summaryrefslogtreecommitdiff
path: root/net/dccp
AgeCommit message (Collapse)Author
2016-05-02dccp: do not assume DCCP code is non preemptibleEric Dumazet
DCCP uses the generic backlog code, and this will soon be changed to not disable BH when protocol is called back. Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27net: snmp: kill STATS_BH macrosEric Dumazet
There is nothing related to BH in SNMP counters anymore, since linux-3.0. Rename helpers to use __ prefix instead of _BH prefix, for contexts where preemption is disabled. This more closely matches convention used to update percpu variables. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27net: rename NET_{ADD|INC}_STATS_BH()Eric Dumazet
Rename NET_INC_STATS_BH() to __NET_INC_STATS() and NET_ADD_STATS_BH() to __NET_ADD_STATS() Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27net: rename ICMP6_INC_STATS_BH()Eric Dumazet
Rename ICMP6_INC_STATS_BH() to __ICMP6_INC_STATS() Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27net: rename IP_INC_STATS_BH()Eric Dumazet
Rename IP_INC_STATS_BH() to __IP_INC_STATS(), to better express this is used in non preemptible context. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27net: rename ICMP_INC_STATS_BH()Eric Dumazet
Rename ICMP_INC_STATS_BH() to __ICMP_INC_STATS() Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27dccp: rename DCCP_INC_STATS_BH()Eric Dumazet
Rename DCCP_INC_STATS_BH() to __DCCP_INC_STATS() Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-07net: introduce lockdep_is_held and update various places to use itHannes Frederic Sowa
The socket is either locked if we hold the slock spin_lock for lock_sock_fast and unlock_sock_fast or we own the lock (sk_lock.owned != 0). Check for this and at the same time improve that the current thread/cpu is really holding the lock. Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-04tcp/dccp: do not touch listener sk_refcnt under synfloodEric Dumazet
When a SYNFLOOD targets a non SO_REUSEPORT listener, multiple cpus contend on sk->sk_refcnt and sk->sk_wmem_alloc changes. By letting listeners use SOCK_RCU_FREE infrastructure, we can relax TCP_LISTEN lookup rules and avoid touching sk_refcnt Note that we still use SLAB_DESTROY_BY_RCU rules for other sockets, only listeners are impacted by this change. Peak performance under SYNFLOOD is increased by ~33% : On my test machine, I could process 3.2 Mpps instead of 2.4 Mpps Most consuming functions are now skb_set_owner_w() and sock_wfree() contending on sk->sk_wmem_alloc when cooking SYNACK and freeing them. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-03-17tcp/dccp: remove obsolete WARN_ON() in icmp handlersEric Dumazet
Now SYN_RECV request sockets are installed in ehash table, an ICMP handler can find a request socket while another cpu handles an incoming packet transforming this SYN_RECV request socket into an ESTABLISHED socket. We need to remove the now obsolete WARN_ON(req->sk), since req->sk is set when a new child is created and added into listener accept queue. If this race happens, the ICMP will do nothing special. Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Ben Lazarus <blazarus@google.com> Reported-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-23Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller
Conflicts: drivers/net/phy/bcm7xxx.c drivers/net/phy/marvell.c drivers/net/vxlan.c All three conflicts were cases of simple overlapping changes. Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-18tcp/dccp: fix another race at listener dismantleEric Dumazet
Ilya reported following lockdep splat: kernel: ========================= kernel: [ BUG: held lock freed! ] kernel: 4.5.0-rc1-ceph-00026-g5e0a311 #1 Not tainted kernel: ------------------------- kernel: swapper/5/0 is freeing memory ffff880035c9d200-ffff880035c9dbff, with a lock still held there! kernel: (&(&queue->rskq_lock)->rlock){+.-...}, at: [<ffffffff816f6a88>] inet_csk_reqsk_queue_add+0x28/0xa0 kernel: 4 locks held by swapper/5/0: kernel: #0: (rcu_read_lock){......}, at: [<ffffffff8169ef6b>] netif_receive_skb_internal+0x4b/0x1f0 kernel: #1: (rcu_read_lock){......}, at: [<ffffffff816e977f>] ip_local_deliver_finish+0x3f/0x380 kernel: #2: (slock-AF_INET){+.-...}, at: [<ffffffff81685ffb>] sk_clone_lock+0x19b/0x440 kernel: #3: (&(&queue->rskq_lock)->rlock){+.-...}, at: [<ffffffff816f6a88>] inet_csk_reqsk_queue_add+0x28/0xa0 To properly fix this issue, inet_csk_reqsk_queue_add() needs to return to its callers if the child as been queued into accept queue. We also need to make sure listener is still there before calling sk->sk_data_ready(), by holding a reference on it, since the reference carried by the child can disappear as soon as the child is put on accept queue. Reported-by: Ilya Dryomov <idryomov@gmail.com> Fixes: ebb516af60e1 ("tcp/dccp: fix race at listener dismantle phase") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-11inet: refactor inet[6]_lookup functions to take skbCraig Gallek
