Re: [patch|rfc] block: fix race between request completion and timeout handling

2013-08-28 Thread Jeff Moyer
Hannes Reinecke writes: >> So, looked into things a bit more. >> It looks as if you're on the right track, although I doubt your >> patch will fix the issue for me :-( >> >> Thing is, you're right there is a race window between requeuing >> and softirq triggering, which could well be fixed by

Re: [patch|rfc] block: fix race between request completion and timeout handling

2013-08-28 Thread Hannes Reinecke
On 08/28/2013 09:04 AM, Hannes Reinecke wrote: > On 08/27/2013 04:28 PM, Jeff Moyer wrote: >> Hi, >> >> We have several reports (against a distro kernel) of panics in >> blk_requeue_request that look like this: >> >> kernel BUG at block/blk-core.c:1045! >> invalid opcode: [#1] SMP >> last

Re: [patch|rfc] block: fix race between request completion and timeout handling

2013-08-28 Thread Hannes Reinecke
On 08/27/2013 04:28 PM, Jeff Moyer wrote: > Hi, > > We have several reports (against a distro kernel) of panics in > blk_requeue_request that look like this: > > kernel BUG at block/blk-core.c:1045! > invalid opcode: [#1] SMP > last sysfs file: >

Re: [patch|rfc] block: fix race between request completion and timeout handling

2013-08-28 Thread Hannes Reinecke
On 08/27/2013 04:28 PM, Jeff Moyer wrote: Hi, We have several reports (against a distro kernel) of panics in blk_requeue_request that look like this: kernel BUG at block/blk-core.c:1045! invalid opcode: [#1] SMP last sysfs file:

Re: [patch|rfc] block: fix race between request completion and timeout handling

2013-08-28 Thread Hannes Reinecke
On 08/28/2013 09:04 AM, Hannes Reinecke wrote: On 08/27/2013 04:28 PM, Jeff Moyer wrote: Hi, We have several reports (against a distro kernel) of panics in blk_requeue_request that look like this: kernel BUG at block/blk-core.c:1045! invalid opcode: [#1] SMP last sysfs file:

Re: [patch|rfc] block: fix race between request completion and timeout handling

2013-08-28 Thread Jeff Moyer
Hannes Reinecke h...@suse.de writes: So, looked into things a bit more. It looks as if you're on the right track, although I doubt your patch will fix the issue for me :-( Thing is, you're right there is a race window between requeuing and softirq triggering, which could well be fixed by

Re: [patch|rfc] block: fix race between request completion and timeout handling

2013-08-27 Thread Hannes Reinecke
On 08/27/2013 04:28 PM, Jeff Moyer wrote: > Hi, > > We have several reports (against a distro kernel) of panics in > blk_requeue_request that look like this: > > kernel BUG at block/blk-core.c:1045! > invalid opcode: [#1] SMP > last sysfs file: >

[patch|rfc] block: fix race between request completion and timeout handling

2013-08-27 Thread Jeff Moyer
Hi, We have several reports (against a distro kernel) of panics in blk_requeue_request that look like this: kernel BUG at block/blk-core.c:1045! invalid opcode: [#1] SMP last sysfs file: /sys/devices/pci:40/:40:03.0/:55:00.0/infiniband_mad/umad0/port CPU 0 Modules linked in:

[patch|rfc] block: fix race between request completion and timeout handling

2013-08-27 Thread Jeff Moyer
Hi, We have several reports (against a distro kernel) of panics in blk_requeue_request that look like this: kernel BUG at block/blk-core.c:1045! invalid opcode: [#1] SMP last sysfs file: /sys/devices/pci:40/:40:03.0/:55:00.0/infiniband_mad/umad0/port CPU 0 Modules linked in:

Re: [patch|rfc] block: fix race between request completion and timeout handling

2013-08-27 Thread Hannes Reinecke
On 08/27/2013 04:28 PM, Jeff Moyer wrote: Hi, We have several reports (against a distro kernel) of panics in blk_requeue_request that look like this: kernel BUG at block/blk-core.c:1045! invalid opcode: [#1] SMP last sysfs file: