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
  ...

9 files changed, 330 insertions, 72 deletions

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 028e26f0bf08..72a6cabb4d5b 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -31,16 +31,33 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip);
 
+/*
+ * FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are
+ * set in the flags member.
+ *
+ * ENABLED - set/unset when ftrace_ops is registered/unregistered
+ * GLOBAL  - set manualy by ftrace_ops user to denote the ftrace_ops
+ *           is part of the global tracers sharing the same filter
+ *           via set_ftrace_* debugfs files.
+ * DYNAMIC - set when ftrace_ops is registered to denote dynamically
+ *           allocated ftrace_ops which need special care
+ * CONTROL - set manualy by ftrace_ops user to denote the ftrace_ops
+ *           could be controled by following calls:
+ *             ftrace_function_local_enable
+ *             ftrace_function_local_disable
+ */
 enum {
 	FTRACE_OPS_FL_ENABLED		= 1 << 0,
 	FTRACE_OPS_FL_GLOBAL		= 1 << 1,
 	FTRACE_OPS_FL_DYNAMIC		= 1 << 2,
+	FTRACE_OPS_FL_CONTROL		= 1 << 3,
 };
 
 struct ftrace_ops {
 	ftrace_func_t			func;
 	struct ftrace_ops		*next;
 	unsigned long			flags;
+	int __percpu			*disabled;
 #ifdef CONFIG_DYNAMIC_FTRACE
 	struct ftrace_hash		*notrace_hash;
 	struct ftrace_hash		*filter_hash;
@@ -97,6 +114,55 @@ int register_ftrace_function(struct ftrace_ops *ops);
 int unregister_ftrace_function(struct ftrace_ops *ops);
 void clear_ftrace_function(void);
 
+/**
+ * ftrace_function_local_enable - enable controlled ftrace_ops on current cpu
+ *
+ * This function enables tracing on current cpu by decreasing
+ * the per cpu control variable.
+ * It must be called with preemption disabled and only on ftrace_ops
+ * registered with FTRACE_OPS_FL_CONTROL. If called without preemption
+ * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
+ */
+static inline void ftrace_function_local_enable(struct ftrace_ops *ops)
+{
+	if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL)))
+		return;
+
+	(*this_cpu_ptr(ops->disabled))--;
+}
+
+/**
+ * ftrace_function_local_disable - enable controlled ftrace_ops on current cpu
+ *
+ * This function enables tracing on current cpu by decreasing
+ * the per cpu control variable.
+ * It must be called with preemption disabled and only on ftrace_ops
+ * registered with FTRACE_OPS_FL_CONTROL. If called without preemption
+ * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
+ */
+static inline void ftrace_function_local_disable(struct ftrace_ops *ops)
+{
+	if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL)))
+		return;
+
+	(*this_cpu_ptr(ops->disabled))++;
+}
+
+/**
+ * ftrace_function_local_disabled - returns ftrace_ops disabled value
+ *                                  on current cpu
+ *
+ * This function returns value of ftrace_ops::disabled on current cpu.
+ * It must be called with preemption disabled and only on ftrace_ops
+ * registered with FTRACE_OPS_FL_CONTROL. If called without preemption
+ * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
+ */
+static inline int ftrace_function_local_disabled(struct ftrace_ops *ops)
+{
+	WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL));
+	return *this_cpu_ptr(ops->disabled);
+}
+
 extern void ftrace_stub(unsigned long a0, unsigned long a1);
 
 #else /* !CONFIG_FUNCTION_TRACER */
@@ -178,12 +244,13 @@ struct dyn_ftrace {
 };
 
 int ftrace_force_update(void);
-void ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
+int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
 		       int len, int reset);
-void ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
+int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
 			int len, int reset);
 void ftrace_set_global_filter(unsigned char *buf, int len, int reset);
 void ftrace_set_global_notrace(unsigned char *buf, int len, int reset);
+void ftrace_free_filter(struct ftrace_ops *ops);
 
 int register_ftrace_command(struct ftrace_func_command *cmd);
 int unregister_ftrace_command(struct ftrace_func_command *cmd);
@@ -314,9 +381,6 @@ extern void ftrace_enable_daemon(void);
 #else
 static inline int skip_trace(unsigned long ip) { return 0; }
 static inline int ftrace_force_update(void) { return 0; }
-static inline void ftrace_set_filter(unsigned char *buf, int len, int reset)
-{
-}
 static inline void ftrace_disable_daemon(void) { }
 static inline void ftrace_enable_daemon(void) { }
 static inline void ftrace_release_mod(struct module *mod) {}
@@ -340,6 +404,9 @@ static inline int ftrace_text_reserved(void *start, void *end)
  */
 #define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; })
 #define ftrace_set_early_filter(ops, buf, enable) do { } while (0)
+#define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; })
+#define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; })
+#define ftrace_free_filter(ops) do { } while (0)
 
 static inline ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf,
 			    size_t cnt, loff_t *ppos) { return -ENODEV; }
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index c3da42dd22ba..dd478fc8f9f5 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -146,6 +146,10 @@ enum trace_reg {
 	TRACE_REG_UNREGISTER,
 	TRACE_REG_PERF_REGISTER,
 	TRACE_REG_PERF_UNREGISTER,
+	TRACE_REG_PERF_OPEN,
+	TRACE_REG_PERF_CLOSE,
+	TRACE_REG_PERF_ADD,
+	TRACE_REG_PERF_DEL,
 };
 
 struct ftrace_event_call;
@@ -157,7 +161,7 @@ struct ftrace_event_class {
 	void			*perf_probe;
 #endif
 	int			(*reg)(struct ftrace_event_call *event,
-				       enum trace_reg type);
+				       enum trace_reg type, void *data);
 	int			(*define_fields)(struct ftrace_event_call *);
 	struct list_head	*(*get_fields)(struct ftrace_event_call *);
 	struct list_head	fields;
@@ -165,7 +169,7 @@ struct ftrace_event_class {
 };
 
 extern int ftrace_event_reg(struct ftrace_event_call *event,
-			    enum trace_reg type);
+			    enum trace_reg type, void *data);
 
 enum {
 	TRACE_EVENT_FL_ENABLED_BIT,
@@ -241,6 +245,7 @@ enum {
 	FILTER_STATIC_STRING,
 	FILTER_DYN_STRING,
 	FILTER_PTR_STRING,
+	FILTER_TRACE_FN,
 };
 
 #define EVENT_STORAGE_SIZE 128
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index a64b00e286f5..3f830e005118 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -20,7 +20,6 @@
 #include <linux/atomic.h>
 #include <asm/ptrace.h>
 #include <asm/system.h>
-#include <trace/events/irq.h>
 
 /*
  * These correspond to the IORESOURCE_IRQ_* defines in
@@ -456,11 +455,7 @@ asmlinkage void do_softirq(void);
 asmlinkage void __do_softirq(void);
 extern void open_softirq(int nr, void (*action)(struct softirq_action *));
 extern void softirq_init(void);
-static inline void __raise_softirq_irqoff(unsigned int nr)
-{
-	trace_softirq_raise(nr);
-	or_softirq_pending(1UL << nr);
-}
+extern void __raise_softirq_irqoff(unsigned int nr);
 
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 5ce8b140428f..c513a40510f5 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -1,22 +1,69 @@
 #ifndef _LINUX_JUMP_LABEL_H
 #define _LINUX_JUMP_LABEL_H
 
+/*
+ * Jump label support
+ *
+ * Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com>
+ * Copyright (C) 2011-2012 Peter Zijlstra <pzijlstr@redhat.com>
+ *
+ * Jump labels provide an interface to generate dynamic branches using
+ * self-modifying code. Assuming toolchain and architecture support the result
+ * of a "if (static_key_false(&key))" statement is a unconditional branch (which
+ * defaults to false - and the true block is placed out of line).
+ *
+ * However at runtime we can change the branch target using
+ * static_key_slow_{inc,dec}(). These function as a 'reference' count on the key
+ * object and for as long as there are references all branches referring to
+ * that particular key will point to the (out of line) true block.
+ *
+ * Since this relies on modifying code the static_key_slow_{inc,dec}() functions
+ * must be considered absolute slow paths (machine wide synchronization etc.).
+ * OTOH, since the affected branches are unconditional their runtime overhead
+ * will be absolutely minimal, esp. in the default (off) case where the total
+ * effect is a single NOP of appropriate size. The on case will patch in a jump
+ * to the out-of-line block.
+ *
+ * When the control is directly exposed to userspace it is prudent to delay the
+ * decrement to avoid high frequency code modifications which can (and do)
+ * cause significant performance degradation. Struct static_key_deferred and
+ * static_key_slow_dec_deferred() provide for this.
+ *
+ * Lacking toolchain and or architecture support, it falls back to a simple
+ * conditional branch.
+ *
+ * struct static_key my_key = STATIC_KEY_INIT_TRUE;
+ *
+ *   if (static_key_true(&my_key)) {
+ *   }
+ *
+ * will result in the true case being in-line and starts the key with a single
+ * reference. Mixing static_key_true() and static_key_false() on the same key is not
+ * allowed.
+ *
+ * Not initializing the key (static data is initialized to 0s anyway) is the
+ * same as using STATIC_KEY_INIT_FALSE and static_key_false() is
+ * equivalent with static_branch().
+ *
+*/
+
 #include <linux/types.h>
 #include <linux/compiler.h>
 #include <linux/workqueue.h>
 
