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

Pull perf events changes for v3.4 from Ingo Molnar:

 - New "hardware based branch profiling" feature both on the kernel and
   the tooling side, on CPUs that support it.  (modern x86 Intel CPUs
   with the 'LBR' hardware feature currently.)

   This new feature is basically a sophisticated 'magnifying glass' for
   branch execution - something that is pretty difficult to extract from
   regular, function histogram centric profiles.

   The simplest mode is activated via 'perf record -b', and the result
   looks like this in perf report:

	$ perf record -b any_call,u -e cycles:u branchy

	$ perf report -b --sort=symbol
	    52.34%  [.] main                   [.] f1
	    24.04%  [.] f1                     [.] f3
	    23.60%  [.] f1                     [.] f2
	     0.01%  [k] _IO_new_file_xsputn    [k] _IO_file_overflow
	     0.01%  [k] _IO_vfprintf_internal  [k] _IO_new_file_xsputn
	     0.01%  [k] _IO_vfprintf_internal  [k] strchrnul
	     0.01%  [k] __printf               [k] _IO_vfprintf_internal
	     0.01%  [k] main                   [k] __printf

   This output shows from/to branch columns and shows the highest
   percentage (from,to) jump combinations - i.e.  the most likely taken
   branches in the system.  "branches" can also include function calls
   and any other synchronous and asynchronous transitions of the
   instruction pointer that are not 'next instruction' - such as system
   calls, traps, interrupts, etc.

   This feature comes with (hopefully intuitive) flat ascii and TUI
   support in perf report.

 - Various 'perf annotate' visual improvements for us assembly junkies.
   It will now recognize function calls in the TUI and by hitting enter
   you can follow the call (recursively) and back, amongst other
   improvements.

 - Multiple threads/processes recording support in perf record, perf
   stat, perf top - which is activated via a comma-list of PIDs:

	perf top -p 21483,21485
	perf stat -p 21483,21485 -ddd
	perf record -p 21483,21485

 - Support for per UID views, via the --uid paramter to perf top, perf
   report, etc.  For example 'perf top --uid mingo' will only show the
   tasks that I am running, excluding other users, root, etc.

 - Jump label restructurings and improvements - this includes the
   factoring out of the (hopefully much clearer) include/linux/static_key.h
   generic facility:

	struct static_key key = STATIC_KEY_INIT_FALSE;

	...

	if (static_key_false(&key))
	        do unlikely code
	else
	        do likely code

	...
	static_key_slow_inc();
	...
	static_key_slow_inc();
	...

   The static_key_false() branch will be generated into the code with as
   little impact to the likely code path as possible.  the
   static_key_slow_*() APIs flip the branch via live kernel code patching.

   This facility can now be used more widely within the kernel to
   micro-optimize hot branches whose likelihood matches the static-key
   usage and fast/slow cost patterns.

 - SW function tracer improvements: perf support and filtering support.

 - Various hardenings of the perf.data ABI, to make older perf.data's
   smoother on newer tool versions, to make new features integrate more
   smoothly, to support cross-endian recording/analyzing workflows
   better, etc.

 - Restructuring of the kprobes code, the splitting out of 'optprobes',
   and a corner case bugfix.

 - Allow the tracing of kernel console output (printk).

 - Improvements/fixes to user-space RDPMC support, allowing user-space
   self-profiling code to extract PMU counts without performing any
   system calls, while playing nice with the kernel side.

 - 'perf bench' improvements

 - ... and lots of internal restructurings, cleanups and fixes that made
   these features possible.  And, as usual this list is incomplete as
   there were also lots of other improvements

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (120 commits)
  perf report: Fix annotate double quit issue in branch view mode
  perf report: Remove duplicate annotate choice in branch view mode
  perf/x86: Prettify pmu config literals
  perf report: Enable TUI in branch view mode
  perf report: Auto-detect branch stack sampling mode
  perf record: Add HEADER_BRANCH_STACK tag
  perf record: Provide default branch stack sampling mode option
  perf tools: Make perf able to read files from older ABIs
  perf tools: Fix ABI compatibility bug in print_event_desc()
  perf tools: Enable reading of perf.data files from different ABI rev
  perf: Add ABI reference sizes
  perf report: Add support for taken branch sampling
  perf record: Add support for sampling taken branch
  perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK
  x86/kprobes: Split out optprobe related code to kprobes-opt.c
  x86/kprobes: Fix a bug which can modify kernel code permanently
  x86/kprobes: Fix instruction recovery on optimized path
  perf: Add callback to flush branch_stack on context switch
  perf: Disable PERF_SAMPLE_BRANCH_* when not supported
  perf/x86: Add LBR software filter support for Intel CPUs
  ...

