This patch is to add reconf_enable field in all of asoc ep and netns
to indicate if they support stream reset.
When initializing, asoc reconf_enable get the default value from ep
reconf_enable which is from netns netns reconf_enable by default.
It is also to add reconf_capable in asoc peer part to know if peer
supports reconf_enable, the value is set if ext params have reconf
chunk support when processing init chunk, just 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>
This patch is to add a per transport timer based on sctp timer frame
for stream reconf chunk retransmission. It would start after sending
a reconf request chunk, and stop after receiving the response chunk.
If the timer expires, besides retransmitting the reconf request chunk,
it would also do the same thing with data RTO timer. like to increase
the appropriate error counts, and perform threshold management, possibly
destroying the asoc if sctp retransmission thresholds are exceeded, just
as section 5.1.1 describes.
This patch is also to add asoc strreset_chunk, it is used to save the
reconf request chunk, so that it can be retransmitted, and to check if
the response is really for this request by comparing the information
inside with the response chunk as well.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is to add asoc strreset_outseq and strreset_inseq for
saving the reconf request sequence, initialize them when create
assoc and process init, and also to define Incoming and Outgoing
SSN Reset Request Parameter described in rfc6525 section 4.1 and
4.2, As they can be in one same chunk as section rfc6525 3.1-3
describes, it makes them in one function.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
sctp stream reconf, described in RFC 6525, needs a structure to
save per stream information in assoc, like stream state.
In the future, sctp stream scheduler also needs it to save some
stream scheduler params and queues.
This patchset is to prepare the stream array in assoc for stream
reconf. It defines sctp_stream that includes stream arrays inside
to replace ssnmap.
Note that we use different structures for IN and OUT streams, as
the members in per OUT stream will get more and more different
from per IN stream.
v1->v2:
- put these patches into a smaller group.
v2->v3:
- define sctp_stream to contain stream arrays, and create stream.c
to put stream-related functions.
- merge 3 patches into 1, as new sctp_stream has the same name
with before.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is no reason to use this cascading. It doesn't add anything.
Let's remove it and simplify.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now sctp transport rhashtable uses hash(lport, dport, daddr) as the key
to hash a node to one chain. If in one host thousands of assocs connect
to one server with the same lport and different laddrs (although it's
not a normal case), all the transports would be hashed into the same
chain.
It may cause to keep returning -EBUSY when inserting a new node, as the
chain is too long and sctp inserts a transport node in a loop, which
could even lead to system hangs there.
The new rhlist interface works for this case that there are many nodes
with the same key in one chain. It puts them into a list then makes this
list be as a node of the chain.
This patch is to replace rhashtable_ interface with rhltable_ interface.
Since a chain would not be too long and it would not return -EBUSY with
this fix when inserting a node, the reinsert loop is also removed here.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The prsctp polices include ttl expires policy already, we should remove
the old ttl expires codes, and just adjust the new polices' codes to be
compatible with the old one for users.
This patch is to remove all the old expires codes, and if prsctp polices
are not set, it will still set msg's expires_at and check the expires in
sctp_check_abandoned.
Note that asoc->prsctp_enable is set by default, so users can't feel any
difference even if they use the old expires api in userspace.
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>
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>
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: a6c2f79287 ("sctp: implement prsctp TTL policy")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now pahole sctp_chunk, it has 2 memory holes:
struct sctp_chunk {
struct list_head list;
atomic_t refcnt;
/* XXX 4 bytes hole, try to pack */
...
long unsigned int prsctp_param;
int sent_count;
/* XXX 4 bytes hole, try to pack */
This patch is to move up sent_count to fill the 1st one and eliminate
the 2nd one.
It's not just another struct compaction, it also fixes the "netperf-
Throughput_Mbps -37.2% regression" issue when overloading the CPU.
Fixes: a6c2f79287 ("sctp: implement prsctp TTL policy")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
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>
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 1cd4d5c432 ("sctp: remove the
unused sctp_datamsg_free()"), commit 69b5777f2e ("sctp: hold the chunks
only after the chunk is enqueued in outq") and commit 8b570dc9f7 ("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: 8b570dc9f7 ("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>
Identifying address family operations during rx path is not something
expensive but it's ugly to the eye to have it done multiple times,
specially when we already validated it during initial rx processing.
This patch takes advantage of the now shared sctp_input_cb and make the
pointer to the operations readily available.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
SCTP will try to access original IP headers on sctp_recvmsg in order to
copy the addresses used. There are also other places that do similar access
to IP or even SCTP headers. But after 90017accff ("sctp: Add GSO
support") they aren't always there because they are only present in the
header skb.
SCTP handles the queueing of incoming data by cloning the incoming skb
and limiting to only the relevant payload. This clone has its cb updated
to something different and it's then queued on socket rx queue. Thus we
need to fix this in two moments.
For rx path, not related to socket queue yet, this patch uses a
partially copied sctp_input_cb to such GSO frags. This restores the
ability to access the headers for this part of the code.
Regarding the socket rx queue, it removes iif member from sctp_event and
also add a chunk pointer on it.
With these changes we're always able to reach the headers again.
The biggest change here is that now the sctp_chunk struct and the
original skb are only freed after the application consumed the buffer.
Note however that the original payload was already like this due to the
skb cloning.
For iif, SCTP's IPv4 code doesn't use it, so no change is necessary.
IPv6 now can fetch it directly from original's IPv6 CB as the original
skb is still accessible.
In the future we probably can simplify sctp_v*_skb_iif() stuff, as
sctp_v4_skb_iif() was called but it's return value not used, and now
it's not even called, but such cleanup is out of scope for this change.
Fixes: 90017accff ("sctp: Add GSO support")
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We process input path in other files too and having access to it is
nice, so move it to a header where it's shared.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
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>
prsctp TTL policy is a policy to abandon chunks when they expire
at the specific time in local stack. It's similar with expires_at
in struct sctp_datamsg.
This patch uses sinfo->sinfo_timetolive to set the specific time for
TTL policy. sinfo->sinfo_timetolive is also used for msg->expires_at.
So if prsctp_enable or TTL policy is not enabled, msg->expires_at
still works as before.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds SCTP_PR_ASSOC_STATUS to sctp sockopt, which is used
to dump the prsctp statistics info from the asoc. The prsctp statistics
includes abandoned_sent/unsent from the asoc. abandoned_sent is the
count of the packets we drop packets from retransmit/transmited queue,
and abandoned_unsent is the count of the packets we drop from out_queue
according to the policy.
Note: another option for prsctp statistics dump described in rfc is
SCTP_PR_STREAM_STATUS, which is used to dump the prsctp statistics
info from each stream. But by now, linux doesn't yet have per stream
statistics info, it needs rfc6525 to be implemented. As the prsctp
statistics for each stream has to be based on per stream statistics,
we will delay it until rfc6525 is done in linux.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
According to section 4.5 of rfc7496, prsctp_enable should be per asoc.
We will add prsctp_enable to both asoc and ep, and replace the places
where it used net.sctp->prsctp_enable with asoc->prsctp_enable.
ep->prsctp_enable will be initialized with net.sctp->prsctp_enable, and
asoc->prsctp_enable will be initialized with ep->prsctp_enable. We can
also modify it's value through sockopt SCTP_PR_SUPPORTED.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
SCTP has this pecualiarity that its packets cannot be just segmented to
(P)MTU. Its chunks must be contained in IP segments, padding respected.
So we can't just generate a big skb, set gso_size to the fragmentation
point and deliver it to IP layer.
This patch takes a different approach. SCTP will now build a skb as it
would be if it was received using GRO. That is, there will be a cover
skb with protocol headers and children ones containing the actual
segments, already segmented to a way that respects SCTP RFCs.
With that, we can tell skb_segment() to just split based on frag_list,
trusting its sizes are already in accordance.
This way SCTP can benefit from GSO and instead of passing several
packets through the stack, it can pass a single large packet.
v2:
- Added support for receiving GSO frames, as requested by Dave Miller.
- Clear skb->cb if packet is GSO (otherwise it's not used by SCTP)
- Added heuristics similar to what we have in TCP for not generating
single GSO packets that fills cwnd.
v3:
- consider sctphdr size in skb_gso_transport_seglen()
- rebased due to 5c7cdf339a ("gso: Remove arbitrary checks for
unsupported GSO")
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Tested-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Dave Miller pointed out that fb586f2530 ("sctp: delay calls to
sk_data_ready() as much as possible") may insert latency specially if
the receiving application is running on another CPU and that it would be
better if we signalled as early as possible.
This patch thus basically inverts the logic on fb586f2530 and signals
it as early as possible, similar to what we had before.
Fixes: fb586f2530 ("sctp: delay calls to sk_data_ready() as much as possible")
Reported-by: Dave Miller <davem@davemloft.net>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts were two cases of simple overlapping changes,
nothing serious.
In the UDP case, we need to add a hlist_add_tail_rcu()
to linux/rculist.h, because we've moved UDP socket handling
away from using nulls lists.
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently processing of multiple chunks in a single SCTP packet leads to
multiple calls to sk_data_ready, causing multiple wake up signals which
are costy and doesn't make it wake up any faster.
With this patch it will note that the wake up is pending and will do it
before leaving the state machine interpreter, latest place possible to
do it realiably and cleanly.
Note that sk_data_ready events are not dependent on asocs, unlike waking
up writers.
v2: series re-checked
v3: use local vars to cleanup the code, suggested by Jakub Sitnicki
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It wastes space and gets worse as we add new flags, so convert bit-wide
flags to a bitfield.
Currently it already saves 4 bytes in sctp_sock, which are left as holes
in it for now. The whole struct needs packing, which should be done in
another patch.
Note that do_auto_asconf cannot be merged, as explained in the comment
before it.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
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>
Pull networking updates from David Miller:
"Highlights:
1) Support more Realtek wireless chips, from Jes Sorenson.
2) New BPF types for per-cpu hash and arrap maps, from Alexei
Starovoitov.
3) Make several TCP sysctls per-namespace, from Nikolay Borisov.
