Revision 002e062e13db10973adb8302f231e48b477c7ccf authored by Yonatan Cohen on 16 November 2016, 08:39:15 UTC, committed by Doug Ledford on 17 November 2016, 01:03:44 UTC
To correctly handle a erroneous WR this fix does the following
1. Make sure the bad WQE causes a user completion event.
2. Call rxe_completer to handle the erred WQE.
Before the fix, when rxe_requester found a bad WQE, it changed its
status to IB_WC_LOC_PROT_ERR and exit with 0 for non RC QPs.
If this was the 1st WQE then there would be no ACK to invoke the
completer and this bad WQE would be stuck in the QP's send-q.
On top of that the requester exiting with 0 caused rxe_do_task to
endlessly invoke rxe_requester, resulting in a soft-lockup attached
below.
In case the WQE was not the 1st and rxe_completer did get a chance to
handle the bad WQE, it did not cause a complete event since the WQE's
IB_SEND_SIGNALED flag was not set.
Setting WQE status to IB_SEND_SIGNALED is subject to IBA spec
version 1.2.1, section 10.7.3.1 Signaled Completions.
NMI watchdog: BUG: soft lockup - CPU#7 stuck for 22s!
[<ffffffffa0590145>] ? rxe_pool_get_index+0x35/0xb0 [rdma_rxe]
[<ffffffffa05952ec>] lookup_mem+0x3c/0xc0 [rdma_rxe]
[<ffffffffa0595534>] copy_data+0x1c4/0x230 [rdma_rxe]
[<ffffffffa058c180>] rxe_requester+0x9d0/0x1100 [rdma_rxe]
[<ffffffff8158e98a>] ? kfree_skbmem+0x5a/0x60
[<ffffffffa05962c9>] rxe_do_task+0x89/0xf0 [rdma_rxe]
[<ffffffffa05963e2>] rxe_run_task+0x12/0x30 [rdma_rxe]
[<ffffffffa059110a>] rxe_post_send+0x41a/0x550 [rdma_rxe]
[<ffffffff811ef922>] ? __kmalloc+0x182/0x200
[<ffffffff816ba512>] ? down_read+0x12/0x40
[<ffffffffa054bd32>] ib_uverbs_post_send+0x532/0x540 [ib_uverbs]
[<ffffffff815f8722>] ? tcp_sendmsg+0x402/0xb80
[<ffffffffa05453dc>] ib_uverbs_write+0x18c/0x3f0 [ib_uverbs]
[<ffffffff81623c2e>] ? inet_recvmsg+0x7e/0xb0
[<ffffffff8158764d>] ? sock_recvmsg+0x3d/0x50
[<ffffffff81215b87>] __vfs_write+0x37/0x140
[<ffffffff81216892>] vfs_write+0xb2/0x1b0
[<ffffffff81217ce5>] SyS_write+0x55/0xc0
[<ffffffff816bc672>] entry_SYSCALL_64_fastpath+0x1a/0xa
Fixes: 8700e3e7c485 ("Soft RoCE driver")
Signed-off-by: Yonatan Cohen <yonatanc@mellanox.com>
Reviewed-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
1 parent 1454ca3
Kconfig.kasan
config HAVE_ARCH_KASAN
bool
if HAVE_ARCH_KASAN
config KASAN
bool "KASan: runtime memory debugger"
depends on SLUB || (SLAB && !DEBUG_SLAB)
select CONSTRUCTORS
select STACKDEPOT
help
Enables kernel address sanitizer - runtime memory debugger,
designed to find out-of-bounds accesses and use-after-free bugs.
This is strictly a debugging feature and it requires a gcc version
of 4.9.2 or later. Detection of out of bounds accesses to stack or
global variables requires gcc 5.0 or later.
This feature consumes about 1/8 of available memory and brings about
~x3 performance slowdown.
For better error detection enable CONFIG_STACKTRACE.
Currently CONFIG_KASAN doesn't work with CONFIG_DEBUG_SLAB
(the resulting kernel does not boot).
choice
prompt "Instrumentation type"
depends on KASAN
default KASAN_OUTLINE
config KASAN_OUTLINE
bool "Outline instrumentation"
help
Before every memory access compiler insert function call
__asan_load*/__asan_store*. These functions performs check
of shadow memory. This is slower than inline instrumentation,
however it doesn't bloat size of kernel's .text section so
much as inline does.
config KASAN_INLINE
bool "Inline instrumentation"
help
Compiler directly inserts code checking shadow memory before
memory accesses. This is faster than outline (in some workloads
it gives about x2 boost over outline instrumentation), but
make kernel's .text size much bigger.
This requires a gcc version of 5.0 or later.
endchoice
config TEST_KASAN
tristate "Module for testing kasan for bug detection"
depends on m && KASAN
help
This is a test module doing various nasty things like
out of bounds accesses, use after free. It is useful for testing
kernel debugging features like kernel address sanitizer.
endif
Computing file changes ...
