summaryrefslogtreecommitdiffstats
path: root/net/sched
Commit message (Collapse)AuthorAgeFilesLines
* netem: Segment GSO packets on enqueueNeil Horman2016-05-031-2/+59
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This was recently reported to me, and reproduced on the latest net kernel, when attempting to run netperf from a host that had a netem qdisc attached to the egress interface: [ 788.073771] ---------------------[ cut here ]--------------------------- [ 788.096716] WARNING: at net/core/dev.c:2253 skb_warn_bad_offload+0xcd/0xda() [ 788.129521] bnx2: caps=(0x00000001801949b3, 0x0000000000000000) len=2962 data_len=0 gso_size=1448 gso_type=1 ip_summed=3 [ 788.182150] Modules linked in: sch_netem kvm_amd kvm crc32_pclmul ipmi_ssif ghash_clmulni_intel sp5100_tco amd64_edac_mod aesni_intel lrw gf128mul glue_helper ablk_helper edac_mce_amd cryptd pcspkr sg edac_core hpilo ipmi_si i2c_piix4 k10temp fam15h_power hpwdt ipmi_msghandler shpchp acpi_power_meter pcc_cpufreq nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c sd_mod crc_t10dif crct10dif_generic mgag200 syscopyarea sysfillrect sysimgblt i2c_algo_bit drm_kms_helper ahci ata_generic pata_acpi ttm libahci crct10dif_pclmul pata_atiixp tg3 libata crct10dif_common drm crc32c_intel ptp serio_raw bnx2 r8169 hpsa pps_core i2c_core mii dm_mirror dm_region_hash dm_log dm_mod [ 788.465294] CPU: 16 PID: 0 Comm: swapper/16 Tainted: G W ------------ 3.10.0-327.el7.x86_64 #1 [ 788.511521] Hardware name: HP ProLiant DL385p Gen8, BIOS A28 12/17/2012 [ 788.542260] ffff880437c036b8 f7afc56532a53db9 ffff880437c03670 ffffffff816351f1 [ 788.576332] ffff880437c036a8 ffffffff8107b200 ffff880633e74200 ffff880231674000 [ 788.611943] 0000000000000001 0000000000000003 0000000000000000 ffff880437c03710 [ 788.647241] Call Trace: [ 788.658817] <IRQ> [<ffffffff816351f1>] dump_stack+0x19/0x1b [ 788.686193] [<ffffffff8107b200>] warn_slowpath_common+0x70/0xb0 [ 788.713803] [<ffffffff8107b29c>] warn_slowpath_fmt+0x5c/0x80 [ 788.741314] [<ffffffff812f92f3>] ? ___ratelimit+0x93/0x100 [ 788.767018] [<ffffffff81637f49>] skb_warn_bad_offload+0xcd/0xda [ 788.796117] [<ffffffff8152950c>] skb_checksum_help+0x17c/0x190 [ 788.823392] [<ffffffffa01463a1>] netem_enqueue+0x741/0x7c0 [sch_netem] [ 788.854487] [<ffffffff8152cb58>] dev_queue_xmit+0x2a8/0x570 [ 788.880870] [<ffffffff8156ae1d>] ip_finish_output+0x53d/0x7d0 ... The problem occurs because netem is not prepared to handle GSO packets (as it uses skb_checksum_help in its enqueue path, which cannot manipulate these frames). The solution I think is to simply segment the skb in a simmilar fashion to the way we do in __dev_queue_xmit (via validate_xmit_skb), with some minor changes. When we decide to corrupt an skb, if the frame is GSO, we segment it, corrupt the first segment, and enqueue the remaining ones. tested successfully by myself on the latest net kernel, to which this applies Signed-off-by: Neil Horman <nhorman@tuxdriver.com> CC: Jamal Hadi Salim <jhs@mojatatu.com> CC: "David S. Miller" <davem@davemloft.net> CC: netem@lists.linux-foundation.org CC: eric.dumazet@gmail.com CC: stephen@networkplumber.org Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* net: sched: do not requeue a NULL skbLars Persson2016-04-141-1/+4
| | | | | | | | | | | | | | | A failure in validate_xmit_skb_list() triggered an unconditional call to dev_requeue_skb with skb=NULL. This slowly grows the queue discipline's qlen count until all traffic through the queue stops. We take the optimistic approach and continue running the queue after a failure since it is unknown if later packets also will fail in the validate path. Fixes: 55a93b3ea780 ("qdisc: validate skb without holding lock") Signed-off-by: Lars Persson <larper@axis.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* cls_bpf: reset class and reuse major in daDaniel Borkmann2016-03-181-5/+8
| | | | | | | | | | | | | | | | | | | | | | | | There are two issues with the current code. First one is that we need to set res->class to 0 in case we use non-default classid matching. This is important for the case where cls_bpf was initially set up with an optional binding to a default class with tcf_bind_filter(), where the underlying qdisc implements bind_tcf() that fills res->class and tests for it later on when doing the classification. Convention for these cases is that after tc_classify() was called, such qdiscs (atm, drr, qfq, cbq, hfsc, htb) first test class, and if 0, then they lookup based on classid. Second, there's a bug with da mode, where res->classid is only assigned a 16 bit minor, but it needs to expand to the full 32 bit major/minor combination instead, therefore we need to expand with the bound major. This is fine as classes belonging to a classful qdisc must share the same major. Fixes: 045efa82ff56 ("cls_bpf: introduce integrated actions") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* net/flower: Fix pointer castAmir Vadai2016-03-111-6/+6
