Doug / smarc-fsl-linux-kernel

Download as
Browse Code ยป

Commit bced76aeaca03b45e3b4bdb868cada328e497847

Authored by Peter Zijlstra
Committed by Ingo Molnar
1 parent 6db9dc150e
Exists in master and in 6 other branches imx_3.10.17_1.0.1_ga, imx_3.10.53_1.1.0_ga, imx_3.14.28_1.0.0_ga, smarc-imx_3.10.53_1.1.0_ga, smarc-imx_3.14.28_1.0.0_ga, smarc-l5.0.0_1.0.0-ga

sched: Fix lockup by limiting load-balance retries on lock-break 

Eric and David reported dead machines and traced it to commit
a195f004 ("sched: Fix load-balance lock-breaking"), it turns out
there's still a scenario where we can end up re-trying forever.

Since there is no strict forward progress guarantee in the
load-balance iteration we can get stuck re-retrying the same
task-set over and over.

Creating a forward progress guarantee with the existing
structure is somewhat non-trivial, for now simply terminate the
retry loop after a few tries.

Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Tested-by: Eric Dumazet <eric.dumazet@gmail.com>
Reported-by: David Ahern <dsahern@gmail.com>
[ logic cleanup as suggested by Eric ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Link: http://lkml.kernel.org/r/1326297936.2442.157.camel@twins
Signed-off-by: Ingo Molnar <mingo@elte.hu>

Showing 1 changed file with 7 additions and 3 deletions Side-by-side Diff

... ... @@ -3130,8 +3130,10 @@
3130 3130 }
3131 3131  
3132 3132 #define LBF_ALL_PINNED 0x01
3133   -#define LBF_NEED_BREAK 0x02
3134   -#define LBF_ABORT 0x04
  3133 +#define LBF_NEED_BREAK 0x02 /* clears into HAD_BREAK */
  3134 +#define LBF_HAD_BREAK 0x04
  3135 +#define LBF_HAD_BREAKS 0x0C /* count HAD_BREAKs overflows into ABORT */
  3136 +#define LBF_ABORT 0x10
3135 3137  
3136 3138 /*
3137 3139 * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
... ... @@ -4508,7 +4510,9 @@
4508 4510 goto out_balanced;
4509 4511  
4510 4512 if (lb_flags & LBF_NEED_BREAK) {
4511   - lb_flags &= ~LBF_NEED_BREAK;
  4513 + lb_flags += LBF_HAD_BREAK - LBF_NEED_BREAK;
  4514 + if (lb_flags & LBF_ABORT)
  4515 + goto out_balanced;
4512 4516 goto redo;
4513 4517 }
4514 4518