Merge tag 'perf-core-2022-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf events updates from Ingo Molnar:

 - Fix Intel Alder Lake PEBS memory access latency & data source
   profiling info bugs.

 - Use Intel large-PEBS hardware feature in more circumstances, to
   reduce PMI overhead & reduce sampling data.

 - Extend the lost-sample profiling output with the PERF_FORMAT_LOST ABI
   variant, which tells tooling the exact number of samples lost.

 - Add new IBS register bits definitions.

 - AMD uncore events: Add PerfMonV2 DF (Data Fabric) enhancements.

* tag 'perf-core-2022-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/ibs: Add new IBS register bits into header
  perf/x86/intel: Fix PEBS data source encoding for ADL
  perf/x86/intel: Fix PEBS memory access info encoding for ADL
  perf/core: Add a new read format to get a number of lost samples
  perf/x86/amd/uncore: Add PerfMonV2 RDPMC assignments
  perf/x86/amd/uncore: Add PerfMonV2 DF event format
  perf/x86/amd/uncore: Detect available DF counters
  perf/x86/amd/uncore: Use attr_update for format attributes
  perf/x86/amd/uncore: Use dynamic events array
  x86/events/intel/ds: Enable large PEBS for PERF_SAMPLE_WEIGHT_TYPE

2 files changed, 90 insertions, 46 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 45024abd929f..bd8b98857609 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4141,6 +4141,8 @@ tnt_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 {
 	struct event_constraint *c;
 
+	c = intel_get_event_constraints(cpuc, idx, event);
+
 	/*
 	 * :ppp means to do reduced skid PEBS,
 	 * which is available on PMC0 and fixed counter 0.
@@ -4153,8 +4155,6 @@ tnt_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 		return &counter0_constraint;
 	}
 
-	c = intel_get_event_constraints(cpuc, idx, event);
-
 	return c;
 }
 
@@ -6241,7 +6241,8 @@ __init int intel_pmu_init(void)
 		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
 		x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
 		x86_pmu.lbr_pt_coexist = true;
-		intel_pmu_pebs_data_source_skl(false);
+		intel_pmu_pebs_data_source_adl();
+		x86_pmu.pebs_latency_data = adl_latency_data_small;
 		x86_pmu.num_topdown_events = 8;
 		x86_pmu.update_topdown_event = adl_update_topdown_event;
 		x86_pmu.set_topdown_event_period = adl_set_topdown_event_period;
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 376cc3d66094..ba60427caa6d 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -94,15 +94,40 @@ void __init intel_pmu_pebs_data_source_nhm(void)
 	pebs_data_source[0x07] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
 }
 
-void __init intel_pmu_pebs_data_source_skl(bool pmem)
+static void __init __intel_pmu_pebs_data_source_skl(bool pmem, u64 *data_source)
 {
 	u64 pmem_or_l4 = pmem ? LEVEL(PMEM) : LEVEL(L4);
 
-	pebs_data_source[0x08] = OP_LH | pmem_or_l4 | P(SNOOP, HIT);
-	pebs_data_source[0x09] = OP_LH | pmem_or_l4 | REM | P(SNOOP, HIT);
-	pebs_data_source[0x0b] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE);
-	pebs_data_source[0x0c] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOPX, FWD);
-	pebs_data_source[0x0d] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOP, HITM);
+	data_source[0x08] = OP_LH | pmem_or_l4 | P(SNOOP, HIT);
+	data_source[0x09] = OP_LH | pmem_or_l4 | REM | P(SNOOP, HIT);
+	data_source[0x0b] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE);
+	data_source[0x0c] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOPX, FWD);
+	data_source[0x0d] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOP, HITM);
+}
+
+void __init intel_pmu_pebs_data_source_skl(bool pmem)
+{
+	__intel_pmu_pebs_data_source_skl(pmem, pebs_data_source);
+}
+
+static void __init intel_pmu_pebs_data_source_grt(u64 *data_source)
+{
+	data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT);
+	data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
+	data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD);
+}
+
+void __init intel_pmu_pebs_data_source_adl(void)
+{
+	u64 *data_source;
+
+	data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].pebs_data_source;
+	memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
+	__intel_pmu_pebs_data_source_skl(false, data_source);
+
+	data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source;
+	memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
+	intel_pmu_pebs_data_source_grt(data_source);
 }
 
 static u64 precise_store_data(u64 status)
@@ -171,7 +196,50 @@ static u64 precise_datala_hsw(struct perf_event *event, u64 status)
 	return dse.val;
 }
 