| | | | | | | | | Cast pointer to unsigned long instead of u64, to fix compilation warning on 32 bit arch, spotted by 0day build. Fixes: 5b33f48 ("net/flower: Introduce hardware offload support") Signed-off-by: Amir Vadai <amir@vadai.me> Signed-off-by: David S. Miller <davem@davemloft.net>
* net/flower: Introduce hardware offload supportAmir Vadai2016-03-101-1/+63
| | | | | | | | | | | | | | | | | This patch is based on a patch made by John Fastabend. It adds support for offloading cls_flower. when NETIF_F_HW_TC is on: flags = 0 => Rule will be processed twice - by hardware, and if still relevant, by software. flags = SKIP_HW => Rull will be processed by software only If hardware fail/not capabale to apply the rule, operation will NOT fail. Filter will be processed by SW only. Acked-by: Jiri Pirko <jiri@mellanox.com> Suggested-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: Amir Vadai <amir@vadai.me> Signed-off-by: David S. Miller <davem@davemloft.net>
* net_sched: dsmark: use qdisc_dequeue_peeked()Kyeong Yoo2016-03-081-1/+1
| | | | | | | | | | | | | | | | | This fix is for dsmark similar to commit 3557619f0f6f7496ed453d4825e249 ("net_sched: prio: use qdisc_dequeue_peeked") and makes use of qdisc_dequeue_peeked() instead of direct dequeue() call. First time, wrr peeks dsmark, which will then peek into sfq. sfq dequeues an skb and it's stored in sch->gso_skb. Next time, wrr tries to dequeue from dsmark, which will call sfq dequeue directly. This results skipping the previously peeked skb. So changed dsmark dequeue to call qdisc_dequeue_peeked() instead to use peeked skb if exists. Signed-off-by: Kyeong Yoo <kyeong.yoo@alliedtelesis.co.nz> Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2016-03-081-0/+2
|\ | | | | | | | | | | | | | | Several cases of overlapping changes, as well as one instance (vxlan) of a bug fix in 'net' overlapping with code movement in 'net-next'. Signed-off-by: David S. Miller <davem@davemloft.net>
| * net: sched: fix act_ipt for LOG targetPhil Sutter2016-03-061-0/+2
| | | | | | | | | | | | | | | | | | | | | | Before calling the destroy() or target() callbacks, the family parameter field has to be initialized. Otherwise at least the LOG target will refuse to work and upon removal oops the kernel. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Phil Sutter <phil@nwl.cc> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | act_ife: fix a typo in kmemdup() parametersWANG Cong2016-03-061-2/+2
| | | | | | | | | | | | | | Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: sched: use pfifo_fast for non real queuesEric Dumazet2016-03-033-2/+4
| | | | | | | | | | | | | | | | | | | | | | Some devices declare a high number of TX queues, then set a much lower real_num_tx_queues This cause setups using fq_codel, sfq or fq as the default qdisc to consume more memory than really needed. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | sch_mqprio: Fix build with older gcc.David S. Miller2016-03-011-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | CC [M] net/sched/sch_mqprio.o net/sched/sch_mqprio.c: In function ?mqprio_init?: net/sched/sch_mqprio.c:145: error: unknown field ?tc? specified in initializer net/sched/sch_mqprio.c:145: warning: missing braces around initializer net/sched/sch_mqprio.c:145: warning: (near initialization for ?tc.<anonymous>?) make[2]: *** [net/sched/sch_mqprio.o] Error 1 make[1]: *** [net/sched] Error 2 make: *** [net] Error 2 Several people reported this, surround the unnamed union member initialization with braces to fix. Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: remove skb_sender_cpu_clear()WANG Cong2016-03-011-1/+0
| | | | | | | | | | | | | | | | | | After commit 52bd2d62ce67 ("net: better skb->sender_cpu and skb->napi_id cohabitation") skb_sender_cpu_clear() becomes empty and can be removed. Cc: Eric Dumazet <edumazet@google.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | Support to encoding decoding skb prio on IFE actionJamal Hadi Salim2016-03-013-0/+82
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Example usage: Set the skb priority using skbedit then allow it to be encoded sudo tc qdisc add dev $ETH root handle 1: prio sudo tc filter add dev $ETH parent 1: protocol ip prio 10 \ u32 match ip protocol 1 0xff flowid 1:2 \ action skbedit prio 17 \ action ife encode \ allow prio \ dst 02:15:15:15:15:15 Note: You dont need the skbedit action if you are already encoding the skb priority earlier. A zero skb priority will not be sent Alternative hard code static priority of decimal 33 (unlike skbedit) then mark of 0x12 every time the filter matches sudo $TC filter add dev $ETH parent 1: protocol ip prio 10 \ u32 match ip protocol 1 0xff flowid 1:2 \ action ife encode \ type 0xDEAD \ use prio 33 \ use mark 0x12 \ dst 02:15:15:15:15:15 Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | Support to encoding decoding skb mark on IFE actionJamal Hadi Salim2016-03-013-0/+85
