg80211_unlock_rdev() - * before being allowed to acquire &cfg80211_mutex! - * - * This is necessary because we need to lock the global - * mutex to get an item off the list safely, and then - * we lock the rdev mutex so it doesn't go away under us. - * - * We don't want to keep cfg80211_mutex locked - * for all the time in order to allow requests on - * other interfaces to go through at the same time. - * - * The result of this can be a PTR_ERR and hence must - * be checked with IS_ERR() for errors. - */ -extern struct cfg80211_registered_device * -cfg80211_get_dev_from_info(struct genl_info *info); - /* requires cfg80211_rdev_mutex to be held! */ struct wiphy *wiphy_idx_to_wiphy(int wiphy_idx); @@ -223,6 +202,14 @@ static inline void wdev_unlock(struct wireless_dev *wdev) #define ASSERT_RDEV_LOCK(rdev) lockdep_assert_held(&(rdev)->mtx) #define ASSERT_WDEV_LOCK(wdev) lockdep_assert_held(&(wdev)->mtx) +static inline bool cfg80211_has_monitors_only(struct cfg80211_registered_device *rdev) +{ + ASSERT_RTNL(); + + return rdev->num_running_ifaces == rdev->num_running_monitor_ifaces && + rdev->num_running_ifaces > 0; +} + enum cfg80211_event_type { EVENT_CONNECT_RESULT, EVENT_ROAMED, @@ -267,6 +254,12 @@ struct cfg80211_cached_keys { int def, defmgmt; }; +enum cfg80211_chan_mode { + CHAN_MODE_UNDEFINED, + CHAN_MODE_SHARED, + CHAN_MODE_EXCLUSIVE, +}; + /* free object */ extern void cfg80211_dev_free(struct cfg80211_registered_device *rdev); @@ -303,14 +296,21 @@ extern const struct mesh_config default_mesh_config; extern const struct mesh_setup default_mesh_setup; int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev, - const struct mesh_setup *setup, + struct mesh_setup *setup, const struct mesh_config *conf); int cfg80211_join_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev, - const struct mesh_setup *setup, + struct mesh_setup *setup, const struct mesh_config *conf); int cfg80211_leave_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev); +int cfg80211_set_mesh_freq(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, int freq, + enum nl80211_channel_type channel_type); + +/* AP */ +int cfg80211_stop_ap(struct cfg80211_registered_device *rdev, + struct net_device *dev); /* MLME */ int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, @@ -369,7 +369,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_pid, void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlpid); void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev); int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, - struct net_device *dev, + struct wireless_dev *wdev, struct ieee80211_channel *chan, bool offchan, enum nl80211_channel_type channel_type, bool channel_type_valid, unsigned int wait, @@ -426,10 +426,22 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, struct net_device *dev, enum nl80211_iftype ntype, u32 *flags, struct vif_params *params); void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev); +void cfg80211_process_wdev_events(struct wireless_dev *wdev); + +int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + enum nl80211_iftype iftype, + struct ieee80211_channel *chan, + enum cfg80211_chan_mode chanmode); -int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev, - enum nl80211_iftype iftype); +static inline int +cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + enum nl80211_iftype iftype) +{ + return cfg80211_can_use_iftype_chan(rdev, wdev, iftype, NULL, + CHAN_MODE_UNDEFINED); +} static inline int cfg80211_can_add_interface(struct cfg80211_registered_device *rdev, @@ -438,12 +450,26 @@ cfg80211_can_add_interface(struct cfg80211_registered_device *rdev, return cfg80211_can_change_interface(rdev, NULL, iftype); } +static inline int +cfg80211_can_use_chan(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct ieee80211_channel *chan, + enum cfg80211_chan_mode chanmode) +{ + return cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype, + chan, chanmode); +} + +void +cfg80211_get_chan_state(struct wireless_dev *wdev, + struct ieee80211_channel **chan, + enum cfg80211_chan_mode *chanmode); + struct ieee80211_channel * rdev_freq_to_chan(struct cfg80211_registered_device *rdev, int freq, enum nl80211_channel_type channel_type); -int cfg80211_set_freq(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev, int freq, - enum nl80211_channel_type channel_type); +int cfg80211_set_monitor_channel(struct cfg80211_registered_device *rdev, + int freq, enum nl80211_channel_type chantype); int ieee80211_get_ratemask(struct ieee80211_supported_band *sband, const u8 *rates, unsigned int n_rates, @@ -452,6 +478,11 @@ int ieee80211_get_ratemask(struct ieee80211_supported_band *sband, int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev, u32 beacon_int); +void cfg80211_update_iface_num(struct cfg80211_registered_device *rdev, + enum nl80211_iftype iftype, int num); + +#define CFG80211_MAX_NUM_DIFFERENT_CHANNELS 10 + #ifdef CONFIG_CFG80211_DEVELOPER_WARNINGS #define CFG80211_DEV_WARN_ON(cond) WARN_ON(cond) #else diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index 89baa332841..ca5672f6ee2 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -113,10 +113,21 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, kfree(wdev->connect_keys); wdev->connect_keys = connkeys; + wdev->ibss_fixed = params->channel_fixed; #ifdef CONFIG_CFG80211_WEXT wdev->wext.ibss.channel = params->channel; #endif wdev->sme_state = CFG80211_SME_CONNECTING; + + err = cfg80211_can_use_chan(rdev, wdev, params->channel, + params->channel_fixed + ? CHAN_MODE_SHARED + : CHAN_MODE_EXCLUSIVE); + if (err) { + wdev->connect_keys = NULL; + return err; + } + err = rdev->ops->join_ibss(&rdev->wiphy, dev, params); if (err) { wdev->connect_keys = NULL; diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index 2749cb86b46..c384e77ff77 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -14,6 +14,9 @@ #define MESH_PATH_TIMEOUT 5000 #define MESH_RANN_INTERVAL 5000 +#define MESH_PATH_TO_ROOT_TIMEOUT 6000 +#define MESH_ROOT_INTERVAL 5000 +#define MESH_ROOT_CONFIRMATION_INTERVAL 2000 /* * Minimum interval between two consecutive PREQs originated by the same @@ -62,9 +65,15 @@ const struct mesh_config default_mesh_config = { .dot11MeshForwarding = true, .rssi_threshold = MESH_RSSI_THRESHOLD, .ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED, + .dot11MeshHWMPactivePathToRootTimeout = MESH_PATH_TO_ROOT_TIMEOUT, + .dot11MeshHWMProotInterval = MESH_ROOT_INTERVAL, + .dot11MeshHWMPconfirmationInterval = MESH_ROOT_CONFIRMATION_INTERVAL, }; const struct mesh_setup default_mesh_setup = { + /* cfg80211_join_mesh() will pick a channel if needed */ + .channel = NULL, + .channel_type = NL80211_CHAN_NO_HT, .sync_method = IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET, .path_sel_proto = IEEE80211_PATH_PROTOCOL_HWMP, .path_metric = IEEE80211_PATH_METRIC_AIRTIME, @@ -75,7 +84,7 @@ const struct mesh_setup default_mesh_setup = { int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev, - const struct mesh_setup *setup, + struct mesh_setup *setup, const struct mesh_config *conf) { struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -101,10 +110,61 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, if (!rdev->ops->join_mesh) return -EOPNOTSUPP; + if (!setup->channel) { + /* if no channel explicitly given, use preset channel */ + setup->channel = wdev->preset_chan; + setup->channel_type = wdev->preset_chantype; + } + + if (!setup->channel) { + /* if we don't have that either, use the first usable channel */ + enum ieee80211_band band; + + for (band = 0; band < IEEE80211_NUM_BANDS; band++) { + struct ieee80211_supported_band *sband; + struct ieee80211_channel *chan; + int i; + + sband = rdev->wiphy.bands[band]; + if (!sband) + continue; + + for (i = 0; i < sband->n_channels; i++) { + chan = &sband->channels[i]; + if (chan->flags & (IEEE80211_CHAN_NO_IBSS | + IEEE80211_CHAN_PASSIVE_SCAN | + IEEE80211_CHAN_DISABLED | + IEEE80211_CHAN_RADAR)) + continue; + setup->channel = chan; + break; + } + + if (setup->channel) + break; + } + + /* no usable channel ... */ + if (!setup->channel) + return -EINVAL; + + setup->channel_type = NL80211_CHAN_NO_HT; + } + + if (!cfg80211_can_beacon_sec_chan(&rdev->wiphy, setup->channel, + setup->channel_type)) + return -EINVAL; + + err = cfg80211_can_use_chan(rdev, wdev, setup->channel, + CHAN_MODE_SHARED); + if (err) + return err; + err = rdev->ops->join_mesh(&rdev->wiphy, dev, conf, setup); if (!err) { memcpy(wdev->ssid, setup->mesh_id, setup->mesh_id_len); wdev->mesh_id_len = setup->mesh_id_len; + wdev->channel = setup->channel; } return err; @@ -112,19 +172,71 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, int cfg80211_join_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev, - const struct mesh_setup *setup, + struct mesh_setup *setup, const struct mesh_config *conf) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; + mutex_lock(&rdev->devlist_mtx); wdev_lock(wdev); err = __cfg80211_join_mesh(rdev, dev, setup, conf); wdev_unlock(wdev); + mutex_unlock(&rdev->devlist_mtx); return err; } +int cfg80211_set_mesh_freq(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, int freq, + enum nl80211_channel_type channel_type) +{ + struct ieee80211_channel *channel; + int err; + + channel = rdev_freq_to_chan(rdev, freq, channel_type); + if (!channel || !cfg80211_can_beacon_sec_chan(&rdev->wiphy, + channel, + channel_type)) { + return -EINVAL; + } + + /* + * Workaround for libertas (only!), it puts the interface + * into mesh mode but doesn't implement join_mesh. Instead, + * it is configured via sysfs and then joins the mesh when + * you set the channel. Note that the libertas mesh isn't + * compatible with 802.11 mesh. + */ + if (rdev->ops->libertas_set_mesh_channel) { + if (channel_type != NL80211_CHAN_NO_HT) + return -EINVAL; + + if (!netif_running(wdev->netdev)) + return -ENETDOWN; + + err = cfg80211_can_use_chan(rdev, wdev, channel, + CHAN_MODE_SHARED); + if (err) + return err; + + err = rdev->ops->libertas_set_mesh_channel(&rdev->wiphy, + wdev->netdev, + channel); + if (!err) + wdev->channel = channel; + + return err; + } + + if (wdev->mesh_id_len) + return -EBUSY; + + wdev->preset_chan = channel; + wdev->preset_chantype = channel_type; + return 0; +} + void cfg80211_notify_new_peer_candidate(struct net_device *dev, const u8 *macaddr, const u8* ie, u8 ie_len, gfp_t gfp) { @@ -156,8 +268,11 @@ static int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev, return -ENOTCONN; err = rdev->ops->leave_mesh(&rdev->wiphy, dev); - if (!err) + if (!err) { wdev->mesh_id_len = 0; + wdev->channel = NULL; + } + return err; } diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index eb90988bbd3..1cdb1d5e6b0 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -302,8 +302,14 @@ int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, if (!req.bss) return -ENOENT; + err = cfg80211_can_use_chan(rdev, wdev, req.bss->channel, + CHAN_MODE_SHARED); + if (err) + goto out; + err = rdev->ops->auth(&rdev->wiphy, dev, &req); +out: cfg80211_put_bss(req.bss); return err; } @@ -317,11 +323,13 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, { int err; + mutex_lock(&rdev->devlist_mtx); wdev_lock(dev->ieee80211_ptr); err = __cfg80211_mlme_auth(rdev, dev, chan, auth_type, bssid, ssid, ssid_len, ie, ie_len, key, key_len, key_idx); wdev_unlock(dev->ieee80211_ptr); + mutex_unlock(&rdev->devlist_mtx); return err; } @@ -397,8 +405,14 @@ int __cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, return -ENOENT; } + err = cfg80211_can_use_chan(rdev, wdev, req.bss->channel, + CHAN_MODE_SHARED); + if (err) + goto out; + err = rdev->ops->assoc(&rdev->wiphy, dev, &req); +out: if (err) { if (was_connected) wdev->sme_state = CFG80211_SME_CONNECTED; @@ -421,11 +435,13 @@ int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev = dev->ieee80211_ptr; int err; + mutex_lock(&rdev->devlist_mtx); wdev_lock(wdev); err = __cfg80211_mlme_assoc(rdev, dev, chan, bssid, prev_bssid, ssid, ssid_len, ie, ie_len, use_mfp, crypt, assoc_flags, ht_capa, ht_capa_mask); wdev_unlock(wdev); + mutex_unlock(&rdev->devlist_mtx); return err; } @@ -551,29 +567,28 @@ void cfg80211_mlme_down(struct cfg80211_registered_device *rdev, } } -void cfg80211_ready_on_channel(struct net_device *dev, u64 cookie, +void cfg80211_ready_on_channel(struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type, unsigned int duration, gfp_t gfp) { - struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; + struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - nl80211_send_remain_on_channel(rdev, dev, cookie, chan, channel_type, + nl80211_send_remain_on_channel(rdev, wdev, cookie, chan, channel_type, duration, gfp); } EXPORT_SYMBOL(cfg80211_ready_on_channel); -void cfg80211_remain_on_channel_expired(struct net_device *dev, - u64 cookie, +void cfg80211_remain_on_channel_expired(struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type, gfp_t gfp) { - struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; + struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - nl80211_send_remain_on_channel_cancel(rdev, dev, cookie, chan, + nl80211_send_remain_on_channel_cancel(rdev, wdev, cookie, chan, channel_type, gfp); } EXPORT_SYMBOL(cfg80211_remain_on_channel_expired); @@ -662,8 +677,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_pid, list_add(&nreg->list, &wdev->mgmt_registrations); if (rdev->ops->mgmt_frame_register) - rdev->ops->mgmt_frame_register(wiphy, wdev->netdev, - frame_type, true); + rdev->ops->mgmt_frame_register(wiphy, wdev, frame_type, true); out: spin_unlock_bh(&wdev->mgmt_registrations_lock); @@ -686,7 +700,7 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlpid) if (rdev->ops->mgmt_frame_register) { u16 frame_type = le16_to_cpu(reg->frame_type); - rdev->ops->mgmt_frame_register(wiphy, wdev->netdev, + rdev->ops->mgmt_frame_register(wiphy, wdev, frame_type, false); } @@ -715,14 +729,14 @@ void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev) } int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, - struct net_device *dev, + struct wireless_dev *wdev, struct ieee80211_channel *chan, bool offchan, enum nl80211_channel_type channel_type, bool channel_type_valid, unsigned int wait, const u8 *buf, size_t len, bool no_cck, bool dont_wait_for_ack, u64 *cookie) { - struct wireless_dev *wdev = dev->ieee80211_ptr; + struct net_device *dev = wdev->netdev; const struct ieee80211_mgmt *mgmt; u16 stype; @@ -809,16 +823,15 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, return -EINVAL; /* Transmit the Action frame as requested by user space */ - return