Revision 3770a42bb8ceb856877699257a43c0585a5d2996 authored by Sagi Grimberg on 05 September 2022, 15:07:06 UTC, committed by Christoph Hellwig on 06 September 2022, 04:40:44 UTC
When we queue requests, we strive to batch as much as possible and also
signal the network stack that more data is about to be sent over a socket
with MSG_SENDPAGE_NOTLAST. This flag looks at the pending requests queued
as well as queue->more_requests that is derived from the block layer
last-in-batch indication.

We set more_request=true when we flush the request directly from
.queue_rq submission context (in nvme_tcp_send_all), however this is
wrongly assuming that no other requests may be queued during the
execution of nvme_tcp_send_all.

Due to this, a race condition may happen where:

 1. request X is queued as !last-in-batch
 2. request X submission context calls nvme_tcp_send_all directly
 3. nvme_tcp_send_all is preempted and schedules to a different cpu
 4. request Y is queued as last-in-batch
 5. nvme_tcp_send_all context sends request X+Y, however signals for
    both MSG_SENDPAGE_NOTLAST because queue->more_requests=true.

==> none of the requests is pushed down to the wire as the network
stack is waiting for more data, both requests timeout.

To fix this, we eliminate queue->more_requests and only rely on
the queue req_list and send_list to be not-empty.

Fixes: 122e5b9f3d37 ("nvme-tcp: optimize network stack with setting msg flags according to batch size")
Reported-by: Jonathan Nicklin <jnicklin@blockbridge.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Tested-by: Jonathan Nicklin <jnicklin@blockbridge.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
1 parent 160f354
Raw File
Kbuild
# SPDX-License-Identifier: GPL-2.0
#
# Kbuild for top-level directory of the kernel

#####
# Generate bounds.h

bounds-file := include/generated/bounds.h

always-y := $(bounds-file)
targets := kernel/bounds.s

$(bounds-file): kernel/bounds.s FORCE
	$(call filechk,offsets,__LINUX_BOUNDS_H__)

#####
# Generate timeconst.h

timeconst-file := include/generated/timeconst.h

filechk_gentimeconst = echo $(CONFIG_HZ) | bc -q $<

$(timeconst-file): kernel/time/timeconst.bc FORCE
	$(call filechk,gentimeconst)

#####
# Generate asm-offsets.h

offsets-file := include/generated/asm-offsets.h

always-y += $(offsets-file)
targets += arch/$(SRCARCH)/kernel/asm-offsets.s

arch/$(SRCARCH)/kernel/asm-offsets.s: $(timeconst-file) $(bounds-file)

$(offsets-file): arch/$(SRCARCH)/kernel/asm-offsets.s FORCE
	$(call filechk,offsets,__ASM_OFFSETS_H__)

#####
# Check for missing system calls

always-y += missing-syscalls

quiet_cmd_syscalls = CALL    $<
      cmd_syscalls = $(CONFIG_SHELL) $< $(CC) $(c_flags) $(missing_syscalls_flags)

missing-syscalls: scripts/checksyscalls.sh $(offsets-file) FORCE
	$(call cmd,syscalls)

#####
# Check atomic headers are up-to-date

always-y += old-atomics

quiet_cmd_atomics = CALL    $<
      cmd_atomics = $(CONFIG_SHELL) $<

old-atomics: scripts/atomic/check-atomics.sh FORCE
	$(call cmd,atomics)
back to top