perf/x86/intel: Add mem-loads/stores support for Haswell
mem-loads is basically the same as Sandy Bridge,
but we use a separate string for changes later.
Haswell doesn't support the full precise store mode,
so we emulate it using the "DataLA" facility.
This allows to do everything, but for data sources we
can only detect L1 hit or not.
There is no explicit enable bit anymore, so we have
to tie it to a perf internal only flag.
The address is supported for all memory related PEBS
events with DataLA. Instead of only logging for the
load and store events we allow logging it for all
(it will be simply 0 if the current event does not
support it)
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Andi Kleen <ak@linux.jf.intel.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lkml.kernel.org/r/1371515812-9646-7-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index f43473c..108dc75 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -67,6 +67,7 @@
*/
#define PERF_X86_EVENT_PEBS_LDLAT 0x1 /* ld+ldlat data address sampling */
#define PERF_X86_EVENT_PEBS_ST 0x2 /* st data address sampling */
+#define PERF_X86_EVENT_PEBS_ST_HSW 0x4 /* haswell style st data sampling */
struct amd_nb {
int nb_id; /* NorthBridge id */
@@ -250,6 +251,11 @@
__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST)
+/* DataLA version of store sampling without extra enable bit. */
+#define INTEL_PST_HSW_CONSTRAINT(c, n) \
+ __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
+
#define EVENT_CONSTRAINT_END \
EVENT_CONSTRAINT(0, 0, 0)