This is a preliminary step to allow fast socket lookup of SO_REUSEPORT groups. Doing so with a BPF filter will require access to the skb in question. This change plumbs the skb (and offset to payload data) through the call stack to the listening socket lookup implementations where it will be used in a following patch. Signed-off-by: Craig Gallek <kraig@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-11inet: create IPv6-equivalent inet_hash functionCraig Gallek
In order to support fast lookups for TCP sockets with SO_REUSEPORT, the function that adds sockets to the listening hash set needs to be able to check receive address equality. Since this equality check is different for IPv4 and IPv6, we will need two different socket hashing functions. This patch adds inet6_hash identical to the existing inet_hash function and updates the appropriate references. A following patch will differentiate the two by passing different comparison functions to __inet_hash. Additionally, in order to use the IPv6 address equality function from inet6_hashtables (which is compiled as a built-in object when IPv6 is enabled) it also needs to be in a built-in object file as well. This moves ipv6_rcv_saddr_equal into inet_hashtables to accomplish this. Signed-off-by: Craig Gallek <kraig@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-03Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller
Conflicts: drivers/net/ethernet/renesas/ravb_main.c kernel/bpf/syscall.c net/ipv4/ipmr.c All three conflicts were cases of overlapping changes. Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-03ipv6: kill sk_dst_lockEric Dumazet
While testing the np->opt RCU conversion, I found that UDP/IPv6 was using a mixture of xchg() and sk_dst_lock to protect concurrent changes to sk->sk_dst_cache, leading to possible corruptions and crashes. ip6_sk_dst_lookup_flow() uses sk_dst_check() anyway, so the simplest way to fix the mess is to remove sk_dst_lock completely, as we did for IPv4. __ip6_dst_store() and ip6_dst_store() share same implementation. sk_setup_caps() being called with socket lock being held or not, we have to use sk_dst_set() instead of __sk_dst_set() Note that I had to move the "np->dst_cookie = rt6_get_cookie(rt);" in ip6_dst_store() before the sk_setup_caps(sk, dst) call. This is because ip6_dst_store() can be called from process context, without any lock held. As soon as the dst is installed in sk->sk_dst_cache, dst can be freed from another cpu doing a concurrent ip6_dst_store() Doing the dst dereference before doing the install is needed to make sure no use after free would trigger. Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-02ipv6: add complete rcu protection around np->optEric Dumazet
This patch addresses multiple problems : UDP/RAW sendmsg() need to get a stable struct ipv6_txoptions while socket is not locked : Other threads can change np->opt concurrently. Dmitry posted a syzkaller (http://github.com/google/syzkaller) program desmonstrating use-after-free. Starting with TCP/DCCP lockless listeners, tcp_v6_syn_recv_sock() and dccp_v6_request_recv_sock() also need to use RCU protection to dereference np->opt once (before calling ipv6_dup_options()) This patch adds full RCU protection to np->opt Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-01net: rename SOCK_ASYNC_NOSPACE and SOCK_ASYNC_WAITDATAEric Dumazet
This patch is a cleanup to make following patch easier to review. Goal is to move SOCK_ASYNC_NOSPACE and SOCK_ASYNC_WAITDATA from (struct socket)->flags to a (struct socket_wq)->flags to benefit from RCU protection in sock_wake_async() To ease backports, we rename both constants. Two new helpers, sk_set_bit(int nr, struct sock *sk) and sk_clear_bit(int net, struct sock *sk) are added so that following patch can change their implementation. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-30net: Generalise wq_has_sleeper helperHerbert Xu
The memory barrier in the helper wq_has_sleeper is needed by just about every user of waitqueue_active. This patch generalises it by making it take a wait_queue_head_t directly. The existing helper is renamed to skwq_has_sleeper. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-02tcp/dccp: fix ireq->pktopts raceEric Dumazet
IPv6 request sockets store a pointer to skb containing the SYN packet to be able to transfer it to full blown socket when 3WHS is done (ireq->pktopts -> np->pktoptions) As explained in commit 5e0724d027f0 ("tcp/dccp: fix hashdance race for passive sessions"), we must transfer the skb only if we won the hashdance race, if multiple cpus receive the 'ack' packet completing 3WHS at the same time. Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets") Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-01Use 64-bit timekeepingTina Ruchandani
This patch changes the use of struct timespec in dccp_probe to use struct timespec64 instead. timespec uses a 32-bit seconds field which will overflow in the year 2038 and beyond. timespec64 uses a 64-bit seconds field. Note that the correctness of the code isn't changed, since the original code only uses the timestamps to compute a small elapsed interval. This patch is part of a larger attempt to remove instances of 32-bit timekeeping structures (timespec, timeval, time_t) from the kernel so it is easier to identify where the real 2038 issues are. Signed-off-by: Tina Ruchandani <ruchandani.tina@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-23tcp/dccp: fix hashdance race for passive sessionsEric Dumazet
Multiple cpus can process duplicates of incoming ACK messages matching a SYN_RECV request socket. This is a rare event under normal operations, but definitely can happen. Only one must win the race, otherwise corruption would occur. To fix this without adding new atomic ops, we use logic in inet_ehash_nolisten() to detect the request was present in the same ehash bucket where we try to insert the new child. If request socket was not found, we have to undo the child creation. This actually removes a spin_lock()/spin_unlock() pair in reqsk_queue_unlink() for the fast path. Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets") Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-16tcp/dccp: add inet_csk_reqsk_queue_drop_and_put() helperEric Dumazet
Let's reduce the confusion about inet_csk_reqsk_queue_drop() : In many cases we also need to release reference on request socket, so add a helper to do this, reducing code size and complexity. Fixes: 4bdc3d66147b ("tcp/dccp: fix behavior of stale SYN_RECV request sockets") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-16Revert "inet: fix double request socket freeing"Eric Dumazet
This reverts commit c69736696cf3742b37d850289dc0d7ead177bb14. At the time of above commit, tcp_req_err() and dccp_req_err() were dead code, as SYN_RECV request sockets were not yet in ehash table. Real bug was fixed later in a different commit. We need to revert to not leak a refcount on request socket. inet_csk_reqsk_queue_drop_and_put() will be added in following commit to make clean inet_csk_reqsk_queue_drop() does not release the reference owned by caller. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-13tcp/dccp: fix behavior of stale SYN_RECV request socketsEric Dumazet
When a TCP/DCCP listener is closed, its pending SYN_RECV request sockets become stale, meaning 3WHS can not complete. But current behavior is wrong : incoming packets finding such stale sockets are dropped. We need instead to cleanup the request socket and perform another lookup : - Incoming ACK will give a RST answer, - SYN rtx might find another listener if available. - We expedite cleanup of request sockets and old listener socket. Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-09net/dccp: dccp_bad_service_code can be booleanYaowei Bai
This patch makes dccp_bad_service_code return bool due to these particular functions only using either one or zero as their return value. dccp_list_has_service is also been made return bool in this patchset. No functional change. Signed-off-by: Yaowei Bai <bywxiaobai@163.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-05tcp: avoid two atomic ops for syncookiesEric Dumazet
inet_reqsk_alloc() is used to allocate a temporary request in order to generate a SYNACK with a cookie. Then later, syncookie validation also uses a temporary request. These paths already took a reference on listener refcount, we can avoid a couple of atomic operations. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-03tcp/dccp: install syn_recv requests into ehash tableEric Dumazet
In this patch, we insert request sockets into TCP/DCCP regular ehash table (where ESTABLISHED and TIMEWAIT sockets are) instead of using the per listener hash table. ACK packets find SYN_RECV pseudo sockets without having to find and lock the listener. In nominal conditions, this halves pressure on listener lock. Note that this will allow for SO_REUSEPORT refinements, so that we can select a listener using cpu/numa affinities instead of the prior 'consistent hash', since only SYN packets will apply this selection logic. We will shrink listen_sock in the following patch to ease code review. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ying Cai <ycai@google.com> Cc: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-29tcp/dccp: constify syn_recv_sock() method sock argumentEric Dumazet
