aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/route.c
Commit message (Collapse)AuthorAge
...
* xfrm: Handle blackhole route creation via afinfo.David S. Miller2011-03-01
| | | | | | | That way we don't have to potentially do this in every xfrm_lookup() caller. Signed-off-by: David S. Miller <davem@davemloft.net>
* xfrm: Kill XFRM_LOOKUP_WAIT flag.David S. Miller2011-03-01
| | | | | | This can be determined from the flow flags instead. Signed-off-by: David S. Miller <davem@davemloft.net>
* ipv4: Kill can_sleep arg to ip_route_output_flow()David S. Miller2011-03-01
| | | | | | This boolean state is now available in the flow flags. Signed-off-by: David S. Miller <davem@davemloft.net>
* ipv4: Make final arg to ip_route_output_flow to be boolean "can_sleep"David S. Miller2011-03-01
| | | | | | Since that is what the current vague "flags" argument means. Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge branch 'master' of ↵David S. Miller2011-02-19
|\ | | | | | | | | | | | | | | | | master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 Conflicts: Documentation/feature-removal-schedule.txt drivers/net/e1000e/netdev.c net/xfrm/xfrm_policy.c
| * net: provide default_advmss() methods to blackhole dst_opsEric Dumazet2011-02-18
| | | | | | | | | | | | | | | | | | | | Commit 0dbaee3b37e118a (net: Abstract default ADVMSS behind an accessor.) introduced a possible crash in tcp_connect_init(), when dst->default_advmss() is called from dst_metric_advmss() Reported-by: George Spelvin <linux@horizon.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ipv4: Use const'ify fib_result deep in the route call chains.David S. Miller2011-02-17
| | | | | | | | | | | | | | | | The only troublesome bit here is __mkroute_output which wants to override res->fi and res->type, compute those in local variables instead. Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: Add initial_ref arg to dst_alloc().David S. Miller2011-02-17
| | | | | | | | | | | | | | | | | | | | This allows avoiding multiple writes to the initial __refcnt. The most simplest cases of wanting an initial reference of "1" in ipv4 and ipv6 have been converted, the rest have been left along and kept at the existing "0". Signed-off-by: David S. Miller <davem@davemloft.net>
* | ipv4: Consolidate ipv4 dst allocation logic.David S. Miller2011-02-17
| | | | | | | | | | | | | | This also allows us to combine all the dst->flags settings and avoid read/modify/write sequences to this struct member. Signed-off-by: David S. Miller <davem@davemloft.net>
* | ipv4: Move rcu_read_{lock,unlock}() into ip_route_output_slow().David S. Miller2011-02-17
| | | | | | | | | | | | Simplifies tail of __ip_route_output_key(). Signed-off-by: David S. Miller <davem@davemloft.net>
* | ipv4: Simplify output route creation call sequence.David S. Miller2011-02-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | There's a lot of redundancy and unnecessary stack frames in the output route creation path. 1) Make __mkroute_output() return error pointers. 2) Eliminate ip_mkroute_output() entirely, made possible by #1. 3) Call __mkroute_output() directly and handling the returning error pointers in ip_route_output_slow(). Signed-off-by: David S. Miller <davem@davemloft.net>
* | ipv4: Cache learned redirect information in inetpeer.David S. Miller2011-02-15
| | | | | | | | | | | | | | | | | | | | Note that we do not generate the redirect netevent any longer, because we don't create a new cached route. Instead, once the new neighbour is bound to the cached route, we emit a neigh update event instead. Signed-off-by: David S. Miller <davem@davemloft.net>
* | ipv4: Cache learned PMTU information in inetpeer.David S. Miller2011-02-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The general idea is that if we learn new PMTU information, we bump the peer genid. This triggers the dst_ops->check() code to validate and if necessary propagate the new PMTU value into the metrics. Learned PMTU information self-expires. This means that it is not necessary to kill a cached route entry just because the PMTU information is too old. As a consequence: 1) When the path appears unreachable (dst_ops->link_failure or dst_ops->negative_advice) we unwind the PMTU state if it is out of date, instead of killing the cached route. A redirected route will still be invalidated in these situations. 2) rt_check_expire(), rt_worker_func(), et al. are no longer necessary at all. Signed-off-by: David S. Miller <davem@davemloft.net>
* | inet: Create a mechanism for upward inetpeer propagation into routes.David S. Miller2011-02-10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If we didn't have a routing cache, we would not be able to properly propagate certain kinds of dynamic path attributes, for example PMTU information and redirects. The reason is that if we didn't have a routing cache, then there would be no way to lookup all of the active cached routes hanging off of sockets, tunnels, IPSEC bundles, etc. Consider the case where we created a cached route, but no inetpeer entry existed and also we were not asked to pre-COW the route metrics and therefore did not force the creation a new inetpeer entry. If we later get a PMTU message, or a redirect, and store this information in a new inetpeer entry, there is no way to teach that cached route about the newly existing inetpeer entry. The facilities implemented here handle this problem. First we create a generation ID. When we create a cached route of any kind, we remember the generation ID at the time of attachment. Any time we force-create an inetpeer entry in response to new path information, we bump that generation ID. The dst_ops->check() callback is where the knowledge of this event is propagated. If the global generation ID does not equal the one stored in the cached route, and the cached route has not attached to an inetpeer yet, we look it up and attach if one is found. Now that we've updated the cached route's information, we update the route's generation ID too. This clears the way for implementing PMTU and redirects directly in the inetpeer cache. There is absolutely no need to consult cached route information in order to maintain this information. At this point nothing bumps the inetpeer genids, that comes in the later changes which handle PMTUs and redirects using inetpeers. Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: Kill NETEVENT_PMTU_UPDATE.David S. Miller2011-02-08
| | | | | | | | | | | | | | Nobody actually does anything in response to the event, so just kill it off. Signed-off-by: David S. Miller <davem@davemloft.net>
* | inetpeer: Move ICMP rate limiting state into inet_peer entries.David S. Miller2011-02-04
| | | | | | | | | | | | | | | | | | | | Like metrics, the ICMP rate limiting bits are cached state about a destination. So move it into the inet_peer entries. If an inet_peer cannot be bound (the reason is memory allocation failure or similar), the policy is to allow. Signed-off-by: David S. Miller <davem@davemloft.net>
* | ipv4: Don't miss existing cached metrics in new routes.David S. Miller2011-02-04
| | | | | | | | | | | | | | | | | | | | | | Always lookup to see if we have an existing inetpeer entry for a route. Let FLOWI_FLAG_PRECOW_METRICS merely influence the "create" argument to rt_bind_peer(). Also, call rt_bind_peer() unconditionally since it is not possible for rt->peer to be non-NULL at this point. Signed-off-by: David S. Miller <davem@davemloft.net>
* | Merge branch 'master' of ↵David S. Miller2011-02-04
|\| | | | | | | master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
| * net: Add default_mtu() methods to blackhole dst_opsRoland Dreier2011-01-31
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When an IPSEC SA is still being set up, __xfrm_lookup() will return -EREMOTE and so ip_route_output_flow() will return a blackhole route. This can happen in a sndmsg call, and after d33e455337ea ("net: Abstract default MTU metric calculation behind an accessor.") this leads to a crash in ip_append_data() because the blackhole dst_ops have no default_mtu() method and so dst_mtu() calls a NULL pointer. Fix this by adding default_mtu() methods (that simply return 0, matching the old behavior) to the blackhole dst_ops. The IPv4 part of this patch fixes a crash that I saw when using an IPSEC VPN; the IPv6 part is untested because I don't have an IPv6 VPN, but it looks to be needed as well. Signed-off-by: Roland Dreier <roland@purestorage.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ipv4: Consolidate all default route selection implementations.David S. Miller2011-01-31
