| Age | Commit message (Collapse) | Author |
|---|
|
RPC_TASK_NO_RETRANS_TIMEOUT is set when cl_noretranstimeo
is set, which happens when RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT is set,
which happens when NFS_CS_NO_RETRANS_TIMEOUT is set.
This flag means "don't resend on a timeout, only resend if the
connection gets broken for some reason".
cl_discrtry is set when RPC_CLNT_CREATE_DISCRTRY is set, which
happens when NFS_CS_DISCRTRY is set.
This flag means "always disconnect before resending".
NFS_CS_NO_RETRANS_TIMEOUT and NFS_CS_DISCRTRY are both only set
in nfs4_init_client(), and it always sets both.
So we will never have a situation where only one of the flags is set.
So this code, which tests if timeout retransmits are allowed, and
disconnection is required, will never run.
So it makes sense to remove this code as it cannot be tested and
could confuse people reading the code (like me).
(alternately we could leave it there with a comment saying
it is never actually used).
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
|
|
Adopt the use of xprt_pin_rqst to eliminate contention between
Call-side users of rb_lock and the use of rb_lock in
rpcrdma_reply_handler.
This replaces the mechanism introduced in 431af645cf66 ("xprtrdma:
Fix client lock-up after application signal fires").
Use recv_lock to quickly find the completing rqst, pin it, then
drop the lock. At that point invalidation and pull-up of the Reply
XDR can be done. Both are often expensive operations.
Finally, take recv_lock again to signal completion to the RPC
layer. It also protects adjustment of "cwnd".
This greatly reduces the amount of time a lock is held by the
reply handler. Comparing lock_stat results shows a marked decrease
in contention on rb_lock and recv_lock.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
[trond.myklebust@primarydata.com: Remove call to rpcrdma_buffer_put() from
the "out_norqst:" path in rpcrdma_reply_handler.]
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
|
|
git://git.linux-nfs.org/projects/anna/linux-nfs into linux-next
NFS-over-RDMA client updates for Linux 4.14
Bugfixes and cleanups:
- Constify rpc_xprt_ops
- Harden RPC call encoding and decoding
- Clean up rpc call decoding to use xdr_streams
- Remove unused variables from various structures
- Refactor code to remove imul instructions
- Rearrange rx_stats structure for better cacheline sharing
|
|
To reduce false cacheline sharing, separate counters that are likely
to be accessed in the Call path from those accessed in the Reply
path.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
|
|
If you
- mount and NFSv3 filesystem
- do some file locking which requires the server
to make a GRANT call back
- unmount
- mount again and do the same locking
then the second attempt at locking suffers a 30 second delay.
Unmounting and remounting causes lockd to stop and restart,
which causes it to bind to a new port.
The server still thinks the old port is valid and gets ECONNREFUSED
when trying to contact it.
ECONNREFUSED should be seen as a hard error that is not worth
retrying. Rebinding is the only reasonable response.
This patch forces a rebind if that makes sense.
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
|
|
This further reduces contention with the transport_lock, and allows us
to convert to using a non-bh-safe spinlock, since the list is now never
accessed from a bh context.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
|
|
Simplify the code to avoid a full copy of the struct xdr_skb_reader.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
|
|
Ensure that we don't hog the workqueue thread by requeuing the job
every 64 loops.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
|
|
The backchannel request has no associated task, so it is going nowhere
until we call xprt_complete_bc_request().
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
|
|
Instead add a mechanism to ensure that the request doesn't disappear
from underneath us while copying from the socket. We do this by
preventing xprt_release() from freeing the XDR buffers until the
flag RPC_TASK_MSG_RECV has been cleared from the request.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
|
|
Re-arrange the pointer arithmetic in the chunk list encoders to
eliminate several more integer multiplication instructions during
Transport Header encoding.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
Re-arrange the pointer arithmetic in rpcrdma_convert_iovs() to
eliminate several integer multiplication instructions during
Transport Header encoding.