We'll soon no longer hold listener socket lock, these functions do not modify the socket in any way. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-29dccp: constify dccp_create_openreq_child() sock argumentEric Dumazet
socket no longer needs to be read/write Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-29dccp: use inet6_csk_route_req() helperEric Dumazet
Before changing dccp_v6_request_recv_sock() sock argument to const, we need to get rid of security_sk_classify_flow(), and it seems doable by reusing inet6_csk_route_req() helper. We need to add a proto parameter to inet6_csk_route_req(), not assume it is TCP. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-29tcp/dccp: constify send_synack and send_reset socket argumentEric Dumazet
None of these functions need to change the socket, make it const. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-26Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller
Conflicts: net/ipv4/arp.c The net/ipv4/arp.c conflict was one commit adding a new local variable while another commit was deleting one. Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25tcp/dccp: constify rtx_synack() and friendsEric Dumazet
This is done to make sure we do not change listener socket while sending SYNACK packets while socket lock is not held. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25dccp: constify dccp_make_response() socket argumentEric Dumazet
Like tcp_make_synack() the only time we might change the socket is when calling sock_wmalloc(), which is using atomic operation to update sk->sk_wmem_alloc Also use MAX_DCCP_HEADER as both IPv4/IPv6 use this value for max_header. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-21tcp/dccp: fix timewait races in timer handlingEric Dumazet
When creating a timewait socket, we need to arm the timer before allowing other cpus to find it. The signal allowing cpus to find the socket is setting tw_refcnt to non zero value. As we set tw_refcnt in __inet_twsk_hashdance(), we therefore need to call inet_twsk_schedule() first. This also means we need to remove tw_refcnt changes from inet_twsk_schedule() and let the caller handle it. Note that because we use mod_timer_pinned(), we have the guarantee the timer wont expire before we set tw_refcnt as we run in BH context. To make things more readable I introduced inet_twsk_reschedule() helper. When rearming the timer, we can use mod_timer_pending() to make sure we do not rearm a canceled timer. Note: This bug can possibly trigger if packets of a flow can hit multiple cpus. This does not normally happen, unless flow steering is broken somehow. This explains this bug was spotted ~5 months after its introduction. A similar fix is needed for SYN_RECV sockets in reqsk_queue_hash_req(), but will be provided in a separate patch for proper tracking. Fixes: 789f558cfb36 ("tcp/dccp: get rid of central timewait timer") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Ying Cai <ycai@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-15dccp: drop null test before destroy functionsJulia Lawall
Remove unneeded NULL test. The semantic patch that makes this change is as follows: (http://coccinelle.lip6.fr/) // <smpl> @@ expression x; @@ -if (x != NULL) \(kmem_cache_destroy\|mempool_destroy\|dma_pool_destroy\)(x); @@ expression x; @@ -if (x != NULL) { \(kmem_cache_destroy\|mempool_destroy\|dma_pool_destroy\)(x); x = NULL; -} // </smpl> Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-27tcp: fix recv with flags MSG_WAITALL | MSG_PEEKSabrina Dubroca
Currently, tcp_recvmsg enters a busy loop in sk_wait_data if called with flags = MSG_WAITALL | MSG_PEEK. sk_wait_data waits for sk_receive_queue not empty, but in this case, the receive queue is not empty, but does not contain any skb that we can use. Add a "last skb seen on receive queue" argument to sk_wait_data, so that it sleeps until the receive queue has new skbs. Link: https://bugzilla.kernel.org/show_bug.cgi?id=99461 Link: https://sourceware.org/bugzilla/show_bug.cgi?id=18493 Link: https://bugzilla.redhat.com/show_bug.cgi?id=1205258 Reported-by: Enrico Scholz <rh-bugzilla@ensc.de> Reported-by: Dan Searle <dan@censornet.com> Signed-off-by: Sabrina Dubroca <sd@queasysnail.net> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-15sock_diag: specify info_size per inet protocolCraig Gallek