4) Allow the use of SO_REUSEPORT in order to do per-thread processing
of incoming TCP/UDP connections. The muxing can be done using a
BPF program which hashes the incoming packet. From Craig Gallek.
5) Add a multiplexer for TCP streams, to provide a messaged based
interface. BPF programs can be used to determine the message
boundaries. From Tom Herbert.
6) Add 802.1AE MACSEC support, from Sabrina Dubroca.
7) Avoid factorial complexity when taking down an inetdev interface
with lots of configured addresses. We were doing things like
traversing the entire address less for each address removed, and
flushing the entire netfilter conntrack table for every address as
well.
8) Add and use SKB bulk free infrastructure, from Jesper Brouer.
9) Allow offloading u32 classifiers to hardware, and implement for
ixgbe, from John Fastabend.
10) Allow configuring IRQ coalescing parameters on a per-queue basis,
from Kan Liang.
11) Extend ethtool so that larger link mode masks can be supported.
From David Decotigny.
12) Introduce devlink, which can be used to configure port link types
(ethernet vs Infiniband, etc.), port splitting, and switch device
level attributes as a whole. From Jiri Pirko.
13) Hardware offload support for flower classifiers, from Amir Vadai.
14) Add "Local Checksum Offload". Basically, for a tunneled packet
the checksum of the outer header is 'constant' (because with the
checksum field filled into the inner protocol header, the payload
of the outer frame checksums to 'zero'), and we can take advantage
of that in various ways. From Edward Cree"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits)
bonding: fix bond_get_stats()
net: bcmgenet: fix dma api length mismatch
net/mlx4_core: Fix backward compatibility on VFs
phy: mdio-thunder: Fix some Kconfig typos
lan78xx: add ndo_get_stats64
lan78xx: handle statistics counter rollover
RDS: TCP: Remove unused constant
RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket
net: smc911x: convert pxa dma to dmaengine
team: remove duplicate set of flag IFF_MULTICAST
bonding: remove duplicate set of flag IFF_MULTICAST
net: fix a comment typo
ethernet: micrel: fix some error codes
ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it
bpf, dst: add and use dst_tclassid helper
bpf: make skb->tc_classid also readable
net: mvneta: bm: clarify dependencies
cls_bpf: reset class and reuse major in da
ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c
ldmvsw: Add ldmvsw.c driver code
...
Pull crypto update from Herbert Xu:
"Here is the crypto update for 4.6:
API:
- Convert remaining crypto_hash users to shash or ahash, also convert
blkcipher/ablkcipher users to skcipher.
- Remove crypto_hash interface.
- Remove crypto_pcomp interface.
- Add crypto engine for async cipher drivers.
- Add akcipher documentation.
- Add skcipher documentation.
Algorithms:
- Rename crypto/crc32 to avoid name clash with lib/crc32.
- Fix bug in keywrap where we zero the wrong pointer.
Drivers:
- Support T5/M5, T7/M7 SPARC CPUs in n2 hwrng driver.
- Add PIC32 hwrng driver.
- Support BCM6368 in bcm63xx hwrng driver.
- Pack structs for 32-bit compat users in qat.
- Use crypto engine in omap-aes.
- Add support for sama5d2x SoCs in atmel-sha.
- Make atmel-sha available again.
- Make sahara hashing available again.
- Make ccp hashing available again.
- Make sha1-mb available again.
- Add support for multiple devices in ccp.
- Improve DMA performance in caam.
- Add hashing support to rockchip"
* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (116 commits)
crypto: qat - remove redundant arbiter configuration
crypto: ux500 - fix checks of error code returned by devm_ioremap_resource()
crypto: atmel - fix checks of error code returned by devm_ioremap_resource()
crypto: qat - Change the definition of icp_qat_uof_regtype
hwrng: exynos - use __maybe_unused to hide pm functions
crypto: ccp - Add abstraction for device-specific calls
crypto: ccp - CCP versioning support
crypto: ccp - Support for multiple CCPs
crypto: ccp - Remove check for x86 family and model
crypto: ccp - memset request context to zero during import
lib/mpi: use "static inline" instead of "extern inline"
lib/mpi: avoid assembler warning
hwrng: bcm63xx - fix non device tree compatibility
crypto: testmgr - allow rfc3686 aes-ctr variants in fips mode.
crypto: qat - The AE id should be less than the maximal AE number
lib/mpi: Endianness fix
crypto: rockchip - add hash support for crypto engine in rk3288
crypto: xts - fix compile errors
crypto: doc - add skcipher API documentation
crypto: doc - update AEAD AD handling
...
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>
Dmitry reported that sctp_add_bind_addr may read more bytes than
expected in case the parameter is a IPv4 addr supplied by the user
through calls such as sctp_bindx_add(), because it always copies
sizeof(union sctp_addr) while the buffer may be just a struct
sockaddr_in, which is smaller.
This patch then fixes it by limiting the memcpy to the min between the
union size and a (new parameter) provided addr size. Where possible this
parameter still is the size of that union, except for reading from
user-provided buffers, which then it accounts for protocol type.
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since commit 8b570dc9f7 ("sctp: only drop the reference on the datamsg
after sending a msg") used sctp_datamsg_put in sctp_sendmsg, instead of
sctp_datamsg_free, this function has no use in sctp.