-static u64 load_latency_data(u64 status)
+static inline void pebs_set_tlb_lock(u64 *val, bool tlb, bool lock)
+{
+	/*
+	 * TLB access
+	 * 0 = did not miss 2nd level TLB
+	 * 1 = missed 2nd level TLB
+	 */
+	if (tlb)
+		*val |= P(TLB, MISS) | P(TLB, L2);
+	else
+		*val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
+
+	/* locked prefix */
+	if (lock)
+		*val |= P(LOCK, LOCKED);
+}
+
+/* Retrieve the latency data for e-core of ADL */
+u64 adl_latency_data_small(struct perf_event *event, u64 status)
+{
+	union intel_x86_pebs_dse dse;
+	u64 val;
+
+	WARN_ON_ONCE(hybrid_pmu(event->pmu)->cpu_type == hybrid_big);
+
+	dse.val = status;
+
+	val = hybrid_var(event->pmu, pebs_data_source)[dse.ld_dse];
+
+	/*
+	 * For the atom core on ADL,
+	 * bit 4: lock, bit 5: TLB access.
+	 */
+	pebs_set_tlb_lock(&val, dse.ld_locked, dse.ld_stlb_miss);
+
+	if (dse.ld_data_blk)
+		val |= P(BLK, DATA);
+	else
+		val |= P(BLK, NA);
+
+	return val;
+}
+
+static u64 load_latency_data(struct perf_event *event, u64 status)
 {
 	union intel_x86_pebs_dse dse;
 	u64 val;
@@ -181,7 +249,7 @@ static u64 load_latency_data(u64 status)
 	/*
 	 * use the mapping table for bit 0-3
 	 */
-	val = pebs_data_source[dse.ld_dse];
+	val = hybrid_var(event->pmu, pebs_data_source)[dse.ld_dse];
 
 	/*
 	 * Nehalem models do not support TLB, Lock infos
@@ -190,21 +258,8 @@ static u64 load_latency_data(u64 status)
 		val |= P(TLB, NA) | P(LOCK, NA);
 		return val;
 	}
-	/*
-	 * bit 4: TLB access
-	 * 0 = did not miss 2nd level TLB
-	 * 1 = missed 2nd level TLB
-	 */
-	if (dse.ld_stlb_miss)
-		val |= P(TLB, MISS) | P(TLB, L2);
-	else
-		val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
 
-	/*
-	 * bit 5: locked prefix
-	 */
-	if (dse.ld_locked)
-		val |= P(LOCK, LOCKED);
+	pebs_set_tlb_lock(&val, dse.ld_stlb_miss, dse.ld_locked);
 
 	/*
 	 * Ice Lake and earlier models do not support block infos.
@@ -233,7 +288,7 @@ static u64 load_latency_data(u64 status)
 	return val;
 }
 
-static u64 store_latency_data(u64 status)
+static u64 store_latency_data(struct perf_event *event, u64 status)
 {
 	union intel_x86_pebs_dse dse;
 	u64 val;
@@ -243,23 +298,9 @@ static u64 store_latency_data(u64 status)
 	/*
 	 * use the mapping table for bit 0-3
 	 */
-	val = pebs_data_source[dse.st_lat_dse];
+	val = hybrid_var(event->pmu, pebs_data_source)[dse.st_lat_dse];
 
-	/*
-	 * bit 4: TLB access
-	 * 0 = did not miss 2nd level TLB
-	 * 1 = missed 2nd level TLB
-	 */
-	if (dse.st_lat_stlb_miss)
-		val |= P(TLB, MISS) | P(TLB, L2);
-	else
-		val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
-
-	/*
-	 * bit 5: locked prefix
-	 */
-	if (dse.st_lat_locked)
-		val |= P(LOCK, LOCKED);
+	pebs_set_tlb_lock(&val, dse.st_lat_stlb_miss, dse.st_lat_locked);
 
 	val |= P(BLK, NA);
 
@@ -781,8 +822,8 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
 
 struct event_constraint intel_grt_pebs_event_constraints[] = {
 	/* Allow all events as PEBS with no flags */
-	INTEL_PLD_CONSTRAINT(0x5d0, 0xf),
-	INTEL_PSD_CONSTRAINT(0x6d0, 0xf),
+	INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0xf),
+	INTEL_HYBRID_LAT_CONSTRAINT(0x6d0, 0xf),
 	EVENT_CONSTRAINT_END
 };
 
@@ -1443,9 +1484,11 @@ static u64 get_data_src(struct perf_event *event, u64 aux)
 	bool fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
 
 	if (fl & PERF_X86_EVENT_PEBS_LDLAT)
-		val = load_latency_data(aux);
+		val = load_latency_data(event, aux);
 	else if (fl & PERF_X86_EVENT_PEBS_STLAT)
-		val = store_latency_data(aux);
+		val = store_latency_data(event, aux);
+	else if (fl & PERF_X86_EVENT_PEBS_LAT_HYBRID)
+		val = x86_pmu.pebs_latency_data(event, aux);
 	else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
 		val = precise_datala_hsw(event, aux);
 	else if (fst)