!119 Add new perf monitor features for amd epyc platforms

Merge Pull Request from: @haochengxie 
 
Add new perf features, backporting these patches from mainline:
1.Performance Monitor Global Controls
2.IBS（Instrument Based Sample）extensions
3.BRS(Branch Sample)

Patches been relied:
69372cf0   5.11   x86/cpu: Add VM page flush MSR availablility as a CPUID feature
fb35d30f   5.12   x86/cpufeatures: Assign dedicated feature word for CPUID_0x8000001F[EAX]

Perf BRS:
bfe4daf8   5.19   perf/core: Add perf_clear_branch_entry_bitfields() helper
a77d41ac   5.19   x86/cpufeatures: Add AMD Fam19h Branch Sampling feature
ada54345   5.19   perf/x86/amd: Add AMD Fam19h Branch Sampling support
44175993   5.19   perf/x86/amd: Add branch-brs helper event for Fam19h BRS
8910075d   5.19   perf/x86/amd: Enable branch sampling priv level filtering
ba2fe750   5.19   perf/x86/amd: Add AMD branch sampling period adjustment
cc37e520   5.19   perf/x86/amd: Make Zen3 branch sampling opt-in
2a606a18   5.19   ACPI: Add perf low power callback
d5616bac   5.19   perf/x86/amd: Add idle hooks for branch sampling

PerfmonV2 controls:
d6d0c7f6
089be16d
21d59e3e
56e026a7   5.19-rc1    PerfmonV2 Controls for Core PMU series
9622e67e
7685665c
bae19fdd  

Perf IBS:
6a371baf   5.15       perf/x86/amd/ibs: Add bitfield definitions in new <asm/amd-ibs.h> header
3d47083b   5.19       perf/amd/ibs: Use interrupt regs ip for stack unwinding
39b2ca75   5.19       perf/amd/ibs: Cascade pmu init functions' return value
2a7a7e65   5.19       perf/amd/ibs: Use ->is_visible callback for dynamic attributes
ba5d35b4   5.19-rc1   perf/amd/ibs: Add support for L3 miss filtering
838de1d8   5.19-rc1   perf/amd/ibs: Advertise zen4_ibs_extensions as pmu capability attribute
 
 
Link:https://gitee.com/openeuler/kernel/pulls/119 
Reviewed-by: Zheng Zengkai <zhengzengkai@huawei.com> 
Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com> 

arch/x86/events/Kconfig

@@ -34,4 +34,11 @@ config PERF_EVENTS_AMD_POWER
 	  (CPUID Fn8000_0007_EDX[12]) interface to calculate the
 	  average power consumption on Family 15h processors.
 
+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

arch/x86/events/amd/Makefile

 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_CPU_SUP_AMD)		+= core.o uncore.o
+obj-$(CONFIG_PERF_EVENTS_AMD_BRS)	+= brs.o
 obj-$(CONFIG_PERF_EVENTS_AMD_POWER)	+= power.o
 obj-$(CONFIG_X86_LOCAL_APIC)		+= ibs.o
 ifdef CONFIG_AMD_IOMMU

arch/x86/events/amd/brs.c

+// 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 (!boot_cpu_has(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)
+{
+	/*
+	 * 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);
+}

arch/x86/events/amd/core.c

 // 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 +763,50 @@ 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);
+	struct hw_perf_event *hwc;
+	int idx;
+
+	amd_brs_enable_all();
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		hwc = &cpuc->events[idx]->hw;
+
+		/* 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 +824,32 @@ 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 +868,8 @@ 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 +886,113 @@ 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 +1198,51 @@ 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 +1251,19 @@ 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 __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 +1273,8 @@ 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 +1293,55 @@ 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 +1359,27 @@ 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 +1412,22 @@ 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;
+		/*
+		 * 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 +1462,24 @@ __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 +1487,7 @@ 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 +1504,6 @@ 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);

arch/x86/events/amd/ibs.c

@@ -26,6 +26,7 @@ static u32 ibs_caps;
 #include <linux/hardirq.h>
 
 #include <asm/nmi.h>
+#include <asm/amd-ibs.h>
 
 #define IBS_FETCH_CONFIG_MASK	(IBS_FETCH_RAND_EN | IBS_FETCH_MAX_CNT)
 #define IBS_OP_CONFIG_MASK	IBS_OP_MAX_CNT
@@ -93,22 +94,9 @@ 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);
 };
 
-struct perf_ibs_data {
-	u32		size;
-	union {
-		u32	data[0];	/* data buffer starts here */
-		u32	caps;
-	};
-	u64		regs[MSR_AMD64_IBS_REG_COUNT_MAX];
-};
-
 static int
 perf_event_set_period(struct hw_perf_event *hwc, u64 min, u64 max, u64 *hw_period)
 {
@@ -312,6 +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;
 }
 
@@ -329,11 +327,14 @@ static int perf_ibs_set_period(struct perf_ibs *perf_ibs,
 
 static u64 get_ibs_fetch_count(u64 config)
 {
-	return (config & IBS_FETCH_CNT) >> 12;
+	union ibs_fetch_ctl fetch_ctl = (union ibs_fetch_ctl)config;
+
+	return fetch_ctl.fetch_cnt << 4;
 }
 
 static u64 get_ibs_op_count(u64 config)
 {
+	union ibs_op_ctl op_ctl = (union ibs_op_ctl)config;
 	u64 count = 0;
 
 	/*
@@ -341,12 +342,12 @@ static u64 get_ibs_op_count(u64 config)
 	 * and the lower 7 bits of CurCnt are randomized.
 	 * Otherwise CurCnt has the full 27-bit current counter value.
 	 */
-	if (config & IBS_OP_VAL) {
-		count = (config & IBS_OP_MAX_CNT) << 4;
+	if (op_ctl.op_val) {
+		count = op_ctl.opmaxcnt << 4;
 		if (ibs_caps & IBS_CAPS_OPCNTEXT)
-			count += config & IBS_OP_MAX_CNT_EXT_MASK;
+			count += op_ctl.opmaxcnt_ext << 20;
 	} else if (ibs_caps & IBS_CAPS_RDWROPCNT) {
-		count = (config & IBS_OP_CUR_CNT) >> 32;
+		count = op_ctl.opcurcnt;
 	}
 
 	return count;
@@ -523,16 +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 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 *ibs_fetch_format_attrs[] = {
+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,
 };
 
@@ -556,7 +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,
 };
@@ -582,7 +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,
 };
@@ -692,6 +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) {
@@ -744,17 +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;
@@ -764,10 +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.
@@ -778,12 +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;
 
-	if (ibs_caps & IBS_CAPS_OPCNT) {
+	perf_ibs_fetch.pmu.attr_groups = fetch_attr_groups;
+	perf_ibs_fetch.pmu.attr_update = fetch_attr_update;
+
+	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;
@@ -791,15 +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
 
@@ -1069,9 +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: */

arch/x86/events/core.c

@@ -1296,6 +1296,10 @@ 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;
@@ -1328,6 +1332,13 @@ int x86_perf_event_set_period(struct perf_event *event)
 	    x86_pmu.set_topdown_event_period)
 		return x86_pmu.set_topdown_event_period(event);
 
+	/*
+	 * 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))
+		period = amd_brs_adjust_period(period);
+
 	/*
 	 * If we are way outside a reasonable range then just skip forward:
 	 */
@@ -1659,11 +1670,15 @@ 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);
 	}

arch/x86/events/intel/lbr.c

@@ -786,6 +786,7 @@ 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;
 
@@ -801,15 +802,11 @@ 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;
@@ -825,6 +822,7 @@ 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;
 	int lbr_format = x86_pmu.intel_cap.lbr_format;
+	struct perf_branch_entry *br = cpuc->lbr_entries;
 	u64 tos = intel_pmu_lbr_tos();
 	int i;
 	int out = 0;
@@ -896,15 +894,14 @@ 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;
@@ -966,6 +963,8 @@ 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);
@@ -974,7 +973,6 @@ 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;

arch/x86/events/perf_event.h

@@ -66,22 +66,23 @@ 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_RDPMC_ALLOWED	0x0080 /* grant rdpmc permission */
-#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_RDPMC_ALLOWED	0x00080 /* grant rdpmc permission */
+#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)
 {
@@ -323,6 +324,8 @@ 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 */
@@ -986,6 +989,11 @@ 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;
@@ -1082,6 +1090,88 @@ static inline bool fixed_counter_disabled(int i)
 
 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);
+
+static inline s64 amd_brs_adjust_period(s64 period)
+{
+	if (period > x86_pmu.lbr_nr)
+		return period - x86_pmu.lbr_nr;
+
+	return period;
+}
+#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 s64 amd_brs_adjust_period(s64 period)
+{
+	return period;
+}
+
+static inline void amd_brs_enable_all(void)
+{
+}
+
+#endif
+
 #else /* CONFIG_CPU_SUP_AMD */
 
 static inline int amd_pmu_init(void)
@@ -1089,6 +1179,27 @@ 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)
+{
+}
+
+static inline s64 amd_brs_adjust_period(s64 period)
+{
+	return period;
+}
 #endif /* CONFIG_CPU_SUP_AMD */
 
 static inline int is_pebs_pt(struct perf_event *event)

arch/x86/include/asm/amd-ibs.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * From PPR Vol 1 for AMD Family 19h Model 01h B1
+ * 55898 Rev 0.35 - Feb 5, 2021
+ */
+
+#include <asm/msr-index.h>
+
+/*
+ * IBS Hardware MSRs
+ */
+
+/* MSR 0xc0011030: IBS Fetch Control */
+union ibs_fetch_ctl {
+	__u64 val;
+	struct {
+		__u64	fetch_maxcnt:16,/* 0-15: instruction fetch max. count */
+			fetch_cnt:16,	/* 16-31: instruction fetch count */
+			fetch_lat:16,	/* 32-47: instruction fetch latency */
+			fetch_en:1,	/* 48: instruction fetch enable */
+			fetch_val:1,	/* 49: instruction fetch valid */
+			fetch_comp:1,	/* 50: instruction fetch complete */
+			ic_miss:1,	/* 51: i-cache miss */
+			phy_addr_valid:1,/* 52: physical address valid */
+			l1tlb_pgsz:2,	/* 53-54: i-cache L1TLB page size
+					 *	  (needs IbsPhyAddrValid) */
+			l1tlb_miss:1,	/* 55: i-cache fetch missed in L1TLB */
+			l2tlb_miss:1,	/* 56: i-cache fetch missed in L2TLB */
+			rand_en:1,	/* 57: random tagging enable */
+			fetch_l2_miss:1,/* 58: L2 miss for sampled fetch
+					 *      (needs IbsFetchComp) */
+			reserved:5;	/* 59-63: reserved */
+	};
+};
+
+/* MSR 0xc0011033: IBS Execution Control */
+union ibs_op_ctl {
+	__u64 val;
+	struct {
+		__u64	opmaxcnt:16,	/* 0-15: periodic op max. count */
+			reserved0:1,	/* 16: reserved */
+			op_en:1,	/* 17: op sampling enable */
+			op_val:1,	/* 18: op sample valid */
+			cnt_ctl:1,	/* 19: periodic op counter control */
+			opmaxcnt_ext:7,	/* 20-26: upper 7 bits of periodic op maximum count */
+			reserved1:5,	/* 27-31: reserved */
+			opcurcnt:27,	/* 32-58: periodic op counter current count */
+			reserved2:5;	/* 59-63: reserved */
+	};
+};
+
+/* MSR 0xc0011035: IBS Op Data 2 */
+union ibs_op_data {
+	__u64 val;
+	struct {
+		__u64	comp_to_ret_ctr:16,	/* 0-15: op completion to retire count */
+			tag_to_ret_ctr:16,	/* 15-31: op tag to retire count */
+			reserved1:2,		/* 32-33: reserved */
+			op_return:1,		/* 34: return op */
+			op_brn_taken:1,		/* 35: taken branch op */
+			op_brn_misp:1,		/* 36: mispredicted branch op */
+			op_brn_ret:1,		/* 37: branch op retired */
+			op_rip_invalid:1,	/* 38: RIP is invalid */
+			op_brn_fuse:1,		/* 39: fused branch op */
+			op_microcode:1,		/* 40: microcode op */
+			reserved2:23;		/* 41-63: reserved */
+	};
+};
+
+/* MSR 0xc0011036: IBS Op Data 2 */
+union ibs_op_data2 {
+	__u64 val;
+	struct {
+		__u64	data_src:3,	/* 0-2: data source */
+			reserved0:1,	/* 3: reserved */
+			rmt_node:1,	/* 4: destination node */
+			cache_hit_st:1,	/* 5: cache hit state */
+			reserved1:57;	/* 5-63: reserved */
+	};
+};
+
+/* MSR 0xc0011037: IBS Op Data 3 */
+union ibs_op_data3 {
+	__u64 val;
+	struct {
+		__u64	ld_op:1,			/* 0: load op */
+			st_op:1,			/* 1: store op */
+			dc_l1tlb_miss:1,		/* 2: data cache L1TLB miss */
+			dc_l2tlb_miss:1,		/* 3: data cache L2TLB hit in 2M page */
+			dc_l1tlb_hit_2m:1,		/* 4: data cache L1TLB hit in 2M page */
+			dc_l1tlb_hit_1g:1,		/* 5: data cache L1TLB hit in 1G page */
+			dc_l2tlb_hit_2m:1,		/* 6: data cache L2TLB hit in 2M page */
+			dc_miss:1,			/* 7: data cache miss */
+			dc_mis_acc:1,			/* 8: misaligned access */
+			reserved:4,			/* 9-12: reserved */
+			dc_wc_mem_acc:1,		/* 13: write combining memory access */
+			dc_uc_mem_acc:1,		/* 14: uncacheable memory access */
+			dc_locked_op:1,			/* 15: locked operation */
+			dc_miss_no_mab_alloc:1,		/* 16: DC miss with no MAB allocated */
+			dc_lin_addr_valid:1,		/* 17: data cache linear address valid */
+			dc_phy_addr_valid:1,		/* 18: data cache physical address valid */
+			dc_l2_tlb_hit_1g:1,		/* 19: data cache L2 hit in 1GB page */
+			l2_miss:1,			/* 20: L2 cache miss */
+			sw_pf:1,			/* 21: software prefetch */
+			op_mem_width:4,			/* 22-25: load/store size in bytes */
+			op_dc_miss_open_mem_reqs:6,	/* 26-31: outstanding mem reqs on DC fill */
+			dc_miss_lat:16,			/* 32-47: data cache miss latency */
+			tlb_refill_lat:16;		/* 48-63: L1 TLB refill latency */
+	};
+};
+
+/* MSR 0xc001103c: IBS Fetch Control Extended */
+union ic_ibs_extd_ctl {
+	__u64 val;
+	struct {
+		__u64	itlb_refill_lat:16,	/* 0-15: ITLB Refill latency for sampled fetch */
+			reserved:48;		/* 16-63: reserved */
+	};
+};
+
+/*
+ * IBS driver related
+ */
+
+struct perf_ibs_data {
+	u32		size;
+	union {
+		u32	data[0];	/* data buffer starts here */
+		u32	caps;
+	};
+	u64		regs[MSR_AMD64_IBS_REG_COUNT_MAX];
+};

arch/x86/include/asm/cpufeature.h

@@ -30,6 +30,7 @@ enum cpuid_leafs
 	CPUID_7_ECX,
 	CPUID_8000_0007_EBX,
 	CPUID_7_EDX,
+	CPUID_8000_001F_EAX,
 };
 
 #ifdef CONFIG_X86_FEATURE_NAMES
@@ -88,8 +89,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) ||	\
 	   REQUIRED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 19))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 20))
 
 #define DISABLED_MASK_BIT_SET(feature_bit)				\
 	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
@@ -111,8 +113,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) ||	\
 	   DISABLED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 19))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 20))
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\

arch/x86/include/asm/cpufeatures.h

@@ -13,7 +13,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS			19	   /* N 32-bit words worth of info */
+#define NCAPINTS			20	   /* N 32-bit words worth of info */
 #define NBUGINTS			1	   /* N 32-bit bug flags */
 
 /*
@@ -96,7 +96,7 @@
 #define X86_FEATURE_SYSCALL32		( 3*32+14) /* "" syscall in IA32 userspace */
 #define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
-#define X86_FEATURE_SME_COHERENT	( 3*32+17) /* "" AMD hardware-enforced cache coherency */
+/* FREE!                                ( 3*32+17) */
 #define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
 #define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
 #define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
@@ -201,7 +201,7 @@
 #define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
-#define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
+/* FREE!                                ( 7*32+10) */
 #define X86_FEATURE_PTI			( 7*32+11) /* Kernel Page Table Isolation enabled */
 #define X86_FEATURE_RETPOLINE		( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_RETPOLINE_LFENCE	( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */
@@ -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 */
-#define X86_FEATURE_SEV			( 7*32+20) /* AMD Secure Encrypted Virtualization */
+#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. */
@@ -236,7 +236,6 @@
 #define X86_FEATURE_EPT_AD		( 8*32+17) /* Intel Extended Page Table access-dirty bit */
 #define X86_FEATURE_VMCALL		( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
 #define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
-#define X86_FEATURE_SEV_ES		( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
@@ -313,6 +312,7 @@
 #define X86_FEATURE_AMD_SSBD		(13*32+24) /* "" Speculative Store Bypass Disable */
 #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_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 */
@@ -393,6 +393,13 @@
 #define X86_FEATURE_CORE_CAPABILITIES	(18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */
 #define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
+/* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */
+#define X86_FEATURE_SME			(19*32+ 0) /* AMD Secure Memory Encryption */
+#define X86_FEATURE_SEV			(19*32+ 1) /* AMD Secure Encrypted Virtualization */
+#define X86_FEATURE_VM_PAGE_FLUSH	(19*32+ 2) /* "" VM Page Flush MSR is supported */
+#define X86_FEATURE_SEV_ES		(19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
+#define X86_FEATURE_SME_COHERENT	(19*32+10) /* "" AMD hardware-enforced cache coherency */
+
 /*
  * BUG word(s)
  */