Also, array overflow does not occur outside development
environments, so replace overflow checking with one spot check
at the end. This reduces the number of conditional branches in
the common case.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
Same changes as in rpcrdma_marshal_req(). This removes
C-structure style encoding from the backchannel.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
While marshaling chunk lists which are variable-length XDR objects,
check for XDR buffer overflow at every step. Measurements show no
significant changes in CPU utilization.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
Initialize an xdr_stream at the top of rpcrdma_marshal_req(), and
use it to encode the fixed transport header fields. This xdr_stream
will be used to encode the chunk lists in a subsequent patch.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
Clean up: Remove a variable whose result is no longer used.
Commit 655fec6987be ("xprtrdma: Use gathered Send for large inline
messages") should have removed it.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
Clean up: The caller already has rpcrdma_xprt, so pass that directly
instead. And provide a documenting comment for this critical
function.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
Updates to tp_reserve can race with reads of the field in
packet_set_ring. Avoid this by holding the socket lock during
updates in setsockopt PACKET_RESERVE.
This bug was discovered by syzkaller.
Fixes: 8913336a7e8d ("packet: add PACKET_RESERVE sockopt")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When iteratively building a UDP datagram with MSG_MORE and that
datagram exceeds MTU, consistently choose UFO or fragmentation.
Once skb_is_gso, always apply ufo. Conversely, once a datagram is
split across multiple skbs, do not consider ufo.
Sendpage already maintains the first invariant, only add the second.
IPv6 does not have a sendpage implementation to modify.
A gso skb must have a partial checksum, do not follow sk_no_check_tx
in udp_send_skb.
Found by syzkaller.
Fixes: e89e9cf539a2 ("[IPv4/IPv6]: UFO Scatter-gather approach")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 55917a21d0cc ("netfilter: x_tables: add context to know if
extension runs from nft_compat") introduced a member nft_compat to
xt_tgchk_param structure.
But it didn't set it's value for ipt_init_target. With unexpected
value in par.nft_compat, it may return unexpected result in some
target's checkentry.
This patch is to set all it's fields as 0 and only initialize the
non-zero fields in ipt_init_target.
v1->v2:
As Wang Cong's suggestion, fix it by setting all it's fields as
0 and only initializing the non-zero fields.
Fixes: 55917a21d0cc ("netfilter: x_tables: add context to know if extension runs from nft_compat")
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit dcd87999d415 ("igmp: net: Move igmp namespace init to correct file")
moved the igmp sysctls initialization from tcp_sk_init to igmp_net_init. This
function is only called as part of per-namespace initialization, only if
CONFIG_IP_MULTICAST is defined, otherwise igmp_mc_init() call in ip_init is
compiled out, casuing the igmp pernet ops to not be registerd and those sysctl
being left initialized with 0. However, there are certain functions, such as
ip_mc_join_group which are always compiled and make use of some of those
sysctls. Let's do a partial revert of the aforementioned commit and move the
sysctl initialization into inet_init_net, that way they will always have
sane values.
Fixes: dcd87999d415 ("igmp: net: Move igmp namespace init to correct file")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=196595
Reported-by: Gerardo Exequiel Pozzi <vmlinuz386@gmail.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When a link between two nodes come up, both endpoints will initially
send out a STATE message to the peer, to increase the probability that
the peer endpoint also is up when the first traffic message arrives.
Thereafter, if the establishing link is the second link between two
nodes, this first "traffic" message is a TUNNEL_PROTOCOL/SYNCH message,
helping the peer to perform initial synchronization between the two
links.
However, the initial STATE message may be lost, in which case the SYNCH
message will be the first one arriving at the peer. This should also
work, as the SYNCH message itself will be used to take up the link
endpoint before initializing synchronization.
