perf/x86/amd/uncore: Prevent UMC counters from saturating

Unlike L3 and DF counters, UMC counters (PERF_CTRs) set the Overflow bit
(bit 48) and saturate on overflow. A subsequent pmu->read() of the event
reports an incorrect accumulated count as there is no difference between
the previous and the current values of the counter.

To avoid this, inspect the current counter value and proactively reset
the corresponding PERF_CTR register on every pmu->read(). Combined with
the periodic reads initiated by the hrtimer, the counters never get a
chance saturate but the resolution reduces to 47 bits.

Fixes: 25e5684 ("perf/x86/amd/uncore: Add memory controller support")
Signed-off-by: Sandipan Das <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Song Liu <[email protected]>
Acked-by: Peter Zijlstra <[email protected]>
Link: https://lore.kernel.org/r/dee9c8af2c6d66814cf4c6224529c144c620cf2c.1744906694.git.sandipan.das@amd.com

Author: sandip4n

arch/x86/events/amd/uncore.c

@@ -956,6 +956,39 @@ static void amd_uncore_umc_start(struct perf_event *event, int flags)
 	perf_event_update_userpage(event);
 }
 
+static void amd_uncore_umc_read(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	u64 prev, new, shift;
+	s64 delta;
+
+	shift = COUNTER_SHIFT + 1;
+	prev = local64_read(&hwc->prev_count);
+
+	/*
+	 * UMC counters do not have RDPMC assignments. Read counts directly
+	 * from the corresponding PERF_CTR.
+	 */
+	rdmsrl(hwc->event_base, new);
+
+	/*
+	 * Unlike the other uncore counters, UMC counters saturate and set the
+	 * Overflow bit (bit 48) on overflow. Since they do not roll over,
+	 * proactively reset the corresponding PERF_CTR when bit 47 is set so
+	 * that the counter never gets a chance to saturate.
+	 */
+	if (new & BIT_ULL(63 - COUNTER_SHIFT)) {
+		wrmsrl(hwc->event_base, 0);
+		local64_set(&hwc->prev_count, 0);
+	} else {
+		local64_set(&hwc->prev_count, new);
+	}
+
+	delta = (new << shift) - (prev << shift);
+	delta >>= shift;
+	local64_add(delta, &event->count);
+}
+
 static
 void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
 {
@@ -1034,7 +1067,7 @@ int amd_uncore_umc_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 				.del		= amd_uncore_del,
 				.start		= amd_uncore_umc_start,
 				.stop		= amd_uncore_stop,
-				.read		= amd_uncore_read,
+				.read		= amd_uncore_umc_read,
 				.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
 				.module		= THIS_MODULE,
 			};