summaryrefslogtreecommitdiff
path: root/net/sctp/outqueue.c
AgeCommit message (Collapse)Author
2019-01-30sctp: add SCTP_FUTURE_ASOC and SCTP_CURRENT_ASSOC for SCTP_STREAM_SCHEDULER ↵Xin Long
sockopt Check with SCTP_ALL_ASSOC instead in sctp_setsockopt_scheduler and check with SCTP_FUTURE_ASSOC instead in sctp_getsockopt_scheduler, it's compatible with 0. SCTP_CURRENT_ASSOC is supported for SCTP_STREAM_SCHEDULER in this patch. It also adds default_ss in sctp_sock to support SCTP_FUTURE_ASSOC. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-03sctp: define SCTP_SS_DEFAULT for Stream schedulersXin Long
According to rfc8260#section-4.3.2, SCTP_SS_DEFAULT is required to defined as SCTP_SS_FCFS or SCTP_SS_RR. SCTP_SS_FCFS is used for SCTP_SS_DEFAULT's value in this patch. Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations") Reported-by: Jianwen Ji <jiji@redhat.com> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-18sctp: count both sk and asoc sndbuf with skb truesize and sctp_chunk sizeXin Long
Now it's confusing that asoc sndbuf_used is doing memory accounting with SCTP_DATA_SNDSIZE(chunk) + sizeof(sk_buff) + sizeof(sctp_chunk) while sk sk_wmem_alloc is doing that with skb->truesize + sizeof(sctp_chunk). It also causes sctp_prsctp_prune to count with a wrong freed memory when sndbuf_policy is not set. To make this right and also keep consistent between asoc sndbuf_used, sk sk_wmem_alloc and sk_wmem_queued, use skb->truesize + sizeof(sctp_chunk) for them. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-03sctp: fix fall-through annotationGustavo A. R. Silva
Replace "fallthru" with a proper "fall through" annotation. This fix is part of the ongoing efforts to enabling -Wimplicit-fallthrough Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-11net/sctp: Make wrappers for accessing in/out streamsKonstantin Khorenko
This patch introduces wrappers for accessing in/out streams indirectly. This will enable to replace physically contiguous memory arrays of streams with flexible arrays (or maybe any other appropriate mechanism) which do memory allocation on a per-page basis. Signed-off-by: Oleg Babin <obabin@virtuozzo.com> Signed-off-by: Konstantin Khorenko <khorenko@virtuozzo.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-14sctp: checkpatch fixupsMarcelo Ricardo Leitner
A collection of fixups from previous patches, left for later to not introduce unnecessary changes while moving code around. Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-14sctp: add asoc and packet to sctp_flush_ctxMarcelo Ricardo Leitner
Pre-compute these so the compiler won't reload them (due to no-strict-aliasing). Changes since v2: - Do not replace a return with a break in sctp_outq_flush_data Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-14sctp: add sctp_flush_ctx, a context struct on outq_flush routinesMarcelo Ricardo Leitner
With this struct we avoid passing lots of variables around and taking care of updating the current transport/packet. Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-14sctp: rework switch cases in sctp_outq_flush_dataMarcelo Ricardo Leitner
Remove an inner one, which tended to be error prone due to the cascading and it can be replaced by a simple if (). Rework the outer one so that the actual flush code is not inside it. Now we first validate if we can or cannot send data, return if not, and then the flush code. Suggested-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-14sctp: make use of gfp on retransmissionsMarcelo Ricardo Leitner
Retransmissions may be triggered when in user context, so lets make use of gfp. Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-14sctp: move transport flush code out of sctp_outq_flushMarcelo Ricardo Leitner
To the new sctp_outq_flush_transports. Comment on Nagle is outdated and removed. Nagle is performed earlier, while checking if the chunk fits the packet: if the outq length is not enough to fill the packet, it returns SCTP_XMIT_DELAY. So by when it gets to sctp_outq_flush_transports, it has to go through all enlisted transports. Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-14sctp: move flushing of data chunks out of sctp_outq_flushMarcelo Ricardo Leitner
To the new sctp_outq_flush_data. Again, smaller functions and with well defined objectives. Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-14sctp: move outq data rtx code out of sctp_outq_flushMarcelo Ricardo Leitner
This patch renames current sctp_outq_flush_rtx to __sctp_outq_flush_rtx and create a new sctp_outq_flush_rtx, with the code that was on sctp_outq_flush. Again, the idea is to have functions with small and defined objectives. Yes, there is an open-coded path selection in the now sctp_outq_flush_rtx. That is kept as is for now because it may be very different when we implement retransmission path selection algorithms for CMT-SCTP. Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-14sctp: move the flush of ctrl chunks into its own functionMarcelo Ricardo Leitner
