diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index ae44421023fa55fe1fca5a495eee7b62ba2c36e7..9075393ff60e62e5047483c8f41475847d95b8e9 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -247,11 +247,33 @@ int forward_event_to_ibs(struct perf_event *event)
 	return -ENOENT;
 }
 
+/*
+ * Grouping of IBS events is not possible since IBS can have only
+ * one event active at any point in time.
+ */
+static int validate_group(struct perf_event *event)
+{
+	struct perf_event *sibling;
+
+	if (event->group_leader == event)
+		return 0;
+
+	if (event->group_leader->pmu == event->pmu)
+		return -EINVAL;
+
+	for_each_sibling_event(sibling, event->group_leader) {
+		if (sibling->pmu == event->pmu)
+			return -EINVAL;
+	}
+	return 0;
+}
+
 static int perf_ibs_init(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct perf_ibs *perf_ibs;
 	u64 max_cnt, config;
+	int ret;
 
 	perf_ibs = get_ibs_pmu(event->attr.type);
 	if (!perf_ibs)
@@ -265,6 +287,10 @@ static int perf_ibs_init(struct perf_event *event)
 	if (config & ~perf_ibs->config_mask)
 		return -EINVAL;
 
+	ret = validate_group(event);
+	if (ret)
+		return ret;
+
 	if (hwc->sample_period) {
 		if (config & perf_ibs->cnt_mask)
 			/* raw max_cnt may not be set */
@@ -712,38 +738,63 @@ static u8 perf_ibs_data_src(union ibs_op_data2 *op_data2)
 	return op_data2->data_src_lo;
 }
 
-static void perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2,
-				 union ibs_op_data3 *op_data3,
-				 struct perf_sample_data *data)
+#define	L(x)		(PERF_MEM_S(LVL, x) | PERF_MEM_S(LVL, HIT))
+#define	LN(x)		PERF_MEM_S(LVLNUM, x)
+#define	REM		PERF_MEM_S(REMOTE, REMOTE)
+#define	HOPS(x)		PERF_MEM_S(HOPS, x)
+
+static u64 g_data_src[8] = {
+	[IBS_DATA_SRC_LOC_CACHE]	  = L(L3) | L(REM_CCE1) | LN(ANY_CACHE) | HOPS(0),
+	[IBS_DATA_SRC_DRAM]		  = L(LOC_RAM) | LN(RAM),
+	[IBS_DATA_SRC_REM_CACHE]	  = L(REM_CCE2) | LN(ANY_CACHE) | REM | HOPS(1),
+	[IBS_DATA_SRC_IO]		  = L(IO) | LN(IO),
+};
+
+#define RMT_NODE_BITS			(1 << IBS_DATA_SRC_DRAM)
+#define RMT_NODE_APPLICABLE(x)		(RMT_NODE_BITS & (1 << x))
+
+static u64 g_zen4_data_src[32] = {
+	[IBS_DATA_SRC_EXT_LOC_CACHE]	  = L(L3) | LN(L3),
+	[IBS_DATA_SRC_EXT_NEAR_CCX_CACHE] = L(REM_CCE1) | LN(ANY_CACHE) | REM | HOPS(0),
+	[IBS_DATA_SRC_EXT_DRAM]		  = L(LOC_RAM) | LN(RAM),
+	[IBS_DATA_SRC_EXT_FAR_CCX_CACHE]  = L(REM_CCE2) | LN(ANY_CACHE) | REM | HOPS(1),
+	[IBS_DATA_SRC_EXT_PMEM]		  = LN(PMEM),
+	[IBS_DATA_SRC_EXT_IO]		  = L(IO) | LN(IO),
+	[IBS_DATA_SRC_EXT_EXT_MEM]	  = LN(CXL),
+};
+
+#define ZEN4_RMT_NODE_BITS		((1 << IBS_DATA_SRC_EXT_DRAM) | \
+					 (1 << IBS_DATA_SRC_EXT_PMEM) | \
+					 (1 << IBS_DATA_SRC_EXT_EXT_MEM))
+#define ZEN4_RMT_NODE_APPLICABLE(x)	(ZEN4_RMT_NODE_BITS & (1 << x))
+
+static __u64 perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2,
+				  union ibs_op_data3 *op_data3,
+				  struct perf_sample_data *data)
 {
 	union perf_mem_data_src *data_src = &data->data_src;
 	u8 ibs_data_src = perf_ibs_data_src(op_data2);
 
 	data_src->mem_lvl = 0;
+	data_src->mem_lvl_num = 0;
 
 	/*
 	 * DcMiss, L2Miss, DataSrc, DcMissLat etc. are all invalid for Uncached
 	 * memory accesses. So, check DcUcMemAcc bit early.
 	 */
-	if (op_data3->dc_uc_mem_acc && ibs_data_src != IBS_DATA_SRC_EXT_IO) {
-		data_src->mem_lvl = PERF_MEM_LVL_UNC | PERF_MEM_LVL_HIT;
-		return;
-	}
+	if (op_data3->dc_uc_mem_acc && ibs_data_src != IBS_DATA_SRC_EXT_IO)
+		return L(UNC) | LN(UNC);
 
 	/* L1 Hit */
-	if (op_data3->dc_miss == 0) {
-		data_src->mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;
-		return;
-	}
+	if (op_data3->dc_miss == 0)
+		return L(L1) | LN(L1);
 
 	/* L2 Hit */
 	if (op_data3->l2_miss == 0) {
 		/* Erratum #1293 */
 		if (boot_cpu_data.x86 != 0x19 || boot_cpu_data.x86_model > 0xF ||
-		    !(op_data3->sw_pf || op_data3->dc_miss_no_mab_alloc)) {
-			data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT;
-			return;
-		}
+		    !(op_data3->sw_pf || op_data3->dc_miss_no_mab_alloc))
+			return L(L2) | LN(L2);
 	}
 
 	/*
@@ -753,82 +804,36 @@ static void perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2,
 	if (data_src->mem_op != PERF_MEM_OP_LOAD)
 		goto check_mab;
 
-	/* L3 Hit */
 	if (ibs_caps & IBS_CAPS_ZEN4) {
-		if (ibs_data_src == IBS_DATA_SRC_EXT_LOC_CACHE) {
-			data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT;
-			return;
-		}
-	} else {
-		if (ibs_data_src == IBS_DATA_SRC_LOC_CACHE) {
-			data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_REM_CCE1 |
-					    PERF_MEM_LVL_HIT;
-			return;
-		}
-	}
+		u64 val = g_zen4_data_src[ibs_data_src];
 
-	/* A peer cache in a near CCX */
-	if (ibs_caps & IBS_CAPS_ZEN4 &&
-	    ibs_data_src == IBS_DATA_SRC_EXT_NEAR_CCX_CACHE) {
-		data_src->mem_lvl = PERF_MEM_LVL_REM_CCE1 | PERF_MEM_LVL_HIT;
-		return;
-	}
+		if (!val)
+			goto check_mab;
 
-	/* A peer cache in a far CCX */
-	if (ibs_caps & IBS_CAPS_ZEN4) {
-		if (ibs_data_src == IBS_DATA_SRC_EXT_FAR_CCX_CACHE) {
-			data_src->mem_lvl = PERF_MEM_LVL_REM_CCE2 | PERF_MEM_LVL_HIT;
-			return;
+		/* HOPS_1 because IBS doesn't provide remote socket detail */
+		if (op_data2->rmt_node && ZEN4_RMT_NODE_APPLICABLE(ibs_data_src)) {
+			if (ibs_data_src == IBS_DATA_SRC_EXT_DRAM)
+				val = L(REM_RAM1) | LN(RAM) | REM | HOPS(1);
+			else
+				val |= REM | HOPS(1);
 		}
-	} else {
-		if (ibs_data_src == IBS_DATA_SRC_REM_CACHE) {
-			data_src->mem_lvl = PERF_MEM_LVL_REM_CCE2 | PERF_MEM_LVL_HIT;
-			return;
-		}
-	}
 
-	/* DRAM */
-	if (ibs_data_src == IBS_DATA_SRC_EXT_DRAM) {
-		if (op_data2->rmt_node == 0)
-			data_src->mem_lvl = PERF_MEM_LVL_LOC_RAM | PERF_MEM_LVL_HIT;
-		else
-			data_src->mem_lvl = PERF_MEM_LVL_REM_RAM1 | PERF_MEM_LVL_HIT;
-		return;
-	}
+		return val;
+	} else {
+		u64 val = g_data_src[ibs_data_src];
 
-	/* PMEM */
-	if (ibs_caps & IBS_CAPS_ZEN4 && ibs_data_src == IBS_DATA_SRC_EXT_PMEM) {
-		data_src->mem_lvl_num = PERF_MEM_LVLNUM_PMEM;
-		if (op_data2->rmt_node) {
-			data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
-			/* IBS doesn't provide Remote socket detail */
-			data_src->mem_hops = PERF_MEM_HOPS_1;
-		}
-		return;
-	}
+		if (!val)
+			goto check_mab;
 
-	/* Extension Memory */
-	if (ibs_caps & IBS_CAPS_ZEN4 &&
-	    ibs_data_src == IBS_DATA_SRC_EXT_EXT_MEM) {
-		data_src->mem_lvl_num = PERF_MEM_LVLNUM_EXTN_MEM;
-		if (op_data2->rmt_node) {
-			data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
-			/* IBS doesn't provide Remote socket detail */
-			data_src->mem_hops = PERF_MEM_HOPS_1;
+		/* HOPS_1 because IBS doesn't provide remote socket detail */
+		if (op_data2->rmt_node && RMT_NODE_APPLICABLE(ibs_data_src)) {
+			if (ibs_data_src == IBS_DATA_SRC_DRAM)
+				val = L(REM_RAM1) | LN(RAM) | REM | HOPS(1);
+			else
+				val |= REM | HOPS(1);
 		}
-		return;
-	}
 
-	/* IO */
-	if (ibs_data_src == IBS_DATA_SRC_EXT_IO) {
-		data_src->mem_lvl = PERF_MEM_LVL_IO;
-		data_src->mem_lvl_num = PERF_MEM_LVLNUM_IO;
-		if (op_data2->rmt_node) {
-			data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
-			/* IBS doesn't provide Remote socket detail */
-			data_src->mem_hops = PERF_MEM_HOPS_1;
-		}
-		return;
+		return val;
 	}
 
 check_mab:
@@ -839,12 +844,11 @@ static void perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2,
 	 * DataSrc simultaneously. Prioritize DataSrc over MAB, i.e. set
 	 * MAB only when IBS fails to provide DataSrc.
 	 */
-	if (op_data3->dc_miss_no_mab_alloc) {
-		data_src->mem_lvl = PERF_MEM_LVL_LFB | PERF_MEM_LVL_HIT;
-		return;
-	}
+	if (op_data3->dc_miss_no_mab_alloc)
+		return L(LFB) | LN(LFB);
 
-	data_src->mem_lvl = PERF_MEM_LVL_NA;
+	/* Don't set HIT with NA */
+	return PERF_MEM_S(LVL, NA) | LN(NA);
 }
 
