diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 459abc5d181953..ea128e32e8ca8f 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -708,6 +708,7 @@ static_assert(offsetof(siginfo_t, si_upper)	== 0x18);
 static_assert(offsetof(siginfo_t, si_pkey)	== 0x14);
 static_assert(offsetof(siginfo_t, si_perf_data)	== 0x10);
 static_assert(offsetof(siginfo_t, si_perf_type)	== 0x14);
+static_assert(offsetof(siginfo_t, si_perf_flags) == 0x18);
 static_assert(offsetof(siginfo_t, si_band)	== 0x0c);
 static_assert(offsetof(siginfo_t, si_fd)	== 0x10);
 static_assert(offsetof(siginfo_t, si_call_addr)	== 0x0c);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 18bf590dc1c72f..edb2d9206a78b4 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -1179,6 +1179,7 @@ static_assert(offsetof(siginfo_t, si_upper)	== 0x28);
 static_assert(offsetof(siginfo_t, si_pkey)	== 0x20);
 static_assert(offsetof(siginfo_t, si_perf_data)	== 0x18);
 static_assert(offsetof(siginfo_t, si_perf_type)	== 0x20);
+static_assert(offsetof(siginfo_t, si_perf_flags) == 0x24);
 static_assert(offsetof(siginfo_t, si_band)	== 0x10);
 static_assert(offsetof(siginfo_t, si_fd)	== 0x18);
 static_assert(offsetof(siginfo_t, si_call_addr)	== 0x10);
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index d984282b979f86..4700f8522d27b1 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -487,6 +487,7 @@ static_assert(offsetof(compat_siginfo_t, si_upper)	== 0x18);
 static_assert(offsetof(compat_siginfo_t, si_pkey)	== 0x14);
 static_assert(offsetof(compat_siginfo_t, si_perf_data)	== 0x10);
 static_assert(offsetof(compat_siginfo_t, si_perf_type)	== 0x14);
+static_assert(offsetof(compat_siginfo_t, si_perf_flags)	== 0x18);
 static_assert(offsetof(compat_siginfo_t, si_band)	== 0x0c);
 static_assert(offsetof(compat_siginfo_t, si_fd)		== 0x10);
 static_assert(offsetof(compat_siginfo_t, si_call_addr)	== 0x0c);
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index 49533f65958a64..b9f6908a31bc39 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -625,6 +625,7 @@ static inline void siginfo_build_tests(void)
 	/* _sigfault._perf */
 	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x10);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x14);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_flags) != 0x18);
 
 	/* _sigpoll */
 	BUILD_BUG_ON(offsetof(siginfo_t, si_band)   != 0x0c);
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index f9fe502b81c65c..dad38960d1a8ac 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -779,5 +779,6 @@ static_assert(offsetof(compat_siginfo_t, si_upper)	== 0x18);
 static_assert(offsetof(compat_siginfo_t, si_pkey)	== 0x14);
 static_assert(offsetof(compat_siginfo_t, si_perf_data)	== 0x10);
 static_assert(offsetof(compat_siginfo_t, si_perf_type)	== 0x14);
+static_assert(offsetof(compat_siginfo_t, si_perf_flags)	== 0x18);
 static_assert(offsetof(compat_siginfo_t, si_band)	== 0x0c);
 static_assert(offsetof(compat_siginfo_t, si_fd)		== 0x10);
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 8b9fc76cd3e026..570e43e6fda5ca 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -590,5 +590,6 @@ static_assert(offsetof(siginfo_t, si_upper)	== 0x28);
 static_assert(offsetof(siginfo_t, si_pkey)	== 0x20);
 static_assert(offsetof(siginfo_t, si_perf_data)	== 0x18);
 static_assert(offsetof(siginfo_t, si_perf_type)	== 0x20);
+static_assert(offsetof(siginfo_t, si_perf_flags) == 0x24);
 static_assert(offsetof(siginfo_t, si_band)	== 0x10);
 static_assert(offsetof(siginfo_t, si_fd)	== 0x14);
diff --git a/arch/x86/events/Kconfig b/arch/x86/events/Kconfig
index d6cdfe63167489..09c56965750ae0 100644
--- a/arch/x86/events/Kconfig
+++ b/arch/x86/events/Kconfig
@@ -44,4 +44,12 @@ config PERF_EVENTS_AMD_UNCORE
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called 'amd-uncore'.
+
+config PERF_EVENTS_AMD_BRS
+	depends on PERF_EVENTS && CPU_SUP_AMD
+	bool "AMD Zen3 Branch Sampling support"
+	help
+	  Enable AMD Zen3 branch sampling support (BRS) which samples up to
+	  16 consecutive taken branches in registers.
+
 endmenu
diff --git a/arch/x86/events/amd/Makefile b/arch/x86/events/amd/Makefile
index 6cbe38d5fd9d1b..b9f5d4610256d1 100644
--- a/arch/x86/events/amd/Makefile
+++ b/arch/x86/events/amd/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_CPU_SUP_AMD)		+= core.o
+obj-$(CONFIG_PERF_EVENTS_AMD_BRS)	+= brs.o
 obj-$(CONFIG_PERF_EVENTS_AMD_POWER)	+= power.o
 obj-$(CONFIG_X86_LOCAL_APIC)		+= ibs.o
 obj-$(CONFIG_PERF_EVENTS_AMD_UNCORE)	+= amd-uncore.o
diff --git a/arch/x86/events/amd/brs.c b/arch/x86/events/amd/brs.c
new file mode 100644
index 00000000000000..bee8765a1e9b63
--- /dev/null
+++ b/arch/x86/events/amd/brs.c
@@ -0,0 +1,367 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Implement support for AMD Fam19h Branch Sampling feature
+ * Based on specifications published in AMD PPR Fam19 Model 01
+ *
+ * Copyright 2021 Google LLC
+ * Contributed by Stephane Eranian <eranian@google.com>
+ */
+#include <linux/kernel.h>
+#include <linux/jump_label.h>
+#include <asm/msr.h>
+#include <asm/cpufeature.h>
+
+#include "../perf_event.h"
+
+#define BRS_POISON	0xFFFFFFFFFFFFFFFEULL /* mark limit of valid entries */
+
+/* Debug Extension Configuration register layout */
+union amd_debug_extn_cfg {
+	__u64 val;
+	struct {
+		__u64	rsvd0:2,  /* reserved */
+			brsmen:1, /* branch sample enable */
+			rsvd4_3:2,/* reserved - must be 0x3 */
+			vb:1,     /* valid branches recorded */
+			rsvd2:10, /* reserved */
+			msroff:4, /* index of next entry to write */
+			rsvd3:4,  /* reserved */
+			pmc:3,    /* #PMC holding the sampling event */
+			rsvd4:37; /* reserved */
+	};
+};
+
+static inline unsigned int brs_from(int idx)
+{
+	return MSR_AMD_SAMP_BR_FROM + 2 * idx;
+}
+
+static inline unsigned int brs_to(int idx)
+{
+	return MSR_AMD_SAMP_BR_FROM + 2 * idx + 1;
+}
+
+static inline void set_debug_extn_cfg(u64 val)
+{
+	/* bits[4:3] must always be set to 11b */
+	wrmsrl(MSR_AMD_DBG_EXTN_CFG, val | 3ULL << 3);
+}
+
+static inline u64 get_debug_extn_cfg(void)
+{
+	u64 val;
+
+	rdmsrl(MSR_AMD_DBG_EXTN_CFG, val);
+	return val;
+}
+
+static bool __init amd_brs_detect(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_BRS))
+		return false;
+
+	switch (boot_cpu_data.x86) {
+	case 0x19: /* AMD Fam19h (Zen3) */
+		x86_pmu.lbr_nr = 16;
+
+		/* No hardware filtering supported */
+		x86_pmu.lbr_sel_map = NULL;
+		x86_pmu.lbr_sel_mask = 0;
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+/*
+ * Current BRS implementation does not support branch type or privilege level
+ * filtering. Therefore, this function simply enforces these limitations. No need for
+ * a br_sel_map. Software filtering is not supported because it would not correlate well
+ * with a sampling period.
+ */
+int amd_brs_setup_filter(struct perf_event *event)
+{
+	u64 type = event->attr.branch_sample_type;
+
+	/* No BRS support */
+	if (!x86_pmu.lbr_nr)
+		return -EOPNOTSUPP;
+
+	/* Can only capture all branches, i.e., no filtering */
+	if ((type & ~PERF_SAMPLE_BRANCH_PLM_ALL) != PERF_SAMPLE_BRANCH_ANY)
+		return -EINVAL;
+
+	return 0;
+}
+
+/* tos = top of stack, i.e., last valid entry written */
+static inline int amd_brs_get_tos(union amd_debug_extn_cfg *cfg)
+{
+	/*
+	 * msroff: index of next entry to write so top-of-stack is one off
+	 * if BRS is full then msroff is set back to 0.
+	 */
+	return (cfg->msroff ? cfg->msroff : x86_pmu.lbr_nr) - 1;
+}
+
+/*
+ * make sure we have a sane BRS offset to begin with
+ * especially with kexec
+ */
+void amd_brs_reset(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_BRS))
+		return;
+
+	/*
+	 * Reset config
+	 */
+	set_debug_extn_cfg(0);
+
+	/*
+	 * Mark first entry as poisoned
+	 */
+	wrmsrl(brs_to(0), BRS_POISON);
+}
+
+int __init amd_brs_init(void)
+{
+	if (!amd_brs_detect())
+		return -EOPNOTSUPP;
+
+	pr_cont("%d-deep BRS, ", x86_pmu.lbr_nr);
+
+	return 0;
+}
+
+void amd_brs_enable(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	union amd_debug_extn_cfg cfg;
+
+	/* Activate only on first user */
+	if (++cpuc->brs_active > 1)
+		return;
+
+	cfg.val    = 0; /* reset all fields */
+	cfg.brsmen = 1; /* enable branch sampling */
+
+	/* Set enable bit */
+	set_debug_extn_cfg(cfg.val);
+}
+
+void amd_brs_enable_all(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	if (cpuc->lbr_users)
+		amd_brs_enable();
+}
+
+void amd_brs_disable(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	union amd_debug_extn_cfg cfg;
+
+	/* Check if active (could be disabled via x86_pmu_disable_all()) */
+	if (!cpuc->brs_active)
+		return;
+
+	/* Only disable for last user */
+	if (--cpuc->brs_active)
+		return;
+
+	/*
+	 * Clear the brsmen bit but preserve the others as they contain
+	 * useful state such as vb and msroff
+	 */
+	cfg.val = get_debug_extn_cfg();
+
+	/*
+	 * When coming in on interrupt and BRS is full, then hw will have
+	 * already stopped BRS, no need to issue wrmsr again
+	 */
+	if (cfg.brsmen) {
+		cfg.brsmen = 0;
+		set_debug_extn_cfg(cfg.val);
+	}
+}
+
+void amd_brs_disable_all(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	if (cpuc->lbr_users)
+		amd_brs_disable();
+}
+
+static bool amd_brs_match_plm(struct perf_event *event, u64 to)
+{
+	int type = event->attr.branch_sample_type;
+	int plm_k = PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_HV;
+	int plm_u = PERF_SAMPLE_BRANCH_USER;
+
+	if (!(type & plm_k) && kernel_ip(to))
+		return 0;
+
+	if (!(type & plm_u) && !kernel_ip(to))
+		return 0;
+
+	return 1;
+}
+
+/*
+ * Caller must ensure amd_brs_inuse() is true before calling
+ * return:
+ */
+void amd_brs_drain(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct perf_event *event = cpuc->events[0];
+	struct perf_branch_entry *br = cpuc->lbr_entries;
+	union amd_debug_extn_cfg cfg;
+	u32 i, nr = 0, num, tos, start;
+	u32 shift = 64 - boot_cpu_data.x86_virt_bits;
+
+	/*
+	 * BRS event forced on PMC0,
+	 * so check if there is an event.
+	 * It is possible to have lbr_users > 0 but the event
+	 * not yet scheduled due to long latency PMU irq
+	 */
+	if (!event)
+		goto empty;
+
+	cfg.val = get_debug_extn_cfg();
+
+	/* Sanity check [0-x86_pmu.lbr_nr] */
+	if (WARN_ON_ONCE(cfg.msroff >= x86_pmu.lbr_nr))
+		goto empty;
+
+	/* No valid branch */
+	if (cfg.vb == 0)
+		goto empty;
+
+	/*
+	 * msr.off points to next entry to be written
+	 * tos = most recent entry index = msr.off - 1
+	 * BRS register buffer saturates, so we know we have
+	 * start < tos and that we have to read from start to tos
+	 */
+	start = 0;
+	tos = amd_brs_get_tos(&cfg);
+
+	num = tos - start + 1;
+
+	/*
+	 * BRS is only one pass (saturation) from MSROFF to depth-1
+	 * MSROFF wraps to zero when buffer is full
+	 */
+	for (i = 0; i < num; i++) {
+		u32 brs_idx = tos - i;
+		u64 from, to;
+
+		rdmsrl(brs_to(brs_idx), to);
+
+		/* Entry does not belong to us (as marked by kernel) */
+		if (to == BRS_POISON)
+			break;
+
+		/*
+		 * Sign-extend SAMP_BR_TO to 64 bits, bits 61-63 are reserved.
+		 * Necessary to generate proper virtual addresses suitable for
+		 * symbolization
+		 */
+		to = (u64)(((s64)to << shift) >> shift);
+
+		if (!amd_brs_match_plm(event, to))
+			continue;
+
+		rdmsrl(brs_from(brs_idx), from);
+
+		perf_clear_branch_entry_bitfields(br+nr);
+
+		br[nr].from = from;
+		br[nr].to   = to;
+
+		nr++;
+	}
+empty:
+	/* Record number of sampled branches */
+	cpuc->lbr_stack.nr = nr;
+}
+
+/*
+ * Poison most recent entry to prevent reuse by next task
+ * required because BRS entry are not tagged by PID
+ */
+static void amd_brs_poison_buffer(void)
+{
+	union amd_debug_extn_cfg cfg;
+	unsigned int idx;
+
+	/* Get current state */
+	cfg.val = get_debug_extn_cfg();
+
+	/* idx is most recently written entry */
+	idx = amd_brs_get_tos(&cfg);
+
+	/* Poison target of entry */
+	wrmsrl(brs_to(idx), BRS_POISON);
+}
+
+/*
+ * On context switch in, we need to make sure no samples from previous user
+ * are left in the BRS.
+ *
+ * On ctxswin, sched_in = true, called after the PMU has started
+ * On ctxswout, sched_in = false, called before the PMU is stopped
+ */
+void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	/* no active users */
+	if (!cpuc->lbr_users)
+		return;
+
+	/*
+	 * On context switch in, we need to ensure we do not use entries
+	 * from previous BRS user on that CPU, so we poison the buffer as
+	 * a faster way compared to resetting all entries.
+	 */
+	if (sched_in)
+		amd_brs_poison_buffer();
+}
+
+/*
+ * called from ACPI processor_idle.c or acpi_pad.c
+ * with interrupts disabled
+ */
+void perf_amd_brs_lopwr_cb(bool lopwr_in)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	union amd_debug_extn_cfg cfg;
+
+	/*
+	 * on mwait in, we may end up in non C0 state.
+	 * we must disable branch sampling to avoid holding the NMI
+	 * for too long. We disable it in hardware but we
+	 * keep the state in cpuc, so we can re-enable.
+	 *
+	 * The hardware will deliver the NMI if needed when brsmen cleared
+	 */
+	if (cpuc->brs_active) {
+		cfg.val = get_debug_extn_cfg();
+		cfg.brsmen = !lopwr_in;
+		set_debug_extn_cfg(cfg.val);
+	}
+}
+
+DEFINE_STATIC_CALL_NULL(perf_lopwr_cb, perf_amd_brs_lopwr_cb);
+EXPORT_STATIC_CALL_TRAMP_GPL(perf_lopwr_cb);
+
+void __init amd_brs_lopwr_init(void)
+{
+	static_call_update(perf_lopwr_cb, perf_amd_brs_lopwr_cb);
+}
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 9687a8aef01c5d..9ac3718410ce4b 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <linux/perf_event.h>
+#include <linux/jump_label.h>
 #include <linux/export.h>
 #include <linux/types.h>
 #include <linux/init.h>
@@ -7,6 +8,7 @@
 #include <linux/delay.h>
 #include <linux/jiffies.h>
 #include <asm/apicdef.h>
+#include <asm/apic.h>
 #include <asm/nmi.h>
 
