diff options
author | Len Brown <len.brown@intel.com> | 2005-12-06 17:31:30 -0500 |
---|---|---|
committer | Len Brown <len.brown@intel.com> | 2005-12-06 17:31:30 -0500 |
commit | 3d5271f9883cba7b54762bc4fe027d4172f06db7 (patch) | |
tree | ab8a881a14478598a0c8bda0d26c62cdccfffd6d /net/core | |
parent | 378b2556f4e09fa6f87ff0cb5c4395ff28257d02 (diff) | |
parent | 9115a6c787596e687df03010d97fccc5e0762506 (diff) |
Pull release into acpica branch
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/datagram.c | 102 | ||||
-rw-r--r-- | net/core/dev.c | 32 | ||||
-rw-r--r-- | net/core/dev_mcast.c | 3 | ||||
-rw-r--r-- | net/core/ethtool.c | 53 | ||||
-rw-r--r-- | net/core/filter.c | 6 | ||||
-rw-r--r-- | net/core/neighbour.c | 76 | ||||
-rw-r--r-- | net/core/netpoll.c | 20 | ||||
-rw-r--r-- | net/core/pktgen.c | 518 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 83 | ||||
-rw-r--r-- | net/core/skbuff.c | 117 | ||||
-rw-r--r-- | net/core/sock.c | 35 | ||||
-rw-r--r-- | net/core/stream.c | 12 | ||||
-rw-r--r-- | net/core/wireless.c | 9 |
13 files changed, 551 insertions, 515 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c index da9bf71421a..1bcfef51ac5 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -211,74 +211,49 @@ void skb_free_datagram(struct sock *sk, struct sk_buff *skb) int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, struct iovec *to, int len) { - int start = skb_headlen(skb); - int i, copy = start - offset; + int i, err, fraglen, end = 0; + struct sk_buff *next = skb_shinfo(skb)->frag_list; - /* Copy header. */ - if (copy > 0) { - if (copy > len) - copy = len; - if (memcpy_toiovec(to, skb->data + offset, copy)) - goto fault; - if ((len -= copy) == 0) - return 0; - offset += copy; - } + if (!len) + return 0; - /* Copy paged appendix. Hmm... why does this look so complicated? */ - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - int end; +next_skb: + fraglen = skb_headlen(skb); + i = -1; - BUG_TRAP(start <= offset + len); + while (1) { + int start = end; - end = start + skb_shinfo(skb)->frags[i].size; - if ((copy = end - offset) > 0) { - int err; - u8 *vaddr; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - struct page *page = frag->page; + if ((end += fraglen) > offset) { + int copy = end - offset, o = offset - start; if (copy > len) copy = len; - vaddr = kmap(page); - err = memcpy_toiovec(to, vaddr + frag->page_offset + - offset - start, copy); - kunmap(page); + if (i == -1) + err = memcpy_toiovec(to, skb->data + o, copy); + else { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct page *page = frag->page; + void *p = kmap(page) + frag->page_offset + o; + err = memcpy_toiovec(to, p, copy); + kunmap(page); + } if (err) goto fault; if (!(len -= copy)) return 0; offset += copy; } - start = end; + if (++i >= skb_shinfo(skb)->nr_frags) + break; + fraglen = skb_shinfo(skb)->frags[i].size; } - - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list; list = list->next) { - int end; - - BUG_TRAP(start <= offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - if (skb_copy_datagram_iovec(list, - offset - start, - to, copy)) - goto fault; - if ((len -= copy) == 0) - return 0; - offset += copy; - } - start = end; - } + if (next) { + skb = next; + BUG_ON(skb_shinfo(skb)->frag_list); + next = skb->next; + goto next_skb; } - if (!len) - return 0; - fault: return -EFAULT; } @@ -375,6 +350,20 @@ fault: return -EFAULT; } +unsigned int __skb_checksum_complete(struct sk_buff *skb) +{ + unsigned int sum; + + sum = (u16)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum)); + if (likely(!sum)) { + if (unlikely(skb->ip_summed == CHECKSUM_HW)) + netdev_rx_csum_fault(skb->dev); + skb->ip_summed = CHECKSUM_UNNECESSARY; + } + return sum; +} +EXPORT_SYMBOL(__skb_checksum_complete); + /** * skb_copy_and_csum_datagram_iovec - Copy and checkum skb to user iovec. * @skb: skbuff @@ -388,7 +377,7 @@ fault: * -EFAULT - fault during copy. Beware, in this case iovec * can be modified! */ -int skb_copy_and_csum_datagram_iovec(const struct sk_buff *skb, +int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, int hlen, struct iovec *iov) { unsigned int csum; @@ -401,8 +390,7 @@ int skb_copy_and_csum_datagram_iovec(const struct sk_buff *skb, iov++; if (iov->iov_len < chunk) { - if ((unsigned short)csum_fold(skb_checksum(skb, 0, chunk + hlen, - skb->csum))) + if (__skb_checksum_complete(skb)) goto csum_error; if (skb_copy_datagram_iovec(skb, hlen, iov, chunk)) goto fault; @@ -413,6 +401,8 @@ int skb_copy_and_csum_datagram_iovec(const struct sk_buff *skb, goto fault; if ((unsigned short)csum_fold(csum)) goto csum_error; + if (unlikely(skb->ip_summed == CHECKSUM_HW)) + netdev_rx_csum_fault(skb->dev); iov->iov_len -= chunk; iov->iov_base += chunk; } diff --git a/net/core/dev.c b/net/core/dev.c index c01511e3d0c..0b48e294aaf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -574,6 +574,8 @@ struct net_device *dev_getbyhwaddr(unsigned short type, char *ha) return dev; } +EXPORT_SYMBOL(dev_getbyhwaddr); + struct net_device *dev_getfirstbyhwtype(unsigned short type) { struct net_device *dev; @@ -1106,6 +1108,18 @@ out: return ret; } +/* Take action when hardware reception checksum errors are detected. */ +#ifdef CONFIG_BUG +void netdev_rx_csum_fault(struct net_device *dev) +{ + if (net_ratelimit()) { + printk(KERN_ERR "%s: hw csum failure.\n", dev->name); + dump_stack(); + } +} +EXPORT_SYMBOL(netdev_rx_csum_fault); +#endif + #ifdef CONFIG_HIGHMEM /* Actually, we should eliminate this check as soon as we know, that: * 1. IOMMU is present and allows to map all the memory. @@ -1130,7 +1144,7 @@ static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb) #endif /* Keep head the same: replace data */ -int __skb_linearize(struct sk_buff *skb, unsigned int __nocast gfp_mask) +int __skb_linearize(struct sk_buff *skb, gfp_t gfp_mask) { unsigned int size; u8 *data; @@ -1257,6 +1271,8 @@ int dev_queue_xmit(struct sk_buff *skb) if (skb_checksum_help(skb, 0)) goto out_kfree_skb; + spin_lock_prefetch(&dev->queue_lock); + /* Disable soft irqs for various locks below. Also * stops preemption for RCU. */ @@ -2713,6 +2729,20 @@ int register_netdevice(struct net_device *dev) dev->name); dev->features &= ~NETIF_F_TSO; } + if (dev->features & NETIF_F_UFO) { + if (!(dev->features & NETIF_F_HW_CSUM)) { + printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no " + "NETIF_F_HW_CSUM feature.\n", + dev->name); + dev->features &= ~NETIF_F_UFO; + } + if (!(dev->features & NETIF_F_SG)) { + printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no " + "NETIF_F_SG feature.\n", + dev->name); + dev->features &= ~NETIF_F_UFO; + } + } /* * nil rebuild_header routine, diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c index db098ff3cd6..cb530eef0e3 100644 --- a/net/core/dev_mcast.c +++ b/net/core/dev_mcast.c @@ -194,8 +194,7 @@ int dev_mc_add(struct net_device *dev, void *addr, int alen, int glbl) done: spin_unlock_bh(&dev->xmit_lock); - if (dmi1) - kfree(dmi1); + kfree(dmi1); return err; } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 404b761e82c..0350586e919 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -93,6 +93,20 @@ int ethtool_op_get_perm_addr(struct net_device *dev, struct ethtool_perm_addr *a } +u32 ethtool_op_get_ufo(struct net_device *dev) +{ + return (dev->features & NETIF_F_UFO) != 0; +} + +int ethtool_op_set_ufo(struct net_device *dev, u32 data) +{ + if (data) + dev->features |= NETIF_F_UFO; + else + dev->features &= ~NETIF_F_UFO; + return 0; +} + /* Handlers for each ethtool command */ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) @@ -483,6 +497,11 @@ static int __ethtool_set_sg(struct net_device *dev, u32 data) return err; } + if (!data && dev->ethtool_ops->set_ufo) { + err = dev->ethtool_ops->set_ufo(dev, 0); + if (err) + return err; + } return dev->ethtool_ops->set_sg(dev, data); } @@ -569,6 +588,32 @@ static int ethtool_set_tso(struct net_device *dev, char __user *useraddr) return dev->ethtool_ops->set_tso(dev, edata.data); } +static int ethtool_get_ufo(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_value edata = { ETHTOOL_GTSO }; + + if (!dev->ethtool_ops->get_ufo) + return -EOPNOTSUPP; + edata.data = dev->ethtool_ops->get_ufo(dev); + if (copy_to_user(useraddr, &edata, sizeof(edata))) + return -EFAULT; + return 0; +} +static int ethtool_set_ufo(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_value edata; + + if (!dev->ethtool_ops->set_ufo) + return -EOPNOTSUPP; + if (copy_from_user(&edata, useraddr, sizeof(edata))) + return -EFAULT; + if (edata.data && !(dev->features & NETIF_F_SG)) + return -EINVAL; + if (edata.data && !(dev->features & NETIF_F_HW_CSUM)) + return -EINVAL; + return dev->ethtool_ops->set_ufo(dev, edata.data); +} + static int ethtool_self_test(struct net_device *dev, char __user *useraddr) { struct ethtool_test test; @@ -854,6 +899,12 @@ int dev_ethtool(struct ifreq *ifr) case ETHTOOL_GPERMADDR: rc = ethtool_get_perm_addr(dev, useraddr); break; + case ETHTOOL_GUFO: + rc = ethtool_get_ufo(dev, useraddr); + break; + case ETHTOOL_SUFO: + rc = ethtool_set_ufo(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } @@ -882,3 +933,5 @@ EXPORT_SYMBOL(ethtool_op_set_sg); EXPORT_SYMBOL(ethtool_op_set_tso); EXPORT_SYMBOL(ethtool_op_set_tx_csum); EXPORT_SYMBOL(ethtool_op_set_tx_hw_csum); +EXPORT_SYMBOL(ethtool_op_set_ufo); +EXPORT_SYMBOL(ethtool_op_get_ufo); diff --git a/net/core/filter.c b/net/core/filter.c index 079c2edff78..2841bfce29d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -116,8 +116,6 @@ int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int flen) A /= X; continue; case BPF_ALU|BPF_DIV|BPF_K: - if (fentry->k == 0) - return 0; A /= fentry->k; continue; case BPF_ALU|BPF_AND|BPF_X: @@ -320,6 +318,10 @@ int sk_chk_filter(struct sock_filter *filter, int flen) } } + /* check for division by zero -Kris Katterjohn 2005-10-30 */ + if (ftest->code == (BPF_ALU|BPF_DIV|BPF_K) && ftest->k == 0) + return -EINVAL; + /* check that memory operations use valid addresses. */ if (ftest->k >= BPF_MEMWORDS) { /* but it might not be a memory operation... */ diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 39fc55edf69..e68700f950a 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -61,7 +61,9 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev); void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); static struct neigh_table *neigh_tables; +#ifdef CONFIG_PROC_FS static struct file_operations neigh_stat_seq_fops; +#endif /* Neighbour hash table buckets are protected with rwlock tbl->lock. @@ -173,39 +175,10 @@ static void pneigh_queue_purge(struct sk_buff_head *list) } } -void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev) -{ - int i; - - write_lock_bh(&tbl->lock); - - for (i=0; i <= tbl->hash_mask; i++) { - struct neighbour *n, **np; - - np = &tbl->hash_buckets[i]; - while ((n = *np) != NULL) { - if (dev && n->dev != dev) { - np = &n->next; - continue; - } - *np = n->next; - write_lock_bh(&n->lock); - n->dead = 1; - neigh_del_timer(n); - write_unlock_bh(&n->lock); - neigh_release(n); - } - } - - write_unlock_bh(&tbl->lock); -} - -int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev) +static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev) { int i; - write_lock_bh(&tbl->lock); - for (i = 0; i <= tbl->hash_mask; i++) { struct neighbour *n, **np = &tbl->hash_buckets[i]; @@ -241,7 +214,19 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev) neigh_release(n); } } +} + +void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev) +{ + write_lock_bh(&tbl->lock); + neigh_flush_dev(tbl, dev); + write_unlock_bh(&tbl->lock); +} +int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev) +{ + write_lock_bh(&tbl->lock); + neigh_flush_dev(tbl, dev); pneigh_ifdown(tbl, dev); write_unlock_bh(&tbl->lock); @@ -725,6 +710,14 @@ static __inline__ int neigh_max_probes(struct neighbour *n) p->ucast_probes + p->app_probes + p->mcast_probes); } +static inline void neigh_add_timer(struct neighbour *n, unsigned long when) +{ + if (unlikely(mod_timer(&n->timer, when))) { + printk("NEIGH: BUG, double timer add, state is %x\n", + n->nud_state); + dump_stack(); + } +} /* Called when a timer expires for a neighbour entry. */ @@ -806,11 +799,10 @@ static void neigh_timer_handler(unsigned long arg) } if (neigh->nud_state & NUD_IN_TIMER) { - neigh_hold(neigh); if (time_before(next, jiffies + HZ/2)) next = jiffies + HZ/2; - neigh->timer.expires = next; - add_timer(&neigh->timer); + if (!mod_timer(&neigh->timer, next)) + neigh_hold(neigh); } if (neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) { struct sk_buff *skb = skb_peek(&neigh->arp_queue); @@ -852,8 +844,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) atomic_set(&neigh->probes, neigh->parms->ucast_probes); neigh->nud_state = NUD_INCOMPLETE; neigh_hold(neigh); - neigh->timer.expires = now + 1; - add_timer(&neigh->timer); + neigh_add_timer(neigh, now + 1); } else { neigh->nud_state = NUD_FAILED; write_unlock_bh(&neigh->lock); @@ -866,8 +857,8 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) NEIGH_PRINTK2("neigh %p is delayed.\n", neigh); neigh_hold(neigh); neigh->nud_state = NUD_DELAY; - neigh->timer.expires = jiffies + neigh->parms->delay_probe_time; - add_timer(&neigh->timer); + neigh_add_timer(neigh, + jiffies + neigh->parms->delay_probe_time); } if (neigh->nud_state == NUD_INCOMPLETE) { @@ -1013,10 +1004,10 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh_del_timer(neigh); if (new & NUD_IN_TIMER) { neigh_hold(neigh); - neigh->timer.expires = jiffies + + neigh_add_timer(neigh, (jiffies + ((new & NUD_REACHABLE) ? - neigh->parms->reachable_time : 0); - add_timer(&neigh->timer); + neigh->parms->reachable_time : + 0))); } neigh->nud_state = new; } @@ -1634,12 +1625,9 @@ static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, memset(&ndst, 0, sizeof(ndst)); - for (cpu = 0; cpu < NR_CPUS; cpu++) { + for_each_cpu(cpu) { struct neigh_statistics *st; - if (!cpu_possible(cpu)) - continue; - st = per_cpu_ptr(tbl->stats, cpu); ndst.ndts_allocs += st->allocs; ndst.ndts_destroys += st->destroys; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 5265dfd6992..49424a42a2c 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -101,16 +101,20 @@ void netpoll_queue(struct sk_buff *skb) static int checksum_udp(struct sk_buff *skb, struct udphdr *uh, unsigned short ulen, u32 saddr, u32 daddr) { - if (uh->check == 0) + unsigned int psum; + + if (uh->check == 0 || skb->ip_summed == CHECKSUM_UNNECESSARY) return 0; - if (skb->ip_summed == CHECKSUM_HW) - return csum_tcpudp_magic( - saddr, daddr, ulen, IPPROTO_UDP, skb->csum); + psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0); + + if (skb->ip_summed == CHECKSUM_HW && + !