Previously, there was no clear distinction between the inet protocols that used struct tcp_info to report information and those that didn't. This change adds a specific size attribute to the inet_diag_handler struct which defines these interfaces. This will make dispatching sock_diag get_info requests identical for all inet protocols in a following patch. Tested: ss -au Tested: ss -at Signed-off-by: Craig Gallek <kraig@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-04-24inet: fix possible panic in reqsk_queue_unlink()Eric Dumazet
[ 3897.923145] BUG: unable to handle kernel NULL pointer dereference at 0000000000000080 [ 3897.931025] IP: [<ffffffffa9f27686>] reqsk_timer_handler+0x1a6/0x243 There is a race when reqsk_timer_handler() and tcp_check_req() call inet_csk_reqsk_queue_unlink() on the same req at the same time. Before commit fa76ce7328b2 ("inet: get rid of central tcp/dccp listener timer"), listener spinlock was held and race could not happen. To solve this bug, we change reqsk_queue_unlink() to not assume req must be found, and we return a status, to conditionally release a refcount on the request sock. This also means tcp_check_req() in non fastopen case might or not consume req refcount, so tcp_v6_hnd_req() & tcp_v4_hnd_req() have to properly handle this. (Same remark for dccp_check_req() and its callers) inet_csk_reqsk_queue_drop() is now too big to be inlined, as it is called 4 times in tcp and 3 times in dccp. Fixes: fa76ce7328b2 ("inet: get rid of central tcp/dccp listener timer") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-04-13tcp/dccp: get rid of central timewait timerEric Dumazet
Using a timer wheel for timewait sockets was nice ~15 years ago when memory was expensive and machines had a single processor. This does not scale, code is ugly and source of huge latencies (Typically 30 ms have been seen, cpus spinning on death_lock spinlock.) We can afford to use an extra 64 bytes per timewait sock and spread timewait load to all cpus to have better behavior. Tested: On following test, /proc/sys/net/ipv4/tcp_tw_recycle is set to 1 on the target (lpaa24) Before patch : lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 419594 lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 437171 While test is running, we can observe 25 or even 33 ms latencies. lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 20601ms rtt min/avg/max/mdev = 0.020/0.217/25.771/1.535 ms, pipe 2 lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 20702ms rtt min/avg/max/mdev = 0.019/0.183/33.761/1.441 ms, pipe 2 After patch : About 90% increase of throughput : lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 810442 lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 800992 And latencies are kept to minimal values during this load, even if network utilization is 90% higher : lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 19991ms rtt min/avg/max/mdev = 0.023/0.064/0.360/0.042 ms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-23inet: fix double request socket freeingFan Du
Eric Hugne reported following error : I'm hitting this warning on latest net-next when i try to SSH into a machine with eth0 added to a bridge (but i think the problem is older than that) Steps to reproduce: node2 ~ # brctl addif br0 eth0 [ 223.758785] device eth0 entered promiscuous mode node2 ~ # ip link set br0 up [ 244.503614] br0: port 1(eth0) entered forwarding state [ 244.505108] br0: port 1(eth0) entered forwarding state node2 ~ # [ 251.160159] ------------[ cut here ]------------ [ 251.160831] WARNING: CPU: 0 PID: 3 at include/net/request_sock.h:102 tcp_v4_err+0x6b1/0x720() [ 251.162077] Modules linked in: [ 251.162496] CPU: 0 PID: 3 Comm: ksoftirqd/0 Not tainted 4.0.0-rc3+ #18 [ 251.163334] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 251.164078] ffffffff81a8365c ffff880038a6ba18 ffffffff8162ace4 0000000000009898 [ 251.165084] 0000000000000000 ffff880038a6ba58 ffffffff8104da85 ffff88003fa437c0 [ 251.166195] ffff88003fa437c0 ffff88003fa74e00 ffff88003fa43bb8 ffff88003fad99a0 [ 251.167203] Call Trace: [ 251.167533] [<ffffffff8162ace4>] dump_stack+0x45/0x57 [ 251.168206] [<ffffffff8104da85>] warn_slowpath_common+0x85/0xc0 [ 251.169239] [<ffffffff8104db65>] warn_slowpath_null+0x15/0x20 [ 251.170271] [<ffffffff81559d51>] tcp_v4_err+0x6b1/0x720 [ 251.171408] [<ffffffff81630d03>] ? _raw_read_lock_irq+0x3/0x10 [ 251.172589] [<ffffffff81534e20>] ? inet_del_offload+0x40/0x40 [ 251.173366] [<ffffffff81569295>] icmp_socket_deliver+0x65/0xb0 [ 251.174134] [<ffffffff815693a2>] icmp_unreach+0xc2/0x280 [ 251.174820] [<ffffffff8156a82d>] icmp_rcv+0x2bd/0x3a0 [ 251.175473] [<ffffffff81534ea2>] ip_local_deliver_finish+0x82/0x1e0 [ 251.176282] [<ffffffff815354d8>] ip_local_deliver+0x88/0x90 [ 