arch/x86/include/asm/disabled-features.h

@@ -88,6 +88,7 @@
 			 DISABLE_ENQCMD)
 #define DISABLED_MASK17	0
 #define DISABLED_MASK18	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
+#define DISABLED_MASK19	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */

arch/x86/include/asm/msr-index.h

@@ -498,6 +498,7 @@
 #define MSR_AMD64_IBSOPDATA4		0xc001103d
 #define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
 #define MSR_AMD64_SVM_AVIC_DOORBELL	0xc001011b
+#define MSR_AMD64_VM_PAGE_FLUSH		0xc001011e
 #define MSR_AMD64_SEV_ES_GHCB		0xc0010130
 #define MSR_AMD64_SEV			0xc0010131
 #define MSR_AMD64_SEV_ENABLED_BIT	0
@@ -507,6 +508,11 @@
 
 #define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
 
+/* 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
 
@@ -673,6 +679,10 @@
 #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
 

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;
@@ -365,6 +379,11 @@ 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
  */
@@ -386,6 +405,7 @@ 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	\
@@ -399,6 +419,7 @@ 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)
@@ -415,6 +436,7 @@ 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 */
@@ -516,6 +538,27 @@ 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) { }

arch/x86/include/asm/required-features.h

@@ -101,6 +101,7 @@
 #define REQUIRED_MASK16	0
 #define REQUIRED_MASK17	0
 #define REQUIRED_MASK18	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
+#define REQUIRED_MASK19	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */

arch/x86/kernel/cpu/common.c

@@ -957,6 +957,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 	if (c->extended_cpuid_level >= 0x8000000a)
 		c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
 
+	if (c->extended_cpuid_level >= 0x8000001f)
+		c->x86_capability[CPUID_8000_001F_EAX] = cpuid_eax(0x8000001f);
+
 	init_scattered_cpuid_features(c);
 	init_speculation_control(c);
 

arch/x86/kernel/cpu/scattered.c

@@ -42,10 +42,7 @@ 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_SME,		CPUID_EAX,  0, 0x8000001f, 0 },
-	{ X86_FEATURE_SEV,		CPUID_EAX,  1, 0x8000001f, 0 },
-	{ X86_FEATURE_SEV_ES,		CPUID_EAX,  3, 0x8000001f, 0 },
-	{ X86_FEATURE_SME_COHERENT,	CPUID_EAX, 10, 0x8000001f, 0 },
+	{ X86_FEATURE_PERFMON_V2,	CPUID_EAX,  0, 0x80000022, 0 },
 	{ 0, 0, 0, 0, 0 }
 };
 

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>
 
@@ -163,6 +164,9 @@ 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();
@@ -171,6 +175,9 @@ 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)) {

drivers/acpi/processor_idle.c

@@ -20,6 +20,7 @@
 #include <linux/tick.h>
 #include <linux/cpuidle.h>
 #include <linux/cpu.h>
+#include <linux/perf_event.h>
 #include <acpi/processor.h>
 
 /*
@@ -551,6 +552,8 @@ 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);
@@ -561,6 +564,8 @@ static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx)
 		inb(cx->address);
 		wait_for_freeze();
 	}
+
+	perf_lopwr_cb(false);
 }
 
 /**

include/linux/perf_event.h

@@ -1062,6 +1062,22 @@ 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,
@@ -1608,4 +1624,11 @@ extern void __weak arch_perf_update_userpage(struct perf_event *event,
 					     struct perf_event_mmap_page *userpg,
 					     u64 now);
 
+
+#ifndef PERF_NEEDS_LOPWR_CB
+static inline void perf_lopwr_cb(bool mode)
+{
+}
+#endif
+
 #endif /* _LINUX_PERF_EVENT_H */

tools/arch/x86/include/asm/disabled-features.h

@@ -85,6 +85,7 @@
 			 DISABLE_ENQCMD)
 #define DISABLED_MASK17	0
 #define DISABLED_MASK18	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
+#define DISABLED_MASK19	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */

tools/arch/x86/include/asm/required-features.h

@@ -101,6 +101,7 @@
 #define REQUIRED_MASK16	0
 #define REQUIRED_MASK17	0
 #define REQUIRED_MASK18	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
+#define REQUIRED_MASK19	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */