summaryrefslogtreecommitdiffstats
path: root/net/ipv4
Commit message (Collapse)AuthorAgeFilesLines
...
| * tcp: ack immediately when a cwr packet arrivesLawrence Brakmo2018-07-251-1/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We observed high 99 and 99.9% latencies when doing RPCs with DCTCP. The problem is triggered when the last packet of a request arrives CE marked. The reply will carry the ECE mark causing TCP to shrink its cwnd to 1 (because there are no packets in flight). When the 1st packet of the next request arrives, the ACK was sometimes delayed even though it is CWR marked, adding up to 40ms to the RPC latency. This patch insures that CWR marked data packets arriving will be acked immediately. Packetdrill script to reproduce the problem: 0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 0.000 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0 0.000 bind(3, ..., ...) = 0 0.000 listen(3, 1) = 0 0.100 < [ect0] SEW 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> 0.100 > SE. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> 0.110 < [ect0] . 1:1(0) ack 1 win 257 0.200 accept(3, ..., ...) = 4 0.200 < [ect0] . 1:1001(1000) ack 1 win 257 0.200 > [ect01] . 1:1(0) ack 1001 0.200 write(4, ..., 1) = 1 0.200 > [ect01] P. 1:2(1) ack 1001 0.200 < [ect0] . 1001:2001(1000) ack 2 win 257 0.200 write(4, ..., 1) = 1 0.200 > [ect01] P. 2:3(1) ack 2001 0.200 < [ect0] . 2001:3001(1000) ack 3 win 257 0.200 < [ect0] . 3001:4001(1000) ack 3 win 257 0.200 > [ect01] . 3:3(0) ack 4001 0.210 < [ce] P. 4001:4501(500) ack 3 win 257 +0.001 read(4, ..., 4500) = 4500 +0 write(4, ..., 1) = 1 +0 > [ect01] PE. 3:4(1) ack 4501 +0.010 < [ect0] W. 4501:5501(1000) ack 4 win 257 // Previously the ACK sequence below would be 4501, causing a long RTO +0.040~+0.045 > [ect01] . 4:4(0) ack 5501 // delayed ack +0.311 < [ect0] . 5501:6501(1000) ack 4 win 257 // More data +0 > [ect01] . 4:4(0) ack 6501 // now acks everything +0.500 < F. 9501:9501(0) ack 4 win 257 Modified based on comments by Neal Cardwell <ncardwell@google.com> Signed-off-by: Lawrence Brakmo <brakmo@fb.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ip_gre: remove redundant variables t_hlenYueHaibing2018-08-011-5/+0
| | | | | | | | | | | | | | | | | | After commit ffc2b6ee4174 ("ip_gre: fix IFLA_MTU ignored on NEWLINK") variable t_hlen is assigned values that are never read, hence they are redundant and can be removed. Signed-off-by: YueHaibing <yuehaibing@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: remove set but not used variable 'skb_size'Wei Yongjun2018-08-011-2/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Fixes gcc '-Wunused-but-set-variable' warning: net/ipv4/tcp_output.c: In function 'tcp_collapse_retrans': net/ipv4/tcp_output.c:2700:6: warning: variable 'skb_size' set but not used [-Wunused-but-set-variable] int skb_size, next_skb_size; ^ Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: add stat of data packet reordering eventsWei Wang2018-08-013-2/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Introduce a new TCP stats to record the number of reordering events seen and expose it in both tcp_info (TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS). Application can use this stats to track the frequency of the reordering events in addition to the existing reordering stats which tracks the magnitude of the latest reordering event. Note: this new stats tracks reordering events triggered by ACKs, which could often be fewer than the actual number of packets being delivered out-of-order. Signed-off-by: Wei Wang <weiwan@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: add dsack blocks received statsWei Wang2018-08-012-0/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | Introduce a new TCP stat to record the number of DSACK blocks received (RFC4989 tcpEStatsStackDSACKDups) and expose it in both tcp_info (TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS). Signed-off-by: Wei Wang <weiwan@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: add data bytes retransmitted statsWei Wang2018-08-012-0/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | Introduce a new TCP stat to record the number of bytes retransmitted (RFC4898 tcpEStatsPerfOctetsRetrans) and expose it in both tcp_info (TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS). Signed-off-by: Wei Wang <weiwan@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: add data bytes sent statsWei Wang2018-08-012-0/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | Introduce a new TCP stat to record the number of bytes sent (RFC4898 tcpEStatsPerfHCDataOctetsOut) and expose it in both tcp_info (TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS). Signed-off-by: Wei Wang <weiwan@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: add a helper to calculate size of opt_statsWei Wang2018-08-011-3/+24