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Both fib_trie and fib_hash have a local implementation of fib_table_select_default(). This is completely unnecessary code duplication. Since we now remember the fib_table and the head of the fib alias list of the default route, we can implement one single generic version of this routine. Looking at the fib_hash implementation you may get the impression that it's possible for there to be multiple top-level routes in the table for the default route. The truth is, it isn't, the insert code will only allow one entry to exist in the zero prefix hash table, because all keys evaluate to zero and all keys in a hash table must be unique. Signed-off-by: David S. Miller <davem@davemloft.net>
* | ipv4: If fib metrics are default, no need to grab ref to FIB info.David S. Miller2011-01-28
| | | | | | | | | | | | | | | | The fib metric memory in this case is static in the kernel image, so we don't need to reference count it since it's never going to go away on us. Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: Pre-COW metrics for TCP.David S. Miller2011-01-28
| | | | | | | | | | | | | | | | | | | | | | | | TCP is going to record metrics for the connection, so pre-COW the route metrics at route cache entry creation time. This avoids several atomic operations that have to occur if we COW the metrics after the entry reaches global visibility. Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: Store ipv4/ipv6 COW'd metrics in inetpeer cache.David S. Miller2011-01-27
| | | | | | | | | | | | | | | | | | | | Please note that the IPSEC dst entry metrics keep using the generic metrics COW'ing mechanism using kmalloc/kfree. This gives the IPSEC routes an opportunity to use metrics which are unique to their encapsulated paths. Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: Implement read-only protection and COW'ing of metrics.David S. Miller2011-01-26
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Routing metrics are now copy-on-write. Initially a route entry points it's metrics at a read-only location. If a routing table entry exists, it will point there. Else it will point at the all zero metric place-holder called 'dst_default_metrics'. The writeability state of the metrics is stored in the low bits of the metrics pointer, we have two bits left to spare if we want to store more states. For the initial implementation, COW is implemented simply via kmalloc. However future enhancements will change this to place the writable metrics somewhere else, in order to increase sharing. Very likely this "somewhere else" will be the inetpeer cache. Note also that this means that metrics updates may transiently fail if we cannot COW the metrics successfully. But even by itself, this patch should decrease memory usage and increase cache locality especially for routing workloads. In those cases the read-only metric copies stay in place and never get written to. TCP workloads where metrics get updated, and those rare cases where PMTU triggers occur, will take a very slight performance hit. But that hit will be alleviated when the long-term writable metrics move to a more sharable location. Since the metrics storage went from a u32 array of RTAX_MAX entries to what is essentially a pointer, some retooling of the dst_entry layout was necessary. Most importantly, we need to preserve the alignment of the reference count so that it doesn't share cache lines with the read-mostly state, as per Eric Dumazet's alignment assertion checks. The only non-trivial bit here is the move of the 'flags' member into the writeable cacheline. This is OK since we are always accessing the flags around the same moment when we made a modification to the reference count. Signed-off-by: David S. Miller <davem@davemloft.net>
* | Merge branch 'master' of git://1984.lsi.us.es/net-next-2.6Patrick McHardy2011-01-14
|\| | | | | | | | | | | | | Conflicts: net/ipv4/route.c Signed-off-by: Patrick McHardy <kaber@trash.net>
| * Merge branch 'master' of ↵David S. Miller2011-01-04
| |\ | | | | | | | | | master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
| | * ipv4/route.c: respect prefsrc for local routesJoel Sing2011-01-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The preferred source address is currently ignored for local routes, which results in all local connections having a src address that is the same as the local dst address. Fix this by respecting the preferred source address when it is provided for local routes. This bug can be demonstrated as follows: # ifconfig dummy0 192.168.0.1 # ip route show table local | grep local.*dummy0 local 192.168.0.1 dev dummy0 proto kernel scope host src 192.168.0.1 # ip route change table local local 192.168.0.1 dev dummy0 \ proto kernel scope host src 127.0.0.1 # ip route show table local | grep local.*dummy0 local 192.168.0.1 dev dummy0 proto kernel scope host src 127.0.0.1 We now establish a local connection and verify the source IP address selection: # nc -l 192.168.0.1 3128 & # nc 192.168.0.1 3128 & # netstat -ant | grep 192.168.0.1:3128.*EST tcp 0 0 192.168.0.1:3128 192.168.0.1:33228 ESTABLISHED tcp 0 0 192.168.0.1:33228 192.168.0.1:3128 ESTABLISHED Signed-off-by: Joel Sing <jsing@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | Merge branch 'master' of ↵David S. Miller2010-12-27
| |\| | | | | | | | | | | | | | | | | | | master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 Conflicts: net/ipv4/fib_frontend.c
| | * ipv4: dont create routes on down devicesEric Dumazet2010-12-25
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In ip_route_output_slow(), instead of allowing a route to be created on a not UPed device, report -ENETUNREACH immediately. # ip tunnel add mode ipip remote 10.16.0.164 local 10.16.0.72 dev eth0 # (Note : tunl1 is down) # ping -I tunl1 10.1.2.3 PING 10.1.2.3 (10.1.2.3) from 192.168.18.5 tunl1: 56(84) bytes of data. (nothing) # ./a.out tunl1 # ip tunnel del tunl1 Message from syslogd@shelby at Dec 22 10:12:08 ... kernel: unregister_netdevice: waiting for tunl1 to become free. Usage count = 3 After patch: # ping -I tunl1 10.1.2.3 connect: Network is unreachable Reported-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Reviewed-by: Octavian Purdila <opurdila@ixiacom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | ipv4: Flush per-ns routing cache more sanely.David S. Miller2010-12-20
| | | | | | | | | | | | | | | | | | | | | | | | Flush the routing cache only of entries that match the network namespace in which the purge event occurred. Signed-off-by: David S. Miller <davem@davemloft.net> Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
| * | net: Abstract default MTU metric calculation behind an accessor.David S. Miller2010-12-14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Like RTAX_ADVMSS, make the default calculation go through a dst_ops method rather than caching the computation in the routing cache entries. Now dst metrics are pretty much left as-is when new entries are created, thus optimizing metric sharing becomes a real possibility. Signed-off-by: David S. Miller <davem@davemloft.net>
| * | net: Abstract default ADVMSS behind an accessor.David S. Miller2010-12-13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Make all RTAX_ADVMSS metric accesses go through a new helper function, dst_metric_advmss(). Leave the actual default metric as "zero" in the real metric slot, and compute the actual default value dynamically via a new dst_ops AF specific callback. For stacked IPSEC routes, we use the advmss of the path which preserves existing behavior. Unlike ipv4/ipv6, DecNET ties the advmss to the mtu and thus updates advmss on pmtu updates. This inconsistency in advmss handling results in more raw metric accesses than I wish we ended up with. Signed-off-by: David S. Miller <davem@davemloft.net>