251.177004] [<ffffffff815350f0>] ip_rcv_finish+0xf0/0x310 [ 251.177693] [<ffffffff815357bc>] ip_rcv+0x2dc/0x390 [ 251.178336] [<ffffffff814f5da3>] __netif_receive_skb_core+0x713/0xa20 [ 251.179170] [<ffffffff814f7fca>] __netif_receive_skb+0x1a/0x80 [ 251.179922] [<ffffffff814f97d4>] process_backlog+0x94/0x120 [ 251.180639] [<ffffffff814f9612>] net_rx_action+0x1e2/0x310 [ 251.181356] [<ffffffff81051267>] __do_softirq+0xa7/0x290 [ 251.182046] [<ffffffff81051469>] run_ksoftirqd+0x19/0x30 [ 251.182726] [<ffffffff8106cc23>] smpboot_thread_fn+0x153/0x1d0 [ 251.183485] [<ffffffff8106cad0>] ? SyS_setgroups+0x130/0x130 [ 251.184228] [<ffffffff8106935e>] kthread+0xee/0x110 [ 251.184871] [<ffffffff81069270>] ? kthread_create_on_node+0x1b0/0x1b0 [ 251.185690] [<ffffffff81631108>] ret_from_fork+0x58/0x90 [ 251.186385] [<ffffffff81069270>] ? kthread_create_on_node+0x1b0/0x1b0 [ 251.187216] ---[ end trace c947fc7b24e42ea1 ]--- [ 259.542268] br0: port 1(eth0) entered forwarding state Remove the double calls to reqsk_put() [edumazet] : I got confused because reqsk_timer_handler() _has_ to call reqsk_put(req) after calling inet_csk_reqsk_queue_drop(), as the timer handler holds a reference on req. Signed-off-by: Fan Du <fan.du@intel.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Erik Hugne <erik.hugne@ericsson.com> Fixes: fa76ce7328b2 ("inet: get rid of central tcp/dccp listener timer") Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-23ipv6: dccp: handle ICMP messages on DCCP_NEW_SYN_RECV request socketsEric Dumazet
dccp_v6_err() can restrict lookups to ehash table, and not to listeners. Note this patch creates the infrastructure, but this means that ICMP messages for request sockets are ignored until complete conversion. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-23ipv4: dccp: handle ICMP messages on DCCP_NEW_SYN_RECV request socketsEric Dumazet
dccp_v4_err() can restrict lookups to ehash table, and not to listeners. Note this patch creates the infrastructure, but this means that ICMP messages for request sockets are ignored until complete conversion. New dccp_req_err() helper is exported so that we can use it in IPv6 in following patch. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-23inet: remove sk_listener parameter from syn_ack_timeout()Eric Dumazet
It is not needed, and req->sk_listener points to the listener anyway. request_sock argument can be const. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-20inet: get rid of central tcp/dccp listener timerEric Dumazet
One of the major issue for TCP is the SYNACK rtx handling, done by inet_csk_reqsk_queue_prune(), fired by the keepalive timer of a TCP_LISTEN socket. This function runs for awful long times, with socket lock held, meaning that other cpus needing this lock have to spin for hundred of ms. SYNACK are sent in huge bursts, likely to cause severe drops anyway. This model was OK 15 years ago when memory was very tight. We now can afford to have a timer per request sock. Timer invocations no longer need to lock the listener, and can be run from all cpus in parallel. With following patch increasing somaxconn width to 32 bits, I tested a listener with more than 4 million active request sockets, and a steady SYNFLOOD of ~200,000 SYN per second. Host was sending ~830,000 SYNACK per second. This is ~100 times more what we could achieve before this patch. Later, we will get rid of the listener hash and use ehash instead. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-20inet: drop prev pointer handling in request sockEric Dumazet
When request sock are put in ehash table, the whole notion of having a previous request to update dl_next is pointless. Also, following patch will get rid of big purge timer, so we want to delete a request sock without holding listener lock. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-18inet: request sock should init IPv6/IPv4 addressesEric Dumazet
In order to be able to use sk_ehashfn() for request socks, we need to initialize their IPv6/IPv4 addresses. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-18ipv6: get rid of __inet6_hash()Eric Dumazet
We can now use inet_hash() and __inet_hash() instead of private functions. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-18inet: add IPv6 support to sk_ehashfn()Eric Dumazet
Intent is to converge IPv4 & IPv6 inet_hash functions to factorize code. IPv4 sockets initialize sk_rcv_saddr and sk_v6_daddr in this patch, thanks to new sk_daddr_set() and sk_rcv_saddr_set() helpers. __inet6_hash can now use sk_ehashfn() instead of a private inet6_sk_ehashfn() and will simply use __inet_hash() in a following patch. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>