 static bool perf_ibs_cache_hit_st_valid(void)
@@ -934,7 +938,9 @@ static void perf_ibs_get_data_src(struct perf_ibs_data *ibs_data,
 				  union ibs_op_data2 *op_data2,
 				  union ibs_op_data3 *op_data3)
 {
-	perf_ibs_get_mem_lvl(op_data2, op_data3, data);
+	union perf_mem_data_src *data_src = &data->data_src;
+
+	data_src->val |= perf_ibs_get_mem_lvl(op_data2, op_data3, data);
 	perf_ibs_get_mem_snoop(op_data2, data);
 	perf_ibs_get_tlb_lvl(op_data3, data);
 	perf_ibs_get_mem_lock(op_data3, data);
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 5b4dcb47f96180e27de2a1807f57c29a53077918..81a9a4ae7b10458b0bbfe4a7ffa0a416335899d4 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -1269,8 +1269,9 @@ union perf_mem_data_src {
 #define PERF_MEM_LVLNUM_L2	0x02 /* L2 */
 #define PERF_MEM_LVLNUM_L3	0x03 /* L3 */
 #define PERF_MEM_LVLNUM_L4	0x04 /* L4 */
-/* 5-0x8 available */
-#define PERF_MEM_LVLNUM_EXTN_MEM 0x09 /* Extension memory */
+/* 5-0x7 available */
+#define PERF_MEM_LVLNUM_UNC	0x08 /* Uncached */
+#define PERF_MEM_LVLNUM_CXL	0x09 /* CXL */
 #define PERF_MEM_LVLNUM_IO	0x0a /* I/O */
 #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
 #define PERF_MEM_LVLNUM_LFB	0x0c /* LFB */
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index 5f7f55624b6fd5678ca107f069f6cbaa30d6a452..0c47da9639490b9fecca276691d6614315f14a2e 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -21,8 +21,8 @@ you to track down the cacheline contentions.
 
 On Intel, the tool is based on load latency and precise store facility events
 provided by Intel CPUs. On PowerPC, the tool uses random instruction sampling
-with thresholding feature. On AMD, the tool uses IBS op pmu (due to hardware
-limitations, perf c2c is not supported on Zen3 cpus).
+with thresholding feature. On AMD and Hygon, the tool uses IBS op pmu (due to
+hardware limitations, perf c2c is not supported on Zen3 cpus).
 
 These events provide:
   - memory address of the access
@@ -142,7 +142,7 @@ default on Intel:
   cpu/mem-loads,ldlat=30/P
   cpu/mem-stores/P
 
-following on AMD:
+following on AMD and Hygon:
 
   ibs_op//
 
diff --git a/tools/perf/arch/x86/util/env.c b/tools/perf/arch/x86/util/env.c
index 33b87f8ac1cc12c571aef74b4bd33f0223cf4649..bcd7b65f54d72a8596619a27e1415a3b34071e05 100644
--- a/tools/perf/arch/x86/util/env.c
+++ b/tools/perf/arch/x86/util/env.c
@@ -17,3 +17,18 @@ bool x86__is_amd_cpu(void)
 ret:
 	return is_amd >= 1 ? true : false;
 }
+
+bool x86__is_hygon_cpu(void)
+{
+	struct perf_env env = { .total_mem = 0, };
+	static int is_hygon; /* 0: Uninitialized, 1: Yes, -1: No */
+
+	if (is_hygon)
+		goto ret;
+
+	perf_env__cpuid(&env);
+	is_hygon = env.cpuid && strstarts(env.cpuid, "HygonGenuine") ? 1 : -1;
+	perf_env__exit(&env);
+ret:
+	return is_hygon >= 1 ? true : false;
+}
diff --git a/tools/perf/arch/x86/util/env.h b/tools/perf/arch/x86/util/env.h
index d78f080b6b3f889a3b5921d4ce5e3295cf340dcf..904d5e2283606a6ddc0d8be9a0538c74c7f63889 100644
--- a/tools/perf/arch/x86/util/env.h
+++ b/tools/perf/arch/x86/util/env.h
@@ -3,5 +3,6 @@
 #define _X86_ENV_H
 
 bool x86__is_amd_cpu(void);
+bool x86__is_hygon_cpu(void);
 
 #endif /* _X86_ENV_H */
diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c
index efc0fae9ed0a7af67b8e9e99387264966e39f7df..7fbace1587cb5b481277ecd4e942c7cc932ff491 100644
--- a/tools/perf/arch/x86/util/mem-events.c
+++ b/tools/perf/arch/x86/util/mem-events.c
@@ -32,7 +32,7 @@ struct perf_mem_event *perf_mem_events__ptr(int i)
 	if (i >= PERF_MEM_EVENTS__MAX)
 		return NULL;
 
-	if (x86__is_amd_cpu())
+	if (x86__is_amd_cpu() || x86__is_hygon_cpu())
 		return &perf_mem_events_amd[i];
 
 	return &perf_mem_events_intel[i];