Merge tag 'perf-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Thomas Gleixner:
 "Core:

   - Allow ftrace to instrument parts of the perf core code

   - Add a new mem_hops field to perf_mem_data_src which allows to
     represent intra-node/package or inter-node/off-package details to
     prepare for next generation systems which have more hieararchy
     within the node/pacakge level.

  Tools:

   - Update for the new mem_hops field in perf_mem_data_src

  Arch:

   - A set of constraints fixes for the Intel uncore PMU

   - The usual set of small fixes and improvements for x86 and PPC"

* tag 'perf-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel: Fix ICL/SPR INST_RETIRED.PREC_DIST encodings
  powerpc/perf: Fix data source encodings for L2.1 and L3.1 accesses
  tools/perf: Add mem_hops field in perf_mem_data_src structure
  perf: Add mem_hops field in perf_mem_data_src structure
  perf: Add comment about current state of PERF_MEM_LVL_* namespace and remove an extra line
  perf/core: Allow ftrace for functions in kernel/event/core.c
  perf/x86: Add new event for AUX output counter index
  perf/x86: Add compiler barrier after updating BTS
  perf/x86/intel/uncore: Fix Intel SPR M3UPI event constraints
  perf/x86/intel/uncore: Fix Intel SPR M2PCIE event constraints
  perf/x86/intel/uncore: Fix Intel SPR IIO event constraints
  perf/x86/intel/uncore: Fix Intel SPR CHA event constraints
  perf/x86/intel/uncore: Fix Intel ICX IIO event constraints
  perf/x86/intel/uncore: Fix invalid unit check
  perf/x86/intel/uncore: Support extra IMC channel on Ice Lake server

arch/powerpc/perf/isa207-common.c

@@ -238,11 +238,27 @@ static inline u64 isa207_find_source(u64 idx, u32 sub_idx)
 		ret |= P(SNOOP, HIT);
 		break;
 	case 5:
-		ret = PH(LVL, REM_CCE1);
-		if ((sub_idx == 0) || (sub_idx == 2) || (sub_idx == 4))
-			ret |= P(SNOOP, HIT);
-		else if ((sub_idx == 1) || (sub_idx == 3) || (sub_idx == 5))
-			ret |= P(SNOOP, HITM);
+		if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+			ret = REM | P(HOPS, 0);
+
+			if (sub_idx == 0 || sub_idx == 4)
+				ret |= PH(LVL, L2) | LEVEL(L2) | P(SNOOP, HIT);
+			else if (sub_idx == 1 || sub_idx == 5)
+				ret |= PH(LVL, L2) | LEVEL(L2) | P(SNOOP, HITM);
+			else if (sub_idx == 2 || sub_idx == 6)
+				ret |= PH(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT);
+			else if (sub_idx == 3 || sub_idx == 7)
+				ret |= PH(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
+		} else {
+			if (sub_idx == 0)
+				ret = PH(LVL, L2) | LEVEL(L2) | REM | P(SNOOP, HIT) | P(HOPS, 0);
+			else if (sub_idx == 1)
+				ret = PH(LVL, L2) | LEVEL(L2) | REM | P(SNOOP, HITM) | P(HOPS, 0);
+			else if (sub_idx == 2 || sub_idx == 4)
+				ret = PH(LVL, L3) | LEVEL(L3) | REM | P(SNOOP, HIT) | P(HOPS, 0);
+			else if (sub_idx == 3 || sub_idx == 5)
+				ret = PH(LVL, L3) | LEVEL(L3) | REM | P(SNOOP, HITM) | P(HOPS, 0);
+		}
 		break;
 	case 6:
 		ret = PH(LVL, REM_CCE2);

arch/powerpc/perf/isa207-common.h

@@ -273,6 +273,8 @@
 #define P(a, b)				PERF_MEM_S(a, b)
 #define PH(a, b)			(P(LVL, HIT) | P(a, b))
 #define PM(a, b)			(P(LVL, MISS) | P(a, b))
+#define LEVEL(x)			P(LVLNUM, x)
+#define REM				P(REMOTE, REMOTE)
 
 int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp, u64 event_config1);
 int isa207_compute_mmcr(u64 event[], int n_ev,

arch/x86/events/core.c

@@ -66,6 +66,8 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_enable_all,  *x86_pmu.enable_all);
 DEFINE_STATIC_CALL_NULL(x86_pmu_enable,	     *x86_pmu.enable);
 DEFINE_STATIC_CALL_NULL(x86_pmu_disable,     *x86_pmu.disable);
 
