]> git.baikalelectronics.ru Git - kernel.git/commit
perf/x86/intel/lbr: Limit LBR accesses to TOS in callstack mode
authorAndi Kleen <ak@linux.intel.com>
Thu, 28 May 2015 04:13:18 +0000 (21:13 -0700)
committerIngo Molnar <mingo@kernel.org>
Tue, 4 Aug 2015 08:16:59 +0000 (10:16 +0200)
commit955ae69be18a7d59e498ae909f5edc149734c385
tree2515d1a1ac3844ac12555b301df2c2e797b81d6c
parentad21417de78de01cc858871d49b28bca538aecd0
perf/x86/intel/lbr: Limit LBR accesses to TOS in callstack mode

In callstack mode the LBR is not a ring buffer, but a stack that grows up
and down. This means in  this case we don't need to access all LBRs, only the
ones up to TOS. Do this optimization for the normal LBR read, and the context
switch save/restore code. For save/restore it can be done unconditionally, as
it only runs when call stack mode is active.

This recovers some of the cost of going to 32 LBRs on Skylake.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@kernel.org
Cc: eranian@google.com
Cc: jolsa@redhat.com
Link: http://lkml.kernel.org/r/1432786398-23861-6-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
arch/x86/kernel/cpu/perf_event_intel_lbr.c