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Example usage: Set the skb using skbedit then allow it to be encoded sudo tc qdisc add dev $ETH root handle 1: prio sudo tc filter add dev $ETH parent 1: protocol ip prio 10 \ u32 match ip protocol 1 0xff flowid 1:2 \ action skbedit mark 17 \ action ife encode \ allow mark \ dst 02:15:15:15:15:15 Note: You dont need the skbedit action if you are already encoding the skb mark earlier. A zero skb mark, when seen, will not be encoded. Alternative hard code static mark of 0x12 every time the filter matches sudo $TC filter add dev $ETH parent 1: protocol ip prio 10 \ u32 match ip protocol 1 0xff flowid 1:2 \ action ife encode \ type 0xDEAD \ use mark 0x12 \ dst 02:15:15:15:15:15 Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | introduce IFE actionJamal Hadi Salim2016-03-013-0/+883
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This action allows for a sending side to encapsulate arbitrary metadata which is decapsulated by the receiving end. The sender runs in encoding mode and the receiver in decode mode. Both sender and receiver must specify the same ethertype. At some point we hope to have a registered ethertype and we'll then provide a default so the user doesnt have to specify it. For now we enforce the user specify it. Lets show example usage where we encode icmp from a sender towards a receiver with an skbmark of 17; both sender and receiver use ethertype of 0xdead to interop. YYYY: Lets start with Receiver-side policy config: xxx: add an ingress qdisc sudo tc qdisc add dev $ETH ingress xxx: any packets with ethertype 0xdead will be subjected to ife decoding xxx: we then restart the classification so we can match on icmp at prio 3 sudo $TC filter add dev $ETH parent ffff: prio 2 protocol 0xdead \ u32 match u32 0 0 flowid 1:1 \ action ife decode reclassify xxx: on restarting the classification from above if it was an icmp xxx: packet, then match it here and continue to the next rule at prio 4 xxx: which will match based on skb mark of 17 sudo tc filter add dev $ETH parent ffff: prio 3 protocol ip \ u32 match ip protocol 1 0xff flowid 1:1 \ action continue xxx: match on skbmark of 0x11 (decimal 17) and accept sudo tc filter add dev $ETH parent ffff: prio 4 protocol ip \ handle 0x11 fw flowid 1:1 \ action ok xxx: Lets show the decoding policy sudo tc -s filter ls dev $ETH parent ffff: protocol 0xdead xxx: filter pref 2 u32 filter pref 2 u32 fh 800: ht divisor 1 filter pref 2 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:1 (rule hit 0 success 0) match 00000000/00000000 at 0 (success 0 ) action order 1: ife decode action reclassify index 1 ref 1 bind 1 installed 14 sec used 14 sec type: 0x0 Metadata: allow mark allow hash allow prio allow qmap Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 xxx: Observe that above lists all metadatum it can decode. Typically these submodules will already be compiled into a monolithic kernel or loaded as modules YYYY: Lets show the sender side now .. xxx: Add an egress qdisc on the sender netdev sudo tc qdisc add dev $ETH root handle 1: prio xxx: xxx: Match all icmp packets to 192.168.122.237/24, then xxx: tag the packet with skb mark of decimal 17, then xxx: Encode it with: xxx: ethertype 0xdead xxx: add skb->mark to whitelist of metadatum to send xxx: rewrite target dst MAC address to 02:15:15:15:15:15 xxx: sudo $TC filter add dev $ETH parent 1: protocol ip prio 10 u32 \ match ip dst 192.168.122.237/24 \ match ip protocol 1 0xff \ flowid 1:2 \ action skbedit mark 17 \ action ife encode \ type 0xDEAD \ allow mark \ dst 02:15:15:15:15:15 xxx: Lets show the encoding policy sudo tc -s filter ls dev $ETH parent 1: protocol ip xxx: filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:2 (rule hit 0 success 0) match c0a87aed/ffffffff at 16 (success 0 ) match 00010000/00ff0000 at 8 (success 0 ) action order 1: skbedit mark 17 index 6 ref 1 bind 1 Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 action order 2: ife encode action pipe index 3 ref 1 bind 1 dst MAC: 02:15:15:15:15:15 type: 0xDEAD Metadata: allow mark Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 xxx: test by sending ping from sender to destination Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: sched: cls_u32 add bit to specify software only rulesJohn Fastabend2016-03-011-10/+27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In the initial implementation the only way to stop a rule from being inserted into the hardware table was via the device feature flag. However this doesn't work well when working on an end host system where packets are expect to hit both the hardware and software datapaths. For example we can imagine a rule that will match an IP address and increment a field. If we install this rule in both hardware and software we may increment the field twice. To date we have only added support for the drop action so we have been able to ignore these cases. But as we extend the action support we will hit this example plus more such cases. Arguably these are not even corner cases in many working systems these cases will be common. To avoid forcing