Named sctp_outq_flush_ctrl and, with that, keep the contexts contained. One small fix embedded is the reset of one_packet at every iteration. This allows bundling of some control chunks in case they were preceeded by another control chunk that cannot be bundled. Other than this, it has the same behavior. Changes since v2: - Fixed panic reported by kbuild test robot if building with only up to this patch applied, due to bad parameter to sctp_outq_select_transport and by not initializing packet after calling sctp_outq_flush_ctrl. Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-14sctp: factor out sctp_outq_select_transportMarcelo Ricardo Leitner
We had two spots doing such complex operation and they were very close to each other, a bit more tailored to here or there. This patch unifies these under the same function, sctp_outq_select_transport, which knows how to handle control chunks and original transmissions (but not retransmissions). Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-14sctp: add sctp_packet_singletonMarcelo Ricardo Leitner
Factor out the code for generating singletons. It's used only once, but helps to keep the context contained. The const variables are to ease the reading of subsequent calls in there. Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-25sctp: fix identification of new acks for SFR-CACCMarcelo Ricardo Leitner
It's currently written as: if (!tchunk->tsn_gap_acked) { [1] tchunk->tsn_gap_acked = 1; ... } if (TSN_lte(tsn, sack_ctsn)) { if (!tchunk->tsn_gap_acked) { /* SFR-CACC processing */ ... } } Which causes the SFR-CACC processing on ack reception to never process, as tchunk->tsn_gap_acked is always true by then. Block [1] was moved to that position by the commit marked below. This patch fixes it by doing SFR-CACC processing earlier, before tsn_gap_acked is set to true. Fixes: 31b02e154940 ("sctp: Failover transmitted list on transport delete") Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Reviewed-by: Xin Long <lucien.xin@gmail.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-01-17Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller
Overlapping changes all over. The mini-qdisc bits were a little bit tricky, however. Signed-off-by: David S. Miller <davem@davemloft.net>
2018-01-15sctp: avoid compiler warning on implicit fallthruMarcelo Ricardo Leitner
These fall-through are expected. Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-15sctp: implement generate_ftsn for sctp_stream_interleaveXin Long
generate_ftsn is added as a member of sctp_stream_interleave, used to create fwdtsn or ifwdtsn chunk according to abandoned chunks, called in sctp_retransmit and sctp_outq_sack. sctp_generate_iftsn works for ifwdtsn, and sctp_generate_fwdtsn is still used for making fwdtsn. Signed-off-by: Xin Long <lucien.xin@gmail.com> Acked-by: Marcelo R. Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-01sctp: do not abandon the other frags in unsent outq if one msg has ↵Xin Long
outstanding frags Now for the abandoned chunks in unsent outq, it would just free the chunks. Because no tsn is assigned to them yet, there's no need to send fwd tsn to peer, unlike for the abandoned chunks in sent outq. The problem is when parts of the msg have been sent and the other frags are still in unsent outq, if they are abandoned/dropped, the peer would never get this msg reassembled. So these frags in unsent outq can't be dropped if this msg already has outstanding frags. This patch does the check in sctp_chunk_abandoned and sctp_prsctp_prune_unsent. Signed-off-by: Xin Long <lucien.xin@gmail.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-01sctp: abandon the whole msg if one part of a fragmented message is abandonedXin Long
As rfc3758#section-3.1 demands: A3) When a TSN is "abandoned", if it is part of a fragmented message, all other TSN's within that fragmented message MUST be abandoned at the same time. Besides, if it couldn't handle this, the rest frags would never get assembled in peer side. This patch supports it by adding abandoned flag in sctp_datamsg, when one chunk is being abandoned, set chunk->msg->abandoned as well. Next time when checking for abandoned, go checking chunk->msg->abandoned first. Signed-off-by: Xin Long <lucien.xin@gmail.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-01sctp: only update outstanding_bytes for transmitted queue when doing ↵Xin Long