So we will remove it.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After we use refcnt to check if transport is alive, the dead can be
removed from sctp_transport.
The traversal of transport_addr_list in procfs dump is using
list_for_each_entry_rcu, no need to check if it has been freed.
sctp_generate_t3_rtx_event and sctp_generate_heartbeat_event is
protected by sock lock, it's not necessary to check dead, either.
also, the timers are cancelled when sctp_transport_free() is
called, that it doesn't wait for refcnt to reach 0 to cancel them.
Signed-off-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>
Now when __sctp_lookup_association is running in BH, it will try to
check if t->dead is set, but meanwhile other CPUs may be freeing this
transport and this assoc and if it happens that
__sctp_lookup_association checked t->dead a bit too early, it may think
that the association is still good while it was already freed.
So we fix this race by using atomic_add_unless in sctp_transport_hold.
After we get one transport from hashtable, we will hold it only when
this transport's refcnt is not 0, so that we can make sure t->asoc
cannot be freed before we hold the asoc again.
Note that sctp association is not freed using RCU so we can't use
atomic_add_unless() with it as it may just be too late for that either.
Fixes: 4f00878126 ("sctp: apply rhashtable api to send/recv path")
Reported-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-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>
This patch replaces uses of the long obsolete hash interface with
shash.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: David S. Miller <davem@davemloft.net>
transport hashtable will replace the association hashtable,
so association hashtable is not used in sctp any more, so
drop the codes about that.
Signed-off-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>
tranport hashtbale will replace the association hashtable to do the
lookup for transport, and then get association by t->assoc, rhashtable
apis will be used because of it's resizable, scalable and using rcu.
lport + rport + paddr will be the base hashkey to locate the chain,
with net to protect one netns from another, then plus the laddr to
compare to get the target.
this patch will provider the lookup functions:
- sctp_epaddr_lookup_transport
- sctp_addrs_lookup_transport
hash/unhash functions:
- sctp_hash_transport
- sctp_unhash_transport
init/destroy functions:
- sctp_transport_hashtable_init
- sctp_transport_hashtable_destroy
Signed-off-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>
when A sends a data to B, then A close() and enter into SHUTDOWN_PENDING
state, if B neither claim his rwnd is 0 nor send SACK for this data, A
will keep retransmitting this data until t5 timeout, Max.Retrans times
can't work anymore, which is bad.
if B's rwnd is not 0, it should send abort after Max.Retrans times, only
when B's rwnd == 0 and A's retransmitting beyonds Max.Retrans times, A
will start t5 timer, which is also commit f8d9605243 ("sctp: Enforce
retransmission limit during shutdown") means, but it lacks the condition
peer rwnd == 0.
so fix it by adding a bit (zero_window_announced) in peer to record if
the last rwnd is 0. If it was, zero_window_announced will be set. and use
this bit to decide if start t5 timer when local.state is SHUTDOWN_PENDING.
Fixes: commit f8d9605243 ("sctp: Enforce retransmission limit during shutdown")
Signed-off-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>
They don't need to be any bigger than that and with this we start a new
bitfield for tracking association runtime stuff, like zero window
situation.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
->auto_asconf_splist is per namespace and mangled by functions like
sctp_setsockopt_auto_asconf() which doesn't guarantee any serialization.
Also, the call to inet_sk_copy_descendant() was backuping
->auto_asconf_list through the copy but was not honoring
->do_auto_asconf, which could lead to list corruption if it was
different between both sockets.
This commit thus fixes the list handling by using ->addr_wq_lock
spinlock to protect the list. A special handling is done upon socket
creation and destruction for that. Error handlig on sctp_init_sock()
will never return an error after having initialized asconf, so
sctp_destroy_sock() can be called without addrq_wq_lock. The lock now
will be take on sctp_close_sock(), before locking the socket, so we
don't do it in inverse order compared to sctp_addr_wq_timeout_handler().
Instead of taking the lock on sctp_sock_migrate() for copying and
restoring the list values, it's preferred to avoid rewritting it by
implementing sctp_copy_descendant().
Issue was found with a test application that kept flipping sysctl
default_auto_asconf on and off, but one could trigger it by issuing
simultaneous setsockopt() calls on multiple sockets or by
creating/destroying sockets fast enough. This is only triggerable
locally.
Fixes: 9f7d653b67 ("sctp: Add Auto-ASCONF support (core).")
Reported-by: Ji Jianwen <jiji@redhat.com>
Suggested-by: Neil Horman <nhorman@tuxdriver.com>
Suggested-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
sctp_addr_is_valid() only appeared in its definition.
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Sébastien Barré <sebastien.barre@uclouvain.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
The SCTP socket extensions API document describes the v4mapping option as
follows:
8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR)
This socket option is a Boolean flag which turns on or off the
mapping of IPv4 addresses. If this option is turned on, then IPv4
addresses will be mapped to V6 representation. If this option is
turned off, then no mapping will be done of V4 addresses and a user
will receive both PF_INET6 and PF_INET type addresses on the socket.
See [RFC3542] for more details on mapped V6 addresses.