+DEFINE_STATIC_CALL_NULL(x86_pmu_assign, *x86_pmu.assign);
+
 DEFINE_STATIC_CALL_NULL(x86_pmu_add,  *x86_pmu.add);
 DEFINE_STATIC_CALL_NULL(x86_pmu_del,  *x86_pmu.del);
 DEFINE_STATIC_CALL_NULL(x86_pmu_read, *x86_pmu.read);
@@ -1215,6 +1217,8 @@ static inline void x86_assign_hw_event(struct perf_event *event,
 	hwc->last_cpu = smp_processor_id();
 	hwc->last_tag = ++cpuc->tags[i];
 
+	static_call_cond(x86_pmu_assign)(event, idx);
+
 	switch (hwc->idx) {
 	case INTEL_PMC_IDX_FIXED_BTS:
 	case INTEL_PMC_IDX_FIXED_VLBR:
@@ -2005,6 +2009,8 @@ static void x86_pmu_static_call_update(void)
 	static_call_update(x86_pmu_enable, x86_pmu.enable);
 	static_call_update(x86_pmu_disable, x86_pmu.disable);
 
+	static_call_update(x86_pmu_assign, x86_pmu.assign);
+
 	static_call_update(x86_pmu_add, x86_pmu.add);
 	static_call_update(x86_pmu_del, x86_pmu.del);
 	static_call_update(x86_pmu_read, x86_pmu.read);

arch/x86/events/intel/bts.c

@@ -209,6 +209,12 @@ static void bts_update(struct bts_ctx *bts)
 	} else {
 		local_set(&buf->data_size, head);
 	}
+
+	/*
+	 * Since BTS is coherent, just add compiler barrier to ensure
+	 * BTS updating is ordered against bts::handle::event.
+	 */
+	barrier();
 }
 
 static int

arch/x86/events/intel/core.c

@@ -243,7 +243,8 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = {
 
 static struct event_constraint intel_icl_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
-	FIXED_EVENT_CONSTRAINT(0x01c0, 0),	/* INST_RETIRED.PREC_DIST */
+	FIXED_EVENT_CONSTRAINT(0x01c0, 0),	/* old INST_RETIRED.PREC_DIST */
+	FIXED_EVENT_CONSTRAINT(0x0100, 0),	/* INST_RETIRED.PREC_DIST */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	FIXED_EVENT_CONSTRAINT(0x0400, 3),	/* SLOTS */
@@ -288,7 +289,7 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = {
 
 static struct event_constraint intel_spr_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
-	FIXED_EVENT_CONSTRAINT(0x01c0, 0),	/* INST_RETIRED.PREC_DIST */
+	FIXED_EVENT_CONSTRAINT(0x0100, 0),	/* INST_RETIRED.PREC_DIST */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	FIXED_EVENT_CONSTRAINT(0x0400, 3),	/* SLOTS */
@@ -2403,6 +2404,12 @@ static void intel_pmu_disable_event(struct perf_event *event)
 		intel_pmu_pebs_disable(event);
 }
 
+static void intel_pmu_assign_event(struct perf_event *event, int idx)
+{
+	if (is_pebs_pt(event))
+		perf_report_aux_output_id(event, idx);
+}
+
 static void intel_pmu_del_event(struct perf_event *event)
 {
 	if (needs_branch_stack(event))
@@ -4495,8 +4502,16 @@ static int intel_pmu_check_period(struct perf_event *event, u64 value)
 	return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
 }
 
+static void intel_aux_output_init(void)
+{
+	/* Refer also intel_pmu_aux_output_match() */
+	if (x86_pmu.intel_cap.pebs_output_pt_available)
+		x86_pmu.assign = intel_pmu_assign_event;
+}
+
 static int intel_pmu_aux_output_match(struct perf_event *event)
 {
+	/* intel_pmu_assign_event() is needed, refer intel_aux_output_init() */
 	if (!x86_pmu.intel_cap.pebs_output_pt_available)
 		return 0;
 
@@ -6302,6 +6317,8 @@ __init int intel_pmu_init(void)
 	if (is_hybrid())
 		intel_pmu_check_hybrid_pmus((u64)fixed_mask);
 