prsctp_prune Now outstanding_bytes is only increased when appending chunks into one packet and sending it at 1st time, while decreased when it is about to move into retransmit queue. It means outstanding_bytes value is already decreased for all chunks in retransmit queue. However sctp_prsctp_prune_sent is a common function to check the chunks in both transmitted and retransmit queue, it decrease outstanding_bytes when moving a chunk into abandoned queue from either of them. It could cause outstanding_bytes underflow, as it also decreases it's value for the chunks in retransmit queue. This patch fixes it by only updating outstanding_bytes for transmitted queue when pruning queues for prsctp prio policy, the same fix is also needed in sctp_check_transmitted. Fixes: 8dbdf1f5b09c ("sctp: implement prsctp PRIO policy") Signed-off-by: Xin Long <lucien.xin@gmail.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-03sctp: introduce stream scheduler foundationsMarcelo Ricardo Leitner
This patch introduces the hooks necessary to do stream scheduling, as per RFC Draft ndata. It also introduces the first scheduler, which is what we do today but now factored out: first come first served (FCFS). With stream scheduling now we have to track which chunk was enqueued on which stream and be able to select another other than the in front of the main outqueue. So we introduce a list on sctp_stream_out_ext structure for this purpose. We reuse sctp_chunk->transmitted_list space for the list above, as the chunk cannot belong to the two lists at the same time. By using the union in there, we can have distinct names for these moments. sctp_sched_ops are the operations expected to be implemented by each scheduler. The dequeueing is a bit particular to this implementation but it is to match how we dequeue packets today. We first dequeue and then check if it fits the packet and if not, we requeue it at head. Thus why we don't have a peek operation but have dequeue_done instead, which is called once the chunk can be safely considered as transmitted. The check removed from sctp_outq_flush is now performed by sctp_stream_outq_migrate, which is only called during assoc setup. (sctp_sendmsg() also checks for it) The only operation that is foreseen but not yet added here is a way to signalize that a new packet is starting or that the packet is done, for round robin scheduler per packet, but is intentionally left to the patch that actually implements it. Support for I-DATA chunks, also described in this RFC, with user message interleaving is straightforward as it just requires the schedulers to probe for the feature and ignore datamsg boundaries when dequeueing. See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13 Tested-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-03sctp: introduce struct sctp_stream_out_extMarcelo Ricardo Leitner
With the stream schedulers, sctp_stream_out will become too big to be allocated by kmalloc and as we need to allocate with BH disabled, we cannot use __vmalloc in sctp_stream_init(). This patch moves out the stats from sctp_stream_out to sctp_stream_out_ext, which will be allocated only when the application tries to sendmsg something on it. Just the introduction of sctp_stream_out_ext would already fix the issue described above by splitting the allocation in two. Moving the stats to it also reduces the pressure on the allocator as we will ask for less memory atomically when creating the socket and we will use GFP_KERNEL later. Then, for stream schedulers, we will just use sctp_stream_out_ext. Tested-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-06sctp: remove the typedef sctp_xmit_tXin Long
This patch is to remove the typedef sctp_xmit_t, and replace with enum sctp_xmit in the places where it's using this typedef. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-06sctp: remove the typedef sctp_retransmit_reason_tXin Long
This patch is to remove the typedef sctp_retransmit_reason_t, and replace with enum sctp_retransmit_reason in the places where it's using this typedef. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-24sctp: remove the typedef sctp_sack_variable_tXin Long
This patch is to remove the typedef sctp_sack_variable_t, and replace with union sctp_sack_variable in the places where it's using this typedef. It is also to fix some indents in sctp_acked(). Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-01net: convert sk_buff.users from atomic_t to refcount_tReshetova, Elena
refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova <elena.reshetova@intel.com> Signed-off-by: Hans Liljestrand <ishkamiel@gmail.com> Signed-off-by: Kees Cook <keescook@chromium.org> Signed-off-by: David Windsor <dwindsor@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-02sctp: define the member stream as an object instead of pointer in asocXin Long