rdev->ops->mgmt_tx(&rdev->wiphy, dev, chan, offchan, + return rdev->ops->mgmt_tx(&rdev->wiphy, wdev, chan, offchan, channel_type, channel_type_valid, wait, buf, len, no_cck, dont_wait_for_ack, cookie); } -bool cfg80211_rx_mgmt(struct net_device *dev, int freq, int sig_mbm, +bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_mbm, const u8 *buf, size_t len, gfp_t gfp) { - struct wireless_dev *wdev = dev->ieee80211_ptr; struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); struct cfg80211_mgmt_registration *reg; @@ -855,7 +868,7 @@ bool cfg80211_rx_mgmt(struct net_device *dev, int freq, int sig_mbm, /* found match! */ /* Indicate the received Action frame to user space */ - if (nl80211_send_mgmt(rdev, dev, reg->nlpid, + if (nl80211_send_mgmt(rdev, wdev, reg->nlpid, freq, sig_mbm, buf, len, gfp)) continue; @@ -870,15 +883,14 @@ bool cfg80211_rx_mgmt(struct net_device *dev, int freq, int sig_mbm, } EXPORT_SYMBOL(cfg80211_rx_mgmt); -void cfg80211_mgmt_tx_status(struct net_device *dev, u64 cookie, +void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, const u8 *buf, size_t len, bool ack, gfp_t gfp) { - struct wireless_dev *wdev = dev->ieee80211_ptr; struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); /* Indicate TX status of the Action frame to user space */ - nl80211_send_mgmt_tx_status(rdev, dev, cookie, buf, len, ack, gfp); + nl80211_send_mgmt_tx_status(rdev, wdev, cookie, buf, len, ack, gfp); } EXPORT_SYMBOL(cfg80211_mgmt_tx_status); @@ -907,6 +919,19 @@ void cfg80211_cqm_pktloss_notify(struct net_device *dev, } EXPORT_SYMBOL(cfg80211_cqm_pktloss_notify); +void cfg80211_cqm_txe_notify(struct net_device *dev, + const u8 *peer, u32 num_packets, + u32 rate, u32 intvl, gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + + nl80211_send_cqm_txe_notify(rdev, dev, peer, num_packets, + rate, intvl, gfp); +} +EXPORT_SYMBOL(cfg80211_cqm_txe_notify); + void cfg80211_gtk_rekey_notify(struct net_device *dev, const u8 *bssid, const u8 *replay_ctr, gfp_t gfp) { @@ -948,7 +973,6 @@ void cfg80211_ch_switch_notify(struct net_device *dev, int freq, goto out; wdev->channel = chan; - nl80211_ch_switch_notify(rdev, dev, freq, type, GFP_KERNEL); out: wdev_unlock(wdev); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 206465dc0ca..97026f3b215 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -46,28 +46,175 @@ static struct genl_family nl80211_fam = { .post_doit = nl80211_post_doit, }; -/* internal helper: get rdev and dev */ -static int get_rdev_dev_by_ifindex(struct net *netns, struct nlattr **attrs, - struct cfg80211_registered_device **rdev, - struct net_device **dev) +/* returns ERR_PTR values */ +static struct wireless_dev * +__cfg80211_wdev_from_attrs(struct net *netns, struct nlattr **attrs) { - int ifindex; + struct cfg80211_registered_device *rdev; + struct wireless_dev *result = NULL; + bool have_ifidx = attrs[NL80211_ATTR_IFINDEX]; + bool have_wdev_id = attrs[NL80211_ATTR_WDEV]; + u64 wdev_id; + int wiphy_idx = -1; + int ifidx = -1; - if (!attrs[NL80211_ATTR_IFINDEX]) - return -EINVAL; + assert_cfg80211_lock(); - ifindex = nla_get_u32(attrs[NL80211_ATTR_IFINDEX]); - *dev = dev_get_by_index(netns, ifindex); - if (!*dev) - return -ENODEV; + if (!have_ifidx && !have_wdev_id) + return ERR_PTR(-EINVAL); - *rdev = cfg80211_get_dev_from_ifindex(netns, ifindex); - if (IS_ERR(*rdev)) { - dev_put(*dev); - return PTR_ERR(*rdev); + if (have_ifidx) + ifidx = nla_get_u32(attrs[NL80211_ATTR_IFINDEX]); + if (have_wdev_id) { + wdev_id = nla_get_u64(attrs[NL80211_ATTR_WDEV]); + wiphy_idx = wdev_id >> 32; } - return 0; + list_for_each_entry(rdev, &cfg80211_rdev_list, list) { + struct wireless_dev *wdev; + + if (wiphy_net(&rdev->wiphy) != netns) + continue; + + if (have_wdev_id && rdev->wiphy_idx != wiphy_idx) + continue; + + mutex_lock(&rdev->devlist_mtx); + list_for_each_entry(wdev, &rdev->wdev_list, list) { + if (have_ifidx && wdev->netdev && + wdev->netdev->ifindex == ifidx) { + result = wdev; + break; + } + if (have_wdev_id && wdev->identifier == (u32)wdev_id) { + result = wdev; + break; + } + } + mutex_unlock(&rdev->devlist_mtx); + + if (result) + break; + } + + if (result) + return result; + return ERR_PTR(-ENODEV); +} + +static struct cfg80211_registered_device * +__cfg80211_rdev_from_attrs(struct net *netns, struct nlattr **attrs) +{ + struct cfg80211_registered_device *rdev = NULL, *tmp; + struct net_device *netdev; + + assert_cfg80211_lock(); + + if (!attrs[NL80211_ATTR_WIPHY] && + !attrs[NL80211_ATTR_IFINDEX] && + !attrs[NL80211_ATTR_WDEV]) + return ERR_PTR(-EINVAL); + + if (attrs[NL80211_ATTR_WIPHY]) + rdev = cfg80211_rdev_by_wiphy_idx( + nla_get_u32(attrs[NL80211_ATTR_WIPHY])); + + if (attrs[NL80211_ATTR_WDEV]) { + u64 wdev_id = nla_get_u64(attrs[NL80211_ATTR_WDEV]); + struct wireless_dev *wdev; + bool found = false; + + tmp = cfg80211_rdev_by_wiphy_idx(wdev_id >> 32); + if (tmp) { + /* make sure wdev exists */ + mutex_lock(&tmp->devlist_mtx); + list_for_each_entry(wdev, &tmp->wdev_list, list) { + if (wdev->identifier != (u32)wdev_id) + continue; + found = true; + break; + } + mutex_unlock(&tmp->devlist_mtx); + + if (!found) + tmp = NULL; + + if (rdev && tmp != rdev) + return ERR_PTR(-EINVAL); + rdev = tmp; + } + } + + if (attrs[NL80211_ATTR_IFINDEX]) { + int ifindex = nla_get_u32(attrs[NL80211_ATTR_IFINDEX]); + netdev = dev_get_by_index(netns, ifindex); + if (netdev) { + if (netdev->ieee80211_ptr) + tmp = wiphy_to_dev( + netdev->ieee80211_ptr->wiphy); + else + tmp = NULL; + + dev_put(netdev); + + /* not wireless device -- return error */ + if (!tmp) + return ERR_PTR(-EINVAL); + + /* mismatch -- return error */ + if (rdev && tmp != rdev) + return ERR_PTR(-EINVAL); + + rdev = tmp; + } + } + + if (!rdev) + return ERR_PTR(-ENODEV); + + if (netns != wiphy_net(&rdev->wiphy)) + return ERR_PTR(-ENODEV); + + return rdev; +} + +/* + * This function returns a pointer to the driver + * that the genl_info item that is passed refers to. + * If successful, it returns non-NULL and also locks + * the driver's mutex! + * + * This means that you need to call cfg80211_unlock_rdev() + * before being allowed to acquire &cfg80211_mutex! + * + * This is necessary because we need to lock the global + * mutex to get an item off the list safely, and then + * we lock the rdev mutex so it doesn't go away under us. + * + * We don't want to keep cfg80211_mutex locked + * for all the time in order to allow requests on + * other interfaces to go through at the same time. + * + * The result of this can be a PTR_ERR and hence must + * be checked with IS_ERR() for errors. + */ +static struct cfg80211_registered_device * +cfg80211_get_dev_from_info(struct net *netns, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev; + + mutex_lock(&cfg80211_mutex); + rdev = __cfg80211_rdev_from_attrs(netns, info->attrs); + + /* if it is not an error we grab the lock on + * it to assure it won't be going away while + * we operate on it */ + if (!IS_ERR(rdev)) + mutex_lock(&rdev->mtx); + + mutex_unlock(&cfg80211_mutex); + + return rdev; } /* policy for the attributes */ @@ -115,7 +262,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_STA_VLAN] = { .type = NLA_U32 }, [NL80211_ATTR_MNTR_FLAGS] = { /* NLA_NESTED can't be empty */ }, [NL80211_ATTR_MESH_ID] = { .type = NLA_BINARY, - .len = IEEE80211_MAX_MESH_ID_LEN }, + .len = IEEE80211_MAX_MESH_ID_LEN }, [NL80211_ATTR_MPATH_NEXT_HOP] = { .type = NLA_U32 }, [NL80211_ATTR_REG_ALPHA2] = { .type = NLA_STRING, .len = 2 }, @@ -206,6 +353,8 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_NOACK_MAP] = { .type = NLA_U16 }, [NL80211_ATTR_INACTIVITY_TIMEOUT] = { .type = NLA_U16 }, [NL80211_ATTR_BG_SCAN_PERIOD] = { .type = NLA_U16 }, + [NL80211_ATTR_WDEV] = { .type = NLA_U64 }, + [NL80211_ATTR_USER_REG_HINT_TYPE] = { .type = NLA_U32 }, }; /* policy for the key attributes */ @@ -250,8 +399,9 @@ nl80211_rekey_policy[NUM_NL80211_REKEY_DATA] = { static const struct nla_policy nl80211_match_policy[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1] = { - [NL80211_ATTR_SCHED_SCAN_MATCH_SSID] = { .type = NLA_BINARY, + [NL80211_SCHED_SCAN_MATCH_ATTR_SSID] = { .type = NLA_BINARY, .len = IEEE80211_MAX_SSID_LEN }, + [NL80211_SCHED_SCAN_MATCH_ATTR_RSSI] = { .type = NLA_U32 }, }; /* ifidx get helper */ @@ -832,6 +982,15 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, dev->wiphy.bands[band]->ht_cap.ampdu_density))) goto nla_put_failure; + /* add VHT info */ + if (dev->wiphy.bands[band]->vht_cap.vht_supported && + (nla_put(msg, NL80211_BAND_ATTR_VHT_MCS_SET, + sizeof(dev->wiphy.bands[band]->vht_cap.vht_mcs), + &dev->wiphy.bands[band]->vht_cap.vht_mcs) || + nla_put_u32(msg, NL80211_BAND_ATTR_VHT_CAPA, + dev->wiphy.bands[band]->vht_cap.cap))) + goto nla_put_failure; + /* add frequencies */ nl_freqs = nla_nest_start(msg, NL80211_BAND_ATTR_FREQS); if (!nl_freqs) @@ -921,7 +1080,12 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, if (nla_put_u32(msg, i, NL80211_CMD_SET_WIPHY_NETNS)) goto nla_put_failure; } - CMD(set_channel, SET_CHANNEL); + if (dev->ops->set_monitor_channel || dev->ops->start_ap || + dev->ops->join_mesh) { + i++; + if (nla_put_u32(msg, i, NL80211_CMD_SET_CHANNEL)) + goto nla_put_failure; + } CMD(set_wds_peer, SET_WDS_PEER); if (dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) { CMD(tdls_mgmt, TDLS_MGMT); @@ -1018,6 +1182,7 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, nla_nest_end(msg, nl_ifs); } +#ifdef CONFIG_PM if (dev->wiphy.wowlan.flags || dev->wiphy.wowlan.n_patterns) { struct nlattr *nl_wowlan; @@ -1058,6 +1223,7 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, nla_nest_end(msg, nl_wowlan); } +#endif if (nl80211_put_iftypes(msg, NL80211_ATTR_SOFTWARE_IFTYPES, dev->wiphy.software_iftypes)) @@ -1162,18 +1328,22 @@ static int parse_txq_params(struct nlattr *tb[], static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev) { /* - * You can only set the channel explicitly for AP, mesh - * and WDS type interfaces; all others have their channel - * managed via their respective "establish a connection" - * command (connect, join, ...) + * You can only set the channel explicitly for WDS interfaces, + * all others have their channel managed via their respective + * "establish a connection" command (connect, join, ...) + * + * For AP/GO and mesh mode, the channel can be set with the + * channel userspace API, but is only stored and passed to the + * low-level driver when the AP starts or the mesh is joined. + * This is for backward compatibility, userspace can also give + * the channel in the start-ap or join-mesh commands instead. * * Monitors are special as they are normally slaved to - * whatever else is going on, so they behave as though - * you tried setting the wiphy channel itself. + * whatever else is going on, so they have their own special + * operation to set the monitor channel if possible. */ return !wdev || wdev->iftype == NL80211_IFTYPE_AP || - wdev->iftype == NL80211_IFTYPE_WDS || wdev->iftype == NL80211_IFTYPE_MESH_POINT || wdev->iftype == NL80211_IFTYPE_MONITOR || wdev->iftype == NL80211_IFTYPE_P2P_GO; @@ -1204,9 +1374,14 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct genl_info *info) { + struct ieee80211_channel *channel; enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; u32 freq; int result; + enum nl80211_iftype iftype = NL80211_IFTYPE_MONITOR; + + if (wdev) + iftype = wdev->iftype; if (!info->attrs[NL80211_ATTR_WIPHY_FREQ]) return -EINVAL; @@ -1221,12 +1396,32 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); mutex_lock(&rdev->devlist_mtx); - if (wdev) { - wdev_lock(wdev); - result = cfg80211_set_freq(rdev, wdev, freq, channel_type); - wdev_unlock(wdev); - } else { - result = cfg80211_set_freq(rdev, NULL, freq, channel_type); + switch (iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: + if (wdev->beacon_interval) { + result = -EBUSY; + break; + } + channel = rdev_freq_to_chan(rdev, freq, channel_type); + if (!channel || !cfg80211_can_beacon_sec_chan(&rdev->wiphy, + channel, + channel_type)) { + result = -EINVAL; + break; + } + wdev->preset_chan = channel; + wdev->preset_chantype = channel_type; + result = 0; + break; + case NL80211_IFTYPE_MESH_POINT: + result = cfg80211_set_mesh_freq(rdev, wdev, freq, channel_type); + break; + case NL80211_IFTYPE_MONITOR: + result = cfg80211_set_monitor_channel(rdev, freq, channel_type); + break; + default: + result = -EINVAL; } mutex_unlock(&rdev->devlist_mtx); @@ -1300,7 +1495,8 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) } if (!netdev) { - rdev = __cfg80211_rdev_from_info(info); + rdev = __cfg80211_rdev_from_attrs(genl_info_net(info), + info->attrs); if (IS_ERR(rdev)) { mutex_unlock(&cfg80211_mutex); return PTR_ERR(rdev); @@ -1310,8 +1506,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) result = 0; mutex_lock(&rdev->mtx); - } else if (netif_running(netdev) && - nl80211_can_set_dev_channel(netdev->ieee80211_ptr)) + } else if (nl80211_can_set_dev_channel(netdev->ieee80211_ptr)) wdev = netdev->ieee80211_ptr; else wdev = NULL; @@ -1534,22 +1729,32 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) return result; } +static inline u64 wdev_id(struct wireless_dev *wdev) +{ + return (u64)wdev->identifier | + ((u64)wiphy_to_dev(wdev->wiphy)->wiphy_idx << 32); +} static int nl80211_send_iface(struct sk_buff *msg, u32 pid, u32 seq, int flags, struct cfg80211_registered_device *rdev, - struct net_device *dev) + struct wireless_dev *wdev) { + struct net_device *dev = wdev->netdev; void *hdr; hdr = nl80211hdr_put(msg, pid, seq, flags, NL80211_CMD_NEW_INTERFACE); if (!hdr) return -1; - if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || - nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || - nla_put_string(msg, NL80211_ATTR_IFNAME, dev->name) || - nla_put_u32(msg, NL80211_ATTR_IFTYPE, - dev->ieee80211_ptr->iftype) || + if (dev && + (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || + nla_put_string(msg, NL80211_ATTR_IFNAME, dev->name) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, dev->dev_addr))) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFTYPE, wdev->iftype) || + nla_put_u64(msg, NL80211_ATTR_WDEV, wdev_id(wdev)) || nla_put_u32(msg, NL80211_ATTR_GENERATION, rdev->devlist_generation ^ (cfg80211_rdev_list_generation << 2))) @@ -1559,12 +1764,13 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 pid, u32 seq, int flags, struct ieee80211_channel *chan; enum nl80211_channel_type channel_type; - chan = rdev->ops->get_channel(&rdev->wiphy, &channel_type); + chan = rdev->ops->get_channel(&rdev->wiphy, wdev, + &channel_type); if (chan && (nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, - chan->center_freq) || + chan->center_freq) || nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE, - channel_type))) + channel_type))) goto nla_put_failure; } @@ -1595,14 +1801,14 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * if_idx = 0; mutex_lock(&rdev->devlist_mtx); - list_for_each_entry(wdev, &rdev->netdev_list, list) { + list_for_each_entry(wdev, &rdev->wdev_list, list) { if (if_idx < if_start) { if_idx++; continue; } if (nl80211_send_iface(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - rdev, wdev->netdev) < 0) { + rdev, wdev) < 0) { mutex_unlock(&rdev->devlist_mtx); goto out; } @@ -1625,14 +1831,14 @@ static int nl80211_get_interface(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; struct cfg80211_registered_device *dev = info->user_ptr[0]; - struct net_device *netdev = info->user_ptr[1]; + struct wireless_dev *wdev = info->user_ptr[1]; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; if (nl80211_send_iface(msg, info->snd_pid, info->snd_seq, 0, - dev, netdev) < 0) { + dev, wdev) < 0) { nlmsg_free(msg); return -ENOBUFS; } @@ -1772,7 +1978,8 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct vif_params params; - struct net_device *dev; + struct wireless_dev *wdev; + struct sk_buff *msg; int err; enum nl80211_iftype type = NL80211_IFTYPE_UNSPECIFIED; u32 flags; @@ -1799,19 +2006,23 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) return err; } + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + err = parse_monitor_flags(type == NL80211_IFTYPE_MONITOR ? info->attrs[NL80211_ATTR_MNTR_FLAGS] : NULL, &flags); - dev = rdev->ops->add_virtual_intf(&rdev->wiphy, + wdev = rdev->ops->add_virtual_intf(&rdev->wiphy, nla_data(info->attrs[NL80211_ATTR_IFNAME]), type, err ? NULL : &flags, ¶ms); - if (IS_ERR(dev)) - return PTR_ERR(dev); + if (IS_ERR(wdev)) { + nlmsg_free(msg); + return PTR_ERR(wdev); + } if (type == NL80211_IFTYPE_MESH_POINT && info->attrs[NL80211_ATTR_MESH_ID]) { - struct wireless_dev *wdev = dev->ieee80211_ptr; - wdev_lock(wdev); BUILD_BUG_ON(IEEE80211_MAX_SSID_LEN != IEEE80211_MAX_MESH_ID_LEN); @@ -1822,18 +2033,34 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) wdev_unlock(wdev); } - return 0; + if (nl80211_send_iface(msg, info->snd_pid, info->snd_seq, 0, + rdev, wdev) < 0) { + nlmsg_free(msg); + return -ENOBUFS; + } + + return genlmsg_reply(msg, info); } static int nl80211_del_interface(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; - struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = info->user_ptr[1]; if (!rdev->ops->del_virtual_intf) return -EOPNOTSUPP; - return rdev->ops->del_virtual_intf(&rdev->wiphy, dev); + /* + * If we remove a wireless device without a netdev then clear + * user_ptr[1] so that nl80211_post_doit won't dereference it + * to check if it needs to do dev_put(). Otherwise it crashes + * since the wdev has been freed, unlike with a netdev where + * we need the dev_put() for the netdev to really be freed. + */ + if (!wdev->netdev) + info->user_ptr[1] = NULL; + + return rdev->ops->del_virtual_intf(&rdev->wiphy, wdev); } static int nl80211_set_noack_map(struct sk_buff *skb, struct genl_info *info) @@ -2213,6 +2440,33 @@ static int nl80211_parse_beacon(struct genl_info *info, return 0; } +static bool nl80211_get_ap_channel(struct cfg80211_registered_device *rdev, + struct cfg80211_ap_settings *params) +{ + struct wireless_dev *wdev; + bool ret = false; + + mutex_lock(&rdev->devlist_mtx); + + list_for_each_entry(wdev, &rdev->wdev_list, list) { + if (wdev->iftype != NL80211_IFTYPE_AP && + wdev->iftype != NL80211_IFTYPE_P2P_GO) + continue; + + if (!wdev->preset_chan) + continue; + + params->channel = wdev->preset_chan; + params->channel_type = wdev->preset_chantype; + ret = true; + break; + } + + mutex_unlock(&rdev->devlist_mtx); + + return ret; +} + static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -2299,9 +2553,44 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) info->attrs[NL80211_ATTR_INACTIVITY_TIMEOUT]); } + if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { + enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; + + if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] && + !nl80211_valid_channel_type(info, &channel_type)) + return -EINVAL; + + params.channel = rdev_freq_to_chan(rdev, + nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]), + channel_type); + if (!params.channel) + return -EINVAL; + params.channel_type = channel_type; + } else if (wdev->preset_chan) { + params.channel = wdev->preset_chan; + params.channel_type = wdev->preset_chantype; + } else if (!nl80211_get_ap_channel(rdev, ¶ms)) + return -EINVAL; + + if (!cfg80211_can_beacon_sec_chan(&rdev->wiphy, params.channel, + params.channel_type)) + return -EINVAL; + + mutex_lock(&rdev->devlist_mtx); + err = cfg80211_can_use_chan(rdev, wdev, params.channel, + CHAN_MODE_SHARED); + mutex_unlock(&rdev->devlist_mtx); + + if (err) + return err; + err = rdev->ops->start_ap(&rdev->wiphy, dev, ¶ms); - if (!err) + if (!err) { + wdev->preset_chan = params.channel; + wdev->preset_chantype = params.channel_type; wdev->beacon_interval = params.beacon_interval; + wdev->channel = params.channel; + } return err; } @@ -2334,23 +2623,8 @@ static int nl80211_stop_ap(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; - struct wireless_dev *wdev = dev->ieee80211_ptr; - int err; - if (!rdev->ops->stop_ap) - return -EOPNOTSUPP; - - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) - return -EOPNOTSUPP; - - if (!wdev->beacon_interval) - return -ENOENT; - - err = rdev->ops->stop_ap(&rdev->wiphy, dev); - if (!err) - wdev->beacon_interval = 0; - return err; + return cfg80211_stop_ap(rdev, dev); } static const struct nla_policy sta_flags_policy[NL80211_STA_FLAG_MAX + 1] = { @@ -2442,7 +2716,8 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, int attr) { struct nlattr *rate; - u16 bitrate; + u32 bitrate; + u16 bitrate_compat; rate = nla_nest_start(msg, attr); if (!rate) @@ -2450,8 +2725,12 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, /* cfg80211_calculate_bitrate will return 0 for mcs >= 32 */ bitrate = cfg80211_calculate_bitrate(info); + /* report 16-bit bitrate only if we can */ + bitrate_compat = bitrate < (1UL << 16) ? bitrate : 0; if ((bitrate > 0 && - nla_put_u16(msg, NL80211_RATE_INFO_BITRATE, bitrate)) || + nla_put_u32(msg, NL80211_RATE_INFO_BITRATE32, bitrate)) || + (bitrate_compat > 0 && + nla_put_u16(msg, NL80211_RATE_INFO_BITRATE, bitrate_compat)) || ((info->flags & RATE_INFO_FLAGS_MCS) && nla_put_u8(msg, NL80211_RATE_INFO_MCS, info->mcs)) || ((info->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH) && @@ -3304,6 +3583,7 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) { int r; char *data = NULL; + enum nl80211_user_reg_hint_type user_reg_hint_type; /* * You should only get this when cfg80211 hasn't yet initialized @@ -3323,7 +3603,21 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) data = nla_data(info->attrs[NL80211_ATTR_REG_ALPHA2]); - r = regulatory_hint_user(data); + if (info->attrs[NL80211_ATTR_USER_REG_HINT_TYPE]) + user_reg_hint_type = + nla_get_u32(info->attrs[NL80211_ATTR_USER_REG_HINT_TYPE]); + else + user_reg_hint_type = NL80211_USER_REG_HINT_USER; + + switch (user_reg_hint_type) { + case NL80211_USER_REG_HINT_USER: + case NL80211_USER_REG_HINT_CELL_BASE: + break; + default: + return -EINVAL; + } + + r = regulatory_hint_user(data, user_reg_hint_type); return r; } @@ -3413,7 +3707,13 @@ static int nl80211_get_mesh_config(struct sk_buff *skb, nla_put_u32(msg, NL80211_MESHCONF_RSSI_THRESHOLD, cur_params.rssi_threshold) || nla_put_u32(msg, NL80211_MESHCONF_HT_OPMODE, - cur_params.ht_opmode)) + cur_params.ht_opmode) || + nla_put_u32(msg, NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT, + cur_params.dot11MeshHWMPactivePathToRootTimeout) || + nla_put_u16(msg, NL80211_MESHCONF_HWMP_ROOT_INTERVAL, + cur_params.dot11MeshHWMProotInterval) || + nla_put_u16(msg, NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL, + cur_params.dot11MeshHWMPconfirmationInterval)) goto nla_put_failure; nla_nest_end(msg, pinfoattr); genlmsg_end(msg, hdr); @@ -3436,7 +3736,6 @@ static const struct nla_policy nl80211_meshconf_params_policy[NL80211_MESHCONF_A [NL80211_MESHCONF_ELEMENT_TTL] = { .type = NLA_U8 }, [NL80211_MESHCONF_AUTO_OPEN_PLINKS] = { .type = NLA_U8 }, [NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR] = { .type = NLA_U32 }, - [NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES] = { .type = NLA_U8 }, [NL80211_MESHCONF_PATH_REFRESH_TIME] = { .type = NLA_U32 }, [NL80211_MESHCONF_MIN_DISCOVERY_TIMEOUT] = { .type = NLA_U16 }, @@ -3448,8 +3747,11 @@ static const struct nla_policy nl80211_meshconf_params_policy[NL80211_MESHCONF_A [NL80211_MESHCONF_HWMP_RANN_INTERVAL] = { .type = NLA_U16 }, [NL80211_MESHCONF_GATE_ANNOUNCEMENTS] = { .type = NLA_U8 }, [NL80211_MESHCONF_FORWARDING] = { .type = NLA_U8 }, - [NL80211_MESHCONF_RSSI_THRESHOLD] = { .type = NLA_U32}, - [NL80211_MESHCONF_HT_OPMODE] = { .type = NLA_U16}, + [NL80211_MESHCONF_RSSI_THRESHOLD] = { .type = NLA_U32 }, + [NL80211_MESHCONF_HT_OPMODE] = { .type = NLA_U16 }, + [NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT] = { .type = NLA_U32 }, + [NL80211_MESHCONF_HWMP_ROOT_INTERVAL] = { .type = NLA_U16 }, + [NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL] = { .type = NLA_U16 }, }; static const struct nla_policy @@ -3459,7 +3761,7 @@ static const struct nla_policy [NL80211_MESH_SETUP_ENABLE_VENDOR_METRIC] = { .type = NLA_U8 }, [NL80211_MESH_SETUP_USERSPACE_AUTH] = { .type = NLA_FLAG }, [NL80211_MESH_SETUP_IE] = { .type = NLA_BINARY, - .len = IEEE80211_MAX_DATA_LEN }, + .len = IEEE80211_MAX_DATA_LEN }, [NL80211_MESH_SETUP_USERSPACE_AMPE] = { .type = NLA_FLAG }, }; @@ -3492,63 +3794,82 @@ do {\ /* Fill in the params struct */ FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshRetryTimeout, - mask, NL80211_MESHCONF_RETRY_TIMEOUT, nla_get_u16); + mask, NL80211_MESHCONF_RETRY_TIMEOUT, + nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshConfirmTimeout, - mask, NL80211_MESHCONF_CONFIRM_TIMEOUT, nla_get_u16); + mask, NL80211_MESHCONF_CONFIRM_TIMEOUT, + nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHoldingTimeout, - mask, NL80211_MESHCONF_HOLDING_TIMEOUT, nla_get_u16); + mask, NL80211_MESHCONF_HOLDING_TIMEOUT, + nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshMaxPeerLinks, - mask, NL80211_MESHCONF_MAX_PEER_LINKS, nla_get_u16); + mask, NL80211_MESHCONF_MAX_PEER_LINKS, + nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshMaxRetries, - mask, NL80211_MESHCONF_MAX_RETRIES, nla_get_u8); + mask, NL80211_MESHCONF_MAX_RETRIES, + nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshTTL, - mask, NL80211_MESHCONF_TTL, nla_get_u8); + mask, NL80211_MESHCONF_TTL, nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, element_ttl, - mask, NL80211_MESHCONF_ELEMENT_TTL, nla_get_u8); + mask, NL80211_MESHCONF_ELEMENT_TTL, + nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, auto_open_plinks, - mask, NL80211_MESHCONF_AUTO_OPEN_PLINKS, nla_get_u8); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshNbrOffsetMaxNeighbor, - mask, NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR, - nla_get_u32); + mask, NL80211_MESHCONF_AUTO_OPEN_PLINKS, + nla_get_u8); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshNbrOffsetMaxNeighbor, mask, + NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR, + nla_get_u32); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPmaxPREQretries, - mask, NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES, - nla_get_u8); + mask, NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES, + nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, path_refresh_time, - mask, NL80211_MESHCONF_PATH_REFRESH_TIME, nla_get_u32); + mask, NL80211_MESHCONF_PATH_REFRESH_TIME, + nla_get_u32); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, min_discovery_timeout, - mask, NL80211_MESHCONF_MIN_DISCOVERY_TIMEOUT, - nla_get_u16); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathTimeout, - mask, NL80211_MESHCONF_HWMP_ACTIVE_PATH_TIMEOUT, - nla_get_u32); + mask, NL80211_MESHCONF_MIN_DISCOVERY_TIMEOUT, + nla_get_u16); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathTimeout, mask, + NL80211_MESHCONF_HWMP_ACTIVE_PATH_TIMEOUT, + nla_get_u32); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPpreqMinInterval, - mask, NL80211_MESHCONF_HWMP_PREQ_MIN_INTERVAL, - nla_get_u16); + mask, NL80211_MESHCONF_HWMP_PREQ_MIN_INTERVAL, + nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPperrMinInterval, - mask, NL80211_MESHCONF_HWMP_PERR_MIN_INTERVAL, - nla_get_u16); + mask, NL80211_MESHCONF_HWMP_PERR_MIN_INTERVAL, + nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, - dot11MeshHWMPnetDiameterTraversalTime, - mask, NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME, - nla_get_u16); + dot11MeshHWMPnetDiameterTraversalTime, mask, + NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME, + nla_get_u16); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPRootMode, mask, + NL80211_MESHCONF_HWMP_ROOTMODE, nla_get_u8); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPRannInterval, mask, + NL80211_MESHCONF_HWMP_RANN_INTERVAL, + nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, - dot11MeshHWMPRootMode, mask, - NL80211_MESHCONF_HWMP_ROOTMODE, - nla_get_u8); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, - dot11MeshHWMPRannInterval, mask, - NL80211_MESHCONF_HWMP_RANN_INTERVAL, - nla_get_u16); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, - dot11MeshGateAnnouncementProtocol, mask, - NL80211_MESHCONF_GATE_ANNOUNCEMENTS, - nla_get_u8); + dot11MeshGateAnnouncementProtocol, mask, + NL80211_MESHCONF_GATE_ANNOUNCEMENTS, + nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshForwarding, - mask, NL80211_MESHCONF_FORWARDING, nla_get_u8); + mask, NL80211_MESHCONF_FORWARDING, + nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, rssi_threshold, - mask, NL80211_MESHCONF_RSSI_THRESHOLD, nla_get_u32); + mask, NL80211_MESHCONF_RSSI_THRESHOLD, + nla_get_u32); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, ht_opmode, - mask, NL80211_MESHCONF_HT_OPMODE, nla_get_u16); + mask, NL80211_MESHCONF_HT_OPMODE, + nla_get_u16); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathToRootTimeout, + mask, + NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT, + nla_get_u32); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMProotInterval, + mask, NL80211_MESHCONF_HWMP_ROOT_INTERVAL, + nla_get_u16); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, + dot11MeshHWMPconfirmationInterval, mask, + NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL, + nla_get_u16); if (mask_out) *mask_out = mask; @@ -3666,6 +3987,11 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) cfg80211_regdomain->dfs_region))) goto nla_put_failure; + if (reg_last_request_cell_base() && + nla_put_u32(msg, NL80211_ATTR_USER_REG_HINT_TYPE, + NL80211_USER_REG_HINT_CELL_BASE)) + goto nla_put_failure; + nl_reg_rules = nla_nest_start(msg, NL80211_ATTR_REG_RULES); if (!nl_reg_rules) goto nla_put_failure; @@ -3831,7 +4157,7 @@ static int validate_scan_freqs(struct nlattr *freqs) static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; - struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = info->user_ptr[1]; struct cfg80211_scan_request *request; struct nlattr *attr; struct wiphy *wiphy; @@ -3991,15 +4317,16 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) request->no_cck = nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]); - request->dev = dev; + request->wdev = wdev; request->wiphy = &rdev->wiphy; rdev->scan_req = request; - err = rdev->ops->scan(&rdev->wiphy, dev, request); + err = rdev->ops->scan(&rdev->wiphy, request); if (!err) { - nl80211_send_scan_start(rdev, dev); - dev_hold(dev); + nl80211_send_scan_start(rdev, wdev); + if (wdev->netdev) + dev_hold(wdev->netdev); } else { out_free: rdev->scan_req = NULL; @@ -4185,12 +4512,12 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH], tmp) { - struct nlattr *ssid; + struct nlattr *ssid, *rssi; nla_parse(tb, NL80211_SCHED_SCAN_MATCH_ATTR_MAX, nla_data(attr), nla_len(attr), nl80211_match_policy); - ssid = tb[NL80211_ATTR_SCHED_SCAN_MATCH_SSID]; + ssid = tb[NL80211_SCHED_SCAN_MATCH_ATTR_SSID]; if (ssid) { if (nla_len(ssid) > IEEE80211_MAX_SSID_LEN) { err = -EINVAL; @@ -4201,6 +4528,12 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, request->match_sets[i].ssid.ssid_len = nla_len(ssid); } + rssi = tb[NL80211_SCHED_SCAN_MATCH_ATTR_RSSI]; + if (rssi) + request->rssi_thold = nla_get_u32(rssi); + else + request->rssi_thold = + NL80211_SCAN_RSSI_THOLD_OFF; i++; } } @@ -5058,21 +5391,18 @@ static int nl80211_testmode_dump(struct sk_buff *skb, nl80211_policy); if (err) return err; - if (nl80211_fam.attrbuf[NL80211_ATTR_WIPHY]) { - phy_idx = nla_get_u32( - nl80211_fam.attrbuf[NL80211_ATTR_WIPHY]); - } else { - struct net_device *netdev; - err = get_rdev_dev_by_ifindex(sock_net(skb->sk), - nl80211_fam.attrbuf, - &rdev, &netdev); - if (err) - return err; - dev_put(netdev); - phy_idx = rdev->wiphy_idx; - cfg80211_unlock_rdev(rdev); + mutex_lock(&cfg80211_mutex); + rdev = __cfg80211_rdev_from_attrs(sock_net(skb->sk), + nl80211_fam.attrbuf); + if (IS_ERR(rdev)) { + mutex_unlock(&cfg80211_mutex); + return PTR_ERR(rdev); } + phy_idx = rdev->wiphy_idx; + rdev = NULL; + mutex_unlock(&cfg80211_mutex); + if (nl80211_fam.attrbuf[NL80211_ATTR_TESTDATA]) cb->args[1] = (long)nl80211_fam.attrbuf[NL80211_ATTR_TESTDATA]; @@ -5474,7 +5804,7 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; - struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = info->user_ptr[1]; struct ieee80211_channel *chan; struct sk_buff *msg; void *hdr; @@ -5489,18 +5819,18 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, duration = nla_get_u32(info->attrs[NL80211_ATTR_DURATION]); + if (!rdev->ops->remain_on_channel || + !(rdev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL)) + return -EOPNOTSUPP; + /* - * We should be on that channel for at least one jiffie, - * and more than 5 seconds seems excessive. + * We should be on that channel for at least a minimum amount of + * time (10ms) but no longer than the driver supports. */ - if (!duration || !msecs_to_jiffies(duration) || + if (duration < NL80211_MIN_REMAIN_ON_CHANNEL_TIME || duration > rdev->wiphy.max_remain_on_channel_duration) return -EINVAL; - if (!rdev->ops->remain_on_channel || - !(rdev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL)) - return -EOPNOTSUPP; - if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] && !nl80211_valid_channel_type(info, &channel_type)) return -EINVAL; @@ -5522,7 +5852,7 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, goto free_msg; } - err = rdev->ops->remain_on_channel(&rdev->wiphy, dev, chan, + err = rdev->ops->remain_on_channel(&rdev->wiphy, wdev, chan, channel_type, duration, &cookie); if (err) @@ -5546,7 +5876,7 @@ static int nl80211_cancel_remain_on_channel(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; - struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = info->user_ptr[1]; u64 cookie; if (!info->attrs[NL80211_ATTR_COOKIE]) @@ -5557,7 +5887,7 @@ static int nl80211_cancel_remain_on_channel(struct sk_buff *skb, cookie = nla_get_u64(info->attrs[NL80211_ATTR_COOKIE]); - return rdev->ops->cancel_remain_on_channel(&rdev->wiphy, dev, cookie); + return rdev->ops->cancel_remain_on_channel(&rdev->wiphy, wdev, cookie); } static u32 rateset_to_mask(struct ieee80211_supported_band *sband, @@ -5706,7 +6036,7 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; - struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = info->user_ptr[1]; u16 frame_type = IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION; if (!info->attrs[NL80211_ATTR_FRAME_MATCH]) @@ -5715,21 +6045,24 @@ static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_FRAME_TYPE]) frame_type = nla_get_u16(info->attrs[NL80211_ATTR_FRAME_TYPE]); - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP_VLAN && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + switch (wdev->iftype) { + case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_P2P_CLIENT: + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_MESH_POINT: + case NL80211_IFTYPE_P2P_GO: + break; + default: return -EOPNOTSUPP; + } /* not much point in registering if we can't reply */ if (!rdev->ops->mgmt_tx) return -EOPNOTSUPP; - return cfg80211_mlme_register_mgmt(dev->ieee80211_ptr, info->snd_pid, - frame_type, + return cfg80211_mlme_register_mgmt(wdev, info->snd_pid, frame_type, nla_data(info->attrs[NL80211_ATTR_FRAME_MATCH]), nla_len(info->attrs[NL80211_ATTR_FRAME_MATCH])); } @@ -5737,7 +6070,7 @@ static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; - struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = info->user_ptr[1]; struct ieee80211_channel *chan; enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; bool channel_type_valid = false; @@ -5758,19 +6091,32 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->mgmt_tx) return -EOPNOTSUPP; - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP_VLAN && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + switch (wdev->iftype) { + case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_P2P_CLIENT: + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_MESH_POINT: + case NL80211_IFTYPE_P2P_GO: + break; + default: return -EOPNOTSUPP; + } if (info->attrs[NL80211_ATTR_DURATION]) { if (!(rdev->wiphy.flags & WIPHY_FLAG_OFFCHAN_TX)) return -EINVAL; wait = nla_get_u32(info->attrs[NL80211_ATTR_DURATION]); + + /* + * We should wait on the channel for at least a minimum amount + * of time (10ms) but no longer than the driver supports. + */ + if (wait < NL80211_MIN_REMAIN_ON_CHANNEL_TIME || + wait > rdev->wiphy.max_remain_on_channel_duration) + return -EINVAL; + } if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) { @@ -5805,7 +6151,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) } } - err = cfg80211_mlme_mgmt_tx(rdev, dev, chan, offchan, channel_type, + err = cfg80211_mlme_mgmt_tx(rdev, wdev, chan, offchan, channel_type, channel_type_valid, wait, nla_data(info->attrs[NL80211_ATTR_FRAME]), nla_len(info->attrs[NL80211_ATTR_FRAME]), @@ -5833,7 +6179,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) static int nl80211_tx_mgmt_cancel_wait(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; - struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = info->user_ptr[1]; u64 cookie; if (!info->attrs[NL80211_ATTR_COOKIE]) @@ -5842,17 +6188,21 @@ static int nl80211_tx_mgmt_cancel_wait(struct sk_buff *skb, struct genl_info *in if (!rdev->ops->mgmt_tx_cancel_wait) return -EOPNOTSUPP; - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP_VLAN && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + switch (wdev->iftype) { + case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_P2P_CLIENT: + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_P2P_GO: + break; + default: return -EOPNOTSUPP; + } cookie = nla_get_u64(info->attrs[NL80211_ATTR_COOKIE]); - return rdev->ops->mgmt_tx_cancel_wait(&rdev->wiphy, dev, cookie); + return rdev->ops->mgmt_tx_cancel_wait(&rdev->wiphy, wdev, cookie); } static int nl80211_set_power_save(struct sk_buff *skb, struct genl_info *info) @@ -5938,8 +6288,35 @@ nl80211_attr_cqm_policy[NL80211_ATTR_CQM_MAX + 1] __read_mostly = { [NL80211_ATTR_CQM_RSSI_THOLD] = { .type = NLA_U32 }, [NL80211_ATTR_CQM_RSSI_HYST] = { .type = NLA_U32 }, [NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT] = { .type = NLA_U32 }, + [NL80211_ATTR_CQM_TXE_RATE] = { .type = NLA_U32 }, + [NL80211_ATTR_CQM_TXE_PKTS] = { .type = NLA_U32 }, + [NL80211_ATTR_CQM_TXE_INTVL] = { .type = NLA_U32 }, }; +static int nl80211_set_cqm_txe(struct genl_info *info, + u32 rate, u32 pkts, u32 intvl) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct wireless_dev *wdev; + struct net_device *dev = info->user_ptr[1]; + + if ((rate < 0 || rate > 100) || + (intvl < 0 || intvl > NL80211_CQM_TXE_MAX_INTVL)) + return -EINVAL; + + wdev = dev->ieee80211_ptr; + + if (!rdev->ops->set_cqm_txe_config) + return -EOPNOTSUPP; + + if (wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; + + return rdev->ops->set_cqm_txe_config(wdev->wiphy, dev, + rate, pkts, intvl); +} + static int nl80211_set_cqm_rssi(struct genl_info *info, s32 threshold, u32 hysteresis) { @@ -5987,6 +6364,14 @@ static int nl80211_set_cqm(struct sk_buff *skb, struct genl_info *info) threshold = nla_get_u32(attrs[NL80211_ATTR_CQM_RSSI_THOLD]); hysteresis = nla_get_u32(attrs[NL80211_ATTR_CQM_RSSI_HYST]); err = nl80211_set_cqm_rssi(info, threshold, hysteresis); + } else if (attrs[NL80211_ATTR_CQM_TXE_RATE] && + attrs[NL80211_ATTR_CQM_TXE_PKTS] && + attrs[NL80211_ATTR_CQM_TXE_INTVL]) { + u32 rate, pkts, intvl; + rate = nla_get_u32(attrs[NL80211_ATTR_CQM_TXE_RATE]); + pkts = nla_get_u32(attrs[NL80211_ATTR_CQM_TXE_PKTS]); + intvl = nla_get_u32(attrs[NL80211_ATTR_CQM_TXE_INTVL]); + err = nl80211_set_cqm_txe(info, rate, pkts, intvl); } else err = -EINVAL; @@ -6032,6 +6417,24 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) return err; } + if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { + enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; + + if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] && + !nl80211_valid_channel_type(info, &channel_type)) + return -EINVAL; + + setup.channel = rdev_freq_to_chan(rdev, + nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]), + channel_type); + if (!setup.channel) + return -EINVAL; + setup.channel_type = channel_type; + } else { + /* cfg80211_join_mesh() will sort it out */ + setup.channel = NULL; + } + return cfg80211_join_mesh(rdev, dev, &setup, &cfg); } @@ -6043,6 +6446,7 @@ static int nl80211_leave_mesh(struct sk_buff *skb, struct genl_info *info) return cfg80211_leave_mesh(rdev, dev); } +#ifdef CONFIG_PM static int nl80211_get_wowlan(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -6124,8 +6528,8 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct nlattr *tb[NUM_NL80211_WOWLAN_TRIG]; - struct cfg80211_wowlan no_triggers = {}; struct cfg80211_wowlan new_triggers = {}; + struct cfg80211_wowlan *ntrig; struct wiphy_wowlan_support *wowlan = &rdev->wiphy.wowlan; int err, i; bool prev_enabled = rdev->wowlan; @@ -6133,8 +6537,11 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) if (!rdev->wiphy.wowlan.flags && !rdev->wiphy.wowlan.n_patterns) return -EOPNOTSUPP; - if (!info->attrs[NL80211_ATTR_WOWLAN_TRIGGERS]) - goto no_triggers; + if (!info->attrs[NL80211_ATTR_WOWLAN_TRIGGERS]) { + cfg80211_rdev_free_wowlan(rdev); + rdev->wowlan = NULL; + goto set_wakeup; + } err = nla_parse(tb, MAX_NL80211_WOWLAN_TRIG, nla_data(info->attrs[NL80211_ATTR_WOWLAN_TRIGGERS]), @@ -6245,22 +6652,15 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) } } - if (memcmp(&new_triggers, &no_triggers, sizeof(new_triggers))) { - struct cfg80211_wowlan *ntrig; - ntrig = kmemdup(&new_triggers, sizeof(new_triggers), - GFP_KERNEL); - if (!ntrig) { - err = -ENOMEM; - goto error; - } - cfg80211_rdev_free_wowlan(rdev); - rdev->wowlan = ntrig; - } else { - no_triggers: - cfg80211_rdev_free_wowlan(rdev); - rdev->wowlan = NULL; + ntrig = kmemdup(&new_triggers, sizeof(new_triggers), GFP_KERNEL); + if (!ntrig) { + err = -ENOMEM; + goto error; } + cfg80211_rdev_free_wowlan(rdev); + rdev->wowlan = ntrig; + set_wakeup: if (rdev->ops->set_wakeup && prev_enabled != !!rdev->wowlan) rdev->ops->set_wakeup(&rdev->wiphy, rdev->wowlan); @@ -6271,6 +6671,7 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) kfree(new_triggers.patterns); return err; } +#endif static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info) { @@ -6415,44 +6816,75 @@ static int nl80211_register_beacons(struct sk_buff *skb, struct genl_info *info) #define NL80211_FLAG_CHECK_NETDEV_UP 0x08 #define NL80211_FLAG_NEED_NETDEV_UP (NL80211_FLAG_NEED_NETDEV |\ NL80211_FLAG_CHECK_NETDEV_UP) +#define NL80211_FLAG_NEED_WDEV 0x10 +/* If a netdev is associated, it must be UP */ +#define NL80211_FLAG_NEED_WDEV_UP (NL80211_FLAG_NEED_WDEV |\ + NL80211_FLAG_CHECK_NETDEV_UP) static int nl80211_pre_doit(struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev; + struct wireless_dev *wdev; struct net_device *dev; - int err; bool rtnl = ops->internal_flags & NL80211_FLAG_NEED_RTNL; if (rtnl) rtnl_lock(); if (ops->internal_flags & NL80211_FLAG_NEED_WIPHY) { - rdev = cfg80211_get_dev_from_info(info); + rdev = cfg80211_get_dev_from_info(genl_info_net(info), info); if (IS_ERR(rdev)) { if (rtnl) rtnl_unlock(); return PTR_ERR(rdev); } info->user_ptr[0] = rdev; - } else if (ops->internal_flags & NL80211_FLAG_NEED_NETDEV) { - err = get_rdev_dev_by_ifindex(genl_info_net(info), info->attrs, - &rdev, &dev); - if (err) { + } else if (ops->internal_flags & NL80211_FLAG_NEED_NETDEV || + ops->internal_flags & NL80211_FLAG_NEED_WDEV) { + mutex_lock(&cfg80211_mutex); + wdev = __cfg80211_wdev_from_attrs(genl_info_net(info), + info->attrs); + if (IS_ERR(wdev)) { + mutex_unlock(&cfg80211_mutex); if (rtnl) rtnl_unlock(); - return err; + return PTR_ERR(wdev); } - if (ops->internal_flags & NL80211_FLAG_CHECK_NETDEV_UP && - !netif_running(dev)) { - cfg80211_unlock_rdev(rdev); - dev_put(dev); - if (rtnl) - rtnl_unlock(); - return -ENETDOWN; + + dev = wdev->netdev; + rdev = wiphy_to_dev(wdev->wiphy); + + if (ops->internal_flags & NL80211_FLAG_NEED_NETDEV) { + if (!dev) { + mutex_unlock(&cfg80211_mutex); + if (rtnl) + rtnl_unlock(); + return -EINVAL; + } + + info->user_ptr[1] = dev; + } else { + info->user_ptr[1] = wdev; } + + if (dev) { + if (ops->internal_flags & NL80211_FLAG_CHECK_NETDEV_UP && + !netif_running(dev)) { + mutex_unlock(&cfg80211_mutex); + if (rtnl) + rtnl_unlock(); + return -ENETDOWN; + } + + dev_hold(dev); + } + + cfg80211_lock_rdev(rdev); + + mutex_unlock(&cfg80211_mutex); + info->user_ptr[0] = rdev; - info->user_ptr[1] = dev; } return 0; @@ -6463,8 +6895,16 @@ static void nl80211_post_doit(struct genl_ops *ops, struct sk_buff *skb, { if (info->user_ptr[0]) cfg80211_unlock_rdev(info->user_ptr[0]); - if (info->user_ptr[1]) - dev_put(info->user_ptr[1]); + if (info->user_ptr[1]) { + if (ops->internal_flags & NL80211_FLAG_NEED_WDEV) { + struct wireless_dev *wdev = info->user_ptr[1]; + + if (wdev->netdev) + dev_put(wdev->netdev); + } else { + dev_put(info->user_ptr[1]); + } + } if (ops->internal_flags & NL80211_FLAG_NEED_RTNL) rtnl_unlock(); } @@ -6491,7 +6931,7 @@ static struct genl_ops nl80211_ops[] = { .dumpit = nl80211_dump_interface, .policy = nl80211_policy, /* can be retrieved by unprivileged users */ - .internal_flags = NL80211_FLAG_NEED_NETDEV, + .internal_flags = NL80211_FLAG_NEED_WDEV, }, { .cmd = NL80211_CMD_SET_INTERFACE, @@ -6514,7 +6954,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_del_interface, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_WDEV | NL80211_FLAG_NEED_RTNL, }, { @@ -6685,7 +7125,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_trigger_scan, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6826,7 +7266,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_remain_on_channel, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6834,7 +7274,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_cancel_remain_on_channel, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6850,7 +7290,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_register_mgmt, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_WDEV | NL80211_FLAG_NEED_RTNL, }, { @@ -6858,7 +7298,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_tx_mgmt, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6866,7 +7306,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_tx_mgmt_cancel_wait, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6925,6 +7365,7 @@ static struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, +#ifdef CONFIG_PM { .cmd = NL80211_CMD_GET_WOWLAN, .doit = nl80211_get_wowlan, @@ -6941,6 +7382,7 @@ static struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_WIPHY | NL80211_FLAG_NEED_RTNL, }, +#endif { .cmd = NL80211_CMD_SET_REKEY_OFFLOAD, .doit = nl80211_set_rekey_data, @@ -7075,7 +7517,7 @@ static int nl80211_add_scan_req(struct sk_buff *msg, static int nl80211_send_scan_msg(struct sk_buff *msg, struct cfg80211_registered_device *rdev, - struct net_device *netdev, + struct wireless_dev *wdev, u32 pid, u32 seq, int flags, u32 cmd) { @@ -7086,7 +7528,9 @@ static int nl80211_send_scan_msg(struct sk_buff *msg, return -1; if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || - nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex)) + (wdev->netdev && nla_put_u32(msg, NL80211_ATTR_IFINDEX, + wdev->netdev->ifindex)) || + nla_put_u64(msg, NL80211_ATTR_WDEV, wdev_id(wdev))) goto nla_put_failure; /* ignore errors and send incomplete event anyway */ @@ -7123,15 +7567,15 @@ nl80211_send_sched_scan_msg(struct sk_buff *msg, } void nl80211_send_scan_start(struct cfg80211_registered_device *rdev, - struct net_device *netdev) + struct wireless_dev *wdev) { struct sk_buff *msg; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; - if (nl80211_send_scan_msg(msg, rdev, netdev, 0, 0, 0, + if (nl80211_send_scan_msg(msg, rdev, wdev, 0, 0, 0, NL80211_CMD_TRIGGER_SCAN) < 0) { nlmsg_free(msg); return; @@ -7142,7 +7586,7 @@ void nl80211_send_scan_start(struct cfg80211_registered_device *rdev, } void nl80211_send_scan_done(struct cfg80211_registered_device *rdev, - struct net_device *netdev) + struct wireless_dev *wdev) { struct sk_buff *msg; @@ -7150,7 +7594,7 @@ void nl80211_send_scan_done(struct cfg80211_registered_device *rdev, if (!msg) return; - if (nl80211_send_scan_msg(msg, rdev, netdev, 0, 0, 0, + if (nl80211_send_scan_msg(msg, rdev, wdev, 0, 0, 0, NL80211_CMD_NEW_SCAN_RESULTS) < 0) { nlmsg_free(msg); return; @@ -7161,7 +7605,7 @@ void nl80211_send_scan_done(struct cfg80211_registered_device *rdev, } void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev, - struct net_device *netdev) + struct wireless_dev *wdev) { struct sk_buff *msg; @@ -7169,7 +7613,7 @@ void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev, if (!msg) return; - if (nl80211_send_scan_msg(msg, rdev, netdev, 0, 0, 0, + if (nl80211_send_scan_msg(msg, rdev, wdev, 0, 0, 0, NL80211_CMD_SCAN_ABORTED) < 0) { nlmsg_free(msg); return; @@ -7203,7 +7647,7 @@ void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev, { struct sk_buff *msg; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; @@ -7419,7 +7863,7 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) return; @@ -7459,7 +7903,7 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) return; @@ -7497,7 +7941,7 @@ void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; @@ -7692,7 +8136,7 @@ nla_put_failure: static void nl80211_send_remain_on_chan_event( int cmd, struct cfg80211_registered_device *rdev, - struct net_device *netdev, u64 cookie, + struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type, unsigned int duration, gfp_t gfp) @@ -7711,7 +8155,9 @@ static void nl80211_send_remain_on_chan_event( } if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || - nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + (wdev->netdev && nla_put_u32(msg, NL80211_ATTR_IFINDEX, + wdev->netdev->ifindex)) || + nla_put_u64(msg, NL80211_ATTR_WDEV, wdev_id(wdev)) || nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, chan->center_freq) || nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE, channel_type) || nla_put_u64(msg, NL80211_ATTR_COOKIE, cookie)) @@ -7733,23 +8179,24 @@ static void nl80211_send_remain_on_chan_event( } void nl80211_send_remain_on_channel(struct cfg80211_registered_device *rdev, - struct net_device *netdev, u64 cookie, + struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type, unsigned int duration, gfp_t gfp) { nl80211_send_remain_on_chan_event(NL80211_CMD_REMAIN_ON_CHANNEL, - rdev, netdev, cookie, chan, + rdev, wdev, cookie, chan, channel_type, duration, gfp); } void nl80211_send_remain_on_channel_cancel( - struct cfg80211_registered_device *rdev, struct net_device *netdev, + struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type, gfp_t gfp) { nl80211_send_remain_on_chan_event(NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL, - rdev, netdev, cookie, chan, + rdev, wdev, cookie, chan, channel_type, 0, gfp); } @@ -7759,7 +8206,7 @@ void nl80211_send_sta_event(struct cfg80211_registered_device *rdev, { struct sk_buff *msg; - msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) return; @@ -7780,7 +8227,7 @@ void nl80211_send_sta_del_event(struct cfg80211_registered_device *rdev, struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) return; @@ -7863,10 +8310,11 @@ bool nl80211_unexpected_4addr_frame(struct net_device *dev, } int nl80211_send_mgmt(struct cfg80211_registered_device *rdev, - struct net_device *netdev, u32 nlpid, + struct wireless_dev *wdev, u32 nlpid, int freq, int sig_dbm, const u8 *buf, size_t len, gfp_t gfp) { + struct net_device *netdev = wdev->netdev; struct sk_buff *msg; void *hdr; @@ -7881,7 +8329,8 @@ int nl80211_send_mgmt(struct cfg80211_registered_device *rdev, } if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || - nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + (netdev && nla_put_u32(msg, NL80211_ATTR_IFINDEX, + netdev->ifindex)) || nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, freq) || (sig_dbm && nla_put_u32(msg, NL80211_ATTR_RX_SIGNAL_DBM, sig_dbm)) || @@ -7899,10 +8348,11 @@ int nl80211_send_mgmt(struct cfg80211_registered_device *rdev, } void nl80211_send_mgmt_tx_status(struct cfg80211_registered_device *rdev, - struct net_device *netdev, u64 cookie, + struct wireless_dev *wdev, u64 cookie, const u8 *buf, size_t len, bool ack, gfp_t gfp) { + struct net_device *netdev = wdev->netdev; struct sk_buff *msg; void *hdr; @@ -7917,7 +8367,8 @@ void nl80211_send_mgmt_tx_status(struct cfg80211_registered_device *rdev, } if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || - nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + (netdev && nla_put_u32(msg, NL80211_ATTR_IFINDEX, + netdev->ifindex)) || nla_put(msg, NL80211_ATTR_FRAME, len, buf) || nla_put_u64(msg, NL80211_ATTR_COOKIE, cookie) || (ack && nla_put_flag(msg, NL80211_ATTR_ACK))) @@ -7943,7 +8394,7 @@ nl80211_send_cqm_rssi_notify(struct cfg80211_registered_device *rdev, struct nlattr *pinfoattr; void *hdr; - msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) return; @@ -7986,7 +8437,7 @@ void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev, struct nlattr *rekey_attr; void *hdr; - msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) return; @@ -8030,7 +8481,7 @@ void nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev, struct nlattr *attr; void *hdr; - msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) return; @@ -8074,7 +8525,7 @@ void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) return; @@ -8101,6 +8552,56 @@ void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, } void +nl80211_send_cqm_txe_notify(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *peer, + u32 num_packets, u32 rate, u32 intvl, gfp_t gfp) +{ + struct sk_buff *msg; + struct nlattr *pinfoattr; + void *hdr; + + msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_NOTIFY_CQM); + if (!hdr) { + nlmsg_free(msg); + return; + } + + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, peer)) + goto nla_put_failure; + + pinfoattr = nla_nest_start(msg, NL80211_ATTR_CQM); + if (!pinfoattr) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_PKTS, num_packets)) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_RATE, rate)) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_INTVL, intvl)) + goto nla_put_failure; + + nla_nest_end(msg, pinfoattr); + + genlmsg_end(msg, hdr); + + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} + +void nl80211_send_cqm_pktloss_notify(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *peer, u32 num_packets, gfp_t gfp) @@ -8109,7 +8610,7 @@ nl80211_send_cqm_pktloss_notify(struct cfg80211_registered_device *rdev, struct nlattr *pinfoattr; void *hdr; - msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) return; @@ -8153,7 +8654,7 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr, void *hdr; int err; - msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) return; @@ -8241,7 +8742,7 @@ static int nl80211_netlink_notify(struct notifier_block * nb, rcu_read_lock(); list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list) { - list_for_each_entry_rcu(wdev, &rdev->netdev_list, list) + list_for_each_entry_rcu(wdev, &rdev->wdev_list, list) cfg80211_mlme_unregister_socket(wdev, notify->pid); if (rdev->ap_beacons_nlpid == notify->pid) rdev->ap_beacons_nlpid = 0; diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 01a1122c3b3..9f2616fffb4 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -7,11 +7,11 @@ int nl80211_init(void); void nl80211_exit(void); void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev); void nl80211_send_scan_start(struct cfg80211_registered_device *rdev, - struct net_device *netdev); + struct wireless_dev *wdev); void nl80211_send_scan_done(struct cfg80211_registered_device *rdev, - struct net_device *netdev); + struct wireless_dev *wdev); void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev, - struct net_device *netdev); + struct wireless_dev *wdev); void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev, struct net_device *netdev, u32 cmd); void nl80211_send_sched_scan_results(struct cfg80211_registered_device *rdev, @@ -74,13 +74,13 @@ void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev, gfp_t gfp); void nl80211_send_remain_on_channel(struct cfg80211_registered_device *rdev, - struct net_device *netdev, - u64 cookie, + struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type, unsigned int duration, gfp_t gfp); void nl80211_send_remain_on_channel_cancel( - struct cfg80211_registered_device *rdev, struct net_device *netdev, + struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type, gfp_t gfp); @@ -92,11 +92,11 @@ void nl80211_send_sta_del_event(struct cfg80211_registered_device *rdev, gfp_t gfp); int nl80211_send_mgmt(struct cfg80211_registered_device *rdev, - struct net_device *netdev, u32 nlpid, + struct wireless_dev *wdev, u32 nlpid, int freq, int sig_dbm, const u8 *buf, size_t len, gfp_t gfp); void nl80211_send_mgmt_tx_status(struct cfg80211_registered_device *rdev, - struct net_device *netdev, u64 cookie, + struct wireless_dev *wdev, u64 cookie, const u8 *buf, size_t len, bool ack, gfp_t gfp); @@ -110,6 +110,11 @@ nl80211_send_cqm_pktloss_notify(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *peer, u32 num_packets, gfp_t gfp); +void +nl80211_send_cqm_txe_notify(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *peer, + u32 num_packets, u32 rate, u32 intvl, gfp_t gfp); + void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *bssid, const u8 *replay_ctr, gfp_t gfp); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index baf5704740e..2ded3c7fad0 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -97,9 +97,16 @@ const struct ieee80211_regdomain *cfg80211_regdomain; * - cfg80211_world_regdom * - cfg80211_regdom * - last_request + * - reg_num_devs_support_basehint */ static DEFINE_MUTEX(reg_mutex); +/* + * Number of devices that registered to the core + * that support cellular base station regulatory hints + */ +static int reg_num_devs_support_basehint; + static inline void assert_reg_lock(void) { lockdep_assert_held(®_mutex); @@ -129,7 +136,7 @@ static DECLARE_DELAYED_WORK(reg_timeout, reg_timeout_work); /* We keep a static world regulatory domain in case of the absence of CRDA */ static const struct ieee80211_regdomain world_regdom = { - .n_reg_rules = 5, + .n_reg_rules = 6, .alpha2 = "00", .reg_rules = { /* IEEE 802.11b/g, channels 1..11 */ @@ -156,6 +163,9 @@ static const