(u16)csum_fold(csum_add(psum, skb->csum))) + return 0; - skb->csum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0); + skb->csum = psum; - return csum_fold(skb_checksum(skb, 0, skb->len, skb->csum)); + return __skb_checksum_complete(skb); } /* @@ -489,7 +493,7 @@ int __netpoll_rx(struct sk_buff *skb) if (ulen != len) goto out; - if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr) < 0) + if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr)) goto out; if (np->local_ip && np->local_ip != ntohl(iph->daddr)) goto out; @@ -703,7 +707,7 @@ int netpoll_setup(struct netpoll *np) if (!np->local_ip) { rcu_read_lock(); - in_dev = __in_dev_get(ndev); + in_dev = __in_dev_get_rcu(ndev); if (!in_dev || !in_dev->ifa_list) { rcu_read_unlock(); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index ef430b1e8e4..7fc3e9e28c3 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -75,7 +75,7 @@ * By design there should only be *one* "controlling" process. In practice * multiple write accesses gives unpredictable result. Understood by "write" * to /proc gives result code thats should be read be the "writer". - * For pratical use this should be no problem. + * For practical use this should be no problem. * * Note when adding devices to a specific CPU there good idea to also assign * /proc/irq/XX/smp_affinity so TX-interrupts gets bound to the same CPU. @@ -96,7 +96,7 @@ * New xmit() return, do_div and misc clean up by Stephen Hemminger * <shemminger@osdl.org> 040923 * - * Rany Dunlap fixed u64 printk compiler waring + * Randy Dunlap fixed u64 printk compiler waring * * Remove FCS from BW calculation. Lennert Buytenhek <buytenh@wantstofly.org> * New time handling. Lennert Buytenhek <buytenh@wantstofly.org> 041213 @@ -137,6 +137,7 @@ #include <linux/ipv6.h> #include <linux/udp.h> #include <linux/proc_fs.h> +#include <linux/seq_file.h> #include <linux/wait.h> #include <net/checksum.h> #include <net/ipv6.h> @@ -151,7 +152,7 @@ #include <asm/timex.h> -#define VERSION "pktgen v2.62: Packet Generator for packet performance testing.\n" +#define VERSION "pktgen v2.63: Packet Generator for packet performance testing.\n" /* #define PG_DEBUG(a) a */ #define PG_DEBUG(a) @@ -177,8 +178,8 @@ #define T_REMDEV (1<<3) /* Remove all devs */ /* Locks */ -#define thread_lock() spin_lock(&_thread_lock) -#define thread_unlock() spin_unlock(&_thread_lock) +#define thread_lock() down(&pktgen_sem) +#define thread_unlock() up(&pktgen_sem) /* If lock -- can be removed after some work */ #define if_lock(t) spin_lock(&(t->if_lock)); @@ -187,6 +188,8 @@ /* Used to help with determining the pkts on receive */ #define PKTGEN_MAGIC 0xbe9be955 #define PG_PROC_DIR "pktgen" +#define PGCTRL "pgctrl" +static struct proc_dir_entry *pg_proc_dir = NULL; #define MAX_CFLOWS 65536 @@ -202,11 +205,8 @@ struct pktgen_dev { * Try to keep frequent/infrequent used vars. separated. */ - char ifname[32]; - struct proc_dir_entry *proc_ent; + char ifname[IFNAMSIZ]; char result[512]; - /* proc file names */ - char fname[80]; struct pktgen_thread* pg_thread; /* the owner */ struct pktgen_dev *next; /* Used for chaining in the thread's run-queue */ @@ -244,7 +244,7 @@ struct pktgen_dev { __u32 seq_num; int clone_skb; /* Use multiple SKBs during packet gen. If this number - * is greater than 1, then that many coppies of the same + * is greater than 1, then that many copies of the same * packet will be sent before a new packet is allocated. * For instance, if you want to send 1024 identical packets * before creating a new packet, set clone_skb to 1024. @@ -330,8 +330,6 @@ struct pktgen_thread { struct pktgen_dev *if_list; /* All device here */ struct pktgen_thread* next; char name[32]; - char fname[128]; /* name of proc file */ - struct proc_dir_entry *proc_ent; char result[512]; u32 max_before_softirq; /* We'll call do_softirq to prevent starvation. */ @@ -396,7 +394,7 @@ static inline s64 divremdi3(s64 x, s64 y, int type) /* End of hacks to deal with 64-bit math on x86 */ -/** Convert to miliseconds */ +/** Convert to milliseconds */ static inline __u64 tv_to_ms(const struct timeval* tv) { __u64 ms = tv->tv_usec / 1000; @@ -425,7 +423,7 @@ static inline __u64 pg_div64(__u64 n, __u64 base) { __u64 tmp = n; /* - * How do we know if the architectrure we are running on + * How do we know if the architecture we are running on * supports division with 64 bit base? * */ @@ -473,16 +471,6 @@ static inline __u64 tv_diff(const struct timeval* a, const struct timeval* b) static char version[] __initdata = VERSION; -static ssize_t proc_pgctrl_read(struct file* file, char __user * buf, size_t count, loff_t *ppos); -static ssize_t proc_pgctrl_write(struct file* file, const char __user * buf, size_t count, loff_t *ppos); -static int proc_if_read(char *buf , char **start, off_t offset, int len, int *eof, void *data); - -static int proc_thread_read(char *buf , char **start, off_t offset, int len, int *eof, void *data); -static int proc_if_write(struct file *file, const char __user *user_buffer, unsigned long count, void *data); -static int proc_thread_write(struct file *file, const char __user *user_buffer, unsigned long count, void *data); -static int create_proc_dir(void); -static int remove_proc_dir(void); - static int pktgen_remove_device(struct pktgen_thread* t, struct pktgen_dev *i); static int pktgen_add_device(struct pktgen_thread* t, const char* ifname); static struct pktgen_thread* pktgen_find_thread(const char* name); @@ -503,83 +491,41 @@ static int pg_delay_d = 0; static int pg_clone_skb_d = 0; static int debug = 0; -static DEFINE_SPINLOCK(_thread_lock); +static DECLARE_MUTEX(pktgen_sem); static struct pktgen_thread *pktgen_threads = NULL; -static char module_fname[128]; -static struct proc_dir_entry *module_proc_ent = NULL; - static struct notifier_block pktgen_notifier_block = { .notifier_call = pktgen_device_event, }; -static struct file_operations pktgen_fops = { - .read = proc_pgctrl_read, - .write = proc_pgctrl_write, - /* .ioctl = pktgen_ioctl, later maybe */ -}; - /* * /proc handling functions * */ -static struct proc_dir_entry *pg_proc_dir = NULL; -static int proc_pgctrl_read_eof=0; - -static ssize_t proc_pgctrl_read(struct file* file, char __user * buf, - size_t count, loff_t *ppos) +static int pgctrl_show(struct seq_file *seq, void *v) { - char data[200]; - int len = 0; - - if(proc_pgctrl_read_eof) { - proc_pgctrl_read_eof=0; - len = 0; - goto out; - } - - sprintf(data, "%s", VERSION); - - len = strlen(data); - - if(len > count) { - len =-EFAULT; - goto out; - } - - if (copy_to_user(buf, data, len)) { - len =-EFAULT; - goto out; - } - - *ppos += len; - proc_pgctrl_read_eof=1; /* EOF next call */ - - out: - return len; + seq_puts(seq, VERSION); + return 0; } -static ssize_t proc_pgctrl_write(struct file* file,const char __user * buf, - size_t count, loff_t *ppos) +static ssize_t pgctrl_write(struct file* file,const char __user * buf, + size_t count, loff_t *ppos) { - char *data = NULL; int err = 0; + char data[128]; if (!capable(CAP_NET_ADMIN)){ err = -EPERM; goto out; } - data = (void*)vmalloc ((unsigned int)count); + if (count > sizeof(data)) + count = sizeof(data); - if(!data) { - err = -ENOMEM; - goto out; - } if (copy_from_user(data, buf, count)) { - err =-EFAULT; - goto out_free; + err = -EFAULT; + goto out; } data[count-1] = 0; /* Make string */ @@ -594,31 +540,40 @@ static ssize_t proc_pgctrl_write(struct file* file,const char __user * buf, err = count; - out_free: - vfree (data); out: return err; } -static int proc_if_read(char *buf , char **start, off_t offset, - int len, int *eof, void *data) +static int pgctrl_open(struct inode *inode, struct file *file) +{ + return single_open(file, pgctrl_show, PDE(inode)->data); +} + +static struct file_operations pktgen_fops = { + .owner = THIS_MODULE, + .open = pgctrl_open, + .read = seq_read, + .llseek = seq_lseek, + .write = pgctrl_write, + .release = single_release, +}; + +static int pktgen_if_show(struct seq_file *seq, void *v) { - char *p; int i; - struct pktgen_dev *pkt_dev = (struct pktgen_dev*)(data); + struct pktgen_dev *pkt_dev = seq->private; __u64 sa; __u64 stopped; __u64 now = getCurUs(); - p = buf; - p += sprintf(p, "Params: count %llu min_pkt_size: %u max_pkt_size: %u\n", - (unsigned long long) pkt_dev->count, - pkt_dev->min_pkt_size, pkt_dev->max_pkt_size); + seq_printf(seq, "Params: count %llu min_pkt_size: %u max_pkt_size: %u\n", + (unsigned long long) pkt_dev->count, + pkt_dev->min_pkt_size, pkt_dev->max_pkt_size); - p += sprintf(p, " frags: %d delay: %u clone_skb: %d ifname: %s\n", - pkt_dev->nfrags, 1000*pkt_dev->delay_us+pkt_dev->delay_ns, pkt_dev->clone_skb, pkt_dev->ifname); + seq_printf(seq, " frags: %d delay: %u clone_skb: %d ifname: %s\n", + pkt_dev->nfrags, 1000*pkt_dev->delay_us+pkt_dev->delay_ns, pkt_dev->clone_skb, pkt_dev->ifname); - p += sprintf(p, " flows: %u flowlen: %u\n", pkt_dev->cflows, pkt_dev->lflow); + seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows, pkt_dev->lflow); if(pkt_dev->flags & F_IPV6) { @@ -626,19 +581,19 @@ static int proc_if_read(char *buf , char **start, off_t offset, fmt_ip6(b1, pkt_dev->in6_saddr.s6_addr); fmt_ip6(b2, pkt_dev->min_in6_saddr.s6_addr); fmt_ip6(b3, pkt_dev->max_in6_saddr.s6_addr); - p += sprintf(p, " saddr: %s min_saddr: %s max_saddr: %s\n", b1, b2, b3); + seq_printf(seq, " saddr: %s min_saddr: %s max_saddr: %s\n", b1, b2, b3); fmt_ip6(b1, pkt_dev->in6_daddr.s6_addr); fmt_ip6(b2, pkt_dev->min_in6_daddr.s6_addr); fmt_ip6(b3, pkt_dev->max_in6_daddr.s6_addr); - p += sprintf(p, " daddr: %s min_daddr: %s max_daddr: %s\n", b1, b2, b3); + seq_printf(seq, " daddr: %s min_daddr: %s max_daddr: %s\n", b1, b2, b3); } else - p += sprintf(p, " dst_min: %s dst_max: %s\n src_min: %s src_max: %s\n", - pkt_dev->dst_min, pkt_dev->dst_max, pkt_dev->src_min, pkt_dev->src_max); + seq_printf(seq," dst_min: %s dst_max: %s\n src_min: %s src_max: %s\n", + pkt_dev->dst_min, pkt_dev->dst_max, pkt_dev->src_min, pkt_dev->src_max); - p += sprintf(p, " src_mac: "); + seq_puts(seq, " src_mac: "); if ((pkt_dev->src_mac[0] == 0) && (pkt_dev->src_mac[1] == 0) && @@ -648,89 +603,89 @@ static int proc_if_read(char *buf , char **start, off_t offset, (pkt_dev->src_mac[5] == 0)) for (i = 0; i < 6; i++) - p += sprintf(p, "%02X%s", pkt_dev->odev->dev_addr[i], i == 5 ? " " : ":"); + seq_printf(seq, "%02X%s", pkt_dev->odev->dev_addr[i], i == 5 ? " " : ":"); else for (i = 0; i < 6; i++) - p += sprintf(p, "%02X%s", pkt_dev->src_mac[i], i == 5 ? " " : ":"); + seq_printf(seq, "%02X%s", pkt_dev->src_mac[i], i == 5 ? " " : ":"); - p += sprintf(p, "dst_mac: "); + seq_printf(seq, "dst_mac: "); for (i = 0; i < 6; i++) - p += sprintf(p, "%02X%s", pkt_dev->dst_mac[i], i == 5 ? "\n" : ":"); + seq_printf(seq, "%02X%s", pkt_dev->dst_mac[i], i == 5 ? "\n" : ":"); - p += sprintf(p, " udp_src_min: %d udp_src_max: %d udp_dst_min: %d udp_dst_max: %d\n", - pkt_dev->udp_src_min, pkt_dev->udp_src_max, pkt_dev->udp_dst_min, - pkt_dev->udp_dst_max); + seq_printf(seq, " udp_src_min: %d udp_src_max: %d udp_dst_min: %d udp_dst_max: %d\n", + pkt_dev->udp_src_min, pkt_dev->udp_src_max, pkt_dev->udp_dst_min, + pkt_dev->udp_dst_max); - p += sprintf(p, " src_mac_count: %d dst_mac_count: %d \n Flags: ", - pkt_dev->src_mac_count, pkt_dev->dst_mac_count); + seq_printf(seq, " src_mac_count: %d dst_mac_count: %d \n Flags: ", + pkt_dev->src_mac_count, pkt_dev->dst_mac_count); if (pkt_dev->flags & F_IPV6) - p += sprintf(p, "IPV6 "); + seq_printf(seq, "IPV6 "); if (pkt_dev->flags & F_IPSRC_RND) - p += sprintf(p, "IPSRC_RND "); + seq_printf(seq, "IPSRC_RND "); if (pkt_dev->flags & F_IPDST_RND) - p += sprintf(p, "IPDST_RND "); + seq_printf(seq, "IPDST_RND "); if (pkt_dev->flags & F_TXSIZE_RND) - p += sprintf(p, "TXSIZE_RND "); + seq_printf(seq, "TXSIZE_RND "); if (pkt_dev->flags & F_UDPSRC_RND) - p += sprintf(p, "UDPSRC_RND "); + seq_printf(seq, "UDPSRC_RND "); if (pkt_dev->flags & F_UDPDST_RND) - p += sprintf(p, "UDPDST_RND "); + seq_printf(seq, "UDPDST_RND "); if (pkt_dev->flags & F_MACSRC_RND) - p += sprintf(p, "MACSRC_RND "); + seq_printf(seq, "MACSRC_RND "); if (pkt_dev->flags & F_MACDST_RND) - p += sprintf(p, "MACDST_RND "); + seq_printf(seq, "MACDST_RND "); - p += sprintf(p, "\n"); + seq_puts(seq, "\n"); sa = pkt_dev->started_at; stopped = pkt_dev->stopped_at; if (pkt_dev->running) stopped = now; /* not really stopped, more like last-running-at */ - p += sprintf(p, "Current:\n pkts-sofar: %llu errors: %llu\n started: %lluus stopped: %lluus idle: %lluus\n", - (unsigned long long) pkt_dev->sofar, - (unsigned long long) pkt_dev->errors, - (unsigned long long) sa, - (unsigned long long) stopped, - (unsigned long long) pkt_dev->idle_acc); + seq_printf(seq, "Current:\n pkts-sofar: %llu errors: %llu\n started: %lluus stopped: %lluus idle: %lluus\n", + (unsigned long long) pkt_dev->sofar, + (unsigned long long) pkt_dev->errors, + (unsigned long long) sa, + (unsigned long long) stopped, + (unsigned long long) pkt_dev->idle_acc); - p += sprintf(p, " seq_num: %d cur_dst_mac_offset: %d cur_src_mac_offset: %d\n", - pkt_dev->seq_num, pkt_dev->cur_dst_mac_offset, pkt_dev->cur_src_mac_offset); + seq_printf(seq, " seq_num: %d cur_dst_mac_offset: %d cur_src_mac_offset: %d\n", + pkt_dev->seq_num, pkt_dev->cur_dst_mac_offset, + pkt_dev->cur_src_mac_offset); if(pkt_dev->flags & F_IPV6) { char b1[128], b2[128]; fmt_ip6(b1, pkt_dev->cur_in6_daddr.s6_addr); fmt_ip6(b2, pkt_dev->cur_in6_saddr.s6_addr); - p += sprintf(p, " cur_saddr: %s cur_daddr: %s\n", b2, b1); + seq_printf(seq, " cur_saddr: %s cur_daddr: %s\n", b2, b1); } else - p += sprintf(p, " cur_saddr: 0x%x cur_daddr: 0x%x\n", - pkt_dev->cur_saddr, pkt_dev->cur_daddr); + seq_printf(seq, " cur_saddr: 0x%x cur_daddr: 0x%x\n", + pkt_dev->cur_saddr, pkt_dev->cur_daddr); - p += sprintf(p, " cur_udp_dst: %d cur_udp_src: %d\n", - pkt_dev->cur_udp_dst, pkt_dev->cur_udp_src); + seq_printf(seq, " cur_udp_dst: %d cur_udp_src: %d\n", + pkt_dev->cur_udp_dst, pkt_dev->cur_udp_src); - p += sprintf(p, " flows: %u\n", pkt_dev->nflows); + seq_printf(seq, " flows: %u\n", pkt_dev->nflows); if (pkt_dev->result[0]) - p += sprintf(p, "Result: %s\n", pkt_dev->result); + seq_printf(seq, "Result: %s\n", pkt_dev->result); else - p += sprintf(p, "Result: Idle\n"); - *eof = 1; + seq_printf(seq, "Result: Idle\n"); - return p - buf; + return 0; } @@ -802,13 +757,14 @@ done_str: return i; } -static int proc_if_write(struct file *file, const char __user *user_buffer, - unsigned long count, void *data) +static ssize_t pktgen_if_write(struct file *file, const char __user *user_buffer, + size_t count, loff_t *offset) { + struct seq_file *seq = (struct seq_file *) file->private_data; + struct pktgen_dev *pkt_dev = seq->private; int i = 0, max, len; char name[16], valstr[32]; unsigned long value = 0; - struct pktgen_dev *pkt_dev = (struct pktgen_dev*)(data); char* pg_result = NULL; int tmp = 0; char buf[128]; @@ -849,7 +805,8 @@ static int proc_if_write(struct file *file, const char __user *user_buffer, if (copy_from_user(tb, user_buffer, count)) return -EFAULT; tb[count] = 0; - printk("pktgen: %s,%lu buffer -:%s:-\n", name, count, tb); + printk("pktgen: %s,%lu buffer -:%s:-\n", name, + (unsigned long) count, tb); } if (!strcmp(name, "min_pkt_size")) { @@ -1335,92 +1292,98 @@ static int proc_if_write(struct file *file, const char __user *user_buffer, return -EINVAL; } -static int proc_thread_read(char *buf , char **start, off_t offset, - int len, int *eof, void *data) +static int pktgen_if_open(struct inode *inode, struct file *file) { - char *p; - struct pktgen_thread *t = (struct pktgen_thread*)(data); - struct pktgen_dev *pkt_dev = NULL; + return single_open(file, pktgen_if_show, PDE(inode)->data); +} +static struct file_operations pktgen_if_fops = { + .owner = THIS_MODULE, + .open = pktgen_if_open, + .read = seq_read, + .llseek = seq_lseek, + .write = pktgen_if_write, + .release = single_release, +}; - if (!t) { - printk("pktgen: ERROR: could not find thread in proc_thread_read\n"); - return -EINVAL; - } +static int pktgen_thread_show(struct seq_file *seq, void *v) +{ + struct pktgen_thread *t = seq->private; + struct pktgen_dev *pkt_dev = NULL; - p = buf; - p += sprintf(p, "Name: %s max_before_softirq: %d\n", + BUG_ON(!t); + + seq_printf(seq, "Name: %s max_before_softirq: %d\n", t->name, t->max_before_softirq); - p += sprintf(p, "Running: "); + seq_printf(seq, "Running: "); if_lock(t); for(pkt_dev = t->if_list;pkt_dev; pkt_dev = pkt_dev->next) if(pkt_dev->running) - p += sprintf(p, "%s ", pkt_dev->ifname); + seq_printf(seq, "%s ", pkt_dev->ifname); - p += sprintf(p, "\nStopped: "); + seq_printf(seq, "\nStopped: "); for(pkt_dev = t->if_list;pkt_dev; pkt_dev = pkt_dev->next) if(!pkt_dev->running) - p += sprintf(p, "%s ", pkt_dev->ifname); + seq_printf(seq, "%s ", pkt_dev->ifname); if (t->result[0]) - p += sprintf(p, "\nResult: %s\n", t->result); + seq_printf(seq, "\nResult: %s\n", t->result); else - p += sprintf(p, "\nResult: NA\n"); - - *eof = 1; + seq_printf(seq, "\nResult: NA\n"); if_unlock(t); - return p - buf; + return 0; } -static int proc_thread_write(struct file *file, const char __user *user_buffer, - unsigned long count, void *data) +static ssize_t pktgen_thread_write(struct file *file, + const char __user *user_buffer, + size_t count, loff_t *offset) { + struct seq_file *seq = (struct seq_file *) file->private_data; + struct pktgen_thread *t = seq->private; int i = 0, max, len, ret; char name[40]; - struct pktgen_thread *t; char *pg_result; unsigned long value = 0; - + if (count < 1) { // sprintf(pg_result, "Wrong command format"); return -EINVAL; } - + max = count - i; len = count_trail_chars(&user_buffer[i], max); - if (len < 0) - return len; - + if (len < 0) + return len; + i += len; - + /* Read variable name */ len = strn_len(&user_buffer[i], sizeof(name) - 1); - if (len < 0) - return len; + if (len < 0) + return len; memset(name, 0, sizeof(name)); if (copy_from_user(name, &user_buffer[i], len)) return -EFAULT; i += len; - + max = count -i; len = count_trail_chars(&user_buffer[i], max); - if (len < 0) - return len; - + if (len < 0) + return len; + i += len; - if (debug) - printk("pktgen: t=%s, count=%lu\n", name, count); - + if (debug) + printk("pktgen: t=%s, count=%lu\n", name, + (unsigned long) count); - t = (struct pktgen_thread*)(data); if(!t) { printk("pktgen: ERROR: No thread\n"); ret = -EINVAL; @@ -1474,32 +1437,19 @@ static int proc_thread_write(struct file *file, const char __user *user_buffer, return ret; } -static int create_proc_dir(void) +static int pktgen_thread_open(struct inode *inode, struct file *file) { - int len; - /* does proc_dir already exists */ - len = strlen(PG_PROC_DIR); - - for (pg_proc_dir = proc_net->subdir; pg_proc_dir; pg_proc_dir=pg_proc_dir->next) { - if ((pg_proc_dir->namelen == len) && - (! memcmp(pg_proc_dir->name, PG_PROC_DIR, len))) - break; - } - - if (!pg_proc_dir) - pg_proc_dir = create_proc_entry(PG_PROC_DIR, S_IFDIR, proc_net); - - if (!pg_proc_dir) - return -ENODEV; - - return 0; + return single_open(file, pktgen_thread_show, PDE(inode)->data); } -static int remove_proc_dir(void) -{ - remove_proc_entry(PG_PROC_DIR, proc_net); - return 0; -} +static struct file_operations pktgen_thread_fops = { + .owner = THIS_MODULE, + .open = pktgen_thread_open, + .read = seq_read, + .llseek = seq_lseek, + .write = pktgen_thread_write, + .release = single_release, +}; /* Think find or remove for NN */ static struct pktgen_dev *__pktgen_NN_threads(const char* ifname, int remove) @@ -1678,13 +1628,12 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) struct in_device *in_dev; rcu_read_lock(); - in_dev = __in_dev_get(pkt_dev->odev); + in_dev = __in_dev_get_rcu(pkt_dev->odev); if (in_dev) { if (in_dev->ifa_list) { pkt_dev->saddr_min = in_dev->ifa_list->ifa_address; pkt_dev->saddr_max = pkt_dev->saddr_min; } - __in_dev_put(in_dev); } rcu_read_unlock(); } @@ -1714,7 +1663,7 @@ static void spin(struct pktgen_dev *pkt_dev, __u64 spin_until_us) start = now = getCurUs(); printk(KERN_INFO "sleeping for %d\n", (int)(spin_until_us - now)); while (now < spin_until_us) { - /* TODO: optimise sleeping behavior */ + /* TODO: optimize sleeping behavior */ if (spin_until_us - now > jiffies_to_usecs(1)+1) schedule_timeout_interruptible(1); else if (spin_until_us - now > 100) { @@ -2373,7 +2322,7 @@ static void pktgen_stop_all_threads_ifs(void) pktgen_stop(t); t = t->next; } - thread_unlock(); + thread_unlock(); } static int thread_is_running(struct pktgen_thread *t ) @@ -2564,10 +2513,9 @@ static void pktgen_rem_thread(struct pktgen_thread *t) struct pktgen_thread *tmp = pktgen_threads; - if (strlen(t->fname)) - remove_proc_entry(t->fname, NULL); + remove_proc_entry(t->name, pg_proc_dir); - thread_lock(); + thread_lock(); if (tmp == t) pktgen_threads = tmp->next; @@ -2837,7 +2785,7 @@ static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, const char* i if_lock(t); for(pkt_dev=t->if_list; pkt_dev; pkt_dev = pkt_dev->next ) { - if (strcmp(pkt_dev->ifname, ifname) == 0) { + if (strncmp(pkt_dev->ifname, ifname, IFNAMSIZ) == 0) { break; } } @@ -2876,74 +2824,70 @@ static int add_dev_to_thread(struct pktgen_thread *t, struct pktgen_dev *pkt_dev static int pktgen_add_device(struct pktgen_thread *t, const char* ifname) { struct pktgen_dev *pkt_dev; + struct proc_dir_entry *pe; /* We don't allow a device to be on several threads */ - if( (pkt_dev = __pktgen_NN_threads(ifname, FIND)) == NULL) { - - pkt_dev = kmalloc(sizeof(struct pktgen_dev), GFP_KERNEL); - if (!pkt_dev) - return -ENOMEM; + pkt_dev = __pktgen_NN_threads(ifname, FIND); + if (pkt_dev) { + printk("pktgen: ERROR: interface already used.\n"); + return -EBUSY; + } - memset(pkt_dev, 0, sizeof(struct pktgen_dev)); + pkt_dev = kzalloc(sizeof(struct pktgen_dev), GFP_KERNEL); + if (!pkt_dev) + return -ENOMEM; - pkt_dev->flows = vmalloc(MAX_CFLOWS*sizeof(struct flow_state)); - if (pkt_dev->flows == NULL) { - kfree(pkt_dev); - return -ENOMEM; - } - memset(pkt_dev->flows, 0, MAX_CFLOWS*sizeof(struct flow_state)); - - pkt_dev->min_pkt_size = ETH_ZLEN; - pkt_dev->max_pkt_size = ETH_ZLEN; - pkt_dev->nfrags = 0; - pkt_dev->clone_skb = pg_clone_skb_d; - pkt_dev->delay_us = pg_delay_d / 1000; - pkt_dev->delay_ns = pg_delay_d % 1000; - pkt_dev->count = pg_count_d; - pkt_dev->sofar = 0; - pkt_dev->udp_src_min = 9; /* sink port */ - pkt_dev->udp_src_max = 9; - pkt_dev->udp_dst_min = 9; - pkt_dev->udp_dst_max = 9; - - strncpy(pkt_dev->ifname, ifname, 31); - sprintf(pkt_dev->fname, "net/%s/%s", PG_PROC_DIR, ifname); - - if (! pktgen_setup_dev(pkt_dev)) { - printk("pktgen: ERROR: pktgen_setup_dev failed.\n"); - if (pkt_dev->flows) - vfree(pkt_dev->flows); - kfree(pkt_dev); - return -ENODEV; - } + pkt_dev->flows = vmalloc(MAX_CFLOWS*sizeof(struct flow_state)); + if (pkt_dev->flows == NULL) { + kfree(pkt_dev); + return -ENOMEM; + } + memset(pkt_dev->flows, 0, MAX_CFLOWS*sizeof(struct flow_state)); - pkt_dev->proc_ent = create_proc_entry(pkt_dev->fname, 0600, NULL); - if (!pkt_dev->proc_ent) { - printk("pktgen: cannot create %s procfs entry.\n", pkt_dev->fname); - if (pkt_dev->flows) - vfree(pkt_dev->flows); - kfree(pkt_dev); - return -EINVAL; - } - pkt_dev->proc_ent->read_proc = proc_if_read; - pkt_dev->proc_ent->write_proc = proc_if_write; - pkt_dev->proc_ent->data = (void*)(pkt_dev); - pkt_dev->proc_ent->owner = THIS_MODULE; + pkt_dev->min_pkt_size = ETH_ZLEN; + pkt_dev->max_pkt_size = ETH_ZLEN; + pkt_dev->nfrags = 0; + pkt_dev->clone_skb = pg_clone_skb_d; + pkt_dev->delay_us = pg_delay_d / 1000; + pkt_dev->delay_ns = pg_delay_d % 1000; + pkt_dev->count = pg_count_d; + pkt_dev->sofar = 0; + pkt_dev->udp_src_min = 9; /* sink port */ + pkt_dev->udp_src_max = 9; + pkt_dev->udp_dst_min = 9; + pkt_dev->udp_dst_max = 9; + + strncpy(pkt_dev->ifname, ifname, IFNAMSIZ); + + if (! pktgen_setup_dev(pkt_dev)) { + printk("pktgen: ERROR: pktgen_setup_dev failed.\n"); + if (pkt_dev->flows) + vfree(pkt_dev->flows); + kfree(pkt_dev); + return -ENODEV; + } + + pe = create_proc_entry(ifname, 0600, pg_proc_dir); + if (!pe) { + printk("pktgen: cannot create %s/%s procfs entry.\n", + PG_PROC_DIR, ifname); + if (pkt_dev->flows) + vfree(pkt_dev->flows); + kfree(pkt_dev); + return -EINVAL; + } + pe->proc_fops = &pktgen_if_fops; + pe->data = pkt_dev; - return add_dev_to_thread(t, pkt_dev); - } - else { - printk("pktgen: ERROR: interface already used.\n"); - return -EBUSY; - } + return add_dev_to_thread(t, pkt_dev); } static struct pktgen_thread *pktgen_find_thread(const char* name) { struct pktgen_thread *t = NULL; - thread_lock(); + thread_lock(); t = pktgen_threads; while (t) { @@ -2959,6 +2903,7 @@ static struct pktgen_thread *pktgen_find_thread(const char* name) static int pktgen_create_thread(const char* name, int cpu) { struct pktgen_thread *t = NULL; + struct proc_dir_entry *pe; if (strlen(name) > 31) { printk("pktgen: ERROR: Thread name cannot be more than 31 characters.\n"); @@ -2970,28 +2915,26 @@ static int pktgen_create_thread(const char* name, int cpu) return -EINVAL; } - t = (struct pktgen_thread*)(kmalloc(sizeof(struct pktgen_thread), GFP_KERNEL)); + t = kzalloc(sizeof(struct pktgen_thread), GFP_KERNEL); if (!t) { printk("pktgen: ERROR: out of memory, can't create new thread.\n"); return -ENOMEM; } - memset(t, 0, sizeof(struct pktgen_thread)); strcpy(t->name, name); spin_lock_init(&t->if_lock); t->cpu = cpu; - sprintf(t->fname, "net/%s/%s", PG_PROC_DIR, t->name); - t->proc_ent = create_proc_entry(t->fname, 0600, NULL); - if (!t->proc_ent) { - printk("pktgen: cannot create %s procfs entry.\n", t->fname); + pe = create_proc_entry(t->name, 0600, pg_proc_dir); + if (!pe) { + printk("pktgen: cannot create %s/%s procfs entry.\n", + PG_PROC_DIR, t->name); kfree(t); return -EINVAL; } - t->proc_ent->read_proc = proc_thread_read; - t->proc_ent->write_proc = proc_thread_write; - t->proc_ent->data = (void*)(t); - t->proc_ent->owner = THIS_MODULE; + + pe->proc_fops = &pktgen_thread_fops; + pe->data = t; t->next = pktgen_threads; pktgen_threads = t; @@ -3046,8 +2989,7 @@ static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *pkt_ /* Clean up proc file system */ - if (strlen(pkt_dev->fname)) - remove_proc_entry(pkt_dev->fname, NULL); + remove_proc_entry(pkt_dev->ifname, pg_proc_dir); if (pkt_dev->flows) vfree(pkt_dev->flows); @@ -3058,31 +3000,31 @@ static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *pkt_ static int __init pg_init(void) { int cpu; - printk(version); + struct proc_dir_entry *pe; - module_fname[0] = 0; + printk(version); - create_proc_dir(); + pg_proc_dir = proc_mkdir(PG_PROC_DIR, proc_net); + if (!pg_proc_dir) + return -ENODEV; + pg_proc_dir->owner = THIS_MODULE; - sprintf(module_fname, "net/%s/pgctrl", PG_PROC_DIR); - module_proc_ent = create_proc_entry(module_fname, 0600, NULL); - if (!module_proc_ent) { - printk("pktgen: ERROR: cannot create %s procfs entry.\n", module_fname); + pe = create_proc_entry(PGCTRL, 0600, pg_proc_dir); + if (pe == NULL) { + printk("pktgen: ERROR: cannot create %s procfs entry.