From 4bf84c35c65f36a344fb7a6cde6274df4120efb8 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 27 Dec 2012 23:49:37 +0000 Subject: net: add change_carrier netdev op This allows a driver to register change_carrier callback which will be called whenever user will like to change carrier state. This is useful for devices like dummy, gre, team and so on. Signed-off-by: Jiri Pirko Acked-by: Flavio Leitner Signed-off-by: David S. Miller --- net/core/dev.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index 515473ee52c..21c5b976dcf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5027,6 +5027,25 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) } EXPORT_SYMBOL(dev_set_mac_address); +/** + * dev_change_carrier - Change device carrier + * @dev: device + * @new_carries: new value + * + * Change device carrier + */ +int dev_change_carrier(struct net_device *dev, bool new_carrier) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!ops->ndo_change_carrier) + return -EOPNOTSUPP; + if (!netif_device_present(dev)) + return -ENODEV; + return ops->ndo_change_carrier(dev, new_carrier); +} +EXPORT_SYMBOL(dev_change_carrier); + /* * Perform the SIOCxIFxxx calls, inside rcu_read_lock() */ -- cgit v1.2.3-70-g09d2 From fdae0fde5352790030d89edd09f1b43b9bed97f8 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 27 Dec 2012 23:49:38 +0000 Subject: net: allow to change carrier via sysfs Make carrier writable Signed-off-by: Jiri Pirko Acked-by: Flavio Leitner Signed-off-by: David S. Miller --- net/core/net-sysfs.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 28c5f5aa7ca..29c884a74c3 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -126,6 +126,19 @@ static ssize_t show_broadcast(struct device *dev, return -EINVAL; } +static int change_carrier(struct net_device *net, unsigned long new_carrier) +{ + if (!netif_running(net)) + return -EINVAL; + return dev_change_carrier(net, (bool) new_carrier); +} + +static ssize_t store_carrier(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) +{ + return netdev_store(dev, attr, buf, len, change_carrier); +} + static ssize_t show_carrier(struct device *dev, struct device_attribute *attr, char *buf) { @@ -331,7 +344,7 @@ static struct device_attribute net_class_attributes[] = { __ATTR(link_mode, S_IRUGO, show_link_mode, NULL), __ATTR(address, S_IRUGO, show_address, NULL), __ATTR(broadcast, S_IRUGO, show_broadcast, NULL), - __ATTR(carrier, S_IRUGO, show_carrier, NULL), + __ATTR(carrier, S_IRUGO | S_IWUSR, show_carrier, store_carrier), __ATTR(speed, S_IRUGO, show_speed, NULL), __ATTR(duplex, S_IRUGO, show_duplex, NULL), __ATTR(dormant, S_IRUGO, show_dormant, NULL), -- cgit v1.2.3-70-g09d2 From 9a57247f31e361f80508c40363366222dbbb6aa5 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 27 Dec 2012 23:49:39 +0000 Subject: rtnl: expose carrier value with possibility to set it Signed-off-by: Jiri Pirko Acked-by: Flavio Leitner Signed-off-by: David S. Miller --- Documentation/networking/operstates.txt | 4 ++++ include/uapi/linux/if_link.h | 1 + net/core/rtnetlink.c | 10 ++++++++++ 3 files changed, 15 insertions(+) (limited to 'net/core') diff --git a/Documentation/networking/operstates.txt b/Documentation/networking/operstates.txt index 1a77a3cfae5..97694572338 100644 --- a/Documentation/networking/operstates.txt +++ b/Documentation/networking/operstates.txt @@ -88,6 +88,10 @@ set this flag. On netif_carrier_off(), the scheduler stops sending packets. The name 'carrier' and the inversion are historical, think of it as lower layer. +Note that for certain kind of soft-devices, which are not managing any +real hardware, there is possible to set this bit from userpsace. +One should use TVL IFLA_CARRIER to do so. + netif_carrier_ok() can be used to query that bit. __LINK_STATE_DORMANT, maps to IFF_DORMANT: diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 60f3b6b9060..c4edfe11f1f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -142,6 +142,7 @@ enum { #define IFLA_PROMISCUITY IFLA_PROMISCUITY IFLA_NUM_TX_QUEUES, IFLA_NUM_RX_QUEUES, + IFLA_CARRIER, __IFLA_MAX }; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1868625af25..2ef7a56ba11 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -780,6 +780,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(4) /* IFLA_MASTER */ + + nla_total_size(1) /* IFLA_CARRIER */ + nla_total_size(4) /* IFLA_PROMISCUITY */ + nla_total_size(4) /* IFLA_NUM_TX_QUEUES */ + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */ @@ -909,6 +910,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put_u32(skb, IFLA_LINK, dev->iflink)) || (dev->master && nla_put_u32(skb, IFLA_MASTER, dev->master->ifindex)) || + nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) || (dev->qdisc && nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) || (dev->ifalias && @@ -1108,6 +1110,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_MTU] = { .type = NLA_U32 }, [IFLA_LINK] = { .type = NLA_U32 }, [IFLA_MASTER] = { .type = NLA_U32 }, + [IFLA_CARRIER] = { .type = NLA_U8 }, [IFLA_TXQLEN] = { .type = NLA_U32 }, [IFLA_WEIGHT] = { .type = NLA_U32 }, [IFLA_OPERSTATE] = { .type = NLA_U8 }, @@ -1438,6 +1441,13 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, modified = 1; } + if (tb[IFLA_CARRIER]) { + err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER])); + if (err) + goto errout; + modified = 1; + } + if (tb[IFLA_TXQLEN]) dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]); -- cgit v1.2.3-70-g09d2 From b2111724a639ec31a19fdca62ea3a0a222d59d11 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Dec 2012 06:06:37 +0000 Subject: net: use per task frag allocator in skb_append_datato_frags Use the new per task frag allocator in skb_append_datato_frags(), to reduce number of frags and page allocator overhead. Tested: ifconfig lo mtu 16436 perf record netperf -t UDP_STREAM ; perf report before : Throughput: 32928 Mbit/s 51.79% netperf [kernel.kallsyms] [k] copy_user_generic_string 5.98% netperf [kernel.kallsyms] [k] __alloc_pages_nodemask 5.58% netperf [kernel.kallsyms] [k] get_page_from_freelist 5.01% netperf [kernel.kallsyms] [k] __rmqueue 3.74% netperf [kernel.kallsyms] [k] skb_append_datato_frags 1.87% netperf [kernel.kallsyms] [k] prep_new_page 1.42% netperf [kernel.kallsyms] [k] next_zones_zonelist 1.28% netperf [kernel.kallsyms] [k] __inc_zone_state 1.26% netperf [kernel.kallsyms] [k] alloc_pages_current 0.78% netperf [kernel.kallsyms] [k] sock_alloc_send_pskb 0.74% netperf [kernel.kallsyms] [k] udp_sendmsg 0.72% netperf [kernel.kallsyms] [k] zone_watermark_ok 0.68% netperf [kernel.kallsyms] [k] __cpuset_node_allowed_softwall 0.67% netperf [kernel.kallsyms] [k] fib_table_lookup 0.60% netperf [kernel.kallsyms] [k] memcpy_fromiovecend 0.55% netperf [kernel.kallsyms] [k] __udp4_lib_lookup after: Throughput: 47185 Mbit/s 61.74% netperf [kernel.kallsyms] [k] copy_user_generic_string 2.07% netperf [kernel.kallsyms] [k] prep_new_page 1.98% netperf [kernel.kallsyms] [k] skb_append_datato_frags 1.02% netperf [kernel.kallsyms] [k] sock_alloc_send_pskb 0.97% netperf [kernel.kallsyms] [k] enqueue_task_fair 0.97% netperf [kernel.kallsyms] [k] udp_sendmsg 0.91% netperf [kernel.kallsyms] [k] __ip_route_output_key 0.88% netperf [kernel.kallsyms] [k] __netif_receive_skb 0.87% netperf [kernel.kallsyms] [k] fib_table_lookup 0.85% netperf [kernel.kallsyms] [k] resched_task 0.78% netperf [kernel.kallsyms] [k] __udp4_lib_lookup 0.77% netperf [kernel.kallsyms] [k] _raw_spin_lock_irqsave Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/skbuff.c | 43 ++++++++++++++++--------------------------- 1 file changed, 16 insertions(+), 27 deletions(-) (limited to 'net/core') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3ab989b0de4..ec8737ec59b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2686,48 +2686,37 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, int len, int odd, struct sk_buff *skb), void *from, int length) { - int frg_cnt = 0; - skb_frag_t *frag = NULL; - struct page *page = NULL; - int copy, left; + int frg_cnt = skb_shinfo(skb)->nr_frags; + int copy; int offset = 0; int ret; + struct page_frag *pfrag = ¤t->task_frag; do { /* Return error if we don't have space for new frag */ - frg_cnt = skb_shinfo(skb)->nr_frags; if (frg_cnt >= MAX_SKB_FRAGS) - return -EFAULT; - - /* allocate a new page for next frag */ - page = alloc_pages(sk->sk_allocation, 0); + return -EMSGSIZE; - /* If alloc_page fails just return failure and caller will - * free previous allocated pages by doing kfree_skb() - */ - if (page == NULL) + if (!sk_page_frag_refill(sk, pfrag)) return -ENOMEM; - /* initialize the next frag */ - skb_fill_page_desc(skb, frg_cnt, page, 0, 0); - skb->truesize += PAGE_SIZE; - atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc); - - /* get the new initialized frag */ - frg_cnt = skb_shinfo(skb)->nr_frags; - frag = &skb_shinfo(skb)->frags[frg_cnt - 1]; - /* copy the user data to page */ - left = PAGE_SIZE - frag->page_offset; - copy = (length > left)? left : length; + copy = min_t(int, length, pfrag->size - pfrag->offset); - ret = getfrag(from, skb_frag_address(frag) + skb_frag_size(frag), - offset, copy, 0, skb); + ret = getfrag(from, page_address(pfrag->page) + pfrag->offset, + offset, copy, 0, skb); if (ret < 0) return -EFAULT; /* copy was successful so update the size parameters */ - skb_frag_size_add(frag, copy); + skb_fill_page_desc(skb, frg_cnt, pfrag->page, pfrag->offset, + copy); + frg_cnt++; + pfrag->offset += copy; + get_page(pfrag->page); + + skb->truesize += copy; + atomic_add(copy, &sk->sk_wmem_alloc); skb->len += copy; skb->data_len += copy; offset += copy; -- cgit v1.2.3-70-g09d2 From 61c5e88aecd6fbf2480f39394bb495964e6d9984 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Fri, 28 Dec 2012 18:24:28 +0000 Subject: skbuff: make __kmalloc_reserve static Sparse detected case where this local function should be static. It may even allow some compiler optimizations. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/core/skbuff.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net/core') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ec8737ec59b..bc96100fe23 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -155,8 +155,9 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here) */ #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) + +static void *__kmalloc_reserve(size_t size, gfp_t flags, int node, + unsigned long ip, bool *pfmemalloc) { void *obj; bool ret_pfmemalloc = false; -- cgit v1.2.3-70-g09d2 From aa1113d9f85da59dcbdd32aeb5d71da566e46def Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 28 Dec 2012 10:50:17 +0000 Subject: net: filter: return -EINVAL if BPF_S_ANC* operation is not supported Currently, we return -EINVAL for malformed or wrong BPF filters. However, this is not done for BPF_S_ANC* operations, which makes it more difficult to detect if it's actually supported or not by the BPF machine. Therefore, we should also return -EINVAL if K is within the SKF_AD_OFF universe and the ancillary operation did not match. Why exactly is it needed? If tools such as libpcap/tcpdump want to make use of new ancillary operations (like filtering VLAN in kernel space), there is currently no sane way to test if this feature / BPF_S_ANC* op is present or not, since no error is returned. This patch will make life easier for that and allow for a proper usage for user space applications. There was concern, if this patch will break userland. Short answer: Yes and no. Long answer: It will "break" only for code that calls ... { BPF_LD | BPF_(W|H|B) | BPF_ABS, 0, 0, }, ... where is in [0xfffff000, 0xffffffff] _and_ is *not* an ancillary. And here comes the BUT: assuming some *old* code will have such an instruction where is between [0xfffff000, 0xffffffff] and it doesn't know ancillary operations, then this will give a non-expected / unwanted behavior as well (since we do not return the BPF machine with 0 after a failed load_pointer(), which was the case before introducing ancillary operations, but load sth. into the accumulator instead, and continue with the next instruction, for instance). Thus, user space code would already have been broken by introducing ancillary operations into the BPF machine per se. Code that does such a direct load, e.g. "load word at packet offset 0xffffffff into accumulator" ("ld [0xffffffff]") is quite broken, isn't it? The whole assumption of ancillary operations is that no-one intentionally calls things like "ld [0xffffffff]" and expect this word to be loaded from such a packet offset. Hence, we can also safely make use of this feature testing patch and facilitate application development. Therefore, at least from this patch onwards, we have *for sure* a check whether current or in future implemented BPF_S_ANC* ops are supported in the kernel. Patch was tested on x86_64. (Thanks to Eric for the previous review.) Cc: Eric Dumazet Reported-by: Ani Sinha Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- net/core/filter.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'net/core') diff --git a/net/core/filter.c b/net/core/filter.c index c23543cba13..2ead2a9b185 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -532,6 +532,7 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) [BPF_JMP|BPF_JSET|BPF_X] = BPF_S_JMP_JSET_X, }; int pc; + bool anc_found; if (flen == 0 || flen > BPF_MAXINSNS) return -EINVAL; @@ -592,8 +593,10 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) case BPF_S_LD_W_ABS: case BPF_S_LD_H_ABS: case BPF_S_LD_B_ABS: + anc_found = false; #define ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \ code = BPF_S_ANC_##CODE; \ + anc_found = true; \ break switch (ftest->k) { ANCILLARY(PROTOCOL); @@ -610,6 +613,10 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) ANCILLARY(VLAN_TAG); ANCILLARY(VLAN_TAG_PRESENT); } + + /* ancillary operation unknown or unsupported */ + if (anc_found == false && ftest->k >= SKF_AD_OFF) + return -EINVAL; } ftest->code = code; } -- cgit v1.2.3-70-g09d2 From e7c3273ec2a04bbce27e0991c405fe6dc6811d7d Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 1 Jan 2013 03:30:13 +0000 Subject: rtnl: use dev_set_mac_address() instead of plain ndo_ Benefit from existence of dev_set_mac_address() and remove duplicate code. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 20 ++------------------ 1 file changed, 2 insertions(+), 18 deletions(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2ef7a56ba11..78d05a9dcea 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1310,7 +1310,6 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, struct nlattr **tb, char *ifname, int modified) { const struct net_device_ops *ops = dev->netdev_ops; - int send_addr_notify = 0; int err; if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD]) { @@ -1363,16 +1362,6 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, struct sockaddr *sa; int len; - if (!ops->ndo_set_mac_address) { - err = -EOPNOTSUPP; - goto errout; - } - - if (!netif_device_present(dev)) { - err = -ENODEV; - goto errout; - } - len = sizeof(sa_family_t) + dev->addr_len; sa = kmalloc(len, GFP_KERNEL); if (!sa) { @@ -1382,13 +1371,11 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, sa->sa_family = dev->type; memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]), dev->addr_len); - err = ops->ndo_set_mac_address(dev, sa); + err = dev_set_mac_address(dev, sa); kfree(sa); if (err) goto errout; - send_addr_notify = 1; modified = 1; - add_device_randomness(dev->dev_addr, dev->addr_len); } if (tb[IFLA_MTU]) { @@ -1425,7 +1412,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, if (tb[IFLA_BROADCAST]) { nla_memcpy(dev->broadcast, tb[IFLA_BROADCAST], dev->addr_len); - send_addr_notify = 1; + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); } if (ifm->ifi_flags || ifm->ifi_change) { @@ -1546,9 +1533,6 @@ errout: net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n", dev->name); - if (send_addr_notify) - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - return err; } -- cgit v1.2.3-70-g09d2 From f652151640344f8faee21fcf702b4fd46b8fe70b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 1 Jan 2013 03:30:14 +0000 Subject: net: call add_device_randomness() only after successful mac change Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/dev.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index 21c5b976dcf..c85e32b30f0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5020,10 +5020,11 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) if (!netif_device_present(dev)) return -ENODEV; err = ops->ndo_set_mac_address(dev, sa); - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + if (err) + return err; + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); add_device_randomness(dev->dev_addr, dev->addr_len); - return err; + return 0; } EXPORT_SYMBOL(dev_set_mac_address); -- cgit v1.2.3-70-g09d2 From fbdeca2d7753aa1ab929aeb77ccc46489eed02b9 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 1 Jan 2013 03:30:16 +0000 Subject: net: add address assign type "SET" This is the way to indicate that mac address of a device has been set by dev_set_mac_address() Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ net/core/dev.c | 1 + 2 files changed, 3 insertions(+) (limited to 'net/core') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6835b5837f9..c5031a45e18 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -64,6 +64,8 @@ struct wireless_dev; #define NET_ADDR_PERM 0 /* address is permanent (default) */ #define NET_ADDR_RANDOM 1 /* address is generated randomly */ #define NET_ADDR_STOLEN 2 /* address is stolen from other device */ +#define NET_ADDR_SET 3 /* address is set using + * dev_set_mac_address() */ /* Backlog congestion levels */ #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ diff --git a/net/core/dev.c b/net/core/dev.c index c85e32b30f0..bddb2f2ccaa 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5022,6 +5022,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) err = ops->ndo_set_mac_address(dev, sa); if (err) return err; + dev->addr_assign_type = NET_ADDR_SET; call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); add_device_randomness(dev->dev_addr, dev->addr_len); return 0; -- cgit v1.2.3-70-g09d2 From 9ff162a8b96c96238773972e26288a366e403b0c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Jan 2013 22:48:49 +0000 Subject: net: introduce upper device lists This lists are supposed to serve for storing pointers to all upper devices. Eventually it will replace dev->master pointer which is used for bonding, bridge, team but it cannot be used for vlan, macvlan where there might be multiple upper present. In case the upper link is replacement for dev->master, it is marked with "master" flag. New upper device list resolves this limitation. Also, the information stored in lists is used for preventing looping setups like "bond->somethingelse->samebond" Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 14 +++ net/core/dev.c | 239 +++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 249 insertions(+), 4 deletions(-) (limited to 'net/core') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c5031a45e18..e324601f48e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1174,6 +1174,8 @@ struct net_device { * which this device is member of. */ + struct list_head upper_dev_list; /* List of upper devices */ + /* Interface address info used in eth_type_trans() */ unsigned char *dev_addr; /* hw address, (before bcast because most packets are @@ -2636,6 +2638,18 @@ extern int netdev_max_backlog; extern int netdev_tstamp_prequeue; extern int weight_p; extern int bpf_jit_enable; + +extern bool netdev_has_upper_dev(struct net_device *dev, + struct net_device *upper_dev); +extern bool netdev_has_any_upper_dev(struct net_device *dev); +extern struct net_device *netdev_master_upper_dev_get(struct net_device *dev); +extern struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); +extern int netdev_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev); +extern int netdev_master_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev); +extern void netdev_upper_dev_unlink(struct net_device *dev, + struct net_device *upper_dev); extern int netdev_set_master(struct net_device *dev, struct net_device *master); extern int netdev_set_bond_master(struct net_device *dev, struct net_device *master); diff --git a/net/core/dev.c b/net/core/dev.c index bddb2f2ccaa..53a9fefbc9a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4600,6 +4600,232 @@ static int __init dev_proc_init(void) #endif /* CONFIG_PROC_FS */ +struct netdev_upper { + struct net_device *dev; + bool master; + struct list_head list; + struct rcu_head rcu; + struct list_head search_list; +}; + +static void __append_search_uppers(struct list_head *search_list, + struct net_device *dev) +{ + struct netdev_upper *upper; + + list_for_each_entry(upper, &dev->upper_dev_list, list) { + /* check if this upper is not already in search list */ + if (list_empty(&upper->search_list)) + list_add_tail(&upper->search_list, search_list); + } +} + +static bool __netdev_search_upper_dev(struct net_device *dev, + struct net_device *upper_dev) +{ + LIST_HEAD(search_list); + struct netdev_upper *upper; + struct netdev_upper *tmp; + bool ret = false; + + __append_search_uppers(&search_list, dev); + list_for_each_entry(upper, &search_list, search_list) { + if (upper->dev == upper_dev) { + ret = true; + break; + } + __append_search_uppers(&search_list, upper->dev); + } + list_for_each_entry_safe(upper, tmp, &search_list, search_list) + INIT_LIST_HEAD(&upper->search_list); + return ret; +} + +static struct netdev_upper *__netdev_find_upper(struct net_device *dev, + struct net_device *upper_dev) +{ + struct netdev_upper *upper; + + list_for_each_entry(upper, &dev->upper_dev_list, list) { + if (upper->dev == upper_dev) + return upper; + } + return NULL; +} + +/** + * netdev_has_upper_dev - Check if device is linked to an upper device + * @dev: device + * @upper_dev: upper device to check + * + * Find out if a device is linked to specified upper device and return true + * in case it is. Note that this checks only immediate upper device, + * not through a complete stack of devices. The caller must hold the RTNL lock. + */ +bool netdev_has_upper_dev(struct net_device *dev, + struct net_device *upper_dev) +{ + ASSERT_RTNL(); + + return __netdev_find_upper(dev, upper_dev); +} +EXPORT_SYMBOL(netdev_has_upper_dev); + +/** + * netdev_has_any_upper_dev - Check if device is linked to some device + * @dev: device + * + * Find out if a device is linked to an upper device and return true in case + * it is. The caller must hold the RTNL lock. + */ +bool netdev_has_any_upper_dev(struct net_device *dev) +{ + ASSERT_RTNL(); + + return !list_empty(&dev->upper_dev_list); +} +EXPORT_SYMBOL(netdev_has_any_upper_dev); + +/** + * netdev_master_upper_dev_get - Get master upper device + * @dev: device + * + * Find a master upper device and return pointer to it or NULL in case + * it's not there. The caller must hold the RTNL lock. + */ +struct net_device *netdev_master_upper_dev_get(struct net_device *dev) +{ + struct netdev_upper *upper; + + ASSERT_RTNL(); + + if (list_empty(&dev->upper_dev_list)) + return NULL; + + upper = list_first_entry(&dev->upper_dev_list, + struct netdev_upper, list); + if (likely(upper->master)) + return upper->dev; + return NULL; +} +EXPORT_SYMBOL(netdev_master_upper_dev_get); + +/** + * netdev_master_upper_dev_get_rcu - Get master upper device + * @dev: device + * + * Find a master upper device and return pointer to it or NULL in case + * it's not there. The caller must hold the RCU read lock. + */ +struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) +{ + struct netdev_upper *upper; + + upper = list_first_or_null_rcu(&dev->upper_dev_list, + struct netdev_upper, list); + if (upper && likely(upper->master)) + return upper->dev; + return NULL; +} +EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); + +static int __netdev_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev, bool master) +{ + struct netdev_upper *upper; + + ASSERT_RTNL(); + + if (dev == upper_dev) + return -EBUSY; + + /* To prevent loops, check if dev is not upper device to upper_dev. */ + if (__netdev_search_upper_dev(upper_dev, dev)) + return -EBUSY; + + if (__netdev_find_upper(dev, upper_dev)) + return -EEXIST; + + if (master && netdev_master_upper_dev_get(dev)) + return -EBUSY; + + upper = kmalloc(sizeof(*upper), GFP_KERNEL); + if (!upper) + return -ENOMEM; + + upper->dev = upper_dev; + upper->master = master; + INIT_LIST_HEAD(&upper->search_list); + + /* Ensure that master upper link is always the first item in list. */ + if (master) + list_add_rcu(&upper->list, &dev->upper_dev_list); + else + list_add_tail_rcu(&upper->list, &dev->upper_dev_list); + dev_hold(upper_dev); + + return 0; +} + +/** + * netdev_upper_dev_link - Add a link to the upper device + * @dev: device + * @upper_dev: new upper device + * + * Adds a link to device which is upper to this one. The caller must hold + * the RTNL lock. On a failure a negative errno code is returned. + * On success the reference counts are adjusted and the function + * returns zero. + */ +int netdev_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev) +{ + return __netdev_upper_dev_link(dev, upper_dev, false); +} +EXPORT_SYMBOL(netdev_upper_dev_link); + +/** + * netdev_master_upper_dev_link - Add a master link to the upper device + * @dev: device + * @upper_dev: new upper device + * + * Adds a link to device which is upper to this one. In this case, only + * one master upper device can be linked, although other non-master devices + * might be linked as well. The caller must hold the RTNL lock. + * On a failure a negative errno code is returned. On success the reference + * counts are adjusted and the function returns zero. + */ +int netdev_master_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev) +{ + return __netdev_upper_dev_link(dev, upper_dev, true); +} +EXPORT_SYMBOL(netdev_master_upper_dev_link); + +/** + * netdev_upper_dev_unlink - Removes a link to upper device + * @dev: device + * @upper_dev: new upper device + * + * Removes a link to device which is upper to this one. The caller must hold + * the RTNL lock. + */ +void netdev_upper_dev_unlink(struct net_device *dev, + struct net_device *upper_dev) +{ + struct netdev_upper *upper; + + ASSERT_RTNL(); + + upper = __netdev_find_upper(dev, upper_dev); + if (!upper) + return; + list_del_rcu(&upper->list); + dev_put(upper_dev); + kfree_rcu(upper, rcu); +} +EXPORT_SYMBOL(netdev_upper_dev_unlink); + /** * netdev_set_master - set up master pointer * @slave: slave device @@ -4613,19 +4839,23 @@ static int __init dev_proc_init(void) int netdev_set_master(struct net_device *slave, struct net_device *master) { struct net_device *old = slave->master; + int err; ASSERT_RTNL(); if (master) { if (old) return -EBUSY; - dev_hold(master); + err = netdev_master_upper_dev_link(slave, master); + if (err) + return err; } slave->master = master; if (old) - dev_put(old); + netdev_upper_dev_unlink(slave, master); + return 0; } EXPORT_SYMBOL(netdev_set_master); @@ -5503,8 +5733,8 @@ static void rollback_registered_many(struct list_head *head) if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); - /* Notifier chain MUST detach us from master device. */ - WARN_ON(dev->master); + /* Notifier chain MUST detach us all upper devices. */ + WARN_ON(netdev_has_any_upper_dev(dev)); /* Remove entries from kobject tree */ netdev_unregister_kobject(dev); @@ -6212,6 +6442,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); INIT_LIST_HEAD(&dev->link_watch_list); + INIT_LIST_HEAD(&dev->upper_dev_list); dev->priv_flags = IFF_XMIT_DST_RELEASE; setup(dev); -- cgit v1.2.3-70-g09d2 From 898e506171b2c6132cdebd450ab4db81ae9a59bc Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Jan 2013 22:48:52 +0000 Subject: rtnetlink: remove usage of dev->master Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 69 ++++++++++++++++++++++++++++------------------------ 1 file changed, 37 insertions(+), 32 deletions(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 78d05a9dcea..d26becbcddc 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -880,6 +880,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, const struct rtnl_link_stats64 *stats; struct nlattr *attr, *af_spec; struct rtnl_af_ops *af_ops; + struct net_device *upper_dev = netdev_master_upper_dev_get(dev); ASSERT_RTNL(); nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); @@ -908,8 +909,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, #endif (dev->ifindex != dev->iflink && nla_put_u32(skb, IFLA_LINK, dev->iflink)) || - (dev->master && - nla_put_u32(skb, IFLA_MASTER, dev->master->ifindex)) || + (upper_dev && + nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex)) || nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) || (dev->qdisc && nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) || @@ -1273,16 +1274,16 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) static int do_set_master(struct net_device *dev, int ifindex) { - struct net_device *master_dev; + struct net_device *upper_dev = netdev_master_upper_dev_get(dev); const struct net_device_ops *ops; int err; - if (dev->master) { - if (dev->master->ifindex == ifindex) + if (upper_dev) { + if (upper_dev->ifindex == ifindex) return 0; - ops = dev->master->netdev_ops; + ops = upper_dev->netdev_ops; if (ops->ndo_del_slave) { - err = ops->ndo_del_slave(dev->master, dev); + err = ops->ndo_del_slave(upper_dev, dev); if (err) return err; } else { @@ -1291,12 +1292,12 @@ static int do_set_master(struct net_device *dev, int ifindex) } if (ifindex) { - master_dev = __dev_get_by_index(dev_net(dev), ifindex); - if (!master_dev) + upper_dev = __dev_get_by_index(dev_net(dev), ifindex); + if (!upper_dev) return -EINVAL; - ops = master_dev->netdev_ops; + ops = upper_dev->netdev_ops; if (ops->ndo_add_slave) { - err = ops->ndo_add_slave(master_dev, dev); + err = ops->ndo_add_slave(upper_dev, dev); if (err) return err; } else { @@ -2048,7 +2049,6 @@ errout: static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); - struct net_device *master = NULL; struct ndmsg *ndm; struct nlattr *tb[NDA_MAX+1]; struct net_device *dev; @@ -2090,10 +2090,10 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) /* Support fdb on master device the net/bridge default case */ if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && (dev->priv_flags & IFF_BRIDGE_PORT)) { - master = dev->master; - err = master->netdev_ops->ndo_fdb_add(ndm, tb, - dev, addr, - nlh->nlmsg_flags); + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + const struct net_device_ops *ops = br_dev->netdev_ops; + + err = ops->ndo_fdb_add(ndm, tb, dev, addr, nlh->nlmsg_flags); if (err) goto out; else @@ -2154,10 +2154,11 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) /* Support fdb on master device the net/bridge default case */ if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && (dev->priv_flags & IFF_BRIDGE_PORT)) { - struct net_device *master = dev->master; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + const struct net_device_ops *ops = br_dev->netdev_ops; - if (master->netdev_ops->ndo_fdb_del) - err = master->netdev_ops->ndo_fdb_del(ndm, dev, addr); + if (ops->ndo_fdb_del) + err = ops->ndo_fdb_del(ndm, dev, addr); if (err) goto out; @@ -2241,9 +2242,11 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); for_each_netdev_rcu(net, dev) { if (dev->priv_flags & IFF_BRIDGE_PORT) { - struct net_device *master = dev->master; - const struct net_device_ops *ops = master->netdev_ops; + struct net_device *br_dev; + const struct net_device_ops *ops; + br_dev = netdev_master_upper_dev_get(dev); + ops = br_dev->netdev_ops; if (ops->ndo_fdb_dump) idx = ops->ndo_fdb_dump(skb, cb, dev, idx); } @@ -2264,6 +2267,7 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct ifinfomsg *ifm; struct nlattr *br_afspec; u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), NLM_F_MULTI); if (nlh == NULL) @@ -2281,8 +2285,8 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, if (nla_put_string(skb, IFLA_IFNAME, dev->name) || nla_put_u32(skb, IFLA_MTU, dev->mtu) || nla_put_u8(skb, IFLA_OPERSTATE, operstate) || - (dev->master && - nla_put_u32(skb, IFLA_MASTER, dev->master->ifindex)) || + (br_dev && + nla_put_u32(skb, IFLA_MASTER, br_dev->ifindex)) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || (dev->ifindex != dev->iflink && @@ -2318,11 +2322,11 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); for_each_netdev_rcu(net, dev) { const struct net_device_ops *ops = dev->netdev_ops; - struct net_device *master = dev->master; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); - if (master && master->netdev_ops->ndo_bridge_getlink) { + if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { if (idx >= cb->args[0] && - master->netdev_ops->ndo_bridge_getlink( + br_dev->netdev_ops->ndo_bridge_getlink( skb, portid, seq, dev) < 0) break; idx++; @@ -2359,7 +2363,7 @@ static inline size_t bridge_nlmsg_size(void) static int rtnl_bridge_notify(struct net_device *dev, u16 flags) { struct net *net = dev_net(dev); - struct net_device *master = dev->master; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); struct sk_buff *skb; int err = -EOPNOTSUPP; @@ -2370,8 +2374,8 @@ static int rtnl_bridge_notify(struct net_device *dev, u16 flags) } if ((!flags || (flags & BRIDGE_FLAGS_MASTER)) && - master && master->netdev_ops->ndo_bridge_getlink) { - err = master->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev); + br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { + err = br_dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev); if (err < 0) goto errout; } @@ -2430,13 +2434,14 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, oflags = flags; if (!flags || (flags & BRIDGE_FLAGS_MASTER)) { - if (!dev->master || - !dev->master->netdev_ops->ndo_bridge_setlink) { + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + + if (!br_dev || !br_dev->netdev_ops->ndo_bridge_setlink) { err = -EOPNOTSUPP; goto out; } - err = dev->master->netdev_ops->ndo_bridge_setlink(dev, nlh); + err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh); if (err) goto out; -- cgit v1.2.3-70-g09d2 From 49bd8fb0b18944fc0b6b11d999619d3687c3914a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Jan 2013 22:48:55 +0000 Subject: netpoll: remove usage of dev->master Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/netpoll.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'net/core') diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 3151acf5ec1..d2bda8eb08e 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -210,9 +210,12 @@ static void netpoll_poll_dev(struct net_device *dev) if (dev->flags & IFF_SLAVE) { if (ni) { - struct net_device *bond_dev = dev->master; + struct net_device *bond_dev; struct sk_buff *skb; - struct netpoll_info *bond_ni = rcu_dereference_bh(bond_dev->npinfo); + struct netpoll_info *bond_ni; + + bond_dev = netdev_master_upper_dev_get_rcu(dev); + bond_ni = rcu_dereference_bh(bond_dev->npinfo); while ((skb = skb_dequeue(&ni->arp_tx))) { skb->dev = bond_dev; skb_queue_tail(&bond_ni->arp_tx, skb); @@ -815,7 +818,7 @@ int netpoll_setup(struct netpoll *np) return -ENODEV; } - if (ndev->master) { + if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", np->dev_name); err = -EBUSY; goto put; -- cgit v1.2.3-70-g09d2 From 471cb5a33dcbd7c529684a2ac7ba4451414ee4a7 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Jan 2013 22:49:01 +0000 Subject: bonding: remove usage of dev->master Benefit from new upper dev list and free bonding from dev->master usage. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/bonding/bond_3ad.c | 30 ++++++------- drivers/net/bonding/bond_alb.c | 6 +-- drivers/net/bonding/bond_main.c | 94 ++++++++++++++++++++++++----------------- drivers/net/bonding/bonding.h | 14 +++--- net/core/rtnetlink.c | 1 + 5 files changed, 81 insertions(+), 64 deletions(-) (limited to 'net/core') diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index a030e635f00..84fabd69df4 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -1127,7 +1127,7 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) // INFO_RECEIVED_LOOPBACK_FRAMES pr_err("%s: An illegal loopback occurred on adapter (%s).\n" "Check the configuration to verify that all adapters are connected to 802.3ad compliant switch ports\n", - port->slave->dev->master->name, port->slave->dev->name); + port->slave->bond->dev->name, port->slave->dev->name); return; } __update_selected(lacpdu, port); @@ -1306,7 +1306,7 @@ static void ad_port_selection_logic(struct port *port) } if (!curr_port) { // meaning: the port was related to an aggregator but was not on the aggregator port list pr_warning("%s: Warning: Port %d (on %s) was related to aggregator %d but was not on its port list\n", - port->slave->dev->master->name, + port->slave->bond->dev->name, port->actor_port_number, port->slave->dev->name, port->aggregator->aggregator_identifier); @@ -1386,7 +1386,7 @@ static void ad_port_selection_logic(struct port *port) port->aggregator->aggregator_identifier); } else { pr_err("%s: Port %d (on %s) did not find a suitable aggregator\n", - port->slave->dev->master->name, + port->slave->bond->dev->name, port->actor_port_number, port->slave->dev->name); } } @@ -1463,7 +1463,7 @@ static struct aggregator *ad_agg_selection_test(struct aggregator *best, default: pr_warning("%s: Impossible agg select mode %d\n", - curr->slave->dev->master->name, + curr->slave->bond->dev->name, __get_agg_selection_mode(curr->lag_ports)); break; } @@ -1571,7 +1571,7 @@ static void ad_agg_selection_logic(struct aggregator *agg) // check if any partner replys if (best->is_individual) { pr_warning("%s: Warning: No 802.3ad response from the link partner for any adapters in the bond\n", - best->slave ? best->slave->dev->master->name : "NULL"); + best->slave ? best->slave->bond->dev->name : "NULL"); } best->is_active = 1; @@ -1898,7 +1898,7 @@ int bond_3ad_bind_slave(struct slave *slave) if (bond == NULL) { pr_err("%s: The slave %s is not attached to its bond\n", - slave->dev->master->name, slave->dev->name); + slave->bond->dev->name, slave->dev->name); return -1; } @@ -1973,7 +1973,7 @@ void bond_3ad_unbind_slave(struct slave *slave) // if slave is null, the whole port is not initialized if (!port->slave) { pr_warning("Warning: %s: Trying to unbind an uninitialized port on %s\n", - slave->dev->master->name, slave->dev->name); + slave->bond->dev->name, slave->dev->name); return; } @@ -2009,7 +2009,7 @@ void bond_3ad_unbind_slave(struct slave *slave) if ((new_aggregator->lag_ports == port) && new_aggregator->is_active) { pr_info("%s: Removing an active aggregator\n", - aggregator->slave->dev->master->name); + aggregator->slave->bond->dev->name); // select new active aggregator select_new_active_agg = 1; } @@ -2040,7 +2040,7 @@ void bond_3ad_unbind_slave(struct slave *slave) ad_agg_selection_logic(__get_first_agg(port)); } else { pr_warning("%s: Warning: unbinding aggregator, and could not find a new aggregator for its ports\n", - slave->dev->master->name); + slave->bond->dev->name); } } else { // in case that the only port related to this aggregator is the one we want to remove select_new_active_agg = aggregator->is_active; @@ -2048,7 +2048,7 @@ void bond_3ad_unbind_slave(struct slave *slave) ad_clear_agg(aggregator); if (select_new_active_agg) { pr_info("%s: Removing an active aggregator\n", - slave->dev->master->name); + slave->bond->dev->name); // select new active aggregator ad_agg_selection_logic(__get_first_agg(port)); } @@ -2076,7 +2076,7 @@ void bond_3ad_unbind_slave(struct slave *slave) ad_clear_agg(temp_aggregator); if (select_new_active_agg) { pr_info("%s: Removing an active aggregator\n", - slave->dev->master->name); + slave->bond->dev->name); // select new active aggregator ad_agg_selection_logic(__get_first_agg(port)); } @@ -2184,7 +2184,7 @@ static int bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, u1 if (!port->slave) { pr_warning("%s: Warning: port of slave %s is uninitialized\n", - slave->dev->name, slave->dev->master->name); + slave->dev->name, slave->bond->dev->name); return ret; } @@ -2240,7 +2240,7 @@ void bond_3ad_adapter_speed_changed(struct slave *slave) // if slave is null, the whole port is not initialized if (!port->slave) { pr_warning("Warning: %s: speed changed for uninitialized port on %s\n", - slave->dev->master->name, slave->dev->name); + slave->bond->dev->name, slave->dev->name); return; } @@ -2268,7 +2268,7 @@ void bond_3ad_adapter_duplex_changed(struct slave *slave) // if slave is null, the whole port is not initialized if (!port->slave) { pr_warning("%s: Warning: duplex changed for uninitialized port on %s\n", - slave->dev->master->name, slave->dev->name); + slave->bond->dev->name, slave->dev->name); return; } @@ -2297,7 +2297,7 @@ void bond_3ad_handle_link_change(struct slave *slave, char link) // if slave is null, the whole port is not initialized if (!port->slave) { pr_warning("Warning: %s: link status changed for uninitialized port on %s\n", - slave->dev->master->name, slave->dev->name); + slave->bond->dev->name, slave->dev->name); return; } diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 7c9d136e74b..f5e05272302 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -507,7 +507,7 @@ static void rlb_update_client(struct rlb_client_info *client_info) client_info->mac_dst); if (!skb) { pr_err("%s: Error: failed to create an ARP packet\n", - client_info->slave->dev->master->name); + client_info->slave->bond->dev->name); continue; } @@ -517,7 +517,7 @@ static void rlb_update_client(struct rlb_client_info *client_info) skb = vlan_put_tag(skb, client_info->vlan_id); if (!skb) { pr_err("%s: Error: failed to insert VLAN tag\n", - client_info->slave->dev->master->name); + client_info->slave->bond->dev->name); continue; } } @@ -1043,7 +1043,7 @@ static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[]) if (dev_set_mac_address(dev, &s_addr)) { pr_err("%s: Error: dev_set_mac_address of dev %s failed!\n" "ALB mode requires that the base driver support setting the hw address also when the network device's interface is open\n", - dev->master->name, dev->name); + slave->bond->dev->name, dev->name); return -EOPNOTSUPP; } return 0; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b7d45f367d4..c4952985c08 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -746,11 +746,9 @@ static void __bond_resend_igmp_join_requests(struct net_device *dev) { struct in_device *in_dev; - rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) ip_mc_rejoin_groups(in_dev); - rcu_read_unlock(); } /* @@ -760,9 +758,10 @@ static void __bond_resend_igmp_join_requests(struct net_device *dev) */ static void bond_resend_igmp_join_requests(struct bonding *bond) { - struct net_device *bond_dev, *vlan_dev, *master_dev; + struct net_device *bond_dev, *vlan_dev, *upper_dev; struct vlan_entry *vlan; + rcu_read_lock(); read_lock(&bond->lock); bond_dev = bond->dev; @@ -774,18 +773,14 @@ static void bond_resend_igmp_join_requests(struct bonding *bond) * if bond is enslaved to a bridge, * then rejoin all groups on its master */ - master_dev = bond_dev->master; - if (master_dev) - if ((master_dev->priv_flags & IFF_EBRIDGE) - && (bond_dev->priv_flags & IFF_BRIDGE_PORT)) - __bond_resend_igmp_join_requests(master_dev); + upper_dev = netdev_master_upper_dev_get_rcu(bond_dev); + if (upper_dev && upper_dev->priv_flags & IFF_EBRIDGE) + __bond_resend_igmp_join_requests(upper_dev); /* rejoin all groups on vlan devices */ list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - rcu_read_lock(); vlan_dev = __vlan_find_dev_deep(bond_dev, vlan->vlan_id); - rcu_read_unlock(); if (vlan_dev) __bond_resend_igmp_join_requests(vlan_dev); } @@ -794,13 +789,16 @@ static void bond_resend_igmp_join_requests(struct bonding *bond) queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5); read_unlock(&bond->lock); + rcu_read_unlock(); } static void bond_resend_igmp_join_requests_delayed(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, mcast_work.work); + rcu_read_lock(); bond_resend_igmp_join_requests(bond); + rcu_read_unlock(); } /* @@ -1493,6 +1491,27 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) return ret; } +static int bond_master_upper_dev_link(struct net_device *bond_dev, + struct net_device *slave_dev) +{ + int err; + + err = netdev_master_upper_dev_link(slave_dev, bond_dev); + if (err) + return err; + slave_dev->flags |= IFF_SLAVE; + rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE); + return 0; +} + +static void bond_upper_dev_unlink(struct net_device *bond_dev, + struct net_device *slave_dev) +{ + netdev_upper_dev_unlink(slave_dev, bond_dev); + slave_dev->flags &= ~IFF_SLAVE; + rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE); +} + /* enslave device to bond device */ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) { @@ -1655,9 +1674,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } } - res = netdev_set_bond_master(slave_dev, bond_dev); + res = bond_master_upper_dev_link(bond_dev, slave_dev); if (res) { - pr_debug("Error %d calling netdev_set_bond_master\n", res); + pr_debug("Error %d calling bond_master_upper_dev_link\n", res); goto err_restore_mac; } @@ -1891,7 +1910,7 @@ err_close: dev_close(slave_dev); err_unset_master: - netdev_set_bond_master(slave_dev, NULL); + bond_upper_dev_unlink(bond_dev, slave_dev); err_restore_mac: if (!bond->params.fail_over_mac) { @@ -1936,7 +1955,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) /* slave is not a slave or master is not master of this slave */ if (!(slave_dev->flags & IFF_SLAVE) || - (slave_dev->master != bond_dev)) { + !netdev_has_upper_dev(slave_dev, bond_dev)) { pr_err("%s: Error: cannot release %s.\n", bond_dev->name, slave_dev->name); return -EINVAL; @@ -2080,7 +2099,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) netif_addr_unlock_bh(bond_dev); } - netdev_set_bond_master(slave_dev, NULL); + bond_upper_dev_unlink(bond_dev, slave_dev); slave_disable_netpoll(slave); @@ -2195,7 +2214,7 @@ static int bond_release_all(struct net_device *bond_dev) netif_addr_unlock_bh(bond_dev); } - netdev_set_bond_master(slave_dev, NULL); + bond_upper_dev_unlink(bond_dev, slave_dev); slave_disable_netpoll(slave); @@ -2259,8 +2278,9 @@ static int bond_ioctl_change_active(struct net_device *bond_dev, struct net_devi if (!USES_PRIMARY(bond->params.mode)) return -EINVAL; - /* Verify that master_dev is indeed the master of slave_dev */ - if (!(slave_dev->flags & IFF_SLAVE) || (slave_dev->master != bond_dev)) + /* Verify that bond_dev is indeed the master of slave_dev */ + if (!(slave_dev->flags & IFF_SLAVE) || + !netdev_has_upper_dev(slave_dev, bond_dev)) return -EINVAL; read_lock(&bond->lock); @@ -3258,36 +3278,32 @@ static int bond_master_netdev_event(unsigned long event, static int bond_slave_netdev_event(unsigned long event, struct net_device *slave_dev) { - struct net_device *bond_dev = slave_dev->master; - struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave = NULL; + struct slave *slave = bond_slave_get_rtnl(slave_dev); + struct bonding *bond = slave->bond; + struct net_device *bond_dev = slave->bond->dev; + u32 old_speed; + u8 old_duplex; switch (event) { case NETDEV_UNREGISTER: - if (bond_dev) { - if (bond->setup_by_slave) - bond_release_and_destroy(bond_dev, slave_dev); - else - bond_release(bond_dev, slave_dev); - } + if (bond->setup_by_slave) + bond_release_and_destroy(bond_dev, slave_dev); + else + bond_release(bond_dev, slave_dev); break; case NETDEV_UP: case NETDEV_CHANGE: - slave = bond_get_slave_by_dev(bond, slave_dev); - if (slave) { - u32 old_speed = slave->speed; - u8 old_duplex = slave->duplex; + old_speed = slave->speed; + old_duplex = slave->duplex; - bond_update_speed_duplex(slave); + bond_update_speed_duplex(slave); - if (bond->params.mode == BOND_MODE_8023AD) { - if (old_speed != slave->speed) - bond_3ad_adapter_speed_changed(slave); - if (old_duplex != slave->duplex) - bond_3ad_adapter_duplex_changed(slave); - } + if (bond->params.mode == BOND_MODE_8023AD) { + if (old_speed != slave->speed) + bond_3ad_adapter_speed_changed(slave); + if (old_duplex != slave->duplex) + bond_3ad_adapter_duplex_changed(slave); } - break; case NETDEV_DOWN: /* diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 21b68e5c14f..0d282d20b5a 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -258,6 +258,9 @@ static inline bool bond_vlan_used(struct bonding *bond) #define bond_slave_get_rcu(dev) \ ((struct slave *) rcu_dereference(dev->rx_handler_data)) +#define bond_slave_get_rtnl(dev) \ + ((struct slave *) rtnl_dereference(dev->rx_handler_data)) + /** * Returns NULL if the net_device does not belong to any of the bond's slaves * @@ -280,11 +283,9 @@ static inline struct slave *bond_get_slave_by_dev(struct bonding *bond, static inline struct bonding *bond_get_bond_by_slave(struct slave *slave) { - if (!slave || !slave->dev->master) { + if (!slave || !slave->bond) return NULL; - } - - return netdev_priv(slave->dev->master); + return slave->bond; } static inline bool bond_is_lb(const struct bonding *bond) @@ -360,10 +361,9 @@ static inline void bond_netpoll_send_skb(const struct slave *slave, static inline void bond_set_slave_inactive_flags(struct slave *slave) { - struct bonding *bond = netdev_priv(slave->dev->master); - if (!bond_is_lb(bond)) + if (!bond_is_lb(slave->bond)) bond_set_backup_slave(slave); - if (!bond->params.all_slaves_active) + if (!slave->bond->params.all_slaves_active) slave->inactive = 1; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d26becbcddc..9969afb8227 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1987,6 +1987,7 @@ errout: if (err < 0) rtnl_set_sk_err(net, RTNLGRP_LINK, err); } +EXPORT_SYMBOL(rtmsg_ifinfo); static int nlmsg_populate_fdb_fill(struct sk_buff *skb, struct net_device *dev, -- cgit v1.2.3-70-g09d2 From 8b98a70c28a607a02b3c3d41bc9a4c141f421052 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Jan 2013 22:49:02 +0000 Subject: net: remove no longer used netdev_set_bond_master() and netdev_set_master() Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 +---- net/core/dev.c | 63 ----------------------------------------------- 2 files changed, 1 insertion(+), 68 deletions(-) (limited to 'net/core') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e324601f48e..3cad8eab02b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -858,8 +858,7 @@ struct netdev_fcoe_hbainfo { * flow_id is a flow ID to be passed to rps_may_expire_flow() later. * Return the filter ID on success, or a negative error code. * - * Slave management functions (for bridge, bonding, etc). User should - * call netdev_set_master() to set dev->master properly. + * Slave management functions (for bridge, bonding, etc). * int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev); * Called to make another netdev an underling. * @@ -2650,9 +2649,6 @@ extern int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev); extern void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); -extern int netdev_set_master(struct net_device *dev, struct net_device *master); -extern int netdev_set_bond_master(struct net_device *dev, - struct net_device *master); extern int skb_checksum_help(struct sk_buff *skb); extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features); diff --git a/net/core/dev.c b/net/core/dev.c index 53a9fefbc9a..a51ccf46e8b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4826,69 +4826,6 @@ void netdev_upper_dev_unlink(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_dev_unlink); -/** - * netdev_set_master - set up master pointer - * @slave: slave device - * @master: new master device - * - * Changes the master device of the slave. Pass %NULL to break the - * bonding. The caller must hold the RTNL semaphore. On a failure - * a negative errno code is returned. On success the reference counts - * are adjusted and the function returns zero. - */ -int netdev_set_master(struct net_device *slave, struct net_device *master) -{ - struct net_device *old = slave->master; - int err; - - ASSERT_RTNL(); - - if (master) { - if (old) - return -EBUSY; - err = netdev_master_upper_dev_link(slave, master); - if (err) - return err; - } - - slave->master = master; - - if (old) - netdev_upper_dev_unlink(slave, master); - - return 0; -} -EXPORT_SYMBOL(netdev_set_master); - -/** - * netdev_set_bond_master - set up bonding master/slave pair - * @slave: slave device - * @master: new master device - * - * Changes the master device of the slave. Pass %NULL to break the - * bonding. The caller must hold the RTNL semaphore. On a failure - * a negative errno code is returned. On success %RTM_NEWLINK is sent - * to the routing socket and the function returns zero. - */ -int netdev_set_bond_master(struct net_device *slave, struct net_device *master) -{ - int err; - - ASSERT_RTNL(); - - err = netdev_set_master(slave, master); - if (err) - return err; - if (master) - slave->flags |= IFF_SLAVE; - else - slave->flags &= ~IFF_SLAVE; - - rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE); - return 0; -} -EXPORT_SYMBOL(netdev_set_bond_master); - static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; -- cgit v1.2.3-70-g09d2 From 2afb9b533423a9b97f84181e773cf9361d98fed6 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sun, 6 Jan 2013 12:41:57 +0000 Subject: ethtool: set addr_assign_type to NET_ADDR_SET when addr is passed on create In case user passed address via netlink during create, NET_ADDR_PERM was set. That is not correct so fix this by setting NET_ADDR_SET. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 9969afb8227..9a419b09948 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1667,9 +1667,11 @@ struct net_device *rtnl_create_link(struct net *net, if (tb[IFLA_MTU]) dev->mtu = nla_get_u32(tb[IFLA_MTU]); - if (tb[IFLA_ADDRESS]) + if (tb[IFLA_ADDRESS]) { memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]), nla_len(tb[IFLA_ADDRESS])); + dev->addr_assign_type = NET_ADDR_SET; + } if (tb[IFLA_BROADCAST]) memcpy(dev->broadcast, nla_data(tb[IFLA_BROADCAST]), nla_len(tb[IFLA_BROADCAST])); -- cgit v1.2.3-70-g09d2 From 9ca1b22d6d228177e6f929f6818a1cd3d5e30c4a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 5 Jan 2013 21:31:18 +0000 Subject: net: splice: avoid high order page splitting splice() can handle pages of any order, but network code tries hard to split them in PAGE_SIZE units. Not quite successfully anyway, as __splice_segment() assumed poff < PAGE_SIZE. This is true for the skb->data part, not necessarily for the fragments. This patch removes this logic to give the pages as they are in the skb. Signed-off-by: Eric Dumazet Cc: Willy Tarreau Signed-off-by: David S. Miller --- net/core/skbuff.c | 38 +++++++++----------------------------- 1 file changed, 9 insertions(+), 29 deletions(-) (limited to 'net/core') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index bc96100fe23..b03fc0c6a95 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1707,20 +1707,6 @@ static bool spd_fill_page(struct splice_pipe_desc *spd, return false; } -static inline void __segment_seek(struct page **page, unsigned int *poff, - unsigned int *plen, unsigned int off) -{ - unsigned long n; - - *poff += off; - n = *poff / PAGE_SIZE; - if (n) - *page = nth_page(*page, n); - - *poff = *poff % PAGE_SIZE; - *plen -= off; -} - static bool __splice_segment(struct page *page, unsigned int poff, unsigned int plen, unsigned int *off, unsigned int *len, struct sk_buff *skb, @@ -1728,6 +1714,8 @@ static bool __splice_segment(struct page *page, unsigned int poff, struct sock *sk, struct pipe_inode_info *pipe) { + unsigned int flen; + if (!*len) return true; @@ -1738,24 +1726,16 @@ static bool __splice_segment(struct page *page, unsigned int poff, } /* ignore any bits we already processed */ - if (*off) { - __segment_seek(&page, &poff, &plen, *off); - *off = 0; - } - - do { - unsigned int flen = min(*len, plen); + poff += *off; + plen -= *off; + *off = 0; - /* the linear region may spread across several pages */ - flen = min_t(unsigned int, flen, PAGE_SIZE - poff); + flen = min(*len, plen); - if (spd_fill_page(spd, pipe, page, &flen, poff, skb, linear, sk)) - return true; - - __segment_seek(&page, &poff, &plen, flen); - *len -= flen; + if (spd_fill_page(spd, pipe, page, &flen, poff, skb, linear, sk)) + return true; - } while (*len && plen); + *len -= flen; return false; } -- cgit v1.2.3-70-g09d2 From c03a14e8db06d6687f470f9769f47aa5764b1fe3 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 7 Jan 2013 09:02:08 +0000 Subject: ethtool: consolidate work with ethtool_ops No need to check if ethtool_ops == NULL since it can't be. Use local variable "ops" in functions where it is present instead of dev->ethtool_ops Introduce local variable "ops" in functions where dev->ethtool_ops is used many times. Signed-off-by: Jiri Pirko Reviewed-by: Ben Hutchings Reviewed-by: Flavio Leitner Signed-off-by: David S. Miller --- net/core/ethtool.c | 45 +++++++++++++++++++++------------------------ 1 file changed, 21 insertions(+), 24 deletions(-) (limited to 'net/core') diff --git a/net/core/ethtool.c b/net/core/ethtool.c index a8705432e4b..d9d55209db6 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -175,7 +175,7 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset) if (sset == ETH_SS_FEATURES) return ARRAY_SIZE(netdev_features_strings); - if (ops && ops->get_sset_count && ops->get_strings) + if (ops->get_sset_count && ops->get_strings) return ops->get_sset_count(dev, sset); else return -EOPNOTSUPP; @@ -311,7 +311,7 @@ int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { ASSERT_RTNL(); - if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings) + if (!dev->ethtool_ops->get_settings) return -EOPNOTSUPP; memset(cmd, 0, sizeof(struct ethtool_cmd)); @@ -355,7 +355,7 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, memset(&info, 0, sizeof(info)); info.cmd = ETHTOOL_GDRVINFO; - if (ops && ops->get_drvinfo) { + if (ops->get_drvinfo) { ops->get_drvinfo(dev, &info); } else if (dev->dev.parent && dev->dev.parent->driver) { strlcpy(info.bus_info, dev_name(dev->dev.parent), @@ -370,7 +370,7 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, * this method of obtaining string set info is deprecated; * Use ETHTOOL_GSSET_INFO instead. */ - if (ops && ops->get_sset_count) { + if (ops->get_sset_count) { int rc; rc = ops->get_sset_count(dev, ETH_SS_TEST); @@ -383,9 +383,9 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, if (rc >= 0) info.n_priv_flags = rc; } - if (ops && ops->get_regs_len) + if (ops->get_regs_len) info.regdump_len = ops->get_regs_len(dev); - if (ops && ops->get_eeprom_len) + if (ops->get_eeprom_len) info.eedump_len = ops->get_eeprom_len(dev); if (copy_to_user(useraddr, &info, sizeof(info))) @@ -590,13 +590,14 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, struct ethtool_rxnfc rx_rings; u32 user_size, dev_size, i; u32 *indir; + const struct ethtool_ops *ops = dev->ethtool_ops; int ret; - if (!dev->ethtool_ops->get_rxfh_indir_size || - !dev->ethtool_ops->set_rxfh_indir || - !dev->ethtool_ops->get_rxnfc) + if (!ops->get_rxfh_indir_size || !ops->set_rxfh_indir || + !ops->get_rxnfc) return -EOPNOTSUPP; - dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev); + + dev_size = ops->get_rxfh_indir_size(dev); if (dev_size == 0) return -EOPNOTSUPP; @@ -613,7 +614,7 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, return -ENOMEM; rx_rings.cmd = ETHTOOL_GRXRINGS; - ret = dev->ethtool_ops->get_rxnfc(dev, &rx_rings, NULL); + ret = ops->get_rxnfc(dev, &rx_rings, NULL); if (ret) goto out; @@ -639,7 +640,7 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, } } - ret = dev->ethtool_ops->set_rxfh_indir(dev, indir); + ret = ops->set_rxfh_indir(dev, indir); out: kfree(indir); @@ -1082,9 +1083,10 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) { struct ethtool_value id; static bool busy; + const struct ethtool_ops *ops = dev->ethtool_ops; int rc; - if (!dev->ethtool_ops->set_phys_id) + if (!ops->set_phys_id) return -EOPNOTSUPP; if (busy) @@ -1093,7 +1095,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) if (copy_from_user(&id, useraddr, sizeof(id))) return -EFAULT; - rc = dev->ethtool_ops->set_phys_id(dev, ETHTOOL_ID_ACTIVE); + rc = ops->set_phys_id(dev, ETHTOOL_ID_ACTIVE); if (rc < 0) return rc; @@ -1118,7 +1120,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) i = n; do { rtnl_lock(); - rc = dev->ethtool_ops->set_phys_id(dev, + rc = ops->set_phys_id(dev, (i & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON); rtnl_unlock(); if (rc) @@ -1133,7 +1135,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) dev_put(dev); busy = false; - (void)dev->ethtool_ops->set_phys_id(dev, ETHTOOL_ID_INACTIVE); + (void) ops->set_phys_id(dev, ETHTOOL_ID_INACTIVE); return rc; } @@ -1275,7 +1277,7 @@ static int ethtool_get_dump_flag(struct net_device *dev, struct ethtool_dump dump; const struct ethtool_ops *ops = dev->ethtool_ops; - if (!dev->ethtool_ops->get_dump_flag) + if (!ops->get_dump_flag) return -EOPNOTSUPP; if (copy_from_user(&dump, useraddr, sizeof(dump))) @@ -1299,8 +1301,7 @@ static int ethtool_get_dump_data(struct net_device *dev, const struct ethtool_ops *ops = dev->ethtool_ops; void *data = NULL; - if (!dev->ethtool_ops->get_dump_data || - !dev->ethtool_ops->get_dump_flag) + if (!ops->get_dump_data || !ops->get_dump_flag) return -EOPNOTSUPP; if (copy_from_user(&dump, useraddr, sizeof(dump))) @@ -1346,13 +1347,9 @@ static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr) info.cmd = ETHTOOL_GET_TS_INFO; if (phydev && phydev->drv && phydev->drv->ts_info) { - err = phydev->drv->ts_info(phydev, &info); - - } else if (dev->ethtool_ops && dev->ethtool_ops->get_ts_info) { - + } else if (ops->get_ts_info) { err = ops->get_ts_info(dev, &info); - } else { info.so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE | -- cgit v1.2.3-70-g09d2 From fda55eca5a33f33ffcd4192c6b2d75179714a52c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 7 Jan 2013 09:28:21 +0000 Subject: net: introduce skb_transport_header_was_set() We have skb_mac_header_was_set() helper to tell if mac_header was set on a skb. We would like the same for transport_header. __netif_receive_skb() doesn't reset the transport header if already set by GRO layer. Note that network stacks usually reset the transport header anyway, after pulling the network header, so this change only allows a followup patch to have more precise qdisc pkt_len computation for GSO packets at ingress side. Signed-off-by: Eric Dumazet Cc: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/skbuff.h | 10 ++++++++++ net/core/dev.c | 3 ++- net/core/skbuff.c | 2 ++ 3 files changed, 14 insertions(+), 1 deletion(-) (limited to 'net/core') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 320e976d5ab..8b2256e880e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1492,6 +1492,11 @@ static inline void skb_set_inner_network_header(struct sk_buff *skb, skb->inner_network_header += offset; } +static inline bool skb_transport_header_was_set(const struct sk_buff *skb) +{ + return skb->transport_header != ~0U; +} + static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { return skb->head + skb->transport_header; @@ -1580,6 +1585,11 @@ static inline void skb_set_inner_network_header(struct sk_buff *skb, skb->inner_network_header = skb->data + offset; } +static inline bool skb_transport_header_was_set(const struct sk_buff *skb) +{ + return skb->transport_header != NULL; +} + static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { return skb->transport_header; diff --git a/net/core/dev.c b/net/core/dev.c index a51ccf46e8b..2e2448201a7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3352,7 +3352,8 @@ static int __netif_receive_skb(struct sk_buff *skb) orig_dev = skb->dev; skb_reset_network_header(skb); - skb_reset_transport_header(skb); + if (!skb_transport_header_was_set(skb)) + skb_reset_transport_header(skb); skb_reset_mac_len(skb); pt_prev = NULL; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b03fc0c6a95..1e1b9ea0296 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -260,6 +260,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, skb->end = skb->tail + size; #ifdef NET_SKBUFF_DATA_USES_OFFSET skb->mac_header = ~0U; + skb->transport_header = ~0U; #endif /* make sure we initialize shinfo sequentially */ @@ -328,6 +329,7 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) skb->end = skb->tail + size; #ifdef NET_SKBUFF_DATA_USES_OFFSET skb->mac_header = ~0U; + skb->transport_header = ~0U; #endif /* make sure we initialize shinfo sequentially */ -- cgit v1.2.3-70-g09d2 From b7394d2429c198b1da3d46ac39192e891029ec0f Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 7 Jan 2013 20:52:39 +0000 Subject: netpoll: prepare for ipv6 This patch adjusts some struct and functions, to prepare for supporting IPv6. Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- drivers/net/netconsole.c | 12 +- include/linux/netpoll.h | 13 +- net/core/netpoll.c | 402 ++++++++++++++++++++++++++--------------------- 3 files changed, 243 insertions(+), 184 deletions(-) (limited to 'net/core') diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 6989ebe2bc7..998fa0257a9 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -269,12 +269,14 @@ static ssize_t show_remote_port(struct netconsole_target *nt, char *buf) static ssize_t show_local_ip(struct netconsole_target *nt, char *buf) { - return snprintf(buf, PAGE_SIZE, "%pI4\n", &nt->np.local_ip); + if (!nt->np.ipv6) + return snprintf(buf, PAGE_SIZE, "%pI4\n", &nt->np.local_ip); } static ssize_t show_remote_ip(struct netconsole_target *nt, char *buf) { - return snprintf(buf, PAGE_SIZE, "%pI4\n", &nt->np.remote_ip); + if (!nt->np.ipv6) + return snprintf(buf, PAGE_SIZE, "%pI4\n", &nt->np.remote_ip); } static ssize_t show_local_mac(struct netconsole_target *nt, char *buf) @@ -410,7 +412,8 @@ static ssize_t store_local_ip(struct netconsole_target *nt, return -EINVAL; } - nt->np.local_ip = in_aton(buf); + if (!strnchr(buf, count, ':')) + nt->np.local_ip.ip = in_aton(buf); return strnlen(buf, count); } @@ -426,7 +429,8 @@ static ssize_t store_remote_ip(struct netconsole_target *nt, return -EINVAL; } - nt->np.remote_ip = in_aton(buf); + if (!strnchr(buf, count, ':')) + nt->np.remote_ip.ip = in_aton(buf); return strnlen(buf, count); } diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 66d5379c305..f54c3bb6a22 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -12,13 +12,22 @@ #include #include +union inet_addr { + __u32 all[4]; + __be32 ip; + __be32 ip6[4]; + struct in_addr in; + struct in6_addr in6; +}; + struct netpoll { struct net_device *dev; char dev_name[IFNAMSIZ]; const char *name; void (*rx_hook)(struct netpoll *, int, char *, int); - __be32 local_ip, remote_ip; + union inet_addr local_ip, remote_ip; + bool ipv6; u16 local_port, remote_port; u8 remote_mac[ETH_ALEN]; @@ -33,7 +42,7 @@ struct netpoll_info { spinlock_t rx_lock; struct list_head rx_np; /* netpolls that registered an rx_hook */ - struct sk_buff_head arp_tx; /* list of arp requests to reply to */ + struct sk_buff_head neigh_tx; /* list of neigh requests to reply to */ struct sk_buff_head txq; struct delayed_work tx_work; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index d2bda8eb08e..6bd073688f6 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -55,7 +55,7 @@ static atomic_t trapped; MAX_UDP_CHUNK) static void zap_completion_queue(void); -static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo); +static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo); static unsigned int carrier_timeout = 4; module_param(carrier_timeout, uint, 0644); @@ -181,13 +181,13 @@ static void poll_napi(struct net_device *dev) } } -static void service_arp_queue(struct netpoll_info *npi) +static void service_neigh_queue(struct netpoll_info *npi) { if (npi) { struct sk_buff *skb; - while ((skb = skb_dequeue(&npi->arp_tx))) - netpoll_arp_reply(skb, npi); + while ((skb = skb_dequeue(&npi->neigh_tx))) + netpoll_neigh_reply(skb, npi); } } @@ -216,14 +216,14 @@ static void netpoll_poll_dev(struct net_device *dev) bond_dev = netdev_master_upper_dev_get_rcu(dev); bond_ni = rcu_dereference_bh(bond_dev->npinfo); - while ((skb = skb_dequeue(&ni->arp_tx))) { + while ((skb = skb_dequeue(&ni->neigh_tx))) { skb->dev = bond_dev; - skb_queue_tail(&bond_ni->arp_tx, skb); + skb_queue_tail(&bond_ni->neigh_tx, skb); } } } - service_arp_queue(ni); + service_neigh_queue(ni); zap_completion_queue(); } @@ -386,7 +386,9 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) static atomic_t ip_ident; udp_len = len + sizeof(*udph); - ip_len = udp_len + sizeof(*iph); + if (!np->ipv6) + ip_len = udp_len + sizeof(*iph); + total_len = ip_len + LL_RESERVED_SPACE(np->dev); skb = find_skb(np, total_len + np->dev->needed_tailroom, @@ -403,34 +405,38 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) udph->source = htons(np->local_port); udph->dest = htons(np->remote_port); udph->len = htons(udp_len); - udph->check = 0; - udph->check = csum_tcpudp_magic(np->local_ip, - np->remote_ip, - udp_len, IPPROTO_UDP, - csum_partial(udph, udp_len, 0)); - if (udph->check == 0) - udph->check = CSUM_MANGLED_0; - - skb_push(skb, sizeof(*iph)); - skb_reset_network_header(skb); - iph = ip_hdr(skb); - - /* iph->version = 4; iph->ihl = 5; */ - put_unaligned(0x45, (unsigned char *)iph); - iph->tos = 0; - put_unaligned(htons(ip_len), &(iph->tot_len)); - iph->id = htons(atomic_inc_return(&ip_ident)); - iph->frag_off = 0; - iph->ttl = 64; - iph->protocol = IPPROTO_UDP; - iph->check = 0; - put_unaligned(np->local_ip, &(iph->saddr)); - put_unaligned(np->remote_ip, &(iph->daddr)); - iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); - - eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); - skb_reset_mac_header(skb); - skb->protocol = eth->h_proto = htons(ETH_P_IP); + + if (!np->ipv6) { + udph->check = 0; + udph->check = csum_tcpudp_magic(np->local_ip.ip, + np->remote_ip.ip, + udp_len, IPPROTO_UDP, + csum_partial(udph, udp_len, 0)); + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; + + skb_push(skb, sizeof(*iph)); + skb_reset_network_header(skb); + iph = ip_hdr(skb); + + /* iph->version = 4; iph->ihl = 5; */ + put_unaligned(0x45, (unsigned char *)iph); + iph->tos = 0; + put_unaligned(htons(ip_len), &(iph->tot_len)); + iph->id = htons(atomic_inc_return(&ip_ident)); + iph->frag_off = 0; + iph->ttl = 64; + iph->protocol = IPPROTO_UDP; + iph->check = 0; + put_unaligned(np->local_ip.ip, &(iph->saddr)); + put_unaligned(np->remote_ip.ip, &(iph->daddr)); + iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); + + eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb->protocol = eth->h_proto = htons(ETH_P_IP); + } + memcpy(eth->h_source, np->dev->dev_addr, ETH_ALEN); memcpy(eth->h_dest, np->remote_mac, ETH_ALEN); @@ -440,7 +446,7 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) } EXPORT_SYMBOL(netpoll_send_udp); -static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo) +static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo) { struct arphdr *arp; unsigned char *arp_ptr; @@ -451,7 +457,7 @@ static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo) struct netpoll *np, *tmp; unsigned long flags; int hlen, tlen; - int hits = 0; + int hits = 0, proto; if (list_empty(&npinfo->rx_np)) return; @@ -469,94 +475,97 @@ static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo) if (!hits) return; - /* No arp on this interface */ - if (skb->dev->flags & IFF_NOARP) - return; - - if (!pskb_may_pull(skb, arp_hdr_len(skb->dev))) - return; + proto = ntohs(eth_hdr(skb)->h_proto); + if (proto == ETH_P_IP) { + /* No arp on this interface */ + if (skb->dev->flags & IFF_NOARP) + return; - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - arp = arp_hdr(skb); + if (!pskb_may_pull(skb, arp_hdr_len(skb->dev))) + return; - if ((arp->ar_hrd != htons(ARPHRD_ETHER) && - arp->ar_hrd != htons(ARPHRD_IEEE802)) || - arp->ar_pro != htons(ETH_P_IP) || - arp->ar_op != htons(ARPOP_REQUEST)) - return; + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + arp = arp_hdr(skb); - arp_ptr = (unsigned char *)(arp+1); - /* save the location of the src hw addr */ - sha = arp_ptr; - arp_ptr += skb->dev->addr_len; - memcpy(&sip, arp_ptr, 4); - arp_ptr += 4; - /* If we actually cared about dst hw addr, - it would get copied here */ - arp_ptr += skb->dev->addr_len; - memcpy(&tip, arp_ptr, 4); - - /* Should we ignore arp? */ - if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) - return; + if ((arp->ar_hrd != htons(ARPHRD_ETHER) && + arp->ar_hrd != htons(ARPHRD_IEEE802)) || + arp->ar_pro != htons(ETH_P_IP) || + arp->ar_op != htons(ARPOP_REQUEST)) + return; - size = arp_hdr_len(skb->dev); + arp_ptr = (unsigned char *)(arp+1); + /* save the location of the src hw addr */ + sha = arp_ptr; + arp_ptr += skb->dev->addr_len; + memcpy(&sip, arp_ptr, 4); + arp_ptr += 4; + /* If we actually cared about dst hw addr, + it would get copied here */ + arp_ptr += skb->dev->addr_len; + memcpy(&tip, arp_ptr, 4); - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (tip != np->local_ip) - continue; + /* Should we ignore arp? */ + if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) + return; - hlen = LL_RESERVED_SPACE(np->dev); - tlen = np->dev->needed_tailroom; - send_skb = find_skb(np, size + hlen + tlen, hlen); - if (!send_skb) - continue; + size = arp_hdr_len(skb->dev); - skb_reset_network_header(send_skb); - arp = (struct arphdr *) skb_put(send_skb, size); - send_skb->dev = skb->dev; - send_skb->protocol = htons(ETH_P_ARP); + spin_lock_irqsave(&npinfo->rx_lock, flags); + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (tip != np->local_ip.ip) + continue; + + hlen = LL_RESERVED_SPACE(np->dev); + tlen = np->dev->needed_tailroom; + send_skb = find_skb(np, size + hlen + tlen, hlen); + if (!send_skb) + continue; + + skb_reset_network_header(send_skb); + arp = (struct arphdr *) skb_put(send_skb, size); + send_skb->dev = skb->dev; + send_skb->protocol = htons(ETH_P_ARP); + + /* Fill the device header for the ARP frame */ + if (dev_hard_header(send_skb, skb->dev, ptype, + sha, np->dev->dev_addr, + send_skb->len) < 0) { + kfree_skb(send_skb); + continue; + } - /* Fill the device header for the ARP frame */ - if (dev_hard_header(send_skb, skb->dev, ptype, - sha, np->dev->dev_addr, - send_skb->len) < 0) { - kfree_skb(send_skb); - continue; + /* + * Fill out the arp protocol part. + * + * we only support ethernet device type, + * which (according to RFC 1390) should + * always equal 1 (Ethernet). + */ + + arp->ar_hrd = htons(np->dev->type); + arp->ar_pro = htons(ETH_P_IP); + arp->ar_hln = np->dev->addr_len; + arp->ar_pln = 4; + arp->ar_op = htons(type); + + arp_ptr = (unsigned char *)(arp + 1); + memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len); + arp_ptr += np->dev->addr_len; + memcpy(arp_ptr, &tip, 4); + arp_ptr += 4; + memcpy(arp_ptr, sha, np->dev->addr_len); + arp_ptr += np->dev->addr_len; + memcpy(arp_ptr, &sip, 4); + + netpoll_send_skb(np, send_skb); + + /* If there are several rx_hooks for the same address, + we're fine by sending a single reply */ + break; } - - /* - * Fill out the arp protocol part. - * - * we only support ethernet device type, - * which (according to RFC 1390) should - * always equal 1 (Ethernet). - */ - - arp->ar_hrd = htons(np->dev->type); - arp->ar_pro = htons(ETH_P_IP); - arp->ar_hln = np->dev->addr_len; - arp->ar_pln = 4; - arp->ar_op = htons(type); - - arp_ptr = (unsigned char *)(arp + 1); - memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &tip, 4); - arp_ptr += 4; - memcpy(arp_ptr, sha, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &sip, 4); - - netpoll_send_skb(np, send_skb); - - /* If there are several rx_hooks for the same address, - we're fine by sending a single reply */ - break; + spin_unlock_irqrestore(&npinfo->rx_lock, flags); } - spin_unlock_irqrestore(&npinfo->rx_lock, flags); } int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) @@ -576,7 +585,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) /* check if netpoll clients need ARP */ if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) { - skb_queue_tail(&npinfo->arp_tx, skb); + skb_queue_tail(&npinfo->neigh_tx, skb); return 1; } @@ -587,60 +596,61 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) } proto = ntohs(eth_hdr(skb)->h_proto); - if (proto != ETH_P_IP) + if (proto != ETH_P_IP && proto != ETH_P_IPV6) goto out; if (skb->pkt_type == PACKET_OTHERHOST) goto out; if (skb_shared(skb)) goto out; - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - goto out; - iph = (struct iphdr *)skb->data; - if (iph->ihl < 5 || iph->version != 4) - goto out; - if (!pskb_may_pull(skb, iph->ihl*4)) - goto out; - iph = (struct iphdr *)skb->data; - if (ip_fast_csum((u8 *)iph, iph->ihl) != 0) - goto out; - - len = ntohs(iph->tot_len); - if (skb->len < len || len < iph->ihl*4) - goto out; - - /* - * Our transport medium may have padded the buffer out. - * Now We trim to the true length of the frame. - */ - if (pskb_trim_rcsum(skb, len)) - goto out; + if (proto == ETH_P_IP) { + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + goto out; + iph = (struct iphdr *)skb->data; + if (iph->ihl < 5 || iph->version != 4) + goto out; + if (!pskb_may_pull(skb, iph->ihl*4)) + goto out; + iph = (struct iphdr *)skb->data; + if (ip_fast_csum((u8 *)iph, iph->ihl) != 0) + goto out; - iph = (struct iphdr *)skb->data; - if (iph->protocol != IPPROTO_UDP) - goto out; + len = ntohs(iph->tot_len); + if (skb->len < len || len < iph->ihl*4) + goto out; - len -= iph->ihl*4; - uh = (struct udphdr *)(((char *)iph) + iph->ihl*4); - ulen = ntohs(uh->len); + /* + * Our transport medium may have padded the buffer out. + * Now We trim to the true length of the frame. + */ + if (pskb_trim_rcsum(skb, len)) + goto out; - if (ulen != len) - goto out; - if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr)) - goto out; + iph = (struct iphdr *)skb->data; + if (iph->protocol != IPPROTO_UDP) + goto out; - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (np->local_ip && np->local_ip != iph->daddr) - continue; - if (np->remote_ip && np->remote_ip != iph->saddr) - continue; - if (np->local_port && np->local_port != ntohs(uh->dest)) - continue; + len -= iph->ihl*4; + uh = (struct udphdr *)(((char *)iph) + iph->ihl*4); + ulen = ntohs(uh->len); - np->rx_hook(np, ntohs(uh->source), - (char *)(uh+1), - ulen - sizeof(struct udphdr)); - hits++; + if (ulen != len) + goto out; + if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr)) + goto out; + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (np->local_ip.ip && np->local_ip.ip != iph->daddr) + continue; + if (np->remote_ip.ip && np->remote_ip.ip != iph->saddr) + continue; + if (np->local_port && np->local_port != ntohs(uh->dest)) + continue; + + np->rx_hook(np, ntohs(uh->source), + (char *)(uh+1), + ulen - sizeof(struct udphdr)); + hits++; + } } if (!hits) @@ -661,17 +671,40 @@ out: void netpoll_print_options(struct netpoll *np) { np_info(np, "local port %d\n", np->local_port); - np_info(np, "local IP %pI4\n", &np->local_ip); + if (!np->ipv6) + np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip); np_info(np, "interface '%s'\n", np->dev_name); np_info(np, "remote port %d\n", np->remote_port); - np_info(np, "remote IP %pI4\n", &np->remote_ip); + if (!np->ipv6) + np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip); np_info(np, "remote ethernet address %pM\n", np->remote_mac); } EXPORT_SYMBOL(netpoll_print_options); +static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr) +{ + const char *end; + + if (!strchr(str, ':') && + in4_pton(str, -1, (void *)addr, -1, &end) > 0) { + if (!*end) + return 0; + } + if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) { +#if IS_ENABLED(CONFIG_IPV6) + if (!*end) + return 1; +#else + return -1; +#endif + } + return -1; +} + int netpoll_parse_options(struct netpoll *np, char *opt) { char *cur=opt, *delim; + int ipv6; if (*cur != '@') { if ((delim = strchr(cur, '@')) == NULL) @@ -687,7 +720,11 @@ int netpoll_parse_options(struct netpoll *np, char *opt) if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; - np->local_ip = in_aton(cur); + ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip); + if (ipv6 < 0) + goto parse_failed; + else + np->ipv6 = (bool)ipv6; cur = delim; } cur++; @@ -719,7 +756,13 @@ int netpoll_parse_options(struct netpoll *np, char *opt) if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; - np->remote_ip = in_aton(cur); + ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip); + if (ipv6 < 0) + goto parse_failed; + else if (np->ipv6 != (bool)ipv6) + goto parse_failed; + else + np->ipv6 = (bool)ipv6; cur = delim + 1; if (*cur != 0) { @@ -767,7 +810,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) INIT_LIST_HEAD(&npinfo->rx_np); spin_lock_init(&npinfo->rx_lock); - skb_queue_head_init(&npinfo->arp_tx); + skb_queue_head_init(&npinfo->neigh_tx); skb_queue_head_init(&npinfo->txq); INIT_DELAYED_WORK(&npinfo->tx_work, queue_process); @@ -859,21 +902,24 @@ int netpoll_setup(struct netpoll *np) } } - if (!np->local_ip) { - rcu_read_lock(); - in_dev = __in_dev_get_rcu(ndev); + if (!np->local_ip.ip) { + if (!np->ipv6) { + rcu_read_lock(); + in_dev = __in_dev_get_rcu(ndev); - if (!in_dev || !in_dev->ifa_list) { + + if (!in_dev || !in_dev->ifa_list) { + rcu_read_unlock(); + np_err(np, "no IP address for %s, aborting\n", + np->dev_name); + err = -EDESTADDRREQ; + goto put; + } + + np->local_ip.ip = in_dev->ifa_list->ifa_local; rcu_read_unlock(); - np_err(np, "no IP address for %s, aborting\n", - np->dev_name); - err = -EDESTADDRREQ; - goto put; + np_info(np, "local IP %pI4\n", &np->local_ip.ip); } - - np->local_ip = in_dev->ifa_list->ifa_local; - rcu_read_unlock(); - np_info(np, "local IP %pI4\n", &np->local_ip); } /* fill up the skb queue */ @@ -906,7 +952,7 @@ 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->neigh_tx); skb_queue_purge(&npinfo->txq); /* we can't call cancel_delayed_work_sync here, as we are in softirq */ -- cgit v1.2.3-70-g09d2 From b3d936f3ea1c97c32680e0cd235474cf9dadb762 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 7 Jan 2013 20:52:41 +0000 Subject: netpoll: add IPv6 support Currently, netpoll only supports IPv4. This patch adds IPv6 support to netpoll so that we can run netconsole over IPv6 network. Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- drivers/net/netconsole.c | 44 +++++++-- net/core/netpoll.c | 246 +++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 274 insertions(+), 16 deletions(-) (limited to 'net/core') diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 998fa0257a9..37add21a3d7 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -269,13 +269,17 @@ static ssize_t show_remote_port(struct netconsole_target *nt, char *buf) static ssize_t show_local_ip(struct netconsole_target *nt, char *buf) { - if (!nt->np.ipv6) + if (nt->np.ipv6) + return snprintf(buf, PAGE_SIZE, "%pI6c\n", &nt->np.local_ip.in6); + else return snprintf(buf, PAGE_SIZE, "%pI4\n", &nt->np.local_ip); } static ssize_t show_remote_ip(struct netconsole_target *nt, char *buf) { - if (!nt->np.ipv6) + if (nt->np.ipv6) + return snprintf(buf, PAGE_SIZE, "%pI6c\n", &nt->np.remote_ip.in6); + else return snprintf(buf, PAGE_SIZE, "%pI4\n", &nt->np.remote_ip); } @@ -412,8 +416,22 @@ static ssize_t store_local_ip(struct netconsole_target *nt, return -EINVAL; } - if (!strnchr(buf, count, ':')) - nt->np.local_ip.ip = in_aton(buf); + if (strnchr(buf, count, ':')) { + const char *end; + if (in6_pton(buf, count, nt->np.local_ip.in6.s6_addr, -1, &end) > 0) { + if (*end && *end != '\n') { + printk(KERN_ERR "netconsole: invalid IPv6 address at: <%c>\n", *end); + return -EINVAL; + } + nt->np.ipv6 = true; + } else + return -EINVAL; + } else { + if (!nt->np.ipv6) { + nt->np.local_ip.ip = in_aton(buf); + } else + return -EINVAL; + } return strnlen(buf, count); } @@ -429,8 +447,22 @@ static ssize_t store_remote_ip(struct netconsole_target *nt, return -EINVAL; } - if (!strnchr(buf, count, ':')) - nt->np.remote_ip.ip = in_aton(buf); + if (strnchr(buf, count, ':')) { + const char *end; + if (in6_pton(buf, count, nt->np.remote_ip.in6.s6_addr, -1, &end) > 0) { + if (*end && *end != '\n') { + printk(KERN_ERR "netconsole: invalid IPv6 address at: <%c>\n", *end); + return -EINVAL; + } + nt->np.ipv6 = true; + } else + return -EINVAL; + } else { + if (!nt->np.ipv6) { + nt->np.remote_ip.ip = in_aton(buf); + } else + return -EINVAL; + } return strnlen(buf, count); } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 6bd073688f6..9f050672610 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -29,6 +29,9 @@ #include #include #include +#include +#include +#include #include #include @@ -384,9 +387,12 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) struct iphdr *iph; struct ethhdr *eth; static atomic_t ip_ident; + struct ipv6hdr *ip6h; udp_len = len + sizeof(*udph); - if (!np->ipv6) + if (np->ipv6) + ip_len = udp_len + sizeof(*ip6h); + else ip_len = udp_len + sizeof(*iph); total_len = ip_len + LL_RESERVED_SPACE(np->dev); @@ -406,7 +412,35 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) udph->dest = htons(np->remote_port); udph->len = htons(udp_len); - if (!np->ipv6) { + if (np->ipv6) { + udph->check = 0; + udph->check = csum_ipv6_magic(&np->local_ip.in6, + &np->remote_ip.in6, + udp_len, IPPROTO_UDP, + csum_partial(udph, udp_len, 0)); + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; + + skb_push(skb, sizeof(*ip6h)); + skb_reset_network_header(skb); + ip6h = ipv6_hdr(skb); + + /* ip6h->version = 6; ip6h->priority = 0; */ + put_unaligned(0x60, (unsigned char *)ip6h); + ip6h->flow_lbl[0] = 0; + ip6h->flow_lbl[1] = 0; + ip6h->flow_lbl[2] = 0; + + ip6h->payload_len = htons(sizeof(struct udphdr) + len); + ip6h->nexthdr = IPPROTO_UDP; + ip6h->hop_limit = 32; + ip6h->saddr = np->local_ip.in6; + ip6h->daddr = np->remote_ip.in6; + + eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb->protocol = eth->h_proto = htons(ETH_P_IPV6); + } else { udph->check = 0; udph->check = csum_tcpudp_magic(np->local_ip.ip, np->remote_ip.ip, @@ -448,9 +482,7 @@ EXPORT_SYMBOL(netpoll_send_udp); static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo) { - struct arphdr *arp; - unsigned char *arp_ptr; - int size, type = ARPOP_REPLY, ptype = ETH_P_ARP; + int size, type = ARPOP_REPLY; __be32 sip, tip; unsigned char *sha; struct sk_buff *send_skb; @@ -477,6 +509,8 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo proto = ntohs(eth_hdr(skb)->h_proto); if (proto == ETH_P_IP) { + struct arphdr *arp; + unsigned char *arp_ptr; /* No arp on this interface */ if (skb->dev->flags & IFF_NOARP) return; @@ -528,7 +562,7 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo send_skb->protocol = htons(ETH_P_ARP); /* Fill the device header for the ARP frame */ - if (dev_hard_header(send_skb, skb->dev, ptype, + if (dev_hard_header(send_skb, skb->dev, ETH_P_ARP, sha, np->dev->dev_addr, send_skb->len) < 0) { kfree_skb(send_skb); @@ -565,9 +599,124 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo break; } spin_unlock_irqrestore(&npinfo->rx_lock, flags); + } else if( proto == ETH_P_IPV6) { +#if IS_ENABLED(CONFIG_IPV6) + struct nd_msg *msg; + u8 *lladdr = NULL; + struct ipv6hdr *hdr; + struct icmp6hdr *icmp6h; + const struct in6_addr *saddr; + const struct in6_addr *daddr; + struct inet6_dev *in6_dev = NULL; + struct in6_addr *target; + + in6_dev = in6_dev_get(skb->dev); + if (!in6_dev || !in6_dev->cnf.accept_ra) + return; + + if (!pskb_may_pull(skb, skb->len)) + return; + + msg = (struct nd_msg *)skb_transport_header(skb); + + __skb_push(skb, skb->data - skb_transport_header(skb)); + + if (ipv6_hdr(skb)->hop_limit != 255) + return; + if (msg->icmph.icmp6_code != 0) + return; + if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) + return; + + saddr = &ipv6_hdr(skb)->saddr; + daddr = &ipv6_hdr(skb)->daddr; + + size = sizeof(struct icmp6hdr) + sizeof(struct in6_addr); + + spin_lock_irqsave(&npinfo->rx_lock, flags); + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (memcmp(daddr, &np->local_ip, sizeof(*daddr))) + continue; + + hlen = LL_RESERVED_SPACE(np->dev); + tlen = np->dev->needed_tailroom; + send_skb = find_skb(np, size + hlen + tlen, hlen); + if (!send_skb) + continue; + + send_skb->protocol = htons(ETH_P_IPV6); + send_skb->dev = skb->dev; + + skb_reset_network_header(send_skb); + skb_put(send_skb, sizeof(struct ipv6hdr)); + hdr = ipv6_hdr(send_skb); + + *(__be32*)hdr = htonl(0x60000000); + + hdr->payload_len = htons(size); + hdr->nexthdr = IPPROTO_ICMPV6; + hdr->hop_limit = 255; + hdr->saddr = *saddr; + hdr->daddr = *daddr; + + send_skb->transport_header = send_skb->tail; + skb_put(send_skb, size); + + icmp6h = (struct icmp6hdr *)skb_transport_header(skb); + icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; + icmp6h->icmp6_router = 0; + icmp6h->icmp6_solicited = 1; + target = (struct in6_addr *)skb_transport_header(send_skb) + sizeof(struct icmp6hdr); + *target = msg->target; + icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size, + IPPROTO_ICMPV6, + csum_partial(icmp6h, + size, 0)); + + if (dev_hard_header(send_skb, skb->dev, ETH_P_IPV6, + lladdr, np->dev->dev_addr, + send_skb->len) < 0) { + kfree_skb(send_skb); + continue; + } + + netpoll_send_skb(np, send_skb); + + /* If there are several rx_hooks for the same address, + we're fine by sending a single reply */ + break; + } + spin_unlock_irqrestore(&npinfo->rx_lock, flags); +#endif } } +static bool pkt_is_ns(struct sk_buff *skb) +{ + struct nd_msg *msg; + struct ipv6hdr *hdr; + + if (skb->protocol != htons(ETH_P_ARP)) + return false; + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg))) + return false; + + msg = (struct nd_msg *)skb_transport_header(skb); + __skb_push(skb, skb->data - skb_transport_header(skb)); + hdr = ipv6_hdr(skb); + + if (hdr->nexthdr != IPPROTO_ICMPV6) + return false; + if (hdr->hop_limit != 255) + return false; + if (msg->icmph.icmp6_code != 0) + return false; + if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) + return false; + + return true; +} + int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) { int proto, len, ulen; @@ -583,8 +732,10 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) goto out; /* check if netpoll clients need ARP */ - if (skb->protocol == htons(ETH_P_ARP) && - atomic_read(&trapped)) { + if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) { + skb_queue_tail(&npinfo->neigh_tx, skb); + return 1; + } else if (pkt_is_ns(skb) && atomic_read(&trapped)) { skb_queue_tail(&npinfo->neigh_tx, skb); return 1; } @@ -651,6 +802,45 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) ulen - sizeof(struct udphdr)); hits++; } + } else { +#if IS_ENABLED(CONFIG_IPV6) + const struct ipv6hdr *ip6h; + + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + goto out; + ip6h = (struct ipv6hdr *)skb->data; + if (ip6h->version != 6) + goto out; + len = ntohs(ip6h->payload_len); + if (!len) + goto out; + if (len + sizeof(struct ipv6hdr) > skb->len) + goto out; + if (pskb_trim_rcsum(skb, len + sizeof(struct ipv6hdr))) + goto out; + ip6h = ipv6_hdr(skb); + if (!pskb_may_pull(skb, sizeof(struct udphdr))) + goto out; + uh = udp_hdr(skb); + ulen = ntohs(uh->len); + if (ulen != skb->len) + goto out; + if (udp6_csum_init(skb, uh, IPPROTO_UDP)) + goto out; + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (memcmp(&np->local_ip.in6, &ip6h->daddr, sizeof(struct in6_addr)) != 0) + continue; + if (memcmp(&np->remote_ip.in6, &ip6h->saddr, sizeof(struct in6_addr)) != 0) + continue; + if (np->local_port && np->local_port != ntohs(uh->dest)) + continue; + + np->rx_hook(np, ntohs(uh->source), + (char *)(uh+1), + ulen - sizeof(struct udphdr)); + hits++; + } +#endif } if (!hits) @@ -671,11 +861,15 @@ out: void netpoll_print_options(struct netpoll *np) { np_info(np, "local port %d\n", np->local_port); - if (!np->ipv6) + if (np->ipv6) + np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6); + else np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip); np_info(np, "interface '%s'\n", np->dev_name); np_info(np, "remote port %d\n", np->remote_port); - if (!np->ipv6) + if (np->ipv6) + np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6); + else np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip); np_info(np, "remote ethernet address %pM\n", np->remote_mac); } @@ -919,6 +1113,38 @@ int netpoll_setup(struct netpoll *np) np->local_ip.ip = in_dev->ifa_list->ifa_local; rcu_read_unlock(); np_info(np, "local IP %pI4\n", &np->local_ip.ip); + } else { +#if IS_ENABLED(CONFIG_IPV6) + struct inet6_dev *idev; + + err = -EDESTADDRREQ; + rcu_read_lock(); + idev = __in6_dev_get(ndev); + if (idev) { + struct inet6_ifaddr *ifp; + + read_lock_bh(&idev->lock); + list_for_each_entry(ifp, &idev->addr_list, if_list) { + if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) + continue; + np->local_ip.in6 = ifp->addr; + err = 0; + break; + } + read_unlock_bh(&idev->lock); + } + rcu_read_unlock(); + if (err) { + np_err(np, "no IPv6 address for %s, aborting\n", + np->dev_name); + goto put; + } else + np_info(np, "local IPv6 %pI6c\n", &np->local_ip.in6); +#else + np_err(np, "IPv6 is not supported %s, aborting\n", + np->dev_name); + goto put; +#endif } } -- cgit v1.2.3-70-g09d2 From 948b337e62ca96b6e7de06fdd5f6fe44769d7e9c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 8 Jan 2013 01:38:25 +0000 Subject: net: init perm_addr in register_netdevice() Benefit from the fact that dev->addr_assign_type is set to NET_ADDR_PERM in case the device has permanent address. This also fixes the problem that many drivers do not set perm_addr at all. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/dev.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index 2e2448201a7..594830e8358 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6004,6 +6004,13 @@ int register_netdevice(struct net_device *dev) list_netdevice(dev); add_device_randomness(dev->dev_addr, dev->addr_len); + /* If the device has permanent device address, driver should + * set dev_addr and also addr_assign_type should be set to + * NET_ADDR_PERM (default value). + */ + if (dev->addr_assign_type == NET_ADDR_PERM) + memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); + /* Notify protocols, that a new device appeared. */ ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); ret = notifier_to_errno(ret); -- cgit v1.2.3-70-g09d2 From 1def9238d4aa2146924994aa4b7dc861f03b9362 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 10 Jan 2013 12:36:42 +0000 Subject: net_sched: more precise pkt_len computation One long standing problem with TSO/GSO/GRO packets is that skb->len doesn't represent a precise amount of bytes on wire. Headers are only accounted for the first segment. For TCP, thats typically 66 bytes per 1448 bytes segment missing, an error of 4.5 % for normal MSS value. As consequences : 1) TBF/CBQ/HTB/NETEM/... can send more bytes than the assigned limits. 2) Device stats are slightly under estimated as well. Fix this by taking account of headers in qdisc_skb_cb(skb)->pkt_len computation. Packet schedulers should use qdisc pkt_len instead of skb->len for their bandwidth limitations, and TSO enabled devices drivers could use pkt_len if their statistics are not hardware assisted, and if they don't scratch skb->cb[] first word. Both egress and ingress paths work, thanks to commit fda55eca5a (net: introduce skb_transport_header_was_set()) : If GRO built a GSO packet, it also set the transport header for us. Signed-off-by: Eric Dumazet Cc: Jamal Hadi Salim Cc: Stephen Hemminger Cc: Paolo Valente Cc: Herbert Xu Cc: Patrick McHardy Signed-off-by: David S. Miller --- net/core/dev.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index 594830e8358..4794cae8493 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2532,6 +2532,26 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, return netdev_get_tx_queue(dev, queue_index); } +static void qdisc_pkt_len_init(struct sk_buff *skb) +{ + const struct skb_shared_info *shinfo = skb_shinfo(skb); + + qdisc_skb_cb(skb)->pkt_len = skb->len; + + /* To get more precise estimation of bytes sent on wire, + * we add to pkt_len the headers size of all segments + */ + if (shinfo->gso_size) { + unsigned int hdr_len = skb_transport_offset(skb); + + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + hdr_len += tcp_hdrlen(skb); + else + hdr_len += sizeof(struct udphdr); + qdisc_skb_cb(skb)->pkt_len += (shinfo->gso_segs - 1) * hdr_len; + } +} + static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq) @@ -2540,7 +2560,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, bool contended; int rc; - qdisc_skb_cb(skb)->pkt_len = skb->len; + qdisc_pkt_len_init(skb); qdisc_calculate_pkt_len(skb, q); /* * Heuristic to force contended enqueues to serialize on a -- cgit v1.2.3-70-g09d2 From 416186fbf8c5b4e4465a10c6ac7a45b6c47144b2 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 10 Jan 2013 08:56:51 +0000 Subject: net: Split core bits of netdev_pick_tx into __netdev_pick_tx This change splits the core bits of netdev_pick_tx into a separate function. The main idea behind this is to make this code accessible to select queue functions when they decide to process the standard path instead of their own custom path in their select queue routine. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + net/core/dev.c | 57 ++++++++++++++++++++++++++--------------------- 2 files changed, 33 insertions(+), 25 deletions(-) (limited to 'net/core') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0209ac328e8..608c3ac4d04 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1403,6 +1403,7 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, extern struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb); +extern u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb); /* * Net namespace inlines diff --git a/net/core/dev.c b/net/core/dev.c index 4794cae8493..81ff67149f6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2495,37 +2495,44 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) #endif } -struct netdev_queue *netdev_pick_tx(struct net_device *dev, - struct sk_buff *skb) +u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) { - int queue_index; - const struct net_device_ops *ops = dev->netdev_ops; - - if (dev->real_num_tx_queues == 1) - queue_index = 0; - else if (ops->ndo_select_queue) { - queue_index = ops->ndo_select_queue(dev, skb); - queue_index = dev_cap_txqueue(dev, queue_index); - } else { - struct sock *sk = skb->sk; - queue_index = sk_tx_queue_get(sk); + struct sock *sk = skb->sk; + int queue_index = sk_tx_queue_get(sk); - if (queue_index < 0 || skb->ooo_okay || - queue_index >= dev->real_num_tx_queues) { - int old_index = queue_index; + if (queue_index < 0 || skb->ooo_okay || + queue_index >= dev->real_num_tx_queues) { + int new_index = get_xps_queue(dev, skb); + if (new_index < 0) + new_index = skb_tx_hash(dev, skb); - queue_index = get_xps_queue(dev, skb); - if (queue_index < 0) - queue_index = skb_tx_hash(dev, skb); - - if (queue_index != old_index && sk) { - struct dst_entry *dst = + if (queue_index != new_index && sk) { + struct dst_entry *dst = rcu_dereference_check(sk->sk_dst_cache, 1); - if (dst && skb_dst(skb) == dst) - sk_tx_queue_set(sk, queue_index); - } + if (dst && skb_dst(skb) == dst) + sk_tx_queue_set(sk, queue_index); + } + + queue_index = new_index; + } + + return queue_index; +} + +struct netdev_queue *netdev_pick_tx(struct net_device *dev, + struct sk_buff *skb) +{ + int queue_index = 0; + + if (dev->real_num_tx_queues != 1) { + const struct net_device_ops *ops = dev->netdev_ops; + if (ops->ndo_select_queue) + queue_index = ops->ndo_select_queue(dev, skb); + else + queue_index = __netdev_pick_tx(dev, skb); + queue_index = dev_cap_txqueue(dev, queue_index); } skb_set_queue_mapping(skb, queue_index); -- cgit v1.2.3-70-g09d2 From 537c00de1c9ba9876b91d869e84caceefe2b8bf9 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 10 Jan 2013 08:57:02 +0000 Subject: net: Add functions netif_reset_xps_queue and netif_set_xps_queue This patch adds two functions, netif_reset_xps_queue and netif_set_xps_queue. The main idea behind these two functions is to provide a mechanism through which drivers can update their defaults in regards to XPS. Currently no such mechanism exists and as a result we cannot use XPS for things such as ATR which would require a basic configuration to start in which the Tx queues are mapped to CPUs via a 1:1 mapping. With this change I am making it possible for drivers such as ixgbe to be able to use the XPS feature by controlling the default configuration. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 13 ++++ net/core/dev.c | 155 ++++++++++++++++++++++++++++++++++++++++++++++ net/core/net-sysfs.c | 148 ++----------------------------------------- 3 files changed, 173 insertions(+), 143 deletions(-) (limited to 'net/core') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 608c3ac4d04..59fe9da4e31 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2103,6 +2103,19 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) __netif_schedule(txq->qdisc); } +#ifdef CONFIG_XPS +extern void netif_reset_xps_queue(struct net_device *dev, u16 index); +extern int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, + u16 index); +#else +static inline int netif_set_xps_queue(struct net_device *dev, + struct cpumask *mask, + u16 index) +{ + return 0; +} +#endif + /* * Returns a Tx hash for the given packet when dev->real_num_tx_queues is used * as a distribution range limit for the returned value. diff --git a/net/core/dev.c b/net/core/dev.c index 81ff67149f6..257b29516f6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1857,6 +1857,161 @@ static void netif_setup_tc(struct net_device *dev, unsigned int txq) } } +#ifdef CONFIG_XPS +static DEFINE_MUTEX(xps_map_mutex); +#define xmap_dereference(P) \ + rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) + +void netif_reset_xps_queue(struct net_device *dev, u16 index) +{ + struct xps_dev_maps *dev_maps; + struct xps_map *map; + int i, pos, nonempty = 0; + + mutex_lock(&xps_map_mutex); + dev_maps = xmap_dereference(dev->xps_maps); + + if (!dev_maps) + goto out_no_maps; + + for_each_possible_cpu(i) { + map = xmap_dereference(dev_maps->cpu_map[i]); + if (!map) + continue; + + for (pos = 0; pos < map->len; pos++) + if (map->queues[pos] == index) + break; + + if (pos < map->len) { + if (map->len > 1) { + map->queues[pos] = map->queues[--map->len]; + } else { + RCU_INIT_POINTER(dev_maps->cpu_map[i], NULL); + kfree_rcu(map, rcu); + map = NULL; + } + } + if (map) + nonempty = 1; + } + + if (!nonempty) { + RCU_INIT_POINTER(dev->xps_maps, NULL); + kfree_rcu(dev_maps, rcu); + } + +out_no_maps: + mutex_unlock(&xps_map_mutex); +} + +int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, u16 index) +{ + int i, cpu, pos, map_len, alloc_len, need_set; + struct xps_map *map, *new_map; + struct xps_dev_maps *dev_maps, *new_dev_maps; + int nonempty = 0; + int numa_node_id = -2; + int maps_sz = max_t(unsigned int, XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES); + + new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); + if (!new_dev_maps) + return -ENOMEM; + + mutex_lock(&xps_map_mutex); + + dev_maps = xmap_dereference(dev->xps_maps); + + for_each_possible_cpu(cpu) { + map = dev_maps ? + xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; + new_map = map; + if (map) { + for (pos = 0; pos < map->len; pos++) + if (map->queues[pos] == index) + break; + map_len = map->len; + alloc_len = map->alloc_len; + } else + pos = map_len = alloc_len = 0; + + need_set = cpumask_test_cpu(cpu, mask) && cpu_online(cpu); +#ifdef CONFIG_NUMA + if (need_set) { + if (numa_node_id == -2) + numa_node_id = cpu_to_node(cpu); + else if (numa_node_id != cpu_to_node(cpu)) + numa_node_id = -1; + } +#endif + if (need_set && pos >= map_len) { + /* Need to add queue to this CPU's map */ + if (map_len >= alloc_len) { + alloc_len = alloc_len ? + 2 * alloc_len : XPS_MIN_MAP_ALLOC; + new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), + GFP_KERNEL, + cpu_to_node(cpu)); + if (!new_map) + goto error; + new_map->alloc_len = alloc_len; + for (i = 0; i < map_len; i++) + new_map->queues[i] = map->queues[i]; + new_map->len = map_len; + } + new_map->queues[new_map->len++] = index; + } else if (!need_set && pos < map_len) { + /* Need to remove queue from this CPU's map */ + if (map_len > 1) + new_map->queues[pos] = + new_map->queues[--new_map->len]; + else + new_map = NULL; + } + RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], new_map); + } + + /* Cleanup old maps */ + for_each_possible_cpu(cpu) { + map = dev_maps ? + xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; + if (map && xmap_dereference(new_dev_maps->cpu_map[cpu]) != map) + kfree_rcu(map, rcu); + if (new_dev_maps->cpu_map[cpu]) + nonempty = 1; + } + + if (nonempty) { + rcu_assign_pointer(dev->xps_maps, new_dev_maps); + } else { + kfree(new_dev_maps); + RCU_INIT_POINTER(dev->xps_maps, NULL); + } + + if (dev_maps) + kfree_rcu(dev_maps, rcu); + + netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), + (numa_node_id >= 0) ? numa_node_id : + NUMA_NO_NODE); + + mutex_unlock(&xps_map_mutex); + + return 0; +error: + mutex_unlock(&xps_map_mutex); + + if (new_dev_maps) + for_each_possible_cpu(i) + kfree(rcu_dereference_protected( + new_dev_maps->cpu_map[i], + 1)); + kfree(new_dev_maps); + return -ENOMEM; +} +EXPORT_SYMBOL(netif_set_xps_queue); + +#endif /* * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater then real_num_tx_queues stale skbs on the qdisc must be flushed. diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 29c884a74c3..5ad489d5d06 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1002,54 +1002,14 @@ static ssize_t show_xps_map(struct netdev_queue *queue, return len; } -static DEFINE_MUTEX(xps_map_mutex); -#define xmap_dereference(P) \ - rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) - static void xps_queue_release(struct netdev_queue *queue) { struct net_device *dev = queue->dev; - struct xps_dev_maps *dev_maps; - struct xps_map *map; unsigned long index; - int i, pos, nonempty = 0; index = get_netdev_queue_index(queue); - mutex_lock(&xps_map_mutex); - dev_maps = xmap_dereference(dev->xps_maps); - - if (dev_maps) { - for_each_possible_cpu(i) { - map = xmap_dereference(dev_maps->cpu_map[i]); - if (!map) - continue; - - for (pos = 0; pos < map->len; pos++) - if (map->queues[pos] == index) - break; - - if (pos < map->len) { - if (map->len > 1) - map->queues[pos] = - map->queues[--map->len]; - else { - RCU_INIT_POINTER(dev_maps->cpu_map[i], - NULL); - kfree_rcu(map, rcu); - map = NULL; - } - } - if (map) - nonempty = 1; - } - - if (!nonempty) { - RCU_INIT_POINTER(dev->xps_maps, NULL); - kfree_rcu(dev_maps, rcu); - } - } - mutex_unlock(&xps_map_mutex); + netif_reset_xps_queue(dev, index); } static ssize_t store_xps_map(struct netdev_queue *queue, @@ -1057,13 +1017,9 @@ static ssize_t store_xps_map(struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; - cpumask_var_t mask; - int err, i, cpu, pos, map_len, alloc_len, need_set; unsigned long index; - struct xps_map *map, *new_map; - struct xps_dev_maps *dev_maps, *new_dev_maps; - int nonempty = 0; - int numa_node_id = -2; + cpumask_var_t mask; + int err; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -1079,105 +1035,11 @@ static ssize_t store_xps_map(struct netdev_queue *queue, return err; } - new_dev_maps = kzalloc(max_t(unsigned int, - XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES), GFP_KERNEL); - if (!new_dev_maps) { - free_cpumask_var(mask); - return -ENOMEM; - } - - mutex_lock(&xps_map_mutex); - - dev_maps = xmap_dereference(dev->xps_maps); - - for_each_possible_cpu(cpu) { - map = dev_maps ? - xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; - new_map = map; - if (map) { - for (pos = 0; pos < map->len; pos++) - if (map->queues[pos] == index) - break; - map_len = map->len; - alloc_len = map->alloc_len; - } else - pos = map_len = alloc_len = 0; - - need_set = cpumask_test_cpu(cpu, mask) && cpu_online(cpu); -#ifdef CONFIG_NUMA - if (need_set) { - if (numa_node_id == -2) - numa_node_id = cpu_to_node(cpu); - else if (numa_node_id != cpu_to_node(cpu)) - numa_node_id = -1; - } -#endif - if (need_set && pos >= map_len) { - /* Need to add queue to this CPU's map */ - if (map_len >= alloc_len) { - alloc_len = alloc_len ? - 2 * alloc_len : XPS_MIN_MAP_ALLOC; - new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), - GFP_KERNEL, - cpu_to_node(cpu)); - if (!new_map) - goto error; - new_map->alloc_len = alloc_len; - for (i = 0; i < map_len; i++) - new_map->queues[i] = map->queues[i]; - new_map->len = map_len; - } - new_map->queues[new_map->len++] = index; - } else if (!need_set && pos < map_len) { - /* Need to remove queue from this CPU's map */ - if (map_len > 1) - new_map->queues[pos] = - new_map->queues[--new_map->len]; - else - new_map = NULL; - } - RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], new_map); - } - - /* Cleanup old maps */ - for_each_possible_cpu(cpu) { - map = dev_maps ? - xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; - if (map && xmap_dereference(new_dev_maps->cpu_map[cpu]) != map) - kfree_rcu(map, rcu); - if (new_dev_maps->cpu_map[cpu]) - nonempty = 1; - } - - if (nonempty) { - rcu_assign_pointer(dev->xps_maps, new_dev_maps); - } else { - kfree(new_dev_maps); - RCU_INIT_POINTER(dev->xps_maps, NULL); - } - - if (dev_maps) - kfree_rcu(dev_maps, rcu); - - netdev_queue_numa_node_write(queue, (numa_node_id >= 0) ? numa_node_id : - NUMA_NO_NODE); - - mutex_unlock(&xps_map_mutex); + err = netif_set_xps_queue(dev, mask, index); free_cpumask_var(mask); - return len; -error: - mutex_unlock(&xps_map_mutex); - - if (new_dev_maps) - for_each_possible_cpu(i) - kfree(rcu_dereference_protected( - new_dev_maps->cpu_map[i], - 1)); - kfree(new_dev_maps); - free_cpumask_var(mask); - return -ENOMEM; + return err ? : len; } static struct netdev_queue_attribute xps_cpus_attribute = -- cgit v1.2.3-70-g09d2 From 10cdc3f3cd541bfeaaf1c6e1710b1500ca19aa7f Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 10 Jan 2013 08:57:17 +0000 Subject: net: Rewrite netif_reset_xps_queue to allow for better code reuse This patch does a minor refactor on netif_reset_xps_queue to address a few items I noticed. First is the fact that we are doing removal of queues in both netif_reset_xps_queue and netif_set_xps_queue. Since there is no need to have the code in two places I am pushing it out into a separate function and will come back in another patch and reuse the code in netif_set_xps_queue. The second item this change addresses is the fact that the Tx queues were not getting their numa_node value cleared as a part of the XPS queue reset. This patch resolves that by resetting the numa_node value if the dev_maps value is set. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- net/core/dev.c | 56 +++++++++++++++++++++++++++++++++----------------------- 1 file changed, 33 insertions(+), 23 deletions(-) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index 257b29516f6..231de873814 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1862,45 +1862,55 @@ static DEFINE_MUTEX(xps_map_mutex); #define xmap_dereference(P) \ rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) -void netif_reset_xps_queue(struct net_device *dev, u16 index) +static struct xps_map *remove_xps_queue(struct xps_dev_maps *dev_maps, + int cpu, u16 index) { - struct xps_dev_maps *dev_maps; - struct xps_map *map; - int i, pos, nonempty = 0; - - mutex_lock(&xps_map_mutex); - dev_maps = xmap_dereference(dev->xps_maps); - - if (!dev_maps) - goto out_no_maps; + struct xps_map *map = NULL; + int pos; - for_each_possible_cpu(i) { - map = xmap_dereference(dev_maps->cpu_map[i]); - if (!map) - continue; - - for (pos = 0; pos < map->len; pos++) - if (map->queues[pos] == index) - break; + if (dev_maps) + map = xmap_dereference(dev_maps->cpu_map[cpu]); - if (pos < map->len) { + for (pos = 0; map && pos < map->len; pos++) { + if (map->queues[pos] == index) { if (map->len > 1) { map->queues[pos] = map->queues[--map->len]; } else { - RCU_INIT_POINTER(dev_maps->cpu_map[i], NULL); + RCU_INIT_POINTER(dev_maps->cpu_map[cpu], NULL); kfree_rcu(map, rcu); map = NULL; } + break; } - if (map) - nonempty = 1; } - if (!nonempty) { + return map; +} + +void netif_reset_xps_queue(struct net_device *dev, u16 index) +{ + struct xps_dev_maps *dev_maps; + int cpu; + bool active = false; + + mutex_lock(&xps_map_mutex); + dev_maps = xmap_dereference(dev->xps_maps); + + if (!dev_maps) + goto out_no_maps; + + for_each_possible_cpu(cpu) { + if (remove_xps_queue(dev_maps, cpu, index)) + active = true; + } + + if (!active) { RCU_INIT_POINTER(dev->xps_maps, NULL); kfree_rcu(dev_maps, rcu); } + netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), + NUMA_NO_NODE); out_no_maps: mutex_unlock(&xps_map_mutex); } -- cgit v1.2.3-70-g09d2 From 01c5f864e62b1c1ee72fb492c6c5e47a162a507b Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 10 Jan 2013 08:57:35 +0000 Subject: net: Rewrite netif_set_xps_queues to address several issues This change is meant to address several issues I found within the netif_set_xps_queues function. If the allocation of one of the maps to be assigned to new_dev_maps failed we could end up with the device map in an inconsistent state since we had already worked through a number of CPUs and removed or added the queue. To address that I split the process into several steps. The first of which is just the allocation of updated maps for CPUs that will need larger maps to store the queue. By doing this we can fail gracefully without actually altering the contents of the current device map. The second issue I found was the fact that we were always allocating a new device map even if we were not adding any queues. I have updated the code so that we only allocate a new device map if we are adding queues, otherwise if we are not adding any queues to CPUs we just skip to the removal process. The last change I made was to reuse the code from remove_xps_queue to remove the queue from the CPU. By making this change we can be consistent in how we go about adding and removing the queues from the CPUs. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- net/core/dev.c | 183 ++++++++++++++++++++++++++++++++++++--------------------- 1 file changed, 117 insertions(+), 66 deletions(-) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index 231de873814..41d5120df46 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1915,107 +1915,158 @@ out_no_maps: mutex_unlock(&xps_map_mutex); } +static struct xps_map *expand_xps_map(struct xps_map *map, + int cpu, u16 index) +{ + struct xps_map *new_map; + int alloc_len = XPS_MIN_MAP_ALLOC; + int i, pos; + + for (pos = 0; map && pos < map->len; pos++) { + if (map->queues[pos] != index) + continue; + return map; + } + + /* Need to add queue to this CPU's existing map */ + if (map) { + if (pos < map->alloc_len) + return map; + + alloc_len = map->alloc_len * 2; + } + + /* Need to allocate new map to store queue on this CPU's map */ + new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, + cpu_to_node(cpu)); + if (!new_map) + return NULL; + + for (i = 0; i < pos; i++) + new_map->queues[i] = map->queues[i]; + new_map->alloc_len = alloc_len; + new_map->len = pos; + + return new_map; +} + int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, u16 index) { - int i, cpu, pos, map_len, alloc_len, need_set; + struct xps_dev_maps *dev_maps, *new_dev_maps = NULL; struct xps_map *map, *new_map; - struct xps_dev_maps *dev_maps, *new_dev_maps; - int nonempty = 0; - int numa_node_id = -2; int maps_sz = max_t(unsigned int, XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES); - - new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); - if (!new_dev_maps) - return -ENOMEM; + int cpu, numa_node_id = -2; + bool active = false; mutex_lock(&xps_map_mutex); dev_maps = xmap_dereference(dev->xps_maps); + /* allocate memory for queue storage */ + for_each_online_cpu(cpu) { + if (!cpumask_test_cpu(cpu, mask)) + continue; + + if (!new_dev_maps) + new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); + if (!new_dev_maps) + return -ENOMEM; + + map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : + NULL; + + map = expand_xps_map(map, cpu, index); + if (!map) + goto error; + + RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map); + } + + if (!new_dev_maps) + goto out_no_new_maps; + for_each_possible_cpu(cpu) { - map = dev_maps ? - xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; - new_map = map; - if (map) { - for (pos = 0; pos < map->len; pos++) - if (map->queues[pos] == index) - break; - map_len = map->len; - alloc_len = map->alloc_len; - } else - pos = map_len = alloc_len = 0; + if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) { + /* add queue to CPU maps */ + int pos = 0; - need_set = cpumask_test_cpu(cpu, mask) && cpu_online(cpu); + map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + while ((pos < map->len) && (map->queues[pos] != index)) + pos++; + + if (pos == map->len) + map->queues[map->len++] = index; #ifdef CONFIG_NUMA - if (need_set) { if (numa_node_id == -2) numa_node_id = cpu_to_node(cpu); else if (numa_node_id != cpu_to_node(cpu)) numa_node_id = -1; - } #endif - if (need_set && pos >= map_len) { - /* Need to add queue to this CPU's map */ - if (map_len >= alloc_len) { - alloc_len = alloc_len ? - 2 * alloc_len : XPS_MIN_MAP_ALLOC; - new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), - GFP_KERNEL, - cpu_to_node(cpu)); - if (!new_map) - goto error; - new_map->alloc_len = alloc_len; - for (i = 0; i < map_len; i++) - new_map->queues[i] = map->queues[i]; - new_map->len = map_len; - } - new_map->queues[new_map->len++] = index; - } else if (!need_set && pos < map_len) { - /* Need to remove queue from this CPU's map */ - if (map_len > 1) - new_map->queues[pos] = - new_map->queues[--new_map->len]; - else - new_map = NULL; + } else if (dev_maps) { + /* fill in the new device map from the old device map */ + map = xmap_dereference(dev_maps->cpu_map[cpu]); + RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map); } - RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], new_map); + } + rcu_assign_pointer(dev->xps_maps, new_dev_maps); + /* Cleanup old maps */ - for_each_possible_cpu(cpu) { - map = dev_maps ? - xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; - if (map && xmap_dereference(new_dev_maps->cpu_map[cpu]) != map) - kfree_rcu(map, rcu); - if (new_dev_maps->cpu_map[cpu]) - nonempty = 1; - } + if (dev_maps) { + for_each_possible_cpu(cpu) { + new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + map = xmap_dereference(dev_maps->cpu_map[cpu]); + if (map && map != new_map) + kfree_rcu(map, rcu); + } - if (nonempty) { - rcu_assign_pointer(dev->xps_maps, new_dev_maps); - } else { - kfree(new_dev_maps); - RCU_INIT_POINTER(dev->xps_maps, NULL); + kfree_rcu(dev_maps, rcu); } - if (dev_maps) - kfree_rcu(dev_maps, rcu); + dev_maps = new_dev_maps; + active = true; +out_no_new_maps: + /* update Tx queue numa node */ netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), (numa_node_id >= 0) ? numa_node_id : NUMA_NO_NODE); + if (!dev_maps) + goto out_no_maps; + + /* removes queue from unused CPUs */ + for_each_possible_cpu(cpu) { + if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) + continue; + + if (remove_xps_queue(dev_maps, cpu, index)) + active = true; + } + + /* free map if not active */ + if (!active) { + RCU_INIT_POINTER(dev->xps_maps, NULL); + kfree_rcu(dev_maps, rcu); + } + +out_no_maps: mutex_unlock(&xps_map_mutex); return 0; error: + /* remove any maps that we added */ + for_each_possible_cpu(cpu) { + new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : + NULL; + if (new_map && new_map != map) + kfree(new_map); + } + mutex_unlock(&xps_map_mutex); - if (new_dev_maps) - for_each_possible_cpu(i) - kfree(rcu_dereference_protected( - new_dev_maps->cpu_map[i], - 1)); kfree(new_dev_maps); return -ENOMEM; } -- cgit v1.2.3-70-g09d2 From 024e9679a2daaa67642693366fb63a6b8c61b9f3 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 10 Jan 2013 08:57:46 +0000 Subject: net: Add support for XPS without sysfs being defined This patch makes it so that we can support transmit packet steering without sysfs needing to be enabled. The reason for making this change is to make it so that a driver can make use of the XPS even while the sysfs portion of the interface is not present. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - net/Kconfig | 2 +- net/core/dev.c | 26 ++++++++++++++++++++------ net/core/net-sysfs.c | 14 -------------- 4 files changed, 21 insertions(+), 22 deletions(-) (limited to 'net/core') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 59fe9da4e31..aa7ad8a96e7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2104,7 +2104,6 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) } #ifdef CONFIG_XPS -extern void netif_reset_xps_queue(struct net_device *dev, u16 index); extern int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, u16 index); #else diff --git a/net/Kconfig b/net/Kconfig index 30b48f52313..3cc5be0fe42 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -232,7 +232,7 @@ config RFS_ACCEL config XPS boolean - depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS + depends on SMP && USE_GENERIC_SMP_HELPERS default y config NETPRIO_CGROUP diff --git a/net/core/dev.c b/net/core/dev.c index 41d5120df46..95de4c01180 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1887,10 +1887,10 @@ static struct xps_map *remove_xps_queue(struct xps_dev_maps *dev_maps, return map; } -void netif_reset_xps_queue(struct net_device *dev, u16 index) +static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) { struct xps_dev_maps *dev_maps; - int cpu; + int cpu, i; bool active = false; mutex_lock(&xps_map_mutex); @@ -1900,7 +1900,11 @@ void netif_reset_xps_queue(struct net_device *dev, u16 index) goto out_no_maps; for_each_possible_cpu(cpu) { - if (remove_xps_queue(dev_maps, cpu, index)) + for (i = index; i < dev->num_tx_queues; i++) { + if (!remove_xps_queue(dev_maps, cpu, i)) + break; + } + if (i == dev->num_tx_queues) active = true; } @@ -1909,8 +1913,10 @@ void netif_reset_xps_queue(struct net_device *dev, u16 index) kfree_rcu(dev_maps, rcu); } - netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), - NUMA_NO_NODE); + for (i = index; i < dev->num_tx_queues; i++) + netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i), + NUMA_NO_NODE); + out_no_maps: mutex_unlock(&xps_map_mutex); } @@ -2096,8 +2102,12 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) if (dev->num_tc) netif_setup_tc(dev, txq); - if (txq < dev->real_num_tx_queues) + if (txq < dev->real_num_tx_queues) { qdisc_reset_all_tx_gt(dev, txq); +#ifdef CONFIG_XPS + netif_reset_xps_queues_gt(dev, txq); +#endif + } } dev->real_num_tx_queues = txq; @@ -5919,6 +5929,10 @@ static void rollback_registered_many(struct list_head *head) /* Remove entries from kobject tree */ netdev_unregister_kobject(dev); +#ifdef CONFIG_XPS + /* Remove XPS queueing entries */ + netif_reset_xps_queues_gt(dev, 0); +#endif } synchronize_net(); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 5ad489d5d06..a5b89a6fec6 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1002,16 +1002,6 @@ static ssize_t show_xps_map(struct netdev_queue *queue, return len; } -static void xps_queue_release(struct netdev_queue *queue) -{ - struct net_device *dev = queue->dev; - unsigned long index; - - index = get_netdev_queue_index(queue); - - netif_reset_xps_queue(dev, index); -} - static ssize_t store_xps_map(struct netdev_queue *queue, struct netdev_queue_attribute *attribute, const char *buf, size_t len) @@ -1058,10 +1048,6 @@ static void netdev_queue_release(struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); -#ifdef CONFIG_XPS - xps_queue_release(queue); -#endif - memset(kobj, 0, sizeof(*kobj)); dev_put(queue->dev); } -- cgit v1.2.3-70-g09d2 From 87696f9234cb681ded2697b0f0fd01bb15a2aff2 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 11 Jan 2013 10:38:42 -0800 Subject: net: Export __netdev_pick_tx so that it can be used in modules When testing with FCoE enabled we discovered that I had not exported __netdev_pick_tx. As a result ixgbe doesn't build with the RFC patches applied because ixgbe_select_queue was calling the function. This change corrects that build issue by correctly exporting __netdev_pick_tx so it can be used by modules. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- net/core/dev.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index 95de4c01180..d1e8116e93c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2746,6 +2746,7 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) return queue_index; } +EXPORT_SYMBOL(__netdev_pick_tx); struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) -- cgit v1.2.3-70-g09d2 From 18aafc622abf492809723d9c5a3c5dcea287169e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 11 Jan 2013 14:46:37 +0000 Subject: net: splice: fix __splice_segment() commit 9ca1b22d6d2 (net: splice: avoid high order page splitting) forgot that skb->head could need a copy into several page frags. This could be the case for loopback traffic mostly. Also remove now useless skb argument from linear_to_page() and __splice_segment() prototypes. Signed-off-by: Eric Dumazet Cc: Willy Tarreau Signed-off-by: David S. Miller --- net/core/skbuff.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) (limited to 'net/core') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1e1b9ea0296..2568c449fe3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1652,7 +1652,7 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) static struct page *linear_to_page(struct page *page, unsigned int *len, unsigned int *offset, - struct sk_buff *skb, struct sock *sk) + struct sock *sk) { struct page_frag *pfrag = sk_page_frag(sk); @@ -1685,14 +1685,14 @@ static bool spd_can_coalesce(const struct splice_pipe_desc *spd, static bool spd_fill_page(struct splice_pipe_desc *spd, struct pipe_inode_info *pipe, struct page *page, unsigned int *len, unsigned int offset, - struct sk_buff *skb, bool linear, + bool linear, struct sock *sk) { if (unlikely(spd->nr_pages == MAX_SKB_FRAGS)) return true; if (linear) { - page = linear_to_page(page, len, &offset, skb, sk); + page = linear_to_page(page, len, &offset, sk); if (!page) return true; } @@ -1711,13 +1711,11 @@ static bool spd_fill_page(struct splice_pipe_desc *spd, static bool __splice_segment(struct page *page, unsigned int poff, unsigned int plen, unsigned int *off, - unsigned int *len, struct sk_buff *skb, + unsigned int *len, struct splice_pipe_desc *spd, bool linear, struct sock *sk, struct pipe_inode_info *pipe) { - unsigned int flen; - if (!*len) return true; @@ -1732,12 +1730,16 @@ static bool __splice_segment(struct page *page, unsigned int poff, plen -= *off; *off = 0; - flen = min(*len, plen); - - if (spd_fill_page(spd, pipe, page, &flen, poff, skb, linear, sk)) - return true; + do { + unsigned int flen = min(*len, plen); - *len -= flen; + if (spd_fill_page(spd, pipe, page, &flen, poff, + linear, sk)) + return true; + poff += flen; + plen -= flen; + *len -= flen; + } while (*len && plen); return false; } @@ -1760,7 +1762,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), - offset, len, skb, spd, + offset, len, spd, skb_head_is_locked(skb), sk, pipe)) return true; @@ -1773,7 +1775,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, if (__splice_segment(skb_frag_page(f), f->page_offset, skb_frag_size(f), - offset, len, skb, spd, false, sk, pipe)) + offset, len, spd, false, sk, pipe)) return true; } -- cgit v1.2.3-70-g09d2 From 757b8b1d2bfa1210592bfd2984852b155eb58746 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 15 Jan 2013 21:14:21 -0800 Subject: net_sched: fix qdisc_pkt_len_init() commit 1def9238d4aa2 (net_sched: more precise pkt_len computation) does a wrong computation of mac + network headers length, as it includes the padding before the frame. Signed-off-by: Eric Dumazet Cc: Yuval Mintz Signed-off-by: David S. Miller --- net/core/dev.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index 862eaa744a5..b6d2b32933b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2776,8 +2776,12 @@ static void qdisc_pkt_len_init(struct sk_buff *skb) * we add to pkt_len the headers size of all segments */ if (shinfo->gso_size) { - unsigned int hdr_len = skb_transport_offset(skb); + unsigned int hdr_len; + /* mac layer + network layer */ + hdr_len = skb_transport_header(skb) - skb_mac_header(skb); + + /* + transport layer */ if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) hdr_len += tcp_hdrlen(skb); else -- cgit v1.2.3-70-g09d2 From f92d318023ff70a273690a91568597168ac32f05 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 14 Jan 2013 23:34:06 +0000 Subject: netpoll: fix a rtnl lock assertion failure v4: hold rtnl lock for the whole netpoll_setup() v3: remove the comment v2: use RCU read lock This patch fixes the following warning: [ 72.013864] RTNL: assertion failed at net/core/dev.c (4955) [ 72.017758] Pid: 668, comm: netpoll-prep-v6 Not tainted 3.8.0-rc1+ #474 [ 72.019582] Call Trace: [ 72.020295] [] netdev_master_upper_dev_get+0x35/0x58 [ 72.022545] [] netpoll_setup+0x61/0x340 [ 72.024846] [] store_enabled+0x82/0xc3 [ 72.027466] [] netconsole_target_attr_store+0x35/0x37 [ 72.029348] [] configfs_write_file+0xe2/0x10c [ 72.030959] [] vfs_write+0xaf/0xf6 [ 72.032359] [] ? sysret_check+0x22/0x5d [ 72.033824] [] sys_write+0x5c/0x84 [ 72.035328] [] system_call_fastpath+0x16/0x1b In case of other races, hold rtnl lock for the entire netpoll_setup() function. Cc: Eric Dumazet Cc: Jiri Pirko Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/core/netpoll.c | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-) (limited to 'net/core') diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 9f050672610..a5ad1c1c4b1 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -1048,11 +1048,13 @@ int netpoll_setup(struct netpoll *np) struct in_device *in_dev; int err; + rtnl_lock(); if (np->dev_name) - ndev = dev_get_by_name(&init_net, np->dev_name); + ndev = __dev_get_by_name(&init_net, np->dev_name); if (!ndev) { np_err(np, "%s doesn't exist, aborting\n", np->dev_name); - return -ENODEV; + err = -ENODEV; + goto unlock; } if (netdev_master_upper_dev_get(ndev)) { @@ -1066,15 +1068,14 @@ int netpoll_setup(struct netpoll *np) np_info(np, "device %s not up yet, forcing it\n", np->dev_name); - rtnl_lock(); err = dev_open(ndev); - rtnl_unlock(); if (err) { np_err(np, "failed to open %s\n", ndev->name); goto put; } + rtnl_unlock(); atleast = jiffies + HZ/10; atmost = jiffies + carrier_timeout * HZ; while (!netif_carrier_ok(ndev)) { @@ -1094,16 +1095,14 @@ int netpoll_setup(struct netpoll *np) np_notice(np, "carrier detect appears untrustworthy, waiting 4 seconds\n"); msleep(4000); } + rtnl_lock(); } if (!np->local_ip.ip) { if (!np->ipv6) { - rcu_read_lock(); - in_dev = __in_dev_get_rcu(ndev); - + in_dev = __in_dev_get_rtnl(ndev); if (!in_dev || !in_dev->ifa_list) { - rcu_read_unlock(); np_err(np, "no IP address for %s, aborting\n", np->dev_name); err = -EDESTADDRREQ; @@ -1111,14 +1110,12 @@ int netpoll_setup(struct netpoll *np) } np->local_ip.ip = in_dev->ifa_list->ifa_local; - rcu_read_unlock(); np_info(np, "local IP %pI4\n", &np->local_ip.ip); } else { #if IS_ENABLED(CONFIG_IPV6) struct inet6_dev *idev; err = -EDESTADDRREQ; - rcu_read_lock(); idev = __in6_dev_get(ndev); if (idev) { struct inet6_ifaddr *ifp; @@ -1133,7 +1130,6 @@ int netpoll_setup(struct netpoll *np) } read_unlock_bh(&idev->lock); } - rcu_read_unlock(); if (err) { np_err(np, "no IPv6 address for %s, aborting\n", np->dev_name); @@ -1151,17 +1147,17 @@ int netpoll_setup(struct netpoll *np) /* fill up the skb queue */ refill_skbs(); - rtnl_lock(); err = __netpoll_setup(np, ndev, GFP_KERNEL); - rtnl_unlock(); - if (err) goto put; + rtnl_unlock(); return 0; put: dev_put(ndev); +unlock: + rtnl_unlock(); return err; } EXPORT_SYMBOL(netpoll_setup); -- cgit v1.2.3-70-g09d2 From 5bd30d398792eb6351da2087fe81bbf755900991 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 17 Jan 2013 12:21:08 +0800 Subject: netpoll: fix a missing dev refcounting __dev_get_by_name() doesn't refcount the network device, so we have to do this by ourselves. Noticed by Eric. Cc: Eric Dumazet Cc: Jiri Pirko Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/core/netpoll.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/core') diff --git a/net/core/netpoll.c b/net/core/netpoll.c index a5ad1c1c4b1..a9b10048388 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -1056,6 +1056,7 @@ int netpoll_setup(struct netpoll *np) err = -ENODEV; goto unlock; } + dev_hold(ndev); if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", np->dev_name); -- cgit v1.2.3-70-g09d2 From d59577b6ffd313d0ab3be39cb1ab47e29bdc9182 Mon Sep 17 00:00:00 2001 From: Vincent Bernat Date: Wed, 16 Jan 2013 22:55:49 +0100 Subject: sk-filter: Add ability to lock a socket filter program While a privileged program can open a raw socket, attach some restrictive filter and drop its privileges (or send the socket to an unprivileged program through some Unix socket), the filter can still be removed or modified by the unprivileged program. This commit adds a socket option to lock the filter (SO_LOCK_FILTER) preventing any modification of a socket filter program. This is similar to OpenBSD BIOCLOCK ioctl on bpf sockets, except even root is not allowed change/drop the filter. The state of the lock can be read with getsockopt(). No error is triggered if the state is not changed. -EPERM is returned when a user tries to remove the lock or to change/remove the filter while the lock is active. The check is done directly in sk_attach_filter() and sk_detach_filter() and does not affect only setsockopt() syscall. Signed-off-by: Vincent Bernat Signed-off-by: David S. Miller --- Documentation/networking/filter.txt | 11 +++++++++-- arch/alpha/include/uapi/asm/socket.h | 1 + arch/avr32/include/uapi/asm/socket.h | 2 ++ arch/cris/include/uapi/asm/socket.h | 2 ++ arch/frv/include/uapi/asm/socket.h | 2 ++ arch/h8300/include/uapi/asm/socket.h | 2 ++ arch/ia64/include/uapi/asm/socket.h | 2 ++ arch/m32r/include/uapi/asm/socket.h | 2 ++ arch/mips/include/uapi/asm/socket.h | 1 + arch/mn10300/include/uapi/asm/socket.h | 2 ++ arch/parisc/include/uapi/asm/socket.h | 1 + arch/powerpc/include/uapi/asm/socket.h | 2 ++ arch/s390/include/uapi/asm/socket.h | 2 ++ arch/sparc/include/uapi/asm/socket.h | 1 + arch/xtensa/include/uapi/asm/socket.h | 2 ++ include/net/sock.h | 1 + include/uapi/asm-generic/socket.h | 2 ++ net/core/filter.c | 6 ++++++ net/core/sock.c | 11 +++++++++++ 19 files changed, 53 insertions(+), 2 deletions(-) (limited to 'net/core') diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt index bbf2005270b..cdb3e40b9d1 100644 --- a/Documentation/networking/filter.txt +++ b/Documentation/networking/filter.txt @@ -17,12 +17,12 @@ creating filters. LSF is much simpler than BPF. One does not have to worry about devices or anything like that. You simply create your filter -code, send it to the kernel via the SO_ATTACH_FILTER ioctl and +code, send it to the kernel via the SO_ATTACH_FILTER option and if your filter code passes the kernel check on it, you then immediately begin filtering data on that socket. You can also detach filters from your socket via the -SO_DETACH_FILTER ioctl. This will probably not be used much +SO_DETACH_FILTER option. This will probably not be used much since when you close a socket that has a filter on it the filter is automagically removed. The other less common case may be adding a different filter on the same socket where you had another @@ -31,12 +31,19 @@ the old one and placing your new one in its place, assuming your filter has passed the checks, otherwise if it fails the old filter will remain on that socket. +SO_LOCK_FILTER option allows to lock the filter attached to a +socket. Once set, a filter cannot be removed or changed. This allows +one process to setup a socket, attach a filter, lock it then drop +privileges and be assured that the filter will be kept until the +socket is closed. + Examples ======== Ioctls- setsockopt(sockfd, SOL_SOCKET, SO_ATTACH_FILTER, &Filter, sizeof(Filter)); setsockopt(sockfd, SOL_SOCKET, SO_DETACH_FILTER, &value, sizeof(value)); +setsockopt(sockfd, SOL_SOCKET, SO_LOCK_FILTER, &value, sizeof(value)); See the BSD bpf.4 manpage and the BSD Packet Filter paper written by Steven McCanne and Van Jacobson of Lawrence Berkeley Laboratory. diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 097c1577735..755702eefd9 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -77,5 +77,6 @@ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 43 +#define SO_LOCK_FILTER 44 #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h index 486df68abee..f3f38a0e2ef 100644 --- a/arch/avr32/include/uapi/asm/socket.h +++ b/arch/avr32/include/uapi/asm/socket.h @@ -70,4 +70,6 @@ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 43 +#define SO_LOCK_FILTER 44 + #endif /* __ASM_AVR32_SOCKET_H */ diff --git a/arch/cris/include/uapi/asm/socket.h b/arch/cris/include/uapi/asm/socket.h index b681b043f6c..406b5838def 100644 --- a/arch/cris/include/uapi/asm/socket.h +++ b/arch/cris/include/uapi/asm/socket.h @@ -72,6 +72,8 @@ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 43 +#define SO_LOCK_FILTER 44 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h index 871f89b7fbd..d8e1132a1ab 100644 --- a/arch/frv/include/uapi/asm/socket.h +++ b/arch/frv/include/uapi/asm/socket.h @@ -70,5 +70,7 @@ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 43 +#define SO_LOCK_FILTER 44 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/h8300/include/uapi/asm/socket.h b/arch/h8300/include/uapi/asm/socket.h index 90a2e573c7e..c8b87a82820 100644 --- a/arch/h8300/include/uapi/asm/socket.h +++ b/arch/h8300/include/uapi/asm/socket.h @@ -70,4 +70,6 @@ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 43 +#define SO_LOCK_FILTER 44 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index 23d6759bb57..f390896c310 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -79,4 +79,6 @@ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 43 +#define SO_LOCK_FILTER 44 + #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h index 5e7088a2672..6a895155e7a 100644 --- a/arch/m32r/include/uapi/asm/socket.h +++ b/arch/m32r/include/uapi/asm/socket.h @@ -70,4 +70,6 @@ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 43 +#define SO_LOCK_FILTER 44 + #endif /* _ASM_M32R_SOCKET_H */ diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 17307ab9047..9d11a771392 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -90,5 +90,6 @@ To add: #define SO_REUSEPORT 0x0200 /* Allow local address and port reuse. */ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 43 +#define SO_LOCK_FILTER 44 #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h index af5366bbfe6..ab702c40b30 100644 --- a/arch/mn10300/include/uapi/asm/socket.h +++ b/arch/mn10300/include/uapi/asm/socket.h @@ -70,4 +70,6 @@ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 43 +#define SO_LOCK_FILTER 44 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index d9ff4731253..da2c8d3c209 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -69,6 +69,7 @@ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 0x4024 +#define SO_LOCK_FILTER 0x4025 /* O_NONBLOCK clashes with the bits used for socket types. Therefore we * have to define SOCK_NONBLOCK to a different value here. diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index eb0b1864d40..e6ca31816cc 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -77,4 +77,6 @@ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 43 +#define SO_LOCK_FILTER 44 + #endif /* _ASM_POWERPC_SOCKET_H */ diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index 436d07c23be..9ce60b68f07 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -76,4 +76,6 @@ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 43 +#define SO_LOCK_FILTER 44 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index c83a937ead0..fbbba57547d 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -66,6 +66,7 @@ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 0x0027 +#define SO_LOCK_FILTER 0x0028 /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index 38079be1cf1..dbf316487b5 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -81,4 +81,6 @@ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 43 +#define SO_LOCK_FILTER 44 + #endif /* _XTENSA_SOCKET_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 182ca99405a..5a34e2f0365 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -664,6 +664,7 @@ enum sock_flags { * Will use last 4 bytes of packet sent from * user-space instead. */ + SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */ }; static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 2d32d073a6f..3f6a9920141 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -73,4 +73,6 @@ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 43 +#define SO_LOCK_FILTER 44 + #endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/net/core/filter.c b/net/core/filter.c index 2ead2a9b185..2e20b55a783 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -721,6 +721,9 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) unsigned int fsize = sizeof(struct sock_filter) * fprog->len; int err; + if (sock_flag(sk, SOCK_FILTER_LOCKED)) + return -EPERM; + /* Make sure new filter is there and in the right amounts. */ if (fprog->filter == NULL) return -EINVAL; @@ -757,6 +760,9 @@ int sk_detach_filter(struct sock *sk) int ret = -ENOENT; struct sk_filter *filter; + if (sock_flag(sk, SOCK_FILTER_LOCKED)) + return -EPERM; + filter = rcu_dereference_protected(sk->sk_filter, sock_owned_by_user(sk)); if (filter) { diff --git a/net/core/sock.c b/net/core/sock.c index bc131d41968..8258fb741e9 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -861,6 +861,13 @@ set_rcvbuf: ret = sk_detach_filter(sk); break; + case SO_LOCK_FILTER: + if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool) + ret = -EPERM; + else + sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool); + break; + case SO_PASSSEC: if (valbool) set_bit(SOCK_PASSSEC, &sock->flags); @@ -1140,6 +1147,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, goto lenout; + case SO_LOCK_FILTER: + v.val = sock_flag(sk, SOCK_FILTER_LOCKED); + break; + default: return -ENOPROTOOPT; } -- cgit v1.2.3-70-g09d2 From 441d9d327f1e770f5aa76fd91735851ac6e1e236 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 21 Jan 2013 00:39:24 +0000 Subject: net: move rx and tx hash functions to net/core/flow_dissector.c __skb_tx_hash() and __skb_get_rxhash() are all for calculating hash value based by some fields in skb, mostly used for selecting queues by device drivers. Meanwhile, net/core/dev.c is bloating. Cc: "David S. Miller" Cc: Eric Dumazet Cc: Ben Hutchings Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/core/dev.c | 175 ---------------------------------------------- net/core/flow_dissector.c | 173 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 173 insertions(+), 175 deletions(-) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index b6d2b32933b..c69cd8721b2 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -134,7 +134,6 @@ #include #include #include -#include #include "net-sysfs.h" @@ -2636,136 +2635,6 @@ out: return rc; } -static u32 hashrnd __read_mostly; - -/* - * Returns a Tx hash based on the given packet descriptor a Tx queues' number - * to be used as a distribution range. - */ -u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, - unsigned int num_tx_queues) -{ - u32 hash; - u16 qoffset = 0; - u16 qcount = num_tx_queues; - - if (skb_rx_queue_recorded(skb)) { - hash = skb_get_rx_queue(skb); - while (unlikely(hash >= num_tx_queues)) - hash -= num_tx_queues; - return hash; - } - - if (dev->num_tc) { - u8 tc = netdev_get_prio_tc_map(dev, skb->priority); - qoffset = dev->tc_to_txq[tc].offset; - qcount = dev->tc_to_txq[tc].count; - } - - if (skb->sk && skb->sk->sk_hash) - hash = skb->sk->sk_hash; - else - hash = (__force u16) skb->protocol; - hash = jhash_1word(hash, hashrnd); - - return (u16) (((u64) hash * qcount) >> 32) + qoffset; -} -EXPORT_SYMBOL(__skb_tx_hash); - -static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) -{ - if (unlikely(queue_index >= dev->real_num_tx_queues)) { - net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", - dev->name, queue_index, - dev->real_num_tx_queues); - return 0; - } - return queue_index; -} - -static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) -{ -#ifdef CONFIG_XPS - struct xps_dev_maps *dev_maps; - struct xps_map *map; - int queue_index = -1; - - rcu_read_lock(); - dev_maps = rcu_dereference(dev->xps_maps); - if (dev_maps) { - map = rcu_dereference( - dev_maps->cpu_map[raw_smp_processor_id()]); - if (map) { - if (map->len == 1) - queue_index = map->queues[0]; - else { - u32 hash; - if (skb->sk && skb->sk->sk_hash) - hash = skb->sk->sk_hash; - else - hash = (__force u16) skb->protocol ^ - skb->rxhash; - hash = jhash_1word(hash, hashrnd); - queue_index = map->queues[ - ((u64)hash * map->len) >> 32]; - } - if (unlikely(queue_index >= dev->real_num_tx_queues)) - queue_index = -1; - } - } - rcu_read_unlock(); - - return queue_index; -#else - return -1; -#endif -} - -u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) -{ - struct sock *sk = skb->sk; - int queue_index = sk_tx_queue_get(sk); - - if (queue_index < 0 || skb->ooo_okay || - queue_index >= dev->real_num_tx_queues) { - int new_index = get_xps_queue(dev, skb); - if (new_index < 0) - new_index = skb_tx_hash(dev, skb); - - if (queue_index != new_index && sk) { - struct dst_entry *dst = - rcu_dereference_check(sk->sk_dst_cache, 1); - - if (dst && skb_dst(skb) == dst) - sk_tx_queue_set(sk, queue_index); - - } - - queue_index = new_index; - } - - return queue_index; -} -EXPORT_SYMBOL(__netdev_pick_tx); - -struct netdev_queue *netdev_pick_tx(struct net_device *dev, - struct sk_buff *skb) -{ - int queue_index = 0; - - if (dev->real_num_tx_queues != 1) { - const struct net_device_ops *ops = dev->netdev_ops; - if (ops->ndo_select_queue) - queue_index = ops->ndo_select_queue(dev, skb); - else - queue_index = __netdev_pick_tx(dev, skb); - queue_index = dev_cap_txqueue(dev, queue_index); - } - - skb_set_queue_mapping(skb, queue_index); - return netdev_get_tx_queue(dev, queue_index); -} - static void qdisc_pkt_len_init(struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); @@ -3015,41 +2884,6 @@ static inline void ____napi_schedule(struct softnet_data *sd, __raise_softirq_irqoff(NET_RX_SOFTIRQ); } -/* - * __skb_get_rxhash: calculate a flow hash based on src/dst addresses - * and src/dst port numbers. Sets rxhash in skb to non-zero hash value - * on success, zero indicates no valid hash. Also, sets l4_rxhash in skb - * if hash is a canonical 4-tuple hash over transport ports. - */ -void __skb_get_rxhash(struct sk_buff *skb) -{ - struct flow_keys keys; - u32 hash; - - if (!skb_flow_dissect(skb, &keys)) - return; - - if (keys.ports) - skb->l4_rxhash = 1; - - /* get a consistent hash (same value on both flow directions) */ - if (((__force u32)keys.dst < (__force u32)keys.src) || - (((__force u32)keys.dst == (__force u32)keys.src) && - ((__force u16)keys.port16[1] < (__force u16)keys.port16[0]))) { - swap(keys.dst, keys.src); - swap(keys.port16[0], keys.port16[1]); - } - - hash = jhash_3words((__force u32)keys.dst, - (__force u32)keys.src, - (__force u32)keys.ports, hashrnd); - if (!hash) - hash = 1; - - skb->rxhash = hash; -} -EXPORT_SYMBOL(__skb_get_rxhash); - #ifdef CONFIG_RPS /* One global table that all flow-based protocols share. */ @@ -7308,12 +7142,3 @@ out: } subsys_initcall(net_dev_init); - -static int __init initialize_hashrnd(void) -{ - get_random_bytes(&hashrnd, sizeof(hashrnd)); - return 0; -} - -late_initcall_sync(initialize_hashrnd); - diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 466820b6e34..9d4c7201400 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -143,3 +143,176 @@ ipv6: return true; } EXPORT_SYMBOL(skb_flow_dissect); + +static u32 hashrnd __read_mostly; + +/* + * __skb_get_rxhash: calculate a flow hash based on src/dst addresses + * and src/dst port numbers. Sets rxhash in skb to non-zero hash value + * on success, zero indicates no valid hash. Also, sets l4_rxhash in skb + * if hash is a canonical 4-tuple hash over transport ports. + */ +void __skb_get_rxhash(struct sk_buff *skb) +{ + struct flow_keys keys; + u32 hash; + + if (!skb_flow_dissect(skb, &keys)) + return; + + if (keys.ports) + skb->l4_rxhash = 1; + + /* get a consistent hash (same value on both flow directions) */ + if (((__force u32)keys.dst < (__force u32)keys.src) || + (((__force u32)keys.dst == (__force u32)keys.src) && + ((__force u16)keys.port16[1] < (__force u16)keys.port16[0]))) { + swap(keys.dst, keys.src); + swap(keys.port16[0], keys.port16[1]); + } + + hash = jhash_3words((__force u32)keys.dst, + (__force u32)keys.src, + (__force u32)keys.ports, hashrnd); + if (!hash) + hash = 1; + + skb->rxhash = hash; +} +EXPORT_SYMBOL(__skb_get_rxhash); + +/* + * Returns a Tx hash based on the given packet descriptor a Tx queues' number + * to be used as a distribution range. + */ +u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, + unsigned int num_tx_queues) +{ + u32 hash; + u16 qoffset = 0; + u16 qcount = num_tx_queues; + + if (skb_rx_queue_recorded(skb)) { + hash = skb_get_rx_queue(skb); + while (unlikely(hash >= num_tx_queues)) + hash -= num_tx_queues; + return hash; + } + + if (dev->num_tc) { + u8 tc = netdev_get_prio_tc_map(dev, skb->priority); + qoffset = dev->tc_to_txq[tc].offset; + qcount = dev->tc_to_txq[tc].count; + } + + if (skb->sk && skb->sk->sk_hash) + hash = skb->sk->sk_hash; + else + hash = (__force u16) skb->protocol; + hash = jhash_1word(hash, hashrnd); + + return (u16) (((u64) hash * qcount) >> 32) + qoffset; +} +EXPORT_SYMBOL(__skb_tx_hash); + +static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) +{ + if (unlikely(queue_index >= dev->real_num_tx_queues)) { + net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", + dev->name, queue_index, + dev->real_num_tx_queues); + return 0; + } + return queue_index; +} + +static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) +{ +#ifdef CONFIG_XPS + struct xps_dev_maps *dev_maps; + struct xps_map *map; + int queue_index = -1; + + rcu_read_lock(); + dev_maps = rcu_dereference(dev->xps_maps); + if (dev_maps) { + map = rcu_dereference( + dev_maps->cpu_map[raw_smp_processor_id()]); + if (map) { + if (map->len == 1) + queue_index = map->queues[0]; + else { + u32 hash; + if (skb->sk && skb->sk->sk_hash) + hash = skb->sk->sk_hash; + else + hash = (__force u16) skb->protocol ^ + skb->rxhash; + hash = jhash_1word(hash, hashrnd); + queue_index = map->queues[ + ((u64)hash * map->len) >> 32]; + } + if (unlikely(queue_index >= dev->real_num_tx_queues)) + queue_index = -1; + } + } + rcu_read_unlock(); + + return queue_index; +#else + return -1; +#endif +} + +u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + int queue_index = sk_tx_queue_get(sk); + + if (queue_index < 0 || skb->ooo_okay || + queue_index >= dev->real_num_tx_queues) { + int new_index = get_xps_queue(dev, skb); + if (new_index < 0) + new_index = skb_tx_hash(dev, skb); + + if (queue_index != new_index && sk) { + struct dst_entry *dst = + rcu_dereference_check(sk->sk_dst_cache, 1); + + if (dst && skb_dst(skb) == dst) + sk_tx_queue_set(sk, queue_index); + + } + + queue_index = new_index; + } + + return queue_index; +} +EXPORT_SYMBOL(__netdev_pick_tx); + +struct netdev_queue *netdev_pick_tx(struct net_device *dev, + struct sk_buff *skb) +{ + int queue_index = 0; + + if (dev->real_num_tx_queues != 1) { + const struct net_device_ops *ops = dev->netdev_ops; + if (ops->ndo_select_queue) + queue_index = ops->ndo_select_queue(dev, skb); + else + queue_index = __netdev_pick_tx(dev, skb); + queue_index = dev_cap_txqueue(dev, queue_index); + } + + skb_set_queue_mapping(skb, queue_index); + return netdev_get_tx_queue(dev, queue_index); +} + +static int __init initialize_hashrnd(void) +{ + get_random_bytes(&hashrnd, sizeof(hashrnd)); + return 0; +} + +late_initcall_sync(initialize_hashrnd); -- cgit v1.2.3-70-g09d2 From 2724680bceee94eac391552863771af105a7355c Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki / 吉藤英明 Date: Tue, 22 Jan 2013 05:20:05 +0000 Subject: neigh: Keep neighbour cache entries if number of them is small enough. Since we have removed NCE (Neighbour Cache Entry) reference from routing entries, the only refcnt holders of an NCE are its timer (if running) and its owner table, in usual cases. As a result, neigh_periodic_work() purges NCEs over and over again even for gateways. It does not make sense to purge entries, if number of them is very small, so keep them. The minimum number of entries to keep is specified by gc_thresh1. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 5 +++++ net/core/neighbour.c | 4 ++++ 2 files changed, 9 insertions(+) (limited to 'net/core') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 497656473b1..19ac1802bfd 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -26,6 +26,11 @@ route/max_size - INTEGER Maximum number of routes allowed in the kernel. Increase this when using large numbers of interfaces and/or routes. +neigh/default/gc_thresh1 - INTEGER + Minimum number of entries to keep. Garbage collector will not + purge entries if there are fewer than this number. + Default: 256 + neigh/default/gc_thresh3 - INTEGER Maximum number of neighbor entries allowed. Increase this when using large numbers of interfaces and when communicating diff --git a/net/core/neighbour.c b/net/core/neighbour.c index c815f285e5a..7bd0eedb357 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -778,6 +778,9 @@ static void neigh_periodic_work(struct work_struct *work) nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); + if (atomic_read(&tbl->entries) < tbl->gc_thresh1) + goto out; + /* * periodically recompute ReachableTime from random function */ @@ -832,6 +835,7 @@ next_elt: nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); } +out: /* Cycle through all hash buckets every base_reachable_time/2 ticks. * ARP entry timeouts range from 1/2 base_reachable_time to 3/2 * base_reachable_time. -- cgit v1.2.3-70-g09d2 From 8fbcec241df21d1ba2aba09974ea9017832b69b0 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki / 吉藤英明 Date: Tue, 22 Jan 2013 06:32:44 +0000 Subject: net: Use IS_ERR_OR_NULL(). Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- net/core/flow.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/flow.c b/net/core/flow.c index b0901ee5a00..43f7495df27 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -286,7 +286,7 @@ nocache: else fle->genid--; } else { - if (flo && !IS_ERR(flo)) + if (!IS_ERR_OR_NULL(flo)) flo->ops->delete(flo); } ret_object: -- cgit v1.2.3-70-g09d2 From e39363a9def53dd4086be107dc8b3ebca09f045d Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 22 Jan 2013 17:39:11 +0000 Subject: netpoll: fix an uninitialized variable Fengguang reported: net/core/netpoll.c: In function 'netpoll_setup': net/core/netpoll.c:1049:6: warning: 'err' may be used uninitialized in this function [-Wmaybe-uninitialized] in !CONFIG_IPV6 case, we may error out without initializing 'err'. Reported-by: Fengguang Wu Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/core/netpoll.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/core') diff --git a/net/core/netpoll.c b/net/core/netpoll.c index a9b10048388..e2f79a14625 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -1140,6 +1140,7 @@ int netpoll_setup(struct netpoll *np) #else np_err(np, "IPv6 is not supported %s, aborting\n", np->dev_name); + err = -EINVAL; goto put; #endif } -- cgit v1.2.3-70-g09d2 From 055dc21a1d1d219608cd4baac7d0683fb2cbbe8a Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 22 Jan 2013 09:49:50 +0000 Subject: soreuseport: infrastructure Definitions and macros for implementing soreusport. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- arch/alpha/include/uapi/asm/socket.h | 2 +- arch/avr32/include/uapi/asm/socket.h | 2 +- arch/cris/include/uapi/asm/socket.h | 2 +- arch/frv/include/uapi/asm/socket.h | 2 +- arch/h8300/include/uapi/asm/socket.h | 2 +- arch/ia64/include/uapi/asm/socket.h | 2 +- arch/m32r/include/uapi/asm/socket.h | 2 +- arch/mips/include/uapi/asm/socket.h | 3 +-- arch/mn10300/include/uapi/asm/socket.h | 2 +- arch/parisc/include/uapi/asm/socket.h | 2 +- arch/powerpc/include/uapi/asm/socket.h | 2 +- arch/s390/include/uapi/asm/socket.h | 2 +- arch/sparc/include/uapi/asm/socket.h | 2 +- arch/xtensa/include/uapi/asm/socket.h | 2 +- include/linux/random.h | 6 ++++++ include/net/sock.h | 5 ++++- include/uapi/asm-generic/socket.h | 3 +-- net/core/sock.c | 7 +++++++ 18 files changed, 32 insertions(+), 18 deletions(-) (limited to 'net/core') diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 755702eefd9..c5195524d1e 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -19,7 +19,7 @@ #define SO_BROADCAST 0x0020 #define SO_LINGER 0x0080 #define SO_OOBINLINE 0x0100 -/* To add :#define SO_REUSEPORT 0x0200 */ +#define SO_REUSEPORT 0x0200 #define SO_TYPE 0x1008 #define SO_ERROR 0x1007 diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h index f3f38a0e2ef..51c6401582e 100644 --- a/arch/avr32/include/uapi/asm/socket.h +++ b/arch/avr32/include/uapi/asm/socket.h @@ -22,7 +22,7 @@ #define SO_PRIORITY 12 #define SO_LINGER 13 #define SO_BSDCOMPAT 14 -/* To add :#define SO_REUSEPORT 15 */ +#define SO_REUSEPORT 15 #define SO_PASSCRED 16 #define SO_PEERCRED 17 #define SO_RCVLOWAT 18 diff --git a/arch/cris/include/uapi/asm/socket.h b/arch/cris/include/uapi/asm/socket.h index 406b5838def..50692b738c7 100644 --- a/arch/cris/include/uapi/asm/socket.h +++ b/arch/cris/include/uapi/asm/socket.h @@ -24,7 +24,7 @@ #define SO_PRIORITY 12 #define SO_LINGER 13 #define SO_BSDCOMPAT 14 -/* To add :#define SO_REUSEPORT 15 */ +#define SO_REUSEPORT 15 #define SO_PASSCRED 16 #define SO_PEERCRED 17 #define SO_RCVLOWAT 18 diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h index d8e1132a1ab..595391f0f98 100644 --- a/arch/frv/include/uapi/asm/socket.h +++ b/arch/frv/include/uapi/asm/socket.h @@ -22,7 +22,7 @@ #define SO_PRIORITY 12 #define SO_LINGER 13 #define SO_BSDCOMPAT 14 -/* To add :#define SO_REUSEPORT 15 */ +#define SO_REUSEPORT 15 #define SO_PASSCRED 16 #define SO_PEERCRED 17 #define SO_RCVLOWAT 18 diff --git a/arch/h8300/include/uapi/asm/socket.h b/arch/h8300/include/uapi/asm/socket.h index c8b87a82820..43e32621da7 100644 --- a/arch/h8300/include/uapi/asm/socket.h +++ b/arch/h8300/include/uapi/asm/socket.h @@ -22,7 +22,7 @@ #define SO_PRIORITY 12 #define SO_LINGER 13 #define SO_BSDCOMPAT 14 -/* To add :#define SO_REUSEPORT 15 */ +#define SO_REUSEPORT 15 #define SO_PASSCRED 16 #define SO_PEERCRED 17 #define SO_RCVLOWAT 18 diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index f390896c310..c567adc8bea 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -31,7 +31,7 @@ #define SO_PRIORITY 12 #define SO_LINGER 13 #define SO_BSDCOMPAT 14 -/* To add :#define SO_REUSEPORT 15 */ +#define SO_REUSEPORT 15 #define SO_PASSCRED 16 #define SO_PEERCRED 17 #define SO_RCVLOWAT 18 diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h index 6a895155e7a..519afa2755d 100644 --- a/arch/m32r/include/uapi/asm/socket.h +++ b/arch/m32r/include/uapi/asm/socket.h @@ -22,7 +22,7 @@ #define SO_PRIORITY 12 #define SO_LINGER 13 #define SO_BSDCOMPAT 14 -/* To add :#define SO_REUSEPORT 15 */ +#define SO_REUSEPORT 15 #define SO_PASSCRED 16 #define SO_PEERCRED 17 #define SO_RCVLOWAT 18 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 9d11a771392..7e2723637b3 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -28,8 +28,7 @@ #define SO_LINGER 0x0080 /* Block on close of a reliable socket to transmit pending data. */ #define SO_OOBINLINE 0x0100 /* Receive out-of-band data in-band. */ -#if 0 -To add: #define SO_REUSEPORT 0x0200 /* Allow local address and port reuse. */ +#define SO_REUSEPORT 0x0200 /* Allow local address and port reuse. */ #endif #define SO_TYPE 0x1008 /* Compatible name for SO_STYLE. */ diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h index ab702c40b30..5c7c7c98854 100644 --- a/arch/mn10300/include/uapi/asm/socket.h +++ b/arch/mn10300/include/uapi/asm/socket.h @@ -22,7 +22,7 @@ #define SO_PRIORITY 12 #define SO_LINGER 13 #define SO_BSDCOMPAT 14 -/* To add :#define SO_REUSEPORT 15 */ +#define SO_REUSEPORT 15 #define SO_PASSCRED 16 #define SO_PEERCRED 17 #define SO_RCVLOWAT 18 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index da2c8d3c209..526e4b9aece 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -13,7 +13,7 @@ #define SO_BROADCAST 0x0020 #define SO_LINGER 0x0080 #define SO_OOBINLINE 0x0100 -/* To add :#define SO_REUSEPORT 0x0200 */ +#define SO_REUSEPORT 0x0200 #define SO_SNDBUF 0x1001 #define SO_RCVBUF 0x1002 #define SO_SNDBUFFORCE 0x100a diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index e6ca31816cc..a26dcaece50 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -29,7 +29,7 @@ #define SO_PRIORITY 12 #define SO_LINGER 13 #define SO_BSDCOMPAT 14 -/* To add :#define SO_REUSEPORT 15 */ +#define SO_REUSEPORT 15 #define SO_RCVLOWAT 16 #define SO_SNDLOWAT 17 #define SO_RCVTIMEO 18 diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index 9ce60b68f07..f99eea7fff0 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -28,7 +28,7 @@ #define SO_PRIORITY 12 #define SO_LINGER 13 #define SO_BSDCOMPAT 14 -/* To add :#define SO_REUSEPORT 15 */ +#define SO_REUSEPORT 15 #define SO_PASSCRED 16 #define SO_PEERCRED 17 #define SO_RCVLOWAT 18 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index fbbba57547d..cbbad74b2e0 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -15,7 +15,7 @@ #define SO_PEERCRED 0x0040 #define SO_LINGER 0x0080 #define SO_OOBINLINE 0x0100 -/* To add :#define SO_REUSEPORT 0x0200 */ +#define SO_REUSEPORT 0x0200 #define SO_BSDCOMPAT 0x0400 #define SO_RCVLOWAT 0x0800 #define SO_SNDLOWAT 0x1000 diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index dbf316487b5..35905cb6e41 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -32,7 +32,7 @@ #define SO_PRIORITY 12 #define SO_LINGER 13 #define SO_BSDCOMPAT 14 -/* To add :#define SO_REUSEPORT 15 */ +#define SO_REUSEPORT 15 #define SO_PASSCRED 16 #define SO_PEERCRED 17 #define SO_RCVLOWAT 18 diff --git a/include/linux/random.h b/include/linux/random.h index d9846088c2c..347ce553a30 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -74,4 +74,10 @@ static inline int arch_get_random_int(unsigned int *v) } #endif +/* Pseudo random number generator from numerical recipes. */ +static inline u32 next_pseudo_random32(u32 seed) +{ + return seed * 1664525 + 1013904223; +} + #endif /* _LINUX_RANDOM_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 5a34e2f0365..581dc6bd7dc 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -140,6 +140,7 @@ typedef __u64 __bitwise __addrpair; * @skc_family: network address family * @skc_state: Connection state * @skc_reuse: %SO_REUSEADDR setting + * @skc_reuseport: %SO_REUSEPORT setting * @skc_bound_dev_if: bound device index if != 0 * @skc_bind_node: bind hash linkage for various protocol lookup tables * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol @@ -179,7 +180,8 @@ struct sock_common { unsigned short skc_family; volatile unsigned char skc_state; - unsigned char skc_reuse; + unsigned char skc_reuse:4; + unsigned char skc_reuseport:4; int skc_bound_dev_if; union { struct hlist_node skc_bind_node; @@ -297,6 +299,7 @@ struct sock { #define sk_family __sk_common.skc_family #define sk_state __sk_common.skc_state #define sk_reuse __sk_common.skc_reuse +#define sk_reuseport __sk_common.skc_reuseport #define sk_bound_dev_if __sk_common.skc_bound_dev_if #define sk_bind_node __sk_common.skc_bind_node #define sk_prot __sk_common.skc_prot diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 3f6a9920141..4ef3acbba5d 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -22,8 +22,7 @@ #define SO_PRIORITY 12 #define SO_LINGER 13 #define SO_BSDCOMPAT 14 -/* To add :#define SO_REUSEPORT 15 */ - +#define SO_REUSEPORT 15 #ifndef SO_PASSCRED /* powerpc only differs in these */ #define SO_PASSCRED 16 #define SO_PEERCRED 17 diff --git a/net/core/sock.c b/net/core/sock.c index 8258fb741e9..235fb89e897 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -665,6 +665,9 @@ int sock_setsockopt(struct socket *sock, int level, int optname, case SO_REUSEADDR: sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); break; + case SO_REUSEPORT: + sk->sk_reuseport = valbool; + break; case SO_TYPE: case SO_PROTOCOL: case SO_DOMAIN: @@ -972,6 +975,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_reuse; break; + case SO_REUSEPORT: + v.val = sk->sk_reuseport; + break; + case SO_KEEPALIVE: v.val = sock_flag(sk, SOCK_KEEPOPEN); break; -- cgit v1.2.3-70-g09d2 From cef401de7be8c4e155c6746bfccf721a4fa5fab9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Jan 2013 20:34:37 +0000 Subject: net: fix possible wrong checksum generation Pravin Shelar mentioned that GSO could potentially generate wrong TX checksum if skb has fragments that are overwritten by the user between the checksum computation and transmit. He suggested to linearize skbs but this extra copy can be avoided for normal tcp skbs cooked by tcp_sendmsg(). This patch introduces a new SKB_GSO_SHARED_FRAG flag, set in skb_shinfo(skb)->gso_type if at least one frag can be modified by the user. Typical sources of such possible overwrites are {vm}splice(), sendfile(), and macvtap/tun/virtio_net drivers. Tested: $ netperf -H 7.7.8.84 MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.8.84 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 10.00 3959.52 $ netperf -H 7.7.8.84 -t TCP_SENDFILE TCP SENDFILE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.8.84 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 10.00 3216.80 Performance of the SENDFILE is impacted by the extra allocation and copy, and because we use order-0 pages, while the TCP_STREAM uses bigger pages. Reported-by: Pravin Shelar Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 3 ++- drivers/net/tun.c | 12 ++++++++---- drivers/net/virtio_net.c | 12 ++++++++---- include/linux/skbuff.h | 19 +++++++++++++++++++ net/core/dev.c | 9 +++++++++ net/core/skbuff.c | 4 ++++ net/ipv4/af_inet.c | 1 + net/ipv4/ip_gre.c | 4 +++- net/ipv4/ipip.c | 4 +++- net/ipv4/tcp.c | 3 +++ net/ipv4/tcp_input.c | 4 ++-- net/ipv4/tcp_output.c | 4 ++-- net/ipv6/ip6_offload.c | 1 + 13 files changed, 65 insertions(+), 15 deletions(-) (limited to 'net/core') diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 0f0f9ce3a77..b181dfb3d6d 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -543,6 +543,7 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from, skb->data_len += len; skb->len += len; skb->truesize += truesize; + skb_shinfo(skb)->gso_type |= SKB_GSO_SHARED_FRAG; atomic_add(truesize, &skb->sk->sk_wmem_alloc); while (len) { int off = base & ~PAGE_MASK; @@ -598,7 +599,7 @@ static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb, if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { skb_shinfo(skb)->gso_size = vnet_hdr->gso_size; - skb_shinfo(skb)->gso_type = gso_type; + skb_shinfo(skb)->gso_type |= gso_type; /* Header must be checked, and gso_segs computed. */ skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index c81680dc10e..293ce8dfc9e 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1005,6 +1005,7 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from, skb->data_len += len; skb->len += len; skb->truesize += truesize; + skb_shinfo(skb)->gso_type |= SKB_GSO_SHARED_FRAG; atomic_add(truesize, &skb->sk->sk_wmem_alloc); while (len) { int off = base & ~PAGE_MASK; @@ -1150,16 +1151,18 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, } if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) { + unsigned short gso_type = 0; + pr_debug("GSO!\n"); switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + gso_type = SKB_GSO_TCPV4; break; case VIRTIO_NET_HDR_GSO_TCPV6: - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + gso_type = SKB_GSO_TCPV6; break; case VIRTIO_NET_HDR_GSO_UDP: - skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + gso_type = SKB_GSO_UDP; break; default: tun->dev->stats.rx_frame_errors++; @@ -1168,9 +1171,10 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, } if (gso.gso_type & VIRTIO_NET_HDR_GSO_ECN) - skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; + gso_type |= SKB_GSO_TCP_ECN; skb_shinfo(skb)->gso_size = gso.gso_size; + skb_shinfo(skb)->gso_type |= gso_type; if (skb_shinfo(skb)->gso_size == 0) { tun->dev->stats.rx_frame_errors++; kfree_skb(skb); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 701408a1ded..58914c8ea68 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -220,6 +220,7 @@ static void set_skb_frag(struct sk_buff *skb, struct page *page, skb->len += size; skb->truesize += PAGE_SIZE; skb_shinfo(skb)->nr_frags++; + skb_shinfo(skb)->gso_type |= SKB_GSO_SHARED_FRAG; *len -= size; } @@ -379,16 +380,18 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len) ntohs(skb->protocol), skb->len, skb->pkt_type); if (hdr->hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) { + unsigned short gso_type = 0; + pr_debug("GSO!\n"); switch (hdr->hdr.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + gso_type = SKB_GSO_TCPV4; break; case VIRTIO_NET_HDR_GSO_UDP: - skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + gso_type = SKB_GSO_UDP; break; case VIRTIO_NET_HDR_GSO_TCPV6: - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + gso_type = SKB_GSO_TCPV6; break; default: net_warn_ratelimited("%s: bad gso type %u.\n", @@ -397,7 +400,7 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len) } if (hdr->hdr.gso_type & VIRTIO_NET_HDR_GSO_ECN) - skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; + gso_type |= SKB_GSO_TCP_ECN; skb_shinfo(skb)->gso_size = hdr->hdr.gso_size; if (skb_shinfo(skb)->gso_size == 0) { @@ -405,6 +408,7 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len) goto frame_err; } + skb_shinfo(skb)->gso_type |= gso_type; /* Header must be checked, and gso_segs computed. */ skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; skb_shinfo(skb)->gso_segs = 0; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8b2256e880e..0259b719beb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -307,6 +307,13 @@ enum { SKB_GSO_TCPV6 = 1 << 4, SKB_GSO_FCOE = 1 << 5, + + /* This indicates at least one fragment might be overwritten + * (as in vmsplice(), sendfile() ...) + * If we need to compute a TX checksum, we'll need to copy + * all frags to avoid possible bad checksum + */ + SKB_GSO_SHARED_FRAG = 1 << 6, }; #if BITS_PER_LONG > 32 @@ -2200,6 +2207,18 @@ static inline int skb_linearize(struct sk_buff *skb) return skb_is_nonlinear(skb) ? __skb_linearize(skb) : 0; } +/** + * skb_has_shared_frag - can any frag be overwritten + * @skb: buffer to test + * + * Return true if the skb has at least one frag that might be modified + * by an external entity (as in vmsplice()/sendfile()) + */ +static inline bool skb_has_shared_frag(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->gso_type & SKB_GSO_SHARED_FRAG; +} + /** * skb_linearize_cow - make sure skb is linear and writable * @skb: buffer to process diff --git a/net/core/dev.c b/net/core/dev.c index c69cd8721b2..a83375d3af7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2271,6 +2271,15 @@ int skb_checksum_help(struct sk_buff *skb) return -EINVAL; } + /* Before computing a checksum, we should make sure no frag could + * be modified by an external entity : checksum could be wrong. + */ + if (skb_has_shared_frag(skb)) { + ret = __skb_linearize(skb); + if (ret) + goto out; + } + offset = skb_checksum_start_offset(skb); BUG_ON(offset >= skb_headlen(skb)); csum = skb_checksum(skb, offset, skb->len - offset, 0); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2568c449fe3..bddc1dd2e7f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2340,6 +2340,8 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); + skb_shinfo(skb1)->gso_type = skb_shinfo(skb)->gso_type; + if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); else /* Second chunk has no header, nothing to copy. */ @@ -2845,6 +2847,8 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) skb_copy_from_linear_data_offset(skb, offset, skb_put(nskb, hsize), hsize); + skb_shinfo(nskb)->gso_type = skb_shinfo(skb)->gso_type; + while (pos < offset + len && i < nfrags) { *frag = skb_shinfo(skb)->frags[i]; __skb_frag_ref(frag); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 4b705391997..49ddca31c4d 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1306,6 +1306,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_TCP_ECN | + SKB_GSO_SHARED_FRAG | 0))) goto out; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 303012adf9e..af6be70821c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -738,7 +738,7 @@ drop: static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - const struct iphdr *old_iph = ip_hdr(skb); + const struct iphdr *old_iph; const struct iphdr *tiph; struct flowi4 fl4; u8 tos; @@ -756,6 +756,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev skb_checksum_help(skb)) goto tx_error; + old_iph = ip_hdr(skb); + if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 191fc24a745..8f024d41eef 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -472,7 +472,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ struct net_device *tdev; /* Device to other host */ - const struct iphdr *old_iph = ip_hdr(skb); + const struct iphdr *old_iph; struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst = tiph->daddr; @@ -486,6 +486,8 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) skb_checksum_help(skb)) goto tx_error; + old_iph = ip_hdr(skb); + if (tos & 1) tos = old_iph->tos; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 52271947a47..3ec1f69c5ce 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -896,6 +896,8 @@ new_segment: skb_fill_page_desc(skb, i, page, offset, copy); } + skb_shinfo(skb)->gso_type |= SKB_GSO_SHARED_FRAG; + skb->len += copy; skb->data_len += copy; skb->truesize += copy; @@ -3032,6 +3034,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, SKB_GSO_DODGY | SKB_GSO_TCP_ECN | SKB_GSO_TCPV6 | + SKB_GSO_SHARED_FRAG | 0) || !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))) goto out; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0905997e587..492c7cfe145 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1240,13 +1240,13 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, */ if (!skb_shinfo(prev)->gso_size) { skb_shinfo(prev)->gso_size = mss; - skb_shinfo(prev)->gso_type = sk->sk_gso_type; + skb_shinfo(prev)->gso_type |= sk->sk_gso_type; } /* CHECKME: To clear or not to clear? Mimics normal skb currently */ if (skb_shinfo(skb)->gso_segs <= 1) { skb_shinfo(skb)->gso_size = 0; - skb_shinfo(skb)->gso_type = 0; + skb_shinfo(skb)->gso_type &= SKB_GSO_SHARED_FRAG; } /* Difference in this won't matter, both ACKed by the same cumul. ACK */ diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 667a6adfccf..367e2ec01da 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1133,6 +1133,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { + skb_shinfo(skb)->gso_type &= SKB_GSO_SHARED_FRAG; if (skb->len <= mss_now || !sk_can_gso(sk) || skb->ip_summed == CHECKSUM_NONE) { /* Avoid the costly divide in the normal @@ -1140,11 +1141,10 @@ static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb, */ skb_shinfo(skb)->gso_segs = 1; skb_shinfo(skb)->gso_size = 0; - skb_shinfo(skb)->gso_type = 0; } else { skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss_now); skb_shinfo(skb)->gso_size = mss_now; - skb_shinfo(skb)->gso_type = sk->sk_gso_type; + skb_shinfo(skb)->gso_type |= sk->sk_gso_type; } } diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index f26f0da7f09..d141fc32a2e 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -100,6 +100,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, SKB_GSO_DODGY | SKB_GSO_TCP_ECN | SKB_GSO_TCPV6 | + SKB_GSO_SHARED_FRAG | 0))) goto out; -- cgit v1.2.3-70-g09d2 From faeed828f9607923e9dc22182e819908e95c8852 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sun, 27 Jan 2013 15:55:20 +0000 Subject: netpoll: use ipv6_addr_equal() to compare ipv6 addr ipv6_addr_equal() is faster. Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/core/netpoll.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/core') diff --git a/net/core/netpoll.c b/net/core/netpoll.c index e2f79a14625..a6f39b6aeec 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -635,7 +635,7 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo spin_lock_irqsave(&npinfo->rx_lock, flags); list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (memcmp(daddr, &np->local_ip, sizeof(*daddr))) + if (!ipv6_addr_equal(daddr, &np->local_ip.in6)) continue; hlen = LL_RESERVED_SPACE(np->dev); @@ -828,9 +828,9 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) if (udp6_csum_init(skb, uh, IPPROTO_UDP)) goto out; list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (memcmp(&np->local_ip.in6, &ip6h->daddr, sizeof(struct in6_addr)) != 0) + if (!ipv6_addr_equal(&np->local_ip.in6, &ip6h->daddr)) continue; - if (memcmp(&np->remote_ip.in6, &ip6h->saddr, sizeof(struct in6_addr)) != 0) + if (!ipv6_addr_equal(&np->remote_ip.in6, &ip6h->saddr)) continue; if (np->local_port && np->local_port != ntohs(uh->dest)) continue; -- cgit v1.2.3-70-g09d2 From 556e6256c813063b95a9f4e55109f77c1a7d3fdd Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sun, 27 Jan 2013 15:55:21 +0000 Subject: netpoll: use the net namespace of current process instead of init_net This will allow us to setup netconsole in a different namespace rather than where init_net is. Cc: Eric W. Biederman Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/core/netpoll.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net/core') diff --git a/net/core/netpoll.c b/net/core/netpoll.c index a6f39b6aeec..331ccb90f91 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -1049,8 +1049,10 @@ int netpoll_setup(struct netpoll *np) int err; rtnl_lock(); - if (np->dev_name) - ndev = __dev_get_by_name(&init_net, np->dev_name); + if (np->dev_name) { + struct net *net = current->nsproxy->net_ns; + ndev = __dev_get_by_name(net, np->dev_name); + } if (!ndev) { np_err(np, "%s doesn't exist, aborting\n", np->dev_name); err = -ENODEV; -- cgit v1.2.3-70-g09d2 From cdda88912d62f9603d27433338a18be83ef23ac1 Mon Sep 17 00:00:00 2001 From: "bingtian.ly@taobao.com" Date: Wed, 23 Jan 2013 20:35:28 +0000 Subject: net: avoid to hang up on sending due to sysctl configuration overflow. I found if we write a larger than 4GB value to some sysctl variables, the sending syscall will hang up forever, because these variables are 32 bits, such large values make them overflow to 0 or negative. This patch try to fix overflow or prevent from zero value setup of below sysctl variables: net.core.wmem_default net.core.rmem_default net.core.rmem_max net.core.wmem_max net.ipv4.udp_rmem_min net.ipv4.udp_wmem_min net.ipv4.tcp_wmem net.ipv4.tcp_rmem Signed-off-by: Eric Dumazet Signed-off-by: Li Yu Signed-off-by: David S. Miller --- net/core/sysctl_net_core.c | 14 ++++++++++---- net/ipv4/sysctl_net_ipv4.c | 11 +++++++---- 2 files changed, 17 insertions(+), 8 deletions(-) (limited to 'net/core') diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index d1b08045a9d..cfdb46ab3a7 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -20,6 +20,8 @@ #include #include +static int one = 1; + #ifdef CONFIG_RPS static int rps_sock_flow_sysctl(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -92,28 +94,32 @@ static struct ctl_table net_core_table[] = { .data = &sysctl_wmem_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "rmem_max", .data = &sysctl_rmem_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "wmem_default", .data = &sysctl_wmem_default, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "rmem_default", .data = &sysctl_rmem_default, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "dev_weight", diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index a25e1d286b9..2622707602d 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -27,6 +27,7 @@ #include static int zero; +static int one = 1; static int two = 2; static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; @@ -549,14 +550,16 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_wmem, .maxlen = sizeof(sysctl_tcp_wmem), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "tcp_rmem", .data = &sysctl_tcp_rmem, .maxlen = sizeof(sysctl_tcp_rmem), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "tcp_app_win", @@ -779,7 +782,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_udp_rmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .extra1 = &one }, { .procname = "udp_wmem_min", @@ -787,7 +790,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_udp_wmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .extra1 = &one }, { } }; -- cgit v1.2.3-70-g09d2 From 08433eff2d041b263c68306f6a6ccb4e1f75e196 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki / 吉藤英明 Date: Thu, 24 Jan 2013 00:44:23 +0000 Subject: net neigh: Optimize neighbor entry size calculation. When allocating memory for neighbour cache entry, if tbl->entry_size is not set, we always calculate sizeof(struct neighbour) + tbl->key_len, which is common in the same table. With this change, set tbl->entry_size during the table initialization phase, if it was not set, and use it in neigh_alloc() and neighbour_priv(). This change also allow us to have both of protocol private data and device priate data at tha same time. Note that the only user of prototcol private is DECnet and the only user of device private is ATM CLIP. Since those are exclusive, we have not been facing issues here. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/net/neighbour.h | 2 +- net/core/neighbour.c | 16 +++++++--------- 2 files changed, 8 insertions(+), 10 deletions(-) (limited to 'net/core') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 0dab173e27d..629ee573c6d 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -184,7 +184,7 @@ struct neigh_table { static inline void *neighbour_priv(const struct neighbour *n) { - return (char *)n + ALIGN(sizeof(*n) + n->tbl->key_len, NEIGH_PRIV_ALIGN); + return (char *)n + n->tbl->entry_size; } /* flags for neigh_update() */ diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 7bd0eedb357..3863b8f639c 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -290,15 +290,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device goto out_entries; } - if (tbl->entry_size) - n = kzalloc(tbl->entry_size, GFP_ATOMIC); - else { - int sz = sizeof(*n) + tbl->key_len; - - sz = ALIGN(sz, NEIGH_PRIV_ALIGN); - sz += dev->neigh_priv_len; - n = kzalloc(sz, GFP_ATOMIC); - } + n = kzalloc(tbl->entry_size + dev->neigh_priv_len, GFP_ATOMIC); if (!n) goto out_entries; @@ -1546,6 +1538,12 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl) if (!tbl->nht || !tbl->phash_buckets) panic("cannot allocate neighbour cache hashes"); + if (!tbl->entry_size) + tbl->entry_size = ALIGN(offsetof(struct neighbour, primary_key) + + tbl->key_len, NEIGH_PRIV_ALIGN); + else + WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN); + rwlock_init(&tbl->lock); INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time); -- cgit v1.2.3-70-g09d2 From 4e58a0275015e5c8988bda9cd0635e2ef405c985 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 28 Jan 2013 19:55:53 +0000 Subject: pktgen: support net namespace v3: make pktgen_threads list per-namespace v2: remove a useless check This patch add net namespace to pktgen, so that we can use pktgen in different namespaces. Cc: Eric W. Biederman Cc: David S. Miller Signed-off-by: Cong Wang Acked-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- net/core/pktgen.c | 196 ++++++++++++++++++++++++++++++++---------------------- 1 file changed, 117 insertions(+), 79 deletions(-) (limited to 'net/core') diff --git a/net/core/pktgen.c b/net/core/pktgen.c index b29dacf900f..797769551b9 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -164,6 +164,7 @@ #ifdef CONFIG_XFRM #include #endif +#include #include #include #include @@ -212,7 +213,6 @@ #define PKTGEN_MAGIC 0xbe9be955 #define PG_PROC_DIR "pktgen" #define PGCTRL "pgctrl" -static struct proc_dir_entry *pg_proc_dir; #define MAX_CFLOWS 65536 @@ -397,7 +397,15 @@ struct pktgen_hdr { __be32 tv_usec; }; -static bool pktgen_exiting __read_mostly; + +static int pg_net_id __read_mostly; + +struct pktgen_net { + struct net *net; + struct proc_dir_entry *proc_dir; + struct list_head pktgen_threads; + bool pktgen_exiting; +}; struct pktgen_thread { spinlock_t if_lock; /* for list of devices */ @@ -414,6 +422,7 @@ struct pktgen_thread { wait_queue_head_t queue; struct completion start_done; + struct pktgen_net *net; }; #define REMOVE 1 @@ -428,9 +437,9 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname); static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, const char *ifname, bool exact); static int pktgen_device_event(struct notifier_block *, unsigned long, void *); -static void pktgen_run_all_threads(void); -static void pktgen_reset_all_threads(void); -static void pktgen_stop_all_threads_ifs(void); +static void pktgen_run_all_threads(struct pktgen_net *pn); +static void pktgen_reset_all_threads(struct pktgen_net *pn); +static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn); static void pktgen_stop(struct pktgen_thread *t); static void pktgen_clear_counters(struct pktgen_dev *pkt_dev); @@ -442,7 +451,6 @@ static int pg_clone_skb_d __read_mostly; static int debug __read_mostly; static DEFINE_MUTEX(pktgen_thread_lock); -static LIST_HEAD(pktgen_threads); static struct notifier_block pktgen_notifier_block = { .notifier_call = pktgen_device_event, @@ -464,6 +472,7 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, { int err = 0; char data[128]; + struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id); if (!capable(CAP_NET_ADMIN)) { err = -EPERM; @@ -480,13 +489,13 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, data[count - 1] = 0; /* Make string */ if (!strcmp(data, "stop")) - pktgen_stop_all_threads_ifs(); + pktgen_stop_all_threads_ifs(pn); else if (!strcmp(data, "start")) - pktgen_run_all_threads(); + pktgen_run_all_threads(pn); else if (!strcmp(data, "reset")) - pktgen_reset_all_threads(); + pktgen_reset_all_threads(pn); else pr_warning("Unknown command: %s\n", data); @@ -1824,13 +1833,14 @@ static const struct file_operations pktgen_thread_fops = { }; /* Think find or remove for NN */ -static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) +static struct pktgen_dev *__pktgen_NN_threads(const struct pktgen_net *pn, + const char *ifname, int remove) { struct pktgen_thread *t; struct pktgen_dev *pkt_dev = NULL; bool exact = (remove == FIND); - list_for_each_entry(t, &pktgen_threads, th_list) { + list_for_each_entry(t, &pn->pktgen_threads, th_list) { pkt_dev = pktgen_find_dev(t, ifname, exact); if (pkt_dev) { if (remove) { @@ -1848,7 +1858,7 @@ static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) /* * mark a device for removal */ -static void pktgen_mark_device(const char *ifname) +static void pktgen_mark_device(const struct pktgen_net *pn, const char *ifname) { struct pktgen_dev *pkt_dev = NULL; const int max_tries = 10, msec_per_try = 125; @@ -1859,7 +1869,7 @@ static void pktgen_mark_device(const char *ifname) while (1) { - pkt_dev = __pktgen_NN_threads(ifname, REMOVE); + pkt_dev = __pktgen_NN_threads(pn, ifname, REMOVE); if (pkt_dev == NULL) break; /* success */ @@ -1880,21 +1890,21 @@ static void pktgen_mark_device(const char *ifname) mutex_unlock(&pktgen_thread_lock); } -static void pktgen_change_name(struct net_device *dev) +static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *dev) { struct pktgen_thread *t; - list_for_each_entry(t, &pktgen_threads, th_list) { + list_for_each_entry(t, &pn->pktgen_threads, th_list) { struct pktgen_dev *pkt_dev; list_for_each_entry(pkt_dev, &t->if_list, list) { if (pkt_dev->odev != dev) continue; - remove_proc_entry(pkt_dev->entry->name, pg_proc_dir); + remove_proc_entry(pkt_dev->entry->name, pn->proc_dir); pkt_dev->entry = proc_create_data(dev->name, 0600, - pg_proc_dir, + pn->proc_dir, &pktgen_if_fops, pkt_dev); if (!pkt_dev->entry) @@ -1909,8 +1919,9 @@ static int pktgen_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = ptr; + struct pktgen_net *pn = net_generic(dev_net(dev), pg_net_id); - if (!net_eq(dev_net(dev), &init_net) || pktgen_exiting) + if (pn->pktgen_exiting) return NOTIFY_DONE; /* It is OK that we do not hold the group lock right now, @@ -1919,18 +1930,19 @@ static int pktgen_device_event(struct notifier_block *unused, switch (event) { case NETDEV_CHANGENAME: - pktgen_change_name(dev); + pktgen_change_name(pn, dev); break; case NETDEV_UNREGISTER: - pktgen_mark_device(dev->name); + pktgen_mark_device(pn, dev->name); break; } return NOTIFY_DONE; } -static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev, +static struct net_device *pktgen_dev_get_by_name(const struct pktgen_net *pn, + struct pktgen_dev *pkt_dev, const char *ifname) { char b[IFNAMSIZ+5]; @@ -1944,13 +1956,14 @@ static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev, } b[i] = 0; - return dev_get_by_name(&init_net, b); + return dev_get_by_name(pn->net, b); } /* Associate pktgen_dev with a device. */ -static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname) +static int pktgen_setup_dev(const struct pktgen_net *pn, + struct pktgen_dev *pkt_dev, const char *ifname) { struct net_device *odev; int err; @@ -1961,7 +1974,7 @@ static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname) pkt_dev->odev = NULL; } - odev = pktgen_dev_get_by_name(pkt_dev, ifname); + odev = pktgen_dev_get_by_name(pn, pkt_dev, ifname); if (!odev) { pr_err("no such netdevice: \"%s\"\n", ifname); return -ENODEV; @@ -2203,9 +2216,10 @@ static inline int f_pick(struct pktgen_dev *pkt_dev) static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) { struct xfrm_state *x = pkt_dev->flows[flow].x; + struct pktgen_net *pn = net_generic(dev_net(pkt_dev->odev), pg_net_id); if (!x) { /*slow path: we dont already have xfrm_state*/ - x = xfrm_stateonly_find(&init_net, DUMMY_MARK, + x = xfrm_stateonly_find(pn->net, DUMMY_MARK, (xfrm_address_t *)&pkt_dev->cur_daddr, (xfrm_address_t *)&pkt_dev->cur_saddr, AF_INET, @@ -2912,7 +2926,7 @@ static void pktgen_run(struct pktgen_thread *t) t->control &= ~(T_STOP); } -static void pktgen_stop_all_threads_ifs(void) +static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn) { struct pktgen_thread *t; @@ -2920,7 +2934,7 @@ static void pktgen_stop_all_threads_ifs(void) mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= T_STOP; mutex_unlock(&pktgen_thread_lock); @@ -2956,28 +2970,28 @@ signal: return 0; } -static int pktgen_wait_all_threads_run(void) +static int pktgen_wait_all_threads_run(struct pktgen_net *pn) { struct pktgen_thread *t; int sig = 1; mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) { + list_for_each_entry(t, &pn->pktgen_threads, th_list) { sig = pktgen_wait_thread_run(t); if (sig == 0) break; } if (sig == 0) - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= (T_STOP); mutex_unlock(&pktgen_thread_lock); return sig; } -static void pktgen_run_all_threads(void) +static void pktgen_run_all_threads(struct pktgen_net *pn) { struct pktgen_thread *t; @@ -2985,7 +2999,7 @@ static void pktgen_run_all_threads(void) mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= (T_RUN); mutex_unlock(&pktgen_thread_lock); @@ -2993,10 +3007,10 @@ static void pktgen_run_all_threads(void) /* Propagate thread->control */ schedule_timeout_interruptible(msecs_to_jiffies(125)); - pktgen_wait_all_threads_run(); + pktgen_wait_all_threads_run(pn); } -static void pktgen_reset_all_threads(void) +static void pktgen_reset_all_threads(struct pktgen_net *pn) { struct pktgen_thread *t; @@ -3004,7 +3018,7 @@ static void pktgen_reset_all_threads(void) mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= (T_REMDEVALL); mutex_unlock(&pktgen_thread_lock); @@ -3012,7 +3026,7 @@ static void pktgen_reset_all_threads(void) /* Propagate thread->control */ schedule_timeout_interruptible(msecs_to_jiffies(125)); - pktgen_wait_all_threads_run(); + pktgen_wait_all_threads_run(pn); } static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) @@ -3154,9 +3168,7 @@ static void pktgen_rem_all_ifs(struct pktgen_thread *t) static void pktgen_rem_thread(struct pktgen_thread *t) { /* Remove from the thread list */ - - remove_proc_entry(t->tsk->comm, pg_proc_dir); - + remove_proc_entry(t->tsk->comm, t->net->proc_dir); } static void pktgen_resched(struct pktgen_dev *pkt_dev) @@ -3302,7 +3314,7 @@ static int pktgen_thread_worker(void *arg) pkt_dev = next_to_run(t); if (unlikely(!pkt_dev && t->control == 0)) { - if (pktgen_exiting) + if (t->net->pktgen_exiting) break; wait_event_interruptible_timeout(t->queue, t->control != 0, @@ -3424,7 +3436,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) /* We don't allow a device to be on several threads */ - pkt_dev = __pktgen_NN_threads(ifname, FIND); + pkt_dev = __pktgen_NN_threads(t->net, ifname, FIND); if (pkt_dev) { pr_err("ERROR: interface already used\n"); return -EBUSY; @@ -3459,13 +3471,13 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->svlan_id = 0xffff; pkt_dev->node = -1; - err = pktgen_setup_dev(pkt_dev, ifname); + err = pktgen_setup_dev(t->net, pkt_dev, ifname); if (err) goto out1; if (pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING) pkt_dev->clone_skb = pg_clone_skb_d; - pkt_dev->entry = proc_create_data(ifname, 0600, pg_proc_dir, + pkt_dev->entry = proc_create_data(ifname, 0600, t->net->proc_dir, &pktgen_if_fops, pkt_dev); if (!pkt_dev->entry) { pr_err("cannot create %s/%s procfs entry\n", @@ -3490,7 +3502,7 @@ out1: return err; } -static int __init pktgen_create_thread(int cpu) +static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn) { struct pktgen_thread *t; struct proc_dir_entry *pe; @@ -3508,7 +3520,7 @@ static int __init pktgen_create_thread(int cpu) INIT_LIST_HEAD(&t->if_list); - list_add_tail(&t->th_list, &pktgen_threads); + list_add_tail(&t->th_list, &pn->pktgen_threads); init_completion(&t->start_done); p = kthread_create_on_node(pktgen_thread_worker, @@ -3524,7 +3536,7 @@ static int __init pktgen_create_thread(int cpu) kthread_bind(p, cpu); t->tsk = p; - pe = proc_create_data(t->tsk->comm, 0600, pg_proc_dir, + pe = proc_create_data(t->tsk->comm, 0600, pn->proc_dir, &pktgen_thread_fops, t); if (!pe) { pr_err("cannot create %s/%s procfs entry\n", @@ -3535,6 +3547,7 @@ static int __init pktgen_create_thread(int cpu) return -EINVAL; } + t->net = pn; wake_up_process(p); wait_for_completion(&t->start_done); @@ -3560,6 +3573,7 @@ static void _rem_dev_from_if_list(struct pktgen_thread *t, static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *pkt_dev) { + struct pktgen_net *pn = t->net; pr_debug("remove_device pkt_dev=%p\n", pkt_dev); @@ -3580,7 +3594,7 @@ static int pktgen_remove_device(struct pktgen_thread *t, _rem_dev_from_if_list(t, pkt_dev); if (pkt_dev->entry) - remove_proc_entry(pkt_dev->entry->name, pg_proc_dir); + remove_proc_entry(pkt_dev->entry->name, pn->proc_dir); #ifdef CONFIG_XFRM free_SAs(pkt_dev); @@ -3592,63 +3606,63 @@ static int pktgen_remove_device(struct pktgen_thread *t, return 0; } -static int __init pg_init(void) +static int __net_init pg_net_init(struct net *net) { - int cpu; + struct pktgen_net *pn = net_generic(net, pg_net_id); struct proc_dir_entry *pe; - int ret = 0; - - pr_info("%s", version); - - pg_proc_dir = proc_mkdir(PG_PROC_DIR, init_net.proc_net); - if (!pg_proc_dir) + int cpu, ret = 0; + + pn->net = net; + INIT_LIST_HEAD(&pn->pktgen_threads); + pn->pktgen_exiting = false; + pn->proc_dir = proc_mkdir(PG_PROC_DIR, pn->net->proc_net); + if (!pn->proc_dir) { + pr_warn("cannot create /proc/net/%s\n", PG_PROC_DIR); return -ENODEV; - - pe = proc_create(PGCTRL, 0600, pg_proc_dir, &pktgen_fops); + } + pe = proc_create(PGCTRL, 0600, pn->proc_dir, &pktgen_fops); if (pe == NULL) { - pr_err("ERROR: cannot create %s procfs entry\n", PGCTRL); + pr_err("cannot create %s procfs entry\n", PGCTRL); ret = -EINVAL; - goto remove_dir; + goto remove; } - register_netdevice_notifier(&pktgen_notifier_block); - for_each_online_cpu(cpu) { int err; - err = pktgen_create_thread(cpu); + err = pktgen_create_thread(cpu, pn); if (err) - pr_warning("WARNING: Cannot create thread for cpu %d (%d)\n", + pr_warn("Cannot create thread for cpu %d (%d)\n", cpu, err); } - if (list_empty(&pktgen_threads)) { - pr_err("ERROR: Initialization failed for all threads\n"); + if (list_empty(&pn->pktgen_threads)) { + pr_err("Initialization failed for all threads\n"); ret = -ENODEV; - goto unregister; + goto remove_entry; } return 0; - unregister: - unregister_netdevice_notifier(&pktgen_notifier_block); - remove_proc_entry(PGCTRL, pg_proc_dir); - remove_dir: - proc_net_remove(&init_net, PG_PROC_DIR); +remove_entry: + remove_proc_entry(PGCTRL, pn->proc_dir); +remove: + proc_net_remove(pn->net, PG_PROC_DIR); return ret; } -static void __exit pg_cleanup(void) +static void __net_exit pg_net_exit(struct net *net) { + struct pktgen_net *pn = net_generic(net, pg_net_id); struct pktgen_thread *t; struct list_head *q, *n; LIST_HEAD(list); /* Stop all interfaces & threads */ - pktgen_exiting = true; + pn->pktgen_exiting = true; mutex_lock(&pktgen_thread_lock); - list_splice_init(&pktgen_threads, &list); + list_splice_init(&pn->pktgen_threads, &list); mutex_unlock(&pktgen_thread_lock); list_for_each_safe(q, n, &list) { @@ -3658,12 +3672,36 @@ static void __exit pg_cleanup(void) kfree(t); } - /* Un-register us from receiving netdevice events */ - unregister_netdevice_notifier(&pktgen_notifier_block); + remove_proc_entry(PGCTRL, pn->proc_dir); + proc_net_remove(pn->net, PG_PROC_DIR); +} + +static struct pernet_operations pg_net_ops = { + .init = pg_net_init, + .exit = pg_net_exit, + .id = &pg_net_id, + .size = sizeof(struct pktgen_net), +}; + +static int __init pg_init(void) +{ + int ret = 0; - /* Clean up proc file system */ - remove_proc_entry(PGCTRL, pg_proc_dir); - proc_net_remove(&init_net, PG_PROC_DIR); + pr_info("%s", version); + ret = register_pernet_subsys(&pg_net_ops); + if (ret) + return ret; + ret = register_netdevice_notifier(&pktgen_notifier_block); + if (ret) + unregister_pernet_subsys(&pg_net_ops); + + return ret; +} + +static void __exit pg_cleanup(void) +{ + unregister_netdevice_notifier(&pktgen_notifier_block); + unregister_pernet_subsys(&pg_net_ops); } module_init(pg_init); -- cgit v1.2.3-70-g09d2 From d2ed273d30c5ffd14f6b5ec7ecc751d960f832fc Mon Sep 17 00:00:00 2001 From: Michał Mirosław Date: Tue, 29 Jan 2013 15:14:16 +0000 Subject: net: disallow drivers with buggy VLAN accel to register_netdevice() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of jumping aroung bugs that are easily fixed just don't let them in: affected drivers should be either fixed or have NETIF_F_HW_VLAN_FILTER removed from advertised features. Quick grep in drivers/net shows two drivers that have NETIF_F_HW_VLAN_FILTER but not ndo_vlan_rx_add/kill_vid(), but those are false-positives (features are commented out). OTOH two drivers have ndo_vlan_rx_add/kill_vid() implemented but don't advertise NETIF_F_HW_VLAN_FILTER. Those are: +ethernet/cisco/enic/enic_main.c +ethernet/qlogic/qlcnic/qlcnic_main.c Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- net/8021q/vlan.c | 7 ------- net/8021q/vlan_core.c | 6 ++---- net/core/dev.c | 8 ++++++++ 3 files changed, 10 insertions(+), 11 deletions(-) (limited to 'net/core') diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index babfde9f734..addc578d544 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -117,19 +117,12 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id) { const char *name = real_dev->name; - const struct net_device_ops *ops = real_dev->netdev_ops; if (real_dev->features & NETIF_F_VLAN_CHALLENGED) { pr_info("VLANs not supported on %s\n", name); return -EOPNOTSUPP; } - if ((real_dev->features & NETIF_F_HW_VLAN_FILTER) && - (!ops->ndo_vlan_rx_add_vid || !ops->ndo_vlan_rx_kill_vid)) { - pr_info("Device %s has buggy VLAN hw accel\n", name); - return -EOPNOTSUPP; - } - if (vlan_find_dev(real_dev, vlan_id) != NULL) return -EEXIST; diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 380440b8ea8..71b64fde8dc 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -224,8 +224,7 @@ static int __vlan_vid_add(struct vlan_info *vlan_info, unsigned short vid, if (!vid_info) return -ENOMEM; - if ((dev->features & NETIF_F_HW_VLAN_FILTER) && - ops->ndo_vlan_rx_add_vid) { + if (dev->features & NETIF_F_HW_VLAN_FILTER) { err = ops->ndo_vlan_rx_add_vid(dev, vid); if (err) { kfree(vid_info); @@ -282,8 +281,7 @@ static void __vlan_vid_del(struct vlan_info *vlan_info, unsigned short vid = vid_info->vid; int err; - if ((dev->features & NETIF_F_HW_VLAN_FILTER) && - ops->ndo_vlan_rx_kill_vid) { + if (dev->features & NETIF_F_HW_VLAN_FILTER) { err = ops->ndo_vlan_rx_kill_vid(dev, vid); if (err) { pr_warn("failed to kill vid %d for device %s\n", diff --git a/net/core/dev.c b/net/core/dev.c index a83375d3af7..a87bc74e9fd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6054,6 +6054,14 @@ int register_netdevice(struct net_device *dev) } } + if (((dev->hw_features | dev->features) & NETIF_F_HW_VLAN_FILTER) && + (!dev->netdev_ops->ndo_vlan_rx_add_vid || + !dev->netdev_ops->ndo_vlan_rx_kill_vid)) { + netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n"); + ret = -EINVAL; + goto err_uninit; + } + ret = -EBUSY; if (!dev->ifindex) dev->ifindex = dev_new_index(net); -- cgit v1.2.3-70-g09d2 From c5c351088ae76b46ae08dec1bb7f621e0721c78b Mon Sep 17 00:00:00 2001 From: Gao feng Date: Thu, 31 Jan 2013 16:30:57 +0000 Subject: netns: fdb: allow unprivileged users to add/del fdb entries Right now,only ixgdb,macvlan,vxlan and bridge implement fdb_add/fdb_del operations. these operations only operate the private data of net device. So allowing the unprivileged users who creates the userns and netns to add/del fdb entries will do no harm to other netns. Signed-off-by: Gao feng Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 9a419b09948..c1e4db60eec 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2058,9 +2058,6 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) u8 *addr; int err; - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); if (err < 0) return err; @@ -2127,9 +2124,6 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) int err = -EINVAL; __u8 *addr; - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - if (nlmsg_len(nlh) < sizeof(*ndm)) return -EINVAL; -- cgit v1.2.3-70-g09d2 From 25cc4ae913a46bcc11b03c37bec59568f2122a36 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Sun, 3 Feb 2013 20:32:57 +0000 Subject: net: remove redundant check for timer pending state before del_timer As in del_timer() there has already placed a timer_pending() function to check whether the timer to be deleted is pending or not, it's unnecessary to check timer pending state again before del_timer() is called. Signed-off-by: Ying Xue Cc: Eric Dumazet Signed-off-by: David S. Miller --- net/bluetooth/rfcomm/core.c | 4 ++-- net/bridge/netfilter/ebt_ulog.c | 6 ++---- net/core/sock.c | 2 +- net/ipv4/netfilter/ipt_ULOG.c | 12 ++++-------- net/irda/af_irda.c | 3 +-- net/netfilter/ipvs/ip_vs_conn.c | 3 +-- net/sctp/associola.c | 5 ++--- net/sctp/input.c | 3 +-- net/sctp/outqueue.c | 4 +--- net/sctp/sm_sideeffect.c | 6 ++---- net/sctp/transport.c | 11 ++++------- 11 files changed, 21 insertions(+), 38 deletions(-) (limited to 'net/core') diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 201fdf73720..b23e2713fea 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -257,7 +257,7 @@ static void rfcomm_session_clear_timer(struct rfcomm_session *s) { BT_DBG("session %p state %ld", s, s->state); - if (timer_pending(&s->timer) && del_timer(&s->timer)) + if (del_timer(&s->timer)) rfcomm_session_put(s); } @@ -285,7 +285,7 @@ static void rfcomm_dlc_clear_timer(struct rfcomm_dlc *d) { BT_DBG("dlc %p state %ld", d, d->state); - if (timer_pending(&d->timer) && del_timer(&d->timer)) + if (del_timer(&d->timer)) rfcomm_dlc_put(d); } diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index 3476ec46974..3bf43f7bb9d 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -70,8 +70,7 @@ static void ulog_send(unsigned int nlgroup) { ebt_ulog_buff_t *ub = &ulog_buffers[nlgroup]; - if (timer_pending(&ub->timer)) - del_timer(&ub->timer); + del_timer(&ub->timer); if (!ub->skb) return; @@ -319,8 +318,7 @@ static void __exit ebt_ulog_fini(void) xt_unregister_target(&ebt_ulog_tg_reg); for (i = 0; i < EBT_ULOG_MAXNLGROUPS; i++) { ub = &ulog_buffers[i]; - if (timer_pending(&ub->timer)) - del_timer(&ub->timer); + del_timer(&ub->timer); spin_lock_bh(&ub->lock); if (ub->skb) { kfree_skb(ub->skb); diff --git a/net/core/sock.c b/net/core/sock.c index 235fb89e897..f1e14e20d18 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2230,7 +2230,7 @@ EXPORT_SYMBOL(sk_reset_timer); void sk_stop_timer(struct sock *sk, struct timer_list* timer) { - if (timer_pending(timer) && del_timer(timer)) + if (del_timer(timer)) __sock_put(sk); } EXPORT_SYMBOL(sk_stop_timer); diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index b5ef3cba225..7d168dcbd13 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -88,10 +88,8 @@ static void ulog_send(unsigned int nlgroupnum) { ulog_buff_t *ub = &ulog_buffers[nlgroupnum]; - if (timer_pending(&ub->timer)) { - pr_debug("ulog_send: timer was pending, deleting\n"); - del_timer(&ub->timer); - } + pr_debug("ulog_send: timer is deleting\n"); + del_timer(&ub->timer); if (!ub->skb) { pr_debug("ulog_send: nothing to send\n"); @@ -426,10 +424,8 @@ static void __exit ulog_tg_exit(void) /* remove pending timers and free allocated skb's */ for (i = 0; i < ULOG_MAXNLGROUPS; i++) { ub = &ulog_buffers[i]; - if (timer_pending(&ub->timer)) { - pr_debug("timer was pending, deleting\n"); - del_timer(&ub->timer); - } + pr_debug("timer is deleting\n"); + del_timer(&ub->timer); if (ub->skb) { kfree_skb(ub->skb); diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index b833677d83d..d07e3a62644 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -2567,8 +2567,7 @@ bed: err); /* If watchdog is still activated, kill it! */ - if(timer_pending(&(self->watchdog))) - del_timer(&(self->watchdog)); + del_timer(&(self->watchdog)); IRDA_DEBUG(1, "%s(), ...waking up !\n", __func__); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 30e764ad021..68e368a4bee 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -796,8 +796,7 @@ static void ip_vs_conn_expire(unsigned long data) */ if (likely(atomic_read(&cp->refcnt) == 1)) { /* delete the timer if it is activated by other users */ - if (timer_pending(&cp->timer)) - del_timer(&cp->timer); + del_timer(&cp->timer); /* does anybody control me? */ if (cp->control) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index b45ed1f9692..2f95f5a5145 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -434,8 +434,7 @@ void sctp_association_free(struct sctp_association *asoc) * on our state. */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) { - if (timer_pending(&asoc->timers[i]) && - del_timer(&asoc->timers[i])) + if (del_timer(&asoc->timers[i])) sctp_association_put(asoc); } @@ -1497,7 +1496,7 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) /* Stop the SACK timer. */ timer = &asoc->timers[SCTP_EVENT_TIMEOUT_SACK]; - if (timer_pending(timer) && del_timer(timer)) + if (del_timer(timer)) sctp_association_put(asoc); } } diff --git a/net/sctp/input.c b/net/sctp/input.c index 8bd3c279427..965bbbbe48d 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -468,8 +468,7 @@ void sctp_icmp_proto_unreachable(struct sock *sk, } else { struct net *net = sock_net(sk); - if (timer_pending(&t->proto_unreach_timer) && - del_timer(&t->proto_unreach_timer)) + if (del_timer(&t->proto_unreach_timer)) sctp_association_put(asoc); sctp_do_sm(net, SCTP_EVENT_T_OTHER, diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 9bcdbd02d77..01dca753db1 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -1700,10 +1700,8 @@ static void sctp_check_transmitted(struct sctp_outq *q, * address. */ if (!transport->flight_size) { - if (timer_pending(&transport->T3_rtx_timer) && - del_timer(&transport->T3_rtx_timer)) { + if (del_timer(&transport->T3_rtx_timer)) sctp_transport_put(transport); - } } else if (restart_timer) { if (!mod_timer(&transport->T3_rtx_timer, jiffies + transport->rto)) diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index c9577754a70..8aab894aeab 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -674,10 +674,8 @@ static void sctp_cmd_t3_rtx_timers_stop(sctp_cmd_seq_t *cmds, list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { - if (timer_pending(&t->T3_rtx_timer) && - del_timer(&t->T3_rtx_timer)) { + if (del_timer(&t->T3_rtx_timer)) sctp_transport_put(t); - } } } @@ -1517,7 +1515,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_TIMER_STOP: timer = &asoc->timers[cmd->obj.to]; - if (timer_pending(timer) && del_timer(timer)) + if (del_timer(timer)) sctp_association_put(asoc); break; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index ca5331cc1ed..fafd2a461ba 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -151,13 +151,11 @@ void sctp_transport_free(struct sctp_transport *transport) * structure hang around in memory since we know * the tranport is going away. */ - if (timer_pending(&transport->T3_rtx_timer) && - del_timer(&transport->T3_rtx_timer)) + if (del_timer(&transport->T3_rtx_timer)) sctp_transport_put(transport); /* Delete the ICMP proto unreachable timer if it's active. */ - if (timer_pending(&transport->proto_unreach_timer) && - del_timer(&transport->proto_unreach_timer)) + if (del_timer(&transport->proto_unreach_timer)) sctp_association_put(transport->asoc); sctp_transport_put(transport); @@ -655,10 +653,9 @@ void sctp_transport_reset(struct sctp_transport *t) void sctp_transport_immediate_rtx(struct sctp_transport *t) { /* Stop pending T3_rtx_timer */ - if (timer_pending(&t->T3_rtx_timer)) { - (void)del_timer(&t->T3_rtx_timer); + if (del_timer(&t->T3_rtx_timer)) sctp_transport_put(t); - } + sctp_retransmit(&t->asoc->outqueue, t, SCTP_RTXR_T3_RTX); if (!timer_pending(&t->T3_rtx_timer)) { if (!mod_timer(&t->T3_rtx_timer, jiffies + t->rto)) -- cgit v1.2.3-70-g09d2 From 62b5942aa5182686e6bab2c6db5dbf2672b8981e Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 4 Feb 2013 16:48:16 +0000 Subject: net: core: Remove unnecessary alloc/OOM messages alloc failures already get standardized OOM messages and a dump_stack. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- net/core/dev.c | 14 +++++--------- net/core/netprio_cgroup.c | 4 +--- 2 files changed, 6 insertions(+), 12 deletions(-) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index a87bc74e9fd..e04bfdc9e3e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5958,10 +5958,9 @@ static int netif_alloc_rx_queues(struct net_device *dev) BUG_ON(count < 1); rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL); - if (!rx) { - pr_err("netdev: Unable to allocate %u rx queues\n", count); + if (!rx) return -ENOMEM; - } + dev->_rx = rx; for (i = 0; i < count; i++) @@ -5992,10 +5991,9 @@ static int netif_alloc_netdev_queues(struct net_device *dev) BUG_ON(count < 1); tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL); - if (!tx) { - pr_err("netdev: Unable to allocate %u tx queues\n", count); + if (!tx) return -ENOMEM; - } + dev->_tx = tx; netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); @@ -6482,10 +6480,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, alloc_size += NETDEV_ALIGN - 1; p = kzalloc(alloc_size, GFP_KERNEL); - if (!p) { - pr_err("alloc_netdev: Unable to allocate device\n"); + if (!p) return NULL; - } dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 5e67defe2cb..0777d0aa18c 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -69,10 +69,8 @@ static int extend_netdev_table(struct net_device *dev, u32 target_idx) /* allocate & copy */ new = kzalloc(new_sz, GFP_KERNEL); - if (!new) { - pr_warn("Unable to alloc new priomap!\n"); + if (!new) return -ENOMEM; - } if (old) memcpy(new->priomap, old->priomap, -- cgit v1.2.3-70-g09d2 From ca99ca14c95ae49fb4c9cd3abf5f84d11a7e8a61 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Tue, 5 Feb 2013 08:05:43 +0000 Subject: netpoll: protect napi_poll and poll_controller during dev_[open|close] Ivan Vercera was recently backporting commit 9c13cb8bb477a83b9a3c9e5a5478a4e21294a760 to a RHEL kernel, and I noticed that, while this patch protects the tg3 driver from having its ndo_poll_controller routine called during device initalization, it does nothing for the driver during shutdown. I.e. it would be entirely possible to have the ndo_poll_controller method (or subsequently the ndo_poll) routine called for a driver in the netpoll path on CPU A while in parallel on CPU B, the ndo_close or ndo_open routine could be called. Given that the two latter routines tend to initizlize and free many data structures that the former two rely on, the result can easily be data corruption or various other crashes. Furthermore, it seems that this is potentially a problem with all net drivers that support netpoll, and so this should ideally be fixed in a common path. As Ben H Pointed out to me, we can't preform dev_open/dev_close in atomic context, so I've come up with this solution. We can use a mutex to sleep in open/close paths and just do a mutex_trylock in the napi poll path and abandon the poll attempt if we're locked, as we'll just retry the poll on the next send anyway. I've tested this here by flooding netconsole with messages on a system whos nic driver I modfied to periodically return NETDEV_TX_BUSY, so that the netpoll tx workqueue would be forced to send frames and poll the device. While this was going on I rapidly ifdown/up'ed the interface and watched for any problems. I've not found any. Signed-off-by: Neil Horman CC: Ivan Vecera CC: "David S. Miller" CC: Ben Hutchings CC: Francois Romieu CC: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netpoll.h | 11 ++++++++++- net/core/dev.c | 27 ++++++++++++++++++++++++++- net/core/netpoll.c | 40 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 76 insertions(+), 2 deletions(-) (limited to 'net/core') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index f54c3bb6a22..ab856d507b7 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -38,8 +38,9 @@ struct netpoll { struct netpoll_info { atomic_t refcnt; - int rx_flags; + unsigned long rx_flags; spinlock_t rx_lock; + struct mutex dev_lock; struct list_head rx_np; /* netpolls that registered an rx_hook */ struct sk_buff_head neigh_tx; /* list of neigh requests to reply to */ @@ -51,6 +52,14 @@ struct netpoll_info { struct rcu_head rcu; }; +#ifdef CONFIG_NETPOLL +extern int netpoll_rx_disable(struct net_device *dev); +extern void netpoll_rx_enable(struct net_device *dev); +#else +static inline int netpoll_rx_disable(struct net_device *dev) { return 0; } +static inline void netpoll_rx_enable(struct net_device *dev) { return; } +#endif + void netpoll_send_udp(struct netpoll *np, const char *msg, int len); void netpoll_print_options(struct netpoll *np); int netpoll_parse_options(struct netpoll *np, char *opt); diff --git a/net/core/dev.c b/net/core/dev.c index e04bfdc9e3e..2b275a7b867 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1266,6 +1266,14 @@ static int __dev_open(struct net_device *dev) if (!netif_device_present(dev)) return -ENODEV; + /* Block netpoll from trying to do any rx path servicing. + * If we don't do this there is a chance ndo_poll_controller + * or ndo_poll may be running while we open the device + */ + ret = netpoll_rx_disable(dev); + if (ret) + return ret; + ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev); ret = notifier_to_errno(ret); if (ret) @@ -1279,6 +1287,8 @@ static int __dev_open(struct net_device *dev) if (!ret && ops->ndo_open) ret = ops->ndo_open(dev); + netpoll_rx_enable(dev); + if (ret) clear_bit(__LINK_STATE_START, &dev->state); else { @@ -1370,9 +1380,16 @@ static int __dev_close(struct net_device *dev) int retval; LIST_HEAD(single); + /* Temporarily disable netpoll until the interface is down */ + retval = netpoll_rx_disable(dev); + if (retval) + return retval; + list_add(&dev->unreg_list, &single); retval = __dev_close_many(&single); list_del(&single); + + netpoll_rx_enable(dev); return retval; } @@ -1408,14 +1425,22 @@ static int dev_close_many(struct list_head *head) */ int dev_close(struct net_device *dev) { + int ret = 0; if (dev->flags & IFF_UP) { LIST_HEAD(single); + /* Block netpoll rx while the interface is going down */ + ret = netpoll_rx_disable(dev); + if (ret) + return ret; + list_add(&dev->unreg_list, &single); dev_close_many(&single); list_del(&single); + + netpoll_rx_enable(dev); } - return 0; + return ret; } EXPORT_SYMBOL(dev_close); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 331ccb90f91..edcd9ad9530 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -47,6 +47,8 @@ static struct sk_buff_head skb_pool; static atomic_t trapped; +static struct srcu_struct netpoll_srcu; + #define USEC_PER_POLL 50 #define NETPOLL_RX_ENABLED 1 #define NETPOLL_RX_DROP 2 @@ -199,6 +201,13 @@ static void netpoll_poll_dev(struct net_device *dev) const struct net_device_ops *ops; struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); + /* Don't do any rx activity if the dev_lock mutex is held + * the dev_open/close paths use this to block netpoll activity + * while changing device state + */ + if (!mutex_trylock(&dev->npinfo->dev_lock)) + return; + if (!dev || !netif_running(dev)) return; @@ -211,6 +220,8 @@ static void netpoll_poll_dev(struct net_device *dev) poll_napi(dev); + mutex_unlock(&dev->npinfo->dev_lock); + if (dev->flags & IFF_SLAVE) { if (ni) { struct net_device *bond_dev; @@ -231,6 +242,31 @@ static void netpoll_poll_dev(struct net_device *dev) zap_completion_queue(); } +int netpoll_rx_disable(struct net_device *dev) +{ + struct netpoll_info *ni; + int idx; + might_sleep(); + idx = srcu_read_lock(&netpoll_srcu); + ni = srcu_dereference(dev->npinfo, &netpoll_srcu); + if (ni) + mutex_lock(&ni->dev_lock); + srcu_read_unlock(&netpoll_srcu, idx); + return 0; +} +EXPORT_SYMBOL(netpoll_rx_disable); + +void netpoll_rx_enable(struct net_device *dev) +{ + struct netpoll_info *ni; + rcu_read_lock(); + ni = rcu_dereference(dev->npinfo); + if (ni) + mutex_unlock(&ni->dev_lock); + rcu_read_unlock(); +} +EXPORT_SYMBOL(netpoll_rx_enable); + static void refill_skbs(void) { struct sk_buff *skb; @@ -1004,6 +1040,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) INIT_LIST_HEAD(&npinfo->rx_np); spin_lock_init(&npinfo->rx_lock); + mutex_init(&npinfo->dev_lock); skb_queue_head_init(&npinfo->neigh_tx); skb_queue_head_init(&npinfo->txq); INIT_DELAYED_WORK(&npinfo->tx_work, queue_process); @@ -1169,6 +1206,7 @@ EXPORT_SYMBOL(netpoll_setup); static int __init netpoll_init(void) { skb_queue_head_init(&skb_pool); + init_srcu_struct(&netpoll_srcu); return 0; } core_initcall(netpoll_init); @@ -1208,6 +1246,8 @@ void __netpoll_cleanup(struct netpoll *np) spin_unlock_irqrestore(&npinfo->rx_lock, flags); } + synchronize_srcu(&netpoll_srcu); + if (atomic_dec_and_test(&npinfo->refcnt)) { const struct net_device_ops *ops; -- cgit v1.2.3-70-g09d2 From 12b0004d1d1e2a9aa667412d479041e403bcafae Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 5 Feb 2013 16:36:38 +0000 Subject: net: adjust skb_gso_segment() for calling in rx path skb_gso_segment() is almost always called in tx path, except for openvswitch. It calls this function when it receives the packet and tries to queue it to user-space. In this special case, the ->ip_summed check inside skb_gso_segment() is no longer true, as ->ip_summed value has different meanings on rx path. This patch adjusts skb_gso_segment() so that we can at least avoid such warnings on checksum. Cc: Jesse Gross Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 11 +++++++++-- net/core/dev.c | 21 ++++++++++++++++----- net/openvswitch/datapath.c | 2 +- 3 files changed, 26 insertions(+), 8 deletions(-) (limited to 'net/core') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 85b0949d994..ab2774eb49e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2662,8 +2662,15 @@ extern int netdev_master_upper_dev_link(struct net_device *dev, extern void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); extern int skb_checksum_help(struct sk_buff *skb); -extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, - netdev_features_t features); +extern struct sk_buff *__skb_gso_segment(struct sk_buff *skb, + netdev_features_t features, bool tx_path); + +static inline +struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features) +{ + return __skb_gso_segment(skb, features, true); +} + #ifdef CONFIG_BUG extern void netdev_rx_csum_fault(struct net_device *dev); #else diff --git a/net/core/dev.c b/net/core/dev.c index 2b275a7b867..65da698c500 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2327,18 +2327,29 @@ out: } EXPORT_SYMBOL(skb_checksum_help); +/* openvswitch calls this on rx path, so we need a different check. + */ +static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) +{ + if (tx_path) + return skb->ip_summed != CHECKSUM_PARTIAL; + else + return skb->ip_summed == CHECKSUM_NONE; +} + /** - * skb_gso_segment - Perform segmentation on skb. + * __skb_gso_segment - Perform segmentation on skb. * @skb: buffer to segment * @features: features for the output path (see dev->features) + * @tx_path: whether it is called in TX path * * This function segments the given skb and returns a list of segments. * * It may return NULL if the skb requires no segmentation. This is * only possible when GSO is used for verifying header integrity. */ -struct sk_buff *skb_gso_segment(struct sk_buff *skb, - netdev_features_t features) +struct sk_buff *__skb_gso_segment(struct sk_buff *skb, + netdev_features_t features, bool tx_path) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_offload *ptype; @@ -2361,7 +2372,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, skb->mac_len = skb->network_header - skb->mac_header; __skb_pull(skb, skb->mac_len); - if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { + if (unlikely(skb_needs_check(skb, tx_path))) { skb_warn_bad_offload(skb); if (skb_header_cloned(skb) && @@ -2390,7 +2401,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, return segs; } -EXPORT_SYMBOL(skb_gso_segment); +EXPORT_SYMBOL(__skb_gso_segment); /* Take action when hardware reception checksum errors are detected. */ #ifdef CONFIG_BUG diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index d8c13a96545..9dc537df46c 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -301,7 +301,7 @@ static int queue_gso_packets(struct net *net, int dp_ifindex, struct sk_buff *segs, *nskb; int err; - segs = skb_gso_segment(skb, NETIF_F_SG | NETIF_F_HW_CSUM); + segs = __skb_gso_segment(skb, NETIF_F_SG | NETIF_F_HW_CSUM, false); if (IS_ERR(segs)) return PTR_ERR(segs); -- cgit v1.2.3-70-g09d2 From 6d1ccff627806829c46091bd9d9835302a3fbf5f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Feb 2013 20:22:20 +0000 Subject: net: reset mac header in dev_start_xmit() On 64 bit arches : There is a off-by-one error in qdisc_pkt_len_init() because mac_header is not set in xmit path. skb_mac_header() returns an out of bound value that was harmless because hdr_len is an 'unsigned int' On 32bit arches, the error is abysmal. This patch is also a prereq for "macvlan: add multicast filter" Signed-off-by: Eric Dumazet Cc: Ben Greear Signed-off-by: David S. Miller --- net/core/dev.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index 65da698c500..2f31bf97ba6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2835,6 +2835,8 @@ int dev_queue_xmit(struct sk_buff *skb) struct Qdisc *q; int rc = -ENOMEM; + skb_reset_mac_header(skb); + /* Disable soft irqs for various locks below. Also * stops preemption for RCU. */ -- cgit v1.2.3-70-g09d2 From e5e67305885eb12849b5475764b0542f03dc2b59 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 8 Feb 2013 10:17:15 +0000 Subject: skbuff: Move definition of NETDEV_FRAG_PAGE_MAX_SIZE In order to address the fact that some devices cannot support the full 32K frag size we need to have the value accessible somewhere so that we can use it to do comparisons against what the device can support. As such I am moving the values out of skbuff.c and into skbuff.h. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++++ net/core/skbuff.c | 4 ---- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'net/core') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0259b719beb..d7573c37a51 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1832,6 +1832,10 @@ static inline void __skb_queue_purge(struct sk_buff_head *list) kfree_skb(skb); } +#define NETDEV_FRAG_PAGE_MAX_ORDER get_order(32768) +#define NETDEV_FRAG_PAGE_MAX_SIZE (PAGE_SIZE << NETDEV_FRAG_PAGE_MAX_ORDER) +#define NETDEV_PAGECNT_MAX_BIAS NETDEV_FRAG_PAGE_MAX_SIZE + extern void *netdev_alloc_frag(unsigned int fragsz); extern struct sk_buff *__netdev_alloc_skb(struct net_device *dev, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 55f7ef6ada6..6114c114356 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -351,10 +351,6 @@ struct netdev_alloc_cache { }; static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache); -#define NETDEV_FRAG_PAGE_MAX_ORDER get_order(32768) -#define NETDEV_FRAG_PAGE_MAX_SIZE (PAGE_SIZE << NETDEV_FRAG_PAGE_MAX_ORDER) -#define NETDEV_PAGECNT_MAX_BIAS NETDEV_FRAG_PAGE_MAX_SIZE - static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { struct netdev_alloc_cache *nc; -- cgit v1.2.3-70-g09d2 From f05de73bf82fbbc00265c06d12efb7273f7dc54a Mon Sep 17 00:00:00 2001 From: Jean Sacren Date: Mon, 11 Feb 2013 13:30:38 +0000 Subject: skbuff: create skb_panic() function and its wrappers Create skb_panic() function in lieu of both skb_over_panic() and skb_under_panic() so that code duplication would be avoided. Update type and variable name where necessary. Jiri Pirko suggested using wrappers so that we would be able to keep the fruits of the original code. Signed-off-by: Jean Sacren Cc: Jiri Pirko Signed-off-by: David S. Miller --- net/core/skbuff.c | 48 +++++++++++++++++++----------------------------- 1 file changed, 19 insertions(+), 29 deletions(-) (limited to 'net/core') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6114c114356..8731c39b7a5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -104,47 +104,37 @@ static const struct pipe_buf_operations sock_pipe_buf_ops = { .get = sock_pipe_buf_get, }; -/* - * Keep out-of-line to prevent kernel bloat. - * __builtin_return_address is not used because it is not always - * reliable. - */ - /** - * skb_over_panic - private function - * @skb: buffer - * @sz: size - * @here: address - * - * Out of line support code for skb_put(). Not user callable. + * skb_panic - private function for out-of-line support + * @skb: buffer + * @sz: size + * @addr: address + * @panic: skb_over_panic or skb_under_panic + * + * Out-of-line support for skb_put() and skb_push(). + * Called via the wrapper skb_over_panic() or skb_under_panic(). + * Keep out of line to prevent kernel bloat. + * __builtin_return_address is not used because it is not always reliable. */ -static void skb_over_panic(struct sk_buff *skb, int sz, void *here) +static void skb_panic(struct sk_buff *skb, unsigned int sz, void *addr, + const char panic[]) { pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n", - __func__, here, skb->len, sz, skb->head, skb->data, + panic, addr, skb->len, sz, skb->head, skb->data, (unsigned long)skb->tail, (unsigned long)skb->end, skb->dev ? skb->dev->name : ""); BUG(); } -/** - * skb_under_panic - private function - * @skb: buffer - * @sz: size - * @here: address - * - * Out of line support code for skb_push(). Not user callable. - */ - -static void skb_under_panic(struct sk_buff *skb, int sz, void *here) +static void skb_over_panic(struct sk_buff *skb, unsigned int sz, void *addr) { - pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n", - __func__, here, skb->len, sz, skb->head, skb->data, - (unsigned long)skb->tail, (unsigned long)skb->end, - skb->dev ? skb->dev->name : ""); - BUG(); + skb_panic(skb, sz, addr, __func__); } +static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) +{ + skb_panic(skb, sz, addr, __func__); +} /* * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells -- cgit v1.2.3-70-g09d2 From 2cde6acd49daca58b96f1fbc697492825511ad31 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Mon, 11 Feb 2013 10:25:30 +0000 Subject: netpoll: Fix __netpoll_rcu_free so that it can hold the rtnl lock __netpoll_rcu_free is used to free netpoll structures when the rtnl_lock is already held. The mechanism is used to asynchronously call __netpoll_cleanup outside of the holding of the rtnl_lock, so as to avoid deadlock. Unfortunately, __netpoll_cleanup modifies pointers (dev->np), which means the rtnl_lock must be held while calling it. Further, it cannot be held, because rcu callbacks may be issued in softirq contexts, which cannot sleep. Fix this by converting the rcu callback to a work queue that is guaranteed to get scheduled in process context, so that we can hold the rtnl properly while calling __netpoll_cleanup Tested successfully by myself. Signed-off-by: Neil Horman CC: "David S. Miller" CC: Cong Wang CC: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 2 +- include/linux/netpoll.h | 4 ++-- net/8021q/vlan_dev.c | 2 +- net/bridge/br_device.c | 2 +- net/core/netpoll.c | 16 ++++++++++------ 5 files changed, 15 insertions(+), 11 deletions(-) (limited to 'net/core') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 22399374b1e..94c1534dd57 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1249,7 +1249,7 @@ static inline void slave_disable_netpoll(struct slave *slave) return; slave->np = NULL; - __netpoll_free_rcu(np); + __netpoll_free_async(np); } static inline bool slave_dev_support_netpoll(struct net_device *slave_dev) { diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index ab856d507b7..9d7d8c64f7c 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -32,7 +32,7 @@ struct netpoll { u8 remote_mac[ETH_ALEN]; struct list_head rx; /* rx_np list element */ - struct rcu_head rcu; + struct work_struct cleanup_work; }; struct netpoll_info { @@ -68,7 +68,7 @@ int netpoll_setup(struct netpoll *np); int netpoll_trap(void); void netpoll_set_trap(int trap); void __netpoll_cleanup(struct netpoll *np); -void __netpoll_free_rcu(struct netpoll *np); +void __netpoll_free_async(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo); void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 34df5b3c9b7..19cf81bf9f6 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -733,7 +733,7 @@ static void vlan_dev_netpoll_cleanup(struct net_device *dev) vlan->netpoll = NULL; - __netpoll_free_rcu(netpoll); + __netpoll_free_async(netpoll); } #endif /* CONFIG_NET_POLL_CONTROLLER */ diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index ba6fb2d6094..ca98fa5b2c7 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -265,7 +265,7 @@ void br_netpoll_disable(struct net_bridge_port *p) p->np = NULL; - __netpoll_free_rcu(np); + __netpoll_free_async(np); } #endif diff --git a/net/core/netpoll.c b/net/core/netpoll.c index edcd9ad9530..c536474e226 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -61,6 +61,7 @@ static struct srcu_struct netpoll_srcu; static void zap_completion_queue(void); static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo); +static void netpoll_async_cleanup(struct work_struct *work); static unsigned int carrier_timeout = 4; module_param(carrier_timeout, uint, 0644); @@ -1020,6 +1021,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) np->dev = ndev; strlcpy(np->dev_name, ndev->name, IFNAMSIZ); + INIT_WORK(&np->cleanup_work, netpoll_async_cleanup); if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) || !ndev->netdev_ops->ndo_poll_controller) { @@ -1255,25 +1257,27 @@ void __netpoll_cleanup(struct netpoll *np) if (ops->ndo_netpoll_cleanup) ops->ndo_netpoll_cleanup(np->dev); - RCU_INIT_POINTER(np->dev->npinfo, NULL); + rcu_assign_pointer(np->dev->npinfo, NULL); call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info); } } EXPORT_SYMBOL_GPL(__netpoll_cleanup); -static void rcu_cleanup_netpoll(struct rcu_head *rcu_head) +static void netpoll_async_cleanup(struct work_struct *work) { - struct netpoll *np = container_of(rcu_head, struct netpoll, rcu); + struct netpoll *np = container_of(work, struct netpoll, cleanup_work); + rtnl_lock(); __netpoll_cleanup(np); + rtnl_unlock(); kfree(np); } -void __netpoll_free_rcu(struct netpoll *np) +void __netpoll_free_async(struct netpoll *np) { - call_rcu_bh(&np->rcu, rcu_cleanup_netpoll); + schedule_work(&np->cleanup_work); } -EXPORT_SYMBOL_GPL(__netpoll_free_rcu); +EXPORT_SYMBOL_GPL(__netpoll_free_async); void netpoll_cleanup(struct netpoll *np) { -- cgit v1.2.3-70-g09d2 From 0790bbb68f9d483348c1d65381f3dd92602bfd05 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Mon, 11 Feb 2013 10:25:31 +0000 Subject: netpoll: cleanup sparse warnings With my recent commit I introduced two sparse warnings. Looking closer there were a few more in the same file, so I fixed them all up. Basic rcu pointer dereferencing suff. I've validated these changes using CONFIG_PROVE_RCU while starting and stopping netconsole repeatedly in bonded and non-bonded configurations Signed-off-by: Neil Horman CC: fengguang.wu@intel.com CC: David Miller CC: eric.dumazet@gmail.com Signed-off-by: David S. Miller --- net/core/netpoll.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'net/core') diff --git a/net/core/netpoll.c b/net/core/netpoll.c index c536474e226..bcfd4f4599a 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -206,7 +206,7 @@ static void netpoll_poll_dev(struct net_device *dev) * the dev_open/close paths use this to block netpoll activity * while changing device state */ - if (!mutex_trylock(&dev->npinfo->dev_lock)) + if (!mutex_trylock(&ni->dev_lock)) return; if (!dev || !netif_running(dev)) @@ -221,7 +221,7 @@ static void netpoll_poll_dev(struct net_device *dev) poll_napi(dev); - mutex_unlock(&dev->npinfo->dev_lock); + mutex_unlock(&ni->dev_lock); if (dev->flags & IFF_SLAVE) { if (ni) { @@ -1056,7 +1056,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) goto free_npinfo; } } else { - npinfo = ndev->npinfo; + npinfo = rtnl_dereference(ndev->npinfo); atomic_inc(&npinfo->refcnt); } @@ -1236,7 +1236,11 @@ void __netpoll_cleanup(struct netpoll *np) struct netpoll_info *npinfo; unsigned long flags; - npinfo = np->dev->npinfo; + /* rtnl_dereference would be preferable here but + * rcu_cleanup_netpoll path can put us in here safely without + * holding the rtnl, so plain rcu_dereference it is + */ + npinfo = rtnl_dereference(np->dev->npinfo); if (!npinfo) return; -- cgit v1.2.3-70-g09d2 From 99d5851eefe589346c976a4b539ee498267bc5fd Mon Sep 17 00:00:00 2001 From: James Hogan Date: Wed, 13 Feb 2013 11:20:27 +0000 Subject: net: skbuff: fix compile error in skb_panic() I get the following build error on next-20130213 due to the following commit: commit f05de73bf82fbbc00265c06d12efb7273f7dc54a ("skbuff: create skb_panic() function and its wrappers"). It adds an argument called panic to a function that uses the BUG() macro which tries to call panic, but the argument masks the panic() function declaration, resulting in the following error (gcc 4.2.4): net/core/skbuff.c In function 'skb_panic': net/core/skbuff.c +126 : error: called object 'panic' is not a function This is fixed by renaming the argument to msg. Signed-off-by: James Hogan Cc: Jean Sacren Cc: Jiri Pirko Cc: David S. Miller Signed-off-by: David S. Miller --- net/core/skbuff.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/core') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8731c39b7a5..21a22cce6e5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -109,7 +109,7 @@ static const struct pipe_buf_operations sock_pipe_buf_ops = { * @skb: buffer * @sz: size * @addr: address - * @panic: skb_over_panic or skb_under_panic + * @msg: skb_over_panic or skb_under_panic * * Out-of-line support for skb_put() and skb_push(). * Called via the wrapper skb_over_panic() or skb_under_panic(). @@ -117,10 +117,10 @@ static const struct pipe_buf_operations sock_pipe_buf_ops = { * __builtin_return_address is not used because it is not always reliable. */ static void skb_panic(struct sk_buff *skb, unsigned int sz, void *addr, - const char panic[]) + const char msg[]) { pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n", - panic, addr, skb->len, sz, skb->head, skb->data, + msg, addr, skb->len, sz, skb->head, skb->data, (unsigned long)skb->tail, (unsigned long)skb->end, skb->dev ? skb->dev->name : ""); BUG(); -- cgit v1.2.3-70-g09d2 From 959d5fdee7aa32fa04bc2c37e3d3871ad266fe97 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Wed, 13 Feb 2013 11:32:42 -0500 Subject: netpoll: fix smatch warnings in netpoll core code Dan Carpenter contacted me with some notes regarding some smatch warnings in the netpoll code, some of which I introduced with my recent netpoll locking fixes, some which were there prior. Specifically they were: net-next/net/core/netpoll.c:243 netpoll_poll_dev() warn: inconsistent returns mutex:&ni->dev_lock: locked (213,217) unlocked (210,243) net-next/net/core/netpoll.c:706 netpoll_neigh_reply() warn: potential pointer math issue ('skb_transport_header(send_skb)' is a 128 bit pointer) This patch corrects the locking imbalance (the first error), and adds some parenthesis to correct the second error. Tested by myself. Applies to net-next Signed-off-by: Neil Horman CC: Dan Carpenter CC: "David S. Miller" Signed-off-by: David S. Miller --- net/core/netpoll.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'net/core') diff --git a/net/core/netpoll.c b/net/core/netpoll.c index bcfd4f4599a..fa32899006a 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -209,12 +209,16 @@ static void netpoll_poll_dev(struct net_device *dev) if (!mutex_trylock(&ni->dev_lock)) return; - if (!dev || !netif_running(dev)) + if (!netif_running(dev)) { + mutex_unlock(&ni->dev_lock); return; + } ops = dev->netdev_ops; - if (!ops->ndo_poll_controller) + if (!ops->ndo_poll_controller) { + mutex_unlock(&ni->dev_lock); return; + } /* Process pending work on NIC */ ops->ndo_poll_controller(dev); @@ -703,7 +707,7 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; icmp6h->icmp6_router = 0; icmp6h->icmp6_solicited = 1; - target = (struct in6_addr *)skb_transport_header(send_skb) + sizeof(struct icmp6hdr); + target = (struct in6_addr *)(skb_transport_header(send_skb) + sizeof(struct icmp6hdr)); *target = msg->target; icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size, IPPROTO_ICMPV6, -- cgit v1.2.3-70-g09d2 From c9af6db4c11ccc6c3e7f19bbc15d54023956f97c Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Mon, 11 Feb 2013 09:27:41 +0000 Subject: net: Fix possible wrong checksum generation. Patch cef401de7be8c4e (net: fix possible wrong checksum generation) fixed wrong checksum calculation but it broke TSO by defining new GSO type but not a netdev feature for that type. net_gso_ok() would not allow hardware checksum/segmentation offload of such packets without the feature. Following patch fixes TSO and wrong checksum. This patch uses same logic that Eric Dumazet used. Patch introduces new flag SKBTX_SHARED_FRAG if at least one frag can be modified by the user. but SKBTX_SHARED_FRAG flag is kept in skb shared info tx_flags rather than gso_type. tx_flags is better compared to gso_type since we can have skb with shared frag without gso packet. It does not link SHARED_FRAG to GSO, So there is no need to define netdev feature for this. Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 4 ++-- drivers/net/tun.c | 13 +++++-------- drivers/net/virtio_net.c | 13 +++++-------- include/linux/skbuff.h | 17 +++++++++-------- net/core/skbuff.c | 5 ++--- net/ipv4/af_inet.c | 1 - net/ipv4/ip_output.c | 1 + net/ipv4/tcp.c | 4 +--- net/ipv4/tcp_input.c | 4 ++-- net/ipv4/tcp_output.c | 4 ++-- net/ipv6/ip6_offload.c | 1 - 11 files changed, 29 insertions(+), 38 deletions(-) (limited to 'net/core') diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index b181dfb3d6d..97243011d31 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -543,7 +543,6 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from, skb->data_len += len; skb->len += len; skb->truesize += truesize; - skb_shinfo(skb)->gso_type |= SKB_GSO_SHARED_FRAG; atomic_add(truesize, &skb->sk->sk_wmem_alloc); while (len) { int off = base & ~PAGE_MASK; @@ -599,7 +598,7 @@ static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb, if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { skb_shinfo(skb)->gso_size = vnet_hdr->gso_size; - skb_shinfo(skb)->gso_type |= gso_type; + skb_shinfo(skb)->gso_type = gso_type; /* Header must be checked, and gso_segs computed. */ skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; @@ -743,6 +742,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, if (zerocopy) { skb_shinfo(skb)->destructor_arg = m->msg_control; skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; } if (vlan) macvlan_start_xmit(skb, vlan->dev); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index b1038c0e224..b6f45c5d84d 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1019,7 +1019,6 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from, skb->data_len += len; skb->len += len; skb->truesize += truesize; - skb_shinfo(skb)->gso_type |= SKB_GSO_SHARED_FRAG; atomic_add(truesize, &skb->sk->sk_wmem_alloc); while (len) { int off = base & ~PAGE_MASK; @@ -1165,18 +1164,16 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, } if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) { - unsigned short gso_type = 0; - pr_debug("GSO!\n"); switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: - gso_type = SKB_GSO_TCPV4; + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; break; case VIRTIO_NET_HDR_GSO_TCPV6: - gso_type = SKB_GSO_TCPV6; + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; break; case VIRTIO_NET_HDR_GSO_UDP: - gso_type = SKB_GSO_UDP; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP; break; default: tun->dev->stats.rx_frame_errors++; @@ -1185,10 +1182,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, } if (gso.gso_type & VIRTIO_NET_HDR_GSO_ECN) - gso_type |= SKB_GSO_TCP_ECN; + skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; skb_shinfo(skb)->gso_size = gso.gso_size; - skb_shinfo(skb)->gso_type |= gso_type; if (skb_shinfo(skb)->gso_size == 0) { tun->dev->stats.rx_frame_errors++; kfree_skb(skb); @@ -1204,6 +1200,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, if (zerocopy) { skb_shinfo(skb)->destructor_arg = msg_control; skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; } skb_reset_network_header(skb); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 381a2d8d8a8..192c91c8e79 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -227,7 +227,7 @@ static void set_skb_frag(struct sk_buff *skb, struct page *page, skb->len += size; skb->truesize += PAGE_SIZE; skb_shinfo(skb)->nr_frags++; - skb_shinfo(skb)->gso_type |= SKB_GSO_SHARED_FRAG; + skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; *len -= size; } @@ -387,18 +387,16 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len) ntohs(skb->protocol), skb->len, skb->pkt_type); if (hdr->hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) { - unsigned short gso_type = 0; - pr_debug("GSO!\n"); switch (hdr->hdr.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: - gso_type = SKB_GSO_TCPV4; + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; break; case VIRTIO_NET_HDR_GSO_UDP: - gso_type = SKB_GSO_UDP; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP; break; case VIRTIO_NET_HDR_GSO_TCPV6: - gso_type = SKB_GSO_TCPV6; + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; break; default: net_warn_ratelimited("%s: bad gso type %u.\n", @@ -407,7 +405,7 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len) } if (hdr->hdr.gso_type & VIRTIO_NET_HDR_GSO_ECN) - gso_type |= SKB_GSO_TCP_ECN; + skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; skb_shinfo(skb)->gso_size = hdr->hdr.gso_size; if (skb_shinfo(skb)->gso_size == 0) { @@ -415,7 +413,6 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len) goto frame_err; } - skb_shinfo(skb)->gso_type |= gso_type; /* Header must be checked, and gso_segs computed. */ skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; skb_shinfo(skb)->gso_segs = 0; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d7573c37a51..9da99520ccd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -230,6 +230,13 @@ enum { /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, + + /* This indicates at least one fragment might be overwritten + * (as in vmsplice(), sendfile() ...) + * If we need to compute a TX checksum, we'll need to copy + * all frags to avoid possible bad checksum + */ + SKBTX_SHARED_FRAG = 1 << 5, }; /* @@ -307,13 +314,6 @@ enum { SKB_GSO_TCPV6 = 1 << 4, SKB_GSO_FCOE = 1 << 5, - - /* This indicates at least one fragment might be overwritten - * (as in vmsplice(), sendfile() ...) - * If we need to compute a TX checksum, we'll need to copy - * all frags to avoid possible bad checksum - */ - SKB_GSO_SHARED_FRAG = 1 << 6, }; #if BITS_PER_LONG > 32 @@ -2220,7 +2220,8 @@ static inline int skb_linearize(struct sk_buff *skb) */ static inline bool skb_has_shared_frag(const struct sk_buff *skb) { - return skb_shinfo(skb)->gso_type & SKB_GSO_SHARED_FRAG; + return skb_is_nonlinear(skb) && + skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; } /** diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 21a22cce6e5..6c1ad09f879 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2326,8 +2326,7 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); - skb_shinfo(skb1)->gso_type = skb_shinfo(skb)->gso_type; - + skb_shinfo(skb)->tx_flags = skb_shinfo(skb1)->tx_flags & SKBTX_SHARED_FRAG; if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); else /* Second chunk has no header, nothing to copy. */ @@ -2833,7 +2832,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) skb_copy_from_linear_data_offset(skb, offset, skb_put(nskb, hsize), hsize); - skb_shinfo(nskb)->gso_type = skb_shinfo(skb)->gso_type; + skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; while (pos < offset + len && i < nfrags) { *frag = skb_shinfo(skb)->frags[i]; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 1aec92bf801..e6e5d850633 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1287,7 +1287,6 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_TCP_ECN | - SKB_GSO_SHARED_FRAG | 0))) goto out; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 3e98ed2bff5..5e12dca7b3d 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -598,6 +598,7 @@ slow_path: /* for offloaded checksums cleanup checksum before fragmentation */ if ((skb->ip_summed == CHECKSUM_PARTIAL) && skb_checksum_help(skb)) goto fail; + iph = ip_hdr(skb); left = skb->len - hlen; /* Space per frame */ ptr = hlen; /* Where to start from */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 801b07b796f..1f0bedb8622 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -897,8 +897,7 @@ new_segment: get_page(page); skb_fill_page_desc(skb, i, page, offset, copy); } - - skb_shinfo(skb)->gso_type |= SKB_GSO_SHARED_FRAG; + skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; skb->len += copy; skb->data_len += copy; @@ -3044,7 +3043,6 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, SKB_GSO_DODGY | SKB_GSO_TCP_ECN | SKB_GSO_TCPV6 | - SKB_GSO_SHARED_FRAG | 0) || !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))) goto out; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d9bfaea3432..a759e19496d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1239,13 +1239,13 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, */ if (!skb_shinfo(prev)->gso_size) { skb_shinfo(prev)->gso_size = mss; - skb_shinfo(prev)->gso_type |= sk->sk_gso_type; + skb_shinfo(prev)->gso_type = sk->sk_gso_type; } /* CHECKME: To clear or not to clear? Mimics normal skb currently */ if (skb_shinfo(skb)->gso_segs <= 1) { skb_shinfo(skb)->gso_size = 0; - skb_shinfo(skb)->gso_type &= SKB_GSO_SHARED_FRAG; + skb_shinfo(skb)->gso_type = 0; } /* Difference in this won't matter, both ACKed by the same cumul. ACK */ diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 564bf89d9fd..6182d90e97b 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1133,7 +1133,6 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { - skb_shinfo(skb)->gso_type &= SKB_GSO_SHARED_FRAG; if (skb->len <= mss_now || !sk_can_gso(sk) || skb->ip_summed == CHECKSUM_NONE) { /* Avoid the costly divide in the normal @@ -1141,10 +1140,11 @@ static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb, */ skb_shinfo(skb)->gso_segs = 1; skb_shinfo(skb)->gso_size = 0; + skb_shinfo(skb)->gso_type = 0; } else { skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss_now); skb_shinfo(skb)->gso_size = mss_now; - skb_shinfo(skb)->gso_type |= sk->sk_gso_type; + skb_shinfo(skb)->gso_type = sk->sk_gso_type; } } diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index d141fc32a2e..f26f0da7f09 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -100,7 +100,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, SKB_GSO_DODGY | SKB_GSO_TCP_ECN | SKB_GSO_TCPV6 | - SKB_GSO_SHARED_FRAG | 0))) goto out; -- cgit v1.2.3-70-g09d2 From 407af3299ef1ac7e87ce3fb530e32a009d1a9efd Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 13 Feb 2013 12:00:12 +0000 Subject: bridge: Add netlink interface to configure vlans on bridge ports Add a netlink interface to add and remove vlan configuration on bridge port. The interface uses the RTM_SETLINK message and encodes the vlan configuration inside the IFLA_AF_SPEC. It is possble to include multiple vlans to either add or remove in a single message. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 + include/uapi/linux/if_bridge.h | 9 +++ net/bridge/br_device.c | 1 + net/bridge/br_if.c | 1 + net/bridge/br_netlink.c | 139 +++++++++++++++++++++++++++++++++++------ net/bridge/br_private.h | 1 + net/core/rtnetlink.c | 72 +++++++++++++++++++++ 7 files changed, 207 insertions(+), 18 deletions(-) (limited to 'net/core') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 25bd46f5287..1b90f940100 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1020,6 +1020,8 @@ struct net_device_ops { int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev); + int (*ndo_bridge_dellink)(struct net_device *dev, + struct nlmsghdr *nlh); int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); }; diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 5db297514ae..3ca9817ca7e 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -108,15 +108,24 @@ struct __fdb_entry { * [IFLA_AF_SPEC] = { * [IFLA_BRIDGE_FLAGS] * [IFLA_BRIDGE_MODE] + * [IFLA_BRIDGE_VLAN_INFO] * } */ enum { IFLA_BRIDGE_FLAGS, IFLA_BRIDGE_MODE, + IFLA_BRIDGE_VLAN_INFO, __IFLA_BRIDGE_MAX, }; #define IFLA_BRIDGE_MAX (__IFLA_BRIDGE_MAX - 1) +#define BRIDGE_VLAN_INFO_MASTER (1<<0) /* Operate on Bridge device as well */ + +struct bridge_vlan_info { + u16 flags; + u16 vid; +}; + /* Bridge multicast database attributes * [MDBA_MDB] = { * [MDBA_MDB_ENTRY] = { diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 35a2c2c84f3..091bedf266a 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -316,6 +316,7 @@ static const struct net_device_ops br_netdev_ops = { .ndo_fdb_dump = br_fdb_dump, .ndo_bridge_getlink = br_getlink, .ndo_bridge_setlink = br_setlink, + .ndo_bridge_dellink = br_dellink, }; static void br_dev_free(struct net_device *dev) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index af9d65ab400..335c60cebfd 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "br_private.h" diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 39ca9796f3f..534a9f4587a 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "br_private.h" #include "br_private_stp.h" @@ -119,10 +120,14 @@ nla_put_failure: */ void br_ifinfo_notify(int event, struct net_bridge_port *port) { - struct net *net = dev_net(port->dev); + struct net *net; struct sk_buff *skb; int err = -ENOBUFS; + if (!port) + return; + + net = dev_net(port->dev); br_debug(port->br, "port %u(%s) event %d\n", (unsigned int)port->port_no, port->dev->name, event); @@ -144,6 +149,7 @@ errout: rtnl_set_sk_err(net, RTNLGRP_LINK, err); } + /* * Dump information about all ports, in response to GETLINK */ @@ -162,6 +168,64 @@ out: return err; } +const struct nla_policy ifla_br_policy[IFLA_MAX+1] = { + [IFLA_BRIDGE_FLAGS] = { .type = NLA_U16 }, + [IFLA_BRIDGE_MODE] = { .type = NLA_U16 }, + [IFLA_BRIDGE_VLAN_INFO] = { .type = NLA_BINARY, + .len = sizeof(struct bridge_vlan_info), }, +}; + +static int br_afspec(struct net_bridge *br, + struct net_bridge_port *p, + struct nlattr *af_spec, + int cmd) +{ + struct nlattr *tb[IFLA_BRIDGE_MAX+1]; + int err = 0; + + err = nla_parse_nested(tb, IFLA_BRIDGE_MAX, af_spec, ifla_br_policy); + if (err) + return err; + + if (tb[IFLA_BRIDGE_VLAN_INFO]) { + struct bridge_vlan_info *vinfo; + + vinfo = nla_data(tb[IFLA_BRIDGE_VLAN_INFO]); + + if (vinfo->vid >= VLAN_N_VID) + return -EINVAL; + + switch (cmd) { + case RTM_SETLINK: + if (p) { + err = nbp_vlan_add(p, vinfo->vid); + if (err) + break; + + if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER) + err = br_vlan_add(p->br, vinfo->vid); + } else + err = br_vlan_add(br, vinfo->vid); + + if (err) + break; + + break; + + case RTM_DELLINK: + if (p) { + nbp_vlan_delete(p, vinfo->vid); + if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER) + br_vlan_delete(p->br, vinfo->vid); + } else + br_vlan_delete(br, vinfo->vid); + break; + } + } + + return err; +} + static const struct nla_policy ifla_brport_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, [IFLA_BRPORT_COST] = { .type = NLA_U32 }, @@ -241,6 +305,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh) { struct ifinfomsg *ifm; struct nlattr *protinfo; + struct nlattr *afspec; struct net_bridge_port *p; struct nlattr *tb[IFLA_BRPORT_MAX + 1]; int err; @@ -248,38 +313,76 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh) ifm = nlmsg_data(nlh); protinfo = nlmsg_find_attr(nlh, sizeof(*ifm), IFLA_PROTINFO); - if (!protinfo) + afspec = nlmsg_find_attr(nlh, sizeof(*ifm), IFLA_AF_SPEC); + if (!protinfo && !afspec) return 0; p = br_port_get_rtnl(dev); - if (!p) + /* We want to accept dev as bridge itself if the AF_SPEC + * is set to see if someone is setting vlan info on the brigde + */ + if (!p && ((dev->priv_flags & IFF_EBRIDGE) && !afspec)) return -EINVAL; - if (protinfo->nla_type & NLA_F_NESTED) { - err = nla_parse_nested(tb, IFLA_BRPORT_MAX, - protinfo, ifla_brport_policy); + if (p && protinfo) { + if (protinfo->nla_type & NLA_F_NESTED) { + err = nla_parse_nested(tb, IFLA_BRPORT_MAX, + protinfo, ifla_brport_policy); + if (err) + return err; + + spin_lock_bh(&p->br->lock); + err = br_setport(p, tb); + spin_unlock_bh(&p->br->lock); + } else { + /* Binary compatability with old RSTP */ + if (nla_len(protinfo) < sizeof(u8)) + return -EINVAL; + + spin_lock_bh(&p->br->lock); + err = br_set_port_state(p, nla_get_u8(protinfo)); + spin_unlock_bh(&p->br->lock); + } if (err) - return err; - - spin_lock_bh(&p->br->lock); - err = br_setport(p, tb); - spin_unlock_bh(&p->br->lock); - } else { - /* Binary compatability with old RSTP */ - if (nla_len(protinfo) < sizeof(u8)) - return -EINVAL; + goto out; + } - spin_lock_bh(&p->br->lock); - err = br_set_port_state(p, nla_get_u8(protinfo)); - spin_unlock_bh(&p->br->lock); + if (afspec) { + err = br_afspec((struct net_bridge *)netdev_priv(dev), p, + afspec, RTM_SETLINK); } if (err == 0) br_ifinfo_notify(RTM_NEWLINK, p); +out: return err; } +/* Delete port information */ +int br_dellink(struct net_device *dev, struct nlmsghdr *nlh) +{ + struct ifinfomsg *ifm; + struct nlattr *afspec; + struct net_bridge_port *p; + int err; + + ifm = nlmsg_data(nlh); + + afspec = nlmsg_find_attr(nlh, sizeof(*ifm), IFLA_AF_SPEC); + if (!afspec) + return 0; + + p = br_port_get_rtnl(dev); + /* We want to accept dev as bridge itself as well */ + if (!p && !(dev->priv_flags & IFF_EBRIDGE)) + return -EINVAL; + + err = br_afspec((struct net_bridge *)netdev_priv(dev), p, + afspec, RTM_DELLINK); + + return err; +} static int br_validate(struct nlattr *tb[], struct nlattr *data[]) { if (tb[IFLA_ADDRESS]) { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index f0f24610d11..a42f9d49a64 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -713,6 +713,7 @@ extern int br_netlink_init(void); extern void br_netlink_fini(void); extern void br_ifinfo_notify(int event, struct net_bridge_port *port); extern int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg); +extern int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg); extern int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index c1e4db60eec..2c9ccbfbd93 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2464,6 +2464,77 @@ out: return err; } +static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, + void *arg) +{ + struct net *net = sock_net(skb->sk); + struct ifinfomsg *ifm; + struct net_device *dev; + struct nlattr *br_spec, *attr = NULL; + int rem, err = -EOPNOTSUPP; + u16 oflags, flags = 0; + bool have_flags = false; + + if (nlmsg_len(nlh) < sizeof(*ifm)) + return -EINVAL; + + ifm = nlmsg_data(nlh); + if (ifm->ifi_family != AF_BRIDGE) + return -EPFNOSUPPORT; + + dev = __dev_get_by_index(net, ifm->ifi_index); + if (!dev) { + pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n"); + return -ENODEV; + } + + br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (br_spec) { + nla_for_each_nested(attr, br_spec, rem) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { + have_flags = true; + flags = nla_get_u16(attr); + break; + } + } + } + + oflags = flags; + + if (!flags || (flags & BRIDGE_FLAGS_MASTER)) { + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + + if (!br_dev || !br_dev->netdev_ops->ndo_bridge_dellink) { + err = -EOPNOTSUPP; + goto out; + } + + err = br_dev->netdev_ops->ndo_bridge_dellink(dev, nlh); + if (err) + goto out; + + flags &= ~BRIDGE_FLAGS_MASTER; + } + + if ((flags & BRIDGE_FLAGS_SELF)) { + if (!dev->netdev_ops->ndo_bridge_dellink) + err = -EOPNOTSUPP; + else + err = dev->netdev_ops->ndo_bridge_dellink(dev, nlh); + + if (!err) + flags &= ~BRIDGE_FLAGS_SELF; + } + + if (have_flags) + memcpy(nla_data(attr), &flags, sizeof(flags)); + /* Generate event to notify upper layer of bridge change */ + if (!err) + err = rtnl_bridge_notify(dev, oflags); +out: + return err; +} + /* Protected by RTNL sempahore. */ static struct rtattr **rta_buf; static int rtattr_max; @@ -2647,6 +2718,7 @@ void __init rtnetlink_init(void) rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, NULL); rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, NULL); + rtnl_register(PF_BRIDGE, RTM_DELLINK, rtnl_bridge_dellink, NULL, NULL); rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, NULL); } -- cgit v1.2.3-70-g09d2 From 6cbdceeb1cb12c7d620161925a8c3e81daadb2e4 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 13 Feb 2013 12:00:13 +0000 Subject: bridge: Dump vlan information from a bridge port Using the RTM_GETLINK dump the vlan filter list of a given bridge port. The information depends on setting the filter flag similar to how nic VF info is dumped. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +- include/linux/netdevice.h | 3 +- include/uapi/linux/rtnetlink.h | 1 + net/bridge/br_netlink.c | 94 +++++++++++++++++++++++---- net/bridge/br_private.h | 3 +- net/bridge/br_vlan.c | 2 + net/core/rtnetlink.c | 16 +++-- 7 files changed, 104 insertions(+), 18 deletions(-) (limited to 'net/core') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 6999269b3a4..4e2aa47193c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7079,7 +7079,8 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev, } static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev) + struct net_device *dev, + u32 filter_mask) { struct ixgbe_adapter *adapter = netdev_priv(dev); u16 mode; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1b90f940100..1964ca66df5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1019,7 +1019,8 @@ struct net_device_ops { struct nlmsghdr *nlh); int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev); + struct net_device *dev, + u32 filter_mask); int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh); int (*ndo_change_carrier)(struct net_device *dev, diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 7a5eb196ade..7a2144e1afa 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -630,6 +630,7 @@ struct tcamsg { /* New extended info filters for IFLA_EXT_MASK */ #define RTEXT_FILTER_VF (1 << 0) +#define RTEXT_FILTER_BRVLAN (1 << 1) /* End of information exported to user level */ diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 534a9f4587a..fe1980d5a7e 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -65,15 +65,21 @@ static int br_port_fill_attrs(struct sk_buff *skb, * Create one netlink message for one interface * Contains port and master info as well as carrier and bridge state. */ -static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *port, - u32 pid, u32 seq, int event, unsigned int flags) +static int br_fill_ifinfo(struct sk_buff *skb, + const struct net_bridge_port *port, + u32 pid, u32 seq, int event, unsigned int flags, + u32 filter_mask, const struct net_device *dev) { - const struct net_bridge *br = port->br; - const struct net_device *dev = port->dev; + const struct net_bridge *br; struct ifinfomsg *hdr; struct nlmsghdr *nlh; u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; + if (port) + br = port->br; + else + br = netdev_priv(dev); + br_debug(br, "br_fill_info event %d port %s master %s\n", event, dev->name, br->dev->name); @@ -99,7 +105,7 @@ static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *por nla_put_u32(skb, IFLA_LINK, dev->iflink))) goto nla_put_failure; - if (event == RTM_NEWLINK) { + if (event == RTM_NEWLINK && port) { struct nlattr *nest = nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED); @@ -108,6 +114,40 @@ static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *por nla_nest_end(skb, nest); } + /* Check if the VID information is requested */ + if (filter_mask & RTEXT_FILTER_BRVLAN) { + struct nlattr *af; + const struct net_port_vlans *pv; + struct bridge_vlan_info vinfo; + u16 vid; + + if (port) + pv = nbp_get_vlan_info(port); + else + pv = br_get_vlan_info(br); + + if (!pv || bitmap_empty(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN)) + goto done; + + af = nla_nest_start(skb, IFLA_AF_SPEC); + if (!af) + goto nla_put_failure; + + for (vid = find_first_bit(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN); + vid < BR_VLAN_BITMAP_LEN; + vid = find_next_bit(pv->vlan_bitmap, + BR_VLAN_BITMAP_LEN, vid+1)) { + vinfo.vid = vid; + vinfo.flags = 0; + if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, + sizeof(vinfo), &vinfo)) + goto nla_put_failure; + } + + nla_nest_end(skb, af); + } + +done: return nlmsg_end(skb, nlh); nla_put_failure: @@ -135,7 +175,7 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port) if (skb == NULL) goto errout; - err = br_fill_ifinfo(skb, port, 0, 0, event, 0); + err = br_fill_ifinfo(skb, port, 0, 0, event, 0, 0, port->dev); if (err < 0) { /* -EMSGSIZE implies BUG in br_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -154,16 +194,17 @@ errout: * Dump information about all ports, in response to GETLINK */ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev) + struct net_device *dev, u32 filter_mask) { int err = 0; struct net_bridge_port *port = br_port_get_rcu(dev); - /* not a bridge port */ - if (!port) + /* not a bridge port and */ + if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN)) goto out; - err = br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, NLM_F_MULTI); + err = br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, NLM_F_MULTI, + filter_mask, dev); out: return err; } @@ -395,6 +436,29 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } +static size_t br_get_link_af_size(const struct net_device *dev) +{ + struct net_port_vlans *pv; + + if (br_port_exists(dev)) + pv = nbp_get_vlan_info(br_port_get_rcu(dev)); + else if (dev->priv_flags & IFF_EBRIDGE) + pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev)); + else + return 0; + + if (!pv) + return 0; + + /* Each VLAN is returned in bridge_vlan_info along with flags */ + return pv->num_vlans * nla_total_size(sizeof(struct bridge_vlan_info)); +} + +struct rtnl_af_ops br_af_ops = { + .family = AF_BRIDGE, + .get_link_af_size = br_get_link_af_size, +}; + struct rtnl_link_ops br_link_ops __read_mostly = { .kind = "bridge", .priv_size = sizeof(struct net_bridge), @@ -408,11 +472,18 @@ int __init br_netlink_init(void) int err; br_mdb_init(); - err = rtnl_link_register(&br_link_ops); + err = rtnl_af_register(&br_af_ops); if (err) goto out; + err = rtnl_link_register(&br_link_ops); + if (err) + goto out_af; + return 0; + +out_af: + rtnl_af_unregister(&br_af_ops); out: br_mdb_uninit(); return err; @@ -421,5 +492,6 @@ out: void __exit br_netlink_fini(void) { br_mdb_uninit(); + rtnl_af_unregister(&br_af_ops); rtnl_link_unregister(&br_link_ops); } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index a42f9d49a64..ce2235255c2 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -73,6 +73,7 @@ struct net_port_vlans { } parent; struct rcu_head rcu; unsigned long vlan_bitmap[BR_VLAN_BITMAP_LEN]; + u16 num_vlans; }; struct net_bridge_fdb_entry @@ -715,7 +716,7 @@ extern void br_ifinfo_notify(int event, struct net_bridge_port *port); extern int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg); extern int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg); extern int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev); + struct net_device *dev, u32 filter_mask); #ifdef CONFIG_SYSFS /* br_sysfs_if.c */ diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index d8690bfe63d..f2bf5a197ea 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -28,6 +28,7 @@ static int __vlan_add(struct net_port_vlans *v, u16 vid) } set_bit(vid, v->vlan_bitmap); + v->num_vlans++; return 0; } @@ -44,6 +45,7 @@ static int __vlan_del(struct net_port_vlans *v, u16 vid) } clear_bit(vid, v->vlan_bitmap); + v->num_vlans--; if (bitmap_empty(v->vlan_bitmap, BR_VLAN_BITMAP_LEN)) { if (v->port_idx) rcu_assign_pointer(v->parent.port->vlan_info, NULL); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2c9ccbfbd93..f3a112ec86d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2315,6 +2315,13 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) int idx = 0; u32 portid = NETLINK_CB(cb->skb).portid; u32 seq = cb->nlh->nlmsg_seq; + struct nlattr *extfilt; + u32 filter_mask = 0; + + extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct rtgenmsg), + IFLA_EXT_MASK); + if (extfilt) + filter_mask = nla_get_u32(extfilt); rcu_read_lock(); for_each_netdev_rcu(net, dev) { @@ -2324,14 +2331,15 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { if (idx >= cb->args[0] && br_dev->netdev_ops->ndo_bridge_getlink( - skb, portid, seq, dev) < 0) + skb, portid, seq, dev, filter_mask) < 0) break; idx++; } if (ops->ndo_bridge_getlink) { if (idx >= cb->args[0] && - ops->ndo_bridge_getlink(skb, portid, seq, dev) < 0) + ops->ndo_bridge_getlink(skb, portid, seq, dev, + filter_mask) < 0) break; idx++; } @@ -2372,14 +2380,14 @@ static int rtnl_bridge_notify(struct net_device *dev, u16 flags) if ((!flags || (flags & BRIDGE_FLAGS_MASTER)) && br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { - err = br_dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev); + err = br_dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0); if (err < 0) goto errout; } if ((flags & BRIDGE_FLAGS_SELF) && dev->netdev_ops->ndo_bridge_getlink) { - err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev); + err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0); if (err < 0) goto errout; } -- cgit v1.2.3-70-g09d2 From 1690be63a27b20ae65c792729a44f5970561ffa4 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 13 Feb 2013 12:00:18 +0000 Subject: bridge: Add vlan support to static neighbors When a user adds bridge neighbors, allow him to specify VLAN id. If the VLAN id is not specified, the neighbor will be added for VLANs currently in the ports filter list. If no VLANs are configured on the port, we use vlan 0 and only add 1 entry. Signed-off-by: Vlad Yasevich Acked-by: Jitendra Kalsaria Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 1 + drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 4 +- drivers/net/macvlan.c | 2 +- drivers/net/vxlan.c | 3 +- include/linux/netdevice.h | 4 +- include/uapi/linux/neighbour.h | 1 + net/bridge/br_fdb.c | 148 ++++++++++++++++++++--- net/bridge/br_private.h | 6 +- net/core/rtnetlink.c | 26 ++-- 10 files changed, 162 insertions(+), 35 deletions(-) (limited to 'net/core') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 4e2aa47193c..1c0efcb7920 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7002,7 +7002,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], return err; } -static int ixgbe_ndo_fdb_del(struct ndmsg *ndm, +static int ixgbe_ndo_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr) { diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 937bcc3d321..5088dc5c3d1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1959,6 +1959,7 @@ static int mlx4_en_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], } static int mlx4_en_fdb_del(struct ndmsg *ndm, + struct nlattr *tb[], struct net_device *dev, const unsigned char *addr) { diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index b745194391a..b9531683158 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -247,8 +247,8 @@ static int qlcnic_set_mac(struct net_device *netdev, void *p) return 0; } -static int qlcnic_fdb_del(struct ndmsg *ndm, struct net_device *netdev, - const unsigned char *addr) +static int qlcnic_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *netdev, const unsigned char *addr) { struct qlcnic_adapter *adapter = netdev_priv(netdev); int err = -EOPNOTSUPP; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index e4b8078e88a..defcd8a8574 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -599,7 +599,7 @@ static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], return err; } -static int macvlan_fdb_del(struct ndmsg *ndm, +static int macvlan_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr) { diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 72485b9b900..9d70421cf3a 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -393,7 +393,8 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], } /* Delete entry (via netlink) */ -static int vxlan_fdb_delete(struct ndmsg *ndm, struct net_device *dev, +static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, const unsigned char *addr) { struct vxlan_dev *vxlan = netdev_priv(dev); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1964ca66df5..9deb672d999 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -884,7 +884,8 @@ struct netdev_fcoe_hbainfo { * struct net_device *dev, * const unsigned char *addr, u16 flags) * Adds an FDB entry to dev for addr. - * int (*ndo_fdb_del)(struct ndmsg *ndm, struct net_device *dev, + * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], + * struct net_device *dev, * const unsigned char *addr) * Deletes the FDB entry from dev coresponding to addr. * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, @@ -1008,6 +1009,7 @@ struct net_device_ops { const unsigned char *addr, u16 flags); int (*ndo_fdb_del)(struct ndmsg *ndm, + struct nlattr *tb[], struct net_device *dev, const unsigned char *addr); int (*ndo_fdb_dump)(struct sk_buff *skb, diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 275e5d65dcb..adb068c53c4 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -20,6 +20,7 @@ enum { NDA_LLADDR, NDA_CACHEINFO, NDA_PROBES, + NDA_VLAN, __NDA_MAX }; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 276a5225460..4b75ad43aa8 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -505,6 +505,10 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, ci.ndm_refcnt = 0; if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; + + if (nla_put(skb, NDA_VLAN, sizeof(u16), &fdb->vlan_id)) + goto nla_put_failure; + return nlmsg_end(skb, nlh); nla_put_failure: @@ -516,6 +520,7 @@ static inline size_t fdb_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + + nla_total_size(sizeof(u16)) /* NDA_VLAN */ + nla_total_size(sizeof(struct nda_cacheinfo)); } @@ -617,6 +622,25 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, return 0; } +static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p, + const unsigned char *addr, u16 nlh_flags, u16 vid) +{ + int err = 0; + + if (ndm->ndm_flags & NTF_USE) { + rcu_read_lock(); + br_fdb_update(p->br, p, addr, vid); + rcu_read_unlock(); + } else { + spin_lock_bh(&p->br->hash_lock); + err = fdb_add_entry(p, addr, ndm->ndm_state, + nlh_flags, vid); + spin_unlock_bh(&p->br->hash_lock); + } + + return err; +} + /* Add new permanent fdb entry with RTM_NEWNEIGH */ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, @@ -624,12 +648,29 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], { struct net_bridge_port *p; int err = 0; + struct net_port_vlans *pv; + unsigned short vid = VLAN_N_VID; if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) { pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state); return -EINVAL; } + if (tb[NDA_VLAN]) { + if (nla_len(tb[NDA_VLAN]) != sizeof(unsigned short)) { + pr_info("bridge: RTM_NEWNEIGH with invalid vlan\n"); + return -EINVAL; + } + + vid = nla_get_u16(tb[NDA_VLAN]); + + if (vid >= VLAN_N_VID) { + pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n", + vid); + return -EINVAL; + } + } + p = br_port_get_rtnl(dev); if (p == NULL) { pr_info("bridge: RTM_NEWNEIGH %s not a bridge port\n", @@ -637,41 +678,90 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], return -EINVAL; } - if (ndm->ndm_flags & NTF_USE) { - rcu_read_lock(); - br_fdb_update(p->br, p, addr, 0); - rcu_read_unlock(); + pv = nbp_get_vlan_info(p); + if (vid != VLAN_N_VID) { + if (!pv || !test_bit(vid, pv->vlan_bitmap)) { + pr_info("bridge: RTM_NEWNEIGH with unconfigured " + "vlan %d on port %s\n", vid, dev->name); + return -EINVAL; + } + + /* VID was specified, so use it. */ + err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); } else { - spin_lock_bh(&p->br->hash_lock); - err = fdb_add_entry(p, addr, ndm->ndm_state, nlh_flags, - 0); - spin_unlock_bh(&p->br->hash_lock); + if (!pv || bitmap_empty(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN)) { + err = __br_fdb_add(ndm, p, addr, nlh_flags, 0); + goto out; + } + + /* We have vlans configured on this port and user didn't + * specify a VLAN. To be nice, add/update entry for every + * vlan on this port. + */ + vid = find_first_bit(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN); + while (vid < BR_VLAN_BITMAP_LEN) { + err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); + if (err) + goto out; + vid = find_next_bit(pv->vlan_bitmap, + BR_VLAN_BITMAP_LEN, vid+1); + } } +out: return err; } -static int fdb_delete_by_addr(struct net_bridge_port *p, const u8 *addr) +static int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, + u16 vlan) { - struct net_bridge *br = p->br; - struct hlist_head *head = &br->hash[br_mac_hash(addr, 0)]; + struct hlist_head *head = &br->hash[br_mac_hash(addr, vlan)]; struct net_bridge_fdb_entry *fdb; - fdb = fdb_find(head, addr, 0); + fdb = fdb_find(head, addr, vlan); if (!fdb) return -ENOENT; - fdb_delete(p->br, fdb); + fdb_delete(br, fdb); return 0; } +static int __br_fdb_delete(struct net_bridge_port *p, + const unsigned char *addr, u16 vid) +{ + int err; + + spin_lock_bh(&p->br->hash_lock); + err = fdb_delete_by_addr(p->br, addr, vid); + spin_unlock_bh(&p->br->hash_lock); + + return err; +} + /* Remove neighbor entry with RTM_DELNEIGH */ -int br_fdb_delete(struct ndmsg *ndm, struct net_device *dev, +int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, const unsigned char *addr) { struct net_bridge_port *p; int err; + struct net_port_vlans *pv; + unsigned short vid = VLAN_N_VID; + if (tb[NDA_VLAN]) { + if (nla_len(tb[NDA_VLAN]) != sizeof(unsigned short)) { + pr_info("bridge: RTM_NEWNEIGH with invalid vlan\n"); + return -EINVAL; + } + + vid = nla_get_u16(tb[NDA_VLAN]); + + if (vid >= VLAN_N_VID) { + pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n", + vid); + return -EINVAL; + } + } p = br_port_get_rtnl(dev); if (p == NULL) { pr_info("bridge: RTM_DELNEIGH %s not a bridge port\n", @@ -679,9 +769,33 @@ int br_fdb_delete(struct ndmsg *ndm, struct net_device *dev, return -EINVAL; } - spin_lock_bh(&p->br->hash_lock); - err = fdb_delete_by_addr(p, addr); - spin_unlock_bh(&p->br->hash_lock); + pv = nbp_get_vlan_info(p); + if (vid != VLAN_N_VID) { + if (!pv || !test_bit(vid, pv->vlan_bitmap)) { + pr_info("bridge: RTM_DELNEIGH with unconfigured " + "vlan %d on port %s\n", vid, dev->name); + return -EINVAL; + } + err = __br_fdb_delete(p, addr, vid); + } else { + if (!pv || bitmap_empty(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN)) { + err = __br_fdb_delete(p, addr, 0); + goto out; + } + + /* We have vlans configured on this port and user didn't + * specify a VLAN. To be nice, add/update entry for every + * vlan on this port. + */ + err = -ENOENT; + vid = find_first_bit(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN); + while (vid < BR_VLAN_BITMAP_LEN) { + err &= __br_fdb_delete(p, addr, vid); + vid = find_next_bit(pv->vlan_bitmap, + BR_VLAN_BITMAP_LEN, vid+1); + } + } +out: return err; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 22915c8e996..799dbb37e5a 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -388,7 +388,7 @@ extern void br_fdb_update(struct net_bridge *br, const unsigned char *addr, u16 vid); -extern int br_fdb_delete(struct ndmsg *ndm, +extern int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr); extern int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], @@ -577,13 +577,13 @@ extern void nbp_vlan_flush(struct net_bridge_port *port); static inline struct net_port_vlans *br_get_vlan_info( const struct net_bridge *br) { - return rcu_dereference(br->vlan_info); + return rcu_dereference_rtnl(br->vlan_info); } static inline struct net_port_vlans *nbp_get_vlan_info( const struct net_bridge_port *p) { - return rcu_dereference(p->vlan_info); + return rcu_dereference_rtnl(p->vlan_info); } /* Since bridge now depends on 8021Q module, but the time bridge sees the diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f3a112ec86d..d8aa20f6a46 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2119,13 +2119,17 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); struct ndmsg *ndm; - struct nlattr *llattr; + struct nlattr *tb[NDA_MAX+1]; struct net_device *dev; int err = -EINVAL; __u8 *addr; - if (nlmsg_len(nlh) < sizeof(*ndm)) - return -EINVAL; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); + if (err < 0) + return err; ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex == 0) { @@ -2139,13 +2143,17 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) return -ENODEV; } - llattr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_LLADDR); - if (llattr == NULL || nla_len(llattr) != ETH_ALEN) { - pr_info("PF_BRIGDE: RTM_DELNEIGH with invalid address\n"); + if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) { + pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid address\n"); + return -EINVAL; + } + + addr = nla_data(tb[NDA_LLADDR]); + if (!is_valid_ether_addr(addr)) { + pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ether address\n"); return -EINVAL; } - addr = nla_data(llattr); err = -EOPNOTSUPP; /* Support fdb on master device the net/bridge default case */ @@ -2155,7 +2163,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) const struct net_device_ops *ops = br_dev->netdev_ops; if (ops->ndo_fdb_del) - err = ops->ndo_fdb_del(ndm, dev, addr); + err = ops->ndo_fdb_del(ndm, tb, dev, addr); if (err) goto out; @@ -2165,7 +2173,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) /* Embedded bridge, macvlan, and any other device support */ if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_del) { - err = dev->netdev_ops->ndo_fdb_del(ndm, dev, addr); + err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr); if (!err) { rtnl_fdb_notify(dev, addr, RTM_DELNEIGH); -- cgit v1.2.3-70-g09d2 From 9754e293491e3a4e6c1ac020d25140b1ed3d9cd2 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 14 Feb 2013 15:57:38 -0500 Subject: net: Don't write to current task flags on every packet received. Even for non-pfmalloc SKBs, __netif_receive_skb() will do a tsk_restore_flags() on current unconditionally. Make __netif_receive_skb() a shim around the existing code, renamed to __netif_receive_skb_core(). Let __netif_receive_skb() wrap the __netif_receive_skb_core() call with the task flag modifications, if necessary. Signed-off-by: David S. Miller --- net/core/dev.c | 46 ++++++++++++++++++++++++++++------------------ 1 file changed, 28 insertions(+), 18 deletions(-) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index 2f31bf97ba6..f44473696b8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3457,7 +3457,7 @@ static bool skb_pfmemalloc_protocol(struct sk_buff *skb) } } -static int __netif_receive_skb(struct sk_buff *skb) +static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc) { struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; @@ -3466,24 +3466,11 @@ 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)) goto out; @@ -3517,7 +3504,7 @@ another_round: } #endif - if (sk_memalloc_socks() && skb_pfmemalloc(skb)) + if (pfmemalloc) goto skip_taps; list_for_each_entry_rcu(ptype, &ptype_all, list) { @@ -3536,8 +3523,7 @@ skip_taps: ncls: #endif - if (sk_memalloc_socks() && skb_pfmemalloc(skb) - && !skb_pfmemalloc_protocol(skb)) + if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; if (vlan_tx_tag_present(skb)) { @@ -3607,7 +3593,31 @@ drop: unlock: rcu_read_unlock(); out: - tsk_restore_flags(current, pflags, PF_MEMALLOC); + return ret; +} + +static int __netif_receive_skb(struct sk_buff *skb) +{ + int ret; + + if (sk_memalloc_socks() && skb_pfmemalloc(skb)) { + unsigned long pflags = current->flags; + + /* + * 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. + */ + current->flags |= PF_MEMALLOC; + ret = __netif_receive_skb_core(skb, true); + tsk_restore_flags(current, pflags, PF_MEMALLOC); + } else + ret = __netif_receive_skb_core(skb, false); + return ret; } -- cgit v1.2.3-70-g09d2 From 05e8ef4ab2d8087d360e814d14da20b9f7fb2283 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 14 Feb 2013 09:44:55 +0000 Subject: net: factor out skb_mac_gso_segment() from skb_gso_segment() This function will be used in next GRE_GSO patch. This patch does not change any functionality. It only exports skb_mac_gso_segment() function. [ Use skb_reset_mac_len() -DaveM ] Signed-off-by: Pravin B Shelar Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ net/core/dev.c | 79 ++++++++++++++++++++++++++++------------------- 2 files changed, 50 insertions(+), 31 deletions(-) (limited to 'net/core') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9deb672d999..920361bc27e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2671,6 +2671,8 @@ extern void netdev_upper_dev_unlink(struct net_device *dev, extern int skb_checksum_help(struct sk_buff *skb); extern struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); +extern struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, + netdev_features_t features); static inline struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features) diff --git a/net/core/dev.c b/net/core/dev.c index f44473696b8..67deae60214 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2327,37 +2327,20 @@ out: } EXPORT_SYMBOL(skb_checksum_help); -/* openvswitch calls this on rx path, so we need a different check. - */ -static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) -{ - if (tx_path) - return skb->ip_summed != CHECKSUM_PARTIAL; - else - return skb->ip_summed == CHECKSUM_NONE; -} - /** - * __skb_gso_segment - Perform segmentation on skb. + * skb_mac_gso_segment - mac layer segmentation handler. * @skb: buffer to segment * @features: features for the output path (see dev->features) - * @tx_path: whether it is called in TX path - * - * This function segments the given skb and returns a list of segments. - * - * It may return NULL if the skb requires no segmentation. This is - * only possible when GSO is used for verifying header integrity. */ -struct sk_buff *__skb_gso_segment(struct sk_buff *skb, - netdev_features_t features, bool tx_path) +struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_offload *ptype; __be16 type = skb->protocol; - int vlan_depth = ETH_HLEN; - int err; while (type == htons(ETH_P_8021Q)) { + int vlan_depth = ETH_HLEN; struct vlan_hdr *vh; if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN))) @@ -2368,22 +2351,14 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, vlan_depth += VLAN_HLEN; } - skb_reset_mac_header(skb); - skb->mac_len = skb->network_header - skb->mac_header; __skb_pull(skb, skb->mac_len); - if (unlikely(skb_needs_check(skb, tx_path))) { - skb_warn_bad_offload(skb); - - if (skb_header_cloned(skb) && - (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) - return ERR_PTR(err); - } - rcu_read_lock(); list_for_each_entry_rcu(ptype, &offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { + int err; + err = ptype->callbacks.gso_send_check(skb); segs = ERR_PTR(err); if (err || skb_gso_ok(skb, features)) @@ -2401,6 +2376,48 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, return segs; } +EXPORT_SYMBOL(skb_mac_gso_segment); + + +/* openvswitch calls this on rx path, so we need a different check. + */ +static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) +{ + if (tx_path) + return skb->ip_summed != CHECKSUM_PARTIAL; + else + return skb->ip_summed == CHECKSUM_NONE; +} + +/** + * __skb_gso_segment - Perform segmentation on skb. + * @skb: buffer to segment + * @features: features for the output path (see dev->features) + * @tx_path: whether it is called in TX path + * + * This function segments the given skb and returns a list of segments. + * + * It may return NULL if the skb requires no segmentation. This is + * only possible when GSO is used for verifying header integrity. + */ +struct sk_buff *__skb_gso_segment(struct sk_buff *skb, + netdev_features_t features, bool tx_path) +{ + if (unlikely(skb_needs_check(skb, tx_path))) { + int err; + + skb_warn_bad_offload(skb); + + if (skb_header_cloned(skb) && + (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + return ERR_PTR(err); + } + + skb_reset_mac_header(skb); + skb_reset_mac_len(skb); + + return skb_mac_gso_segment(skb, features); +} EXPORT_SYMBOL(__skb_gso_segment); /* Take action when hardware reception checksum errors are detected. */ -- cgit v1.2.3-70-g09d2 From 68c331631143f5f039baac99a650e0b9e1ea02b6 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 14 Feb 2013 14:02:41 +0000 Subject: v4 GRE: Add TCP segmentation offload for GRE Following patch adds GRE protocol offload handler so that skb_gso_segment() can segment GRE packets. SKB GSO CB is added to keep track of total header length so that skb_segment can push entire header. e.g. in case of GRE, skb_segment need to push inner and outer headers to every segment. New NETIF_F_GRE_GSO feature is added for devices which support HW GRE TSO offload. Currently none of devices support it therefore GRE GSO always fall backs to software GSO. [ Compute pkt_len before ip_local_out() invocation. -DaveM ] Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 3 +- include/linux/skbuff.h | 17 ++++++ net/core/dev.c | 1 + net/core/ethtool.c | 1 + net/core/skbuff.c | 6 +- net/ipv4/af_inet.c | 1 + net/ipv4/gre.c | 118 ++++++++++++++++++++++++++++++++++++++++ net/ipv4/ip_gre.c | 82 +++++++++++++++++++++++++--- net/ipv4/tcp.c | 1 + net/ipv4/udp.c | 3 +- net/ipv6/ip6_offload.c | 1 + net/ipv6/udp_offload.c | 3 +- 12 files changed, 226 insertions(+), 11 deletions(-) (limited to 'net/core') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 5ac32123035..3dd39340430 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -41,7 +41,7 @@ enum { NETIF_F_TSO_ECN_BIT, /* ... TCP ECN support */ NETIF_F_TSO6_BIT, /* ... TCPv6 segmentation */ NETIF_F_FSO_BIT, /* ... FCoE segmentation */ - NETIF_F_GSO_RESERVED1, /* ... free (fill GSO_MASK to 8 bits) */ + NETIF_F_GSO_GRE_BIT, /* ... GRE with TSO */ /**/NETIF_F_GSO_LAST, /* [can't be last bit, see GSO_MASK] */ NETIF_F_GSO_RESERVED2 /* ... free (fill GSO_MASK to 8 bits) */ = NETIF_F_GSO_LAST, @@ -102,6 +102,7 @@ enum { #define NETIF_F_VLAN_CHALLENGED __NETIF_F(VLAN_CHALLENGED) #define NETIF_F_RXFCS __NETIF_F(RXFCS) #define NETIF_F_RXALL __NETIF_F(RXALL) +#define NETIF_F_GRE_GSO __NETIF_F(GSO_GRE) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ca6ee7d93ed..821c7f45d2a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -314,6 +314,8 @@ enum { SKB_GSO_TCPV6 = 1 << 4, SKB_GSO_FCOE = 1 << 5, + + SKB_GSO_GRE = 1 << 6, }; #if BITS_PER_LONG > 32 @@ -2732,6 +2734,21 @@ static inline struct sec_path *skb_sec_path(struct sk_buff *skb) } #endif +/* Keeps track of mac header offset relative to skb->head. + * It is useful for TSO of Tunneling protocol. e.g. GRE. + * For non-tunnel skb it points to skb_mac_header() and for + * tunnel skb it points to outer mac header. */ +struct skb_gso_cb { + int mac_offset; +}; +#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)(skb)->cb) + +static inline int skb_tnl_header_len(const struct sk_buff *inner_skb) +{ + return (skb_mac_header(inner_skb) - inner_skb->head) - + SKB_GSO_CB(inner_skb)->mac_offset; +} + static inline bool skb_is_gso(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_size; diff --git a/net/core/dev.c b/net/core/dev.c index 67deae60214..1cd6297fd34 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2413,6 +2413,7 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, return ERR_PTR(err); } + SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb); skb_reset_mac_header(skb); skb_reset_mac_len(skb); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index d9d55209db6..3e9b2c3e30f 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -77,6 +77,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_TSO_ECN_BIT] = "tx-tcp-ecn-segmentation", [NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation", [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", + [NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation", [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", [NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp", diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6c1ad09f879..2a3ca33c30a 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2738,6 +2738,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) unsigned int mss = skb_shinfo(skb)->gso_size; unsigned int doffset = skb->data - skb_mac_header(skb); unsigned int offset = doffset; + unsigned int tnl_hlen = skb_tnl_header_len(skb); unsigned int headroom; unsigned int len; int sg = !!(features & NETIF_F_SG); @@ -2814,7 +2815,10 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) skb_set_network_header(nskb, skb->mac_len); nskb->transport_header = (nskb->network_header + skb_network_header_len(skb)); - skb_copy_from_linear_data(skb, nskb->data, doffset); + + skb_copy_from_linear_data_offset(skb, -tnl_hlen, + nskb->data - tnl_hlen, + doffset + tnl_hlen); if (fskb != skb_shinfo(skb)->frag_list) continue; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e6e5d850633..e225a4e5b57 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1287,6 +1287,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_TCP_ECN | + SKB_GSO_GRE | 0))) goto out; diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c index 42a491055c7..7a4c710c4cd 100644 --- a/net/ipv4/gre.c +++ b/net/ipv4/gre.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -26,6 +27,11 @@ static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly; static DEFINE_SPINLOCK(gre_proto_lock); +struct gre_base_hdr { + __be16 flags; + __be16 protocol; +}; +#define GRE_HEADER_SECTION 4 int gre_add_protocol(const struct gre_protocol *proto, u8 version) { @@ -112,12 +118,117 @@ static void gre_err(struct sk_buff *skb, u32 info) rcu_read_unlock(); } +static struct sk_buff *gre_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + netdev_features_t enc_features; + int ghl = GRE_HEADER_SECTION; + struct gre_base_hdr *greh; + int mac_len = skb->mac_len; + int tnl_hlen; + bool csum; + + if (unlikely(skb_shinfo(skb)->gso_type & + ~(SKB_GSO_TCPV4 | + SKB_GSO_TCPV6 | + SKB_GSO_UDP | + SKB_GSO_DODGY | + SKB_GSO_TCP_ECN | + SKB_GSO_GRE))) + goto out; + + if (unlikely(!pskb_may_pull(skb, sizeof(*greh)))) + goto out; + + greh = (struct gre_base_hdr *)skb_transport_header(skb); + + if (greh->flags & GRE_KEY) + ghl += GRE_HEADER_SECTION; + if (greh->flags & GRE_SEQ) + ghl += GRE_HEADER_SECTION; + if (greh->flags & GRE_CSUM) { + ghl += GRE_HEADER_SECTION; + csum = true; + } else + csum = false; + + /* setup inner skb. */ + if (greh->protocol == htons(ETH_P_TEB)) { + struct ethhdr *eth = eth_hdr(skb); + skb->protocol = eth->h_proto; + } else { + skb->protocol = greh->protocol; + } + + skb->encapsulation = 0; + + if (unlikely(!pskb_may_pull(skb, ghl))) + goto out; + __skb_pull(skb, ghl); + skb_reset_mac_header(skb); + skb_set_network_header(skb, skb_inner_network_offset(skb)); + skb->mac_len = skb_inner_network_offset(skb); + + /* segment inner packet. */ + enc_features = skb->dev->hw_enc_features & netif_skb_features(skb); + segs = skb_mac_gso_segment(skb, enc_features); + if (!segs || IS_ERR(segs)) + goto out; + + skb = segs; + tnl_hlen = skb_tnl_header_len(skb); + do { + __skb_push(skb, ghl); + if (csum) { + __be32 *pcsum; + + if (skb_has_shared_frag(skb)) { + int err; + + err = __skb_linearize(skb); + if (err) { + kfree_skb(segs); + segs = ERR_PTR(err); + goto out; + } + } + + greh = (struct gre_base_hdr *)(skb->data); + pcsum = (__be32 *)(greh + 1); + *pcsum = 0; + *(__sum16 *)pcsum = csum_fold(skb_checksum(skb, 0, skb->len, 0)); + } + __skb_push(skb, tnl_hlen - ghl); + + skb_reset_mac_header(skb); + skb_set_network_header(skb, mac_len); + skb->mac_len = mac_len; + } while ((skb = skb->next)); +out: + return segs; +} + +static int gre_gso_send_check(struct sk_buff *skb) +{ + if (!skb->encapsulation) + return -EINVAL; + return 0; +} + static const struct net_protocol net_gre_protocol = { .handler = gre_rcv, .err_handler = gre_err, .netns_ok = 1, }; +static const struct net_offload gre_offload = { + .callbacks = { + .gso_send_check = gre_gso_send_check, + .gso_segment = gre_gso_segment, + }, +}; + static int __init gre_init(void) { pr_info("GRE over IPv4 demultiplexor driver\n"); @@ -127,11 +238,18 @@ static int __init gre_init(void) return -EAGAIN; } + if (inet_add_offload(&gre_offload, IPPROTO_GRE)) { + pr_err("can't add protocol offload\n"); + inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); + return -EAGAIN; + } + return 0; } static void __exit gre_exit(void) { + inet_del_offload(&gre_offload, IPPROTO_GRE); inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 00a14b9864e..a56f1182c17 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -735,8 +735,33 @@ drop: return 0; } +static struct sk_buff *handle_offloads(struct sk_buff *skb) +{ + int err; + + if (skb_is_gso(skb)) { + err = skb_unclone(skb, GFP_ATOMIC); + if (unlikely(err)) + goto error; + skb_shinfo(skb)->gso_type |= SKB_GSO_GRE; + return skb; + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + err = skb_checksum_help(skb); + if (unlikely(err)) + goto error; + } + skb->ip_summed = CHECKSUM_NONE; + + return skb; + +error: + kfree_skb(skb); + return ERR_PTR(err); +} + static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { + struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats); struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *old_iph; const struct iphdr *tiph; @@ -751,10 +776,19 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev __be32 dst; int mtu; u8 ttl; + int err; + int pkt_len; - if (skb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_help(skb)) - goto tx_error; + skb = handle_offloads(skb); + if (IS_ERR(skb)) { + dev->stats.tx_dropped++; + return NETDEV_TX_OK; + } + + if (!skb->encapsulation) { + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + } old_iph = ip_hdr(skb); @@ -855,7 +889,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (skb->protocol == htons(ETH_P_IP)) { df |= (old_iph->frag_off&htons(IP_DF)); - if ((old_iph->frag_off&htons(IP_DF)) && + if (!skb_is_gso(skb) && + (old_iph->frag_off&htons(IP_DF)) && mtu < ntohs(old_iph->tot_len)) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); ip_rt_put(rt); @@ -875,7 +910,9 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } } - if (mtu >= IPV6_MIN_MTU && mtu < skb->len - tunnel->hlen + gre_hlen) { + if (!skb_is_gso(skb) && + mtu >= IPV6_MIN_MTU && + mtu < skb->len - tunnel->hlen + gre_hlen) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ip_rt_put(rt); goto tx_error; @@ -936,6 +973,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev iph->daddr = fl4.daddr; iph->saddr = fl4.saddr; iph->ttl = ttl; + iph->id = 0; if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) @@ -964,9 +1002,19 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev *ptr = tunnel->parms.o_key; ptr--; } - if (tunnel->parms.o_flags&GRE_CSUM) { + /* Skip GRE checksum if skb is getting offloaded. */ + if (!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE) && + (tunnel->parms.o_flags&GRE_CSUM)) { int offset = skb_transport_offset(skb); + if (skb_has_shared_frag(skb)) { + err = __skb_linearize(skb); + if (err) { + ip_rt_put(rt); + goto tx_error; + } + } + *ptr = 0; *(__sum16 *)ptr = csum_fold(skb_checksum(skb, offset, skb->len - offset, @@ -974,7 +1022,19 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } } - iptunnel_xmit(skb, dev); + nf_reset(skb); + + pkt_len = skb->len - skb_transport_offset(skb); + err = ip_local_out(skb); + if (likely(net_xmit_eval(err) == 0)) { + u64_stats_update_begin(&tstats->syncp); + tstats->tx_bytes += pkt_len; + tstats->tx_packets++; + u64_stats_update_end(&tstats->syncp); + } else { + dev->stats.tx_errors++; + dev->stats.tx_aborted_errors++; + } return NETDEV_TX_OK; #if IS_ENABLED(CONFIG_IPV6) @@ -1044,6 +1104,11 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev) mtu = 68; tunnel->hlen = addend; + /* TCP offload with GRE SEQ is not supported. */ + if (!(tunnel->parms.o_flags & GRE_SEQ)) { + dev->features |= NETIF_F_GSO_SOFTWARE; + dev->hw_features |= NETIF_F_GSO_SOFTWARE; + } return mtu; } @@ -1593,6 +1658,9 @@ static void ipgre_tap_setup(struct net_device *dev) dev->iflink = 0; dev->features |= NETIF_F_NETNS_LOCAL; + + dev->features |= GRE_FEATURES; + dev->hw_features |= GRE_FEATURES; } static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1f0bedb8622..7a5ba48c2cc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3043,6 +3043,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, SKB_GSO_DODGY | SKB_GSO_TCP_ECN | SKB_GSO_TCPV6 | + SKB_GSO_GRE | 0) || !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))) goto out; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 6791aac06ea..39a5e7a9a77 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2305,7 +2305,8 @@ struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, /* Packet is from an untrusted source, reset gso_segs. */ int type = skb_shinfo(skb)->gso_type; - if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || + if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY | + SKB_GSO_GRE) || !(type & (SKB_GSO_UDP)))) goto out; diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index f26f0da7f09..8234c1dcdf7 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -99,6 +99,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, ~(SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_TCP_ECN | + SKB_GSO_GRE | SKB_GSO_TCPV6 | 0))) goto out; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 0c8934a317c..cf05cf073c5 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -56,7 +56,8 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, /* Packet is from an untrusted source, reset gso_segs. */ int type = skb_shinfo(skb)->gso_type; - if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || + if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY | + SKB_GSO_GRE) || !(type & (SKB_GSO_UDP)))) goto out; -- cgit v1.2.3-70-g09d2 From efd9450e7e36717f24dff3bd584faa80a85231d6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 14 Feb 2013 17:31:48 +0000 Subject: net: use skb_reset_mac_len() in dev_gro_receive() We no longer need to use mac_len, lets cleanup things. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index 1cd6297fd34..6ad37896a32 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3802,7 +3802,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff __be16 type = skb->protocol; struct list_head *head = &offload_base; int same_flow; - int mac_len; enum gro_result ret; if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb)) @@ -3819,8 +3818,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff continue; skb_set_network_header(skb, skb_gro_offset(skb)); - mac_len = skb->network_header - skb->mac_header; - skb->mac_len = mac_len; + skb_reset_mac_len(skb); NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; -- cgit v1.2.3-70-g09d2 From 96b45cbd956ce83908378d87d009b05645353f22 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 15 Feb 2013 22:20:46 +0000 Subject: net: move ioctl functions into a separated file They well deserve a separated unit. Cc: "David S. Miller" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/core/Makefile | 2 +- net/core/dev.c | 573 -------------------------------------------------- net/core/dev_ioctl.c | 576 +++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 577 insertions(+), 574 deletions(-) create mode 100644 net/core/dev_ioctl.c (limited to 'net/core') diff --git a/net/core/Makefile b/net/core/Makefile index 674641b13ae..0c5e3618c80 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -9,7 +9,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ - sock_diag.o + sock_diag.o dev_ioctl.o obj-$(CONFIG_XFRM) += flow.o obj-y += net-sysfs.o diff --git a/net/core/dev.c b/net/core/dev.c index 6ad37896a32..1932d351ed7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -106,7 +106,6 @@ #include #include #include -#include #include #include #include @@ -132,7 +131,6 @@ #include #include #include -#include #include #include "net-sysfs.h" @@ -1226,36 +1224,6 @@ void netdev_notify_peers(struct net_device *dev) } EXPORT_SYMBOL(netdev_notify_peers); -/** - * dev_load - load a network module - * @net: the applicable net namespace - * @name: name of interface - * - * If a network interface is not present and the process has suitable - * privileges this function loads the module. If module loading is not - * available in this kernel then it becomes a nop. - */ - -void dev_load(struct net *net, const char *name) -{ - struct net_device *dev; - int no_module; - - rcu_read_lock(); - dev = dev_get_by_name_rcu(net, name); - rcu_read_unlock(); - - no_module = !dev; - if (no_module && capable(CAP_NET_ADMIN)) - no_module = request_module("netdev-%s", name); - if (no_module && capable(CAP_SYS_MODULE)) { - if (!request_module("%s", name)) - pr_warn("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n", - name); - } -} -EXPORT_SYMBOL(dev_load); - static int __dev_open(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; @@ -1645,57 +1613,6 @@ static inline void net_timestamp_set(struct sk_buff *skb) __net_timestamp(SKB); \ } \ -static int net_hwtstamp_validate(struct ifreq *ifr) -{ - struct hwtstamp_config cfg; - enum hwtstamp_tx_types tx_type; - enum hwtstamp_rx_filters rx_filter; - int tx_type_valid = 0; - int rx_filter_valid = 0; - - if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) - return -EFAULT; - - if (cfg.flags) /* reserved for future extensions */ - return -EINVAL; - - tx_type = cfg.tx_type; - rx_filter = cfg.rx_filter; - - switch (tx_type) { - case HWTSTAMP_TX_OFF: - case HWTSTAMP_TX_ON: - case HWTSTAMP_TX_ONESTEP_SYNC: - tx_type_valid = 1; - break; - } - - switch (rx_filter) { - case HWTSTAMP_FILTER_NONE: - case HWTSTAMP_FILTER_ALL: - case HWTSTAMP_FILTER_SOME: - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - rx_filter_valid = 1; - break; - } - - if (!tx_type_valid || !rx_filter_valid) - return -ERANGE; - - return 0; -} - static inline bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb) { @@ -4300,127 +4217,6 @@ softnet_break: goto out; } -static gifconf_func_t *gifconf_list[NPROTO]; - -/** - * register_gifconf - register a SIOCGIF handler - * @family: Address family - * @gifconf: Function handler - * - * Register protocol dependent address dumping routines. The handler - * that is passed must not be freed or reused until it has been replaced - * by another handler. - */ -int register_gifconf(unsigned int family, gifconf_func_t *gifconf) -{ - if (family >= NPROTO) - return -EINVAL; - gifconf_list[family] = gifconf; - return 0; -} -EXPORT_SYMBOL(register_gifconf); - - -/* - * Map an interface index to its name (SIOCGIFNAME) - */ - -/* - * We need this ioctl for efficient implementation of the - * if_indextoname() function required by the IPv6 API. Without - * it, we would have to search all the interfaces to find a - * match. --pb - */ - -static int dev_ifname(struct net *net, struct ifreq __user *arg) -{ - struct net_device *dev; - struct ifreq ifr; - unsigned seq; - - /* - * Fetch the caller's info block. - */ - - if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) - return -EFAULT; - -retry: - seq = read_seqcount_begin(&devnet_rename_seq); - rcu_read_lock(); - dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex); - if (!dev) { - rcu_read_unlock(); - return -ENODEV; - } - - strcpy(ifr.ifr_name, dev->name); - rcu_read_unlock(); - if (read_seqcount_retry(&devnet_rename_seq, seq)) - goto retry; - - if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) - return -EFAULT; - return 0; -} - -/* - * Perform a SIOCGIFCONF call. This structure will change - * size eventually, and there is nothing I can do about it. - * Thus we will need a 'compatibility mode'. - */ - -static int dev_ifconf(struct net *net, char __user *arg) -{ - struct ifconf ifc; - struct net_device *dev; - char __user *pos; - int len; - int total; - int i; - - /* - * Fetch the caller's info block. - */ - - if (copy_from_user(&ifc, arg, sizeof(struct ifconf))) - return -EFAULT; - - pos = ifc.ifc_buf; - len = ifc.ifc_len; - - /* - * Loop over the interfaces, and write an info block for each. - */ - - total = 0; - for_each_netdev(net, dev) { - for (i = 0; i < NPROTO; i++) { - if (gifconf_list[i]) { - int done; - if (!pos) - done = gifconf_list[i](dev, NULL, 0); - else - done = gifconf_list[i](dev, pos + total, - len - total); - if (done < 0) - return -EFAULT; - total += done; - } - } - } - - /* - * All done. Write the updated control block back to the caller. - */ - ifc.ifc_len = total; - - /* - * Both BSD and Solaris return 0 here, so we do too. - */ - return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0; -} - #ifdef CONFIG_PROC_FS #define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1) @@ -5381,375 +5177,6 @@ int dev_change_carrier(struct net_device *dev, bool new_carrier) } EXPORT_SYMBOL(dev_change_carrier); -/* - * Perform the SIOCxIFxxx calls, inside rcu_read_lock() - */ -static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd) -{ - int err; - struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name); - - if (!dev) - return -ENODEV; - - switch (cmd) { - case SIOCGIFFLAGS: /* Get interface flags */ - ifr->ifr_flags = (short) dev_get_flags(dev); - return 0; - - case SIOCGIFMETRIC: /* Get the metric on the interface - (currently unused) */ - ifr->ifr_metric = 0; - return 0; - - case SIOCGIFMTU: /* Get the MTU of a device */ - ifr->ifr_mtu = dev->mtu; - return 0; - - case SIOCGIFHWADDR: - if (!dev->addr_len) - memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data); - else - memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr, - min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); - ifr->ifr_hwaddr.sa_family = dev->type; - return 0; - - case SIOCGIFSLAVE: - err = -EINVAL; - break; - - case SIOCGIFMAP: - ifr->ifr_map.mem_start = dev->mem_start; - ifr->ifr_map.mem_end = dev->mem_end; - ifr->ifr_map.base_addr = dev->base_addr; - ifr->ifr_map.irq = dev->irq; - ifr->ifr_map.dma = dev->dma; - ifr->ifr_map.port = dev->if_port; - return 0; - - case SIOCGIFINDEX: - ifr->ifr_ifindex = dev->ifindex; - return 0; - - case SIOCGIFTXQLEN: - ifr->ifr_qlen = dev->tx_queue_len; - return 0; - - default: - /* dev_ioctl() should ensure this case - * is never reached - */ - WARN_ON(1); - err = -ENOTTY; - break; - - } - return err; -} - -/* - * Perform the SIOCxIFxxx calls, inside rtnl_lock() - */ -static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) -{ - int err; - struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); - const struct net_device_ops *ops; - - if (!dev) - return -ENODEV; - - ops = dev->netdev_ops; - - switch (cmd) { - case SIOCSIFFLAGS: /* Set interface flags */ - return dev_change_flags(dev, ifr->ifr_flags); - - case SIOCSIFMETRIC: /* Set the metric on the interface - (currently unused) */ - return -EOPNOTSUPP; - - case SIOCSIFMTU: /* Set the MTU of a device */ - return dev_set_mtu(dev, ifr->ifr_mtu); - - case SIOCSIFHWADDR: - return dev_set_mac_address(dev, &ifr->ifr_hwaddr); - - case SIOCSIFHWBROADCAST: - if (ifr->ifr_hwaddr.sa_family != dev->type) - return -EINVAL; - memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, - min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - return 0; - - case SIOCSIFMAP: - if (ops->ndo_set_config) { - if (!netif_device_present(dev)) - return -ENODEV; - return ops->ndo_set_config(dev, &ifr->ifr_map); - } - return -EOPNOTSUPP; - - case SIOCADDMULTI: - if (!ops->ndo_set_rx_mode || - ifr->ifr_hwaddr.sa_family != AF_UNSPEC) - return -EINVAL; - if (!netif_device_present(dev)) - return -ENODEV; - return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data); - - case SIOCDELMULTI: - if (!ops->ndo_set_rx_mode || - ifr->ifr_hwaddr.sa_family != AF_UNSPEC) - return -EINVAL; - if (!netif_device_present(dev)) - return -ENODEV; - return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data); - - case SIOCSIFTXQLEN: - if (ifr->ifr_qlen < 0) - return -EINVAL; - dev->tx_queue_len = ifr->ifr_qlen; - return 0; - - case SIOCSIFNAME: - ifr->ifr_newname[IFNAMSIZ-1] = '\0'; - return dev_change_name(dev, ifr->ifr_newname); - - case SIOCSHWTSTAMP: - err = net_hwtstamp_validate(ifr); - if (err) - return err; - /* fall through */ - - /* - * Unknown or private ioctl - */ - default: - if ((cmd >= SIOCDEVPRIVATE && - cmd <= SIOCDEVPRIVATE + 15) || - cmd == SIOCBONDENSLAVE || - cmd == SIOCBONDRELEASE || - cmd == SIOCBONDSETHWADDR || - cmd == SIOCBONDSLAVEINFOQUERY || - cmd == SIOCBONDINFOQUERY || - cmd == SIOCBONDCHANGEACTIVE || - cmd == SIOCGMIIPHY || - cmd == SIOCGMIIREG || - cmd == SIOCSMIIREG || - cmd == SIOCBRADDIF || - cmd == SIOCBRDELIF || - cmd == SIOCSHWTSTAMP || - cmd == SIOCWANDEV) { - err = -EOPNOTSUPP; - if (ops->ndo_do_ioctl) { - if (netif_device_present(dev)) - err = ops->ndo_do_ioctl(dev, ifr, cmd); - else - err = -ENODEV; - } - } else - err = -EINVAL; - - } - return err; -} - -/* - * This function handles all "interface"-type I/O control requests. The actual - * 'doing' part of this is dev_ifsioc above. - */ - -/** - * dev_ioctl - network device ioctl - * @net: the applicable net namespace - * @cmd: command to issue - * @arg: pointer to a struct ifreq in user space - * - * Issue ioctl functions to devices. This is normally called by the - * user space syscall interfaces but can sometimes be useful for - * other purposes. The return value is the return from the syscall if - * positive or a negative errno code on error. - */ - -int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) -{ - struct ifreq ifr; - int ret; - char *colon; - - /* One special case: SIOCGIFCONF takes ifconf argument - and requires shared lock, because it sleeps writing - to user space. - */ - - if (cmd == SIOCGIFCONF) { - rtnl_lock(); - ret = dev_ifconf(net, (char __user *) arg); - rtnl_unlock(); - return ret; - } - if (cmd == SIOCGIFNAME) - return dev_ifname(net, (struct ifreq __user *)arg); - - if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) - return -EFAULT; - - ifr.ifr_name[IFNAMSIZ-1] = 0; - - colon = strchr(ifr.ifr_name, ':'); - if (colon) - *colon = 0; - - /* - * See which interface the caller is talking about. - */ - - switch (cmd) { - /* - * These ioctl calls: - * - can be done by all. - * - atomic and do not require locking. - * - return a value - */ - case SIOCGIFFLAGS: - case SIOCGIFMETRIC: - case SIOCGIFMTU: - case SIOCGIFHWADDR: - case SIOCGIFSLAVE: - case SIOCGIFMAP: - case SIOCGIFINDEX: - case SIOCGIFTXQLEN: - dev_load(net, ifr.ifr_name); - rcu_read_lock(); - ret = dev_ifsioc_locked(net, &ifr, cmd); - rcu_read_unlock(); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; - - case SIOCETHTOOL: - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ethtool(net, &ifr); - rtnl_unlock(); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; - - /* - * These ioctl calls: - * - require superuser power. - * - require strict serialization. - * - return a value - */ - case SIOCGMIIPHY: - case SIOCGMIIREG: - case SIOCSIFNAME: - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) - return -EPERM; - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(net, &ifr, cmd); - rtnl_unlock(); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; - - /* - * These ioctl calls: - * - require superuser power. - * - require strict serialization. - * - do not return a value - */ - case SIOCSIFMAP: - case SIOCSIFTXQLEN: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - /* fall through */ - /* - * These ioctl calls: - * - require local superuser power. - * - require strict serialization. - * - do not return a value - */ - case SIOCSIFFLAGS: - case SIOCSIFMETRIC: - case SIOCSIFMTU: - case SIOCSIFHWADDR: - case SIOCSIFSLAVE: - case SIOCADDMULTI: - case SIOCDELMULTI: - case SIOCSIFHWBROADCAST: - case SIOCSMIIREG: - case SIOCBONDENSLAVE: - case SIOCBONDRELEASE: - case SIOCBONDSETHWADDR: - case SIOCBONDCHANGEACTIVE: - case SIOCBRADDIF: - case SIOCBRDELIF: - case SIOCSHWTSTAMP: - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) - return -EPERM; - /* fall through */ - case SIOCBONDSLAVEINFOQUERY: - case SIOCBONDINFOQUERY: - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(net, &ifr, cmd); - rtnl_unlock(); - return ret; - - case SIOCGIFMEM: - /* Get the per device memory space. We can add this but - * currently do not support it */ - case SIOCSIFMEM: - /* Set the per device memory buffer space. - * Not applicable in our case */ - case SIOCSIFLINK: - return -ENOTTY; - - /* - * Unknown or private ioctl. - */ - default: - if (cmd == SIOCWANDEV || - (cmd >= SIOCDEVPRIVATE && - cmd <= SIOCDEVPRIVATE + 15)) { - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(net, &ifr, cmd); - rtnl_unlock(); - if (!ret && copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - return ret; - } - /* Take care of Wireless Extensions */ - if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) - return wext_handle_ioctl(net, &ifr, cmd, arg); - return -ENOTTY; - } -} - - /** * dev_new_index - allocate an ifindex * @net: the applicable net namespace diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c new file mode 100644 index 00000000000..6cc0481faad --- /dev/null +++ b/net/core/dev_ioctl.c @@ -0,0 +1,576 @@ +#include +#include +#include +#include +#include +#include +#include + +/* + * Map an interface index to its name (SIOCGIFNAME) + */ + +/* + * We need this ioctl for efficient implementation of the + * if_indextoname() function required by the IPv6 API. Without + * it, we would have to search all the interfaces to find a + * match. --pb + */ + +static int dev_ifname(struct net *net, struct ifreq __user *arg) +{ + struct net_device *dev; + struct ifreq ifr; + unsigned seq; + + /* + * Fetch the caller's info block. + */ + + if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) + return -EFAULT; + +retry: + seq = read_seqcount_begin(&devnet_rename_seq); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; + } + + strcpy(ifr.ifr_name, dev->name); + rcu_read_unlock(); + if (read_seqcount_retry(&devnet_rename_seq, seq)) + goto retry; + + if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) + return -EFAULT; + return 0; +} + +static gifconf_func_t *gifconf_list[NPROTO]; + +/** + * register_gifconf - register a SIOCGIF handler + * @family: Address family + * @gifconf: Function handler + * + * Register protocol dependent address dumping routines. The handler + * that is passed must not be freed or reused until it has been replaced + * by another handler. + */ +int register_gifconf(unsigned int family, gifconf_func_t *gifconf) +{ + if (family >= NPROTO) + return -EINVAL; + gifconf_list[family] = gifconf; + return 0; +} +EXPORT_SYMBOL(register_gifconf); + +/* + * Perform a SIOCGIFCONF call. This structure will change + * size eventually, and there is nothing I can do about it. + * Thus we will need a 'compatibility mode'. + */ + +static int dev_ifconf(struct net *net, char __user *arg) +{ + struct ifconf ifc; + struct net_device *dev; + char __user *pos; + int len; + int total; + int i; + + /* + * Fetch the caller's info block. + */ + + if (copy_from_user(&ifc, arg, sizeof(struct ifconf))) + return -EFAULT; + + pos = ifc.ifc_buf; + len = ifc.ifc_len; + + /* + * Loop over the interfaces, and write an info block for each. + */ + + total = 0; + for_each_netdev(net, dev) { + for (i = 0; i < NPROTO; i++) { + if (gifconf_list[i]) { + int done; + if (!pos) + done = gifconf_list[i](dev, NULL, 0); + else + done = gifconf_list[i](dev, pos + total, + len - total); + if (done < 0) + return -EFAULT; + total += done; + } + } + } + + /* + * All done. Write the updated control block back to the caller. + */ + ifc.ifc_len = total; + + /* + * Both BSD and Solaris return 0 here, so we do too. + */ + return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0; +} + +/* + * Perform the SIOCxIFxxx calls, inside rcu_read_lock() + */ +static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd) +{ + int err; + struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name); + + if (!dev) + return -ENODEV; + + switch (cmd) { + case SIOCGIFFLAGS: /* Get interface flags */ + ifr->ifr_flags = (short) dev_get_flags(dev); + return 0; + + case SIOCGIFMETRIC: /* Get the metric on the interface + (currently unused) */ + ifr->ifr_metric = 0; + return 0; + + case SIOCGIFMTU: /* Get the MTU of a device */ + ifr->ifr_mtu = dev->mtu; + return 0; + + case SIOCGIFHWADDR: + if (!dev->addr_len) + memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data); + else + memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr, + min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); + ifr->ifr_hwaddr.sa_family = dev->type; + return 0; + + case SIOCGIFSLAVE: + err = -EINVAL; + break; + + case SIOCGIFMAP: + ifr->ifr_map.mem_start = dev->mem_start; + ifr->ifr_map.mem_end = dev->mem_end; + ifr->ifr_map.base_addr = dev->base_addr; + ifr->ifr_map.irq = dev->irq; + ifr->ifr_map.dma = dev->dma; + ifr->ifr_map.port = dev->if_port; + return 0; + + case SIOCGIFINDEX: + ifr->ifr_ifindex = dev->ifindex; + return 0; + + case SIOCGIFTXQLEN: + ifr->ifr_qlen = dev->tx_queue_len; + return 0; + + default: + /* dev_ioctl() should ensure this case + * is never reached + */ + WARN_ON(1); + err = -ENOTTY; + break; + + } + return err; +} + +static int net_hwtstamp_validate(struct ifreq *ifr) +{ + struct hwtstamp_config cfg; + enum hwtstamp_tx_types tx_type; + enum hwtstamp_rx_filters rx_filter; + int tx_type_valid = 0; + int rx_filter_valid = 0; + + if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) + return -EFAULT; + + if (cfg.flags) /* reserved for future extensions */ + return -EINVAL; + + tx_type = cfg.tx_type; + rx_filter = cfg.rx_filter; + + switch (tx_type) { + case HWTSTAMP_TX_OFF: + case HWTSTAMP_TX_ON: + case HWTSTAMP_TX_ONESTEP_SYNC: + tx_type_valid = 1; + break; + } + + switch (rx_filter) { + case HWTSTAMP_FILTER_NONE: + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + rx_filter_valid = 1; + break; + } + + if (!tx_type_valid || !rx_filter_valid) + return -ERANGE; + + return 0; +} + +/* + * Perform the SIOCxIFxxx calls, inside rtnl_lock() + */ +static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) +{ + int err; + struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); + const struct net_device_ops *ops; + + if (!dev) + return -ENODEV; + + ops = dev->netdev_ops; + + switch (cmd) { + case SIOCSIFFLAGS: /* Set interface flags */ + return dev_change_flags(dev, ifr->ifr_flags); + + case SIOCSIFMETRIC: /* Set the metric on the interface + (currently unused) */ + return -EOPNOTSUPP; + + case SIOCSIFMTU: /* Set the MTU of a device */ + return dev_set_mtu(dev, ifr->ifr_mtu); + + case SIOCSIFHWADDR: + return dev_set_mac_address(dev, &ifr->ifr_hwaddr); + + case SIOCSIFHWBROADCAST: + if (ifr->ifr_hwaddr.sa_family != dev->type) + return -EINVAL; + memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, + min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + return 0; + + case SIOCSIFMAP: + if (ops->ndo_set_config) { + if (!netif_device_present(dev)) + return -ENODEV; + return ops->ndo_set_config(dev, &ifr->ifr_map); + } + return -EOPNOTSUPP; + + case SIOCADDMULTI: + if (!ops->ndo_set_rx_mode || + ifr->ifr_hwaddr.sa_family != AF_UNSPEC) + return -EINVAL; + if (!netif_device_present(dev)) + return -ENODEV; + return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data); + + case SIOCDELMULTI: + if (!ops->ndo_set_rx_mode || + ifr->ifr_hwaddr.sa_family != AF_UNSPEC) + return -EINVAL; + if (!netif_device_present(dev)) + return -ENODEV; + return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data); + + case SIOCSIFTXQLEN: + if (ifr->ifr_qlen < 0) + return -EINVAL; + dev->tx_queue_len = ifr->ifr_qlen; + return 0; + + case SIOCSIFNAME: + ifr->ifr_newname[IFNAMSIZ-1] = '\0'; + return dev_change_name(dev, ifr->ifr_newname); + + case SIOCSHWTSTAMP: + err = net_hwtstamp_validate(ifr); + if (err) + return err; + /* fall through */ + + /* + * Unknown or private ioctl + */ + default: + if ((cmd >= SIOCDEVPRIVATE && + cmd <= SIOCDEVPRIVATE + 15) || + cmd == SIOCBONDENSLAVE || + cmd == SIOCBONDRELEASE || + cmd == SIOCBONDSETHWADDR || + cmd == SIOCBONDSLAVEINFOQUERY || + cmd == SIOCBONDINFOQUERY || + cmd == SIOCBONDCHANGEACTIVE || + cmd == SIOCGMIIPHY || + cmd == SIOCGMIIREG || + cmd == SIOCSMIIREG || + cmd == SIOCBRADDIF || + cmd == SIOCBRDELIF || + cmd == SIOCSHWTSTAMP || + cmd == SIOCWANDEV) { + err = -EOPNOTSUPP; + if (ops->ndo_do_ioctl) { + if (netif_device_present(dev)) + err = ops->ndo_do_ioctl(dev, ifr, cmd); + else + err = -ENODEV; + } + } else + err = -EINVAL; + + } + return err; +} + +/** + * dev_load - load a network module + * @net: the applicable net namespace + * @name: name of interface + * + * If a network interface is not present and the process has suitable + * privileges this function loads the module. If module loading is not + * available in this kernel then it becomes a nop. + */ + +void dev_load(struct net *net, const char *name) +{ + struct net_device *dev; + int no_module; + + rcu_read_lock(); + dev = dev_get_by_name_rcu(net, name); + rcu_read_unlock(); + + no_module = !dev; + if (no_module && capable(CAP_NET_ADMIN)) + no_module = request_module("netdev-%s", name); + if (no_module && capable(CAP_SYS_MODULE)) { + if (!request_module("%s", name)) + pr_warn("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n", + name); + } +} +EXPORT_SYMBOL(dev_load); + +/* + * This function handles all "interface"-type I/O control requests. The actual + * 'doing' part of this is dev_ifsioc above. + */ + +/** + * dev_ioctl - network device ioctl + * @net: the applicable net namespace + * @cmd: command to issue + * @arg: pointer to a struct ifreq in user space + * + * Issue ioctl functions to devices. This is normally called by the + * user space syscall interfaces but can sometimes be useful for + * other purposes. The return value is the return from the syscall if + * positive or a negative errno code on error. + */ + +int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) +{ + struct ifreq ifr; + int ret; + char *colon; + + /* One special case: SIOCGIFCONF takes ifconf argument + and requires shared lock, because it sleeps writing + to user space. + */ + + if (cmd == SIOCGIFCONF) { + rtnl_lock(); + ret = dev_ifconf(net, (char __user *) arg); + rtnl_unlock(); + return ret; + } + if (cmd == SIOCGIFNAME) + return dev_ifname(net, (struct ifreq __user *)arg); + + if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) + return -EFAULT; + + ifr.ifr_name[IFNAMSIZ-1] = 0; + + colon = strchr(ifr.ifr_name, ':'); + if (colon) + *colon = 0; + + /* + * See which interface the caller is talking about. + */ + + switch (cmd) { + /* + * These ioctl calls: + * - can be done by all. + * - atomic and do not require locking. + * - return a value + */ + case SIOCGIFFLAGS: + case SIOCGIFMETRIC: + case SIOCGIFMTU: + case SIOCGIFHWADDR: + case SIOCGIFSLAVE: + case SIOCGIFMAP: + case SIOCGIFINDEX: + case SIOCGIFTXQLEN: + dev_load(net, ifr.ifr_name); + rcu_read_lock(); + ret = dev_ifsioc_locked(net, &ifr, cmd); + rcu_read_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; + + case SIOCETHTOOL: + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ethtool(net, &ifr); + rtnl_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; + + /* + * These ioctl calls: + * - require superuser power. + * - require strict serialization. + * - return a value + */ + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCSIFNAME: + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; + + /* + * These ioctl calls: + * - require superuser power. + * - require strict serialization. + * - do not return a value + */ + case SIOCSIFMAP: + case SIOCSIFTXQLEN: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + /* fall through */ + /* + * These ioctl calls: + * - require local superuser power. + * - require strict serialization. + * - do not return a value + */ + case SIOCSIFFLAGS: + case SIOCSIFMETRIC: + case SIOCSIFMTU: + case SIOCSIFHWADDR: + case SIOCSIFSLAVE: + case SIOCADDMULTI: + case SIOCDELMULTI: + case SIOCSIFHWBROADCAST: + case SIOCSMIIREG: + case SIOCBONDENSLAVE: + case SIOCBONDRELEASE: + case SIOCBONDSETHWADDR: + case SIOCBONDCHANGEACTIVE: + case SIOCBRADDIF: + case SIOCBRDELIF: + case SIOCSHWTSTAMP: + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + /* fall through */ + case SIOCBONDSLAVEINFOQUERY: + case SIOCBONDINFOQUERY: + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + return ret; + + case SIOCGIFMEM: + /* Get the per device memory space. We can add this but + * currently do not support it */ + case SIOCSIFMEM: + /* Set the per device memory buffer space. + * Not applicable in our case */ + case SIOCSIFLINK: + return -ENOTTY; + + /* + * Unknown or private ioctl. + */ + default: + if (cmd == SIOCWANDEV || + (cmd >= SIOCDEVPRIVATE && + cmd <= SIOCDEVPRIVATE + 15)) { + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + if (!ret && copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + return ret; + } + /* Take care of Wireless Extensions */ + if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) + return wext_handle_ioctl(net, &ifr, cmd, arg); + return -ENOTTY; + } +} -- cgit v1.2.3-70-g09d2 From d4beaa66add8aebf83ab16d2fde4e4de8dac36df Mon Sep 17 00:00:00 2001 From: Gao feng Date: Mon, 18 Feb 2013 01:34:54 +0000 Subject: net: proc: change proc_net_fops_create to proc_create Right now, some modules such as bonding use proc_create to create proc entries under /proc/net/, and other modules such as ipv4 use proc_net_fops_create. It looks a little chaos.this patch changes all of proc_net_fops_create to proc_create. we can remove proc_net_fops_create after this patch. Signed-off-by: Gao feng Signed-off-by: David S. Miller --- drivers/connector/connector.c | 2 +- drivers/net/hamradio/bpqether.c | 3 ++- drivers/net/hamradio/scc.c | 2 +- drivers/net/hamradio/yam.c | 2 +- drivers/net/ppp/pppoe.c | 2 +- net/ax25/af_ax25.c | 7 ++++--- net/bluetooth/af_bluetooth.c | 2 +- net/core/dev.c | 7 ++++--- net/core/dev_addr_lists.c | 2 +- net/core/sock.c | 2 +- net/dccp/probe.c | 2 +- net/decnet/af_decnet.c | 2 +- net/decnet/dn_dev.c | 2 +- net/decnet/dn_neigh.c | 3 ++- net/decnet/dn_route.c | 3 ++- net/ipv4/arp.c | 2 +- net/ipv4/fib_trie.c | 8 ++++---- net/ipv4/igmp.c | 5 +++-- net/ipv4/ipconfig.c | 2 +- net/ipv4/ipmr.c | 4 ++-- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c | 6 +++--- net/ipv4/ping.c | 2 +- net/ipv4/proc.c | 7 ++++--- net/ipv4/raw.c | 2 +- net/ipv4/route.c | 4 ++-- net/ipv4/tcp_probe.c | 2 +- net/ipv6/addrconf.c | 2 +- net/ipv6/anycast.c | 2 +- net/ipv6/ip6_flowlabel.c | 4 ++-- net/ipv6/ip6mr.c | 4 ++-- net/ipv6/mcast.c | 6 +++--- net/ipv6/proc.c | 6 +++--- net/ipv6/raw.c | 2 +- net/ipv6/route.c | 4 ++-- net/key/af_key.c | 2 +- net/l2tp/l2tp_ppp.c | 3 ++- net/netfilter/ipvs/ip_vs_app.c | 2 +- net/netfilter/ipvs/ip_vs_conn.c | 4 ++-- net/netfilter/ipvs/ip_vs_ctl.c | 8 ++++---- net/netfilter/nf_conntrack_expect.c | 3 ++- net/netfilter/nf_conntrack_standalone.c | 2 +- net/netlink/af_netlink.c | 2 +- net/netrom/af_netrom.c | 6 +++--- net/packet/af_packet.c | 2 +- net/phonet/pn_dev.c | 4 ++-- net/rose/af_rose.c | 11 +++++++---- net/rxrpc/af_rxrpc.c | 5 +++-- net/sched/sch_api.c | 2 +- net/sctp/probe.c | 4 ++-- net/unix/af_unix.c | 2 +- net/wireless/wext-proc.c | 3 ++- net/xfrm/xfrm_proc.c | 4 ++-- 52 files changed, 100 insertions(+), 86 deletions(-) (limited to 'net/core') diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index 7b695913cb3..ed17a57ab3c 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -276,7 +276,7 @@ static int cn_init(void) cn_already_initialized = 1; - proc_net_fops_create(&init_net, "connector", S_IRUGO, &cn_file_ops); + proc_create("connector", S_IRUGO, init_net.proc_net, &cn_file_ops); return 0; } diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index c2e5497397d..61f28842163 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -586,7 +586,8 @@ static int bpq_device_event(struct notifier_block *this,unsigned long event, voi static int __init bpq_init_driver(void) { #ifdef CONFIG_PROC_FS - if (!proc_net_fops_create(&init_net, "bpqether", S_IRUGO, &bpq_info_fops)) { + if (!proc_create("bpqether", S_IRUGO, init_net.proc_net, + &bpq_info_fops)) { printk(KERN_ERR "bpq: cannot create /proc/net/bpqether entry.\n"); return -ENOENT; diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c index 1b4a47bd32b..cab13f4d294 100644 --- a/drivers/net/hamradio/scc.c +++ b/drivers/net/hamradio/scc.c @@ -2118,7 +2118,7 @@ static int __init scc_init_driver (void) } rtnl_unlock(); - proc_net_fops_create(&init_net, "z8530drv", 0, &scc_net_seq_fops); + proc_create("z8530drv", 0, init_net.proc_net, &scc_net_seq_fops); return 0; } diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index c6645f1017a..92847d27b2e 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -1167,7 +1167,7 @@ static int __init yam_init_driver(void) yam_timer.expires = jiffies + HZ / 100; add_timer(&yam_timer); - proc_net_fops_create(&init_net, "yam", S_IRUGO, &yam_info_fops); + proc_create("yam", S_IRUGO, init_net.proc_net, &yam_info_fops); return 0; error: while (--i >= 0) { diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 20f31d0d153..d7fa96c42ae 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -1134,7 +1134,7 @@ static __net_init int pppoe_init_net(struct net *net) rwlock_init(&pn->hash_lock); - pde = proc_net_fops_create(net, "pppoe", S_IRUGO, &pppoe_seq_fops); + pde = proc_create("pppoe", S_IRUGO, net->proc_net, &pppoe_seq_fops); #ifdef CONFIG_PROC_FS if (!pde) return -ENOMEM; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 779095ded68..b6ccbea3477 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1992,9 +1992,10 @@ static int __init ax25_init(void) dev_add_pack(&ax25_packet_type); register_netdevice_notifier(&ax25_dev_notifier); - proc_net_fops_create(&init_net, "ax25_route", S_IRUGO, &ax25_route_fops); - proc_net_fops_create(&init_net, "ax25", S_IRUGO, &ax25_info_fops); - proc_net_fops_create(&init_net, "ax25_calls", S_IRUGO, &ax25_uid_fops); + proc_create("ax25_route", S_IRUGO, init_net.proc_net, + &ax25_route_fops); + proc_create("ax25", S_IRUGO, init_net.proc_net, &ax25_info_fops); + proc_create("ax25_calls", S_IRUGO, init_net.proc_net, &ax25_uid_fops); out: return rc; } diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 5355df63d39..8412b637407 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -641,7 +641,7 @@ int bt_procfs_init(struct module* module, struct net *net, const char *name, sk_list->fops.llseek = seq_lseek; sk_list->fops.release = seq_release_private; - pde = proc_net_fops_create(net, name, 0, &sk_list->fops); + pde = proc_create(name, 0, net->proc_net, &sk_list->fops); if (!pde) return -ENOMEM; diff --git a/net/core/dev.c b/net/core/dev.c index 1932d351ed7..f2f81ef5bbd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4518,11 +4518,12 @@ static int __net_init dev_proc_net_init(struct net *net) { int rc = -ENOMEM; - if (!proc_net_fops_create(net, "dev", S_IRUGO, &dev_seq_fops)) + if (!proc_create("dev", S_IRUGO, net->proc_net, &dev_seq_fops)) goto out; - if (!proc_net_fops_create(net, "softnet_stat", S_IRUGO, &softnet_seq_fops)) + if (!proc_create("softnet_stat", S_IRUGO, net->proc_net, + &softnet_seq_fops)) goto out_dev; - if (!proc_net_fops_create(net, "ptype", S_IRUGO, &ptype_seq_fops)) + if (!proc_create("ptype", S_IRUGO, net->proc_net, &ptype_seq_fops)) goto out_softnet; if (wext_proc_init(net)) diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index b079c7bbc15..7c62ec449f3 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -780,7 +780,7 @@ static const struct file_operations dev_mc_seq_fops = { static int __net_init dev_mc_net_init(struct net *net) { - if (!proc_net_fops_create(net, "dev_mcast", 0, &dev_mc_seq_fops)) + if (!proc_create("dev_mcast", 0, net->proc_net, &dev_mc_seq_fops)) return -ENOMEM; return 0; } diff --git a/net/core/sock.c b/net/core/sock.c index f1e14e20d18..b4d562ef36f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2836,7 +2836,7 @@ static const struct file_operations proto_seq_fops = { static __net_init int proto_init_net(struct net *net) { - if (!proc_net_fops_create(net, "protocols", S_IRUGO, &proto_seq_fops)) + if (!proc_create("protocols", S_IRUGO, net->proc_net, &proto_seq_fops)) return -ENOMEM; return 0; diff --git a/net/dccp/probe.c b/net/dccp/probe.c index 0a8d6ebd9b4..d183589b77e 100644 --- a/net/dccp/probe.c +++ b/net/dccp/probe.c @@ -171,7 +171,7 @@ static __init int dccpprobe_init(void) spin_lock_init(&dccpw.lock); if (kfifo_alloc(&dccpw.fifo, bufsize, GFP_KERNEL)) return ret; - if (!proc_net_fops_create(&init_net, procname, S_IRUSR, &dccpprobe_fops)) + if (!proc_create(procname, S_IRUSR, init_net.proc_net, &dccpprobe_fops)) goto err0; ret = setup_jprobe(); diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 64d9843f9e0..f916013d907 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -2384,7 +2384,7 @@ static int __init decnet_init(void) dev_add_pack(&dn_dix_packet_type); register_netdevice_notifier(&dn_dev_notifier); - proc_net_fops_create(&init_net, "decnet", S_IRUGO, &dn_socket_seq_fops); + proc_create("decnet", S_IRUGO, init_net.proc_net, &dn_socket_seq_fops); dn_register_sysctl(); out: return rc; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index e47ba9fc4a0..a04894a2c26 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -1412,7 +1412,7 @@ void __init dn_dev_init(void) rtnl_register(PF_DECnet, RTM_DELADDR, dn_nl_deladdr, NULL, NULL); rtnl_register(PF_DECnet, RTM_GETADDR, NULL, dn_nl_dump_ifaddr, NULL); - proc_net_fops_create(&init_net, "decnet_dev", S_IRUGO, &dn_dev_seq_fops); + proc_create("decnet_dev", S_IRUGO, init_net.proc_net, &dn_dev_seq_fops); #ifdef CONFIG_SYSCTL { diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 856636addd7..f3408f369fe 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -590,7 +590,8 @@ static const struct file_operations dn_neigh_seq_fops = { void __init dn_neigh_init(void) { neigh_table_init(&dn_neigh_table); - proc_net_fops_create(&init_net, "decnet_neigh", S_IRUGO, &dn_neigh_seq_fops); + proc_create("decnet_neigh", S_IRUGO, init_net.proc_net, + &dn_neigh_seq_fops); } void __exit dn_neigh_cleanup(void) diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 1550028fcd8..8afb257f279 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1901,7 +1901,8 @@ void __init dn_route_init(void) dn_dst_ops.gc_thresh = (dn_rt_hash_mask + 1); - proc_net_fops_create(&init_net, "decnet_cache", S_IRUGO, &dn_rt_cache_seq_fops); + proc_create("decnet_cache", S_IRUGO, init_net.proc_net, + &dn_rt_cache_seq_fops); #ifdef CONFIG_DECNET_ROUTER rtnl_register(PF_DECnet, RTM_GETROUTE, dn_cache_getroute, diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index ded146b217f..b04c114ef05 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1405,7 +1405,7 @@ static const struct file_operations arp_seq_fops = { static int __net_init arp_net_init(struct net *net) { - if (!proc_net_fops_create(net, "arp", S_IRUGO, &arp_seq_fops)) + if (!proc_create("arp", S_IRUGO, net->proc_net, &arp_seq_fops)) return -ENOMEM; return 0; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 31d771ca9a7..67c1d4b641d 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2607,14 +2607,14 @@ static const struct file_operations fib_route_fops = { int __net_init fib_proc_init(struct net *net) { - if (!proc_net_fops_create(net, "fib_trie", S_IRUGO, &fib_trie_fops)) + if (!proc_create("fib_trie", S_IRUGO, net->proc_net, &fib_trie_fops)) goto out1; - if (!proc_net_fops_create(net, "fib_triestat", S_IRUGO, - &fib_triestat_fops)) + if (!proc_create("fib_triestat", S_IRUGO, net->proc_net, + &fib_triestat_fops)) goto out2; - if (!proc_net_fops_create(net, "route", S_IRUGO, &fib_route_fops)) + if (!proc_create("route", S_IRUGO, net->proc_net, &fib_route_fops)) goto out3; return 0; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 736ab70fd17..be85628e6a8 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2646,10 +2646,11 @@ static int __net_init igmp_net_init(struct net *net) { struct proc_dir_entry *pde; - pde = proc_net_fops_create(net, "igmp", S_IRUGO, &igmp_mc_seq_fops); + pde = proc_create("igmp", S_IRUGO, net->proc_net, &igmp_mc_seq_fops); if (!pde) goto out_igmp; - pde = proc_net_fops_create(net, "mcfilter", S_IRUGO, &igmp_mcf_seq_fops); + pde = proc_create("mcfilter", S_IRUGO, net->proc_net, + &igmp_mcf_seq_fops); if (!pde) goto out_mcfilter; return 0; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index a2e50ae80b5..98cbc687701 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1394,7 +1394,7 @@ static int __init ip_auto_config(void) unsigned int i; #ifdef CONFIG_PROC_FS - proc_net_fops_create(&init_net, "pnp", S_IRUGO, &pnp_seq_fops); + proc_create("pnp", S_IRUGO, init_net.proc_net, &pnp_seq_fops); #endif /* CONFIG_PROC_FS */ if (!ic_enable) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 7085b9b51e7..160a8b8e9ca 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2703,9 +2703,9 @@ static int __net_init ipmr_net_init(struct net *net) #ifdef CONFIG_PROC_FS err = -ENOMEM; - if (!proc_net_fops_create(net, "ip_mr_vif", 0, &ipmr_vif_fops)) + if (!proc_create("ip_mr_vif", 0, net->proc_net, &ipmr_vif_fops)) goto proc_vif_fail; - if (!proc_net_fops_create(net, "ip_mr_cache", 0, &ipmr_mfc_fops)) + if (!proc_create("ip_mr_cache", 0, net->proc_net, &ipmr_mfc_fops)) goto proc_cache_fail; #endif return 0; diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index 9682b36df38..48bc681f5d3 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -417,12 +417,12 @@ static int __net_init ip_conntrack_net_init(struct net *net) { struct proc_dir_entry *proc, *proc_exp, *proc_stat; - proc = proc_net_fops_create(net, "ip_conntrack", 0440, &ct_file_ops); + proc = proc_create("ip_conntrack", 0440, net->proc_net, &ct_file_ops); if (!proc) goto err1; - proc_exp = proc_net_fops_create(net, "ip_conntrack_expect", 0440, - &ip_exp_file_ops); + proc_exp = proc_create("ip_conntrack_expect", 0440, net->proc_net, + &ip_exp_file_ops); if (!proc_exp) goto err2; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 6f9c07268cf..fc62a13b5ee 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -889,7 +889,7 @@ static int ping_proc_register(struct net *net) struct proc_dir_entry *p; int rc = 0; - p = proc_net_fops_create(net, "icmp", S_IRUGO, &ping_seq_fops); + p = proc_create("icmp", S_IRUGO, net->proc_net, &ping_seq_fops); if (!p) rc = -ENOMEM; return rc; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 8de53e1ddd5..954bcd42d50 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -471,11 +471,12 @@ static const struct file_operations netstat_seq_fops = { static __net_init int ip_proc_init_net(struct net *net) { - if (!proc_net_fops_create(net, "sockstat", S_IRUGO, &sockstat_seq_fops)) + if (!proc_create("sockstat", S_IRUGO, net->proc_net, + &sockstat_seq_fops)) goto out_sockstat; - if (!proc_net_fops_create(net, "netstat", S_IRUGO, &netstat_seq_fops)) + if (!proc_create("netstat", S_IRUGO, net->proc_net, &netstat_seq_fops)) goto out_netstat; - if (!proc_net_fops_create(net, "snmp", S_IRUGO, &snmp_seq_fops)) + if (!proc_create("snmp", S_IRUGO, net->proc_net, &snmp_seq_fops)) goto out_snmp; return 0; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 6f08991409c..5043a7d0c64 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -1050,7 +1050,7 @@ static const struct file_operations raw_seq_fops = { static __net_init int raw_init_net(struct net *net) { - if (!proc_net_fops_create(net, "raw", S_IRUGO, &raw_seq_fops)) + if (!proc_create("raw", S_IRUGO, net->proc_net, &raw_seq_fops)) return -ENOMEM; return 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a0fcc47fee7..3bdd1b1ad1b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -384,8 +384,8 @@ static int __net_init ip_rt_do_proc_init(struct net *net) { struct proc_dir_entry *pde; - pde = proc_net_fops_create(net, "rt_cache", S_IRUGO, - &rt_cache_seq_fops); + pde = proc_create("rt_cache", S_IRUGO, net->proc_net, + &rt_cache_seq_fops); if (!pde) goto err1; diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 4526fe68e60..1e3a1fb3c0c 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -234,7 +234,7 @@ static __init int tcpprobe_init(void) if (!tcp_probe.log) goto err0; - if (!proc_net_fops_create(&init_net, procname, S_IRUSR, &tcpprobe_fops)) + if (!proc_create(procname, S_IRUSR, init_net.proc_net, &tcpprobe_fops)) goto err0; ret = register_jprobe(&tcp_jprobe); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 86c235d05ab..bad71083db8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3325,7 +3325,7 @@ static const struct file_operations if6_fops = { static int __net_init if6_proc_net_init(struct net *net) { - if (!proc_net_fops_create(net, "if_inet6", S_IRUGO, &if6_fops)) + if (!proc_create("if_inet6", S_IRUGO, net->proc_net, &if6_fops)) return -ENOMEM; return 0; } diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 921b8b398a8..5a8c00983de 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -509,7 +509,7 @@ static const struct file_operations ac6_seq_fops = { int __net_init ac6_proc_init(struct net *net) { - if (!proc_net_fops_create(net, "anycast6", S_IRUGO, &ac6_seq_fops)) + if (!proc_create("anycast6", S_IRUGO, net->proc_net, &ac6_seq_fops)) return -ENOMEM; return 0; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index a7da2f47247..900d79eda51 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -806,8 +806,8 @@ static const struct file_operations ip6fl_seq_fops = { static int __net_init ip6_flowlabel_proc_init(struct net *net) { - if (!proc_net_fops_create(net, "ip6_flowlabel", - S_IRUGO, &ip6fl_seq_fops)) + if (!proc_create("ip6_flowlabel", S_IRUGO, net->proc_net, + &ip6fl_seq_fops)) return -ENOMEM; return 0; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 351ce98e90d..fdfd96d288e 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1359,9 +1359,9 @@ static int __net_init ip6mr_net_init(struct net *net) #ifdef CONFIG_PROC_FS err = -ENOMEM; - if (!proc_net_fops_create(net, "ip6_mr_vif", 0, &ip6mr_vif_fops)) + if (!proc_create("ip6_mr_vif", 0, net->proc_net, &ip6mr_vif_fops)) goto proc_vif_fail; - if (!proc_net_fops_create(net, "ip6_mr_cache", 0, &ip6mr_mfc_fops)) + if (!proc_create("ip6_mr_cache", 0, net->proc_net, &ip6mr_mfc_fops)) goto proc_cache_fail; #endif diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 3a2849f660c..de7d4b9a58b 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2599,10 +2599,10 @@ static int __net_init igmp6_proc_init(struct net *net) int err; err = -ENOMEM; - if (!proc_net_fops_create(net, "igmp6", S_IRUGO, &igmp6_mc_seq_fops)) + if (!proc_create("igmp6", S_IRUGO, net->proc_net, &igmp6_mc_seq_fops)) goto out; - if (!proc_net_fops_create(net, "mcfilter6", S_IRUGO, - &igmp6_mcf_seq_fops)) + if (!proc_create("mcfilter6", S_IRUGO, net->proc_net, + &igmp6_mcf_seq_fops)) goto out_proc_net_igmp6; err = 0; diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 745a3204295..cf8901dc653 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -295,11 +295,11 @@ int snmp6_unregister_dev(struct inet6_dev *idev) static int __net_init ipv6_proc_init_net(struct net *net) { - if (!proc_net_fops_create(net, "sockstat6", S_IRUGO, - &sockstat6_seq_fops)) + if (!proc_create("sockstat6", S_IRUGO, net->proc_net, + &sockstat6_seq_fops)) return -ENOMEM; - if (!proc_net_fops_create(net, "snmp6", S_IRUGO, &snmp6_seq_fops)) + if (!proc_create("snmp6", S_IRUGO, net->proc_net, &snmp6_seq_fops)) goto proc_snmp6_fail; net->mib.proc_net_devsnmp6 = proc_mkdir("dev_snmp6", net->proc_net); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 70fa8144999..ff42fb309ee 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1292,7 +1292,7 @@ static const struct file_operations raw6_seq_fops = { static int __net_init raw6_init_net(struct net *net) { - if (!proc_net_fops_create(net, "raw6", S_IRUGO, &raw6_seq_fops)) + if (!proc_create("raw6", S_IRUGO, net->proc_net, &raw6_seq_fops)) return -ENOMEM; return 0; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f3328bc1174..e1228d839eb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2995,8 +2995,8 @@ static void __net_exit ip6_route_net_exit(struct net *net) static int __net_init ip6_route_net_init_late(struct net *net) { #ifdef CONFIG_PROC_FS - proc_net_fops_create(net, "ipv6_route", 0, &ipv6_route_proc_fops); - proc_net_fops_create(net, "rt6_stats", S_IRUGO, &rt6_stats_seq_fops); + proc_create("ipv6_route", 0, net->proc_net, &ipv6_route_proc_fops); + proc_create("rt6_stats", S_IRUGO, net->proc_net, &rt6_stats_seq_fops); #endif return 0; } diff --git a/net/key/af_key.c b/net/key/af_key.c index 7b3ba32ca67..021a429312b 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3740,7 +3740,7 @@ static int __net_init pfkey_init_proc(struct net *net) { struct proc_dir_entry *e; - e = proc_net_fops_create(net, "pfkey", 0, &pfkey_proc_ops); + e = proc_create("pfkey", 0, net->proc_net, &pfkey_proc_ops); if (e == NULL) return -ENOMEM; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 716605c241f..3ca270b4d47 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1783,7 +1783,8 @@ static __net_init int pppol2tp_init_net(struct net *net) struct proc_dir_entry *pde; int err = 0; - pde = proc_net_fops_create(net, "pppol2tp", S_IRUGO, &pppol2tp_proc_fops); + pde = proc_create("pppol2tp", S_IRUGO, net->proc_net, + &pppol2tp_proc_fops); if (!pde) { err = -ENOMEM; goto out; diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 9713e6e86d4..1db8a25fe4b 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -605,7 +605,7 @@ int __net_init ip_vs_app_net_init(struct net *net) struct netns_ipvs *ipvs = net_ipvs(net); INIT_LIST_HEAD(&ipvs->app_list); - proc_net_fops_create(net, "ip_vs_app", 0, &ip_vs_app_fops); + proc_create("ip_vs_app", 0, net->proc_net, &ip_vs_app_fops); return 0; } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 68e368a4bee..91ae11280c2 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1291,8 +1291,8 @@ int __net_init ip_vs_conn_net_init(struct net *net) atomic_set(&ipvs->conn_count, 0); - proc_net_fops_create(net, "ip_vs_conn", 0, &ip_vs_conn_fops); - proc_net_fops_create(net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops); + proc_create("ip_vs_conn", 0, net->proc_net, &ip_vs_conn_fops); + proc_create("ip_vs_conn_sync", 0, net->proc_net, &ip_vs_conn_sync_fops); return 0; } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index ec664cbb119..7d69181f8da 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3800,10 +3800,10 @@ int __net_init ip_vs_control_net_init(struct net *net) spin_lock_init(&ipvs->tot_stats.lock); - proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops); - proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops); - proc_net_fops_create(net, "ip_vs_stats_percpu", 0, - &ip_vs_stats_percpu_fops); + proc_create("ip_vs", 0, net->proc_net, &ip_vs_info_fops); + proc_create("ip_vs_stats", 0, net->proc_net, &ip_vs_stats_fops); + proc_create("ip_vs_stats_percpu", 0, net->proc_net, + &ip_vs_stats_percpu_fops); if (ip_vs_control_net_init_sysctl(net)) goto err; diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index bdd341899ed..4c15f8d0b74 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -571,7 +571,8 @@ static int exp_proc_init(struct net *net) #ifdef CONFIG_NF_CONNTRACK_PROCFS struct proc_dir_entry *proc; - proc = proc_net_fops_create(net, "nf_conntrack_expect", 0440, &exp_file_ops); + proc = proc_create("nf_conntrack_expect", 0440, net->proc_net, + &exp_file_ops); if (!proc) return -ENOMEM; #endif /* CONFIG_NF_CONNTRACK_PROCFS */ diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 7936bf7f90b..bee9aecc7ba 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -366,7 +366,7 @@ static int nf_conntrack_standalone_init_proc(struct net *net) { struct proc_dir_entry *pde; - pde = proc_net_fops_create(net, "nf_conntrack", 0440, &ct_file_ops); + pde = proc_create("nf_conntrack", 0440, net->proc_net, &ct_file_ops); if (!pde) goto out_nf_conntrack; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 74827e3b26a..50084c40a12 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2145,7 +2145,7 @@ static const struct net_proto_family netlink_family_ops = { static int __net_init netlink_net_init(struct net *net) { #ifdef CONFIG_PROC_FS - if (!proc_net_fops_create(net, "netlink", 0, &netlink_seq_fops)) + if (!proc_create("netlink", 0, net->proc_net, &netlink_seq_fops)) return -ENOMEM; #endif return 0; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 7261eb81974..71b86133840 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1452,9 +1452,9 @@ static int __init nr_proto_init(void) nr_loopback_init(); - proc_net_fops_create(&init_net, "nr", S_IRUGO, &nr_info_fops); - proc_net_fops_create(&init_net, "nr_neigh", S_IRUGO, &nr_neigh_fops); - proc_net_fops_create(&init_net, "nr_nodes", S_IRUGO, &nr_nodes_fops); + proc_create("nr", S_IRUGO, init_net.proc_net, &nr_info_fops); + proc_create("nr_neigh", S_IRUGO, init_net.proc_net, &nr_neigh_fops); + proc_create("nr_nodes", S_IRUGO, init_net.proc_net, &nr_nodes_fops); out: return rc; fail: diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c111bd0e083..b7b2d56126c 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3828,7 +3828,7 @@ static int __net_init packet_net_init(struct net *net) mutex_init(&net->packet.sklist_lock); INIT_HLIST_HEAD(&net->packet.sklist); - if (!proc_net_fops_create(net, "packet", 0, &packet_seq_fops)) + if (!proc_create("packet", 0, net->proc_net, &packet_seq_fops)) return -ENOMEM; return 0; diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 5bf6341e2dd..0e527c9dd04 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -320,7 +320,7 @@ static int __net_init phonet_init_net(struct net *net) { struct phonet_net *pnn = phonet_pernet(net); - if (!proc_net_fops_create(net, "phonet", 0, &pn_sock_seq_fops)) + if (!proc_create("phonet", 0, net->proc_net, &pn_sock_seq_fops)) return -ENOMEM; INIT_LIST_HEAD(&pnn->pndevs.list); @@ -348,7 +348,7 @@ int __init phonet_device_init(void) if (err) return err; - proc_net_fops_create(&init_net, "pnresource", 0, &pn_res_seq_fops); + proc_create("pnresource", 0, init_net.proc_net, &pn_res_seq_fops); register_netdevice_notifier(&phonet_device_notifier); err = phonet_netlink_register(); if (err) diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index c4719ce604c..5fd8aacbb5a 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1575,10 +1575,13 @@ static int __init rose_proto_init(void) rose_add_loopback_neigh(); - proc_net_fops_create(&init_net, "rose", S_IRUGO, &rose_info_fops); - proc_net_fops_create(&init_net, "rose_neigh", S_IRUGO, &rose_neigh_fops); - proc_net_fops_create(&init_net, "rose_nodes", S_IRUGO, &rose_nodes_fops); - proc_net_fops_create(&init_net, "rose_routes", S_IRUGO, &rose_routes_fops); + proc_create("rose", S_IRUGO, init_net.proc_net, &rose_info_fops); + proc_create("rose_neigh", S_IRUGO, init_net.proc_net, + &rose_neigh_fops); + proc_create("rose_nodes", S_IRUGO, init_net.proc_net, + &rose_nodes_fops); + proc_create("rose_routes", S_IRUGO, init_net.proc_net, + &rose_routes_fops); out: return rc; fail: diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 5b0fd291bab..59c7c7d5940 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -839,8 +839,9 @@ static int __init af_rxrpc_init(void) } #ifdef CONFIG_PROC_FS - proc_net_fops_create(&init_net, "rxrpc_calls", 0, &rxrpc_call_seq_fops); - proc_net_fops_create(&init_net, "rxrpc_conns", 0, &rxrpc_connection_seq_fops); + proc_create("rxrpc_calls", 0, init_net.proc_net, &rxrpc_call_seq_fops); + proc_create("rxrpc_conns", 0, init_net.proc_net, + &rxrpc_connection_seq_fops); #endif return 0; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index fe1ba54b93f..d8cf7d3dfe8 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1768,7 +1768,7 @@ static int __net_init psched_net_init(struct net *net) { struct proc_dir_entry *e; - e = proc_net_fops_create(net, "psched", 0, &psched_fops); + e = proc_create("psched", 0, net->proc_net, &psched_fops); if (e == NULL) return -ENOMEM; diff --git a/net/sctp/probe.c b/net/sctp/probe.c index 261b7b9858a..dd507f5ca8e 100644 --- a/net/sctp/probe.c +++ b/net/sctp/probe.c @@ -195,8 +195,8 @@ static __init int sctpprobe_init(void) if (kfifo_alloc(&sctpw.fifo, bufsize, GFP_KERNEL)) return ret; - if (!proc_net_fops_create(&init_net, procname, S_IRUSR, - &sctpprobe_fops)) + if (!proc_create(procname, S_IRUSR, init_net.proc_net, + &sctpprobe_fops)) goto free_kfifo; ret = register_jprobe(&sctp_recv_probe); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0c612361c15..0c479b6f407 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2402,7 +2402,7 @@ static int __net_init unix_net_init(struct net *net) goto out; #ifdef CONFIG_PROC_FS - if (!proc_net_fops_create(net, "unix", 0, &unix_seq_fops)) { + if (!proc_create("unix", 0, net->proc_net, &unix_seq_fops)) { unix_sysctl_unregister(net); goto out; } diff --git a/net/wireless/wext-proc.c b/net/wireless/wext-proc.c index 8bafa31fa9f..00fc5bb3fb6 100644 --- a/net/wireless/wext-proc.c +++ b/net/wireless/wext-proc.c @@ -143,7 +143,8 @@ static const struct file_operations wireless_seq_fops = { int __net_init wext_proc_init(struct net *net) { /* Create /proc/net/wireless entry */ - if (!proc_net_fops_create(net, "wireless", S_IRUGO, &wireless_seq_fops)) + if (!proc_create("wireless", S_IRUGO, net->proc_net, + &wireless_seq_fops)) return -ENOMEM; return 0; diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c index 603903853e8..9abe14fb59b 100644 --- a/net/xfrm/xfrm_proc.c +++ b/net/xfrm/xfrm_proc.c @@ -74,8 +74,8 @@ static const struct file_operations xfrm_statistics_seq_fops = { int __net_init xfrm_proc_init(struct net *net) { - if (!proc_net_fops_create(net, "xfrm_stat", S_IRUGO, - &xfrm_statistics_seq_fops)) + if (!proc_create("xfrm_stat", S_IRUGO, net->proc_net, + &xfrm_statistics_seq_fops)) return -ENOMEM; return 0; } -- cgit v1.2.3-70-g09d2 From ece31ffd539e8e2b586b1ca5f50bc4f4591e3893 Mon Sep 17 00:00:00 2001 From: Gao feng Date: Mon, 18 Feb 2013 01:34:56 +0000 Subject: net: proc: change proc_net_remove to remove_proc_entry proc_net_remove is only used to remove proc entries that under /proc/net,it's not a general function for removing proc entries of netns. if we want to remove some proc entries which under /proc/net/stat/, we still need to call remove_proc_entry. this patch use remove_proc_entry to replace proc_net_remove. we can remove proc_net_remove after this patch. Signed-off-by: Gao feng Signed-off-by: David S. Miller --- drivers/connector/connector.c | 2 +- drivers/net/hamradio/bpqether.c | 2 +- drivers/net/hamradio/scc.c | 2 +- drivers/net/hamradio/yam.c | 2 +- drivers/net/ppp/pppoe.c | 2 +- net/8021q/vlanproc.c | 2 +- net/atm/proc.c | 2 +- net/ax25/af_ax25.c | 6 +++--- net/bluetooth/af_bluetooth.c | 2 +- net/can/bcm.c | 2 +- net/can/proc.c | 2 +- net/core/dev.c | 12 ++++++------ net/core/dev_addr_lists.c | 2 +- net/core/pktgen.c | 4 ++-- net/core/sock.c | 2 +- net/dccp/probe.c | 4 ++-- net/decnet/af_decnet.c | 2 +- net/decnet/dn_dev.c | 2 +- net/decnet/dn_neigh.c | 2 +- net/decnet/dn_route.c | 2 +- net/ipv4/arp.c | 2 +- net/ipv4/fib_trie.c | 10 +++++----- net/ipv4/igmp.c | 6 +++--- net/ipv4/ipmr.c | 6 +++--- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c | 8 ++++---- net/ipv4/ping.c | 2 +- net/ipv4/proc.c | 10 +++++----- net/ipv4/raw.c | 2 +- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_probe.c | 4 ++-- net/ipv4/udp.c | 2 +- net/ipv6/addrconf.c | 2 +- net/ipv6/anycast.c | 2 +- net/ipv6/ip6_flowlabel.c | 2 +- net/ipv6/ip6mr.c | 6 +++--- net/ipv6/mcast.c | 6 +++--- net/ipv6/proc.c | 10 +++++----- net/ipv6/raw.c | 2 +- net/ipv6/route.c | 4 ++-- net/key/af_key.c | 2 +- net/l2tp/l2tp_ppp.c | 2 +- net/netfilter/ipvs/ip_vs_app.c | 2 +- net/netfilter/ipvs/ip_vs_conn.c | 4 ++-- net/netfilter/ipvs/ip_vs_ctl.c | 6 +++--- net/netfilter/nf_conntrack_expect.c | 2 +- net/netfilter/nf_conntrack_standalone.c | 4 ++-- net/netfilter/x_tables.c | 10 +++++----- net/netfilter/xt_hashlimit.c | 6 +++--- net/netfilter/xt_recent.c | 2 +- net/netlink/af_netlink.c | 2 +- net/netrom/af_netrom.c | 6 +++--- net/packet/af_packet.c | 2 +- net/phonet/pn_dev.c | 4 ++-- net/rose/af_rose.c | 8 ++++---- net/rxrpc/af_rxrpc.c | 4 ++-- net/sched/sch_api.c | 2 +- net/sctp/probe.c | 4 ++-- net/unix/af_unix.c | 2 +- net/wireless/wext-proc.c | 2 +- net/xfrm/xfrm_proc.c | 2 +- 60 files changed, 112 insertions(+), 112 deletions(-) (limited to 'net/core') diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index ed17a57ab3c..f1b7e244bfc 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -287,7 +287,7 @@ static void cn_fini(void) cn_already_initialized = 0; - proc_net_remove(&init_net, "connector"); + remove_proc_entry("connector", init_net.proc_net); cn_queue_free_dev(dev->cbdev); netlink_kernel_release(dev->nls); diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index 61f28842163..02de6c89167 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -611,7 +611,7 @@ static void __exit bpq_cleanup_driver(void) unregister_netdevice_notifier(&bpq_dev_notifier); - proc_net_remove(&init_net, "bpqether"); + remove_proc_entry("bpqether", init_net.proc_net); rtnl_lock(); while (!list_empty(&bpq_devices)) { diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c index cab13f4d294..bc1d5217038 100644 --- a/drivers/net/hamradio/scc.c +++ b/drivers/net/hamradio/scc.c @@ -2173,7 +2173,7 @@ static void __exit scc_cleanup_driver(void) if (Vector_Latch) release_region(Vector_Latch, 1); - proc_net_remove(&init_net, "z8530drv"); + remove_proc_entry("z8530drv", init_net.proc_net); } MODULE_AUTHOR("Joerg Reuter "); diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index 92847d27b2e..4cf8f1017aa 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -1199,7 +1199,7 @@ static void __exit yam_cleanup_driver(void) kfree(p); } - proc_net_remove(&init_net, "yam"); + remove_proc_entry("yam", init_net.proc_net); } /* --------------------------------------------------------------------- */ diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index d7fa96c42ae..bb07ba94c3a 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -1145,7 +1145,7 @@ static __net_init int pppoe_init_net(struct net *net) static __net_exit void pppoe_exit_net(struct net *net) { - proc_net_remove(net, "pppoe"); + remove_proc_entry("pppoe", net->proc_net); } static struct pernet_operations pppoe_net_ops = { diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index 4de77ea5fa3..dc526ec965e 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -131,7 +131,7 @@ void vlan_proc_cleanup(struct net *net) remove_proc_entry(name_conf, vn->proc_vlan_dir); if (vn->proc_vlan_dir) - proc_net_remove(net, name_root); + remove_proc_entry(name_root, net->proc_net); /* Dynamically added entries should be cleaned up as their vlan_device * is removed, so we should not have to take care of it here... diff --git a/net/atm/proc.c b/net/atm/proc.c index 0d020de8d23..b4e75340b16 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -460,7 +460,7 @@ static void atm_proc_dirs_remove(void) if (e->dirent) remove_proc_entry(e->name, atm_proc_root); } - proc_net_remove(&init_net, "atm"); + remove_proc_entry("atm", init_net.proc_net); } int __init atm_proc_init(void) diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index b6ccbea3477..69a06c47b64 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -2009,9 +2009,9 @@ MODULE_ALIAS_NETPROTO(PF_AX25); static void __exit ax25_exit(void) { - proc_net_remove(&init_net, "ax25_route"); - proc_net_remove(&init_net, "ax25"); - proc_net_remove(&init_net, "ax25_calls"); + remove_proc_entry("ax25_route", init_net.proc_net); + remove_proc_entry("ax25", init_net.proc_net); + remove_proc_entry("ax25_calls", init_net.proc_net); unregister_netdevice_notifier(&ax25_dev_notifier); diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 8412b637407..d3ee69b35a7 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -652,7 +652,7 @@ int bt_procfs_init(struct module* module, struct net *net, const char *name, void bt_procfs_cleanup(struct net *net, const char *name) { - proc_net_remove(net, name); + remove_proc_entry(name, net->proc_net); } #else int bt_procfs_init(struct module* module, struct net *net, const char *name, diff --git a/net/can/bcm.c b/net/can/bcm.c index 28e12d18f0f..5dcb20076f3 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1633,7 +1633,7 @@ static void __exit bcm_module_exit(void) can_proto_unregister(&bcm_can_proto); if (proc_dir) - proc_net_remove(&init_net, "can-bcm"); + remove_proc_entry("can-bcm", init_net.proc_net); } module_init(bcm_module_init); diff --git a/net/can/proc.c b/net/can/proc.c index ae566902d2b..49733589214 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -531,5 +531,5 @@ void can_remove_proc(void) can_remove_proc_readentry(CAN_PROC_RCVLIST_SFF); if (can_dir) - proc_net_remove(&init_net, "can"); + remove_proc_entry("can", init_net.proc_net); } diff --git a/net/core/dev.c b/net/core/dev.c index f2f81ef5bbd..decf55f9ad8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4532,11 +4532,11 @@ static int __net_init dev_proc_net_init(struct net *net) out: return rc; out_ptype: - proc_net_remove(net, "ptype"); + remove_proc_entry("ptype", net->proc_net); out_softnet: - proc_net_remove(net, "softnet_stat"); + remove_proc_entry("softnet_stat", net->proc_net); out_dev: - proc_net_remove(net, "dev"); + remove_proc_entry("dev", net->proc_net); goto out; } @@ -4544,9 +4544,9 @@ static void __net_exit dev_proc_net_exit(struct net *net) { wext_proc_exit(net); - proc_net_remove(net, "ptype"); - proc_net_remove(net, "softnet_stat"); - proc_net_remove(net, "dev"); + remove_proc_entry("ptype", net->proc_net); + remove_proc_entry("softnet_stat", net->proc_net); + remove_proc_entry("dev", net->proc_net); } static struct pernet_operations __net_initdata dev_proc_ops = { diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 7c62ec449f3..89562529df4 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -787,7 +787,7 @@ static int __net_init dev_mc_net_init(struct net *net) static void __net_exit dev_mc_net_exit(struct net *net) { - proc_net_remove(net, "dev_mcast"); + remove_proc_entry("dev_mcast", net->proc_net); } static struct pernet_operations __net_initdata dev_mc_net_ops = { diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 2201e699ad6..6048fc1da1c 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3650,7 +3650,7 @@ static int __net_init pg_net_init(struct net *net) remove_entry: remove_proc_entry(PGCTRL, pn->proc_dir); remove: - proc_net_remove(pn->net, PG_PROC_DIR); + remove_proc_entry(PG_PROC_DIR, pn->net->proc_net); return ret; } @@ -3676,7 +3676,7 @@ static void __net_exit pg_net_exit(struct net *net) } remove_proc_entry(PGCTRL, pn->proc_dir); - proc_net_remove(pn->net, PG_PROC_DIR); + remove_proc_entry(PG_PROC_DIR, pn->net->proc_net); } static struct pernet_operations pg_net_ops = { diff --git a/net/core/sock.c b/net/core/sock.c index b4d562ef36f..fe96c5d3429 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2844,7 +2844,7 @@ static __net_init int proto_init_net(struct net *net) static __net_exit void proto_exit_net(struct net *net) { - proc_net_remove(net, "protocols"); + remove_proc_entry("protocols", net->proc_net); } diff --git a/net/dccp/probe.c b/net/dccp/probe.c index d183589b77e..4c6bdf97a65 100644 --- a/net/dccp/probe.c +++ b/net/dccp/probe.c @@ -181,7 +181,7 @@ static __init int dccpprobe_init(void) pr_info("DCCP watch registered (port=%d)\n", port); return 0; err1: - proc_net_remove(&init_net, procname); + remove_proc_entry(procname, init_net.proc_net); err0: kfifo_free(&dccpw.fifo); return ret; @@ -191,7 +191,7 @@ module_init(dccpprobe_init); static __exit void dccpprobe_exit(void) { kfifo_free(&dccpw.fifo); - proc_net_remove(&init_net, procname); + remove_proc_entry(procname, init_net.proc_net); unregister_jprobe(&dccp_send_probe); } diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index f916013d907..c4a2def5b7b 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -2413,7 +2413,7 @@ static void __exit decnet_exit(void) dn_neigh_cleanup(); dn_fib_cleanup(); - proc_net_remove(&init_net, "decnet"); + remove_proc_entry("decnet", init_net.proc_net); proto_unregister(&dn_proto); diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index a04894a2c26..c8da116d84a 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -1433,7 +1433,7 @@ void __exit dn_dev_cleanup(void) } #endif /* CONFIG_SYSCTL */ - proc_net_remove(&init_net, "decnet_dev"); + remove_proc_entry("decnet_dev", init_net.proc_net); dn_dev_devices_off(); } diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index f3408f369fe..f8637f93d31 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -596,6 +596,6 @@ void __init dn_neigh_init(void) void __exit dn_neigh_cleanup(void) { - proc_net_remove(&init_net, "decnet_neigh"); + remove_proc_entry("decnet_neigh", init_net.proc_net); neigh_table_clear(&dn_neigh_table); } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 8afb257f279..5ac0e153ef8 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1918,7 +1918,7 @@ void __exit dn_route_cleanup(void) del_timer(&dn_route_timer); dn_run_flush(0); - proc_net_remove(&init_net, "decnet_cache"); + remove_proc_entry("decnet_cache", init_net.proc_net); dst_entries_destroy(&dn_dst_ops); } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index b04c114ef05..fea4929f620 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1412,7 +1412,7 @@ static int __net_init arp_net_init(struct net *net) static void __net_exit arp_net_exit(struct net *net) { - proc_net_remove(net, "arp"); + remove_proc_entry("arp", net->proc_net); } static struct pernet_operations arp_net_ops = { diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 67c1d4b641d..61e03da3e1f 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2620,18 +2620,18 @@ int __net_init fib_proc_init(struct net *net) return 0; out3: - proc_net_remove(net, "fib_triestat"); + remove_proc_entry("fib_triestat", net->proc_net); out2: - proc_net_remove(net, "fib_trie"); + remove_proc_entry("fib_trie", net->proc_net); out1: return -ENOMEM; } void __net_exit fib_proc_exit(struct net *net) { - proc_net_remove(net, "fib_trie"); - proc_net_remove(net, "fib_triestat"); - proc_net_remove(net, "route"); + remove_proc_entry("fib_trie", net->proc_net); + remove_proc_entry("fib_triestat", net->proc_net); + remove_proc_entry("route", net->proc_net); } #endif /* CONFIG_PROC_FS */ diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index be85628e6a8..d8c232794bc 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2656,15 +2656,15 @@ static int __net_init igmp_net_init(struct net *net) return 0; out_mcfilter: - proc_net_remove(net, "igmp"); + remove_proc_entry("igmp", net->proc_net); out_igmp: return -ENOMEM; } static void __net_exit igmp_net_exit(struct net *net) { - proc_net_remove(net, "mcfilter"); - proc_net_remove(net, "igmp"); + remove_proc_entry("mcfilter", net->proc_net); + remove_proc_entry("igmp", net->proc_net); } static struct pernet_operations igmp_net_ops = { diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 160a8b8e9ca..5f95b3aa579 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2712,7 +2712,7 @@ static int __net_init ipmr_net_init(struct net *net) #ifdef CONFIG_PROC_FS proc_cache_fail: - proc_net_remove(net, "ip_mr_vif"); + remove_proc_entry("ip_mr_vif", net->proc_net); proc_vif_fail: ipmr_rules_exit(net); #endif @@ -2723,8 +2723,8 @@ fail: static void __net_exit ipmr_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS - proc_net_remove(net, "ip_mr_cache"); - proc_net_remove(net, "ip_mr_vif"); + remove_proc_entry("ip_mr_cache", net->proc_net); + remove_proc_entry("ip_mr_vif", net->proc_net); #endif ipmr_rules_exit(net); } diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index 48bc681f5d3..f2ca1279408 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -433,9 +433,9 @@ static int __net_init ip_conntrack_net_init(struct net *net) return 0; err3: - proc_net_remove(net, "ip_conntrack_expect"); + remove_proc_entry("ip_conntrack_expect", net->proc_net); err2: - proc_net_remove(net, "ip_conntrack"); + remove_proc_entry("ip_conntrack", net->proc_net); err1: return -ENOMEM; } @@ -443,8 +443,8 @@ err1: static void __net_exit ip_conntrack_net_exit(struct net *net) { remove_proc_entry("ip_conntrack", net->proc_net_stat); - proc_net_remove(net, "ip_conntrack_expect"); - proc_net_remove(net, "ip_conntrack"); + remove_proc_entry("ip_conntrack_expect", net->proc_net); + remove_proc_entry("ip_conntrack", net->proc_net); } static struct pernet_operations ip_conntrack_net_ops = { diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index fc62a13b5ee..55c4ee1bba0 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -897,7 +897,7 @@ static int ping_proc_register(struct net *net) static void ping_proc_unregister(struct net *net) { - proc_net_remove(net, "icmp"); + remove_proc_entry("icmp", net->proc_net); } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 954bcd42d50..32030a24e77 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -482,18 +482,18 @@ static __net_init int ip_proc_init_net(struct net *net) return 0; out_snmp: - proc_net_remove(net, "netstat"); + remove_proc_entry("netstat", net->proc_net); out_netstat: - proc_net_remove(net, "sockstat"); + remove_proc_entry("sockstat", net->proc_net); out_sockstat: return -ENOMEM; } static __net_exit void ip_proc_exit_net(struct net *net) { - proc_net_remove(net, "snmp"); - proc_net_remove(net, "netstat"); - proc_net_remove(net, "sockstat"); + remove_proc_entry("snmp", net->proc_net); + remove_proc_entry("netstat", net->proc_net); + remove_proc_entry("sockstat", net->proc_net); } static __net_initdata struct pernet_operations ip_proc_ops = { diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 5043a7d0c64..53ddebc292b 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -1058,7 +1058,7 @@ static __net_init int raw_init_net(struct net *net) static __net_exit void raw_exit_net(struct net *net) { - proc_net_remove(net, "raw"); + remove_proc_entry("raw", net->proc_net); } static __net_initdata struct pernet_operations raw_net_ops = { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 77f5050efc8..145d3bf8df8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2616,7 +2616,7 @@ EXPORT_SYMBOL(tcp_proc_register); void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo) { - proc_net_remove(net, afinfo->name); + remove_proc_entry(afinfo->name, net->proc_net); } EXPORT_SYMBOL(tcp_proc_unregister); diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 1e3a1fb3c0c..d4943f67aff 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -244,7 +244,7 @@ static __init int tcpprobe_init(void) pr_info("probe registered (port=%d) bufsize=%u\n", port, bufsize); return 0; err1: - proc_net_remove(&init_net, procname); + remove_proc_entry(procname, init_net.proc_net); err0: kfree(tcp_probe.log); return ret; @@ -253,7 +253,7 @@ module_init(tcpprobe_init); static __exit void tcpprobe_exit(void) { - proc_net_remove(&init_net, procname); + remove_proc_entry(procname, init_net.proc_net); unregister_jprobe(&tcp_jprobe); kfree(tcp_probe.log); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 39a5e7a9a77..265c42cf963 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2122,7 +2122,7 @@ EXPORT_SYMBOL(udp_proc_register); void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo) { - proc_net_remove(net, afinfo->name); + remove_proc_entry(afinfo->name, net->proc_net); } EXPORT_SYMBOL(udp_proc_unregister); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index bad71083db8..4dc0d44a5d3 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3332,7 +3332,7 @@ static int __net_init if6_proc_net_init(struct net *net) static void __net_exit if6_proc_net_exit(struct net *net) { - proc_net_remove(net, "if_inet6"); + remove_proc_entry("if_inet6", net->proc_net); } static struct pernet_operations if6_proc_net_ops = { diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 5a8c00983de..5a80f15a9de 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -517,7 +517,7 @@ int __net_init ac6_proc_init(struct net *net) void ac6_proc_exit(struct net *net) { - proc_net_remove(net, "anycast6"); + remove_proc_entry("anycast6", net->proc_net); } #endif diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 900d79eda51..b973ed3d06c 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -814,7 +814,7 @@ static int __net_init ip6_flowlabel_proc_init(struct net *net) static void __net_exit ip6_flowlabel_proc_fini(struct net *net) { - proc_net_remove(net, "ip6_flowlabel"); + remove_proc_entry("ip6_flowlabel", net->proc_net); } #else static inline int ip6_flowlabel_proc_init(struct net *net) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index fdfd96d288e..96bfb4e4b82 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1369,7 +1369,7 @@ static int __net_init ip6mr_net_init(struct net *net) #ifdef CONFIG_PROC_FS proc_cache_fail: - proc_net_remove(net, "ip6_mr_vif"); + remove_proc_entry("ip6_mr_vif", net->proc_net); proc_vif_fail: ip6mr_rules_exit(net); #endif @@ -1380,8 +1380,8 @@ fail: static void __net_exit ip6mr_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS - proc_net_remove(net, "ip6_mr_cache"); - proc_net_remove(net, "ip6_mr_vif"); + remove_proc_entry("ip6_mr_cache", net->proc_net); + remove_proc_entry("ip6_mr_vif", net->proc_net); #endif ip6mr_rules_exit(net); } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index de7d4b9a58b..bfa6cc36ef2 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2610,14 +2610,14 @@ out: return err; out_proc_net_igmp6: - proc_net_remove(net, "igmp6"); + remove_proc_entry("igmp6", net->proc_net); goto out; } static void __net_exit igmp6_proc_exit(struct net *net) { - proc_net_remove(net, "mcfilter6"); - proc_net_remove(net, "igmp6"); + remove_proc_entry("mcfilter6", net->proc_net); + remove_proc_entry("igmp6", net->proc_net); } #else static inline int igmp6_proc_init(struct net *net) diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index cf8901dc653..bbbe53a99b5 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -308,17 +308,17 @@ static int __net_init ipv6_proc_init_net(struct net *net) return 0; proc_dev_snmp6_fail: - proc_net_remove(net, "snmp6"); + remove_proc_entry("snmp6", net->proc_net); proc_snmp6_fail: - proc_net_remove(net, "sockstat6"); + remove_proc_entry("sockstat6", net->proc_net); return -ENOMEM; } static void __net_exit ipv6_proc_exit_net(struct net *net) { - proc_net_remove(net, "sockstat6"); - proc_net_remove(net, "dev_snmp6"); - proc_net_remove(net, "snmp6"); + remove_proc_entry("sockstat6", net->proc_net); + remove_proc_entry("dev_snmp6", net->proc_net); + remove_proc_entry("snmp6", net->proc_net); } static struct pernet_operations ipv6_proc_ops = { diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ff42fb309ee..c65907db8c4 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1300,7 +1300,7 @@ static int __net_init raw6_init_net(struct net *net) static void __net_exit raw6_exit_net(struct net *net) { - proc_net_remove(net, "raw6"); + remove_proc_entry("raw6", net->proc_net); } static struct pernet_operations raw6_net_ops = { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e1228d839eb..515bb51e05a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3004,8 +3004,8 @@ static int __net_init ip6_route_net_init_late(struct net *net) static void __net_exit ip6_route_net_exit_late(struct net *net) { #ifdef CONFIG_PROC_FS - proc_net_remove(net, "ipv6_route"); - proc_net_remove(net, "rt6_stats"); + remove_proc_entry("ipv6_route", net->proc_net); + remove_proc_entry("rt6_stats", net->proc_net); #endif } diff --git a/net/key/af_key.c b/net/key/af_key.c index 021a429312b..9ef79851f29 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3749,7 +3749,7 @@ static int __net_init pfkey_init_proc(struct net *net) static void __net_exit pfkey_exit_proc(struct net *net) { - proc_net_remove(net, "pfkey"); + remove_proc_entry("pfkey", net->proc_net); } #else static inline int pfkey_init_proc(struct net *net) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 3ca270b4d47..3f4e3afc191 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1796,7 +1796,7 @@ out: static __net_exit void pppol2tp_exit_net(struct net *net) { - proc_net_remove(net, "pppol2tp"); + remove_proc_entry("pppol2tp", net->proc_net); } static struct pernet_operations pppol2tp_net_ops = { diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 1db8a25fe4b..0b779d7df88 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -612,5 +612,5 @@ int __net_init ip_vs_app_net_init(struct net *net) void __net_exit ip_vs_app_net_cleanup(struct net *net) { unregister_ip_vs_app(net, NULL /* all */); - proc_net_remove(net, "ip_vs_app"); + remove_proc_entry("ip_vs_app", net->proc_net); } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 91ae11280c2..9f00db7e03f 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1300,8 +1300,8 @@ void __net_exit ip_vs_conn_net_cleanup(struct net *net) { /* flush all the connection entries first */ ip_vs_conn_flush(net); - proc_net_remove(net, "ip_vs_conn"); - proc_net_remove(net, "ip_vs_conn_sync"); + remove_proc_entry("ip_vs_conn", net->proc_net); + remove_proc_entry("ip_vs_conn_sync", net->proc_net); } int __init ip_vs_conn_init(void) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 7d69181f8da..c68198bf912 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3822,9 +3822,9 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net) ip_vs_trash_cleanup(net); ip_vs_stop_estimator(net, &ipvs->tot_stats); ip_vs_control_net_cleanup_sysctl(net); - proc_net_remove(net, "ip_vs_stats_percpu"); - proc_net_remove(net, "ip_vs_stats"); - proc_net_remove(net, "ip_vs"); + remove_proc_entry("ip_vs_stats_percpu", net->proc_net); + remove_proc_entry("ip_vs_stats", net->proc_net); + remove_proc_entry("ip_vs", net->proc_net); free_percpu(ipvs->tot_stats.cpustats); } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 4c15f8d0b74..3921e5bc123 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -582,7 +582,7 @@ static int exp_proc_init(struct net *net) static void exp_proc_remove(struct net *net) { #ifdef CONFIG_NF_CONNTRACK_PROCFS - proc_net_remove(net, "nf_conntrack_expect"); + remove_proc_entry("nf_conntrack_expect", net->proc_net); #endif /* CONFIG_NF_CONNTRACK_PROCFS */ } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index bee9aecc7ba..6bcce401fd1 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -377,7 +377,7 @@ static int nf_conntrack_standalone_init_proc(struct net *net) return 0; out_stat_nf_conntrack: - proc_net_remove(net, "nf_conntrack"); + remove_proc_entry("nf_conntrack", net->proc_net); out_nf_conntrack: return -ENOMEM; } @@ -385,7 +385,7 @@ out_nf_conntrack: static void nf_conntrack_standalone_fini_proc(struct net *net) { remove_proc_entry("nf_conntrack", net->proc_net_stat); - proc_net_remove(net, "nf_conntrack"); + remove_proc_entry("nf_conntrack", net->proc_net); } #else static int nf_conntrack_standalone_init_proc(struct net *net) diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 7b3a9e5999c..686c7715d77 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1323,12 +1323,12 @@ int xt_proto_init(struct net *net, u_int8_t af) out_remove_matches: strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); - proc_net_remove(net, buf); + remove_proc_entry(buf, net->proc_net); out_remove_tables: strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); - proc_net_remove(net, buf); + remove_proc_entry(buf, net->proc_net); out: return -1; #endif @@ -1342,15 +1342,15 @@ void xt_proto_fini(struct net *net, u_int8_t af) strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); - proc_net_remove(net, buf); + remove_proc_entry(buf, net->proc_net); strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TARGETS, sizeof(buf)); - proc_net_remove(net, buf); + remove_proc_entry(buf, net->proc_net); strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); - proc_net_remove(net, buf); + remove_proc_entry(buf, net->proc_net); #endif /*CONFIG_PROC_FS*/ } EXPORT_SYMBOL_GPL(xt_proto_fini); diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index a9d7af953ce..98218c896d2 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -867,7 +867,7 @@ static int __net_init hashlimit_proc_net_init(struct net *net) #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) hashlimit_net->ip6t_hashlimit = proc_mkdir("ip6t_hashlimit", net->proc_net); if (!hashlimit_net->ip6t_hashlimit) { - proc_net_remove(net, "ipt_hashlimit"); + remove_proc_entry("ipt_hashlimit", net->proc_net); return -ENOMEM; } #endif @@ -897,9 +897,9 @@ static void __net_exit hashlimit_proc_net_exit(struct net *net) hashlimit_net->ip6t_hashlimit = NULL; mutex_unlock(&hashlimit_mutex); - proc_net_remove(net, "ipt_hashlimit"); + remove_proc_entry("ipt_hashlimit", net->proc_net); #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) - proc_net_remove(net, "ip6t_hashlimit"); + remove_proc_entry("ip6t_hashlimit", net->proc_net); #endif } diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 978efc9b555..31bf233dae9 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -643,7 +643,7 @@ static void __net_exit recent_proc_net_exit(struct net *net) recent_net->xt_recent = NULL; spin_unlock_bh(&recent_lock); - proc_net_remove(net, "xt_recent"); + remove_proc_entry("xt_recent", net->proc_net); } #else static inline int recent_proc_net_init(struct net *net) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 50084c40a12..3d55e0c713e 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2154,7 +2154,7 @@ static int __net_init netlink_net_init(struct net *net) static void __net_exit netlink_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS - proc_net_remove(net, "netlink"); + remove_proc_entry("netlink", net->proc_net); #endif } diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 71b86133840..297b07a029d 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1482,9 +1482,9 @@ static void __exit nr_exit(void) { int i; - proc_net_remove(&init_net, "nr"); - proc_net_remove(&init_net, "nr_neigh"); - proc_net_remove(&init_net, "nr_nodes"); + remove_proc_entry("nr", init_net.proc_net); + remove_proc_entry("nr_neigh", init_net.proc_net); + remove_proc_entry("nr_nodes", init_net.proc_net); nr_loopback_clear(); nr_rt_free(); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b7b2d56126c..c7bfeff1076 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3836,7 +3836,7 @@ static int __net_init packet_net_init(struct net *net) static void __net_exit packet_net_exit(struct net *net) { - proc_net_remove(net, "packet"); + remove_proc_entry("packet", net->proc_net); } static struct pernet_operations packet_net_ops = { diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 0e527c9dd04..45a7df6575d 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -331,7 +331,7 @@ static int __net_init phonet_init_net(struct net *net) static void __net_exit phonet_exit_net(struct net *net) { - proc_net_remove(net, "phonet"); + remove_proc_entry("phonet", net->proc_net); } static struct pernet_operations phonet_net_ops = { @@ -361,7 +361,7 @@ void phonet_device_exit(void) rtnl_unregister_all(PF_PHONET); unregister_netdevice_notifier(&phonet_device_notifier); unregister_pernet_subsys(&phonet_net_ops); - proc_net_remove(&init_net, "pnresource"); + remove_proc_entry("pnresource", init_net.proc_net); } int phonet_route_add(struct net_device *dev, u8 daddr) diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 5fd8aacbb5a..b768fe9d5e7 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1608,10 +1608,10 @@ static void __exit rose_exit(void) { int i; - proc_net_remove(&init_net, "rose"); - proc_net_remove(&init_net, "rose_neigh"); - proc_net_remove(&init_net, "rose_nodes"); - proc_net_remove(&init_net, "rose_routes"); + remove_proc_entry("rose", init_net.proc_net); + remove_proc_entry("rose_neigh", init_net.proc_net); + remove_proc_entry("rose_nodes", init_net.proc_net); + remove_proc_entry("rose_routes", init_net.proc_net); rose_loopback_clear(); rose_rt_free(); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 59c7c7d5940..e61aa6001c6 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -879,8 +879,8 @@ static void __exit af_rxrpc_exit(void) _debug("flush scheduled work"); flush_workqueue(rxrpc_workqueue); - proc_net_remove(&init_net, "rxrpc_conns"); - proc_net_remove(&init_net, "rxrpc_calls"); + remove_proc_entry("rxrpc_conns", init_net.proc_net); + remove_proc_entry("rxrpc_calls", init_net.proc_net); destroy_workqueue(rxrpc_workqueue); kmem_cache_destroy(rxrpc_call_jar); _leave(""); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index d8cf7d3dfe8..a181b484812 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1777,7 +1777,7 @@ static int __net_init psched_net_init(struct net *net) static void __net_exit psched_net_exit(struct net *net) { - proc_net_remove(net, "psched"); + remove_proc_entry("psched", net->proc_net); } #else static int __net_init psched_net_init(struct net *net) diff --git a/net/sctp/probe.c b/net/sctp/probe.c index dd507f5ca8e..ad0dba87034 100644 --- a/net/sctp/probe.c +++ b/net/sctp/probe.c @@ -208,7 +208,7 @@ static __init int sctpprobe_init(void) return 0; remove_proc: - proc_net_remove(&init_net, procname); + remove_proc_entry(procname, init_net.proc_net); free_kfifo: kfifo_free(&sctpw.fifo); return ret; @@ -217,7 +217,7 @@ free_kfifo: static __exit void sctpprobe_exit(void) { kfifo_free(&sctpw.fifo); - proc_net_remove(&init_net, procname); + remove_proc_entry(procname, init_net.proc_net); unregister_jprobe(&sctp_recv_probe); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0c479b6f407..87d28428901 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2415,7 +2415,7 @@ out: static void __net_exit unix_net_exit(struct net *net) { unix_sysctl_unregister(net); - proc_net_remove(net, "unix"); + remove_proc_entry("unix", net->proc_net); } static struct pernet_operations unix_net_ops = { diff --git a/net/wireless/wext-proc.c b/net/wireless/wext-proc.c index 00fc5bb3fb6..e98a01c1034 100644 --- a/net/wireless/wext-proc.c +++ b/net/wireless/wext-proc.c @@ -152,5 +152,5 @@ int __net_init wext_proc_init(struct net *net) void __net_exit wext_proc_exit(struct net *net) { - proc_net_remove(net, "wireless"); + remove_proc_entry("wireless", net->proc_net); } diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c index 9abe14fb59b..c721b0d9ab8 100644 --- a/net/xfrm/xfrm_proc.c +++ b/net/xfrm/xfrm_proc.c @@ -82,5 +82,5 @@ int __net_init xfrm_proc_init(struct net *net) void xfrm_proc_fini(struct net *net) { - proc_net_remove(net, "xfrm_stat"); + remove_proc_entry("xfrm_stat", net->proc_net); } -- cgit v1.2.3-70-g09d2 From 900ff8c6321418dafa03c22e215cb9646a2541b9 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 18 Feb 2013 19:20:33 +0000 Subject: net: move procfs code to net/core/net-procfs.c Similar to net/core/net-sysfs.c, group procfs code to a single unit. Cc: "David S. Miller" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 36 +++- net/core/Makefile | 1 + net/core/dev.c | 384 +----------------------------------------- net/core/dev_addr_lists.c | 74 --------- net/core/net-procfs.c | 414 ++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 450 insertions(+), 459 deletions(-) create mode 100644 net/core/net-procfs.c (limited to 'net/core') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 920361bc27e..f111b4f038f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2692,9 +2692,9 @@ extern void net_enable_timestamp(void); extern void net_disable_timestamp(void); #ifdef CONFIG_PROC_FS -extern void *dev_seq_start(struct seq_file *seq, loff_t *pos); -extern void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos); -extern void dev_seq_stop(struct seq_file *seq, void *v); +extern int __init dev_proc_init(void); +#else +#define dev_proc_init() 0 #endif extern int netdev_class_create_file(struct class_attribute *class_attr); @@ -2896,4 +2896,34 @@ do { \ }) #endif +/* + * The list of packet types we will receive (as opposed to discard) + * and the routines to invoke. + * + * Why 16. Because with 16 the only overlap we get on a hash of the + * low nibble of the protocol value is RARP/SNAP/X.25. + * + * NOTE: That is no longer true with the addition of VLAN tags. Not + * sure which should go first, but I bet it won't make much + * difference if we are running VLANs. The good news is that + * this protocol won't be in the list unless compiled in, so + * the average user (w/out VLANs) will not be adversely affected. + * --BLG + * + * 0800 IP + * 8100 802.1Q VLAN + * 0001 802.3 + * 0002 AX.25 + * 0004 802.2 + * 8035 RARP + * 0005 SNAP + * 0805 X.25 + * 0806 ARP + * 8137 IPX + * 0009 Localtalk + * 86DD IPv6 + */ +#define PTYPE_HASH_SIZE (16) +#define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1) + #endif /* _LINUX_NETDEVICE_H */ diff --git a/net/core/Makefile b/net/core/Makefile index 0c5e3618c80..b33b996f5dd 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -13,6 +13,7 @@ obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ obj-$(CONFIG_XFRM) += flow.o obj-y += net-sysfs.o +obj-$(CONFIG_PROC_FS) += net-procfs.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o obj-$(CONFIG_NETPOLL) += netpoll.o obj-$(CONFIG_NET_DMA) += user_dma.o diff --git a/net/core/dev.c b/net/core/dev.c index decf55f9ad8..8d9ddb09f20 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -97,8 +97,6 @@ #include #include #include -#include -#include #include #include #include @@ -110,7 +108,6 @@ #include #include #include -#include #include #include #include @@ -141,41 +138,10 @@ /* This should be increased if a protocol with a bigger head is added. */ #define GRO_MAX_HEAD (MAX_HEADER + 128) -/* - * The list of packet types we will receive (as opposed to discard) - * and the routines to invoke. - * - * Why 16. Because with 16 the only overlap we get on a hash of the - * low nibble of the protocol value is RARP/SNAP/X.25. - * - * NOTE: That is no longer true with the addition of VLAN tags. Not - * sure which should go first, but I bet it won't make much - * difference if we are running VLANs. The good news is that - * this protocol won't be in the list unless compiled in, so - * the average user (w/out VLANs) will not be adversely affected. - * --BLG - * - * 0800 IP - * 8100 802.1Q VLAN - * 0001 802.3 - * 0002 AX.25 - * 0004 802.2 - * 8035 RARP - * 0005 SNAP - * 0805 X.25 - * 0806 ARP - * 8137 IPX - * 0009 Localtalk - * 86DD IPv6 - */ - -#define PTYPE_HASH_SIZE (16) -#define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1) - static DEFINE_SPINLOCK(ptype_lock); static DEFINE_SPINLOCK(offload_lock); -static struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; -static struct list_head ptype_all __read_mostly; /* Taps */ +struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; +struct list_head ptype_all __read_mostly; /* Taps */ static struct list_head offload_base __read_mostly; /* @@ -4217,352 +4183,6 @@ softnet_break: goto out; } -#ifdef CONFIG_PROC_FS - -#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1) - -#define get_bucket(x) ((x) >> BUCKET_SPACE) -#define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1)) -#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o)) - -static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos) -{ - struct net *net = seq_file_net(seq); - struct net_device *dev; - struct hlist_node *p; - struct hlist_head *h; - unsigned int count = 0, offset = get_offset(*pos); - - h = &net->dev_name_head[get_bucket(*pos)]; - hlist_for_each_entry_rcu(dev, p, h, name_hlist) { - if (++count == offset) - return dev; - } - - return NULL; -} - -static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos) -{ - struct net_device *dev; - unsigned int bucket; - - do { - dev = dev_from_same_bucket(seq, pos); - if (dev) - return dev; - - bucket = get_bucket(*pos) + 1; - *pos = set_bucket_offset(bucket, 1); - } while (bucket < NETDEV_HASHENTRIES); - - return NULL; -} - -/* - * This is invoked by the /proc filesystem handler to display a device - * in detail. - */ -void *dev_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) -{ - rcu_read_lock(); - if (!*pos) - return SEQ_START_TOKEN; - - if (get_bucket(*pos) >= NETDEV_HASHENTRIES) - return NULL; - - return dev_from_bucket(seq, pos); -} - -void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - ++*pos; - return dev_from_bucket(seq, pos); -} - -void dev_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) -{ - rcu_read_unlock(); -} - -static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) -{ - struct rtnl_link_stats64 temp; - const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); - - seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu " - "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n", - dev->name, stats->rx_bytes, stats->rx_packets, - stats->rx_errors, - stats->rx_dropped + stats->rx_missed_errors, - stats->rx_fifo_errors, - stats->rx_length_errors + stats->rx_over_errors + - stats->rx_crc_errors + stats->rx_frame_errors, - stats->rx_compressed, stats->multicast, - stats->tx_bytes, stats->tx_packets, - stats->tx_errors, stats->tx_dropped, - stats->tx_fifo_errors, stats->collisions, - stats->tx_carrier_errors + - stats->tx_aborted_errors + - stats->tx_window_errors + - stats->tx_heartbeat_errors, - stats->tx_compressed); -} - -/* - * Called from the PROCfs module. This now uses the new arbitrary sized - * /proc/net interface to create /proc/net/dev - */ -static int dev_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) - seq_puts(seq, "Inter-| Receive " - " | Transmit\n" - " face |bytes packets errs drop fifo frame " - "compressed multicast|bytes packets errs " - "drop fifo colls carrier compressed\n"); - else - dev_seq_printf_stats(seq, v); - return 0; -} - -static struct softnet_data *softnet_get_online(loff_t *pos) -{ - struct softnet_data *sd = NULL; - - while (*pos < nr_cpu_ids) - if (cpu_online(*pos)) { - sd = &per_cpu(softnet_data, *pos); - break; - } else - ++*pos; - return sd; -} - -static void *softnet_seq_start(struct seq_file *seq, loff_t *pos) -{ - return softnet_get_online(pos); -} - -static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - ++*pos; - return softnet_get_online(pos); -} - -static void softnet_seq_stop(struct seq_file *seq, void *v) -{ -} - -static int softnet_seq_show(struct seq_file *seq, void *v) -{ - struct softnet_data *sd = v; - - seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", - sd->processed, sd->dropped, sd->time_squeeze, 0, - 0, 0, 0, 0, /* was fastroute */ - sd->cpu_collision, sd->received_rps); - return 0; -} - -static const struct seq_operations dev_seq_ops = { - .start = dev_seq_start, - .next = dev_seq_next, - .stop = dev_seq_stop, - .show = dev_seq_show, -}; - -static int dev_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &dev_seq_ops, - sizeof(struct seq_net_private)); -} - -static const struct file_operations dev_seq_fops = { - .owner = THIS_MODULE, - .open = dev_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; - -static const struct seq_operations softnet_seq_ops = { - .start = softnet_seq_start, - .next = softnet_seq_next, - .stop = softnet_seq_stop, - .show = softnet_seq_show, -}; - -static int softnet_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &softnet_seq_ops); -} - -static const struct file_operations softnet_seq_fops = { - .owner = THIS_MODULE, - .open = softnet_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static void *ptype_get_idx(loff_t pos) -{ - struct packet_type *pt = NULL; - loff_t i = 0; - int t; - - list_for_each_entry_rcu(pt, &ptype_all, list) { - if (i == pos) - return pt; - ++i; - } - - for (t = 0; t < PTYPE_HASH_SIZE; t++) { - list_for_each_entry_rcu(pt, &ptype_base[t], list) { - if (i == pos) - return pt; - ++i; - } - } - return NULL; -} - -static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) -{ - rcu_read_lock(); - return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN; -} - -static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct packet_type *pt; - struct list_head *nxt; - int hash; - - ++*pos; - if (v == SEQ_START_TOKEN) - return ptype_get_idx(0); - - pt = v; - nxt = pt->list.next; - if (pt->type == htons(ETH_P_ALL)) { - if (nxt != &ptype_all) - goto found; - hash = 0; - nxt = ptype_base[0].next; - } else - hash = ntohs(pt->type) & PTYPE_HASH_MASK; - - while (nxt == &ptype_base[hash]) { - if (++hash >= PTYPE_HASH_SIZE) - return NULL; - nxt = ptype_base[hash].next; - } -found: - return list_entry(nxt, struct packet_type, list); -} - -static void ptype_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) -{ - rcu_read_unlock(); -} - -static int ptype_seq_show(struct seq_file *seq, void *v) -{ - struct packet_type *pt = v; - - if (v == SEQ_START_TOKEN) - seq_puts(seq, "Type Device Function\n"); - else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { - if (pt->type == htons(ETH_P_ALL)) - seq_puts(seq, "ALL "); - else - seq_printf(seq, "%04x", ntohs(pt->type)); - - seq_printf(seq, " %-8s %pF\n", - pt->dev ? pt->dev->name : "", pt->func); - } - - return 0; -} - -static const struct seq_operations ptype_seq_ops = { - .start = ptype_seq_start, - .next = ptype_seq_next, - .stop = ptype_seq_stop, - .show = ptype_seq_show, -}; - -static int ptype_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &ptype_seq_ops, - sizeof(struct seq_net_private)); -} - -static const struct file_operations ptype_seq_fops = { - .owner = THIS_MODULE, - .open = ptype_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; - - -static int __net_init dev_proc_net_init(struct net *net) -{ - int rc = -ENOMEM; - - if (!proc_create("dev", S_IRUGO, net->proc_net, &dev_seq_fops)) - goto out; - if (!proc_create("softnet_stat", S_IRUGO, net->proc_net, - &softnet_seq_fops)) - goto out_dev; - if (!proc_create("ptype", S_IRUGO, net->proc_net, &ptype_seq_fops)) - goto out_softnet; - - if (wext_proc_init(net)) - goto out_ptype; - rc = 0; -out: - return rc; -out_ptype: - remove_proc_entry("ptype", net->proc_net); -out_softnet: - remove_proc_entry("softnet_stat", net->proc_net); -out_dev: - remove_proc_entry("dev", net->proc_net); - goto out; -} - -static void __net_exit dev_proc_net_exit(struct net *net) -{ - wext_proc_exit(net); - - remove_proc_entry("ptype", net->proc_net); - remove_proc_entry("softnet_stat", net->proc_net); - remove_proc_entry("dev", net->proc_net); -} - -static struct pernet_operations __net_initdata dev_proc_ops = { - .init = dev_proc_net_init, - .exit = dev_proc_net_exit, -}; - -static int __init dev_proc_init(void) -{ - return register_pernet_subsys(&dev_proc_ops); -} -#else -#define dev_proc_init() 0 -#endif /* CONFIG_PROC_FS */ - - struct netdev_upper { struct net_device *dev; bool master; diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 89562529df4..bd2eb9d3e36 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -15,7 +15,6 @@ #include #include #include -#include /* * General list handling functions @@ -727,76 +726,3 @@ void dev_mc_init(struct net_device *dev) __hw_addr_init(&dev->mc); } EXPORT_SYMBOL(dev_mc_init); - -#ifdef CONFIG_PROC_FS -#include - -static int dev_mc_seq_show(struct seq_file *seq, void *v) -{ - struct netdev_hw_addr *ha; - struct net_device *dev = v; - - if (v == SEQ_START_TOKEN) - return 0; - - netif_addr_lock_bh(dev); - netdev_for_each_mc_addr(ha, dev) { - int i; - - seq_printf(seq, "%-4d %-15s %-5d %-5d ", dev->ifindex, - dev->name, ha->refcount, ha->global_use); - - for (i = 0; i < dev->addr_len; i++) - seq_printf(seq, "%02x", ha->addr[i]); - - seq_putc(seq, '\n'); - } - netif_addr_unlock_bh(dev); - return 0; -} - -static const struct seq_operations dev_mc_seq_ops = { - .start = dev_seq_start, - .next = dev_seq_next, - .stop = dev_seq_stop, - .show = dev_mc_seq_show, -}; - -static int dev_mc_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &dev_mc_seq_ops, - sizeof(struct seq_net_private)); -} - -static const struct file_operations dev_mc_seq_fops = { - .owner = THIS_MODULE, - .open = dev_mc_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; - -#endif - -static int __net_init dev_mc_net_init(struct net *net) -{ - if (!proc_create("dev_mcast", 0, net->proc_net, &dev_mc_seq_fops)) - return -ENOMEM; - return 0; -} - -static void __net_exit dev_mc_net_exit(struct net *net) -{ - remove_proc_entry("dev_mcast", net->proc_net); -} - -static struct pernet_operations __net_initdata dev_mc_net_ops = { - .init = dev_mc_net_init, - .exit = dev_mc_net_exit, -}; - -void __init dev_mcast_init(void) -{ - register_pernet_subsys(&dev_mc_net_ops); -} - diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c new file mode 100644 index 00000000000..ac87066491e --- /dev/null +++ b/net/core/net-procfs.c @@ -0,0 +1,414 @@ +#include +#include +#include +#include + +#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1) + +#define get_bucket(x) ((x) >> BUCKET_SPACE) +#define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1)) +#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o)) + +extern struct list_head ptype_all __read_mostly; +extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; + +static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos) +{ + struct net *net = seq_file_net(seq); + struct net_device *dev; + struct hlist_node *p; + struct hlist_head *h; + unsigned int count = 0, offset = get_offset(*pos); + + h = &net->dev_name_head[get_bucket(*pos)]; + hlist_for_each_entry_rcu(dev, p, h, name_hlist) { + if (++count == offset) + return dev; + } + + return NULL; +} + +static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos) +{ + struct net_device *dev; + unsigned int bucket; + + do { + dev = dev_from_same_bucket(seq, pos); + if (dev) + return dev; + + bucket = get_bucket(*pos) + 1; + *pos = set_bucket_offset(bucket, 1); + } while (bucket < NETDEV_HASHENTRIES); + + return NULL; +} + +/* + * This is invoked by the /proc filesystem handler to display a device + * in detail. + */ +static void *dev_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU) +{ + rcu_read_lock(); + if (!*pos) + return SEQ_START_TOKEN; + + if (get_bucket(*pos) >= NETDEV_HASHENTRIES) + return NULL; + + return dev_from_bucket(seq, pos); +} + +static void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + ++*pos; + return dev_from_bucket(seq, pos); +} + +static void dev_seq_stop(struct seq_file *seq, void *v) + __releases(RCU) +{ + rcu_read_unlock(); +} + +static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) +{ + struct rtnl_link_stats64 temp; + const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); + + seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu " + "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n", + dev->name, stats->rx_bytes, stats->rx_packets, + stats->rx_errors, + stats->rx_dropped + stats->rx_missed_errors, + stats->rx_fifo_errors, + stats->rx_length_errors + stats->rx_over_errors + + stats->rx_crc_errors + stats->rx_frame_errors, + stats->rx_compressed, stats->multicast, + stats->tx_bytes, stats->tx_packets, + stats->tx_errors, stats->tx_dropped, + stats->tx_fifo_errors, stats->collisions, + stats->tx_carrier_errors + + stats->tx_aborted_errors + + stats->tx_window_errors + + stats->tx_heartbeat_errors, + stats->tx_compressed); +} + +/* + * Called from the PROCfs module. This now uses the new arbitrary sized + * /proc/net interface to create /proc/net/dev + */ +static int dev_seq_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) + seq_puts(seq, "Inter-| Receive " + " | Transmit\n" + " face |bytes packets errs drop fifo frame " + "compressed multicast|bytes packets errs " + "drop fifo colls carrier compressed\n"); + else + dev_seq_printf_stats(seq, v); + return 0; +} + +static struct softnet_data *softnet_get_online(loff_t *pos) +{ + struct softnet_data *sd = NULL; + + while (*pos < nr_cpu_ids) + if (cpu_online(*pos)) { + sd = &per_cpu(softnet_data, *pos); + break; + } else + ++*pos; + return sd; +} + +static void *softnet_seq_start(struct seq_file *seq, loff_t *pos) +{ + return softnet_get_online(pos); +} + +static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + ++*pos; + return softnet_get_online(pos); +} + +static void softnet_seq_stop(struct seq_file *seq, void *v) +{ +} + +static int softnet_seq_show(struct seq_file *seq, void *v) +{ + struct softnet_data *sd = v; + + seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", + sd->processed, sd->dropped, sd->time_squeeze, 0, + 0, 0, 0, 0, /* was fastroute */ + sd->cpu_collision, sd->received_rps); + return 0; +} + +static const struct seq_operations dev_seq_ops = { + .start = dev_seq_start, + .next = dev_seq_next, + .stop = dev_seq_stop, + .show = dev_seq_show, +}; + +static int dev_seq_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &dev_seq_ops, + sizeof(struct seq_net_private)); +} + +static const struct file_operations dev_seq_fops = { + .owner = THIS_MODULE, + .open = dev_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + +static const struct seq_operations softnet_seq_ops = { + .start = softnet_seq_start, + .next = softnet_seq_next, + .stop = softnet_seq_stop, + .show = softnet_seq_show, +}; + +static int softnet_seq_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &softnet_seq_ops); +} + +static const struct file_operations softnet_seq_fops = { + .owner = THIS_MODULE, + .open = softnet_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static void *ptype_get_idx(loff_t pos) +{ + struct packet_type *pt = NULL; + loff_t i = 0; + int t; + + list_for_each_entry_rcu(pt, &ptype_all, list) { + if (i == pos) + return pt; + ++i; + } + + for (t = 0; t < PTYPE_HASH_SIZE; t++) { + list_for_each_entry_rcu(pt, &ptype_base[t], list) { + if (i == pos) + return pt; + ++i; + } + } + return NULL; +} + +static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU) +{ + rcu_read_lock(); + return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN; +} + +static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct packet_type *pt; + struct list_head *nxt; + int hash; + + ++*pos; + if (v == SEQ_START_TOKEN) + return ptype_get_idx(0); + + pt = v; + nxt = pt->list.next; + if (pt->type == htons(ETH_P_ALL)) { + if (nxt != &ptype_all) + goto found; + hash = 0; + nxt = ptype_base[0].next; + } else + hash = ntohs(pt->type) & PTYPE_HASH_MASK; + + while (nxt == &ptype_base[hash]) { + if (++hash >= PTYPE_HASH_SIZE) + return NULL; + nxt = ptype_base[hash].next; + } +found: + return list_entry(nxt, struct packet_type, list); +} + +static void ptype_seq_stop(struct seq_file *seq, void *v) + __releases(RCU) +{ + rcu_read_unlock(); +} + +static int ptype_seq_show(struct seq_file *seq, void *v) +{ + struct packet_type *pt = v; + + if (v == SEQ_START_TOKEN) + seq_puts(seq, "Type Device Function\n"); + else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { + if (pt->type == htons(ETH_P_ALL)) + seq_puts(seq, "ALL "); + else + seq_printf(seq, "%04x", ntohs(pt->type)); + + seq_printf(seq, " %-8s %pF\n", + pt->dev ? pt->dev->name : "", pt->func); + } + + return 0; +} + +static const struct seq_operations ptype_seq_ops = { + .start = ptype_seq_start, + .next = ptype_seq_next, + .stop = ptype_seq_stop, + .show = ptype_seq_show, +}; + +static int ptype_seq_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &ptype_seq_ops, + sizeof(struct seq_net_private)); +} + +static const struct file_operations ptype_seq_fops = { + .owner = THIS_MODULE, + .open = ptype_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + + +static int __net_init dev_proc_net_init(struct net *net) +{ + int rc = -ENOMEM; + + if (!proc_create("dev", S_IRUGO, net->proc_net, &dev_seq_fops)) + goto out; + if (!proc_create("softnet_stat", S_IRUGO, net->proc_net, + &softnet_seq_fops)) + goto out_dev; + if (!proc_create("ptype", S_IRUGO, net->proc_net, &ptype_seq_fops)) + goto out_softnet; + + if (wext_proc_init(net)) + goto out_ptype; + rc = 0; +out: + return rc; +out_ptype: + remove_proc_entry("ptype", net->proc_net); +out_softnet: + remove_proc_entry("softnet_stat", net->proc_net); +out_dev: + remove_proc_entry("dev", net->proc_net); + goto out; +} + +static void __net_exit dev_proc_net_exit(struct net *net) +{ + wext_proc_exit(net); + + remove_proc_entry("ptype", net->proc_net); + remove_proc_entry("softnet_stat", net->proc_net); + remove_proc_entry("dev", net->proc_net); +} + +static struct pernet_operations __net_initdata dev_proc_ops = { + .init = dev_proc_net_init, + .exit = dev_proc_net_exit, +}; + +int __init dev_proc_init(void) +{ + return register_pernet_subsys(&dev_proc_ops); +} + +static int dev_mc_seq_show(struct seq_file *seq, void *v) +{ + struct netdev_hw_addr *ha; + struct net_device *dev = v; + + if (v == SEQ_START_TOKEN) + return 0; + + netif_addr_lock_bh(dev); + netdev_for_each_mc_addr(ha, dev) { + int i; + + seq_printf(seq, "%-4d %-15s %-5d %-5d ", dev->ifindex, + dev->name, ha->refcount, ha->global_use); + + for (i = 0; i < dev->addr_len; i++) + seq_printf(seq, "%02x", ha->addr[i]); + + seq_putc(seq, '\n'); + } + netif_addr_unlock_bh(dev); + return 0; +} + +static const struct seq_operations dev_mc_seq_ops = { + .start = dev_seq_start, + .next = dev_seq_next, + .stop = dev_seq_stop, + .show = dev_mc_seq_show, +}; + +static int dev_mc_seq_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &dev_mc_seq_ops, + sizeof(struct seq_net_private)); +} + +static const struct file_operations dev_mc_seq_fops = { + .owner = THIS_MODULE, + .open = dev_mc_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + +static int __net_init dev_mc_net_init(struct net *net) +{ + if (!proc_create("dev_mcast", 0, net->proc_net, &dev_mc_seq_fops)) + return -ENOMEM; + return 0; +} + +static void __net_exit dev_mc_net_exit(struct net *net) +{ + remove_proc_entry("dev_mcast", net->proc_net); +} + +static struct pernet_operations __net_initdata dev_mc_net_ops = { + .init = dev_mc_net_init, + .exit = dev_mc_net_exit, +}; + +void __init dev_mcast_init(void) +{ + register_pernet_subsys(&dev_mc_net_ops); +} -- cgit v1.2.3-70-g09d2 From cd0615746ba0f6643fb984345ae6ee0b73404ca6 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 19 Feb 2013 02:47:05 +0000 Subject: net: fix a build failure when !CONFIG_PROC_FS When !CONFIG_PROC_FS dev_mcast_init() is not defined, actually we can just merge dev_mcast_init() into dev_proc_init(). Reported-by: Gao feng Cc: Gao feng Cc: "David S. Miller" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - net/core/dev.c | 1 - net/core/net-procfs.c | 12 +++++------- 3 files changed, 5 insertions(+), 9 deletions(-) (limited to 'net/core') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f111b4f038f..b3d00fa4b31 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2646,7 +2646,6 @@ extern void netdev_notify_peers(struct net_device *dev); extern void netdev_features_change(struct net_device *dev); /* Load a device via the kmod */ extern void dev_load(struct net *net, const char *name); -extern void dev_mcast_init(void); extern struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, struct rtnl_link_stats64 *storage); extern void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, diff --git a/net/core/dev.c b/net/core/dev.c index 8d9ddb09f20..17bc535115d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6260,7 +6260,6 @@ static int __init net_dev_init(void) hotcpu_notifier(dev_cpu_callback, 0); dst_init(); - dev_mcast_init(); rc = 0; out: return rc; diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index ac87066491e..0f6bb6f8d39 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -341,11 +341,6 @@ static struct pernet_operations __net_initdata dev_proc_ops = { .exit = dev_proc_net_exit, }; -int __init dev_proc_init(void) -{ - return register_pernet_subsys(&dev_proc_ops); -} - static int dev_mc_seq_show(struct seq_file *seq, void *v) { struct netdev_hw_addr *ha; @@ -408,7 +403,10 @@ static struct pernet_operations __net_initdata dev_mc_net_ops = { .exit = dev_mc_net_exit, }; -void __init dev_mcast_init(void) +int __init dev_proc_init(void) { - register_pernet_subsys(&dev_mc_net_ops); + int ret = register_pernet_subsys(&dev_proc_ops); + if (!ret) + return register_pernet_subsys(&dev_mc_net_ops); + return ret; } -- cgit v1.2.3-70-g09d2 From 68534c682e8f5c333f835818ca5a89d3e6288870 Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Tue, 19 Feb 2013 22:51:30 +0000 Subject: net: fix a wrong assignment in skb_split() commit c9af6db4c11ccc6c3e7f1 (net: Fix possible wrong checksum generation) has a suspicous piece: - skb_shinfo(skb1)->gso_type = skb_shinfo(skb)->gso_type; - + skb_shinfo(skb)->tx_flags = skb_shinfo(skb1)->tx_flags & SKBTX_SHARED_FRAG; skb1 is the new skb, therefore should be on the left side of the assignment. This patch fixes it. Cc: Pravin B Shelar Cc: David S. Miller Signed-off-by: Cong Wang Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/core/skbuff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2a3ca33c30a..33245ef54c3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2326,7 +2326,7 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); - skb_shinfo(skb)->tx_flags = skb_shinfo(skb1)->tx_flags & SKBTX_SHARED_FRAG; + skb_shinfo(skb1)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); else /* Second chunk has no header, nothing to copy. */ -- cgit v1.2.3-70-g09d2 From ecd9883724b78cc72ed92c98bcb1a46c764fff21 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki / 吉藤英明 Date: Wed, 20 Feb 2013 00:29:08 +0000 Subject: ipv6: fix race condition regarding dst->expires and dst->from. Eric Dumazet wrote: | Some strange crashes happen in rt6_check_expired(), with access | to random addresses. | | At first glance, it looks like the RTF_EXPIRES and | stuff added in commit 1716a96101c49186b | (ipv6: fix problem with expired dst cache) | are racy : same dst could be manipulated at the same time | on different cpus. | | At some point, our stack believes rt->dst.from contains a dst pointer, | while its really a jiffie value (as rt->dst.expires shares the same area | of memory) | | rt6_update_expires() should be fixed, or am I missing something ? | | CC Neil because of https://bugzilla.redhat.com/show_bug.cgi?id=892060 Because we do not have any locks for dst_entry, we cannot change essential structure in the entry; e.g., we cannot change reference to other entity. To fix this issue, split 'from' and 'expires' field in dst_entry out of union. Once it is 'from' is assigned in the constructor, keep the reference until the very last stage of the life time of the object. Of course, it is unsafe to change 'from', so make rt6_set_from simple just for fresh entries. Reported-by: Eric Dumazet Reported-by: Neil Horman CC: Gao Feng Signed-off-by: YOSHIFUJI Hideaki Reviewed-by: Eric Dumazet Reported-by: Steinar H. Gunderson Reviewed-by: Neil Horman Signed-off-by: David S. Miller --- include/net/dst.h | 8 ++------ include/net/ip6_fib.h | 39 ++++++++++++--------------------------- net/core/dst.c | 1 + net/ipv6/route.c | 8 +++----- 4 files changed, 18 insertions(+), 38 deletions(-) (limited to 'net/core') diff --git a/include/net/dst.h b/include/net/dst.h index 3da47e0a4a1..853cda11e51 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -36,13 +36,9 @@ struct dst_entry { struct net_device *dev; struct dst_ops *ops; unsigned long _metrics; - union { - unsigned long expires; - /* point to where the dst_entry copied from */ - struct dst_entry *from; - }; + unsigned long expires; struct dst_entry *path; - void *__pad0; + struct dst_entry *from; #ifdef CONFIG_XFRM struct xfrm_state *xfrm; #else diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 6919a501f99..2a601e7da1b 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -164,50 +164,35 @@ static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) static inline void rt6_clean_expires(struct rt6_info *rt) { - if (!(rt->rt6i_flags & RTF_EXPIRES) && rt->dst.from) - dst_release(rt->dst.from); - rt->rt6i_flags &= ~RTF_EXPIRES; - rt->dst.from = NULL; } static inline void rt6_set_expires(struct rt6_info *rt, unsigned long expires) { - if (!(rt->rt6i_flags & RTF_EXPIRES) && rt->dst.from) - dst_release(rt->dst.from); - - rt->rt6i_flags |= RTF_EXPIRES; rt->dst.expires = expires; + rt->rt6i_flags |= RTF_EXPIRES; } -static inline void rt6_update_expires(struct rt6_info *rt, int timeout) +static inline void rt6_update_expires(struct rt6_info *rt0, int timeout) { - if (!(rt->rt6i_flags & RTF_EXPIRES)) { - if (rt->dst.from) - dst_release(rt->dst.from); - /* dst_set_expires relies on expires == 0 - * if it has not been set previously. - */ - rt->dst.expires = 0; - } - - dst_set_expires(&rt->dst, timeout); - rt->rt6i_flags |= RTF_EXPIRES; + struct rt6_info *rt; + + for (rt = rt0; rt && !(rt->rt6i_flags & RTF_EXPIRES); + rt = (struct rt6_info *)rt->dst.from); + if (rt && rt != rt0) + rt0->dst.expires = rt->dst.expires; + + dst_set_expires(&rt0->dst, timeout); + rt0->rt6i_flags |= RTF_EXPIRES; } static inline void rt6_set_from(struct rt6_info *rt, struct rt6_info *from) { struct dst_entry *new = (struct dst_entry *) from; - if (!(rt->rt6i_flags & RTF_EXPIRES) && rt->dst.from) { - if (new == rt->dst.from) - return; - dst_release(rt->dst.from); - } - rt->rt6i_flags &= ~RTF_EXPIRES; - rt->dst.from = new; dst_hold(new); + rt->dst.from = new; } static inline void ip6_rt_put(struct rt6_info *rt) diff --git a/net/core/dst.c b/net/core/dst.c index ee6153e2cf4..35fd12f1a69 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -179,6 +179,7 @@ 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; + dst->from = NULL; #ifdef CONFIG_XFRM dst->xfrm = NULL; #endif diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 515bb51e05a..92826656968 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -287,6 +287,7 @@ 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 dst_entry *from = dst->from; if (!(rt->dst.flags & DST_HOST)) dst_destroy_metrics_generic(dst); @@ -296,8 +297,8 @@ static void ip6_dst_destroy(struct dst_entry *dst) in6_dev_put(idev); } - if (!(rt->rt6i_flags & RTF_EXPIRES) && dst->from) - dst_release(dst->from); + dst->from = NULL; + dst_release(from); if (rt6_has_peer(rt)) { struct inet_peer *peer = rt6_peer_ptr(rt); @@ -1010,7 +1011,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags; - rt6_clean_expires(rt); rt->rt6i_metric = 0; memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); @@ -1784,8 +1784,6 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) == (RTF_DEFAULT | RTF_ADDRCONF)) rt6_set_from(rt, ort); - else - rt6_clean_expires(rt); rt->rt6i_metric = 0; #ifdef CONFIG_IPV6_SUBTREES -- cgit v1.2.3-70-g09d2