Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The main kernel side changes in this cycle were:

   - Various Intel-PT updates and optimizations (Alexander Shishkin)

   - Prohibit kprobes on Xen/KVM emulate prefixes (Masami Hiramatsu)

   - Add support for LSM and SELinux checks to control access to the
     perf syscall (Joel Fernandes)

   - Misc other changes, optimizations, fixes and cleanups - see the
     shortlog for details.

  There were numerous tooling changes as well - 254 non-merge commits.
  Here are the main changes - too many to list in detail:

   - Enhancements to core tooling infrastructure, perf.data, libperf,
     libtraceevent, event parsing, vendor events, Intel PT, callchains,
     BPF support and instruction decoding.

   - There were updates to the following tools:

        perf annotate
        perf diff
        perf inject
        perf kvm
        perf list
        perf maps
        perf parse
        perf probe
        perf record
        perf report
        perf script
        perf stat
        perf test
        perf trace

   - And a lot of other changes: please see the shortlog and Git log for
     more details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (279 commits)
  perf parse: Fix potential memory leak when handling tracepoint errors
  perf probe: Fix spelling mistake "addrees" -> "address"
  libtraceevent: Fix memory leakage in copy_filter_type
  libtraceevent: Fix header installation
  perf intel-bts: Does not support AUX area sampling
  perf intel-pt: Add support for decoding AUX area samples
  perf intel-pt: Add support for recording AUX area samples
  perf pmu: When using default config, record which bits of config were changed by the user
  perf auxtrace: Add support for queuing AUX area samples
  perf session: Add facility to peek at all events
  perf auxtrace: Add support for dumping AUX area samples
  perf inject: Cut AUX area samples
  perf record: Add aux-sample-size config term
  perf record: Add support for AUX area sampling
  perf auxtrace: Add support for AUX area sample recording
  perf auxtrace: Move perf_evsel__find_pmu()
  perf record: Add a function to test for kernel support for AUX area sampling
  perf tools: Add kernel AUX area sampling definitions
  perf/core: Make the mlock accounting simple again
  perf report: Jump to symbol source view from total cycles view
  ...

17 files changed, 321 insertions, 73 deletions

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 64c3e70b0556..a7752cd78b89 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -652,15 +652,7 @@ static void amd_pmu_disable_event(struct perf_event *event)
  */
 static int amd_pmu_handle_irq(struct pt_regs *regs)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	int active, handled;
-
-	/*
-	 * Obtain the active count before calling x86_pmu_handle_irq() since
-	 * it is possible that x86_pmu_handle_irq() may make a counter
-	 * inactive (through x86_pmu_stop).
-	 */
-	active = __bitmap_weight(cpuc->active_mask, X86_PMC_IDX_MAX);
+	int handled;
 
 	/* Process any counter overflows */
 	handled = x86_pmu_handle_irq(regs);
@@ -670,8 +662,7 @@ static int amd_pmu_handle_irq(struct pt_regs *regs)
 	 * NMIs will be claimed if arriving within that window.
 	 */
 	if (handled) {
-		this_cpu_write(perf_nmi_tstamp,
-			       jiffies + perf_nmi_window);
+		this_cpu_write(perf_nmi_tstamp, jiffies + perf_nmi_window);
 
 		return handled;
 	}
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 7b21455d7504..6e3f0c18908e 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2243,6 +2243,13 @@ static void x86_pmu_sched_task(struct perf_event_context *ctx, bool sched_in)
 		x86_pmu.sched_task(ctx, sched_in);
 }
 
+static void x86_pmu_swap_task_ctx(struct perf_event_context *prev,
+				  struct perf_event_context *next)
+{
+	if (x86_pmu.swap_task_ctx)
+		x86_pmu.swap_task_ctx(prev, next);
+}
+
 void perf_check_microcode(void)
 {
 	if (x86_pmu.check_microcode)
@@ -2297,6 +2304,7 @@ 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,
 
 	.aux_output_match	= x86_pmu_aux_output_match,
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 5ee3fed881d3..38de4a7f6752 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -549,9 +549,11 @@ static int bts_event_init(struct perf_event *event)
 	 * Note that the default paranoia setting permits unprivileged
 	 * users to profile the kernel.
 	 */
-	if (event->attr.exclude_kernel && perf_paranoid_kernel() &&
-	    !capable(CAP_SYS_ADMIN))
-		return -EACCES;
+	if (event->attr.exclude_kernel) {
+		ret = perf_allow_kernel(&event->attr);
+		if (ret)
+			return ret;
+	}
 
 	if (x86_add_exclusive(x86_lbr_exclusive_bts))
 		return -EBUSY;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 937363b803c1..3be51aa06e67 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3315,8 +3315,9 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (x86_pmu.version < 3)
 		return -EINVAL;
 
-	if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
-		return -EACCES;
+	ret = perf_allow_cpu(&event->attr);
+	if (ret)
+		return ret;
 
 	event->hw.config |= ARCH_PERFMON_EVENTSEL_ANY;
 
@@ -3830,6 +3831,12 @@ static void intel_pmu_sched_task(struct perf_event_context *ctx,
 	intel_pmu_lbr_sched_task(ctx, sched_in);
 }
 
+static void intel_pmu_swap_task_ctx(struct perf_event_context *prev,
+				    struct perf_event_context *next)
+{
+	intel_pmu_lbr_swap_task_ctx(prev, next);
+}
+
 static int intel_pmu_check_period(struct perf_event *event, u64 value)
 {
 	return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
@@ -3965,6 +3972,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 
 	.guest_get_msrs		= intel_guest_get_msrs,
 	.sched_task		= intel_pmu_sched_task,
+	.swap_task_ctx		= intel_pmu_swap_task_ctx,
 
 	.check_period		= intel_pmu_check_period,
 
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index ea54634eabf3..534c76606049 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -417,6 +417,29 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 	cpuc->last_log_id = ++task_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;
+
+	swap(prev->task_ctx_data, next->task_ctx_data);
+
+	/*
+	 * Architecture specific synchronization makes sense in
+	 * case both prev->task_ctx_data and next->task_ctx_data
+	 * pointers are allocated.
+	 */
+
+	prev_ctx_data = next->task_ctx_data;
+	next_ctx_data = prev->task_ctx_data;
+
+	if (!prev_ctx_data || !next_ctx_data)
+		return;
+
+	swap(prev_ctx_data->lbr_callstack_users,
+	     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);
diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c
index dee579efb2b2..a4cc66005ce8 100644
--- a/arch/x86/events/intel/p4.c
+++ b/arch/x86/events/intel/p4.c
@@ -776,8 +776,9 @@ static int p4_validate_raw_event(struct perf_event *event)
 	 * the user needs special permissions to be able to use it
 	 */
 	if (p4_ht_active() && p4_event_bind_map[v].shared) {
-		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
-			return -EACCES;
+		v = perf_allow_cpu(&event->attr);
+		if (v)
+			return v;
 	}
 
 	/* ESCR EventMask bits may be invalid */
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 05e43d0f430b..1db7a51d9792 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -397,6 +397,20 @@ static bool pt_event_valid(struct perf_event *event)
  * These all are cpu affine and operate on a local PT
  */
 
+static void pt_config_start(struct perf_event *event)
+{
+	struct pt *pt = this_cpu_ptr(&pt_ctx);
+	u64 ctl = event->hw.config;
+
+	ctl |= RTIT_CTL_TRACEEN;
+	if (READ_ONCE(pt->vmx_on))
+		perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_PARTIAL);
+	else
+		wrmsrl(MSR_IA32_RTIT_CTL, ctl);
+
+	WRITE_ONCE(event->hw.config, ctl);
+}
+
 /* Address ranges and their corresponding msr configuration registers */
 static const struct pt_address_range {
 	unsigned long	msr_a;
@@ -469,6 +483,7 @@ static u64 pt_config_filters(struct perf_event *event)
 static void pt_config(struct perf_event *event)
 {
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
+	struct pt_buffer *buf = perf_get_aux(&pt->handle);
 	u64 reg;
 
 	/* First round: clear STATUS, in particular the PSB byte counter. */
@@ -478,7 +493,9 @@ static void pt_config(struct perf_event *event)
 	}
 
 	reg = pt_config_filters(event);
-	reg |= RTIT_CTL_TOPA | RTIT_CTL_TRACEEN;
+	reg |= RTIT_CTL_TRACEEN;
+	if (!buf->single)
+		reg |= RTIT_CTL_TOPA;
 
 	/*
 	 * Previously, we had BRANCH_EN on by default, but now that PT has
@@ -501,10 +518,7 @@ static void pt_config(struct perf_event *event)
 	reg |= (event->attr.config & PT_CONFIG_MASK);
 
 	event->hw.config = reg;
-	if (READ_ONCE(pt->vmx_on))
-		perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_PARTIAL);
-	else
-		wrmsrl(MSR_IA32_RTIT_CTL, reg);
+	pt_config_start(event);
 }
 
 static void pt_config_stop(struct perf_event *event)
@@ -533,18 +547,6 @@ static void pt_config_stop(struct perf_event *event)
 	wmb();
 }
 
-static void pt_config_buffer(void *buf, unsigned int topa_idx,
-			     unsigned int output_off)
-{
-	u64 reg;
-
-	wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, virt_to_phys(buf));
-
-	reg = 0x7f | ((u64)topa_idx << 7) | ((u64)output_off << 32);
-
-	wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, reg);
-}
-
 /**
  * struct topa - ToPA metadata
  * @list:	linkage to struct pt_buffer's list of tables
@@ -602,6 +604,33 @@ static inline phys_addr_t topa_pfn(struct topa *topa)
 #define TOPA_ENTRY_SIZE(t, i) (sizes(TOPA_ENTRY((t), (i))->size))
 #define TOPA_ENTRY_PAGES(t, i) (1 << TOPA_ENTRY((t), (i))->size)
 
+static void pt_config_buffer(struct pt_buffer *buf)
+{
+	struct pt *pt = this_cpu_ptr(&pt_ctx);
+	u64 reg, mask;
+	void *base;
+
+	if (buf->single) {
+		base = buf->data_pages[0];
+		mask = (buf->nr_pages * PAGE_SIZE - 1) >> 7;
+	} else {
+		base = topa_to_page(buf->cur)->table;
+		mask = (u64)buf->cur_idx;
+	}
+
+	reg = virt_to_phys(base);
+	if (pt->output_base != reg) {
+		pt->output_base = reg;
+		wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, reg);
+	}
+
+	reg = 0x7f | (mask << 7) | ((u64)buf->output_off << 32);
+	if (pt->output_mask != reg) {
+		pt->output_mask = reg;
+		wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, reg);
+	}
+}
+
 /**
  * topa_alloc() - allocate page-sized ToPA table
  * @cpu:	CPU on which to allocate.
@@ -802,6 +831,11 @@ static void pt_update_head(struct pt *pt)
 	struct pt_buffer *buf = perf_get_aux(&pt->handle);
 	u64 topa_idx, base, old;
 
+	if (buf->single) {
+		local_set(&buf->data_size, buf->output_off);
+		return;
+	}
+
 	/* offset of the first region in this table from the beginning of buf */
 	base = buf->cur->offset + buf->output_off;
 
@@ -903,18 +937,21 @@ static void pt_handle_status(struct pt *pt)
  */
 static void pt_read_offset(struct pt_buffer *buf)
 {
-	u64 offset, base_topa;
+	struct pt *pt = this_cpu_ptr(&pt_ctx);
 	struct topa_page *tp;
 
-	rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, base_topa);
-	tp = phys_to_virt(base_topa);
-	buf->cur = &tp->topa;
+	if (!buf->single) {
+		rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, pt->output_base);
+		tp = phys_to_virt(pt->output_base);
+		buf->cur = &tp->topa;
+	}
 
-	rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, offset);
+	rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, pt->output_mask);
 	/* offset within current output region */
-	buf->output_off = offset >> 32;
+	buf->output_off = pt->output_mask >> 32;
 	/* index of current output region within this table */
-	buf->cur_idx = (offset & 0xffffff80) >> 7;
+	if (!buf->single)
+		buf->cur_idx = (pt->output_mask & 0xffffff80) >> 7;
 }
 
 static struct topa_entry *
@@ -1030,6 +1067,9 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 	unsigned long head = local64_read(&buf->head);
 	unsigned long idx, npages, wakeup;
 
+	if (buf->single)
+		return 0;
+
 	/* can't stop in the middle of an output region */
 	if (buf->output_off + handle->size + 1 < pt_buffer_region_size(buf)) {
 		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
@@ -1111,13 +1151,17 @@ static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head)
 	if (buf->snapshot)
 		head &= (buf->nr_pages << PAGE_SHIFT) - 1;
 
-	pg = (head >> PAGE_SHIFT) & (buf->nr_pages - 1);
-	te = pt_topa_entry_for_page(buf, pg);
+	if (!buf->single) {
+		pg = (head >> PAGE_SHIFT) & (buf->nr_pages - 1);
+		te = pt_topa_entry_for_page(buf, pg);
 
-	cur_tp = topa_entry_to_page(te);
-	buf->cur = &cur_tp->topa;
-	buf->cur_idx = te - TOPA_ENTRY(buf->cur, 0);
-	buf->output_off = head & (pt_buffer_region_size(buf) - 1);
+		cur_tp = topa_entry_to_page(te);
+		buf->cur = &cur_tp->topa;
+		buf->cur_idx = te - TOPA_ENTRY(buf->cur, 0);
+		buf->output_off = head & (pt_buffer_region_size(buf) - 1);
+	} else {
+		buf->output_off = head;
+	}
 
 	local64_set(&buf->head, head);
 	local_set(&buf->data_size, 0);
@@ -1131,6 +1175,9 @@ static void pt_buffer_fini_topa(struct pt_buffer *buf)
 {
 	struct topa *topa, *iter;
 
+	if (buf->single)
+		return;
+
 	list_for_each_entry_safe(topa, iter, &buf->tables, list) {
 		/*
 		 * right now, this is in free_aux() path only, so
@@ -1176,6 +1223,36 @@ static int pt_buffer_init_topa(struct pt_buffer *buf, int cpu,
 	return 0;
 }
 
+static int pt_buffer_try_single(struct pt_buffer *buf, int nr_pages)
+{
+	struct page *p = virt_to_page(buf->data_pages[0]);
+	int ret = -ENOTSUPP, order = 0;
+
+	/*
+	 * We can use single range output mode
+	 * + in snapshot mode, where we don't need interrupts;
+	 * + if the hardware supports it;
+	 * + if the entire buffer is one contiguous allocation.
+	 */
+	if (!buf->snapshot)
+		goto out;
+
+	if (!intel_pt_validate_hw_cap(PT_CAP_single_range_output))
+		goto out;
+
+	if (PagePrivate(p))
+		order = page_private(p);
+
+	if (1 << order != nr_pages)
+		goto out;
+
+	buf->single = true;
+	buf->nr_pages = nr_pages;
+	ret = 0;
+out:
+	return ret;
+}
+
 /**
  * pt_buffer_setup_aux() - set up topa tables for a PT buffer
  * @cpu:	Cpu on which to allocate, -1 means current.
@@ -1198,6 +1275,13 @@ pt_buffer_setup_aux(struct perf_event *event, void **pages,
 	if (!nr_pages)
 		return NULL;
 
+	/*
+	 * Only support AUX sampling in snapshot mode, where we don't
+	 * generate NMIs.
+	 */
+	if (event->attr.aux_sample_size && !snapshot)
+		return NULL;
+
 	if (cpu == -1)
 		cpu = raw_smp_processor_id();
 	node = cpu_to_node(cpu);
@@ -1213,6 +1297,10 @@ pt_buffer_setup_aux(struct perf_event *event, void **pages,
 
 	INIT_LIST_HEAD(&buf->tables);
 
+	ret = pt_buffer_try_single(buf, nr_pages);
+	if (!ret)
+		return buf;
+
 	ret = pt_buffer_init_topa(buf, cpu, nr_pages, GFP_KERNEL);
 	if (ret) {
 		kfree(buf);
@@ -1379,9 +1467,8 @@ void intel_pt_interrupt(void)
 			return;
 		}
 
-		pt_config_buffer(topa_to_page(buf->cur)->table, buf->cur_idx,
-				 buf->output_off);
-		pt_config(event);
+		pt_config_buffer(buf);
+		pt_config_start(event);
 	}
 }
 
@@ -1444,8 +1531,7 @@ static void pt_event_start(struct perf_event *event, int mode)
 	WRITE_ONCE(pt->handle_nmi, 1);
 	hwc->state = 0;
 
-	pt_config_buffer(topa_to_page(buf->cur)->table, buf->cur_idx,
-			 buf->output_off);
+	pt_config_buffer(buf);
 	pt_config(event);
 
 	return;
@@ -1496,6 +1582,52 @@ static void pt_event_stop(struct perf_event *event, int mode)
 	}
 }
 
+static long pt_event_snapshot_aux(struct perf_event *event,
+				  struct perf_output_handle *handle,
+				  unsigned long size)
+{
+	struct pt *pt = this_cpu_ptr(&pt_ctx);
+	struct pt_buffer *buf = perf_get_aux(&pt->handle);
+	unsigned long from = 0, to;
+	long ret;
+
+	if (WARN_ON_ONCE(!buf))
+		return 0;
+
+	/*
+	 * Sampling is only allowed on snapshot events;
+	 * see pt_buffer_setup_aux().
+	 */
+	if (WARN_ON_ONCE(!buf->snapshot))
+		return 0;
+
+	/*
+	 * Here, handle_nmi tells us if the tracing is on
+	 */
+	if (READ_ONCE(pt->handle_nmi))
+		pt_config_stop(event);
+
+	pt_read_offset(buf);
+	pt_update_head(pt);
+
+	to = local_read(&buf->data_size);
+	if (to < size)
+		from = buf->nr_pages << PAGE_SHIFT;
+	from += to - size;
+
+	ret = perf_output_copy_aux(&pt->handle, handle, from, to);
+
+	/*
+	 * If the tracing was on when we turned up, restart it.
+	 * Compiler barrier not needed as we couldn't have been
+	 * preempted by anything that touches pt->handle_nmi.
+	 */
+	if (pt->handle_nmi)
+		pt_config_start(event);
+
+	return ret;
+}
+
 static void pt_event_del(struct perf_event *event, int mode)
 {
 	pt_event_stop(event, PERF_EF_UPDATE);
@@ -1615,6 +1747,7 @@ static __init int pt_init(void)
 	pt_pmu.pmu.del			 = pt_event_del;
 	pt_pmu.pmu.start		 = pt_event_start;
 	pt_pmu.pmu.stop			 = pt_event_stop;
+	pt_pmu.pmu.snapshot_aux		 = pt_event_snapshot_aux;
 	pt_pmu.pmu.read			 = pt_event_read;
 	pt_pmu.pmu.setup_aux		 = pt_buffer_setup_aux;
 	pt_pmu.pmu.free_aux		 = pt_buffer_free_aux;
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index 1d2bb7572374..96906a62aacd 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -64,6 +64,7 @@ struct pt_pmu {
  * @lost:	if data was lost/truncated
  * @head:	logical write offset inside the buffer
  * @snapshot:	if this is for a snapshot/overwrite counter
+ * @single:	use Single Range Output instead of ToPA
  * @stop_pos:	STOP topa entry index
  * @intr_pos:	INT topa entry index
  * @stop_te:	STOP topa entry pointer
@@ -80,6 +81,7 @@ struct pt_buffer {
 	local_t			data_size;
 	local64_t		head;
 	bool			snapshot;
+	bool			single;
 	long			stop_pos, intr_pos;
 	struct topa_entry	*stop_te, *intr_te;
 	void			**data_pages;
@@ -111,16 +113,20 @@ struct pt_filters {
 
 /**
  * struct pt - per-cpu pt context
- * @handle:	perf output handle
+ * @handle:		perf output handle
  * @filters:		last configured filters
- * @handle_nmi:	do handle PT PMI on this cpu, there's an active event
- * @vmx_on:	1 if VMX is ON on this cpu
+ * @handle_nmi:		do handle PT PMI on this cpu, there's an active event
+ * @vmx_on:		1 if VMX is ON on this cpu
+ * @output_base:	cached RTIT_OUTPUT_BASE MSR value
+ * @output_mask:	cached RTIT_OUTPUT_MASK MSR value
  */
 struct pt {
 	struct perf_output_handle handle;
 	struct pt_filters	filters;
 	int			handle_nmi;
 	int			vmx_on;
+	u64			output_base;
+	u64			output_mask;
 };
 
 #endif /* __INTEL_PT_H__ */
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ecacfbf4ebc1..930611db8f9a 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -683,6 +683,14 @@ struct x86_pmu {
 	atomic_t	lbr_exclusive[x86_lbr_exclusive_max];
 
 	/*
+	 * perf task context (i.e. struct perf_event_context::task_ctx_data)
+	 * switch helper to bridge calls from perf/core to perf/x86.
+	 * See struct pmu::swap_task_ctx() usage for examples;
+	 */
+	void		(*swap_task_ctx)(struct perf_event_context *prev,
+					 struct perf_event_context *next);
+
+	/*
 	 * AMD bits
 	 */
 	unsigned int	amd_nb_constraints : 1;
@@ -1016,6 +1024,9 @@ void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr);
 
 void intel_ds_init(void);
 
+void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
+				 struct perf_event_context *next);
+
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
 
 u64 lbr_from_signext_quirk_wr(u64 val);
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 3ff577c0b102..1b563f9167ea 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -7,9 +7,11 @@
 # define __ASM_FORM_RAW(x)     x
 # define __ASM_FORM_COMMA(x) x,
 #else
-# define __ASM_FORM(x)	" " #x " "
-# define __ASM_FORM_RAW(x)     #x
-# define __ASM_FORM_COMMA(x) " " #x ","
+#include <linux/stringify.h>
+
+# define __ASM_FORM(x)	" " __stringify(x) " "
+# define __ASM_FORM_RAW(x)     __stringify(x)
+# define __ASM_FORM_COMMA(x) " " __stringify(x) ","
 #endif
 
 #ifndef __x86_64__
diff --git a/arch/x86/include/asm/emulate_prefix.h b/arch/x86/include/asm/emulate_prefix.h
new file mode 100644
index 000000000000..70f5b98a5286
--- /dev/null
+++ b/arch/x86/include/asm/emulate_prefix.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_EMULATE_PREFIX_H
+#define _ASM_X86_EMULATE_PREFIX_H
+
+/*
+ * Virt escape sequences to trigger instruction emulation;
+ * ideally these would decode to 'whole' instruction and not destroy
+ * the instruction stream; sadly this is not true for the 'kvm' one :/
+ */
+
+#define __XEN_EMULATE_PREFIX  0x0f,0x0b,0x78,0x65,0x6e  /* ud2 ; .ascii "xen" */
+#define __KVM_EMULATE_PREFIX  0x0f,0x0b,0x6b,0x76,0x6d	/* ud2 ; .ascii "kvm" */
+
+#endif
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 154f27be8bfc..5c1ae3eff9d4 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -45,6 +45,7 @@ struct insn {
 		struct insn_field immediate2;	/* for 64bit imm or seg16 */
 	};
 
+	int	emulate_prefix_size;
 	insn_attr_t attr;
 	unsigned char opnd_bytes;
 	unsigned char addr_bytes;
@@ -128,6 +129,11 @@ static inline int insn_is_evex(struct insn *insn)
 	return (insn->vex_prefix.nbytes == 4);
 }
 
+static inline int insn_has_emulate_prefix(struct insn *insn)
+{
+	return !!insn->emulate_prefix_size;
+}
+
 /* Ensure this instruction is decoded completely */
 static inline int insn_complete(struct insn *insn)
 {
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index 62ca03ef5c65..9139b3e86316 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -379,12 +379,9 @@ struct xen_pmu_arch {
  * Prefix forces emulation of some non-trapping instructions.
  * Currently only CPUID.
  */
-#ifdef __ASSEMBLY__
-#define XEN_EMULATE_PREFIX .byte 0x0f,0x0b,0x78,0x65,0x6e ;
-#define XEN_CPUID          XEN_EMULATE_PREFIX cpuid
-#else
-#define XEN_EMULATE_PREFIX ".byte 0x0f,0x0b,0x78,0x65,0x6e ; "
-#define XEN_CPUID          XEN_EMULATE_PREFIX "cpuid"
-#endif
+#include <asm/emulate_prefix.h>
+
+#define XEN_EMULATE_PREFIX __ASM_FORM(.byte __XEN_EMULATE_PREFIX ;)
+#define XEN_CPUID          XEN_EMULATE_PREFIX __ASM_FORM(cpuid)
 
 #endif /* _ASM_X86_XEN_INTERFACE_H */
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 43fc13c831af..4f13af7cbcdb 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -351,6 +351,10 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
 	kernel_insn_init(insn, dest, MAX_INSN_SIZE);
 	insn_get_length(insn);
 
+	/* We can not probe force emulate prefixed instruction */
+	if (insn_has_emulate_prefix(insn))
+		return 0;
+
 	/* Another subsystem puts a breakpoint, failed to recover */
 	if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
 		return 0;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3ed167e039e5..cf917139de6b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -68,6 +68,7 @@
 #include <asm/mshyperv.h>
 #include <asm/hypervisor.h>
 #include <asm/intel_pt.h>
+#include <asm/emulate_prefix.h>
 #include <clocksource/hyperv_timer.h>
 
 #define CREATE_TRACE_POINTS
@@ -5492,6 +5493,7 @@ EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system);
 
 int handle_ud(struct kvm_vcpu *vcpu)
 {
+	static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX };
 	int emul_type = EMULTYPE_TRAP_UD;
 	char sig[5]; /* ud2; .ascii "kvm" */
 	struct x86_exception e;
@@ -5499,7 +5501,7 @@ int handle_ud(struct kvm_vcpu *vcpu)
 	if (force_emulation_prefix &&
 	    kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu),
 				sig, sizeof(sig), &e) == 0 &&
-	    memcmp(sig, "\xf\xbkvm", sizeof(sig)) == 0) {
+	    memcmp(sig, kvm_emulate_prefix, sizeof(sig)) == 0) {
 		kvm_rip_write(vcpu, kvm_rip_read(vcpu) + sizeof(sig));
 		emul_type = EMULTYPE_TRAP_UD_FORCED;
 	}
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 0b5862ba6a75..404279563891 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -13,6 +13,8 @@
 #include <asm/inat.h>
 #include <asm/insn.h>
 
+#include <asm/emulate_prefix.h>
+
 /* Verify next sizeof(t) bytes can be on the same instruction */
 #define validate_next(t, insn, n)	\
 	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
@@ -58,6 +60,36 @@ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
 		insn->addr_bytes = 4;
 }
 
+static const insn_byte_t xen_prefix[] = { __XEN_EMULATE_PREFIX };
+static const insn_byte_t kvm_prefix[] = { __KVM_EMULATE_PREFIX };
+
+static int __insn_get_emulate_prefix(struct insn *insn,
+				     const insn_byte_t *prefix, size_t len)
+{
+	size_t i;
+
+	for (i = 0; i < len; i++) {
+		if (peek_nbyte_next(insn_byte_t, insn, i) != prefix[i])
+			goto err_out;
+	}
+
+	insn->emulate_prefix_size = len;
+	insn->next_byte += len;
+
+	return 1;
+
+err_out:
+	return 0;
+}
+
+static void insn_get_emulate_prefix(struct insn *insn)
+{
+	if (__insn_get_emulate_prefix(insn, xen_prefix, sizeof(xen_prefix)))
+		return;
+
+	__insn_get_emulate_prefix(insn, kvm_prefix, sizeof(kvm_prefix));
+}
+
 /**
  * insn_get_prefixes - scan x86 instruction prefix bytes
  * @insn:	&struct insn containing instruction
@@ -76,6 +108,8 @@ void insn_get_prefixes(struct insn *insn)
 	if (prefixes->got)
 		return;
 
+	insn_get_emulate_prefix(insn);
+
 	nb = 0;
 	lb = 0;
 	b = peek_next(insn_byte_t, insn);
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index e0b85930dd77..0a0e9112f284 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -333,7 +333,7 @@ AVXcode: 1
 06: CLTS
 07: SYSRET (o64)
 08: INVD
-09: WBINVD
+09: WBINVD | WBNOINVD (F3)
 0a:
 0b: UD2 (1B)
 0c:
@@ -364,7 +364,7 @@ AVXcode: 1
 # a ModR/M byte.
 1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev
 1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv
-1c:
+1c: Grp20 (1A),(1C)
 1d:
 1e:
 1f: NOP Ev
@@ -792,6 +792,8 @@ f3: Grp17 (1A)
 f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
 f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v)
 f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
+f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3)
+f9: MOVDIRI My,Gy
 EndTable
 
 Table: 3-byte opcode 2 (0x0f 0x3a)
@@ -943,9 +945,9 @@ GrpTable: Grp6
 EndTable
 
 GrpTable: Grp7
-0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B)
-1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B)
-2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B)
+0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B)
+1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B)
+2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B)
 3: LIDT Ms
 4: SMSW Mw/Rv
 5: rdpkru (110),(11B) | wrpkru (111),(11B)
@@ -1020,7 +1022,7 @@ GrpTable: Grp15
 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
 4: XSAVE | ptwrite Ey (F3),(11B)
 5: XRSTOR | lfence (11B)
-6: XSAVEOPT | clwb (66) | mfence (11B)
+6: XSAVEOPT | clwb (66) | mfence (11B) | TPAUSE Rd (66),(11B) | UMONITOR Rv (F3),(11B) | UMWAIT Rd (F2),(11B)
 7: clflush | clflushopt (66) | sfence (11B)
 EndTable
 
@@ -1051,6 +1053,10 @@ GrpTable: Grp19
 6: vscatterpf1qps/d Wx (66),(ev)
 EndTable
 
+GrpTable: Grp20
+0: cldemote Mb
+EndTable
+
 # AMD's Prefetch Group
 GrpTable: GrpP
 0: PREFETCH