\n", PGCTRL); + proc_net_remove(PG_PROC_DIR); return -EINVAL; } - module_proc_ent->proc_fops = &pktgen_fops; - module_proc_ent->data = NULL; + pe->proc_fops = &pktgen_fops; + pe->data = NULL; /* Register us to receive netdevice events */ register_netdevice_notifier(&pktgen_notifier_block); - for (cpu = 0; cpu < NR_CPUS ; cpu++) { + for_each_online_cpu(cpu) { char buf[30]; - if (!cpu_online(cpu)) - continue; - sprintf(buf, "kpktgend_%i", cpu); pktgen_create_thread(buf, cpu); } @@ -3107,10 +3049,8 @@ static void __exit pg_cleanup(void) unregister_netdevice_notifier(&pktgen_notifier_block); /* Clean up proc file system */ - - remove_proc_entry(module_fname, NULL); - - remove_proc_dir(); + remove_proc_entry(PGCTRL, pg_proc_dir); + proc_net_remove(PG_PROC_DIR); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 9bed7569ce3..8700379685e 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -49,6 +49,7 @@ #include <net/udp.h> #include <net/sock.h> #include <net/pkt_sched.h> +#include <net/netlink.h> DECLARE_MUTEX(rtnl_sem); @@ -462,11 +463,6 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) netlink_broadcast(rtnl, skb, 0, RTNLGRP_LINK, GFP_KERNEL); } -static int rtnetlink_done(struct netlink_callback *cb) -{ - return 0; -} - /* Protected by RTNL sempahore. */ static struct rtattr **rta_buf; static int rtattr_max; @@ -524,8 +520,6 @@ rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *errp) } if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { - u32 rlen; - if (link->dumpit == NULL) link = &(rtnetlink_links[PF_UNSPEC][type]); @@ -533,14 +527,11 @@ rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *errp) goto err_inval; if ((*errp = netlink_dump_start(rtnl, skb, nlh, - link->dumpit, - rtnetlink_done)) != 0) { + link->dumpit, NULL)) != 0) { return -1; } - rlen = NLMSG_ALIGN(nlh->nlmsg_len); - if (rlen > skb->len) - rlen = skb->len; - skb_pull(skb, rlen); + + netlink_queue_skip(nlh, skb); return -1; } @@ -579,75 +570,13 @@ err_inval: return -1; } -/* - * Process one packet of messages. - * Malformed skbs with wrong lengths of messages are discarded silently. - */ - -static inline int rtnetlink_rcv_skb(struct sk_buff *skb) -{ - int err; - struct nlmsghdr * nlh; - - while (skb->len >= NLMSG_SPACE(0)) { - u32 rlen; - - nlh = (struct nlmsghdr *)skb->data; - if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len) - return 0; - rlen = NLMSG_ALIGN(nlh->nlmsg_len); - if (rlen > skb->len) - rlen = skb->len; - if (rtnetlink_rcv_msg(skb, nlh, &err)) { - /* Not error, but we must interrupt processing here: - * Note, that in this case we do not pull message - * from skb, it will be processed later. - */ - if (err == 0) - return -1; - netlink_ack(skb, nlh, err); - } else if (nlh->nlmsg_flags&NLM_F_ACK) - netlink_ack(skb, nlh, 0); - skb_pull(skb, rlen); - } - - return 0; -} - -/* - * rtnetlink input queue processing routine: - * - process as much as there was in the queue upon entry. - * - feed skbs to rtnetlink_rcv_skb, until it refuse a message, - * that will occur, when a dump started. - */ - static void rtnetlink_rcv(struct sock *sk, int len) { - unsigned int qlen = skb_queue_len(&sk->sk_receive_queue); + unsigned int qlen = 0; do { - struct sk_buff *skb; - rtnl_lock(); - - if (qlen > skb_queue_len(&sk->sk_receive_queue)) - qlen = skb_queue_len(&sk->sk_receive_queue); - - for (; qlen; qlen--) { - skb = skb_dequeue(&sk->sk_receive_queue); - if (rtnetlink_rcv_skb(skb)) { - if (skb->len) - skb_queue_head(&sk->sk_receive_queue, - skb); - else { - kfree_skb(skb); - qlen--; - } - break; - } - kfree_skb(skb); - } - + netlink_run_queue(sk, &qlen, &rtnetlink_rcv_msg); up(&rtnl_sem); netdev_run_todo(); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f80a2878561..b7d13a4fff4 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -71,8 +71,6 @@ static kmem_cache_t *skbuff_head_cache __read_mostly; static kmem_cache_t *skbuff_fclone_cache __read_mostly; -struct timeval __read_mostly skb_tv_base; - /* * Keep out-of-line to prevent kernel bloat. * __builtin_return_address is not used because it is not always @@ -124,6 +122,8 @@ void skb_under_panic(struct sk_buff *skb, int sz, void *here) * __alloc_skb - allocate a network buffer * @size: size to allocate * @gfp_mask: allocation mask + * @fclone: allocate from fclone cache instead of head cache + * and allocate a cloned (child) skb * * Allocate a new &sk_buff. The returned buffer has no headroom and a * tail room of size bytes. The object has a reference count of one. @@ -132,7 +132,7 @@ void skb_under_panic(struct sk_buff *skb, int sz, void *here) * Buffers may only be allocated from interrupts using a @gfp_mask of * %GFP_ATOMIC. */ -struct sk_buff *__alloc_skb(unsigned int size, unsigned int __nocast gfp_mask, +struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, int fclone) { struct sk_buff *skb; @@ -176,6 +176,8 @@ struct sk_buff *__alloc_skb(unsigned int size, unsigned int __nocast gfp_mask, skb_shinfo(skb)->tso_size = 0; skb_shinfo(skb)->tso_segs = 0; skb_shinfo(skb)->frag_list = NULL; + skb_shinfo(skb)->ufo_size = 0; + skb_shinfo(skb)->ip6_frag_id = 0; out: return skb; nodata: @@ -200,7 +202,7 @@ nodata: */ struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp, unsigned int size, - unsigned int __nocast gfp_mask) + gfp_t gfp_mask) { struct sk_buff *skb; u8 *data; @@ -334,6 +336,9 @@ void __kfree_skb(struct sk_buff *skb) } #ifdef CONFIG_NETFILTER nf_conntrack_put(skb->nfct); +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) + nf_conntrack_put_reasm(skb->nfct_reasm); +#endif #ifdef CONFIG_BRIDGE_NETFILTER nf_bridge_put(skb->nf_bridge); #endif @@ -363,7 +368,7 @@ void __kfree_skb(struct sk_buff *skb) * %GFP_ATOMIC. */ -struct sk_buff *skb_clone(struct sk_buff *skb, unsigned int __nocast gfp_mask) +struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff *n; @@ -412,6 +417,17 @@ struct sk_buff *skb_clone(struct sk_buff *skb, unsigned int __nocast gfp_mask) C(nfct); nf_conntrack_get(skb->nfct); C(nfctinfo); +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) + C(nfct_reasm); + nf_conntrack_get_reasm(skb->nfct_reasm); +#endif +#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) + C(ipvs_property); +#endif +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) + C(nfct_reasm); + nf_conntrack_get_reasm(skb->nfct_reasm); +#endif #ifdef CONFIG_BRIDGE_NETFILTER C(nf_bridge); nf_bridge_get(skb->nf_bridge); @@ -469,6 +485,13 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->nfct = old->nfct; nf_conntrack_get(old->nfct); new->nfctinfo = old->nfctinfo; +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) + new->nfct_reasm = old->nfct_reasm; + nf_conntrack_get_reasm(old->nfct_reasm); +#endif +#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) + new->ipvs_property = old->ipvs_property; +#endif #ifdef CONFIG_BRIDGE_NETFILTER new->nf_bridge = old->nf_bridge; nf_bridge_get(old->nf_bridge); @@ -502,7 +525,7 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) * header is going to be modified. Use pskb_copy() instead. */ -struct sk_buff *skb_copy(const struct sk_buff *skb, unsigned int __nocast gfp_mask) +struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { int headerlen = skb->data - skb->head; /* @@ -541,7 +564,7 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, unsigned int __nocast gfp_ma * The returned