| | | | | | | | | | | | | | | | | | | | | | | | | | This is to refactor the calculation of the size of opt_stats to a helper function to make the code cleaner and easier for later changes. Suggested-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Wei Wang <weiwan@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: ipv4: Notify about changes to ip_forward_update_priorityPetr Machata2018-08-011-1/+18
| | | | | | | | | | | | | | | | | | | | Drivers may make offloading decision based on whether ip_forward_update_priority is enabled or not. Therefore distribute netevent notifications to give them a chance to react to a change. Signed-off-by: Petr Machata <petrm@mellanox.com> Reviewed-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: ipv4: Control SKB reprioritization after forwardingPetr Machata2018-08-013-1/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | After IPv4 packets are forwarded, the priority of the corresponding SKB is updated according to the TOS field of IPv4 header. This overrides any prioritization done earlier by e.g. an skbedit action or ingress-qos-map defined at a vlan device. Such overriding may not always be desirable. Even if the packet ends up being routed, which implies this is an L3 network node, an administrator may wish to preserve whatever prioritization was done earlier on in the pipeline. Therefore introduce a sysctl that controls this behavior. Keep the default value at 1 to maintain backward-compatible behavior. Signed-off-by: Petr Machata <petrm@mellanox.com> Reviewed-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: add helpers checking if socket can be bound to nonlocal addressVincent Bernat2018-08-012-6/+3
| | | | | | | | | | | | | | | | | | | | The construction "net->ipv4.sysctl_ip_nonlocal_bind || inet->freebind || inet->transparent" is present three times and its IPv6 counterpart is also present three times. We introduce two small helpers to characterize these tests uniformly. Signed-off-by: Vincent Bernat <vincent@bernat.im> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: simplify sock_poll_waitChristoph Hellwig2018-07-301-1/+1
| | | | | | | | | | | | | | | | The wait_address argument is always directly derived from the filp argument, so remove it. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: David S. Miller <davem@davemloft.net>
* | route: add support for directed broadcast forwardingXin Long2018-07-292-1/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch implements the feature described in rfc1812#section-5.3.5.2 and rfc2644. It allows the router to forward directed broadcast when sysctl bc_forwarding is enabled. Note that this feature could be done by iptables -j TEE, but it would cause some problems: - target TEE's gateway param has to be set with a specific address, and it's not flexible especially when the route wants forward all directed broadcasts. - this duplicates the directed broadcasts so this may cause side effects to applications. Besides, to keep consistent with other os router like BSD, it's also necessary to implement it in the route rx path. Note that route cache needs to be flushed when bc_forwarding is changed. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | Merge branch 'master' of ↵David S. Miller2018-07-271-4/+2
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next Steffen Klassert says: ==================== pull request (net-next): ipsec-next 2018-07-27 1) Extend the output_mark to also support the input direction and masking the mark values before applying to the skb. 2) Add a new lookup key for the upcomming xfrm interfaces. 3) Extend the xfrm lookups to match xfrm interface IDs. 4) Add virtual xfrm interfaces. The purpose of these interfaces is to overcome the design limitations that the existing VTI devices have. The main limitations that we see with the current VTI are the following: VTI interfaces are L3 tunnels with configurable endpoints. For xfrm, the tunnel endpoint are already determined by the SA. So the VTI tunnel endpoints must be either the same as on the SA or wildcards. In case VTI tunnel endpoints are same as on the SA, we get a one to one correlation between the SA and the tunnel. So each SA needs its own tunnel interface. On the other hand, we can have only one VTI tunnel with wildcard src/dst tunnel endpoints in the system because the lookup is based on the tunnel endpoints. The existing tunnel lookup won't work with multiple tunnels with wildcard tunnel endpoints. Some usecases require more than on VTI tunnel of this type, for example if somebody has multiple namespaces and every namespace requires such a VTI. VTI needs separate interfaces for IPv4 and IPv6 tunnels. So when routing to a VTI, we have to know to which address family this traffic class is going to be encapsulated. This is a lmitation because it makes routing more complex and it is not always possible to know what happens behind the VTI, e.g. when the VTI is move to some namespace. VTI works just with tunnel mode SAs. We need generic interfaces that ensures transfomation, regardless of the xfrm mode and the encapsulated address family. VTI is configured with a combination GRE keys and xfrm marks. With this we have to deal with some extra cases in the generic tunnel lookup because the GRE keys on the VTI are actually not GRE keys, the GRE keys were just reused for something else. All extensions to the VTI interfaces would require to add even more complexity to the generic tunnel lookup. So to overcome this, we developed xfrm interfaces with the following design goal: It should be possible to tunnel IPv4 and IPv6 through the same interface. No limitation on xfrm mode (tunnel, transport and beet). Should be a generic virtual interface that ensures IPsec transformation, no need to know what happens behind the interface. Interfaces should be configured with a new key that must match a new policy/SA lookup key. The lookup logic should stay in the xfrm codebase, no need to change or extend generic routing and tunnel lookups. Should be possible to use IPsec hardware offloads of the underlying interface. 5) Remove xfrm pcpu policy cache. This was added after the flowcache removal, but it turned out to make things even worse. From Florian Westphal. 6) Allow to update the set mark on SA updates. From Nathan Harold. 7) Convert some timestamps to time64_t. From Arnd Bergmann. 8) Don't check the offload_handle in xfrm code, it is an opaque data cookie for the driver. From Shannon Nelson. 9) Remove xfrmi interface ID from flowi. After this pach no generic code is touched anymore to do xfrm interface lookups. From Benedict Wong. 10) Allow to update the xfrm interface ID on SA updates. From Nathan Harold. 11) Don't pass zero to ERR_PTR() in xfrm_resolve_and_create_bundle. From YueHaibing. 12) Return more detailed errors on xfrm interface creation. From Benedict Wong. 13) Use PTR_ERR_OR_ZERO instead of IS_ERR + PTR_ERR. From the kbuild test robot. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
| * | xfrm: don't check offload_handle for nonzeroShannon Nelson2018-07-191-4/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The offload_handle should be an opaque data cookie for the driver to use, much like the data cookie for a timer or alarm callback. Thus, the XFRM stack should not be checking for non-zero, because the driver might use that to store an array reference, which could be zero, or some other zero but meaningful value. We can remove the checks for non-zero because there are plenty other attributes also being checked to see if there is an offload in place for the SA in question. Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
* | | tcp: make function tcp_retransmit_stamp() staticWei Yongjun2018-07-251-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fixes the following sparse warnings: net/ipv4/tcp_timer.c:25:5: warning: symbol 'tcp_retransmit_stamp' was not declared. Should it be static? Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | | Merge ra.kernel.org:/pub/scm/linux/kernel/git/davem/netDavid S. Miller2018-07-246-61/+100
|\ \ \ | | |/ | |/|
| * | ip: in cmsg IP(V6)_ORIGDSTADDR call pskb_may_pullWillem de Bruijn2018-07-241-2/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Syzbot reported a read beyond the end of the skb head when returning IPV6_ORIGDSTADDR: BUG: KMSAN: kernel-infoleak in put_cmsg+0x5ef/0x860 net/core/scm.c:242 CPU: 0 PID: 4501 Comm: syz-executor128 Not tainted 4.17.0+ #9 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:113 kmsan_report+0x188/0x2a0 mm/kmsan/kmsan.c:1125 kmsan_internal_check_memory+0x138/0x1f0 mm/kmsan/kmsan.c:1219 kmsan_copy_to_user+0x7a/0x160 mm/kmsan/kmsan.c:1261 copy_to_user include/linux/uaccess.h:184 [inline] put_cmsg+0x5ef/0x860 net/core/scm.c:242 ip6_datagram_recv_specific_ctl+0x1cf3/0x1eb0 net/ipv6/datagram.c:719 ip6_datagram_recv_ctl+0x41c/0x450 net/ipv6/datagram.c:733 rawv6_recvmsg+0x10fb/0x1460 net/ipv6/raw.c:521 [..] This logic and its ipv4 counterpart read the destination port from the packet at skb_transport_offset(skb) + 4. With MSG_MORE and a local SOCK_RAW sender, syzbot was able to cook a packet that stores headers exactly up to skb_transport_offset(skb) in the head and the remainder in a frag. Call pskb_may_pull before accessing the pointer to ensure that it lies in skb head. Link: http://lkml.kernel.org/r/CAF=yD-LEJwZj5a1-bAAj2Oy_hKmGygV6rsJ_WOrAYnv-fnayiQ@mail.gmail.com Reported-by: syzbot+9adb4b567003cac781f0@syzkaller.appspotmail.com Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | tcp: add tcp_ooo_try_coalesce() helperEric Dumazet2018-07-231-4/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In case skb in out_or_order_queue is the result of multiple skbs coalescing, we would like to get a proper gso_segs counter tracking, so that future tcp_drop() can report an accurate number. I chose to not implement this tracking for skbs in receive queue, since they are not dropped, unless socket is disconnected. Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | tcp: call tcp_drop() from tcp_data_queue_ofo()Eric Dumazet2018-07-231-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In order to be able to give better diagnostics and detect malicious traffic, we need to have better sk->sk_drops tracking. Fixes: 9f5afeae5152 ("tcp: use an RB tree for ooo receive queue") Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | tcp: detect malicious patterns in tcp_collapse_ofo_queue()Eric Dumazet2018-07-231-2/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In case an attacker feeds tiny packets completely out of order, tcp_collapse_ofo_queue() might scan the whole rb-tree, performing expensive copies, but not changing socket memory usage at all. 1) Do not attempt to collapse tiny skbs. 2) Add logic to exit early when too many tiny skbs are detected. We prefer not doing aggressive collapsing (which copies packets) for pathological flows, and revert to tcp_prune_ofo_queue() which will be less expensive. In the future, we might add the possibility of terminating flows that are proven to be malicious. 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>
| * | tcp: avoid collapses in tcp_prune_queue() if possibleEric Dumazet2018-07-231-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Right after a TCP flow is created, receiving tiny out of order packets allways hit the condition : if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) tcp_clamp_window(sk); tcp_clamp_window() increases sk_rcvbuf to match sk_rmem_alloc (guarded by tcp_rmem[2]) Calling tcp_collapse_ofo_queue() in this case is not useful, and offers a O(N^2) surface attack to malicious peers. Better not attempt anything before full queue capacity is reached, forcing attacker to spend lots of resource and allow us to more easily detect the abuse. Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | tcp: free batches of packets in tcp_prune_ofo_queue()Eric Dumazet2018-07-231-4/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Juha-Matti Tilli reported that malicious peers could inject tiny packets in out_of_order_queue, forcing very expensive calls to tcp_collapse_ofo_queue() and tcp_prune_ofo_queue() for every incoming packet. out_of_order_queue rb-tree can contain thousands of nodes, iterating over all of them is not nice. Before linux-4.9, we would have pruned all packets in ofo_queue in one go, every XXXX packets. XXXX depends on sk_rcvbuf and skbs truesize, but is about 7000 packets with tcp_rmem[2] default of 6 MB. Since we plan to increase tcp_rmem[2] in the future to cope with modern BDP, can not revert to the old behavior, without great pain. Strategy taken in this patch is to purge ~12.5 % of the queue capacity. Fixes: 36a6503fedda ("tcp: refine tcp_prune_ofo_queue() to not drop all packets") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Juha-Matti Tilli <juha-matti.tilli@iki.fi> Acked-by: Yuchung Cheng <ycheng@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | ip: hash fragments consistentlyPaolo Abeni2018-07-231-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The skb hash for locally generated ip[v6] fragments belonging to the same datagram can vary in several circumstances: * for connected UDP[v6] sockets, the first fragment get its hash via set_owner_w()/skb_set_hash_from_sk() * for unconnected IPv6 UDPv6 sockets, the first fragment can get its hash via ip6_make_flowlabel()/skb_get_hash_flowi6(), if auto_flowlabel is enabled For the following frags the hash is usually computed via skb_get_hash(). The above can cause OoO for unconnected IPv6 UDPv6 socket: in that scenario the egress tx queue can be selected on a per packet basis via the skb hash. It may also fool flow-oriented schedulers to place fragments belonging to the same datagram in different flows. Fix the issue by copying the skb hash from the head frag into the others at fragmentation time. Before this commit: perf probe -a "dev_queue_xmit skb skb->hash skb->l4_hash:b1@0/8 skb->sw_hash:b1@1/8" netperf -H $IPV4 -t UDP_STREAM -l 5 -- -m 2000 -n & perf record -e probe:dev_queue_xmit -e probe:skb_set_owner_w -a sleep 0.1 perf script probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=3713014309 l4_hash=1 sw_hash=0 probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=0 l4_hash=0 sw_hash=0 After this commit: probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=2171763177 l4_hash=1 sw_hash=0 probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=2171763177 l4_hash=1 sw_hash=0 Fixes: b73c3d0e4f0e ("net: Save TX flow hash in sock and set in skbuf on xmit") Fixes: 67800f9b1f4e ("ipv6: Call skb_get_hash_flowi6 to get skb->hash in ip6_make_flowlabel") Signed-off-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | multicast: do not restore deleted record source filter mode to new oneHangbin Liu2018-07-211-2/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There are two scenarios that we will restore deleted records. The first is when device down and up(or unmap/remap). In this scenario the new filter mode is same with previous one. Because we get it from in_dev->mc_list and we do not touch it during device down and up. The other scenario is when a new socket join a group which was just delete and not finish sending status reports. In this scenario, we should use the current filter mode instead of restore old one. Here are 4 cases in total. old_socket new_socket before_fix after_fix IN(A) IN(A) ALLOW(A) ALLOW(A) IN(A) EX( ) TO_IN( ) TO_EX( ) EX( ) IN(A) TO_EX( ) ALLOW(A) EX( ) EX( ) TO_EX( ) TO_EX( ) Fixes: 24803f38a5c0b (igmp: do not remove igmp souce list info when set link down) Fixes: 1666d49e1d416 (mld: do not remove mld souce list info when set link down) Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | tcp: do not delay ACK in DCTCP upon CE status changeYuchung Cheng2018-07-202-13/+20
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Per DCTCP RFC8257 (Section 3.2) the ACK reflecting the CE status change has to be sent immediately so the sender can respond quickly: """ When receiving packets, the CE codepoint MUST be processed as follows: 1. If the CE codepoint is set and DCTCP.CE is false, set DCTCP.CE to true and send an immediate ACK. 2. If the CE codepoint is not set and DCTCP.CE is true, set DCTCP.CE to false and send an immediate ACK. """ Previously DCTCP implementation may continue to delay the ACK. This patch fixes that to implement the RFC by forcing an immediate ACK. Tested with this packetdrill script provided by Larry Brakmo 0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 0.000 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0 0.000 bind(3, ..., ...) = 0 0.000 listen(3, 1) = 0 0.100 < [ect0] SEW 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> 0.100 > SE. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> 0.110 < [ect0] . 1:1(0) ack 1 win 257 0.200 accept(3, ..., ...) = 4 +0 setsockopt(4, SOL_SOCKET, SO_DEBUG, [1], 4) = 0 0.200 < [ect0] . 1:1001(1000) ack 1 win 257 0.200 > [ect01] . 1:1(0) ack 1001 0.200 write(4, ..., 1) = 1 0.200 > [ect01] P. 1:2(1) ack 1001 0.200 < [ect0] . 1001:2001(1000) ack 2 win 257 +0.005 < [ce] . 2001:3001(1000) ack 2 win 257 +0.000 > [ect01] . 2:2(0) ack 2001 // Previously the ACK below would be delayed by 40ms +0.000 > [ect01] E. 2:2(0) ack 3001 +0.500 < F. 9501:9501(0) ack 4 win 257 Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | tcp: do not cancel delay-AcK on DCTCP special ACKYuchung Cheng2018-07-202-33/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently when a DCTCP receiver delays an ACK and receive a data packet with a different CE mark from the previous one's, it sends two immediate ACKs acking previous and latest sequences respectly (for ECN accounting). Previously sending the first ACK may mark off the delayed ACK timer (tcp_event_ack_sent). This may subsequently prevent sending the second ACK to acknowledge the latest sequence (tcp_ack_snd_check). The culprit is that tcp_send_ack() assumes it always acknowleges the latest sequence, which is not true for the first special ACK. The fix is to not make the assumption in tcp_send_ack and check the actual ack sequence before cancelling the delayed ACK. Further it's safer to pass the ack sequence number as a local variable into tcp_send_ack routine, instead of intercepting tp->rcv_nxt to avoid future bugs like this. Reported-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | tcp: helpers to send special DCTCP ackYuchung Cheng2018-07-201-5/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | Refactor and create helpers to send the special ACK in DCTCP. Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | | net: remove blank lines at end of fileStephen Hemminger2018-07-242-3/+3
| | | | | | | | | | | | | | | | | | | | | Several files have extra line at end of file. Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* | | bpfilter: remove trailing newlineStephen Hemminger2018-07-241-1/+0
| | | | | | | | | | | | | | | Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* | | multicast: remove useless parameter for group addHangbin Liu2018-07-211-5/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Remove the mode parameter for igmp/igmp6_group_added as we can get it from first parameter. Fixes: 6e2059b53f988 (ipv4/igmp: init group mode as INCLUDE when join source group) Fixes: c7ea20c9da5b9 (ipv6/mcast: init as INCLUDE when join SSM INCLUDE group) Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | | tcp: Add tcp_clamp_rto_to_user_timeout() helper to improve accuracyJon Maxwell2018-07-211-1/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Create the tcp_clamp_rto_to_user_timeout() helper routine. To calculate the correct rto, so that the TCP_USER_TIMEOUT socket option is more accurate. Taking suggestions and feedback into account from Eric Dumazet, Neal Cardwell and David Laight. Due to the 1st commit we can avoid the msecs_to_jiffies() and jiffies_to_msecs() dance. Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | | tcp: Add tcp_retransmit_stamp() helper routineJon Maxwell2018-07-211-8/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | Create a seperate helper routine as per Neal Cardwells suggestion. To be used by the final commit in this series and retransmits_timed_out(). Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | | tcp: convert icsk_user_timeout from jiffies to msecsJon Maxwell2018-07-212-6/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This is a preparatory commit. Part of this series that improves the socket TCP_USER_TIMEOUT option accuracy. Implement Eric Dumazets idea to convert icsk->icsk_user_timeout from jiffies to msecs. To eliminate the msecs_to_jiffies() and jiffies_to_msecs() dance in future. Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | | Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-nextDavid S. Miller2018-07-205-933/+3
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pablo Neira Ayuso says: ==================== Netfilter/IPVS updates for net-next The following patchset contains Netfilter/IPVS updates for your net-next tree: 1) No need to set ttl from reject action for the bridge family, from Taehee Yoo. 2) Use a fixed timeout for flow that are passed up from the flowtable to conntrack, from Florian Westphal. 3) More preparation patches for tproxy support for nf_tables, from Mate Eckl. 4) Remove unnecessary indirection in core IPv6 checksum function, from Florian Westphal. 5) Use nf_ct_get_tuplepr() from openvswitch, instead of opencoding it. From Florian Westphal. 6) socket match now selects socket infrastructure, instead of depending on it. From Mate Eckl. 7) Patch series to simplify conntrack tuple building/parsing from packet path and ctnetlink, from Florian Westphal. 8) Fetch timeout policy from protocol helpers, instead of doing it from core, from Florian Westphal. 9) Merge IPv4 and IPv6 protocol trackers into conntrack core, from Florian Westphal. 10) Depend on CONFIG_NF_TABLES_IPV6 and CONFIG_IP6_NF_IPTABLES respectively, instead of IPV6. Patch from Mate Eckl. 11) Add specific function for garbage collection in conncount, from Yi-Hung Wei. 12) Catch number of elements in the connlimit list, from Yi-Hung Wei. 13) Move locking to nf_conncount, from Yi-Hung Wei. 14) Series of patches to add lockless tree traversal in nf_conncount, from Yi-Hung Wei. 15) Resolve clash in matching conntracks when race happens, from Martynas Pumputis. 16) If connection entry times out, remove template entry from the ip_vs_conn_tab table to improve behaviour under flood, from Julian Anastasov. 17) Remove useless parameter from nf_ct_helper_ext_add(), from Gao feng. 18) Call abort from 2-phase commit protocol before requesting modules, make sure this is done under the mutex, from Florian Westphal. 19) Grab module reference when starting transaction, also from Florian. 20) Dynamically allocate expression info array for pre-parsing, from Florian. 21) Add per netns mutex for nf_tables, from Florian Westphal. 22) A couple of patches to simplify and refactor nf_osf code to prepare for nft_osf support. 23) Break evaluation on missing socket, from Mate Eckl. 24) Allow to match socket mark from nft_socket, from Mate Eckl. 25) Remove dependency on nf_defrag_ipv6, now that IPv6 tracker is built-in into nf_conntrack. From Florian Westphal. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | netfilter: conntrack: remove l3proto abstractionFlorian Westphal2018-07-174-781/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This unifies ipv4 and ipv6 protocol trackers and removes the l3proto abstraction. This gets rid of all l3proto indirect calls and the need to do a lookup on the function to call for l3 demux. It increases module size by only a small amount (12kbyte), so this reduces size because nf_conntrack.ko is useless without either nf_conntrack_ipv4 or nf_conntrack_ipv6 module. before: text data bss dec hex filename 7357 1088 0 8445 20fd nf_conntrack_ipv4.ko 7405 1084 4 8493 212d nf_conntrack_ipv6.ko 72614 13689 236 86539 1520b nf_conntrack.ko 19K nf_conntrack_ipv4.ko 19K nf_conntrack_ipv6.ko 179K nf_conntrack.ko after: text data bss dec hex filename 79277 13937 236 93450 16d0a nf_conntrack.ko 191K nf_conntrack.ko Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
| * | | netfilter: conntrack: remove get_timeout() indirectionFlorian Westphal2018-07-161-5/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Not needed, we can have the l4trackers fetch it themselvs. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
| * | | netfilter: conntrack: remove get_l4proto indirection from l3 protocol trackersFlorian Westphal2018-07-161-30/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Handle it in the core instead. ipv6_skip_exthdr() is built-in even if ipv6 is a module, i.e. this doesn't create an ipv6 dependency. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
