Sebastian Andrzej Siewior e708d7ad80 perf: Do poll_wait() before checking condition in perf_poll() ... One should first enqueue to the waitqueue and then check for the condition. If the condition gets true after mutex_unlock() but before poll_wait() then we lose it and would have wait for another wakeup. This has been like this since v2.6.31-rc1 commit c7138f37f9 ("perf_counter: fix perf_poll()"). Before that it was slightly worse. I guess we get enough wakeups so if we miss here one it doesn't really matter. It is still a bad example. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1407159068-1478-1-git-send-email-bigeasy@linutronix.de Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@kernel.org>		2014-08-13 07:51:11 +02:00
..
callchain.c	perf: Roll back callchain buffer refcount under the callchain mutex	2013-08-16 17:55:50 +02:00
core.c	perf: Do poll_wait() before checking condition in perf_poll()	2014-08-13 07:51:11 +02:00
hw_breakpoint.c	hw_breakpoint: Introduce "struct bp_cpuinfo"	2013-06-20 17:58:57 +02:00
internal.h	perf: Fix arch_perf_out_copy_user default	2013-11-06 12:34:25 +01:00
Makefile	uprobes: Move to kernel/events/	2012-02-22 11:08:00 +01:00
ring_buffer.c	perf: Optimize ring-buffer write by depending on control dependencies	2013-12-11 15:53:22 +01:00
uprobes.c	uprobes: Change unregister/apply to WARN() if uprobe/consumer is gone	2014-06-30 13:22:15 -04:00