Merge tag 'perf-core-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf event updates from Ingo Molnar:
 "HW support updates:

   - Add uncore support for Intel Comet Lake

   - Add RAPL support for Hygon Fam18h

   - Add Intel "IIO stack to PMON mapping" support on Skylake-SP CPUs,
     which enumerates per device performance counters via sysfs and
     enables the perf stat --iiostat functionality

   - Add support for Intel "Architectural LBRs", which generalized the
     model specific LBR hardware tracing feature into a
     model-independent, architected performance monitoring feature.

     Usage is mostly seamless to tooling, as the pre-existing LBR
     features are kept, but there's a couple of advantages under the
     hood, such as faster context-switching, faster LBR reads, cleaner
     exposure of LBR features to guest kernels, etc.

     ( Since architectural LBRs are supported via XSAVE, there's related
       changes to the x86 FPU code as well. )

  ftrace/perf updates:

   - Add support to add a text poke event to record changes to kernel
     text (i.e. self-modifying code) in order to support tracers like
     Intel PT decoding through jump labels, kprobes and ftrace
     trampolines.

  Misc cleanups, smaller fixes..."

* tag 'perf-core-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (47 commits)
  perf/x86/rapl: Add Hygon Fam18h RAPL support
  kprobes: Remove unnecessary module_mutex locking from kprobe_optimizer()
  x86/perf: Fix a typo
  perf: <linux/perf_event.h>: drop a duplicated word
  perf/x86/intel/lbr: Support XSAVES for arch LBR read
  perf/x86/intel/lbr: Support XSAVES/XRSTORS for LBR context switch
  x86/fpu/xstate: Add helpers for LBR dynamic supervisor feature
  x86/fpu/xstate: Support dynamic supervisor feature for LBR
  x86/fpu: Use proper mask to replace full instruction mask
  perf/x86: Remove task_ctx_size
  perf/x86/intel/lbr: Create kmem_cache for the LBR context data
  perf/core: Use kmem_cache to allocate the PMU specific data
  perf/core: Factor out functions to allocate/free the task_ctx_data
  perf/x86/intel/lbr: Support Architectural LBR
  perf/x86/intel/lbr: Factor out intel_pmu_store_lbr
  perf/x86/intel/lbr: Factor out rdlbr_all() and wrlbr_all()
  perf/x86/intel/lbr: Mark the {rd,wr}lbr_{to,from} wrappers __always_inline
  perf/x86/intel/lbr: Unify the stored format of LBR information
  perf/x86/intel/lbr: Support LBR_CTL
  perf/x86: Expose CPUID enumeration bits for arch LBR
  ...

32 files changed, 1943 insertions, 280 deletions

diff --git a/Documentation/ABI/testing/sysfs-devices-mapping b/Documentation/ABI/testing/sysfs-devices-mapping
new file mode 100644
index 000000000000..490ccfd67f12
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-mapping
@@ -0,0 +1,33 @@
+What:           /sys/devices/uncore_iio_x/dieX
+Date:           February 2020
+Contact:        Roman Sudarikov <roman.sudarikov@linux.intel.com>
+Description:
+                Each IIO stack (PCIe root port) has its own IIO PMON block, so
+                each dieX file (where X is die number) holds "Segment:Root Bus"
+                for PCIe root port, which can be monitored by that IIO PMON
+                block.
+                For example, on 4-die Xeon platform with up to 6 IIO stacks per
+                die and, therefore, 6 IIO PMON blocks per die, the mapping of
+                IIO PMON block 0 exposes as the following:
+
+                $ ls /sys/devices/uncore_iio_0/die*
+                -r--r--r-- /sys/devices/uncore_iio_0/die0
+                -r--r--r-- /sys/devices/uncore_iio_0/die1
+                -r--r--r-- /sys/devices/uncore_iio_0/die2
+                -r--r--r-- /sys/devices/uncore_iio_0/die3
+
+                $ tail /sys/devices/uncore_iio_0/die*
+                ==> /sys/devices/uncore_iio_0/die0 <==
+                0000:00
+                ==> /sys/devices/uncore_iio_0/die1 <==
+                0000:40
+                ==> /sys/devices/uncore_iio_0/die2 <==
+                0000:80
+                ==> /sys/devices/uncore_iio_0/die3 <==
+                0000:c0
+
+                Which means:
+                IIO PMU 0 on die 0 belongs to PCI RP on bus 0x00, domain 0x0000
+                IIO PMU 0 on die 1 belongs to PCI RP on bus 0x40, domain 0x0000
+                IIO PMU 0 on die 2 belongs to PCI RP on bus 0x80, domain 0x0000
+                IIO PMU 0 on die 3 belongs to PCI RP on bus 0xc0, domain 0x0000
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 4103665c6e03..1cbf57dc2ac8 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -71,10 +71,9 @@ u64 x86_perf_event_update(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int shift = 64 - x86_pmu.cntval_bits;
 	u64 prev_raw_count, new_raw_count;
-	int idx = hwc->idx;
 	u64 delta;
 
-	if (idx == INTEL_PMC_IDX_FIXED_BTS)
+	if (unlikely(!hwc->event_base))
 		return 0;
 
 	/*
@@ -359,6 +358,7 @@ void x86_release_hardware(void)
 	if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) {
 		release_pmc_hardware();
 		release_ds_buffers();
+		release_lbr_buffers();
 		mutex_unlock(&pmc_reserve_mutex);
 	}
 }
@@ -1097,22 +1097,31 @@ static inline void x86_assign_hw_event(struct perf_event *event,
 				struct cpu_hw_events *cpuc, int i)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	int idx;
 
-	hwc->idx = cpuc->assign[i];
+	idx = hwc->idx = cpuc->assign[i];
 	hwc->last_cpu = smp_processor_id();
 	hwc->last_tag = ++cpuc->tags[i];
 
-	if (hwc->idx == INTEL_PMC_IDX_FIXED_BTS) {
+	switch (hwc->idx) {
+	case INTEL_PMC_IDX_FIXED_BTS:
+	case INTEL_PMC_IDX_FIXED_VLBR:
 		hwc->config_base = 0;
 		hwc->event_base	= 0;
-	} else if (hwc->idx >= INTEL_PMC_IDX_FIXED) {
+		break;
+
+	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS-1:
 		hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
-		hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - INTEL_PMC_IDX_FIXED);
-		hwc->event_base_rdpmc = (hwc->idx - INTEL_PMC_IDX_FIXED) | 1<<30;
-	} else {
+		hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 +
+				(idx - INTEL_PMC_IDX_FIXED);
+		hwc->event_base_rdpmc = (idx - INTEL_PMC_IDX_FIXED) | 1<<30;
+		break;
+
+	default:
 		hwc->config_base = x86_pmu_config_addr(hwc->idx);
 		hwc->event_base  = x86_pmu_event_addr(hwc->idx);
 		hwc->event_base_rdpmc = x86_pmu_rdpmc_index(hwc->idx);
+		break;
 	}
 }
 
@@ -1233,7 +1242,7 @@ int x86_perf_event_set_period(struct perf_event *event)
 	s64 period = hwc->sample_period;
 	int ret = 0, idx = hwc->idx;
 
-	if (idx == INTEL_PMC_IDX_FIXED_BTS)
+	if (unlikely(!hwc->event_base))
 		return 0;
 
 	/*
@@ -2363,7 +2372,6 @@ static struct pmu pmu = {
 
 	.event_idx		= x86_pmu_event_idx,
 	.sched_task		= x86_pmu_sched_task,
-	.task_ctx_size          = sizeof(struct x86_perf_task_context),
 	.swap_task_ctx		= x86_pmu_swap_task_ctx,
 	.check_period		= x86_pmu_check_period,
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index ca35c8b5ee10..50963472ee85 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2136,8 +2136,35 @@ static inline void intel_pmu_ack_status(u64 ack)
 	wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
 }
 
-static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
+static inline bool event_is_checkpointed(struct perf_event *event)
 {
+	return unlikely(event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
+}
+
+static inline void intel_set_masks(struct perf_event *event, int idx)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (event->attr.exclude_host)
+		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
+	if (event->attr.exclude_guest)
+		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
+	if (event_is_checkpointed(event))
+		__set_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
+}
+
+static inline void intel_clear_masks(struct perf_event *event, int idx)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	__clear_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
+	__clear_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
+	__clear_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
+}
+
+static void intel_pmu_disable_fixed(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
 	u64 ctrl_val, mask;
 
@@ -2148,30 +2175,22 @@ static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
 	wrmsrl(hwc->config_base, ctrl_val);
 }
 
-static inline bool event_is_checkpointed(struct perf_event *event)
-{
-	return (event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
-}
-
 static void intel_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int idx = hwc->idx;
 
-	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		intel_clear_masks(event, idx);
+		x86_pmu_disable_event(event);
+	} else if (idx < INTEL_PMC_IDX_FIXED_BTS) {
+		intel_clear_masks(event, idx);
+		intel_pmu_disable_fixed(event);
+	} else if (idx == INTEL_PMC_IDX_FIXED_BTS) {
 		intel_pmu_disable_bts();
 		intel_pmu_drain_bts_buffer();
-		return;
-	}
-
-	cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
-	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
-	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
-
-	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL))
-		intel_pmu_disable_fixed(hwc);
-	else
-		x86_pmu_disable_event(event);
+	} else if (idx == INTEL_PMC_IDX_FIXED_VLBR)
+		intel_clear_masks(event, idx);
 
 	/*
 	 * Needs to be called after x86_pmu_disable_event,
@@ -2238,33 +2257,23 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 static void intel_pmu_enable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-
-	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
-		if (!__this_cpu_read(cpu_hw_events.enabled))
-			return;
-
-		intel_pmu_enable_bts(hwc->config);
-		return;
-	}
-
-	if (event->attr.exclude_host)
-		cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
-	if (event->attr.exclude_guest)
-		cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx);
-
-	if (unlikely(event_is_checkpointed(event)))
-		cpuc->intel_cp_status |= (1ull << hwc->idx);
+	int idx = hwc->idx;
 
 	if (unlikely(event->attr.precise_ip))
 		intel_pmu_pebs_enable(event);
 
-	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		intel_set_masks(event, idx);
+		__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+	} else if (idx < INTEL_PMC_IDX_FIXED_BTS) {
+		intel_set_masks(event, idx);
 		intel_pmu_enable_fixed(event);
-		return;
-	}
-
-	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+	} else if (idx == INTEL_PMC_IDX_FIXED_BTS) {
+		if (!__this_cpu_read(cpu_hw_events.enabled))
+			return;
+		intel_pmu_enable_bts(hwc->config);
+	} else if (idx == INTEL_PMC_IDX_FIXED_VLBR)
+		intel_set_masks(event, idx);
 }
 
 static void intel_pmu_add_event(struct perf_event *event)
@@ -2614,6 +2623,20 @@ intel_bts_constraints(struct perf_event *event)
 	return NULL;
 }
 
+/*
+ * Note: matches a fake event, like Fixed2.
+ */
+static struct event_constraint *
+intel_vlbr_constraints(struct perf_event *event)
+{
+	struct event_constraint *c = &vlbr_constraint;
+
+	if (unlikely(constraint_match(c, event->hw.config)))
+		return c;
+
+	return NULL;
+}
+
 static int intel_alt_er(int idx, u64 config)
 {
 	int alt_idx = idx;
@@ -2804,6 +2827,10 @@ __intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 {
 	struct event_constraint *c;
 
+	c = intel_vlbr_constraints(event);
+	if (c)
+		return c;
+
 	c = intel_bts_constraints(event);
 	if (c)
 		return c;
@@ -3951,6 +3978,11 @@ static __initconst const struct x86_pmu core_pmu = {
 	.cpu_dead		= intel_pmu_cpu_dead,
 
 	.check_period		= intel_pmu_check_period,
+
+	.lbr_reset		= intel_pmu_lbr_reset_64,
+	.lbr_read		= intel_pmu_lbr_read_64,
+	.lbr_save		= intel_pmu_lbr_save,
+	.lbr_restore		= intel_pmu_lbr_restore,
 };
 
 static __initconst const struct x86_pmu intel_pmu = {
@@ -3996,6 +4028,11 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.check_period		= intel_pmu_check_period,
 
 	.aux_output_match	= intel_pmu_aux_output_match,
+
+	.lbr_reset		= intel_pmu_lbr_reset_64,
+	.lbr_read		= intel_pmu_lbr_read_64,
+	.lbr_save		= intel_pmu_lbr_save,
+	.lbr_restore		= intel_pmu_lbr_restore,
 };
 
 static __init void intel_clovertown_quirk(void)
@@ -4622,6 +4659,14 @@ __init int intel_pmu_init(void)
 		x86_pmu.intel_cap.capabilities = capabilities;
 	}
 
+	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32) {
+		x86_pmu.lbr_reset = intel_pmu_lbr_reset_32;
+		x86_pmu.lbr_read = intel_pmu_lbr_read_32;
+	}
+
+	if (boot_cpu_has(X86_FEATURE_ARCH_LBR))
+		intel_pmu_arch_lbr_init();
+
 	intel_ds_init();
 
 	x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index dc43cc124e09..86848c57b55e 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -954,7 +954,7 @@ static void adaptive_pebs_record_size_update(void)
 	if (pebs_data_cfg & PEBS_DATACFG_XMMS)
 		sz += sizeof(struct pebs_xmm);
 	if (pebs_data_cfg & PEBS_DATACFG_LBRS)
-		sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry);
+		sz += x86_pmu.lbr_nr * sizeof(struct lbr_entry);
 
 	cpuc->pebs_record_size = sz;
 }
@@ -1595,10 +1595,10 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	}
 
 	if (format_size & PEBS_DATACFG_LBRS) {
-		struct pebs_lbr *lbr = next_record;
+		struct lbr_entry *lbr = next_record;
 		int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
 					& 0xff) + 1;
-		next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry);
+		next_record = next_record + num_lbr * sizeof(struct lbr_entry);
 
 		if (has_branch_stack(event)) {
 			intel_pmu_store_pebs_lbrs(lbr);
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 65113b16804a..63f58bdf556c 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -8,17 +8,6 @@
 
 #include "../perf_event.h"
 
-enum {
-	LBR_FORMAT_32		= 0x00,
-	LBR_FORMAT_LIP		= 0x01,
-	LBR_FORMAT_EIP		= 0x02,
-	LBR_FORMAT_EIP_FLAGS	= 0x03,
-	LBR_FORMAT_EIP_FLAGS2	= 0x04,
-	LBR_FORMAT_INFO		= 0x05,
-	LBR_FORMAT_TIME		= 0x06,
-	LBR_FORMAT_MAX_KNOWN    = LBR_FORMAT_TIME,
-};
-
 static const enum {
 	LBR_EIP_FLAGS		= 1,
 	LBR_TSX			= 2,
@@ -143,8 +132,54 @@ enum {
 	 X86_BR_IRQ		|\
 	 X86_BR_INT)
 
+/*
+ * Intel LBR_CTL bits
+ *
+ * Hardware branch filter for Arch LBR
+ */
+#define ARCH_LBR_KERNEL_BIT		1  /* capture at ring0 */
+#define ARCH_LBR_USER_BIT		2  /* capture at ring > 0 */
+#define ARCH_LBR_CALL_STACK_BIT		3  /* enable call stack */
+#define ARCH_LBR_JCC_BIT		16 /* capture conditional branches */
+#define ARCH_LBR_REL_JMP_BIT		17 /* capture relative jumps */
+#define ARCH_LBR_IND_JMP_BIT		18 /* capture indirect jumps */
+#define ARCH_LBR_REL_CALL_BIT		19 /* capture relative calls */
+#define ARCH_LBR_IND_CALL_BIT		20 /* capture indirect calls */
+#define ARCH_LBR_RETURN_BIT		21 /* capture near returns */
+#define ARCH_LBR_OTHER_BRANCH_BIT	22 /* capture other branches */
+
+#define ARCH_LBR_KERNEL			(1ULL << ARCH_LBR_KERNEL_BIT)
+#define ARCH_LBR_USER			(1ULL << ARCH_LBR_USER_BIT)
+#define ARCH_LBR_CALL_STACK		(1ULL << ARCH_LBR_CALL_STACK_BIT)
+#define ARCH_LBR_JCC			(1ULL << ARCH_LBR_JCC_BIT)
+#define ARCH_LBR_REL_JMP		(1ULL << ARCH_LBR_REL_JMP_BIT)
+#define ARCH_LBR_IND_JMP		(1ULL << ARCH_LBR_IND_JMP_BIT)
+#define ARCH_LBR_REL_CALL		(1ULL << ARCH_LBR_REL_CALL_BIT)
+#define ARCH_LBR_IND_CALL		(1ULL << ARCH_LBR_IND_CALL_BIT)
+#define ARCH_LBR_RETURN			(1ULL << ARCH_LBR_RETURN_BIT)
+#define ARCH_LBR_OTHER_BRANCH		(1ULL << ARCH_LBR_OTHER_BRANCH_BIT)
+
+#define ARCH_LBR_ANY			 \
+	(ARCH_LBR_JCC			|\
+	 ARCH_LBR_REL_JMP		|\
+	 ARCH_LBR_IND_JMP		|\
+	 ARCH_LBR_REL_CALL		|\
+	 ARCH_LBR_IND_CALL		|\
+	 ARCH_LBR_RETURN		|\
+	 ARCH_LBR_OTHER_BRANCH)
+
+#define ARCH_LBR_CTL_MASK			0x7f000e
+
 static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);
 
+static __always_inline bool is_lbr_call_stack_bit_set(u64 config)
+{
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
+		return !!(config & ARCH_LBR_CALL_STACK);
+
+	return !!(config & LBR_CALL_STACK);
+}
+
 /*
  * We only support LBR implementations that have FREEZE_LBRS_ON_PMI
  * otherwise it becomes near impossible to get a reliable stack.
@@ -168,33 +203,46 @@ static void __intel_pmu_lbr_enable(bool pmi)
 	 */
 	if (cpuc->lbr_sel)
 		lbr_select = cpuc->lbr_sel->config & x86_pmu.lbr_sel_mask;
-	if (!pmi && cpuc->lbr_sel)
+	if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && !pmi && cpuc->lbr_sel)
 		wrmsrl(MSR_LBR_SELECT, lbr_select);
 
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 	orig_debugctl = debugctl;
-	debugctl |= DEBUGCTLMSR_LBR;
+
+	if (!static_cpu_has(X86_FEATURE_ARCH_LBR))
+		debugctl |= DEBUGCTLMSR_LBR;
 	/*
 	 * LBR callstack does not work well with FREEZE_LBRS_ON_PMI.
 	 * If FREEZE_LBRS_ON_PMI is set, PMI near call/return instructions
 	 * may cause superfluous increase/decrease of LBR_TOS.
 	 */
-	if (!(lbr_select & LBR_CALL_STACK))
+	if (is_lbr_call_stack_bit_set(lbr_select))
+		debugctl &= ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
+	else
 		debugctl |= DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
+
 	if (orig_debugctl != debugctl)
 		wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
+		wrmsrl(MSR_ARCH_LBR_CTL, lbr_select | ARCH_LBR_CTL_LBREN);
 }
 
 static void __intel_pmu_lbr_disable(void)
 {
 	u64 debugctl;
 
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
+		wrmsrl(MSR_ARCH_LBR_CTL, 0);
+		return;
+	}
+
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 	debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
 	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 }
 
-static void intel_pmu_lbr_reset_32(void)
+void intel_pmu_lbr_reset_32(void)
 {
 	int i;
 
@@ -202,7 +250,7 @@ static void intel_pmu_lbr_reset_32(void)
 		wrmsrl(x86_pmu.lbr_from + i, 0);
 }
 
-static void intel_pmu_lbr_reset_64(void)
+void intel_pmu_lbr_reset_64(void)
 {
 	int i;
 
@@ -210,10 +258,16 @@ static void intel_pmu_lbr_reset_64(void)
 		wrmsrl(x86_pmu.lbr_from + i, 0);
 		wrmsrl(x86_pmu.lbr_to   + i, 0);
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
-			wrmsrl(MSR_LBR_INFO_0 + i, 0);
+			wrmsrl(x86_pmu.lbr_info + i, 0);
 	}
 }
 
+static void intel_pmu_arch_lbr_reset(void)
+{
+	/* Write to ARCH_LBR_DEPTH MSR, all LBR entries are reset to 0 */
+	wrmsrl(MSR_ARCH_LBR_DEPTH, x86_pmu.lbr_nr);
+}
+
 void intel_pmu_lbr_reset(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -221,10 +275,7 @@ void intel_pmu_lbr_reset(void)
 	if (!x86_pmu.lbr_nr)
 		return;
 
-	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
-		intel_pmu_lbr_reset_32();
-	else
-		intel_pmu_lbr_reset_64();
+	x86_pmu.lbr_reset();
 
 	cpuc->last_task_ctx = NULL;
 	cpuc->last_log_id = 0;
@@ -308,69 +359,97 @@ static u64 lbr_from_signext_quirk_rd(u64 val)
 	return val;
 }
 
-static inline void wrlbr_from(unsigned int idx, u64 val)
+static __always_inline void wrlbr_from(unsigned int idx, u64 val)
 {
 	val = lbr_from_signext_quirk_wr(val);
 	wrmsrl(x86_pmu.lbr_from + idx, val);
 }
 
-static inline void wrlbr_to(unsigned int idx, u64 val)
+static __always_inline void wrlbr_to(unsigned int idx, u64 val)
 {
 	wrmsrl(x86_pmu.lbr_to + idx, val);
 }
 
-static inline u64 rdlbr_from(unsigned int idx)
+static __always_inline void wrlbr_info(unsigned int idx, u64 val)
+{
+	wrmsrl(x86_pmu.lbr_info + idx, val);
+}
+
+static __always_inline u64 rdlbr_from(unsigned int idx, struct lbr_entry *lbr)
 {
 	u64 val;
 
+	if (lbr)
+		return lbr->from;
+
 	rdmsrl(x86_pmu.lbr_from + idx, val);
 
 	return lbr_from_signext_quirk_rd(val);
 }
 
-static inline u64 rdlbr_to(unsigned int idx)
+static __always_inline u64 rdlbr_to(unsigned int idx, struct lbr_entry *lbr)
 {
 	u64 val;
 
+	if (lbr)
+		return lbr->to;
+
 	rdmsrl(x86_pmu.lbr_to + idx, val);
 
 	return val;
 }
 
-static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
+static __always_inline u64 rdlbr_info(unsigned int idx, struct lbr_entry *lbr)
+{
+	u64 val;
+
+	if (lbr)
+		return lbr->info;
+
+	rdmsrl(x86_pmu.lbr_info + idx, val);
+
+	return val;
+}
+
+static inline void
+wrlbr_all(struct lbr_entry *lbr, unsigned int idx, bool need_info)
+{
+	wrlbr_from(idx, lbr->from);
+	wrlbr_to(idx, lbr->to);
+	if (need_info)
+		wrlbr_info(idx, lbr->info);
+}
+
+static inline bool
+rdlbr_all(struct lbr_entry *lbr, unsigned int idx, bool need_info)
+{
+	u64 from = rdlbr_from(idx, NULL);
+
+	/* Don't read invalid entry */
+	if (!from)
+		return false;
+
+	lbr->from = from;
+	lbr->to = rdlbr_to(idx, NULL);
+	if (need_info)
+		lbr->info = rdlbr_info(idx, NULL);
+
+	return true;
+}
+
+void intel_pmu_lbr_restore(void *ctx)
 {
+	bool need_info = x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO;
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct x86_perf_task_context *task_ctx = ctx;
 	int i;
 	unsigned lbr_idx, mask;
-	u64 tos;
-
-	if (task_ctx->lbr_callstack_users == 0 ||
-	    task_ctx->lbr_stack_state == LBR_NONE) {
-		intel_pmu_lbr_reset();
-		return;
-	}
-
-	tos = task_ctx->tos;
-	/*
-	 * Does not restore the LBR registers, if
-	 * - No one else touched them, and
-	 * - Did not enter C6
-	 */
-	if ((task_ctx == cpuc->last_task_ctx) &&
-	    (task_ctx->log_id == cpuc->last_log_id) &&
-	    rdlbr_from(tos)) {
-		task_ctx->lbr_stack_state = LBR_NONE;
-		return;
-	}
+	u64 tos = task_ctx->tos;
 
 	mask = x86_pmu.lbr_nr - 1;
 	for (i = 0; i < task_ctx->valid_lbrs; i++) {
 		lbr_idx = (tos - i) & mask;
-		wrlbr_from(lbr_idx, task_ctx->lbr_from[i]);
-		wrlbr_to  (lbr_idx, task_ctx->lbr_to[i]);
-
-		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
-			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
+		wrlbr_all(&task_ctx->lbr[i], lbr_idx, need_info);
 	}
 
 	for (; i < x86_pmu.lbr_nr; i++) {
@@ -378,49 +457,149 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		wrlbr_from(lbr_idx, 0);
 		wrlbr_to(lbr_idx, 0);
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
-			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, 0);
+			wrlbr_info(lbr_idx, 0);
 	}
 
 	wrmsrl(x86_pmu.lbr_tos, tos);
-	task_ctx->lbr_stack_state = LBR_NONE;
+
+	if (cpuc->lbr_select)
+		wrmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
 }
 
-static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
+static void intel_pmu_arch_lbr_restore(void *ctx)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	unsigned lbr_idx, mask;
-	u64 tos, from;
+	struct x86_perf_task_context_arch_lbr *task_ctx = ctx;
+	struct lbr_entry *entries = task_ctx->entries;
 	int i;
 
-	if (task_ctx->lbr_callstack_users == 0) {
-		task_ctx->lbr_stack_state = LBR_NONE;
+	/* Fast reset the LBRs before restore if the call stack is not full. */
+	if (!entries[x86_pmu.lbr_nr - 1].from)
+		intel_pmu_arch_lbr_reset();
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		if (!entries[i].from)
+			break;
+		wrlbr_all(&entries[i], i, true);
+	}
+}
+
+/*
+ * Restore the Architecture LBR state from the xsave area in the perf
+ * context data for the task via the XRSTORS instruction.
+ */
+static void intel_pmu_arch_lbr_xrstors(void *ctx)
+{
+	struct x86_perf_task_context_arch_lbr_xsave *task_ctx = ctx;
+
+	copy_kernel_to_dynamic_supervisor(&task_ctx->xsave, XFEATURE_MASK_LBR);
+}
+
+static __always_inline bool lbr_is_reset_in_cstate(void *ctx)
+{
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
+		return x86_pmu.lbr_deep_c_reset && !rdlbr_from(0, NULL);
+
+	return !rdlbr_from(((struct x86_perf_task_context *)ctx)->tos, NULL);
+}
+
+static void __intel_pmu_lbr_restore(void *ctx)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (task_context_opt(ctx)->lbr_callstack_users == 0 ||
+	    task_context_opt(ctx)->lbr_stack_state == LBR_NONE) {
+		intel_pmu_lbr_reset();
+		return;
+	}
+
+	/*
+	 * Does not restore the LBR registers, if
+	 * - No one else touched them, and
+	 * - Was not cleared in Cstate
+	 */
+	if ((ctx == cpuc->last_task_ctx) &&
+	    (task_context_opt(ctx)->log_id == cpuc->last_log_id) &&
+	    !lbr_is_reset_in_cstate(ctx)) {
+		task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
 		return;
 	}
 
+	x86_pmu.lbr_restore(ctx);
+
+	task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
+}
+
+void intel_pmu_lbr_save(void *ctx)
+{
+	bool need_info = x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO;
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct x86_perf_task_context *task_ctx = ctx;
+	unsigned lbr_idx, mask;
+	u64 tos;
+	int i;
+
 	mask = x86_pmu.lbr_nr - 1;
 	tos = intel_pmu_lbr_tos();
 	for (i = 0; i < x86_pmu.lbr_nr; i++) {
 		lbr_idx = (tos - i) & mask;
-		from = rdlbr_from(lbr_idx);
-		if (!from)
+		if (!rdlbr_all(&task_ctx->lbr[i], lbr_idx, need_info))
 			break;
-		task_ctx->lbr_from[i] = from;
-		task_ctx->lbr_to[i]   = rdlbr_to(lbr_idx);
-		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
-			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
 	task_ctx->valid_lbrs = i;
 	task_ctx->tos = tos;
-	task_ctx->lbr_stack_state = LBR_VALID;
 
-	cpuc->last_task_ctx = task_ctx;
-	cpuc->last_log_id = ++task_ctx->log_id;
+	if (cpuc->lbr_select)
+		rdmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
+}
+
+static void intel_pmu_arch_lbr_save(void *ctx)
+{
+	struct x86_perf_task_context_arch_lbr *task_ctx = ctx;
+	struct lbr_entry *entries = task_ctx->entries;
+	int i;
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		if (!rdlbr_all(&entries[i], i, true))
+			break;
+	}
+
+	/* LBR call stack is not full. Reset is required in restore. */
+	if (i < x86_pmu.lbr_nr)
+		entries[x86_pmu.lbr_nr - 1].from = 0;
+}
+
+/*
+ * Save the Architecture LBR state to the xsave area in the perf
+ * context data for the task via the XSAVES instruction.
+ */
+static void intel_pmu_arch_lbr_xsaves(void *ctx)
+{
+	struct x86_perf_task_context_arch_lbr_xsave *task_ctx = ctx;
+
+	copy_dynamic_supervisor_to_kernel(&task_ctx->xsave, XFEATURE_MASK_LBR);
+}
+
+static void __intel_pmu_lbr_save(void *ctx)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (task_context_opt(ctx)->lbr_callstack_users == 0) {
+		task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
+		return;
+	}
+
+	x86_pmu.lbr_save(ctx);
+
+	task_context_opt(ctx)->lbr_stack_state = LBR_VALID;
+
+	cpuc->last_task_ctx = ctx;
+	cpuc->last_log_id = ++task_context_opt(ctx)->log_id;
 }
 
 void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
 				 struct perf_event_context *next)
 {
-	struct x86_perf_task_context *prev_ctx_data, *next_ctx_data;
+	void *prev_ctx_data, *next_ctx_data;
 
 	swap(prev->task_ctx_data, next->task_ctx_data);
 
@@ -436,14 +615,14 @@ void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
 	if (!prev_ctx_data || !next_ctx_data)
 		return;
 
-	swap(prev_ctx_data->lbr_callstack_users,
-	     next_ctx_data->lbr_callstack_users);
+	swap(task_context_opt(prev_ctx_data)->lbr_callstack_users,
+	     task_context_opt(next_ctx_data)->lbr_callstack_users);
 }
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct x86_perf_task_context *task_ctx;
+	void *task_ctx;
 
 	if (!cpuc->lbr_users)
 		return;
@@ -479,18 +658,19 @@ static inline bool branch_user_callstack(unsigned br_sel)
 
 void intel_pmu_lbr_add(struct perf_event *event)
 {
+	struct kmem_cache *kmem_cache = event->pmu->task_ctx_cache;
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct x86_perf_task_context *task_ctx;
 
 	if (!x86_pmu.lbr_nr)
 		return;
 
+	if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT)
+		cpuc->lbr_select = 1;
+
 	cpuc->br_sel = event->hw.branch_reg.reg;
 
-	if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data) {
-		task_ctx = event->ctx->task_ctx_data;
-		task_ctx->lbr_callstack_users++;
-	}
+	if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data)
+		task_context_opt(event->ctx->task_ctx_data)->lbr_callstack_users++;
 
 	/*
 	 * Request pmu::sched_task() callback, which will fire inside the
@@ -516,21 +696,44 @@ void intel_pmu_lbr_add(struct perf_event *event)
 	perf_sched_cb_inc(event->ctx->pmu);
 	if (!cpuc->lbr_users++ && !event->total_time_running)
 		intel_pmu_lbr_reset();
+
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR) &&
+	    kmem_cache && !cpuc->lbr_xsave &&
+	    (cpuc->lbr_users != cpuc->lbr_pebs_users))
+		cpuc->lbr_xsave = kmem_cache_alloc(kmem_cache, GFP_KERNEL);
+}
+
+void release_lbr_buffers(void)
+{
+	struct kmem_cache *kmem_cache = x86_get_pmu()->task_ctx_cache;
+	struct cpu_hw_events *cpuc;
+	int cpu;
+
+	if (!static_cpu_has(X86_FEATURE_ARCH_LBR))
+		return;
+
+	for_each_possible_cpu(cpu) {
+		cpuc = per_cpu_ptr(&cpu_hw_events, cpu);
+		if (kmem_cache && cpuc->lbr_xsave) {
+			kmem_cache_free(kmem_cache, cpuc->lbr_xsave);
+			cpuc->lbr_xsave = NULL;
+		}
+	}
 }
 
 void intel_pmu_lbr_del(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct x86_perf_task_context *task_ctx;
 
 	if (!x86_pmu.lbr_nr)
 		return;
 
 	if (branch_user_callstack(cpuc->br_sel) &&
-	    event->ctx->task_ctx_data) {
-		task_ctx = event->ctx->task_ctx_data;
-		task_ctx->lbr_callstack_users--;
-	}
+	    event->ctx->task_ctx_data)
+		task_context_opt(event->ctx->task_ctx_data)->lbr_callstack_users--;
+
+	if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT)
+		cpuc->lbr_select = 0;
 
 	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
 		cpuc->lbr_pebs_users--;
@@ -540,11 +743,19 @@ void intel_pmu_lbr_del(struct perf_event *event)
 	perf_sched_cb_dec(event->ctx->pmu);
 }
 
+static inline bool vlbr_exclude_host(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	return test_bit(INTEL_PMC_IDX_FIXED_VLBR,
+		(unsigned long *)&cpuc->intel_ctrl_guest_mask);
+}
+
 void intel_pmu_lbr_enable_all(bool pmi)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	if (cpuc->lbr_users)
+	if (cpuc->lbr_users && !vlbr_exclude_host())
 		__intel_pmu_lbr_enable(pmi);
 }
 
@@ -552,11 +763,11 @@ void intel_pmu_lbr_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	if (cpuc->lbr_users)
+	if (cpuc->lbr_users && !vlbr_exclude_host())
 		__intel_pmu_lbr_disable();
 }
 
-static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
+void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 {
 	unsigned long mask = x86_pmu.lbr_nr - 1;
 	u64 tos = intel_pmu_lbr_tos();
@@ -593,7 +804,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
  * is the same as the linear address, allowing us to merge the LIP and EIP
  * LBR formats.
  */
-static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
+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;
@@ -616,8 +827,8 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		u16 cycles = 0;
 		int lbr_flags = lbr_desc[lbr_format];
 
-		from = rdlbr_from(lbr_idx);
-		to   = rdlbr_to(lbr_idx);
+		from = rdlbr_from(lbr_idx, NULL);
+		to   = rdlbr_to(lbr_idx, NULL);
 
 		/*
 		 * Read LBR call stack entries
@@ -629,7 +840,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		if (lbr_format == LBR_FORMAT_INFO && need_info) {
 			u64 info;
 
-			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, info);
+			info = rdlbr_info(lbr_idx, NULL);
 			mis = !!(info & LBR_INFO_MISPRED);
 			pred = !mis;
 			in_tx = !!(info & LBR_INFO_IN_TX);
@@ -684,6 +895,93 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 	cpuc->lbr_stack.hw_idx = tos;
 }
 
+static __always_inline int get_lbr_br_type(u64 info)
+{
+	if (!static_cpu_has(X86_FEATURE_ARCH_LBR) || !x86_pmu.lbr_br_type)
+		return 0;
+
+	return (info & LBR_INFO_BR_TYPE) >> LBR_INFO_BR_TYPE_OFFSET;
+}
+
+static __always_inline bool get_lbr_mispred(u64 info)
+{
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR) && !x86_pmu.lbr_mispred)
+		return 0;
+
+	return !!(info & LBR_INFO_MISPRED);
+}
+
+static __always_inline bool get_lbr_predicted(u64 info)
+{
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR) && !x86_pmu.lbr_mispred)
+		return 0;
+
+	return !(info & LBR_INFO_MISPRED);
+}
+
+static __always_inline bool get_lbr_cycles(u64 info)
+{
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR) &&
+	    !(x86_pmu.lbr_timed_lbr && info & LBR_INFO_CYC_CNT_VALID))
+		return 0;
+
+	return info & LBR_INFO_CYCLES;
+}
+
+static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
+				struct lbr_entry *entries)
+{
+	struct perf_branch_entry *e;
+	struct lbr_entry *lbr;
+	u64 from, to, info;
+	int i;
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		lbr = entries ? &entries[i] : NULL;
+		e = &cpuc->lbr_entries[i];
+
+		from = rdlbr_from(i, lbr);
+		/*
+		 * Read LBR entries until invalid entry (0s) is detected.
+		 */
+		if (!from)
+			break;
+
+		to = rdlbr_to(i, lbr);
+		info = rdlbr_info(i, lbr);
+
+		e->from		= from;
+		e->to		= to;
+		e->mispred	= get_lbr_mispred(info);
+		e->predicted	= get_lbr_predicted(info);
+		e->in_tx	= !!(info & LBR_INFO_IN_TX);
+		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;
+}
+
+static void intel_pmu_arch_lbr_read(struct cpu_hw_events *cpuc)
+{
+	intel_pmu_store_lbr(cpuc, NULL);
+}
+
+static void intel_pmu_arch_lbr_read_xsave(struct cpu_hw_events *cpuc)
+{
+	struct x86_perf_task_context_arch_lbr_xsave *xsave = cpuc->lbr_xsave;
+
+	if (!xsave) {
+		intel_pmu_store_lbr(cpuc, NULL);
+		return;
+	}
+	copy_dynamic_supervisor_to_kernel(&xsave->xsave, XFEATURE_MASK_LBR);
+
+	intel_pmu_store_lbr(cpuc, xsave->lbr.entries);
+}
+
 void intel_pmu_lbr_read(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -694,13 +992,11 @@ void intel_pmu_lbr_read(void)
 	 * This could be smarter and actually check the event,
 	 * but this simple approach seems to work for now.
 	 */
-	if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users)
+	if (!cpuc->lbr_users || vlbr_exclude_host() ||
+	    cpuc->lbr_users == cpuc->lbr_pebs_users)
 		return;
 
-	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
-		intel_pmu_lbr_read_32(cpuc);
-	else
-		intel_pmu_lbr_read_64(cpuc);
+	x86_pmu.lbr_read(cpuc);
 
 	intel_pmu_lbr_filter(cpuc);
 }
@@ -800,6 +1096,11 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 	reg = &event->hw.branch_reg;
 	reg->idx = EXTRA_REG_LBR;
 
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
+		reg->config = mask;
+		return 0;
+	}
+
 	/*
 	 * The first 9 bits (LBR_SEL_MASK) in LBR_SELECT operate
 	 * in suppress mode. So LBR_SELECT should be set to
@@ -1056,6 +1357,27 @@ common_branch_type(int type)
 	return PERF_BR_UNKNOWN;
 }
 
+enum {
+	ARCH_LBR_BR_TYPE_JCC			= 0,
+	ARCH_LBR_BR_TYPE_NEAR_IND_JMP		= 1,
+	ARCH_LBR_BR_TYPE_NEAR_REL_JMP		= 2,
+	ARCH_LBR_BR_TYPE_NEAR_IND_CALL		= 3,
+	ARCH_LBR_BR_TYPE_NEAR_REL_CALL		= 4,
+	ARCH_LBR_BR_TYPE_NEAR_RET		= 5,
+	ARCH_LBR_BR_TYPE_KNOWN_MAX		= ARCH_LBR_BR_TYPE_NEAR_RET,
+
+	ARCH_LBR_BR_TYPE_MAP_MAX		= 16,
+};
+
+static const int arch_lbr_br_type_map[ARCH_LBR_BR_TYPE_MAP_MAX] = {
+	[ARCH_LBR_BR_TYPE_JCC]			= X86_BR_JCC,
+	[ARCH_LBR_BR_TYPE_NEAR_IND_JMP]		= X86_BR_IND_JMP,
+	[ARCH_LBR_BR_TYPE_NEAR_REL_JMP]		= X86_BR_JMP,
+	[ARCH_LBR_BR_TYPE_NEAR_IND_CALL]	= X86_BR_IND_CALL,
+	[ARCH_LBR_BR_TYPE_NEAR_REL_CALL]	= X86_BR_CALL,
+	[ARCH_LBR_BR_TYPE_NEAR_RET]		= X86_BR_RET,
+};
+
 /*
  * implement actual branch filter based on user demand.
  * Hardware may not exactly satisfy that request, thus
@@ -1068,7 +1390,7 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 {
 	u64 from, to;
 	int br_sel = cpuc->br_sel;
-	int i, j, type;
+	int i, j, type, to_plm;
 	bool compress = false;
 
 	/* if sampling all branches, then nothing to filter */
@@ -1080,8 +1402,19 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 
 		from = cpuc->lbr_entries[i].from;
 		to = cpuc->lbr_entries[i].to;
+		type = cpuc->lbr_entries[i].type;
 
-		type = branch_type(from, to, cpuc->lbr_entries[i].abort);
+		/*
+		 * Parse the branch type recorded in LBR_x_INFO MSR.
+		 * Doesn't support OTHER_BRANCH decoding for now.
+		 * OTHER_BRANCH branch type still rely on software decoding.
+		 */
+		if (static_cpu_has(X86_FEATURE_ARCH_LBR) &&
+		    type <= ARCH_LBR_BR_TYPE_KNOWN_MAX) {
+			to_plm = kernel_ip(to) ? X86_BR_KERNEL : X86_BR_USER;
+			type = arch_lbr_br_type_map[type] | to_plm;
+		} else
+			type = branch_type(from, to, cpuc->lbr_entries[i].abort);
 		if (type != X86_BR_NONE && (br_sel & X86_BR_ANYTX)) {
 			if (cpuc->lbr_entries[i].in_tx)
 				type |= X86_BR_IN_TX;
@@ -1116,32 +1449,18 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 	}
 }
 
-void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr)
+void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	int i;
-
-	cpuc->lbr_stack.nr = x86_pmu.lbr_nr;
 
-	/* Cannot get TOS for large PEBS */
-	if (cpuc->n_pebs == cpuc->n_large_pebs)
+	/* Cannot get TOS for large PEBS and Arch LBR */
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR) ||
+	    (cpuc->n_pebs == cpuc->n_large_pebs))
 		cpuc->lbr_stack.hw_idx = -1ULL;
 	else
 		cpuc->lbr_stack.hw_idx = intel_pmu_lbr_tos();
 
-	for (i = 0; i < x86_pmu.lbr_nr; i++) {
-		u64 info = lbr->lbr[i].info;
-		struct perf_branch_entry *e = &cpuc->lbr_entries[i];
-
-		e->from		= lbr->lbr[i].from;
-		e->to		= lbr->lbr[i].to;
-		e->mispred	= !!(info & LBR_INFO_MISPRED);
-		e->predicted	= !(info & LBR_INFO_MISPRED);
-		e->in_tx	= !!(info & LBR_INFO_IN_TX);
-		e->abort	= !!(info & LBR_INFO_ABORT);
-		e->cycles	= info & LBR_INFO_CYCLES;
-		e->reserved	= 0;
-	}
+	intel_pmu_store_lbr(cpuc, lbr);
 	intel_pmu_lbr_filter(cpuc);
 }
 
@@ -1198,6 +1517,26 @@ static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
 	[PERF_SAMPLE_BRANCH_CALL_SHIFT]		= LBR_REL_CALL,
 };
 
+static int arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
+	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= ARCH_LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= ARCH_LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= ARCH_LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= ARCH_LBR_RETURN |
+						  ARCH_LBR_OTHER_BRANCH,
+	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT]     = ARCH_LBR_REL_CALL |
+						  ARCH_LBR_IND_CALL |
+						  ARCH_LBR_OTHER_BRANCH,
+	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]     = ARCH_LBR_IND_CALL,
+	[PERF_SAMPLE_BRANCH_COND_SHIFT]         = ARCH_LBR_JCC,
+	[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT]   = ARCH_LBR_REL_CALL |
+						  ARCH_LBR_IND_CALL |
+						  ARCH_LBR_RETURN |
+						  ARCH_LBR_CALL_STACK,
+	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= ARCH_LBR_IND_JMP,
+	[PERF_SAMPLE_BRANCH_CALL_SHIFT]		= ARCH_LBR_REL_CALL,
+};
+
 /* core */
 void __init intel_pmu_lbr_init_core(void)
 {
@@ -1251,9 +1590,17 @@ void __init intel_pmu_lbr_init_snb(void)
 	 */
 }
 
+static inline struct kmem_cache *
+create_lbr_kmem_cache(size_t size, size_t align)
+{
+	return kmem_cache_create("x86_lbr", size, align, 0, NULL);
+}
+
 /* haswell */
 void intel_pmu_lbr_init_hsw(void)
 {
+	size_t size = sizeof(struct x86_perf_task_context);
+
 	x86_pmu.lbr_nr	 = 16;
 	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
 	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
@@ -1262,6 +1609,8 @@ void intel_pmu_lbr_init_hsw(void)
 	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
 	x86_pmu.lbr_sel_map  = hsw_lbr_sel_map;
 
+	x86_get_pmu()->task_ctx_cache = create_lbr_kmem_cache(size, 0);
+
 	if (lbr_from_signext_quirk_needed())
 		static_branch_enable(&lbr_from_quirk_key);
 }
@@ -1269,14 +1618,19 @@ void intel_pmu_lbr_init_hsw(void)
 /* skylake */
 __init void intel_pmu_lbr_init_skl(void)
 {
+	size_t size = sizeof(struct x86_perf_task_context);
+
 	x86_pmu.lbr_nr	 = 32;
 	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
 	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
 	x86_pmu.lbr_to   = MSR_LBR_NHM_TO;
+	x86_pmu.lbr_info = MSR_LBR_INFO_0;
 
 	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
 	x86_pmu.lbr_sel_map  = hsw_lbr_sel_map;
 
+	x86_get_pmu()->task_ctx_cache = create_lbr_kmem_cache(size, 0);
+
 	/*
 	 * SW branch filter usage:
 	 * - support syscall, sysret capture.
@@ -1343,3 +1697,152 @@ void intel_pmu_lbr_init_knl(void)
 	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_LIP)
 		x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS;
 }
+
+/*
+ * LBR state size is variable based on the max number of registers.
+ * This calculates the expected state size, which should match
+ * what the hardware enumerates for the size of XFEATURE_LBR.
+ */
+static inline unsigned int get_lbr_state_size(void)
+{
+	return sizeof(struct arch_lbr_state) +
+	       x86_pmu.lbr_nr * sizeof(struct lbr_entry);
+}
+
+static bool is_arch_lbr_xsave_available(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_XSAVES))
+		return false;
+
+	/*
+	 * Check the LBR state with the corresponding software structure.
+	 * Disable LBR XSAVES support if the size doesn't match.
+	 */
+	if (WARN_ON(xfeature_size(XFEATURE_LBR) != get_lbr_state_size()))
+		return false;
+
+	return true;
+}
+
+void __init intel_pmu_arch_lbr_init(void)
+{
+	struct pmu *pmu = x86_get_pmu();
+	union cpuid28_eax eax;
+	union cpuid28_ebx ebx;
+	union cpuid28_ecx ecx;
+	unsigned int unused_edx;
+	bool arch_lbr_xsave;
+	size_t size;
+	u64 lbr_nr;
+
+	/* Arch LBR Capabilities */
+	cpuid(28, &eax.full, &ebx.full, &ecx.full, &unused_edx);
+
+	lbr_nr = fls(eax.split.lbr_depth_mask) * 8;
+	if (!lbr_nr)
+		goto clear_arch_lbr;
+
+	/* Apply the max depth of Arch LBR */
+	if (wrmsrl_safe(MSR_ARCH_LBR_DEPTH, lbr_nr))
+		goto clear_arch_lbr;
+
+	x86_pmu.lbr_depth_mask = eax.split.lbr_depth_mask;
+	x86_pmu.lbr_deep_c_reset = eax.split.lbr_deep_c_reset;
+	x86_pmu.lbr_lip = eax.split.lbr_lip;
+	x86_pmu.lbr_cpl = ebx.split.lbr_cpl;
+	x86_pmu.lbr_filter = ebx.split.lbr_filter;
+	x86_pmu.lbr_call_stack = ebx.split.lbr_call_stack;
+	x86_pmu.lbr_mispred = ecx.split.lbr_mispred;
+	x86_pmu.lbr_timed_lbr = ecx.split.lbr_timed_lbr;
+	x86_pmu.lbr_br_type = ecx.split.lbr_br_type;
+	x86_pmu.lbr_nr = lbr_nr;
+
+
+	arch_lbr_xsave = is_arch_lbr_xsave_available();
+	if (arch_lbr_xsave) {
+		size = sizeof(struct x86_perf_task_context_arch_lbr_xsave) +
+		       get_lbr_state_size();
+		pmu->task_ctx_cache = create_lbr_kmem_cache(size,
+							    XSAVE_ALIGNMENT);
+	}
+
+	if (!pmu->task_ctx_cache) {
+		arch_lbr_xsave = false;
+
+		size = sizeof(struct x86_perf_task_context_arch_lbr) +
+		       lbr_nr * sizeof(struct lbr_entry);
+		pmu->task_ctx_cache = create_lbr_kmem_cache(size, 0);
+	}
+
+	x86_pmu.lbr_from = MSR_ARCH_LBR_FROM_0;
+	x86_pmu.lbr_to = MSR_ARCH_LBR_TO_0;
+	x86_pmu.lbr_info = MSR_ARCH_LBR_INFO_0;
+
+	/* LBR callstack requires both CPL and Branch Filtering support */
+	if (!x86_pmu.lbr_cpl ||
+	    !x86_pmu.lbr_filter ||
+	    !x86_pmu.lbr_call_stack)
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] = LBR_NOT_SUPP;
+
+	if (!x86_pmu.lbr_cpl) {
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_USER_SHIFT] = LBR_NOT_SUPP;
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_KERNEL_SHIFT] = LBR_NOT_SUPP;
+	} else if (!x86_pmu.lbr_filter) {
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_ANY_SHIFT] = LBR_NOT_SUPP;
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT] = LBR_NOT_SUPP;
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] = LBR_NOT_SUPP;
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_NOT_SUPP;
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_NOT_SUPP;
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_NOT_SUPP;
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_CALL_SHIFT] = LBR_NOT_SUPP;
+	}
+
+	x86_pmu.lbr_ctl_mask = ARCH_LBR_CTL_MASK;
+	x86_pmu.lbr_ctl_map  = arch_lbr_ctl_map;
+
+	if (!x86_pmu.lbr_cpl && !x86_pmu.lbr_filter)
+		x86_pmu.lbr_ctl_map = NULL;
+
+	x86_pmu.lbr_reset = intel_pmu_arch_lbr_reset;
+	if (arch_lbr_xsave) {
+		x86_pmu.lbr_save = intel_pmu_arch_lbr_xsaves;
+		x86_pmu.lbr_restore = intel_pmu_arch_lbr_xrstors;
+		x86_pmu.lbr_read = intel_pmu_arch_lbr_read_xsave;
+		pr_cont("XSAVE ");
+	} else {
+		x86_pmu.lbr_save = intel_pmu_arch_lbr_save;
+		x86_pmu.lbr_restore = intel_pmu_arch_lbr_restore;
+		x86_pmu.lbr_read = intel_pmu_arch_lbr_read;
+	}
+
+	pr_cont("Architectural LBR, ");
+
+	return;
+
+clear_arch_lbr:
+	clear_cpu_cap(&boot_cpu_data, X86_FEATURE_ARCH_LBR);
+}
+
+/**
+ * x86_perf_get_lbr - get the LBR records information
+ *
+ * @lbr: the caller's memory to store the LBR records information
+ *
+ * Returns: 0 indicates the LBR info has been successfully obtained
+ */
+int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
+{
+	int lbr_fmt = x86_pmu.intel_cap.lbr_format;
+
+	lbr->nr = x86_pmu.lbr_nr;
+	lbr->from = x86_pmu.lbr_from;
+	lbr->to = x86_pmu.lbr_to;
+	lbr->info = (lbr_fmt == LBR_FORMAT_INFO) ? x86_pmu.lbr_info : 0;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(x86_perf_get_lbr);
+
+struct event_constraint vlbr_constraint =
+	__EVENT_CONSTRAINT(INTEL_FIXED_VLBR_EVENT, (1ULL << INTEL_PMC_IDX_FIXED_VLBR),
+			  FIXED_EVENT_FLAGS, 1, 0, PERF_X86_EVENT_LBR_SELECT);
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index cf76d6631afa..d5c6d3b340c5 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -16,7 +16,7 @@ struct pci_driver *uncore_pci_driver;
 DEFINE_RAW_SPINLOCK(pci2phy_map_lock);
 struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head);
 struct pci_extra_dev *uncore_extra_pci_dev;
-static int max_dies;
+int __uncore_max_dies;
 
 /* mask of cpus that collect uncore events */
 static cpumask_t uncore_cpu_mask;
@@ -108,7 +108,7 @@ struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu
 	 * The unsigned check also catches the '-1' return value for non
 	 * existent mappings in the topology map.
 	 */
-	return dieid < max_dies ? pmu->boxes[dieid] : NULL;
+	return dieid < uncore_max_dies() ? pmu->boxes[dieid] : NULL;
 }
 
 u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
@@ -132,6 +132,9 @@ u64 uncore_mmio_read_counter(struct intel_uncore_box *box,
 	if (!box->io_addr)
 		return 0;
 
+	if (!uncore_mmio_is_valid_offset(box, event->hw.event_base))
+		return 0;
+
 	return readq(box->io_addr + event->hw.event_base);
 }
 
@@ -843,10 +846,12 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
 			.read		= uncore_pmu_event_read,
 			.module		= THIS_MODULE,
 			.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
+			.attr_update	= pmu->type->attr_update,
 		};
 	} else {
 		pmu->pmu = *pmu->type->pmu;
 		pmu->pmu.attr_groups = pmu->type->attr_groups;
+		pmu->pmu.attr_update = pmu->type->attr_update;
 	}
 
 	if (pmu->type->num_boxes == 1) {
@@ -877,7 +882,7 @@ static void uncore_free_boxes(struct intel_uncore_pmu *pmu)
 {
 	int die;
 
-	for (die = 0; die < max_dies; die++)
+	for (die = 0; die < uncore_max_dies(); die++)
 		kfree(pmu->boxes[die]);
 	kfree(pmu->boxes);
 }
@@ -887,6 +892,9 @@ static void uncore_type_exit(struct intel_uncore_type *type)
 	struct intel_uncore_pmu *pmu = type->pmus;
 	int i;
 
+	if (type->cleanup_mapping)
+		type->cleanup_mapping(type);
+
 	if (pmu) {
 		for (i = 0; i < type->num_boxes; i++, pmu++) {
 			uncore_pmu_unregister(pmu);
@@ -915,7 +923,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 	if (!pmus)
 		return -ENOMEM;
 
-	size = max_dies * sizeof(struct intel_uncore_box *);
+	size = uncore_max_dies() * sizeof(struct intel_uncore_box *);
 
 	for (i = 0; i < type->num_boxes; i++) {
 		pmus[i].func_id	= setid ? i : -1;
@@ -954,6 +962,9 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 
 	type->pmu_group = &uncore_pmu_attr_group;
 
+	if (type->set_mapping)
+		type->set_mapping(type);
+
 	return 0;
 
 err:
@@ -1112,7 +1123,7 @@ static int __init uncore_pci_init(void)
 	size_t size;
 	int ret;
 
-	size = max_dies * sizeof(struct pci_extra_dev);
+	size = uncore_max_dies() * sizeof(struct pci_extra_dev);
 	uncore_extra_pci_dev = kzalloc(size, GFP_KERNEL);
 	if (!uncore_extra_pci_dev) {
 		ret = -ENOMEM;
@@ -1514,6 +1525,8 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,		&skx_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L,		&skl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE,		&skl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&skl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&skl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&icl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_NNPI,	&icl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&icl_uncore_init),
@@ -1539,7 +1552,8 @@ static int __init intel_uncore_init(void)
 	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		return -ENODEV;
 
-	max_dies = topology_max_packages() * topology_max_die_per_package();
+	__uncore_max_dies =
+		topology_max_packages() * topology_max_die_per_package();
 
 	uncore_init = (struct intel_uncore_init_fun *)id->driver_data;
 	if (uncore_init->pci_init) {
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index b469ddd45515..105fdc69825e 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -61,6 +61,7 @@ struct intel_uncore_type {
 		unsigned msr_offset;
 		unsigned mmio_offset;
 	};
+	unsigned mmio_map_size;
 	unsigned num_shared_regs:8;
 	unsigned single_fixed:1;
 	unsigned pair_ctr_ctl:1;
@@ -72,7 +73,19 @@ struct intel_uncore_type {
 	struct uncore_event_desc *event_descs;
 	struct freerunning_counters *freerunning;
 	const struct attribute_group *attr_groups[4];
+	const struct attribute_group **attr_update;
 	struct pmu *pmu; /* for custom pmu ops */
+	/*
+	 * Uncore PMU would store relevant platform topology configuration here
+	 * to identify which platform component each PMON block of that type is
+	 * supposed to monitor.
+	 */
+	u64 *topology;
+	/*
+	 * Optional callbacks for managing mapping of Uncore units to PMONs
+	 */
+	int (*set_mapping)(struct intel_uncore_type *type);
+	void (*cleanup_mapping)(struct intel_uncore_type *type);
 };
 
 #define pmu_group attr_groups[0]
@@ -169,6 +182,18 @@ int uncore_pcibus_to_physid(struct pci_bus *bus);
 ssize_t uncore_event_show(struct kobject *kobj,
 			  struct kobj_attribute *attr, char *buf);
 
+static inline struct intel_uncore_pmu *dev_to_uncore_pmu(struct device *dev)
+{
+	return container_of(dev_get_drvdata(dev), struct intel_uncore_pmu, pmu);
+}
+
+#define to_device_attribute(n)	container_of(n, struct device_attribute, attr)
+#define to_dev_ext_attribute(n)	container_of(n, struct dev_ext_attribute, attr)
+#define attr_to_ext_attr(n)	to_dev_ext_attribute(to_device_attribute(n))
+
+extern int __uncore_max_dies;
+#define uncore_max_dies()	(__uncore_max_dies)
+
 #define INTEL_UNCORE_EVENT_DESC(_name, _config)			\
 {								\
 	.attr	= __ATTR(_name, 0444, uncore_event_show, NULL),	\
@@ -196,6 +221,18 @@ static inline bool uncore_pmc_freerunning(int idx)
 	return idx == UNCORE_PMC_IDX_FREERUNNING;
 }
 
+static inline bool uncore_mmio_is_valid_offset(struct intel_uncore_box *box,
+					       unsigned long offset)
+{
+	if (offset < box->pmu->type->mmio_map_size)
+		return true;
+
+	pr_warn_once("perf uncore: Invalid offset 0x%lx exceeds mapped area of %s.\n",
+		     offset, box->pmu->type->name);
+
+	return false;
+}
+
 static inline
 unsigned int uncore_mmio_box_ctl(struct intel_uncore_box *box)
 {
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 3de1065eefc4..cb94ba86efd2 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -42,6 +42,17 @@
 #define PCI_DEVICE_ID_INTEL_WHL_UQ_IMC		0x3ed0
 #define PCI_DEVICE_ID_INTEL_WHL_4_UQ_IMC	0x3e34
 #define PCI_DEVICE_ID_INTEL_WHL_UD_IMC		0x3e35
+#define PCI_DEVICE_ID_INTEL_CML_H1_IMC		0x9b44
+#define PCI_DEVICE_ID_INTEL_CML_H2_IMC		0x9b54
+#define PCI_DEVICE_ID_INTEL_CML_H3_IMC		0x9b64
+#define PCI_DEVICE_ID_INTEL_CML_U1_IMC		0x9b51
+#define PCI_DEVICE_ID_INTEL_CML_U2_IMC		0x9b61
+#define PCI_DEVICE_ID_INTEL_CML_U3_IMC		0x9b71
+#define PCI_DEVICE_ID_INTEL_CML_S1_IMC		0x9b33
+#define PCI_DEVICE_ID_INTEL_CML_S2_IMC		0x9b43
+#define PCI_DEVICE_ID_INTEL_CML_S3_IMC		0x9b53
+#define PCI_DEVICE_ID_INTEL_CML_S4_IMC		0x9b63
+#define PCI_DEVICE_ID_INTEL_CML_S5_IMC		0x9b73
 #define PCI_DEVICE_ID_INTEL_ICL_U_IMC		0x8a02
 #define PCI_DEVICE_ID_INTEL_ICL_U2_IMC		0x8a12
 #define PCI_DEVICE_ID_INTEL_TGL_U1_IMC		0x9a02
@@ -415,6 +426,7 @@ static const struct attribute_group snb_uncore_imc_format_group = {
 
 static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
 {
+	struct intel_uncore_type *type = box->pmu->type;
 	struct pci_dev *pdev = box->pci_dev;
 	int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET;
 	resource_size_t addr;
@@ -430,7 +442,10 @@ static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
 
 	addr &= ~(PAGE_SIZE - 1);
 
-	box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
+	box->io_addr = ioremap(addr, type->mmio_map_size);
+	if (!box->io_addr)
+		pr_warn("perf uncore: Failed to ioremap for %s.\n", type->name);
+
 	box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
 }
 
@@ -586,6 +601,7 @@ static struct intel_uncore_type snb_uncore_imc = {
 	.num_counters   = 2,
 	.num_boxes	= 1,
 	.num_freerunning_types	= SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX,
+	.mmio_map_size	= SNB_UNCORE_PCI_IMC_MAP_SIZE,
 	.freerunning	= snb_uncore_imc_freerunning,
 	.event_descs	= snb_uncore_imc_events,
 	.format_group	= &snb_uncore_imc_format_group,
@@ -771,6 +787,50 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_UD_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_H1_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_H2_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_H3_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_U1_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_U2_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_U3_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S1_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S2_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S3_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S4_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S5_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 	{ /* end: all zeroes */ },
 };
 
@@ -863,6 +923,17 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(WHL_UQ_IMC, &skl_uncore_pci_driver),	/* 8th Gen Core U Mobile Quad Core */
 	IMC_DEV(WHL_4_UQ_IMC, &skl_uncore_pci_driver),	/* 8th Gen Core U Mobile Quad Core */
 	IMC_DEV(WHL_UD_IMC, &skl_uncore_pci_driver),	/* 8th Gen Core U Mobile Dual Core */
+	IMC_DEV(CML_H1_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_H2_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_H3_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_U1_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_U2_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_U3_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_S1_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_S2_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_S3_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_S4_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_S5_IMC, &skl_uncore_pci_driver),
 	IMC_DEV(ICL_U_IMC, &icl_uncore_pci_driver),	/* 10th Gen Core Mobile */
 	IMC_DEV(ICL_U2_IMC, &icl_uncore_pci_driver),	/* 10th Gen Core Mobile */
 	{  /* end marker */ }
@@ -1085,11 +1156,13 @@ static struct pci_dev *tgl_uncore_get_mc_dev(void)
 }
 
 #define TGL_UNCORE_MMIO_IMC_MEM_OFFSET		0x10000
+#define TGL_UNCORE_PCI_IMC_MAP_SIZE		0xe000
 
 static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box)
 {
 	struct pci_dev *pdev = tgl_uncore_get_mc_dev();
 	struct intel_uncore_pmu *pmu = box->pmu;
+	struct intel_uncore_type *type = pmu->type;
 	resource_size_t addr;
 	u32 mch_bar;
 
@@ -1112,7 +1185,9 @@ static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box)
 	addr |= ((resource_size_t)mch_bar << 32);
 #endif
 
-	box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
+	box->io_addr = ioremap(addr, type->mmio_map_size);
+	if (!box->io_addr)
+		pr_warn("perf uncore: Failed to ioremap for %s.\n", type->name);
 }
 
 static struct intel_uncore_ops tgl_uncore_imc_freerunning_ops = {
@@ -1138,6 +1213,7 @@ static struct intel_uncore_type tgl_uncore_imc_free_running = {
 	.num_counters		= 3,
 	.num_boxes		= 2,
 	.num_freerunning_types	= TGL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX,
+	.mmio_map_size		= TGL_UNCORE_PCI_IMC_MAP_SIZE,
 	.freerunning		= tgl_uncore_imc_freerunning,
 	.ops			= &tgl_uncore_imc_freerunning_ops,
 	.event_descs		= tgl_uncore_imc_events,
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 07652fa20ebb..62e88ad919ff 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -273,6 +273,30 @@
 #define SKX_CPUNODEID			0xc0
 #define SKX_GIDNIDMAP			0xd4
 
+/*
+ * The CPU_BUS_NUMBER MSR returns the values of the respective CPUBUSNO CSR
+ * that BIOS programmed. MSR has package scope.
+ * |  Bit  |  Default  |  Description
+ * | [63]  |    00h    | VALID - When set, indicates the CPU bus
+ *                       numbers have been initialized. (RO)
+ * |[62:48]|    ---    | Reserved
+ * |[47:40]|    00h    | BUS_NUM_5 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(5). (RO)
+ * |[39:32]|    00h    | BUS_NUM_4 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(4). (RO)
+ * |[31:24]|    00h    | BUS_NUM_3 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(3). (RO)
+ * |[23:16]|    00h    | BUS_NUM_2 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(2). (RO)
+ * |[15:8] |    00h    | BUS_NUM_1 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(1). (RO)
+ * | [7:0] |    00h    | BUS_NUM_0 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(0). (RO)
+ */
+#define SKX_MSR_CPU_BUS_NUMBER		0x300
+#define SKX_MSR_CPU_BUS_VALID_BIT	(1ULL << 63)
+#define BUS_NUM_STRIDE			8
+
 /* SKX CHA */
 #define SKX_CHA_MSR_PMON_BOX_FILTER_TID		(0x1ffULL << 0)
 #define SKX_CHA_MSR_PMON_BOX_FILTER_LINK	(0xfULL << 9)
@@ -3612,6 +3636,170 @@ static struct intel_uncore_ops skx_uncore_iio_ops = {
 	.read_counter		= uncore_msr_read_counter,
 };
 
+static inline u8 skx_iio_stack(struct intel_uncore_pmu *pmu, int die)
+{
+	return pmu->type->topology[die] >> (pmu->pmu_idx * BUS_NUM_STRIDE);
+}
+
+static umode_t
+skx_iio_mapping_visible(struct kobject *kobj, struct attribute *attr, int die)
+{
+	struct intel_uncore_pmu *pmu = dev_to_uncore_pmu(kobj_to_dev(kobj));
+
+	/* Root bus 0x00 is valid only for die 0 AND pmu_idx = 0. */
+	return (!skx_iio_stack(pmu, die) && pmu->pmu_idx) ? 0 : attr->mode;
+}
+
+static ssize_t skx_iio_mapping_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct pci_bus *bus = pci_find_next_bus(NULL);
+	struct intel_uncore_pmu *uncore_pmu = dev_to_uncore_pmu(dev);
+	struct dev_ext_attribute *ea = to_dev_ext_attribute(attr);
+	long die = (long)ea->var;
+
+	/*
+	 * Current implementation is for single segment configuration hence it's
+	 * safe to take the segment value from the first available root bus.
+	 */
+	return sprintf(buf, "%04x:%02x\n", pci_domain_nr(bus),
+					   skx_iio_stack(uncore_pmu, die));
+}
+
+static int skx_msr_cpu_bus_read(int cpu, u64 *topology)
+{
+	u64 msr_value;
+
+	if (rdmsrl_on_cpu(cpu, SKX_MSR_CPU_BUS_NUMBER, &msr_value) ||
+			!(msr_value & SKX_MSR_CPU_BUS_VALID_BIT))
+		return -ENXIO;
+
+	*topology = msr_value;
+
+	return 0;
+}
+
+static int die_to_cpu(int die)
+{
+	int res = 0, cpu, current_die;
+	/*
+	 * Using cpus_read_lock() to ensure cpu is not going down between
+	 * looking at cpu_online_mask.
+	 */
+	cpus_read_lock();
+	for_each_online_cpu(cpu) {
+		current_die = topology_logical_die_id(cpu);
+		if (current_die == die) {
+			res = cpu;
+			break;
+		}
+	}
+	cpus_read_unlock();
+	return res;
+}
+
+static int skx_iio_get_topology(struct intel_uncore_type *type)
+{
+	int i, ret;
+	struct pci_bus *bus = NULL;
+
+	/*
+	 * Verified single-segment environments only; disabled for multiple
+	 * segment topologies for now except VMD domains.
+	 * VMD domains start at 0x10000 to not clash with ACPI _SEG domains.
+	 */
+	while ((bus = pci_find_next_bus(bus))
+		&& (!pci_domain_nr(bus) || pci_domain_nr(bus) > 0xffff))
+		;
+	if (bus)
+		return -EPERM;
+
+	type->topology = kcalloc(uncore_max_dies(), sizeof(u64), GFP_KERNEL);
+	if (!type->topology)
+		return -ENOMEM;
+
+	for (i = 0; i < uncore_max_dies(); i++) {
+		ret = skx_msr_cpu_bus_read(die_to_cpu(i), &type->topology[i]);
+		if (ret) {
+			kfree(type->topology);
+			type->topology = NULL;
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static struct attribute_group skx_iio_mapping_group = {
+	.is_visible	= skx_iio_mapping_visible,
+};
+
+static const struct attribute_group *skx_iio_attr_update[] = {
+	&skx_iio_mapping_group,
+	NULL,
+};
+
+static int skx_iio_set_mapping(struct intel_uncore_type *type)
+{
+	char buf[64];
+	int ret;
+	long die = -1;
+	struct attribute **attrs = NULL;
+	struct dev_ext_attribute *eas = NULL;
+
+	ret = skx_iio_get_topology(type);
+	if (ret)
+		return ret;
+
+	/* One more for NULL. */
+	attrs = kcalloc((uncore_max_dies() + 1), sizeof(*attrs), GFP_KERNEL);
+	if (!attrs)
+		goto err;
+
+	eas = kcalloc(uncore_max_dies(), sizeof(*eas), GFP_KERNEL);
+	if (!eas)
+		goto err;
+
+	for (die = 0; die < uncore_max_dies(); die++) {
+		sprintf(buf, "die%ld", die);
+		sysfs_attr_init(&eas[die].attr.attr);
+		eas[die].attr.attr.name = kstrdup(buf, GFP_KERNEL);
+		if (!eas[die].attr.attr.name)
+			goto err;
+		eas[die].attr.attr.mode = 0444;
+		eas[die].attr.show = skx_iio_mapping_show;
+		eas[die].attr.store = NULL;
+		eas[die].var = (void *)die;
+		attrs[die] = &eas[die].attr.attr;
+	}
+	skx_iio_mapping_group.attrs = attrs;
+
+	return 0;
+err:
+	for (; die >= 0; die--)
+		kfree(eas[die].attr.attr.name);
+	kfree(eas);
+	kfree(attrs);
+	kfree(type->topology);
+	type->attr_update = NULL;
+	return -ENOMEM;
+}
+
+static void skx_iio_cleanup_mapping(struct intel_uncore_type *type)
+{
+	struct attribute **attr = skx_iio_mapping_group.attrs;
+
+	if (!attr)
+		return;
+
+	for (; *attr; attr++)
+		kfree((*attr)->name);
+	kfree(attr_to_ext_attr(*skx_iio_mapping_group.attrs));
+	kfree(skx_iio_mapping_group.attrs);
+	skx_iio_mapping_group.attrs = NULL;
+	kfree(type->topology);
+}
+
 static struct intel_uncore_type skx_uncore_iio = {
 	.name			= "iio",
 	.num_counters		= 4,
@@ -3626,6 +3814,9 @@ static struct intel_uncore_type skx_uncore_iio = {
 	.constraints		= skx_uncore_iio_constraints,
 	.ops			= &skx_uncore_iio_ops,
 	.format_group		= &skx_uncore_iio_format_group,
+	.attr_update		= skx_iio_attr_update,
+	.set_mapping		= skx_iio_set_mapping,
+	.cleanup_mapping	= skx_iio_cleanup_mapping,
 };
 
 enum perf_uncore_iio_freerunning_type_id {
@@ -4421,6 +4612,7 @@ static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box,
 				       unsigned int box_ctl, int mem_offset)
 {
 	struct pci_dev *pdev = snr_uncore_get_mc_dev(box->dieid);
+	struct intel_uncore_type *type = box->pmu->type;
 	resource_size_t addr;
 	u32 pci_dword;
 
@@ -4435,9 +4627,11 @@ static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box,
 
 	addr += box_ctl;
 
-	box->io_addr = ioremap(addr, SNR_IMC_MMIO_SIZE);
-	if (!box->io_addr)
+	box->io_addr = ioremap(addr, type->mmio_map_size);
+	if (!box->io_addr) {
+		pr_warn("perf uncore: Failed to ioremap for %s.\n", type->name);
 		return;
+	}
 
 	writel(IVBEP_PMON_BOX_CTL_INT, box->io_addr);
 }
@@ -4480,6 +4674,9 @@ static void snr_uncore_mmio_enable_event(struct intel_uncore_box *box,
 	if (!box->io_addr)
 		return;
 
+	if (!uncore_mmio_is_valid_offset(box, hwc->config_base))
+		return;
+
 	writel(hwc->config | SNBEP_PMON_CTL_EN,
 	       box->io_addr + hwc->config_base);
 }
@@ -4492,6 +4689,9 @@ static void snr_uncore_mmio_disable_event(struct intel_uncore_box *box,
 	if (!box->io_addr)
 		return;
 
+	if (!uncore_mmio_is_valid_offset(box, hwc->config_base))
+		return;
+
 	writel(hwc->config, box->io_addr + hwc->config_base);
 }
 
@@ -4530,6 +4730,7 @@ static struct intel_uncore_type snr_uncore_imc = {
 	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,
 	.box_ctl	= SNR_IMC_MMIO_PMON_BOX_CTL,
 	.mmio_offset	= SNR_IMC_MMIO_OFFSET,
+	.mmio_map_size	= SNR_IMC_MMIO_SIZE,
 	.ops		= &snr_uncore_mmio_ops,
 	.format_group	= &skx_uncore_format_group,
 };
@@ -4570,6 +4771,7 @@ static struct intel_uncore_type snr_uncore_imc_free_running = {
 	.num_counters		= 3,
 	.num_boxes		= 1,
 	.num_freerunning_types	= SNR_IMC_FREERUNNING_TYPE_MAX,
+	.mmio_map_size		= SNR_IMC_MMIO_SIZE,
 	.freerunning		= snr_imc_freerunning,
 	.ops			= &snr_uncore_imc_freerunning_ops,
 	.event_descs		= snr_uncore_imc_freerunning_events,
@@ -4987,6 +5189,7 @@ static struct intel_uncore_type icx_uncore_imc = {
 	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,
 	.box_ctl	= SNR_IMC_MMIO_PMON_BOX_CTL,
 	.mmio_offset	= SNR_IMC_MMIO_OFFSET,
+	.mmio_map_size	= SNR_IMC_MMIO_SIZE,
 	.ops		= &icx_uncore_mmio_ops,
 	.format_group	= &skx_uncore_format_group,
 };
@@ -5044,6 +5247,7 @@ static struct intel_uncore_type icx_uncore_imc_free_running = {
 	.num_counters		= 5,
 	.num_boxes		= 4,
 	.num_freerunning_types	= ICX_IMC_FREERUNNING_TYPE_MAX,
+	.mmio_map_size		= SNR_IMC_MMIO_SIZE,
 	.freerunning		= icx_imc_freerunning,
 	.ops			= &icx_uncore_imc_freerunning_ops,
 	.event_descs		= icx_uncore_imc_freerunning_events,
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index e17a3d8a47ed..7b68ab5f19e7 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -78,6 +78,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode)
 #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 */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -179,6 +180,17 @@ struct x86_perf_task_context;
 #define MAX_LBR_ENTRIES		32
 
 enum {
+	LBR_FORMAT_32		= 0x00,
+	LBR_FORMAT_LIP		= 0x01,
+	LBR_FORMAT_EIP		= 0x02,
+	LBR_FORMAT_EIP_FLAGS	= 0x03,
+	LBR_FORMAT_EIP_FLAGS2	= 0x04,
+	LBR_FORMAT_INFO		= 0x05,
+	LBR_FORMAT_TIME		= 0x06,
+	LBR_FORMAT_MAX_KNOWN    = LBR_FORMAT_TIME,
+};
+
+enum {
 	X86_PERF_KFREE_SHARED = 0,
 	X86_PERF_KFREE_EXCL   = 1,
 	X86_PERF_KFREE_MAX
@@ -233,10 +245,15 @@ struct cpu_hw_events {
 	int				lbr_pebs_users;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
-	struct er_account		*lbr_sel;
+	union {
+		struct er_account		*lbr_sel;
+		struct er_account		*lbr_ctl;
+	};
 	u64				br_sel;
-	struct x86_perf_task_context	*last_task_ctx;
+	void				*last_task_ctx;
 	int				last_log_id;
+	int				lbr_select;
+	void				*lbr_xsave;
 
 	/*
 	 * Intel host/guest exclude bits
@@ -673,14 +690,38 @@ struct x86_pmu {
 	/*
 	 * Intel LBR
 	 */
-	unsigned long	lbr_tos, lbr_from, lbr_to; /* MSR base regs       */
-	int		lbr_nr;			   /* hardware stack size */
-	u64		lbr_sel_mask;		   /* LBR_SELECT valid bits */
-	const int	*lbr_sel_map;		   /* lbr_select mappings */
+	unsigned int	lbr_tos, lbr_from, lbr_to,
+			lbr_info, lbr_nr;	   /* LBR base regs and size */
+	union {
+		u64	lbr_sel_mask;		   /* LBR_SELECT valid bits */
+		u64	lbr_ctl_mask;		   /* LBR_CTL valid bits */
+	};
+	union {
+		const int	*lbr_sel_map;	   /* lbr_select mappings */
+		int		*lbr_ctl_map;	   /* LBR_CTL mappings */
+	};
 	bool		lbr_double_abort;	   /* duplicated lbr aborts */
 	bool		lbr_pt_coexist;		   /* (LBR|BTS) may coexist with PT */
 
 	/*
+	 * Intel Architectural LBR CPUID Enumeration
+	 */
+	unsigned int	lbr_depth_mask:8;
+	unsigned int	lbr_deep_c_reset:1;
+	unsigned int	lbr_lip:1;
+	unsigned int	lbr_cpl:1;
+	unsigned int	lbr_filter:1;
+	unsigned int	lbr_call_stack:1;
+	unsigned int	lbr_mispred:1;
+	unsigned int	lbr_timed_lbr:1;
+	unsigned int	lbr_br_type:1;
+
+	void		(*lbr_reset)(void);
+	void		(*lbr_read)(struct cpu_hw_events *cpuc);
+	void		(*lbr_save)(void *ctx);
+	void		(*lbr_restore)(void *ctx);
+
+	/*
 	 * Intel PT/LBR/BTS are exclusive
 	 */
 	atomic_t	lbr_exclusive[x86_lbr_exclusive_max];
@@ -718,17 +759,46 @@ struct x86_pmu {
 	int (*aux_output_match) (struct perf_event *event);
 };
 
-struct x86_perf_task_context {
-	u64 lbr_from[MAX_LBR_ENTRIES];
-	u64 lbr_to[MAX_LBR_ENTRIES];
-	u64 lbr_info[MAX_LBR_ENTRIES];
-	int tos;
-	int valid_lbrs;
+struct x86_perf_task_context_opt {
 	int lbr_callstack_users;
 	int lbr_stack_state;
 	int log_id;
 };
 
+struct x86_perf_task_context {
+	u64 lbr_sel;
+	int tos;
+	int valid_lbrs;
+	struct x86_perf_task_context_opt opt;
+	struct lbr_entry lbr[MAX_LBR_ENTRIES];
+};
+
+struct x86_perf_task_context_arch_lbr {
+	struct x86_perf_task_context_opt opt;
+	struct lbr_entry entries[];
+};
+
+/*
+ * Add padding to guarantee the 64-byte alignment of the state buffer.
+ *
+ * The structure is dynamically allocated. The size of the LBR state may vary
+ * based on the number of LBR registers.
+ *
+ * Do not put anything after the LBR state.
+ */
+struct x86_perf_task_context_arch_lbr_xsave {
+	struct x86_perf_task_context_opt		opt;
+
+	union {
+		struct xregs_state			xsave;
+		struct {
+			struct fxregs_state		i387;
+			struct xstate_header		header;
+			struct arch_lbr_state		lbr;
+		} __attribute__ ((packed, aligned (XSAVE_ALIGNMENT)));
+	};
+};
+
 #define x86_add_quirk(func_)						\
 do {									\
 	static struct x86_pmu_quirk __quirk __initdata = {		\
@@ -777,6 +847,14 @@ static struct perf_pmu_events_ht_attr event_attr_##v = {		\
 struct pmu *x86_get_pmu(void);
 extern struct x86_pmu x86_pmu __read_mostly;
 
+static __always_inline struct x86_perf_task_context_opt *task_context_opt(void *ctx)
+{
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
+		return &((struct x86_perf_task_context_arch_lbr *)ctx)->opt;
+
+	return &((struct x86_perf_task_context *)ctx)->opt;
+}
+
 static inline bool x86_pmu_has_lbr_callstack(void)
 {
 	return  x86_pmu.lbr_sel_map &&
@@ -989,7 +1067,10 @@ void release_ds_buffers(void);
 
 void reserve_ds_buffers(void);
 
+void release_lbr_buffers(void);
+
 extern struct event_constraint bts_constraint;
+extern struct event_constraint vlbr_constraint;
 
 void intel_pmu_enable_bts(u64 config);
 
@@ -1041,7 +1122,7 @@ void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
 
 void intel_pmu_auto_reload_read(struct perf_event *event);
 
-void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr);
+void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
 
 void intel_ds_init(void);
 
@@ -1054,6 +1135,10 @@ u64 lbr_from_signext_quirk_wr(u64 val);
 
 void intel_pmu_lbr_reset(void);
 
+void intel_pmu_lbr_reset_32(void);
+
+void intel_pmu_lbr_reset_64(void);
+
 void intel_pmu_lbr_add(struct perf_event *event);
 
 void intel_pmu_lbr_del(struct perf_event *event);
@@ -1064,6 +1149,14 @@ void intel_pmu_lbr_disable_all(void);
 
 void intel_pmu_lbr_read(void);
 
+void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc);
+
+void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc);
+
+void intel_pmu_lbr_save(void *ctx);
+
+void intel_pmu_lbr_restore(void *ctx);
+
 void intel_pmu_lbr_init_core(void);
 
 void intel_pmu_lbr_init_nhm(void);
@@ -1080,6 +1173,8 @@ void intel_pmu_lbr_init_skl(void);
 
 void intel_pmu_lbr_init_knl(void);
 
+void intel_pmu_arch_lbr_init(void);
+
 void intel_pmu_pebs_data_source_nhm(void);
 
 void intel_pmu_pebs_data_source_skl(bool pmem);
@@ -1115,6 +1210,10 @@ static inline void release_ds_buffers(void)
 {
 }
 
+static inline void release_lbr_buffers(void)
+{
+}
+
 static inline int intel_pmu_init(void)
 {
 	return 0;
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 0f2bf59f4354..68b38820b10e 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -787,7 +787,8 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&model_hsx),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&model_skl),
-	X86_MATCH_VENDOR_FAM(AMD, 0x17, &model_amd_fam17h),
+	X86_MATCH_VENDOR_FAM(AMD,	0x17,		&model_amd_fam17h),
+	X86_MATCH_VENDOR_FAM(HYGON,	0x18,		&model_amd_fam17h),
 	{},
 };
 MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
diff --git a/arch/x86/events/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c
index 898fa1ae9ceb..e68827e604ad 100644
--- a/arch/x86/events/zhaoxin/core.c
+++ b/arch/x86/events/zhaoxin/core.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Zhoaxin PMU; like Intel Architectural PerfMon-v2
+ * Zhaoxin PMU; like Intel Architectural PerfMon-v2
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 02dabc9e77b0..72ba4c59ad05 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -366,6 +366,7 @@
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
+#define X86_FEATURE_ARCH_LBR		(18*32+19) /* Intel ARCH LBR */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 845e7481ab77..6b10cdaa7c96 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -274,7 +274,7 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
  */
 static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
 {
-	u64 mask = -1;
+	u64 mask = xfeatures_mask_all;
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
 	int err;
@@ -320,7 +320,7 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
  */
 static inline void copy_xregs_to_kernel(struct xregs_state *xstate)
 {
-	u64 mask = -1;
+	u64 mask = xfeatures_mask_all;
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
 	int err;
@@ -356,6 +356,9 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask)
  */
 static inline int copy_xregs_to_user(struct xregs_state __user *buf)
 {
+	u64 mask = xfeatures_mask_user();
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
 	int err;
 
 	/*
@@ -367,7 +370,7 @@ static inline int copy_xregs_to_user(struct xregs_state __user *buf)
 		return -EFAULT;
 
 	stac();
-	XSTATE_OP(XSAVE, buf, -1, -1, err);
+	XSTATE_OP(XSAVE, buf, lmask, hmask, err);
 	clac();
 
 	return err;
@@ -408,43 +411,7 @@ static inline int copy_kernel_to_xregs_err(struct xregs_state *xstate, u64 mask)
 	return err;
 }
 
-/*
- * These must be called with preempt disabled. Returns
- * 'true' if the FPU state is still intact and we can
- * keep registers active.
- *
- * The legacy FNSAVE instruction cleared all FPU state
- * unconditionally, so registers are essentially destroyed.
- * Modern FPU state can be kept in registers, if there are
- * no pending FP exceptions.
- */
-static inline int copy_fpregs_to_fpstate(struct fpu *fpu)
-{
-	if (likely(use_xsave())) {
-		copy_xregs_to_kernel(&fpu->state.xsave);
-
-		/*
-		 * AVX512 state is tracked here because its use is
-		 * known to slow the max clock speed of the core.
-		 */
-		if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512)
-			fpu->avx512_timestamp = jiffies;
-		return 1;
-	}
-
-	if (likely(use_fxsr())) {
-		copy_fxregs_to_kernel(fpu);
-		return 1;
-	}
-
-	/*
-	 * Legacy FPU register saving, FNSAVE always clears FPU registers,
-	 * so we have to mark them inactive:
-	 */
-	asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave));
-
-	return 0;
-}
+extern int copy_fpregs_to_fpstate(struct fpu *fpu);
 
 static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask)
 {
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index f098f6cab94b..c87364ea6446 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -114,6 +114,12 @@ enum xfeature {
 	XFEATURE_Hi16_ZMM,
 	XFEATURE_PT_UNIMPLEMENTED_SO_FAR,
 	XFEATURE_PKRU,
+	XFEATURE_RSRVD_COMP_10,
+	XFEATURE_RSRVD_COMP_11,
+	XFEATURE_RSRVD_COMP_12,
+	XFEATURE_RSRVD_COMP_13,
+	XFEATURE_RSRVD_COMP_14,
+	XFEATURE_LBR,
 
 	XFEATURE_MAX,
 };
@@ -128,6 +134,7 @@ enum xfeature {
 #define XFEATURE_MASK_Hi16_ZMM		(1 << XFEATURE_Hi16_ZMM)
 #define XFEATURE_MASK_PT		(1 << XFEATURE_PT_UNIMPLEMENTED_SO_FAR)
 #define XFEATURE_MASK_PKRU		(1 << XFEATURE_PKRU)
+#define XFEATURE_MASK_LBR		(1 << XFEATURE_LBR)
 
 #define XFEATURE_MASK_FPSSE		(XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
 #define XFEATURE_MASK_AVX512		(XFEATURE_MASK_OPMASK \
@@ -229,6 +236,26 @@ struct pkru_state {
 	u32				pad;
 } __packed;
 
+/*
+ * State component 15: Architectural LBR configuration state.
+ * The size of Arch LBR state depends on the number of LBRs (lbr_depth).
+ */
+
+struct lbr_entry {
+	u64 from;
+	u64 to;
+	u64 info;
+};
+
+struct arch_lbr_state {
+	u64 lbr_ctl;
+	u64 lbr_depth;
+	u64 ler_from;
+	u64 ler_to;
+	u64 ler_info;
+	struct lbr_entry		entries[];
+} __packed;
+
 struct xstate_header {
 	u64				xfeatures;
 	u64				xcomp_bv;
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 422d8369012a..1559554af931 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -21,6 +21,8 @@
 #define XSAVE_YMM_SIZE	    256
 #define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
 
+#define XSAVE_ALIGNMENT     64
+
 /* All currently supported user features */
 #define XFEATURE_MASK_USER_SUPPORTED (XFEATURE_MASK_FP | \
 				      XFEATURE_MASK_SSE | \
@@ -36,6 +38,27 @@
 #define XFEATURE_MASK_SUPERVISOR_SUPPORTED (0)
 
 /*
+ * A supervisor state component may not always contain valuable information,
+ * and its size may be huge. Saving/restoring such supervisor state components
+ * at each context switch can cause high CPU and space overhead, which should
+ * be avoided. Such supervisor state components should only be saved/restored
+ * on demand. The on-demand dynamic supervisor features are set in this mask.
+ *
+ * Unlike the existing supported supervisor features, a dynamic supervisor
+ * feature does not allocate a buffer in task->fpu, and the corresponding
+ * supervisor state component cannot be saved/restored at each context switch.
+ *
+ * To support a dynamic supervisor feature, a developer should follow the
+ * dos and don'ts as below:
+ * - Do dynamically allocate a buffer for the supervisor state component.
+ * - Do manually invoke the XSAVES/XRSTORS instruction to save/restore the
+ *   state component to/from the buffer.
+ * - Don't set the bit corresponding to the dynamic supervisor feature in
+ *   IA32_XSS at run time, since it has been set at boot time.
+ */
+#define XFEATURE_MASK_DYNAMIC (XFEATURE_MASK_LBR)
+
+/*
  * Unsupported supervisor features. When a supervisor feature in this mask is
  * supported in the future, move it to the supported supervisor feature mask.
  */
@@ -43,6 +66,7 @@
 
 /* All supervisor states including supported and unsupported states. */
 #define XFEATURE_MASK_SUPERVISOR_ALL (XFEATURE_MASK_SUPERVISOR_SUPPORTED | \
+				      XFEATURE_MASK_DYNAMIC | \
 				      XFEATURE_MASK_SUPERVISOR_UNSUPPORTED)
 
 #ifdef CONFIG_X86_64
@@ -63,6 +87,14 @@ static inline u64 xfeatures_mask_user(void)
 	return xfeatures_mask_all & XFEATURE_MASK_USER_SUPPORTED;
 }
 
+static inline u64 xfeatures_mask_dynamic(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_ARCH_LBR))
+		return XFEATURE_MASK_DYNAMIC & ~XFEATURE_MASK_LBR;
+
+	return XFEATURE_MASK_DYNAMIC;
+}
+
 extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 
 extern void __init update_regset_xstate_info(unsigned int size,
@@ -71,11 +103,15 @@ extern void __init update_regset_xstate_info(unsigned int size,
 void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
 const void *get_xsave_field_ptr(int xfeature_nr);
 int using_compacted_format(void);
+int xfeature_size(int xfeature_nr);
 int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
 int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
 int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf);
 int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf);
 void copy_supervisor_to_kernel(struct xregs_state *xsave);
+void copy_dynamic_supervisor_to_kernel(struct xregs_state *xstate, u64 mask);
+void copy_kernel_to_dynamic_supervisor(struct xregs_state *xstate, u64 mask);
+
 
 /* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
 int validate_user_xstate_header(const struct xstate_header *hdr);
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 073eb7ad2f56..143bc9abe99c 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -66,6 +66,8 @@ struct arch_specific_insn {
 	 */
 	bool boostable;
 	bool if_modifier;
+	/* Number of bytes of text poked */
+	int tp_len;
 };
 
 struct arch_optimized_insn {
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e8370e64a155..bdc07fc6e517 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -158,7 +158,23 @@
 #define LBR_INFO_MISPRED		BIT_ULL(63)
 #define LBR_INFO_IN_TX			BIT_ULL(62)
 #define LBR_INFO_ABORT			BIT_ULL(61)
+#define LBR_INFO_CYC_CNT_VALID		BIT_ULL(60)
 #define LBR_INFO_CYCLES			0xffff
+#define LBR_INFO_BR_TYPE_OFFSET		56
+#define LBR_INFO_BR_TYPE		(0xfull << LBR_INFO_BR_TYPE_OFFSET)
+
+#define MSR_ARCH_LBR_CTL		0x000014ce
+#define ARCH_LBR_CTL_LBREN		BIT(0)
+#define ARCH_LBR_CTL_CPL_OFFSET		1
+#define ARCH_LBR_CTL_CPL		(0x3ull << ARCH_LBR_CTL_CPL_OFFSET)
+#define ARCH_LBR_CTL_STACK_OFFSET	3
+#define ARCH_LBR_CTL_STACK		(0x1ull << ARCH_LBR_CTL_STACK_OFFSET)
+#define ARCH_LBR_CTL_FILTER_OFFSET	16
+#define ARCH_LBR_CTL_FILTER		(0x7full << ARCH_LBR_CTL_FILTER_OFFSET)
+#define MSR_ARCH_LBR_DEPTH		0x000014cf
+#define MSR_ARCH_LBR_FROM_0		0x00001500
+#define MSR_ARCH_LBR_TO_0		0x00001600
+#define MSR_ARCH_LBR_INFO_0		0x00001200
 
 #define MSR_IA32_PEBS_ENABLE		0x000003f1
 #define MSR_PEBS_DATA_CFG		0x000003f2
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index e855e9cf2c37..0c1b13720525 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -142,6 +142,46 @@ union cpuid10_edx {
 	unsigned int full;
 };
 
+/*
+ * Intel Architectural LBR CPUID detection/enumeration details:
+ */
+union cpuid28_eax {
+	struct {
+		/* Supported LBR depth values */
+		unsigned int	lbr_depth_mask:8;
+		unsigned int	reserved:22;
+		/* Deep C-state Reset */
+		unsigned int	lbr_deep_c_reset:1;
+		/* IP values contain LIP */
+		unsigned int	lbr_lip:1;
+	} split;
+	unsigned int		full;
+};
+
+union cpuid28_ebx {
+	struct {
+		/* CPL Filtering Supported */
+		unsigned int    lbr_cpl:1;
+		/* Branch Filtering Supported */
+		unsigned int    lbr_filter:1;
+		/* Call-stack Mode Supported */
+		unsigned int    lbr_call_stack:1;
+	} split;
+	unsigned int            full;
+};
+
+union cpuid28_ecx {
+	struct {
+		/* Mispredict Bit Supported */
+		unsigned int    lbr_mispred:1;
+		/* Timed LBRs Supported */
+		unsigned int    lbr_timed_lbr:1;
+		/* Branch Type Field Supported */
+		unsigned int    lbr_br_type:1;
+	} split;
+	unsigned int            full;
+};
+
 struct x86_pmu_capability {
 	int		version;
 	int		num_counters_gp;
@@ -192,10 +232,30 @@ struct x86_pmu_capability {
 #define GLOBAL_STATUS_UNC_OVF				BIT_ULL(61)
 #define GLOBAL_STATUS_ASIF				BIT_ULL(60)
 #define GLOBAL_STATUS_COUNTERS_FROZEN			BIT_ULL(59)
-#define GLOBAL_STATUS_LBRS_FROZEN			BIT_ULL(58)
+#define GLOBAL_STATUS_LBRS_FROZEN_BIT			58
+#define GLOBAL_STATUS_LBRS_FROZEN			BIT_ULL(GLOBAL_STATUS_LBRS_FROZEN_BIT)
 #define GLOBAL_STATUS_TRACE_TOPAPMI			BIT_ULL(55)
 
 /*
+ * We model guest LBR event tracing as another fixed-mode PMC like BTS.
+ *
+ * We choose bit 58 because it's used to indicate LBR stack frozen state
+ * for architectural perfmon v4, also we unconditionally mask that bit in
+ * the handle_pmi_common(), so it'll never be set in the overflow handling.
+ *
+ * With this fake counter assigned, the guest LBR event user (such as KVM),
+ * can program the LBR registers on its own, and we don't actually do anything
+ * with then in the host context.
+ */
+#define INTEL_PMC_IDX_FIXED_VLBR	(GLOBAL_STATUS_LBRS_FROZEN_BIT)
+
+/*
+ * Pseudo-encoding the guest LBR event as event=0x00,umask=0x1b,
+ * since it would claim bit 58 which is effectively Fixed26.
+ */
+#define INTEL_FIXED_VLBR_EVENT	0x1b00
+
+/*
  * Adaptive PEBS v4
  */
 
@@ -222,14 +282,6 @@ struct pebs_xmm {
 	u64 xmm[16*2];	/* two entries for each register */
 };
 
-struct pebs_lbr_entry {
-	u64 from, to, info;
-};
-
-struct pebs_lbr {
-	struct pebs_lbr_entry lbr[0]; /* Variable length */
-};
-
 /*
  * IBS cpuid feature detection
  */
@@ -333,6 +385,13 @@ struct perf_guest_switch_msr {
 	u64 host, guest;
 };
 
+struct x86_pmu_lbr {
+	unsigned int	nr;
+	unsigned int	from;
+	unsigned int	to;
+	unsigned int	info;
+};
+
 extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
 extern void perf_check_microcode(void);
 extern int x86_perf_rdpmc_index(struct perf_event *event);
@@ -348,12 +407,17 @@ static inline void perf_check_microcode(void) { }
 
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
 extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
+extern int x86_perf_get_lbr(struct x86_pmu_lbr *lbr);
 #else
 static inline struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
 {
 	*nr = 0;
 	return NULL;
 }
+static inline int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
+{
+	return -1;
+}
 #endif
 
 #ifdef CONFIG_CPU_SUP_INTEL
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 8fd39ff74a49..f94c9f371411 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -3,6 +3,7 @@
 
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/perf_event.h>
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/stringify.h>
@@ -1001,6 +1002,7 @@ struct text_poke_loc {
 	s32 rel32;
 	u8 opcode;
 	const u8 text[POKE_MAX_OPCODE_SIZE];
+	u8 old;
 };
 
 struct bp_patching_desc {
@@ -1168,8 +1170,10 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	/*
 	 * First step: add a int3 trap to the address that will be patched.
 	 */
-	for (i = 0; i < nr_entries; i++)
+	for (i = 0; i < nr_entries; i++) {
+		tp[i].old = *(u8 *)text_poke_addr(&tp[i]);
 		text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE);
+	}
 
 	text_poke_sync();
 
@@ -1177,14 +1181,45 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	 * Second step: update all but the first byte of the patched range.
 	 */
 	for (do_sync = 0, i = 0; i < nr_entries; i++) {
+		u8 old[POKE_MAX_OPCODE_SIZE] = { tp[i].old, };
 		int len = text_opcode_size(tp[i].opcode);
 
 		if (len - INT3_INSN_SIZE > 0) {
+			memcpy(old + INT3_INSN_SIZE,
+			       text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
+			       len - INT3_INSN_SIZE);
 			text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
 				  (const char *)tp[i].text + INT3_INSN_SIZE,
 				  len - INT3_INSN_SIZE);
 			do_sync++;
 		}
+
+		/*
+		 * Emit a perf event to record the text poke, primarily to
+		 * support Intel PT decoding which must walk the executable code
+		 * to reconstruct the trace. The flow up to here is:
+		 *   - write INT3 byte
+		 *   - IPI-SYNC
+		 *   - write instruction tail
+		 * At this point the actual control flow will be through the
+		 * INT3 and handler and not hit the old or new instruction.
+		 * Intel PT outputs FUP/TIP packets for the INT3, so the flow
+		 * can still be decoded. Subsequently:
+		 *   - emit RECORD_TEXT_POKE with the new instruction
+		 *   - IPI-SYNC
+		 *   - write first byte
+		 *   - IPI-SYNC
+		 * So before the text poke event timestamp, the decoder will see
+		 * either the old instruction flow or FUP/TIP of INT3. After the
+		 * text poke event timestamp, the decoder will see either the
+		 * new instruction flow or FUP/TIP of INT3. Thus decoders can
+		 * use the timestamp as the point at which to modify the
+		 * executable code.
+		 * The old instruction is recorded so that the event can be
+		 * processed forwards or backwards.
+		 */
+		perf_event_text_poke(text_poke_addr(&tp[i]), old, len,
+				     tp[i].text, len);
 	}
 
 	if (do_sync) {
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 15247b96c6ea..eb86a2b831b1 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -82,6 +82,45 @@ bool irq_fpu_usable(void)
 }
 EXPORT_SYMBOL(irq_fpu_usable);
 
+/*
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact and we can
+ * keep registers active.
+ *
+ * The legacy FNSAVE instruction cleared all FPU state
+ * unconditionally, so registers are essentially destroyed.
+ * Modern FPU state can be kept in registers, if there are
+ * no pending FP exceptions.
+ */
+int copy_fpregs_to_fpstate(struct fpu *fpu)
+{
+	if (likely(use_xsave())) {
+		copy_xregs_to_kernel(&fpu->state.xsave);
+
+		/*
+		 * AVX512 state is tracked here because its use is
+		 * known to slow the max clock speed of the core.
+		 */
+		if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512)
+			fpu->avx512_timestamp = jiffies;
+		return 1;
+	}
+
+	if (likely(use_fxsr())) {
+		copy_fxregs_to_kernel(fpu);
+		return 1;
+	}
+
+	/*
+	 * Legacy FPU register saving, FNSAVE always clears FPU registers,
+	 * so we have to mark them inactive:
+	 */
+	asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave));
+
+	return 0;
+}
+EXPORT_SYMBOL(copy_fpregs_to_fpstate);
+
 void kernel_fpu_begin(void)
 {
 	preempt_disable();
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index ad3a2b37927d..be2a68a09d19 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -233,8 +233,10 @@ void fpu__init_cpu_xstate(void)
 	/*
 	 * MSR_IA32_XSS sets supervisor states managed by XSAVES.
 	 */
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
+	if (boot_cpu_has(X86_FEATURE_XSAVES)) {
+		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
+				     xfeatures_mask_dynamic());
+	}
 }
 
 static bool xfeature_enabled(enum xfeature xfeature)
@@ -486,7 +488,7 @@ static int xfeature_uncompacted_offset(int xfeature_nr)
 	return ebx;
 }
 
-static int xfeature_size(int xfeature_nr)
+int xfeature_size(int xfeature_nr)
 {
 	u32 eax, ebx, ecx, edx;
 
@@ -598,7 +600,8 @@ static void check_xstate_against_struct(int nr)
 	 */
 	if ((nr < XFEATURE_YMM) ||
 	    (nr >= XFEATURE_MAX) ||
-	    (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR)) {
+	    (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) ||
+	    ((nr >= XFEATURE_RSRVD_COMP_10) && (nr <= XFEATURE_LBR))) {
 		WARN_ONCE(1, "no structure for xstate: %d\n", nr);
 		XSTATE_WARN_ON(1);
 	}
@@ -847,8 +850,10 @@ void fpu__resume_cpu(void)
 	 * Restore IA32_XSS. The same CPUID bit enumerates support
 	 * of XSAVES and MSR_IA32_XSS.
 	 */
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
+	if (boot_cpu_has(X86_FEATURE_XSAVES)) {
+		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()  |
+				     xfeatures_mask_dynamic());
+	}
 }
 
 /*
@@ -1356,6 +1361,78 @@ void copy_supervisor_to_kernel(struct xregs_state *xstate)
 	}
 }
 
+/**
+ * copy_dynamic_supervisor_to_kernel() - Save dynamic supervisor states to
+ *                                       an xsave area
+ * @xstate: A pointer to an xsave area
+ * @mask: Represent the dynamic supervisor features saved into the xsave area
+ *
+ * Only the dynamic supervisor states sets in the mask are saved into the xsave
+ * area (See the comment in XFEATURE_MASK_DYNAMIC for the details of dynamic
+ * supervisor feature). Besides the dynamic supervisor states, the legacy
+ * region and XSAVE header are also saved into the xsave area. The supervisor
+ * features in the XFEATURE_MASK_SUPERVISOR_SUPPORTED and
+ * XFEATURE_MASK_SUPERVISOR_UNSUPPORTED are not saved.
+ *
+ * The xsave area must be 64-bytes aligned.
+ */
+void copy_dynamic_supervisor_to_kernel(struct xregs_state *xstate, u64 mask)
+{
+	u64 dynamic_mask = xfeatures_mask_dynamic() & mask;
+	u32 lmask, hmask;
+	int err;
+
+	if (WARN_ON_FPU(!boot_cpu_has(X86_FEATURE_XSAVES)))
+		return;
+
+	if (WARN_ON_FPU(!dynamic_mask))
+		return;
+
+	lmask = dynamic_mask;
+	hmask = dynamic_mask >> 32;
+
+	XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
+
+	/* Should never fault when copying to a kernel buffer */
+	WARN_ON_FPU(err);
+}
+
+/**
+ * copy_kernel_to_dynamic_supervisor() - Restore dynamic supervisor states from
+ *                                       an xsave area
+ * @xstate: A pointer to an xsave area
+ * @mask: Represent the dynamic supervisor features restored from the xsave area
+ *
+ * Only the dynamic supervisor states sets in the mask are restored from the
+ * xsave area (See the comment in XFEATURE_MASK_DYNAMIC for the details of
+ * dynamic supervisor feature). Besides the dynamic supervisor states, the
+ * legacy region and XSAVE header are also restored from the xsave area. The
+ * supervisor features in the XFEATURE_MASK_SUPERVISOR_SUPPORTED and
+ * XFEATURE_MASK_SUPERVISOR_UNSUPPORTED are not restored.
+ *
+ * The xsave area must be 64-bytes aligned.
+ */
+void copy_kernel_to_dynamic_supervisor(struct xregs_state *xstate, u64 mask)
+{
+	u64 dynamic_mask = xfeatures_mask_dynamic() & mask;
+	u32 lmask, hmask;
+	int err;
+
+	if (WARN_ON_FPU(!boot_cpu_has(X86_FEATURE_XSAVES)))
+		return;
+
+	if (WARN_ON_FPU(!dynamic_mask))
+		return;
+
+	lmask = dynamic_mask;
+	hmask = dynamic_mask >> 32;
+
+	XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
+
+	/* Should never fault when copying from a kernel buffer */
+	WARN_ON_FPU(err);
+}
+
 #ifdef CONFIG_PROC_PID_ARCH_STATUS
 /*
  * Report the amount of time elapsed in millisecond since last AVX512
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index ada39ddbc922..fdadc37d72af 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -33,6 +33,7 @@
 #include <linux/hardirq.h>
 #include <linux/preempt.h>
 #include <linux/sched/debug.h>
+#include <linux/perf_event.h>
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
@@ -472,6 +473,9 @@ static int arch_copy_kprobe(struct kprobe *p)
 	/* Also, displacement change doesn't affect the first byte */
 	p->opcode = buf[0];
 
+	p->ainsn.tp_len = len;
+	perf_event_text_poke(p->ainsn.insn, NULL, 0, buf, len);
+
 	/* OK, write back the instruction(s) into ROX insn buffer */
 	text_poke(p->ainsn.insn, buf, len);
 
@@ -503,12 +507,18 @@ int arch_prepare_kprobe(struct kprobe *p)
 
 void arch_arm_kprobe(struct kprobe *p)
 {
-	text_poke(p->addr, ((unsigned char []){INT3_INSN_OPCODE}), 1);
+	u8 int3 = INT3_INSN_OPCODE;
+
+	text_poke(p->addr, &int3, 1);
 	text_poke_sync();
+	perf_event_text_poke(p->addr, &p->opcode, 1, &int3, 1);
 }
 
 void arch_disarm_kprobe(struct kprobe *p)
 {
+	u8 int3 = INT3_INSN_OPCODE;
+
+	perf_event_text_poke(p->addr, &int3, 1, &p->opcode, 1);
 	text_poke(p->addr, &p->opcode, 1);
 	text_poke_sync();
 }
@@ -516,6 +526,9 @@ void arch_disarm_kprobe(struct kprobe *p)
 void arch_remove_kprobe(struct kprobe *p)
 {
 	if (p->ainsn.insn) {
+		/* Record the perf event before freeing the slot */
+		perf_event_text_poke(p->ainsn.insn, p->ainsn.insn,
+				     p->ainsn.tp_len, NULL, 0);
 		free_insn_slot(p->ainsn.insn, p->ainsn.boostable);
 		p->ainsn.insn = NULL;
 	}
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 7af4c61dde52..40f380461e6d 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -6,6 +6,7 @@
  * Copyright (C) Hitachi Ltd., 2012
  */
 #include <linux/kprobes.h>
+#include <linux/perf_event.h>
 #include <linux/ptrace.h>
 #include <linux/string.h>
 #include <linux/slab.h>
@@ -352,8 +353,15 @@ int arch_within_optimized_kprobe(struct optimized_kprobe *op,
 static
 void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
 {
-	if (op->optinsn.insn) {
-		free_optinsn_slot(op->optinsn.insn, dirty);
+	u8 *slot = op->optinsn.insn;
+	if (slot) {
+		int len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE;
+
+		/* Record the perf event before freeing the slot */
+		if (dirty)
+			perf_event_text_poke(slot, slot, len, NULL, 0);
+
+		free_optinsn_slot(slot, dirty);
 		op->optinsn.insn = NULL;
 		op->optinsn.size = 0;
 	}
@@ -424,8 +432,15 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
 			   (u8 *)op->kp.addr + op->optinsn.size);
 	len += JMP32_INSN_SIZE;
 
+	/*
+	 * Note	len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE is also
+	 * used in __arch_remove_optimized_kprobe().
+	 */
+
 	/* We have to use text_poke() for instruction buffer because it is RO */
+	perf_event_text_poke(slot, NULL, 0, buf, len);
 	text_poke(slot, buf, len);
+
 	ret = 0;
 out:
 	kfree(buf);
@@ -477,10 +492,23 @@ void arch_optimize_kprobes(struct list_head *oplist)
  */
 void arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
-	arch_arm_kprobe(&op->kp);
-	text_poke(op->kp.addr + INT3_INSN_SIZE,
-		  op->optinsn.copied_insn, DISP32_SIZE);
+	u8 new[JMP32_INSN_SIZE] = { INT3_INSN_OPCODE, };
+	u8 old[JMP32_INSN_SIZE];
+	u8 *addr = op->kp.addr;
+
+	memcpy(old, op->kp.addr, JMP32_INSN_SIZE);
+	memcpy(new + INT3_INSN_SIZE,
+	       op->optinsn.copied_insn,
+	       JMP32_INSN_SIZE - INT3_INSN_SIZE);
+
+	text_poke(addr, new, INT3_INSN_SIZE);
 	text_poke_sync();
+	text_poke(addr + INT3_INSN_SIZE,
+		  new + INT3_INSN_SIZE,
+		  JMP32_INSN_SIZE - INT3_INSN_SIZE);
+	text_poke_sync();
+
+	perf_event_text_poke(op->kp.addr, old, JMP32_INSN_SIZE, new, JMP32_INSN_SIZE);
 }
 
 /*
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index e339dac91ee6..ce2c06f72e86 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -58,9 +58,6 @@ struct ftrace_direct_func;
 const char *
 ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
 		   unsigned long *off, char **modname, char *sym);
-int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
-			   char *type, char *name,
-			   char *module_name, int *exported);
 #else
 static inline const char *
 ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
@@ -68,6 +65,13 @@ ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
 {
 	return NULL;
 }
+#endif
+
+#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
+int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
+			   char *type, char *name,
+			   char *module_name, int *exported);
+#else
 static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
 					 char *type, char *name,
 					 char *module_name, int *exported)
@@ -76,7 +80,6 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val
 }
 #endif
 
-
 #ifdef CONFIG_FUNCTION_TRACER
 
 extern int ftrace_enabled;
@@ -207,6 +210,7 @@ struct ftrace_ops {
 	struct ftrace_ops_hash		old_hash;
 	unsigned long			trampoline;
 	unsigned long			trampoline_size;
+	struct list_head		list;
 #endif
 };
 
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 6adf90f248d7..45b8cdc9fad7 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -242,6 +242,7 @@ struct kprobe_insn_cache {
 	struct mutex mutex;
 	void *(*alloc)(void);	/* allocate insn page */
 	void (*free)(void *);	/* free insn page */
+	const char *sym;	/* symbol for insn pages */
 	struct list_head pages; /* list of kprobe_insn_page */
 	size_t insn_size;	/* size of instruction slot */
 	int nr_garbage;
@@ -272,6 +273,10 @@ static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
 {									\
 	return __is_insn_slot_addr(&kprobe_##__name##_slots, addr);	\
 }
+#define KPROBE_INSN_PAGE_SYM		"kprobe_insn_page"
+#define KPROBE_OPTINSN_PAGE_SYM		"kprobe_optinsn_page"
+int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
+			     unsigned long *value, char *type, char *sym);
 #else /* __ARCH_WANT_KPROBES_INSN_SLOT */
 #define DEFINE_INSN_CACHE_OPS(__name)					\
 static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
@@ -377,6 +382,11 @@ void dump_kprobe(struct kprobe *kp);
 void *alloc_insn_page(void);
 void free_insn_page(void *page);
 
+int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		       char *sym);
+
+int arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
+			    char *type, char *sym);
 #else /* !CONFIG_KPROBES: */
 
 static inline int kprobes_built_in(void)
@@ -439,6 +449,11 @@ static inline bool within_kprobe_blacklist(unsigned long addr)
 {
 	return true;
 }
+static inline int kprobe_get_kallsym(unsigned int symnum, unsigned long *value,
+				     char *type, char *sym)
+{
+	return -ERANGE;
+}
 #endif /* CONFIG_KPROBES */
 static inline int disable_kretprobe(struct kretprobe *rp)
 {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b4bb32082342..0edd257a5916 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -366,7 +366,7 @@ struct pmu {
 	 * ->stop() with PERF_EF_UPDATE will read the counter and update
 	 *  period/count values like ->read() would.
 	 *
-	 * ->start() with PERF_EF_RELOAD will reprogram the the counter
+	 * ->start() with PERF_EF_RELOAD will reprogram the counter
 	 *  value, must be preceded by a ->stop() with PERF_EF_UPDATE.
 	 */
 	void (*start)			(struct perf_event *event, int flags);
@@ -419,10 +419,11 @@ struct pmu {
 	 */
 	void (*sched_task)		(struct perf_event_context *ctx,
 					bool sched_in);
+
 	/*
-	 * PMU specific data size
+	 * Kmem cache of PMU specific data
 	 */
-	size_t				task_ctx_size;
+	struct kmem_cache		*task_ctx_cache;
 
 	/*
 	 * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data)
@@ -1232,6 +1233,9 @@ extern void perf_event_exec(void);
 extern void perf_event_comm(struct task_struct *tsk, bool exec);
 extern void perf_event_namespaces(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
+extern void perf_event_text_poke(const void *addr,
+				 const void *old_bytes, size_t old_len,
+				 const void *new_bytes, size_t new_len);
 
 /* Callchains */
 DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
@@ -1479,6 +1483,11 @@ static inline void perf_event_exec(void)				{ }
 static inline void perf_event_comm(struct task_struct *tsk, bool exec)	{ }
 static inline void perf_event_namespaces(struct task_struct *tsk)	{ }
 static inline void perf_event_fork(struct task_struct *tsk)		{ }
+static inline void perf_event_text_poke(const void *addr,
+					const void *old_bytes,
+					size_t old_len,
+					const void *new_bytes,
+					size_t new_len)			{ }
 static inline void perf_event_init(void)				{ }
 static inline int  perf_swevent_get_recursion_context(void)		{ return -1; }
 static inline void perf_swevent_put_recursion_context(int rctx)		{ }
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 21a1edd08cbe..077e7ee69e3d 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -383,7 +383,8 @@ struct perf_event_attr {
 				bpf_event      :  1, /* include bpf events */
 				aux_output     :  1, /* generate AUX records instead of events */
 				cgroup         :  1, /* include cgroup events */
-				__reserved_1   : 31;
+				text_poke      :  1, /* include text poke events */
+				__reserved_1   : 30;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -1041,12 +1042,35 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_CGROUP			= 19,
 
+	/*
+	 * Records changes to kernel text i.e. self-modified code. 'old_len' is
+	 * the number of old bytes, 'new_len' is the number of new bytes. Either
+	 * 'old_len' or 'new_len' may be zero to indicate, for example, the
+	 * addition or removal of a trampoline. 'bytes' contains the old bytes
+	 * followed immediately by the new bytes.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				addr;
+	 *	u16				old_len;
+	 *	u16				new_len;
+	 *	u8				bytes[];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_TEXT_POKE			= 20,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
 enum perf_record_ksymbol_type {
 	PERF_RECORD_KSYMBOL_TYPE_UNKNOWN	= 0,
 	PERF_RECORD_KSYMBOL_TYPE_BPF		= 1,
+	/*
+	 * Out of line code such as kprobe-replaced instructions or optimized
+	 * kprobes or ftrace trampolines.
+	 */
+	PERF_RECORD_KSYMBOL_TYPE_OOL		= 2,
 	PERF_RECORD_KSYMBOL_TYPE_MAX		/* non-ABI */
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 856d98c36f56..7c436d705fbd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -394,6 +394,7 @@ static atomic_t nr_switch_events __read_mostly;
 static atomic_t nr_ksymbol_events __read_mostly;
 static atomic_t nr_bpf_events __read_mostly;
 static atomic_t nr_cgroup_events __read_mostly;
+static atomic_t nr_text_poke_events __read_mostly;
 
 static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
@@ -1237,12 +1238,26 @@ static void get_ctx(struct perf_event_context *ctx)
 	refcount_inc(&ctx->refcount);
 }
 
+static void *alloc_task_ctx_data(struct pmu *pmu)
+{
+	if (pmu->task_ctx_cache)
+		return kmem_cache_zalloc(pmu->task_ctx_cache, GFP_KERNEL);
+
+	return NULL;
+}
+
+static void free_task_ctx_data(struct pmu *pmu, void *task_ctx_data)
+{
+	if (pmu->task_ctx_cache && task_ctx_data)
+		kmem_cache_free(pmu->task_ctx_cache, task_ctx_data);
+}
+
 static void free_ctx(struct rcu_head *head)
 {
 	struct perf_event_context *ctx;
 
 	ctx = container_of(head, struct perf_event_context, rcu_head);
-	kfree(ctx->task_ctx_data);
+	free_task_ctx_data(ctx->pmu, ctx->task_ctx_data);
 	kfree(ctx);
 }
 