Unfortunately the code for this case is broken. Currently, the link is
brought up through a tipc_link_fsm_evt(ESTABLISHED) when a SYNCH
arrives, whereupon __tipc_node_link_up() is called to distribute the
link slots and take the link into traffic. But, __tipc_node_link_up() is
itself starting with a test for whether the link is up, and if true,
returns without action. Clearly, the tipc_link_fsm_evt(ESTABLISHED) call
is unnecessary, since tipc_node_link_up() is itself issuing such an
event, but also harmful, since it inhibits tipc_node_link_up() to
perform the test of its tasks, and the link endpoint in question hence
is never taken into traffic.
This problem has been exposed when we set up dual links between pre-
and post-4.4 kernels, because the former ones don't send out the
initial STATE message described above.
We fix this by removing the unnecessary event call.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Pull networking fixes from David Miller:
"The pull requests are getting smaller, that's progress I suppose :-)
1) Fix infinite loop in CIPSO option parsing, from Yujuan Qi.
2) Fix remote checksum handling in VXLAN and GUE tunneling drivers,
from Koichiro Den.
3) Missing u64_stats_init() calls in several drivers, from Florian
Fainelli.
4) TCP can set the congestion window to an invalid ssthresh value
after congestion window reductions, from Yuchung Cheng.
5) Fix BPF jit branch generation on s390, from Daniel Borkmann.
6) Correct MIPS ebpf JIT merge, from David Daney.
7) Correct byte order test in BPF test_verifier.c, from Daniel
Borkmann.
8) Fix various crashes and leaks in ASIX driver, from Dean Jenkins.
9) Handle SCTP checksums properly in mlx4 driver, from Davide
Caratti.
10) We can potentially enter tcp_connect() with a cached route
already, due to fastopen, so we have to explicitly invalidate it.
11) skb_warn_bad_offload() can bark in legitimate situations, fix from
Willem de Bruijn"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (52 commits)
net: avoid skb_warn_bad_offload false positives on UFO
qmi_wwan: fix NULL deref on disconnect
ppp: fix xmit recursion detection on ppp channels
rds: Reintroduce statistics counting
tcp: fastopen: tcp_connect() must refresh the route
net: sched: set xt_tgchk_param par.net properly in ipt_init_target
net: dsa: mediatek: add adjust link support for user ports
net/mlx4_en: don't set CHECKSUM_COMPLETE on SCTP packets
qed: Fix a memory allocation failure test in 'qed_mcp_cmd_init()'
hysdn: fix to a race condition in put_log_buffer
s390/qeth: fix L3 next-hop in xmit qeth hdr
asix: Fix small memory leak in ax88772_unbind()
asix: Ensure asix_rx_fixup_info members are all reset
asix: Add rx->ax_skb = NULL after usbnet_skb_return()
bpf: fix selftest/bpf/test_pkt_md_access on s390x
netvsc: fix race on sub channel creation
bpf: fix byte order test in test_verifier
xgene: Always get clk source, but ignore if it's missing for SGMII ports
MIPS: Add missing file for eBPF JIT.
bpf, s390: fix build for libbpf and selftest suite
...
|
|
skb_warn_bad_offload triggers a warning when an skb enters the GSO
stack at __skb_gso_segment that does not have CHECKSUM_PARTIAL
checksum offload set.
Commit b2504a5dbef3 ("net: reduce skb_warn_bad_offload() noise")
observed that SKB_GSO_DODGY producers can trigger the check and
that passing those packets through the GSO handlers will fix it
up. But, the software UFO handler will set ip_summed to
CHECKSUM_NONE.
When __skb_gso_segment is called from the receive path, this
triggers the warning again.
Make UFO set CHECKSUM_UNNECESSARY instead of CHECKSUM_NONE. On
Tx these two are equivalent. On Rx, this better matches the
skb state (checksum computed), as CHECKSUM_NONE here means no
checksum computed.