the driver to always abort (i.e. the above example) this patch adds a flag to add a rule in software only. A careful user can use this flag to build software and hardware datapaths that work together. One example we have found particularly useful is to use hardware resources to set the skb->mark on the skb when the match may be expensive to run in software but a mark lookup in a hash table is cheap. The idea here is hardware can do in one lookup what the u32 classifier may need to traverse multiple lists and hash tables to compute. The flag is only passed down on inserts. On deletion to avoid stale references in hardware we always try to remove a rule if it exists. The flags field is part of the classifier specific options. Although it is tempting to lift this into the generic structure doing this proves difficult do to how the tc netlink attributes are implemented along with how the dump/change routines are called. There is also precedence for putting seemingly generic pieces in the specific classifier options such as TCA_U32_POLICE, TCA_U32_ACT, etc. So although not ideal I've left FLAGS in the u32 options as well as it simplifies the code greatly and user space has already learned how to manage these bits ala 'tc' tool. Another thing if trying to update a rule we require the flags to be unchanged. This is to force user space, software u32 and the hardware u32 to keep in sync. Thanks to Simon Horman for catching this case. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: sched: consolidate offload decision in cls_u32John Fastabend2016-03-011-4/+4
| | | | | | | | | | | | | | | | | | | | | | | | The offload decision was originally very basic and tied to if the dev implemented the appropriate ndo op hook. The next step is to allow the user to more flexibly define if any paticular rule should be offloaded or not. In order to have this logic in one function lift the current check into a helper routine tc_should_offload(). Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | sch_dsmark: update backlog as wellWANG Cong2016-02-291-0/+3
| | | | | | | | | | | | | | | | Similarly, we need to update backlog too when we update qlen. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | sch_htb: update backlog as wellWANG Cong2016-02-291-1/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We saw qlen!=0 but backlog==0 on our production machine: qdisc htb 1: dev eth0 root refcnt 2 r2q 10 default 1 direct_packets_stat 0 ver 3.17 Sent 172680457356 bytes 222469449 pkt (dropped 0, overlimits 123575834 requeues 0) backlog 0b 72p requeues 0 The problem is we only count qlen for HTB qdisc but not backlog. We need to update backlog too when we update qlen, so that we can at least know the average packet length. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net_sched: update hierarchical backlog tooWANG Cong2016-02-2919-47/+84
| | | | | | | | | | | | | | | | | | | | | | | | When the bottom qdisc decides to, for example, drop some packet, it calls qdisc_tree_decrease_qlen() to update the queue length for all its ancestors, we need to update the backlog too to keep the stats on root qdisc accurate. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net_sched: introduce qdisc_replace() helperWANG Cong2016-02-2912-78/+12
| | | | | | | | | | | | | | | | | | Remove nearly duplicated code and prepare for the following patch. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net_sched: add network namespace support for tc actionsWANG Cong2016-02-2513-138/+699
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently tc actions are stored in a per-module hashtable, therefore are visible to all network namespaces. This is probably the last part of the tc subsystem which is not aware of netns now. This patch makes them per-netns, several tc action API's need to be adjusted for this. The tc action API code is ugly due to historical reasons, we need to refactor that code in the future. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net_sched: prepare tcf_hashinfo_destroy() for netns supportWANG Cong2016-02-251-3/+29
| | | | | | | | | | | | | | | | | | | | | | | | | | We only release the memory of the hashtable itself, not its entries inside. This is not a problem yet since we only call it in module release path, and module is refcount'ed by actions. This would be a problem after we move the per module hinfo into per netns in the latter patch. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2016-02-231-0/+1
|\ \ | |/ | | | | | | | | | | | | | | | | | | 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>
| * net_sched fix: reclassification needs to consider ether protocol changesJamal Hadi Salim2016-02-181-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | actions could change the etherproto in particular with ethernet tunnelled data. Typically such actions, after peeling the outer header, will ask for the packet to be reclassified. We then need to restart the classification with the new proto header. Example setup used to catch this: sudo tc qdisc add dev $ETH ingress sudo $TC filter add dev $ETH parent ffff: pref 1 protocol 802.1Q \ u32 match u32 0 0 flowid 1:1 \ action vlan pop reclassify Fixes: 3b3ae880266d ("net: sched: consolidate tc_classify{,_compat}") Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