@@ -4470,7 +4485,7 @@ find_get_context(struct pmu *pmu, struct task_struct *task,
 		goto errout;
 
 	if (event->attach_state & PERF_ATTACH_TASK_DATA) {
-		task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL);
+		task_ctx_data = alloc_task_ctx_data(pmu);
 		if (!task_ctx_data) {
 			err = -ENOMEM;
 			goto errout;
@@ -4528,11 +4543,11 @@ retry:
 		}
 	}
 
-	kfree(task_ctx_data);
+	free_task_ctx_data(pmu, task_ctx_data);
 	return ctx;
 
 errout:
-	kfree(task_ctx_data);
+	free_task_ctx_data(pmu, task_ctx_data);
 	return ERR_PTR(err);
 }
 
@@ -4575,7 +4590,7 @@ static bool is_sb_event(struct perf_event *event)
 	if (attr->mmap || attr->mmap_data || attr->mmap2 ||
 	    attr->comm || attr->comm_exec ||
 	    attr->task || attr->ksymbol ||
-	    attr->context_switch ||
+	    attr->context_switch || attr->text_poke ||
 	    attr->bpf_event)
 		return true;
 	return false;
@@ -4651,6 +4666,8 @@ static void unaccount_event(struct perf_event *event)
 		atomic_dec(&nr_ksymbol_events);
 	if (event->attr.bpf_event)
 		atomic_dec(&nr_bpf_events);
+	if (event->attr.text_poke)
+		atomic_dec(&nr_text_poke_events);
 
 	if (dec) {
 		if (!atomic_add_unless(&perf_sched_count, -1, 1))
@@ -8628,6 +8645,89 @@ void perf_event_bpf_event(struct bpf_prog *prog,
 	perf_iterate_sb(perf_event_bpf_output, &bpf_event, NULL);
 }
 
+struct perf_text_poke_event {
+	const void		*old_bytes;
+	const void		*new_bytes;
+	size_t			pad;
+	u16			old_len;
+	u16			new_len;
+
+	struct {
+		struct perf_event_header	header;
+
+		u64				addr;
+	} event_id;
+};
+
+static int perf_event_text_poke_match(struct perf_event *event)
+{
+	return event->attr.text_poke;
+}
+
+static void perf_event_text_poke_output(struct perf_event *event, void *data)
+{
+	struct perf_text_poke_event *text_poke_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	u64 padding = 0;
+	int ret;
+
+	if (!perf_event_text_poke_match(event))
+		return;
+
+	perf_event_header__init_id(&text_poke_event->event_id.header, &sample, event);
+
+	ret = perf_output_begin(&handle, event, text_poke_event->event_id.header.size);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, text_poke_event->event_id);
+	perf_output_put(&handle, text_poke_event->old_len);
+	perf_output_put(&handle, text_poke_event->new_len);
+
+	__output_copy(&handle, text_poke_event->old_bytes, text_poke_event->old_len);
+	__output_copy(&handle, text_poke_event->new_bytes, text_poke_event->new_len);
+
+	if (text_poke_event->pad)
+		__output_copy(&handle, &padding, text_poke_event->pad);
+
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+}
+
+void perf_event_text_poke(const void *addr, const void *old_bytes,
+			  size_t old_len, const void *new_bytes, size_t new_len)
+{
+	struct perf_text_poke_event text_poke_event;
+	size_t tot, pad;
+
+	if (!atomic_read(&nr_text_poke_events))
+		return;
+
+	tot  = sizeof(text_poke_event.old_len) + old_len;
+	tot += sizeof(text_poke_event.new_len) + new_len;
+	pad  = ALIGN(tot, sizeof(u64)) - tot;
+
+	text_poke_event = (struct perf_text_poke_event){
+		.old_bytes    = old_bytes,
+		.new_bytes    = new_bytes,
+		.pad          = pad,
+		.old_len      = old_len,
+		.new_len      = new_len,
+		.event_id  = {
+			.header = {
+				.type = PERF_RECORD_TEXT_POKE,
+				.misc = PERF_RECORD_MISC_KERNEL,
+				.size = sizeof(text_poke_event.event_id) + tot + pad,
+			},
+			.addr = (unsigned long)addr,
+		},
+	};
+
+	perf_iterate_sb(perf_event_text_poke_output, &text_poke_event, NULL);
+}
+
 void perf_event_itrace_started(struct perf_event *event)
 {
 	event->attach_state |= PERF_ATTACH_ITRACE;
@@ -10945,6 +11045,8 @@ static void account_event(struct perf_event *event)
 		atomic_inc(&nr_ksymbol_events);
 	if (event->attr.bpf_event)
 		atomic_inc(&nr_bpf_events);
+	if (event->attr.text_poke)
+		atomic_inc(&nr_text_poke_events);
 
 	if (inc) {
 		/*
@@ -12409,8 +12511,7 @@ inherit_event(struct perf_event *parent_event,
 	    !child_ctx->task_ctx_data) {
 		struct pmu *pmu = child_event->pmu;
 
-		child_ctx->task_ctx_data = kzalloc(pmu->task_ctx_size,
-						   GFP_KERNEL);
+		child_ctx->task_ctx_data = alloc_task_ctx_data(pmu);
 		if (!child_ctx->task_ctx_data) {
 			free_event(child_event);
 			return ERR_PTR(-ENOMEM);
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index bb14e64f62a4..95cb74f73292 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/filter.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 #include <linux/compiler.h>
 
 /*
@@ -437,6 +438,7 @@ struct kallsym_iter {
 	loff_t pos_arch_end;
 	loff_t pos_mod_end;
 	loff_t pos_ftrace_mod_end;
+	loff_t pos_bpf_end;
 	unsigned long value;
 	unsigned int nameoff; /* If iterating in core kernel symbols. */
 	char type;
@@ -480,6 +482,11 @@ static int get_ksymbol_mod(struct kallsym_iter *iter)
 	return 1;
 }
 
+/*
+ * ftrace_mod_get_kallsym() may also get symbols for pages allocated for ftrace
+ * purposes. In that case "__builtin__ftrace" is used as a module name, even
+ * though "__builtin__ftrace" is not a module.
+ */
 static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 {
 	int ret = ftrace_mod_get_kallsym(iter->pos - iter->pos_mod_end,
@@ -496,11 +503,33 @@ static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 
 static int get_ksymbol_bpf(struct kallsym_iter *iter)
 {
+	int ret;
+
 	strlcpy(iter->module_name, "bpf", MODULE_NAME_LEN);
 	iter->exported = 0;
-	return bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
-			       &iter->value, &iter->type,
-			       iter->name) < 0 ? 0 : 1;
+	ret = bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
+			      &iter->value, &iter->type,
+			      iter->name);
+	if (ret < 0) {
+		iter->pos_bpf_end = iter->pos;
+		return 0;
+	}
+
+	return 1;
+}
+
+/*
+ * This uses "__builtin__kprobes" as a module name for symbols for pages
+ * allocated for kprobes' purposes, even though "__builtin__kprobes" is not a
+ * module.
+ */
+static int get_ksymbol_kprobe(struct kallsym_iter *iter)
+{
+	strlcpy(iter->module_name, "__builtin__kprobes", MODULE_NAME_LEN);
+	iter->exported = 0;
+	return kprobe_get_kallsym(iter->pos - iter->pos_bpf_end,
+				  &iter->value, &iter->type,
+				  iter->name) < 0 ? 0 : 1;
 }
 
 /* Returns space to next name. */
@@ -527,6 +556,7 @@ static void reset_iter(struct kallsym_iter *iter, loff_t new_pos)
 		iter->pos_arch_end = 0;
 		iter->pos_mod_end = 0;
 		iter->pos_ftrace_mod_end = 0;
+		iter->pos_bpf_end = 0;
 	}
 }
 
@@ -551,7 +581,11 @@ static int update_iter_mod(struct kallsym_iter *iter, loff_t pos)
 	    get_ksymbol_ftrace_mod(iter))
 		return 1;
 
-	return get_ksymbol_bpf(iter);
+	if ((!iter->pos_bpf_end || iter->pos_bpf_end > pos) &&
+	    get_ksymbol_bpf(iter))
+		return 1;
+
+	return get_ksymbol_kprobe(iter);
 }
 
 /* Returns false if pos at or past end of file. */
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 2e97febeef77..e87679a48ba2 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -35,6 +35,7 @@
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
 #include <linux/jump_label.h>
+#include <linux/perf_event.h>
 
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
@@ -123,6 +124,7 @@ struct kprobe_insn_cache kprobe_insn_slots = {
 	.mutex = __MUTEX_INITIALIZER(kprobe_insn_slots.mutex),
 	.alloc = alloc_insn_page,
 	.free = free_insn_page,
+	.sym = KPROBE_INSN_PAGE_SYM,
 	.pages = LIST_HEAD_INIT(kprobe_insn_slots.pages),
 	.insn_size = MAX_INSN_SIZE,
 	.nr_garbage = 0,
@@ -188,6 +190,10 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
 	kip->cache = c;
 	list_add_rcu(&kip->list, &c->pages);
 	slot = kip->insns;
+
+	/* Record the perf ksymbol register event after adding the page */
+	perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (unsigned long)kip->insns,
+			   PAGE_SIZE, false, c->sym);
 out:
 	mutex_unlock(&c->mutex);
 	return slot;
@@ -206,6 +212,13 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx)
 		 * next time somebody inserts a probe.
 		 */
 		if (!list_is_singular(&kip->list)) {
+			/*
+			 * Record perf ksymbol unregister event before removing
+			 * the page.
+			 */
+			perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+					   (unsigned long)kip->insns, PAGE_SIZE, true,
+					   kip->cache->sym);
 			list_del_rcu(&kip->list);
 			synchronize_rcu();
 			kip->cache->free(kip->insns);
@@ -295,12 +308,34 @@ bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr)
 	return ret;
 }
 
+int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
+			     unsigned long *value, char *type, char *sym)
+{
+	struct kprobe_insn_page *kip;
+	int ret = -ERANGE;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(kip, &c->pages, list) {
+		if ((*symnum)--)
+			continue;
+		strlcpy(sym, c->sym, KSYM_NAME_LEN);
+		*type = 't';
+		*value = (unsigned long)kip->insns;
+		ret = 0;
+		break;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 #ifdef CONFIG_OPTPROBES
 /* For optimized_kprobe buffer */
 struct kprobe_insn_cache kprobe_optinsn_slots = {
 	.mutex = __MUTEX_INITIALIZER(kprobe_optinsn_slots.mutex),
 	.alloc = alloc_insn_page,
 	.free = free_insn_page,
+	.sym = KPROBE_OPTINSN_PAGE_SYM,
 	.pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages),
 	/* .insn_size is initialized later */
 	.nr_garbage = 0,
@@ -563,8 +598,6 @@ static void kprobe_optimizer(struct work_struct *work)
 	mutex_lock(&kprobe_mutex);
 	cpus_read_lock();
 	mutex_lock(&text_mutex);
-	/* Lock modules while optimizing kprobes */
-	mutex_lock(&module_mutex);
 
 	/*
 	 * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed)
@@ -589,7 +622,6 @@ static void kprobe_optimizer(struct work_struct *work)
 	/* Step 4: Free cleaned kprobes after quiesence period */
 	do_free_cleaned_kprobes();
 
-	mutex_unlock(&module_mutex);
 	mutex_unlock(&text_mutex);
 	cpus_read_unlock();
 
@@ -2232,6 +2264,28 @@ static void kprobe_remove_ksym_blacklist(unsigned long entry)
 	kprobe_remove_area_blacklist(entry, entry + 1);
 }
 
+int __weak arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
+				   char *type, char *sym)
+{
+	return -ERANGE;
+}
+
+int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		       char *sym)
+{
+#ifdef __ARCH_WANT_KPROBES_INSN_SLOT
+	if (!kprobe_cache_get_kallsym(&kprobe_insn_slots, &symnum, value, type, sym))
+		return 0;
+#ifdef CONFIG_OPTPROBES
+	if (!kprobe_cache_get_kallsym(&kprobe_optinsn_slots, &symnum, value, type, sym))
+		return 0;
+#endif
+#endif
+	if (!arch_kprobe_get_kallsym(&symnum, value, type, sym))
+		return 0;
+	return -ERANGE;
+}
+
 int __init __weak arch_populate_kprobe_blacklist(void)
 {
 	return 0;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1903b80db6eb..72064541bef2 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2764,6 +2764,50 @@ void __weak arch_ftrace_trampoline_free(struct ftrace_ops *ops)
 {
 }
 
+/* List of trace_ops that have allocated trampolines */
+static LIST_HEAD(ftrace_ops_trampoline_list);
+
+static void ftrace_add_trampoline_to_kallsyms(struct ftrace_ops *ops)
+{
+	lockdep_assert_held(&ftrace_lock);
+	list_add_rcu(&ops->list, &ftrace_ops_trampoline_list);
+}
+
+static void ftrace_remove_trampoline_from_kallsyms(struct ftrace_ops *ops)
+{
+	lockdep_assert_held(&ftrace_lock);
+	list_del_rcu(&ops->list);
+}
+
+/*
+ * "__builtin__ftrace" is used as a module name in /proc/kallsyms for symbols
+ * for pages allocated for ftrace purposes, even though "__builtin__ftrace" is
+ * not a module.
+ */
+#define FTRACE_TRAMPOLINE_MOD "__builtin__ftrace"
+#define FTRACE_TRAMPOLINE_SYM "ftrace_trampoline"
+
+static void ftrace_trampoline_free(struct ftrace_ops *ops)
+{
+	if (ops && (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP) &&
+	    ops->trampoline) {
+		/*
+		 * Record the text poke event before the ksymbol unregister
+		 * event.
+		 */
+		perf_event_text_poke((void *)ops->trampoline,
+				     (void *)ops->trampoline,
+				     ops->trampoline_size, NULL, 0);
+		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+				   ops->trampoline, ops->trampoline_size,
+				   true, FTRACE_TRAMPOLINE_SYM);
+		/* Remove from kallsyms after the perf events */
+		ftrace_remove_trampoline_from_kallsyms(ops);
+	}
+
+	arch_ftrace_trampoline_free(ops);
+}
+
 static void ftrace_startup_enable(int command)
 {
 	if (saved_ftrace_func != ftrace_trace_function) {
@@ -2934,7 +2978,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
 			synchronize_rcu_tasks();
 
  free_ops:
-		arch_ftrace_trampoline_free(ops);
+		ftrace_trampoline_free(ops);
 	}
 
 	return 0;
@@ -6178,6 +6222,27 @@ struct ftrace_mod_map {
 	unsigned int		num_funcs;
 };
 
+static int ftrace_get_trampoline_kallsym(unsigned int symnum,
+					 unsigned long *value, char *type,
+					 char *name, char *module_name,
+					 int *exported)
+{
+	struct ftrace_ops *op;
+
+	list_for_each_entry_rcu(op, &ftrace_ops_trampoline_list, list) {
+		if (!op->trampoline || symnum--)
+			continue;
+		*value = op->trampoline;
+		*type = 't';
+		strlcpy(name, FTRACE_TRAMPOLINE_SYM, KSYM_NAME_LEN);
+		strlcpy(module_name, FTRACE_TRAMPOLINE_MOD, MODULE_NAME_LEN);
+		*exported = 0;
+		return 0;
+	}
+
+	return -ERANGE;
+}
+
 #ifdef CONFIG_MODULES
 
 #define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next)
@@ -6514,6 +6579,7 @@ int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
 {
 	struct ftrace_mod_map *mod_map;
 	struct ftrace_mod_func *mod_func;
+	int ret;
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod_map, &ftrace_mod_maps, list) {
@@ -6540,8 +6606,10 @@ int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
 		WARN_ON(1);
 		break;
 	}
+	ret = ftrace_get_trampoline_kallsym(symnum, value, type, name,
+					    module_name, exported);
 	preempt_enable();
-	return -ERANGE;
+	return ret;
 }
 
 #else
@@ -6553,6 +6621,18 @@ allocate_ftrace_mod_map(struct module *mod,
 {
 	return NULL;
 }
+int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
+			   char *type, char *name, char *module_name,
+			   int *exported)
+{
+	int ret;
+
+	preempt_disable();
+	ret = ftrace_get_trampoline_kallsym(symnum, value, type, name,
+					    module_name, exported);
+	preempt_enable();
+	return ret;
+}
 #endif /* CONFIG_MODULES */
 
 struct ftrace_init_func {
@@ -6733,7 +6813,24 @@ void __weak arch_ftrace_update_trampoline(struct ftrace_ops *ops)
 
 static void ftrace_update_trampoline(struct ftrace_ops *ops)
 {
+	unsigned long trampoline = ops->trampoline;
+
 	arch_ftrace_update_trampoline(ops);
+	if (ops->trampoline && ops->trampoline != trampoline &&
+	    (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) {
+		/* Add to kallsyms before the perf events */
+		ftrace_add_trampoline_to_kallsyms(ops);
+		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+				   ops->trampoline, ops->trampoline_size, false,
+				   FTRACE_TRAMPOLINE_SYM);
+		/*
+		 * Record the perf text poke event after the ksymbol register
+		 * event.
+		 */
+		perf_event_text_poke((void *)ops->trampoline, NULL, 0,
+				     (void *)ops->trampoline,
+				     ops->trampoline_size);
+	}
 }
 
 void ftrace_init_trace_array(struct trace_array *tr)