+	intel_aux_output_init();
+
 	return 0;
 }
 

arch/x86/events/intel/ds.c

@@ -923,7 +923,8 @@ struct event_constraint intel_skl_pebs_event_constraints[] = {
 };
 
 struct event_constraint intel_icl_pebs_event_constraints[] = {
-	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x100000000ULL),	/* old INST_RETIRED.PREC_DIST */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0100, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),	/* SLOTS */
 
 	INTEL_PLD_CONSTRAINT(0x1cd, 0xff),			/* MEM_TRANS_RETIRED.LOAD_LATENCY */
@@ -943,7 +944,7 @@ struct event_constraint intel_icl_pebs_event_constraints[] = {
 };
 
 struct event_constraint intel_spr_pebs_event_constraints[] = {
-	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
 
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe),

arch/x86/events/intel/uncore_discovery.h

@@ -30,7 +30,7 @@
 
 
 #define uncore_discovery_invalid_unit(unit)			\
-	(!unit.table1 || !unit.ctl || !unit.table3 ||	\
+	(!unit.table1 || !unit.ctl || \
 	 unit.table1 == -1ULL || unit.ctl == -1ULL ||	\
 	 unit.table3 == -1ULL)
 

arch/x86/events/intel/uncore_snbep.c

@@ -452,7 +452,7 @@
 #define ICX_M3UPI_PCI_PMON_BOX_CTL		0xa0
 
 /* ICX IMC */
-#define ICX_NUMBER_IMC_CHN			2
+#define ICX_NUMBER_IMC_CHN			3
 #define ICX_IMC_MEM_STRIDE			0x4
 
 /* SPR */
@@ -5076,8 +5076,10 @@ static struct event_constraint icx_uncore_iio_constraints[] = {
 	UNCORE_EVENT_CONSTRAINT(0x02, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x03, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x83, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x88, 0xc),
 	UNCORE_EVENT_CONSTRAINT(0xc0, 0xc),
 	UNCORE_EVENT_CONSTRAINT(0xc5, 0xc),
+	UNCORE_EVENT_CONSTRAINT(0xd5, 0xc),
 	EVENT_CONSTRAINT_END
 };
 
@@ -5463,7 +5465,7 @@ static struct intel_uncore_ops icx_uncore_mmio_ops = {
 static struct intel_uncore_type icx_uncore_imc = {
 	.name		= "imc",
 	.num_counters   = 4,
-	.num_boxes	= 8,
+	.num_boxes	= 12,
 	.perf_ctr_bits	= 48,
 	.fixed_ctr_bits	= 48,
 	.fixed_ctr	= SNR_IMC_MMIO_PMON_FIXED_CTR,
@@ -5647,6 +5649,7 @@ static struct intel_uncore_type spr_uncore_chabox = {
 	.event_mask		= SPR_CHA_PMON_EVENT_MASK,
 	.event_mask_ext		= SPR_RAW_EVENT_MASK_EXT,
 	.num_shared_regs	= 1,
+	.constraints		= skx_uncore_chabox_constraints,
 	.ops			= &spr_uncore_chabox_ops,
 	.format_group		= &spr_uncore_chabox_format_group,
 	.attr_update		= uncore_alias_groups,
@@ -5658,6 +5661,7 @@ static struct intel_uncore_type spr_uncore_iio = {
 	.event_mask_ext		= SNR_IIO_PMON_RAW_EVENT_MASK_EXT,
 	.format_group		= &snr_uncore_iio_format_group,
 	.attr_update		= uncore_alias_groups,
+	.constraints		= icx_uncore_iio_constraints,
 };
 
 static struct attribute *spr_uncore_raw_formats_attr[] = {
@@ -5686,9 +5690,16 @@ static struct intel_uncore_type spr_uncore_irp = {
 
 };
 