This description isn't really in line with what the code does though.
Introduce addr_to_user (renamed addr_v4map), which should be called
before any sockaddr is passed back to user space. The new function
places the sockaddr into the correct format depending on the
SCTP_I_WANT_MAPPED_V4_ADDR option.
Audit all places that touched v4mapped and either sanely construct
a v4 or v6 address then call addr_to_user, or drop the
unnecessary v4mapped check entirely.
Audit all places that call addr_to_user and verify they are on a sycall
return path.
Add a custom getname that formats the address properly.
Several bugs are addressed:
- SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for
addresses to user space
- The addr_len returned from recvmsg was not correct when
returning AF_INET on a v6 socket
- flowlabel and scope_id were not zerod when promoting
a v4 to v6
- Some syscalls like bind and connect behaved differently
depending on v4mapped
Tested bind, getpeername, getsockname, connect, and recvmsg for proper
behaviour in v4mapped = 1 and 0 cases.
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch implements section 5.3.6. of RFC6458, that is, support
for 'SCTP Next Receive Information Structure' (SCTP_NXTINFO) which
is placed into ancillary data cmsghdr structure for each recvmsg()
call, if this information is already available when delivering the
current message.
This option can be enabled/disabled via setsockopt(2) on SOL_SCTP
level by setting an int value with 1/0 for SCTP_RECVNXTINFO in
user space applications as per RFC6458, section 8.1.30.
The sctp_nxtinfo structure is defined as per RFC as below ...
struct sctp_nxtinfo {
uint16_t nxt_sid;
uint16_t nxt_flags;
uint32_t nxt_ppid;
uint32_t nxt_length;
sctp_assoc_t nxt_assoc_id;
};
... and provided under cmsg_level IPPROTO_SCTP, cmsg_type
SCTP_NXTINFO, while cmsg_data[] contains struct sctp_nxtinfo.
Joint work with Daniel Borkmann.
Signed-off-by: Geir Ola Vaagland <geirola@gmail.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch implements section 5.3.5. of RFC6458, that is, support
for 'SCTP Receive Information Structure' (SCTP_RCVINFO) which is
placed into ancillary data cmsghdr structure for each recvmsg()
call.
This option can be enabled/disabled via setsockopt(2) on SOL_SCTP
level by setting an int value with 1/0 for SCTP_RECVRCVINFO in user
space applications as per RFC6458, section 8.1.29.
The sctp_rcvinfo structure is defined as per RFC as below ...
struct sctp_rcvinfo {
uint16_t rcv_sid;
uint16_t rcv_ssn;
uint16_t rcv_flags;
<-- 2 bytes hole -->
uint32_t rcv_ppid;
uint32_t rcv_tsn;
uint32_t rcv_cumtsn;
uint32_t rcv_context;
sctp_assoc_t rcv_assoc_id;
};
... and provided under cmsg_level IPPROTO_SCTP, cmsg_type
SCTP_RCVINFO, while cmsg_data[] contains struct sctp_rcvinfo.
An sctp_rcvinfo item always corresponds to the data in msg_iov.
Joint work with Daniel Borkmann.
Signed-off-by: Geir Ola Vaagland <geirola@gmail.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch implements section 5.3.4. of RFC6458, that is, support
for 'SCTP Send Information Structure' (SCTP_SNDINFO) which can be
placed into ancillary data cmsghdr structure for sendmsg() calls.
The sctp_sndinfo structure is defined as per RFC as below ...
struct sctp_sndinfo {
uint16_t snd_sid;
uint16_t snd_flags;
uint32_t snd_ppid;
uint32_t snd_context;
sctp_assoc_t snd_assoc_id;
};
... and supplied under cmsg_level IPPROTO_SCTP, cmsg_type
SCTP_SNDINFO, while cmsg_data[] contains struct sctp_sndinfo.
An sctp_sndinfo item always corresponds to the data in msg_iov.
Joint work with Daniel Borkmann.
Signed-off-by: Geir Ola Vaagland <geirola@gmail.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Be more precise in transport path selection and use ktime
helpers instead of jiffies to compare and pick the better
primary and secondary recently used transports. This also
avoids any side-effects during a possible roll-over, and
could lead to better path decision-making.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, it is possible to create an SCTP socket, then switch
auth_enable via sysctl setting to 1 and crash the system on connect:
Oops[#1]:
CPU: 0 PID: 0 Comm: swapper Not tainted 3.14.1-mipsgit-20140415 #1
task: ffffffff8056ce80 ti: ffffffff8055c000 task.ti: ffffffff8055c000
[...]