23 files changed, 993 insertions, 259 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1b5c081d8b9f..c61234b1a988 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -118,6 +118,13 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
 		       PERF_FLAG_FD_OUTPUT  |\
 		       PERF_FLAG_PID_CGROUP)
 
+/*
+ * branch priv levels that need permission checks
+ */
+#define PERF_SAMPLE_BRANCH_PERM_PLM \
+	(PERF_SAMPLE_BRANCH_KERNEL |\
+	 PERF_SAMPLE_BRANCH_HV)
+
 enum event_type_t {
 	EVENT_FLEXIBLE = 0x1,
 	EVENT_PINNED = 0x2,
@@ -128,8 +135,9 @@ enum event_type_t {
  * perf_sched_events : >0 events exist
  * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
  */
-struct jump_label_key_deferred perf_sched_events __read_mostly;
+struct static_key_deferred perf_sched_events __read_mostly;
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
+static DEFINE_PER_CPU(atomic_t, perf_branch_stack_events);
 
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
@@ -881,6 +889,9 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 	if (is_cgroup_event(event))
 		ctx->nr_cgroups++;
 
+	if (has_branch_stack(event))
+		ctx->nr_branch_stack++;
+
 	list_add_rcu(&event->event_entry, &ctx->event_list);
 	if (!ctx->nr_events)
 		perf_pmu_rotate_start(ctx->pmu);
@@ -1020,6 +1031,9 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 			cpuctx->cgrp = NULL;
 	}
 
+	if (has_branch_stack(event))
+		ctx->nr_branch_stack--;
+
 	ctx->nr_events--;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat--;
@@ -2195,6 +2209,66 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 }
 
 /*
+ * When sampling the branck stack in system-wide, it may be necessary
+ * to flush the stack on context switch. This happens when the branch
+ * stack does not tag its entries with the pid of the current task.
+ * Otherwise it becomes impossible to associate a branch entry with a
+ * task. This ambiguity is more likely to appear when the branch stack
+ * supports priv level filtering and the user sets it to monitor only
+ * at the user level (which could be a useful measurement in system-wide
+ * mode). In that case, the risk is high of having a branch stack with
+ * branch from multiple tasks. Flushing may mean dropping the existing
+ * entries or stashing them somewhere in the PMU specific code layer.
+ *
+ * This function provides the context switch callback to the lower code
+ * layer. It is invoked ONLY when there is at least one system-wide context
+ * with at least one active event using taken branch sampling.
+ */
+static void perf_branch_stack_sched_in(struct task_struct *prev,
+				       struct task_struct *task)
+{
+	struct perf_cpu_context *cpuctx;
+	struct pmu *pmu;
+	unsigned long flags;
+
+	/* no need to flush branch stack if not changing task */
+	if (prev == task)
+		return;
+
+	local_irq_save(flags);
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+		/*
+		 * check if the context has at least one
+		 * event using PERF_SAMPLE_BRANCH_STACK
+		 */
+		if (cpuctx->ctx.nr_branch_stack > 0
+		    && pmu->flush_branch_stack) {
+
+			pmu = cpuctx->ctx.pmu;
+
+			perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+
+			perf_pmu_disable(pmu);
+
+			pmu->flush_branch_stack();
+
+			perf_pmu_enable(pmu);
+
+			perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+		}
+	}
+
+	rcu_read_unlock();
+
+	local_irq_restore(flags);
+}
+
+/*
  * Called from scheduler to add the events of the current task
  * with interrupts disabled.
  *
@@ -2225,6 +2299,10 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 	 */
 	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
 		perf_cgroup_sched_in(prev, task);
+
+	/* check for system-wide branch_stack events */
+	if (atomic_read(&__get_cpu_var(perf_branch_stack_events)))
+		perf_branch_stack_sched_in(prev, task);
 }
 