+static struct event_constraint spr_uncore_m2pcie_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x14, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
+	EVENT_CONSTRAINT_END
+};
+
 static struct intel_uncore_type spr_uncore_m2pcie = {
 	SPR_UNCORE_COMMON_FORMAT(),
 	.name			= "m2pcie",
+	.constraints		= spr_uncore_m2pcie_constraints,
 };
 
 static struct intel_uncore_type spr_uncore_pcu = {
@@ -5765,6 +5776,7 @@ static struct intel_uncore_type spr_uncore_upi = {
 static struct intel_uncore_type spr_uncore_m3upi = {
 	SPR_UNCORE_PCI_COMMON_FORMAT(),
 	.name			= "m3upi",
+	.constraints		= icx_uncore_m3upi_constraints,
 };
 
 static struct intel_uncore_type spr_uncore_mdf = {

arch/x86/events/perf_event.h

@@ -726,6 +726,7 @@ struct x86_pmu {
 	void		(*enable_all)(int added);
 	void		(*enable)(struct perf_event *);
 	void		(*disable)(struct perf_event *);
+	void		(*assign)(struct perf_event *event, int idx);
 	void		(*add)(struct perf_event *);
 	void		(*del)(struct perf_event *);
 	void		(*read)(struct perf_event *event);

include/linux/perf_event.h

@@ -1400,6 +1400,7 @@ perf_event_addr_filters(struct perf_event *event)
 }
 
 extern void perf_event_addr_filters_sync(struct perf_event *event);
+extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id);
 
 extern int perf_output_begin(struct perf_output_handle *handle,
 			     struct perf_sample_data *data,

include/uapi/linux/perf_event.h

@@ -1141,6 +1141,21 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_TEXT_POKE			= 20,
 
+	/*
+	 * Data written to the AUX area by hardware due to aux_output, may need
+	 * to be matched to the event by an architecture-specific hardware ID.
+	 * This records the hardware ID, but requires sample_id to provide the
+	 * event ID. e.g. Intel PT uses this record to disambiguate PEBS-via-PT
+	 * records from multiple events.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				hw_id;
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_AUX_OUTPUT_HW_ID		= 21,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
@@ -1210,14 +1225,16 @@ union perf_mem_data_src {
 			mem_remote:1,   /* remote */
 			mem_snoopx:2,	/* snoop mode, ext */
 			mem_blk:3,	/* access blocked */
-			mem_rsvd:21;
+			mem_hops:3,	/* hop level */
+			mem_rsvd:18;
 	};
 };
 #elif defined(__BIG_ENDIAN_BITFIELD)
 union perf_mem_data_src {
 	__u64 val;
 	struct {
-		__u64	mem_rsvd:21,
+		__u64	mem_rsvd:18,
+			mem_hops:3,	/* hop level */
 			mem_blk:3,	/* access blocked */
 			mem_snoopx:2,	/* snoop mode, ext */
 			mem_remote:1,   /* remote */
@@ -1241,7 +1258,13 @@ union perf_mem_data_src {
 #define PERF_MEM_OP_EXEC	0x10 /* code (execution) */
 #define PERF_MEM_OP_SHIFT	0
 
-/* memory hierarchy (memory level, hit or miss) */
+/*
+ * PERF_MEM_LVL_* namespace being depricated to some extent in the
+ * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields.
+ * Supporting this namespace inorder to not break defined ABIs.
+ *
+ * memory hierarchy (memory level, hit or miss)
+ */
 #define PERF_MEM_LVL_NA		0x01  /* not available */
 #define PERF_MEM_LVL_HIT	0x02  /* hit level */
 #define PERF_MEM_LVL_MISS	0x04  /* miss level  */
@@ -1307,6 +1330,11 @@ union perf_mem_data_src {
 #define PERF_MEM_BLK_ADDR	0x04 /* address conflict */
 #define PERF_MEM_BLK_SHIFT	40
 
+/* hop level */
+#define PERF_MEM_HOPS_0		0x01 /* remote core, same node */
+/* 2-7 available */
+#define PERF_MEM_HOPS_SHIFT	43
+
 #define PERF_MEM_S(a, s) \
 	(((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
 

kernel/events/Makefile

 # SPDX-License-Identifier: GPL-2.0
-ifdef CONFIG_FUNCTION_TRACER
-CFLAGS_REMOVE_core.o = $(CC_FLAGS_FTRACE)
-endif
-
 obj-y := core.o ring_buffer.o callchain.o
 
 obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
 obj-$(CONFIG_UPROBES) += uprobes.o
-

kernel/events/core.c

@@ -9099,6 +9099,36 @@ static void perf_log_itrace_start(struct perf_event *event)
 	perf_output_end(&handle);
 }
 
