perf, x86: Update/fix Intel Nehalem cache events

Change the Nehalem cache events to use retired memory instruction counters
(similar to Westmere), this greatly improves the provided stats.

Using:

main ()
{
        int i;

        for (i = 0; i < 1000000000; i++) {
                asm("mov (%%rsp), %%rbx;"
                    "mov %%rbx, (%%rsp);" : : : "rbx");
        }
}

We find:

 $ perf stat --repeat 10 -e instructions:u -e l1-dcache-loads:u -e l1-dcache-stores:u ./loop_1b_loads+stores
  Performance counter stats for './loop_1b_loads+stores' (10 runs):
      4,000,081,056 instructions:u           #      0.000 IPC ( +-   0.000% )
      4,999,502,846 l1-dcache-loads:u          ( +-   0.008% )
      1,000,034,832 l1-dcache-stores:u         ( +-   0.000% )
         1.565184942  seconds time elapsed   ( +-   0.005% )

The 5b is surprising - we'd expect 1b:

 $ perf stat --repeat 10 -e instructions:u -e r10b:u -e l1-dcache-stores:u ./loop_1b_loads+stores
  Performance counter stats for './loop_1b_loads+stores' (10 runs):
      4,000,081,054 instructions:u           #      0.000 IPC ( +-   0.000% )
      1,000,021,961 r10b:u                     ( +-   0.000% )
      1,000,030,951 l1-dcache-stores:u         ( +-   0.000% )
         1.565055422  seconds time elapsed   ( +-   0.003% )

Which this patch thus fixes.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Link: http://lkml.kernel.org/n/tip-q9rtru7b7840tws75xzboapv@git.kernel.orgSigned-off-by: NIngo Molnar <mingo@elte.hu>

arch/x86/kernel/cpu/perf_event_intel.c

@@ -391,12 +391,12 @@ static __initconst const u64 nehalem_hw_cache_event_ids
 {
  [ C(L1D) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI            */
-		[ C(RESULT_MISS)   ] = 0x0140, /* L1D_CACHE_LD.I_STATE         */
+		[ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS       */
+		[ C(RESULT_MISS)   ] = 0x0151, /* L1D.REPL                     */
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI            */
-		[ C(RESULT_MISS)   ] = 0x0141, /* L1D_CACHE_ST.I_STATE         */
+		[ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES      */
+		[ C(RESULT_MISS)   ] = 0x0251, /* L1D.M_REPL                   */
 	},
 	[ C(OP_PREFETCH) ] = {
 		[ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS        */