diff options
author | Linus Torvalds <torvalds@woody.linux-foundation.org> | 2007-10-11 19:40:14 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@woody.linux-foundation.org> | 2007-10-11 19:40:14 -0700 |
commit | 038a5008b2f395c85e6e71d6ddf3c684e7c405b0 (patch) | |
tree | 4735eab577e97e5a22c3141e3f60071c8065585e /net/ipv4/route.c | |
parent | dd6d1844af33acb4edd0a40b1770d091a22c94be (diff) | |
parent | 266918303226cceac7eca38ced30f15f277bd89c (diff) |
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6
* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (867 commits)
[SKY2]: status polling loop (post merge)
[NET]: Fix NAPI completion handling in some drivers.
[TCP]: Limit processing lost_retrans loop to work-to-do cases
[TCP]: Fix lost_retrans loop vs fastpath problems
[TCP]: No need to re-count fackets_out/sacked_out at RTO
[TCP]: Extract tcp_match_queue_to_sack from sacktag code
[TCP]: Kill almost unused variable pcount from sacktag
[TCP]: Fix mark_head_lost to ignore R-bit when trying to mark L
[TCP]: Add bytes_acked (ABC) clearing to FRTO too
[IPv6]: Update setsockopt(IPV6_MULTICAST_IF) to support RFC 3493, try2
[NETFILTER]: x_tables: add missing ip6t_modulename aliases
[NETFILTER]: nf_conntrack_tcp: fix connection reopening
[QETH]: fix qeth_main.c
[NETLINK]: fib_frontend build fixes
[IPv6]: Export userland ND options through netlink (RDNSS support)
[9P]: build fix with !CONFIG_SYSCTL
[NET]: Fix dev_put() and dev_hold() comments
[NET]: make netlink user -> kernel interface synchronious
[NET]: unify netlink kernel socket recognition
[NET]: cleanup 3rd argument in netlink_sendskb
...
Fix up conflicts manually in Documentation/feature-removal-schedule.txt
and my new least favourite crap, the "mod_devicetable" support in the
files include/linux/mod_devicetable.h and scripts/mod/file2alias.c.
(The latter files seem to be explicitly _designed_ to get conflicts when
different subsystems work with them - that have an absolutely horrid
lack of subsystem separation!)
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'net/ipv4/route.c')
-rw-r--r-- | net/ipv4/route.c | 82 |
1 files changed, 31 insertions, 51 deletions
diff --git a/net/ipv4/route.c b/net/ipv4/route.c index c7ca94bd152c..21b12de9e653 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -81,6 +81,7 @@ #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/init.h> +#include <linux/workqueue.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> @@ -91,6 +92,7 @@ #include <linux/jhash.h> #include <linux/rcupdate.h> #include <linux/times.h> +#include <net/net_namespace.h> #include <net/protocol.h> #include <net/ip.h> #include <net/route.h> @@ -135,7 +137,8 @@ static unsigned long rt_deadline; #define RTprint(a...) printk(KERN_DEBUG a) static struct timer_list rt_flush_timer; -static struct timer_list rt_periodic_timer; +static void rt_check_expire(struct work_struct *work); +static DECLARE_DELAYED_WORK(expires_work, rt_check_expire); static struct timer_list rt_secret_timer; /* @@ -243,7 +246,7 @@ static spinlock_t *rt_hash_locks; static struct rt_hash_bucket *rt_hash_table; static unsigned rt_hash_mask; -static int rt_hash_log; +static unsigned int rt_hash_log; static unsigned int rt_hash_rnd; static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); @@ -372,23 +375,8 @@ static const struct seq_operations rt_cache_seq_ops = { static int rt_cache_seq_open(struct inode *inode, struct file *file) { - struct seq_file *seq; - int rc = -ENOMEM; - struct rt_cache_iter_state *s; - - s = kzalloc(sizeof(*s), GFP_KERNEL); - if (!s) - goto out; - rc = seq_open(file, &rt_cache_seq_ops); - if (rc) - goto out_kfree; - seq = file->private_data; - seq->private = s; -out: - return rc; -out_kfree: - kfree(s); - goto out; + return seq_open_private(file, &rt_cache_seq_ops, + sizeof(struct rt_cache_iter_state)); } static const struct file_operations rt_cache_seq_fops = { @@ -571,33 +559,32 @@ static inline int compare_keys(struct flowi *fl1, struct flowi *fl2) (fl1->iif ^ fl2->iif)) == 0; } -/* This runs via a timer and thus is always in BH context. */ -static void rt_check_expire(unsigned long dummy) +static void rt_check_expire(struct work_struct *work) { static unsigned int rover; unsigned int i = rover, goal; struct rtable *rth, **rthp; - unsigned long now = jiffies; u64 mult; mult = ((u64)ip_rt_gc_interval) << rt_hash_log; if (ip_rt_gc_timeout > 1) do_div(mult, ip_rt_gc_timeout); goal = (unsigned int)mult; - if (goal > rt_hash_mask) goal = rt_hash_mask + 1; + if (goal > rt_hash_mask) + goal = rt_hash_mask + 1; for (; goal > 0; goal--) { unsigned long tmo = ip_rt_gc_timeout; i = (i + 1) & rt_hash_mask; rthp = &rt_hash_table[i].chain; - if (*rthp == 0) + if (*rthp == NULL) continue; - spin_lock(rt_hash_lock_addr(i)); + spin_lock_bh(rt_hash_lock_addr(i)); while ((rth = *rthp) != NULL) { if (rth->u.dst.expires) { /* Entry is expired even if it is in use */ - if (time_before_eq(now, rth->u.dst.expires)) { + if (time_before_eq(jiffies, rth->u.dst.expires)) { tmo >>= 1; rthp = &rth->u.dst.rt_next; continue; @@ -612,14 +599,10 @@ static void rt_check_expire(unsigned long dummy) *rthp = rth->u.dst.rt_next; rt_free(rth); } - spin_unlock(rt_hash_lock_addr(i)); - - /* Fallback loop breaker. */ - if (time_after(jiffies, now)) - break; + spin_unlock_bh(rt_hash_lock_addr(i)); } rover = i; - mod_timer(&rt_periodic_timer, jiffies + ip_rt_gc_interval); + schedule_delayed_work(&expires_work, ip_rt_gc_interval); } /* This can run from both BH and non-BH contexts, the latter @@ -1404,8 +1387,8 @@ static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, { struct rtable *rt = (struct rtable *) dst; struct in_device *idev = rt->idev; - if (dev != &loopback_dev && idev && idev->dev == dev) { - struct in_device *loopback_idev = in_dev_get(&loopback_dev); + if (dev != init_net.loopback_dev && idev && idev->dev == dev) { + struct in_device *loopback_idev = in_dev_get(init_net.loopback_dev); if (loopback_idev) { rt->idev = loopback_idev; in_dev_put(idev); @@ -1557,7 +1540,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, #endif rth->rt_iif = rth->fl.iif = dev->ifindex; - rth->u.dst.dev = &loopback_dev; + rth->u.dst.dev = init_net.loopback_dev; dev_hold(rth->u.dst.dev); rth->idev = in_dev_get(rth->u.dst.dev); rth->fl.oif = 0; @@ -1814,7 +1797,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (res.type == RTN_LOCAL) { int result; result = fib_validate_source(saddr, daddr, tos, - loopback_dev.ifindex, + init_net.loopback_dev->ifindex, dev, &spec_dst, &itag); if (result < 0) goto martian_source; @@ -1881,7 +1864,7 @@ local_input: #endif rth->rt_iif = rth->fl.iif = dev->ifindex; - rth->u.dst.dev = &loopback_dev; + rth->u.dst.dev = init_net.loopback_dev; dev_hold(rth->u.dst.dev); rth->idev = in_dev_get(rth->u.dst.dev); rth->rt_gateway = daddr; @@ -2151,7 +2134,7 @@ static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp) RT_SCOPE_UNIVERSE), } }, .mark = oldflp->mark, - .iif = loopback_dev.ifindex, + .iif = init_net.loopback_dev->ifindex, .oif = oldflp->oif }; struct fib_result res; unsigned flags = 0; @@ -2212,7 +2195,7 @@ static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp) if (oldflp->oif) { - dev_out = dev_get_by_index(oldflp->oif); + dev_out = dev_get_by_index(&init_net, oldflp->oif); err = -ENODEV; if (dev_out == NULL) goto out; @@ -2245,9 +2228,9 @@ static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp) fl.fl4_dst = fl.fl4_src = htonl(INADDR_LOOPBACK); if (dev_out) dev_put(dev_out); - dev_out = &loopback_dev; + dev_out = init_net.loopback_dev; dev_hold(dev_out); - fl.oif = loopback_dev.ifindex; + fl.oif = init_net.loopback_dev->ifindex; res.type = RTN_LOCAL; flags |= RTCF_LOCAL; goto make_route; @@ -2292,7 +2275,7 @@ static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp) fl.fl4_src = fl.fl4_dst; if (dev_out) dev_put(dev_out); - dev_out = &loopback_dev; + dev_out = init_net.loopback_dev; dev_hold(dev_out); fl.oif = dev_out->ifindex; if (res.fi) @@ -2591,7 +2574,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void if (iif) { struct net_device *dev; - dev = __dev_get_by_index(iif); + dev = __dev_get_by_index(&init_net, iif); if (dev == NULL) { err = -ENODEV; goto errout_free; @@ -2992,17 +2975,14 @@ int __init ip_rt_init(void) init_timer(&rt_flush_timer); rt_flush_timer.function = rt_run_flush; - init_timer(&rt_periodic_timer); - rt_periodic_timer.function = rt_check_expire; init_timer(&rt_secret_timer); rt_secret_timer.function = rt_secret_rebuild; /* All the timers, started at system startup tend to synchronize. Perturb it a bit. */ - rt_periodic_timer.expires = jiffies + net_random() % ip_rt_gc_interval + - ip_rt_gc_interval; - add_timer(&rt_periodic_timer); + schedule_delayed_work(&expires_work, + net_random() % ip_rt_gc_interval + ip_rt_gc_interval); rt_secret_timer.expires = jiffies + net_random() % ip_rt_secret_interval + ip_rt_secret_interval; @@ -3011,15 +2991,15 @@ int __init ip_rt_init(void) #ifdef CONFIG_PROC_FS { struct proc_dir_entry *rtstat_pde = NULL; /* keep gcc happy */ - if (!proc_net_fops_create("rt_cache", S_IRUGO, &rt_cache_seq_fops) || + if (!proc_net_fops_create(&init_net, "rt_cache", S_IRUGO, &rt_cache_seq_fops) || !(rtstat_pde = create_proc_entry("rt_cache", S_IRUGO, - proc_net_stat))) { + init_net.proc_net_stat))) { return -ENOMEM; } rtstat_pde->proc_fops = &rt_cpu_seq_fops; } #ifdef CONFIG_NET_CLS_ROUTE - create_proc_read_entry("rt_acct", 0, proc_net, ip_rt_acct_read, NULL); + create_proc_read_entry("rt_acct", 0, init_net.proc_net, ip_rt_acct_read, NULL); #endif #endif #ifdef CONFIG_XFRM |