As Marcelo's suggestion, stream is a fixed size member of asoc and would not grow with more streams. To avoid an allocation for it, this patch is to define it as an object instead of pointer and update the places using it, also create sctp_stream_update() called in sctp_assoc_update() to migrate the stream info from one stream to another. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-06Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller
Mostly simple cases of overlapping changes (adding code nearby, a function whose name changes, for example). Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-03sctp: add SCTP_PR_STREAM_STATUS sockopt for prsctpXin Long
Before when implementing sctp prsctp, SCTP_PR_STREAM_STATUS wasn't added, as it needs to save abandoned_(un)sent for every stream. After sctp stream reconf is added in sctp, assoc has structure sctp_stream_out to save per stream info. This patch is to add SCTP_PR_STREAM_STATUS by putting the prsctp per stream statistics into sctp_stream_out. v1->v2: fix an indent issue. Signed-off-by: Xin Long <lucien.xin@gmail.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-01sctp: use right in and out stream cntXin Long
Since sctp reconf was added in sctp, the real cnt of in/out stream have not been c.sinit_max_instreams and c.sinit_num_ostreams any more. This patch is to replace them with stream->in/outcnt. Signed-off-by: Xin Long <lucien.xin@gmail.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-21sctp: out_qlen should be updated when pruning unsent queueXin Long
This patch is to fix the issue that sctp_prsctp_prune_sent forgot to update q->out_qlen when removing a chunk from unsent queue. Fixes: 8dbdf1f5b09c ("sctp: implement prsctp PRIO policy") Signed-off-by: Xin Long <lucien.xin@gmail.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07sctp: add dst_pending_confirm flagJulian Anastasov
Add new transport flag to allow sockets to confirm neighbour. When same struct dst_entry can be used for many different neighbours we can not use it for pending confirmations. The flag is propagated from transport to every packet. It is reset when cached dst is reset. Reported-by: YueHaibing <yuehaibing@huawei.com> Fixes: 5110effee8fd ("net: Do delayed neigh confirmation.") Fixes: f2bb4bedf35d ("ipv4: Cache output routes in fib_info nexthops.") Signed-off-by: Julian Anastasov <ja@ssi.bg> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-18sctp: implement sender-side procedures for SSN Reset Request ParameterXin Long
This patch is to implement sender-side procedures for the Outgoing and Incoming SSN Reset Request Parameter described in rfc6525 section 5.1.2 and 5.1.3. It is also add sockopt SCTP_RESET_STREAMS in rfc6525 section 6.3.2 for users. Note that the new asoc member strreset_outstanding is to make sure only one reconf request chunk on the fly as rfc6525 section 5.1.1 demands. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-11sctp: Fix spelling mistake: "Atempt" -> "Attempt"Colin Ian King
Trivial fix to spelling mistake in WARN_ONCE message Signed-off-by: Colin Ian King <colin.king@canonical.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-13sctp: reuse sent_count to avoid retransmitted chunks for RTT measurementsXin Long
Now sctp uses chunk->resent to record if a chunk is retransmitted, for RTT measurements with retransmitted DATA chunks. chunk->sent_count was introduced to record how many times one chunk has been sent for prsctp RTX policy before. We actually can know if one chunk is retransmitted by checking chunk->sent_count is greater than 1. This patch is to remove resent from sctp_chunk and reuse sent_count to avoid retransmitted chunks for RTT measurements. Signed-off-by: Xin Long <lucien.xin@gmail.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-02Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller
Three sets of overlapping changes. Nothing serious. Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-30sctp: change to check peer prsctp_capable when using prsctp policesXin Long
Now before using prsctp polices, sctp uses asoc->prsctp_enable to check if prsctp is enabled. However asoc->prsctp_enable is set only means local host support prsctp, sctp should not abandon packet if peer host doesn't enable prsctp. So this patch is to use asoc->peer.prsctp_capable to check if prsctp is enabled on both side, instead of asoc->prsctp_enable, as asoc's peer.prsctp_capable is set only when local and peer both enable prsctp. Fixes: a6c2f792873a ("sctp: implement prsctp TTL policy") Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-30sctp: remove prsctp_param from sctp_chunkXin Long
Now sctp uses chunk->prsctp_param to save the prsctp param for all the prsctp polices, we didn't need to introduce prsctp_param to sctp_chunk. We can just use chunk->sinfo.sinfo_timetolive for RTX and BUF polices, and reuse msg->expires_at for TTL policy, as the prsctp polices and old expires policy are mutual exclusive. This patch is to remove prsctp_param from sctp_chunk, and reuse msg's expires_at for TTL and chunk's sinfo.sinfo_timetolive for RTX and BUF polices. Note that sctp can't use chunk's sinfo.sinfo_timetolive for TTL policy, as it needs a u64 variables to save the expires_at time. This one also fixes the "netperf-Throughput_Mbps -37.2% regression" issue. Fixes: a6c2f792873a ("sctp: implement prsctp TTL policy") Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-23sctp: fix the handling of SACK Gap Ack blocksMarcelo Ricardo Leitner
sctp_acked() is using 32bit arithmetics on 16bits vars, via TSN_lte() macros, which is weird and confusing. Once the offset to ctsn is calculated, all wrapping is already handled and thus to verify the Gap Ack blocks we can just use pure less/big-or-equal than checks. Also, rename gap variable to tsn_offset, so it's more meaningful, as it doesn't point to any gap at all. Even so, I don't think this discrepancy resulted in any practical bug. This patch is a preparation for the next one, which will introduce typecheck() for TSN_lte() macros and would cause a compile error here. Suggested-by: David Laight <David.Laight@ACULAB.COM> Reported-by: David Laight <David.Laight@ACULAB.COM> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-18sctp: make sctp_outq_flush/tail/uncork return voidXin Long
sctp_outq_flush return value is meaningless now, this patch is to make sctp_outq_flush return void, as well as sctp_outq_fail and sctp_outq_uncork. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-18sctp: save transmit error to sk_err in sctp_outq_flushXin Long
Every time when sctp calls sctp_outq_flush, it sends out the chunks of control queue, retransmit queue and data queue. Even if some trunks are failed to transmit, it still has to flush all the transports, as it's the only chance to clean that transmit_list. So the latest transmit error here should be returned back. This transmit error is an internal error of sctp stack. I checked all the places where it uses the transmit error (the return value of sctp_outq_flush), most of them are actually just save it to sk_err. Except for sctp_assoc/endpoint_bh_rcv, they will drop the chunk if it's failed to send a REPLY, which is actually incorrect, as we can't be sure the error that sctp_outq_flush returns is from sending that REPLY. So it's meaningless for sctp_outq_flush to return error back. This patch is to save transmit error to sk_err in sctp_outq_flush, the new error can update the old value. Eventually, sctp_wait_for_* would check for it. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-18sctp: free msg->chunks when sctp_primitive_SEND return errXin Long
Last patch "sctp: do not return the transmit err back to sctp_sendmsg" made sctp_primitive_SEND return err only when asoc state is unavailable. In this case, chunks are not enqueued, they have no chance to be freed if we don't take care of them later. This Patch is actually to revert commit 1cd4d5c4326a ("sctp: remove the unused sctp_datamsg_free()"), commit 69b5777f2e57 ("sctp: hold the chunks only after the chunk is enqueued in outq") and commit 8b570dc9f7b6 ("sctp: only drop the reference on the datamsg after sending a msg"), to use sctp_datamsg_free to free the chunks of current msg. Fixes: 8b570dc9f7b6 ("sctp: only drop the reference on the datamsg after sending a msg") Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-18sctp: remove the unnecessary state check in sctp_outq_tailXin Long
Data Chunks are only sent by sctp_primitive_SEND, in which sctp checks the asoc's state through statetable before calling sctp_outq_tail. So there's no need to check the asoc's state again in sctp_outq_tail. Besides, sctp_do_sm is protected by lock_sock, even if sending msg is interrupted by timer events, the event's processes still need to acquire lock_sock first. It means no others CMDs can be enqueue into side effect list before CMD_SEND_MSG to change asoc->state, so it's safe to remove it. This patch is to remove redundant asoc->state check from sctp_outq_tail. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-11sctp: implement prsctp PRIO policyXin Long