| * | ipv4: Don't pre-seed hoplimit metric.David S. Miller2010-12-13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Always go through a new ip4_dst_hoplimit() helper, just like ipv6. This allowed several simplifications: 1) The interim dst_metric_hoplimit() can go as it's no longer userd. 2) The sysctl_ip_default_ttl entry no longer needs to use ipv4_doint_and_flush, since the sysctl is not cached in routing cache metrics any longer. 3) ipv4_doint_and_flush no longer needs to be exported and therefore can be marked static. When ipv4_doint_and_flush_strategy was removed some time ago, the external declaration in ip.h was mistakenly left around so kill that off too. We have to move the sysctl_ip_default_ttl declaration into ipv4's route cache definition header net/route.h, because currently net/ip.h (where the declaration lives now) has a back dependency on net/route.h Signed-off-by: David S. Miller <davem@davemloft.net>
| * | net: Abstract RTAX_HOPLIMIT metric accesses behind helper.David S. Miller2010-12-13
| | | | | | | | | | | | Signed-off-by: David S. Miller <davem@davemloft.net>
| * | net: Abstract away all dst_entry metrics accesses.David S. Miller2010-12-09
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Use helper functions to hide all direct accesses, especially writes, to dst_entry metrics values. This will allow us to: 1) More easily change how the metrics are stored. 2) Implement COW for metrics. In particular this will help us put metrics into the inetpeer cache if that is what we end up doing. We can make the _metrics member a pointer instead of an array, initially have it point at the read-only metrics in the FIB, and then on the first set grab an inetpeer entry and point the _metrics member there. Signed-off-by: David S. Miller <davem@davemloft.net> Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
| * | inetpeer: Make inet_getpeer() take an inet_peer_adress_t pointer.David S. Miller2010-11-30
| | | | | | | | | | | | | | | | | | And make an inet_getpeer_v4() helper, update callers. Signed-off-by: David S. Miller <davem@davemloft.net>
| * | net: use the macros defined for the members of flowiChangli Gao2010-11-17
| | | | | | | | | | | | | | | | | | | | | Use the macros defined for the members of flowi to clean the code up. Signed-off-by: Changli Gao <xiaosuo@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | | netfilter: fix Kconfig dependenciesPatrick McHardy2011-01-14
|/ / | | | | | | | | | | | | | | | | | | | | | | | | Fix dependencies of netfilter realm match: it depends on NET_CLS_ROUTE, which itself depends on NET_SCHED; this dependency is missing from netfilter. Since matching on realms is also useful without having NET_SCHED enabled and the option really only controls whether the tclassid member is included in route and dst entries, rename the config option to IP_ROUTE_CLASSID and move it outside of traffic scheduling context to get rid of the NET_SCHED dependeny. Reported-by: Vladis Kletnieks <Valdis.Kletnieks@vt.edu> Signed-off-by: Patrick McHardy <kaber@trash.net>
* | ipv4: Make rt->fl.iif tests lest obscure.David S. Miller2010-11-11
| | | | | | | | | | | | | | | | | | When we test rt->fl.iif against zero, we're seeing if it's an output or an input route. Make that explicit with some helper functions. Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: get rid of rtable->idevEric Dumazet2010-11-11
|/ | | | | | | | | | | | | | | | | | | | | | | It seems idev field in struct rtable has no special purpose, but adding extra atomic ops. We hold refcounts on the device itself (using percpu data, so pretty cheap in current kernel). infiniband case is solved using dst.dev instead of idev->dev Removal of this field means routing without route cache is now using shared data, percpu data, and only potential contention is a pair of atomic ops on struct neighbour per forwarded packet. About 5% speedup on routing test. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Roland Dreier <rolandd@cisco.com> Cc: Sean Hefty <sean.hefty@intel.com> Cc: Hal Rosenstock <hal.rosenstock@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* ipv4: add __rcu annotations to routes.cEric Dumazet2010-10-27
| | | | | | | | | | | | Add __rcu annotations to : (struct dst_entry)->rt_next (struct rt_hash_bucket)->chain And use appropriate rcu primitives to reduce sparse warnings if CONFIG_SPARSE_RCU_POINTER=y Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* net: avoid RCU for NOCACHE dstEric Dumazet2010-10-20