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
 
-struct jump_label_key {
+struct static_key {
 	atomic_t enabled;
+/* Set lsb bit to 1 if branch is default true, 0 ot */
 	struct jump_entry *entries;
 #ifdef CONFIG_MODULES
-	struct jump_label_mod *next;
+	struct static_key_mod *next;
 #endif
 };
 
-struct jump_label_key_deferred {
-	struct jump_label_key key;
+struct static_key_deferred {
+	struct static_key key;
 	unsigned long timeout;
 	struct delayed_work work;
 };
@@ -34,13 +81,34 @@ struct module;
 
 #ifdef HAVE_JUMP_LABEL
 
-#ifdef CONFIG_MODULES
-#define JUMP_LABEL_INIT {ATOMIC_INIT(0), NULL, NULL}
-#else
-#define JUMP_LABEL_INIT {ATOMIC_INIT(0), NULL}
-#endif
+#define JUMP_LABEL_TRUE_BRANCH 1UL
+
+static
+inline struct jump_entry *jump_label_get_entries(struct static_key *key)
+{
+	return (struct jump_entry *)((unsigned long)key->entries
+						& ~JUMP_LABEL_TRUE_BRANCH);
+}
 
-static __always_inline bool static_branch(struct jump_label_key *key)
+static inline bool jump_label_get_branch_default(struct static_key *key)
+{
+	if ((unsigned long)key->entries & JUMP_LABEL_TRUE_BRANCH)
+		return true;
+	return false;
+}
+
+static __always_inline bool static_key_false(struct static_key *key)
+{
+	return arch_static_branch(key);
+}
+
+static __always_inline bool static_key_true(struct static_key *key)
+{
+	return !static_key_false(key);
+}
+
+/* Deprecated. Please use 'static_key_false() instead. */
+static __always_inline bool static_branch(struct static_key *key)
 {
 	return arch_static_branch(key);
 }
@@ -56,21 +124,23 @@ extern void arch_jump_label_transform(struct jump_entry *entry,
 extern void arch_jump_label_transform_static(struct jump_entry *entry,
 					     enum jump_label_type type);
 extern int jump_label_text_reserved(void *start, void *end);
-extern void jump_label_inc(struct jump_label_key *key);
-extern void jump_label_dec(struct jump_label_key *key);
-extern void jump_label_dec_deferred(struct jump_label_key_deferred *key);
-extern bool jump_label_enabled(struct jump_label_key *key);
+extern void static_key_slow_inc(struct static_key *key);
+extern void static_key_slow_dec(struct static_key *key);
+extern void static_key_slow_dec_deferred(struct static_key_deferred *key);
 extern void jump_label_apply_nops(struct module *mod);
-extern void jump_label_rate_limit(struct jump_label_key_deferred *key,
-		unsigned long rl);
+extern void
+jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl);
+
+#define STATIC_KEY_INIT_TRUE ((struct static_key) \
+	{ .enabled = ATOMIC_INIT(1), .entries = (void *)1 })
+#define STATIC_KEY_INIT_FALSE ((struct static_key) \
+	{ .enabled = ATOMIC_INIT(0), .entries = (void *)0 })
 
 #else  /* !HAVE_JUMP_LABEL */
 
 #include <linux/atomic.h>
 
-#define JUMP_LABEL_INIT {ATOMIC_INIT(0)}
-
-struct jump_label_key {
+struct static_key {
 	atomic_t enabled;
 };
 
