4.9-stable review patch. If anyone has any objections, please let me know.
------------------ From: Ingo Molnar <[email protected]> commit 6a8a75f3235724c5941a33e287b2f98966ad14c5 upstream. This reverts commit cc1582c231ea041fbc68861dfaf957eaf902b829. This commit introduced a regression that broke rr-project, which uses sampling events to receive a signal on overflow (but does not care about the contents of the sample). These signals are critical to the correct operation of rr. There's been some back and forth about how to fix it - but to not keep applications in limbo queue up a revert. Reported-by: Kyle Huey <[email protected]> Acked-by: Kyle Huey <[email protected]> Acked-by: Peter Zijlstra <[email protected]> Cc: Jin Yao <[email protected]> Cc: Vince Weaver <[email protected]> Cc: Linus Torvalds <[email protected]> Cc: Will Deacon <[email protected]> Cc: Arnaldo Carvalho de Melo <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Stephane Eranian <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Jiri Olsa <[email protected]> Link: http://lkml.kernel.org/r/20170628105600.GC5981@leverpostej Signed-off-by: Ingo Molnar <[email protected]> Signed-off-by: Greg Kroah-Hartman <[email protected]> --- kernel/events/core.c | 21 --------------------- 1 file changed, 21 deletions(-) --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7088,21 +7088,6 @@ static void perf_log_itrace_start(struct perf_output_end(&handle); } -static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs) -{ - /* - * Due to interrupt latency (AKA "skid"), we may enter the - * kernel before taking an overflow, even if the PMU is only - * counting user events. - * To avoid leaking information to userspace, we must always - * reject kernel samples when exclude_kernel is set. - */ - if (event->attr.exclude_kernel && !user_mode(regs)) - return false; - - return true; -} - /* * Generic event overflow handling, sampling. */ @@ -7150,12 +7135,6 @@ static int __perf_event_overflow(struct } /* - * For security, drop the skid kernel samples if necessary. - */ - if (!sample_is_allowed(event, regs)) - return ret; - - /* * XXX event_limit might not quite work as expected on inherited * events */