See also this thread for context:
http://patchwork.ozlabs.org/patch/799015/
Fixes: b2504a5dbef3 ("net: reduce skb_warn_bad_offload() noise")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
In commit 7e3f2952eeb1 ("rds: don't let RDS shutdown a connection
while senders are present"), refilling the receive queue was removed
from rds_ib_recv(), along with the increment of
s_ib_rx_refill_from_thread.
Commit 73ce4317bf98 ("RDS: make sure we post recv buffers")
re-introduces filling the receive queue from rds_ib_recv(), but does
not add the statistics counter. rds_ib_recv() was later renamed to
rds_ib_recv_path().
This commit reintroduces the statistics counting of
s_ib_rx_refill_from_thread and s_ib_rx_refill_from_cq.
Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
Reviewed-by: Knut Omang <knut.omang@oracle.com>
Reviewed-by: Wei Lin Guay <wei.lin.guay@oracle.com>
Reviewed-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
With new TCP_FASTOPEN_CONNECT socket option, there is a possibility
to call tcp_connect() while socket sk_dst_cache is either NULL
or invalid.
+0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4
+0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+0 setsockopt(4, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0
+0 connect(4, ..., ...) = 0
<< sk->sk_dst_cache becomes obsolete, or even set to NULL >>
+1 sendto(4, ..., 1000, MSG_FASTOPEN, ..., ...) = 1000
We need to refresh the route otherwise bad things can happen,
especially when syzkaller is running on the host :/
Fixes: 19f6d3f3c8422 ("net/tcp-fastopen: Add new API support")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Wei Wang <weiwan@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Wei Wang <weiwan@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Now xt_tgchk_param par in ipt_init_target is a local varibale,
par.net is not initialized there. Later when xt_check_target
calls target's checkentry in which it may access par.net, it
would cause kernel panic.
Jaroslav found this panic when running:
# ip link add TestIface type dummy
# tc qd add dev TestIface ingress handle ffff:
# tc filter add dev TestIface parent ffff: u32 match u32 0 0 \
action xt -j CONNMARK --set-mark 4
This patch is to pass net param into ipt_init_target and set
par.net with it properly in there.
v1->v2:
As Wang Cong pointed, I missed ipt_net_id != xt_net_id, so fix
it by also passing net_id to __tcf_ipt_init.
v2->v3:
Missed the fixes tag, so add it.
Fixes: ecb2421b5ddf ("netfilter: add and use nf_ct_netns_get/put")
Reported-by: Jaroslav Aster <jaster@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Clean up: Replace C-structure based XDR decoding for consistency
with other areas.
struct rpcrdma_rep is rearranged slightly so that the relevant fields
are in cache when the Receive completion handler is invoked.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
This field is no longer used outside the Receive completion handler.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
Clean up: The opcode check is no longer necessary, because since
commit 2fa8f88d8892 ("xprtrdma: Use new CQ API for RPC-over-RDMA
client send CQs"), this completion handler is invoked only for
RECV work requests.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
Clean up chunk list decoding by using the xdr_stream set up in
rpcrdma_reply_handler. This hardens decoding by checking for buffer
overflow at every step while unmarshaling variable-length XDR
objects.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
Refactor the reply handler's transport header decoding logic to make
it easier to understand and update.
Convert some of the handler to use xdr_streams, which will enable
stricter validation of input data and enable the eventual addition
of support for new combinations of chunks, such as "Write + Reply"
or "PZRC + normal Read".
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
Transport header decoding deals with untrusted input data, therefore
decoding this header needs to be hardened.
Adopt the same infrastructure that is used when XDR decoding NFS
replies. This is slightly more CPU-intensive than the replaced code,
but we're not adding new atomics, locking, or context switches. The
cost is manageable.
Start by initializing an xdr_stream in rpcrdma_reply_handler().
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
Pull ceph fixes from Ilya Dryomov:
"A bunch of fixes and follow-ups for -rc1 Luminous patches: issues with
->reencode_message() and last minute RADOS semantic changes in
v12.1.2"
* tag 'ceph-for-4.13-rc4' of git://github.com/ceph/ceph-client:
libceph: make RECOVERY_DELETES feature create a new interval
libceph: upmap semantic changes
crush: assume weight_set != null imples weight_set_size > 0
libceph: fallback for when there isn't a pool-specific choose_arg
libceph: don't call ->reencode_message() more than once per message
libceph: make encode_request_*() work with r_mempool requests
|
|
Fix a TCP loss recovery performance bug raised recently on the netdev
list, in two threads:
(i) July 26, 2017: netdev thread "TCP fast retransmit issues"
(ii) July 26, 2017: netdev thread:
"[PATCH V2 net-next] TLP: Don't reschedule PTO when there's one
outstanding TLP retransmission"
The basic problem is that incoming TCP packets that did not indicate
forward progress could cause the xmit timer (TLP or RTO) to be rearmed
and pushed back in time. In certain corner cases this could result in
the following problems noted in these threads:
- Repeated ACKs coming in with bogus SACKs corrupted by middleboxes
could cause TCP to repeatedly schedule TLPs forever. We kept
sending TLPs after every ~200ms, which elicited bogus SACKs, which
caused more TLPs, ad infinitum; we never fired an RTO to fill in
the holes.
- Incoming data segments could, in some cases, cause us to reschedule
our RTO or TLP timer further out in time, for no good reason. This
could cause repeated inbound data to result in stalls in outbound
data, in the presence of packet loss.
This commit fixes these bugs by changing the TLP and RTO ACK
processing to:
(a) Only reschedule the xmit timer once per ACK.
(b) Only reschedule the xmit timer if tcp_clean_rtx_queue() deems the
ACK indicates sufficient forward progress (a packet was
cumulatively ACKed, or we got a SACK for a packet that was sent
before the most recent retransmit of the write queue head).
This brings us back into closer compliance with the RFCs, since, as
the comment for tcp_rearm_rto() notes, we should only restart the RTO
timer after forward progress on the connection. Previously we were
restarting the xmit timer even in these cases where there was no
forward progress.
As a side benefit, this commit simplifies and speeds up the TCP timer
arming logic. We had been calling inet_csk_reset_xmit_timer() three
times on normal ACKs that cumulatively acknowledged some data:
1) Once near the top of tcp_ack() to switch from TLP timer to RTO:
if (icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
tcp_rearm_rto(sk);
2) Once in tcp_clean_rtx_queue(), to update the RTO:
if (flag & FLAG_ACKED) {
tcp_rearm_rto(sk);
3) Once in tcp_ack() after tcp_fastretrans_alert() to switch from RTO
to TLP:
if (icsk->icsk_pending == ICSK_TIME_RETRANS)
tcp_schedule_loss_probe(sk);
This commit, by only rescheduling the xmit timer once per ACK,
simplifies the code and reduces CPU overhead.
This commit was tested in an A/B test with Google web server
traffic. SNMP stats and request latency metrics were within noise
levels, substantiating that for normal web traffic patterns this is a
rare issue. This commit was also tested with packetdrill tests to
verify that it fixes the timer behavior in the corner cases discussed
in the netdev threads mentioned above.
This patch is a bug fix patch intended to be queued for -stable
relases.
Fixes: 6ba8a3b19e76 ("tcp: Tail loss probe (TLP)")
Reported-by: Klavs Klavsen <kl@vsen.dk>
Reported-by: Mao Wenan <maowenan@huawei.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Nandita Dukkipati <nanditad@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Have tcp_schedule_loss_probe() base the TLP scheduling decision based
on when the RTO *should* fire. This is to enable the upcoming xmit
timer fix in this series, where tcp_schedule_loss_probe() cannot
assume that the last timer installed was an RTO timer (because we are
no longer doing the "rearm RTO, rearm RTO, rearm TLP" dance on every
ACK). So tcp_schedule_loss_probe() must independently figure out when
an RTO would want to fire.
