perf/amd/uncore: Set all slices and threads to restore perf stat -a b…

…ehaviour

commit c8fe99d upstream.

Commit 2f217d5 ("perf/x86/amd/uncore: Set the thread mask for
F17h L3 PMCs") inadvertently changed the uncore driver's behaviour
wrt perf tool invocations with or without a CPU list, specified with
-C / --cpu=.

Change the behaviour of the driver to assume the former all-cpu (-a)
case, which is the more commonly desired default.  This fixes
'-a -A' invocations without explicit cpu lists (-C) to not count
L3 events only on behalf of the first thread of the first core
in the L3 domain.

BEFORE:

Activity performed by the first thread of the last core (CPU#43) in
CPU#40's L3 domain is not reported by CPU#40:

sudo perf stat -a -A -e l3_request_g1.caching_l3_cache_accesses taskset -c 43 perf bench mem memcpy -s 32mb -l 100 -f default
...
CPU36                 21,835      l3_request_g1.caching_l3_cache_accesses
CPU40                 87,066      l3_request_g1.caching_l3_cache_accesses
CPU44                 17,360      l3_request_g1.caching_l3_cache_accesses
...

AFTER:

The L3 domain activity is now reported by CPU#40:

sudo perf stat -a -A -e l3_request_g1.caching_l3_cache_accesses taskset -c 43 perf bench mem memcpy -s 32mb -l 100 -f default
...
CPU36                354,891      l3_request_g1.caching_l3_cache_accesses
CPU40              1,780,870      l3_request_g1.caching_l3_cache_accesses
CPU44                315,062      l3_request_g1.caching_l3_cache_accesses
...

Fixes: 2f217d5 ("perf/x86/amd/uncore: Set the thread mask for F17h L3 PMCs")
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20200908214740.18097-2-kim.phillips@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

arch/x86/events/amd/uncore.c

@@ -181,28 +181,16 @@ static void amd_uncore_del(struct perf_event *event, int flags)
 }
 
 /*
- * Convert logical CPU number to L3 PMC Config ThreadMask format
+ * Return a full thread and slice mask until per-CPU is
+ * properly supported.
  */
-static u64 l3_thread_slice_mask(int cpu)
+static u64 l3_thread_slice_mask(void)
 {
-	u64 thread_mask, core = topology_core_id(cpu);
-	unsigned int shift, thread = 0;
+	if (boot_cpu_data.x86 <= 0x18)
+		return AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK;
 
-	if (topology_smt_supported() && !topology_is_primary_thread(cpu))
-		thread = 1;
-
-	if (boot_cpu_data.x86 <= 0x18) {
-		shift = AMD64_L3_THREAD_SHIFT + 2 * (core % 4) + thread;
-		thread_mask = BIT_ULL(shift);
-
-		return AMD64_L3_SLICE_MASK | thread_mask;
-	}
-
-	core = (core << AMD64_L3_COREID_SHIFT) & AMD64_L3_COREID_MASK;
-	shift = AMD64_L3_THREAD_SHIFT + thread;
-	thread_mask = BIT_ULL(shift);
-
-	return AMD64_L3_EN_ALL_SLICES | core | thread_mask;
+	return AMD64_L3_EN_ALL_SLICES | AMD64_L3_EN_ALL_CORES |
+	       AMD64_L3_F19H_THREAD_MASK;
 }
 
 static int amd_uncore_event_init(struct perf_event *event)
@@ -232,7 +220,7 @@ static int amd_uncore_event_init(struct perf_event *event)
 	 * For other events, the two fields do not affect the count.
 	 */
 	if (l3_mask && is_llc_event(event))
-		hwc->config |= l3_thread_slice_mask(event->cpu);
+		hwc->config |= l3_thread_slice_mask();
 
 	uncore = event_to_amd_uncore(event);
 	if (!uncore)