prsctp PRIO policy is a policy to abandon lower priority chunks when asoc doesn't have enough snd buffer, so that the current chunk with higher priority can be queued successfully. Similar to TTL/RTX policy, we will set the priority of the chunk to prsctp_param with sinfo->sinfo_timetolive in sctp_set_prsctp_policy(). So if PRIO policy is enabled, msg->expire_at won't work. asoc->sent_cnt_removable will record how many chunks can be checked to remove. If priority policy is enabled, when the chunk is queued into the out_queue, we will increase sent_cnt_removable. When the chunk is moved to abandon_queue or dequeue and free, we will decrease sent_cnt_removable. In sctp_sendmsg, we will check if there is enough snd buffer for current msg and if sent_cnt_removable is not 0. Then try to abandon chunks in sctp_prune_prsctp when sendmsg from the retransmit/transmited queue, and free chunks from out_queue in right order until the abandon+free size > msg_len - sctp_wfree. For the abandon size, we have to wait until it sends FORWARD TSN, receives the sack and the chunks are really freed. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-10sctp: avoid refreshing heartbeat timer too oftenMarcelo Ricardo Leitner
Currently on high rate SCTP streams the heartbeat timer refresh can consume quite a lot of resources as timer updates are costly and it contains a random factor, which a) is also costly and b) invalidates mod_timer() optimization for not editing a timer to the same value. It may even cause the timer to be slightly advanced, for no good reason. As suggested by David Laight this patch now removes this timer update from hot path by leaving the timer on and re-evaluating upon its expiration if the heartbeat is still needed or not, similarly to what is done for TCP. If it's not needed anymore the timer is re-scheduled to the new timeout, considering the time already elapsed. For this, we now record the last tx timestamp per transport, updated in the same spots as hb timer was restarted on tx. Also split up sctp_transport_reset_timers into sctp_transport_reset_t3_rtx and sctp_transport_reset_hb_timer, so we can re-arm T3 without re-arming the heartbeat one. On loopback with MTU of 65535 and data chunks with 1636, so that we have a considerable amount of chunks without stressing system calls, netperf -t SCTP_STREAM -l 30, perf looked like this before: Samples: 103K of event 'cpu-clock', Event count (approx.): 25833000000 Overhead Command Shared Object Symbol + 6,15% netperf [kernel.vmlinux] [k] copy_user_enhanced_fast_string - 5,43% netperf [kernel.vmlinux] [k] _raw_write_unlock_irqrestore - _raw_write_unlock_irqrestore - 96,54% _raw_spin_unlock_irqrestore - 36,14% mod_timer + 97,24% sctp_transport_reset_timers + 2,76% sctp_do_sm + 33,65% __wake_up_sync_key + 28,77% sctp_ulpq_tail_event + 1,40% del_timer - 1,84% mod_timer + 99,03% sctp_transport_reset_timers + 0,97% sctp_do_sm + 1,50% sctp_ulpq_tail_event And after this patch, now with netperf -l 60: Samples: 230K of event 'cpu-clock', Event count (approx.): 57707250000 Overhead Command Shared Object Symbol + 5,65% netperf [kernel.vmlinux] [k] memcpy_erms + 5,59% netperf [kernel.vmlinux] [k] copy_user_enhanced_fast_string - 5,05% netperf [kernel.vmlinux] [k] _raw_spin_unlock_irqrestore - _raw_spin_unlock_irqrestore + 49,89% __wake_up_sync_key + 45,68% sctp_ulpq_tail_event - 2,85% mod_timer + 76,51% sctp_transport_reset_t3_rtx + 23,49% sctp_do_sm + 1,55% del_timer + 2,50% netperf [sctp] [k] sctp_datamsg_from_user + 2,26% netperf [sctp] [k] sctp_sendmsg Throughput-wise, from 6800mbps without the patch to 7050mbps with it, ~3.7%. Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-03-20sctp: do not leak chunks that are sent to unconfirmed pathsMarcelo Ricardo Leitner
Currently, if a chunk is scheduled to be sent through a transport that is currently unconfirmed, it will be leaked as it is dequeued from outq and is not re-queued nor freed. As I'm not aware of any situation that may lead to this situation, I'm fixing this by freeing the chunk and also logging a trace so that we can fix the other bug if it ever happens. Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-03-13sctp: allow sctp_transmit_packet and others to use gfpMarcelo Ricardo Leitner
Currently sctp_sendmsg() triggers some calls that will allocate memory with GFP_ATOMIC even when not necessary. In the case of sctp_packet_transmit it will allocate a linear skb that will be used to construct the packet and this may cause sends to fail due to ENOMEM more often than anticipated specially with big MTUs. This patch thus allows it to inherit gfp flags from upper calls so that it can use GFP_KERNEL if it was triggered by a sctp_sendmsg call or similar. All others, like retransmits or flushes started from BH, are still allocated using GFP_ATOMIC. In netperf tests this didn't result in any performance drawbacks when memory is not too fragmented and made it trigger ENOMEM way less often. Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>