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There is no point using RCU for dst we allocate for a very short time (used once). Change dst_release() to take DST_NOCACHE into account, but also change skb_dst_set_noref() to force a refcount increment for such dst. This is a _huge_ gain, because we dont waste memory to store xx thousand of dsts. Instead of queueing them to RCU, we can free them instantly. CPU caches can stay hot, re-using same memory blocks to hold temporary dsts. Note : remove unneeded smp_mb__before_atomic_dec(); in dst_release(), since atomic_dec_return() implies a full memory barrier. Stress test, 160.000.000 udp frames sent, IP route cache disabled (DDOS). Before: real 0m38.091s user 0m13.189s sys 7m53.018s After: real 0m29.946s user 0m12.157s sys 7m40.605s For reference, if IP route cache was enabled : real 0m32.030s user 0m10.521s sys 8m15.243s Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* IPv4: route.c: Change checks against 0xffffffff to ipv4_is_lbcast()Andy Walls2010-10-18
| | | | | | | | | Change a few checks against the hardcoded broadcast address, 0xffffffff, to ipv4_is_lbcast(). Remove some existing checks using ipv4_is_lbcast() that are now obviously superfluous. Signed-off-by: Andy Walls <awalls@md.metrocast.net> Signed-off-by: David S. Miller <davem@davemloft.net>
* net dst: use a percpu_counter to track entriesEric Dumazet2010-10-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | struct dst_ops tracks number of allocated dst in an atomic_t field, subject to high cache line contention in stress workload. Switch to a percpu_counter, to reduce number of time we need to dirty a central location. Place it on a separate cache line to avoid dirtying read only fields. Stress test : (Sending 160.000.000 UDP frames, IP route cache disabled, dual E5540 @2.53GHz, 32bit kernel, FIB_TRIE, SLUB/NUMA) Before: real 0m51.179s user 0m15.329s sys 10m15.942s After: real 0m45.570s user 0m15.525s sys 9m56.669s With a small reordering of struct neighbour fields, subject of a following patch, (to separate refcnt from other read mostly fields) real 0m41.841s user 0m15.261s sys 8m45.949s Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* ipv4: Remove leftover rcu_read_unlock calls from __mkroute_output()Dimitris Michailidis2010-10-08
| | | | | | | | | | | | Commit "fib: RCU conversion of fib_lookup()" removed rcu_read_lock() from __mkroute_output but left a couple of calls to rcu_read_unlock() in there. This causes lockdep to complain that the rcu_read_unlock() call in __ip_route_output_key causes a lock inbalance and quickly crashes the kernel. The below fixes this for me. Signed-off-by: Dimitris Michailidis <dm@chelsio.com> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* fib: RCU conversion of fib_lookup()Eric Dumazet2010-10-05
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | fib_lookup() converted to be called in RCU protected context, no reference taken and released on a contended cache line (fib_clntref) fib_table_lookup() and fib_semantic_match() get an additional parameter. struct fib_info gets an rcu_head field, and is freed after an rcu grace period. Stress test : (Sending 160.000.000 UDP frames on same neighbour, IP route cache disabled, dual E5540 @2.53GHz, 32bit kernel, FIB_HASH) (about same results for FIB_TRIE) Before patch : real 1m31.199s user 0m13.761s sys 23m24.780s After patch: real 1m5.375s user 0m14.997s sys 15m50.115s Before patch Profile : 13044.00 15.4% __ip_route_output_key vmlinux 8438.00 10.0% dst_destroy vmlinux 5983.00 7.1% fib_semantic_match vmlinux 5410.00 6.4% fib_rules_lookup vmlinux 4803.00 5.7% neigh_lookup vmlinux 4420.00 5.2% _raw_spin_lock vmlinux 3883.00 4.6% rt_set_nexthop vmlinux 3261.00 3.9% _raw_read_lock vmlinux 2794.00 3.3% fib_table_lookup vmlinux 2374.00 2.8% neigh_resolve_output vmlinux 2153.00 2.5% dst_alloc vmlinux 1502.00 1.8% _raw_read_lock_bh vmlinux 1484.00 1.8% kmem_cache_alloc vmlinux 1407.00 1.7% eth_header vmlinux 1406.00 1.7% ipv4_dst_destroy vmlinux 1298.00 1.5% __copy_from_user_ll vmlinux 1174.00 1.4% dev_queue_xmit vmlinux 1000.00 