+void perf_report_aux_output_id(struct perf_event *event, u64 hw_id)
+{
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	struct perf_aux_event {
+		struct perf_event_header        header;
+		u64				hw_id;
+	} rec;
+	int ret;
+
+	if (event->parent)
+		event = event->parent;
+
+	rec.header.type	= PERF_RECORD_AUX_OUTPUT_HW_ID;
+	rec.header.misc	= 0;
+	rec.header.size	= sizeof(rec);
+	rec.hw_id	= hw_id;
+
+	perf_event_header__init_id(&rec.header, &sample, event);
+	ret = perf_output_begin(&handle, &sample, event, rec.header.size);
+
+	if (ret)
+		return;
+
+	perf_output_put(&handle, rec);
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+}
+
 static int
 __perf_event_account_interrupt(struct perf_event *event, int throttle)
 {

tools/include/uapi/linux/perf_event.h

@@ -1210,14 +1210,16 @@ union perf_mem_data_src {
 			mem_remote:1,   /* remote */
 			mem_snoopx:2,	/* snoop mode, ext */
 			mem_blk:3,	/* access blocked */
-			mem_rsvd:21;
+			mem_hops:3,	/* hop level */
+			mem_rsvd:18;
 	};
 };
 #elif defined(__BIG_ENDIAN_BITFIELD)
 union perf_mem_data_src {
 	__u64 val;
 	struct {
-		__u64	mem_rsvd:21,
+		__u64	mem_rsvd:18,
+			mem_hops:3,	/* hop level */
 			mem_blk:3,	/* access blocked */
 			mem_snoopx:2,	/* snoop mode, ext */
 			mem_remote:1,   /* remote */
@@ -1241,7 +1243,13 @@ union perf_mem_data_src {
 #define PERF_MEM_OP_EXEC	0x10 /* code (execution) */
 #define PERF_MEM_OP_SHIFT	0
 
-/* memory hierarchy (memory level, hit or miss) */
+/*
+ * PERF_MEM_LVL_* namespace being depricated to some extent in the
+ * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields.
+ * Supporting this namespace inorder to not break defined ABIs.
+ *
+ * memory hierarchy (memory level, hit or miss)
+ */
 #define PERF_MEM_LVL_NA		0x01  /* not available */
 #define PERF_MEM_LVL_HIT	0x02  /* hit level */
 #define PERF_MEM_LVL_MISS	0x04  /* miss level  */
@@ -1307,6 +1315,11 @@ union perf_mem_data_src {
 #define PERF_MEM_BLK_ADDR	0x04 /* address conflict */
 #define PERF_MEM_BLK_SHIFT	40
 
+/* hop level */
+#define PERF_MEM_HOPS_0		0x01 /* remote core, same node */
+/* 2-7 available */
+#define PERF_MEM_HOPS_SHIFT	43
+
 #define PERF_MEM_S(a, s) \
 	(((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
 

tools/perf/util/mem-events.c

@@ -301,6 +301,16 @@ static const char * const mem_lvlnum[] = {
 	[PERF_MEM_LVLNUM_NA] = "N/A",
 };
 
+static const char * const mem_hops[] = {
+	"N/A",
+	/*
+	 * While printing, 'Remote' will be added to represent
+	 * 'Remote core, same node' accesses as remote field need
+	 * to be set with mem_hops field.
+	 */
+	"core, same node",
+};
+
 int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 {
 	size_t i, l = 0;
@@ -320,12 +330,14 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 	/* already taken care of */
 	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
 
-
 	if (mem_info && mem_info->data_src.mem_remote) {
 		strcat(out, "Remote ");
 		l += 7;
 	}
 
+	if (mem_info && mem_info->data_src.mem_hops)
+		l += scnprintf(out + l, sz - l, "%s ", mem_hops[mem_info->data_src.mem_hops]);
+
 	printed = 0;
 	for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
 		if (!(m & 0x1))
@@ -472,8 +484,12 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
 	/*
 	 * Skylake might report unknown remote level via this
 	 * bit, consider it when evaluating remote HITMs.
+	 *
+	 * Incase of power, remote field can also be used to denote cache
+	 * accesses from the another core of same node. Hence, setting
+	 * mrem only when HOPS is zero along with set remote field.
 	 */
-	bool mrem  = data_src->mem_remote;
+	bool mrem  = (data_src->mem_remote && !data_src->mem_hops);
 	int err = 0;
 
 #define HITM_INC(__f)		\