* | bpf: try harder on clones when writing into skbDaniel Borkmann2016-02-212-19/+7
| | | | | | | | | | | | | | | | | | | | | | When we're dealing with clones and the area is not writeable, try harder and get a copy via pskb_expand_head(). Replace also other occurences in tc actions with the new skb_try_make_writable(). Reported-by: Ashhad Sheikh <ashhadsheikh394@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net_sched: Improve readability of filter processingJamal Hadi Salim2016-02-181-1/+1
| | | | | | | | | | | | Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: sched: add cls_u32 offload hooks for netdevsJohn Fastabend2016-02-171-2/+97
| | | | | | | | | | | | | | | | | | | | | | | | This patch allows netdev drivers to consume cls_u32 offloads via the ndo_setup_tc ndo op. This works aligns with how network drivers have been doing qdisc offloads for mqprio. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: rework setup_tc ndo op to consume general tc operandJohn Fastabend2016-02-171-3/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch updates setup_tc so we can pass additional parameters into the ndo op in a generic way. To do this we provide structured union and type flag. This lets each classifier and qdisc provide its own set of attributes without having to add new ndo ops or grow the signature of the callback. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: rework ndo tc op to consume additional qdisc handle parameterJohn Fastabend2016-02-171-2/+3
|/ | | | | | | | | | | | | | | | | | | | | | | | The ndo_setup_tc() op was added to support drivers offloading tx qdiscs however only support for mqprio was ever added. So we only ever added support for passing the number of traffic classes to the driver. This patch generalizes the ndo_setup_tc op so that a handle can be provided to indicate if the offload is for ingress or egress or potentially even child qdiscs. CC: Murali Karicheri <m-karicheri2@ti.com> CC: Shradha Shah <sshah@solarflare.com> CC: Or Gerlitz <ogerlitz@mellanox.com> CC: Ariel Elior <ariel.elior@qlogic.com> CC: Jeff Kirsher <jeffrey.t.kirsher@intel.com> CC: Bruce Allan <bruce.w.allan@intel.com> CC: Jesse Brandeburg <jesse.brandeburg@intel.com> CC: Don Skidmore <donald.c.skidmore@intel.com> Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* net_sched: drr: check for NULL pointer in drr_dequeueBernie Harris2016-01-291-0/+2
| | | | | | | | | | | | There are cases where qdisc_dequeue_peeked can return NULL, and the result is dereferenced later on in the function. Similarly to the other qdisc dequeue functions, check whether the skb pointer is NULL and if it is, goto out. Signed-off-by: Bernie Harris <bernie.harris@alliedtelesis.co.nz> Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2016-01-111-2/+8
|\ | | | | | | | | | | | | | | | | | | | | | | Conflicts: drivers/net/bonding/bond_main.c drivers/net/ethernet/mellanox/mlxsw/spectrum.h drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c The bond_main.c and mellanox switch conflicts were cases of overlapping changes. Signed-off-by: David S. Miller <davem@davemloft.net>
| * sched,cls_flower: set key address type when presentJamal Hadi Salim2016-01-111-2/+8
| | | | | | | | | | | | | | | | | | only when user space passes the addresses should we consider their presence Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Acked-by: Jiri Pirko <jiri@resnulli.us> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net, sched: add clsact qdiscDaniel Borkmann2016-01-103-7/+97
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This work adds a generalization of the ingress qdisc as a qdisc holding only classifiers. The clsact qdisc works on ingress, but also on egress. In both cases, it's execution happens without taking the qdisc lock, and the main difference for the egress part compared to prior version of [1] is that this can be applied with _any_ underlying real egress qdisc (also classless ones). Besides solving the use-case of [1], that is, allowing for more programmability on assigning skb->priority for the mqprio case that is supported by most popular 10G+ NICs, it also opens up a lot more flexibility for other tc applications. The main work on classification can already be done at clsact egress time if the use-case allows and state stored for later retrieval f.e. again in skb->priority with major/minors (which is checked by most classful qdiscs before consulting tc_classify()) and/or in other skb fields like skb->tc_index for some light-weight post-processing to get to the eventual classid in case of a classful qdisc. Another use case is that the clsact egress part allows to have a central egress counterpart to the ingress classifiers, so