struct ieee80211_regdomain world_regdom = { REG_RULE(5745-10, 5825+10, 40, 6, 20, NL80211_RRF_PASSIVE_SCAN | NL80211_RRF_NO_IBSS), + + /* IEEE 802.11ad (60gHz), channels 1..3 */ + REG_RULE(56160+2160*1-1080, 56160+2160*3+1080, 2160, 0, 0, 0), } }; @@ -670,6 +680,8 @@ static u32 map_regdom_flags(u32 rd_flags) channel_flags |= IEEE80211_CHAN_NO_IBSS; if (rd_flags & NL80211_RRF_DFS) channel_flags |= IEEE80211_CHAN_RADAR; + if (rd_flags & NL80211_RRF_NO_OFDM) + channel_flags |= IEEE80211_CHAN_NO_OFDM; return channel_flags; } @@ -891,7 +903,21 @@ static void handle_channel(struct wiphy *wiphy, chan->max_antenna_gain = min(chan->orig_mag, (int) MBI_TO_DBI(power_rule->max_antenna_gain)); chan->max_reg_power = (int) MBM_TO_DBM(power_rule->max_eirp); - chan->max_power = min(chan->max_power, chan->max_reg_power); + if (chan->orig_mpwr) { + /* + * Devices that have their own custom regulatory domain + * but also use WIPHY_FLAG_STRICT_REGULATORY will follow the + * passed country IE power settings. + */ + if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && + wiphy->flags & WIPHY_FLAG_CUSTOM_REGULATORY && + wiphy->flags & WIPHY_FLAG_STRICT_REGULATORY) + chan->max_power = chan->max_reg_power; + else + chan->max_power = min(chan->orig_mpwr, + chan->max_reg_power); + } else + chan->max_power = chan->max_reg_power; } static void handle_band(struct wiphy *wiphy, @@ -908,6 +934,61 @@ static void handle_band(struct wiphy *wiphy, handle_channel(wiphy, initiator, band, i); } +static bool reg_request_cell_base(struct regulatory_request *request) +{ + if (request->initiator != NL80211_REGDOM_SET_BY_USER) + return false; + if (request->user_reg_hint_type != NL80211_USER_REG_HINT_CELL_BASE) + return false; + return true; +} + +bool reg_last_request_cell_base(void) +{ + bool val; + assert_cfg80211_lock(); + + mutex_lock(®_mutex); + val = reg_request_cell_base(last_request); + mutex_unlock(®_mutex); + return val; +} + +#ifdef CONFIG_CFG80211_CERTIFICATION_ONUS + +/* Core specific check */ +static int reg_ignore_cell_hint(struct regulatory_request *pending_request) +{ + if (!reg_num_devs_support_basehint) + return -EOPNOTSUPP; + + if (reg_request_cell_base(last_request)) { + if (!regdom_changes(pending_request->alpha2)) + return -EALREADY; + return 0; + } + return 0; +} + +/* Device specific check */ +static bool reg_dev_ignore_cell_hint(struct wiphy *wiphy) +{ + if (!(wiphy->features & NL80211_FEATURE_CELL_BASE_REG_HINTS)) + return true; + return false; +} +#else +static int reg_ignore_cell_hint(struct regulatory_request *pending_request) +{ + return -EOPNOTSUPP; +} +static int reg_dev_ignore_cell_hint(struct wiphy *wiphy) +{ + return true; +} +#endif + + static bool ignore_reg_update(struct wiphy *wiphy, enum nl80211_reg_initiator initiator) { @@ -941,6 +1022,9 @@ static bool ignore_reg_update(struct wiphy *wiphy, return true; } + if (reg_request_cell_base(last_request)) + return reg_dev_ignore_cell_hint(wiphy); + return false; } @@ -1166,14 +1250,6 @@ static void wiphy_update_regulatory(struct wiphy *wiphy, wiphy->reg_notifier(wiphy, last_request); } -void regulatory_update(struct wiphy *wiphy, - enum nl80211_reg_initiator setby) -{ - mutex_lock(®_mutex); - wiphy_update_regulatory(wiphy, setby); - mutex_unlock(®_mutex); -} - static void update_all_wiphy_regulatory(enum nl80211_reg_initiator initiator) { struct cfg80211_registered_device *rdev; @@ -1304,6 +1380,13 @@ static int ignore_request(struct wiphy *wiphy, return 0; case NL80211_REGDOM_SET_BY_COUNTRY_IE: + if (reg_request_cell_base(last_request)) { + /* Trust a Cell base station over the AP's country IE */ + if (regdom_changes(pending_request->alpha2)) + return -EOPNOTSUPP; + return -EALREADY; + } + last_wiphy = wiphy_idx_to_wiphy(last_request->wiphy_idx); if (unlikely(!is_an_alpha2(pending_request->alpha2))) @@ -1348,6 +1431,12 @@ static int ignore_request(struct wiphy *wiphy, return REG_INTERSECT; case NL80211_REGDOM_SET_BY_USER: + if (reg_request_cell_base(pending_request)) + return reg_ignore_cell_hint(pending_request); + + if (reg_request_cell_base(last_request)) + return -EOPNOTSUPP; + if (last_request->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE) return REG_INTERSECT; /* @@ -1637,7 +1726,8 @@ static int regulatory_hint_core(const char *alpha2) } /* User hints */ -int regulatory_hint_user(const char *alpha2) +int regulatory_hint_user(const char *alpha2, + enum nl80211_user_reg_hint_type user_reg_hint_type) { struct regulatory_request *request; @@ -1651,6 +1741,7 @@ int regulatory_hint_user(const char *alpha2) request->alpha2[0] = alpha2[0]; request->alpha2[1] = alpha2[1]; request->initiator = NL80211_REGDOM_SET_BY_USER; + request->user_reg_hint_type = user_reg_hint_type; queue_regulatory_request(request); @@ -1810,6 +1901,7 @@ static void restore_custom_reg_settings(struct wiphy *wiphy) chan->flags = chan->orig_flags; chan->max_antenna_gain = chan->orig_mag; chan->max_power = chan->orig_mpwr; + chan->beacon_found = false; } } } @@ -1903,7 +1995,7 @@ static void restore_regulatory_settings(bool reset_user) * settings, user regulatory settings takes precedence. */ if (is_an_alpha2(alpha2)) - regulatory_hint_user(user_alpha2); + regulatory_hint_user(user_alpha2, NL80211_USER_REG_HINT_USER); if (list_empty(&tmp_reg_req_list)) return; @@ -2078,9 +2170,16 @@ static void print_regdomain(const struct ieee80211_regdomain *rd) else { if (is_unknown_alpha2(rd->alpha2)) pr_info("Regulatory domain changed to driver built-in settings (unknown country)\n"); - else - pr_info("Regulatory domain changed to country: %c%c\n", - rd->alpha2[0], rd->alpha2[1]); + else { + if (reg_request_cell_base(last_request)) + pr_info("Regulatory domain changed " + "to country: %c%c by Cell Station\n", + rd->alpha2[0], rd->alpha2[1]); + else + pr_info("Regulatory domain changed " + "to country: %c%c\n", + rd->alpha2[0], rd->alpha2[1]); + } } print_dfs_region(rd->dfs_region); print_rd_rules(rd); @@ -2125,7 +2224,7 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) * checking if the alpha2 changes if CRDA was already called */ if (!regdom_changes(rd->alpha2)) - return -EINVAL; + return -EALREADY; } /* @@ -2245,6 +2344,9 @@ int set_regdom(const struct ieee80211_regdomain *rd) /* Note that this doesn't update the wiphys, this is done below */ r = __set_regdom(rd); if (r) { + if (r == -EALREADY) + reg_set_request_processed(); + kfree(rd); mutex_unlock(®_mutex); return r; @@ -2287,8 +2389,22 @@ int reg_device_uevent(struct device *dev, struct kobj_uevent_env *env) } #endif /* CONFIG_HOTPLUG */ +void wiphy_regulatory_register(struct wiphy *wiphy) +{ + assert_cfg80211_lock(); + + mutex_lock(®_mutex); + + if (!reg_dev_ignore_cell_hint(wiphy)) + reg_num_devs_support_basehint++; + + wiphy_update_regulatory(wiphy, NL80211_REGDOM_SET_BY_CORE); + + mutex_unlock(®_mutex); +} + /* Caller must hold cfg80211_mutex */ -void reg_device_remove(struct wiphy *wiphy) +void wiphy_regulatory_deregister(struct wiphy *wiphy) { struct wiphy *request_wiphy = NULL; @@ -2296,6 +2412,9 @@ void reg_device_remove(struct wiphy *wiphy) mutex_lock(®_mutex); + if (!reg_dev_ignore_cell_hint(wiphy)) + reg_num_devs_support_basehint--; + kfree(wiphy->regd); if (last_request) @@ -2361,7 +2480,8 @@ int __init regulatory_init(void) * as a user hint. */ if (!is_world_regdom(ieee80211_regdom)) - regulatory_hint_user(ieee80211_regdom); + regulatory_hint_user(ieee80211_regdom, + NL80211_USER_REG_HINT_USER); return 0; } diff --git a/net/wireless/reg.h b/net/wireless/reg.h index e2aaaf525a2..f023c8a31c6 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -22,17 +22,19 @@ bool is_world_regdom(const char *alpha2); bool reg_is_valid_request(const char *alpha2); bool reg_supported_dfs_region(u8 dfs_region); -int regulatory_hint_user(const char *alpha2); +int regulatory_hint_user(const char *alpha2, + enum nl80211_user_reg_hint_type user_reg_hint_type); int reg_device_uevent(struct device *dev, struct kobj_uevent_env *env); -void reg_device_remove(struct wiphy *wiphy); +void wiphy_regulatory_register(struct wiphy *wiphy); +void wiphy_regulatory_deregister(struct wiphy *wiphy); int __init regulatory_init(void); void regulatory_exit(void); int set_regdom(const struct ieee80211_regdomain *rd); -void regulatory_update(struct wiphy *wiphy, enum nl80211_reg_initiator setby); +bool reg_last_request_cell_base(void); /** * regulatory_hint_found_beacon - hints a beacon was found on a channel diff --git a/net/wireless/scan.c b/net/wireless/scan.c index af2b1caa37f..848523a2b22 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -23,7 +23,7 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak) { struct cfg80211_scan_request *request; - struct net_device *dev; + struct wireless_dev *wdev; #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif @@ -35,29 +35,31 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak) if (!request) return; - dev = request->dev; + wdev = request->wdev; /* * This must be before sending the other events! * Otherwise, wpa_supplicant gets completely confused with * wext events. */ - cfg80211_sme_scan_done(dev); + if (wdev->netdev) + cfg80211_sme_scan_done(wdev->netdev); if (request->aborted) - nl80211_send_scan_aborted(rdev, dev); + nl80211_send_scan_aborted(rdev, wdev); else - nl80211_send_scan_done(rdev, dev); + nl80211_send_scan_done(rdev, wdev); #ifdef CONFIG_CFG80211_WEXT - if (!request->aborted) { + if (wdev->netdev && !request->aborted) { memset(&wrqu, 0, sizeof(wrqu)); - wireless_send_event(dev, SIOCGIWSCAN, &wrqu, NULL); + wireless_send_event(wdev->netdev, SIOCGIWSCAN, &wrqu, NULL); } #endif - dev_put(dev); + if (wdev->netdev) + dev_put(wdev->netdev); rdev->scan_req = NULL; @@ -955,7 +957,7 @@ int cfg80211_wext_siwscan(struct net_device *dev, } creq->wiphy = wiphy; - creq->dev = dev; + creq->wdev = dev->ieee80211_ptr; /* SSIDs come after channels */ creq->ssids = (void *)&creq->channels[n_channels]; creq->n_channels = n_channels; @@ -1024,12 +1026,12 @@ int cfg80211_wext_siwscan(struct net_device *dev, creq->rates[i] = (1 << wiphy->bands[i]->n_bitrates) - 1; rdev->scan_req = creq; - err = rdev->ops->scan(wiphy, dev, creq); + err = rdev->ops->scan(wiphy, creq); if (err) { rdev->scan_req = NULL; /* creq will be freed below */ } else { - nl80211_send_scan_start(rdev, dev); + nl80211_send_scan_start(rdev, dev->ieee80211_ptr); /* creq now owned by driver */ creq = NULL; dev_hold(dev); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index f7e937ff897..6f39cb80830 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -51,7 +51,7 @@ static bool cfg80211_is_all_idle(void) */ list_for_each_entry(rdev, &cfg80211_rdev_list, list) { cfg80211_lock_rdev(rdev); - list_for_each_entry(wdev, &rdev->netdev_list, list) { + list_for_each_entry(wdev, &rdev->wdev_list, list) { wdev_lock(wdev); if (wdev->sme_state != CFG80211_SME_IDLE) is_all_idle = false; @@ -136,15 +136,15 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev) wdev->conn->params.ssid_len); request->ssids[0].ssid_len = wdev->conn->params.ssid_len; - request->dev = wdev->netdev; + request->wdev = wdev; request->wiphy = &rdev->wiphy; rdev->scan_req = request; - err = rdev->ops->scan(wdev->wiphy, wdev->netdev, request); + err = rdev->ops->scan(wdev->wiphy, request); if (!err) { wdev->conn->state = CFG80211_CONN_SCANNING; - nl80211_send_scan_start(rdev, wdev->netdev); + nl80211_send_scan_start(rdev, wdev); dev_hold(wdev->netdev); } else { rdev->scan_req = NULL; @@ -221,7 +221,7 @@ void cfg80211_conn_work(struct work_struct *work) cfg80211_lock_rdev(rdev); mutex_lock(&rdev->devlist_mtx); - list_for_each_entry(wdev, &rdev->netdev_list, list) { + list_for_each_entry(wdev, &rdev->wdev_list, list) { wdev_lock(wdev); if (!netif_running(wdev->netdev)) { wdev_unlock(wdev); diff --git a/net/wireless/util.c b/net/wireless/util.c index 316cfd00914..994e2f0cc7a 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -35,19 +35,29 @@ int ieee80211_channel_to_frequency(int chan, enum ieee80211_band band) { /* see 802.11 17.3.8.3.2 and Annex J * there are overlapping channel numbers in 5GHz and 2GHz bands */ - if (band == IEEE80211_BAND_5GHZ) { - if (chan >= 182 && chan <= 196) - return 4000 + chan * 5; - else - return 5000 + chan * 5; - } else { /* IEEE80211_BAND_2GHZ */ + if (chan <= 0) + return 0; /* not supported */ + switch (band) { + case IEEE80211_BAND_2GHZ: if (chan == 14) return 2484; else if (chan < 14) return 2407 + chan * 5; + break; + case IEEE80211_BAND_5GHZ: + if (chan >= 182 && chan <= 196) + return 4000 + chan * 5; else - return 0; /* not supported */ + return 5000 + chan * 5; + break; + case IEEE80211_BAND_60GHZ: + if (chan < 5) + return 56160 + chan * 2160; + break; + default: + ; } + return 0; /* not supported */ } EXPORT_SYMBOL(ieee80211_channel_to_frequency); @@ -60,8 +70,12 @@ int ieee80211_frequency_to_channel(int freq) return (freq - 2407) / 5; else if (freq >= 4910 && freq <= 4980) return (freq - 4000) / 5; - else + else if (freq <= 45000) /* DMG band lower limit */ return (freq - 5000) / 5; + else if (freq >= 58320 && freq <= 64800) + return (freq - 56160) / 2160; + else + return 0; } EXPORT_SYMBOL(ieee80211_frequency_to_channel); @@ -137,6 +151,11 @@ static void set_mandatory_flags_band(struct ieee80211_supported_band *sband, } WARN_ON(want != 0 && want != 3 && want != 6); break; + case IEEE80211_BAND_60GHZ: + /* check for mandatory HT MCS 1..4 */ + WARN_ON(!sband->ht_cap.ht_supported); + WARN_ON((sband->ht_cap.mcs.rx_mask[0] & 0x1e) != 0x1e); + break; case IEEE80211_NUM_BANDS: WARN_ON(1); break; @@ -716,7 +735,7 @@ void cfg80211_upload_connect_keys(struct wireless_dev *wdev) wdev->connect_keys = NULL; } -static void cfg80211_process_wdev_events(struct wireless_dev *wdev) +void cfg80211_process_wdev_events(struct wireless_dev *wdev) { struct cfg80211_event *ev; unsigned long flags; @@ -774,7 +793,7 @@ void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev) mutex_lock(&rdev->devlist_mtx); - list_for_each_entry(wdev, &rdev->netdev_list, list) + list_for_each_entry(wdev, &rdev->wdev_list, list) cfg80211_process_wdev_events(wdev); mutex_unlock(&rdev->devlist_mtx); @@ -805,8 +824,10 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, return -EBUSY; if (ntype != otype && netif_running(dev)) { + mutex_lock(&rdev->devlist_mtx); err = cfg80211_can_change_interface(rdev, dev->ieee80211_ptr, ntype); + mutex_unlock(&rdev->devlist_mtx); if (err) return err; @@ -814,6 +835,9 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, dev->ieee80211_ptr->mesh_id_up_len = 0; switch (otype) { + case NL80211_IFTYPE_AP: + cfg80211_stop_ap(rdev, dev); + break; case NL80211_IFTYPE_ADHOC: cfg80211_leave_ibss(rdev, dev, false); break; @@ -868,15 +892,69 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, } } + if (!err && ntype != otype && netif_running(dev)) { + cfg80211_update_iface_num(rdev, ntype, 1); + cfg80211_update_iface_num(rdev, otype, -1); + } + return err; } -u16 cfg80211_calculate_bitrate(struct rate_info *rate) +static u32 cfg80211_calculate_bitrate_60g(struct rate_info *rate) +{ + static const u32 __mcs2bitrate[] = { + /* control PHY */ + [0] = 275, + /* SC PHY */ + [1] = 3850, + [2] = 7700, + [3] = 9625, + [4] = 11550, + [5] = 12512, /* 1251.25 mbps */ + [6] = 15400, + [7] = 19250, + [8] = 23100, + [9] = 25025, + [10] = 30800, + [11] = 38500, + [12] = 46200, + /* OFDM PHY */ + [13] = 6930, + [14] = 8662, /* 866.25 mbps */ + [15] = 13860, + [16] = 17325, + [17] = 20790, + [18] = 27720, + [19] = 34650, + [20] = 41580, + [21] = 45045, + [22] = 51975, + [23] = 62370, + [24] = 67568, /* 6756.75 mbps */ + /* LP-SC PHY */ + [25] = 6260, + [26] = 8340, + [27] = 11120, + [28] = 12510, + [29] = 16680, + [30] = 22240, + [31] = 25030, + }; + + if (WARN_ON_ONCE(rate->mcs >= ARRAY_SIZE(__mcs2bitrate))) + return 0; + + return __mcs2bitrate[rate->mcs]; +} + +u32 cfg80211_calculate_bitrate(struct rate_info *rate) { int modulation, streams, bitrate; if (!