1.2% ip_output vmlinux After patch Profile : 13712.00 15.8% dst_destroy vmlinux 8548.00 9.9% __ip_route_output_key vmlinux 7017.00 8.1% neigh_lookup vmlinux 4554.00 5.3% fib_semantic_match vmlinux 4067.00 4.7% _raw_read_lock vmlinux 3491.00 4.0% dst_alloc vmlinux 3186.00 3.7% neigh_resolve_output vmlinux 3103.00 3.6% fib_table_lookup vmlinux 2098.00 2.4% _raw_read_lock_bh vmlinux 2081.00 2.4% kmem_cache_alloc vmlinux 2013.00 2.3% _raw_spin_lock vmlinux 1763.00 2.0% __copy_from_user_ll vmlinux 1763.00 2.0% ip_output vmlinux 1761.00 2.0% ipv4_dst_destroy vmlinux 1631.00 1.9% eth_header vmlinux 1440.00 1.7% _raw_read_unlock_bh vmlinux Reference results, if IP route cache is enabled : real 0m29.718s user 0m10.845s sys 7m37.341s 25213.00 29.5% __ip_route_output_key vmlinux 9011.00 10.5% dst_release vmlinux 4817.00 5.6% ip_push_pending_frames vmlinux 4232.00 5.0% ip_finish_output vmlinux 3940.00 4.6% udp_sendmsg vmlinux 3730.00 4.4% __copy_from_user_ll vmlinux 3716.00 4.4% ip_route_output_flow vmlinux 2451.00 2.9% __xfrm_lookup vmlinux 2221.00 2.6% ip_append_data vmlinux 1718.00 2.0% _raw_spin_lock_bh vmlinux 1655.00 1.9% __alloc_skb vmlinux 1572.00 1.8% sock_wfree vmlinux 1345.00 1.6% kfree vmlinux Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge branch 'master' of ↵David S. Miller2010-10-04
|\ | | | | | | | | | | | | | | master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 Conflicts: net/ipv4/Kconfig net/ipv4/tcp_timer.c
| * ipv6: add IPv6 to neighbour table overflow warningUlrich Weber2010-09-27
| | | | | | | | | | | | | | | | | | | | IPv4 and IPv6 have separate neighbour tables, so the warning messages should be distinguishable. [ Add a suitable message prefix on the ipv4 side as well -DaveM ] Signed-off-by: Ulrich Weber <uweber@astaro.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: introduce DST_NOCACHE flagEric Dumazet2010-10-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | While doing stress tests with IP route cache disabled, and multi queue devices, I noticed a very high contention on one rwlock used in neighbour code. When many cpus are trying to send frames (possibly using a high performance multiqueue device) to the same neighbour, they fight for the neigh->lock rwlock in order to call neigh_hh_init(), and fight on hh->hh_refcnt (a pair of atomic_inc/atomic_dec_and_test()) But we dont need to call neigh_hh_init() for dst that are used only once. It costs four atomic operations at least, on two contended cache lines, plus the high contention on neigh->lock rwlock. Introduce a new dst flag, DST_NOCACHE, that is set when dst was not inserted in route cache. With the stress test bench, sending 160000000 frames on one neighbour, results are : Before patch: real 2m28.406s user 0m11.781s sys 36m17.964s After patch: real 1m26.532s user 0m12.185s sys 20m3.903s Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ipv4: rcu conversion in ip_route_output_slowEric Dumazet2010-10-01
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ip_route_output_slow() is enclosed in an rcu_read_lock() protected section, so that no references are taken/released on device, thanks to __ip_dev_find() & dev_get_by_index_rcu() Tested with ip route cache disabled, and a stress test : Before patch: elapsed time : real 1m38.347s user 0m11.909s sys 23m51.501s Profile: 13788.00 22.7% ip_route_output_slow [kernel] 7875.00 13.0% dst_destroy [kernel] 3925.00 6.5% fib_semantic_match [kernel] 3144.00 5.2% fib_rules_lookup [kernel] 3061.00 5.0% dst_alloc [kernel] 2276.00 3.7% rt_set_nexthop [kernel] 1762.00 2.9% fib_table_lookup [kernel] 1538.00 2.5% _raw_read_lock [kernel] 1358.00 2.2% ip_output [kernel] After patch: real 1m28.808s user 0m13.245s sys 20m37.293s 10950.00 17.2% ip_route_output_slow [kernel] 10726.00 16.9% dst_destroy [kernel] 5170.00 8.1% fib_semantic_match [kernel] 3937.00 6.2% dst_alloc [kernel] 3635.00 5.7% rt_set_nexthop [kernel] 2900.00 4.6% fib_rules_lookup [kernel] 2240.00 3.5% fib_table_lookup [kernel] 1427.00 2.2% _raw_read_lock [kernel] 1157.00 1.8% kmem_cache_alloc [kernel] Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
generated by cgit v1.2.2 (git 2.25.0) at 2025-03-17 11:13:29 -0400