Merge tag 'perf-core-2022-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf events updates from Ingo Molnar:
 "Platform PMU changes:

   - x86/intel:
      - Add new Intel Alder Lake and Raptor Lake support

   - x86/amd:
      - AMD Zen4 IBS extensions support
      - Add AMD PerfMonV2 support
      - Add AMD Fam19h Branch Sampling support

  Generic changes:

   - signal: Deliver SIGTRAP on perf event asynchronously if blocked

     Perf instrumentation can be driven via SIGTRAP, but this causes a
     problem when SIGTRAP is blocked by a task & terminate the task.

     Allow user-space to request these signals asynchronously (after
     they get unblocked) & also give the information to the signal
     handler when this happens:

       "To give user space the ability to clearly distinguish
        synchronous from asynchronous signals, introduce
        siginfo_t::si_perf_flags and TRAP_PERF_FLAG_ASYNC (opted for
        flags in case more binary information is required in future).

        The resolution to the problem is then to (a) no longer force the
        signal (avoiding the terminations), but (b) tell user space via
        si_perf_flags if the signal was synchronous or not, so that such
        signals can be handled differently (e.g. let user space decide
        to ignore or consider the data imprecise). "

   - Unify/standardize the /sys/devices/cpu/events/* output format.

   - Misc fixes & cleanups"

* tag 'perf-core-2022-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
  perf/x86/amd/core: Fix reloading events for SVM
  perf/x86/amd: Run AMD BRS code only on supported hw
  perf/x86/amd: Fix AMD BRS period adjustment
  perf/x86/amd: Remove unused variable 'hwc'
  perf/ibs: Fix comment
  perf/amd/ibs: Advertise zen4_ibs_extensions as pmu capability attribute
  perf/amd/ibs: Add support for L3 miss filtering
  perf/amd/ibs: Use ->is_visible callback for dynamic attributes
  perf/amd/ibs: Cascade pmu init functions' return value
  perf/x86/uncore: Add new Alder Lake and Raptor Lake support
  perf/x86/uncore: Clean up uncore_pci_ids[]
  perf/x86/cstate: Add new Alder Lake and Raptor Lake support
  perf/x86/msr: Add new Alder Lake and Raptor Lake support
  perf/x86: Add new Alder Lake and Raptor Lake support
  perf/amd/ibs: Use interrupt regs ip for stack unwinding
  perf/x86/amd/core: Add PerfMonV2 overflow handling
  perf/x86/amd/core: Add PerfMonV2 counter control
  perf/x86/amd/core: Detect available counters
  perf/x86/amd/core: Detect PerfMonV2 support
  x86/msr: Add PerfCntrGlobal* registers
  ...

34 files changed, 1445 insertions, 414 deletions

diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 459abc5d1819..ea128e32e8ca 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 18bf590dc1c7..edb2d9206a78 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 d984282b979f..4700f8522d27 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 49533f65958a..b9f6908a31bc 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 f9fe502b81c6..dad38960d1a8 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 8b9fc76cd3e0..570e43e6fda5 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 d6cdfe631674..09c56965750a 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 6cbe38d5fd9d..b9f5d4610256 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 000000000000..bee8765a1e9b
--- /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 9687a8aef01c..9ac3718410ce 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)