| * | | netfilter: conntrack: remove invert_tuple indirection from l3 protocol trackersFlorian Westphal2018-07-162-12/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Its simpler to just handle it directly in nf_ct_invert_tuple(). Also gets rid of need to pass l3proto pointer to resolve_conntrack(). Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
| * | | netfilter: conntrack: remove pkt_to_tuple indirection from l3 protocol trackersFlorian Westphal2018-07-161-17/+0
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
| * | | netfilter: conntrack: remove ctnetlink callbacks from l3 protocol trackersFlorian Westphal2018-07-161-47/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | handle everything from ctnetlink directly. After all these years we still only support ipv4 and ipv6, so it seems reasonable to remove l3 protocol tracker support and instead handle ipv4/ipv6 from a common, always builtin inet tracker. Step 1: Get rid of all the l3proto->func() calls. Start with ctnetlink, then move on to packet-path ones. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
| * | | netfilter: utils: move nf_ip_checksum* from ipv4 to utilsFlorian Westphal2018-07-161-53/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | allows to make nf_ip_checksum_partial static, it no longer has an external caller. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
* | | | Merge ra.kernel.org:/pub/scm/linux/kernel/git/torvalds/linuxDavid S. Miller2018-07-2011-69/+94
|\ \ \ \ | |/ / / |/| / / | |/ / | | | | | | | | | All conflicts were trivial overlapping changes, so reasonably easy to resolve. Signed-off-by: David S. Miller <davem@davemloft.net>
| * | tcp: identify cryptic messages as TCP seq # bugsRandy Dunlap2018-07-181-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Attempt to make cryptic TCP seq number error messages clearer by (1) identifying the source of the message as "TCP", (2) identifying the errors as "seq # bug", and (3) grouping the field identifiers and values by separating them with commas. E.g., the following message is changed from: recvmsg bug 2: copied 73BCB6CD seq 70F17CBE rcvnxt 73BCB9AA fl 0 WARNING: CPU: 2 PID: 1501 at /linux/net/ipv4/tcp.c:1881 tcp_recvmsg+0x649/0xb90 to: TCP recvmsg seq # bug 2: copied 73BCB6CD, seq 70F17CBE, rcvnxt 73BCB9AA, fl 0 WARNING: CPU: 2 PID: 1501 at /linux/net/ipv4/tcp.c:2011 tcp_recvmsg+0x694/0xba0 Suggested-by: 積丹尼 Dan Jacobson <jidanni@jidanni.org> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | tcp: Fix broken repair socket window probe patchStefan Baranoff2018-07-161-6/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Correct previous bad attempt at allowing sockets to come out of TCP repair without sending window probes. To avoid changing size of the repair variable in struct tcp_sock, this lets the decision for sending probes or not to be made when coming out of repair by introducing two ways to turn it off. v2: * Remove erroneous comment; defines now make behavior clear Fixes: 70b7ff130224 ("tcp: allow user to create repair socket without window probes") Signed-off-by: Stefan Baranoff <sbaranoff@gmail.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Andrei Vagin <avagin@virtuozzo.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | ipv4/igmp: init group mode as INCLUDE when join source groupHangbin Liu2018-07-162-18/+44
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Based on RFC3376 5.1 If no interface state existed for that multicast address before the change (i.e., the change consisted of creating a new per-interface record), or if no state exists after the change (i.e., the change consisted of deleting a per-interface record), then the "non-existent" state is considered to have a filter mode of INCLUDE and an empty source list. Which means a new multicast group should start with state IN(). Function ip_mc_join_group() works correctly for IGMP ASM(Any-Source Multicast) mode. It adds a group with state EX() and inits crcount to mc_qrv, so the kernel will send a TO_EX() report message after adding group. But for IGMPv3 SSM(Source-specific multicast) JOIN_SOURCE_GROUP mode, we split the group joining into two steps. First we join the group like ASM, i.e. via ip_mc_join_group(). So the state changes from IN() to EX(). Then we add the source-specific address with INCLUDE mode. So the state changes from EX() to IN(A). Before the first step sends a group change record, we finished the second step. So we will only send the second change record. i.e. TO_IN(A). Regarding the RFC stands, we should actually send an ALLOW(A) message for SSM JOIN_SOURCE_GROUP as the state should mimic the 'IN() to IN(A)' transition. The issue was exposed by commit a052517a8ff65 ("net/multicast: should not send source list records when have filter mode change"). Before this change, we used to send both ALLOW(A) and TO_IN(A). After this change we only send TO_IN(A). Fix it by adding a new parameter to init group mode. Also add new wrapper functions so we don't need to change too much code. v1 -> v2: In my first version I only cleared the group change record. But this is