(rate->flags & RATE_INFO_FLAGS_MCS)) return rate->legacy; + if (rate->flags & RATE_INFO_FLAGS_60G) + return cfg80211_calculate_bitrate_60g(rate); /* the formula below does only work for MCS values smaller than 32 */ if (WARN_ON_ONCE(rate->mcs >= 32)) @@ -916,7 +994,7 @@ int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev, mutex_lock(&rdev->devlist_mtx); - list_for_each_entry(wdev, &rdev->netdev_list, list) { + list_for_each_entry(wdev, &rdev->wdev_list, list) { if (!wdev->beacon_interval) continue; if (wdev->beacon_interval != beacon_int) { @@ -930,28 +1008,49 @@ int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev, return res; } -int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev, - enum nl80211_iftype iftype) +int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + enum nl80211_iftype iftype, + struct ieee80211_channel *chan, + enum cfg80211_chan_mode chanmode) { struct wireless_dev *wdev_iter; u32 used_iftypes = BIT(iftype); int num[NUM_NL80211_IFTYPES]; + struct ieee80211_channel + *used_channels[CFG80211_MAX_NUM_DIFFERENT_CHANNELS]; + struct ieee80211_channel *ch; + enum cfg80211_chan_mode chmode; + int num_different_channels = 0; int total = 1; int i, j; ASSERT_RTNL(); + lockdep_assert_held(&rdev->devlist_mtx); /* Always allow software iftypes */ if (rdev->wiphy.software_iftypes & BIT(iftype)) return 0; memset(num, 0, sizeof(num)); + memset(used_channels, 0, sizeof(used_channels)); num[iftype] = 1; - mutex_lock(&rdev->devlist_mtx); - list_for_each_entry(wdev_iter, &rdev->netdev_list, list) { + switch (chanmode) { + case CHAN_MODE_UNDEFINED: + break; + case CHAN_MODE_SHARED: + WARN_ON(!chan); + used_channels[0] = chan; + num_different_channels++; + break; + case CHAN_MODE_EXCLUSIVE: + num_different_channels++; + break; + } + + list_for_each_entry(wdev_iter, &rdev->wdev_list, list) { if (wdev_iter == wdev) continue; if (!netif_running(wdev_iter->netdev)) @@ -960,11 +1059,42 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, if (rdev->wiphy.software_iftypes & BIT(wdev_iter->iftype)) continue; + /* + * We may be holding the "wdev" mutex, but now need to lock + * wdev_iter. This is OK because once we get here wdev_iter + * is not wdev (tested above), but we need to use the nested + * locking for lockdep. + */ + mutex_lock_nested(&wdev_iter->mtx, 1); + __acquire(wdev_iter->mtx); + cfg80211_get_chan_state(wdev_iter, &ch, &chmode); + wdev_unlock(wdev_iter); + + switch (chmode) { + case CHAN_MODE_UNDEFINED: + break; + case CHAN_MODE_SHARED: + for (i = 0; i < CFG80211_MAX_NUM_DIFFERENT_CHANNELS; i++) + if (!used_channels[i] || used_channels[i] == ch) + break; + + if (i == CFG80211_MAX_NUM_DIFFERENT_CHANNELS) + return -EBUSY; + + if (used_channels[i] == NULL) { + used_channels[i] = ch; + num_different_channels++; + } + break; + case CHAN_MODE_EXCLUSIVE: + num_different_channels++; + break; + } + num[wdev_iter->iftype]++; total++; used_iftypes |= BIT(wdev_iter->iftype); } - mutex_unlock(&rdev->devlist_mtx); if (total == 1) return 0; @@ -976,12 +1106,15 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, c = &rdev->wiphy.iface_combinations[i]; + if (total > c->max_interfaces) + continue; + if (num_different_channels > c->num_different_channels) + continue; + limits = kmemdup(c->limits, sizeof(limits[0]) * c->n_limits, GFP_KERNEL); if (!limits) return -ENOMEM; - if (total > c->max_interfaces) - goto cont; for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { if (rdev->wiphy.software_iftypes & BIT(iftype)) diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 6a6181a673c..494379eb464 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -796,7 +796,15 @@ static int cfg80211_wext_siwfreq(struct net_device *dev, case NL80211_IFTYPE_ADHOC: return cfg80211_ibss_wext_siwfreq(dev, info, wextfreq, extra); case NL80211_IFTYPE_MONITOR: - case NL80211_IFTYPE_WDS: + freq = cfg80211_wext_freq(wdev->wiphy, wextfreq); + if (freq < 0) + return freq; + if (freq == 0) + return -EINVAL; + mutex_lock(&rdev->devlist_mtx); + err = cfg80211_set_monitor_channel(rdev, freq, NL80211_CHAN_NO_HT); + mutex_unlock(&rdev->devlist_mtx); + return err; case NL80211_IFTYPE_MESH_POINT: freq = cfg80211_wext_freq(wdev->wiphy, wextfreq); if (freq < 0) @@ -804,9 +812,8 @@ static int cfg80211_wext_siwfreq(struct net_device *dev, if (freq == 0) return -EINVAL; mutex_lock(&rdev->devlist_mtx); - wdev_lock(wdev); - err = cfg80211_set_freq(rdev, wdev, freq, NL80211_CHAN_NO_HT); - wdev_unlock(wdev); + err = cfg80211_set_mesh_freq(rdev, wdev, freq, + NL80211_CHAN_NO_HT); mutex_unlock(&rdev->devlist_mtx); return err; default: @@ -832,18 +839,14 @@ static int cfg80211_wext_giwfreq(struct net_device *dev, if (!rdev->ops->get_channel) return -EINVAL; - chan = rdev->ops->get_channel(wdev->wiphy, &channel_type); + chan = rdev->ops->get_channel(wdev->wiphy, wdev, &channel_type); if (!chan) return -EINVAL; freq->m = chan->center_freq; freq->e = 6; return 0; default: - if (!wdev->channel) - return -EINVAL; - freq->m = wdev->channel->center_freq; - freq->e = 6; - return 0; + return -EINVAL; } } diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index 7decbd357d5..1f773f668d1 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -111,9 +111,15 @@ int cfg80211_mgd_wext_siwfreq(struct net_device *dev, wdev->wext.connect.channel = chan; - /* SSID is not set, we just want to switch channel */ + /* + * SSID is not set, we just want to switch monitor channel, + * this is really just backward compatibility, if the SSID + * is set then we use the channel to select the BSS to use + * to connect to instead. If we were connected on another + * channel we disconnected above and reconnect below. + */ if (chan && !wdev->wext.connect.ssid_len) { - err = cfg80211_set_freq(rdev, wdev, freq, NL80211_CHAN_NO_HT); + err = cfg80211_set_monitor_channel(rdev, freq, NL80211_CHAN_NO_HT); goto out; } diff --git a/net/x25/x25_route.c b/net/x25/x25_route.c index cf636627005..277c8d2448d 100644 --- a/net/x25/x25_route.c +++ b/net/x25/x25_route.c @@ -66,7 +66,7 @@ out: /** * __x25_remove_route - remove route from x25_route_list - * @rt - route to remove + * @rt: route to remove * * Remove route from x25_route_list. If it was there. * Caller must hold x25_route_list_lock. diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ccfbd328a69..5a2aa17e4d3 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1350,12 +1350,15 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) default: BUG(); } - xdst = dst_alloc(dst_ops, NULL, 0, 0, 0); + xdst = dst_alloc(dst_ops, NULL, 0, DST_OBSOLETE_NONE, 0); if (likely(xdst)) { - memset(&xdst->u.rt6.rt6i_table, 0, - sizeof(*xdst) - sizeof(struct dst_entry)); + struct dst_entry *dst = &xdst->u.dst; + + memset(dst + 1, 0, sizeof(*xdst) - sizeof(*dst)); xdst->flo.ops = &xfrm_bundle_fc_ops; + if (afinfo->init_dst) + afinfo->init_dst(net, xdst); } else xdst = ERR_PTR(-ENOBUFS); @@ -1476,7 +1479,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst1->xfrm = xfrm[i]; xdst->xfrm_genid = xfrm[i]->genid; - dst1->obsolete = -1; + dst1->obsolete = DST_OBSOLETE_FORCE_CHK; dst1->flags |= DST_HOST; dst1->lastuse = now; @@ -1500,9 +1503,6 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, if (!dev) goto free_dst; - /* Copy neighbour for reachability confirmation */ - dst_set_neighbour(dst0, neigh_clone(dst_get_neighbour_noref(dst))); - xfrm_init_path((struct xfrm_dst *)dst0, dst, nfheader_len); xfrm_init_pmtu(dst_prev); @@ -2221,12 +2221,13 @@ EXPORT_SYMBOL(__xfrm_route_forward); static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) { /* Code (such as __xfrm4_bundle_create()) sets dst->obsolete - * to "-1" to force all XFRM destinations to get validated by - * dst_ops->check on every use. We do this because when a - * normal route referenced by an XFRM dst is obsoleted we do - * not go looking around for all parent referencing XFRM dsts - * so that we can invalidate them. It is just too much work. - * Instead we make the checks here on every use. For example: + * to DST_OBSOLETE_FORCE_CHK to force all XFRM destinations to + * get validated by dst_ops->check on every use. We do this + * because when a normal route referenced by an XFRM dst is + * obsoleted we do not go looking around for all parent + * referencing XFRM dsts so that we can invalidate them. It + * is just too much work. Instead we make the checks here on + * every use. For example: * * XFRM dst A --> IPv4 dst X * @@ -2236,9 +2237,9 @@ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) * stale_bundle() check. * * When a policy's bundle is pruned, we dst_free() the XFRM - * dst which causes it's ->obsolete field to be set to a - * positive non-zero integer. If an XFRM dst has been pruned - * like this, we want to force a new route lookup. + * dst which causes it's ->obsolete field to be set to + * DST_OBSOLETE_DEAD. If an XFRM dst has been pruned like + * this, we want to force a new route lookup. */ if (dst->obsolete < 0 && !stale_bundle(dst)) return dst; @@ -2404,9 +2405,11 @@ static unsigned int xfrm_mtu(const struct dst_entry *dst) return mtu ? : dst_mtu(dst->path); } -static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, const void *daddr) +static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) { - return dst_neigh_lookup(dst->path, daddr); + return dst->path->ops->neigh_lookup(dst, skb, daddr); } int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 5b228f97d4b..210be48d8ae 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -415,8 +415,17 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me) if (x->lft.hard_add_expires_seconds) { long tmo = x->lft.hard_add_expires_seconds + x->curlft.add_time - now; - if (tmo <= 0) - goto expired; + if (tmo <= 0) { + if (x->xflags & XFRM_SOFT_EXPIRE) { + /* enter hard expire without soft expire first?! + * setting a new date could trigger this. + * workarbound: fix x->curflt.add_time by below: + */ + x->curlft.add_time = now - x->saved_tmo - 1; + tmo = x->lft.hard_add_expires_seconds - x->saved_tmo; + } else + goto expired; + } if (tmo < next) next = tmo; } @@ -433,10 +442,14 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me) if (x->lft.soft_add_expires_seconds) { long tmo = x->lft.soft_add_expires_seconds + x->curlft.add_time - now; - if (tmo <= 0) + if (tmo <= 0) { warn = 1; - else if (tmo < next) + x->xflags &= ~XFRM_SOFT_EXPIRE; + } else if (tmo < next) { next = tmo; + x->xflags |= XFRM_SOFT_EXPIRE; + x->saved_tmo = tmo; + } } if (x->lft.soft_use_expires_seconds) { long tmo = x->lft.soft_use_expires_seconds + @@ -1981,8 +1994,10 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay) goto error; x->outer_mode = xfrm_get_mode(x->props.mode, family); - if (x->outer_mode == NULL) + if (x->outer_mode == NULL) { + err = -EPROTONOSUPPORT; goto error; + } if (init_replay) { err = xfrm_init_replay(x); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 44293b3fd6a..e75d8e47f35 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -754,58 +754,67 @@ static int copy_to_user_state_extra(struct xfrm_state *x, struct xfrm_usersa_info *p, struct sk_buff *skb) { - copy_to_user_state(x, p); - - if (x->coaddr && - nla_put(skb, XFRMA_COADDR, sizeof(*x->coaddr), x->coaddr)) - goto nla_put_failure; - - if (x->lastused && - nla_put_u64(skb, XFRMA_LASTUSED, x->lastused)) - goto nla_put_failure; - - if (x->aead && - nla_put(skb, XFRMA_ALG_AEAD, aead_len(x->aead), x->aead)) - goto nla_put_failure; - - if (x->aalg && - (copy_to_user_auth(x->aalg, skb) || - nla_put(skb, XFRMA_ALG_AUTH_TRUNC, - xfrm_alg_auth_len(x->aalg), x->aalg))) - goto nla_put_failure; - - if (x->ealg && - nla_put(skb, XFRMA_ALG_CRYPT, xfrm_alg_len(x->ealg), x->ealg)) - goto nla_put_failure; - - if (x->calg && - nla_put(skb, XFRMA_ALG_COMP, sizeof(*(x->calg)), x->calg)) - goto nla_put_failure; - - if (x->encap && - nla_put(skb, XFRMA_ENCAP, sizeof(*x->encap), x->encap)) - goto nla_put_failure; + int ret = 0; - if (x->tfcpad && - nla_put_u32(skb, XFRMA_TFCPAD, x->tfcpad)) - goto nla_put_failure; - - if (xfrm_mark_put(skb, &x->mark)) - goto nla_put_failure; - - if (x->replay_esn && - nla_put(skb, XFRMA_REPLAY_ESN_VAL, - xfrm_replay_state_esn_len(x->replay_esn), - x->replay_esn)) - goto nla_put_failure; - - if (x->security && copy_sec_ctx(x->security, skb)) - goto nla_put_failure; - - return 0; + copy_to_user_state(x, p); -nla_put_failure: - return -EMSGSIZE; + if (x->coaddr) { + ret = nla_put(skb, XFRMA_COADDR, sizeof(*x->coaddr), x->coaddr); + if (ret) + goto out; + } + if (x->lastused) { + ret = nla_put_u64(skb, XFRMA_LASTUSED, x->lastused); + if (ret) + goto out; + } + if (x->aead) { + ret = nla_put(skb, XFRMA_ALG_AEAD, aead_len(x->aead), x->aead); + if (ret) + goto out; + } + if (x->aalg) { + ret = copy_to_user_auth(x->aalg, skb); + if (!ret) + ret = nla_put(skb, XFRMA_ALG_AUTH_TRUNC, + xfrm_alg_auth_len(x->aalg), x->aalg); + if (ret) + goto out; + } + if (x->ealg) { + ret = nla_put(skb, XFRMA_ALG_CRYPT, xfrm_alg_len(x->ealg), x->ealg); + if (ret) + goto out; + } + if (x->calg) { + ret = nla_put(skb, XFRMA_ALG_COMP, sizeof(*(x->calg)), x->calg); + if (ret) + goto out; + } + if (x->encap) { + ret = nla_put(skb, XFRMA_ENCAP, sizeof(*x->encap), x->encap); + if (ret) + goto out; + } + if (x->tfcpad) { + ret = nla_put_u32(skb, XFRMA_TFCPAD, x->tfcpad); + if (ret) + goto out; + } + ret = xfrm_mark_put(skb, &x->mark); + if (ret) + goto out; + if (x->replay_esn) { + ret = nla_put(skb, XFRMA_REPLAY_ESN_VAL, + xfrm_replay_state_esn_len(x->replay_esn), + x->replay_esn); + if (ret) + goto out; + } + if (x->security) + ret = copy_sec_ctx(x->security, skb); +out: + return ret; } static int dump_one_state(struct xfrm_state *x, int count, void *ptr) @@ -825,15 +834,12 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr) p = nlmsg_data(nlh); err = copy_to_user_state_extra(x, p, skb); - if (err) - goto nla_put_failure; - + if (err) { + nlmsg_cancel(skb, nlh); + return err; + } nlmsg_end(skb, nlh); return 0; - -nla_put_failure: - nlmsg_cancel(skb, nlh); - return err; } static int xfrm_dump_sa_done(struct netlink_callback *cb) @@ -904,6 +910,7 @@ static int build_spdinfo(struct sk_buff *skb, struct net *net, struct xfrmu_spdinfo spc; struct xfrmu_spdhinfo sph; struct nlmsghdr *nlh; + int err; u32 *f; nlh = nlmsg_put(skb, pid, seq, XFRM_MSG_NEWSPDINFO, sizeof(u32), 0); @@ -922,15 +929,15 @@ static int build_spdinfo(struct sk_buff *skb, struct net *net, sph.spdhcnt = si.spdhcnt; sph.spdhmcnt = si.spdhmcnt; - if (nla_put(skb, XFRMA_SPD_INFO, sizeof(spc), &spc) || - nla_put(skb, XFRMA_SPD_HINFO, sizeof(sph), &sph)) - goto nla_put_failure; + err = nla_put(skb, XFRMA_SPD_INFO, sizeof(spc), &spc); + if (!err) + err = nla_put(skb, XFRMA_SPD_HINFO, sizeof(sph), &sph); + if (err) { + nlmsg_cancel(skb, nlh); + return err; + } return nlmsg_end(skb, nlh); - -nla_put_failure: - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; } static int xfrm_get_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -965,6 +972,7 @@ static int build_sadinfo(struct sk_buff *skb, struct net *net, struct xfrmk_sadinfo si; struct xfrmu_sadhinfo sh; struct nlmsghdr *nlh; + int err; u32 *f; nlh = nlmsg_put(skb, pid, seq, XFRM_MSG_NEWSADINFO, sizeof(u32), 0); @@ -978,15 +986,15 @@ static int build_sadinfo(struct sk_buff *skb, struct net *net, sh.sadhmcnt = si.sadhmcnt; sh.sadhcnt = si.sadhcnt; - if (nla_put_u32(skb, XFRMA_SAD_CNT, si.sadcnt) || - nla_put(skb, XFRMA_SAD_HINFO, sizeof(sh), &sh)) - goto nla_put_failure; + err = nla_put_u32(skb, XFRMA_SAD_CNT, si.sadcnt); + if (!err) + err = nla_put(skb, XFRMA_SAD_HINFO, sizeof(sh), &sh); + if (err) { + nlmsg_cancel(skb, nlh); + return err; + } return nlmsg_end(skb, nlh); - -nla_put_failure: - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; } static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -1439,9 +1447,8 @@ static inline int copy_to_user_state_sec_ctx(struct xfrm_state *x, struct sk_buf static inline int copy_to_user_sec_ctx(struct xfrm_policy *xp, struct sk_buff *skb) { - if (xp->security) { + if (xp->security) return copy_sec_ctx(xp->security, skb); - } return 0; } static inline size_t userpolicy_type_attrsize(void) @@ -1477,6 +1484,7 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr struct sk_buff *in_skb = sp->in_skb; struct sk_buff *skb = sp->out_skb; struct nlmsghdr *nlh; + int err; nlh = nlmsg_put(skb, NETLINK_CB(in_skb).pid, sp->nlmsg_seq, XFRM_MSG_NEWPOLICY, sizeof(*p), sp->nlmsg_flags); @@ -1485,22 +1493,19 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr p = nlmsg_data(nlh); copy_to_user_policy(xp, p, dir); - if (copy_to_user_tmpl(xp, skb) < 0) - goto nlmsg_failure; - if (copy_to_user_sec_ctx(xp, skb)) - goto nlmsg_failure; - if (copy_to_user_policy_type(xp->type, skb) < 0) - goto nlmsg_failure; - if (xfrm_mark_put(skb, &xp->mark)) - goto nla_put_failure; - + err = copy_to_user_tmpl(xp, skb); + if (!err) + err = copy_to_user_sec_ctx(xp, skb); + if (!err) + err = copy_to_user_policy_type(xp->type, skb); + if (!err) + err = xfrm_mark_put(skb, &xp->mark); + if (err) { + nlmsg_cancel(skb, nlh); + return err; + } nlmsg_end(skb, nlh); return 0; - -nla_put_failure: -nlmsg_failure: - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; } static int xfrm_dump_policy_done(struct netlink_callback *cb) @@ -1688,6 +1693,7 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct { struct xfrm_aevent_id *id; struct nlmsghdr *nlh; + int err; nlh = nlmsg_put(skb, c->pid, c->seq, XFRM_MSG_NEWAE, sizeof(*id), 0); if (nlh == NULL) @@ -1703,35 +1709,39 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct id->flags = c->data.aevent; if (x->replay_esn) { - if (nla_put(skb, XFRMA_REPLAY_ESN_VAL, - xfrm_replay_state_esn_len(x->replay_esn), - x->replay_esn)) - goto nla_put_failure; + err = nla_put(skb, XFRMA_REPLAY_ESN_VAL, + xfrm_replay_state_esn_len(x->replay_esn), + x->replay_esn); } else { - if (nla_put(skb, XFRMA_REPLAY_VAL, sizeof(x->replay), - &x->replay)) - goto nla_put_failure; + err = nla_put(skb, XFRMA_REPLAY_VAL, sizeof(x->replay), + &x->replay); } - if (nla_put(skb, XFRMA_LTIME_VAL, sizeof(x->curlft), &x->curlft)) - goto nla_put_failure; - - if ((id->flags & XFRM_AE_RTHR) && - nla_put_u32(skb, XFRMA_REPLAY_THRESH, x->replay_maxdiff)) - goto nla_put_failure; - - if ((id->flags & XFRM_AE_ETHR) && - nla_put_u32(skb, XFRMA_ETIMER_THRESH, - x->replay_maxage * 10 / HZ)) - goto nla_put_failure; + if (err) + goto out_cancel; + err = nla_put(skb, XFRMA_LTIME_VAL, sizeof(x->curlft), &x->curlft); + if (err) + goto out_cancel; - if (xfrm_mark_put(skb, &x->mark)) - goto nla_put_failure; + if (id->flags & XFRM_AE_RTHR) { + err = nla_put_u32(skb, XFRMA_REPLAY_THRESH, x->replay_maxdiff); + if (err) + goto out_cancel; + } + if (id->flags & XFRM_AE_ETHR) { + err = nla_put_u32(skb, XFRMA_ETIMER_THRESH, + x->replay_maxage * 10 / HZ); + if (err) + goto out_cancel; + } + err = xfrm_mark_put(skb, &x->mark); + if (err) + goto out_cancel; return nlmsg_end(skb, nlh); -nla_put_failure: +out_cancel: nlmsg_cancel(skb, nlh); - return -EMSGSIZE; + return err; } static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2155,7 +2165,7 @@ static int build_migrate(struct sk_buff *skb, const struct xfrm_migrate *m, const struct xfrm_migrate *mp; struct xfrm_userpolicy_id *pol_id; struct nlmsghdr *nlh; - int i; + int i, err; nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_MIGRATE, sizeof(*pol_id), 0); if (nlh == NULL) @@ -2167,21 +2177,25 @@ static int build_migrate(struct sk_buff *skb, const struct xfrm_migrate *m, memcpy(&pol_id->sel, sel, sizeof(pol_id->sel)); pol_id->dir = dir; - if (k != NULL && (copy_to_user_kmaddress(k, skb) < 0)) - goto nlmsg_failure; - - if (copy_to_user_policy_type(type, skb) < 0) - goto nlmsg_failure; - + if (k != NULL) { + err = copy_to_user_kmaddress(k, skb); + if (err) + goto out_cancel; + } + err = copy_to_user_policy_type(type, skb); + if (err) + goto out_cancel; for (i = 0, mp = m ; i < num_migrate; i++, mp++) { - if (copy_to_user_migrate(mp, skb) < 0) - goto nlmsg_failure; + err = copy_to_user_migrate(mp, skb); + if (err) + goto out_cancel; } return nlmsg_end(skb, nlh); -nlmsg_failure: + +out_cancel: nlmsg_cancel(skb, nlh); - return -EMSGSIZE; + return err; } static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, @@ -2354,6 +2368,7 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct { struct xfrm_user_expire *ue; struct nlmsghdr *nlh; + int err; nlh = nlmsg_put(skb, c->pid, 0, XFRM_MSG_EXPIRE, sizeof(*ue), 0); if (nlh == NULL) @@ -2363,13 +2378,11 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct copy_to_user_state(x, &ue->state); ue->hard = (c->data.hard != 0) ? 1 : 0; - if (xfrm_mark_put(skb, &x->mark)) - goto nla_put_failure; + err = xfrm_mark_put(skb, &x->mark); + if (err) + return err; return nlmsg_end(skb, nlh); - -nla_put_failure: - return -EMSGSIZE; } static int xfrm_exp_state_notify(struct xfrm_state *x, const struct km_event *c) @@ -2470,7 +2483,7 @@ static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c) struct nlmsghdr *nlh; struct sk_buff *skb; int len = xfrm_sa_len(x); - int headlen; + int headlen, err; headlen = sizeof(*p); if (c->event == XFRM_MSG_DELSA) { @@ -2485,8 +2498,9 @@ static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c) return -ENOMEM; nlh = nlmsg_put(skb, c->pid, c->seq, c->event, headlen, 0); + err = -EMSGSIZE; if (nlh == NULL) - goto nla_put_failure; + goto out_free_skb; p = nlmsg_data(nlh); if (c->event == XFRM_MSG_DELSA) { @@ -2499,24 +2513,23 @@ static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c) id->proto = x->id.proto; attr = nla_reserve(skb, XFRMA_SA, sizeof(*p)); + err = -EMSGSIZE; if (attr == NULL) - goto nla_put_failure; + goto out_free_skb; p = nla_data(attr); } - - if (copy_to_user_state_extra(x, p, skb)) - goto nla_put_failure; + err = copy_to_user_state_extra(x, p, skb); + if (err) + goto out_free_skb; nlmsg_end(skb, nlh); return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_SA, GFP_ATOMIC); -nla_put_failure: - /* Somebody screwed up with xfrm_sa_len! */ - WARN_ON(1); +out_free_skb: kfree_skb(skb); - return -1; + return err; } static int xfrm_send_state_notify(struct xfrm_state *x, const struct km_event *c) @@ -2557,9 +2570,10 @@ static int build_acquire(struct sk_buff *skb, struct xfrm_state *x, struct xfrm_tmpl *xt, struct xfrm_policy *xp, int dir) { + __u32 seq = xfrm_get_acqseq(); struct xfrm_user_acquire *ua; struct nlmsghdr *nlh; - __u32 seq = xfrm_get_acqseq(); + int err; nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_ACQUIRE, sizeof(*ua), 0); if (nlh == NULL) @@ -2575,21 +2589,19 @@ static int build_acquire(struct sk_buff *skb, struct xfrm_state *x, ua->calgos = xt->calgos; ua->seq = x->km.seq = seq; - if (copy_to_user_tmpl(xp, skb) < 0) - goto nlmsg_failure; - if (copy_to_user_state_sec_ctx(x, skb)) - goto nlmsg_failure; - if (copy_to_user_policy_type(xp->type, skb) < 0) - goto nlmsg_failure; - if (xfrm_mark_put(skb, &xp->mark)) - goto nla_put_failure; + err = copy_to_user_tmpl(xp, skb); + if (!err) + err = copy_to_user_state_sec_ctx(x, skb); + if (!err) + err = copy_to_user_policy_type(xp->type, skb); + if (!err) + err = xfrm_mark_put(skb, &xp->mark); + if (err) { + nlmsg_cancel(skb, nlh); + return err; + } return nlmsg_end(skb, nlh); - -nla_put_failure: -nlmsg_failure: - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; } static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt, @@ -2681,8 +2693,9 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp, int dir, const struct km_event *c) { struct xfrm_user_polexpire *upe; - struct nlmsghdr *nlh; int hard = c->data.hard; + struct nlmsghdr *nlh; + int err; nlh = nlmsg_put(skb, c->pid, 0, XFRM_MSG_POLEXPIRE, sizeof(*upe), 0); if (nlh == NULL) @@ -2690,22 +2703,20 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp, upe = nlmsg_data(nlh); copy_to_user_policy(xp, &upe->pol, dir); - if (copy_to_user_tmpl(xp, skb) < 0) - goto nlmsg_failure; - if (copy_to_user_sec_ctx(xp, skb)) - goto nlmsg_failure; - if (copy_to_user_policy_type(xp->type, skb) < 0) - goto nlmsg_failure; - if (xfrm_mark_put(skb, &xp->mark)) - goto nla_put_failure; + err = copy_to_user_tmpl(xp, skb); + if (!err) + err = copy_to_user_sec_ctx(xp, skb); + if (!err) + err = copy_to_user_policy_type(xp->type, skb); + if (!err) + err = xfrm_mark_put(skb, &xp->mark); + if (err) { + nlmsg_cancel(skb, nlh); + return err; + } upe->hard = !!hard; return nlmsg_end(skb, nlh); - -nla_put_failure: -nlmsg_failure: - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; } static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) @@ -2725,13 +2736,13 @@ static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c) { + int len = nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr); struct net *net = xp_net(xp); struct xfrm_userpolicy_info *p; struct xfrm_userpolicy_id *id; struct nlmsghdr *nlh; struct sk_buff *skb; - int len = nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr); - int headlen; + int headlen, err; headlen = sizeof(*p); if (c->event == XFRM_MSG_DELPOLICY) { @@ -2747,8 +2758,9 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_e return -ENOMEM; nlh = nlmsg_put(skb, c->pid, c->seq, c->event, headlen, 0); + err = -EMSGSIZE; if (nlh == NULL) - goto nlmsg_failure; + goto out_free_skb; p = nlmsg_data(nlh); if (c->event == XFRM_MSG_DELPOLICY) { @@ -2763,29 +2775,29 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_e memcpy(&id->sel, &xp->selector, sizeof(id->sel)); attr = nla_reserve(skb, XFRMA_POLICY, sizeof(*p)); + err = -EMSGSIZE; if (attr == NULL) - goto nlmsg_failure; + goto out_free_skb; p = nla_data(attr); } copy_to_user_policy(xp, p, dir); - if (copy_to_user_tmpl(xp, skb) < 0) - goto nlmsg_failure; - if (copy_to_user_policy_type(xp->type, skb) < 0) - goto nlmsg_failure; - - if (xfrm_mark_put(skb, &xp->mark)) - goto nla_put_failure; + err = copy_to_user_tmpl(xp, skb); + if (!err) + err = copy_to_user_policy_type(xp->type, skb); + if (!err) + err = xfrm_mark_put(skb, &xp->mark); + if (err) + goto out_free_skb; nlmsg_end(skb, nlh); return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC); -nla_put_failure: -nlmsg_failure: +out_free_skb: kfree_skb(skb); - return -1; + return err; } static int xfrm_notify_policy_flush(const struct km_event *c) @@ -2793,24 +2805,27 @@ static int xfrm_notify_policy_flush(const struct km_event *c) struct net *net = c->net; struct nlmsghdr *nlh; struct sk_buff *skb; + int err; skb = nlmsg_new(userpolicy_type_attrsize(), GFP_ATOMIC); if (skb == NULL) return -ENOMEM; nlh = nlmsg_put(skb, c->pid, c->seq, XFRM_MSG_FLUSHPOLICY, 0, 0); + err = -EMSGSIZE; if (nlh == NULL) - goto nlmsg_failure; - if (copy_to_user_policy_type(c->data.type, skb) < 0) - goto nlmsg_failure; + goto out_free_skb; + err = copy_to_user_policy_type(c->data.type, skb); + if (err) + goto out_free_skb; nlmsg_end(skb, nlh); return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC); -nlmsg_failure: +out_free_skb: kfree_skb(skb); - return -1; + return err; } static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) @@ -2853,15 +2868,14 @@ static int build_report(struct sk_buff *skb, u8 proto, ur->proto = proto; memcpy(&ur->sel, sel, sizeof(ur->sel)); - if (addr && - nla_put(skb, XFRMA_COADDR, sizeof(*addr), addr)) - goto nla_put_failure; - + if (addr) { + int err = nla_put(skb, XFRMA_COADDR, sizeof(*addr), addr); + if (err) { + nlmsg_cancel(skb, nlh); + return err; + } + } return nlmsg_end(skb, nlh); - -nla_put_failure: - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; } static int xfrm_send_report(struct net *net, u8 proto, @@ -2945,9 +2959,12 @@ static struct xfrm_mgr netlink_mgr = { static int __net_init xfrm_user_net_init(struct net *net) { struct sock *nlsk; + struct netlink_kernel_cfg cfg = { + .groups = XFRMNLGRP_MAX, + .input = xfrm_netlink_rcv, + }; - nlsk = netlink_kernel_create(net, NETLINK_XFRM, XFRMNLGRP_MAX, - xfrm_netlink_rcv, NULL, THIS_MODULE); + nlsk = netlink_kernel_create(net, NETLINK_XFRM, THIS_MODULE, &cfg); if (nlsk == NULL) return -ENOMEM; net->xfrm.nlsk_stash = nlsk; /* Don't set to NULL */ |