that classifiers can easily share state (e.g. in cls_bpf via eBPF maps) for ingress and egress. Currently, default setups like mq + pfifo_fast would require for this to use, for example, prio qdisc instead (to get a tc_classify() run) and to duplicate the egress classifier for each queue. With clsact, it allows for leaving the setup as is, it can additionally assign skb->priority to put the skb in one of pfifo_fast's bands and it can share state with maps. Moreover, we can access the skb's dst entry (f.e. to retrieve tclassid) w/o the need to perform a skb_dst_force() to hold on to it any longer. In lwt case, we can also use this facility to setup dst metadata via cls_bpf (bpf_skb_set_tunnel_key()) without needing a real egress qdisc just for that (case of IFF_NO_QUEUE devices, for example). The realization can be done without any changes to the scheduler core framework. All it takes is that we have two a-priori defined minors/child classes, where we can mux between ingress and egress classifier list (dev->ingress_cl_list and dev->egress_cl_list, latter stored close to dev->_tx to avoid extra cacheline miss for moderate loads). The egress part is a bit similar modelled to handle_ing() and patched to a noop in case the functionality is not used. Both handlers are now called sch_handle_ingress() and sch_handle_egress(), code sharing among the two doesn't seem practical as there are various minor differences in both paths, so that making them conditional in a single handler would rather slow things down. Full compatibility to ingress qdisc is provided as well. Since both piggyback on TC_H_CLSACT, only one of them (ingress/clsact) can exist per netdevice, and thus ingress qdisc specific behaviour can be retained for user space. This means, either a user does 'tc qdisc add dev foo ingress' and configures ingress qdisc as usual, or the 'tc qdisc add dev foo clsact' alternative, where both, ingress and egress classifier can be configured as in the below example. ingress qdisc supports attaching classifier to any minor number whereas clsact has two fixed minors for muxing between the lists, therefore to not break user space setups, they are better done as two separate qdiscs. I decided to extend the sch_ingress module with clsact functionality so that commonly used code can be reused, the module is being aliased with sch_clsact so that it can be auto-loaded properly. Alternative would have been to add a flag when initializing ingress to alter its behaviour plus aliasing to a different name (as it's more than just ingress). However, the first would end up, based on the flag, choosing the new/old behaviour by calling different function implementations to handle each anyway, the latter would require to register ingress qdisc once again under different alias. So, this really begs to provide a minimal, cleaner approach to have Qdisc_ops and Qdisc_class_ops by its own that share callbacks used by both. Example, adding qdisc: # tc qdisc add dev foo clsact # tc qdisc show dev foo qdisc mq 0: root qdisc pfifo_fast 0: parent :1 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc pfifo_fast 0: parent :2 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc pfifo_fast 0: parent :3 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc pfifo_fast 0: parent :4 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc clsact ffff: parent ffff:fff1 Adding filters (deleting, etc works analogous by specifying ingress/egress): # tc filter add dev foo ingress bpf da obj bar.o sec ingress # tc filter add dev foo egress bpf da obj bar.o sec egress # tc filter show dev foo ingress filter protocol all pref 49152 bpf filter protocol all pref 49152 bpf handle 0x1 bar.o:[ingress] direct-action # tc filter show dev foo egress filter protocol all pref 49152 bpf filter protocol all pref 49152 bpf handle 0x1 bar.o:[egress] direct-action A 'tc filter show dev foo' or 'tc filter show dev foo parent ffff:' will show an empty list for clsact. Either using the parent names (ingress/egress) or specifying the full major/minor will then show the related filter lists. Prior work on a mqprio prequeue() facility [1] was done mainly by John Fastabend. [1] http://patchwork.ozlabs.org/patch/512949/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net, sched: add skb_at_tc_ingress helperDaniel Borkmann2016-01-101-5/+1
|/ | | | | | | | | Add a skb_at_tc_ingress() as this will be needed elsewhere as well and can hide the ugly ifdef. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* net: sched: fix missing free per cpu on qstatsJohn Fastabend2016-01-061-1/+3
| | | | | | | | | | | When a qdisc is using per cpu stats (currently just the ingress qdisc) only the bstats are being freed. This also free's the qstats. Fixes: b0ab6f92752b9f9d8 ("net: sched: enable per cpu qstats") Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
* net_sched: make qdisc_tree_decrease_qlen() work for non mqEric Dumazet2015-12-151-1/+1