@@ -78,30 +148,45 @@ static __always_inline void jump_label_init(void)
 {
 }
 
-struct jump_label_key_deferred {
-	struct jump_label_key  key;
+struct static_key_deferred {
+	struct static_key  key;
 };
 
-static __always_inline bool static_branch(struct jump_label_key *key)
+static __always_inline bool static_key_false(struct static_key *key)
+{
+	if (unlikely(atomic_read(&key->enabled)) > 0)
+		return true;
+	return false;
+}
+
+static __always_inline bool static_key_true(struct static_key *key)
 {
-	if (unlikely(atomic_read(&key->enabled)))
+	if (likely(atomic_read(&key->enabled)) > 0)
 		return true;
 	return false;
 }
 
-static inline void jump_label_inc(struct jump_label_key *key)
+/* Deprecated. Please use 'static_key_false() instead. */
+static __always_inline bool static_branch(struct static_key *key)
+{
+	if (unlikely(atomic_read(&key->enabled)) > 0)
+		return true;
+	return false;
+}
+
+static inline void static_key_slow_inc(struct static_key *key)
 {
 	atomic_inc(&key->enabled);
 }
 
-static inline void jump_label_dec(struct jump_label_key *key)
+static inline void static_key_slow_dec(struct static_key *key)
 {
 	atomic_dec(&key->enabled);
 }
 
-static inline void jump_label_dec_deferred(struct jump_label_key_deferred *key)
+static inline void static_key_slow_dec_deferred(struct static_key_deferred *key)
 {
-	jump_label_dec(&key->key);
+	static_key_slow_dec(&key->key);
 }
 
 static inline int jump_label_text_reserved(void *start, void *end)
@@ -112,23 +197,30 @@ static inline int jump_label_text_reserved(void *start, void *end)
 static inline void jump_label_lock(void) {}
 static inline void jump_label_unlock(void) {}
 
-static inline bool jump_label_enabled(struct jump_label_key *key)
-{
-	return !!atomic_read(&key->enabled);
-}
-
 static inline int jump_label_apply_nops(struct module *mod)
 {
 	return 0;
 }
 
-static inline void jump_label_rate_limit(struct jump_label_key_deferred *key,
+static inline void
+jump_label_rate_limit(struct static_key_deferred *key,
 		unsigned long rl)
 {
 }
+
+#define STATIC_KEY_INIT_TRUE ((struct static_key) \
+		{ .enabled = ATOMIC_INIT(1) })
+#define STATIC_KEY_INIT_FALSE ((struct static_key) \
+		{ .enabled = ATOMIC_INIT(0) })
+
 #endif	/* HAVE_JUMP_LABEL */
 
-#define jump_label_key_enabled	((struct jump_label_key){ .enabled = ATOMIC_INIT(1), })
-#define jump_label_key_disabled	((struct jump_label_key){ .enabled = ATOMIC_INIT(0), })
+#define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE
+#define jump_label_enabled static_key_enabled
+
+static inline bool static_key_enabled(struct static_key *key)
+{
+	return (atomic_read(&key->enabled) > 0);
+}
 
 #endif	/* _LINUX_JUMP_LABEL_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0eac07c95255..7dfaae7846ab 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -214,8 +214,8 @@ enum {
 #include <linux/skbuff.h>
 
 #ifdef CONFIG_RPS
-#include <linux/jump_label.h>
-extern struct jump_label_key rps_needed;
+#include <linux/static_key.h>
+extern struct static_key rps_needed;
 #endif
 
 struct neighbour;
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index b809265607d0..29734be334c1 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -163,13 +163,13 @@ extern struct ctl_path nf_net_ipv4_netfilter_sysctl_path[];
 extern struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
 
 #if defined(CONFIG_JUMP_LABEL)
-#include <linux/jump_label.h>
-extern struct jump_label_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
+#include <linux/static_key.h>
+extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
 static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook)
 {
 	if (__builtin_constant_p(pf) &&
 	    __builtin_constant_p(hook))
-		return static_branch(&nf_hooks_needed[pf][hook]);
+		return static_key_false(&nf_hooks_needed[pf][hook]);
 
 	return !list_empty(&nf_hooks[pf][hook]);
 }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index abb2776be1ba..bd9f55a5958d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -129,11 +129,40 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_PERIOD			= 1U << 8,
 	PERF_SAMPLE_STREAM_ID			= 1U << 9,
 	PERF_SAMPLE_RAW				= 1U << 10,
+	PERF_SAMPLE_BRANCH_STACK		= 1U << 11,
 