 #include "../perf_event.h"
@@ -18,6 +20,9 @@ static unsigned long perf_nmi_window;
 #define AMD_MERGE_EVENT ((0xFULL << 32) | 0xFFULL)
 #define AMD_MERGE_EVENT_ENABLE (AMD_MERGE_EVENT | ARCH_PERFMON_EVENTSEL_ENABLE)
 
+/* PMC Enable and Overflow bits for PerfCntrGlobal* registers */
+static u64 amd_pmu_global_cntr_mask __read_mostly;
+
 static __initconst const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -325,8 +330,16 @@ static inline bool amd_is_pair_event_code(struct hw_perf_event *hwc)
 	}
 }
 
+#define AMD_FAM19H_BRS_EVENT 0xc4 /* RETIRED_TAKEN_BRANCH_INSTRUCTIONS */
+static inline int amd_is_brs_event(struct perf_event *e)
+{
+	return (e->hw.config & AMD64_RAW_EVENT_MASK) == AMD_FAM19H_BRS_EVENT;
+}
+
 static int amd_core_hw_config(struct perf_event *event)
 {
+	int ret = 0;
+
 	if (event->attr.exclude_host && event->attr.exclude_guest)
 		/*
 		 * When HO == GO == 1 the hardware treats that as GO == HO == 0
@@ -343,7 +356,66 @@ static int amd_core_hw_config(struct perf_event *event)
 	if ((x86_pmu.flags & PMU_FL_PAIR) && amd_is_pair_event_code(&event->hw))
 		event->hw.flags |= PERF_X86_EVENT_PAIR;
 
-	return 0;
+	/*
+	 * if branch stack is requested
+	 */
+	if (has_branch_stack(event)) {
+		/*
+		 * Due to interrupt holding, BRS is not recommended in
+		 * counting mode.
+		 */
+		if (!is_sampling_event(event))
+			return -EINVAL;
+
+		/*
+		 * Due to the way BRS operates by holding the interrupt until
+		 * lbr_nr entries have been captured, it does not make sense
+		 * to allow sampling on BRS with an event that does not match
+		 * what BRS is capturing, i.e., retired taken branches.
+		 * Otherwise the correlation with the event's period is even
+		 * more loose:
+		 *
+		 * With retired taken branch:
+		 *   Effective P = P + 16 + X
+		 * With any other event:
+		 *   Effective P = P + Y + X
+		 *
+		 * Where X is the number of taken branches due to interrupt
+		 * skid. Skid is large.
+		 *
+		 * Where Y is the occurences of the event while BRS is
+		 * capturing the lbr_nr entries.
+		 *
+		 * By using retired taken branches, we limit the impact on the
+		 * Y variable. We know it cannot be more than the depth of
+		 * BRS.
+		 */
+		if (!amd_is_brs_event(event))
+			return -EINVAL;
+
+		/*
+		 * BRS implementation does not work with frequency mode
+		 * reprogramming of the period.
+		 */
+		if (event->attr.freq)
+			return -EINVAL;
+		/*
+		 * The kernel subtracts BRS depth from period, so it must
+		 * be big enough.
+		 */
+		if (event->attr.sample_period <= x86_pmu.lbr_nr)
+			return -EINVAL;
+
+		/*
+		 * Check if we can allow PERF_SAMPLE_BRANCH_STACK
+		 */
+		ret = amd_brs_setup_filter(event);
+
+		/* only set in case of success */
+		if (!ret)
+			event->hw.flags |= PERF_X86_EVENT_AMD_BRS;
+	}
+	return ret;
 }
 
 static inline int amd_is_nb_event(struct hw_perf_event *hwc)
@@ -366,7 +438,7 @@ static int amd_pmu_hw_config(struct perf_event *event)
 	if (event->attr.precise_ip && get_ibs_caps())
 		return -ENOENT;
 
-	if (has_branch_stack(event))
+	if (has_branch_stack(event) && !x86_pmu.lbr_nr)
 		return -EOPNOTSUPP;
 
 	ret = x86_pmu_hw_config(event);
@@ -510,6 +582,18 @@ static struct amd_nb *amd_alloc_nb(int cpu)
 	return nb;
 }
 
+static void amd_pmu_cpu_reset(int cpu)
+{
+	if (x86_pmu.version < 2)
+		return;
+
+	/* Clear enable bits i.e. PerfCntrGlobalCtl.PerfCntrEn */
+	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, 0);
+
+	/* Clear overflow bits i.e. PerfCntrGLobalStatus.PerfCntrOvfl */
+	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, amd_pmu_global_cntr_mask);
+}
+
 static int amd_pmu_cpu_prepare(int cpu)
 {
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
@@ -555,6 +639,9 @@ static void amd_pmu_cpu_starting(int cpu)
 
 	cpuc->amd_nb->nb_id = nb_id;
 	cpuc->amd_nb->refcnt++;
+
+	amd_brs_reset();
+	amd_pmu_cpu_reset(cpu);
 }
 
 static void amd_pmu_cpu_dead(int cpu)
@@ -574,8 +661,54 @@ static void amd_pmu_cpu_dead(int cpu)
 
 		cpuhw->amd_nb = NULL;
 	}
+
+	amd_pmu_cpu_reset(cpu);
+}
+
+static inline void amd_pmu_set_global_ctl(u64 ctl)
+{
+	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, ctl);
 }
 
