]> git.hungrycats.org Git - linux/commitdiff
perf/x86: Honor the architectural performance monitoring version
authorPalik, Imre <imrep@amazon.de>
Mon, 8 Jun 2015 12:46:49 +0000 (14:46 +0200)
committerJiri Slaby <jslaby@suse.cz>
Tue, 12 Jul 2016 07:56:58 +0000 (09:56 +0200)
commit 2c33645d366d13b969d936b68b9f4875b1fdddea upstream.

Architectural performance monitoring, version 1, doesn't support fixed counters.

Currently, even if a hypervisor advertises support for architectural
performance monitoring version 1, perf may still try to use the fixed
counters, as the constraints are set up based on the CPU model.

This patch ensures that perf honors the architectural performance monitoring
version returned by CPUID, and it only uses the fixed counters for version 2
and above.

(Some of the ideas in this patch came from Peter Zijlstra.)

Signed-off-by: Imre Palik <imrep@amazon.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Anthony Liguori <aliguori@amazon.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1433767609-1039-1-git-send-email-imrep.amz@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Kevin Christopher <kevinc@vmware.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
arch/x86/kernel/cpu/perf_event_intel.c

index 0c8fc76b2d2c5971ddd9c5c2a5b9aa1c9435f981..491d6813ea3fa9f95b5c76b1ec47f43baedfcdcb 100644 (file)
@@ -2538,13 +2538,13 @@ __init int intel_pmu_init(void)
                 * counter, so do not extend mask to generic counters
                 */
                for_each_event_constraint(c, x86_pmu.event_constraints) {
-                       if (c->cmask != FIXED_EVENT_FLAGS
-                           || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) {
-                               continue;
+                       if (c->cmask == FIXED_EVENT_FLAGS
+                           && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) {
+                               c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
                        }
-
-                       c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
-                       c->weight += x86_pmu.num_counters;
+                       c->idxmsk64 &=
+                               ~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
+                       c->weight = hweight64(c->idxmsk64);
                }
        }