| | | | | | | | | | | | | | | | | Stas Nichiporovich reported a regression in his HFSC qdisc setup on a non multi queue device. It turns out I mistakenly added a TCQ_F_NOPARENT flag on all qdisc allocated in qdisc_create() for non multi queue devices, which was rather buggy. I was clearly mislead by the TCQ_F_ONETXQUEUE that is also set here for no good reason, since it only matters for the root qdisc. Fixes: 4eaf3b84f288 ("net_sched: fix qdisc_tree_decrease_qlen() races") Reported-by: Stas Nichiporovich <stasn77@gmail.com> Tested-by: Stas Nichiporovich <stasn77@gmail.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* net_sched: fix qdisc_tree_decrease_qlen() racesEric Dumazet2015-12-034-14/+23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | qdisc_tree_decrease_qlen() suffers from two problems on multiqueue devices. One problem is that it updates sch->q.qlen and sch->qstats.drops on the mq/mqprio root qdisc, while it should not : Daniele reported underflows errors : [ 681.774821] PAX: sch->q.qlen: 0 n: 1 [ 681.774825] PAX: size overflow detected in function qdisc_tree_decrease_qlen net/sched/sch_api.c:769 cicus.693_49 min, count: 72, decl: qlen; num: 0; context: sk_buff_head; [ 681.774954] CPU: 2 PID: 19 Comm: ksoftirqd/2 Tainted: G O 4.2.6.201511282239-1-grsec #1 [ 681.774955] Hardware name: ASUSTeK COMPUTER INC. X302LJ/X302LJ, BIOS X302LJ.202 03/05/2015 [ 681.774956] ffffffffa9a04863 0000000000000000 0000000000000000 ffffffffa990ff7c [ 681.774959] ffffc90000d3bc38 ffffffffa95d2810 0000000000000007 ffffffffa991002b [ 681.774960] ffffc90000d3bc68 ffffffffa91a44f4 0000000000000001 0000000000000001 [ 681.774962] Call Trace: [ 681.774967] [<ffffffffa95d2810>] dump_stack+0x4c/0x7f [ 681.774970] [<ffffffffa91a44f4>] report_size_overflow+0x34/0x50 [ 681.774972] [<ffffffffa94d17e2>] qdisc_tree_decrease_qlen+0x152/0x160 [ 681.774976] [<ffffffffc02694b1>] fq_codel_dequeue+0x7b1/0x820 [sch_fq_codel] [ 681.774978] [<ffffffffc02680a0>] ? qdisc_peek_dequeued+0xa0/0xa0 [sch_fq_codel] [ 681.774980] [<ffffffffa94cd92d>] __qdisc_run+0x4d/0x1d0 [ 681.774983] [<ffffffffa949b2b2>] net_tx_action+0xc2/0x160 [ 681.774985] [<ffffffffa90664c1>] __do_softirq+0xf1/0x200 [ 681.774987] [<ffffffffa90665ee>] run_ksoftirqd+0x1e/0x30 [ 681.774989] [<ffffffffa90896b0>] smpboot_thread_fn+0x150/0x260 [ 681.774991] [<ffffffffa9089560>] ? sort_range+0x40/0x40 [ 681.774992] [<ffffffffa9085fe4>] kthread+0xe4/0x100 [ 681.774994] [<ffffffffa9085f00>] ? kthread_worker_fn+0x170/0x170 [ 681.774995] [<ffffffffa95d8d1e>] ret_from_fork+0x3e/0x70 mq/mqprio have their own ways to report qlen/drops by folding stats on all their queues, with appropriate locking. A second problem is that qdisc_tree_decrease_qlen() calls qdisc_lookup() without proper locking : concurrent qdisc updates could corrupt the list that qdisc_match_from_root() parses to find a qdisc given its handle. Fix first problem adding a TCQ_F_NOPARENT qdisc flag that qdisc_tree_decrease_qlen() can use to abort its tree traversal, as soon as it meets a mq/mqprio qdisc children. Second problem can be fixed by RCU protection. Qdisc are already freed after RCU grace period, so qdisc_list_add() and qdisc_list_del() simply have to use appropriate rcu list variants. A future patch will add a per struct netdev_queue list anchor, so that qdisc_tree_decrease_qlen() can have more efficient lookups. Reported-by: Daniele Fucini <dfucini@gmail.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Cong Wang <cwang@twopensource.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* net_sched: em_meta: use skb_to_full_sk() helperEric Dumazet2015-11-081-46/+92
| | | | | | | | SYNACK packets might be attached to request sockets. Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* sched: cls_flow: use skb_to_full_sk() helperEric Dumazet2015-11-081-4/+11
| | | | | | | | SYNACK packets might be attached to request sockets. Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* net: sched: kill dead code in sch_choke.cPhil Sutter2015-11-031-59/+0
| | | | | | | It looks like this has never been used at all. Signed-off-by: Phil Sutter <phil@nwl.cc> Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2015-10-202-5/+24
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | Conflicts: drivers/net/usb/asix_common.c net/ipv4/inet_connection_sock.c net/switchdev/switchdev.c In the inet_connection_sock.c case the request socket hashing scheme is completely different in net-next. The other two conflicts were overlapping changes. Signed-off-by: David S. Miller <davem@davemloft.net>
| * sch_hhf: fix return value of hhf_drop()WANG Cong2015-10-111-1/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | Similar to commit c0afd9ce4d6a ("fq_codel: fix return value of fq_codel_drop()") ->drop() is supposed to return the number of bytes it dropped, but hhf_drop () returns the id of the bucket where it drops a packet from. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Terry Lam <vtlam@google.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * act_mirred: clear sender cpu before sending to txWANG Cong2015-10-081-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Similar to commit c29390c6dfee ("xps: must clear sender_cpu before forwarding") the skb->sender_cpu needs to be cleared when moving from Rx Tx, otherwise kernel could crash. Fixes: 2bd82484bb4c ("xps: fix xps for stacked devices") Cc: Eric Dumazet <edumazet@google.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * act_mirred: always release tcf hashWANG Cong2015-10-051-3/+3