+static inline u64 amd_pmu_get_global_status(void)
+{
+	u64 status;
+
+	/* PerfCntrGlobalStatus is read-only */
+	rdmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, status);
+
+	return status & amd_pmu_global_cntr_mask;
+}
+
+static inline void amd_pmu_ack_global_status(u64 status)
+{
+	/*
+	 * PerfCntrGlobalStatus is read-only but an overflow acknowledgment
+	 * mechanism exists; writing 1 to a bit in PerfCntrGlobalStatusClr
+	 * clears the same bit in PerfCntrGlobalStatus
+	 */
+
+	/* Only allow modifications to PerfCntrGlobalStatus.PerfCntrOvfl */
+	status &= amd_pmu_global_cntr_mask;
+	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, status);
+}
+
+static bool amd_pmu_test_overflow_topbit(int idx)
+{
+	u64 counter;
+
+	rdmsrl(x86_pmu_event_addr(idx), counter);
+
+	return !(counter & BIT_ULL(x86_pmu.cntval_bits - 1));
+}
+
+static bool amd_pmu_test_overflow_status(int idx)
+{
+	return amd_pmu_get_global_status() & BIT_ULL(idx);
+}
+
+DEFINE_STATIC_CALL(amd_pmu_test_overflow, amd_pmu_test_overflow_topbit);
+
 /*
  * When a PMC counter overflows, an NMI is used to process the event and
  * reset the counter. NMI latency can result in the counter being updated
@@ -588,7 +721,6 @@ static void amd_pmu_cpu_dead(int cpu)
 static void amd_pmu_wait_on_overflow(int idx)
 {
 	unsigned int i;
-	u64 counter;
 
 	/*
 	 * Wait for the counter to be reset if it has overflowed. This loop
@@ -596,8 +728,7 @@ static void amd_pmu_wait_on_overflow(int idx)
 	 * forever...
 	 */
 	for (i = 0; i < OVERFLOW_WAIT_COUNT; i++) {
-		rdmsrl(x86_pmu_event_addr(idx), counter);
-		if (counter & (1ULL << (x86_pmu.cntval_bits - 1)))
+		if (!static_call(amd_pmu_test_overflow)(idx))
 			break;
 
 		/* Might be in IRQ context, so can't sleep */
@@ -605,13 +736,11 @@ static void amd_pmu_wait_on_overflow(int idx)
 	}
 }
 
-static void amd_pmu_disable_all(void)
+static void amd_pmu_check_overflow(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
-	x86_pmu_disable_all();
-
 	/*
 	 * This shouldn't be called from NMI context, but add a safeguard here
 	 * to return, since if we're in NMI context we can't wait for an NMI
@@ -634,6 +763,47 @@ static void amd_pmu_disable_all(void)
 	}
 }
 
+static void amd_pmu_enable_event(struct perf_event *event)
+{
+	x86_pmu_enable_event(event);
+}
+
+static void amd_pmu_enable_all(int added)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int idx;
+
+	amd_brs_enable_all();
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		/* only activate events which are marked as active */
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+
+		amd_pmu_enable_event(cpuc->events[idx]);
+	}
+}
+
+static void amd_pmu_v2_enable_event(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/*
+	 * Testing cpu_hw_events.enabled should be skipped in this case unlike
+	 * in x86_pmu_enable_event().
+	 *
+	 * Since cpu_hw_events.enabled is set only after returning from
+	 * x86_pmu_start(), the PMCs must be programmed and kept ready.
+	 * Counting starts only after x86_pmu_enable_all() is called.
+	 */
+	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+}
+
+static void amd_pmu_v2_enable_all(int added)
+{
+	amd_pmu_set_global_ctl(amd_pmu_global_cntr_mask);
+}
+
 static void amd_pmu_disable_event(struct perf_event *event)
 {
 	x86_pmu_disable_event(event);
@@ -651,6 +821,32 @@ static void amd_pmu_disable_event(struct perf_event *event)
 	amd_pmu_wait_on_overflow(event->hw.idx);
 }
 
+static void amd_pmu_disable_all(void)
+{
+	amd_brs_disable_all();
+	x86_pmu_disable_all();
+	amd_pmu_check_overflow();
+}
+
+static void amd_pmu_v2_disable_all(void)
+{
+	/* Disable all PMCs */
+	amd_pmu_set_global_ctl(0);
+	amd_pmu_check_overflow();
+}
+
+static void amd_pmu_add_event(struct perf_event *event)
+{
+	if (needs_branch_stack(event))
+		amd_pmu_brs_add(event);
+}
+
+static void amd_pmu_del_event(struct perf_event *event)
+{
+	if (needs_branch_stack(event))
+		amd_pmu_brs_del(event);
+}
+
 /*
  * Because of NMI latency, if multiple PMC counters are active or other sources
  * of NMIs are received, the perf NMI handler can handle one or more overflowed
@@ -669,13 +865,8 @@ static void amd_pmu_disable_event(struct perf_event *event)
  * handled a counter. When an un-handled NMI is received, it will be claimed
  * only if arriving within that window.
  */
-static int amd_pmu_handle_irq(struct pt_regs *regs)
+static inline int amd_pmu_adjust_nmi_window(int handled)
 {
-	int handled;
-
-	/* Process any counter overflows */
-	handled = x86_pmu_handle_irq(regs);
-
 	/*
 	 * If a counter was handled, record a timestamp such that un-handled
 	 * NMIs will be claimed if arriving within that window.
@@ -692,6 +883,113 @@ static int amd_pmu_handle_irq(struct pt_regs *regs)
 	return NMI_HANDLED;
 }
 
+static int amd_pmu_handle_irq(struct pt_regs *regs)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int handled;
+	int pmu_enabled;
+
+	/*
+	 * Save the PMU state.
+	 * It needs to be restored when leaving the handler.
+	 */
+	pmu_enabled = cpuc->enabled;
+	cpuc->enabled = 0;
+
+	/* stop everything (includes BRS) */
+	amd_pmu_disable_all();
+
+	/* Drain BRS is in use (could be inactive) */
+	if (cpuc->lbr_users)
+		amd_brs_drain();
+
+	/* Process any counter overflows */
+	handled = x86_pmu_handle_irq(regs);
+
+	cpuc->enabled = pmu_enabled;
+	if (pmu_enabled)
+		amd_pmu_enable_all(0);
+
+	return amd_pmu_adjust_nmi_window(handled);
+}
+
+static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct perf_sample_data data;
+	struct hw_perf_event *hwc;
+	struct perf_event *event;
+	int handled = 0, idx;
+	u64 status, mask;
+	bool pmu_enabled;
+
+	/*
+	 * Save the PMU state as it needs to be restored when leaving the
+	 * handler
+	 */
+	pmu_enabled = cpuc->enabled;
+	cpuc->enabled = 0;
+
+	/* Stop counting */
+	amd_pmu_v2_disable_all();
+
+	status = amd_pmu_get_global_status();
+
+	/* Check if any overflows are pending */
+	if (!status)
+		goto done;
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+
+		event = cpuc->events[idx];
+		hwc = &event->hw;
+		x86_perf_event_update(event);
+		mask = BIT_ULL(idx);
+
+		if (!(status & mask))
+			continue;
+
+		/* Event overflow */
+		handled++;
+		perf_sample_data_init(&data, 0, hwc->last_period);
+
+		if (!x86_perf_event_set_period(event))
+			continue;
+
+		if (perf_event_overflow(event, &data, regs))
+			x86_pmu_stop(event, 0);
+
+		status &= ~mask;
+	}
+
+	/*
+	 * It should never be the case that some overflows are not handled as
+	 * the corresponding PMCs are expected to be inactive according to the
+	 * active_mask
+	 */
+	WARN_ON(status > 0);
+
+	/* Clear overflow bits */
+	amd_pmu_ack_global_status(~status);
+
+	/*
+	 * Unmasking the LVTPC is not required as the Mask (M) bit of the LVT
+	 * PMI entry is not set by the local APIC when a PMC overflow occurs
+	 */
+	inc_irq_stat(apic_perf_irqs);
+
+done:
+	cpuc->enabled = pmu_enabled;
+
+	/* Resume counting only if PMU is active */
+	if (pmu_enabled)
+		amd_pmu_v2_enable_all(0);
+
+	return amd_pmu_adjust_nmi_window(handled);
+}
+
 static struct event_constraint *
 amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			  struct perf_event *event)
@@ -897,6 +1195,51 @@ static void amd_put_event_constraints_f17h(struct cpu_hw_events *cpuc,
 		--cpuc->n_pair;
 }
 
+/*
+ * Because of the way BRS operates with an inactive and active phases, and
+ * the link to one counter, it is not possible to have two events using BRS
+ * scheduled at the same time. There would be an issue with enforcing the
+ * period of each one and given that the BRS saturates, it would not be possible
+ * to guarantee correlated content for all events. Therefore, in situations
+ * where multiple events want to use BRS, the kernel enforces mutual exclusion.
+ * Exclusion is enforced by chosing only one counter for events using BRS.
+ * The event scheduling logic will then automatically multiplex the
+ * events and ensure that at most one event is actively using BRS.
+ *
+ * The BRS counter could be any counter, but there is no constraint on Fam19h,
+ * therefore all counters are equal and thus we pick the first one: PMC0
+ */
+static struct event_constraint amd_fam19h_brs_cntr0_constraint =
+	EVENT_CONSTRAINT(0, 0x1, AMD64_RAW_EVENT_MASK);
+
+static struct event_constraint amd_fam19h_brs_pair_cntr0_constraint =
+	__EVENT_CONSTRAINT(0, 0x1, AMD64_RAW_EVENT_MASK, 1, 0, PERF_X86_EVENT_PAIR);
+
+static struct event_constraint *
+amd_get_event_constraints_f19h(struct cpu_hw_events *cpuc, int idx,
+			  struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	bool has_brs = has_amd_brs(hwc);
+
+	/*
+	 * In case BRS is used with an event requiring a counter pair,
+	 * the kernel allows it but only on counter 0 & 1 to enforce
+	 * multiplexing requiring to protect BRS in case of multiple
+	 * BRS users
+	 */
+	if (amd_is_pair_event_code(hwc)) {
+		return has_brs ? &amd_fam19h_brs_pair_cntr0_constraint
+			       : &pair_constraint;
+	}
+
+	if (has_brs)
+		return &amd_fam19h_brs_cntr0_constraint;
+
+	return &unconstrained;
+}
+
+
 static ssize_t amd_event_sysfs_show(char *page, u64 config)
 {
 	u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT) |
@@ -905,12 +1248,31 @@ static ssize_t amd_event_sysfs_show(char *page, u64 config)
 	return x86_event_sysfs_show(page, config, event);
 }
 
+static void amd_pmu_sched_task(struct perf_event_context *ctx,
+				 bool sched_in)
+{
+	if (sched_in && x86_pmu.lbr_nr)
+		amd_pmu_brs_sched_task(ctx, sched_in);
+}
+
+static u64 amd_pmu_limit_period(struct perf_event *event, u64 left)
+{
+	/*
+	 * Decrease period by the depth of the BRS feature to get the last N
+	 * taken branches and approximate the desired period
+	 */
+	if (has_branch_stack(event) && left > x86_pmu.lbr_nr)
+		left -= x86_pmu.lbr_nr;
+
+	return left;
+}
+
 static __initconst const struct x86_pmu amd_pmu = {
 	.name			= "AMD",
 	.handle_irq		= amd_pmu_handle_irq,
 	.disable_all		= amd_pmu_disable_all,
-	.enable_all		= x86_pmu_enable_all,
-	.enable			= x86_pmu_enable_event,
+	.enable_all		= amd_pmu_enable_all,
+	.enable			= amd_pmu_enable_event,
 	.disable		= amd_pmu_disable_event,
 	.hw_config		= amd_pmu_hw_config,
 	.schedule_events	= x86_schedule_events,
@@ -920,6 +1282,8 @@ static __initconst const struct x86_pmu amd_pmu = {
 	.event_map		= amd_pmu_event_map,
 	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
 	.num_counters		= AMD64_NUM_COUNTERS,
+	.add			= amd_pmu_add_event,
+	.del			= amd_pmu_del_event,
 	.cntval_bits		= 48,
 	.cntval_mask		= (1ULL << 48) - 1,
 	.apic			= 1,
@@ -938,8 +1302,55 @@ static __initconst const struct x86_pmu amd_pmu = {
 	.amd_nb_constraints	= 1,
 };
 
+static ssize_t branches_show(struct device *cdev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", x86_pmu.lbr_nr);
+}
+
+static DEVICE_ATTR_RO(branches);
+
+static struct attribute *amd_pmu_brs_attrs[] = {
+	&dev_attr_branches.attr,
+	NULL,
+};
+
+static umode_t
+amd_brs_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	return x86_pmu.lbr_nr ? attr->mode : 0;
+}
+
+static struct attribute_group group_caps_amd_brs = {
+	.name  = "caps",
+	.attrs = amd_pmu_brs_attrs,
+	.is_visible = amd_brs_is_visible,
+};
+
+EVENT_ATTR_STR(branch-brs, amd_branch_brs,
+	       "event=" __stringify(AMD_FAM19H_BRS_EVENT)"\n");
+
+static struct attribute *amd_brs_events_attrs[] = {
+	EVENT_PTR(amd_branch_brs),
+	NULL,
+};
+
+static struct attribute_group group_events_amd_brs = {
+	.name       = "events",
+	.attrs      = amd_brs_events_attrs,
+	.is_visible = amd_brs_is_visible,
+};
+
+static const struct attribute_group *amd_attr_update[] = {
+	&group_caps_amd_brs,
+	&group_events_amd_brs,
+	NULL,
+};
+
 static int __init amd_core_pmu_init(void)
 {
+	union cpuid_0x80000022_ebx ebx;
 	u64 even_ctr_mask = 0ULL;
 	int i;
 
@@ -957,6 +1368,27 @@ static int __init amd_core_pmu_init(void)
 	x86_pmu.eventsel	= MSR_F15H_PERF_CTL;
 	x86_pmu.perfctr		= MSR_F15H_PERF_CTR;
 	x86_pmu.num_counters	= AMD64_NUM_COUNTERS_CORE;
+
+	/* Check for Performance Monitoring v2 support */
+	if (boot_cpu_has(X86_FEATURE_PERFMON_V2)) {
+		ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES);
+
+		/* Update PMU version for later usage */
+		x86_pmu.version = 2;
+
+		/* Find the number of available Core PMCs */
+		x86_pmu.num_counters = ebx.split.num_core_pmc;
+
+		amd_pmu_global_cntr_mask = (1ULL << x86_pmu.num_counters) - 1;
+
+		/* Update PMC handling functions */
+		x86_pmu.enable_all = amd_pmu_v2_enable_all;
+		x86_pmu.disable_all = amd_pmu_v2_disable_all;
+		x86_pmu.enable = amd_pmu_v2_enable_event;
+		x86_pmu.handle_irq = amd_pmu_v2_handle_irq;
+		static_call_update(amd_pmu_test_overflow, amd_pmu_test_overflow_status);
+	}
+
 	/*
 	 * AMD Core perfctr has separate MSRs for the NB events, see
 	 * the amd/uncore.c driver.
@@ -989,6 +1421,23 @@ static int __init amd_core_pmu_init(void)
 		x86_pmu.flags |= PMU_FL_PAIR;
 	}
 
+	/*
+	 * BRS requires special event constraints and flushing on ctxsw.
+	 */
+	if (boot_cpu_data.x86 >= 0x19 && !amd_brs_init()) {
+		x86_pmu.get_event_constraints = amd_get_event_constraints_f19h;
+		x86_pmu.sched_task = amd_pmu_sched_task;
+		x86_pmu.limit_period = amd_pmu_limit_period;
+		/*
+		 * put_event_constraints callback same as Fam17h, set above
+		 */
+
+		/* branch sampling must be stopped when entering low power */
+		amd_brs_lopwr_init();
+	}
+
+	x86_pmu.attr_update = amd_attr_update;
+
 	pr_cont("core perfctr, ");
 	return 0;
 }
@@ -1023,6 +1472,24 @@ __init int amd_pmu_init(void)
 	return 0;
 }
 
+static inline void amd_pmu_reload_virt(void)
+{
+	if (x86_pmu.version >= 2) {
+		/*
+		 * Clear global enable bits, reprogram the PERF_CTL
+		 * registers with updated perf_ctr_virt_mask and then
+		 * set global enable bits once again
+		 */
+		amd_pmu_v2_disable_all();
+		amd_pmu_enable_all(0);
+		amd_pmu_v2_enable_all(0);
+		return;
+	}
+
+	amd_pmu_disable_all();
+	amd_pmu_enable_all(0);
+}
+
 void amd_pmu_enable_virt(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1030,8 +1497,7 @@ void amd_pmu_enable_virt(void)
 	cpuc->perf_ctr_virt_mask = 0;
 
 	/* Reload all events */
-	amd_pmu_disable_all();
-	x86_pmu_enable_all(0);
+	amd_pmu_reload_virt();
 }
 EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
 
@@ -1048,7 +1514,6 @@ void amd_pmu_disable_virt(void)
 	cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
 
 	/* Reload all events */
-	amd_pmu_disable_all();
-	x86_pmu_enable_all(0);
+	amd_pmu_reload_virt();
 }
 EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 9739019d4b67af..c251bc44c088d8 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -94,10 +94,6 @@ struct perf_ibs {
 	unsigned int			fetch_ignore_if_zero_rip : 1;
 	struct cpu_perf_ibs __percpu	*pcpu;
 
-	struct attribute		**format_attrs;
-	struct attribute_group		format_group;
-	const struct attribute_group	*attr_groups[2];
-
 	u64				(*get_count)(u64 config);
 };
 
@@ -304,6 +300,16 @@ static int perf_ibs_init(struct perf_event *event)
 	hwc->config_base = perf_ibs->msr;
 	hwc->config = config;
 
+	/*
+	 * rip recorded by IbsOpRip will not be consistent with rsp and rbp
+	 * recorded as part of interrupt regs. Thus we need to use rip from
+	 * interrupt regs while unwinding call stack. Setting _EARLY flag
+	 * makes sure we unwind call-stack before perf sample rip is set to
+	 * IbsOpRip.
+	 */
+	if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+		event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY;
+
 	return 0;
 }
 
@@ -518,16 +524,118 @@ static void perf_ibs_del(struct perf_event *event, int flags)
 
 static void perf_ibs_read(struct perf_event *event) { }
 
+/*
+ * We need to initialize with empty group if all attributes in the
+ * group are dynamic.
+ */
+static struct attribute *attrs_empty[] = {
+	NULL,
+};
+
+static struct attribute_group empty_format_group = {
+	.name = "format",
+	.attrs = attrs_empty,
+};
+
+static struct attribute_group empty_caps_group = {
+	.name = "caps",
+	.attrs = attrs_empty,
+};
+
+static const struct attribute_group *empty_attr_groups[] = {
+	&empty_format_group,
+	&empty_caps_group,
+	NULL,
+};
+
 PMU_FORMAT_ATTR(rand_en,	"config:57");
 PMU_FORMAT_ATTR(cnt_ctl,	"config:19");
+PMU_EVENT_ATTR_STRING(l3missonly, fetch_l3missonly, "config:59");
+PMU_EVENT_ATTR_STRING(l3missonly, op_l3missonly, "config:16");
+PMU_EVENT_ATTR_STRING(zen4_ibs_extensions, zen4_ibs_extensions, "1");
 
-static struct attribute *ibs_fetch_format_attrs[] = {
+static umode_t
+zen4_ibs_extensions_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	return ibs_caps & IBS_CAPS_ZEN4 ? attr->mode : 0;
+}
+
+static struct attribute *rand_en_attrs[] = {
 	&format_attr_rand_en.attr,
 	NULL,
 };
 
-static struct attribute *ibs_op_format_attrs[] = {
-	NULL,	/* &format_attr_cnt_ctl.attr if IBS_CAPS_OPCNT */
+static struct attribute *fetch_l3missonly_attrs[] = {
+	&fetch_l3missonly.attr.attr,
+	NULL,
+};
+
+static struct attribute *zen4_ibs_extensions_attrs[] = {
+	&zen4_ibs_extensions.attr.attr,
+	NULL,
+};
+
+static struct attribute_group group_rand_en = {
+	.name = "format",
+	.attrs = rand_en_attrs,
+};
+
+static struct attribute_group group_fetch_l3missonly = {
+	.name = "format",
+	.attrs = fetch_l3missonly_attrs,
+	.is_visible = zen4_ibs_extensions_is_visible,
+};
+
+static struct attribute_group group_zen4_ibs_extensions = {
+	.name = "caps",
+	.attrs = zen4_ibs_extensions_attrs,
+	.is_visible = zen4_ibs_extensions_is_visible,
+};
+
+static const struct attribute_group *fetch_attr_groups[] = {
+	&group_rand_en,
+	&empty_caps_group,
+	NULL,
+};
+
+static const struct attribute_group *fetch_attr_update[] = {
+	&group_fetch_l3missonly,
+	&group_zen4_ibs_extensions,
+	NULL,
+};
+
+static umode_t
+cnt_ctl_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	return ibs_caps & IBS_CAPS_OPCNT ? attr->mode : 0;
+}
+
+static struct attribute *cnt_ctl_attrs[] = {
+	&format_attr_cnt_ctl.attr,
+	NULL,
+};
+
+static struct attribute *op_l3missonly_attrs[] = {
+	&op_l3missonly.attr.attr,
+	NULL,
+};
+
+static struct attribute_group group_cnt_ctl = {
+	.name = "format",
+	.attrs = cnt_ctl_attrs,
+	.is_visible = cnt_ctl_is_visible,
+};
+
+static struct attribute_group group_op_l3missonly = {
+	.name = "format",
+	.attrs = op_l3missonly_attrs,
+	.is_visible = zen4_ibs_extensions_is_visible,
+};
+
+static const struct attribute_group *op_attr_update[] = {
+	&group_cnt_ctl,
+	&group_op_l3missonly,
+	&group_zen4_ibs_extensions,
 	NULL,
 };
 
@@ -551,7 +659,6 @@ static struct perf_ibs perf_ibs_fetch = {
 	.max_period		= IBS_FETCH_MAX_CNT << 4,
 	.offset_mask		= { MSR_AMD64_IBSFETCH_REG_MASK },
 	.offset_max		= MSR_AMD64_IBSFETCH_REG_COUNT,
-	.format_attrs		= ibs_fetch_format_attrs,
 
 	.get_count		= get_ibs_fetch_count,
 };
@@ -577,7 +684,6 @@ static struct perf_ibs perf_ibs_op = {
 	.max_period		= IBS_OP_MAX_CNT << 4,
 	.offset_mask		= { MSR_AMD64_IBSOP_REG_MASK },
 	.offset_max		= MSR_AMD64_IBSOP_REG_COUNT,
-	.format_attrs		= ibs_op_format_attrs,
 
 	.get_count		= get_ibs_op_count,
 };
@@ -687,6 +793,14 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 		data.raw = &raw;
 	}
 
+	/*
+	 * rip recorded by IbsOpRip will not be consistent with rsp and rbp
+	 * recorded as part of interrupt regs. Thus we need to use rip from
+	 * interrupt regs while unwinding call stack.
+	 */
+	if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+		data.callchain = perf_callchain(event, iregs);
+
 	throttle = perf_event_overflow(event, &data, &regs);
 out:
 	if (throttle) {
@@ -739,17 +853,6 @@ static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name)
 
 	perf_ibs->pcpu = pcpu;
 
-	/* register attributes */
-	if (perf_ibs->format_attrs[0]) {
-		memset(&perf_ibs->format_group, 0, sizeof(perf_ibs->format_group));
-		perf_ibs->format_group.name	= "format";
-		perf_ibs->format_group.attrs	= perf_ibs->format_attrs;
-
-		memset(&perf_ibs->attr_groups, 0, sizeof(perf_ibs->attr_groups));
-		perf_ibs->attr_groups[0]	= &perf_ibs->format_group;
-		perf_ibs->pmu.attr_groups	= perf_ibs->attr_groups;
-	}
-
 	ret = perf_pmu_register(&perf_ibs->pmu, name, -1);
 	if (ret) {
 		perf_ibs->pcpu = NULL;
@@ -759,10 +862,8 @@ static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name)
 	return ret;
 }
 
-static __init void perf_event_ibs_init(void)
+static __init int perf_ibs_fetch_init(void)
 {
-	struct attribute **attr = ibs_op_format_attrs;
-
 	/*
 	 * Some chips fail to reset the fetch count when it is written; instead
 	 * they need a 0-1 transition of IbsFetchEn.
@@ -773,12 +874,19 @@ static __init void perf_event_ibs_init(void)
 	if (boot_cpu_data.x86 == 0x19 && boot_cpu_data.x86_model < 0x10)
 		perf_ibs_fetch.fetch_ignore_if_zero_rip = 1;
 
-	perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch");
+	if (ibs_caps & IBS_CAPS_ZEN4)
+		perf_ibs_fetch.config_mask |= IBS_FETCH_L3MISSONLY;
+
+	perf_ibs_fetch.pmu.attr_groups = fetch_attr_groups;
+	perf_ibs_fetch.pmu.attr_update = fetch_attr_update;
 
-	if (ibs_caps & IBS_CAPS_OPCNT) {
+	return perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch");
+}
+
+static __init int perf_ibs_op_init(void)
+{
+	if (ibs_caps & IBS_CAPS_OPCNT)
 		perf_ibs_op.config_mask |= IBS_OP_CNT_CTL;
-		*attr++ = &format_attr_cnt_ctl.attr;
-	}
 
 	if (ibs_caps & IBS_CAPS_OPCNTEXT) {
 		perf_ibs_op.max_period  |= IBS_OP_MAX_CNT_EXT_MASK;
@@ -786,15 +894,52 @@ static __init void perf_event_ibs_init(void)
 		perf_ibs_op.cnt_mask    |= IBS_OP_MAX_CNT_EXT_MASK;
 	}
 
-	perf_ibs_pmu_init(&perf_ibs_op, "ibs_op");
+	if (ibs_caps & IBS_CAPS_ZEN4)
+		perf_ibs_op.config_mask |= IBS_OP_L3MISSONLY;
+
+	perf_ibs_op.pmu.attr_groups = empty_attr_groups;
+	perf_ibs_op.pmu.attr_update = op_attr_update;
+
+	return perf_ibs_pmu_init(&perf_ibs_op, "ibs_op");
+}
+
+static __init int perf_event_ibs_init(void)
+{
+	int ret;
+
+	ret = perf_ibs_fetch_init();
+	if (ret)
+		return ret;
+
+	ret = perf_ibs_op_init();
+	if (ret)
+		goto err_op;
+
+	ret = register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs");
+	if (ret)
+		goto err_nmi;
 
-	register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs");
 	pr_info("perf: AMD IBS detected (0x%08x)\n", ibs_caps);
+	return 0;
+
+err_nmi:
+	perf_pmu_unregister(&perf_ibs_op.pmu);
+	free_percpu(perf_ibs_op.pcpu);
+	perf_ibs_op.pcpu = NULL;
+err_op:
+	perf_pmu_unregister(&perf_ibs_fetch.pmu);
+	free_percpu(perf_ibs_fetch.pcpu);
+	perf_ibs_fetch.pcpu = NULL;
+
+	return ret;
 }
 
 #else /* defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) */
 
-static __init void perf_event_ibs_init(void) { }
+static __init int perf_event_ibs_init(void)
+{
+	return 0;
+}
 
 #endif
 
@@ -1064,9 +1209,7 @@ static __init int amd_ibs_init(void)
 			  x86_pmu_amd_ibs_starting_cpu,
 			  x86_pmu_amd_ibs_dying_cpu);
 
-	perf_event_ibs_init();
-
-	return 0;
+	return perf_event_ibs_init();
 }
 
 /* Since we need the pci subsystem to init ibs we can't do this earlier: */
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index eef816fc216d34..30788894124f0e 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1338,6 +1338,10 @@ static void x86_pmu_enable(struct pmu *pmu)
 			if (hwc->state & PERF_HES_ARCH)
 				continue;
 
+			/*
+			 * if cpuc->enabled = 0, then no wrmsr as
+			 * per x86_pmu_enable_event()
+			 */
 			x86_pmu_start(event, PERF_EF_RELOAD);
 		}
 		cpuc->n_added = 0;
@@ -1704,11 +1708,15 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 		 * event overflow
 		 */
 		handled++;
-		perf_sample_data_init(&data, 0, event->hw.last_period);
 
 		if (!x86_perf_event_set_period(event))
 			continue;
 
+		perf_sample_data_init(&data, 0, event->hw.last_period);
+
+		if (has_branch_stack(event))
+			data.br_stack = &cpuc->lbr_stack;
+
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
 	}
@@ -1837,7 +1845,7 @@ ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, cha
 
 	/* string trumps id */
 	if (pmu_attr->event_str)
-		return sprintf(page, "%s", pmu_attr->event_str);
+		return sprintf(page, "%s\n", pmu_attr->event_str);
 
 	return x86_pmu.events_sysfs_show(page, config);
 }
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index fc7f458eb3de63..955ae91c56dca5 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -6216,7 +6216,9 @@ __init int intel_pmu_init(void)
 
 	case INTEL_FAM6_ALDERLAKE:
 	case INTEL_FAM6_ALDERLAKE_L:
+	case INTEL_FAM6_ALDERLAKE_N:
 	case INTEL_FAM6_RAPTORLAKE:
+	case INTEL_FAM6_RAPTORLAKE_P:
 		/*
 		 * Alder Lake has 2 types of CPU, core and atom.
 		 *
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 48e5db21142c22..8ec23f47fee9a7 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -682,7 +682,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&adl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&adl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,		&adl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&adl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&adl_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index fe1742c4ca4986..13179f31fe10fa 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -769,6 +769,7 @@ void intel_pmu_lbr_disable_all(void)
 void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 {
 	unsigned long mask = x86_pmu.lbr_nr - 1;
+	struct perf_branch_entry *br = cpuc->lbr_entries;
 	u64 tos = intel_pmu_lbr_tos();
 	int i;
 
@@ -784,15 +785,11 @@ void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
 
-		cpuc->lbr_entries[i].from	= msr_lastbranch.from;
-		cpuc->lbr_entries[i].to		= msr_lastbranch.to;
-		cpuc->lbr_entries[i].mispred	= 0;
-		cpuc->lbr_entries[i].predicted	= 0;
-		cpuc->lbr_entries[i].in_tx	= 0;
-		cpuc->lbr_entries[i].abort	= 0;
-		cpuc->lbr_entries[i].cycles	= 0;
-		cpuc->lbr_entries[i].type	= 0;
-		cpuc->lbr_entries[i].reserved	= 0;
+		perf_clear_branch_entry_bitfields(br);
+
+		br->from	= msr_lastbranch.from;
+		br->to		= msr_lastbranch.to;
+		br++;
 	}
 	cpuc->lbr_stack.nr = i;
 	cpuc->lbr_stack.hw_idx = tos;
@@ -807,6 +804,7 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 {
 	bool need_info = false, call_stack = false;
 	unsigned long mask = x86_pmu.lbr_nr - 1;
+	struct perf_branch_entry *br = cpuc->lbr_entries;
 	u64 tos = intel_pmu_lbr_tos();
 	int i;
 	int out = 0;
@@ -878,15 +876,14 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		if (abort && x86_pmu.lbr_double_abort && out > 0)
 			out--;
 
-		cpuc->lbr_entries[out].from	 = from;
-		cpuc->lbr_entries[out].to	 = to;
-		cpuc->lbr_entries[out].mispred	 = mis;
-		cpuc->lbr_entries[out].predicted = pred;
-		cpuc->lbr_entries[out].in_tx	 = in_tx;
-		cpuc->lbr_entries[out].abort	 = abort;
-		cpuc->lbr_entries[out].cycles	 = cycles;
-		cpuc->lbr_entries[out].type	 = 0;
-		cpuc->lbr_entries[out].reserved	 = 0;
+		perf_clear_branch_entry_bitfields(br+out);
+		br[out].from	 = from;
+		br[out].to	 = to;
+		br[out].mispred	 = mis;
+		br[out].predicted = pred;
+		br[out].in_tx	 = in_tx;
+		br[out].abort	 = abort;
+		br[out].cycles	 = cycles;
 		out++;
 	}
 	cpuc->lbr_stack.nr = out;
@@ -951,6 +948,8 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
 		to = rdlbr_to(i, lbr);
 		info = rdlbr_info(i, lbr);
 