Call Trace:
[<ffffffff8043c4e8>] sctp_auth_asoc_set_default_hmac+0x68/0x80
[<ffffffff8042b300>] sctp_process_init+0x5e0/0x8a4
[<ffffffff8042188c>] sctp_sf_do_5_1B_init+0x234/0x34c
[<ffffffff804228c8>] sctp_do_sm+0xb4/0x1e8
[<ffffffff80425a08>] sctp_endpoint_bh_rcv+0x1c4/0x214
[<ffffffff8043af68>] sctp_rcv+0x588/0x630
[<ffffffff8043e8e8>] sctp6_rcv+0x10/0x24
[<ffffffff803acb50>] ip6_input+0x2c0/0x440
[<ffffffff8030fc00>] __netif_receive_skb_core+0x4a8/0x564
[<ffffffff80310650>] process_backlog+0xb4/0x18c
[<ffffffff80313cbc>] net_rx_action+0x12c/0x210
[<ffffffff80034254>] __do_softirq+0x17c/0x2ac
[<ffffffff800345e0>] irq_exit+0x54/0xb0
[<ffffffff800075a4>] ret_from_irq+0x0/0x4
[<ffffffff800090ec>] rm7k_wait_irqoff+0x24/0x48
[<ffffffff8005e388>] cpu_startup_entry+0xc0/0x148
[<ffffffff805a88b0>] start_kernel+0x37c/0x398
Code: dd0900b8 000330f8 0126302d <dcc60000> 50c0fff1 0047182a a48306a0
03e00008 00000000
---[ end trace b530b0551467f2fd ]---
Kernel panic - not syncing: Fatal exception in interrupt
What happens while auth_enable=0 in that case is, that
ep->auth_hmacs is initialized to NULL in sctp_auth_init_hmacs()
when endpoint is being created.
After that point, if an admin switches over to auth_enable=1,
the machine can crash due to NULL pointer dereference during
reception of an INIT chunk. When we enter sctp_process_init()
via sctp_sf_do_5_1B_init() in order to respond to an INIT chunk,
the INIT verification succeeds and while we walk and process
all INIT params via sctp_process_param() we find that
net->sctp.auth_enable is set, therefore do not fall through,
but invoke sctp_auth_asoc_set_default_hmac() instead, and thus,
dereference what we have set to NULL during endpoint
initialization phase.
The fix is to make auth_enable immutable by caching its value
during endpoint initialization, so that its original value is
being carried along until destruction. The bug seems to originate
from the very first days.
Fix in joint work with Daniel Borkmann.
Reported-by: Joshua Kinard <kumba@gentoo.org>
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Tested-by: Joshua Kinard <kumba@gentoo.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Implementation of (a)rwnd calculation might lead to severe performance issues
and associations completely stalling. These problems are described and solution
is proposed which improves lksctp's robustness in congestion state.
1) Sudden drop of a_rwnd and incomplete window recovery afterwards
Data accounted in sctp_assoc_rwnd_decrease takes only payload size (sctp data),
but size of sk_buff, which is blamed against receiver buffer, is not accounted
in rwnd. Theoretically, this should not be the problem as actual size of buffer
is double the amount requested on the socket (SO_RECVBUF). Problem here is
that this will have bad scaling for data which is less then sizeof sk_buff.
E.g. in 4G (LTE) networks, link interfacing radio side will have a large portion
of traffic of this size (less then 100B).
An example of sudden drop and incomplete window recovery is given below. Node B
exhibits problematic behavior. Node A initiates association and B is configured
to advertise rwnd of 10000. A sends messages of size 43B (size of typical sctp
message in 4G (LTE) network). On B data is left in buffer by not reading socket
in userspace.
Lets examine when we will hit pressure state and declare rwnd to be 0 for
scenario with above stated parameters (rwnd == 10000, chunk size == 43, each
chunk is sent in separate sctp packet)
Logic is implemented in sctp_assoc_rwnd_decrease:
socket_buffer (see below) is maximum size which can be held in socket buffer
(sk_rcvbuf). current_alloced is amount of data currently allocated (rx_count)
A simple expression is given for which it will be examined after how many
packets for above stated parameters we enter pressure state:
We start by condition which has to be met in order to enter pressure state:
socket_buffer < currently_alloced;
currently_alloced is represented as size of sctp packets received so far and not
yet delivered to userspace. x is the number of chunks/packets (since there is no
bundling, and each chunk is delivered in separate packet, we can observe each
chunk also as sctp packet, and what is important here, having its own sk_buff):
socket_buffer < x*each_sctp_packet;
each_sctp_packet is sctp chunk size + sizeof(struct sk_buff). socket_buffer is
twice the amount of initially requested size of socket buffer, which is in case
of sctp, twice the a_rwnd requested:
2*rwnd < x*(payload+sizeof(struc sk_buff));
sizeof(struct sk_buff) is 190 (3.13.0-rc4+). Above is stated that rwnd is 10000
and each payload size is 43
20000 < x(43+190);
x > 20000/233;
x ~> 84;
After ~84 messages, pressure state is entered and 0 rwnd is advertised while
received 84*43B ~= 3612B sctp data. This is why external observer notices sudden
drop from 6474 to 0, as it will be now shown in example:
IP A.34340 > B.12345: sctp (1) [INIT] [init tag: 1875509148] [rwnd: 81920] [OS: 10] [MIS: 65535] [init TSN: 1096057017]
IP B.12345 > A.34340: sctp (1) [INIT ACK] [init tag: 3198966556] [rwnd: 10000] [OS: 10] [MIS: 10] [init TSN: 902132839]
IP A.34340 > B.12345: sctp (1) [COOKIE ECHO]
IP B.12345 > A.34340: sctp (1) [COOKIE ACK]
IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057017] [SID: 0] [SSEQ 0] [PPID 0x18]
IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057017] [a_rwnd 9957] [#gap acks 0] [#dup tsns 0]
IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057018] [SID: 0] [SSEQ 1] [PPID 0x18]
IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057018] [a_rwnd 9957] [#gap acks 0] [#dup tsns 0]
IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057019] [SID: 0] [SSEQ 2] [PPID 0x18]
IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057019] [a_rwnd 9914] [#gap acks 0] [#dup tsns 0]
<...>
IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057098] [SID: 0] [SSEQ 81] [PPID 0x18]
IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057098] [a_rwnd 6517] [#gap acks 0] [#dup tsns 0]
IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057099] [SID: 0] [SSEQ 82] [PPID 0x18]
IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057099] [a_rwnd 6474] [#gap acks 0] [#dup tsns 0]
IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057100] [SID: 0] [SSEQ 83] [PPID 0x18]
--> Sudden drop
IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057100] [a_rwnd 0] [#gap acks 0] [#dup tsns 0]
At this point, rwnd_press stores current rwnd value so it can be later restored
in sctp_assoc_rwnd_increase. This however doesn't happen as condition to start
slowly increasing rwnd until rwnd_press is returned to rwnd is never met. This
condition is not met since rwnd, after it hit 0, must first reach rwnd_press by
adding amount which is read from userspace. Let us observe values in above
example. Initial a_rwnd is 10000, pressure was hit when rwnd was ~6500 and the
amount of actual sctp data currently waiting to be delivered to userspace
is ~3500. When userspace starts to read, sctp_assoc_rwnd_increase will be blamed
only for sctp data, which is ~3500. Condition is never met, and when userspace
reads all data, rwnd stays on 3569.
IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057100] [a_rwnd 1505] [#gap acks 0] [#dup tsns 0]
IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057100] [a_rwnd 3010] [#gap acks 0] [#dup tsns 0]
IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057101] [SID: 0] [SSEQ 84] [PPID 0x18]
IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057101] [a_rwnd 3569] [#gap acks 0] [#dup tsns 0]
--> At this point userspace read everything, rwnd recovered only to 3569
IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057102] [SID: 0] [SSEQ 85] [PPID 0x18]
IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057102] [a_rwnd 3569] [#gap acks 0] [#dup tsns 0]
Reproduction is straight forward, it is enough for sender to send packets of
size less then sizeof(struct sk_buff) and receiver keeping them in its buffers.
2) Minute size window for associations sharing the same socket buffer
In case multiple associations share the same socket, and same socket buffer
(sctp.rcvbuf_policy == 0), different scenarios exist in which congestion on one
of the associations can permanently drop rwnd of other association(s).
Situation will be typically observed as one association suddenly having rwnd
dropped to size of last packet received and never recovering beyond that point.
Different scenarios will lead to it, but all have in common that one of the
associations (let it be association from 1)) nearly depleted socket buffer, and
the other association blames socket buffer just for the amount enough to start
the pressure. This association will enter pressure state, set rwnd_press and
announce 0 rwnd.
When data is read by userspace, similar situation as in 1) will occur, rwnd will
increase just for the size read by userspace but rwnd_press will be high enough
so that association doesn't have enough credit to reach rwnd_press and restore
to previous state. This case is special case of 1), being worse as there is, in
the worst case, only one packet in buffer for which size rwnd will be increased.
Consequence is association which has very low maximum rwnd ('minute size', in
our case down to 43B - size of packet which caused pressure) and as such
unusable.
Scenario happened in the field and labs frequently after congestion state (link
breaks, different probabilities of packet drop, packet reordering) and with
scenario 1) preceding. Here is given a deterministic scenario for reproduction:
>From node A establish two associations on the same socket, with rcvbuf_policy
being set to share one common buffer (sctp.rcvbuf_policy == 0). On association 1
repeat scenario from 1), that is, bring it down to 0 and restore up. Observe
scenario 1). Use small payload size (here we use 43). Once rwnd is 'recovered',
bring it down close to 0, as in just one more packet would close it. This has as
a consequence that association number 2 is able to receive (at least) one more
packet which will bring it in pressure state. E.g. if association 2 had rwnd of
10000, packet received was 43, and we enter at this point into pressure,
rwnd_press will have 9957. Once payload is delivered to userspace, rwnd will
increase for 43, but conditions to restore rwnd to original state, just as in
1), will never be satisfied.
--> Association 1, between A.y and B.12345
IP A.55915 > B.12345: sctp (1) [INIT] [init tag: 836880897] [rwnd: 10000] [OS: 10] [MIS: 65535] [init TSN: 4032536569]
IP B.12345 > A.55915: sctp (1) [INIT ACK] [init tag: 2873310749] [rwnd: 81920] [OS: 10] [MIS: 10] [init TSN: 3799315613]
IP A.55915 > B.12345: sctp (1) [COOKIE ECHO]
IP B.12345 > A.55915: sctp (1) [COOKIE ACK]
--> Association 2, between A.z and B.12346
IP A.55915 > B.12346: sctp (1) [INIT] [init tag: 534798321] [rwnd: 10000] [OS: 10] [MIS: 65535] [init TSN: 2099285173]
IP B.12346 > A.55915: sctp (1) [INIT ACK] [init tag: 516668823] [rwnd: 81920] [OS: 10] [MIS: 10] [init TSN: 3676403240]
IP A.55915 > B.12346: sctp (1) [COOKIE ECHO]
IP B.12346 > A.55915: sctp (1) [COOKIE ACK]
--> Deplete socket buffer by sending messages of size 43B over association 1
IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315613] [SID: 0] [SSEQ 0] [PPID 0x18]
IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315613] [a_rwnd 9957] [#gap acks 0] [#dup tsns 0]
<...>
IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315696] [a_rwnd 6388] [#gap acks 0] [#dup tsns 0]
IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315697] [SID: 0] [SSEQ 84] [PPID 0x18]
IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315697] [a_rwnd 6345] [#gap acks 0] [#dup tsns 0]
--> Sudden drop on 1
IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315698] [SID: 0] [SSEQ 85] [PPID 0x18]
IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315698] [a_rwnd 0] [#gap acks 0] [#dup tsns 0]
--> Here userspace read, rwnd 'recovered' to 3698, now deplete again using
association 1 so there is place in buffer for only one more packet
IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315799] [SID: 0] [SSEQ 186] [PPID 0x18]
IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315799] [a_rwnd 86] [#gap acks 0] [#dup tsns 0]
IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315800] [SID: 0] [SSEQ 187] [PPID 0x18]
IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315800] [a_rwnd 43] [#gap acks 0] [#dup tsns 0]
--> Socket buffer is almost depleted, but there is space for one more packet,
send them over association 2, size 43B
IP B.12346 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3676403240] [SID: 0] [SSEQ 0] [PPID 0x18]
IP A.55915 > B.12346: sctp (1) [SACK] [cum ack 3676403240] [a_rwnd 0] [#gap acks 0] [#dup tsns 0]
--> Immediate drop
IP A.60995 > B.12346: sctp (1) [SACK] [cum ack 387491510] [a_rwnd 0] [#gap acks 0] [#dup tsns 0]
--> Read everything from the socket, both association recover up to maximum rwnd
they are capable of reaching, note that association 1 recovered up to 3698,
and association 2 recovered only to 43
IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315800] [a_rwnd 1548] [#gap acks 0] [#dup tsns 0]
IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315800] [a_rwnd 3053] [#gap acks 0] [#dup tsns 0]
IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315801] [SID: 0] [SSEQ 188] [PPID 0x18]
IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315801] [a_rwnd 3698] [#gap acks 0] [#dup tsns 0]
IP B.12346 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3676403241] [SID: 0] [SSEQ 1] [PPID 0x18]
IP A.55915 > B.12346: sctp (1) [SACK] [cum ack 3676403241] [a_rwnd 43] [#gap acks 0] [#dup tsns 0]
A careful reader might wonder why it is necessary to reproduce 1) prior
reproduction of 2). It is simply easier to observe when to send packet over
association 2 which will push association into the pressure state.
Proposed solution:
Both problems share the same root cause, and that is improper scaling of socket
buffer with rwnd. Solution in which sizeof(sk_buff) is taken into concern while
calculating rwnd is not possible due to fact that there is no linear
relationship between amount of data blamed in increase/decrease with IP packet
in which payload arrived. Even in case such solution would be followed,
complexity of the code would increase. Due to nature of current rwnd handling,
slow increase (in sctp_assoc_rwnd_increase) of rwnd after pressure state is
entered is rationale, but it gives false representation to the sender of current
buffer space. Furthermore, it implements additional congestion control mechanism
which is defined on implementation, and not on standard basis.
Proposed solution simplifies whole algorithm having on mind definition from rfc:
o Receiver Window (rwnd): This gives the sender an indication of the space
available in the receiver's inbound buffer.
Core of the proposed solution is given with these lines:
sctp_assoc_rwnd_update:
if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0)
asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1;
else
asoc->rwnd = 0;
We advertise to sender (half of) actual space we have. Half is in the braces
depending whether you would like to observe size of socket buffer as SO_RECVBUF
or twice the amount, i.e. size is the one visible from userspace, that is,
from kernelspace.
In this way sender is given with good approximation of our buffer space,
regardless of the buffer policy - we always advertise what we have. Proposed
solution fixes described problems and removes necessity for rwnd restoration
algorithm. Finally, as proposed solution is simplification, some lines of code,
along with some bytes in struct sctp_association are saved.
Version 2 of the patch addressed comments from Vlad. Name of the function is set
to be more descriptive, and two parts of code are changed, in one removing the
superfluous call to sctp_assoc_rwnd_update since call would not result in update
of rwnd, and the other being reordering of the code in a way that call to
sctp_assoc_rwnd_update updates rwnd. Version 3 corrected change introduced in v2
in a way that existing function is not reordered/copied in line, but it is
correctly called. Thanks Vlad for suggesting.
Signed-off-by: Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nsn.com>
Reviewed-by: Alexander Sverdlin <alexander.sverdlin@nsn.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>