| | | | | | | | | | | | | | | | | | | | Align with other tc actions. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * act_mirred: fix a race condition on mirred_listWANG Cong2015-10-051-1/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | After commit 1ce87720d456 ("net: sched: make cls_u32 lockless") we began to release tc actions in a RCU callback. However, mirred action relies on RTNL lock to protect the global mirred_list, therefore we could have a race condition between RCU callback and netdevice event, which caused a list corruption as reported by Vinson. Instead of relying on RTNL lock, introduce a spinlock to protect this list. Note, in non-bind case, it is still called with RTNL lock, therefore should disable BH too. Reported-by: Vinson Lee <vlee@twopensource.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: synack packets can be attached to request socketsEric Dumazet2015-10-111-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | selinux needs few changes to accommodate fact that SYNACK messages can be attached to a request socket, lacking sk_security pointer (Only syncookies are still attached to a TCP_LISTEN socket) Adds a new sk_listener() helper, and use it in selinux and sch_fq Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported by: kernel test robot <ying.huang@linux.intel.com> Cc: Paul Moore <paul@paul-moore.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: Eric Paris <eparis@parisplace.org> Acked-by: Paul Moore <paul@paul-moore.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net/sched: make sch_blackhole.c explicitly non-modularPaul Gortmaker2015-10-091-12/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The Kconfig currently controlling compilation of this code is: net/sched/Kconfig:menuconfig NET_SCHED net/sched/Kconfig: bool "QoS and/or fair queueing" ...meaning that it currently is not being built as a module by anyone. Lets remove the modular code that is essentially orphaned, so that when reading the driver there is no doubt it is builtin-only. Since module_init translates to device_initcall in the non-modular case, the init ordering remains unchanged with this commit. We can change to one of the other priority initcalls (subsys?) at any later date, if desired. We also delete the MODULE_LICENSE tag since all that information is already contained at the top of the file in the comments. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: netdev@vger.kernel.org Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | sched, bpf: add helper for retrieving routing realmsDaniel Borkmann2015-10-031-2/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Using routing realms as part of the classifier is quite useful, it can be viewed as a tag for one or multiple routing entries (think of an analogy to net_cls cgroup for processes), set by user space routing daemons or via iproute2 as an indicator for traffic classifiers and later on processed in the eBPF program. Unlike actions, the classifier can inspect device flags and enable netif_keep_dst() if necessary. tc actions don't have that possibility, but in case people know what they are doing, it can be used from there as well (e.g. via devs that must keep dsts by design anyway). If a realm is set, the handler returns the non-zero realm. User space can set the full 32bit realm for the dst. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: attach SYNACK messages to request sockets instead of listenerEric Dumazet2015-10-031-5/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If a listen backlog is very big (to avoid syncookies), then the listener sk->sk_wmem_alloc is the main source of false sharing, as we need to touch it twice per SYNACK re-transmit and TX completion. (One SYN packet takes listener lock once, but up to 6 SYNACK are generated) By attaching the skb to the request socket, we remove this source of contention. Tested: listen(fd, 10485760); // single listener (no SO_REUSEPORT) 16 RX/TX queue NIC Sustain a SYNFLOOD attack of ~320,000 SYN per second, Sending ~1,400,000 SYNACK per second. Perf profiles now show listener spinlock being next bottleneck. 20.29% [kernel] [k] queued_spin_lock_slowpath 10.06% [kernel] [k] __inet_lookup_established 5.12% [kernel] [k] reqsk_timer_handler 3.22% [kernel] [k] get_next_timer_interrupt 3.00% [kernel] [k] tcp_make_synack 2.77% [kernel] [k] ipt_do_table 2.70% [kernel] [k] run_timer_softirq 2.50% [kernel] [k] ip_finish_output 2.04% [kernel] [k] cascade Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
OpenPOWER on IntegriCloud