not enough. Because when a new group join, it will init as EXCLUDE and trigger an filter mode change in ip/ip6_mc_add_src(), which will clear all source addresses' sf_crcount. This will prevent early joined address sending state change records if multi source addressed joined at the same time. In v2 patch, I fixed it by directly initializing the mode to INCLUDE for SSM JOIN_SOURCE_GROUP. I also split the original patch into two separated patches for IPv4 and IPv6. Fixes: a052517a8ff65 ("net/multicast: should not send source list records when have filter mode change") Reviewed-by: Stefano Brivio <sbrivio@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | tcp: remove DELAYED ACK events in DCTCPYuchung Cheng2018-07-132-29/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | After fixing the way DCTCP tracking delayed ACKs, the delayed-ACK related callbacks are no longer needed Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Lawrence Brakmo <brakmo@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | tcp: fix dctcp delayed ACK scheduleYuchung Cheng2018-07-131-2/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Previously, when a data segment was sent an ACK was piggybacked on the data segment without generating a CA_EVENT_NON_DELAYED_ACK event to notify congestion control modules. So the DCTCP ca->delayed_ack_reserved flag could incorrectly stay set when in fact there were no delayed ACKs being reserved. This could result in sending a special ECN notification ACK that carries an older ACK sequence, when in fact there was no need for such an ACK. DCTCP keeps track of the delayed ACK status with its own separate state ca->delayed_ack_reserved. Previously it may accidentally cancel the delayed ACK without updating this field upon sending a special ACK that carries a older ACK sequence. This inconsistency would lead to DCTCP receiver never acknowledging the latest data until the sender times out and retry in some cases. Packetdrill script (provided by Larry Brakmo) 0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 0.000 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0 0.000 bind(3, ..., ...) = 0 0.000 listen(3, 1) = 0 0.100 < [ect0] SEW 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> 0.100 > SE. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> 0.110 < [ect0] . 1:1(0) ack 1 win 257 0.200 accept(3, ..., ...) = 4 0.200 < [ect0] . 1:1001(1000) ack 1 win 257 0.200 > [ect01] . 1:1(0) ack 1001 0.200 write(4, ..., 1) = 1 0.200 > [ect01] P. 1:2(1) ack 1001 0.200 < [ect0] . 1001:2001(1000) ack 2 win 257 0.200 write(4, ..., 1) = 1 0.200 > [ect01] P. 2:3(1) ack 2001 0.200 < [ect0] . 2001:3001(1000) ack 3 win 257 0.200 < [ect0] . 3001:4001(1000) ack 3 win 257 0.200 > [ect01] . 3:3(0) ack 4001 0.210 < [ce] P. 4001:4501(500) ack 3 win 257 +0.001 read(4, ..., 4500) = 4500 +0 write(4, ..., 1) = 1 +0 > [ect01] PE. 3:4(1) ack 4501 +0.010 < [ect0] W. 4501:5501(1000) ack 4 win 257 // Previously the ACK sequence below would be 4501, causing a long RTO +0.040~+0.045 > [ect01] . 4:4(0) ack 5501 // delayed ack +0.311 < [ect0] . 5501:6501(1000) ack 4 win 257 // More data +0 > [ect01] . 4:4(0) ack 6501 // now acks everything +0.500 < F. 9501:9501(0) ack 4 win 257 Reported-by: Larry Brakmo <brakmo@fb.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Lawrence Brakmo <brakmo@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | tcp: allow user to create repair socket without window probesStefan Baranoff2018-07-121-3/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Under rare conditions where repair code may be used it is possible that window probes are either unnecessary or undesired. If the user knows that window probes are not wanted or needed this change allows them to skip sending them when a socket comes out of repair. Signed-off-by: Stefan Baranoff <sbaranoff@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | tcp: fix sequence numbers for repaired sockets re-using TIME-WAIT socketsStefan Baranoff2018-07-121-5/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes a bug where the sequence numbers of a socket created using TCP repair functionality are lower than set after connect is called. This occurs when the repair socket overlaps with a TIME-WAIT socket and triggers the re-use code. The amount lower is equal to the number of times that a particular IP/port set is re-used and then put back into TIME-WAIT. Re-using the first time the sequence number is 1 lower, closing that socket and then re-opening (with repair) a new socket with the same addresses/ports puts the sequence number 2 lower than set via setsockopt. The third time is 3 lower, etc. I have not tested what the limit of this acrewal is, if any. The fix is, if a socket is in repair mode, to respect the already set sequence number and timestamp when it would have already re-used the TIME-WAIT socket. Signed-off-by: Stefan Baranoff <sbaranoff@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-09 00:37:55 +0000