buffer has a reference count of 1. */ -struct sk_buff *pskb_copy(struct sk_buff *skb, unsigned int __nocast gfp_mask) +struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) { /* * Allocate the copy buffer @@ -600,7 +623,7 @@ out: */ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, - unsigned int __nocast gfp_mask) + gfp_t gfp_mask) { int i; u8 *data; @@ -691,7 +714,7 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom) */ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, - unsigned int __nocast gfp_mask) + gfp_t gfp_mask) { /* * Allocate the copy buffer @@ -1690,6 +1713,78 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, return textsearch_find(config, state); } +/** + * skb_append_datato_frags: - append the user data to a skb + * @sk: sock structure + * @skb: skb structure to be appened with user data. + * @getfrag: call back function to be used for getting the user data + * @from: pointer to user message iov + * @length: length of the iov message + * + * Description: This procedure append the user data in the fragment part + * of the skb if any page alloc fails user this procedure returns -ENOMEM + */ +int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, + int getfrag(void *from, char *to, int offset, + 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 offset = 0; + int ret; + + 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); + + /* If alloc_page fails just return failure and caller will + * free previous allocated pages by doing kfree_skb() + */ + if (page == NULL) + return -ENOMEM; + + /* initialize the next frag */ + sk->sk_sndmsg_page = page; + sk->sk_sndmsg_off = 0; + 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; + + ret = getfrag(from, (page_address(frag->page) + + frag->page_offset + frag->size), + offset, copy, 0, skb); + if (ret < 0) + return -EFAULT; + + /* copy was successful so update the size parameters */ + sk->sk_sndmsg_off += copy; + frag->size += copy; + skb->len += copy; + skb->data_len += copy; + offset += copy; + length -= copy; + + } while (length > 0); + + return 0; +} + void __init skb_init(void) { skbuff_head_cache = kmem_cache_create("skbuff_head_cache", @@ -1708,8 +1803,6 @@ void __init skb_init(void) NULL, NULL); if (!skbuff_fclone_cache) panic("cannot create skbuff cache"); - - do_gettimeofday(&skb_tv_base); } EXPORT_SYMBOL(___pskb_trim); @@ -1743,4 +1836,4 @@ EXPORT_SYMBOL(skb_prepare_seq_read); EXPORT_SYMBOL(skb_seq_read); EXPORT_SYMBOL(skb_abort_seq_read); EXPORT_SYMBOL(skb_find_text); -EXPORT_SYMBOL(skb_tv_base); +EXPORT_SYMBOL(skb_append_datato_frags); diff --git a/net/core/sock.c b/net/core/sock.c index ac63b56e23b..13cc3be4f05 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -637,7 +637,7 @@ lenout: * @prot: struct proto associated with this new sock instance * @zero_it: if we should zero the newly allocated sock */ -struct sock *sk_alloc(int family, unsigned int __nocast priority, +struct sock *sk_alloc(int family, gfp_t priority, struct proto *prot, int zero_it) { struct sock *sk = NULL; @@ -660,16 +660,20 @@ struct sock *sk_alloc(int family, unsigned int __nocast priority, sock_lock_init(sk); } - if (security_sk_alloc(sk, family, priority)) { - if (slab != NULL) - kmem_cache_free(slab, sk); - else - kfree(sk); - sk = NULL; - } else - __module_get(prot->owner); + if (security_sk_alloc(sk, family, priority)) + goto out_free; + + if (!try_module_get(prot->owner)) + goto out_free; } return sk; + +out_free: + if (slab != NULL) + kmem_cache_free(slab, sk); + else + kfree(sk); + return NULL; } void sk_free(struct sock *sk) @@ -700,7 +704,7 @@ void sk_free(struct sock *sk) module_put(owner); } -struct sock *sk_clone(const struct sock *sk, const unsigned int __nocast priority) +struct sock *sk_clone(const struct sock *sk, const gfp_t priority) { struct sock *newsk = sk_alloc(sk->sk_family, priority, sk->sk_prot, 0); @@ -841,7 +845,7 @@ unsigned long sock_i_ino(struct sock *sk) * Allocate a skb from the socket's send buffer. */ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, - unsigned int __nocast priority) + gfp_t priority) { if (force || atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { struct sk_buff * skb = alloc_skb(size, priority); @@ -857,7 +861,7 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, * Allocate a skb from the socket's receive buffer. */ struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force, - unsigned int __nocast priority) + gfp_t priority) { if (force || atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { struct sk_buff *skb = alloc_skb(size, priority); @@ -872,7 +876,7 @@ struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force, /* * Allocate a memory block from the socket's option memory buffer. */ -void *sock_kmalloc(struct sock *sk, int size, unsigned int __nocast priority) +void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) { if ((unsigned)size <= sysctl_optmem_max && atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) { @@ -936,7 +940,7 @@ static struct sk_buff *sock_alloc_send_pskb(struct sock *sk, int noblock, int *errcode) { struct sk_buff *skb; - unsigned int gfp_mask; + gfp_t gfp_mask; long timeo; int err; @@ -1238,8 +1242,7 @@ static void sock_def_write_space(struct sock *sk) static void sock_def_destruct(struct sock *sk) { - if (sk->sk_protinfo) - kfree(sk->sk_protinfo); + kfree(sk->sk_protinfo); } void sk_send_sigurg(struct sock *sk) diff --git a/net/core/stream.c b/net/core/stream.c index ac9edfdf874..15bfd03e802 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -52,8 +52,9 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p) { struct task_struct *tsk = current; DEFINE_WAIT(wait); + int done; - while (1) { + do { if (sk->sk_err) return sock_error(sk); if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV)) @@ -65,13 +66,12 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p) prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); sk->sk_write_pending++; - if (sk_wait_event(sk, timeo_p, - !((1 << sk->sk_state) & - ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)))) - break; + done = sk_wait_event(sk, timeo_p, + !((1 << sk->sk_state) & + ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))); finish_wait(sk->sk_sleep, &wait); sk->sk_write_pending--; - } + } while (!done); return 0; } diff --git a/net/core/wireless.c b/net/core/wireless.c index d17f1583ea3..271ddb35b0b 100644 --- a/net/core/wireless.c +++ b/net/core/wireless.c @@ -455,10 +455,15 @@ static inline struct iw_statistics *get_wireless_stats(struct net_device *dev) /* Old location, field to be removed in next WE */ if(dev->get_wireless_stats) { - printk(KERN_DEBUG "%s (WE) : Driver using old /proc/net/wireless support, please fix driver !\n", - dev->name); + static int printed_message; + + if (!printed_message++) + printk(KERN_DEBUG "%s (WE) : Driver using old /proc/net/wireless support, please fix driver !\n", + dev->name); + return dev->get_wireless_stats(dev); } + /* Not found */ return (struct iw_statistics *) NULL; } |