+		perf_clear_branch_entry_bitfields(e);
+
 		e->from		= from;
 		e->to		= to;
 		e->mispred	= get_lbr_mispred(info);
@@ -959,7 +958,6 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
 		e->abort	= !!(info & LBR_INFO_ABORT);
 		e->cycles	= get_lbr_cycles(info);
 		e->type		= get_lbr_br_type(info);
-		e->reserved	= 0;
 	}
 
 	cpuc->lbr_stack.nr = i;
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 7695dcae280e70..db6c31bca80927 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1828,7 +1828,9 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE,		&rkl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&adl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,		&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&adl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&spr_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&snr_uncore_init),
 	{},
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 4262351f52b60b..ce440011cc4e41 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -79,10 +79,43 @@
 #define PCI_DEVICE_ID_INTEL_ADL_14_IMC		0x4650
 #define PCI_DEVICE_ID_INTEL_ADL_15_IMC		0x4668
 #define PCI_DEVICE_ID_INTEL_ADL_16_IMC		0x4670
+#define PCI_DEVICE_ID_INTEL_ADL_17_IMC		0x4614
+#define PCI_DEVICE_ID_INTEL_ADL_18_IMC		0x4617
+#define PCI_DEVICE_ID_INTEL_ADL_19_IMC		0x4618
+#define PCI_DEVICE_ID_INTEL_ADL_20_IMC		0x461B
+#define PCI_DEVICE_ID_INTEL_ADL_21_IMC		0x461C
 #define PCI_DEVICE_ID_INTEL_RPL_1_IMC		0xA700
 #define PCI_DEVICE_ID_INTEL_RPL_2_IMC		0xA702
 #define PCI_DEVICE_ID_INTEL_RPL_3_IMC		0xA706
 #define PCI_DEVICE_ID_INTEL_RPL_4_IMC		0xA709
+#define PCI_DEVICE_ID_INTEL_RPL_5_IMC		0xA701
+#define PCI_DEVICE_ID_INTEL_RPL_6_IMC		0xA703
+#define PCI_DEVICE_ID_INTEL_RPL_7_IMC		0xA704
+#define PCI_DEVICE_ID_INTEL_RPL_8_IMC		0xA705
+#define PCI_DEVICE_ID_INTEL_RPL_9_IMC		0xA706
+#define PCI_DEVICE_ID_INTEL_RPL_10_IMC		0xA707
+#define PCI_DEVICE_ID_INTEL_RPL_11_IMC		0xA708
+#define PCI_DEVICE_ID_INTEL_RPL_12_IMC		0xA709
+#define PCI_DEVICE_ID_INTEL_RPL_13_IMC		0xA70a
+#define PCI_DEVICE_ID_INTEL_RPL_14_IMC		0xA70b
+#define PCI_DEVICE_ID_INTEL_RPL_15_IMC		0xA715
+#define PCI_DEVICE_ID_INTEL_RPL_16_IMC		0xA716
+#define PCI_DEVICE_ID_INTEL_RPL_17_IMC		0xA717
+#define PCI_DEVICE_ID_INTEL_RPL_18_IMC		0xA718
+#define PCI_DEVICE_ID_INTEL_RPL_19_IMC		0xA719
+#define PCI_DEVICE_ID_INTEL_RPL_20_IMC		0xA71A
+#define PCI_DEVICE_ID_INTEL_RPL_21_IMC		0xA71B
+#define PCI_DEVICE_ID_INTEL_RPL_22_IMC		0xA71C
+#define PCI_DEVICE_ID_INTEL_RPL_23_IMC		0xA728
+#define PCI_DEVICE_ID_INTEL_RPL_24_IMC		0xA729
+#define PCI_DEVICE_ID_INTEL_RPL_25_IMC		0xA72A
+
+
+#define IMC_UNCORE_DEV(a)						\
+{									\
+	PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_##a##_IMC),	\
+	.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),	\
+}
 
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
@@ -849,242 +882,80 @@ static struct intel_uncore_type *snb_pci_uncores[] = {
 };
 
 static const struct pci_device_id snb_uncore_pci_ids[] = {
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
+	IMC_UNCORE_DEV(SNB),
 	{ /* end: all zeroes */ },
 };
 
 static const struct pci_device_id ivb_uncore_pci_ids[] = {
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_E3_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
+	IMC_UNCORE_DEV(IVB),
+	IMC_UNCORE_DEV(IVB_E3),
 	{ /* end: all zeroes */ },
 };
 
 static const struct pci_device_id hsw_uncore_pci_ids[] = {
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_U_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
+	IMC_UNCORE_DEV(HSW),
+	IMC_UNCORE_DEV(HSW_U),
 	{ /* end: all zeroes */ },
 };
 
 static const struct pci_device_id bdw_uncore_pci_ids[] = {
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
+	IMC_UNCORE_DEV(BDW),
 	{ /* end: all zeroes */ },
 };
 
 static const struct pci_device_id skl_uncore_pci_ids[] = {
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_Y_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_U_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HD_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HQ_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SD_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_E3_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_Y_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_U_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_UQ_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SD_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SQ_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_HQ_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_WQ_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2U_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4U_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4H_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6H_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_D_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_W_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_W_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_W_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_AML_YD_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_AML_YQ_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_UQ_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_4_UQ_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_UD_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_H1_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_H2_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_H3_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_U1_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_U2_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_U3_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S1_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S2_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S3_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S4_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S5_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
+	IMC_UNCORE_DEV(SKL_Y),
+	IMC_UNCORE_DEV(SKL_U),
+	IMC_UNCORE_DEV(SKL_HD),
+	IMC_UNCORE_DEV(SKL_HQ),
+	IMC_UNCORE_DEV(SKL_SD),
+	IMC_UNCORE_DEV(SKL_SQ),
+	IMC_UNCORE_DEV(SKL_E3),
+	IMC_UNCORE_DEV(KBL_Y),
+	IMC_UNCORE_DEV(KBL_U),
+	IMC_UNCORE_DEV(KBL_UQ),
+	IMC_UNCORE_DEV(KBL_SD),
+	IMC_UNCORE_DEV(KBL_SQ),
+	IMC_UNCORE_DEV(KBL_HQ),
+	IMC_UNCORE_DEV(KBL_WQ),
+	IMC_UNCORE_DEV(CFL_2U),
+	IMC_UNCORE_DEV(CFL_4U),
+	IMC_UNCORE_DEV(CFL_4H),
+	IMC_UNCORE_DEV(CFL_6H),
+	IMC_UNCORE_DEV(CFL_2S_D),
+	IMC_UNCORE_DEV(CFL_4S_D),
+	IMC_UNCORE_DEV(CFL_6S_D),
+	IMC_UNCORE_DEV(CFL_8S_D),
+	IMC_UNCORE_DEV(CFL_4S_W),
+	IMC_UNCORE_DEV(CFL_6S_W),
+	IMC_UNCORE_DEV(CFL_8S_W),
+	IMC_UNCORE_DEV(CFL_4S_S),
+	IMC_UNCORE_DEV(CFL_6S_S),
+	IMC_UNCORE_DEV(CFL_8S_S),
+	IMC_UNCORE_DEV(AML_YD),
+	IMC_UNCORE_DEV(AML_YQ),
+	IMC_UNCORE_DEV(WHL_UQ),
+	IMC_UNCORE_DEV(WHL_4_UQ),
+	IMC_UNCORE_DEV(WHL_UD),
+	IMC_UNCORE_DEV(CML_H1),
+	IMC_UNCORE_DEV(CML_H2),
+	IMC_UNCORE_DEV(CML_H3),
+	IMC_UNCORE_DEV(CML_U1),
+	IMC_UNCORE_DEV(CML_U2),
+	IMC_UNCORE_DEV(CML_U3),
+	IMC_UNCORE_DEV(CML_S1),
+	IMC_UNCORE_DEV(CML_S2),
+	IMC_UNCORE_DEV(CML_S3),
+	IMC_UNCORE_DEV(CML_S4),
+	IMC_UNCORE_DEV(CML_S5),
 	{ /* end: all zeroes */ },
 };
 
 static const struct pci_device_id icl_uncore_pci_ids[] = {
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U2_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RKL_1_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RKL_2_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
+	IMC_UNCORE_DEV(ICL_U),
+	IMC_UNCORE_DEV(ICL_U2),
+	IMC_UNCORE_DEV(RKL_1),
+	IMC_UNCORE_DEV(RKL_2),
 	{ /* end: all zeroes */ },
 };
 
@@ -1326,106 +1197,57 @@ void nhm_uncore_cpu_init(void)
 /* Tiger Lake MMIO uncore support */
 
 static const struct pci_device_id tgl_uncore_pci_ids[] = {
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U1_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U2_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U3_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U4_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_H_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_1_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_2_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_3_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_4_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_5_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_6_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_7_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_8_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_9_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_10_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_11_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_12_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_13_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_14_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_15_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_16_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_1_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_2_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_3_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_4_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
+	IMC_UNCORE_DEV(TGL_U1),
+	IMC_UNCORE_DEV(TGL_U2),
+	IMC_UNCORE_DEV(TGL_U3),
+	IMC_UNCORE_DEV(TGL_U4),
+	IMC_UNCORE_DEV(TGL_H),
+	IMC_UNCORE_DEV(ADL_1),
+	IMC_UNCORE_DEV(ADL_2),
+	IMC_UNCORE_DEV(ADL_3),
+	IMC_UNCORE_DEV(ADL_4),
+	IMC_UNCORE_DEV(ADL_5),
+	IMC_UNCORE_DEV(ADL_6),
+	IMC_UNCORE_DEV(ADL_7),
+	IMC_UNCORE_DEV(ADL_8),
+	IMC_UNCORE_DEV(ADL_9),
+	IMC_UNCORE_DEV(ADL_10),
+	IMC_UNCORE_DEV(ADL_11),
+	IMC_UNCORE_DEV(ADL_12),
+	IMC_UNCORE_DEV(ADL_13),
+	IMC_UNCORE_DEV(ADL_14),
+	IMC_UNCORE_DEV(ADL_15),
+	IMC_UNCORE_DEV(ADL_16),
+	IMC_UNCORE_DEV(ADL_17),
+	IMC_UNCORE_DEV(ADL_18),
+	IMC_UNCORE_DEV(ADL_19),
+	IMC_UNCORE_DEV(ADL_20),
+	IMC_UNCORE_DEV(ADL_21),
+	IMC_UNCORE_DEV(RPL_1),
+	IMC_UNCORE_DEV(RPL_2),
+	IMC_UNCORE_DEV(RPL_3),
+	IMC_UNCORE_DEV(RPL_4),
+	IMC_UNCORE_DEV(RPL_5),
+	IMC_UNCORE_DEV(RPL_6),
+	IMC_UNCORE_DEV(RPL_7),
+	IMC_UNCORE_DEV(RPL_8),
+	IMC_UNCORE_DEV(RPL_9),
+	IMC_UNCORE_DEV(RPL_10),
+	IMC_UNCORE_DEV(RPL_11),
+	IMC_UNCORE_DEV(RPL_12),
+	IMC_UNCORE_DEV(RPL_13),
+	IMC_UNCORE_DEV(RPL_14),
+	IMC_UNCORE_DEV(RPL_15),
+	IMC_UNCORE_DEV(RPL_16),
+	IMC_UNCORE_DEV(RPL_17),
+	IMC_UNCORE_DEV(RPL_18),
+	IMC_UNCORE_DEV(RPL_19),
+	IMC_UNCORE_DEV(RPL_20),
+	IMC_UNCORE_DEV(RPL_21),
+	IMC_UNCORE_DEV(RPL_22),
+	IMC_UNCORE_DEV(RPL_23),
+	IMC_UNCORE_DEV(RPL_24),
+	IMC_UNCORE_DEV(RPL_25),
 	{ /* end: all zeroes */ }
 };
 
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 6d759f88315c6b..ac542f98c0705e 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -103,7 +103,9 @@ static bool test_intel(int idx, void *data)
 	case INTEL_FAM6_ROCKETLAKE:
 	case INTEL_FAM6_ALDERLAKE:
 	case INTEL_FAM6_ALDERLAKE_L:
+	case INTEL_FAM6_ALDERLAKE_N:
 	case INTEL_FAM6_RAPTORLAKE:
+	case INTEL_FAM6_RAPTORLAKE_P:
 		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
 			return true;
 		break;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 150261d929b9e9..21a5482bcf8458 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -67,22 +67,23 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode)
 /*
  * struct hw_perf_event.flags flags
  */
-#define PERF_X86_EVENT_PEBS_LDLAT	0x0001 /* ld+ldlat data address sampling */
-#define PERF_X86_EVENT_PEBS_ST		0x0002 /* st data address sampling */
-#define PERF_X86_EVENT_PEBS_ST_HSW	0x0004 /* haswell style datala, store */
-#define PERF_X86_EVENT_PEBS_LD_HSW	0x0008 /* haswell style datala, load */
-#define PERF_X86_EVENT_PEBS_NA_HSW	0x0010 /* haswell style datala, unknown */
-#define PERF_X86_EVENT_EXCL		0x0020 /* HT exclusivity on counter */
-#define PERF_X86_EVENT_DYNAMIC		0x0040 /* dynamic alloc'd constraint */
-
-#define PERF_X86_EVENT_EXCL_ACCT	0x0100 /* accounted EXCL event */
-#define PERF_X86_EVENT_AUTO_RELOAD	0x0200 /* use PEBS auto-reload */
-#define PERF_X86_EVENT_LARGE_PEBS	0x0400 /* use large PEBS */
-#define PERF_X86_EVENT_PEBS_VIA_PT	0x0800 /* use PT buffer for PEBS */
-#define PERF_X86_EVENT_PAIR		0x1000 /* Large Increment per Cycle */
-#define PERF_X86_EVENT_LBR_SELECT	0x2000 /* Save/Restore MSR_LBR_SELECT */
-#define PERF_X86_EVENT_TOPDOWN		0x4000 /* Count Topdown slots/metrics events */
-#define PERF_X86_EVENT_PEBS_STLAT	0x8000 /* st+stlat data address sampling */
+#define PERF_X86_EVENT_PEBS_LDLAT	0x00001 /* ld+ldlat data address sampling */
+#define PERF_X86_EVENT_PEBS_ST		0x00002 /* st data address sampling */
+#define PERF_X86_EVENT_PEBS_ST_HSW	0x00004 /* haswell style datala, store */
+#define PERF_X86_EVENT_PEBS_LD_HSW	0x00008 /* haswell style datala, load */
+#define PERF_X86_EVENT_PEBS_NA_HSW	0x00010 /* haswell style datala, unknown */
+#define PERF_X86_EVENT_EXCL		0x00020 /* HT exclusivity on counter */
+#define PERF_X86_EVENT_DYNAMIC		0x00040 /* dynamic alloc'd constraint */
+
+#define PERF_X86_EVENT_EXCL_ACCT	0x00100 /* accounted EXCL event */
+#define PERF_X86_EVENT_AUTO_RELOAD	0x00200 /* use PEBS auto-reload */
+#define PERF_X86_EVENT_LARGE_PEBS	0x00400 /* use large PEBS */
+#define PERF_X86_EVENT_PEBS_VIA_PT	0x00800 /* use PT buffer for PEBS */
+#define PERF_X86_EVENT_PAIR		0x01000 /* Large Increment per Cycle */
+#define PERF_X86_EVENT_LBR_SELECT	0x02000 /* Save/Restore MSR_LBR_SELECT */
+#define PERF_X86_EVENT_TOPDOWN		0x04000 /* Count Topdown slots/metrics events */
+#define PERF_X86_EVENT_PEBS_STLAT	0x08000 /* st+stlat data address sampling */
+#define PERF_X86_EVENT_AMD_BRS		0x10000 /* AMD Branch Sampling */
 
 static inline bool is_topdown_count(struct perf_event *event)
 {
@@ -325,6 +326,8 @@ struct cpu_hw_events {
 	 * AMD specific bits
 	 */
 	struct amd_nb			*amd_nb;
+	int				brs_active; /* BRS is enabled */
+
 	/* Inverted mask of bits to clear in the perf_ctr ctrl registers */
 	u64				perf_ctr_virt_mask;
 	int				n_pair; /* Large increment events */
@@ -1105,6 +1108,11 @@ int x86_pmu_hw_config(struct perf_event *event);
 
 void x86_pmu_disable_all(void);
 
+static inline bool has_amd_brs(struct hw_perf_event *hwc)
+{
+	return hwc->flags & PERF_X86_EVENT_AMD_BRS;
+}
+
 static inline bool is_counter_pair(struct hw_perf_event *hwc)
 {
 	return hwc->flags & PERF_X86_EVENT_PAIR;
@@ -1211,6 +1219,75 @@ static inline bool fixed_counter_disabled(int i, struct pmu *pmu)
 
 int amd_pmu_init(void);
 
+#ifdef CONFIG_PERF_EVENTS_AMD_BRS
+int amd_brs_init(void);
+void amd_brs_disable(void);
+void amd_brs_enable(void);
+void amd_brs_enable_all(void);
+void amd_brs_disable_all(void);
+void amd_brs_drain(void);
+void amd_brs_lopwr_init(void);
+void amd_brs_disable_all(void);
+int amd_brs_setup_filter(struct perf_event *event);
+void amd_brs_reset(void);
+
+static inline void amd_pmu_brs_add(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	perf_sched_cb_inc(event->ctx->pmu);
+	cpuc->lbr_users++;
+	/*
+	 * No need to reset BRS because it is reset
+	 * on brs_enable() and it is saturating
+	 */
+}
+
+static inline void amd_pmu_brs_del(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	cpuc->lbr_users--;
+	WARN_ON_ONCE(cpuc->lbr_users < 0);
+
+	perf_sched_cb_dec(event->ctx->pmu);
+}
+
+void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in);
+#else
+static inline int amd_brs_init(void)
+{
+	return 0;
+}
+static inline void amd_brs_disable(void) {}
+static inline void amd_brs_enable(void) {}
+static inline void amd_brs_drain(void) {}
+static inline void amd_brs_lopwr_init(void) {}
+static inline void amd_brs_disable_all(void) {}
+static inline int amd_brs_setup_filter(struct perf_event *event)
+{
+	return 0;
+}
+static inline void amd_brs_reset(void) {}
+
+static inline void amd_pmu_brs_add(struct perf_event *event)
+{
+}
+
+static inline void amd_pmu_brs_del(struct perf_event *event)
+{
+}
+
+static inline void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in)
+{
+}
+
+static inline void amd_brs_enable_all(void)
+{
+}
+
+#endif
+
 #else /* CONFIG_CPU_SUP_AMD */
 
 static inline int amd_pmu_init(void)
@@ -1218,6 +1295,22 @@ static inline int amd_pmu_init(void)
 	return 0;
 }
 
+static inline int amd_brs_init(void)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void amd_brs_drain(void)
+{
+}
+
+static inline void amd_brs_enable_all(void)
+{
+}
+
+static inline void amd_brs_disable_all(void)
+{
+}
 #endif /* CONFIG_CPU_SUP_AMD */
 
 static inline int is_pebs_pt(struct perf_event *event)
diff --git a/arch/x86/include/asm/amd-ibs.h b/arch/x86/include/asm/amd-ibs.h
index 46e1df45efc046..aabdbb5ab92008 100644
--- a/arch/x86/include/asm/amd-ibs.h
+++ b/arch/x86/include/asm/amd-ibs.h
@@ -49,7 +49,7 @@ union ibs_op_ctl {
 	};
 };
 
-/* MSR 0xc0011035: IBS Op Data 2 */
+/* MSR 0xc0011035: IBS Op Data 1 */
 union ibs_op_data {
 	__u64 val;
 	struct {
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 6e0dbbf847f33e..21bb78dfd41d40 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -211,7 +211,7 @@
 #define X86_FEATURE_SSBD		( 7*32+17) /* Speculative Store Bypass Disable */
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* "" Fill RSB on context switches */
-/* FREE!                                ( 7*32+20) */
+#define X86_FEATURE_PERFMON_V2		( 7*32+20) /* AMD Performance Monitoring Version 2 */
 #define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
 #define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* "" Use IBRS during runtime firmware calls */
 #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* "" Disable Speculative Store Bypass. */
@@ -316,6 +316,7 @@
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 #define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
 #define X86_FEATURE_CPPC		(13*32+27) /* Collaborative Processor Performance Control */
+#define X86_FEATURE_BRS			(13*32+31) /* Branch Sampling available */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index a51208d10df4dc..14154b8b1720a3 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -533,6 +533,11 @@
 #define AMD_CPPC_DES_PERF(x)		(((x) & 0xff) << 16)
 #define AMD_CPPC_ENERGY_PERF_PREF(x)	(((x) & 0xff) << 24)
 
+/* AMD Performance Counter Global Status and Control MSRs */
+#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS	0xc0000300
+#define MSR_AMD64_PERF_CNTR_GLOBAL_CTL		0xc0000301
+#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR	0xc0000302
+
 /* Fam 17h MSRs */
 #define MSR_F17H_IRPERF			0xc00000e9
 
@@ -697,6 +702,10 @@
 #define MSR_IA32_PERF_CTL		0x00000199
 #define INTEL_PERF_CTL_MASK		0xffff
 
+/* AMD Branch Sampling configuration */
+#define MSR_AMD_DBG_EXTN_CFG		0xc000010f
+#define MSR_AMD_SAMP_BR_FROM		0xc0010300
+
 #define MSR_IA32_MPERF			0x000000e7
 #define MSR_IA32_APERF			0x000000e8
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index b06e4c573addda..409725e86f42c4 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_PERF_EVENT_H
 #define _ASM_X86_PERF_EVENT_H
 
+#include <linux/static_call.h>
+
 /*
  * Performance event hw details:
  */
@@ -184,6 +186,18 @@ union cpuid28_ecx {
 	unsigned int            full;
 };
 
+/*
+ * AMD "Extended Performance Monitoring and Debug" CPUID
+ * detection/enumeration details:
+ */
+union cpuid_0x80000022_ebx {
+	struct {
+		/* Number of Core Performance Counters */
+		unsigned int	num_core_pmc:4;
+	} split;
+	unsigned int		full;
+};
+
 struct x86_pmu_capability {
 	int		version;
 	int		num_counters_gp;
@@ -370,6 +384,11 @@ struct pebs_xmm {
 	u64 xmm[16*2];	/* two entries for each register */
 };
 
+/*
+ * AMD Extended Performance Monitoring and Debug cpuid feature detection
+ */
+#define EXT_PERFMON_DEBUG_FEATURES		0x80000022
+
 /*
  * IBS cpuid feature detection
  */
@@ -391,6 +410,7 @@ struct pebs_xmm {
 #define IBS_CAPS_OPBRNFUSE		(1U<<8)
 #define IBS_CAPS_FETCHCTLEXTD		(1U<<9)
 #define IBS_CAPS_OPDATA4		(1U<<10)
+#define IBS_CAPS_ZEN4			(1U<<11)
 
 #define IBS_CAPS_DEFAULT		(IBS_CAPS_AVAIL		\
 					 | IBS_CAPS_FETCHSAM	\
@@ -404,6 +424,7 @@ struct pebs_xmm {
 #define IBSCTL_LVT_OFFSET_MASK		0x0F
 
 /* IBS fetch bits/masks */
+#define IBS_FETCH_L3MISSONLY	(1ULL<<59)
 #define IBS_FETCH_RAND_EN	(1ULL<<57)
 #define IBS_FETCH_VAL		(1ULL<<49)
 #define IBS_FETCH_ENABLE	(1ULL<<48)
@@ -420,6 +441,7 @@ struct pebs_xmm {
 #define IBS_OP_CNT_CTL		(1ULL<<19)
 #define IBS_OP_VAL		(1ULL<<18)
 #define IBS_OP_ENABLE		(1ULL<<17)
+#define IBS_OP_L3MISSONLY	(1ULL<<16)
 #define IBS_OP_MAX_CNT		0x0000FFFFULL
 #define IBS_OP_MAX_CNT_EXT	0x007FFFFFULL	/* not a register bit mask */
 #define IBS_OP_MAX_CNT_EXT_MASK	(0x7FULL<<20)	/* separate upper 7 bits */
@@ -518,6 +540,27 @@ static inline void intel_pt_handle_vmx(int on)
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
  extern void amd_pmu_enable_virt(void);
  extern void amd_pmu_disable_virt(void);
+
+#if defined(CONFIG_PERF_EVENTS_AMD_BRS)
+
+#define PERF_NEEDS_LOPWR_CB 1
+
+/*
+ * architectural low power callback impacts
+ * drivers/acpi/processor_idle.c
+ * drivers/acpi/acpi_pad.c
+ */
+extern void perf_amd_brs_lopwr_cb(bool lopwr_in);
+
+DECLARE_STATIC_CALL(perf_lopwr_cb, perf_amd_brs_lopwr_cb);
+
+static inline void perf_lopwr_cb(bool lopwr_in)
+{
+	static_call_mod(perf_lopwr_cb)(lopwr_in);
+}
+
+#endif /* PERF_NEEDS_LOPWR_CB */
+
 #else
  static inline void amd_pmu_enable_virt(void) { }
  static inline void amd_pmu_disable_virt(void) { }
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 4143b1e4c5c6d8..dbaa8326d6f289 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -43,6 +43,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
 	{ X86_FEATURE_PROC_FEEDBACK,    CPUID_EDX, 11, 0x80000007, 0 },
 	{ X86_FEATURE_MBA,		CPUID_EBX,  6, 0x80000008, 0 },
+	{ X86_FEATURE_PERFMON_V2,	CPUID_EAX,  0, 0x80000022, 0 },
 	{ 0, 0, 0, 0, 0 }
 };
 
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index b52407c56000e1..879ef8c72f5c0f 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -149,8 +149,10 @@ static inline void signal_compat_build_tests(void)
 
 	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x18);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x20);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_flags) != 0x24);
 	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_data) != 0x10);
 	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_type) != 0x14);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_flags) != 0x18);
 
 	CHECK_CSI_OFFSET(_sigpoll);
 	CHECK_CSI_SIZE  (_sigpoll, 2*sizeof(int));
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index f45979aa2d648d..ec0e22a1e25d64 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -17,6 +17,7 @@
 #include <linux/tick.h>
 #include <linux/slab.h>
 #include <linux/acpi.h>
+#include <linux/perf_event.h>
 #include <asm/mwait.h>
 #include <xen/xen.h>
 
@@ -164,6 +165,9 @@ static int power_saving_thread(void *data)
 				tsc_marked_unstable = 1;
 			}
 			local_irq_disable();
+
+			perf_lopwr_cb(true);
+
 			tick_broadcast_enable();
 			tick_broadcast_enter();
 			stop_critical_timings();
@@ -172,6 +176,9 @@ static int power_saving_thread(void *data)
 
 			start_critical_timings();
 			tick_broadcast_exit();
+
+			perf_lopwr_cb(false);
+
 			local_irq_enable();
 
 			if (time_before(expire_time, jiffies)) {
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index eb95e188d62bc2..e9c84d0ac55bd8 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -21,6 +21,7 @@
 #include <linux/cpuidle.h>
 #include <linux/cpu.h>
 #include <linux/minmax.h>
+#include <linux/perf_event.h>
 #include <acpi/processor.h>
 
 /*
@@ -544,6 +545,8 @@ static void wait_for_freeze(void)
  */
 static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx)
 {
+	perf_lopwr_cb(true);
+
 	if (cx->entry_method == ACPI_CSTATE_FFH) {
 		/* Call into architectural FFH based C-state */
 		acpi_processor_ffh_cstate_enter(cx);
@@ -554,6 +557,8 @@ static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx)
 		inb(cx->address);
 		wait_for_freeze();
 	}
+
+	perf_lopwr_cb(false);
 }
 
 /**
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 1c758b0e03598f..01fddf72a81f08 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -235,6 +235,7 @@ typedef struct compat_siginfo {
 				struct {
 					compat_ulong_t _data;
 					u32 _type;
+					u32 _flags;
 				} _perf;
 			};
 		} _sigfault;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index af97dd427501cb..da759560eec564 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1063,6 +1063,22 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->txn = 0;
 }
 
+/*
+ * Clear all bitfields in the perf_branch_entry.
+ * The to and from fields are not cleared because they are
+ * systematically modified by caller.
+ */
+static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br)
+{
+	br->mispred = 0;
+	br->predicted = 0;
+	br->in_tx = 0;
+	br->abort = 0;
+	br->cycles = 0;
+	br->type = 0;
+	br->reserved = 0;
+}
+
 extern void perf_output_sample(struct perf_output_handle *handle,
 			       struct perf_event_header *header,
 			       struct perf_sample_data *data,
@@ -1660,4 +1676,10 @@ typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries,
 					   unsigned int cnt);
 DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t);
 
+#ifndef PERF_NEEDS_LOPWR_CB
+static inline void perf_lopwr_cb(bool mode)
+{
+}
+#endif
+
 #endif /* _LINUX_PERF_EVENT_H */
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 66b689f6cfcb01..20ed5ba2bde436 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -320,7 +320,7 @@ int send_sig_mceerr(int code, void __user *, short, struct task_struct *);
 
 int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper);
 int force_sig_pkuerr(void __user *addr, u32 pkey);
-int force_sig_perf(void __user *addr, u32 type, u64 sig_data);
+int send_sig_perf(void __user *addr, u32 type, u64 sig_data);
 
 int force_sig_ptrace_errno_trap(int errno, void __user *addr);
 int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno);
diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index 3ba180f550d7cf..ffbe4cec9f32de 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -99,6 +99,7 @@ union __sifields {
 			struct {
 				unsigned long _data;
 				__u32 _type;
+				__u32 _flags;
 			} _perf;
 		};
 	} _sigfault;
@@ -164,6 +165,7 @@ typedef struct siginfo {
 #define si_pkey		_sifields._sigfault._addr_pkey._pkey
 #define si_perf_data	_sifields._sigfault._perf._data
 #define si_perf_type	_sifields._sigfault._perf._type
+#define si_perf_flags	_sifields._sigfault._perf._flags
 #define si_band		_sifields._sigpoll._band
 #define si_fd		_sifields._sigpoll._fd
 #define si_call_addr	_sifields._sigsys._call_addr
@@ -270,6 +272,11 @@ typedef struct siginfo {
  * that are of the form: ((PTRACE_EVENT_XXX << 8) | SIGTRAP)
  */
 
+/*
+ * Flags for si_perf_flags if SIGTRAP si_code is TRAP_PERF.
+ */
+#define TRAP_PERF_FLAG_ASYNC (1u << 0)
+
 /*
  * SIGCHLD si_codes
  */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7f1e4c5897e755..950b25c3f21035 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6428,8 +6428,8 @@ static void perf_sigtrap(struct perf_event *event)
 	if (current->flags & PF_EXITING)
 		return;
 
-	force_sig_perf((void __user *)event->pending_addr,
-		       event->attr.type, event->attr.sig_data);
+	send_sig_perf((void __user *)event->pending_addr,
+		      event->attr.type, event->attr.sig_data);
 }
 
 static void perf_pending_event_disable(struct perf_event *event)
diff --git a/kernel/signal.c b/kernel/signal.c
index 30cd1ca43bcd5b..e43bc2a692f5e3 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1805,7 +1805,7 @@ int force_sig_pkuerr(void __user *addr, u32 pkey)
 }
 #endif
 
-int force_sig_perf(void __user *addr, u32 type, u64 sig_data)
+int send_sig_perf(void __user *addr, u32 type, u64 sig_data)
 {
 	struct kernel_siginfo info;
 
@@ -1817,7 +1817,18 @@ int force_sig_perf(void __user *addr, u32 type, u64 sig_data)
 	info.si_perf_data = sig_data;
 	info.si_perf_type = type;
 
-	return force_sig_info(&info);
+	/*
+	 * Signals generated by perf events should not terminate the whole
+	 * process if SIGTRAP is blocked, however, delivering the signal
+	 * asynchronously is better than not delivering at all. But tell user
+	 * space if the signal was asynchronous, so it can clearly be
+	 * distinguished from normal synchronous ones.
+	 */
+	info.si_perf_flags = sigismember(&current->blocked, info.si_signo) ?
+				     TRAP_PERF_FLAG_ASYNC :
+				     0;
+
+	return send_sig_info(info.si_signo, &info, current);
 }
 
 /**
@@ -3432,6 +3443,7 @@ void copy_siginfo_to_external32(struct compat_siginfo *to,
 		to->si_addr = ptr_to_compat(from->si_addr);
 		to->si_perf_data = from->si_perf_data;
 		to->si_perf_type = from->si_perf_type;
+		to->si_perf_flags = from->si_perf_flags;
 		break;
 	case SIL_CHLD:
 		to->si_pid = from->si_pid;
@@ -3509,6 +3521,7 @@ static int post_copy_siginfo_from_user32(kernel_siginfo_t *to,
 		to->si_addr = compat_ptr(from->si_addr);
 		to->si_perf_data = from->si_perf_data;
 		to->si_perf_type = from->si_perf_type;
+		to->si_perf_flags = from->si_perf_flags;
 		break;
 	case SIL_CHLD:
 		to->si_pid    = from->si_pid;
@@ -4722,6 +4735,7 @@ static inline void siginfo_buildtime_checks(void)
 	CHECK_OFFSET(si_pkey);
 	CHECK_OFFSET(si_perf_data);
 	CHECK_OFFSET(si_perf_type);
+	CHECK_OFFSET(si_perf_flags);
 
 	/* sigpoll */
 	CHECK_OFFSET(si_band);
diff --git a/tools/arch/x86/include/asm/amd-ibs.h b/tools/arch/x86/include/asm/amd-ibs.h
index 174e7d83fcbdb2..765e9e752d038e 100644
--- a/tools/arch/x86/include/asm/amd-ibs.h
+++ b/tools/arch/x86/include/asm/amd-ibs.h
@@ -49,7 +49,7 @@ union ibs_op_ctl {
 	};
 };
 
-/* MSR 0xc0011035: IBS Op Data 2 */
+/* MSR 0xc0011035: IBS Op Data 1 */
 union ibs_op_data {
 	__u64 val;
 	struct {