In the new TLP implementation following in this series, we cannot
assume that icsk_timeout was set based on an RTO; after processing a
cumulative ACK the icsk_timeout we see can be from a previous TLP or
RTO. So we need to independently recalculate the RTO time (instead of
reading it out of icsk_timeout). Removing this dependency on the
nature of icsk_timeout makes things a little easier to reason about
anyway.
Note that the old and new code should be equivalent, since they are
both saying: "if the RTO is in the future, but at an earlier time than
the normal TLP time, then set the TLP timer to fire when the RTO would
have fired".
Fixes: 6ba8a3b19e76 ("tcp: Tail loss probe (TLP)")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Nandita Dukkipati <nanditad@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Pure refactor. This helper will be required in the xmit timer fix
later in the patch series. (Because the TLP logic will want to make
this calculation.)
Fixes: 6ba8a3b19e76 ("tcp: Tail loss probe (TLP)")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Nandita Dukkipati <nanditad@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
After commit c2ed1880fd61 ("net: ipv6: check route protocol when
deleting routes"), ipv6 route checks rt protocol when trying to
remove a rt entry.
It introduced a side effect causing 'ip -6 route flush cache' not
to work well. When flushing caches with iproute, all route caches
get dumped from kernel then removed one by one by sending DELROUTE
requests to kernel for each cache.
The thing is iproute sends the request with the cache whose proto
is set with RTPROT_REDIRECT by rt6_fill_node() when kernel dumps
it. But in kernel the rt_cache protocol is still 0, which causes
the cache not to be matched and removed.
So the real reason is rt6i_protocol in the route is not set when
it is allocated. As David Ahern's suggestion, this patch is to
set rt6i_protocol properly in the route when it is installed and
remove the codes setting rtm_protocol according to rt6i_flags in
rt6_fill_node.
This is also an improvement to keep rt6i_protocol consistent with
rtm_protocol.
Fixes: c2ed1880fd61 ("net: ipv6: check route protocol when deleting routes")
Reported-by: Jianlin Shi <jishi@redhat.com>
Suggested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
syzkaller was able to trigger a divide by 0 in TCP stack [1]
Issue here is that keepalive timer needs to be updated to not attempt
to send a probe if the connection setup was deferred using
TCP_FASTOPEN_CONNECT socket option added in linux-4.11
[1]
divide error: 0000 [#1] SMP
CPU: 18 PID: 0 Comm: swapper/18 Not tainted
task: ffff986f62f4b040 ti: ffff986f62fa2000 task.ti: ffff986f62fa2000
RIP: 0010:[<ffffffff8409cc0d>] [<ffffffff8409cc0d>] __tcp_select_window+0x8d/0x160
Call Trace:
<IRQ>
[<ffffffff8409d951>] tcp_transmit_skb+0x11/0x20
[<ffffffff8409da21>] tcp_xmit_probe_skb+0xc1/0xe0
[<ffffffff840a0ee8>] tcp_write_wakeup+0x68/0x160
[<ffffffff840a151b>] tcp_keepalive_timer+0x17b/0x230
[<ffffffff83b3f799>] call_timer_fn+0x39/0xf0
[<ffffffff83b40797>] run_timer_softirq+0x1d7/0x280
[<ffffffff83a04ddb>] __do_softirq+0xcb/0x257
[<ffffffff83ae03ac>] irq_exit+0x9c/0xb0
[<ffffffff83a04c1a>] smp_apic_timer_interrupt+0x6a/0x80
[<ffffffff83a03eaf>] apic_timer_interrupt+0x7f/0x90
<EOI>
[<ffffffff83fed2ea>] ? cpuidle_enter_state+0x13a/0x3b0
[<ffffffff83fed2cd>] ? cpuidle_enter_state+0x11d/0x3b0
Tested:
Following packetdrill no longer crashes the kernel
`echo 0 >/proc/sys/net/ipv4/tcp_timestamps`
// Cache warmup: send a Fast Open cookie request
0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+0 setsockopt(3, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0
+0 connect(3, ..., ...) = -1 EINPROGRESS (Operation is now in progress)