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -2778,7 +2856,7 @@ static void free_event(struct perf_event *event)
 
 	if (!event->parent) {
 		if (event->attach_state & PERF_ATTACH_TASK)
-			jump_label_dec_deferred(&perf_sched_events);
+			static_key_slow_dec_deferred(&perf_sched_events);
 		if (event->attr.mmap || event->attr.mmap_data)
 			atomic_dec(&nr_mmap_events);
 		if (event->attr.comm)
@@ -2789,7 +2867,15 @@ static void free_event(struct perf_event *event)
 			put_callchain_buffers();
 		if (is_cgroup_event(event)) {
 			atomic_dec(&per_cpu(perf_cgroup_events, event->cpu));
-			jump_label_dec_deferred(&perf_sched_events);
+			static_key_slow_dec_deferred(&perf_sched_events);
+		}
+
+		if (has_branch_stack(event)) {
+			static_key_slow_dec_deferred(&perf_sched_events);
+			/* is system-wide event */
+			if (!(event->attach_state & PERF_ATTACH_TASK))
+				atomic_dec(&per_cpu(perf_branch_stack_events,
+						    event->cpu));
 		}
 	}
 
@@ -3238,10 +3324,6 @@ int perf_event_task_disable(void)
 	return 0;
 }
 
-#ifndef PERF_EVENT_INDEX_OFFSET
-# define PERF_EVENT_INDEX_OFFSET 0
-#endif
-
 static int perf_event_index(struct perf_event *event)
 {
 	if (event->hw.state & PERF_HES_STOPPED)
@@ -3250,21 +3332,26 @@ static int perf_event_index(struct perf_event *event)
 	if (event->state != PERF_EVENT_STATE_ACTIVE)
 		return 0;
 
-	return event->hw.idx + 1 - PERF_EVENT_INDEX_OFFSET;
+	return event->pmu->event_idx(event);
 }
 
 static void calc_timer_values(struct perf_event *event,
+				u64 *now,
 				u64 *enabled,
 				u64 *running)
 {
-	u64 now, ctx_time;
+	u64 ctx_time;
 
-	now = perf_clock();
-	ctx_time = event->shadow_ctx_time + now;
+	*now = perf_clock();
+	ctx_time = event->shadow_ctx_time + *now;
 	*enabled = ctx_time - event->tstamp_enabled;
 	*running = ctx_time - event->tstamp_running;
 }
 
+void __weak perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)
+{
+}
+
 /*
  * Callers need to ensure there can be no nesting of this function, otherwise
  * the seqlock logic goes bad. We can not serialize this because the arch
@@ -3274,7 +3361,7 @@ void perf_event_update_userpage(struct perf_event *event)
 {
 	struct perf_event_mmap_page *userpg;
 	struct ring_buffer *rb;
-	u64 enabled, running;
+	u64 enabled, running, now;
 
 	rcu_read_lock();
 	/*
@@ -3286,7 +3373,7 @@ void perf_event_update_userpage(struct perf_event *event)
 	 * because of locking issue as we can be called in
 	 * NMI context
 	 */
-	calc_timer_values(event, &enabled, &running);
+	calc_timer_values(event, &now, &enabled, &running);
 	rb = rcu_dereference(event->rb);
 	if (!rb)
 		goto unlock;
@@ -3302,7 +3389,7 @@ void perf_event_update_userpage(struct perf_event *event)
 	barrier();
 	userpg->index = perf_event_index(event);
 	userpg->offset = perf_event_count(event);
-	if (event->state == PERF_EVENT_STATE_ACTIVE)
+	if (userpg->index)
 		userpg->offset -= local64_read(&event->hw.prev_count);
 
 	userpg->time_enabled = enabled +
@@ -3311,6 +3398,8 @@ void perf_event_update_userpage(struct perf_event *event)
 	userpg->time_running = running +
 			atomic64_read(&event->child_total_time_running);
 
+	perf_update_user_clock(userpg, now);
+
 	barrier();
 	++userpg->lock;
 	preempt_enable();
@@ -3568,6 +3657,8 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	event->mmap_user = get_current_user();
 	vma->vm_mm->pinned_vm += event->mmap_locked;
 
+	perf_event_update_userpage(event);
+
 unlock:
 	if (!ret)
 		atomic_inc(&event->mmap_count);
@@ -3799,7 +3890,7 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 static void perf_output_read(struct perf_output_handle *handle,
 			     struct perf_event *event)
 {
-	u64 enabled = 0, running = 0;
+	u64 enabled = 0, running = 0, now;
 	u64 read_format = event->attr.read_format;
 
 	/*
@@ -3812,7 +3903,7 @@ static void perf_output_read(struct perf_output_handle *handle,
 	 * NMI context
 	 */
 	if (read_format & PERF_FORMAT_TOTAL_TIMES)
-		calc_timer_values(event, &enabled, &running);
+		calc_timer_values(event, &now, &enabled, &running);
 
 	if (event->attr.read_format & PERF_FORMAT_GROUP)
 		perf_output_read_group(handle, event, enabled, running);
@@ -3902,6 +3993,24 @@ void perf_output_sample(struct perf_output_handle *handle,
 			}
 		}
 	}
+
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+		if (data->br_stack) {
+			size_t size;
+
+			size = data->br_stack->nr
+			     * sizeof(struct perf_branch_entry);
+
+			perf_output_put(handle, data->br_stack->nr);
+			perf_output_copy(handle, data->br_stack->entries, size);
+		} else {
+			/*
+			 * we always store at least the value of nr
+			 */
+			u64 nr = 0;
+			perf_output_put(handle, nr);
+		}
+	}
 }
 
 void perf_prepare_sample(struct perf_event_header *header,
@@ -3944,6 +4053,15 @@ void perf_prepare_sample(struct perf_event_header *header,
 		WARN_ON_ONCE(size & (sizeof(u64)-1));
 		header->size += size;
 	}
+
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+		int size = sizeof(u64); /* nr */
+		if (data->br_stack) {
+			size += data->br_stack->nr
+			      * sizeof(struct perf_branch_entry);
+		}
+		header->size += size;
+	}
 }
 
 static void perf_event_output(struct perf_event *event,
@@ -4986,7 +5104,7 @@ fail:
 	return err;
 }
 
-struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
+struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
 static void sw_perf_event_destroy(struct perf_event *event)
 {
@@ -4994,7 +5112,7 @@ static void sw_perf_event_destroy(struct perf_event *event)
 
 	WARN_ON(event->parent);
 
-	jump_label_dec(&perf_swevent_enabled[event_id]);
+	static_key_slow_dec(&perf_swevent_enabled[event_id]);
 	swevent_hlist_put(event);
 }
 
@@ -5005,6 +5123,12 @@ static int perf_swevent_init(struct perf_event *event)
 	if (event->attr.type != PERF_TYPE_SOFTWARE)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for software events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event_id) {
 	case PERF_COUNT_SW_CPU_CLOCK:
 	case PERF_COUNT_SW_TASK_CLOCK:
@@ -5024,13 +5148,18 @@ static int perf_swevent_init(struct perf_event *event)
 		if (err)
 			return err;
 
-		jump_label_inc(&perf_swevent_enabled[event_id]);
+		static_key_slow_inc(&perf_swevent_enabled[event_id]);
 		event->destroy = sw_perf_event_destroy;
 	}
 
 	return 0;
 }
 
+static int perf_swevent_event_idx(struct perf_event *event)
+{
+	return 0;
+}
+
 static struct pmu perf_swevent = {
 	.task_ctx_nr	= perf_sw_context,
 
@@ -5040,6 +5169,8 @@ static struct pmu perf_swevent = {
 	.start		= perf_swevent_start,
 	.stop		= perf_swevent_stop,
 	.read		= perf_swevent_read,
+
+	.event_idx	= perf_swevent_event_idx,
 };
 
 #ifdef CONFIG_EVENT_TRACING
@@ -5108,6 +5239,12 @@ static int perf_tp_event_init(struct perf_event *event)
 	if (event->attr.type != PERF_TYPE_TRACEPOINT)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for tracepoint events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	err = perf_trace_init(event);
 	if (err)
 		return err;
@@ -5126,6 +5263,8 @@ static struct pmu perf_tracepoint = {
 	.start		= perf_swevent_start,
 	.stop		= perf_swevent_stop,
 	.read		= perf_swevent_read,
+
+	.event_idx	= perf_swevent_event_idx,
 };
 
 static inline void perf_tp_register(void)
@@ -5331,6 +5470,12 @@ static int cpu_clock_event_init(struct perf_event *event)
 	if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for software events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	perf_swevent_init_hrtimer(event);
 
 	return 0;
@@ -5345,6 +5490,8 @@ static struct pmu perf_cpu_clock = {
 	.start		= cpu_clock_event_start,
 	.stop		= cpu_clock_event_stop,
 	.read		= cpu_clock_event_read,
+
+	.event_idx	= perf_swevent_event_idx,
 };
 
 /*
@@ -5403,6 +5550,12 @@ static int task_clock_event_init(struct perf_event *event)
 	if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for software events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	perf_swevent_init_hrtimer(event);
 
 	return 0;
@@ -5417,6 +5570,8 @@ static struct pmu perf_task_clock = {
 	.start		= task_clock_event_start,
 	.stop		= task_clock_event_stop,
 	.read		= task_clock_event_read,
+
+	.event_idx	= perf_swevent_event_idx,
 };
 
 static void perf_pmu_nop_void(struct pmu *pmu)
@@ -5444,6 +5599,11 @@ static void perf_pmu_cancel_txn(struct pmu *pmu)
 	perf_pmu_enable(pmu);
 }
 
+static int perf_event_idx_default(struct perf_event *event)
+{
+	return event->hw.idx + 1;
+}
+
 /*
  * Ensures all contexts with the same task_ctx_nr have the same
  * pmu_cpu_context too.
@@ -5530,6 +5690,7 @@ static int pmu_dev_alloc(struct pmu *pmu)
 	if (!pmu->dev)
 		goto out;
 
+	pmu->dev->groups = pmu->attr_groups;
 	device_initialize(pmu->dev);
 	ret = dev_set_name(pmu->dev, "%s", pmu->name);
 	if (ret)
@@ -5633,6 +5794,9 @@ got_cpu_context:
 		pmu->pmu_disable = perf_pmu_nop_void;
 	}
 
+	if (!pmu->event_idx)
+		pmu->event_idx = perf_event_idx_default;
+
 	list_add_rcu(&pmu->entry, &pmus);
 	ret = 0;
 unlock:
@@ -5825,7 +5989,7 @@ done:
 
 	if (!event->parent) {
 		if (event->attach_state & PERF_ATTACH_TASK)
-			jump_label_inc(&perf_sched_events.key);
+			static_key_slow_inc(&perf_sched_events.key);
 		if (event->attr.mmap || event->attr.mmap_data)
 			atomic_inc(&nr_mmap_events);
 		if (event->attr.comm)
@@ -5839,6 +6003,12 @@ done:
 				return ERR_PTR(err);
 			}
 		}
+		if (has_branch_stack(event)) {
+			static_key_slow_inc(&perf_sched_events.key);
+			if (!(event->attach_state & PERF_ATTACH_TASK))
+				atomic_inc(&per_cpu(perf_branch_stack_events,
+						    event->cpu));
+		}
 	}
 
 	return event;
@@ -5908,6 +6078,40 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	if (attr->read_format & ~(PERF_FORMAT_MAX-1))
 		return -EINVAL;
 
+	if (attr->sample_type & PERF_SAMPLE_BRANCH_STACK) {
+		u64 mask = attr->branch_sample_type;
+
+		/* only using defined bits */
+		if (mask & ~(PERF_SAMPLE_BRANCH_MAX-1))
+			return -EINVAL;
+
+		/* at least one branch bit must be set */
+		if (!(mask & ~PERF_SAMPLE_BRANCH_PLM_ALL))
+			return -EINVAL;
+
+		/* kernel level capture: check permissions */
+		if ((mask & PERF_SAMPLE_BRANCH_PERM_PLM)
+		    && perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+			return -EACCES;
+
+		/* propagate priv level, when not set for branch */
+		if (!(mask & PERF_SAMPLE_BRANCH_PLM_ALL)) {
+
+			/* exclude_kernel checked on syscall entry */
+			if (!attr->exclude_kernel)
+				mask |= PERF_SAMPLE_BRANCH_KERNEL;
+
+			if (!attr->exclude_user)
+				mask |= PERF_SAMPLE_BRANCH_USER;
+
+			if (!attr->exclude_hv)
+				mask |= PERF_SAMPLE_BRANCH_HV;
+			/*
+			 * adjust user setting (for HW filter setup)
+			 */
+			attr->branch_sample_type = mask;
+		}
+	}
 out:
 	return ret;
 
@@ -6063,7 +6267,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		 * - that may need work on context switch
 		 */
 		atomic_inc(&per_cpu(perf_cgroup_events, event->cpu));
-		jump_label_inc(&perf_sched_events.key);
+		static_key_slow_inc(&perf_sched_events.key);
 	}
 
 	/*
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index ee706ce44aa0..bb38c4d3ee12 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -581,6 +581,12 @@ static int hw_breakpoint_event_init(struct perf_event *bp)
 	if (bp->attr.type != PERF_TYPE_BREAKPOINT)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for breakpoint events
+	 */
+	if (has_branch_stack(bp))
+		return -EOPNOTSUPP;
+
 	err = register_perf_hw_breakpoint(bp);
 	if (err)
 		return err;
@@ -613,6 +619,11 @@ static void hw_breakpoint_stop(struct perf_event *bp, int flags)
 	bp->hw.state = PERF_HES_STOPPED;
 }
 
+static int hw_breakpoint_event_idx(struct perf_event *bp)
+{
+	return 0;
+}
+
 static struct pmu perf_breakpoint = {
 	.task_ctx_nr	= perf_sw_context, /* could eventually get its own */
 
@@ -622,6 +633,8 @@ static struct pmu perf_breakpoint = {
 	.start		= hw_breakpoint_start,
 	.stop		= hw_breakpoint_stop,
 	.read		= hw_breakpoint_pmu_read,
+
+	.event_idx	= hw_breakpoint_event_idx,
 };
 
 int __init init_hw_breakpoint(void)
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 25784d630a12..6080f6bc8c33 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -16,6 +16,8 @@
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 
+#include <trace/events/irq.h>
+
 #include "internals.h"
 
 /**
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 01d3b70fc98a..43049192b5ec 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -12,7 +12,7 @@
 #include <linux/slab.h>
 #include <linux/sort.h>
 #include <linux/err.h>
-#include <linux/jump_label.h>
+#include <linux/static_key.h>
 
 #ifdef HAVE_JUMP_LABEL
 
@@ -29,11 +29,6 @@ void jump_label_unlock(void)
 	mutex_unlock(&jump_label_mutex);
 }
 
-bool jump_label_enabled(struct jump_label_key *key)
-{
-	return !!atomic_read(&key->enabled);
-}
-
 static int jump_label_cmp(const void *a, const void *b)
 {
 	const struct jump_entry *jea = a;
@@ -58,56 +53,66 @@ jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop)
 	sort(start, size, sizeof(struct jump_entry), jump_label_cmp, NULL);
 }
 
-static void jump_label_update(struct jump_label_key *key, int enable);
+static void jump_label_update(struct static_key *key, int enable);
 
-void jump_label_inc(struct jump_label_key *key)
+void static_key_slow_inc(struct static_key *key)
 {
 	if (atomic_inc_not_zero(&key->enabled))
 		return;
 
 	jump_label_lock();
-	if (atomic_read(&key->enabled) == 0)
-		jump_label_update(key, JUMP_LABEL_ENABLE);
+	if (atomic_read(&key->enabled) == 0) {
+		if (!jump_label_get_branch_default(key))
+			jump_label_update(key, JUMP_LABEL_ENABLE);
+		else
+			jump_label_update(key, JUMP_LABEL_DISABLE);
+	}
 	atomic_inc(&key->enabled);
 	jump_label_unlock();
 }
-EXPORT_SYMBOL_GPL(jump_label_inc);
+EXPORT_SYMBOL_GPL(static_key_slow_inc);
 
-static void __jump_label_dec(struct jump_label_key *key,
+static void __static_key_slow_dec(struct static_key *key,
 		unsigned long rate_limit, struct delayed_work *work)
 {
-	if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex))
+	if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
+		WARN(atomic_read(&key->enabled) < 0,
+		     "jump label: negative count!\n");
 		return;
+	}
 
 	if (rate_limit) {
 		atomic_inc(&key->enabled);
 		schedule_delayed_work(work, rate_limit);
-	} else
-		jump_label_update(key, JUMP_LABEL_DISABLE);
-
+	} else {
+		if (!jump_label_get_branch_default(key))
+			jump_label_update(key, JUMP_LABEL_DISABLE);
+		else
+			jump_label_update(key, JUMP_LABEL_ENABLE);
+	}
 	jump_label_unlock();
 }
-EXPORT_SYMBOL_GPL(jump_label_dec);
 
 static void jump_label_update_timeout(struct work_struct *work)
 {
-	struct jump_label_key_deferred *key =
-		container_of(work, struct jump_label_key_deferred, work.work);
-	__jump_label_dec(&key->key, 0, NULL);
+	struct static_key_deferred *key =
+		container_of(work, struct static_key_deferred, work.work);
+	__static_key_slow_dec(&key->key, 0, NULL);
 }
 
-void jump_label_dec(struct jump_label_key *key)
+void static_key_slow_dec(struct static_key *key)
 {
-	__jump_label_dec(key, 0, NULL);
+	__static_key_slow_dec(key, 0, NULL);
 }
+EXPORT_SYMBOL_GPL(static_key_slow_dec);
 
-void jump_label_dec_deferred(struct jump_label_key_deferred *key)
+void static_key_slow_dec_deferred(struct static_key_deferred *key)
 {
-	__jump_label_dec(&key->key, key->timeout, &key->work);
+	__static_key_slow_dec(&key->key, key->timeout, &key->work);
 }
+EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
 
-
-void jump_label_rate_limit(struct jump_label_key_deferred *key,
+void jump_label_rate_limit(struct static_key_deferred *key,
 		unsigned long rl)
 {
 	key->timeout = rl;
@@ -150,7 +155,7 @@ void __weak __init_or_module arch_jump_label_transform_static(struct jump_entry
 	arch_jump_label_transform(entry, type);	
 }
 
-static void __jump_label_update(struct jump_label_key *key,
+static void __jump_label_update(struct static_key *key,
 				struct jump_entry *entry,
 				struct jump_entry *stop, int enable)
 {
@@ -167,27 +172,40 @@ static void __jump_label_update(struct jump_label_key *key,
 	}
 }
 
+static enum jump_label_type jump_label_type(struct static_key *key)
+{
+	bool true_branch = jump_label_get_branch_default(key);
+	bool state = static_key_enabled(key);
+
+	if ((!true_branch && state) || (true_branch && !state))
+		return JUMP_LABEL_ENABLE;
+
+	return JUMP_LABEL_DISABLE;
+}
+
 void __init jump_label_init(void)
 {
 	struct jump_entry *iter_start = __start___jump_table;
 	struct jump_entry *iter_stop = __stop___jump_table;
-	struct jump_label_key *key = NULL;
+	struct static_key *key = NULL;
 	struct jump_entry *iter;
 
 	jump_label_lock();
 	jump_label_sort_entries(iter_start, iter_stop);
 
 	for (iter = iter_start; iter < iter_stop; iter++) {
-		struct jump_label_key *iterk;
+		struct static_key *iterk;
 
-		iterk = (struct jump_label_key *)(unsigned long)iter->key;
-		arch_jump_label_transform_static(iter, jump_label_enabled(iterk) ?
-						 JUMP_LABEL_ENABLE : JUMP_LABEL_DISABLE);
+		iterk = (struct static_key *)(unsigned long)iter->key;
+		arch_jump_label_transform_static(iter, jump_label_type(iterk));
 		if (iterk == key)
 			continue;
 
 		key = iterk;
-		key->entries = iter;
+		/*
+		 * Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH.
+		 */
+		*((unsigned long *)&key->entries) += (unsigned long)iter;
 #ifdef CONFIG_MODULES
 		key->next = NULL;
 #endif
@@ -197,8 +215,8 @@ void __init jump_label_init(void)
 
 #ifdef CONFIG_MODULES
 
-struct jump_label_mod {
-	struct jump_label_mod *next;
+struct static_key_mod {
+	struct static_key_mod *next;
 	struct jump_entry *entries;
 	struct module *mod;
 };
@@ -218,9 +236,9 @@ static int __jump_label_mod_text_reserved(void *start, void *end)
 				start, end);
 }
 
-static void __jump_label_mod_update(struct jump_label_key *key, int enable)
+static void __jump_label_mod_update(struct static_key *key, int enable)
 {
-	struct jump_label_mod *mod = key->next;
+	struct static_key_mod *mod = key->next;
 
 	while (mod) {
 		struct module *m = mod->mod;
@@ -251,11 +269,7 @@ void jump_label_apply_nops(struct module *mod)
 		return;
 
 	for (iter = iter_start; iter < iter_stop; iter++) {
-		struct jump_label_key *iterk;
-
-		iterk = (struct jump_label_key *)(unsigned long)iter->key;
-		arch_jump_label_transform_static(iter, jump_label_enabled(iterk) ?
-				JUMP_LABEL_ENABLE : JUMP_LABEL_DISABLE);
+		arch_jump_label_transform_static(iter, JUMP_LABEL_DISABLE);
 	}
 }
 
@@ -264,8 +278,8 @@ static int jump_label_add_module(struct module *mod)
 	struct jump_entry *iter_start = mod->jump_entries;
 	struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
 	struct jump_entry *iter;
-	struct jump_label_key *key = NULL;
-	struct jump_label_mod *jlm;
+	struct static_key *key = NULL;
+	struct static_key_mod *jlm;
 
 	/* if the module doesn't have jump label entries, just return */
 	if (iter_start == iter_stop)
@@ -274,28 +288,30 @@ static int jump_label_add_module(struct module *mod)
 	jump_label_sort_entries(iter_start, iter_stop);
 
 	for (iter = iter_start; iter < iter_stop; iter++) {
-		if (iter->key == (jump_label_t)(unsigned long)key)
-			continue;
+		struct static_key *iterk;
 
-		key = (struct jump_label_key *)(unsigned long)iter->key;
+		iterk = (struct static_key *)(unsigned long)iter->key;
+		if (iterk == key)
+			continue;
 
+		key = iterk;
 		if (__module_address(iter->key) == mod) {
-			atomic_set(&key->enabled, 0);
-			key->entries = iter;
+			/*
+			 * Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH.
+			 */
+			*((unsigned long *)&key->entries) += (unsigned long)iter;
 			key->next = NULL;
 			continue;
 		}
-
-		jlm = kzalloc(sizeof(struct jump_label_mod), GFP_KERNEL);
+		jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL);
 		if (!jlm)
 			return -ENOMEM;
-
 		jlm->mod = mod;
 		jlm->entries = iter;
 		jlm->next = key->next;
 		key->next = jlm;
 
-		if (jump_label_enabled(key))
+		if (jump_label_type(key) == JUMP_LABEL_ENABLE)
 			__jump_label_update(key, iter, iter_stop, JUMP_LABEL_ENABLE);
 	}
 
@@ -307,14 +323,14 @@ static void jump_label_del_module(struct module *mod)
 	struct jump_entry *iter_start = mod->jump_entries;
 	struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
 	struct jump_entry *iter;
-	struct jump_label_key *key = NULL;
-	struct jump_label_mod *jlm, **prev;
+	struct static_key *key = NULL;
+	struct static_key_mod *jlm, **prev;
 
 	for (iter = iter_start; iter < iter_stop; iter++) {
 		if (iter->key == (jump_label_t)(unsigned long)key)
 			continue;
 
-		key = (struct jump_label_key *)(unsigned long)iter->key;
+		key = (struct static_key *)(unsigned long)iter->key;
 
 		if (__module_address(iter->key) == mod)
 			continue;