-	PERF_SAMPLE_MAX = 1U << 11,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 12,		/* non-ABI */
 };
 
 /*
+ * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set
+ *
+ * If the user does not pass priv level information via branch_sample_type,
+ * the kernel uses the event's priv level. Branch and event priv levels do
+ * not have to match. Branch priv level is checked for permissions.
+ *
+ * The branch types can be combined, however BRANCH_ANY covers all types
+ * of branches and therefore it supersedes all the other types.
+ */
+enum perf_branch_sample_type {
+	PERF_SAMPLE_BRANCH_USER		= 1U << 0, /* user branches */
+	PERF_SAMPLE_BRANCH_KERNEL	= 1U << 1, /* kernel branches */
+	PERF_SAMPLE_BRANCH_HV		= 1U << 2, /* hypervisor branches */
+
+	PERF_SAMPLE_BRANCH_ANY		= 1U << 3, /* any branch types */
+	PERF_SAMPLE_BRANCH_ANY_CALL	= 1U << 4, /* any call branch */
+	PERF_SAMPLE_BRANCH_ANY_RETURN	= 1U << 5, /* any return branch */
+	PERF_SAMPLE_BRANCH_IND_CALL	= 1U << 6, /* indirect calls */
+
+	PERF_SAMPLE_BRANCH_MAX		= 1U << 7, /* non-ABI */
+};
+
+#define PERF_SAMPLE_BRANCH_PLM_ALL \
+	(PERF_SAMPLE_BRANCH_USER|\
+	 PERF_SAMPLE_BRANCH_KERNEL|\
+	 PERF_SAMPLE_BRANCH_HV)
+
+/*
  * The format of the data returned by read() on a perf event fd,
  * as specified by attr.read_format:
  *
@@ -163,6 +192,8 @@ enum perf_event_read_format {
 };
 
 #define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
+#define PERF_ATTR_SIZE_VER1	72	/* add: config2 */
+#define PERF_ATTR_SIZE_VER2	80	/* add: branch_sample_type */
 
 /*
  * Hardware event_id to monitor via a performance monitoring event:
@@ -240,6 +271,7 @@ struct perf_event_attr {
 		__u64		bp_len;
 		__u64		config2; /* extension of config1 */
 	};
+	__u64	branch_sample_type; /* enum branch_sample_type */
 };
 
 /*
@@ -291,12 +323,14 @@ struct perf_event_mmap_page {
 	__s64	offset;			/* add to hardware event value */
 	__u64	time_enabled;		/* time event active */
 	__u64	time_running;		/* time event on cpu */
+	__u32	time_mult, time_shift;
+	__u64	time_offset;
 
 		/*
 		 * Hole for extension of the self monitor capabilities
 		 */
 
-	__u64	__reserved[123];	/* align to 1k */
+	__u64	__reserved[121];	/* align to 1k */
 
 	/*
 	 * Control data for the mmap() data buffer.
@@ -456,6 +490,8 @@ enum perf_event_type {
 	 *
 	 *	{ u32			size;
 	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
+	 *
+	 *	{ u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
@@ -512,7 +548,7 @@ struct perf_guest_info_callbacks {
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
 #include <linux/irq_work.h>
-#include <linux/jump_label.h>
+#include <linux/static_key.h>
 #include <linux/atomic.h>
 #include <asm/local.h>
 
@@ -528,12 +564,34 @@ struct perf_raw_record {
 	void				*data;
 };
 
+/*
+ * single taken branch record layout:
+ *
+ *      from: source instruction (may not always be a branch insn)
+ *        to: branch target
+ *   mispred: branch target was mispredicted
+ * predicted: branch target was predicted
+ *
+ * support for mispred, predicted is optional. In case it
+ * is not supported mispred = predicted = 0.
+ */
 struct perf_branch_entry {
-	__u64				from;
-	__u64				to;
-	__u64				flags;
+	__u64	from;
+	__u64	to;
+	__u64	mispred:1,  /* target mispredicted */
+		predicted:1,/* target predicted */
+		reserved:62;
 };
 
+/*
+ * branch stack layout:
+ *  nr: number of taken branches stored in entries[]
+ *
+ * Note that nr can vary from sample to sample
+ * branches (to, from) are stored from most recent
+ * to least recent, i.e., entries[0] contains the most
+ * recent branch.
+ */
 struct perf_branch_stack {
 	__u64				nr;
 	struct perf_branch_entry	entries[0];
@@ -564,7 +622,9 @@ struct hw_perf_event {
 			unsigned long	event_base;
 			int		idx;
 			int		last_cpu;
+
 			struct hw_perf_event_extra extra_reg;
+			struct hw_perf_event_extra branch_reg;
 		};
 		struct { /* software */
 			struct hrtimer	hrtimer;
@@ -616,6 +676,7 @@ struct pmu {
 	struct list_head		entry;
 
 	struct device			*dev;
+	const struct attribute_group	**attr_groups;
 	char				*name;
 	int				type;
 
@@ -681,6 +742,17 @@ struct pmu {
 	 * for each successful ->add() during the transaction.
 	 */
 	void (*cancel_txn)		(struct pmu *pmu); /* optional */
+
+	/*
+	 * Will return the value for perf_event_mmap_page::index for this event,
+	 * if no implementation is provided it will default to: event->hw.idx + 1.
+	 */
+	int (*event_idx)		(struct perf_event *event); /*optional */
+
+	/*
+	 * flush branch stack on context-switches (needed in cpu-wide mode)
+	 */
+	void (*flush_branch_stack)	(void);
 };
 
 /**
@@ -850,6 +922,9 @@ struct perf_event {
 #ifdef CONFIG_EVENT_TRACING
 	struct ftrace_event_call	*tp_event;
 	struct event_filter		*filter;
+#ifdef CONFIG_FUNCTION_TRACER
+	struct ftrace_ops               ftrace_ops;
+#endif
 #endif
 
 #ifdef CONFIG_CGROUP_PERF
@@ -911,7 +986,8 @@ struct perf_event_context {
 	u64				parent_gen;
 	u64				generation;
 	int				pin_count;
-	int				nr_cgroups; /* cgroup events present */
+	int				nr_cgroups;	 /* cgroup evts */
+	int				nr_branch_stack; /* branch_stack evt */
 	struct rcu_head			rcu_head;
 };
 
@@ -976,6 +1052,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr,
 extern u64 perf_event_read_value(struct perf_event *event,
 				 u64 *enabled, u64 *running);
 
+
 struct perf_sample_data {
 	u64				type;
 
@@ -995,12 +1072,14 @@ struct perf_sample_data {
 	u64				period;
 	struct perf_callchain_entry	*callchain;
 	struct perf_raw_record		*raw;
+	struct perf_branch_stack	*br_stack;
 };
 
 static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr)
 {
 	data->addr = addr;
 	data->raw  = NULL;
+	data->br_stack = NULL;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
@@ -1029,7 +1108,7 @@ static inline int is_software_event(struct perf_event *event)
 	return event->pmu->task_ctx_nr == perf_sw_context;
 }
 
-extern struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
+extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
 extern void __perf_sw_event(u32, u64, struct pt_regs *, u64);
 
@@ -1057,7 +1136,7 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
 {
 	struct pt_regs hot_regs;
 
-	if (static_branch(&perf_swevent_enabled[event_id])) {
+	if (static_key_false(&perf_swevent_enabled[event_id])) {
 		if (!regs) {
 			perf_fetch_caller_regs(&hot_regs);
 			regs = &hot_regs;
@@ -1066,12 +1145,12 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
 	}
 }
 
-extern struct jump_label_key_deferred perf_sched_events;
+extern struct static_key_deferred perf_sched_events;
 
 static inline void perf_event_task_sched_in(struct task_struct *prev,
 					    struct task_struct *task)
 {
-	if (static_branch(&perf_sched_events.key))
+	if (static_key_false(&perf_sched_events.key))
 		__perf_event_task_sched_in(prev, task);
 }
 
@@ -1080,7 +1159,7 @@ static inline void perf_event_task_sched_out(struct task_struct *prev,
 {
 	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
 
-	if (static_branch(&perf_sched_events.key))
+	if (static_key_false(&perf_sched_events.key))
 		__perf_event_task_sched_out(prev, next);
 }
 
@@ -1139,6 +1218,11 @@ extern void perf_bp_event(struct perf_event *event, void *data);
 # define perf_instruction_pointer(regs)	instruction_pointer(regs)
 #endif
 
+static inline bool has_branch_stack(struct perf_event *event)
+{
+	return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
+}
+
 extern int perf_output_begin(struct perf_output_handle *handle,
 			     struct perf_event *event, unsigned int size);
 extern void perf_output_end(struct perf_output_handle *handle);
diff --git a/include/linux/static_key.h b/include/linux/static_key.h
new file mode 100644
index 000000000000..27bd3f8a0857
--- /dev/null
+++ b/include/linux/static_key.h
@@ -0,0 +1 @@
+#include <linux/jump_label.h>
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index df0a779c1bbd..bd96ecd0e05c 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -17,7 +17,7 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/rcupdate.h>
-#include <linux/jump_label.h>
+#include <linux/static_key.h>
 
 struct module;
 struct tracepoint;
@@ -29,7 +29,7 @@ struct tracepoint_func {
 
 struct tracepoint {
 	const char *name;		/* Tracepoint name */
-	struct jump_label_key key;
+	struct static_key key;
 	void (*regfunc)(void);
 	void (*unregfunc)(void);
 	struct tracepoint_func __rcu *funcs;
@@ -114,7 +114,7 @@ static inline void tracepoint_synchronize_unregister(void)
  * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just
  * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto".
  */
-#define __DO_TRACE(tp, proto, args, cond)				\
+#define __DO_TRACE(tp, proto, args, cond, prercu, postrcu)		\
 	do {								\
 		struct tracepoint_func *it_func_ptr;			\
 		void *it_func;						\
@@ -122,6 +122,7 @@ static inline void tracepoint_synchronize_unregister(void)
 									\
 		if (!(cond))						\
 			return;						\
+		prercu;							\
 		rcu_read_lock_sched_notrace();				\
 		it_func_ptr = rcu_dereference_sched((tp)->funcs);	\
 		if (it_func_ptr) {					\
@@ -132,6 +133,7 @@ static inline void tracepoint_synchronize_unregister(void)
 			} while ((++it_func_ptr)->func);		\
 		}							\
 		rcu_read_unlock_sched_notrace();			\
+		postrcu;						\
 	} while (0)
 
 /*
@@ -139,15 +141,25 @@ static inline void tracepoint_synchronize_unregister(void)
  * not add unwanted padding between the beginning of the section and the
  * structure. Force alignment to the same alignment as the section start.
  */
-#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args)	\
+#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
 	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
+		if (static_key_false(&__tracepoint_##name.key))		\
+			__DO_TRACE(&__tracepoint_##name,		\
+				TP_PROTO(data_proto),			\
+				TP_ARGS(data_args),			\
+				TP_CONDITION(cond),,);			\
+	}								\
+	static inline void trace_##name##_rcuidle(proto)		\
+	{								\
 		if (static_branch(&__tracepoint_##name.key))		\
 			__DO_TRACE(&__tracepoint_##name,		\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
-				TP_CONDITION(cond));			\
+				TP_CONDITION(cond),			\
+				rcu_idle_exit(),			\
+				rcu_idle_enter());			\
 	}								\
 	static inline int						\
 	register_trace_##name(void (*probe)(data_proto), void *data)	\
@@ -176,7 +188,7 @@ static inline void tracepoint_synchronize_unregister(void)
 	__attribute__((section("__tracepoints_strings"))) = #name;	 \
 	struct tracepoint __tracepoint_##name				 \
 	__attribute__((section("__tracepoints"))) =			 \
-		{ __tpstrtab_##name, JUMP_LABEL_INIT, reg, unreg, NULL };\
+		{ __tpstrtab_##name, STATIC_KEY_INIT_FALSE, reg, unreg, NULL };\
 	static struct tracepoint * const __tracepoint_ptr_##name __used	 \
 	__attribute__((section("__tracepoints_ptrs"))) =		 \
 		&__tracepoint_##name;
@@ -190,9 +202,11 @@ static inline void tracepoint_synchronize_unregister(void)
 	EXPORT_SYMBOL(__tracepoint_##name)
 
 #else /* !CONFIG_TRACEPOINTS */
-#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args)	\
+#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
 	static inline void trace_##name(proto)				\
 	{ }								\
+	static inline void trace_##name##_rcuidle(proto)		\
+	{ }								\
 	static inline int						\
 	register_trace_##name(void (*probe)(data_proto),		\
 			      void *data)				\