+0 > S 0:0(0) <mss 1460,nop,nop,sackOK,nop,wscale 8,FO,nop,nop>
+.01 < S. 123:123(0) ack 1 win 14600 <mss 1460,nop,nop,sackOK,nop,wscale 6,FO abcd1234,nop,nop>
+0 > . 1:1(0) ack 1
+0 close(3) = 0
+0 > F. 1:1(0) ack 1
+0 < F. 1:1(0) ack 2 win 92
+0 > . 2:2(0) ack 2
+0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4
+0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+0 setsockopt(4, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0
+0 setsockopt(4, SOL_SOCKET, SO_KEEPALIVE, [1], 4) = 0
+.01 connect(4, ..., ...) = 0
+0 setsockopt(4, SOL_TCP, TCP_KEEPIDLE, [5], 4) = 0
+10 close(4) = 0
`echo 1 >/proc/sys/net/ipv4/tcp_timestamps`
Fixes: 19f6d3f3c842 ("net/tcp-fastopen: Add new API support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Wei Wang <weiwan@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Simon Wunderlich says:
====================
Here is a batman-adv bugfix:
- fix TT sync flag inconsistency problems, which can lead to excess packets,
by Linus Luessing
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
If the sender switches the congestion control during ECN-triggered
cwnd-reduction state (CA_CWR), upon exiting recovery cwnd is set to
the ssthresh value calculated by the previous congestion control. If
the previous congestion control is BBR that always keep ssthresh
to TCP_INIFINITE_SSTHRESH, cwnd ends up being infinite. The safe
step is to avoid assigning invalid ssthresh value when recovery ends.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
In the case that GRO is turned on and the original received packet is
CHECKSUM_PARTIAL, if the outer UDP header is exactly at the last
csum-unnecessary point, which for instance could occur if the packet
comes from another Linux guest on the same Linux host, we have to do
either remcsum_adjust or set up CHECKSUM_PARTIAL again with its
csum_start properly reset considering RCO.
However, since b7fe10e5ebac ("gro: Fix remcsum offload to deal with frags
in GRO") that barrier in such case could be skipped if GRO turned on,
hence we pass over it and the inner L4 validation mistakenly reckons
it as a bad csum.
This patch makes remcsum_offload being reset at the same time of GRO
remcsum cleanup, so as to make it work in such case as before.
Fixes: b7fe10e5ebac ("gro: Fix remcsum offload to deal with frags in GRO")
Signed-off-by: Koichiro Den <den@klaipeden.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
in for(),if((optlen > 0) && (optptr[1] == 0)), enter infinite loop.
Test: receive a packet which the ip length > 20 and the first byte of ip option is 0, produce this issue
Signed-off-by: yujuan.qi <yujuan.qi@mediatek.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
After transport instance creation, these function pointers never
change. Mark them as constant to prevent their use as an attack
vector for code injections.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
|
|
This is needed so that the OSDs can regenerate the missing set at the
start of a new interval where support for recovery deletes changed.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Sage Weil <sage@redhat.com>
|
|
- apply both pg_upmap and pg_upmap_items
- allow bidirectional swap of pg-upmap-items
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Sage Weil <sage@redhat.com>
|
|
Reflects ceph.git commit 5e8fa3e06b68fae1582c9230a3a8d1abc6146286.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Sage Weil <sage@redhat.com>
|
|
There is now a fallback to a choose_arg index of -1 if there isn't
a pool-specific choose_arg set. If you create a per-pool weight-set,
that works for that pool. Otherwise we try the compat/default one. If
that doesn't exist either, then we use the normal CRUSH weights.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Sage Weil <sage@redhat.com>
|
