diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-format b/Documentation/ABI/testing/sysfs-bus-event_source-devices-format
new file mode 100644
index 0000000..079afc7
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-format
@@ -0,0 +1,14 @@
+Where:		/sys/bus/event_source/devices/<dev>/format
+Date:		January 2012
+Kernel Version: 3.3
+Contact:	Jiri Olsa <jolsa@redhat.com>
+Description:
+		Attribute group to describe the magic bits that go into
+		perf_event_attr::config[012] for a particular pmu.
+		Each attribute of this group defines the 'hardware' bitmask
+		we want to export, so that userspace can deal with sane
+		name/value pairs.
+
+		Example: 'config1:1,6-10,44'
+		Defines contents of attribute that occupies bits 1,6-10,44 of
+		perf_event_attr::config1.
diff --git a/Documentation/lockup-watchdogs.txt b/Documentation/lockup-watchdogs.txt
new file mode 100644
index 0000000..d2a3660
--- /dev/null
+++ b/Documentation/lockup-watchdogs.txt
@@ -0,0 +1,63 @@
+===============================================================
+Softlockup detector and hardlockup detector (aka nmi_watchdog)
+===============================================================
+
+The Linux kernel can act as a watchdog to detect both soft and hard
+lockups.
+
+A 'softlockup' is defined as a bug that causes the kernel to loop in
+kernel mode for more than 20 seconds (see "Implementation" below for
+details), without giving other tasks a chance to run. The current
+stack trace is displayed upon detection and, by default, the system
+will stay locked up. Alternatively, the kernel can be configured to
+panic; a sysctl, "kernel.softlockup_panic", a kernel parameter,
+"softlockup_panic" (see "Documentation/kernel-parameters.txt" for
+details), and a compile option, "BOOTPARAM_HARDLOCKUP_PANIC", are
+provided for this.
+
+A 'hardlockup' is defined as a bug that causes the CPU to loop in
+kernel mode for more than 10 seconds (see "Implementation" below for
+details), without letting other interrupts have a chance to run.
+Similarly to the softlockup case, the current stack trace is displayed
+upon detection and the system will stay locked up unless the default
+behavior is changed, which can be done through a compile time knob,
+"BOOTPARAM_HARDLOCKUP_PANIC", and a kernel parameter, "nmi_watchdog"
+(see "Documentation/kernel-parameters.txt" for details).
+
+The panic option can be used in combination with panic_timeout (this
+timeout is set through the confusingly named "kernel.panic" sysctl),
+to cause the system to reboot automatically after a specified amount
+of time.
+
+=== Implementation ===
+
+The soft and hard lockup detectors are built on top of the hrtimer and
+perf subsystems, respectively. A direct consequence of this is that,
+in principle, they should work in any architecture where these
+subsystems are present.
+
+A periodic hrtimer runs to generate interrupts and kick the watchdog
+task. An NMI perf event is generated every "watchdog_thresh"
+(compile-time initialized to 10 and configurable through sysctl of the
+same name) seconds to check for hardlockups. If any CPU in the system
+does not receive any hrtimer interrupt during that time the
+'hardlockup detector' (the handler for the NMI perf event) will
+generate a kernel warning or call panic, depending on the
+configuration.
+
+The watchdog task is a high priority kernel thread that updates a
+timestamp every time it is scheduled. If that timestamp is not updated
+for 2*watchdog_thresh seconds (the softlockup threshold) the
+'softlockup detector' (coded inside the hrtimer callback function)
+will dump useful debug information to the system log, after which it
+will call panic if it was instructed to do so or resume execution of
+other kernel code.
+
+The period of the hrtimer is 2*watchdog_thresh/5, which means it has
+two or three chances to generate an interrupt before the hardlockup
+detector kicks in.
+
+As explained above, a kernel knob is provided that allows
+administrators to configure the period of the hrtimer and the perf
+event. The right value for a particular environment is a trade-off
+between fast response to lockups and detection overhead.
diff --git a/Documentation/nmi_watchdog.txt b/Documentation/nmi_watchdog.txt
deleted file mode 100644
index bf9f80a..0000000
--- a/Documentation/nmi_watchdog.txt
+++ /dev/null
@@ -1,83 +0,0 @@
-
-[NMI watchdog is available for x86 and x86-64 architectures]
-
-Is your system locking up unpredictably? No keyboard activity, just
-a frustrating complete hard lockup? Do you want to help us debugging
-such lockups? If all yes then this document is definitely for you.
-
-On many x86/x86-64 type hardware there is a feature that enables
-us to generate 'watchdog NMI interrupts'.  (NMI: Non Maskable Interrupt
-which get executed even if the system is otherwise locked up hard).
-This can be used to debug hard kernel lockups.  By executing periodic
-NMI interrupts, the kernel can monitor whether any CPU has locked up,
-and print out debugging messages if so.
-
-In order to use the NMI watchdog, you need to have APIC support in your
-kernel. For SMP kernels, APIC support gets compiled in automatically. For
-UP, enable either CONFIG_X86_UP_APIC (Processor type and features -> Local
-APIC support on uniprocessors) or CONFIG_X86_UP_IOAPIC (Processor type and
-features -> IO-APIC support on uniprocessors) in your kernel config.
-CONFIG_X86_UP_APIC is for uniprocessor machines without an IO-APIC.
-CONFIG_X86_UP_IOAPIC is for uniprocessor with an IO-APIC. [Note: certain
-kernel debugging options, such as Kernel Stack Meter or Kernel Tracer,
-may implicitly disable the NMI watchdog.]
-
-For x86-64, the needed APIC is always compiled in.
-
-Using local APIC (nmi_watchdog=2) needs the first performance register, so
-you can't use it for other purposes (such as high precision performance
-profiling.) However, at least oprofile and the perfctr driver disable the
-local APIC NMI watchdog automatically.
-
-To actually enable the NMI watchdog, use the 'nmi_watchdog=N' boot
-parameter.  Eg. the relevant lilo.conf entry:
-
-        append="nmi_watchdog=1"
-
-For SMP machines and UP machines with an IO-APIC use nmi_watchdog=1.
-For UP machines without an IO-APIC use nmi_watchdog=2, this only works
-for some processor types.  If in doubt, boot with nmi_watchdog=1 and
-check the NMI count in /proc/interrupts; if the count is zero then
-reboot with nmi_watchdog=2 and check the NMI count.  If it is still
-zero then log a problem, you probably have a processor that needs to be
-added to the nmi code.
-
-A 'lockup' is the following scenario: if any CPU in the system does not
-execute the period local timer interrupt for more than 5 seconds, then
-the NMI handler generates an oops and kills the process. This
-'controlled crash' (and the resulting kernel messages) can be used to
-debug the lockup. Thus whenever the lockup happens, wait 5 seconds and
-the oops will show up automatically. If the kernel produces no messages
-then the system has crashed so hard (eg. hardware-wise) that either it
-cannot even accept NMI interrupts, or the crash has made the kernel
-unable to print messages.
-
-Be aware that when using local APIC, the frequency of NMI interrupts
-it generates, depends on the system load. The local APIC NMI watchdog,
-lacking a better source, uses the "cycles unhalted" event. As you may
-guess it doesn't tick when the CPU is in the halted state (which happens
-when the system is idle), but if your system locks up on anything but the
-"hlt" processor instruction, the watchdog will trigger very soon as the
-"cycles unhalted" event will happen every clock tick. If it locks up on
-"hlt", then you are out of luck -- the event will not happen at all and the
-watchdog won't trigger. This is a shortcoming of the local APIC watchdog
--- unfortunately there is no "clock ticks" event that would work all the
-time. The I/O APIC watchdog is driven externally and has no such shortcoming.
-But its NMI frequency is much higher, resulting in a more significant hit
-to the overall system performance.
-
-On x86 nmi_watchdog is disabled by default so you have to enable it with
-a boot time parameter.
-
-It's possible to disable the NMI watchdog in run-time by writing "0" to
-/proc/sys/kernel/nmi_watchdog. Writing "1" to the same file will re-enable
-the NMI watchdog. Notice that you still need to use "nmi_watchdog=" parameter
-at boot time.
-
-NOTE: In kernels prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
-on x86 SMP boxes.
-
-[ feel free to send bug reports, suggestions and patches to
-  Ingo Molnar <mingo@redhat.com> or the Linux SMP mailing
-  list at <linux-smp@vger.kernel.org> ]
-
diff --git a/Documentation/static-keys.txt b/Documentation/static-keys.txt
new file mode 100644
index 0000000..d93f3c0
--- /dev/null
+++ b/Documentation/static-keys.txt
@@ -0,0 +1,286 @@
+			Static Keys
+			-----------
+
+By: Jason Baron <jbaron@redhat.com>
+
+0) Abstract
+
+Static keys allows the inclusion of seldom used features in
+performance-sensitive fast-path kernel code, via a GCC feature and a code
+patching technique. A quick example:
+
+	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.
+
+
+1) Motivation
+
+
+Currently, tracepoints are implemented using a conditional branch. The
+conditional check requires checking a global variable for each tracepoint.
+Although the overhead of this check is small, it increases when the memory
+cache comes under pressure (memory cache lines for these global variables may
+be shared with other memory accesses). As we increase the number of tracepoints
+in the kernel this overhead may become more of an issue. In addition,
+tracepoints are often dormant (disabled) and provide no direct kernel
+functionality. Thus, it is highly desirable to reduce their impact as much as
+possible. Although tracepoints are the original motivation for this work, other
+kernel code paths should be able to make use of the static keys facility.
+
+
+2) Solution
+
+
+gcc (v4.5) adds a new 'asm goto' statement that allows branching to a label:
+
+http://gcc.gnu.org/ml/gcc-patches/2009-07/msg01556.html
+
+Using the 'asm goto', we can create branches that are either taken or not taken
+by default, without the need to check memory. Then, at run-time, we can patch
+the branch site to change the branch direction.
+
+For example, if we have a simple branch that is disabled by default:
+
+	if (static_key_false(&key))
+		printk("I am the true branch\n");
+
+Thus, by default the 'printk' will not be emitted. And the code generated will
+consist of a single atomic 'no-op' instruction (5 bytes on x86), in the
+straight-line code path. When the branch is 'flipped', we will patch the
+'no-op' in the straight-line codepath with a 'jump' instruction to the
+out-of-line true branch. Thus, changing branch direction is expensive but
+branch selection is basically 'free'. That is the basic tradeoff of this
+optimization.
+
+This lowlevel patching mechanism is called 'jump label patching', and it gives
+the basis for the static keys facility.
+
+3) Static key label API, usage and examples:
+
+
+In order to make use of this optimization you must first define a key:
+
+	struct static_key key;
+
+Which is initialized as:
+
+	struct static_key key = STATIC_KEY_INIT_TRUE;
+
+or:
+
+	struct static_key key = STATIC_KEY_INIT_FALSE;
+
+If the key is not initialized, it is default false. The 'struct static_key',
+must be a 'global'. That is, it can't be allocated on the stack or dynamically
+allocated at run-time.
+
+The key is then used in code as:
+
+        if (static_key_false(&key))
+                do unlikely code
+        else
+                do likely code
+
+Or:
+
+        if (static_key_true(&key))
+                do likely code
+        else
+                do unlikely code
+
+A key that is initialized via 'STATIC_KEY_INIT_FALSE', must be used in a
+'static_key_false()' construct. Likewise, a key initialized via
+'STATIC_KEY_INIT_TRUE' must be used in a 'static_key_true()' construct. A
+single key can be used in many branches, but all the branches must match the
+way that the key has been initialized.
+
+The branch(es) can then be switched via:
+
+	static_key_slow_inc(&key);
+	...
+	static_key_slow_dec(&key);
+
+Thus, 'static_key_slow_inc()' means 'make the branch true', and
+'static_key_slow_dec()' means 'make the the branch false' with appropriate
+reference counting. For example, if the key is initialized true, a
+static_key_slow_dec(), will switch the branch to false. And a subsequent
+static_key_slow_inc(), will change the branch back to true. Likewise, if the
+key is initialized false, a 'static_key_slow_inc()', will change the branch to
+true. And then a 'static_key_slow_dec()', will again make the branch false.
+
+An example usage in the kernel is the implementation of tracepoints:
+
+        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));                    \
+        }
+
+Tracepoints are disabled by default, and can be placed in performance critical
+pieces of the kernel. Thus, by using a static key, the tracepoints can have
+absolutely minimal impact when not in use.
+
+
+4) Architecture level code patching interface, 'jump labels'
+
+
+There are a few functions and macros that architectures must implement in order
+to take advantage of this optimization. If there is no architecture support, we
+simply fall back to a traditional, load, test, and jump sequence.
+
+* select HAVE_ARCH_JUMP_LABEL, see: arch/x86/Kconfig
+
+* #define JUMP_LABEL_NOP_SIZE, see: arch/x86/include/asm/jump_label.h
+
+* __always_inline bool arch_static_branch(struct static_key *key), see:
+					arch/x86/include/asm/jump_label.h
+
+* void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type),
+					see: arch/x86/kernel/jump_label.c
+
+* __init_or_module void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type),
+					see: arch/x86/kernel/jump_label.c
+
+
+* struct jump_entry, see: arch/x86/include/asm/jump_label.h
+
+
+5) Static keys / jump label analysis, results (x86_64):
+
+
+As an example, let's add the following branch to 'getppid()', such that the
+system call now looks like:
+
+SYSCALL_DEFINE0(getppid)
+{
+        int pid;
+
++       if (static_key_false(&key))
++               printk("I am the true branch\n");
+
+        rcu_read_lock();
+        pid = task_tgid_vnr(rcu_dereference(current->real_parent));
+        rcu_read_unlock();
+
+        return pid;
+}
+
+The resulting instructions with jump labels generated by GCC is:
+
+ffffffff81044290 <sys_getppid>:
+ffffffff81044290:       55                      push   %rbp
+ffffffff81044291:       48 89 e5                mov    %rsp,%rbp
+ffffffff81044294:       e9 00 00 00 00          jmpq   ffffffff81044299 <sys_getppid+0x9>
+ffffffff81044299:       65 48 8b 04 25 c0 b6    mov    %gs:0xb6c0,%rax
+ffffffff810442a0:       00 00
+ffffffff810442a2:       48 8b 80 80 02 00 00    mov    0x280(%rax),%rax
+ffffffff810442a9:       48 8b 80 b0 02 00 00    mov    0x2b0(%rax),%rax
+ffffffff810442b0:       48 8b b8 e8 02 00 00    mov    0x2e8(%rax),%rdi
+ffffffff810442b7:       e8 f4 d9 00 00          callq  ffffffff81051cb0 <pid_vnr>
+ffffffff810442bc:       5d                      pop    %rbp
+ffffffff810442bd:       48 98                   cltq
+ffffffff810442bf:       c3                      retq
+ffffffff810442c0:       48 c7 c7 e3 54 98 81    mov    $0xffffffff819854e3,%rdi
+ffffffff810442c7:       31 c0                   xor    %eax,%eax
+ffffffff810442c9:       e8 71 13 6d 00          callq  ffffffff8171563f <printk>
+ffffffff810442ce:       eb c9                   jmp    ffffffff81044299 <sys_getppid+0x9>
+
+Without the jump label optimization it looks like:
+
+ffffffff810441f0 <sys_getppid>:
+ffffffff810441f0:       8b 05 8a 52 d8 00       mov    0xd8528a(%rip),%eax        # ffffffff81dc9480 <key>
+ffffffff810441f6:       55                      push   %rbp
+ffffffff810441f7:       48 89 e5                mov    %rsp,%rbp
+ffffffff810441fa:       85 c0                   test   %eax,%eax
+ffffffff810441fc:       75 27                   jne    ffffffff81044225 <sys_getppid+0x35>
+ffffffff810441fe:       65 48 8b 04 25 c0 b6    mov    %gs:0xb6c0,%rax
+ffffffff81044205:       00 00
+ffffffff81044207:       48 8b 80 80 02 00 00    mov    0x280(%rax),%rax
+ffffffff8104420e:       48 8b 80 b0 02 00 00    mov    0x2b0(%rax),%rax
+ffffffff81044215:       48 8b b8 e8 02 00 00    mov    0x2e8(%rax),%rdi
+ffffffff8104421c:       e8 2f da 00 00          callq  ffffffff81051c50 <pid_vnr>
+ffffffff81044221:       5d                      pop    %rbp
+ffffffff81044222:       48 98                   cltq
+ffffffff81044224:       c3                      retq
+ffffffff81044225:       48 c7 c7 13 53 98 81    mov    $0xffffffff81985313,%rdi
+ffffffff8104422c:       31 c0                   xor    %eax,%eax
+ffffffff8104422e:       e8 60 0f 6d 00          callq  ffffffff81715193 <printk>
+ffffffff81044233:       eb c9                   jmp    ffffffff810441fe <sys_getppid+0xe>
+ffffffff81044235:       66 66 2e 0f 1f 84 00    data32 nopw %cs:0x0(%rax,%rax,1)
+ffffffff8104423c:       00 00 00 00
+
+Thus, the disable jump label case adds a 'mov', 'test' and 'jne' instruction
+vs. the jump label case just has a 'no-op' or 'jmp 0'. (The jmp 0, is patched
+to a 5 byte atomic no-op instruction at boot-time.) Thus, the disabled jump
+label case adds:
+
+6 (mov) + 2 (test) + 2 (jne) = 10 - 5 (5 byte jump 0) = 5 addition bytes.
+
+If we then include the padding bytes, the jump label code saves, 16 total bytes
+of instruction memory for this small fucntion. In this case the non-jump label
+function is 80 bytes long. Thus, we have have saved 20% of the instruction
+footprint. We can in fact improve this even further, since the 5-byte no-op
+really can be a 2-byte no-op since we can reach the branch with a 2-byte jmp.
+However, we have not yet implemented optimal no-op sizes (they are currently
+hard-coded).
+
+Since there are a number of static key API uses in the scheduler paths,
+'pipe-test' (also known as 'perf bench sched pipe') can be used to show the
+performance improvement. Testing done on 3.3.0-rc2:
+
+jump label disabled:
+
+ Performance counter stats for 'bash -c /tmp/pipe-test' (50 runs):
+
+        855.700314 task-clock                #    0.534 CPUs utilized            ( +-  0.11% )
+           200,003 context-switches          #    0.234 M/sec                    ( +-  0.00% )
+                 0 CPU-migrations            #    0.000 M/sec                    ( +- 39.58% )
+               487 page-faults               #    0.001 M/sec                    ( +-  0.02% )
+     1,474,374,262 cycles                    #    1.723 GHz                      ( +-  0.17% )
+   <not supported> stalled-cycles-frontend
+   <not supported> stalled-cycles-backend
+     1,178,049,567 instructions              #    0.80  insns per cycle          ( +-  0.06% )
+       208,368,926 branches                  #  243.507 M/sec                    ( +-  0.06% )
+         5,569,188 branch-misses             #    2.67% of all branches          ( +-  0.54% )
+
+       1.601607384 seconds time elapsed                                          ( +-  0.07% )
+
+jump label enabled:
+
+ Performance counter stats for 'bash -c /tmp/pipe-test' (50 runs):
+
+        841.043185 task-clock                #    0.533 CPUs utilized            ( +-  0.12% )
+           200,004 context-switches          #    0.238 M/sec                    ( +-  0.00% )
+                 0 CPU-migrations            #    0.000 M/sec                    ( +- 40.87% )
+               487 page-faults               #    0.001 M/sec                    ( +-  0.05% )
+     1,432,559,428 cycles                    #    1.703 GHz                      ( +-  0.18% )
+   <not supported> stalled-cycles-frontend
+   <not supported> stalled-cycles-backend
+     1,175,363,994 instructions              #    0.82  insns per cycle          ( +-  0.04% )
+       206,859,359 branches                  #  245.956 M/sec                    ( +-  0.04% )
+         4,884,119 branch-misses             #    2.36% of all branches          ( +-  0.85% )
+
+       1.579384366 seconds time elapsed
+
+The percentage of saved branches is .7%, and we've saved 12% on
+'branch-misses'. This is where we would expect to get the most savings, since
+this optimization is about reducing the number of branches. In addition, we've
+saved .2% on instructions, and 2.8% on cycles and 1.4% on elapsed time.
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 1ebc24c..6f51fed 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -226,6 +226,13 @@
 	Traces and records the max latency that it takes for
 	the highest priority task to get scheduled after
 	it has been woken up.
+        Traces all tasks as an average developer would expect.
+
+  "wakeup_rt"
+
+        Traces and records the max latency that it takes for just
+        RT tasks (as the current "wakeup" does). This is useful
+        for those interested in wake up timings of RT tasks.
 
   "hw-branch-tracer"
 
diff --git a/arch/Kconfig b/arch/Kconfig
index 4f55c73..5b448a7 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -47,18 +47,29 @@
 	  If in doubt, say "N".
 
 config JUMP_LABEL
-       bool "Optimize trace point call sites"
+       bool "Optimize very unlikely/likely branches"
        depends on HAVE_ARCH_JUMP_LABEL
        help
-         If it is detected that the compiler has support for "asm goto",
-	 the kernel will compile trace point locations with just a
-	 nop instruction. When trace points are enabled, the nop will
-	 be converted to a jump to the trace function. This technique
-	 lowers overhead and stress on the branch prediction of the
-	 processor.
+         This option enables a transparent branch optimization that
+	 makes certain almost-always-true or almost-always-false branch
+	 conditions even cheaper to execute within the kernel.
 
-	 On i386, options added to the compiler flags may increase
-	 the size of the kernel slightly.
+	 Certain performance-sensitive kernel code, such as trace points,
+	 scheduler functionality, networking code and KVM have such
+	 branches and include support for this optimization technique.
+
+         If it is detected that the compiler has support for "asm goto",
+	 the kernel will compile such branches with just a nop
+	 instruction. When the condition flag is toggled to true, the
+	 nop will be converted to a jump instruction to execute the
+	 conditional block of instructions.
+
+	 This technique lowers overhead and stress on the branch prediction
+	 of the processor and generally makes the kernel faster. The update
+	 of the condition is slower, but those are always very rare.
+
+	 ( On 32-bit x86, the necessary options added to the compiler
+	   flags may increase the size of the kernel slightly. )
 
 config OPTPROBES
 	def_bool y
diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index 8143cd7..0dae252 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -685,6 +685,10 @@
 {
 	int err;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_RAW:
 	case PERF_TYPE_HARDWARE:
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
index 99cfe36..7523340 100644
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@@ -12,10 +12,6 @@
 #ifndef __ARM_PERF_EVENT_H__
 #define __ARM_PERF_EVENT_H__
 
-/* ARM performance counters start from 1 (in the cp15 accesses) so use the
- * same indexes here for consistency. */
-#define PERF_EVENT_INDEX_OFFSET 1
-
 /* ARM perf PMU IDs for use by internal perf clients. */
 enum arm_perf_pmu_ids {
 	ARM_PERF_PMU_ID_XSCALE1	= 0,
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index b2abfa1..8a89d3b 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -539,6 +539,10 @@
 	int err = 0;
 	atomic_t *active_events = &armpmu->active_events;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	if (armpmu->map_event(event) == -ENOENT)
 		return -ENOENT;
 
diff --git a/arch/frv/include/asm/perf_event.h b/arch/frv/include/asm/perf_event.h
index a69e015..c52ea55 100644
--- a/arch/frv/include/asm/perf_event.h
+++ b/arch/frv/include/asm/perf_event.h
@@ -12,6 +12,4 @@
 #ifndef _ASM_PERF_EVENT_H
 #define _ASM_PERF_EVENT_H
 
-#define PERF_EVENT_INDEX_OFFSET	0
-
 #endif /* _ASM_PERF_EVENT_H */
diff --git a/arch/hexagon/include/asm/perf_event.h b/arch/hexagon/include/asm/perf_event.h
index 6c2910f..8b8526b 100644
--- a/arch/hexagon/include/asm/perf_event.h
+++ b/arch/hexagon/include/asm/perf_event.h
@@ -19,6 +19,4 @@
 #ifndef _ASM_PERF_EVENT_H
 #define _ASM_PERF_EVENT_H
 
-#define PERF_EVENT_INDEX_OFFSET	0
-
 #endif /* _ASM_PERF_EVENT_H */
diff --git a/arch/ia64/include/asm/paravirt.h b/arch/ia64/include/asm/paravirt.h
index 32551d3..b149b88 100644
--- a/arch/ia64/include/asm/paravirt.h
+++ b/arch/ia64/include/asm/paravirt.h
@@ -281,9 +281,9 @@
 		pv_time_ops.init_missing_ticks_accounting(cpu);
 }
 
-struct jump_label_key;
-extern struct jump_label_key paravirt_steal_enabled;
-extern struct jump_label_key paravirt_steal_rq_enabled;
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
 
 static inline int
 paravirt_do_steal_accounting(unsigned long *new_itm)
diff --git a/arch/ia64/kernel/paravirt.c b/arch/ia64/kernel/paravirt.c
index 1008682..1b22f6de 100644
--- a/arch/ia64/kernel/paravirt.c
+++ b/arch/ia64/kernel/paravirt.c
@@ -634,8 +634,8 @@
  * pv_time_ops
  * time operations
  */
-struct jump_label_key paravirt_steal_enabled;
-struct jump_label_key paravirt_steal_rq_enabled;
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
 
 static int
 ia64_native_do_steal_accounting(unsigned long *new_itm)
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index 1881b31..4d6d77e 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -20,7 +20,7 @@
 #define WORD_INSN ".word"
 #endif
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("1:\tnop\n\t"
 		"nop\n\t"
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index e3b897a..811084f 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -606,6 +606,10 @@
 {
 	int err = 0;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_RAW:
 	case PERF_TYPE_HARDWARE:
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index 938986e..ae098c4 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -17,7 +17,7 @@
 #define JUMP_ENTRY_TYPE		stringify_in_c(FTR_ENTRY_LONG)
 #define JUMP_LABEL_NOP_SIZE	4
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("1:\n\t"
 		 "nop\n\t"
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 8f1df12..1a8093f 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -61,8 +61,6 @@
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 
-#define PERF_EVENT_INDEX_OFFSET	1
-
 /*
  * Only override the default definitions in include/linux/perf_event.h
  * if we have hardware PMU support.
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index 64483fd..c2e27ed 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -1084,6 +1084,10 @@
 	if (!ppmu)
 		return -ENOENT;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_HARDWARE:
 		ev = event->attr.config;
@@ -1193,6 +1197,11 @@
 	return err;
 }
 
+static int power_pmu_event_idx(struct perf_event *event)
+{
+	return event->hw.idx;
+}
+
 struct pmu power_pmu = {
 	.pmu_enable	= power_pmu_enable,
 	.pmu_disable	= power_pmu_disable,
@@ -1205,6 +1214,7 @@
 	.start_txn	= power_pmu_start_txn,
 	.cancel_txn	= power_pmu_cancel_txn,
 	.commit_txn	= power_pmu_commit_txn,
+	.event_idx	= power_pmu_event_idx,
 };
 
 /*
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 95a6cf2..6c32190 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -13,7 +13,7 @@
 #define ASM_ALIGN ".balign 4"
 #endif
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("0:	brcl 0,0\n"
 		".pushsection __jump_table, \"aw\"\n"
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index a75f168..4eb444e 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -6,4 +6,3 @@
 
 /* Empty, just to avoid compiling error */
 
-#define PERF_EVENT_INDEX_OFFSET 0
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 10b14e3..068b8a2 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -310,6 +310,10 @@
 {
 	int err;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_RAW:
 	case PERF_TYPE_HW_CACHE:
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index fc73a82..5080d16 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -7,7 +7,7 @@
 
 #define JUMP_LABEL_NOP_SIZE 4
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 		asm goto("1:\n\t"
 			 "nop\n\t"
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 614da62..8e16a4a 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1105,6 +1105,10 @@
 	if (atomic_read(&nmi_active) < 0)
 		return -ENODEV;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (attr->type) {
 	case PERF_TYPE_HARDWARE:
 		if (attr->config >= sparc_pmu->max_events)
diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index 205b063..74a2e31 100644
--- a/arch/x86/include/asm/inat.h
+++ b/arch/x86/include/asm/inat.h
@@ -97,11 +97,12 @@
 
 /* Attribute search APIs */
 extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
+extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
 extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode,
-					     insn_byte_t last_pfx,
+					     int lpfx_id,
 					     insn_attr_t esc_attr);
 extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm,
-					    insn_byte_t last_pfx,
+					    int lpfx_id,
 					    insn_attr_t esc_attr);
 extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode,
 					  insn_byte_t vex_m,
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 74df3f1..48eb30a 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -96,12 +96,6 @@
 #define X86_VEX_P(vex)	((vex) & 0x03)		/* VEX3 Byte2, VEX2 Byte1 */
 #define X86_VEX_M_MAX	0x1f			/* VEX3.M Maximum value */
 
-/* The last prefix is needed for two-byte and three-byte opcodes */
-static inline insn_byte_t insn_last_prefix(struct insn *insn)
-{
-	return insn->prefixes.bytes[3];
-}
-
 extern void insn_init(struct insn *insn, const void *kaddr, int x86_64);
 extern void insn_get_prefixes(struct insn *insn);
 extern void insn_get_opcode(struct insn *insn);
@@ -160,6 +154,18 @@
 		return X86_VEX_P(insn->vex_prefix.bytes[2]);
 }
 
+/* Get the last prefix id from last prefix or VEX prefix */
+static inline int insn_last_prefix_id(struct insn *insn)
+{
+	if (insn_is_avx(insn))
+		return insn_vex_p_bits(insn);	/* VEX_p is a SIMD prefix id */
+
+	if (insn->prefixes.bytes[3])
+		return inat_get_last_prefix_id(insn->prefixes.bytes[3]);
+
+	return 0;
+}
+
 /* Offset of each field from kaddr */
 static inline int insn_offset_rex_prefix(struct insn *insn)
 {
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index a32b18c..3a16c14 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -9,12 +9,12 @@
 
 #define JUMP_LABEL_NOP_SIZE 5
 
-#define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
+#define STATIC_KEY_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("1:"
-		JUMP_LABEL_INITIAL_NOP
+		STATIC_KEY_INITIAL_NOP
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
 		_ASM_PTR "1b, %l[l_yes], %c0 \n\t"
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index a6962d9..ccb8059 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -56,6 +56,13 @@
 #define MSR_OFFCORE_RSP_0		0x000001a6
 #define MSR_OFFCORE_RSP_1		0x000001a7
 
+#define MSR_LBR_SELECT			0x000001c8
+#define MSR_LBR_TOS			0x000001c9
+#define MSR_LBR_NHM_FROM		0x00000680
+#define MSR_LBR_NHM_TO			0x000006c0
+#define MSR_LBR_CORE_FROM		0x00000040
+#define MSR_LBR_CORE_TO			0x00000060
+
 #define MSR_IA32_PEBS_ENABLE		0x000003f1
 #define MSR_IA32_DS_AREA		0x00000600
 #define MSR_IA32_PERF_CAPABILITIES	0x00000345
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index a7d2db9..c0180fd 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -230,9 +230,9 @@
 	return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
 }
 
-struct jump_label_key;
-extern struct jump_label_key paravirt_steal_enabled;
-extern struct jump_label_key paravirt_steal_rq_enabled;
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
 
 static inline u64 paravirt_steal_clock(int cpu)
 {
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 461ce43..e8fb2c7 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -188,8 +188,6 @@
 #ifdef CONFIG_PERF_EVENTS
 extern void perf_events_lapic_init(void);
 
-#define PERF_EVENT_INDEX_OFFSET			0
-
 /*
  * Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups.
  * This flag is otherwise unused and ABI specified to be 0, so nobody should
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 5369059..532d2e0 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -69,6 +69,7 @@
 obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
+obj-$(CONFIG_OPTPROBES)		+= kprobes-opt.o
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault_32.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f4773f4..0a44b90 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -5,6 +5,7 @@
 #include <linux/mm.h>
 
 #include <linux/io.h>
+#include <linux/sched.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cpu.h>
@@ -456,6 +457,8 @@
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+		if (!check_tsc_unstable())
+			sched_clock_stable = 1;
 	}
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 5adce10..453ac94 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/bitops.h>
+#include <linux/device.h>
 
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
@@ -31,6 +32,7 @@
 #include <asm/compat.h>
 #include <asm/smp.h>
 #include <asm/alternative.h>
+#include <asm/timer.h>
 
 #include "perf_event.h"
 
@@ -351,6 +353,36 @@
 	return 0;
 }
 
+/*
+ * check that branch_sample_type is compatible with
+ * settings needed for precise_ip > 1 which implies
+ * using the LBR to capture ALL taken branches at the
+ * priv levels of the measurement
+ */
+static inline int precise_br_compat(struct perf_event *event)
+{
+	u64 m = event->attr.branch_sample_type;
+	u64 b = 0;
+
+	/* must capture all branches */
+	if (!(m & PERF_SAMPLE_BRANCH_ANY))
+		return 0;
+
+	m &= PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_USER;
+
+	if (!event->attr.exclude_user)
+		b |= PERF_SAMPLE_BRANCH_USER;
+
+	if (!event->attr.exclude_kernel)
+		b |= PERF_SAMPLE_BRANCH_KERNEL;
+
+	/*
+	 * ignore PERF_SAMPLE_BRANCH_HV, not supported on x86
+	 */
+
+	return m == b;
+}
+
 int x86_pmu_hw_config(struct perf_event *event)
 {
 	if (event->attr.precise_ip) {
@@ -367,6 +399,36 @@
 
 		if (event->attr.precise_ip > precise)
 			return -EOPNOTSUPP;
+		/*
+		 * check that PEBS LBR correction does not conflict with
+		 * whatever the user is asking with attr->branch_sample_type
+		 */
+		if (event->attr.precise_ip > 1) {
+			u64 *br_type = &event->attr.branch_sample_type;
+
+			if (has_branch_stack(event)) {
+				if (!precise_br_compat(event))
+					return -EOPNOTSUPP;
+
+				/* branch_sample_type is compatible */
+
+			} else {
+				/*
+				 * user did not specify  branch_sample_type
+				 *
+				 * For PEBS fixups, we capture all
+				 * the branches at the priv level of the
+				 * event.
+				 */
+				*br_type = PERF_SAMPLE_BRANCH_ANY;
+
+				if (!event->attr.exclude_user)
+					*br_type |= PERF_SAMPLE_BRANCH_USER;
+
+				if (!event->attr.exclude_kernel)
+					*br_type |= PERF_SAMPLE_BRANCH_KERNEL;
+			}
+		}
 	}
 
 	/*
@@ -424,6 +486,10 @@
 	/* mark unused */
 	event->hw.extra_reg.idx = EXTRA_REG_NONE;
 
+	/* mark not used */
+	event->hw.extra_reg.idx = EXTRA_REG_NONE;
+	event->hw.branch_reg.idx = EXTRA_REG_NONE;
+
 	return x86_pmu.hw_config(event);
 }
 
@@ -1210,6 +1276,8 @@
 		break;
 
 	case CPU_STARTING:
+		if (x86_pmu.attr_rdpmc)
+			set_in_cr4(X86_CR4_PCE);
 		if (x86_pmu.cpu_starting)
 			x86_pmu.cpu_starting(cpu);
 		break;
@@ -1246,6 +1314,11 @@
 	pr_info("no hardware sampling interrupt available.\n");
 }
 
+static struct attribute_group x86_pmu_format_group = {
+	.name = "format",
+	.attrs = NULL,
+};
+
 static int __init init_hw_perf_events(void)
 {
 	struct x86_pmu_quirk *quirk;
@@ -1319,6 +1392,9 @@
 		}
 	}
 
+	x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
+	x86_pmu_format_group.attrs = x86_pmu.format_attrs;
+
 	pr_info("... version:                %d\n",     x86_pmu.version);
 	pr_info("... bit width:              %d\n",     x86_pmu.cntval_bits);
 	pr_info("... generic registers:      %d\n",     x86_pmu.num_counters);
@@ -1542,23 +1618,107 @@
 	return err;
 }
 
+static int x86_pmu_event_idx(struct perf_event *event)
+{
+	int idx = event->hw.idx;
+
+	if (x86_pmu.num_counters_fixed && idx >= X86_PMC_IDX_FIXED) {
+		idx -= X86_PMC_IDX_FIXED;
+		idx |= 1 << 30;
+	}
+
+	return idx + 1;
+}
+
+static ssize_t get_attr_rdpmc(struct device *cdev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	return snprintf(buf, 40, "%d\n", x86_pmu.attr_rdpmc);
+}
+
+static void change_rdpmc(void *info)
+{
+	bool enable = !!(unsigned long)info;
+
+	if (enable)
+		set_in_cr4(X86_CR4_PCE);
+	else
+		clear_in_cr4(X86_CR4_PCE);
+}
+
+static ssize_t set_attr_rdpmc(struct device *cdev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	unsigned long val = simple_strtoul(buf, NULL, 0);
+
+	if (!!val != !!x86_pmu.attr_rdpmc) {
+		x86_pmu.attr_rdpmc = !!val;
+		smp_call_function(change_rdpmc, (void *)val, 1);
+	}
+
+	return count;
+}
+
+static DEVICE_ATTR(rdpmc, S_IRUSR | S_IWUSR, get_attr_rdpmc, set_attr_rdpmc);
+
+static struct attribute *x86_pmu_attrs[] = {
+	&dev_attr_rdpmc.attr,
+	NULL,
+};
+
+static struct attribute_group x86_pmu_attr_group = {
+	.attrs = x86_pmu_attrs,
+};
+
+static const struct attribute_group *x86_pmu_attr_groups[] = {
+	&x86_pmu_attr_group,
+	&x86_pmu_format_group,
+	NULL,
+};
+
+static void x86_pmu_flush_branch_stack(void)
+{
+	if (x86_pmu.flush_branch_stack)
+		x86_pmu.flush_branch_stack();
+}
+
 static struct pmu pmu = {
-	.pmu_enable	= x86_pmu_enable,
-	.pmu_disable	= x86_pmu_disable,
+	.pmu_enable		= x86_pmu_enable,
+	.pmu_disable		= x86_pmu_disable,
+
+	.attr_groups	= x86_pmu_attr_groups,
 
 	.event_init	= x86_pmu_event_init,
 
-	.add		= x86_pmu_add,
-	.del		= x86_pmu_del,
-	.start		= x86_pmu_start,
-	.stop		= x86_pmu_stop,
-	.read		= x86_pmu_read,
+	.add			= x86_pmu_add,
+	.del			= x86_pmu_del,
+	.start			= x86_pmu_start,
+	.stop			= x86_pmu_stop,
+	.read			= x86_pmu_read,
 
 	.start_txn	= x86_pmu_start_txn,
 	.cancel_txn	= x86_pmu_cancel_txn,
 	.commit_txn	= x86_pmu_commit_txn,
+
+	.event_idx	= x86_pmu_event_idx,
+	.flush_branch_stack	= x86_pmu_flush_branch_stack,
 };
 
+void perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)
+{
+	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+		return;
+
+	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+		return;
+
+	userpg->time_mult = this_cpu_read(cyc2ns);
+	userpg->time_shift = CYC2NS_SCALE_FACTOR;
+	userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
+}
+
 /*
  * callchain support
  */
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index c30c807..6638aaf 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -33,6 +33,7 @@
 
 	EXTRA_REG_RSP_0 = 0,	/* offcore_response_0 */
 	EXTRA_REG_RSP_1 = 1,	/* offcore_response_1 */
+	EXTRA_REG_LBR   = 2,	/* lbr_select */
 
 	EXTRA_REG_MAX		/* number of entries needed */
 };
@@ -130,6 +131,8 @@
 	void				*lbr_context;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
+	struct er_account		*lbr_sel;
+	u64				br_sel;
 
 	/*
 	 * Intel host/guest exclude bits
@@ -268,6 +271,29 @@
 	void (*func)(void);
 };
 
+union x86_pmu_config {
+	struct {
+		u64 event:8,
+		    umask:8,
+		    usr:1,
+		    os:1,
+		    edge:1,
+		    pc:1,
+		    interrupt:1,
+		    __reserved1:1,
+		    en:1,
+		    inv:1,
+		    cmask:8,
+		    event2:4,
+		    __reserved2:4,
+		    go:1,
+		    ho:1;
+	} bits;
+	u64 value;
+};
+
+#define X86_CONFIG(args...) ((union x86_pmu_config){.bits = {args}}).value
+
 /*
  * struct x86_pmu - generic x86 pmu
  */
@@ -309,10 +335,20 @@
 	struct x86_pmu_quirk *quirks;
 	int		perfctr_second_write;
 
+	/*
+	 * sysfs attrs
+	 */
+	int		attr_rdpmc;
+	struct attribute **format_attrs;
+
+	/*
+	 * CPU Hotplug hooks
+	 */
 	int		(*cpu_prepare)(int cpu);
 	void		(*cpu_starting)(int cpu);
 	void		(*cpu_dying)(int cpu);
 	void		(*cpu_dead)(int cpu);
+	void		(*flush_branch_stack)(void);
 
 	/*
 	 * Intel Arch Perfmon v2+
@@ -334,6 +370,8 @@
 	 */
 	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 */
 
 	/*
 	 * Extra registers for events
@@ -447,6 +485,15 @@
 
 extern struct event_constraint unconstrained;
 
+static inline bool kernel_ip(unsigned long ip)
+{
+#ifdef CONFIG_X86_32
+	return ip > PAGE_OFFSET;
+#else
+	return (long)ip < 0;
+#endif
+}
+
 #ifdef CONFIG_CPU_SUP_AMD
 
 int amd_pmu_init(void);
@@ -527,6 +574,10 @@
 
 void intel_pmu_lbr_init_atom(void);
 
+void intel_pmu_lbr_init_snb(void);
+
+int intel_pmu_setup_lbr_filter(struct perf_event *event);
+
 int p4_pmu_init(void);
 
 int p6_pmu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 67250a5..95e7fe1 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -139,6 +139,9 @@
 	if (ret)
 		return ret;
 
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	if (event->attr.exclude_host && event->attr.exclude_guest)
 		/*
 		 * When HO == GO == 1 the hardware treats that as GO == HO == 0
@@ -401,6 +404,21 @@
 	}
 }
 
+PMU_FORMAT_ATTR(event,	"config:0-7,32-35");
+PMU_FORMAT_ATTR(umask,	"config:8-15"	);
+PMU_FORMAT_ATTR(edge,	"config:18"	);
+PMU_FORMAT_ATTR(inv,	"config:23"	);
+PMU_FORMAT_ATTR(cmask,	"config:24-31"	);
+
+static struct attribute *amd_format_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask.attr,
+	NULL,
+};
+
 static __initconst const struct x86_pmu amd_pmu = {
 	.name			= "AMD",
 	.handle_irq		= x86_pmu_handle_irq,
@@ -423,6 +441,8 @@
 	.get_event_constraints	= amd_get_event_constraints,
 	.put_event_constraints	= amd_put_event_constraints,
 
+	.format_attrs		= amd_format_attr,
+
 	.cpu_prepare		= amd_pmu_cpu_prepare,
 	.cpu_starting		= amd_pmu_cpu_starting,
 	.cpu_dead		= amd_pmu_cpu_dead,
@@ -593,6 +613,7 @@
 	.cpu_dead		= amd_pmu_cpu_dead,
 #endif
 	.cpu_starting		= amd_pmu_cpu_starting,
+	.format_attrs		= amd_format_attr,
 };
 
 __init int amd_pmu_init(void)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 61d4f79..26b3e2f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -728,6 +728,19 @@
  },
 };
 
+static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
+{
+	/* user explicitly requested branch sampling */
+	if (has_branch_stack(event))
+		return true;
+
+	/* implicit branch sampling to correct PEBS skid */
+	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
+		return true;
+
+	return false;
+}
+
 static void intel_pmu_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -882,6 +895,13 @@
 	cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 
+	/*
+	 * must disable before any actual event
+	 * because any event may be combined with LBR
+	 */
+	if (intel_pmu_needs_lbr_smpl(event))
+		intel_pmu_lbr_disable(event);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
@@ -936,6 +956,12 @@
 		intel_pmu_enable_bts(hwc->config);
 		return;
 	}
+	/*
+	 * must enabled before any actual event
+	 * because any event may be combined with LBR
+	 */
+	if (intel_pmu_needs_lbr_smpl(event))
+		intel_pmu_lbr_enable(event);
 
 	if (event->attr.exclude_host)
 		cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
@@ -1058,6 +1084,9 @@
 
 		data.period = event->hw.last_period;
 
+		if (has_branch_stack(event))
+			data.br_stack = &cpuc->lbr_stack;
+
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
 	}
@@ -1124,17 +1153,17 @@
  */
 static struct event_constraint *
 __intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc,
-				   struct perf_event *event)
+				   struct perf_event *event,
+				   struct hw_perf_event_extra *reg)
 {
 	struct event_constraint *c = &emptyconstraint;
-	struct hw_perf_event_extra *reg = &event->hw.extra_reg;
 	struct er_account *era;
 	unsigned long flags;
 	int orig_idx = reg->idx;
 
 	/* already allocated shared msr */
 	if (reg->alloc)
-		return &unconstrained;
+		return NULL; /* call x86_get_event_constraint() */
 
 again:
 	era = &cpuc->shared_regs->regs[reg->idx];
@@ -1157,14 +1186,10 @@
 		reg->alloc = 1;
 
 		/*
-		 * All events using extra_reg are unconstrained.
-		 * Avoids calling x86_get_event_constraints()
-		 *
-		 * Must revisit if extra_reg controlling events
-		 * ever have constraints. Worst case we go through
-		 * the regular event constraint table.
+		 * need to call x86_get_event_constraint()
+		 * to check if associated event has constraints
 		 */
-		c = &unconstrained;
+		c = NULL;
 	} else if (intel_try_alt_er(event, orig_idx)) {
 		raw_spin_unlock_irqrestore(&era->lock, flags);
 		goto again;
@@ -1201,11 +1226,23 @@
 intel_shared_regs_constraints(struct cpu_hw_events *cpuc,
 			      struct perf_event *event)
 {
-	struct event_constraint *c = NULL;
+	struct event_constraint *c = NULL, *d;
+	struct hw_perf_event_extra *xreg, *breg;
 
-	if (event->hw.extra_reg.idx != EXTRA_REG_NONE)
-		c = __intel_shared_reg_get_constraints(cpuc, event);
-
+	xreg = &event->hw.extra_reg;
+	if (xreg->idx != EXTRA_REG_NONE) {
+		c = __intel_shared_reg_get_constraints(cpuc, event, xreg);
+		if (c == &emptyconstraint)
+			return c;
+	}
+	breg = &event->hw.branch_reg;
+	if (breg->idx != EXTRA_REG_NONE) {
+		d = __intel_shared_reg_get_constraints(cpuc, event, breg);
+		if (d == &emptyconstraint) {
+			__intel_shared_reg_put_constraints(cpuc, xreg);
+			c = d;
+		}
+	}
 	return c;
 }
 
@@ -1253,6 +1290,10 @@
 	reg = &event->hw.extra_reg;
 	if (reg->idx != EXTRA_REG_NONE)
 		__intel_shared_reg_put_constraints(cpuc, reg);
+
+	reg = &event->hw.branch_reg;
+	if (reg->idx != EXTRA_REG_NONE)
+		__intel_shared_reg_put_constraints(cpuc, reg);
 }
 
 static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
@@ -1288,12 +1329,19 @@
 		 *
 		 * Thereby we gain a PEBS capable cycle counter.
 		 */
-		u64 alt_config = 0x108000c0; /* INST_RETIRED.TOTAL_CYCLES */
+		u64 alt_config = X86_CONFIG(.event=0xc0, .inv=1, .cmask=16);
+
 
 		alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
 		event->hw.config = alt_config;
 	}
 
+	if (intel_pmu_needs_lbr_smpl(event)) {
+		ret = intel_pmu_setup_lbr_filter(event);
+		if (ret)
+			return ret;
+	}
+
 	if (event->attr.type != PERF_TYPE_RAW)
 		return 0;
 
@@ -1383,6 +1431,24 @@
 	}
 }
 
+PMU_FORMAT_ATTR(event,	"config:0-7"	);
+PMU_FORMAT_ATTR(umask,	"config:8-15"	);
+PMU_FORMAT_ATTR(edge,	"config:18"	);
+PMU_FORMAT_ATTR(pc,	"config:19"	);
+PMU_FORMAT_ATTR(any,	"config:21"	); /* v3 + */
+PMU_FORMAT_ATTR(inv,	"config:23"	);
+PMU_FORMAT_ATTR(cmask,	"config:24-31"	);
+
+static struct attribute *intel_arch_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_pc.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask.attr,
+	NULL,
+};
+
 static __initconst const struct x86_pmu core_pmu = {
 	.name			= "core",
 	.handle_irq		= x86_pmu_handle_irq,
@@ -1407,6 +1473,7 @@
 	.put_event_constraints	= intel_put_event_constraints,
 	.event_constraints	= intel_core_event_constraints,
 	.guest_get_msrs		= core_guest_get_msrs,
+	.format_attrs		= intel_arch_formats_attr,
 };
 
 struct intel_shared_regs *allocate_shared_regs(int cpu)
@@ -1432,7 +1499,7 @@
 {
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
 
-	if (!x86_pmu.extra_regs)
+	if (!(x86_pmu.extra_regs || x86_pmu.lbr_sel_map))
 		return NOTIFY_OK;
 
 	cpuc->shared_regs = allocate_shared_regs(cpu);
@@ -1454,22 +1521,28 @@
 	 */
 	intel_pmu_lbr_reset();
 
-	if (!cpuc->shared_regs || (x86_pmu.er_flags & ERF_NO_HT_SHARING))
+	cpuc->lbr_sel = NULL;
+
+	if (!cpuc->shared_regs)
 		return;
 
-	for_each_cpu(i, topology_thread_cpumask(cpu)) {
-		struct intel_shared_regs *pc;
+	if (!(x86_pmu.er_flags & ERF_NO_HT_SHARING)) {
+		for_each_cpu(i, topology_thread_cpumask(cpu)) {
+			struct intel_shared_regs *pc;
 
-		pc = per_cpu(cpu_hw_events, i).shared_regs;
-		if (pc && pc->core_id == core_id) {
-			cpuc->kfree_on_online = cpuc->shared_regs;
-			cpuc->shared_regs = pc;
-			break;
+			pc = per_cpu(cpu_hw_events, i).shared_regs;
+			if (pc && pc->core_id == core_id) {
+				cpuc->kfree_on_online = cpuc->shared_regs;
+				cpuc->shared_regs = pc;
+				break;
+			}
 		}
+		cpuc->shared_regs->core_id = core_id;
+		cpuc->shared_regs->refcnt++;
 	}
 
-	cpuc->shared_regs->core_id = core_id;
-	cpuc->shared_regs->refcnt++;
+	if (x86_pmu.lbr_sel_map)
+		cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR];
 }
 
 static void intel_pmu_cpu_dying(int cpu)
@@ -1487,6 +1560,33 @@
 	fini_debug_store_on_cpu(cpu);
 }
 
+static void intel_pmu_flush_branch_stack(void)
+{
+	/*
+	 * Intel LBR does not tag entries with the
+	 * PID of the current task, then we need to
+	 * flush it on ctxsw
+	 * For now, we simply reset it
+	 */
+	if (x86_pmu.lbr_nr)
+		intel_pmu_lbr_reset();
+}
+
+PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
+
+static struct attribute *intel_arch3_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_pc.attr,
+	&format_attr_any.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask.attr,
+
+	&format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */
+	NULL,
+};
+
 static __initconst const struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,
@@ -1510,10 +1610,13 @@
 	.get_event_constraints	= intel_get_event_constraints,
 	.put_event_constraints	= intel_put_event_constraints,
 
+	.format_attrs		= intel_arch3_formats_attr,
+
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
 	.guest_get_msrs		= intel_guest_get_msrs,
+	.flush_branch_stack	= intel_pmu_flush_branch_stack,
 };
 
 static __init void intel_clovertown_quirk(void)
@@ -1690,9 +1793,11 @@
 		x86_pmu.extra_regs = intel_nehalem_extra_regs;
 
 		/* UOPS_ISSUED.STALLED_CYCLES */
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
 		/* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
+			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
 		x86_add_quirk(intel_nehalem_quirk);
 
@@ -1727,9 +1832,11 @@
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 
 		/* UOPS_ISSUED.STALLED_CYCLES */
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
 		/* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
+			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
 		pr_cont("Westmere events, ");
 		break;
@@ -1740,7 +1847,7 @@
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
-		intel_pmu_lbr_init_nhm();
+		intel_pmu_lbr_init_snb();
 
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
@@ -1750,9 +1857,11 @@
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
 
 		/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
 		/* UOPS_DISPATCHED.THREAD,c=1,i=1 to count stall cycles*/
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x18001b1;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
+			X86_CONFIG(.event=0xb1, .umask=0x01, .inv=1, .cmask=1);
 
 		pr_cont("SandyBridge events, ");
 		break;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index d6bd49f..7f64df1 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -3,6 +3,7 @@
 #include <linux/slab.h>
 
 #include <asm/perf_event.h>
+#include <asm/insn.h>
 
 #include "perf_event.h"
 
@@ -439,9 +440,6 @@
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
-
-	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
-		intel_pmu_lbr_enable(event);
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
@@ -454,9 +452,6 @@
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
 	hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
-
-	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
-		intel_pmu_lbr_disable(event);
 }
 
 void intel_pmu_pebs_enable_all(void)
@@ -475,17 +470,6 @@
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 }
 
-#include <asm/insn.h>
-
-static inline bool kernel_ip(unsigned long ip)
-{
-#ifdef CONFIG_X86_32
-	return ip > PAGE_OFFSET;
-#else
-	return (long)ip < 0;
-#endif
-}
-
 static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -572,6 +556,7 @@
 	 * both formats and we don't use the other fields in this
 	 * routine.
 	 */
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct pebs_record_core *pebs = __pebs;
 	struct perf_sample_data data;
 	struct pt_regs regs;
@@ -602,6 +587,9 @@
 	else
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 
+	if (has_branch_stack(event))
+		data.br_stack = &cpuc->lbr_stack;
+
 	if (perf_event_overflow(event, &data, &regs))
 		x86_pmu_stop(event, 0);
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 47a7e63..520b426 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -3,6 +3,7 @@
 
 #include <asm/perf_event.h>
 #include <asm/msr.h>
+#include <asm/insn.h>
 
 #include "perf_event.h"
 
@@ -14,6 +15,100 @@
 };
 
 /*
+ * Intel LBR_SELECT bits
+ * Intel Vol3a, April 2011, Section 16.7 Table 16-10
+ *
+ * Hardware branch filter (not available on all CPUs)
+ */
+#define LBR_KERNEL_BIT		0 /* do not capture at ring0 */
+#define LBR_USER_BIT		1 /* do not capture at ring > 0 */
+#define LBR_JCC_BIT		2 /* do not capture conditional branches */
+#define LBR_REL_CALL_BIT	3 /* do not capture relative calls */
+#define LBR_IND_CALL_BIT	4 /* do not capture indirect calls */
+#define LBR_RETURN_BIT		5 /* do not capture near returns */
+#define LBR_IND_JMP_BIT		6 /* do not capture indirect jumps */
+#define LBR_REL_JMP_BIT		7 /* do not capture relative jumps */
+#define LBR_FAR_BIT		8 /* do not capture far branches */
+
+#define LBR_KERNEL	(1 << LBR_KERNEL_BIT)
+#define LBR_USER	(1 << LBR_USER_BIT)
+#define LBR_JCC		(1 << LBR_JCC_BIT)
+#define LBR_REL_CALL	(1 << LBR_REL_CALL_BIT)
+#define LBR_IND_CALL	(1 << LBR_IND_CALL_BIT)
+#define LBR_RETURN	(1 << LBR_RETURN_BIT)
+#define LBR_REL_JMP	(1 << LBR_REL_JMP_BIT)
+#define LBR_IND_JMP	(1 << LBR_IND_JMP_BIT)
+#define LBR_FAR		(1 << LBR_FAR_BIT)
+
+#define LBR_PLM (LBR_KERNEL | LBR_USER)
+
+#define LBR_SEL_MASK	0x1ff	/* valid bits in LBR_SELECT */
+#define LBR_NOT_SUPP	-1	/* LBR filter not supported */
+#define LBR_IGN		0	/* ignored */
+
+#define LBR_ANY		 \
+	(LBR_JCC	|\
+	 LBR_REL_CALL	|\
+	 LBR_IND_CALL	|\
+	 LBR_RETURN	|\
+	 LBR_REL_JMP	|\
+	 LBR_IND_JMP	|\
+	 LBR_FAR)
+
+#define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
+
+#define for_each_branch_sample_type(x) \
+	for ((x) = PERF_SAMPLE_BRANCH_USER; \
+	     (x) < PERF_SAMPLE_BRANCH_MAX; (x) <<= 1)
+
+/*
+ * x86control flow change classification
+ * x86control flow changes include branches, interrupts, traps, faults
+ */
+enum {
+	X86_BR_NONE     = 0,      /* unknown */
+
+	X86_BR_USER     = 1 << 0, /* branch target is user */
+	X86_BR_KERNEL   = 1 << 1, /* branch target is kernel */
+
+	X86_BR_CALL     = 1 << 2, /* call */
+	X86_BR_RET      = 1 << 3, /* return */
+	X86_BR_SYSCALL  = 1 << 4, /* syscall */
+	X86_BR_SYSRET   = 1 << 5, /* syscall return */
+	X86_BR_INT      = 1 << 6, /* sw interrupt */
+	X86_BR_IRET     = 1 << 7, /* return from interrupt */
+	X86_BR_JCC      = 1 << 8, /* conditional */
+	X86_BR_JMP      = 1 << 9, /* jump */
+	X86_BR_IRQ      = 1 << 10,/* hw interrupt or trap or fault */
+	X86_BR_IND_CALL = 1 << 11,/* indirect calls */
+};
+
+#define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
+
+#define X86_BR_ANY       \
+	(X86_BR_CALL    |\
+	 X86_BR_RET     |\
+	 X86_BR_SYSCALL |\
+	 X86_BR_SYSRET  |\
+	 X86_BR_INT     |\
+	 X86_BR_IRET    |\
+	 X86_BR_JCC     |\
+	 X86_BR_JMP	 |\
+	 X86_BR_IRQ	 |\
+	 X86_BR_IND_CALL)
+
+#define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)
+
+#define X86_BR_ANY_CALL		 \
+	(X86_BR_CALL		|\
+	 X86_BR_IND_CALL	|\
+	 X86_BR_SYSCALL		|\
+	 X86_BR_IRQ		|\
+	 X86_BR_INT)
+
+static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);
+
+/*
  * We only support LBR implementations that have FREEZE_LBRS_ON_PMI
  * otherwise it becomes near impossible to get a reliable stack.
  */
@@ -21,6 +116,10 @@
 static void __intel_pmu_lbr_enable(void)
 {
 	u64 debugctl;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (cpuc->lbr_sel)
+		wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config);
 
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 	debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
@@ -76,11 +175,11 @@
 	 * Reset the LBR stack if we changed task context to
 	 * avoid data leaks.
 	 */
-
 	if (event->ctx->task && cpuc->lbr_context != event->ctx) {
 		intel_pmu_lbr_reset();
 		cpuc->lbr_context = event->ctx;
 	}
+	cpuc->br_sel = event->hw.branch_reg.reg;
 
 	cpuc->lbr_users++;
 }
@@ -95,8 +194,11 @@
 	cpuc->lbr_users--;
 	WARN_ON_ONCE(cpuc->lbr_users < 0);
 
-	if (cpuc->enabled && !cpuc->lbr_users)
+	if (cpuc->enabled && !cpuc->lbr_users) {
 		__intel_pmu_lbr_disable();
+		/* avoid stale pointer */
+		cpuc->lbr_context = NULL;
+	}
 }
 
 void intel_pmu_lbr_enable_all(void)
@@ -115,6 +217,9 @@
 		__intel_pmu_lbr_disable();
 }
 
+/*
+ * TOS = most recently recorded branch
+ */
 static inline u64 intel_pmu_lbr_tos(void)
 {
 	u64 tos;
@@ -142,15 +247,15 @@
 
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
 
-		cpuc->lbr_entries[i].from  = msr_lastbranch.from;
-		cpuc->lbr_entries[i].to    = msr_lastbranch.to;
-		cpuc->lbr_entries[i].flags = 0;
+		cpuc->lbr_entries[i].from	= msr_lastbranch.from;
+		cpuc->lbr_entries[i].to		= msr_lastbranch.to;
+		cpuc->lbr_entries[i].mispred	= 0;
+		cpuc->lbr_entries[i].predicted	= 0;
+		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
 }
 
-#define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
-
 /*
  * Due to lack of segmentation in Linux the effective address (offset)
  * is the same as the linear address, allowing us to merge the LIP and EIP
@@ -165,19 +270,22 @@
 
 	for (i = 0; i < x86_pmu.lbr_nr; i++) {
 		unsigned long lbr_idx = (tos - i) & mask;
-		u64 from, to, flags = 0;
+		u64 from, to, mis = 0, pred = 0;
 
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
 		rdmsrl(x86_pmu.lbr_to   + lbr_idx, to);
 
 		if (lbr_format == LBR_FORMAT_EIP_FLAGS) {
-			flags = !!(from & LBR_FROM_FLAG_MISPRED);
+			mis = !!(from & LBR_FROM_FLAG_MISPRED);
+			pred = !mis;
 			from = (u64)((((s64)from) << 1) >> 1);
 		}
 
-		cpuc->lbr_entries[i].from  = from;
-		cpuc->lbr_entries[i].to    = to;
-		cpuc->lbr_entries[i].flags = flags;
+		cpuc->lbr_entries[i].from	= from;
+		cpuc->lbr_entries[i].to		= to;
+		cpuc->lbr_entries[i].mispred	= mis;
+		cpuc->lbr_entries[i].predicted	= pred;
+		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
 }
@@ -193,28 +301,404 @@
 		intel_pmu_lbr_read_32(cpuc);
 	else
 		intel_pmu_lbr_read_64(cpuc);
+
+	intel_pmu_lbr_filter(cpuc);
 }
 
+/*
+ * SW filter is used:
+ * - in case there is no HW filter
+ * - in case the HW filter has errata or limitations
+ */
+static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
+{
+	u64 br_type = event->attr.branch_sample_type;
+	int mask = 0;
+
+	if (br_type & PERF_SAMPLE_BRANCH_USER)
+		mask |= X86_BR_USER;
+
+	if (br_type & PERF_SAMPLE_BRANCH_KERNEL)
+		mask |= X86_BR_KERNEL;
+
+	/* we ignore BRANCH_HV here */
+
+	if (br_type & PERF_SAMPLE_BRANCH_ANY)
+		mask |= X86_BR_ANY;
+
+	if (br_type & PERF_SAMPLE_BRANCH_ANY_CALL)
+		mask |= X86_BR_ANY_CALL;
+
+	if (br_type & PERF_SAMPLE_BRANCH_ANY_RETURN)
+		mask |= X86_BR_RET | X86_BR_IRET | X86_BR_SYSRET;
+
+	if (br_type & PERF_SAMPLE_BRANCH_IND_CALL)
+		mask |= X86_BR_IND_CALL;
+	/*
+	 * stash actual user request into reg, it may
+	 * be used by fixup code for some CPU
+	 */
+	event->hw.branch_reg.reg = mask;
+}
+
+/*
+ * setup the HW LBR filter
+ * Used only when available, may not be enough to disambiguate
+ * all branches, may need the help of the SW filter
+ */
+static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg;
+	u64 br_type = event->attr.branch_sample_type;
+	u64 mask = 0, m;
+	u64 v;
+
+	for_each_branch_sample_type(m) {
+		if (!(br_type & m))
+			continue;
+
+		v = x86_pmu.lbr_sel_map[m];
+		if (v == LBR_NOT_SUPP)
+			return -EOPNOTSUPP;
+
+		if (v != LBR_IGN)
+			mask |= v;
+	}
+	reg = &event->hw.branch_reg;
+	reg->idx = EXTRA_REG_LBR;
+
+	/* LBR_SELECT operates in suppress mode so invert mask */
+	reg->config = ~mask & x86_pmu.lbr_sel_mask;
+
+	return 0;
+}
+
+int intel_pmu_setup_lbr_filter(struct perf_event *event)
+{
+	int ret = 0;
+
+	/*
+	 * no LBR on this PMU
+	 */
+	if (!x86_pmu.lbr_nr)
+		return -EOPNOTSUPP;
+
+	/*
+	 * setup SW LBR filter
+	 */
+	intel_pmu_setup_sw_lbr_filter(event);
+
+	/*
+	 * setup HW LBR filter, if any
+	 */
+	if (x86_pmu.lbr_sel_map)
+		ret = intel_pmu_setup_hw_lbr_filter(event);
+
+	return ret;
+}
+
+/*
+ * return the type of control flow change at address "from"
+ * intruction is not necessarily a branch (in case of interrupt).
+ *
+ * The branch type returned also includes the priv level of the
+ * target of the control flow change (X86_BR_USER, X86_BR_KERNEL).
+ *
+ * If a branch type is unknown OR the instruction cannot be
+ * decoded (e.g., text page not present), then X86_BR_NONE is
+ * returned.
+ */
+static int branch_type(unsigned long from, unsigned long to)
+{
+	struct insn insn;
+	void *addr;
+	int bytes, size = MAX_INSN_SIZE;
+	int ret = X86_BR_NONE;
+	int ext, to_plm, from_plm;
+	u8 buf[MAX_INSN_SIZE];
+	int is64 = 0;
+
+	to_plm = kernel_ip(to) ? X86_BR_KERNEL : X86_BR_USER;
+	from_plm = kernel_ip(from) ? X86_BR_KERNEL : X86_BR_USER;
+
+	/*
+	 * maybe zero if lbr did not fill up after a reset by the time
+	 * we get a PMU interrupt
+	 */
+	if (from == 0 || to == 0)
+		return X86_BR_NONE;
+
+	if (from_plm == X86_BR_USER) {
+		/*
+		 * can happen if measuring at the user level only
+		 * and we interrupt in a kernel thread, e.g., idle.
+		 */
+		if (!current->mm)
+			return X86_BR_NONE;
+
+		/* may fail if text not present */
+		bytes = copy_from_user_nmi(buf, (void __user *)from, size);
+		if (bytes != size)
+			return X86_BR_NONE;
+
+		addr = buf;
+	} else
+		addr = (void *)from;
+
+	/*
+	 * decoder needs to know the ABI especially
+	 * on 64-bit systems running 32-bit apps
+	 */
+#ifdef CONFIG_X86_64
+	is64 = kernel_ip((unsigned long)addr) || !test_thread_flag(TIF_IA32);
+#endif
+	insn_init(&insn, addr, is64);
+	insn_get_opcode(&insn);
+
+	switch (insn.opcode.bytes[0]) {
+	case 0xf:
+		switch (insn.opcode.bytes[1]) {
+		case 0x05: /* syscall */
+		case 0x34: /* sysenter */
+			ret = X86_BR_SYSCALL;
+			break;
+		case 0x07: /* sysret */
+		case 0x35: /* sysexit */
+			ret = X86_BR_SYSRET;
+			break;
+		case 0x80 ... 0x8f: /* conditional */
+			ret = X86_BR_JCC;
+			break;
+		default:
+			ret = X86_BR_NONE;
+		}
+		break;
+	case 0x70 ... 0x7f: /* conditional */
+		ret = X86_BR_JCC;
+		break;
+	case 0xc2: /* near ret */
+	case 0xc3: /* near ret */
+	case 0xca: /* far ret */
+	case 0xcb: /* far ret */
+		ret = X86_BR_RET;
+		break;
+	case 0xcf: /* iret */
+		ret = X86_BR_IRET;
+		break;
+	case 0xcc ... 0xce: /* int */
+		ret = X86_BR_INT;
+		break;
+	case 0xe8: /* call near rel */
+	case 0x9a: /* call far absolute */
+		ret = X86_BR_CALL;
+		break;
+	case 0xe0 ... 0xe3: /* loop jmp */
+		ret = X86_BR_JCC;
+		break;
+	case 0xe9 ... 0xeb: /* jmp */
+		ret = X86_BR_JMP;
+		break;
+	case 0xff: /* call near absolute, call far absolute ind */
+		insn_get_modrm(&insn);
+		ext = (insn.modrm.bytes[0] >> 3) & 0x7;
+		switch (ext) {
+		case 2: /* near ind call */
+		case 3: /* far ind call */
+			ret = X86_BR_IND_CALL;
+			break;
+		case 4:
+		case 5:
+			ret = X86_BR_JMP;
+			break;
+		}
+		break;
+	default:
+		ret = X86_BR_NONE;
+	}
+	/*
+	 * interrupts, traps, faults (and thus ring transition) may
+	 * occur on any instructions. Thus, to classify them correctly,
+	 * we need to first look at the from and to priv levels. If they
+	 * are different and to is in the kernel, then it indicates
+	 * a ring transition. If the from instruction is not a ring
+	 * transition instr (syscall, systenter, int), then it means
+	 * it was a irq, trap or fault.
+	 *
+	 * we have no way of detecting kernel to kernel faults.
+	 */
+	if (from_plm == X86_BR_USER && to_plm == X86_BR_KERNEL
+	    && ret != X86_BR_SYSCALL && ret != X86_BR_INT)
+		ret = X86_BR_IRQ;
+
+	/*
+	 * branch priv level determined by target as
+	 * is done by HW when LBR_SELECT is implemented
+	 */
+	if (ret != X86_BR_NONE)
+		ret |= to_plm;
+
+	return ret;
+}
+
+/*
+ * implement actual branch filter based on user demand.
+ * Hardware may not exactly satisfy that request, thus
+ * we need to inspect opcodes. Mismatched branches are
+ * discarded. Therefore, the number of branches returned
+ * in PERF_SAMPLE_BRANCH_STACK sample may vary.
+ */
+static void
+intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
+{
+	u64 from, to;
+	int br_sel = cpuc->br_sel;
+	int i, j, type;
+	bool compress = false;
+
+	/* if sampling all branches, then nothing to filter */
+	if ((br_sel & X86_BR_ALL) == X86_BR_ALL)
+		return;
+
+	for (i = 0; i < cpuc->lbr_stack.nr; i++) {
+
+		from = cpuc->lbr_entries[i].from;
+		to = cpuc->lbr_entries[i].to;
+
+		type = branch_type(from, to);
+
+		/* if type does not correspond, then discard */
+		if (type == X86_BR_NONE || (br_sel & type) != type) {
+			cpuc->lbr_entries[i].from = 0;
+			compress = true;
+		}
+	}
+
+	if (!compress)
+		return;
+
+	/* remove all entries with from=0 */
+	for (i = 0; i < cpuc->lbr_stack.nr; ) {
+		if (!cpuc->lbr_entries[i].from) {
+			j = i;
+			while (++j < cpuc->lbr_stack.nr)
+				cpuc->lbr_entries[j-1] = cpuc->lbr_entries[j];
+			cpuc->lbr_stack.nr--;
+			if (!cpuc->lbr_entries[i].from)
+				continue;
+		}
+		i++;
+	}
+}
+
+/*
+ * Map interface branch filters onto LBR filters
+ */
+static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
+	[PERF_SAMPLE_BRANCH_ANY]	= LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER]	= LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL]	= LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN]	= LBR_RETURN | LBR_REL_JMP
+					| LBR_IND_JMP | LBR_FAR,
+	/*
+	 * NHM/WSM erratum: must include REL_JMP+IND_JMP to get CALL branches
+	 */
+	[PERF_SAMPLE_BRANCH_ANY_CALL] =
+	 LBR_REL_CALL | LBR_IND_CALL | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR,
+	/*
+	 * NHM/WSM erratum: must include IND_JMP to capture IND_CALL
+	 */
+	[PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP,
+};
+
+static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
+	[PERF_SAMPLE_BRANCH_ANY]	= LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER]	= LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL]	= LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN]	= LBR_RETURN | LBR_FAR,
+	[PERF_SAMPLE_BRANCH_ANY_CALL]	= LBR_REL_CALL | LBR_IND_CALL
+					| LBR_FAR,
+	[PERF_SAMPLE_BRANCH_IND_CALL]	= LBR_IND_CALL,
+};
+
+/* core */
 void intel_pmu_lbr_init_core(void)
 {
 	x86_pmu.lbr_nr     = 4;
-	x86_pmu.lbr_tos    = 0x01c9;
-	x86_pmu.lbr_from   = 0x40;
-	x86_pmu.lbr_to     = 0x60;
+	x86_pmu.lbr_tos    = MSR_LBR_TOS;
+	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
+	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
+
+	/*
+	 * SW branch filter usage:
+	 * - compensate for lack of HW filter
+	 */
+	pr_cont("4-deep LBR, ");
 }
 
+/* nehalem/westmere */
 void intel_pmu_lbr_init_nhm(void)
 {
 	x86_pmu.lbr_nr     = 16;
-	x86_pmu.lbr_tos    = 0x01c9;
-	x86_pmu.lbr_from   = 0x680;
-	x86_pmu.lbr_to     = 0x6c0;
+	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_sel_mask = LBR_SEL_MASK;
+	x86_pmu.lbr_sel_map  = nhm_lbr_sel_map;
+
+	/*
+	 * SW branch filter usage:
+	 * - workaround LBR_SEL errata (see above)
+	 * - support syscall, sysret capture.
+	 *   That requires LBR_FAR but that means far
+	 *   jmp need to be filtered out
+	 */
+	pr_cont("16-deep LBR, ");
 }
 
+/* sandy bridge */
+void intel_pmu_lbr_init_snb(void)
+{
+	x86_pmu.lbr_nr	 = 16;
+	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_sel_mask = LBR_SEL_MASK;
+	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;
+
+	/*
+	 * SW branch filter usage:
+	 * - support syscall, sysret capture.
+	 *   That requires LBR_FAR but that means far
+	 *   jmp need to be filtered out
+	 */
+	pr_cont("16-deep LBR, ");
+}
+
+/* atom */
 void intel_pmu_lbr_init_atom(void)
 {
+	/*
+	 * only models starting at stepping 10 seems
+	 * to have an operational LBR which can freeze
+	 * on PMU interrupt
+	 */
+	if (boot_cpu_data.x86_mask < 10) {
+		pr_cont("LBR disabled due to erratum");
+		return;
+	}
+
 	x86_pmu.lbr_nr	   = 8;
-	x86_pmu.lbr_tos    = 0x01c9;
-	x86_pmu.lbr_from   = 0x40;
-	x86_pmu.lbr_to     = 0x60;
+	x86_pmu.lbr_tos    = MSR_LBR_TOS;
+	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
+	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
+
+	/*
+	 * SW branch filter usage:
+	 * - compensate for lack of HW filter
+	 */
+	pr_cont("8-deep LBR, ");
 }
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index c7181be..32bcfc7 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -87,6 +87,23 @@
 	(void)checking_wrmsrl(hwc->config_base, val);
 }
 
+PMU_FORMAT_ATTR(event,	"config:0-7"	);
+PMU_FORMAT_ATTR(umask,	"config:8-15"	);
+PMU_FORMAT_ATTR(edge,	"config:18"	);
+PMU_FORMAT_ATTR(pc,	"config:19"	);
+PMU_FORMAT_ATTR(inv,	"config:23"	);
+PMU_FORMAT_ATTR(cmask,	"config:24-31"	);
+
+static struct attribute *intel_p6_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_pc.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask.attr,
+	NULL,
+};
+
 static __initconst const struct x86_pmu p6_pmu = {
 	.name			= "p6",
 	.handle_irq		= x86_pmu_handle_irq,
@@ -115,6 +132,8 @@
 	.cntval_mask		= (1ULL << 32) - 1,
 	.get_event_constraints	= x86_get_event_constraints,
 	.event_constraints	= p6_event_constraints,
+
+	.format_attrs		= intel_p6_formats_attr,
 };
 
 __init int p6_pmu_init(void)
diff --git a/arch/x86/kernel/kprobes-common.h b/arch/x86/kernel/kprobes-common.h
new file mode 100644
index 0000000..3230b68
--- /dev/null
+++ b/arch/x86/kernel/kprobes-common.h
@@ -0,0 +1,102 @@
+#ifndef __X86_KERNEL_KPROBES_COMMON_H
+#define __X86_KERNEL_KPROBES_COMMON_H
+
+/* Kprobes and Optprobes common header */
+
+#ifdef CONFIG_X86_64
+#define SAVE_REGS_STRING			\
+	/* Skip cs, ip, orig_ax. */		\
+	"	subq $24, %rsp\n"		\
+	"	pushq %rdi\n"			\
+	"	pushq %rsi\n"			\
+	"	pushq %rdx\n"			\
+	"	pushq %rcx\n"			\
+	"	pushq %rax\n"			\
+	"	pushq %r8\n"			\
+	"	pushq %r9\n"			\
+	"	pushq %r10\n"			\
+	"	pushq %r11\n"			\
+	"	pushq %rbx\n"			\
+	"	pushq %rbp\n"			\
+	"	pushq %r12\n"			\
+	"	pushq %r13\n"			\
+	"	pushq %r14\n"			\
+	"	pushq %r15\n"
+#define RESTORE_REGS_STRING			\
+	"	popq %r15\n"			\
+	"	popq %r14\n"			\
+	"	popq %r13\n"			\
+	"	popq %r12\n"			\
+	"	popq %rbp\n"			\
+	"	popq %rbx\n"			\
+	"	popq %r11\n"			\
+	"	popq %r10\n"			\
+	"	popq %r9\n"			\
+	"	popq %r8\n"			\
+	"	popq %rax\n"			\
+	"	popq %rcx\n"			\
+	"	popq %rdx\n"			\
+	"	popq %rsi\n"			\
+	"	popq %rdi\n"			\
+	/* Skip orig_ax, ip, cs */		\
+	"	addq $24, %rsp\n"
+#else
+#define SAVE_REGS_STRING			\
+	/* Skip cs, ip, orig_ax and gs. */	\
+	"	subl $16, %esp\n"		\
+	"	pushl %fs\n"			\
+	"	pushl %es\n"			\
+	"	pushl %ds\n"			\
+	"	pushl %eax\n"			\
+	"	pushl %ebp\n"			\
+	"	pushl %edi\n"			\
+	"	pushl %esi\n"			\
+	"	pushl %edx\n"			\
+	"	pushl %ecx\n"			\
+	"	pushl %ebx\n"
+#define RESTORE_REGS_STRING			\
+	"	popl %ebx\n"			\
+	"	popl %ecx\n"			\
+	"	popl %edx\n"			\
+	"	popl %esi\n"			\
+	"	popl %edi\n"			\
+	"	popl %ebp\n"			\
+	"	popl %eax\n"			\
+	/* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\
+	"	addl $24, %esp\n"
+#endif
+
+/* Ensure if the instruction can be boostable */
+extern int can_boost(kprobe_opcode_t *instruction);
+/* Recover instruction if given address is probed */
+extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
+					 unsigned long addr);
+/*
+ * Copy an instruction and adjust the displacement if the instruction
+ * uses the %rip-relative addressing mode.
+ */
+extern int __copy_instruction(u8 *dest, u8 *src);
+
+/* Generate a relative-jump/call instruction */
+extern void synthesize_reljump(void *from, void *to);
+extern void synthesize_relcall(void *from, void *to);
+
+#ifdef	CONFIG_OPTPROBES
+extern int arch_init_optprobes(void);
+extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter);
+extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr);
+#else	/* !CONFIG_OPTPROBES */
+static inline int arch_init_optprobes(void)
+{
+	return 0;
+}
+static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
+{
+	return 0;
+}
+static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
+{
+	return addr;
+}
+#endif
+#endif
diff --git a/arch/x86/kernel/kprobes-opt.c b/arch/x86/kernel/kprobes-opt.c
new file mode 100644
index 0000000..c5e410e
--- /dev/null
+++ b/arch/x86/kernel/kprobes-opt.c
@@ -0,0 +1,512 @@
+/*
+ *  Kernel Probes Jump Optimization (Optprobes)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2002, 2004
+ * Copyright (C) Hitachi Ltd., 2012
+ */
+#include <linux/kprobes.h>
+#include <linux/ptrace.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/hardirq.h>
+#include <linux/preempt.h>
+#include <linux/module.h>
+#include <linux/kdebug.h>
+#include <linux/kallsyms.h>
+#include <linux/ftrace.h>
+
+#include <asm/cacheflush.h>
+#include <asm/desc.h>
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+#include <asm/alternative.h>
+#include <asm/insn.h>
+#include <asm/debugreg.h>
+
+#include "kprobes-common.h"
+
+unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
+{
+	struct optimized_kprobe *op;
+	struct kprobe *kp;
+	long offs;
+	int i;
+
+	for (i = 0; i < RELATIVEJUMP_SIZE; i++) {
+		kp = get_kprobe((void *)addr - i);
+		/* This function only handles jump-optimized kprobe */
+		if (kp && kprobe_optimized(kp)) {
+			op = container_of(kp, struct optimized_kprobe, kp);
+			/* If op->list is not empty, op is under optimizing */
+			if (list_empty(&op->list))
+				goto found;
+		}
+	}
+
+	return addr;
+found:
+	/*
+	 * If the kprobe can be optimized, original bytes which can be
+	 * overwritten by jump destination address. In this case, original
+	 * bytes must be recovered from op->optinsn.copied_insn buffer.
+	 */
+	memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+	if (addr == (unsigned long)kp->addr) {
+		buf[0] = kp->opcode;
+		memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+	} else {
+		offs = addr - (unsigned long)kp->addr - 1;
+		memcpy(buf, op->optinsn.copied_insn + offs, RELATIVE_ADDR_SIZE - offs);
+	}
+
+	return (unsigned long)buf;
+}
+
+/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */
+static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val)
+{
+#ifdef CONFIG_X86_64
+	*addr++ = 0x48;
+	*addr++ = 0xbf;
+#else
+	*addr++ = 0xb8;
+#endif
+	*(unsigned long *)addr = val;
+}
+
+static void __used __kprobes kprobes_optinsn_template_holder(void)
+{
+	asm volatile (
+			".global optprobe_template_entry\n"
+			"optprobe_template_entry:\n"
+#ifdef CONFIG_X86_64
+			/* We don't bother saving the ss register */
+			"	pushq %rsp\n"
+			"	pushfq\n"
+			SAVE_REGS_STRING
+			"	movq %rsp, %rsi\n"
+			".global optprobe_template_val\n"
+			"optprobe_template_val:\n"
+			ASM_NOP5
+			ASM_NOP5
+			".global optprobe_template_call\n"
+			"optprobe_template_call:\n"
+			ASM_NOP5
+			/* Move flags to rsp */
+			"	movq 144(%rsp), %rdx\n"
+			"	movq %rdx, 152(%rsp)\n"
+			RESTORE_REGS_STRING
+			/* Skip flags entry */
+			"	addq $8, %rsp\n"
+			"	popfq\n"
+#else /* CONFIG_X86_32 */
+			"	pushf\n"
+			SAVE_REGS_STRING
+			"	movl %esp, %edx\n"
+			".global optprobe_template_val\n"
+			"optprobe_template_val:\n"
+			ASM_NOP5
+			".global optprobe_template_call\n"
+			"optprobe_template_call:\n"
+			ASM_NOP5
+			RESTORE_REGS_STRING
+			"	addl $4, %esp\n"	/* skip cs */
+			"	popf\n"
+#endif
+			".global optprobe_template_end\n"
+			"optprobe_template_end:\n");
+}
+
+#define TMPL_MOVE_IDX \
+	((long)&optprobe_template_val - (long)&optprobe_template_entry)
+#define TMPL_CALL_IDX \
+	((long)&optprobe_template_call - (long)&optprobe_template_entry)
+#define TMPL_END_IDX \
+	((long)&optprobe_template_end - (long)&optprobe_template_entry)
+
+#define INT3_SIZE sizeof(kprobe_opcode_t)
+
+/* Optimized kprobe call back function: called from optinsn */
+static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	unsigned long flags;
+
+	/* This is possible if op is under delayed unoptimizing */
+	if (kprobe_disabled(&op->kp))
+		return;
+
+	local_irq_save(flags);
+	if (kprobe_running()) {
+		kprobes_inc_nmissed_count(&op->kp);
+	} else {
+		/* Save skipped registers */
+#ifdef CONFIG_X86_64
+		regs->cs = __KERNEL_CS;
+#else
+		regs->cs = __KERNEL_CS | get_kernel_rpl();
+		regs->gs = 0;
+#endif
+		regs->ip = (unsigned long)op->kp.addr + INT3_SIZE;
+		regs->orig_ax = ~0UL;
+
+		__this_cpu_write(current_kprobe, &op->kp);
+		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+		opt_pre_handler(&op->kp, regs);
+		__this_cpu_write(current_kprobe, NULL);
+	}
+	local_irq_restore(flags);
+}
+
+static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
+{
+	int len = 0, ret;
+
+	while (len < RELATIVEJUMP_SIZE) {
+		ret = __copy_instruction(dest + len, src + len);
+		if (!ret || !can_boost(dest + len))
+			return -EINVAL;
+		len += ret;
+	}
+	/* Check whether the address range is reserved */
+	if (ftrace_text_reserved(src, src + len - 1) ||
+	    alternatives_text_reserved(src, src + len - 1) ||
+	    jump_label_text_reserved(src, src + len - 1))
+		return -EBUSY;
+
+	return len;
+}
+
+/* Check whether insn is indirect jump */
+static int __kprobes insn_is_indirect_jump(struct insn *insn)
+{
+	return ((insn->opcode.bytes[0] == 0xff &&
+		(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
+		insn->opcode.bytes[0] == 0xea);	/* Segment based jump */
+}
+
+/* Check whether insn jumps into specified address range */
+static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
+{
+	unsigned long target = 0;
+
+	switch (insn->opcode.bytes[0]) {
+	case 0xe0:	/* loopne */
+	case 0xe1:	/* loope */
+	case 0xe2:	/* loop */
+	case 0xe3:	/* jcxz */
+	case 0xe9:	/* near relative jump */
+	case 0xeb:	/* short relative jump */
+		break;
+	case 0x0f:
+		if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */
+			break;
+		return 0;
+	default:
+		if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */
+			break;
+		return 0;
+	}
+	target = (unsigned long)insn->next_byte + insn->immediate.value;
+
+	return (start <= target && target <= start + len);
+}
+
+/* Decode whole function to ensure any instructions don't jump into target */
+static int __kprobes can_optimize(unsigned long paddr)
+{
+	unsigned long addr, size = 0, offset = 0;
+	struct insn insn;
+	kprobe_opcode_t buf[MAX_INSN_SIZE];
+
+	/* Lookup symbol including addr */
+	if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
+		return 0;
+
+	/*
+	 * Do not optimize in the entry code due to the unstable
+	 * stack handling.
+	 */
+	if ((paddr >= (unsigned long)__entry_text_start) &&
+	    (paddr <  (unsigned long)__entry_text_end))
+		return 0;
+
+	/* Check there is enough space for a relative jump. */
+	if (size - offset < RELATIVEJUMP_SIZE)
+		return 0;
+
+	/* Decode instructions */
+	addr = paddr - offset;
+	while (addr < paddr - offset + size) { /* Decode until function end */
+		if (search_exception_tables(addr))
+			/*
+			 * Since some fixup code will jumps into this function,
+			 * we can't optimize kprobe in this function.
+			 */
+			return 0;
+		kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, addr));
+		insn_get_length(&insn);
+		/* Another subsystem puts a breakpoint */
+		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
+			return 0;
+		/* Recover address */
+		insn.kaddr = (void *)addr;
+		insn.next_byte = (void *)(addr + insn.length);
+		/* Check any instructions don't jump into target */
+		if (insn_is_indirect_jump(&insn) ||
+		    insn_jump_into_range(&insn, paddr + INT3_SIZE,
+					 RELATIVE_ADDR_SIZE))
+			return 0;
+		addr += insn.length;
+	}
+
+	return 1;
+}
+
+/* Check optimized_kprobe can actually be optimized. */
+int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op)
+{
+	int i;
+	struct kprobe *p;
+
+	for (i = 1; i < op->optinsn.size; i++) {
+		p = get_kprobe(op->kp.addr + i);
+		if (p && !kprobe_disabled(p))
+			return -EEXIST;
+	}
+
+	return 0;
+}
+
+/* Check the addr is within the optimized instructions. */
+int __kprobes
+arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr)
+{
+	return ((unsigned long)op->kp.addr <= addr &&
+		(unsigned long)op->kp.addr + op->optinsn.size > addr);
+}
+
+/* Free optimized instruction slot */
+static __kprobes
+void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
+{
+	if (op->optinsn.insn) {
+		free_optinsn_slot(op->optinsn.insn, dirty);
+		op->optinsn.insn = NULL;
+		op->optinsn.size = 0;
+	}
+}
+
+void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op)
+{
+	__arch_remove_optimized_kprobe(op, 1);
+}
+
+/*
+ * Copy replacing target instructions
+ * Target instructions MUST be relocatable (checked inside)
+ * This is called when new aggr(opt)probe is allocated or reused.
+ */
+int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
+{
+	u8 *buf;
+	int ret;
+	long rel;
+
+	if (!can_optimize((unsigned long)op->kp.addr))
+		return -EILSEQ;
+
+	op->optinsn.insn = get_optinsn_slot();
+	if (!op->optinsn.insn)
+		return -ENOMEM;
+
+	/*
+	 * Verify if the address gap is in 2GB range, because this uses
+	 * a relative jump.
+	 */
+	rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE;
+	if (abs(rel) > 0x7fffffff)
+		return -ERANGE;
+
+	buf = (u8 *)op->optinsn.insn;
+
+	/* Copy instructions into the out-of-line buffer */
+	ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr);
+	if (ret < 0) {
+		__arch_remove_optimized_kprobe(op, 0);
+		return ret;
+	}
+	op->optinsn.size = ret;
+
+	/* Copy arch-dep-instance from template */
+	memcpy(buf, &optprobe_template_entry, TMPL_END_IDX);
+
+	/* Set probe information */
+	synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op);
+
+	/* Set probe function call */
+	synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback);
+
+	/* Set returning jmp instruction at the tail of out-of-line buffer */
+	synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size,
+			   (u8 *)op->kp.addr + op->optinsn.size);
+
+	flush_icache_range((unsigned long) buf,
+			   (unsigned long) buf + TMPL_END_IDX +
+			   op->optinsn.size + RELATIVEJUMP_SIZE);
+	return 0;
+}
+
+#define MAX_OPTIMIZE_PROBES 256
+static struct text_poke_param *jump_poke_params;
+static struct jump_poke_buffer {
+	u8 buf[RELATIVEJUMP_SIZE];
+} *jump_poke_bufs;
+
+static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
+					    u8 *insn_buf,
+					    struct optimized_kprobe *op)
+{
+	s32 rel = (s32)((long)op->optinsn.insn -
+			((long)op->kp.addr + RELATIVEJUMP_SIZE));
+
+	/* Backup instructions which will be replaced by jump address */
+	memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
+	       RELATIVE_ADDR_SIZE);
+
+	insn_buf[0] = RELATIVEJUMP_OPCODE;
+	*(s32 *)(&insn_buf[1]) = rel;
+
+	tprm->addr = op->kp.addr;
+	tprm->opcode = insn_buf;
+	tprm->len = RELATIVEJUMP_SIZE;
+}
+
+/*
+ * Replace breakpoints (int3) with relative jumps.
+ * Caller must call with locking kprobe_mutex and text_mutex.
+ */
+void __kprobes arch_optimize_kprobes(struct list_head *oplist)
+{
+	struct optimized_kprobe *op, *tmp;
+	int c = 0;
+
+	list_for_each_entry_safe(op, tmp, oplist, list) {
+		WARN_ON(kprobe_disabled(&op->kp));
+		/* Setup param */
+		setup_optimize_kprobe(&jump_poke_params[c],
+				      jump_poke_bufs[c].buf, op);
+		list_del_init(&op->list);
+		if (++c >= MAX_OPTIMIZE_PROBES)
+			break;
+	}
+
+	/*
+	 * text_poke_smp doesn't support NMI/MCE code modifying.
+	 * However, since kprobes itself also doesn't support NMI/MCE
+	 * code probing, it's not a problem.
+	 */
+	text_poke_smp_batch(jump_poke_params, c);
+}
+
+static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm,
+					      u8 *insn_buf,
+					      struct optimized_kprobe *op)
+{
+	/* Set int3 to first byte for kprobes */
+	insn_buf[0] = BREAKPOINT_INSTRUCTION;
+	memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+
+	tprm->addr = op->kp.addr;
+	tprm->opcode = insn_buf;
+	tprm->len = RELATIVEJUMP_SIZE;
+}
+
+/*
+ * Recover original instructions and breakpoints from relative jumps.
+ * Caller must call with locking kprobe_mutex.
+ */
+extern void arch_unoptimize_kprobes(struct list_head *oplist,
+				    struct list_head *done_list)
+{
+	struct optimized_kprobe *op, *tmp;
+	int c = 0;
+
+	list_for_each_entry_safe(op, tmp, oplist, list) {
+		/* Setup param */
+		setup_unoptimize_kprobe(&jump_poke_params[c],
+					jump_poke_bufs[c].buf, op);
+		list_move(&op->list, done_list);
+		if (++c >= MAX_OPTIMIZE_PROBES)
+			break;
+	}
+
+	/*
+	 * text_poke_smp doesn't support NMI/MCE code modifying.
+	 * However, since kprobes itself also doesn't support NMI/MCE
+	 * code probing, it's not a problem.
+	 */
+	text_poke_smp_batch(jump_poke_params, c);
+}
+
+/* Replace a relative jump with a breakpoint (int3).  */
+void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
+{
+	u8 buf[RELATIVEJUMP_SIZE];
+
+	/* Set int3 to first byte for kprobes */
+	buf[0] = BREAKPOINT_INSTRUCTION;
+	memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+	text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE);
+}
+
+int  __kprobes
+setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
+{
+	struct optimized_kprobe *op;
+
+	if (p->flags & KPROBE_FLAG_OPTIMIZED) {
+		/* This kprobe is really able to run optimized path. */
+		op = container_of(p, struct optimized_kprobe, kp);
+		/* Detour through copied instructions */
+		regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX;
+		if (!reenter)
+			reset_current_kprobe();
+		preempt_enable_no_resched();
+		return 1;
+	}
+	return 0;
+}
+
+int __kprobes arch_init_optprobes(void)
+{
+	/* Allocate code buffer and parameter array */
+	jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) *
+				 MAX_OPTIMIZE_PROBES, GFP_KERNEL);
+	if (!jump_poke_bufs)
+		return -ENOMEM;
+
+	jump_poke_params = kmalloc(sizeof(struct text_poke_param) *
+				   MAX_OPTIMIZE_PROBES, GFP_KERNEL);
+	if (!jump_poke_params) {
+		kfree(jump_poke_bufs);
+		jump_poke_bufs = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 7da647d..e213fc8 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -30,16 +30,15 @@
  *		<jkenisto@us.ibm.com> and Prasanna S Panchamukhi
  *		<prasanna@in.ibm.com> added function-return probes.
  * 2005-May	Rusty Lynch <rusty.lynch@intel.com>
- * 		Added function return probes functionality
+ *		Added function return probes functionality
  * 2006-Feb	Masami Hiramatsu <hiramatu@sdl.hitachi.co.jp> added
- * 		kprobe-booster and kretprobe-booster for i386.
+ *		kprobe-booster and kretprobe-booster for i386.
  * 2007-Dec	Masami Hiramatsu <mhiramat@redhat.com> added kprobe-booster
- * 		and kretprobe-booster for x86-64
+ *		and kretprobe-booster for x86-64
  * 2007-Dec	Masami Hiramatsu <mhiramat@redhat.com>, Arjan van de Ven
- * 		<arjan@infradead.org> and Jim Keniston <jkenisto@us.ibm.com>
- * 		unified x86 kprobes code.
+ *		<arjan@infradead.org> and Jim Keniston <jkenisto@us.ibm.com>
+ *		unified x86 kprobes code.
  */
-
 #include <linux/kprobes.h>
 #include <linux/ptrace.h>
 #include <linux/string.h>
@@ -59,6 +58,8 @@
 #include <asm/insn.h>
 #include <asm/debugreg.h>
 
+#include "kprobes-common.h"
+
 void jprobe_return_end(void);
 
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
@@ -108,6 +109,7 @@
 			      doesn't switch kernel stack.*/
 	{NULL, NULL}	/* Terminator */
 };
+
 const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist);
 
 static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op)
@@ -123,11 +125,17 @@
 }
 
 /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/
-static void __kprobes synthesize_reljump(void *from, void *to)
+void __kprobes synthesize_reljump(void *from, void *to)
 {
 	__synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE);
 }
 
+/* Insert a call instruction at address 'from', which calls address 'to'.*/
+void __kprobes synthesize_relcall(void *from, void *to)
+{
+	__synthesize_relative_insn(from, to, RELATIVECALL_OPCODE);
+}
+
 /*
  * Skip the prefixes of the instruction.
  */
@@ -151,7 +159,7 @@
  * Returns non-zero if opcode is boostable.
  * RIP relative instructions are adjusted at copying time in 64 bits mode
  */
-static int __kprobes can_boost(kprobe_opcode_t *opcodes)
+int __kprobes can_boost(kprobe_opcode_t *opcodes)
 {
 	kprobe_opcode_t opcode;
 	kprobe_opcode_t *orig_opcodes = opcodes;
@@ -207,13 +215,15 @@
 	}
 }
 
-/* Recover the probed instruction at addr for further analysis. */
-static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
+static unsigned long
+__recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
 {
 	struct kprobe *kp;
+
 	kp = get_kprobe((void *)addr);
+	/* There is no probe, return original address */
 	if (!kp)
-		return -EINVAL;
+		return addr;
 
 	/*
 	 *  Basically, kp->ainsn.insn has an original instruction.
@@ -230,14 +240,29 @@
 	 */
 	memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
 	buf[0] = kp->opcode;
-	return 0;
+	return (unsigned long)buf;
+}
+
+/*
+ * Recover the probed instruction at addr for further analysis.
+ * Caller must lock kprobes by kprobe_mutex, or disable preemption
+ * for preventing to release referencing kprobes.
+ */
+unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
+{
+	unsigned long __addr;
+
+	__addr = __recover_optprobed_insn(buf, addr);
+	if (__addr != addr)
+		return __addr;
+
+	return __recover_probed_insn(buf, addr);
 }
 
 /* Check if paddr is at an instruction boundary */
 static int __kprobes can_probe(unsigned long paddr)
 {
-	int ret;
-	unsigned long addr, offset = 0;
+	unsigned long addr, __addr, offset = 0;
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
 
@@ -247,26 +272,24 @@
 	/* Decode instructions */
 	addr = paddr - offset;
 	while (addr < paddr) {
-		kernel_insn_init(&insn, (void *)addr);
-		insn_get_opcode(&insn);
-
 		/*
 		 * Check if the instruction has been modified by another
 		 * kprobe, in which case we replace the breakpoint by the
 		 * original instruction in our buffer.
+		 * Also, jump optimization will change the breakpoint to
+		 * relative-jump. Since the relative-jump itself is
+		 * normally used, we just go through if there is no kprobe.
 		 */
-		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) {
-			ret = recover_probed_instruction(buf, addr);
-			if (ret)
-				/*
-				 * Another debugging subsystem might insert
-				 * this breakpoint. In that case, we can't
-				 * recover it.
-				 */
-				return 0;
-			kernel_insn_init(&insn, buf);
-		}
+		__addr = recover_probed_instruction(buf, addr);
+		kernel_insn_init(&insn, (void *)__addr);
 		insn_get_length(&insn);
+
+		/*
+		 * Another debugging subsystem might insert this breakpoint.
+		 * In that case, we can't recover it.
+		 */
+		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
+			return 0;
 		addr += insn.length;
 	}
 
@@ -299,24 +322,16 @@
  * If not, return null.
  * Only applicable to 64-bit x86.
  */
-static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover)
+int __kprobes __copy_instruction(u8 *dest, u8 *src)
 {
 	struct insn insn;
-	int ret;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
 
-	kernel_insn_init(&insn, src);
-	if (recover) {
-		insn_get_opcode(&insn);
-		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) {
-			ret = recover_probed_instruction(buf,
-							 (unsigned long)src);
-			if (ret)
-				return 0;
-			kernel_insn_init(&insn, buf);
-		}
-	}
+	kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src));
 	insn_get_length(&insn);
+	/* Another subsystem puts a breakpoint, failed to recover */
+	if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
+		return 0;
 	memcpy(dest, insn.kaddr, insn.length);
 
 #ifdef CONFIG_X86_64
@@ -337,8 +352,7 @@
 		 * extension of the original signed 32-bit displacement would
 		 * have given.
 		 */
-		newdisp = (u8 *) src + (s64) insn.displacement.value -
-			  (u8 *) dest;
+		newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest;
 		BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check.  */
 		disp = (u8 *) dest + insn_offset_displacement(&insn);
 		*(s32 *) disp = (s32) newdisp;
@@ -349,18 +363,20 @@
 
 static void __kprobes arch_copy_kprobe(struct kprobe *p)
 {
-	/*
-	 * Copy an instruction without recovering int3, because it will be
-	 * put by another subsystem.
-	 */
-	__copy_instruction(p->ainsn.insn, p->addr, 0);
+	/* Copy an instruction with recovering if other optprobe modifies it.*/
+	__copy_instruction(p->ainsn.insn, p->addr);
 
-	if (can_boost(p->addr))
+	/*
+	 * __copy_instruction can modify the displacement of the instruction,
+	 * but it doesn't affect boostable check.
+	 */
+	if (can_boost(p->ainsn.insn))
 		p->ainsn.boostable = 0;
 	else
 		p->ainsn.boostable = -1;
 
-	p->opcode = *p->addr;
+	/* Also, displacement change doesn't affect the first byte */
+	p->opcode = p->ainsn.insn[0];
 }
 
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
@@ -442,8 +458,8 @@
 	}
 }
 
-void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
-				      struct pt_regs *regs)
+void __kprobes
+arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	unsigned long *sara = stack_addr(regs);
 
@@ -453,16 +469,8 @@
 	*sara = (unsigned long) &kretprobe_trampoline;
 }
 
-#ifdef CONFIG_OPTPROBES
-static int  __kprobes setup_detour_execution(struct kprobe *p,
-					     struct pt_regs *regs,
-					     int reenter);
-#else
-#define setup_detour_execution(p, regs, reenter) (0)
-#endif
-
-static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs,
-				       struct kprobe_ctlblk *kcb, int reenter)
+static void __kprobes
+setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, int reenter)
 {
 	if (setup_detour_execution(p, regs, reenter))
 		return;
@@ -504,8 +512,8 @@
  * within the handler. We save the original kprobes variables and just single
  * step on the instruction of the new probe without calling any user handlers.
  */
-static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs,
-				    struct kprobe_ctlblk *kcb)
+static int __kprobes
+reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
 {
 	switch (kcb->kprobe_status) {
 	case KPROBE_HIT_SSDONE:
@@ -600,69 +608,6 @@
 	return 0;
 }
 
-#ifdef CONFIG_X86_64
-#define SAVE_REGS_STRING		\
-	/* Skip cs, ip, orig_ax. */	\
-	"	subq $24, %rsp\n"	\
-	"	pushq %rdi\n"		\
-	"	pushq %rsi\n"		\
-	"	pushq %rdx\n"		\
-	"	pushq %rcx\n"		\
-	"	pushq %rax\n"		\
-	"	pushq %r8\n"		\
-	"	pushq %r9\n"		\
-	"	pushq %r10\n"		\
-	"	pushq %r11\n"		\
-	"	pushq %rbx\n"		\
-	"	pushq %rbp\n"		\
-	"	pushq %r12\n"		\
-	"	pushq %r13\n"		\
-	"	pushq %r14\n"		\
-	"	pushq %r15\n"
-#define RESTORE_REGS_STRING		\
-	"	popq %r15\n"		\
-	"	popq %r14\n"		\
-	"	popq %r13\n"		\
-	"	popq %r12\n"		\
-	"	popq %rbp\n"		\
-	"	popq %rbx\n"		\
-	"	popq %r11\n"		\
-	"	popq %r10\n"		\
-	"	popq %r9\n"		\
-	"	popq %r8\n"		\
-	"	popq %rax\n"		\
-	"	popq %rcx\n"		\
-	"	popq %rdx\n"		\
-	"	popq %rsi\n"		\
-	"	popq %rdi\n"		\
-	/* Skip orig_ax, ip, cs */	\
-	"	addq $24, %rsp\n"
-#else
-#define SAVE_REGS_STRING		\
-	/* Skip cs, ip, orig_ax and gs. */	\
-	"	subl $16, %esp\n"	\
-	"	pushl %fs\n"		\
-	"	pushl %es\n"		\
-	"	pushl %ds\n"		\
-	"	pushl %eax\n"		\
-	"	pushl %ebp\n"		\
-	"	pushl %edi\n"		\
-	"	pushl %esi\n"		\
-	"	pushl %edx\n"		\
-	"	pushl %ecx\n"		\
-	"	pushl %ebx\n"
-#define RESTORE_REGS_STRING		\
-	"	popl %ebx\n"		\
-	"	popl %ecx\n"		\
-	"	popl %edx\n"		\
-	"	popl %esi\n"		\
-	"	popl %edi\n"		\
-	"	popl %ebp\n"		\
-	"	popl %eax\n"		\
-	/* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\
-	"	addl $24, %esp\n"
-#endif
-
 /*
  * When a retprobed function returns, this code saves registers and
  * calls trampoline_handler() runs, which calls the kretprobe's handler.
@@ -816,8 +761,8 @@
  * jump instruction after the copied instruction, that jumps to the next
  * instruction after the probepoint.
  */
-static void __kprobes resume_execution(struct kprobe *p,
-		struct pt_regs *regs, struct kprobe_ctlblk *kcb)
+static void __kprobes
+resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
 {
 	unsigned long *tos = stack_addr(regs);
 	unsigned long copy_ip = (unsigned long)p->ainsn.insn;
@@ -996,8 +941,8 @@
 /*
  * Wrapper routine for handling exceptions.
  */
-int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
-				       unsigned long val, void *data)
+int __kprobes
+kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data)
 {
 	struct die_args *args = data;
 	int ret = NOTIFY_DONE;
@@ -1107,466 +1052,9 @@
 	return 0;
 }
 
-
-#ifdef CONFIG_OPTPROBES
-
-/* Insert a call instruction at address 'from', which calls address 'to'.*/
-static void __kprobes synthesize_relcall(void *from, void *to)
-{
-	__synthesize_relative_insn(from, to, RELATIVECALL_OPCODE);
-}
-
-/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */
-static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr,
-					  unsigned long val)
-{
-#ifdef CONFIG_X86_64
-	*addr++ = 0x48;
-	*addr++ = 0xbf;
-#else
-	*addr++ = 0xb8;
-#endif
-	*(unsigned long *)addr = val;
-}
-
-static void __used __kprobes kprobes_optinsn_template_holder(void)
-{
-	asm volatile (
-			".global optprobe_template_entry\n"
-			"optprobe_template_entry: \n"
-#ifdef CONFIG_X86_64
-			/* We don't bother saving the ss register */
-			"	pushq %rsp\n"
-			"	pushfq\n"
-			SAVE_REGS_STRING
-			"	movq %rsp, %rsi\n"
-			".global optprobe_template_val\n"
-			"optprobe_template_val: \n"
-			ASM_NOP5
-			ASM_NOP5
-			".global optprobe_template_call\n"
-			"optprobe_template_call: \n"
-			ASM_NOP5
-			/* Move flags to rsp */
-			"	movq 144(%rsp), %rdx\n"
-			"	movq %rdx, 152(%rsp)\n"
-			RESTORE_REGS_STRING
-			/* Skip flags entry */
-			"	addq $8, %rsp\n"
-			"	popfq\n"
-#else /* CONFIG_X86_32 */
-			"	pushf\n"
-			SAVE_REGS_STRING
-			"	movl %esp, %edx\n"
-			".global optprobe_template_val\n"
-			"optprobe_template_val: \n"
-			ASM_NOP5
-			".global optprobe_template_call\n"
-			"optprobe_template_call: \n"
-			ASM_NOP5
-			RESTORE_REGS_STRING
-			"	addl $4, %esp\n"	/* skip cs */
-			"	popf\n"
-#endif
-			".global optprobe_template_end\n"
-			"optprobe_template_end: \n");
-}
-
-#define TMPL_MOVE_IDX \
-	((long)&optprobe_template_val - (long)&optprobe_template_entry)
-#define TMPL_CALL_IDX \
-	((long)&optprobe_template_call - (long)&optprobe_template_entry)
-#define TMPL_END_IDX \
-	((long)&optprobe_template_end - (long)&optprobe_template_entry)
-
-#define INT3_SIZE sizeof(kprobe_opcode_t)
-
-/* Optimized kprobe call back function: called from optinsn */
-static void __kprobes optimized_callback(struct optimized_kprobe *op,
-					 struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long flags;
-
-	/* This is possible if op is under delayed unoptimizing */
-	if (kprobe_disabled(&op->kp))
-		return;
-
-	local_irq_save(flags);
-	if (kprobe_running()) {
-		kprobes_inc_nmissed_count(&op->kp);
-	} else {
-		/* Save skipped registers */
-#ifdef CONFIG_X86_64
-		regs->cs = __KERNEL_CS;
-#else
-		regs->cs = __KERNEL_CS | get_kernel_rpl();
-		regs->gs = 0;
-#endif
-		regs->ip = (unsigned long)op->kp.addr + INT3_SIZE;
-		regs->orig_ax = ~0UL;
-
-		__this_cpu_write(current_kprobe, &op->kp);
-		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-		opt_pre_handler(&op->kp, regs);
-		__this_cpu_write(current_kprobe, NULL);
-	}
-	local_irq_restore(flags);
-}
-
-static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
-{
-	int len = 0, ret;
-
-	while (len < RELATIVEJUMP_SIZE) {
-		ret = __copy_instruction(dest + len, src + len, 1);
-		if (!ret || !can_boost(dest + len))
-			return -EINVAL;
-		len += ret;
-	}
-	/* Check whether the address range is reserved */
-	if (ftrace_text_reserved(src, src + len - 1) ||
-	    alternatives_text_reserved(src, src + len - 1) ||
-	    jump_label_text_reserved(src, src + len - 1))
-		return -EBUSY;
-
-	return len;
-}
-
-/* Check whether insn is indirect jump */
-static int __kprobes insn_is_indirect_jump(struct insn *insn)
-{
-	return ((insn->opcode.bytes[0] == 0xff &&
-		(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
-		insn->opcode.bytes[0] == 0xea);	/* Segment based jump */
-}
-
-/* Check whether insn jumps into specified address range */
-static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
-{
-	unsigned long target = 0;
-
-	switch (insn->opcode.bytes[0]) {
-	case 0xe0:	/* loopne */
-	case 0xe1:	/* loope */
-	case 0xe2:	/* loop */
-	case 0xe3:	/* jcxz */
-	case 0xe9:	/* near relative jump */
-	case 0xeb:	/* short relative jump */
-		break;
-	case 0x0f:
-		if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */
-			break;
-		return 0;
-	default:
-		if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */
-			break;
-		return 0;
-	}
-	target = (unsigned long)insn->next_byte + insn->immediate.value;
-
-	return (start <= target && target <= start + len);
-}
-
-/* Decode whole function to ensure any instructions don't jump into target */
-static int __kprobes can_optimize(unsigned long paddr)
-{
-	int ret;
-	unsigned long addr, size = 0, offset = 0;
-	struct insn insn;
-	kprobe_opcode_t buf[MAX_INSN_SIZE];
-
-	/* Lookup symbol including addr */
-	if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
-		return 0;
-
-	/*
-	 * Do not optimize in the entry code due to the unstable
-	 * stack handling.
-	 */
-	if ((paddr >= (unsigned long )__entry_text_start) &&
-	    (paddr <  (unsigned long )__entry_text_end))
-		return 0;
-
-	/* Check there is enough space for a relative jump. */
-	if (size - offset < RELATIVEJUMP_SIZE)
-		return 0;
-
-	/* Decode instructions */
-	addr = paddr - offset;
-	while (addr < paddr - offset + size) { /* Decode until function end */
-		if (search_exception_tables(addr))
-			/*
-			 * Since some fixup code will jumps into this function,
-			 * we can't optimize kprobe in this function.
-			 */
-			return 0;
-		kernel_insn_init(&insn, (void *)addr);
-		insn_get_opcode(&insn);
-		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) {
-			ret = recover_probed_instruction(buf, addr);
-			if (ret)
-				return 0;
-			kernel_insn_init(&insn, buf);
-		}
-		insn_get_length(&insn);
-		/* Recover address */
-		insn.kaddr = (void *)addr;
-		insn.next_byte = (void *)(addr + insn.length);
-		/* Check any instructions don't jump into target */
-		if (insn_is_indirect_jump(&insn) ||
-		    insn_jump_into_range(&insn, paddr + INT3_SIZE,
-					 RELATIVE_ADDR_SIZE))
-			return 0;
-		addr += insn.length;
-	}
-
-	return 1;
-}
-
-/* Check optimized_kprobe can actually be optimized. */
-int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op)
-{
-	int i;
-	struct kprobe *p;
-
-	for (i = 1; i < op->optinsn.size; i++) {
-		p = get_kprobe(op->kp.addr + i);
-		if (p && !kprobe_disabled(p))
-			return -EEXIST;
-	}
-
-	return 0;
-}
-
-/* Check the addr is within the optimized instructions. */
-int __kprobes arch_within_optimized_kprobe(struct optimized_kprobe *op,
-					   unsigned long addr)
-{
-	return ((unsigned long)op->kp.addr <= addr &&
-		(unsigned long)op->kp.addr + op->optinsn.size > addr);
-}
-
-/* Free optimized instruction slot */
-static __kprobes
-void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
-{
-	if (op->optinsn.insn) {
-		free_optinsn_slot(op->optinsn.insn, dirty);
-		op->optinsn.insn = NULL;
-		op->optinsn.size = 0;
-	}
-}
-
-void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op)
-{
-	__arch_remove_optimized_kprobe(op, 1);
-}
-
-/*
- * Copy replacing target instructions
- * Target instructions MUST be relocatable (checked inside)
- */
-int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
-{
-	u8 *buf;
-	int ret;
-	long rel;
-
-	if (!can_optimize((unsigned long)op->kp.addr))
-		return -EILSEQ;
-
-	op->optinsn.insn = get_optinsn_slot();
-	if (!op->optinsn.insn)
-		return -ENOMEM;
-
-	/*
-	 * Verify if the address gap is in 2GB range, because this uses
-	 * a relative jump.
-	 */
-	rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE;
-	if (abs(rel) > 0x7fffffff)
-		return -ERANGE;
-
-	buf = (u8 *)op->optinsn.insn;
-
-	/* Copy instructions into the out-of-line buffer */
-	ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr);
-	if (ret < 0) {
-		__arch_remove_optimized_kprobe(op, 0);
-		return ret;
-	}
-	op->optinsn.size = ret;
-
-	/* Copy arch-dep-instance from template */
-	memcpy(buf, &optprobe_template_entry, TMPL_END_IDX);
-
-	/* Set probe information */
-	synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op);
-
-	/* Set probe function call */
-	synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback);
-
-	/* Set returning jmp instruction at the tail of out-of-line buffer */
-	synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size,
-			   (u8 *)op->kp.addr + op->optinsn.size);
-
-	flush_icache_range((unsigned long) buf,
-			   (unsigned long) buf + TMPL_END_IDX +
-			   op->optinsn.size + RELATIVEJUMP_SIZE);
-	return 0;
-}
-
-#define MAX_OPTIMIZE_PROBES 256
-static struct text_poke_param *jump_poke_params;
-static struct jump_poke_buffer {
-	u8 buf[RELATIVEJUMP_SIZE];
-} *jump_poke_bufs;
-
-static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
-					    u8 *insn_buf,
-					    struct optimized_kprobe *op)
-{
-	s32 rel = (s32)((long)op->optinsn.insn -
-			((long)op->kp.addr + RELATIVEJUMP_SIZE));
-
-	/* Backup instructions which will be replaced by jump address */
-	memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
-	       RELATIVE_ADDR_SIZE);
-
-	insn_buf[0] = RELATIVEJUMP_OPCODE;
-	*(s32 *)(&insn_buf[1]) = rel;
-
-	tprm->addr = op->kp.addr;
-	tprm->opcode = insn_buf;
-	tprm->len = RELATIVEJUMP_SIZE;
-}
-
-/*
- * Replace breakpoints (int3) with relative jumps.
- * Caller must call with locking kprobe_mutex and text_mutex.
- */
-void __kprobes arch_optimize_kprobes(struct list_head *oplist)
-{
-	struct optimized_kprobe *op, *tmp;
-	int c = 0;
-
-	list_for_each_entry_safe(op, tmp, oplist, list) {
-		WARN_ON(kprobe_disabled(&op->kp));
-		/* Setup param */
-		setup_optimize_kprobe(&jump_poke_params[c],
-				      jump_poke_bufs[c].buf, op);
-		list_del_init(&op->list);
-		if (++c >= MAX_OPTIMIZE_PROBES)
-			break;
-	}
-
-	/*
-	 * text_poke_smp doesn't support NMI/MCE code modifying.
-	 * However, since kprobes itself also doesn't support NMI/MCE
-	 * code probing, it's not a problem.
-	 */
-	text_poke_smp_batch(jump_poke_params, c);
-}
-
-static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm,
-					      u8 *insn_buf,
-					      struct optimized_kprobe *op)
-{
-	/* Set int3 to first byte for kprobes */
-	insn_buf[0] = BREAKPOINT_INSTRUCTION;
-	memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
-
-	tprm->addr = op->kp.addr;
-	tprm->opcode = insn_buf;
-	tprm->len = RELATIVEJUMP_SIZE;
-}
-
-/*
- * Recover original instructions and breakpoints from relative jumps.
- * Caller must call with locking kprobe_mutex.
- */
-extern void arch_unoptimize_kprobes(struct list_head *oplist,
-				    struct list_head *done_list)
-{
-	struct optimized_kprobe *op, *tmp;
-	int c = 0;
-
-	list_for_each_entry_safe(op, tmp, oplist, list) {
-		/* Setup param */
-		setup_unoptimize_kprobe(&jump_poke_params[c],
-					jump_poke_bufs[c].buf, op);
-		list_move(&op->list, done_list);
-		if (++c >= MAX_OPTIMIZE_PROBES)
-			break;
-	}
-
-	/*
-	 * text_poke_smp doesn't support NMI/MCE code modifying.
-	 * However, since kprobes itself also doesn't support NMI/MCE
-	 * code probing, it's not a problem.
-	 */
-	text_poke_smp_batch(jump_poke_params, c);
-}
-
-/* Replace a relative jump with a breakpoint (int3).  */
-void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
-{
-	u8 buf[RELATIVEJUMP_SIZE];
-
-	/* Set int3 to first byte for kprobes */
-	buf[0] = BREAKPOINT_INSTRUCTION;
-	memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
-	text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE);
-}
-
-static int  __kprobes setup_detour_execution(struct kprobe *p,
-					     struct pt_regs *regs,
-					     int reenter)
-{
-	struct optimized_kprobe *op;
-
-	if (p->flags & KPROBE_FLAG_OPTIMIZED) {
-		/* This kprobe is really able to run optimized path. */
-		op = container_of(p, struct optimized_kprobe, kp);
-		/* Detour through copied instructions */
-		regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX;
-		if (!reenter)
-			reset_current_kprobe();
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-
-static int __kprobes init_poke_params(void)
-{
-	/* Allocate code buffer and parameter array */
-	jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) *
-				 MAX_OPTIMIZE_PROBES, GFP_KERNEL);
-	if (!jump_poke_bufs)
-		return -ENOMEM;
-
-	jump_poke_params = kmalloc(sizeof(struct text_poke_param) *
-				   MAX_OPTIMIZE_PROBES, GFP_KERNEL);
-	if (!jump_poke_params) {
-		kfree(jump_poke_bufs);
-		jump_poke_bufs = NULL;
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-#else	/* !CONFIG_OPTPROBES */
-static int __kprobes init_poke_params(void)
-{
-	return 0;
-}
-#endif
-
 int __init arch_init_kprobes(void)
 {
-	return init_poke_params();
+	return arch_init_optprobes();
 }
 
 int __kprobes arch_trampoline_kprobe(struct kprobe *p)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index f0c6fd6..694d801 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -438,9 +438,9 @@
 static __init int activate_jump_labels(void)
 {
 	if (has_steal_clock) {
-		jump_label_inc(&paravirt_steal_enabled);
+		static_key_slow_inc(&paravirt_steal_enabled);
 		if (steal_acc)
-			jump_label_inc(&paravirt_steal_rq_enabled);
+			static_key_slow_inc(&paravirt_steal_rq_enabled);
 	}
 
 	return 0;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index d90272e..ada2f99 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -202,8 +202,8 @@
 	__native_flush_tlb_single(addr);
 }
 
-struct jump_label_key paravirt_steal_enabled;
-struct jump_label_key paravirt_steal_rq_enabled;
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
 
 static u64 native_steal_clock(int cpu)
 {
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 15763af..44eefde 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -377,8 +377,8 @@
 void default_idle(void)
 {
 	if (hlt_use_halt()) {
-		trace_power_start(POWER_CSTATE, 1, smp_processor_id());
-		trace_cpu_idle(1, smp_processor_id());
+		trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id());
+		trace_cpu_idle_rcuidle(1, smp_processor_id());
 		current_thread_info()->status &= ~TS_POLLING;
 		/*
 		 * TS_POLLING-cleared state must be visible before we
@@ -391,8 +391,8 @@
 		else
 			local_irq_enable();
 		current_thread_info()->status |= TS_POLLING;
-		trace_power_end(smp_processor_id());
-		trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
+		trace_power_end_rcuidle(smp_processor_id());
+		trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	} else {
 		local_irq_enable();
 		/* loop is done by the caller */
@@ -450,8 +450,8 @@
 static void mwait_idle(void)
 {
 	if (!need_resched()) {
-		trace_power_start(POWER_CSTATE, 1, smp_processor_id());
-		trace_cpu_idle(1, smp_processor_id());
+		trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id());
+		trace_cpu_idle_rcuidle(1, smp_processor_id());
 		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
 			clflush((void *)&current_thread_info()->flags);
 
@@ -461,8 +461,8 @@
 			__sti_mwait(0, 0);
 		else
 			local_irq_enable();
-		trace_power_end(smp_processor_id());
-		trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
+		trace_power_end_rcuidle(smp_processor_id());
+		trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	} else
 		local_irq_enable();
 }
@@ -474,13 +474,13 @@
  */
 static void poll_idle(void)
 {
-	trace_power_start(POWER_CSTATE, 0, smp_processor_id());
-	trace_cpu_idle(0, smp_processor_id());
+	trace_power_start_rcuidle(POWER_CSTATE, 0, smp_processor_id());
+	trace_cpu_idle_rcuidle(0, smp_processor_id());
 	local_irq_enable();
 	while (!need_resched())
 		cpu_relax();
-	trace_power_end(smp_processor_id());
-	trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
+	trace_power_end_rcuidle(smp_processor_id());
+	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 }
 
 /*
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index fe15dcc..ea7b4fd 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -234,7 +234,7 @@
 }
 
 static bool mmu_audit;
-static struct jump_label_key mmu_audit_key;
+static struct static_key mmu_audit_key;
 
 static void __kvm_mmu_audit(struct kvm_vcpu *vcpu, int point)
 {
@@ -250,7 +250,7 @@
 
 static inline void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point)
 {
-	if (static_branch((&mmu_audit_key)))
+	if (static_key_false((&mmu_audit_key)))
 		__kvm_mmu_audit(vcpu, point);
 }
 
@@ -259,7 +259,7 @@
 	if (mmu_audit)
 		return;
 
-	jump_label_inc(&mmu_audit_key);
+	static_key_slow_inc(&mmu_audit_key);
 	mmu_audit = true;
 }
 
@@ -268,7 +268,7 @@
 	if (!mmu_audit)
 		return;
 
-	jump_label_dec(&mmu_audit_key);
+	static_key_slow_dec(&mmu_audit_key);
 	mmu_audit = false;
 }
 
diff --git a/arch/x86/lib/inat.c b/arch/x86/lib/inat.c
index 88ad5fb..c1f01a8 100644
--- a/arch/x86/lib/inat.c
+++ b/arch/x86/lib/inat.c
@@ -29,46 +29,46 @@
 	return inat_primary_table[opcode];
 }
 
-insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, insn_byte_t last_pfx,
+int inat_get_last_prefix_id(insn_byte_t last_pfx)
+{
+	insn_attr_t lpfx_attr;
+
+	lpfx_attr = inat_get_opcode_attribute(last_pfx);
+	return inat_last_prefix_id(lpfx_attr);
+}
+
+insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, int lpfx_id,
 				      insn_attr_t esc_attr)
 {
 	const insn_attr_t *table;
-	insn_attr_t lpfx_attr;
-	int n, m = 0;
+	int n;
 
 	n = inat_escape_id(esc_attr);
-	if (last_pfx) {
-		lpfx_attr = inat_get_opcode_attribute(last_pfx);
-		m = inat_last_prefix_id(lpfx_attr);
-	}
+
 	table = inat_escape_tables[n][0];
 	if (!table)
 		return 0;
-	if (inat_has_variant(table[opcode]) && m) {
-		table = inat_escape_tables[n][m];
+	if (inat_has_variant(table[opcode]) && lpfx_id) {
+		table = inat_escape_tables[n][lpfx_id];
 		if (!table)
 			return 0;
 	}
 	return table[opcode];
 }
 
-insn_attr_t inat_get_group_attribute(insn_byte_t modrm, insn_byte_t last_pfx,
+insn_attr_t inat_get_group_attribute(insn_byte_t modrm, int lpfx_id,
 				     insn_attr_t grp_attr)
 {
 	const insn_attr_t *table;
-	insn_attr_t lpfx_attr;
-	int n, m = 0;
+	int n;
 
 	n = inat_group_id(grp_attr);
-	if (last_pfx) {
-		lpfx_attr = inat_get_opcode_attribute(last_pfx);
-		m = inat_last_prefix_id(lpfx_attr);
-	}
+
 	table = inat_group_tables[n][0];
 	if (!table)
 		return inat_group_common_attribute(grp_attr);
-	if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && m) {
-		table = inat_group_tables[n][m];
+	if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && lpfx_id) {
+		table = inat_group_tables[n][lpfx_id];
 		if (!table)
 			return inat_group_common_attribute(grp_attr);
 	}
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 5a1f9f3..25feb1a 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -185,7 +185,8 @@
 void insn_get_opcode(struct insn *insn)
 {
 	struct insn_field *opcode = &insn->opcode;
-	insn_byte_t op, pfx;
+	insn_byte_t op;
+	int pfx_id;
 	if (opcode->got)
 		return;
 	if (!insn->prefixes.got)
@@ -212,8 +213,8 @@
 		/* Get escaped opcode */
 		op = get_next(insn_byte_t, insn);
 		opcode->bytes[opcode->nbytes++] = op;
-		pfx = insn_last_prefix(insn);
-		insn->attr = inat_get_escape_attribute(op, pfx, insn->attr);
+		pfx_id = insn_last_prefix_id(insn);
+		insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr);
 	}
 	if (inat_must_vex(insn->attr))
 		insn->attr = 0;	/* This instruction is bad */
@@ -235,7 +236,7 @@
 void insn_get_modrm(struct insn *insn)
 {
 	struct insn_field *modrm = &insn->modrm;
-	insn_byte_t pfx, mod;
+	insn_byte_t pfx_id, mod;
 	if (modrm->got)
 		return;
 	if (!insn->opcode.got)
@@ -246,8 +247,8 @@
 		modrm->value = mod;
 		modrm->nbytes = 1;
 		if (inat_is_group(insn->attr)) {
-			pfx = insn_last_prefix(insn);
-			insn->attr = inat_get_group_attribute(mod, pfx,
+			pfx_id = insn_last_prefix_id(insn);
+			insn->attr = inat_get_group_attribute(mod, pfx_id,
 							      insn->attr);
 			if (insn_is_avx(insn) && !inat_accept_vex(insn->attr))
 				insn->attr = 0;	/* This is bad */
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 59f4261..6588f43 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -94,13 +94,13 @@
 
 	target_state = &drv->states[next_state];
 
-	trace_power_start(POWER_CSTATE, next_state, dev->cpu);
-	trace_cpu_idle(next_state, dev->cpu);
+	trace_power_start_rcuidle(POWER_CSTATE, next_state, dev->cpu);
+	trace_cpu_idle_rcuidle(next_state, dev->cpu);
 
 	entered_state = target_state->enter(dev, drv, next_state);
 
-	trace_power_end(dev->cpu);
-	trace_cpu_idle(PWR_EVENT_EXIT, dev->cpu);
+	trace_power_end_rcuidle(dev->cpu);
+	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
 
 	if (entered_state >= 0) {
 		/* Update cpuidle counters */
diff --git a/fs/exec.c b/fs/exec.c
index 153dee1..b0695a9 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -63,6 +63,8 @@
 #include <trace/events/task.h>
 #include "internal.h"
 
+#include <trace/events/sched.h>
+
 int core_uses_pid;
 char core_pattern[CORENAME_MAX_SIZE] = "core";
 unsigned int core_pipe_limit;
@@ -1402,9 +1404,10 @@
 			 */
 			bprm->recursion_depth = depth;
 			if (retval >= 0) {
-				if (depth == 0)
-					ptrace_event(PTRACE_EVENT_EXEC,
-							old_pid);
+				if (depth == 0) {
+					trace_sched_process_exec(current, old_pid, bprm);
+					ptrace_event(PTRACE_EVENT_EXEC, old_pid);
+				}
 				put_binfmt(fmt);
 				allow_write_access(bprm->file);
 				if (bprm->file)
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 028e26f..72a6cab 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -31,16 +31,33 @@
 
 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 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 @@
 };
 
 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 @@
 #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 @@
  */
 #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 c3da42d..dd478fc 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -146,6 +146,10 @@
 	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 @@
 	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 @@
 };
 
 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 @@
 	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 a64b00e..3f830e0 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);
 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 5ce8b14..c513a40 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 @@
 
 #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 __always_inline bool static_branch(struct jump_label_key *key)
+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 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_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 @@
 {
 }
 
-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)))
+	if (unlikely(atomic_read(&key->enabled)) > 0)
 		return true;
 	return false;
 }
 
-static inline void jump_label_inc(struct jump_label_key *key)
+static __always_inline bool static_key_true(struct static_key *key)
+{
+	if (likely(atomic_read(&key->enabled)) > 0)
+		return true;
+	return false;
+}
+
+/* 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 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 0eac07c..7dfaae7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -214,8 +214,8 @@
 #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 b809265..29734be 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -163,13 +163,13 @@
 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 abb2776..57ae485 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -129,11 +129,40 @@
 	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 @@
 };
 
 #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 @@
 		__u64		bp_len;
 		__u64		config2; /* extension of config1 */
 	};
+	__u64	branch_sample_type; /* enum branch_sample_type */
 };
 
 /*
@@ -291,12 +323,14 @@
 	__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 @@
 	 *
 	 *	{ u32			size;
 	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
+	 *
+	 *	{ u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
@@ -512,8 +548,9 @@
 #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 <linux/sysfs.h>
 #include <asm/local.h>
 
 #define PERF_MAX_STACK_DEPTH		255
@@ -528,12 +565,34 @@
 	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 +623,9 @@
 			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 +677,7 @@
 	struct list_head		entry;
 
 	struct device			*dev;
+	const struct attribute_group	**attr_groups;
 	char				*name;
 	int				type;
 
@@ -681,6 +743,17 @@
 	 * 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 +923,9 @@
 #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 +987,8 @@
 	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 +1053,7 @@
 extern u64 perf_event_read_value(struct perf_event *event,
 				 u64 *enabled, u64 *running);
 
+
 struct perf_sample_data {
 	u64				type;
 
@@ -995,12 +1073,14 @@
 	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 +1109,7 @@
 	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 +1137,7 @@
 {
 	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 +1146,12 @@
 	}
 }
 
-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 +1160,7 @@
 {
 	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 +1219,11 @@
 # 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);
@@ -1207,5 +1292,18 @@
 	register_cpu_notifier(&fn##_nb);				\
 } while (0)
 
+
+#define PMU_FORMAT_ATTR(_name, _format)					\
+static ssize_t								\
+_name##_show(struct device *dev,					\
+			       struct device_attribute *attr,		\
+			       char *page)				\
+{									\
+	BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE);			\
+	return sprintf(page, _format "\n");				\
+}									\
+									\
+static struct device_attribute format_attr_##_name = __ATTR_RO(_name)
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_PERF_EVENT_H */
diff --git a/include/linux/static_key.h b/include/linux/static_key.h
new file mode 100644
index 0000000..27bd3f8
--- /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 df0a779..bd96ecd 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 {
 	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 @@
  * 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 @@
 									\
 		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 @@
 			} while ((++it_func_ptr)->func);		\
 		}							\
 		rcu_read_unlock_sched_notrace();			\
+		postrcu;						\
 	} while (0)
 
 /*
@@ -139,15 +141,25 @@
  * 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 @@
 	__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 @@
 	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)				\
diff --git a/include/net/sock.h b/include/net/sock.h
index 91c1c8b..dcde2d9 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -55,7 +55,7 @@
 #include <linux/uaccess.h>
 #include <linux/memcontrol.h>
 #include <linux/res_counter.h>
-#include <linux/jump_label.h>
+#include <linux/static_key.h>
 
 #include <linux/filter.h>
 #include <linux/rculist_nulls.h>
@@ -924,13 +924,13 @@
 #endif /* SOCK_REFCNT_DEBUG */
 
 #if defined(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) && defined(CONFIG_NET)
-extern struct jump_label_key memcg_socket_limit_enabled;
+extern struct static_key memcg_socket_limit_enabled;
 static inline struct cg_proto *parent_cg_proto(struct proto *proto,
 					       struct cg_proto *cg_proto)
 {
 	return proto->proto_cgroup(parent_mem_cgroup(cg_proto->memcg));
 }
-#define mem_cgroup_sockets_enabled static_branch(&memcg_socket_limit_enabled)
+#define mem_cgroup_sockets_enabled static_key_false(&memcg_socket_limit_enabled)
 #else
 #define mem_cgroup_sockets_enabled 0
 static inline struct cg_proto *parent_cg_proto(struct proto *proto,
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 1bcc2a8..14b3894 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -151,6 +151,8 @@
    events get removed */
 static inline void trace_power_start(u64 type, u64 state, u64 cpuid) {};
 static inline void trace_power_end(u64 cpuid) {};
+static inline void trace_power_start_rcuidle(u64 type, u64 state, u64 cpuid) {};
+static inline void trace_power_end_rcuidle(u64 cpuid) {};
 static inline void trace_power_frequency(u64 type, u64 state, u64 cpuid) {};
 #endif /* _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED */
 
diff --git a/include/trace/events/printk.h b/include/trace/events/printk.h
new file mode 100644
index 0000000..94ec79c
--- /dev/null
+++ b/include/trace/events/printk.h
@@ -0,0 +1,41 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM printk
+
+#if !defined(_TRACE_PRINTK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PRINTK_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT_CONDITION(console,
+	TP_PROTO(const char *log_buf, unsigned start, unsigned end,
+		 unsigned log_buf_len),
+
+	TP_ARGS(log_buf, start, end, log_buf_len),
+
+	TP_CONDITION(start != end),
+
+	TP_STRUCT__entry(
+		__dynamic_array(char, msg, end - start + 1)
+	),
+
+	TP_fast_assign(
+		if ((start & (log_buf_len - 1)) > (end & (log_buf_len - 1))) {
+			memcpy(__get_dynamic_array(msg),
+			       log_buf + (start & (log_buf_len - 1)),
+			       log_buf_len - (start & (log_buf_len - 1)));
+			memcpy((char *)__get_dynamic_array(msg) +
+			       log_buf_len - (start & (log_buf_len - 1)),
+			       log_buf, end & (log_buf_len - 1));
+		} else
+			memcpy(__get_dynamic_array(msg),
+			       log_buf + (start & (log_buf_len - 1)),
+			       end - start);
+		((char *)__get_dynamic_array(msg))[end - start] = 0;
+	),
+
+	TP_printk("%s", __get_str(msg))
+);
+#endif /* _TRACE_PRINTK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index e33ed1b..fbc7b1a 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -6,6 +6,7 @@
 
 #include <linux/sched.h>
 #include <linux/tracepoint.h>
+#include <linux/binfmts.h>
 
 /*
  * Tracepoint for calling kthread_stop, performed to end a kthread:
@@ -276,6 +277,32 @@
 );
 
 /*
+ * Tracepoint for exec:
+ */
+TRACE_EVENT(sched_process_exec,
+
+	TP_PROTO(struct task_struct *p, pid_t old_pid,
+		 struct linux_binprm *bprm),
+
+	TP_ARGS(p, old_pid, bprm),
+
+	TP_STRUCT__entry(
+		__string(	filename,	bprm->filename	)
+		__field(	pid_t,		pid		)
+		__field(	pid_t,		old_pid		)
+	),
+
+	TP_fast_assign(
+		__assign_str(filename, bprm->filename);
+		__entry->pid		= p->pid;
+		__entry->old_pid	= p->pid;
+	),
+
+	TP_printk("filename=%s pid=%d old_pid=%d", __get_str(filename),
+		  __entry->pid, __entry->old_pid)
+);
+
+/*
  * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE
  *     adding sched_stat support to SCHED_FIFO/RR would be welcome.
  */
diff --git a/include/trace/events/signal.h b/include/trace/events/signal.h
index 17df434..39a8a43 100644
--- a/include/trace/events/signal.h
+++ b/include/trace/events/signal.h
@@ -23,11 +23,23 @@
 		}						\
 	} while (0)
 
+#ifndef TRACE_HEADER_MULTI_READ
+enum {
+	TRACE_SIGNAL_DELIVERED,
+	TRACE_SIGNAL_IGNORED,
+	TRACE_SIGNAL_ALREADY_PENDING,
+	TRACE_SIGNAL_OVERFLOW_FAIL,
+	TRACE_SIGNAL_LOSE_INFO,
+};
+#endif
+
 /**
  * signal_generate - called when a signal is generated
  * @sig: signal number
  * @info: pointer to struct siginfo
  * @task: pointer to struct task_struct
+ * @group: shared or private
+ * @result: TRACE_SIGNAL_*
  *
  * Current process sends a 'sig' signal to 'task' process with
  * 'info' siginfo. If 'info' is SEND_SIG_NOINFO or SEND_SIG_PRIV,
@@ -37,9 +49,10 @@
  */
 TRACE_EVENT(signal_generate,
 
-	TP_PROTO(int sig, struct siginfo *info, struct task_struct *task),
+	TP_PROTO(int sig, struct siginfo *info, struct task_struct *task,
+			int group, int result),
 
-	TP_ARGS(sig, info, task),
+	TP_ARGS(sig, info, task, group, result),
 
 	TP_STRUCT__entry(
 		__field(	int,	sig			)
@@ -47,6 +60,8 @@
 		__field(	int,	code			)
 		__array(	char,	comm,	TASK_COMM_LEN	)
 		__field(	pid_t,	pid			)
+		__field(	int,	group			)
+		__field(	int,	result			)
 	),
 
 	TP_fast_assign(
@@ -54,11 +69,14 @@
 		TP_STORE_SIGINFO(__entry, info);
 		memcpy(__entry->comm, task->comm, TASK_COMM_LEN);
 		__entry->pid	= task->pid;
+		__entry->group	= group;
+		__entry->result	= result;
 	),
 
-	TP_printk("sig=%d errno=%d code=%d comm=%s pid=%d",
+	TP_printk("sig=%d errno=%d code=%d comm=%s pid=%d grp=%d res=%d",
 		  __entry->sig, __entry->errno, __entry->code,
-		  __entry->comm, __entry->pid)
+		  __entry->comm, __entry->pid, __entry->group,
+		  __entry->result)
 );
 
 /**
@@ -101,65 +119,6 @@
 		  __entry->sa_handler, __entry->sa_flags)
 );
 
-DECLARE_EVENT_CLASS(signal_queue_overflow,
-
-	TP_PROTO(int sig, int group, struct siginfo *info),
-
-	TP_ARGS(sig, group, info),
-
-	TP_STRUCT__entry(
-		__field(	int,	sig	)
-		__field(	int,	group	)
-		__field(	int,	errno	)
-		__field(	int,	code	)
-	),
-
-	TP_fast_assign(
-		__entry->sig	= sig;
-		__entry->group	= group;
-		TP_STORE_SIGINFO(__entry, info);
-	),
-
-	TP_printk("sig=%d group=%d errno=%d code=%d",
-		  __entry->sig, __entry->group, __entry->errno, __entry->code)
-);
-
-/**
- * signal_overflow_fail - called when signal queue is overflow
- * @sig: signal number
- * @group: signal to process group or not (bool)
- * @info: pointer to struct siginfo
- *
- * Kernel fails to generate 'sig' signal with 'info' siginfo, because
- * siginfo queue is overflow, and the signal is dropped.
- * 'group' is not 0 if the signal will be sent to a process group.
- * 'sig' is always one of RT signals.
- */
-DEFINE_EVENT(signal_queue_overflow, signal_overflow_fail,
-
-	TP_PROTO(int sig, int group, struct siginfo *info),
-
-	TP_ARGS(sig, group, info)
-);
-
-/**
- * signal_lose_info - called when siginfo is lost
- * @sig: signal number
- * @group: signal to process group or not (bool)
- * @info: pointer to struct siginfo
- *
- * Kernel generates 'sig' signal but loses 'info' siginfo, because siginfo
- * queue is overflow.
- * 'group' is not 0 if the signal will be sent to a process group.
- * 'sig' is always one of non-RT signals.
- */
-DEFINE_EVENT(signal_queue_overflow, signal_lose_info,
-
-	TP_PROTO(int sig, int group, struct siginfo *info),
-
-	TP_ARGS(sig, group, info)
-);
-
 #endif /* _TRACE_SIGNAL_H */
 
 /* This part must be outside protection */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1b5c081..c61234b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -118,6 +118,13 @@
 		       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 @@
  * 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 @@
 	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 @@
 			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 @@
 }
 
 /*
+ * 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 @@
 	 */
 	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 @@
 
 	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 @@
 			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 @@
 	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 @@
 	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 @@
 {
 	struct perf_event_mmap_page *userpg;
 	struct ring_buffer *rb;
-	u64 enabled, running;
+	u64 enabled, running, now;
 
 	rcu_read_lock();
 	/*
@@ -3286,7 +3373,7 @@
 	 * 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 @@
 	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 @@
 	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 @@
 	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(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 @@
 	 * 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 @@
 			}
 		}
 	}
+
+	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 @@
 		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 @@
 	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 @@
 
 	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 @@
 	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 @@
 		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 @@
 	.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 @@
 	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 @@
 	.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 @@
 	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 @@
 	.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 @@
 	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 @@
 	.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 @@
 	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 @@
 	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 @@
 		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 @@
 
 	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 @@
 				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 @@
 	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 @@
 		 * - 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 ee706ce..bb38c4d 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -581,6 +581,12 @@
 	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 @@
 	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 @@
 	.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 fb7db75..838687e 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 01d3b70..4304919 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 @@
 	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 @@
 	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 @@
 	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 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 @@
 
 #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 @@
 				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 @@
 		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 @@
 	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 @@
 	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)
+		struct static_key *iterk;
+
+		iterk = (struct static_key *)(unsigned long)iter->key;
+		if (iterk == key)
 			continue;
 
-		key = (struct jump_label_key *)(unsigned long)iter->key;
-
+		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 @@
 	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;
@@ -416,12 +432,13 @@
 	return ret;
 }
 
-static void jump_label_update(struct jump_label_key *key, int enable)
+static void jump_label_update(struct static_key *key, int enable)
 {
-	struct jump_entry *entry = key->entries, *stop = __stop___jump_table;
+	struct jump_entry *stop = __stop___jump_table;
+	struct jump_entry *entry = jump_label_get_entries(key);
 
 #ifdef CONFIG_MODULES
-	struct module *mod = __module_address((jump_label_t)key);
+	struct module *mod = __module_address((unsigned long)key);
 
 	__jump_label_mod_update(key, enable);
 
diff --git a/kernel/printk.c b/kernel/printk.c
index 32690a0..0b3ea2c 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -44,6 +44,9 @@
 
 #include <asm/uaccess.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/printk.h>
+
 /*
  * Architectures can override it:
  */
@@ -542,6 +545,8 @@
 static void _call_console_drivers(unsigned start,
 				unsigned end, int msg_log_level)
 {
+	trace_console(&LOG_BUF(0), start, end, log_buf_len);
+
 	if ((msg_log_level < console_loglevel || ignore_loglevel) &&
 			console_drivers && start != end) {
 		if ((start & LOG_BUF_MASK) > (end & LOG_BUF_MASK)) {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b342f57..6c41ba4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -162,13 +162,13 @@
 
 #ifdef HAVE_JUMP_LABEL
 
-#define jump_label_key__true  jump_label_key_enabled
-#define jump_label_key__false jump_label_key_disabled
+#define jump_label_key__true  STATIC_KEY_INIT_TRUE
+#define jump_label_key__false STATIC_KEY_INIT_FALSE
 
 #define SCHED_FEAT(name, enabled)	\
 	jump_label_key__##enabled ,
 
-struct jump_label_key sched_feat_keys[__SCHED_FEAT_NR] = {
+struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
 #include "features.h"
 };
 
@@ -176,14 +176,14 @@
 
 static void sched_feat_disable(int i)
 {
-	if (jump_label_enabled(&sched_feat_keys[i]))
-		jump_label_dec(&sched_feat_keys[i]);
+	if (static_key_enabled(&sched_feat_keys[i]))
+		static_key_slow_dec(&sched_feat_keys[i]);
 }
 
 static void sched_feat_enable(int i)
 {
-	if (!jump_label_enabled(&sched_feat_keys[i]))
-		jump_label_inc(&sched_feat_keys[i]);
+	if (!static_key_enabled(&sched_feat_keys[i]))
+		static_key_slow_inc(&sched_feat_keys[i]);
 }
 #else
 static void sched_feat_disable(int i) { };
@@ -894,7 +894,7 @@
 	delta -= irq_delta;
 #endif
 #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
-	if (static_branch((&paravirt_steal_rq_enabled))) {
+	if (static_key_false((&paravirt_steal_rq_enabled))) {
 		u64 st;
 
 		steal = paravirt_steal_clock(cpu_of(rq));
@@ -2755,7 +2755,7 @@
 static __always_inline bool steal_account_process_tick(void)
 {
 #ifdef CONFIG_PARAVIRT
-	if (static_branch(&paravirt_steal_enabled)) {
+	if (static_key_false(&paravirt_steal_enabled)) {
 		u64 steal, st = 0;
 
 		steal = paravirt_steal_clock(smp_processor_id());
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index aca16b8..fd974fa 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1401,20 +1401,20 @@
 #ifdef CONFIG_CFS_BANDWIDTH
 
 #ifdef HAVE_JUMP_LABEL
-static struct jump_label_key __cfs_bandwidth_used;
+static struct static_key __cfs_bandwidth_used;
 
 static inline bool cfs_bandwidth_used(void)
 {
-	return static_branch(&__cfs_bandwidth_used);
+	return static_key_false(&__cfs_bandwidth_used);
 }
 
 void account_cfs_bandwidth_used(int enabled, int was_enabled)
 {
 	/* only need to count groups transitioning between enabled/!enabled */
 	if (enabled && !was_enabled)
-		jump_label_inc(&__cfs_bandwidth_used);
+		static_key_slow_inc(&__cfs_bandwidth_used);
 	else if (!enabled && was_enabled)
-		jump_label_dec(&__cfs_bandwidth_used);
+		static_key_slow_dec(&__cfs_bandwidth_used);
 }
 #else /* HAVE_JUMP_LABEL */
 static bool cfs_bandwidth_used(void)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 98c0c26..b4cd6d8 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -611,7 +611,7 @@
  * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
  */
 #ifdef CONFIG_SCHED_DEBUG
-# include <linux/jump_label.h>
+# include <linux/static_key.h>
 # define const_debug __read_mostly
 #else
 # define const_debug const
@@ -630,18 +630,18 @@
 #undef SCHED_FEAT
 
 #if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL)
-static __always_inline bool static_branch__true(struct jump_label_key *key)
+static __always_inline bool static_branch__true(struct static_key *key)
 {
-	return likely(static_branch(key)); /* Not out of line branch. */
+	return static_key_true(key); /* Not out of line branch. */
 }
 
-static __always_inline bool static_branch__false(struct jump_label_key *key)
+static __always_inline bool static_branch__false(struct static_key *key)
 {
-	return unlikely(static_branch(key)); /* Out of line branch. */
+	return static_key_false(key); /* Out of line branch. */
 }
 
 #define SCHED_FEAT(name, enabled)					\
-static __always_inline bool static_branch_##name(struct jump_label_key *key) \
+static __always_inline bool static_branch_##name(struct static_key *key) \
 {									\
 	return static_branch__##enabled(key);				\
 }
@@ -650,7 +650,7 @@
 
 #undef SCHED_FEAT
 
-extern struct jump_label_key sched_feat_keys[__SCHED_FEAT_NR];
+extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
 #define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x]))
 #else /* !(SCHED_DEBUG && HAVE_JUMP_LABEL) */
 #define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
diff --git a/kernel/signal.c b/kernel/signal.c
index c73c428..8511e39 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1054,13 +1054,13 @@
 	struct sigpending *pending;
 	struct sigqueue *q;
 	int override_rlimit;
-
-	trace_signal_generate(sig, info, t);
+	int ret = 0, result;
 
 	assert_spin_locked(&t->sighand->siglock);
 
+	result = TRACE_SIGNAL_IGNORED;
 	if (!prepare_signal(sig, t, from_ancestor_ns))
-		return 0;
+		goto ret;
 
 	pending = group ? &t->signal->shared_pending : &t->pending;
 	/*
@@ -1068,8 +1068,11 @@
 	 * exactly one non-rt signal, so that we can get more
 	 * detailed information about the cause of the signal.
 	 */
+	result = TRACE_SIGNAL_ALREADY_PENDING;
 	if (legacy_queue(pending, sig))
-		return 0;
+		goto ret;
+
+	result = TRACE_SIGNAL_DELIVERED;
 	/*
 	 * fast-pathed signals for kernel-internal things like SIGSTOP
 	 * or SIGKILL.
@@ -1127,14 +1130,15 @@
 			 * signal was rt and sent by user using something
 			 * other than kill().
 			 */
-			trace_signal_overflow_fail(sig, group, info);
-			return -EAGAIN;
+			result = TRACE_SIGNAL_OVERFLOW_FAIL;
+			ret = -EAGAIN;
+			goto ret;
 		} else {
 			/*
 			 * This is a silent loss of information.  We still
 			 * send the signal, but the *info bits are lost.
 			 */
-			trace_signal_lose_info(sig, group, info);
+			result = TRACE_SIGNAL_LOSE_INFO;
 		}
 	}
 
@@ -1142,7 +1146,9 @@
 	signalfd_notify(t, sig);
 	sigaddset(&pending->signal, sig);
 	complete_signal(sig, t, group);
-	return 0;
+ret:
+	trace_signal_generate(sig, info, t, group, result);
+	return ret;
 }
 
 static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
@@ -1585,7 +1591,7 @@
 	int sig = q->info.si_signo;
 	struct sigpending *pending;
 	unsigned long flags;
-	int ret;
+	int ret, result;
 
 	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
 
@@ -1594,6 +1600,7 @@
 		goto ret;
 
 	ret = 1; /* the signal is ignored */
+	result = TRACE_SIGNAL_IGNORED;
 	if (!prepare_signal(sig, t, 0))
 		goto out;
 
@@ -1605,6 +1612,7 @@
 		 */
 		BUG_ON(q->info.si_code != SI_TIMER);
 		q->info.si_overrun++;
+		result = TRACE_SIGNAL_ALREADY_PENDING;
 		goto out;
 	}
 	q->info.si_overrun = 0;
@@ -1614,7 +1622,9 @@
 	list_add_tail(&q->list, &pending->list);
 	sigaddset(&pending->signal, sig);
 	complete_signal(sig, t, group);
+	result = TRACE_SIGNAL_DELIVERED;
 out:
+	trace_signal_generate(sig, &q->info, t, group, result);
 	unlock_task_sighand(t, &flags);
 ret:
 	return ret;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 4eb3a0f..06d4099 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -385,6 +385,12 @@
 	local_irq_restore(flags);
 }
 
+void __raise_softirq_irqoff(unsigned int nr)
+{
+	trace_softirq_raise(nr);
+	or_softirq_pending(1UL << nr);
+}
+
 void open_softirq(int nr, void (*action)(struct softirq_action *))
 {
 	softirq_vec[nr].action = action;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 683d559..867bd1d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -62,6 +62,8 @@
 #define FTRACE_HASH_DEFAULT_BITS 10
 #define FTRACE_HASH_MAX_BITS 12
 
+#define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL)
+
 /* ftrace_enabled is a method to turn ftrace on or off */
 int ftrace_enabled __read_mostly;
 static int last_ftrace_enabled;
@@ -89,12 +91,14 @@
 };
 
 static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end;
+static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end;
 static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
 static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub;
 ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
 static struct ftrace_ops global_ops;
+static struct ftrace_ops control_ops;
 
 static void
 ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
@@ -168,6 +172,32 @@
 }
 #endif
 
+static void control_ops_disable_all(struct ftrace_ops *ops)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		*per_cpu_ptr(ops->disabled, cpu) = 1;
+}
+
+static int control_ops_alloc(struct ftrace_ops *ops)
+{
+	int __percpu *disabled;
+
+	disabled = alloc_percpu(int);
+	if (!disabled)
+		return -ENOMEM;
+
+	ops->disabled = disabled;
+	control_ops_disable_all(ops);
+	return 0;
+}
+
+static void control_ops_free(struct ftrace_ops *ops)
+{
+	free_percpu(ops->disabled);
+}
+
 static void update_global_ops(void)
 {
 	ftrace_func_t func;
@@ -259,6 +289,26 @@
 	return 0;
 }
 
+static void add_ftrace_list_ops(struct ftrace_ops **list,
+				struct ftrace_ops *main_ops,
+				struct ftrace_ops *ops)
+{
+	int first = *list == &ftrace_list_end;
+	add_ftrace_ops(list, ops);
+	if (first)
+		add_ftrace_ops(&ftrace_ops_list, main_ops);
+}
+
+static int remove_ftrace_list_ops(struct ftrace_ops **list,
+				  struct ftrace_ops *main_ops,
+				  struct ftrace_ops *ops)
+{
+	int ret = remove_ftrace_ops(list, ops);
+	if (!ret && *list == &ftrace_list_end)
+		ret = remove_ftrace_ops(&ftrace_ops_list, main_ops);
+	return ret;
+}
+
 static int __register_ftrace_function(struct ftrace_ops *ops)
 {
 	if (ftrace_disabled)
@@ -270,15 +320,20 @@
 	if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED))
 		return -EBUSY;
 
+	/* We don't support both control and global flags set. */
+	if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK)
+		return -EINVAL;
+
 	if (!core_kernel_data((unsigned long)ops))
 		ops->flags |= FTRACE_OPS_FL_DYNAMIC;
 
 	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
-		int first = ftrace_global_list == &ftrace_list_end;
-		add_ftrace_ops(&ftrace_global_list, ops);
+		add_ftrace_list_ops(&ftrace_global_list, &global_ops, ops);
 		ops->flags |= FTRACE_OPS_FL_ENABLED;
-		if (first)
-			add_ftrace_ops(&ftrace_ops_list, &global_ops);
+	} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
+		if (control_ops_alloc(ops))
+			return -ENOMEM;
+		add_ftrace_list_ops(&ftrace_control_list, &control_ops, ops);
 	} else
 		add_ftrace_ops(&ftrace_ops_list, ops);
 
@@ -302,11 +357,23 @@
 		return -EINVAL;
 
 	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
-		ret = remove_ftrace_ops(&ftrace_global_list, ops);
-		if (!ret && ftrace_global_list == &ftrace_list_end)
-			ret = remove_ftrace_ops(&ftrace_ops_list, &global_ops);
+		ret = remove_ftrace_list_ops(&ftrace_global_list,
+					     &global_ops, ops);
 		if (!ret)
 			ops->flags &= ~FTRACE_OPS_FL_ENABLED;
+	} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
+		ret = remove_ftrace_list_ops(&ftrace_control_list,
+					     &control_ops, ops);
+		if (!ret) {
+			/*
+			 * The ftrace_ops is now removed from the list,
+			 * so there'll be no new users. We must ensure
+			 * all current users are done before we free
+			 * the control data.
+			 */
+			synchronize_sched();
+			control_ops_free(ops);
+		}
 	} else
 		ret = remove_ftrace_ops(&ftrace_ops_list, ops);
 
@@ -1119,6 +1186,12 @@
 	call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu);
 }
 
+void ftrace_free_filter(struct ftrace_ops *ops)
+{
+	free_ftrace_hash(ops->filter_hash);
+	free_ftrace_hash(ops->notrace_hash);
+}
+
 static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
 {
 	struct ftrace_hash *hash;
@@ -1129,7 +1202,7 @@
 		return NULL;
 
 	size = 1 << size_bits;
-	hash->buckets = kzalloc(sizeof(*hash->buckets) * size, GFP_KERNEL);
+	hash->buckets = kcalloc(size, sizeof(*hash->buckets), GFP_KERNEL);
 
 	if (!hash->buckets) {
 		kfree(hash);
@@ -3146,8 +3219,10 @@
 	mutex_lock(&ftrace_regex_lock);
 	if (reset)
 		ftrace_filter_reset(hash);
-	if (buf)
-		ftrace_match_records(hash, buf, len);
+	if (buf && !ftrace_match_records(hash, buf, len)) {
+		ret = -EINVAL;
+		goto out_regex_unlock;
+	}
 
 	mutex_lock(&ftrace_lock);
 	ret = ftrace_hash_move(ops, enable, orig_hash, hash);
@@ -3157,6 +3232,7 @@
 
 	mutex_unlock(&ftrace_lock);
 
+ out_regex_unlock:
 	mutex_unlock(&ftrace_regex_lock);
 
 	free_ftrace_hash(hash);
@@ -3173,10 +3249,10 @@
  * Filters denote which functions should be enabled when tracing is enabled.
  * If @buf is NULL and reset is set, all functions will be enabled for tracing.
  */
-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)
 {
-	ftrace_set_regex(ops, buf, len, reset, 1);
+	return ftrace_set_regex(ops, buf, len, reset, 1);
 }
 EXPORT_SYMBOL_GPL(ftrace_set_filter);
 
@@ -3191,10 +3267,10 @@
  * is enabled. If @buf is NULL and reset is set, all functions will be enabled
  * for tracing.
  */
-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)
 {
-	ftrace_set_regex(ops, buf, len, reset, 0);
+	return ftrace_set_regex(ops, buf, len, reset, 0);
 }
 EXPORT_SYMBOL_GPL(ftrace_set_notrace);
 /**
@@ -3871,6 +3947,36 @@
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 static void
+ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip)
+{
+	struct ftrace_ops *op;
+
+	if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT)))
+		return;
+
+	/*
+	 * Some of the ops may be dynamically allocated,
+	 * they must be freed after a synchronize_sched().
+	 */
+	preempt_disable_notrace();
+	trace_recursion_set(TRACE_CONTROL_BIT);
+	op = rcu_dereference_raw(ftrace_control_list);
+	while (op != &ftrace_list_end) {
+		if (!ftrace_function_local_disabled(op) &&
+		    ftrace_ops_test(op, ip))
+			op->func(ip, parent_ip);
+
+		op = rcu_dereference_raw(op->next);
+	};
+	trace_recursion_clear(TRACE_CONTROL_BIT);
+	preempt_enable_notrace();
+}
+
+static struct ftrace_ops control_ops = {
+	.func = ftrace_ops_control_func,
+};
+
+static void
 ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
 {
 	struct ftrace_ops *op;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a3f1bc5..10d5503 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2764,12 +2764,12 @@
 	"tracing mini-HOWTO:\n\n"
 	"# mount -t debugfs nodev /sys/kernel/debug\n\n"
 	"# cat /sys/kernel/debug/tracing/available_tracers\n"
-	"wakeup preemptirqsoff preemptoff irqsoff function sched_switch nop\n\n"
+	"wakeup wakeup_rt preemptirqsoff preemptoff irqsoff function nop\n\n"
 	"# cat /sys/kernel/debug/tracing/current_tracer\n"
 	"nop\n"
-	"# echo sched_switch > /sys/kernel/debug/tracing/current_tracer\n"
+	"# echo wakeup > /sys/kernel/debug/tracing/current_tracer\n"
 	"# cat /sys/kernel/debug/tracing/current_tracer\n"
-	"sched_switch\n"
+	"wakeup\n"
 	"# cat /sys/kernel/debug/tracing/trace_options\n"
 	"noprint-parent nosym-offset nosym-addr noverbose\n"
 	"# echo print-parent > /sys/kernel/debug/tracing/trace_options\n"
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index b93ecba..54faec7 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -56,17 +56,23 @@
 #define F_STRUCT(args...)		args
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)	\
-	struct struct_name {					\
-		struct trace_entry	ent;			\
-		tstruct						\
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter)	\
+	struct struct_name {						\
+		struct trace_entry	ent;				\
+		tstruct							\
 	}
 
 #undef TP_ARGS
 #define TP_ARGS(args...)	args
 
 #undef FTRACE_ENTRY_DUP
-#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk)
+#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter)
+
+#undef FTRACE_ENTRY_REG
+#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print,	\
+			 filter, regfn) \
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+		     filter)
 
 #include "trace_entries.h"
 
@@ -288,6 +294,8 @@
 /* for function tracing recursion */
 #define TRACE_INTERNAL_BIT		(1<<11)
 #define TRACE_GLOBAL_BIT		(1<<12)
+#define TRACE_CONTROL_BIT		(1<<13)
+
 /*
  * Abuse of the trace_recursion.
  * As we need a way to maintain state if we are tracing the function
@@ -589,6 +597,8 @@
 static inline int ftrace_is_dead(void) { return 0; }
 #endif
 
+int ftrace_event_is_function(struct ftrace_event_call *call);
+
 /*
  * struct trace_parser - servers for reading the user input separated by spaces
  * @cont: set if the input is not complete - no final space char was found
@@ -766,9 +776,7 @@
 	u64 			val;
 	struct regex		regex;
 	unsigned short		*ops;
-#ifdef CONFIG_FTRACE_STARTUP_TEST
 	struct ftrace_event_field *field;
-#endif
 	int 			offset;
 	int 			not;
 	int 			op;
@@ -818,12 +826,22 @@
 extern const char *__stop___trace_bprintk_fmt[];
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(call, struct_name, id, tstruct, print)		\
+#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter)	\
 	extern struct ftrace_event_call					\
 	__attribute__((__aligned__(4))) event_##call;
 #undef FTRACE_ENTRY_DUP
-#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print)		\
-	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
+#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter)	\
+	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+		     filter)
 #include "trace_entries.h"
 
+#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_FUNCTION_TRACER
+int perf_ftrace_event_register(struct ftrace_event_call *call,
+			       enum trace_reg type, void *data);
+#else
+#define perf_ftrace_event_register NULL
+#endif /* CONFIG_FUNCTION_TRACER */
+#endif /* CONFIG_PERF_EVENTS */
+
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 9336590..d91eb05 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -55,7 +55,7 @@
 /*
  * Function trace entry - function address and parent function address:
  */
-FTRACE_ENTRY(function, ftrace_entry,
+FTRACE_ENTRY_REG(function, ftrace_entry,
 
 	TRACE_FN,
 
@@ -64,7 +64,11 @@
 		__field(	unsigned long,	parent_ip	)
 	),
 
-	F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip)
+	F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip),
+
+	FILTER_TRACE_FN,
+
+	perf_ftrace_event_register
 );
 
 /* Function call entry */
@@ -78,7 +82,9 @@
 		__field_desc(	int,		graph_ent,	depth		)
 	),
 
-	F_printk("--> %lx (%d)", __entry->func, __entry->depth)
+	F_printk("--> %lx (%d)", __entry->func, __entry->depth),
+
+	FILTER_OTHER
 );
 
 /* Function return entry */
@@ -98,7 +104,9 @@
 	F_printk("<-- %lx (%d) (start: %llx  end: %llx) over: %d",
 		 __entry->func, __entry->depth,
 		 __entry->calltime, __entry->rettime,
-		 __entry->depth)
+		 __entry->depth),
+
+	FILTER_OTHER
 );
 
 /*
@@ -127,8 +135,9 @@
 	F_printk("%u:%u:%u  ==> %u:%u:%u [%03u]",
 		 __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
 		 __entry->next_pid, __entry->next_prio, __entry->next_state,
-		 __entry->next_cpu
-		)
+		 __entry->next_cpu),
+
+	FILTER_OTHER
 );
 
 /*
@@ -146,8 +155,9 @@
 	F_printk("%u:%u:%u  ==+ %u:%u:%u [%03u]",
 		 __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
 		 __entry->next_pid, __entry->next_prio, __entry->next_state,
-		 __entry->next_cpu
-		)
+		 __entry->next_cpu),
+
+	FILTER_OTHER
 );
 
 /*
@@ -169,7 +179,9 @@
 		 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
 		 __entry->caller[0], __entry->caller[1], __entry->caller[2],
 		 __entry->caller[3], __entry->caller[4], __entry->caller[5],
-		 __entry->caller[6], __entry->caller[7])
+		 __entry->caller[6], __entry->caller[7]),
+
+	FILTER_OTHER
 );
 
 FTRACE_ENTRY(user_stack, userstack_entry,
@@ -185,7 +197,9 @@
 		 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
 		 __entry->caller[0], __entry->caller[1], __entry->caller[2],
 		 __entry->caller[3], __entry->caller[4], __entry->caller[5],
-		 __entry->caller[6], __entry->caller[7])
+		 __entry->caller[6], __entry->caller[7]),
+
+	FILTER_OTHER
 );
 
 /*
@@ -202,7 +216,9 @@
 	),
 
 	F_printk("%08lx fmt:%p",
-		 __entry->ip, __entry->fmt)
+		 __entry->ip, __entry->fmt),
+
+	FILTER_OTHER
 );
 
 FTRACE_ENTRY(print, print_entry,
@@ -215,7 +231,9 @@
 	),
 
 	F_printk("%08lx %s",
-		 __entry->ip, __entry->buf)
+		 __entry->ip, __entry->buf),
+
+	FILTER_OTHER
 );
 
 FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
@@ -234,7 +252,9 @@
 
 	F_printk("%lx %lx %lx %d %x %x",
 		 (unsigned long)__entry->phys, __entry->value, __entry->pc,
-		 __entry->map_id, __entry->opcode, __entry->width)
+		 __entry->map_id, __entry->opcode, __entry->width),
+
+	FILTER_OTHER
 );
 
 FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
@@ -252,7 +272,9 @@
 
 	F_printk("%lx %lx %lx %d %x",
 		 (unsigned long)__entry->phys, __entry->virt, __entry->len,
-		 __entry->map_id, __entry->opcode)
+		 __entry->map_id, __entry->opcode),
+
+	FILTER_OTHER
 );
 
 
@@ -272,6 +294,8 @@
 
 	F_printk("%u:%s:%s (%u)",
 		 __entry->line,
-		 __entry->func, __entry->file, __entry->correct)
+		 __entry->func, __entry->file, __entry->correct),
+
+	FILTER_OTHER
 );
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 19a359d..fee3752 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -24,6 +24,11 @@
 static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
 				 struct perf_event *p_event)
 {
+	/* The ftrace function trace is allowed only for root. */
+	if (ftrace_event_is_function(tp_event) &&
+	    perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	/* No tracing, just counting, so no obvious leak */
 	if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
 		return 0;
@@ -44,23 +49,17 @@
 	return 0;
 }
 
-static int perf_trace_event_init(struct ftrace_event_call *tp_event,
-				 struct perf_event *p_event)
+static int perf_trace_event_reg(struct ftrace_event_call *tp_event,
+				struct perf_event *p_event)
 {
 	struct hlist_head __percpu *list;
-	int ret;
+	int ret = -ENOMEM;
 	int cpu;
 
-	ret = perf_trace_event_perm(tp_event, p_event);
-	if (ret)
-		return ret;
-
 	p_event->tp_event = tp_event;
 	if (tp_event->perf_refcount++ > 0)
 		return 0;
 
-	ret = -ENOMEM;
-
 	list = alloc_percpu(struct hlist_head);
 	if (!list)
 		goto fail;
@@ -83,7 +82,7 @@
 		}
 	}
 
-	ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER);
+	ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER, NULL);
 	if (ret)
 		goto fail;
 
@@ -108,6 +107,69 @@
 	return ret;
 }
 
+static void perf_trace_event_unreg(struct perf_event *p_event)
+{
+	struct ftrace_event_call *tp_event = p_event->tp_event;
+	int i;
+
+	if (--tp_event->perf_refcount > 0)
+		goto out;
+
+	tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER, NULL);
+
+	/*
+	 * Ensure our callback won't be called anymore. The buffers
+	 * will be freed after that.
+	 */
+	tracepoint_synchronize_unregister();
+
+	free_percpu(tp_event->perf_events);
+	tp_event->perf_events = NULL;
+
+	if (!--total_ref_count) {
+		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
+			free_percpu(perf_trace_buf[i]);
+			perf_trace_buf[i] = NULL;
+		}
+	}
+out:
+	module_put(tp_event->mod);
+}
+
+static int perf_trace_event_open(struct perf_event *p_event)
+{
+	struct ftrace_event_call *tp_event = p_event->tp_event;
+	return tp_event->class->reg(tp_event, TRACE_REG_PERF_OPEN, p_event);
+}
+
+static void perf_trace_event_close(struct perf_event *p_event)
+{
+	struct ftrace_event_call *tp_event = p_event->tp_event;
+	tp_event->class->reg(tp_event, TRACE_REG_PERF_CLOSE, p_event);
+}
+
+static int perf_trace_event_init(struct ftrace_event_call *tp_event,
+				 struct perf_event *p_event)
+{
+	int ret;
+
+	ret = perf_trace_event_perm(tp_event, p_event);
+	if (ret)
+		return ret;
+
+	ret = perf_trace_event_reg(tp_event, p_event);
+	if (ret)
+		return ret;
+
+	ret = perf_trace_event_open(p_event);
+	if (ret) {
+		perf_trace_event_unreg(p_event);
+		return ret;
+	}
+
+	return 0;
+}
+
 int perf_trace_init(struct perf_event *p_event)
 {
 	struct ftrace_event_call *tp_event;
@@ -130,6 +192,14 @@
 	return ret;
 }
 
+void perf_trace_destroy(struct perf_event *p_event)
+{
+	mutex_lock(&event_mutex);
+	perf_trace_event_close(p_event);
+	perf_trace_event_unreg(p_event);
+	mutex_unlock(&event_mutex);
+}
+
 int perf_trace_add(struct perf_event *p_event, int flags)
 {
 	struct ftrace_event_call *tp_event = p_event->tp_event;
@@ -146,43 +216,14 @@
 	list = this_cpu_ptr(pcpu_list);
 	hlist_add_head_rcu(&p_event->hlist_entry, list);
 
-	return 0;
+	return tp_event->class->reg(tp_event, TRACE_REG_PERF_ADD, p_event);
 }
 
 void perf_trace_del(struct perf_event *p_event, int flags)
 {
-	hlist_del_rcu(&p_event->hlist_entry);
-}
-
-void perf_trace_destroy(struct perf_event *p_event)
-{
 	struct ftrace_event_call *tp_event = p_event->tp_event;
-	int i;
-
-	mutex_lock(&event_mutex);
-	if (--tp_event->perf_refcount > 0)
-		goto out;
-
-	tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
-
-	/*
-	 * Ensure our callback won't be called anymore. The buffers
-	 * will be freed after that.
-	 */
-	tracepoint_synchronize_unregister();
-
-	free_percpu(tp_event->perf_events);
-	tp_event->perf_events = NULL;
-
-	if (!--total_ref_count) {
-		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
-			free_percpu(perf_trace_buf[i]);
-			perf_trace_buf[i] = NULL;
-		}
-	}
-out:
-	module_put(tp_event->mod);
-	mutex_unlock(&event_mutex);
+	hlist_del_rcu(&p_event->hlist_entry);
+	tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event);
 }
 
 __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
@@ -214,3 +255,86 @@
 	return raw_data;
 }
 EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
+
+#ifdef CONFIG_FUNCTION_TRACER
+static void
+perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip)
+{
+	struct ftrace_entry *entry;
+	struct hlist_head *head;
+	struct pt_regs regs;
+	int rctx;
+
+#define ENTRY_SIZE (ALIGN(sizeof(struct ftrace_entry) + sizeof(u32), \
+		    sizeof(u64)) - sizeof(u32))
+
+	BUILD_BUG_ON(ENTRY_SIZE > PERF_MAX_TRACE_SIZE);
+
+	perf_fetch_caller_regs(&regs);
+
+	entry = perf_trace_buf_prepare(ENTRY_SIZE, TRACE_FN, NULL, &rctx);
+	if (!entry)
+		return;
+
+	entry->ip = ip;
+	entry->parent_ip = parent_ip;
+
+	head = this_cpu_ptr(event_function.perf_events);
+	perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0,
+			      1, &regs, head);
+
+#undef ENTRY_SIZE
+}
+
+static int perf_ftrace_function_register(struct perf_event *event)
+{
+	struct ftrace_ops *ops = &event->ftrace_ops;
+
+	ops->flags |= FTRACE_OPS_FL_CONTROL;
+	ops->func = perf_ftrace_function_call;
+	return register_ftrace_function(ops);
+}
+
+static int perf_ftrace_function_unregister(struct perf_event *event)
+{
+	struct ftrace_ops *ops = &event->ftrace_ops;
+	int ret = unregister_ftrace_function(ops);
+	ftrace_free_filter(ops);
+	return ret;
+}
+
+static void perf_ftrace_function_enable(struct perf_event *event)
+{
+	ftrace_function_local_enable(&event->ftrace_ops);
+}
+
+static void perf_ftrace_function_disable(struct perf_event *event)
+{
+	ftrace_function_local_disable(&event->ftrace_ops);
+}
+
+int perf_ftrace_event_register(struct ftrace_event_call *call,
+			       enum trace_reg type, void *data)
+{
+	switch (type) {
+	case TRACE_REG_REGISTER:
+	case TRACE_REG_UNREGISTER:
+		break;
+	case TRACE_REG_PERF_REGISTER:
+	case TRACE_REG_PERF_UNREGISTER:
+		return 0;
+	case TRACE_REG_PERF_OPEN:
+		return perf_ftrace_function_register(data);
+	case TRACE_REG_PERF_CLOSE:
+		return perf_ftrace_function_unregister(data);
+	case TRACE_REG_PERF_ADD:
+		perf_ftrace_function_enable(data);
+		return 0;
+	case TRACE_REG_PERF_DEL:
+		perf_ftrace_function_disable(data);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+#endif /* CONFIG_FUNCTION_TRACER */
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index c212a7f..079a93a 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -147,7 +147,8 @@
 }
 EXPORT_SYMBOL_GPL(trace_event_raw_init);
 
-int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type)
+int ftrace_event_reg(struct ftrace_event_call *call,
+		     enum trace_reg type, void *data)
 {
 	switch (type) {
 	case TRACE_REG_REGISTER:
@@ -170,6 +171,11 @@
 					    call->class->perf_probe,
 					    call);
 		return 0;
+	case TRACE_REG_PERF_OPEN:
+	case TRACE_REG_PERF_CLOSE:
+	case TRACE_REG_PERF_ADD:
+	case TRACE_REG_PERF_DEL:
+		return 0;
 #endif
 	}
 	return 0;
@@ -209,7 +215,7 @@
 				tracing_stop_cmdline_record();
 				call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD;
 			}
-			call->class->reg(call, TRACE_REG_UNREGISTER);
+			call->class->reg(call, TRACE_REG_UNREGISTER, NULL);
 		}
 		break;
 	case 1:
@@ -218,7 +224,7 @@
 				tracing_start_cmdline_record();
 				call->flags |= TRACE_EVENT_FL_RECORDED_CMD;
 			}
-			ret = call->class->reg(call, TRACE_REG_REGISTER);
+			ret = call->class->reg(call, TRACE_REG_REGISTER, NULL);
 			if (ret) {
 				tracing_stop_cmdline_record();
 				pr_info("event trace: Could not enable event "
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 24aee71..431dba8 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -81,6 +81,7 @@
 	FILT_ERR_TOO_MANY_PREDS,
 	FILT_ERR_MISSING_FIELD,
 	FILT_ERR_INVALID_FILTER,
+	FILT_ERR_IP_FIELD_ONLY,
 };
 
 static char *err_text[] = {
@@ -96,6 +97,7 @@
 	"Too many terms in predicate expression",
 	"Missing field name and/or value",
 	"Meaningless filter expression",
+	"Only 'ip' field is supported for function trace",
 };
 
 struct opstack_op {
@@ -685,7 +687,7 @@
 
 static int __alloc_pred_stack(struct pred_stack *stack, int n_preds)
 {
-	stack->preds = kzalloc(sizeof(*stack->preds)*(n_preds + 1), GFP_KERNEL);
+	stack->preds = kcalloc(n_preds + 1, sizeof(*stack->preds), GFP_KERNEL);
 	if (!stack->preds)
 		return -ENOMEM;
 	stack->index = n_preds;
@@ -826,8 +828,7 @@
 	if (filter->preds)
 		__free_preds(filter);
 
-	filter->preds =
-		kzalloc(sizeof(*filter->preds) * n_preds, GFP_KERNEL);
+	filter->preds = kcalloc(n_preds, sizeof(*filter->preds), GFP_KERNEL);
 
 	if (!filter->preds)
 		return -ENOMEM;
@@ -900,6 +901,11 @@
 	return FILTER_OTHER;
 }
 
+static bool is_function_field(struct ftrace_event_field *field)
+{
+	return field->filter_type == FILTER_TRACE_FN;
+}
+
 static bool is_string_field(struct ftrace_event_field *field)
 {
 	return field->filter_type == FILTER_DYN_STRING ||
@@ -987,6 +993,11 @@
 			fn = filter_pred_strloc;
 		else
 			fn = filter_pred_pchar;
+	} else if (is_function_field(field)) {
+		if (strcmp(field->name, "ip")) {
+			parse_error(ps, FILT_ERR_IP_FIELD_ONLY, 0);
+			return -EINVAL;
+		}
 	} else {
 		if (field->is_signed)
 			ret = strict_strtoll(pred->regex.pattern, 0, &val);
@@ -1334,10 +1345,7 @@
 
 	strcpy(pred.regex.pattern, operand2);
 	pred.regex.len = strlen(pred.regex.pattern);
-
-#ifdef CONFIG_FTRACE_STARTUP_TEST
 	pred.field = field;
-#endif
 	return init_pred(ps, field, &pred) ? NULL : &pred;
 }
 
@@ -1486,7 +1494,7 @@
 	children = count_leafs(preds, &preds[root->left]);
 	children += count_leafs(preds, &preds[root->right]);
 
-	root->ops = kzalloc(sizeof(*root->ops) * children, GFP_KERNEL);
+	root->ops = kcalloc(children, sizeof(*root->ops), GFP_KERNEL);
 	if (!root->ops)
 		return -ENOMEM;
 
@@ -1950,6 +1958,148 @@
 	__free_filter(filter);
 }
 
+struct function_filter_data {
+	struct ftrace_ops *ops;
+	int first_filter;
+	int first_notrace;
+};
+
+#ifdef CONFIG_FUNCTION_TRACER
+static char **
+ftrace_function_filter_re(char *buf, int len, int *count)
+{
+	char *str, *sep, **re;
+
+	str = kstrndup(buf, len, GFP_KERNEL);
+	if (!str)
+		return NULL;
+
+	/*
+	 * The argv_split function takes white space
+	 * as a separator, so convert ',' into spaces.
+	 */
+	while ((sep = strchr(str, ',')))
+		*sep = ' ';
+
+	re = argv_split(GFP_KERNEL, str, count);
+	kfree(str);
+	return re;
+}
+
+static int ftrace_function_set_regexp(struct ftrace_ops *ops, int filter,
+				      int reset, char *re, int len)
+{
+	int ret;
+
+	if (filter)
+		ret = ftrace_set_filter(ops, re, len, reset);
+	else
+		ret = ftrace_set_notrace(ops, re, len, reset);
+
+	return ret;
+}
+
+static int __ftrace_function_set_filter(int filter, char *buf, int len,
+					struct function_filter_data *data)
+{
+	int i, re_cnt, ret;
+	int *reset;
+	char **re;
+
+	reset = filter ? &data->first_filter : &data->first_notrace;
+
+	/*
+	 * The 'ip' field could have multiple filters set, separated
+	 * either by space or comma. We first cut the filter and apply
+	 * all pieces separatelly.
+	 */
+	re = ftrace_function_filter_re(buf, len, &re_cnt);
+	if (!re)
+		return -EINVAL;
+
+	for (i = 0; i < re_cnt; i++) {
+		ret = ftrace_function_set_regexp(data->ops, filter, *reset,
+						 re[i], strlen(re[i]));
+		if (ret)
+			break;
+
+		if (*reset)
+			*reset = 0;
+	}
+
+	argv_free(re);
+	return ret;
+}
+
+static int ftrace_function_check_pred(struct filter_pred *pred, int leaf)
+{
+	struct ftrace_event_field *field = pred->field;
+
+	if (leaf) {
+		/*
+		 * Check the leaf predicate for function trace, verify:
+		 *  - only '==' and '!=' is used
+		 *  - the 'ip' field is used
+		 */
+		if ((pred->op != OP_EQ) && (pred->op != OP_NE))
+			return -EINVAL;
+
+		if (strcmp(field->name, "ip"))
+			return -EINVAL;
+	} else {
+		/*
+		 * Check the non leaf predicate for function trace, verify:
+		 *  - only '||' is used
+		*/
+		if (pred->op != OP_OR)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ftrace_function_set_filter_cb(enum move_type move,
+					 struct filter_pred *pred,
+					 int *err, void *data)
+{
+	/* Checking the node is valid for function trace. */
+	if ((move != MOVE_DOWN) ||
+	    (pred->left != FILTER_PRED_INVALID)) {
+		*err = ftrace_function_check_pred(pred, 0);
+	} else {
+		*err = ftrace_function_check_pred(pred, 1);
+		if (*err)
+			return WALK_PRED_ABORT;
+
+		*err = __ftrace_function_set_filter(pred->op == OP_EQ,
+						    pred->regex.pattern,
+						    pred->regex.len,
+						    data);
+	}
+
+	return (*err) ? WALK_PRED_ABORT : WALK_PRED_DEFAULT;
+}
+
+static int ftrace_function_set_filter(struct perf_event *event,
+				      struct event_filter *filter)
+{
+	struct function_filter_data data = {
+		.first_filter  = 1,
+		.first_notrace = 1,
+		.ops           = &event->ftrace_ops,
+	};
+
+	return walk_pred_tree(filter->preds, filter->root,
+			      ftrace_function_set_filter_cb, &data);
+}
+#else
+static int ftrace_function_set_filter(struct perf_event *event,
+				      struct event_filter *filter)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_FUNCTION_TRACER */
+
 int ftrace_profile_set_filter(struct perf_event *event, int event_id,
 			      char *filter_str)
 {
@@ -1970,9 +2120,16 @@
 		goto out_unlock;
 
 	err = create_filter(call, filter_str, false, &filter);
-	if (!err)
-		event->filter = filter;
+	if (err)
+		goto free_filter;
+
+	if (ftrace_event_is_function(call))
+		err = ftrace_function_set_filter(event, filter);
 	else
+		event->filter = filter;
+
+free_filter:
+	if (err || ftrace_event_is_function(call))
 		__free_filter(filter);
 
 out_unlock:
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index bbeec31..7b46c9b 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -18,6 +18,16 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM	ftrace
 
+/*
+ * The FTRACE_ENTRY_REG macro allows ftrace entry to define register
+ * function and thus become accesible via perf.
+ */
+#undef FTRACE_ENTRY_REG
+#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \
+			 filter, regfn) \
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+		     filter)
+
 /* not needed for this file */
 #undef __field_struct
 #define __field_struct(type, item)
@@ -44,21 +54,22 @@
 #define F_printk(fmt, args...) fmt, args
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)	\
-struct ____ftrace_##name {					\
-	tstruct							\
-};								\
-static void __always_unused ____ftrace_check_##name(void)	\
-{								\
-	struct ____ftrace_##name *__entry = NULL;		\
-								\
-	/* force compile-time check on F_printk() */		\
-	printk(print);						\
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter)	\
+struct ____ftrace_##name {						\
+	tstruct								\
+};									\
+static void __always_unused ____ftrace_check_##name(void)		\
+{									\
+	struct ____ftrace_##name *__entry = NULL;			\
+									\
+	/* force compile-time check on F_printk() */			\
+	printk(print);							\
 }
 
 #undef FTRACE_ENTRY_DUP
-#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print)	\
-	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
+#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print, filter)	\
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+		     filter)
 
 #include "trace_entries.h"
 
@@ -67,7 +78,7 @@
 	ret = trace_define_field(event_call, #type, #item,		\
 				 offsetof(typeof(field), item),		\
 				 sizeof(field.item),			\
-				 is_signed_type(type), FILTER_OTHER);	\
+				 is_signed_type(type), filter_type);	\
 	if (ret)							\
 		return ret;
 
@@ -77,7 +88,7 @@
 				 offsetof(typeof(field),		\
 					  container.item),		\
 				 sizeof(field.container.item),		\
-				 is_signed_type(type), FILTER_OTHER);	\
+				 is_signed_type(type), filter_type);	\
 	if (ret)							\
 		return ret;
 
@@ -91,7 +102,7 @@
 		ret = trace_define_field(event_call, event_storage, #item, \
 				 offsetof(typeof(field), item),		\
 				 sizeof(field.item),			\
-				 is_signed_type(type), FILTER_OTHER);	\
+				 is_signed_type(type), filter_type);	\
 		mutex_unlock(&event_storage_mutex);			\
 		if (ret)						\
 			return ret;					\
@@ -104,7 +115,7 @@
 				 offsetof(typeof(field),		\
 					  container.item),		\
 				 sizeof(field.container.item),		\
-				 is_signed_type(type), FILTER_OTHER);	\
+				 is_signed_type(type), filter_type);	\
 	if (ret)							\
 		return ret;
 
@@ -112,17 +123,18 @@
 #define __dynamic_array(type, item)					\
 	ret = trace_define_field(event_call, #type, #item,		\
 				 offsetof(typeof(field), item),		\
-				 0, is_signed_type(type), FILTER_OTHER);\
+				 0, is_signed_type(type), filter_type);\
 	if (ret)							\
 		return ret;
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)		\
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter)	\
 int									\
 ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 {									\
 	struct struct_name field;					\
 	int ret;							\
+	int filter_type = filter;					\
 									\
 	tstruct;							\
 									\
@@ -152,13 +164,15 @@
 #undef F_printk
 #define F_printk(fmt, args...) #fmt ", "  __stringify(args)
 
-#undef FTRACE_ENTRY
-#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print)		\
+#undef FTRACE_ENTRY_REG
+#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\
+			 regfn)						\
 									\
 struct ftrace_event_class event_class_ftrace_##call = {			\
 	.system			= __stringify(TRACE_SYSTEM),		\
 	.define_fields		= ftrace_define_fields_##call,		\
 	.fields			= LIST_HEAD_INIT(event_class_ftrace_##call.fields),\
+	.reg			= regfn,				\
 };									\
 									\
 struct ftrace_event_call __used event_##call = {			\
@@ -170,4 +184,14 @@
 struct ftrace_event_call __used						\
 __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
 
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print, filter)	\
+	FTRACE_ENTRY_REG(call, struct_name, etype,			\
+			 PARAMS(tstruct), PARAMS(print), filter, NULL)
+
+int ftrace_event_is_function(struct ftrace_event_call *call)
+{
+	return call == &event_function;
+}
+
 #include "trace_entries.h"
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 00d527c..580a05e 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1892,7 +1892,8 @@
 #endif	/* CONFIG_PERF_EVENTS */
 
 static __kprobes
-int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
+int kprobe_register(struct ftrace_event_call *event,
+		    enum trace_reg type, void *data)
 {
 	struct trace_probe *tp = (struct trace_probe *)event->data;
 
@@ -1909,6 +1910,11 @@
 	case TRACE_REG_PERF_UNREGISTER:
 		disable_trace_probe(tp, TP_FLAG_PROFILE);
 		return 0;
+	case TRACE_REG_PERF_OPEN:
+	case TRACE_REG_PERF_CLOSE:
+	case TRACE_REG_PERF_ADD:
+	case TRACE_REG_PERF_DEL:
+		return 0;
 #endif
 	}
 	return 0;
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 0d6ff35..c5a0187 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -300,7 +300,7 @@
 	unsigned long mask;
 	const char *str;
 	const char *ret = p->buffer + p->len;
-	int i;
+	int i, first = 1;
 
 	for (i = 0;  flag_array[i].name && flags; i++) {
 
@@ -310,14 +310,16 @@
 
 		str = flag_array[i].name;
 		flags &= ~mask;
-		if (p->len && delim)
+		if (!first && delim)
 			trace_seq_puts(p, delim);
+		else
+			first = 0;
 		trace_seq_puts(p, str);
 	}
 
 	/* check for left over flags */
 	if (flags) {
-		if (p->len && delim)
+		if (!first && delim)
 			trace_seq_puts(p, delim);
 		trace_seq_printf(p, "0x%lx", flags);
 	}
@@ -344,7 +346,7 @@
 		break;
 	}
 
-	if (!p->len)
+	if (ret == (const char *)(p->buffer + p->len))
 		trace_seq_printf(p, "0x%lx", val);
 		
 	trace_seq_putc(p, 0);
@@ -370,7 +372,7 @@
 		break;
 	}
 
-	if (!p->len)
+	if (ret == (const char *)(p->buffer + p->len))
 		trace_seq_printf(p, "0x%llx", val);
 
 	trace_seq_putc(p, 0);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index cb65454..96fc733 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -17,9 +17,9 @@
 static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
 
 static int syscall_enter_register(struct ftrace_event_call *event,
-				 enum trace_reg type);
+				 enum trace_reg type, void *data);
 static int syscall_exit_register(struct ftrace_event_call *event,
-				 enum trace_reg type);
+				 enum trace_reg type, void *data);
 
 static int syscall_enter_define_fields(struct ftrace_event_call *call);
 static int syscall_exit_define_fields(struct ftrace_event_call *call);
@@ -468,8 +468,8 @@
 	unsigned long addr;
 	int i;
 
-	syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
-					NR_syscalls, GFP_KERNEL);
+	syscalls_metadata = kcalloc(NR_syscalls, sizeof(*syscalls_metadata),
+				    GFP_KERNEL);
 	if (!syscalls_metadata) {
 		WARN_ON(1);
 		return -ENOMEM;
@@ -649,7 +649,7 @@
 #endif /* CONFIG_PERF_EVENTS */
 
 static int syscall_enter_register(struct ftrace_event_call *event,
-				 enum trace_reg type)
+				 enum trace_reg type, void *data)
 {
 	switch (type) {
 	case TRACE_REG_REGISTER:
@@ -664,13 +664,18 @@
 	case TRACE_REG_PERF_UNREGISTER:
 		perf_sysenter_disable(event);
 		return 0;
+	case TRACE_REG_PERF_OPEN:
+	case TRACE_REG_PERF_CLOSE:
+	case TRACE_REG_PERF_ADD:
+	case TRACE_REG_PERF_DEL:
+		return 0;
 #endif
 	}
 	return 0;
 }
 
 static int syscall_exit_register(struct ftrace_event_call *event,
-				 enum trace_reg type)
+				 enum trace_reg type, void *data)
 {
 	switch (type) {
 	case TRACE_REG_REGISTER:
@@ -685,6 +690,11 @@
 	case TRACE_REG_PERF_UNREGISTER:
 		perf_sysexit_disable(event);
 		return 0;
+	case TRACE_REG_PERF_OPEN:
+	case TRACE_REG_PERF_CLOSE:
+	case TRACE_REG_PERF_ADD:
+	case TRACE_REG_PERF_DEL:
+		return 0;
 #endif
 	}
 	return 0;
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index f1539de..d96ba22 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -25,7 +25,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
-#include <linux/jump_label.h>
+#include <linux/static_key.h>
 
 extern struct tracepoint * const __start___tracepoints_ptrs[];
 extern struct tracepoint * const __stop___tracepoints_ptrs[];
@@ -256,9 +256,9 @@
 {
 	WARN_ON(strcmp((*entry)->name, elem->name) != 0);
 
-	if (elem->regfunc && !jump_label_enabled(&elem->key) && active)
+	if (elem->regfunc && !static_key_enabled(&elem->key) && active)
 		elem->regfunc();
-	else if (elem->unregfunc && jump_label_enabled(&elem->key) && !active)
+	else if (elem->unregfunc && static_key_enabled(&elem->key) && !active)
 		elem->unregfunc();
 
 	/*
@@ -269,10 +269,10 @@
 	 * is used.
 	 */
 	rcu_assign_pointer(elem->funcs, (*entry)->funcs);
-	if (active && !jump_label_enabled(&elem->key))
-		jump_label_inc(&elem->key);
-	else if (!active && jump_label_enabled(&elem->key))
-		jump_label_dec(&elem->key);
+	if (active && !static_key_enabled(&elem->key))
+		static_key_slow_inc(&elem->key);
+	else if (!active && static_key_enabled(&elem->key))
+		static_key_slow_dec(&elem->key);
 }
 
 /*
@@ -283,11 +283,11 @@
  */
 static void disable_tracepoint(struct tracepoint *elem)
 {
-	if (elem->unregfunc && jump_label_enabled(&elem->key))
+	if (elem->unregfunc && static_key_enabled(&elem->key))
 		elem->unregfunc();
 
-	if (jump_label_enabled(&elem->key))
-		jump_label_dec(&elem->key);
+	if (static_key_enabled(&elem->key))
+		static_key_slow_dec(&elem->key);
 	rcu_assign_pointer(elem->funcs, NULL);
 }
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index d117262..14bc092 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -3,12 +3,9 @@
  *
  * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
  *
- * this code detects hard lockups: incidents in where on a CPU
- * the kernel does not respond to anything except NMI.
- *
- * Note: Most of this code is borrowed heavily from softlockup.c,
- * so thanks to Ingo for the initial implementation.
- * Some chunks also taken from arch/x86/kernel/apic/nmi.c, thanks
+ * Note: Most of this code is borrowed heavily from the original softlockup
+ * detector, so thanks to Ingo for the initial implementation.
+ * Some chunks also taken from the old x86-specific nmi watchdog code, thanks
  * to those contributors as well.
  */
 
@@ -117,9 +114,10 @@
 {
 	/*
 	 * convert watchdog_thresh from seconds to ns
-	 * the divide by 5 is to give hrtimer 5 chances to
-	 * increment before the hardlockup detector generates
-	 * a warning
+	 * the divide by 5 is to give hrtimer several chances (two
+	 * or three with the current relation between the soft
+	 * and hard thresholds) to increment before the
+	 * hardlockup detector generates a warning
 	 */
 	return get_softlockup_thresh() * (NSEC_PER_SEC / 5);
 }
@@ -336,9 +334,11 @@
 
 	set_current_state(TASK_INTERRUPTIBLE);
 	/*
-	 * Run briefly once per second to reset the softlockup timestamp.
-	 * If this gets delayed for more than 60 seconds then the
-	 * debug-printout triggers in watchdog_timer_fn().
+	 * Run briefly (kicked by the hrtimer callback function) once every
+	 * get_sample_period() seconds (4 seconds by default) to reset the
+	 * softlockup timestamp. If this gets delayed for more than
+	 * 2*watchdog_thresh seconds then the debug-printout triggers in
+	 * watchdog_timer_fn().
 	 */
 	while (!kthread_should_stop()) {
 		__touch_watchdog();
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 8745ac7..9739c0b 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -166,18 +166,21 @@
 	  hard and soft lockups.
 
 	  Softlockups are bugs that cause the kernel to loop in kernel
-	  mode for more than 60 seconds, without giving other tasks a
+	  mode for more than 20 seconds, without giving other tasks a
 	  chance to run.  The current stack trace is displayed upon
 	  detection and the system will stay locked up.
 
 	  Hardlockups are bugs that cause the CPU to loop in kernel mode
-	  for more than 60 seconds, without letting other interrupts have a
+	  for more than 10 seconds, without letting other interrupts have a
 	  chance to run.  The current stack trace is displayed upon detection
 	  and the system will stay locked up.
 
 	  The overhead should be minimal.  A periodic hrtimer runs to
-	  generate interrupts and kick the watchdog task every 10-12 seconds.
-	  An NMI is generated every 60 seconds or so to check for hardlockups.
+	  generate interrupts and kick the watchdog task every 4 seconds.
+	  An NMI is generated every 10 seconds or so to check for hardlockups.
+
+	  The frequency of hrtimer and NMI events and the soft and hard lockup
+	  thresholds can be controlled through the sysctl watchdog_thresh.
 
 config HARDLOCKUP_DETECTOR
 	def_bool LOCKUP_DETECTOR && PERF_EVENTS && HAVE_PERF_EVENTS_NMI && \
@@ -189,7 +192,8 @@
 	help
 	  Say Y here to enable the kernel to panic on "hard lockups",
 	  which are bugs that cause the kernel to loop in kernel
-	  mode with interrupts disabled for more than 60 seconds.
+	  mode with interrupts disabled for more than 10 seconds (configurable
+	  using the watchdog_thresh sysctl).
 
 	  Say N if unsure.
 
@@ -206,8 +210,8 @@
 	help
 	  Say Y here to enable the kernel to panic on "soft lockups",
 	  which are bugs that cause the kernel to loop in kernel
-	  mode for more than 60 seconds, without giving other tasks a
-	  chance to run.
+	  mode for more than 20 seconds (configurable using the watchdog_thresh
+	  sysctl), without giving other tasks a chance to run.
 
 	  The panic can be used in combination with panic_timeout,
 	  to cause the system to reboot automatically after a
diff --git a/net/core/dev.c b/net/core/dev.c
index 6ca32f6..6982bfd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -134,7 +134,7 @@
 #include <linux/inetdevice.h>
 #include <linux/cpu_rmap.h>
 #include <linux/net_tstamp.h>
-#include <linux/jump_label.h>
+#include <linux/static_key.h>
 #include <net/flow_keys.h>
 
 #include "net-sysfs.h"
@@ -1441,11 +1441,11 @@
 }
 EXPORT_SYMBOL(call_netdevice_notifiers);
 
-static struct jump_label_key netstamp_needed __read_mostly;
+static struct static_key netstamp_needed __read_mostly;
 #ifdef HAVE_JUMP_LABEL
-/* We are not allowed to call jump_label_dec() from irq context
+/* We are not allowed to call static_key_slow_dec() from irq context
  * If net_disable_timestamp() is called from irq context, defer the
- * jump_label_dec() calls.
+ * static_key_slow_dec() calls.
  */
 static atomic_t netstamp_needed_deferred;
 #endif
@@ -1457,12 +1457,12 @@
 
 	if (deferred) {
 		while (--deferred)
-			jump_label_dec(&netstamp_needed);
+			static_key_slow_dec(&netstamp_needed);
 		return;
 	}
 #endif
 	WARN_ON(in_interrupt());
-	jump_label_inc(&netstamp_needed);
+	static_key_slow_inc(&netstamp_needed);
 }
 EXPORT_SYMBOL(net_enable_timestamp);
 
@@ -1474,19 +1474,19 @@
 		return;
 	}
 #endif
-	jump_label_dec(&netstamp_needed);
+	static_key_slow_dec(&netstamp_needed);
 }
 EXPORT_SYMBOL(net_disable_timestamp);
 
 static inline void net_timestamp_set(struct sk_buff *skb)
 {
 	skb->tstamp.tv64 = 0;
-	if (static_branch(&netstamp_needed))
+	if (static_key_false(&netstamp_needed))
 		__net_timestamp(skb);
 }
 
 #define net_timestamp_check(COND, SKB)			\
-	if (static_branch(&netstamp_needed)) {		\
+	if (static_key_false(&netstamp_needed)) {		\
 		if ((COND) && !(SKB)->tstamp.tv64)	\
 			__net_timestamp(SKB);		\
 	}						\
@@ -2660,7 +2660,7 @@
 struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly;
 EXPORT_SYMBOL(rps_sock_flow_table);
 
-struct jump_label_key rps_needed __read_mostly;
+struct static_key rps_needed __read_mostly;
 
 static struct rps_dev_flow *
 set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
@@ -2945,7 +2945,7 @@
 
 	trace_netif_rx(skb);
 #ifdef CONFIG_RPS
-	if (static_branch(&rps_needed))	{
+	if (static_key_false(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
 		int cpu;
 
@@ -3309,7 +3309,7 @@
 		return NET_RX_SUCCESS;
 
 #ifdef CONFIG_RPS
-	if (static_branch(&rps_needed)) {
+	if (static_key_false(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
 		int cpu, ret;
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index a1727cd..4955862 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -608,10 +608,10 @@
 	spin_unlock(&rps_map_lock);
 
 	if (map)
-		jump_label_inc(&rps_needed);
+		static_key_slow_inc(&rps_needed);
 	if (old_map) {
 		kfree_rcu(old_map, rcu);
-		jump_label_dec(&rps_needed);
+		static_key_slow_dec(&rps_needed);
 	}
 	free_cpumask_var(mask);
 	return len;
diff --git a/net/core/sock.c b/net/core/sock.c
index 02f8dfe..95aff9c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -111,7 +111,7 @@
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/user_namespace.h>
-#include <linux/jump_label.h>
+#include <linux/static_key.h>
 #include <linux/memcontrol.h>
 
 #include <asm/uaccess.h>
@@ -184,7 +184,7 @@
 static struct lock_class_key af_family_keys[AF_MAX];
 static struct lock_class_key af_family_slock_keys[AF_MAX];
 
-struct jump_label_key memcg_socket_limit_enabled;
+struct static_key memcg_socket_limit_enabled;
 EXPORT_SYMBOL(memcg_socket_limit_enabled);
 
 /*
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index d05559d..0c28508 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -69,9 +69,9 @@
 		if (sock_table != orig_sock_table) {
 			rcu_assign_pointer(rps_sock_flow_table, sock_table);
 			if (sock_table)
-				jump_label_inc(&rps_needed);
+				static_key_slow_inc(&rps_needed);
 			if (orig_sock_table) {
-				jump_label_dec(&rps_needed);
+				static_key_slow_dec(&rps_needed);
 				synchronize_rcu();
 				vfree(orig_sock_table);
 			}
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 4997878..602fb30 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -111,7 +111,7 @@
 	val = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
 
 	if (val != RESOURCE_MAX)
-		jump_label_dec(&memcg_socket_limit_enabled);
+		static_key_slow_dec(&memcg_socket_limit_enabled);
 }
 EXPORT_SYMBOL(tcp_destroy_cgroup);
 
@@ -143,9 +143,9 @@
 					     net->ipv4.sysctl_tcp_mem[i]);
 
 	if (val == RESOURCE_MAX && old_lim != RESOURCE_MAX)
-		jump_label_dec(&memcg_socket_limit_enabled);
+		static_key_slow_dec(&memcg_socket_limit_enabled);
 	else if (old_lim == RESOURCE_MAX && val != RESOURCE_MAX)
-		jump_label_inc(&memcg_socket_limit_enabled);
+		static_key_slow_inc(&memcg_socket_limit_enabled);
 
 	return 0;
 }
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index b4e8ff0..e1b7e05 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -56,7 +56,7 @@
 EXPORT_SYMBOL(nf_hooks);
 
 #if defined(CONFIG_JUMP_LABEL)
-struct jump_label_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
+struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
 EXPORT_SYMBOL(nf_hooks_needed);
 #endif
 
@@ -77,7 +77,7 @@
 	list_add_rcu(&reg->list, elem->list.prev);
 	mutex_unlock(&nf_hook_mutex);
 #if defined(CONFIG_JUMP_LABEL)
-	jump_label_inc(&nf_hooks_needed[reg->pf][reg->hooknum]);
+	static_key_slow_inc(&nf_hooks_needed[reg->pf][reg->hooknum]);
 #endif
 	return 0;
 }
@@ -89,7 +89,7 @@
 	list_del_rcu(&reg->list);
 	mutex_unlock(&nf_hook_mutex);
 #if defined(CONFIG_JUMP_LABEL)
-	jump_label_dec(&nf_hooks_needed[reg->pf][reg->hooknum]);
+	static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]);
 #endif
 	synchronize_net();
 }
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index 4626a39..ca600e0 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -1,3 +1,10 @@
+OUTPUT := ./
+ifeq ("$(origin O)", "command line")
+  ifneq ($(O),)
+	OUTPUT := $(O)/
+  endif
+endif
+
 MAN1_TXT= \
 	$(filter-out $(addsuffix .txt, $(ARTICLES) $(SP_ARTICLES)), \
 		$(wildcard perf-*.txt)) \
@@ -6,10 +13,11 @@
 MAN7_TXT=
 
 MAN_TXT = $(MAN1_TXT) $(MAN5_TXT) $(MAN7_TXT)
-MAN_XML=$(patsubst %.txt,%.xml,$(MAN_TXT))
-MAN_HTML=$(patsubst %.txt,%.html,$(MAN_TXT))
+_MAN_XML=$(patsubst %.txt,%.xml,$(MAN_TXT))
+_MAN_HTML=$(patsubst %.txt,%.html,$(MAN_TXT))
 
-DOC_HTML=$(MAN_HTML)
+MAN_XML=$(addprefix $(OUTPUT),$(_MAN_XML))
+MAN_HTML=$(addprefix $(OUTPUT),$(_MAN_HTML))
 
 ARTICLES =
 # with their own formatting rules.
@@ -18,11 +26,17 @@
 SP_ARTICLES += $(API_DOCS)
 SP_ARTICLES += technical/api-index
 
-DOC_HTML += $(patsubst %,%.html,$(ARTICLES) $(SP_ARTICLES))
+_DOC_HTML = $(_MAN_HTML)
+_DOC_HTML+=$(patsubst %,%.html,$(ARTICLES) $(SP_ARTICLES))
+DOC_HTML=$(addprefix $(OUTPUT),$(_DOC_HTML))
 
-DOC_MAN1=$(patsubst %.txt,%.1,$(MAN1_TXT))
-DOC_MAN5=$(patsubst %.txt,%.5,$(MAN5_TXT))
-DOC_MAN7=$(patsubst %.txt,%.7,$(MAN7_TXT))
+_DOC_MAN1=$(patsubst %.txt,%.1,$(MAN1_TXT))
+_DOC_MAN5=$(patsubst %.txt,%.5,$(MAN5_TXT))
+_DOC_MAN7=$(patsubst %.txt,%.7,$(MAN7_TXT))
+
+DOC_MAN1=$(addprefix $(OUTPUT),$(_DOC_MAN1))
+DOC_MAN5=$(addprefix $(OUTPUT),$(_DOC_MAN5))
+DOC_MAN7=$(addprefix $(OUTPUT),$(_DOC_MAN7))
 
 # Make the path relative to DESTDIR, not prefix
 ifndef DESTDIR
@@ -150,9 +164,9 @@
 man5: $(DOC_MAN5)
 man7: $(DOC_MAN7)
 
-info: perf.info perfman.info
+info: $(OUTPUT)perf.info $(OUTPUT)perfman.info
 
-pdf: user-manual.pdf
+pdf: $(OUTPUT)user-manual.pdf
 
 install: install-man
 
@@ -166,7 +180,7 @@
 
 install-info: info
 	$(INSTALL) -d -m 755 $(DESTDIR)$(infodir)
-	$(INSTALL) -m 644 perf.info perfman.info $(DESTDIR)$(infodir)
+	$(INSTALL) -m 644 $(OUTPUT)perf.info $(OUTPUT)perfman.info $(DESTDIR)$(infodir)
 	if test -r $(DESTDIR)$(infodir)/dir; then \
 	  $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perf.info ;\
 	  $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perfman.info ;\
@@ -176,7 +190,7 @@
 
 install-pdf: pdf
 	$(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir)
-	$(INSTALL) -m 644 user-manual.pdf $(DESTDIR)$(pdfdir)
+	$(INSTALL) -m 644 $(OUTPUT)user-manual.pdf $(DESTDIR)$(pdfdir)
 
 #install-html: html
 #	'$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
@@ -189,14 +203,14 @@
 #
 # Determine "include::" file references in asciidoc files.
 #
-doc.dep : $(wildcard *.txt) build-docdep.perl
+$(OUTPUT)doc.dep : $(wildcard *.txt) build-docdep.perl
 	$(QUIET_GEN)$(RM) $@+ $@ && \
 	$(PERL_PATH) ./build-docdep.perl >$@+ $(QUIET_STDERR) && \
 	mv $@+ $@
 
--include doc.dep
+-include $(OUPTUT)doc.dep
 
-cmds_txt = cmds-ancillaryinterrogators.txt \
+_cmds_txt = cmds-ancillaryinterrogators.txt \
 	cmds-ancillarymanipulators.txt \
 	cmds-mainporcelain.txt \
 	cmds-plumbinginterrogators.txt \
@@ -205,32 +219,36 @@
 	cmds-synchelpers.txt \
 	cmds-purehelpers.txt \
 	cmds-foreignscminterface.txt
+cmds_txt=$(addprefix $(OUTPUT),$(_cmds_txt))
 
-$(cmds_txt): cmd-list.made
+$(cmds_txt): $(OUTPUT)cmd-list.made
 
-cmd-list.made: cmd-list.perl ../command-list.txt $(MAN1_TXT)
+$(OUTPUT)cmd-list.made: cmd-list.perl ../command-list.txt $(MAN1_TXT)
 	$(QUIET_GEN)$(RM) $@ && \
 	$(PERL_PATH) ./cmd-list.perl ../command-list.txt $(QUIET_STDERR) && \
 	date >$@
 
 clean:
-	$(RM) *.xml *.xml+ *.html *.html+ *.1 *.5 *.7
-	$(RM) *.texi *.texi+ *.texi++ perf.info perfman.info
-	$(RM) howto-index.txt howto/*.html doc.dep
-	$(RM) technical/api-*.html technical/api-index.txt
-	$(RM) $(cmds_txt) *.made
+	$(RM) $(MAN_XML) $(addsuffix +,$(MAN_XML))
+	$(RM) $(MAN_HTML) $(addsuffix +,$(MAN_HTML))
+	$(RM) $(DOC_HTML) $(DOC_MAN1) $(DOC_MAN5) $(DOC_MAN7)
+	$(RM) $(OUTPUT)*.texi $(OUTPUT)*.texi+ $(OUTPUT)*.texi++
+	$(RM) $(OUTPUT)perf.info $(OUTPUT)perfman.info
+	$(RM) $(OUTPUT)howto-index.txt $(OUTPUT)howto/*.html $(OUTPUT)doc.dep
+	$(RM) $(OUTPUT)technical/api-*.html $(OUTPUT)technical/api-index.txt
+	$(RM) $(cmds_txt) $(OUTPUT)*.made
 
-$(MAN_HTML): %.html : %.txt
+$(MAN_HTML): $(OUTPUT)%.html : %.txt
 	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
 	$(ASCIIDOC) -b xhtml11 -d manpage -f asciidoc.conf \
 		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
 	mv $@+ $@
 
-%.1 %.5 %.7 : %.xml
+$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml
 	$(QUIET_XMLTO)$(RM) $@ && \
-	xmlto -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
+	xmlto -o $(OUTPUT) -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
 
-%.xml : %.txt
+$(OUTPUT)%.xml : %.txt
 	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
 	$(ASCIIDOC) -b docbook -d manpage -f asciidoc.conf \
 		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
@@ -239,25 +257,25 @@
 XSLT = docbook.xsl
 XSLTOPTS = --xinclude --stringparam html.stylesheet docbook-xsl.css
 
-user-manual.html: user-manual.xml
+$(OUTPUT)user-manual.html: $(OUTPUT)user-manual.xml
 	$(QUIET_XSLTPROC)xsltproc $(XSLTOPTS) -o $@ $(XSLT) $<
 
-perf.info: user-manual.texi
-	$(QUIET_MAKEINFO)$(MAKEINFO) --no-split -o $@ user-manual.texi
+$(OUTPUT)perf.info: $(OUTPUT)user-manual.texi
+	$(QUIET_MAKEINFO)$(MAKEINFO) --no-split -o $@ $(OUTPUT)user-manual.texi
 
-user-manual.texi: user-manual.xml
+$(OUTPUT)user-manual.texi: $(OUTPUT)user-manual.xml
 	$(QUIET_DB2TEXI)$(RM) $@+ $@ && \
-	$(DOCBOOK2X_TEXI) user-manual.xml --encoding=UTF-8 --to-stdout >$@++ && \
+	$(DOCBOOK2X_TEXI) $(OUTPUT)user-manual.xml --encoding=UTF-8 --to-stdout >$@++ && \
 	$(PERL_PATH) fix-texi.perl <$@++ >$@+ && \
 	rm $@++ && \
 	mv $@+ $@
 
-user-manual.pdf: user-manual.xml
+$(OUTPUT)user-manual.pdf: $(OUTPUT)user-manual.xml
 	$(QUIET_DBLATEX)$(RM) $@+ $@ && \
 	$(DBLATEX) -o $@+ -p /etc/asciidoc/dblatex/asciidoc-dblatex.xsl -s /etc/asciidoc/dblatex/asciidoc-dblatex.sty $< && \
 	mv $@+ $@
 
-perfman.texi: $(MAN_XML) cat-texi.perl
+$(OUTPUT)perfman.texi: $(MAN_XML) cat-texi.perl
 	$(QUIET_DB2TEXI)$(RM) $@+ $@ && \
 	($(foreach xml,$(MAN_XML),$(DOCBOOK2X_TEXI) --encoding=UTF-8 \
 		--to-stdout $(xml) &&) true) > $@++ && \
@@ -265,7 +283,7 @@
 	rm $@++ && \
 	mv $@+ $@
 
-perfman.info: perfman.texi
+$(OUTPUT)perfman.info: $(OUTPUT)perfman.texi
 	$(QUIET_MAKEINFO)$(MAKEINFO) --no-split --no-validate $*.texi
 
 $(patsubst %.txt,%.texi,$(MAN_TXT)): %.texi : %.xml
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index d6b2a4f..c7f5f55 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -8,7 +8,7 @@
 SYNOPSIS
 --------
 [verse]
-'perf lock' {record|report|trace}
+'perf lock' {record|report|script|info}
 
 DESCRIPTION
 -----------
@@ -20,10 +20,13 @@
   produces the file "perf.data" which contains tracing
   results of lock events.
 
-  'perf lock trace' shows raw lock events.
-
   'perf lock report' reports statistical data.
 
+  'perf lock script' shows raw lock events.
+
+  'perf lock info' shows metadata like threads or addresses
+  of lock instances.
+
 COMMON OPTIONS
 --------------
 
@@ -47,6 +50,17 @@
         Sorting key. Possible values: acquired (default), contended,
         wait_total, wait_max, wait_min.
 
+INFO OPTIONS
+------------
+
+-t::
+--threads::
+	dump thread list in perf.data
+
+-m::
+--map::
+	dump map of lock instances (address:name table)
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 2937f7e..a1386b2 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -52,11 +52,15 @@
 
 -p::
 --pid=::
-	Record events on existing process ID.
+	Record events on existing process ID (comma separated list).
 
 -t::
 --tid=::
-        Record events on existing thread ID.
+        Record events on existing thread ID (comma separated list).
+
+-u::
+--uid=::
+        Record events in threads owned by uid. Name or number.
 
 -r::
 --realtime=::
@@ -148,6 +152,36 @@
 corresponding events, i.e., they always refer to events defined earlier on the command
 line.
 
+-b::
+--branch-any::
+Enable taken branch stack sampling. Any type of taken branch may be sampled.
+This is a shortcut for --branch-filter any. See --branch-filter for more infos.
+
+-j::
+--branch-filter::
+Enable taken branch stack sampling. Each sample captures a series of consecutive
+taken branches. The number of branches captured with each sample depends on the
+underlying hardware, the type of branches of interest, and the executed code.
+It is possible to select the types of branches captured by enabling filters. The
+following filters are defined:
+
+        - any:  any type of branches
+        - any_call: any function call or system call
+        - any_ret: any function return or system call return
+        - any_ind: any indirect branch
+        - u:  only when the branch target is at the user level
+        - k: only when the branch target is in the kernel
+        - hv: only when the target is at the hypervisor level
+
++
+The option requires at least one branch type among any, any_call, any_ret, ind_call.
+The privilege levels may be ommitted, in which case, the privilege levels of the associated
+event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege
+levels are subject to permissions.  When sampling on multiple events, branch stack sampling
+is enabled for all the sampling events. The sampled branch type is the same for all events.
+The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
+Note that this feature may not be available on all processors.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 9b430e9..2d89f02 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -48,6 +48,9 @@
 	Only consider these symbols. CSV that understands
 	file://filename entries.
 
+--symbol-filter=::
+	Only show symbols that match (partially) with this filter.
+
 -U::
 --hide-unresolved::
         Only display entries resolved to a symbol.
@@ -110,6 +113,8 @@
 	requires a tty, if one is not present, as when piping to other
 	commands, the stdio interface is used.
 
+--gtk:: Use the GTK2 interface.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname
@@ -153,6 +158,16 @@
 	information which may be very large and thus may clutter the display.
 	It currently includes: cpu and numa topology of the host system.
 
+-b::
+--branch-stack::
+	Use the addresses of sampled taken branches instead of the instruction
+	address to build the histograms. To generate meaningful output, the
+	perf.data file must have been obtained using perf record -b or
+	perf record --branch-filter xxx where xxx is a branch filter option.
+	perf report is able to auto-detect whether a perf.data file contains
+	branch stacks and it will automatically switch to the branch view mode,
+	unless --no-branch-stack is used.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 2f6cef4..e9cbfcd 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -115,7 +115,7 @@
 -f::
 --fields::
         Comma separated list of fields to print. Options are:
-        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr.
+        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -f sw:comm,tid,time,ip,sym  and -f trace:time,cpu,trace
@@ -200,6 +200,9 @@
 	It currently includes: cpu and numa topology of the host system.
 	It can only be used with the perf script report mode.
 
+--show-kernel-path::
+	Try to resolve the path of [kernel.kallsyms]
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 8966b9a..2fa173b 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -35,11 +35,11 @@
         child tasks do not inherit counters
 -p::
 --pid=<pid>::
-        stat events on existing process id
+        stat events on existing process id (comma separated list)
 
 -t::
 --tid=<tid>::
-        stat events on existing thread id
+        stat events on existing thread id (comma separated list)
 
 
 -a::
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index b1a5bbb..4a5680c 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -72,11 +72,15 @@
 
 -p <pid>::
 --pid=<pid>::
-	Profile events on existing Process ID.
+	Profile events on existing Process ID (comma separated list).
 
 -t <tid>::
 --tid=<tid>::
-        Profile events on existing thread ID.
+        Profile events on existing thread ID (comma separated list).
+
+-u::
+--uid=::
+        Record events in threads owned by uid. Name or number.
 
 -r <priority>::
 --realtime=<priority>::
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 1078c5f..5476bc0 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -9,6 +9,7 @@
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
 arch/*/lib/memcpy*.S
+arch/*/lib/memset*.S
 include/linux/poison.h
 include/linux/magic.h
 include/linux/hw_breakpoint.h
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 8a4b9bc..b492e3a 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -15,6 +15,16 @@
 
 # Define V to have a more verbose compile.
 #
+# Define O to save output files in a separate directory.
+#
+# Define ARCH as name of target architecture if you want cross-builds.
+#
+# Define CROSS_COMPILE as prefix name of compiler if you want cross-builds.
+#
+# Define NO_LIBPERL to disable perl script extension.
+#
+# Define NO_LIBPYTHON to disable python script extension.
+#
 # Define PYTHON to point to the python binary if the default
 # `python' is not correct; for example: PYTHON=python2
 #
@@ -32,6 +42,10 @@
 # Define NO_DWARF if you do not want debug-info analysis feature at all.
 #
 # Define WERROR=0 to disable treating any warnings as errors.
+#
+# Define NO_NEWT if you do not want TUI support.
+#
+# Define NO_DEMANGLE if you do not want C++ symbol demangling.
 
 $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
 	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
@@ -47,6 +61,8 @@
 
 CC = $(CROSS_COMPILE)gcc
 AR = $(CROSS_COMPILE)ar
+FLEX = $(CROSS_COMPILE)flex
+BISON= $(CROSS_COMPILE)bison
 
 # Additional ARCH settings for x86
 ifeq ($(ARCH),i386)
@@ -61,7 +77,7 @@
 	ifeq (${IS_X86_64}, 1)
 		RAW_ARCH := x86_64
 		ARCH_CFLAGS := -DARCH_X86_64
-		ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
+		ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
 	endif
 endif
 
@@ -183,7 +199,10 @@
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
 
-$(OUTPUT)python/perf.so: $(PYRF_OBJS)
+PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
+PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py
+
+$(OUTPUT)python/perf.so: $(PYRF_OBJS) $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
 	$(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
 	mkdir -p $(OUTPUT)python && \
@@ -258,6 +277,8 @@
 LIB_H += util/build-id.h
 LIB_H += util/debug.h
 LIB_H += util/debugfs.h
+LIB_H += util/sysfs.h
+LIB_H += util/pmu.h
 LIB_H += util/event.h
 LIB_H += util/evsel.h
 LIB_H += util/evlist.h
@@ -304,6 +325,8 @@
 LIB_OBJS += $(OUTPUT)util/config.o
 LIB_OBJS += $(OUTPUT)util/ctype.o
 LIB_OBJS += $(OUTPUT)util/debugfs.o
+LIB_OBJS += $(OUTPUT)util/sysfs.o
+LIB_OBJS += $(OUTPUT)util/pmu.o
 LIB_OBJS += $(OUTPUT)util/environment.o
 LIB_OBJS += $(OUTPUT)util/event.o
 LIB_OBJS += $(OUTPUT)util/evlist.o
@@ -340,6 +363,10 @@
 LIB_OBJS += $(OUTPUT)util/thread.o
 LIB_OBJS += $(OUTPUT)util/thread_map.o
 LIB_OBJS += $(OUTPUT)util/trace-event-parse.o
+LIB_OBJS += $(OUTPUT)util/parse-events-flex.o
+LIB_OBJS += $(OUTPUT)util/parse-events-bison.o
+LIB_OBJS += $(OUTPUT)util/pmu-flex.o
+LIB_OBJS += $(OUTPUT)util/pmu-bison.o
 LIB_OBJS += $(OUTPUT)util/trace-event-read.o
 LIB_OBJS += $(OUTPUT)util/trace-event-info.o
 LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o
@@ -361,8 +388,10 @@
 BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
 ifeq ($(RAW_ARCH),x86_64)
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o
 endif
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
 BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o
@@ -480,6 +509,20 @@
 	endif
 endif
 
+ifdef NO_GTK2
+	BASIC_CFLAGS += -DNO_GTK2
+else
+	FLAGS_GTK2=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0)
+	ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2)),y)
+		msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev);
+		BASIC_CFLAGS += -DNO_GTK2_SUPPORT
+	else
+		BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0)
+		EXTLIBS += $(shell pkg-config --libs gtk+-2.0)
+		LIB_OBJS += $(OUTPUT)util/gtk/browser.o
+	endif
+endif
+
 ifdef NO_LIBPERL
 	BASIC_CFLAGS += -DNO_LIBPERL
 else
@@ -626,6 +669,8 @@
 	QUIET_LINK     = @echo '   ' LINK $@;
 	QUIET_MKDIR    = @echo '   ' MKDIR $@;
 	QUIET_GEN      = @echo '   ' GEN $@;
+	QUIET_FLEX     = @echo '   ' FLEX $@;
+	QUIET_BISON    = @echo '   ' BISON $@;
 endif
 endif
 
@@ -706,12 +751,19 @@
 	$(SCRIPTS) \
 	: $(OUTPUT)PERF-VERSION-FILE
 
+.SUFFIXES:
+.SUFFIXES: .o .c .S .s
+
 $(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+$(OUTPUT)%.i: %.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -E $(ALL_CFLAGS) $<
 $(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $<
+	$(QUIET_CC)$(CC) -o $@ -S $(ALL_CFLAGS) $<
 $(OUTPUT)%.o: %.S
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+$(OUTPUT)%.s: %.S
+	$(QUIET_CC)$(CC) -o $@ -E $(ALL_CFLAGS) $<
 
 $(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
@@ -738,6 +790,12 @@
 $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
+$(OUTPUT)util/parse-events-flex.o: util/parse-events-flex.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Wno-redundant-decls -Wno-switch-default -Wno-unused-function $<
+
+$(OUTPUT)util/pmu-flex.o: util/pmu-flex.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Wno-redundant-decls -Wno-switch-default -Wno-unused-function $<
+
 $(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
 
@@ -774,6 +832,8 @@
 	@echo '  html		- make html documentation'
 	@echo '  info		- make GNU info documentation (access with info <foo>)'
 	@echo '  pdf		- make pdf documentation'
+	@echo '  event-parser	- make event parser code'
+	@echo '  pmu-parser	- make pmu format parser code'
 	@echo '  TAGS		- use etags to make tag information for source browsing'
 	@echo '  tags		- use ctags to make tag information for source browsing'
 	@echo '  cscope	- use cscope to make interactive browsing database'
@@ -794,7 +854,6 @@
 	@echo '  quick-install-html	- install the html documentation quickly'
 	@echo ''
 	@echo 'Perf maintainer targets:'
-	@echo '  distclean		- alias to clean'
 	@echo '  clean			- clean all binary objects and build output'
 
 doc:
@@ -824,6 +883,14 @@
 	$(RM) cscope*
 	$(FIND) . -name '*.[hcS]' -print | xargs cscope -b
 
+event-parser:
+	$(QUIET_BISON)$(BISON) -v util/parse-events.y -d -o util/parse-events-bison.c
+	$(QUIET_FLEX)$(FLEX) --header-file=util/parse-events-flex.h -t util/parse-events.l > util/parse-events-flex.c
+
+pmu-parser:
+	$(QUIET_BISON)$(BISON) -v util/pmu.y -d -o util/pmu-bison.c
+	$(QUIET_FLEX)$(FLEX) --header-file=util/pmu-flex.h -t util/pmu.l > util/pmu-flex.c
+
 ### Detect prefix changes
 TRACK_CFLAGS = $(subst ','\'',$(ALL_CFLAGS)):\
              $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ)
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index f7781c6..a09bece 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -4,6 +4,7 @@
 extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
 extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
 extern int bench_mem_memcpy(int argc, const char **argv, const char *prefix __used);
+extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
index d588b87..d66ab79 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
@@ -2,3 +2,11 @@
 MEMCPY_FN(__memcpy,
 	"x86-64-unrolled",
 	"unrolled memcpy() in arch/x86/lib/memcpy_64.S")
+
+MEMCPY_FN(memcpy_c,
+	"x86-64-movsq",
+	"movsq-based memcpy() in arch/x86/lib/memcpy_64.S")
+
+MEMCPY_FN(memcpy_c_e,
+	"x86-64-movsb",
+	"movsb-based memcpy() in arch/x86/lib/memcpy_64.S")
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index 185a96d..fcd9cf0 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -1,4 +1,8 @@
-
+#define memcpy MEMCPY /* don't hide glibc's memcpy() */
+#define altinstr_replacement text
+#define globl p2align 4; .globl
+#define Lmemcpy_c globl memcpy_c; memcpy_c
+#define Lmemcpy_c_e globl memcpy_c_e; memcpy_c_e
 #include "../../../arch/x86/lib/memcpy_64.S"
 /*
  * We need to provide note.GNU-stack section, saying that we want
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index db82021..7155722 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -5,7 +5,6 @@
  *
  * Written by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
  */
-#include <ctype.h>
 
 #include "../perf.h"
 #include "../util/util.h"
@@ -24,6 +23,7 @@
 
 static const char	*length_str	= "1MB";
 static const char	*routine	= "default";
+static int		iterations	= 1;
 static bool		use_clock;
 static int		clock_fd;
 static bool		only_prefault;
@@ -35,6 +35,8 @@
 		    "available unit: B, MB, GB (upper and lower)"),
 	OPT_STRING('r', "routine", &routine, "default",
 		    "Specify routine to copy"),
+	OPT_INTEGER('i', "iterations", &iterations,
+		    "repeat memcpy() invocation this number of times"),
 	OPT_BOOLEAN('c', "clock", &use_clock,
 		    "Use CPU clock for measuring"),
 	OPT_BOOLEAN('o', "only-prefault", &only_prefault,
@@ -121,6 +123,7 @@
 {
 	u64 clock_start = 0ULL, clock_end = 0ULL;
 	void *src = NULL, *dst = NULL;
+	int i;
 
 	alloc_mem(&src, &dst, len);
 
@@ -128,7 +131,8 @@
 		fn(dst, src, len);
 
 	clock_start = get_clock();
-	fn(dst, src, len);
+	for (i = 0; i < iterations; ++i)
+		fn(dst, src, len);
 	clock_end = get_clock();
 
 	free(src);
@@ -140,6 +144,7 @@
 {
 	struct timeval tv_start, tv_end, tv_diff;
 	void *src = NULL, *dst = NULL;
+	int i;
 
 	alloc_mem(&src, &dst, len);
 
@@ -147,7 +152,8 @@
 		fn(dst, src, len);
 
 	BUG_ON(gettimeofday(&tv_start, NULL));
-	fn(dst, src, len);
+	for (i = 0; i < iterations; ++i)
+		fn(dst, src, len);
 	BUG_ON(gettimeofday(&tv_end, NULL));
 
 	timersub(&tv_end, &tv_start, &tv_diff);
diff --git a/tools/perf/bench/mem-memset-arch.h b/tools/perf/bench/mem-memset-arch.h
new file mode 100644
index 0000000..a040fa7
--- /dev/null
+++ b/tools/perf/bench/mem-memset-arch.h
@@ -0,0 +1,12 @@
+
+#ifdef ARCH_X86_64
+
+#define MEMSET_FN(fn, name, desc)		\
+	extern void *fn(void *, int, size_t);
+
+#include "mem-memset-x86-64-asm-def.h"
+
+#undef MEMSET_FN
+
+#endif
+
diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h
new file mode 100644
index 0000000..a71dff9
--- /dev/null
+++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h
@@ -0,0 +1,12 @@
+
+MEMSET_FN(__memset,
+	"x86-64-unrolled",
+	"unrolled memset() in arch/x86/lib/memset_64.S")
+
+MEMSET_FN(memset_c,
+	"x86-64-stosq",
+	"movsq-based memset() in arch/x86/lib/memset_64.S")
+
+MEMSET_FN(memset_c_e,
+	"x86-64-stosb",
+	"movsb-based memset() in arch/x86/lib/memset_64.S")
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
new file mode 100644
index 0000000..9e5af89
--- /dev/null
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -0,0 +1,13 @@
+#define memset MEMSET /* don't hide glibc's memset() */
+#define altinstr_replacement text
+#define globl p2align 4; .globl
+#define Lmemset_c globl memset_c; memset_c
+#define Lmemset_c_e globl memset_c_e; memset_c_e
+#include "../../../arch/x86/lib/memset_64.S"
+
+/*
+ * We need to provide note.GNU-stack section, saying that we want
+ * NOT executable stack. Otherwise the final linking will assume that
+ * the ELF stack should not be restricted at all and set it RWX.
+ */
+.section .note.GNU-stack,"",@progbits
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
new file mode 100644
index 0000000..e907918
--- /dev/null
+++ b/tools/perf/bench/mem-memset.c
@@ -0,0 +1,297 @@
+/*
+ * mem-memset.c
+ *
+ * memset: Simple memory set in various ways
+ *
+ * Trivial clone of mem-memcpy.c.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "mem-memset-arch.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/time.h>
+#include <errno.h>
+
+#define K 1024
+
+static const char	*length_str	= "1MB";
+static const char	*routine	= "default";
+static int		iterations	= 1;
+static bool		use_clock;
+static int		clock_fd;
+static bool		only_prefault;
+static bool		no_prefault;
+
+static const struct option options[] = {
+	OPT_STRING('l', "length", &length_str, "1MB",
+		    "Specify length of memory to copy. "
+		    "available unit: B, MB, GB (upper and lower)"),
+	OPT_STRING('r', "routine", &routine, "default",
+		    "Specify routine to copy"),
+	OPT_INTEGER('i', "iterations", &iterations,
+		    "repeat memset() invocation this number of times"),
+	OPT_BOOLEAN('c', "clock", &use_clock,
+		    "Use CPU clock for measuring"),
+	OPT_BOOLEAN('o', "only-prefault", &only_prefault,
+		    "Show only the result with page faults before memset()"),
+	OPT_BOOLEAN('n', "no-prefault", &no_prefault,
+		    "Show only the result without page faults before memset()"),
+	OPT_END()
+};
+
+typedef void *(*memset_t)(void *, int, size_t);
+
+struct routine {
+	const char *name;
+	const char *desc;
+	memset_t fn;
+};
+
+static const struct routine routines[] = {
+	{ "default",
+	  "Default memset() provided by glibc",
+	  memset },
+#ifdef ARCH_X86_64
+
+#define MEMSET_FN(fn, name, desc) { name, desc, fn },
+#include "mem-memset-x86-64-asm-def.h"
+#undef MEMSET_FN
+
+#endif
+
+	{ NULL,
+	  NULL,
+	  NULL   }
+};
+
+static const char * const bench_mem_memset_usage[] = {
+	"perf bench mem memset <options>",
+	NULL
+};
+
+static struct perf_event_attr clock_attr = {
+	.type		= PERF_TYPE_HARDWARE,
+	.config		= PERF_COUNT_HW_CPU_CYCLES
+};
+
+static void init_clock(void)
+{
+	clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0);
+
+	if (clock_fd < 0 && errno == ENOSYS)
+		die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
+	else
+		BUG_ON(clock_fd < 0);
+}
+
+static u64 get_clock(void)
+{
+	int ret;
+	u64 clk;
+
+	ret = read(clock_fd, &clk, sizeof(u64));
+	BUG_ON(ret != sizeof(u64));
+
+	return clk;
+}
+
+static double timeval2double(struct timeval *ts)
+{
+	return (double)ts->tv_sec +
+		(double)ts->tv_usec / (double)1000000;
+}
+
+static void alloc_mem(void **dst, size_t length)
+{
+	*dst = zalloc(length);
+	if (!dst)
+		die("memory allocation failed - maybe length is too large?\n");
+}
+
+static u64 do_memset_clock(memset_t fn, size_t len, bool prefault)
+{
+	u64 clock_start = 0ULL, clock_end = 0ULL;
+	void *dst = NULL;
+	int i;
+
+	alloc_mem(&dst, len);
+
+	if (prefault)
+		fn(dst, -1, len);
+
+	clock_start = get_clock();
+	for (i = 0; i < iterations; ++i)
+		fn(dst, i, len);
+	clock_end = get_clock();
+
+	free(dst);
+	return clock_end - clock_start;
+}
+
+static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault)
+{
+	struct timeval tv_start, tv_end, tv_diff;
+	void *dst = NULL;
+	int i;
+
+	alloc_mem(&dst, len);
+
+	if (prefault)
+		fn(dst, -1, len);
+
+	BUG_ON(gettimeofday(&tv_start, NULL));
+	for (i = 0; i < iterations; ++i)
+		fn(dst, i, len);
+	BUG_ON(gettimeofday(&tv_end, NULL));
+
+	timersub(&tv_end, &tv_start, &tv_diff);
+
+	free(dst);
+	return (double)((double)len / timeval2double(&tv_diff));
+}
+
+#define pf (no_prefault ? 0 : 1)
+
+#define print_bps(x) do {					\
+		if (x < K)					\
+			printf(" %14lf B/Sec", x);		\
+		else if (x < K * K)				\
+			printf(" %14lfd KB/Sec", x / K);	\
+		else if (x < K * K * K)				\
+			printf(" %14lf MB/Sec", x / K / K);	\
+		else						\
+			printf(" %14lf GB/Sec", x / K / K / K); \
+	} while (0)
+
+int bench_mem_memset(int argc, const char **argv,
+		     const char *prefix __used)
+{
+	int i;
+	size_t len;
+	double result_bps[2];
+	u64 result_clock[2];
+
+	argc = parse_options(argc, argv, options,
+			     bench_mem_memset_usage, 0);
+
+	if (use_clock)
+		init_clock();
+
+	len = (size_t)perf_atoll((char *)length_str);
+
+	result_clock[0] = result_clock[1] = 0ULL;
+	result_bps[0] = result_bps[1] = 0.0;
+
+	if ((s64)len <= 0) {
+		fprintf(stderr, "Invalid length:%s\n", length_str);
+		return 1;
+	}
+
+	/* same to without specifying either of prefault and no-prefault */
+	if (only_prefault && no_prefault)
+		only_prefault = no_prefault = false;
+
+	for (i = 0; routines[i].name; i++) {
+		if (!strcmp(routines[i].name, routine))
+			break;
+	}
+	if (!routines[i].name) {
+		printf("Unknown routine:%s\n", routine);
+		printf("Available routines...\n");
+		for (i = 0; routines[i].name; i++) {
+			printf("\t%s ... %s\n",
+			       routines[i].name, routines[i].desc);
+		}
+		return 1;
+	}
+
+	if (bench_format == BENCH_FORMAT_DEFAULT)
+		printf("# Copying %s Bytes ...\n\n", length_str);
+
+	if (!only_prefault && !no_prefault) {
+		/* show both of results */
+		if (use_clock) {
+			result_clock[0] =
+				do_memset_clock(routines[i].fn, len, false);
+			result_clock[1] =
+				do_memset_clock(routines[i].fn, len, true);
+		} else {
+			result_bps[0] =
+				do_memset_gettimeofday(routines[i].fn,
+						len, false);
+			result_bps[1] =
+				do_memset_gettimeofday(routines[i].fn,
+						len, true);
+		}
+	} else {
+		if (use_clock) {
+			result_clock[pf] =
+				do_memset_clock(routines[i].fn,
+						len, only_prefault);
+		} else {
+			result_bps[pf] =
+				do_memset_gettimeofday(routines[i].fn,
+						len, only_prefault);
+		}
+	}
+
+	switch (bench_format) {
+	case BENCH_FORMAT_DEFAULT:
+		if (!only_prefault && !no_prefault) {
+			if (use_clock) {
+				printf(" %14lf Clock/Byte\n",
+					(double)result_clock[0]
+					/ (double)len);
+				printf(" %14lf Clock/Byte (with prefault)\n ",
+					(double)result_clock[1]
+					/ (double)len);
+			} else {
+				print_bps(result_bps[0]);
+				printf("\n");
+				print_bps(result_bps[1]);
+				printf(" (with prefault)\n");
+			}
+		} else {
+			if (use_clock) {
+				printf(" %14lf Clock/Byte",
+					(double)result_clock[pf]
+					/ (double)len);
+			} else
+				print_bps(result_bps[pf]);
+
+			printf("%s\n", only_prefault ? " (with prefault)" : "");
+		}
+		break;
+	case BENCH_FORMAT_SIMPLE:
+		if (!only_prefault && !no_prefault) {
+			if (use_clock) {
+				printf("%lf %lf\n",
+					(double)result_clock[0] / (double)len,
+					(double)result_clock[1] / (double)len);
+			} else {
+				printf("%lf %lf\n",
+					result_bps[0], result_bps[1]);
+			}
+		} else {
+			if (use_clock) {
+				printf("%lf\n", (double)result_clock[pf]
+					/ (double)len);
+			} else
+				printf("%lf\n", result_bps[pf]);
+		}
+		break;
+	default:
+		/* reaching this means there's some disaster: */
+		die("unknown format: %d\n", bench_format);
+		break;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index fcb9626..b0e74ab 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -52,6 +52,9 @@
 	{ "memcpy",
 	  "Simple memory copy in various ways",
 	  bench_mem_memcpy },
+	{ "memset",
+	  "Simple memory set in various ways",
+	  bench_mem_memset },
 	suite_all,
 	{ NULL,
 	  NULL,
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 2296c39..12c8148 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -922,12 +922,12 @@
 	OPT_BOOLEAN('t', "threads", &info_threads,
 		    "dump thread list in perf.data"),
 	OPT_BOOLEAN('m', "map", &info_map,
-		    "map of lock instances (name:address table)"),
+		    "map of lock instances (address:name table)"),
 	OPT_END()
 };
 
 static const char * const lock_usage[] = {
-	"perf lock [<options>] {record|trace|report}",
+	"perf lock [<options>] {record|report|script|info}",
 	NULL
 };
 
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index fb85661..4935c09 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -58,7 +58,7 @@
 	struct perf_probe_event events[MAX_PROBES];
 	struct strlist *dellist;
 	struct line_range line_range;
-	const char *target_module;
+	const char *target;
 	int max_probe_points;
 	struct strfilter *filter;
 } params;
@@ -246,7 +246,7 @@
 		   "file", "vmlinux pathname"),
 	OPT_STRING('s', "source", &symbol_conf.source_prefix,
 		   "directory", "path to kernel source"),
-	OPT_STRING('m', "module", &params.target_module,
+	OPT_STRING('m', "module", &params.target,
 		   "modname|path",
 		   "target module name (for online) or path (for offline)"),
 #endif
@@ -333,7 +333,7 @@
 		if (!params.filter)
 			params.filter = strfilter__new(DEFAULT_FUNC_FILTER,
 						       NULL);
-		ret = show_available_funcs(params.target_module,
+		ret = show_available_funcs(params.target,
 					   params.filter);
 		strfilter__delete(params.filter);
 		if (ret < 0)
@@ -354,7 +354,7 @@
 			usage_with_options(probe_usage, options);
 		}
 
-		ret = show_line_range(&params.line_range, params.target_module);
+		ret = show_line_range(&params.line_range, params.target);
 		if (ret < 0)
 			pr_err("  Error: Failed to show lines. (%d)\n", ret);
 		return ret;
@@ -371,7 +371,7 @@
 
 		ret = show_available_vars(params.events, params.nevents,
 					  params.max_probe_points,
-					  params.target_module,
+					  params.target,
 					  params.filter,
 					  params.show_ext_vars);
 		strfilter__delete(params.filter);
@@ -393,7 +393,7 @@
 	if (params.nevents) {
 		ret = add_perf_probe_events(params.events, params.nevents,
 					    params.max_probe_points,
-					    params.target_module,
+					    params.target,
 					    params.force_add);
 		if (ret < 0) {
 			pr_err("  Error: Failed to add events. (%d)\n", ret);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 227b6ae..be4e1ee 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -44,6 +44,7 @@
 	struct perf_evlist	*evlist;
 	struct perf_session	*session;
 	const char		*progname;
+	const char		*uid_str;
 	int			output;
 	unsigned int		page_size;
 	int			realtime_prio;
@@ -208,7 +209,7 @@
 		if (opts->exclude_guest_missing)
 			attr->exclude_guest = attr->exclude_host = 0;
 retry_sample_id:
-		attr->sample_id_all = opts->sample_id_all_avail ? 1 : 0;
+		attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1;
 try_again:
 		if (perf_evsel__open(pos, evlist->cpus, evlist->threads,
 				     opts->group, group_fd) < 0) {
@@ -227,11 +228,11 @@
 						 "guest or host samples.\n");
 					opts->exclude_guest_missing = true;
 					goto fallback_missing_features;
-				} else if (opts->sample_id_all_avail) {
+				} else if (!opts->sample_id_all_missing) {
 					/*
 					 * Old kernel, no attr->sample_id_type_all field
 					 */
-					opts->sample_id_all_avail = false;
+					opts->sample_id_all_missing = true;
 					if (!opts->sample_time && !opts->raw_samples && !time_needed)
 						attr->sample_type &= ~PERF_SAMPLE_TIME;
 
@@ -396,7 +397,7 @@
 {
 	struct stat st;
 	int flags;
-	int err, output;
+	int err, output, feat;
 	unsigned long waking = 0;
 	const bool forks = argc > 0;
 	struct machine *machine;
@@ -463,8 +464,17 @@
 
 	rec->session = session;
 
-	if (!rec->no_buildid)
-		perf_header__set_feat(&session->header, HEADER_BUILD_ID);
+	for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
+		perf_header__set_feat(&session->header, feat);
+
+	if (rec->no_buildid)
+		perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
+
+	if (!have_tracepoints(&evsel_list->entries))
+		perf_header__clear_feat(&session->header, HEADER_TRACE_INFO);
+
+	if (!rec->opts.branch_stack)
+		perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
 
 	if (!rec->file_new) {
 		err = perf_session__read_header(session, output);
@@ -472,22 +482,6 @@
 			goto out_delete_session;
 	}
 
-	if (have_tracepoints(&evsel_list->entries))
-		perf_header__set_feat(&session->header, HEADER_TRACE_INFO);
-
-	perf_header__set_feat(&session->header, HEADER_HOSTNAME);
-	perf_header__set_feat(&session->header, HEADER_OSRELEASE);
-	perf_header__set_feat(&session->header, HEADER_ARCH);
-	perf_header__set_feat(&session->header, HEADER_CPUDESC);
-	perf_header__set_feat(&session->header, HEADER_NRCPUS);
-	perf_header__set_feat(&session->header, HEADER_EVENT_DESC);
-	perf_header__set_feat(&session->header, HEADER_CMDLINE);
-	perf_header__set_feat(&session->header, HEADER_VERSION);
-	perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
-	perf_header__set_feat(&session->header, HEADER_TOTAL_MEM);
-	perf_header__set_feat(&session->header, HEADER_NUMA_TOPOLOGY);
-	perf_header__set_feat(&session->header, HEADER_CPUID);
-
 	if (forks) {
 		err = perf_evlist__prepare_workload(evsel_list, opts, argv);
 		if (err < 0) {
@@ -647,6 +641,90 @@
 	return err;
 }
 
+#define BRANCH_OPT(n, m) \
+	{ .name = n, .mode = (m) }
+
+#define BRANCH_END { .name = NULL }
+
+struct branch_mode {
+	const char *name;
+	int mode;
+};
+
+static const struct branch_mode branch_modes[] = {
+	BRANCH_OPT("u", PERF_SAMPLE_BRANCH_USER),
+	BRANCH_OPT("k", PERF_SAMPLE_BRANCH_KERNEL),
+	BRANCH_OPT("hv", PERF_SAMPLE_BRANCH_HV),
+	BRANCH_OPT("any", PERF_SAMPLE_BRANCH_ANY),
+	BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL),
+	BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN),
+	BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL),
+	BRANCH_END
+};
+
+static int
+parse_branch_stack(const struct option *opt, const char *str, int unset)
+{
+#define ONLY_PLM \
+	(PERF_SAMPLE_BRANCH_USER	|\
+	 PERF_SAMPLE_BRANCH_KERNEL	|\
+	 PERF_SAMPLE_BRANCH_HV)
+
+	uint64_t *mode = (uint64_t *)opt->value;
+	const struct branch_mode *br;
+	char *s, *os = NULL, *p;
+	int ret = -1;
+
+	if (unset)
+		return 0;
+
+	/*
+	 * cannot set it twice, -b + --branch-filter for instance
+	 */
+	if (*mode)
+		return -1;
+
+	/* str may be NULL in case no arg is passed to -b */
+	if (str) {
+		/* because str is read-only */
+		s = os = strdup(str);
+		if (!s)
+			return -1;
+
+		for (;;) {
+			p = strchr(s, ',');
+			if (p)
+				*p = '\0';
+
+			for (br = branch_modes; br->name; br++) {
+				if (!strcasecmp(s, br->name))
+					break;
+			}
+			if (!br->name) {
+				ui__warning("unknown branch filter %s,"
+					    " check man page\n", s);
+				goto error;
+			}
+
+			*mode |= br->mode;
+
+			if (!p)
+				break;
+
+			s = p + 1;
+		}
+	}
+	ret = 0;
+
+	/* default to any branch */
+	if ((*mode & ~ONLY_PLM) == 0) {
+		*mode = PERF_SAMPLE_BRANCH_ANY;
+	}
+error:
+	free(os);
+	return ret;
+}
+
 static const char * const record_usage[] = {
 	"perf record [<options>] [<command>]",
 	"perf record [<options>] -- <command> [<options>]",
@@ -665,13 +743,10 @@
  */
 static struct perf_record record = {
 	.opts = {
-		.target_pid	     = -1,
-		.target_tid	     = -1,
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
 		.freq		     = 1000,
-		.sample_id_all_avail = true,
 	},
 	.write_mode = WRITE_FORCE,
 	.file_new   = true,
@@ -690,9 +765,9 @@
 		     parse_events_option),
 	OPT_CALLBACK(0, "filter", &record.evlist, "filter",
 		     "event filter", parse_filter),
-	OPT_INTEGER('p', "pid", &record.opts.target_pid,
+	OPT_STRING('p', "pid", &record.opts.target_pid, "pid",
 		    "record events on existing process id"),
-	OPT_INTEGER('t', "tid", &record.opts.target_tid,
+	OPT_STRING('t', "tid", &record.opts.target_tid, "tid",
 		    "record events on existing thread id"),
 	OPT_INTEGER('r', "realtime", &record.realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
@@ -738,6 +813,15 @@
 	OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
 		     "monitor event in cgroup name only",
 		     parse_cgroups),
+	OPT_STRING('u', "uid", &record.uid_str, "user", "user to profile"),
+
+	OPT_CALLBACK_NOOPT('b', "branch-any", &record.opts.branch_stack,
+		     "branch any", "sample any taken branches",
+		     parse_branch_stack),
+
+	OPT_CALLBACK('j', "branch-filter", &record.opts.branch_stack,
+		     "branch filter mask", "branch stack filter modes",
+		     parse_branch_stack),
 	OPT_END()
 };
 
@@ -758,8 +842,8 @@
 
 	argc = parse_options(argc, argv, record_options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc && rec->opts.target_pid == -1 && rec->opts.target_tid == -1 &&
-		!rec->opts.system_wide && !rec->opts.cpu_list)
+	if (!argc && !rec->opts.target_pid && !rec->opts.target_tid &&
+		!rec->opts.system_wide && !rec->opts.cpu_list && !rec->uid_str)
 		usage_with_options(record_usage, record_options);
 
 	if (rec->force && rec->append_file) {
@@ -799,11 +883,17 @@
 		goto out_symbol_exit;
 	}
 
-	if (rec->opts.target_pid != -1)
+	rec->opts.uid = parse_target_uid(rec->uid_str, rec->opts.target_tid,
+					 rec->opts.target_pid);
+	if (rec->uid_str != NULL && rec->opts.uid == UINT_MAX - 1)
+		goto out_free_fd;
+
+	if (rec->opts.target_pid)
 		rec->opts.target_tid = rec->opts.target_pid;
 
 	if (perf_evlist__create_maps(evsel_list, rec->opts.target_pid,
-				     rec->opts.target_tid, rec->opts.cpu_list) < 0)
+				     rec->opts.target_tid, rec->opts.uid,
+				     rec->opts.cpu_list) < 0)
 		usage_with_options(record_usage, record_options);
 
 	list_for_each_entry(pos, &evsel_list->entries, node) {
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 25d34d4..2e31743 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -40,7 +40,7 @@
 	struct perf_tool	tool;
 	struct perf_session	*session;
 	char const		*input_name;
-	bool			force, use_tui, use_stdio;
+	bool			force, use_tui, use_gtk, use_stdio;
 	bool			hide_unresolved;
 	bool			dont_use_callchains;
 	bool			show_full_info;
@@ -50,9 +50,86 @@
 	const char		*pretty_printing_style;
 	symbol_filter_t		annotate_init;
 	const char		*cpu_list;
+	const char		*symbol_filter_str;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
+					struct addr_location *al,
+					struct perf_sample *sample,
+					struct perf_evsel *evsel,
+				      struct machine *machine)
+{
+	struct perf_report *rep = container_of(tool, struct perf_report, tool);
+	struct symbol *parent = NULL;
+	int err = 0;
+	unsigned i;
+	struct hist_entry *he;
+	struct branch_info *bi, *bx;
+
+	if ((sort__has_parent || symbol_conf.use_callchain)
+	    && sample->callchain) {
+		err = machine__resolve_callchain(machine, evsel, al->thread,
+						 sample->callchain, &parent);
+		if (err)
+			return err;
+	}
+
+	bi = machine__resolve_bstack(machine, al->thread,
+				     sample->branch_stack);
+	if (!bi)
+		return -ENOMEM;
+
+	for (i = 0; i < sample->branch_stack->nr; i++) {
+		if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
+			continue;
+		/*
+		 * The report shows the percentage of total branches captured
+		 * and not events sampled. Thus we use a pseudo period of 1.
+		 */
+		he = __hists__add_branch_entry(&evsel->hists, al, parent,
+				&bi[i], 1);
+		if (he) {
+			struct annotation *notes;
+			err = -ENOMEM;
+			bx = he->branch_info;
+			if (bx->from.sym && use_browser > 0) {
+				notes = symbol__annotation(bx->from.sym);
+				if (!notes->src
+				    && symbol__alloc_hist(bx->from.sym) < 0)
+					goto out;
+
+				err = symbol__inc_addr_samples(bx->from.sym,
+							       bx->from.map,
+							       evsel->idx,
+							       bx->from.al_addr);
+				if (err)
+					goto out;
+			}
+
+			if (bx->to.sym && use_browser > 0) {
+				notes = symbol__annotation(bx->to.sym);
+				if (!notes->src
+				    && symbol__alloc_hist(bx->to.sym) < 0)
+					goto out;
+
+				err = symbol__inc_addr_samples(bx->to.sym,
+							       bx->to.map,
+							       evsel->idx,
+							       bx->to.al_addr);
+				if (err)
+					goto out;
+			}
+			evsel->hists.stats.total_period += 1;
+			hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+			err = 0;
+		} else
+			return -ENOMEM;
+	}
+out:
+	return err;
+}
+
 static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 				      struct addr_location *al,
 				      struct perf_sample *sample,
@@ -126,14 +203,21 @@
 	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
 		return 0;
 
-	if (al.map != NULL)
-		al.map->dso->hit = 1;
+	if (sort__branch_mode == 1) {
+		if (perf_report__add_branch_hist_entry(tool, &al, sample,
+						       evsel, machine)) {
+			pr_debug("problem adding lbr entry, skipping event\n");
+			return -1;
+		}
+	} else {
+		if (al.map != NULL)
+			al.map->dso->hit = 1;
 
-	if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) {
-		pr_debug("problem incrementing symbol period, skipping event\n");
-		return -1;
+		if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) {
+			pr_debug("problem incrementing symbol period, skipping event\n");
+			return -1;
+		}
 	}
-
 	return 0;
 }
 
@@ -188,6 +272,15 @@
 			}
 	}
 
+	if (sort__branch_mode == 1) {
+		if (!(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) {
+			fprintf(stderr, "selected -b but no branch data."
+					" Did you call perf record without"
+					" -b?\n");
+			return -1;
+		}
+	}
+
 	return 0;
 }
 
@@ -246,7 +339,7 @@
 {
 	int ret = -EINVAL;
 	u64 nr_samples;
-	struct perf_session *session;
+	struct perf_session *session = rep->session;
 	struct perf_evsel *pos;
 	struct map *kernel_map;
 	struct kmap *kernel_kmap;
@@ -254,13 +347,6 @@
 
 	signal(SIGINT, sig_handler);
 
-	session = perf_session__new(rep->input_name, O_RDONLY,
-				    rep->force, false, &rep->tool);
-	if (session == NULL)
-		return -ENOMEM;
-
-	rep->session = session;
-
 	if (rep->cpu_list) {
 		ret = perf_session__cpu_bitmap(session, rep->cpu_list,
 					       rep->cpu_bitmap);
@@ -315,6 +401,9 @@
 	list_for_each_entry(pos, &session->evlist->entries, node) {
 		struct hists *hists = &pos->hists;
 
+		if (pos->idx == 0)
+			hists->symbol_filter_str = rep->symbol_filter_str;
+
 		hists__collapse_resort(hists);
 		hists__output_resort(hists);
 		nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
@@ -326,8 +415,13 @@
 	}
 
 	if (use_browser > 0) {
-		perf_evlist__tui_browse_hists(session->evlist, help,
-					      NULL, NULL, 0);
+		if (use_browser == 1) {
+			perf_evlist__tui_browse_hists(session->evlist, help,
+						      NULL, NULL, 0);
+		} else if (use_browser == 2) {
+			perf_evlist__gtk_browse_hists(session->evlist, help,
+						      NULL, NULL, 0);
+		}
 	} else
 		perf_evlist__tty_browse_hists(session->evlist, rep, help);
 
@@ -427,9 +521,19 @@
 	return 0;
 }
 
+static int
+parse_branch_mode(const struct option *opt __used, const char *str __used, int unset)
+{
+	sort__branch_mode = !unset;
+	return 0;
+}
+
 int cmd_report(int argc, const char **argv, const char *prefix __used)
 {
+	struct perf_session *session;
 	struct stat st;
+	bool has_br_stack = false;
+	int ret = -1;
 	char callchain_default_opt[] = "fractal,0.5,callee";
 	const char * const report_usage[] = {
 		"perf report [<options>]",
@@ -474,10 +578,12 @@
 	OPT_STRING(0, "pretty", &report.pretty_printing_style, "key",
 		   "pretty printing style key: normal raw"),
 	OPT_BOOLEAN(0, "tui", &report.use_tui, "Use the TUI interface"),
+	OPT_BOOLEAN(0, "gtk", &report.use_gtk, "Use the GTK2 interface"),
 	OPT_BOOLEAN(0, "stdio", &report.use_stdio,
 		    "Use the stdio interface"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   "sort by key(s): pid, comm, dso, symbol, parent"),
+		   "sort by key(s): pid, comm, dso, symbol, parent, dso_to,"
+		   " dso_from, symbol_to, symbol_from, mispredict"),
 	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
 		    "Show sample percentage for different cpu modes"),
 	OPT_STRING('p', "parent", &parent_pattern, "regex",
@@ -495,6 +601,8 @@
 		   "only consider symbols in these comms"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
 		   "only consider these symbols"),
+	OPT_STRING(0, "symbol-filter", &report.symbol_filter_str, "filter",
+		   "only show symbols that (partially) match with this filter"),
 	OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
 		   "width[,width...]",
 		   "don't try to adjust column width, use these fixed values"),
@@ -517,6 +625,8 @@
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
+	OPT_CALLBACK_NOOPT('b', "branch-stack", &sort__branch_mode, "",
+		    "use branch records for histogram filling", parse_branch_mode),
 	OPT_END()
 	};
 
@@ -526,6 +636,8 @@
 		use_browser = 0;
 	else if (report.use_tui)
 		use_browser = 1;
+	else if (report.use_gtk)
+		use_browser = 2;
 
 	if (report.inverted_callchain)
 		callchain_param.order = ORDER_CALLER;
@@ -536,11 +648,39 @@
 		else
 			report.input_name = "perf.data";
 	}
+	session = perf_session__new(report.input_name, O_RDONLY,
+				    report.force, false, &report.tool);
+	if (session == NULL)
+		return -ENOMEM;
 
-	if (strcmp(report.input_name, "-") != 0)
-		setup_browser(true);
-	else
+	report.session = session;
+
+	has_br_stack = perf_header__has_feat(&session->header,
+					     HEADER_BRANCH_STACK);
+
+	if (sort__branch_mode == -1 && has_br_stack)
+		sort__branch_mode = 1;
+
+	/* sort__branch_mode could be 0 if --no-branch-stack */
+	if (sort__branch_mode == 1) {
+		/*
+		 * if no sort_order is provided, then specify
+		 * branch-mode specific order
+		 */
+		if (sort_order == default_sort_order)
+			sort_order = "comm,dso_from,symbol_from,"
+				     "dso_to,symbol_to";
+
+	}
+
+	if (strcmp(report.input_name, "-") != 0) {
+		if (report.use_gtk)
+			perf_gtk_setup_browser(argc, argv, true);
+		else
+			setup_browser(true);
+	} else {
 		use_browser = 0;
+	}
 
 	/*
 	 * Only in the newt browser we are doing integrated annotation,
@@ -568,13 +708,13 @@
 	}
 
 	if (symbol__init() < 0)
-		return -1;
+		goto error;
 
 	setup_sorting(report_usage, options);
 
 	if (parent_pattern != default_parent_pattern) {
 		if (sort_dimension__add("parent") < 0)
-			return -1;
+			goto error;
 
 		/*
 		 * Only show the parent fields if we explicitly
@@ -586,15 +726,31 @@
 	} else
 		symbol_conf.exclude_other = false;
 
-	/*
-	 * Any (unrecognized) arguments left?
-	 */
-	if (argc)
-		usage_with_options(report_usage, options);
+	if (argc) {
+		/*
+		 * Special case: if there's an argument left then assume that
+		 * it's a symbol filter:
+		 */
+		if (argc > 1)
+			usage_with_options(report_usage, options);
 
-	sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
+		report.symbol_filter_str = argv[0];
+	}
+
 	sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout);
-	sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
 
-	return __cmd_report(&report);
+	if (sort__branch_mode == 1) {
+		sort_entry__setup_elide(&sort_dso_from, symbol_conf.dso_from_list, "dso_from", stdout);
+		sort_entry__setup_elide(&sort_dso_to, symbol_conf.dso_to_list, "dso_to", stdout);
+		sort_entry__setup_elide(&sort_sym_from, symbol_conf.sym_from_list, "sym_from", stdout);
+		sort_entry__setup_elide(&sort_sym_to, symbol_conf.sym_to_list, "sym_to", stdout);
+	} else {
+		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
+		sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
+	}
+
+	ret = __cmd_report(&report);
+error:
+	perf_session__delete(session);
+	return ret;
 }
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index bb68ddf..d4ce733 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -40,6 +40,7 @@
 	PERF_OUTPUT_SYM             = 1U << 8,
 	PERF_OUTPUT_DSO             = 1U << 9,
 	PERF_OUTPUT_ADDR            = 1U << 10,
+	PERF_OUTPUT_SYMOFFSET       = 1U << 11,
 };
 
 struct output_option {
@@ -57,6 +58,7 @@
 	{.str = "sym",   .field = PERF_OUTPUT_SYM},
 	{.str = "dso",   .field = PERF_OUTPUT_DSO},
 	{.str = "addr",  .field = PERF_OUTPUT_ADDR},
+	{.str = "symoff", .field = PERF_OUTPUT_SYMOFFSET},
 };
 
 /* default set to maintain compatibility with current format */
@@ -193,6 +195,11 @@
 		       "to symbols.\n");
 		return -EINVAL;
 	}
+	if (PRINT_FIELD(SYMOFFSET) && !PRINT_FIELD(SYM)) {
+		pr_err("Display of offsets requested but symbol is not"
+		       "selected.\n");
+		return -EINVAL;
+	}
 	if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
 		pr_err("Display of DSO requested but neither sample IP nor "
 			   "sample address\nis selected. Hence, no addresses to convert "
@@ -300,10 +307,17 @@
 		} else
 			evname = __event_name(attr->type, attr->config);
 
-		printf("%s: ", evname ? evname : "(unknown)");
+		printf("%s: ", evname ? evname : "[unknown]");
 	}
 }
 
+static bool is_bts_event(struct perf_event_attr *attr)
+{
+	return ((attr->type == PERF_TYPE_HARDWARE) &&
+		(attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
+		(attr->sample_period == 1));
+}
+
 static bool sample_addr_correlates_sym(struct perf_event_attr *attr)
 {
 	if ((attr->type == PERF_TYPE_SOFTWARE) &&
@@ -312,6 +326,9 @@
 	     (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)))
 		return true;
 
+	if (is_bts_event(attr))
+		return true;
+
 	return false;
 }
 
@@ -323,7 +340,6 @@
 {
 	struct addr_location al;
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	const char *symname, *dsoname;
 
 	printf("%16" PRIx64, sample->addr);
 
@@ -343,24 +359,48 @@
 		al.sym = map__find_symbol(al.map, al.addr, NULL);
 
 	if (PRINT_FIELD(SYM)) {
-		if (al.sym && al.sym->name)
-			symname = al.sym->name;
+		printf(" ");
+		if (PRINT_FIELD(SYMOFFSET))
+			symbol__fprintf_symname_offs(al.sym, &al, stdout);
 		else
-			symname = "";
-
-		printf(" %16s", symname);
+			symbol__fprintf_symname(al.sym, stdout);
 	}
 
 	if (PRINT_FIELD(DSO)) {
-		if (al.map && al.map->dso && al.map->dso->name)
-			dsoname = al.map->dso->name;
-		else
-			dsoname = "";
-
-		printf(" (%s)", dsoname);
+		printf(" (");
+		map__fprintf_dsoname(al.map, stdout);
+		printf(")");
 	}
 }
 
+static void print_sample_bts(union perf_event *event,
+			     struct perf_sample *sample,
+			     struct perf_evsel *evsel,
+			     struct machine *machine,
+			     struct thread *thread)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+
+	/* print branch_from information */
+	if (PRINT_FIELD(IP)) {
+		if (!symbol_conf.use_callchain)
+			printf(" ");
+		else
+			printf("\n");
+		perf_event__print_ip(event, sample, machine, evsel,
+				     PRINT_FIELD(SYM), PRINT_FIELD(DSO),
+				     PRINT_FIELD(SYMOFFSET));
+	}
+
+	printf(" => ");
+
+	/* print branch_to information */
+	if (PRINT_FIELD(ADDR))
+		print_sample_addr(event, sample, machine, thread, attr);
+
+	printf("\n");
+}
+
 static void process_event(union perf_event *event __unused,
 			  struct perf_sample *sample,
 			  struct perf_evsel *evsel,
@@ -374,6 +414,11 @@
 
 	print_sample_start(sample, thread, attr);
 
+	if (is_bts_event(attr)) {
+		print_sample_bts(event, sample, evsel, machine, thread);
+		return;
+	}
+
 	if (PRINT_FIELD(TRACE))
 		print_trace_event(sample->cpu, sample->raw_data,
 				  sample->raw_size);
@@ -387,7 +432,8 @@
 		else
 			printf("\n");
 		perf_event__print_ip(event, sample, machine, evsel,
-				     PRINT_FIELD(SYM), PRINT_FIELD(DSO));
+				     PRINT_FIELD(SYM), PRINT_FIELD(DSO),
+				     PRINT_FIELD(SYMOFFSET));
 	}
 
 	printf("\n");
@@ -1097,7 +1143,10 @@
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		    "Look for files with symbols relative to this directory"),
 	OPT_CALLBACK('f', "fields", NULL, "str",
-		     "comma separated output fields prepend with 'type:'. Valid types: hw,sw,trace,raw. Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,addr",
+		     "comma separated output fields prepend with 'type:'. "
+		     "Valid types: hw,sw,trace,raw. "
+		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
+		     "addr,symoff",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		     "system-wide collection from all CPUs"),
@@ -1106,6 +1155,9 @@
 		   "only display events for these comms"),
 	OPT_BOOLEAN('I', "show-info", &show_full_info,
 		    "display extended information from perf.data file"),
+	OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path,
+		    "Show the path of [kernel.kallsyms]"),
+
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f5d2a63..c941bb6 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -182,8 +182,8 @@
 static bool			no_inherit			= false;
 static bool			scale				=  true;
 static bool			no_aggr				= false;
-static pid_t			target_pid			= -1;
-static pid_t			target_tid			= -1;
+static const char		*target_pid;
+static const char		*target_tid;
 static pid_t			child_pid			= -1;
 static bool			null_run			=  false;
 static int			detailed_run			=  0;
@@ -296,7 +296,7 @@
 	if (system_wide)
 		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus,
 						group, group_fd);
-	if (target_pid == -1 && target_tid == -1) {
+	if (!target_pid && !target_tid && (!group || evsel == first)) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
@@ -446,7 +446,7 @@
 			exit(-1);
 		}
 
-		if (target_tid == -1 && target_pid == -1 && !system_wide)
+		if (!target_tid && !target_pid && !system_wide)
 			evsel_list->threads->map[0] = child_pid;
 
 		/*
@@ -576,6 +576,8 @@
 	if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
 		fprintf(output, " # %8.3f CPUs utilized          ",
 			avg / avg_stats(&walltime_nsecs_stats));
+	else
+		fprintf(output, "                                   ");
 }
 
 /* used for get_ratio_color() */
@@ -844,12 +846,18 @@
 
 		fprintf(output, " # %8.3f GHz                    ", ratio);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
+		char unit = 'M';
+
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
 		if (total)
 			ratio = 1000.0 * avg / total;
+		if (ratio < 0.001) {
+			ratio *= 1000;
+			unit = 'K';
+		}
 
-		fprintf(output, " # %8.3f M/sec                  ", ratio);
+		fprintf(output, " # %8.3f %c/sec                  ", ratio, unit);
 	} else {
 		fprintf(output, "                                   ");
 	}
@@ -960,14 +968,14 @@
 	if (!csv_output) {
 		fprintf(output, "\n");
 		fprintf(output, " Performance counter stats for ");
-		if(target_pid == -1 && target_tid == -1) {
+		if (!target_pid && !target_tid) {
 			fprintf(output, "\'%s", argv[0]);
 			for (i = 1; i < argc; i++)
 				fprintf(output, " %s", argv[i]);
-		} else if (target_pid != -1)
-			fprintf(output, "process id \'%d", target_pid);
+		} else if (target_pid)
+			fprintf(output, "process id \'%s", target_pid);
 		else
-			fprintf(output, "thread id \'%d", target_tid);
+			fprintf(output, "thread id \'%s", target_tid);
 
 		fprintf(output, "\'");
 		if (run_count > 1)
@@ -1041,10 +1049,10 @@
 		     "event filter", parse_filter),
 	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
 		    "child tasks do not inherit counters"),
-	OPT_INTEGER('p', "pid", &target_pid,
-		    "stat events on existing process id"),
-	OPT_INTEGER('t', "tid", &target_tid,
-		    "stat events on existing thread id"),
+	OPT_STRING('p', "pid", &target_pid, "pid",
+		   "stat events on existing process id"),
+	OPT_STRING('t', "tid", &target_tid, "tid",
+		   "stat events on existing thread id"),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_BOOLEAN('g', "group", &group,
@@ -1182,7 +1190,7 @@
 	} else if (big_num_opt == 0) /* User passed --no-big-num */
 		big_num = false;
 
-	if (!argc && target_pid == -1 && target_tid == -1)
+	if (!argc && !target_pid && !target_tid)
 		usage_with_options(stat_usage, options);
 	if (run_count <= 0)
 		usage_with_options(stat_usage, options);
@@ -1198,10 +1206,11 @@
 	if (add_default_attributes())
 		goto out;
 
-	if (target_pid != -1)
+	if (target_pid)
 		target_tid = target_pid;
 
-	evsel_list->threads = thread_map__new(target_pid, target_tid);
+	evsel_list->threads = thread_map__new_str(target_pid,
+						  target_tid, UINT_MAX);
 	if (evsel_list->threads == NULL) {
 		pr_err("Problems finding threads of monitor\n");
 		usage_with_options(stat_usage, options);
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 3854e86..8687423 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -13,8 +13,11 @@
 #include "util/parse-events.h"
 #include "util/symbol.h"
 #include "util/thread_map.h"
+#include "util/pmu.h"
 #include "../../include/linux/hw_breakpoint.h"
 
+#include <sys/mman.h>
+
 static int vmlinux_matches_kallsyms_filter(struct map *map __used, struct symbol *sym)
 {
 	bool *visited = symbol__priv(sym);
@@ -276,7 +279,7 @@
 		return -1;
 	}
 
-	threads = thread_map__new(-1, getpid());
+	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	if (threads == NULL) {
 		pr_debug("thread_map__new\n");
 		return -1;
@@ -342,7 +345,7 @@
 		return -1;
 	}
 
-	threads = thread_map__new(-1, getpid());
+	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	if (threads == NULL) {
 		pr_debug("thread_map__new\n");
 		return -1;
@@ -490,7 +493,7 @@
 		expected_nr_events[i] = random() % 257;
 	}
 
-	threads = thread_map__new(-1, getpid());
+	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	if (threads == NULL) {
 		pr_debug("thread_map__new\n");
 		return -1;
@@ -648,7 +651,7 @@
 
 	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
-	TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong config", 0x1a == evsel->attr.config);
 	return 0;
 }
 
@@ -675,6 +678,24 @@
 	return 0;
 }
 
+static int test__checkevent_symbolic_name_config(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong period",
+			100000 == evsel->attr.sample_period);
+	TEST_ASSERT_VAL("wrong config1",
+			0 == evsel->attr.config1);
+	TEST_ASSERT_VAL("wrong config2",
+			1 == evsel->attr.config2);
+	return 0;
+}
+
 static int test__checkevent_symbolic_alias(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = list_entry(evlist->entries.next,
@@ -856,6 +877,22 @@
 	return test__checkevent_genhw(evlist);
 }
 
+static int test__checkevent_pmu(struct perf_evlist *evlist)
+{
+
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",    10 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong config1",    1 == evsel->attr.config1);
+	TEST_ASSERT_VAL("wrong config2",    3 == evsel->attr.config2);
+	TEST_ASSERT_VAL("wrong period",  1000 == evsel->attr.sample_period);
+
+	return 0;
+}
+
 static struct test__event_st {
 	const char *name;
 	__u32 type;
@@ -870,7 +907,7 @@
 		.check = test__checkevent_tracepoint_multi,
 	},
 	{
-		.name  = "r1",
+		.name  = "r1a",
 		.check = test__checkevent_raw,
 	},
 	{
@@ -882,6 +919,10 @@
 		.check = test__checkevent_symbolic_name,
 	},
 	{
+		.name  = "cycles/period=100000,config2/",
+		.check = test__checkevent_symbolic_name_config,
+	},
+	{
 		.name  = "faults",
 		.check = test__checkevent_symbolic_alias,
 	},
@@ -914,7 +955,7 @@
 		.check = test__checkevent_tracepoint_multi_modifier,
 	},
 	{
-		.name  = "r1:kp",
+		.name  = "r1a:kp",
 		.check = test__checkevent_raw_modifier,
 	},
 	{
@@ -933,6 +974,10 @@
 		.name  = "L1-dcache-load-miss:kp",
 		.check = test__checkevent_genhw_modifier,
 	},
+	{
+		.name  = "cpu/config=10,config1,config2=3,period=1000/u",
+		.check = test__checkevent_pmu,
+	},
 };
 
 #define TEST__EVENTS_CNT (sizeof(test__events) / sizeof(struct test__event_st))
@@ -1008,12 +1053,9 @@
 static int test__PERF_RECORD(void)
 {
 	struct perf_record_opts opts = {
-		.target_pid = -1,
-		.target_tid = -1,
 		.no_delay   = true,
 		.freq	    = 10,
 		.mmap_pages = 256,
-		.sample_id_all_avail = true,
 	};
 	cpu_set_t *cpu_mask = NULL;
 	size_t cpu_mask_size = 0;
@@ -1054,7 +1096,7 @@
 	 * we're monitoring, the one forked there.
 	 */
 	err = perf_evlist__create_maps(evlist, opts.target_pid,
-				       opts.target_tid, opts.cpu_list);
+				       opts.target_tid, UINT_MAX, opts.cpu_list);
 	if (err < 0) {
 		pr_debug("Not enough memory to create thread/cpu maps\n");
 		goto out_delete_evlist;
@@ -1296,6 +1338,178 @@
 	return (err < 0 || errs > 0) ? -1 : 0;
 }
 
+
+#if defined(__x86_64__) || defined(__i386__)
+
+#define barrier() asm volatile("" ::: "memory")
+
+static u64 rdpmc(unsigned int counter)
+{
+	unsigned int low, high;
+
+	asm volatile("rdpmc" : "=a" (low), "=d" (high) : "c" (counter));
+
+	return low | ((u64)high) << 32;
+}
+
+static u64 rdtsc(void)
+{
+	unsigned int low, high;
+
+	asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+	return low | ((u64)high) << 32;
+}
+
+static u64 mmap_read_self(void *addr)
+{
+	struct perf_event_mmap_page *pc = addr;
+	u32 seq, idx, time_mult = 0, time_shift = 0;
+	u64 count, cyc = 0, time_offset = 0, enabled, running, delta;
+
+	do {
+		seq = pc->lock;
+		barrier();
+
+		enabled = pc->time_enabled;
+		running = pc->time_running;
+
+		if (enabled != running) {
+			cyc = rdtsc();
+			time_mult = pc->time_mult;
+			time_shift = pc->time_shift;
+			time_offset = pc->time_offset;
+		}
+
+		idx = pc->index;
+		count = pc->offset;
+		if (idx)
+			count += rdpmc(idx - 1);
+
+		barrier();
+	} while (pc->lock != seq);
+
+	if (enabled != running) {
+		u64 quot, rem;
+
+		quot = (cyc >> time_shift);
+		rem = cyc & ((1 << time_shift) - 1);
+		delta = time_offset + quot * time_mult +
+			((rem * time_mult) >> time_shift);
+
+		enabled += delta;
+		if (idx)
+			running += delta;
+
+		quot = count / running;
+		rem = count % running;
+		count = quot * enabled + (rem * enabled) / running;
+	}
+
+	return count;
+}
+
+/*
+ * If the RDPMC instruction faults then signal this back to the test parent task:
+ */
+static void segfault_handler(int sig __used, siginfo_t *info __used, void *uc __used)
+{
+	exit(-1);
+}
+
+static int __test__rdpmc(void)
+{
+	long page_size = sysconf(_SC_PAGE_SIZE);
+	volatile int tmp = 0;
+	u64 i, loops = 1000;
+	int n;
+	int fd;
+	void *addr;
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_INSTRUCTIONS,
+		.exclude_kernel = 1,
+	};
+	u64 delta_sum = 0;
+        struct sigaction sa;
+
+	sigfillset(&sa.sa_mask);
+	sa.sa_sigaction = segfault_handler;
+	sigaction(SIGSEGV, &sa, NULL);
+
+	fprintf(stderr, "\n\n");
+
+	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+	if (fd < 0) {
+		die("Error: sys_perf_event_open() syscall returned "
+		    "with %d (%s)\n", fd, strerror(errno));
+	}
+
+	addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0);
+	if (addr == (void *)(-1)) {
+		die("Error: mmap() syscall returned "
+		    "with (%s)\n", strerror(errno));
+	}
+
+	for (n = 0; n < 6; n++) {
+		u64 stamp, now, delta;
+
+		stamp = mmap_read_self(addr);
+
+		for (i = 0; i < loops; i++)
+			tmp++;
+
+		now = mmap_read_self(addr);
+		loops *= 10;
+
+		delta = now - stamp;
+		fprintf(stderr, "%14d: %14Lu\n", n, (long long)delta);
+
+		delta_sum += delta;
+	}
+
+	munmap(addr, page_size);
+	close(fd);
+
+	fprintf(stderr, "   ");
+
+	if (!delta_sum)
+		return -1;
+
+	return 0;
+}
+
+static int test__rdpmc(void)
+{
+	int status = 0;
+	int wret = 0;
+	int ret;
+	int pid;
+
+	pid = fork();
+	if (pid < 0)
+		return -1;
+
+	if (!pid) {
+		ret = __test__rdpmc();
+
+		exit(ret);
+	}
+
+	wret = waitpid(pid, &status, 0);
+	if (wret < 0 || status)
+		return -1;
+
+	return 0;
+}
+
+#endif
+
+static int test__perf_pmu(void)
+{
+	return perf_pmu__test();
+}
+
 static struct test {
 	const char *desc;
 	int (*func)(void);
@@ -1320,11 +1534,21 @@
 		.desc = "parse events tests",
 		.func = test__parse_events,
 	},
+#if defined(__x86_64__) || defined(__i386__)
+	{
+		.desc = "x86 rdpmc test",
+		.func = test__rdpmc,
+	},
+#endif
 	{
 		.desc = "Validate PERF_RECORD_* events & perf_sample fields",
 		.func = test__PERF_RECORD,
 	},
 	{
+		.desc = "Test perf pmu format parsing",
+		.func = test__perf_pmu,
+	},
+	{
 		.func = NULL,
 	},
 };
@@ -1412,7 +1636,5 @@
 	if (symbol__init() < 0)
 		return -1;
 
-	setup_pager();
-
 	return __cmd_test(argc, argv);
 }
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ecff312..e3c63ae 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -64,7 +64,6 @@
 #include <linux/unistd.h>
 #include <linux/types.h>
 
-
 void get_term_dimensions(struct winsize *ws)
 {
 	char *s = getenv("LINES");
@@ -544,10 +543,20 @@
 
 static void *display_thread_tui(void *arg)
 {
+	struct perf_evsel *pos;
 	struct perf_top *top = arg;
 	const char *help = "For a higher level overview, try: perf top --sort comm,dso";
 
 	perf_top__sort_new_samples(top);
+
+	/*
+	 * Initialize the uid_filter_str, in the future the TUI will allow
+	 * Zooming in/out UIDs. For now juse use whatever the user passed
+	 * via --uid.
+	 */
+	list_for_each_entry(pos, &top->evlist->entries, node)
+		pos->hists.uid_filter_str = top->uid_str;
+
 	perf_evlist__tui_browse_hists(top->evlist, help,
 				      perf_top__sort_new_samples,
 				      top, top->delay_secs);
@@ -668,6 +677,12 @@
 		return;
 	}
 
+	if (!machine) {
+		pr_err("%u unprocessable samples recorded.",
+		       top->session->hists.stats.nr_unprocessable_samples++);
+		return;
+	}
+
 	if (event->header.misc & PERF_RECORD_MISC_EXACT_IP)
 		top->exact_samples++;
 
@@ -861,7 +876,7 @@
 		if (top->exclude_guest_missing)
 			attr->exclude_guest = attr->exclude_host = 0;
 retry_sample_id:
-		attr->sample_id_all = top->sample_id_all_avail ? 1 : 0;
+		attr->sample_id_all = top->sample_id_all_missing ? 0 : 1;
 try_again:
 		if (perf_evsel__open(counter, top->evlist->cpus,
 				     top->evlist->threads, top->group,
@@ -878,11 +893,11 @@
 						 "guest or host samples.\n");
 					top->exclude_guest_missing = true;
 					goto fallback_missing_features;
-				} else if (top->sample_id_all_avail) {
+				} else if (!top->sample_id_all_missing) {
 					/*
 					 * Old kernel, no attr->sample_id_type_all field
 					 */
-					top->sample_id_all_avail = false;
+					top->sample_id_all_missing = true;
 					goto retry_sample_id;
 				}
 			}
@@ -967,7 +982,7 @@
 	if (ret)
 		goto out_delete;
 
-	if (top->target_tid != -1)
+	if (top->target_tid || top->uid != UINT_MAX)
 		perf_event__synthesize_thread_map(&top->tool, top->evlist->threads,
 						  perf_event__process,
 						  &top->session->host_machine);
@@ -1105,10 +1120,8 @@
 	struct perf_top top = {
 		.count_filter	     = 5,
 		.delay_secs	     = 2,
-		.target_pid	     = -1,
-		.target_tid	     = -1,
+		.uid		     = UINT_MAX,
 		.freq		     = 1000, /* 1 KHz */
-		.sample_id_all_avail = true,
 		.mmap_pages	     = 128,
 		.sym_pcnt_filter     = 5,
 	};
@@ -1119,9 +1132,9 @@
 		     parse_events_option),
 	OPT_INTEGER('c', "count", &top.default_interval,
 		    "event period to sample"),
-	OPT_INTEGER('p', "pid", &top.target_pid,
+	OPT_STRING('p', "pid", &top.target_pid, "pid",
 		    "profile events on existing process id"),
-	OPT_INTEGER('t', "tid", &top.target_tid,
+	OPT_STRING('t', "tid", &top.target_tid, "tid",
 		    "profile events on existing thread id"),
 	OPT_BOOLEAN('a', "all-cpus", &top.system_wide,
 			    "system-wide collection from all CPUs"),
@@ -1180,6 +1193,7 @@
 		    "Display raw encoding of assembly instructions (default)"),
 	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
+	OPT_STRING('u', "uid", &top.uid_str, "user", "user to profile"),
 	OPT_END()
 	};
 
@@ -1205,18 +1219,22 @@
 
 	setup_browser(false);
 
+	top.uid = parse_target_uid(top.uid_str, top.target_tid, top.target_pid);
+	if (top.uid_str != NULL && top.uid == UINT_MAX - 1)
+		goto out_delete_evlist;
+
 	/* CPU and PID are mutually exclusive */
-	if (top.target_tid > 0 && top.cpu_list) {
+	if (top.target_tid && top.cpu_list) {
 		printf("WARNING: PID switch overriding CPU\n");
 		sleep(1);
 		top.cpu_list = NULL;
 	}
 
-	if (top.target_pid != -1)
+	if (top.target_pid)
 		top.target_tid = top.target_pid;
 
 	if (perf_evlist__create_maps(top.evlist, top.target_pid,
-				     top.target_tid, top.cpu_list) < 0)
+				     top.target_tid, top.uid, top.cpu_list) < 0)
 		usage_with_options(top_usage, options);
 
 	if (!top.evlist->nr_entries &&
@@ -1280,6 +1298,7 @@
 
 	status = __cmd_top(&top);
 
+out_delete_evlist:
 	perf_evlist__delete(top.evlist);
 
 	return status;
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index 6170fd2..d9084e0 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -65,6 +65,21 @@
 endef
 endif
 
+ifndef NO_GTK2
+define SOURCE_GTK2
+#pragma GCC diagnostic ignored \"-Wstrict-prototypes\"
+#include <gtk/gtk.h>
+#pragma GCC diagnostic error \"-Wstrict-prototypes\"
+
+int main(int argc, char *argv[])
+{
+        gtk_init(&argc, &argv);
+
+        return 0;
+}
+endef
+endif
+
 ifndef NO_LIBPERL
 define SOURCE_PERL_EMBED
 #include <EXTERN.h>
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 3afa39a..89e3355 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -173,7 +173,6 @@
 		      pid_t pid, int cpu, int group_fd,
 		      unsigned long flags)
 {
-	attr->size = sizeof(*attr);
 	return syscall(__NR_perf_event_open, attr, pid, cpu,
 		       group_fd, flags);
 }
@@ -186,14 +185,32 @@
 	u64 ips[0];
 };
 
+struct branch_flags {
+	u64 mispred:1;
+	u64 predicted:1;
+	u64 reserved:62;
+};
+
+struct branch_entry {
+	u64				from;
+	u64				to;
+	struct branch_flags flags;
+};
+
+struct branch_stack {
+	u64				nr;
+	struct branch_entry	entries[0];
+};
+
 extern bool perf_host, perf_guest;
 extern const char perf_version_string[];
 
 void pthread__unblock_sigwinch(void);
 
 struct perf_record_opts {
-	pid_t	     target_pid;
-	pid_t	     target_tid;
+	const char   *target_pid;
+	const char   *target_tid;
+	uid_t	     uid;
 	bool	     call_graph;
 	bool	     group;
 	bool	     inherit_stat;
@@ -204,13 +221,14 @@
 	bool	     raw_samples;
 	bool	     sample_address;
 	bool	     sample_time;
-	bool	     sample_id_all_avail;
+	bool	     sample_id_all_missing;
 	bool	     exclude_guest_missing;
 	bool	     system_wide;
 	bool	     period;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int user_freq;
+	int	     branch_stack;
 	u64	     default_interval;
 	u64	     user_interval;
 	const char   *cpu_list;
diff --git a/tools/perf/python/twatch.py b/tools/perf/python/twatch.py
index df638c4..b11cca5 100755
--- a/tools/perf/python/twatch.py
+++ b/tools/perf/python/twatch.py
@@ -19,7 +19,7 @@
 	cpus = perf.cpu_map()
 	threads = perf.thread_map()
 	evsel = perf.evsel(task = 1, comm = 1, mmap = 0,
-			   wakeup_events = 1, sample_period = 1,
+			   wakeup_events = 1, watermark = 1,
 			   sample_id_all = 1,
 			   sample_type = perf.SAMPLE_PERIOD | perf.SAMPLE_TID | perf.SAMPLE_CPU | perf.SAMPLE_TID)
 	evsel.open(cpus = cpus, threads = threads);
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 011ed26..e5a462f 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -315,7 +315,7 @@
 		       "Please use:\n\n"
 		       "  perf buildid-cache -av vmlinux\n\n"
 		       "or:\n\n"
-		       "  --vmlinux vmlinux",
+		       "  --vmlinux vmlinux\n",
 		       sym->name, build_id_msg ?: "");
 		goto out_free_filename;
 	}
diff --git a/tools/perf/util/bitmap.c b/tools/perf/util/bitmap.c
index 5e230ac..0a1adc1 100644
--- a/tools/perf/util/bitmap.c
+++ b/tools/perf/util/bitmap.c
@@ -19,3 +19,13 @@
 
 	return w;
 }
+
+void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
+		 const unsigned long *bitmap2, int bits)
+{
+	int k;
+	int nr = BITS_TO_LONGS(bits);
+
+	for (k = 0; k < nr; k++)
+		dst[k] = bitmap1[k] | bitmap2[k];
+}
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index fc5e5a0..8dd224d 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -45,6 +45,18 @@
 void exit_browser(bool wait_for_ok);
 #endif
 
+#ifdef NO_GTK2_SUPPORT
+static inline void perf_gtk_setup_browser(int argc __used, const char *argv[] __used, bool fallback_to_pager)
+{
+	if (fallback_to_pager)
+		setup_pager();
+}
+static inline void perf_gtk_exit_browser(bool wait_for_ok __used) {}
+#else
+void perf_gtk_setup_browser(int argc, const char *argv[], bool fallback_to_pager);
+void perf_gtk_exit_browser(bool wait_for_ok);
+#endif
+
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
 
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 6893eec..adc72f0 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -166,6 +166,17 @@
 	return cpus;
 }
 
+size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp)
+{
+	int i;
+	size_t printed = fprintf(fp, "%d cpu%s: ",
+				 map->nr, map->nr > 1 ? "s" : "");
+	for (i = 0; i < map->nr; ++i)
+		printed += fprintf(fp, "%s%d", i ? ", " : "", map->map[i]);
+
+	return printed + fprintf(fp, "\n");
+}
+
 struct cpu_map *cpu_map__dummy_new(void)
 {
 	struct cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int));
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 072c0a3..c415185 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -1,6 +1,8 @@
 #ifndef __PERF_CPUMAP_H
 #define __PERF_CPUMAP_H
 
+#include <stdio.h>
+
 struct cpu_map {
 	int nr;
 	int map[];
@@ -10,4 +12,6 @@
 struct cpu_map *cpu_map__dummy_new(void);
 void cpu_map__delete(struct cpu_map *map);
 
+size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
+
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c
index 3507362..aada3ac 100644
--- a/tools/perf/util/ctype.c
+++ b/tools/perf/util/ctype.c
@@ -3,7 +3,7 @@
  *
  * No surprises, and works with signed and unsigned chars.
  */
-#include "cache.h"
+#include "util.h"
 
 enum {
 	S = GIT_SPACE,
diff --git a/tools/perf/util/debugfs.c b/tools/perf/util/debugfs.c
index ffc35e7..dd8b193 100644
--- a/tools/perf/util/debugfs.c
+++ b/tools/perf/util/debugfs.c
@@ -15,32 +15,6 @@
 	0,
 };
 
-/* use this to force a umount */
-void debugfs_force_cleanup(void)
-{
-	debugfs_find_mountpoint();
-	debugfs_premounted = 0;
-	debugfs_umount();
-}
-
-/* construct a full path to a debugfs element */
-int debugfs_make_path(const char *element, char *buffer, int size)
-{
-	int len;
-
-	if (strlen(debugfs_mountpoint) == 0) {
-		buffer[0] = '\0';
-		return -1;
-	}
-
-	len = strlen(debugfs_mountpoint) + strlen(element) + 1;
-	if (len >= size)
-		return len+1;
-
-	snprintf(buffer, size-1, "%s/%s", debugfs_mountpoint, element);
-	return 0;
-}
-
 static int debugfs_found;
 
 /* find the path to the mounted debugfs */
@@ -97,17 +71,6 @@
 	return 0;
 }
 
-
-int debugfs_valid_entry(const char *path)
-{
-	struct stat st;
-
-	if (stat(path, &st))
-		return -errno;
-
-	return 0;
-}
-
 static void debugfs_set_tracing_events_path(const char *mountpoint)
 {
 	snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s",
@@ -149,107 +112,3 @@
 	snprintf(debugfs_mountpoint, sizeof(debugfs_mountpoint), "%s", mountpoint);
 	debugfs_set_tracing_events_path(mountpoint);
 }
-
-/* umount the debugfs */
-
-int debugfs_umount(void)
-{
-	char umountcmd[128];
-	int ret;
-
-	/* if it was already mounted, leave it */
-	if (debugfs_premounted)
-		return 0;
-
-	/* make sure it's a valid mount point */
-	ret = debugfs_valid_mountpoint(debugfs_mountpoint);
-	if (ret)
-		return ret;
-
-	snprintf(umountcmd, sizeof(umountcmd),
-		 "/bin/umount %s", debugfs_mountpoint);
-	return system(umountcmd);
-}
-
-int debugfs_write(const char *entry, const char *value)
-{
-	char path[PATH_MAX + 1];
-	int ret, count;
-	int fd;
-
-	/* construct the path */
-	snprintf(path, sizeof(path), "%s/%s", debugfs_mountpoint, entry);
-
-	/* verify that it exists */
-	ret = debugfs_valid_entry(path);
-	if (ret)
-		return ret;
-
-	/* get how many chars we're going to write */
-	count = strlen(value);
-
-	/* open the debugfs entry */
-	fd = open(path, O_RDWR);
-	if (fd < 0)
-		return -errno;
-
-	while (count > 0) {
-		/* write it */
-		ret = write(fd, value, count);
-		if (ret <= 0) {
-			if (ret == EAGAIN)
-				continue;
-			close(fd);
-			return -errno;
-		}
-		count -= ret;
-	}
-
-	/* close it */
-	close(fd);
-
-	/* return success */
-	return 0;
-}
-
-/*
- * read a debugfs entry
- * returns the number of chars read or a negative errno
- */
-int debugfs_read(const char *entry, char *buffer, size_t size)
-{
-	char path[PATH_MAX + 1];
-	int ret;
-	int fd;
-
-	/* construct the path */
-	snprintf(path, sizeof(path), "%s/%s", debugfs_mountpoint, entry);
-
-	/* verify that it exists */
-	ret = debugfs_valid_entry(path);
-	if (ret)
-		return ret;
-
-	/* open the debugfs entry */
-	fd = open(path, O_RDONLY);
-	if (fd < 0)
-		return -errno;
-
-	do {
-		/* read it */
-		ret = read(fd, buffer, size);
-		if (ret == 0) {
-			close(fd);
-			return EOF;
-		}
-	} while (ret < 0 && errno == EAGAIN);
-
-	/* close it */
-	close(fd);
-
-	/* make *sure* there's a null character at the end */
-	buffer[ret] = '\0';
-
-	/* return the number of chars read */
-	return ret;
-}
diff --git a/tools/perf/util/debugfs.h b/tools/perf/util/debugfs.h
index 4a878f7..68f3e87 100644
--- a/tools/perf/util/debugfs.h
+++ b/tools/perf/util/debugfs.h
@@ -3,14 +3,8 @@
 
 const char *debugfs_find_mountpoint(void);
 int debugfs_valid_mountpoint(const char *debugfs);
-int debugfs_valid_entry(const char *path);
 char *debugfs_mount(const char *mountpoint);
-int debugfs_umount(void);
 void debugfs_set_path(const char *mountpoint);
-int debugfs_write(const char *entry, const char *value);
-int debugfs_read(const char *entry, char *buffer, size_t size);
-void debugfs_force_cleanup(void);
-int debugfs_make_path(const char *element, char *buffer, int size);
 
 extern char debugfs_mountpoint[];
 extern char tracing_events_path[];
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index cbdeaad..1b19728 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -81,6 +81,7 @@
 	u32 raw_size;
 	void *raw_data;
 	struct ip_callchain *callchain;
+	struct branch_stack *branch_stack;
 };
 
 #define BUILD_ID_SIZE 20
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index ea32a06..1986d80 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -51,13 +51,15 @@
 void perf_evlist__config_attrs(struct perf_evlist *evlist,
 			       struct perf_record_opts *opts)
 {
-	struct perf_evsel *evsel;
+	struct perf_evsel *evsel, *first;
 
 	if (evlist->cpus->map[0] < 0)
 		opts->no_inherit = true;
 
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
 	list_for_each_entry(evsel, &evlist->entries, node) {
-		perf_evsel__config(evsel, opts);
+		perf_evsel__config(evsel, opts, first);
 
 		if (evlist->nr_entries > 1)
 			evsel->attr.sample_type |= PERF_SAMPLE_ID;
@@ -97,9 +99,9 @@
 	++evlist->nr_entries;
 }
 
-static void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
-					  struct list_head *list,
-					  int nr_entries)
+void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
+				   struct list_head *list,
+				   int nr_entries)
 {
 	list_splice_tail(list, &evlist->entries);
 	evlist->nr_entries += nr_entries;
@@ -597,15 +599,15 @@
 	return perf_evlist__mmap_per_cpu(evlist, prot, mask);
 }
 
-int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
-			     pid_t target_tid, const char *cpu_list)
+int perf_evlist__create_maps(struct perf_evlist *evlist, const char *target_pid,
+			     const char *target_tid, uid_t uid, const char *cpu_list)
 {
-	evlist->threads = thread_map__new(target_pid, target_tid);
+	evlist->threads = thread_map__new_str(target_pid, target_tid, uid);
 
 	if (evlist->threads == NULL)
 		return -1;
 
-	if (cpu_list == NULL && target_tid != -1)
+	if (uid != UINT_MAX || (cpu_list == NULL && target_tid))
 		evlist->cpus = cpu_map__dummy_new();
 	else
 		evlist->cpus = cpu_map__new(cpu_list);
@@ -765,6 +767,7 @@
 	list_for_each_entry_reverse(evsel, &evlist->entries, node)
 		perf_evsel__close(evsel, ncpus, nthreads);
 
+	errno = -err;
 	return err;
 }
 
@@ -824,7 +827,7 @@
 		exit(-1);
 	}
 
-	if (!opts->system_wide && opts->target_tid == -1 && opts->target_pid == -1)
+	if (!opts->system_wide && !opts->target_tid && !opts->target_pid)
 		evlist->threads->map[0] = evlist->workload.pid;
 
 	close(child_ready_pipe[1]);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 8922aee..21f1c9e 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -106,8 +106,8 @@
 	evlist->threads	= threads;
 }
 
-int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
-			     pid_t target_tid, const char *cpu_list);
+int perf_evlist__create_maps(struct perf_evlist *evlist, const char *target_pid,
+			     const char *tid, uid_t uid, const char *cpu_list);
 void perf_evlist__delete_maps(struct perf_evlist *evlist);
 int perf_evlist__set_filters(struct perf_evlist *evlist);
 
@@ -117,4 +117,9 @@
 
 bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
 bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
+
+void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
+				   struct list_head *list,
+				   int nr_entries);
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7132ee8..0221700 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -63,12 +63,13 @@
 	return evsel;
 }
 
-void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
+void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts,
+			struct perf_evsel *first)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
 
-	attr->sample_id_all = opts->sample_id_all_avail ? 1 : 0;
+	attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1;
 	attr->inherit	    = !opts->no_inherit;
 	attr->read_format   = PERF_FORMAT_TOTAL_TIME_ENABLED |
 			      PERF_FORMAT_TOTAL_TIME_RUNNING |
@@ -111,7 +112,7 @@
 	if (opts->period)
 		attr->sample_type	|= PERF_SAMPLE_PERIOD;
 
-	if (opts->sample_id_all_avail &&
+	if (!opts->sample_id_all_missing &&
 	    (opts->sample_time || opts->system_wide ||
 	     !opts->no_inherit || opts->cpu_list))
 		attr->sample_type	|= PERF_SAMPLE_TIME;
@@ -126,11 +127,16 @@
 		attr->watermark = 0;
 		attr->wakeup_events = 1;
 	}
+	if (opts->branch_stack) {
+		attr->sample_type	|= PERF_SAMPLE_BRANCH_STACK;
+		attr->branch_sample_type = opts->branch_stack;
+	}
 
 	attr->mmap = track;
 	attr->comm = track;
 
-	if (opts->target_pid == -1 && opts->target_tid == -1 && !opts->system_wide) {
+	if (!opts->target_pid && !opts->target_tid && !opts->system_wide &&
+	    (!opts->group || evsel == first)) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
@@ -536,7 +542,7 @@
 	}
 
 	if (type & PERF_SAMPLE_READ) {
-		fprintf(stderr, "PERF_SAMPLE_READ is unsuported for now\n");
+		fprintf(stderr, "PERF_SAMPLE_READ is unsupported for now\n");
 		return -1;
 	}
 
@@ -576,6 +582,16 @@
 		data->raw_data = (void *) pdata;
 	}
 
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		u64 sz;
+
+		data->branch_stack = (struct branch_stack *)array;
+		array++; /* nr */
+
+		sz = data->branch_stack->nr * sizeof(struct branch_entry);
+		sz /= sizeof(u64);
+		array += sz;
+	}
 	return 0;
 }
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 326b8e4..3158ca3 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -80,7 +80,8 @@
 void perf_evsel__delete(struct perf_evsel *evsel);
 
 void perf_evsel__config(struct perf_evsel *evsel,
-			struct perf_record_opts *opts);
+			struct perf_record_opts *opts,
+			struct perf_evsel *first);
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
diff --git a/tools/perf/util/gtk/browser.c b/tools/perf/util/gtk/browser.c
new file mode 100644
index 0000000..258352a
--- /dev/null
+++ b/tools/perf/util/gtk/browser.c
@@ -0,0 +1,189 @@
+#include "../evlist.h"
+#include "../cache.h"
+#include "../evsel.h"
+#include "../sort.h"
+#include "../hist.h"
+#include "gtk.h"
+
+#include <signal.h>
+
+#define MAX_COLUMNS			32
+
+void perf_gtk_setup_browser(int argc, const char *argv[],
+			    bool fallback_to_pager __used)
+{
+	gtk_init(&argc, (char ***)&argv);
+}
+
+void perf_gtk_exit_browser(bool wait_for_ok __used)
+{
+	gtk_main_quit();
+}
+
+static void perf_gtk_signal(int sig)
+{
+	psignal(sig, "perf");
+	gtk_main_quit();
+}
+
+static void perf_gtk_resize_window(GtkWidget *window)
+{
+	GdkRectangle rect;
+	GdkScreen *screen;
+	int monitor;
+	int height;
+	int width;
+
+	screen = gtk_widget_get_screen(window);
+
+	monitor = gdk_screen_get_monitor_at_window(screen, window->window);
+
+	gdk_screen_get_monitor_geometry(screen, monitor, &rect);
+
+	width	= rect.width * 3 / 4;
+	height	= rect.height * 3 / 4;
+
+	gtk_window_resize(GTK_WINDOW(window), width, height);
+}
+
+static void perf_gtk_show_hists(GtkWidget *window, struct hists *hists)
+{
+	GType col_types[MAX_COLUMNS];
+	GtkCellRenderer *renderer;
+	struct sort_entry *se;
+	GtkListStore *store;
+	struct rb_node *nd;
+	u64 total_period;
+	GtkWidget *view;
+	int col_idx;
+	int nr_cols;
+
+	nr_cols = 0;
+
+	/* The percentage column */
+	col_types[nr_cols++] = G_TYPE_STRING;
+
+	list_for_each_entry(se, &hist_entry__sort_list, list) {
+		if (se->elide)
+			continue;
+
+		col_types[nr_cols++] = G_TYPE_STRING;
+	}
+
+	store = gtk_list_store_newv(nr_cols, col_types);
+
+	view = gtk_tree_view_new();
+
+	renderer = gtk_cell_renderer_text_new();
+
+	col_idx = 0;
+
+	/* The percentage column */
+	gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+						    -1, "Overhead (%)",
+						    renderer, "text",
+						    col_idx++, NULL);
+
+	list_for_each_entry(se, &hist_entry__sort_list, list) {
+		if (se->elide)
+			continue;
+
+		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+							    -1, se->se_header,
+							    renderer, "text",
+							    col_idx++, NULL);
+	}
+
+	gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
+
+	g_object_unref(GTK_TREE_MODEL(store));
+
+	total_period = hists->stats.total_period;
+
+	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		GtkTreeIter iter;
+		double percent;
+		char s[512];
+
+		if (h->filtered)
+			continue;
+
+		gtk_list_store_append(store, &iter);
+
+		col_idx = 0;
+
+		percent = (h->period * 100.0) / total_period;
+
+		snprintf(s, ARRAY_SIZE(s), "%.2f", percent);
+
+		gtk_list_store_set(store, &iter, col_idx++, s, -1);
+
+		list_for_each_entry(se, &hist_entry__sort_list, list) {
+			if (se->elide)
+				continue;
+
+			se->se_snprintf(h, s, ARRAY_SIZE(s),
+					hists__col_len(hists, se->se_width_idx));
+
+			gtk_list_store_set(store, &iter, col_idx++, s, -1);
+		}
+	}
+
+	gtk_container_add(GTK_CONTAINER(window), view);
+}
+
+int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
+				  const char *help __used,
+				  void (*timer) (void *arg)__used,
+				  void *arg __used, int delay_secs __used)
+{
+	struct perf_evsel *pos;
+	GtkWidget *notebook;
+	GtkWidget *window;
+
+	signal(SIGSEGV, perf_gtk_signal);
+	signal(SIGFPE,  perf_gtk_signal);
+	signal(SIGINT,  perf_gtk_signal);
+	signal(SIGQUIT, perf_gtk_signal);
+	signal(SIGTERM, perf_gtk_signal);
+
+	window = gtk_window_new(GTK_WINDOW_TOPLEVEL);
+
+	gtk_window_set_title(GTK_WINDOW(window), "perf report");
+
+	g_signal_connect(window, "delete_event", gtk_main_quit, NULL);
+
+	notebook = gtk_notebook_new();
+
+	list_for_each_entry(pos, &evlist->entries, node) {
+		struct hists *hists = &pos->hists;
+		const char *evname = event_name(pos);
+		GtkWidget *scrolled_window;
+		GtkWidget *tab_label;
+
+		scrolled_window = gtk_scrolled_window_new(NULL, NULL);
+
+		gtk_scrolled_window_set_policy(GTK_SCROLLED_WINDOW(scrolled_window),
+							GTK_POLICY_AUTOMATIC,
+							GTK_POLICY_AUTOMATIC);
+
+		perf_gtk_show_hists(scrolled_window, hists);
+
+		tab_label = gtk_label_new(evname);
+
+		gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, tab_label);
+	}
+
+	gtk_container_add(GTK_CONTAINER(window), notebook);
+
+	gtk_widget_show_all(window);
+
+	perf_gtk_resize_window(window);
+
+	gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER);
+
+	gtk_main();
+
+	return 0;
+}
diff --git a/tools/perf/util/gtk/gtk.h b/tools/perf/util/gtk/gtk.h
new file mode 100644
index 0000000..75177ee
--- /dev/null
+++ b/tools/perf/util/gtk/gtk.h
@@ -0,0 +1,8 @@
+#ifndef _PERF_GTK_H_
+#define _PERF_GTK_H_ 1
+
+#pragma GCC diagnostic ignored "-Wstrict-prototypes"
+#include <gtk/gtk.h>
+#pragma GCC diagnostic error "-Wstrict-prototypes"
+
+#endif /* _PERF_GTK_H_ */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 14bb035..fcd9cf3 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -63,9 +63,20 @@
 	return NULL;
 }
 
-static const char *__perf_magic = "PERFFILE";
+/*
+ * magic2 = "PERFILE2"
+ * must be a numerical value to let the endianness
+ * determine the memory layout. That way we are able
+ * to detect endianness when reading the perf.data file
+ * back.
+ *
+ * we check for legacy (PERFFILE) format.
+ */
+static const char *__perf_magic1 = "PERFFILE";
+static const u64 __perf_magic2    = 0x32454c4946524550ULL;
+static const u64 __perf_magic2_sw = 0x50455246494c4532ULL;
 
-#define PERF_MAGIC	(*(u64 *)__perf_magic)
+#define PERF_MAGIC	__perf_magic2
 
 struct perf_file_attr {
 	struct perf_event_attr	attr;
@@ -1012,6 +1023,12 @@
 	return do_write_string(fd, buffer);
 }
 
+static int write_branch_stack(int fd __used, struct perf_header *h __used,
+		       struct perf_evlist *evlist __used)
+{
+	return 0;
+}
+
 static void print_hostname(struct perf_header *ph, int fd, FILE *fp)
 {
 	char *str = do_read_string(fd, ph);
@@ -1133,8 +1150,9 @@
 	uint64_t id;
 	void *buf = NULL;
 	char *str;
-	u32 nre, sz, nr, i, j, msz;
-	int ret;
+	u32 nre, sz, nr, i, j;
+	ssize_t ret;
+	size_t msz;
 
 	/* number of events */
 	ret = read(fd, &nre, sizeof(nre));
@@ -1151,25 +1169,23 @@
 	if (ph->needs_swap)
 		sz = bswap_32(sz);
 
-	/*
-	 * ensure it is at least to our ABI rev
-	 */
-	if (sz < (u32)sizeof(attr))
-		goto error;
-
 	memset(&attr, 0, sizeof(attr));
 
-	/* read entire region to sync up to next field */
+	/* buffer to hold on file attr struct */
 	buf = malloc(sz);
 	if (!buf)
 		goto error;
 
 	msz = sizeof(attr);
-	if (sz < msz)
+	if (sz < (ssize_t)msz)
 		msz = sz;
 
 	for (i = 0 ; i < nre; i++) {
 
+		/*
+		 * must read entire on-file attr struct to
+		 * sync up with layout.
+		 */
 		ret = read(fd, buf, sz);
 		if (ret != (ssize_t)sz)
 			goto error;
@@ -1305,25 +1321,204 @@
 	free(str);
 }
 
+static void print_branch_stack(struct perf_header *ph __used, int fd __used,
+			       FILE *fp)
+{
+	fprintf(fp, "# contains samples with branch stack\n");
+}
+
+static int __event_process_build_id(struct build_id_event *bev,
+				    char *filename,
+				    struct perf_session *session)
+{
+	int err = -1;
+	struct list_head *head;
+	struct machine *machine;
+	u16 misc;
+	struct dso *dso;
+	enum dso_kernel_type dso_type;
+
+	machine = perf_session__findnew_machine(session, bev->pid);
+	if (!machine)
+		goto out;
+
+	misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+	switch (misc) {
+	case PERF_RECORD_MISC_KERNEL:
+		dso_type = DSO_TYPE_KERNEL;
+		head = &machine->kernel_dsos;
+		break;
+	case PERF_RECORD_MISC_GUEST_KERNEL:
+		dso_type = DSO_TYPE_GUEST_KERNEL;
+		head = &machine->kernel_dsos;
+		break;
+	case PERF_RECORD_MISC_USER:
+	case PERF_RECORD_MISC_GUEST_USER:
+		dso_type = DSO_TYPE_USER;
+		head = &machine->user_dsos;
+		break;
+	default:
+		goto out;
+	}
+
+	dso = __dsos__findnew(head, filename);
+	if (dso != NULL) {
+		char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+		dso__set_build_id(dso, &bev->build_id);
+
+		if (filename[0] == '[')
+			dso->kernel = dso_type;
+
+		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
+				  sbuild_id);
+		pr_debug("build id event received for %s: %s\n",
+			 dso->long_name, sbuild_id);
+	}
+
+	err = 0;
+out:
+	return err;
+}
+
+static int perf_header__read_build_ids_abi_quirk(struct perf_header *header,
+						 int input, u64 offset, u64 size)
+{
+	struct perf_session *session = container_of(header, struct perf_session, header);
+	struct {
+		struct perf_event_header   header;
+		u8			   build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))];
+		char			   filename[0];
+	} old_bev;
+	struct build_id_event bev;
+	char filename[PATH_MAX];
+	u64 limit = offset + size;
+
+	while (offset < limit) {
+		ssize_t len;
+
+		if (read(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev))
+			return -1;
+
+		if (header->needs_swap)
+			perf_event_header__bswap(&old_bev.header);
+
+		len = old_bev.header.size - sizeof(old_bev);
+		if (read(input, filename, len) != len)
+			return -1;
+
+		bev.header = old_bev.header;
+
+		/*
+		 * As the pid is the missing value, we need to fill
+		 * it properly. The header.misc value give us nice hint.
+		 */
+		bev.pid	= HOST_KERNEL_ID;
+		if (bev.header.misc == PERF_RECORD_MISC_GUEST_USER ||
+		    bev.header.misc == PERF_RECORD_MISC_GUEST_KERNEL)
+			bev.pid	= DEFAULT_GUEST_KERNEL_ID;
+
+		memcpy(bev.build_id, old_bev.build_id, sizeof(bev.build_id));
+		__event_process_build_id(&bev, filename, session);
+
+		offset += bev.header.size;
+	}
+
+	return 0;
+}
+
+static int perf_header__read_build_ids(struct perf_header *header,
+				       int input, u64 offset, u64 size)
+{
+	struct perf_session *session = container_of(header, struct perf_session, header);
+	struct build_id_event bev;
+	char filename[PATH_MAX];
+	u64 limit = offset + size, orig_offset = offset;
+	int err = -1;
+
+	while (offset < limit) {
+		ssize_t len;
+
+		if (read(input, &bev, sizeof(bev)) != sizeof(bev))
+			goto out;
+
+		if (header->needs_swap)
+			perf_event_header__bswap(&bev.header);
+
+		len = bev.header.size - sizeof(bev);
+		if (read(input, filename, len) != len)
+			goto out;
+		/*
+		 * The a1645ce1 changeset:
+		 *
+		 * "perf: 'perf kvm' tool for monitoring guest performance from host"
+		 *
+		 * Added a field to struct build_id_event that broke the file
+		 * format.
+		 *
+		 * Since the kernel build-id is the first entry, process the
+		 * table using the old format if the well known
+		 * '[kernel.kallsyms]' string for the kernel build-id has the
+		 * first 4 characters chopped off (where the pid_t sits).
+		 */
+		if (memcmp(filename, "nel.kallsyms]", 13) == 0) {
+			if (lseek(input, orig_offset, SEEK_SET) == (off_t)-1)
+				return -1;
+			return perf_header__read_build_ids_abi_quirk(header, input, offset, size);
+		}
+
+		__event_process_build_id(&bev, filename, session);
+
+		offset += bev.header.size;
+	}
+	err = 0;
+out:
+	return err;
+}
+
+static int process_trace_info(struct perf_file_section *section __unused,
+			      struct perf_header *ph __unused,
+			      int feat __unused, int fd)
+{
+	trace_report(fd, false);
+	return 0;
+}
+
+static int process_build_id(struct perf_file_section *section,
+			    struct perf_header *ph,
+			    int feat __unused, int fd)
+{
+	if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
+		pr_debug("Failed to read buildids, continuing...\n");
+	return 0;
+}
+
 struct feature_ops {
 	int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
 	void (*print)(struct perf_header *h, int fd, FILE *fp);
+	int (*process)(struct perf_file_section *section,
+		       struct perf_header *h, int feat, int fd);
 	const char *name;
 	bool full_only;
 };
 
 #define FEAT_OPA(n, func) \
 	[n] = { .name = #n, .write = write_##func, .print = print_##func }
+#define FEAT_OPP(n, func) \
+	[n] = { .name = #n, .write = write_##func, .print = print_##func, \
+		.process = process_##func }
 #define FEAT_OPF(n, func) \
-	[n] = { .name = #n, .write = write_##func, .print = print_##func, .full_only = true }
+	[n] = { .name = #n, .write = write_##func, .print = print_##func, \
+		.full_only = true }
 
 /* feature_ops not implemented: */
 #define print_trace_info		NULL
 #define print_build_id			NULL
 
 static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
-	FEAT_OPA(HEADER_TRACE_INFO,	trace_info),
-	FEAT_OPA(HEADER_BUILD_ID,	build_id),
+	FEAT_OPP(HEADER_TRACE_INFO,	trace_info),
+	FEAT_OPP(HEADER_BUILD_ID,	build_id),
 	FEAT_OPA(HEADER_HOSTNAME,	hostname),
 	FEAT_OPA(HEADER_OSRELEASE,	osrelease),
 	FEAT_OPA(HEADER_VERSION,	version),
@@ -1336,6 +1531,7 @@
 	FEAT_OPA(HEADER_CMDLINE,	cmdline),
 	FEAT_OPF(HEADER_CPU_TOPOLOGY,	cpu_topology),
 	FEAT_OPF(HEADER_NUMA_TOPOLOGY,	numa_topology),
+	FEAT_OPA(HEADER_BRANCH_STACK,	branch_stack),
 };
 
 struct header_print_data {
@@ -1620,24 +1816,128 @@
 	return err;
 }
 
+static const int attr_file_abi_sizes[] = {
+	[0] = PERF_ATTR_SIZE_VER0,
+	[1] = PERF_ATTR_SIZE_VER1,
+	0,
+};
+
+/*
+ * In the legacy file format, the magic number is not used to encode endianness.
+ * hdr_sz was used to encode endianness. But given that hdr_sz can vary based
+ * on ABI revisions, we need to try all combinations for all endianness to
+ * detect the endianness.
+ */
+static int try_all_file_abis(uint64_t hdr_sz, struct perf_header *ph)
+{
+	uint64_t ref_size, attr_size;
+	int i;
+
+	for (i = 0 ; attr_file_abi_sizes[i]; i++) {
+		ref_size = attr_file_abi_sizes[i]
+			 + sizeof(struct perf_file_section);
+		if (hdr_sz != ref_size) {
+			attr_size = bswap_64(hdr_sz);
+			if (attr_size != ref_size)
+				continue;
+
+			ph->needs_swap = true;
+		}
+		pr_debug("ABI%d perf.data file detected, need_swap=%d\n",
+			 i,
+			 ph->needs_swap);
+		return 0;
+	}
+	/* could not determine endianness */
+	return -1;
+}
+
+#define PERF_PIPE_HDR_VER0	16
+
+static const size_t attr_pipe_abi_sizes[] = {
+	[0] = PERF_PIPE_HDR_VER0,
+	0,
+};
+
+/*
+ * In the legacy pipe format, there is an implicit assumption that endiannesss
+ * between host recording the samples, and host parsing the samples is the
+ * same. This is not always the case given that the pipe output may always be
+ * redirected into a file and analyzed on a different machine with possibly a
+ * different endianness and perf_event ABI revsions in the perf tool itself.
+ */
+static int try_all_pipe_abis(uint64_t hdr_sz, struct perf_header *ph)
+{
+	u64 attr_size;
+	int i;
+
+	for (i = 0 ; attr_pipe_abi_sizes[i]; i++) {
+		if (hdr_sz != attr_pipe_abi_sizes[i]) {
+			attr_size = bswap_64(hdr_sz);
+			if (attr_size != hdr_sz)
+				continue;
+
+			ph->needs_swap = true;
+		}
+		pr_debug("Pipe ABI%d perf.data file detected\n", i);
+		return 0;
+	}
+	return -1;
+}
+
+static int check_magic_endian(u64 magic, uint64_t hdr_sz,
+			      bool is_pipe, struct perf_header *ph)
+{
+	int ret;
+
+	/* check for legacy format */
+	ret = memcmp(&magic, __perf_magic1, sizeof(magic));
+	if (ret == 0) {
+		pr_debug("legacy perf.data format\n");
+		if (is_pipe)
+			return try_all_pipe_abis(hdr_sz, ph);
+
+		return try_all_file_abis(hdr_sz, ph);
+	}
+	/*
+	 * the new magic number serves two purposes:
+	 * - unique number to identify actual perf.data files
+	 * - encode endianness of file
+	 */
+
+	/* check magic number with one endianness */
+	if (magic == __perf_magic2)
+		return 0;
+
+	/* check magic number with opposite endianness */
+	if (magic != __perf_magic2_sw)
+		return -1;
+
+	ph->needs_swap = true;
+
+	return 0;
+}
+
 int perf_file_header__read(struct perf_file_header *header,
 			   struct perf_header *ph, int fd)
 {
+	int ret;
+
 	lseek(fd, 0, SEEK_SET);
 
-	if (readn(fd, header, sizeof(*header)) <= 0 ||
-	    memcmp(&header->magic, __perf_magic, sizeof(header->magic)))
+	ret = readn(fd, header, sizeof(*header));
+	if (ret <= 0)
 		return -1;
 
-	if (header->attr_size != sizeof(struct perf_file_attr)) {
-		u64 attr_size = bswap_64(header->attr_size);
+	if (check_magic_endian(header->magic,
+			       header->attr_size, false, ph) < 0) {
+		pr_debug("magic/endian check failed\n");
+		return -1;
+	}
 
-		if (attr_size != sizeof(struct perf_file_attr))
-			return -1;
-
+	if (ph->needs_swap) {
 		mem_bswap_64(header, offsetof(struct perf_file_header,
-					    adds_features));
-		ph->needs_swap = true;
+			     adds_features));
 	}
 
 	if (header->size != sizeof(*header)) {
@@ -1689,156 +1989,6 @@
 	return 0;
 }
 
-static int __event_process_build_id(struct build_id_event *bev,
-				    char *filename,
-				    struct perf_session *session)
-{
-	int err = -1;
-	struct list_head *head;
-	struct machine *machine;
-	u16 misc;
-	struct dso *dso;
-	enum dso_kernel_type dso_type;
-
-	machine = perf_session__findnew_machine(session, bev->pid);
-	if (!machine)
-		goto out;
-
-	misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-
-	switch (misc) {
-	case PERF_RECORD_MISC_KERNEL:
-		dso_type = DSO_TYPE_KERNEL;
-		head = &machine->kernel_dsos;
-		break;
-	case PERF_RECORD_MISC_GUEST_KERNEL:
-		dso_type = DSO_TYPE_GUEST_KERNEL;
-		head = &machine->kernel_dsos;
-		break;
-	case PERF_RECORD_MISC_USER:
-	case PERF_RECORD_MISC_GUEST_USER:
-		dso_type = DSO_TYPE_USER;
-		head = &machine->user_dsos;
-		break;
-	default:
-		goto out;
-	}
-
-	dso = __dsos__findnew(head, filename);
-	if (dso != NULL) {
-		char sbuild_id[BUILD_ID_SIZE * 2 + 1];
-
-		dso__set_build_id(dso, &bev->build_id);
-
-		if (filename[0] == '[')
-			dso->kernel = dso_type;
-
-		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
-				  sbuild_id);
-		pr_debug("build id event received for %s: %s\n",
-			 dso->long_name, sbuild_id);
-	}
-
-	err = 0;
-out:
-	return err;
-}
-
-static int perf_header__read_build_ids_abi_quirk(struct perf_header *header,
-						 int input, u64 offset, u64 size)
-{
-	struct perf_session *session = container_of(header, struct perf_session, header);
-	struct {
-		struct perf_event_header   header;
-		u8			   build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))];
-		char			   filename[0];
-	} old_bev;
-	struct build_id_event bev;
-	char filename[PATH_MAX];
-	u64 limit = offset + size;
-
-	while (offset < limit) {
-		ssize_t len;
-
-		if (read(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev))
-			return -1;
-
-		if (header->needs_swap)
-			perf_event_header__bswap(&old_bev.header);
-
-		len = old_bev.header.size - sizeof(old_bev);
-		if (read(input, filename, len) != len)
-			return -1;
-
-		bev.header = old_bev.header;
-
-		/*
-		 * As the pid is the missing value, we need to fill
-		 * it properly. The header.misc value give us nice hint.
-		 */
-		bev.pid	= HOST_KERNEL_ID;
-		if (bev.header.misc == PERF_RECORD_MISC_GUEST_USER ||
-		    bev.header.misc == PERF_RECORD_MISC_GUEST_KERNEL)
-			bev.pid	= DEFAULT_GUEST_KERNEL_ID;
-
-		memcpy(bev.build_id, old_bev.build_id, sizeof(bev.build_id));
-		__event_process_build_id(&bev, filename, session);
-
-		offset += bev.header.size;
-	}
-
-	return 0;
-}
-
-static int perf_header__read_build_ids(struct perf_header *header,
-				       int input, u64 offset, u64 size)
-{
-	struct perf_session *session = container_of(header, struct perf_session, header);
-	struct build_id_event bev;
-	char filename[PATH_MAX];
-	u64 limit = offset + size, orig_offset = offset;
-	int err = -1;
-
-	while (offset < limit) {
-		ssize_t len;
-
-		if (read(input, &bev, sizeof(bev)) != sizeof(bev))
-			goto out;
-
-		if (header->needs_swap)
-			perf_event_header__bswap(&bev.header);
-
-		len = bev.header.size - sizeof(bev);
-		if (read(input, filename, len) != len)
-			goto out;
-		/*
-		 * The a1645ce1 changeset:
-		 *
-		 * "perf: 'perf kvm' tool for monitoring guest performance from host"
-		 *
-		 * Added a field to struct build_id_event that broke the file
-		 * format.
-		 *
-		 * Since the kernel build-id is the first entry, process the
-		 * table using the old format if the well known
-		 * '[kernel.kallsyms]' string for the kernel build-id has the
-		 * first 4 characters chopped off (where the pid_t sits).
-		 */
-		if (memcmp(filename, "nel.kallsyms]", 13) == 0) {
-			if (lseek(input, orig_offset, SEEK_SET) == (off_t)-1)
-				return -1;
-			return perf_header__read_build_ids_abi_quirk(header, input, offset, size);
-		}
-
-		__event_process_build_id(&bev, filename, session);
-
-		offset += bev.header.size;
-	}
-	err = 0;
-out:
-	return err;
-}
-
 static int perf_file_section__process(struct perf_file_section *section,
 				      struct perf_header *ph,
 				      int feat, int fd, void *data __used)
@@ -1854,41 +2004,33 @@
 		return 0;
 	}
 
-	switch (feat) {
-	case HEADER_TRACE_INFO:
-		trace_report(fd, false);
-		break;
-	case HEADER_BUILD_ID:
-		if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
-			pr_debug("Failed to read buildids, continuing...\n");
-		break;
-	default:
-		break;
-	}
+	if (!feat_ops[feat].process)
+		return 0;
 
-	return 0;
+	return feat_ops[feat].process(section, ph, feat, fd);
 }
 
 static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
 				       struct perf_header *ph, int fd,
 				       bool repipe)
 {
-	if (readn(fd, header, sizeof(*header)) <= 0 ||
-	    memcmp(&header->magic, __perf_magic, sizeof(header->magic)))
+	int ret;
+
+	ret = readn(fd, header, sizeof(*header));
+	if (ret <= 0)
 		return -1;
 
+	if (check_magic_endian(header->magic, header->size, true, ph) < 0) {
+		pr_debug("endian/magic failed\n");
+		return -1;
+	}
+
+	if (ph->needs_swap)
+		header->size = bswap_64(header->size);
+
 	if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
 		return -1;
 
-	if (header->size != sizeof(*header)) {
-		u64 size = bswap_64(header->size);
-
-		if (size != sizeof(*header))
-			return -1;
-
-		ph->needs_swap = true;
-	}
-
 	return 0;
 }
 
@@ -1908,6 +2050,52 @@
 	return 0;
 }
 
+static int read_attr(int fd, struct perf_header *ph,
+		     struct perf_file_attr *f_attr)
+{
+	struct perf_event_attr *attr = &f_attr->attr;
+	size_t sz, left;
+	size_t our_sz = sizeof(f_attr->attr);
+	int ret;
+
+	memset(f_attr, 0, sizeof(*f_attr));
+
+	/* read minimal guaranteed structure */
+	ret = readn(fd, attr, PERF_ATTR_SIZE_VER0);
+	if (ret <= 0) {
+		pr_debug("cannot read %d bytes of header attr\n",
+			 PERF_ATTR_SIZE_VER0);
+		return -1;
+	}
+
+	/* on file perf_event_attr size */
+	sz = attr->size;
+
+	if (ph->needs_swap)
+		sz = bswap_32(sz);
+
+	if (sz == 0) {
+		/* assume ABI0 */
+		sz =  PERF_ATTR_SIZE_VER0;
+	} else if (sz > our_sz) {
+		pr_debug("file uses a more recent and unsupported ABI"
+			 " (%zu bytes extra)\n", sz - our_sz);
+		return -1;
+	}
+	/* what we have not yet read and that we know about */
+	left = sz - PERF_ATTR_SIZE_VER0;
+	if (left) {
+		void *ptr = attr;
+		ptr += PERF_ATTR_SIZE_VER0;
+
+		ret = readn(fd, ptr, left);
+	}
+	/* read perf_file_section, ids are read in caller */
+	ret = readn(fd, &f_attr->ids, sizeof(f_attr->ids));
+
+	return ret <= 0 ? -1 : 0;
+}
+
 int perf_session__read_header(struct perf_session *session, int fd)
 {
 	struct perf_header *header = &session->header;
@@ -1923,19 +2111,17 @@
 	if (session->fd_pipe)
 		return perf_header__read_pipe(session, fd);
 
-	if (perf_file_header__read(&f_header, header, fd) < 0) {
-		pr_debug("incompatible file format\n");
+	if (perf_file_header__read(&f_header, header, fd) < 0)
 		return -EINVAL;
-	}
 
-	nr_attrs = f_header.attrs.size / sizeof(f_attr);
+	nr_attrs = f_header.attrs.size / f_header.attr_size;
 	lseek(fd, f_header.attrs.offset, SEEK_SET);
 
 	for (i = 0; i < nr_attrs; i++) {
 		struct perf_evsel *evsel;
 		off_t tmp;
 
-		if (readn(fd, &f_attr, sizeof(f_attr)) <= 0)
+		if (read_attr(fd, header, &f_attr) < 0)
 			goto out_errno;
 
 		if (header->needs_swap)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index ac4ec95..21a6be0 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -11,6 +11,7 @@
 
 enum {
 	HEADER_RESERVED		= 0,	/* always cleared */
+	HEADER_FIRST_FEATURE	= 1,
 	HEADER_TRACE_INFO	= 1,
 	HEADER_BUILD_ID,
 
@@ -26,7 +27,7 @@
 	HEADER_EVENT_DESC,
 	HEADER_CPU_TOPOLOGY,
 	HEADER_NUMA_TOPOLOGY,
-
+	HEADER_BRANCH_STACK,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index e11e482..5fb1901 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -10,11 +10,14 @@
 				       struct hist_entry *he);
 static bool hists__filter_entry_by_thread(struct hists *hists,
 					  struct hist_entry *he);
+static bool hists__filter_entry_by_symbol(struct hists *hists,
+					  struct hist_entry *he);
 
 enum hist_filter {
 	HIST_FILTER__DSO,
 	HIST_FILTER__THREAD,
 	HIST_FILTER__PARENT,
+	HIST_FILTER__SYMBOL,
 };
 
 struct callchain_param	callchain_param = {
@@ -50,21 +53,25 @@
 		hists__set_col_len(hists, col, 0);
 }
 
+static void hists__set_unres_dso_col_len(struct hists *hists, int dso)
+{
+	const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
+
+	if (hists__col_len(hists, dso) < unresolved_col_width &&
+	    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
+	    !symbol_conf.dso_list)
+		hists__set_col_len(hists, dso, unresolved_col_width);
+}
+
 static void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 {
+	const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
 	u16 len;
 
 	if (h->ms.sym)
-		hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen);
-	else {
-		const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
-
-		if (hists__col_len(hists, HISTC_DSO) < unresolved_col_width &&
-		    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
-		    !symbol_conf.dso_list)
-			hists__set_col_len(hists, HISTC_DSO,
-					   unresolved_col_width);
-	}
+		hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen + 4);
+	else
+		hists__set_unres_dso_col_len(hists, HISTC_DSO);
 
 	len = thread__comm_len(h->thread);
 	if (hists__new_col_len(hists, HISTC_COMM, len))
@@ -74,6 +81,37 @@
 		len = dso__name_len(h->ms.map->dso);
 		hists__new_col_len(hists, HISTC_DSO, len);
 	}
+
+	if (h->branch_info) {
+		int symlen;
+		/*
+		 * +4 accounts for '[x] ' priv level info
+		 * +2 account of 0x prefix on raw addresses
+		 */
+		if (h->branch_info->from.sym) {
+			symlen = (int)h->branch_info->from.sym->namelen + 4;
+			hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
+
+			symlen = dso__name_len(h->branch_info->from.map->dso);
+			hists__new_col_len(hists, HISTC_DSO_FROM, symlen);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
+			hists__set_unres_dso_col_len(hists, HISTC_DSO_FROM);
+		}
+
+		if (h->branch_info->to.sym) {
+			symlen = (int)h->branch_info->to.sym->namelen + 4;
+			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
+
+			symlen = dso__name_len(h->branch_info->to.map->dso);
+			hists__new_col_len(hists, HISTC_DSO_TO, symlen);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
+			hists__set_unres_dso_col_len(hists, HISTC_DSO_TO);
+		}
+	}
 }
 
 static void hist_entry__add_cpumode_period(struct hist_entry *he,
@@ -195,26 +233,14 @@
 	return 0;
 }
 
-struct hist_entry *__hists__add_entry(struct hists *hists,
+static struct hist_entry *add_hist_entry(struct hists *hists,
+				      struct hist_entry *entry,
 				      struct addr_location *al,
-				      struct symbol *sym_parent, u64 period)
+				      u64 period)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
-	struct hist_entry entry = {
-		.thread	= al->thread,
-		.ms = {
-			.map	= al->map,
-			.sym	= al->sym,
-		},
-		.cpu	= al->cpu,
-		.ip	= al->addr,
-		.level	= al->level,
-		.period	= period,
-		.parent = sym_parent,
-		.filtered = symbol__parent_filter(sym_parent),
-	};
 	int cmp;
 
 	pthread_mutex_lock(&hists->lock);
@@ -225,7 +251,7 @@
 		parent = *p;
 		he = rb_entry(parent, struct hist_entry, rb_node_in);
 
-		cmp = hist_entry__cmp(&entry, he);
+		cmp = hist_entry__cmp(entry, he);
 
 		if (!cmp) {
 			he->period += period;
@@ -239,7 +265,7 @@
 			p = &(*p)->rb_right;
 	}
 
-	he = hist_entry__new(&entry);
+	he = hist_entry__new(entry);
 	if (!he)
 		goto out_unlock;
 
@@ -252,6 +278,51 @@
 	return he;
 }
 
+struct hist_entry *__hists__add_branch_entry(struct hists *self,
+					     struct addr_location *al,
+					     struct symbol *sym_parent,
+					     struct branch_info *bi,
+					     u64 period)
+{
+	struct hist_entry entry = {
+		.thread	= al->thread,
+		.ms = {
+			.map	= bi->to.map,
+			.sym	= bi->to.sym,
+		},
+		.cpu	= al->cpu,
+		.ip	= bi->to.addr,
+		.level	= al->level,
+		.period	= period,
+		.parent = sym_parent,
+		.filtered = symbol__parent_filter(sym_parent),
+		.branch_info = bi,
+	};
+
+	return add_hist_entry(self, &entry, al, period);
+}
+
+struct hist_entry *__hists__add_entry(struct hists *self,
+				      struct addr_location *al,
+				      struct symbol *sym_parent, u64 period)
+{
+	struct hist_entry entry = {
+		.thread	= al->thread,
+		.ms = {
+			.map	= al->map,
+			.sym	= al->sym,
+		},
+		.cpu	= al->cpu,
+		.ip	= al->addr,
+		.level	= al->level,
+		.period	= period,
+		.parent = sym_parent,
+		.filtered = symbol__parent_filter(sym_parent),
+	};
+
+	return add_hist_entry(self, &entry, al, period);
+}
+
 int64_t
 hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -352,6 +423,7 @@
 {
 	hists__filter_entry_by_dso(hists, he);
 	hists__filter_entry_by_thread(hists, he);
+	hists__filter_entry_by_symbol(hists, he);
 }
 
 static void __hists__collapse_resort(struct hists *hists, bool threaded)
@@ -1179,6 +1251,37 @@
 	}
 }
 
+static bool hists__filter_entry_by_symbol(struct hists *hists,
+					  struct hist_entry *he)
+{
+	if (hists->symbol_filter_str != NULL &&
+	    (!he->ms.sym || strstr(he->ms.sym->name,
+				   hists->symbol_filter_str) == NULL)) {
+		he->filtered |= (1 << HIST_FILTER__SYMBOL);
+		return true;
+	}
+
+	return false;
+}
+
+void hists__filter_by_symbol(struct hists *hists)
+{
+	struct rb_node *nd;
+
+	hists->nr_entries = hists->stats.total_period = 0;
+	hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+	hists__reset_col_len(hists);
+
+	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		if (hists__filter_entry_by_symbol(hists, h))
+			continue;
+
+		hists__remove_entry_filter(hists, h, HIST_FILTER__SYMBOL);
+	}
+}
+
 int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
 {
 	return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index f55f0a8d..2cae9df 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -32,6 +32,7 @@
 	u32 nr_unknown_events;
 	u32 nr_invalid_chains;
 	u32 nr_unknown_id;
+	u32 nr_unprocessable_samples;
 };
 
 enum hist_column {
@@ -41,6 +42,11 @@
 	HISTC_COMM,
 	HISTC_PARENT,
 	HISTC_CPU,
+	HISTC_MISPREDICT,
+	HISTC_SYMBOL_FROM,
+	HISTC_SYMBOL_TO,
+	HISTC_DSO_FROM,
+	HISTC_DSO_TO,
 	HISTC_NR_COLS, /* Last entry */
 };
 
@@ -55,6 +61,8 @@
 	u64			nr_entries;
 	const struct thread	*thread_filter;
 	const struct dso	*dso_filter;
+	const char		*uid_filter_str;
+	const char		*symbol_filter_str;
 	pthread_mutex_t		lock;
 	struct events_stats	stats;
 	u64			event_stream;
@@ -72,6 +80,12 @@
 			 struct hists *hists);
 void hist_entry__free(struct hist_entry *);
 
+struct hist_entry *__hists__add_branch_entry(struct hists *self,
+					     struct addr_location *al,
+					     struct symbol *sym_parent,
+					     struct branch_info *bi,
+					     u64 period);
+
 void hists__output_resort(struct hists *self);
 void hists__output_resort_threaded(struct hists *hists);
 void hists__collapse_resort(struct hists *self);
@@ -94,6 +108,7 @@
 
 void hists__filter_by_dso(struct hists *hists);
 void hists__filter_by_thread(struct hists *hists);
+void hists__filter_by_symbol(struct hists *hists);
 
 u16 hists__col_len(struct hists *self, enum hist_column col);
 void hists__set_col_len(struct hists *self, enum hist_column col, u16 len);
@@ -132,6 +147,23 @@
 				  int refresh);
 #endif
 
+#ifdef NO_GTK2_SUPPORT
+static inline
+int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __used,
+				  const char *help __used,
+				  void(*timer)(void *arg) __used,
+				  void *arg __used,
+				  int refresh __used)
+{
+	return 0;
+}
+
+#else
+int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help,
+				  void(*timer)(void *arg), void *arg,
+				  int refresh);
+#endif
+
 unsigned int hists__sort_list_width(struct hists *self);
 
 #endif	/* __PERF_HIST_H */
diff --git a/tools/perf/util/include/asm/dwarf2.h b/tools/perf/util/include/asm/dwarf2.h
index bb4198e..afe3819 100644
--- a/tools/perf/util/include/asm/dwarf2.h
+++ b/tools/perf/util/include/asm/dwarf2.h
@@ -2,10 +2,12 @@
 #ifndef PERF_DWARF2_H
 #define PERF_DWARF2_H
 
-/* dwarf2.h ... dummy header file for including arch/x86/lib/memcpy_64.S */
+/* dwarf2.h ... dummy header file for including arch/x86/lib/mem{cpy,set}_64.S */
 
 #define CFI_STARTPROC
 #define CFI_ENDPROC
+#define CFI_REMEMBER_STATE
+#define CFI_RESTORE_STATE
 
 #endif	/* PERF_DWARF2_H */
 
diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h
index eda4416..bb162e4 100644
--- a/tools/perf/util/include/linux/bitmap.h
+++ b/tools/perf/util/include/linux/bitmap.h
@@ -5,6 +5,8 @@
 #include <linux/bitops.h>
 
 int __bitmap_weight(const unsigned long *bitmap, int bits);
+void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
+		 const unsigned long *bitmap2, int bits);
 
 #define BITMAP_LAST_WORD_MASK(nbits)					\
 (									\
@@ -32,4 +34,13 @@
 	return __bitmap_weight(src, nbits);
 }
 
+static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
+			     const unsigned long *src2, int nbits)
+{
+	if (small_const_nbits(nbits))
+		*dst = *src1 | *src2;
+	else
+		__bitmap_or(dst, src1, src2, nbits);
+}
+
 #endif /* _PERF_BITOPS_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 316aa0a..dea6d1c 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -212,6 +212,21 @@
 		       self->start, self->end, self->pgoff, self->dso->name);
 }
 
+size_t map__fprintf_dsoname(struct map *map, FILE *fp)
+{
+	const char *dsoname;
+
+	if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+		if (symbol_conf.show_kernel_path && map->dso->long_name)
+			dsoname = map->dso->long_name;
+		else if (map->dso->name)
+			dsoname = map->dso->name;
+	} else
+		dsoname = "[unknown]";
+
+	return fprintf(fp, "%s", dsoname);
+}
+
 /*
  * objdump wants/reports absolute IPs for ET_EXEC, and RIPs for ET_DYN.
  * map->dso->adjust_symbols==1 for ET_EXEC-like cases.
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 2b8017f..b100c20 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -118,6 +118,7 @@
 struct map *map__clone(struct map *self);
 int map__overlap(struct map *l, struct map *r);
 size_t map__fprintf(struct map *self, FILE *fp);
+size_t map__fprintf_dsoname(struct map *map, FILE *fp);
 
 int map__load(struct map *self, symbol_filter_t filter);
 struct symbol *map__find_symbol(struct map *self,
diff --git a/tools/perf/util/parse-events-bison.c b/tools/perf/util/parse-events-bison.c
new file mode 100644
index 0000000..4a0fd6d
--- /dev/null
+++ b/tools/perf/util/parse-events-bison.c
@@ -0,0 +1,1852 @@
+/* A Bison parser, made by GNU Bison 2.4.3.  */
+
+/* Skeleton implementation for Bison's Yacc-like parsers in C
+   
+      Copyright (C) 1984, 1989, 1990, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
+   2009, 2010 Free Software Foundation, Inc.
+   
+   This program is free software: you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation, either version 3 of the License, or
+   (at your option) any later version.
+   
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+   
+   You should have received a copy of the GNU General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
+
+/* As a special exception, you may create a larger work that contains
+   part or all of the Bison parser skeleton and distribute that work
+   under terms of your choice, so long as that work isn't itself a
+   parser generator using the skeleton or a modified version thereof
+   as a parser skeleton.  Alternatively, if you modify or redistribute
+   the parser skeleton itself, you may (at your option) remove this
+   special exception, which will cause the skeleton and the resulting
+   Bison output files to be licensed under the GNU General Public
+   License without this special exception.
+   
+   This special exception was added by the Free Software Foundation in
+   version 2.2 of Bison.  */
+
+/* C LALR(1) parser skeleton written by Richard Stallman, by
+   simplifying the original so-called "semantic" parser.  */
+
+/* All symbols defined below should begin with yy or YY, to avoid
+   infringing on user name space.  This should be done even for local
+   variables, as they might otherwise be expanded by user macros.
+   There are some unavoidable exceptions within include files to
+   define necessary library symbols; they are noted "INFRINGES ON
+   USER NAME SPACE" below.  */
+
+/* Identify Bison output.  */
+#define YYBISON 1
+
+/* Bison version.  */
+#define YYBISON_VERSION "2.4.3"
+
+/* Skeleton name.  */
+#define YYSKELETON_NAME "yacc.c"
+
+/* Pure parsers.  */
+#define YYPURE 0
+
+/* Push parsers.  */
+#define YYPUSH 0
+
+/* Pull parsers.  */
+#define YYPULL 1
+
+/* Using locations.  */
+#define YYLSP_NEEDED 0
+
+/* Substitute the variable and function names.  */
+#define yyparse         parse_events_parse
+#define yylex           parse_events_lex
+#define yyerror         parse_events_error
+#define yylval          parse_events_lval
+#define yychar          parse_events_char
+#define yydebug         parse_events_debug
+#define yynerrs         parse_events_nerrs
+
+
+/* Copy the first part of user declarations.  */
+
+/* Line 189 of yacc.c  */
+#line 6 "util/parse-events.y"
+
+
+#define YYDEBUG 1
+
+#include <linux/compiler.h>
+#include <linux/list.h>
+#include "types.h"
+#include "util.h"
+#include "parse-events.h"
+
+extern int parse_events_lex (void);
+
+#define ABORT_ON(val) \
+do { \
+	if (val) \
+		YYABORT; \
+} while (0)
+
+
+
+/* Line 189 of yacc.c  */
+#line 101 "util/parse-events-bison.c"
+
+/* Enabling traces.  */
+#ifndef YYDEBUG
+# define YYDEBUG 0
+#endif
+
+/* Enabling verbose error messages.  */
+#ifdef YYERROR_VERBOSE
+# undef YYERROR_VERBOSE
+# define YYERROR_VERBOSE 1
+#else
+# define YYERROR_VERBOSE 0
+#endif
+
+/* Enabling the token table.  */
+#ifndef YYTOKEN_TABLE
+# define YYTOKEN_TABLE 0
+#endif
+
+
+/* Tokens.  */
+#ifndef YYTOKENTYPE
+# define YYTOKENTYPE
+   /* Put the tokens into the symbol table, so that GDB and other debuggers
+      know about them.  */
+   enum yytokentype {
+     PE_VALUE = 258,
+     PE_VALUE_SYM = 259,
+     PE_RAW = 260,
+     PE_TERM = 261,
+     PE_NAME = 262,
+     PE_MODIFIER_EVENT = 263,
+     PE_MODIFIER_BP = 264,
+     PE_NAME_CACHE_TYPE = 265,
+     PE_NAME_CACHE_OP_RESULT = 266,
+     PE_PREFIX_MEM = 267,
+     PE_PREFIX_RAW = 268,
+     PE_ERROR = 269
+   };
+#endif
+
+
+
+#if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED
+typedef union YYSTYPE
+{
+
+/* Line 214 of yacc.c  */
+#line 45 "util/parse-events.y"
+
+	char *str;
+	unsigned long num;
+	struct list_head *head;
+	struct parse_events__term *term;
+
+
+
+/* Line 214 of yacc.c  */
+#line 160 "util/parse-events-bison.c"
+} YYSTYPE;
+# define YYSTYPE_IS_TRIVIAL 1
+# define yystype YYSTYPE /* obsolescent; will be withdrawn */
+# define YYSTYPE_IS_DECLARED 1
+#endif
+
+
+/* Copy the second part of user declarations.  */
+
+
+/* Line 264 of yacc.c  */
+#line 172 "util/parse-events-bison.c"
+
+#ifdef short
+# undef short
+#endif
+
+#ifdef YYTYPE_UINT8
+typedef YYTYPE_UINT8 yytype_uint8;
+#else
+typedef unsigned char yytype_uint8;
+#endif
+
+#ifdef YYTYPE_INT8
+typedef YYTYPE_INT8 yytype_int8;
+#elif (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+typedef signed char yytype_int8;
+#else
+typedef short int yytype_int8;
+#endif
+
+#ifdef YYTYPE_UINT16
+typedef YYTYPE_UINT16 yytype_uint16;
+#else
+typedef unsigned short int yytype_uint16;
+#endif
+
+#ifdef YYTYPE_INT16
+typedef YYTYPE_INT16 yytype_int16;
+#else
+typedef short int yytype_int16;
+#endif
+
+#ifndef YYSIZE_T
+# ifdef __SIZE_TYPE__
+#  define YYSIZE_T __SIZE_TYPE__
+# elif defined size_t
+#  define YYSIZE_T size_t
+# elif ! defined YYSIZE_T && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+#  include <stddef.h> /* INFRINGES ON USER NAME SPACE */
+#  define YYSIZE_T size_t
+# else
+#  define YYSIZE_T unsigned int
+# endif
+#endif
+
+#define YYSIZE_MAXIMUM ((YYSIZE_T) -1)
+
+#ifndef YY_
+# if defined YYENABLE_NLS && YYENABLE_NLS
+#  if ENABLE_NLS
+#   include <libintl.h> /* INFRINGES ON USER NAME SPACE */
+#   define YY_(msgid) dgettext ("bison-runtime", msgid)
+#  endif
+# endif
+# ifndef YY_
+#  define YY_(msgid) msgid
+# endif
+#endif
+
+/* Suppress unused-variable warnings by "using" E.  */
+#if ! defined lint || defined __GNUC__
+# define YYUSE(e) ((void) (e))
+#else
+# define YYUSE(e) /* empty */
+#endif
+
+/* Identity function, used to suppress warnings about constant conditions.  */
+#ifndef lint
+# define YYID(n) (n)
+#else
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static int
+YYID (int yyi)
+#else
+static int
+YYID (yyi)
+    int yyi;
+#endif
+{
+  return yyi;
+}
+#endif
+
+#if ! defined yyoverflow || YYERROR_VERBOSE
+
+/* The parser invokes alloca or malloc; define the necessary symbols.  */
+
+# ifdef YYSTACK_USE_ALLOCA
+#  if YYSTACK_USE_ALLOCA
+#   ifdef __GNUC__
+#    define YYSTACK_ALLOC __builtin_alloca
+#   elif defined __BUILTIN_VA_ARG_INCR
+#    include <alloca.h> /* INFRINGES ON USER NAME SPACE */
+#   elif defined _AIX
+#    define YYSTACK_ALLOC __alloca
+#   elif defined _MSC_VER
+#    include <malloc.h> /* INFRINGES ON USER NAME SPACE */
+#    define alloca _alloca
+#   else
+#    define YYSTACK_ALLOC alloca
+#    if ! defined _ALLOCA_H && ! defined _STDLIB_H && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+#     include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
+#     ifndef _STDLIB_H
+#      define _STDLIB_H 1
+#     endif
+#    endif
+#   endif
+#  endif
+# endif
+
+# ifdef YYSTACK_ALLOC
+   /* Pacify GCC's `empty if-body' warning.  */
+#  define YYSTACK_FREE(Ptr) do { /* empty */; } while (YYID (0))
+#  ifndef YYSTACK_ALLOC_MAXIMUM
+    /* The OS might guarantee only one guard page at the bottom of the stack,
+       and a page size can be as small as 4096 bytes.  So we cannot safely
+       invoke alloca (N) if N exceeds 4096.  Use a slightly smaller number
+       to allow for a few compiler-allocated temporary stack slots.  */
+#   define YYSTACK_ALLOC_MAXIMUM 4032 /* reasonable circa 2006 */
+#  endif
+# else
+#  define YYSTACK_ALLOC YYMALLOC
+#  define YYSTACK_FREE YYFREE
+#  ifndef YYSTACK_ALLOC_MAXIMUM
+#   define YYSTACK_ALLOC_MAXIMUM YYSIZE_MAXIMUM
+#  endif
+#  if (defined __cplusplus && ! defined _STDLIB_H \
+       && ! ((defined YYMALLOC || defined malloc) \
+	     && (defined YYFREE || defined free)))
+#   include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
+#   ifndef _STDLIB_H
+#    define _STDLIB_H 1
+#   endif
+#  endif
+#  ifndef YYMALLOC
+#   define YYMALLOC malloc
+#   if ! defined malloc && ! defined _STDLIB_H && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+void *malloc (YYSIZE_T); /* INFRINGES ON USER NAME SPACE */
+#   endif
+#  endif
+#  ifndef YYFREE
+#   define YYFREE free
+#   if ! defined free && ! defined _STDLIB_H && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+void free (void *); /* INFRINGES ON USER NAME SPACE */
+#   endif
+#  endif
+# endif
+#endif /* ! defined yyoverflow || YYERROR_VERBOSE */
+
+
+#if (! defined yyoverflow \
+     && (! defined __cplusplus \
+	 || (defined YYSTYPE_IS_TRIVIAL && YYSTYPE_IS_TRIVIAL)))
+
+/* A type that is properly aligned for any stack member.  */
+union yyalloc
+{
+  yytype_int16 yyss_alloc;
+  YYSTYPE yyvs_alloc;
+};
+
+/* The size of the maximum gap between one aligned stack and the next.  */
+# define YYSTACK_GAP_MAXIMUM (sizeof (union yyalloc) - 1)
+
+/* The size of an array large to enough to hold all stacks, each with
+   N elements.  */
+# define YYSTACK_BYTES(N) \
+     ((N) * (sizeof (yytype_int16) + sizeof (YYSTYPE)) \
+      + YYSTACK_GAP_MAXIMUM)
+
+/* Copy COUNT objects from FROM to TO.  The source and destination do
+   not overlap.  */
+# ifndef YYCOPY
+#  if defined __GNUC__ && 1 < __GNUC__
+#   define YYCOPY(To, From, Count) \
+      __builtin_memcpy (To, From, (Count) * sizeof (*(From)))
+#  else
+#   define YYCOPY(To, From, Count)		\
+      do					\
+	{					\
+	  YYSIZE_T yyi;				\
+	  for (yyi = 0; yyi < (Count); yyi++)	\
+	    (To)[yyi] = (From)[yyi];		\
+	}					\
+      while (YYID (0))
+#  endif
+# endif
+
+/* Relocate STACK from its old location to the new one.  The
+   local variables YYSIZE and YYSTACKSIZE give the old and new number of
+   elements in the stack, and YYPTR gives the new location of the
+   stack.  Advance YYPTR to a properly aligned location for the next
+   stack.  */
+# define YYSTACK_RELOCATE(Stack_alloc, Stack)				\
+    do									\
+      {									\
+	YYSIZE_T yynewbytes;						\
+	YYCOPY (&yyptr->Stack_alloc, Stack, yysize);			\
+	Stack = &yyptr->Stack_alloc;					\
+	yynewbytes = yystacksize * sizeof (*Stack) + YYSTACK_GAP_MAXIMUM; \
+	yyptr += yynewbytes / sizeof (*yyptr);				\
+      }									\
+    while (YYID (0))
+
+#endif
+
+/* YYFINAL -- State number of the termination state.  */
+#define YYFINAL  25
+/* YYLAST -- Last index in YYTABLE.  */
+#define YYLAST   43
+
+/* YYNTOKENS -- Number of terminals.  */
+#define YYNTOKENS  20
+/* YYNNTS -- Number of nonterminals.  */
+#define YYNNTS  15
+/* YYNRULES -- Number of rules.  */
+#define YYNRULES  35
+/* YYNRULES -- Number of states.  */
+#define YYNSTATES  57
+
+/* YYTRANSLATE(YYLEX) -- Bison symbol number corresponding to YYLEX.  */
+#define YYUNDEFTOK  2
+#define YYMAXUTOK   269
+
+#define YYTRANSLATE(YYX)						\
+  ((unsigned int) (YYX) <= YYMAXUTOK ? yytranslate[YYX] : YYUNDEFTOK)
+
+/* YYTRANSLATE[YYLEX] -- Bison symbol number corresponding to YYLEX.  */
+static const yytype_uint8 yytranslate[] =
+{
+       0,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,    15,    17,     2,    16,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,    18,     2,
+       2,    19,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     1,     2,     3,     4,
+       5,     6,     7,     8,     9,    10,    11,    12,    13,    14
+};
+
+#if YYDEBUG
+/* YYPRHS[YYN] -- Index of the first RHS symbol of rule number YYN in
+   YYRHS.  */
+static const yytype_uint8 yyprhs[] =
+{
+       0,     0,     3,     7,     9,    12,    14,    16,    18,    21,
+      23,    26,    29,    32,    37,    42,    45,    51,    55,    57,
+      63,    67,    71,    75,    77,    81,    83,    87,    91,    93,
+      97,    99,   101,   102,   104,   106
+};
+
+/* YYRHS -- A `-1'-separated list of the rules' RHS.  */
+static const yytype_int8 yyrhs[] =
+{
+      21,     0,    -1,    21,    15,    22,    -1,    22,    -1,    23,
+       8,    -1,    23,    -1,    24,    -1,    25,    -1,    26,    33,
+      -1,    27,    -1,    28,    33,    -1,    29,    33,    -1,    30,
+      33,    -1,     7,    16,    31,    16,    -1,     4,    16,    31,
+      16,    -1,     4,    34,    -1,    10,    17,    11,    17,    11,
+      -1,    10,    17,    11,    -1,    10,    -1,    12,     3,    18,
+       9,    33,    -1,    12,     3,    33,    -1,     7,    18,     7,
+      -1,     3,    18,     3,    -1,     5,    -1,    31,    15,    32,
+      -1,    32,    -1,     7,    19,     7,    -1,     7,    19,     3,
+      -1,     7,    -1,     6,    19,     3,    -1,     6,    -1,    18,
+      -1,    -1,    16,    -1,    18,    -1,    -1
+};
+
+/* YYRLINE[YYN] -- source line where rule number YYN was defined.  */
+static const yytype_uint8 yyrline[] =
+{
+       0,    54,    54,    54,    57,    62,    64,    65,    66,    67,
+      68,    69,    70,    73,    80,    89,    98,   103,   108,   114,
+     119,   125,   131,   137,   143,   153,   165,   174,   183,   192,
+     200,   208,   208,   210,   210,   210
+};
+#endif
+
+#if YYDEBUG || YYERROR_VERBOSE || YYTOKEN_TABLE
+/* YYTNAME[SYMBOL-NUM] -- String name of the symbol SYMBOL-NUM.
+   First, the terminals, then, starting at YYNTOKENS, nonterminals.  */
+static const char *const yytname[] =
+{
+  "$end", "error", "$undefined", "PE_VALUE", "PE_VALUE_SYM", "PE_RAW",
+  "PE_TERM", "PE_NAME", "PE_MODIFIER_EVENT", "PE_MODIFIER_BP",
+  "PE_NAME_CACHE_TYPE", "PE_NAME_CACHE_OP_RESULT", "PE_PREFIX_MEM",
+  "PE_PREFIX_RAW", "PE_ERROR", "','", "'/'", "'-'", "':'", "'='",
+  "$accept", "events", "event", "event_def", "event_pmu",
+  "event_legacy_symbol", "event_legacy_cache", "event_legacy_mem",
+  "event_legacy_tracepoint", "event_legacy_numeric", "event_legacy_raw",
+  "event_config", "event_term", "sep_dc", "sep_slash_dc", 0
+};
+#endif
+
+# ifdef YYPRINT
+/* YYTOKNUM[YYLEX-NUM] -- Internal token number corresponding to
+   token YYLEX-NUM.  */
+static const yytype_uint16 yytoknum[] =
+{
+       0,   256,   257,   258,   259,   260,   261,   262,   263,   264,
+     265,   266,   267,   268,   269,    44,    47,    45,    58,    61
+};
+# endif
+
+/* YYR1[YYN] -- Symbol number of symbol that rule YYN derives.  */
+static const yytype_uint8 yyr1[] =
+{
+       0,    20,    21,    21,    22,    22,    23,    23,    23,    23,
+      23,    23,    23,    24,    25,    25,    26,    26,    26,    27,
+      27,    28,    29,    30,    31,    31,    32,    32,    32,    32,
+      32,    33,    33,    34,    34,    34
+};
+
+/* YYR2[YYN] -- Number of symbols composing right hand side of rule YYN.  */
+static const yytype_uint8 yyr2[] =
+{
+       0,     2,     3,     1,     2,     1,     1,     1,     2,     1,
+       2,     2,     2,     4,     4,     2,     5,     3,     1,     5,
+       3,     3,     3,     1,     3,     1,     3,     3,     1,     3,
+       1,     1,     0,     1,     1,     0
+};
+
+/* YYDEFACT[STATE-NAME] -- Default rule to reduce with in state
+   STATE-NUM when YYTABLE doesn't specify something else to do.  Zero
+   means the default is an error.  */
+static const yytype_uint8 yydefact[] =
+{
+       0,     0,    35,    23,     0,    18,     0,     0,     3,     5,
+       6,     7,    32,     9,    32,    32,    32,     0,    33,    34,
+      15,     0,     0,     0,    32,     1,     0,     4,    31,     8,
+      10,    11,    12,    22,    30,    28,     0,    25,     0,    21,
+      17,    31,    20,     2,     0,     0,     0,    14,    13,     0,
+      32,    29,    27,    26,    24,    16,    19
+};
+
+/* YYDEFGOTO[NTERM-NUM].  */
+static const yytype_int8 yydefgoto[] =
+{
+      -1,     7,     8,     9,    10,    11,    12,    13,    14,    15,
+      16,    36,    37,    29,    20
+};
+
+/* YYPACT[STATE-NUM] -- Index in YYTABLE of the portion describing
+   STATE-NUM.  */
+#define YYPACT_NINF -15
+static const yytype_int8 yypact[] =
+{
+       1,    -4,    -9,   -15,    -1,    10,    22,     3,   -15,    18,
+     -15,   -15,    11,   -15,    11,    11,    11,    25,    13,   -15,
+     -15,    13,    23,    20,    14,   -15,     1,   -15,   -15,   -15,
+     -15,   -15,   -15,   -15,    15,    16,     6,   -15,     8,   -15,
+      21,    24,   -15,   -15,    34,     9,    13,   -15,   -15,    28,
+      11,   -15,   -15,   -15,   -15,   -15,   -15
+};
+
+/* YYPGOTO[NTERM-NUM].  */
+static const yytype_int8 yypgoto[] =
+{
+     -15,   -15,    17,   -15,   -15,   -15,   -15,   -15,   -15,   -15,
+     -15,    19,    -5,   -14,   -15
+};
+
+/* YYTABLE[YYPACT[STATE-NUM]].  What to do in state STATE-NUM.  If
+   positive, shift that token.  If negative, reduce the rule which
+   number is the opposite.  If zero, do what YYDEFACT says.
+   If YYTABLE_NINF, syntax error.  */
+#define YYTABLE_NINF -1
+static const yytype_uint8 yytable[] =
+{
+      30,    31,    32,    25,     1,     2,     3,    18,     4,    19,
+      42,     5,    52,     6,    17,    21,    53,    22,    26,    34,
+      35,    46,    47,    46,    48,    24,    27,    23,    33,    28,
+      39,    40,    41,    50,    44,    45,    56,    51,    49,    55,
+      38,    54,     0,    43
+};
+
+static const yytype_int8 yycheck[] =
+{
+      14,    15,    16,     0,     3,     4,     5,    16,     7,    18,
+      24,    10,     3,    12,    18,    16,     7,    18,    15,     6,
+       7,    15,    16,    15,    16,     3,     8,    17,     3,    18,
+       7,    11,    18,     9,    19,    19,    50,     3,    17,    11,
+      21,    46,    -1,    26
+};
+
+/* YYSTOS[STATE-NUM] -- The (internal number of the) accessing
+   symbol of state STATE-NUM.  */
+static const yytype_uint8 yystos[] =
+{
+       0,     3,     4,     5,     7,    10,    12,    21,    22,    23,
+      24,    25,    26,    27,    28,    29,    30,    18,    16,    18,
+      34,    16,    18,    17,     3,     0,    15,     8,    18,    33,
+      33,    33,    33,     3,     6,     7,    31,    32,    31,     7,
+      11,    18,    33,    22,    19,    19,    15,    16,    16,    17,
+       9,     3,     3,     7,    32,    11,    33
+};
+
+#define yyerrok		(yyerrstatus = 0)
+#define yyclearin	(yychar = YYEMPTY)
+#define YYEMPTY		(-2)
+#define YYEOF		0
+
+#define YYACCEPT	goto yyacceptlab
+#define YYABORT		goto yyabortlab
+#define YYERROR		goto yyerrorlab
+
+
+/* Like YYERROR except do call yyerror.  This remains here temporarily
+   to ease the transition to the new meaning of YYERROR, for GCC.
+   Once GCC version 2 has supplanted version 1, this can go.  However,
+   YYFAIL appears to be in use.  Nevertheless, it is formally deprecated
+   in Bison 2.4.2's NEWS entry, where a plan to phase it out is
+   discussed.  */
+
+#define YYFAIL		goto yyerrlab
+#if defined YYFAIL
+  /* This is here to suppress warnings from the GCC cpp's
+     -Wunused-macros.  Normally we don't worry about that warning, but
+     some users do, and we want to make it easy for users to remove
+     YYFAIL uses, which will produce warnings from Bison 2.5.  */
+#endif
+
+#define YYRECOVERING()  (!!yyerrstatus)
+
+#define YYBACKUP(Token, Value)					\
+do								\
+  if (yychar == YYEMPTY && yylen == 1)				\
+    {								\
+      yychar = (Token);						\
+      yylval = (Value);						\
+      yytoken = YYTRANSLATE (yychar);				\
+      YYPOPSTACK (1);						\
+      goto yybackup;						\
+    }								\
+  else								\
+    {								\
+      yyerror (list, idx, YY_("syntax error: cannot back up")); \
+      YYERROR;							\
+    }								\
+while (YYID (0))
+
+
+#define YYTERROR	1
+#define YYERRCODE	256
+
+
+/* YYLLOC_DEFAULT -- Set CURRENT to span from RHS[1] to RHS[N].
+   If N is 0, then set CURRENT to the empty location which ends
+   the previous symbol: RHS[0] (always defined).  */
+
+#define YYRHSLOC(Rhs, K) ((Rhs)[K])
+#ifndef YYLLOC_DEFAULT
+# define YYLLOC_DEFAULT(Current, Rhs, N)				\
+    do									\
+      if (YYID (N))                                                    \
+	{								\
+	  (Current).first_line   = YYRHSLOC (Rhs, 1).first_line;	\
+	  (Current).first_column = YYRHSLOC (Rhs, 1).first_column;	\
+	  (Current).last_line    = YYRHSLOC (Rhs, N).last_line;		\
+	  (Current).last_column  = YYRHSLOC (Rhs, N).last_column;	\
+	}								\
+      else								\
+	{								\
+	  (Current).first_line   = (Current).last_line   =		\
+	    YYRHSLOC (Rhs, 0).last_line;				\
+	  (Current).first_column = (Current).last_column =		\
+	    YYRHSLOC (Rhs, 0).last_column;				\
+	}								\
+    while (YYID (0))
+#endif
+
+
+/* YY_LOCATION_PRINT -- Print the location on the stream.
+   This macro was not mandated originally: define only if we know
+   we won't break user code: when these are the locations we know.  */
+
+#ifndef YY_LOCATION_PRINT
+# if defined YYLTYPE_IS_TRIVIAL && YYLTYPE_IS_TRIVIAL
+#  define YY_LOCATION_PRINT(File, Loc)			\
+     fprintf (File, "%d.%d-%d.%d",			\
+	      (Loc).first_line, (Loc).first_column,	\
+	      (Loc).last_line,  (Loc).last_column)
+# else
+#  define YY_LOCATION_PRINT(File, Loc) ((void) 0)
+# endif
+#endif
+
+
+/* YYLEX -- calling `yylex' with the right arguments.  */
+
+#ifdef YYLEX_PARAM
+# define YYLEX yylex (YYLEX_PARAM)
+#else
+# define YYLEX yylex ()
+#endif
+
+/* Enable debugging if requested.  */
+#if YYDEBUG
+
+# ifndef YYFPRINTF
+#  include <stdio.h> /* INFRINGES ON USER NAME SPACE */
+#  define YYFPRINTF fprintf
+# endif
+
+# define YYDPRINTF(Args)			\
+do {						\
+  if (yydebug)					\
+    YYFPRINTF Args;				\
+} while (YYID (0))
+
+# define YY_SYMBOL_PRINT(Title, Type, Value, Location)			  \
+do {									  \
+  if (yydebug)								  \
+    {									  \
+      YYFPRINTF (stderr, "%s ", Title);					  \
+      yy_symbol_print (stderr,						  \
+		  Type, Value, list, idx); \
+      YYFPRINTF (stderr, "\n");						  \
+    }									  \
+} while (YYID (0))
+
+
+/*--------------------------------.
+| Print this symbol on YYOUTPUT.  |
+`--------------------------------*/
+
+/*ARGSUSED*/
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_symbol_value_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep, struct list_head *list, int *idx)
+#else
+static void
+yy_symbol_value_print (yyoutput, yytype, yyvaluep, list, idx)
+    FILE *yyoutput;
+    int yytype;
+    YYSTYPE const * const yyvaluep;
+    struct list_head *list;
+    int *idx;
+#endif
+{
+  if (!yyvaluep)
+    return;
+  YYUSE (list);
+  YYUSE (idx);
+# ifdef YYPRINT
+  if (yytype < YYNTOKENS)
+    YYPRINT (yyoutput, yytoknum[yytype], *yyvaluep);
+# else
+  YYUSE (yyoutput);
+# endif
+  switch (yytype)
+    {
+      default:
+	break;
+    }
+}
+
+
+/*--------------------------------.
+| Print this symbol on YYOUTPUT.  |
+`--------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_symbol_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep, struct list_head *list, int *idx)
+#else
+static void
+yy_symbol_print (yyoutput, yytype, yyvaluep, list, idx)
+    FILE *yyoutput;
+    int yytype;
+    YYSTYPE const * const yyvaluep;
+    struct list_head *list;
+    int *idx;
+#endif
+{
+  if (yytype < YYNTOKENS)
+    YYFPRINTF (yyoutput, "token %s (", yytname[yytype]);
+  else
+    YYFPRINTF (yyoutput, "nterm %s (", yytname[yytype]);
+
+  yy_symbol_value_print (yyoutput, yytype, yyvaluep, list, idx);
+  YYFPRINTF (yyoutput, ")");
+}
+
+/*------------------------------------------------------------------.
+| yy_stack_print -- Print the state stack from its BOTTOM up to its |
+| TOP (included).                                                   |
+`------------------------------------------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_stack_print (yytype_int16 *yybottom, yytype_int16 *yytop)
+#else
+static void
+yy_stack_print (yybottom, yytop)
+    yytype_int16 *yybottom;
+    yytype_int16 *yytop;
+#endif
+{
+  YYFPRINTF (stderr, "Stack now");
+  for (; yybottom <= yytop; yybottom++)
+    {
+      int yybot = *yybottom;
+      YYFPRINTF (stderr, " %d", yybot);
+    }
+  YYFPRINTF (stderr, "\n");
+}
+
+# define YY_STACK_PRINT(Bottom, Top)				\
+do {								\
+  if (yydebug)							\
+    yy_stack_print ((Bottom), (Top));				\
+} while (YYID (0))
+
+
+/*------------------------------------------------.
+| Report that the YYRULE is going to be reduced.  |
+`------------------------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_reduce_print (YYSTYPE *yyvsp, int yyrule, struct list_head *list, int *idx)
+#else
+static void
+yy_reduce_print (yyvsp, yyrule, list, idx)
+    YYSTYPE *yyvsp;
+    int yyrule;
+    struct list_head *list;
+    int *idx;
+#endif
+{
+  int yynrhs = yyr2[yyrule];
+  int yyi;
+  unsigned long int yylno = yyrline[yyrule];
+  YYFPRINTF (stderr, "Reducing stack by rule %d (line %lu):\n",
+	     yyrule - 1, yylno);
+  /* The symbols being reduced.  */
+  for (yyi = 0; yyi < yynrhs; yyi++)
+    {
+      YYFPRINTF (stderr, "   $%d = ", yyi + 1);
+      yy_symbol_print (stderr, yyrhs[yyprhs[yyrule] + yyi],
+		       &(yyvsp[(yyi + 1) - (yynrhs)])
+		       		       , list, idx);
+      YYFPRINTF (stderr, "\n");
+    }
+}
+
+# define YY_REDUCE_PRINT(Rule)		\
+do {					\
+  if (yydebug)				\
+    yy_reduce_print (yyvsp, Rule, list, idx); \
+} while (YYID (0))
+
+/* Nonzero means print parse trace.  It is left uninitialized so that
+   multiple parsers can coexist.  */
+int yydebug;
+#else /* !YYDEBUG */
+# define YYDPRINTF(Args)
+# define YY_SYMBOL_PRINT(Title, Type, Value, Location)
+# define YY_STACK_PRINT(Bottom, Top)
+# define YY_REDUCE_PRINT(Rule)
+#endif /* !YYDEBUG */
+
+
+/* YYINITDEPTH -- initial size of the parser's stacks.  */
+#ifndef	YYINITDEPTH
+# define YYINITDEPTH 200
+#endif
+
+/* YYMAXDEPTH -- maximum size the stacks can grow to (effective only
+   if the built-in stack extension method is used).
+
+   Do not make this value too large; the results are undefined if
+   YYSTACK_ALLOC_MAXIMUM < YYSTACK_BYTES (YYMAXDEPTH)
+   evaluated with infinite-precision integer arithmetic.  */
+
+#ifndef YYMAXDEPTH
+# define YYMAXDEPTH 10000
+#endif
+
+
+
+#if YYERROR_VERBOSE
+
+# ifndef yystrlen
+#  if defined __GLIBC__ && defined _STRING_H
+#   define yystrlen strlen
+#  else
+/* Return the length of YYSTR.  */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static YYSIZE_T
+yystrlen (const char *yystr)
+#else
+static YYSIZE_T
+yystrlen (yystr)
+    const char *yystr;
+#endif
+{
+  YYSIZE_T yylen;
+  for (yylen = 0; yystr[yylen]; yylen++)
+    continue;
+  return yylen;
+}
+#  endif
+# endif
+
+# ifndef yystpcpy
+#  if defined __GLIBC__ && defined _STRING_H && defined _GNU_SOURCE
+#   define yystpcpy stpcpy
+#  else
+/* Copy YYSRC to YYDEST, returning the address of the terminating '\0' in
+   YYDEST.  */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static char *
+yystpcpy (char *yydest, const char *yysrc)
+#else
+static char *
+yystpcpy (yydest, yysrc)
+    char *yydest;
+    const char *yysrc;
+#endif
+{
+  char *yyd = yydest;
+  const char *yys = yysrc;
+
+  while ((*yyd++ = *yys++) != '\0')
+    continue;
+
+  return yyd - 1;
+}
+#  endif
+# endif
+
+# ifndef yytnamerr
+/* Copy to YYRES the contents of YYSTR after stripping away unnecessary
+   quotes and backslashes, so that it's suitable for yyerror.  The
+   heuristic is that double-quoting is unnecessary unless the string
+   contains an apostrophe, a comma, or backslash (other than
+   backslash-backslash).  YYSTR is taken from yytname.  If YYRES is
+   null, do not copy; instead, return the length of what the result
+   would have been.  */
+static YYSIZE_T
+yytnamerr (char *yyres, const char *yystr)
+{
+  if (*yystr == '"')
+    {
+      YYSIZE_T yyn = 0;
+      char const *yyp = yystr;
+
+      for (;;)
+	switch (*++yyp)
+	  {
+	  case '\'':
+	  case ',':
+	    goto do_not_strip_quotes;
+
+	  case '\\':
+	    if (*++yyp != '\\')
+	      goto do_not_strip_quotes;
+	    /* Fall through.  */
+	  default:
+	    if (yyres)
+	      yyres[yyn] = *yyp;
+	    yyn++;
+	    break;
+
+	  case '"':
+	    if (yyres)
+	      yyres[yyn] = '\0';
+	    return yyn;
+	  }
+    do_not_strip_quotes: ;
+    }
+
+  if (! yyres)
+    return yystrlen (yystr);
+
+  return yystpcpy (yyres, yystr) - yyres;
+}
+# endif
+
+/* Copy into YYRESULT an error message about the unexpected token
+   YYCHAR while in state YYSTATE.  Return the number of bytes copied,
+   including the terminating null byte.  If YYRESULT is null, do not
+   copy anything; just return the number of bytes that would be
+   copied.  As a special case, return 0 if an ordinary "syntax error"
+   message will do.  Return YYSIZE_MAXIMUM if overflow occurs during
+   size calculation.  */
+static YYSIZE_T
+yysyntax_error (char *yyresult, int yystate, int yychar)
+{
+  int yyn = yypact[yystate];
+
+  if (! (YYPACT_NINF < yyn && yyn <= YYLAST))
+    return 0;
+  else
+    {
+      int yytype = YYTRANSLATE (yychar);
+      YYSIZE_T yysize0 = yytnamerr (0, yytname[yytype]);
+      YYSIZE_T yysize = yysize0;
+      YYSIZE_T yysize1;
+      int yysize_overflow = 0;
+      enum { YYERROR_VERBOSE_ARGS_MAXIMUM = 5 };
+      char const *yyarg[YYERROR_VERBOSE_ARGS_MAXIMUM];
+      int yyx;
+
+# if 0
+      /* This is so xgettext sees the translatable formats that are
+	 constructed on the fly.  */
+      YY_("syntax error, unexpected %s");
+      YY_("syntax error, unexpected %s, expecting %s");
+      YY_("syntax error, unexpected %s, expecting %s or %s");
+      YY_("syntax error, unexpected %s, expecting %s or %s or %s");
+      YY_("syntax error, unexpected %s, expecting %s or %s or %s or %s");
+# endif
+      char *yyfmt;
+      char const *yyf;
+      static char const yyunexpected[] = "syntax error, unexpected %s";
+      static char const yyexpecting[] = ", expecting %s";
+      static char const yyor[] = " or %s";
+      char yyformat[sizeof yyunexpected
+		    + sizeof yyexpecting - 1
+		    + ((YYERROR_VERBOSE_ARGS_MAXIMUM - 2)
+		       * (sizeof yyor - 1))];
+      char const *yyprefix = yyexpecting;
+
+      /* Start YYX at -YYN if negative to avoid negative indexes in
+	 YYCHECK.  */
+      int yyxbegin = yyn < 0 ? -yyn : 0;
+
+      /* Stay within bounds of both yycheck and yytname.  */
+      int yychecklim = YYLAST - yyn + 1;
+      int yyxend = yychecklim < YYNTOKENS ? yychecklim : YYNTOKENS;
+      int yycount = 1;
+
+      yyarg[0] = yytname[yytype];
+      yyfmt = yystpcpy (yyformat, yyunexpected);
+
+      for (yyx = yyxbegin; yyx < yyxend; ++yyx)
+	if (yycheck[yyx + yyn] == yyx && yyx != YYTERROR)
+	  {
+	    if (yycount == YYERROR_VERBOSE_ARGS_MAXIMUM)
+	      {
+		yycount = 1;
+		yysize = yysize0;
+		yyformat[sizeof yyunexpected - 1] = '\0';
+		break;
+	      }
+	    yyarg[yycount++] = yytname[yyx];
+	    yysize1 = yysize + yytnamerr (0, yytname[yyx]);
+	    yysize_overflow |= (yysize1 < yysize);
+	    yysize = yysize1;
+	    yyfmt = yystpcpy (yyfmt, yyprefix);
+	    yyprefix = yyor;
+	  }
+
+      yyf = YY_(yyformat);
+      yysize1 = yysize + yystrlen (yyf);
+      yysize_overflow |= (yysize1 < yysize);
+      yysize = yysize1;
+
+      if (yysize_overflow)
+	return YYSIZE_MAXIMUM;
+
+      if (yyresult)
+	{
+	  /* Avoid sprintf, as that infringes on the user's name space.
+	     Don't have undefined behavior even if the translation
+	     produced a string with the wrong number of "%s"s.  */
+	  char *yyp = yyresult;
+	  int yyi = 0;
+	  while ((*yyp = *yyf) != '\0')
+	    {
+	      if (*yyp == '%' && yyf[1] == 's' && yyi < yycount)
+		{
+		  yyp += yytnamerr (yyp, yyarg[yyi++]);
+		  yyf += 2;
+		}
+	      else
+		{
+		  yyp++;
+		  yyf++;
+		}
+	    }
+	}
+      return yysize;
+    }
+}
+#endif /* YYERROR_VERBOSE */
+
+
+/*-----------------------------------------------.
+| Release the memory associated to this symbol.  |
+`-----------------------------------------------*/
+
+/*ARGSUSED*/
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yydestruct (const char *yymsg, int yytype, YYSTYPE *yyvaluep, struct list_head *list, int *idx)
+#else
+static void
+yydestruct (yymsg, yytype, yyvaluep, list, idx)
+    const char *yymsg;
+    int yytype;
+    YYSTYPE *yyvaluep;
+    struct list_head *list;
+    int *idx;
+#endif
+{
+  YYUSE (yyvaluep);
+  YYUSE (list);
+  YYUSE (idx);
+
+  if (!yymsg)
+    yymsg = "Deleting";
+  YY_SYMBOL_PRINT (yymsg, yytype, yyvaluep, yylocationp);
+
+  switch (yytype)
+    {
+
+      default:
+	break;
+    }
+}
+
+/* Prevent warnings from -Wmissing-prototypes.  */
+#ifdef YYPARSE_PARAM
+#if defined __STDC__ || defined __cplusplus
+int yyparse (void *YYPARSE_PARAM);
+#else
+int yyparse ();
+#endif
+#else /* ! YYPARSE_PARAM */
+#if defined __STDC__ || defined __cplusplus
+int yyparse (struct list_head *list, int *idx);
+#else
+int yyparse ();
+#endif
+#endif /* ! YYPARSE_PARAM */
+
+
+/* The lookahead symbol.  */
+int yychar;
+
+/* The semantic value of the lookahead symbol.  */
+YYSTYPE yylval;
+
+/* Number of syntax errors so far.  */
+int yynerrs;
+
+
+
+/*-------------------------.
+| yyparse or yypush_parse.  |
+`-------------------------*/
+
+#ifdef YYPARSE_PARAM
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+int
+yyparse (void *YYPARSE_PARAM)
+#else
+int
+yyparse (YYPARSE_PARAM)
+    void *YYPARSE_PARAM;
+#endif
+#else /* ! YYPARSE_PARAM */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+int
+yyparse (struct list_head *list, int *idx)
+#else
+int
+yyparse (list, idx)
+    struct list_head *list;
+    int *idx;
+#endif
+#endif
+{
+
+
+    int yystate;
+    /* Number of tokens to shift before error messages enabled.  */
+    int yyerrstatus;
+
+    /* The stacks and their tools:
+       `yyss': related to states.
+       `yyvs': related to semantic values.
+
+       Refer to the stacks thru separate pointers, to allow yyoverflow
+       to reallocate them elsewhere.  */
+
+    /* The state stack.  */
+    yytype_int16 yyssa[YYINITDEPTH];
+    yytype_int16 *yyss;
+    yytype_int16 *yyssp;
+
+    /* The semantic value stack.  */
+    YYSTYPE yyvsa[YYINITDEPTH];
+    YYSTYPE *yyvs;
+    YYSTYPE *yyvsp;
+
+    YYSIZE_T yystacksize;
+
+  int yyn;
+  int yyresult;
+  /* Lookahead token as an internal (translated) token number.  */
+  int yytoken;
+  /* The variables used to return semantic value and location from the
+     action routines.  */
+  YYSTYPE yyval;
+
+#if YYERROR_VERBOSE
+  /* Buffer for error messages, and its allocated size.  */
+  char yymsgbuf[128];
+  char *yymsg = yymsgbuf;
+  YYSIZE_T yymsg_alloc = sizeof yymsgbuf;
+#endif
+
+#define YYPOPSTACK(N)   (yyvsp -= (N), yyssp -= (N))
+
+  /* The number of symbols on the RHS of the reduced rule.
+     Keep to zero when no symbol should be popped.  */
+  int yylen = 0;
+
+  yytoken = 0;
+  yyss = yyssa;
+  yyvs = yyvsa;
+  yystacksize = YYINITDEPTH;
+
+  YYDPRINTF ((stderr, "Starting parse\n"));
+
+  yystate = 0;
+  yyerrstatus = 0;
+  yynerrs = 0;
+  yychar = YYEMPTY; /* Cause a token to be read.  */
+
+  /* Initialize stack pointers.
+     Waste one element of value and location stack
+     so that they stay on the same level as the state stack.
+     The wasted elements are never initialized.  */
+  yyssp = yyss;
+  yyvsp = yyvs;
+
+  goto yysetstate;
+
+/*------------------------------------------------------------.
+| yynewstate -- Push a new state, which is found in yystate.  |
+`------------------------------------------------------------*/
+ yynewstate:
+  /* In all cases, when you get here, the value and location stacks
+     have just been pushed.  So pushing a state here evens the stacks.  */
+  yyssp++;
+
+ yysetstate:
+  *yyssp = yystate;
+
+  if (yyss + yystacksize - 1 <= yyssp)
+    {
+      /* Get the current used size of the three stacks, in elements.  */
+      YYSIZE_T yysize = yyssp - yyss + 1;
+
+#ifdef yyoverflow
+      {
+	/* Give user a chance to reallocate the stack.  Use copies of
+	   these so that the &'s don't force the real ones into
+	   memory.  */
+	YYSTYPE *yyvs1 = yyvs;
+	yytype_int16 *yyss1 = yyss;
+
+	/* Each stack pointer address is followed by the size of the
+	   data in use in that stack, in bytes.  This used to be a
+	   conditional around just the two extra args, but that might
+	   be undefined if yyoverflow is a macro.  */
+	yyoverflow (YY_("memory exhausted"),
+		    &yyss1, yysize * sizeof (*yyssp),
+		    &yyvs1, yysize * sizeof (*yyvsp),
+		    &yystacksize);
+
+	yyss = yyss1;
+	yyvs = yyvs1;
+      }
+#else /* no yyoverflow */
+# ifndef YYSTACK_RELOCATE
+      goto yyexhaustedlab;
+# else
+      /* Extend the stack our own way.  */
+      if (YYMAXDEPTH <= yystacksize)
+	goto yyexhaustedlab;
+      yystacksize *= 2;
+      if (YYMAXDEPTH < yystacksize)
+	yystacksize = YYMAXDEPTH;
+
+      {
+	yytype_int16 *yyss1 = yyss;
+	union yyalloc *yyptr =
+	  (union yyalloc *) YYSTACK_ALLOC (YYSTACK_BYTES (yystacksize));
+	if (! yyptr)
+	  goto yyexhaustedlab;
+	YYSTACK_RELOCATE (yyss_alloc, yyss);
+	YYSTACK_RELOCATE (yyvs_alloc, yyvs);
+#  undef YYSTACK_RELOCATE
+	if (yyss1 != yyssa)
+	  YYSTACK_FREE (yyss1);
+      }
+# endif
+#endif /* no yyoverflow */
+
+      yyssp = yyss + yysize - 1;
+      yyvsp = yyvs + yysize - 1;
+
+      YYDPRINTF ((stderr, "Stack size increased to %lu\n",
+		  (unsigned long int) yystacksize));
+
+      if (yyss + yystacksize - 1 <= yyssp)
+	YYABORT;
+    }
+
+  YYDPRINTF ((stderr, "Entering state %d\n", yystate));
+
+  if (yystate == YYFINAL)
+    YYACCEPT;
+
+  goto yybackup;
+
+/*-----------.
+| yybackup.  |
+`-----------*/
+yybackup:
+
+  /* Do appropriate processing given the current state.  Read a
+     lookahead token if we need one and don't already have one.  */
+
+  /* First try to decide what to do without reference to lookahead token.  */
+  yyn = yypact[yystate];
+  if (yyn == YYPACT_NINF)
+    goto yydefault;
+
+  /* Not known => get a lookahead token if don't already have one.  */
+
+  /* YYCHAR is either YYEMPTY or YYEOF or a valid lookahead symbol.  */
+  if (yychar == YYEMPTY)
+    {
+      YYDPRINTF ((stderr, "Reading a token: "));
+      yychar = YYLEX;
+    }
+
+  if (yychar <= YYEOF)
+    {
+      yychar = yytoken = YYEOF;
+      YYDPRINTF ((stderr, "Now at end of input.\n"));
+    }
+  else
+    {
+      yytoken = YYTRANSLATE (yychar);
+      YY_SYMBOL_PRINT ("Next token is", yytoken, &yylval, &yylloc);
+    }
+
+  /* If the proper action on seeing token YYTOKEN is to reduce or to
+     detect an error, take that action.  */
+  yyn += yytoken;
+  if (yyn < 0 || YYLAST < yyn || yycheck[yyn] != yytoken)
+    goto yydefault;
+  yyn = yytable[yyn];
+  if (yyn <= 0)
+    {
+      if (yyn == 0 || yyn == YYTABLE_NINF)
+	goto yyerrlab;
+      yyn = -yyn;
+      goto yyreduce;
+    }
+
+  /* Count tokens shifted since error; after three, turn off error
+     status.  */
+  if (yyerrstatus)
+    yyerrstatus--;
+
+  /* Shift the lookahead token.  */
+  YY_SYMBOL_PRINT ("Shifting", yytoken, &yylval, &yylloc);
+
+  /* Discard the shifted token.  */
+  yychar = YYEMPTY;
+
+  yystate = yyn;
+  *++yyvsp = yylval;
+
+  goto yynewstate;
+
+
+/*-----------------------------------------------------------.
+| yydefault -- do the default action for the current state.  |
+`-----------------------------------------------------------*/
+yydefault:
+  yyn = yydefact[yystate];
+  if (yyn == 0)
+    goto yyerrlab;
+  goto yyreduce;
+
+
+/*-----------------------------.
+| yyreduce -- Do a reduction.  |
+`-----------------------------*/
+yyreduce:
+  /* yyn is the number of a rule to reduce with.  */
+  yylen = yyr2[yyn];
+
+  /* If YYLEN is nonzero, implement the default value of the action:
+     `$$ = $1'.
+
+     Otherwise, the following line sets YYVAL to garbage.
+     This behavior is undocumented and Bison
+     users should not rely upon it.  Assigning to YYVAL
+     unconditionally makes the parser a bit smaller, and it avoids a
+     GCC warning that YYVAL may be used uninitialized.  */
+  yyval = yyvsp[1-yylen];
+
+
+  YY_REDUCE_PRINT (yyn);
+  switch (yyn)
+    {
+        case 4:
+
+/* Line 1464 of yacc.c  */
+#line 58 "util/parse-events.y"
+    {
+	ABORT_ON(parse_events_modifier(list, (yyvsp[(2) - (2)].str)));
+;}
+    break;
+
+  case 13:
+
+/* Line 1464 of yacc.c  */
+#line 74 "util/parse-events.y"
+    {
+	ABORT_ON(parse_events_add_pmu(list, idx, (yyvsp[(1) - (4)].str), (yyvsp[(3) - (4)].head)));
+	parse_events__free_terms((yyvsp[(3) - (4)].head));
+;}
+    break;
+
+  case 14:
+
+/* Line 1464 of yacc.c  */
+#line 81 "util/parse-events.y"
+    {
+	int type = (yyvsp[(1) - (4)].num) >> 16;
+	int config = (yyvsp[(1) - (4)].num) & 255;
+
+	ABORT_ON(parse_events_add_numeric(list, idx, type, config, (yyvsp[(3) - (4)].head)));
+	parse_events__free_terms((yyvsp[(3) - (4)].head));
+;}
+    break;
+
+  case 15:
+
+/* Line 1464 of yacc.c  */
+#line 90 "util/parse-events.y"
+    {
+	int type = (yyvsp[(1) - (2)].num) >> 16;
+	int config = (yyvsp[(1) - (2)].num) & 255;
+
+	ABORT_ON(parse_events_add_numeric(list, idx, type, config, NULL));
+;}
+    break;
+
+  case 16:
+
+/* Line 1464 of yacc.c  */
+#line 99 "util/parse-events.y"
+    {
+	ABORT_ON(parse_events_add_cache(list, idx, (yyvsp[(1) - (5)].str), (yyvsp[(3) - (5)].str), (yyvsp[(5) - (5)].str)));
+;}
+    break;
+
+  case 17:
+
+/* Line 1464 of yacc.c  */
+#line 104 "util/parse-events.y"
+    {
+	ABORT_ON(parse_events_add_cache(list, idx, (yyvsp[(1) - (3)].str), (yyvsp[(3) - (3)].str), NULL));
+;}
+    break;
+
+  case 18:
+
+/* Line 1464 of yacc.c  */
+#line 109 "util/parse-events.y"
+    {
+	ABORT_ON(parse_events_add_cache(list, idx, (yyvsp[(1) - (1)].str), NULL, NULL));
+;}
+    break;
+
+  case 19:
+
+/* Line 1464 of yacc.c  */
+#line 115 "util/parse-events.y"
+    {
+	ABORT_ON(parse_events_add_breakpoint(list, idx, (void *) (yyvsp[(2) - (5)].num), (yyvsp[(4) - (5)].str)));
+;}
+    break;
+
+  case 20:
+
+/* Line 1464 of yacc.c  */
+#line 120 "util/parse-events.y"
+    {
+	ABORT_ON(parse_events_add_breakpoint(list, idx, (void *) (yyvsp[(2) - (3)].num), NULL));
+;}
+    break;
+
+  case 21:
+
+/* Line 1464 of yacc.c  */
+#line 126 "util/parse-events.y"
+    {
+	ABORT_ON(parse_events_add_tracepoint(list, idx, (yyvsp[(1) - (3)].str), (yyvsp[(3) - (3)].str)));
+;}
+    break;
+
+  case 22:
+
+/* Line 1464 of yacc.c  */
+#line 132 "util/parse-events.y"
+    {
+	ABORT_ON(parse_events_add_numeric(list, idx, (yyvsp[(1) - (3)].num), (yyvsp[(3) - (3)].num), NULL));
+;}
+    break;
+
+  case 23:
+
+/* Line 1464 of yacc.c  */
+#line 138 "util/parse-events.y"
+    {
+	ABORT_ON(parse_events_add_numeric(list, idx, PERF_TYPE_RAW, (yyvsp[(1) - (1)].num), NULL));
+;}
+    break;
+
+  case 24:
+
+/* Line 1464 of yacc.c  */
+#line 144 "util/parse-events.y"
+    {
+	struct list_head *head = (yyvsp[(1) - (3)].head);
+	struct parse_events__term *term = (yyvsp[(3) - (3)].term);
+
+	ABORT_ON(!head);
+	list_add_tail(&term->list, head);
+	(yyval.head) = (yyvsp[(1) - (3)].head);
+;}
+    break;
+
+  case 25:
+
+/* Line 1464 of yacc.c  */
+#line 154 "util/parse-events.y"
+    {
+	struct list_head *head = malloc(sizeof(*head));
+	struct parse_events__term *term = (yyvsp[(1) - (1)].term);
+
+	ABORT_ON(!head);
+	INIT_LIST_HEAD(head);
+	list_add_tail(&term->list, head);
+	(yyval.head) = head;
+;}
+    break;
+
+  case 26:
+
+/* Line 1464 of yacc.c  */
+#line 166 "util/parse-events.y"
+    {
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, PARSE_EVENTS__TERM_TYPE_STR,
+		 (yyvsp[(1) - (3)].str), (yyvsp[(3) - (3)].str), 0));
+	(yyval.term) = term;
+;}
+    break;
+
+  case 27:
+
+/* Line 1464 of yacc.c  */
+#line 175 "util/parse-events.y"
+    {
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, PARSE_EVENTS__TERM_TYPE_NUM,
+		 (yyvsp[(1) - (3)].str), NULL, (yyvsp[(3) - (3)].num)));
+	(yyval.term) = term;
+;}
+    break;
+
+  case 28:
+
+/* Line 1464 of yacc.c  */
+#line 184 "util/parse-events.y"
+    {
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, PARSE_EVENTS__TERM_TYPE_NUM,
+		 (yyvsp[(1) - (1)].str), NULL, 1));
+	(yyval.term) = term;
+;}
+    break;
+
+  case 29:
+
+/* Line 1464 of yacc.c  */
+#line 193 "util/parse-events.y"
+    {
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, (yyvsp[(1) - (3)].num), NULL, NULL, (yyvsp[(3) - (3)].num)));
+	(yyval.term) = term;
+;}
+    break;
+
+  case 30:
+
+/* Line 1464 of yacc.c  */
+#line 201 "util/parse-events.y"
+    {
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, (yyvsp[(1) - (1)].num), NULL, NULL, 1));
+	(yyval.term) = term;
+;}
+    break;
+
+
+
+/* Line 1464 of yacc.c  */
+#line 1634 "util/parse-events-bison.c"
+      default: break;
+    }
+  YY_SYMBOL_PRINT ("-> $$ =", yyr1[yyn], &yyval, &yyloc);
+
+  YYPOPSTACK (yylen);
+  yylen = 0;
+  YY_STACK_PRINT (yyss, yyssp);
+
+  *++yyvsp = yyval;
+
+  /* Now `shift' the result of the reduction.  Determine what state
+     that goes to, based on the state we popped back to and the rule
+     number reduced by.  */
+
+  yyn = yyr1[yyn];
+
+  yystate = yypgoto[yyn - YYNTOKENS] + *yyssp;
+  if (0 <= yystate && yystate <= YYLAST && yycheck[yystate] == *yyssp)
+    yystate = yytable[yystate];
+  else
+    yystate = yydefgoto[yyn - YYNTOKENS];
+
+  goto yynewstate;
+
+
+/*------------------------------------.
+| yyerrlab -- here on detecting error |
+`------------------------------------*/
+yyerrlab:
+  /* If not already recovering from an error, report this error.  */
+  if (!yyerrstatus)
+    {
+      ++yynerrs;
+#if ! YYERROR_VERBOSE
+      yyerror (list, idx, YY_("syntax error"));
+#else
+      {
+	YYSIZE_T yysize = yysyntax_error (0, yystate, yychar);
+	if (yymsg_alloc < yysize && yymsg_alloc < YYSTACK_ALLOC_MAXIMUM)
+	  {
+	    YYSIZE_T yyalloc = 2 * yysize;
+	    if (! (yysize <= yyalloc && yyalloc <= YYSTACK_ALLOC_MAXIMUM))
+	      yyalloc = YYSTACK_ALLOC_MAXIMUM;
+	    if (yymsg != yymsgbuf)
+	      YYSTACK_FREE (yymsg);
+	    yymsg = (char *) YYSTACK_ALLOC (yyalloc);
+	    if (yymsg)
+	      yymsg_alloc = yyalloc;
+	    else
+	      {
+		yymsg = yymsgbuf;
+		yymsg_alloc = sizeof yymsgbuf;
+	      }
+	  }
+
+	if (0 < yysize && yysize <= yymsg_alloc)
+	  {
+	    (void) yysyntax_error (yymsg, yystate, yychar);
+	    yyerror (list, idx, yymsg);
+	  }
+	else
+	  {
+	    yyerror (list, idx, YY_("syntax error"));
+	    if (yysize != 0)
+	      goto yyexhaustedlab;
+	  }
+      }
+#endif
+    }
+
+
+
+  if (yyerrstatus == 3)
+    {
+      /* If just tried and failed to reuse lookahead token after an
+	 error, discard it.  */
+
+      if (yychar <= YYEOF)
+	{
+	  /* Return failure if at end of input.  */
+	  if (yychar == YYEOF)
+	    YYABORT;
+	}
+      else
+	{
+	  yydestruct ("Error: discarding",
+		      yytoken, &yylval, list, idx);
+	  yychar = YYEMPTY;
+	}
+    }
+
+  /* Else will try to reuse lookahead token after shifting the error
+     token.  */
+  goto yyerrlab1;
+
+
+/*---------------------------------------------------.
+| yyerrorlab -- error raised explicitly by YYERROR.  |
+`---------------------------------------------------*/
+yyerrorlab:
+
+  /* Pacify compilers like GCC when the user code never invokes
+     YYERROR and the label yyerrorlab therefore never appears in user
+     code.  */
+  if (/*CONSTCOND*/ 0)
+     goto yyerrorlab;
+
+  /* Do not reclaim the symbols of the rule which action triggered
+     this YYERROR.  */
+  YYPOPSTACK (yylen);
+  yylen = 0;
+  YY_STACK_PRINT (yyss, yyssp);
+  yystate = *yyssp;
+  goto yyerrlab1;
+
+
+/*-------------------------------------------------------------.
+| yyerrlab1 -- common code for both syntax error and YYERROR.  |
+`-------------------------------------------------------------*/
+yyerrlab1:
+  yyerrstatus = 3;	/* Each real token shifted decrements this.  */
+
+  for (;;)
+    {
+      yyn = yypact[yystate];
+      if (yyn != YYPACT_NINF)
+	{
+	  yyn += YYTERROR;
+	  if (0 <= yyn && yyn <= YYLAST && yycheck[yyn] == YYTERROR)
+	    {
+	      yyn = yytable[yyn];
+	      if (0 < yyn)
+		break;
+	    }
+	}
+
+      /* Pop the current state because it cannot handle the error token.  */
+      if (yyssp == yyss)
+	YYABORT;
+
+
+      yydestruct ("Error: popping",
+		  yystos[yystate], yyvsp, list, idx);
+      YYPOPSTACK (1);
+      yystate = *yyssp;
+      YY_STACK_PRINT (yyss, yyssp);
+    }
+
+  *++yyvsp = yylval;
+
+
+  /* Shift the error token.  */
+  YY_SYMBOL_PRINT ("Shifting", yystos[yyn], yyvsp, yylsp);
+
+  yystate = yyn;
+  goto yynewstate;
+
+
+/*-------------------------------------.
+| yyacceptlab -- YYACCEPT comes here.  |
+`-------------------------------------*/
+yyacceptlab:
+  yyresult = 0;
+  goto yyreturn;
+
+/*-----------------------------------.
+| yyabortlab -- YYABORT comes here.  |
+`-----------------------------------*/
+yyabortlab:
+  yyresult = 1;
+  goto yyreturn;
+
+#if !defined(yyoverflow) || YYERROR_VERBOSE
+/*-------------------------------------------------.
+| yyexhaustedlab -- memory exhaustion comes here.  |
+`-------------------------------------------------*/
+yyexhaustedlab:
+  yyerror (list, idx, YY_("memory exhausted"));
+  yyresult = 2;
+  /* Fall through.  */
+#endif
+
+yyreturn:
+  if (yychar != YYEMPTY)
+     yydestruct ("Cleanup: discarding lookahead",
+		 yytoken, &yylval, list, idx);
+  /* Do not reclaim the symbols of the rule which action triggered
+     this YYABORT or YYACCEPT.  */
+  YYPOPSTACK (yylen);
+  YY_STACK_PRINT (yyss, yyssp);
+  while (yyssp != yyss)
+    {
+      yydestruct ("Cleanup: popping",
+		  yystos[*yyssp], yyvsp, list, idx);
+      YYPOPSTACK (1);
+    }
+#ifndef yyoverflow
+  if (yyss != yyssa)
+    YYSTACK_FREE (yyss);
+#endif
+#if YYERROR_VERBOSE
+  if (yymsg != yymsgbuf)
+    YYSTACK_FREE (yymsg);
+#endif
+  /* Make sure YYID is used.  */
+  return YYID (yyresult);
+}
+
+
+
+/* Line 1684 of yacc.c  */
+#line 212 "util/parse-events.y"
+
+
+void parse_events_error(struct list_head *list __used, int *idx __used,
+			char const *msg __used)
+{
+}
+
diff --git a/tools/perf/util/parse-events-bison.h b/tools/perf/util/parse-events-bison.h
new file mode 100644
index 0000000..c58b765
--- /dev/null
+++ b/tools/perf/util/parse-events-bison.h
@@ -0,0 +1,82 @@
+/* A Bison parser, made by GNU Bison 2.4.3.  */
+
+/* Skeleton interface for Bison's Yacc-like parsers in C
+   
+      Copyright (C) 1984, 1989, 1990, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
+   2009, 2010 Free Software Foundation, Inc.
+   
+   This program is free software: you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation, either version 3 of the License, or
+   (at your option) any later version.
+   
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+   
+   You should have received a copy of the GNU General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
+
+/* As a special exception, you may create a larger work that contains
+   part or all of the Bison parser skeleton and distribute that work
+   under terms of your choice, so long as that work isn't itself a
+   parser generator using the skeleton or a modified version thereof
+   as a parser skeleton.  Alternatively, if you modify or redistribute
+   the parser skeleton itself, you may (at your option) remove this
+   special exception, which will cause the skeleton and the resulting
+   Bison output files to be licensed under the GNU General Public
+   License without this special exception.
+   
+   This special exception was added by the Free Software Foundation in
+   version 2.2 of Bison.  */
+
+
+/* Tokens.  */
+#ifndef YYTOKENTYPE
+# define YYTOKENTYPE
+   /* Put the tokens into the symbol table, so that GDB and other debuggers
+      know about them.  */
+   enum yytokentype {
+     PE_VALUE = 258,
+     PE_VALUE_SYM = 259,
+     PE_RAW = 260,
+     PE_TERM = 261,
+     PE_NAME = 262,
+     PE_MODIFIER_EVENT = 263,
+     PE_MODIFIER_BP = 264,
+     PE_NAME_CACHE_TYPE = 265,
+     PE_NAME_CACHE_OP_RESULT = 266,
+     PE_PREFIX_MEM = 267,
+     PE_PREFIX_RAW = 268,
+     PE_ERROR = 269
+   };
+#endif
+
+
+
+#if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED
+typedef union YYSTYPE
+{
+
+/* Line 1685 of yacc.c  */
+#line 45 "util/parse-events.y"
+
+	char *str;
+	unsigned long num;
+	struct list_head *head;
+	struct parse_events__term *term;
+
+
+
+/* Line 1685 of yacc.c  */
+#line 74 "util/parse-events-bison.h"
+} YYSTYPE;
+# define YYSTYPE_IS_TRIVIAL 1
+# define yystype YYSTYPE /* obsolescent; will be withdrawn */
+# define YYSTYPE_IS_DECLARED 1
+#endif
+
+extern YYSTYPE parse_events_lval;
+
+
diff --git a/tools/perf/util/parse-events-flex.c b/tools/perf/util/parse-events-flex.c
new file mode 100644
index 0000000..34cfc85
--- /dev/null
+++ b/tools/perf/util/parse-events-flex.c
@@ -0,0 +1,2272 @@
+
+#line 3 "<stdout>"
+
+#define  YY_INT_ALIGNED short int
+
+/* A lexical scanner generated by flex */
+
+#define yy_create_buffer parse_events__create_buffer
+#define yy_delete_buffer parse_events__delete_buffer
+#define yy_flex_debug parse_events__flex_debug
+#define yy_init_buffer parse_events__init_buffer
+#define yy_flush_buffer parse_events__flush_buffer
+#define yy_load_buffer_state parse_events__load_buffer_state
+#define yy_switch_to_buffer parse_events__switch_to_buffer
+#define yyin parse_events_in
+#define yyleng parse_events_leng
+#define yylex parse_events_lex
+#define yylineno parse_events_lineno
+#define yyout parse_events_out
+#define yyrestart parse_events_restart
+#define yytext parse_events_text
+#define yywrap parse_events_wrap
+#define yyalloc parse_events_alloc
+#define yyrealloc parse_events_realloc
+#define yyfree parse_events_free
+
+#define FLEX_SCANNER
+#define YY_FLEX_MAJOR_VERSION 2
+#define YY_FLEX_MINOR_VERSION 5
+#define YY_FLEX_SUBMINOR_VERSION 35
+#if YY_FLEX_SUBMINOR_VERSION > 0
+#define FLEX_BETA
+#endif
+
+/* First, we deal with  platform-specific or compiler-specific issues. */
+
+/* begin standard C headers. */
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <stdlib.h>
+
+/* end standard C headers. */
+
+/* flex integer type definitions */
+
+#ifndef FLEXINT_H
+#define FLEXINT_H
+
+/* C99 systems have <inttypes.h>. Non-C99 systems may or may not. */
+
+#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+
+/* C99 says to define __STDC_LIMIT_MACROS before including stdint.h,
+ * if you want the limit (max/min) macros for int types. 
+ */
+#ifndef __STDC_LIMIT_MACROS
+#define __STDC_LIMIT_MACROS 1
+#endif
+
+#include <inttypes.h>
+typedef int8_t flex_int8_t;
+typedef uint8_t flex_uint8_t;
+typedef int16_t flex_int16_t;
+typedef uint16_t flex_uint16_t;
+typedef int32_t flex_int32_t;
+typedef uint32_t flex_uint32_t;
+#else
+typedef signed char flex_int8_t;
+typedef short int flex_int16_t;
+typedef int flex_int32_t;
+typedef unsigned char flex_uint8_t; 
+typedef unsigned short int flex_uint16_t;
+typedef unsigned int flex_uint32_t;
+#endif /* ! C99 */
+
+/* Limits of integral types. */
+#ifndef INT8_MIN
+#define INT8_MIN               (-128)
+#endif
+#ifndef INT16_MIN
+#define INT16_MIN              (-32767-1)
+#endif
+#ifndef INT32_MIN
+#define INT32_MIN              (-2147483647-1)
+#endif
+#ifndef INT8_MAX
+#define INT8_MAX               (127)
+#endif
+#ifndef INT16_MAX
+#define INT16_MAX              (32767)
+#endif
+#ifndef INT32_MAX
+#define INT32_MAX              (2147483647)
+#endif
+#ifndef UINT8_MAX
+#define UINT8_MAX              (255U)
+#endif
+#ifndef UINT16_MAX
+#define UINT16_MAX             (65535U)
+#endif
+#ifndef UINT32_MAX
+#define UINT32_MAX             (4294967295U)
+#endif
+
+#endif /* ! FLEXINT_H */
+
+#ifdef __cplusplus
+
+/* The "const" storage-class-modifier is valid. */
+#define YY_USE_CONST
+
+#else	/* ! __cplusplus */
+
+/* C99 requires __STDC__ to be defined as 1. */
+#if defined (__STDC__)
+
+#define YY_USE_CONST
+
+#endif	/* defined (__STDC__) */
+#endif	/* ! __cplusplus */
+
+#ifdef YY_USE_CONST
+#define yyconst const
+#else
+#define yyconst
+#endif
+
+/* Returned upon end-of-file. */
+#define YY_NULL 0
+
+/* Promotes a possibly negative, possibly signed char to an unsigned
+ * integer for use as an array index.  If the signed char is negative,
+ * we want to instead treat it as an 8-bit unsigned char, hence the
+ * double cast.
+ */
+#define YY_SC_TO_UI(c) ((unsigned int) (unsigned char) c)
+
+/* Enter a start condition.  This macro really ought to take a parameter,
+ * but we do it the disgusting crufty way forced on us by the ()-less
+ * definition of BEGIN.
+ */
+#define BEGIN (yy_start) = 1 + 2 *
+
+/* Translate the current start state into a value that can be later handed
+ * to BEGIN to return to the state.  The YYSTATE alias is for lex
+ * compatibility.
+ */
+#define YY_START (((yy_start) - 1) / 2)
+#define YYSTATE YY_START
+
+/* Action number for EOF rule of a given start state. */
+#define YY_STATE_EOF(state) (YY_END_OF_BUFFER + state + 1)
+
+/* Special action meaning "start processing a new file". */
+#define YY_NEW_FILE parse_events_restart(parse_events_in  )
+
+#define YY_END_OF_BUFFER_CHAR 0
+
+/* Size of default input buffer. */
+#ifndef YY_BUF_SIZE
+#define YY_BUF_SIZE 16384
+#endif
+
+/* The state buf must be large enough to hold one state per character in the main buffer.
+ */
+#define YY_STATE_BUF_SIZE   ((YY_BUF_SIZE + 2) * sizeof(yy_state_type))
+
+#ifndef YY_TYPEDEF_YY_BUFFER_STATE
+#define YY_TYPEDEF_YY_BUFFER_STATE
+typedef struct yy_buffer_state *YY_BUFFER_STATE;
+#endif
+
+extern int parse_events_leng;
+
+extern FILE *parse_events_in, *parse_events_out;
+
+#define EOB_ACT_CONTINUE_SCAN 0
+#define EOB_ACT_END_OF_FILE 1
+#define EOB_ACT_LAST_MATCH 2
+
+    #define YY_LESS_LINENO(n)
+    
+/* Return all but the first "n" matched characters back to the input stream. */
+#define yyless(n) \
+	do \
+		{ \
+		/* Undo effects of setting up parse_events_text. */ \
+        int yyless_macro_arg = (n); \
+        YY_LESS_LINENO(yyless_macro_arg);\
+		*yy_cp = (yy_hold_char); \
+		YY_RESTORE_YY_MORE_OFFSET \
+		(yy_c_buf_p) = yy_cp = yy_bp + yyless_macro_arg - YY_MORE_ADJ; \
+		YY_DO_BEFORE_ACTION; /* set up parse_events_text again */ \
+		} \
+	while ( 0 )
+
+#define unput(c) yyunput( c, (yytext_ptr)  )
+
+#ifndef YY_TYPEDEF_YY_SIZE_T
+#define YY_TYPEDEF_YY_SIZE_T
+typedef size_t yy_size_t;
+#endif
+
+#ifndef YY_STRUCT_YY_BUFFER_STATE
+#define YY_STRUCT_YY_BUFFER_STATE
+struct yy_buffer_state
+	{
+	FILE *yy_input_file;
+
+	char *yy_ch_buf;		/* input buffer */
+	char *yy_buf_pos;		/* current position in input buffer */
+
+	/* Size of input buffer in bytes, not including room for EOB
+	 * characters.
+	 */
+	yy_size_t yy_buf_size;
+
+	/* Number of characters read into yy_ch_buf, not including EOB
+	 * characters.
+	 */
+	int yy_n_chars;
+
+	/* Whether we "own" the buffer - i.e., we know we created it,
+	 * and can realloc() it to grow it, and should free() it to
+	 * delete it.
+	 */
+	int yy_is_our_buffer;
+
+	/* Whether this is an "interactive" input source; if so, and
+	 * if we're using stdio for input, then we want to use getc()
+	 * instead of fread(), to make sure we stop fetching input after
+	 * each newline.
+	 */
+	int yy_is_interactive;
+
+	/* Whether we're considered to be at the beginning of a line.
+	 * If so, '^' rules will be active on the next match, otherwise
+	 * not.
+	 */
+	int yy_at_bol;
+
+    int yy_bs_lineno; /**< The line count. */
+    int yy_bs_column; /**< The column count. */
+    
+	/* Whether to try to fill the input buffer when we reach the
+	 * end of it.
+	 */
+	int yy_fill_buffer;
+
+	int yy_buffer_status;
+
+#define YY_BUFFER_NEW 0
+#define YY_BUFFER_NORMAL 1
+	/* When an EOF's been seen but there's still some text to process
+	 * then we mark the buffer as YY_EOF_PENDING, to indicate that we
+	 * shouldn't try reading from the input source any more.  We might
+	 * still have a bunch of tokens to match, though, because of
+	 * possible backing-up.
+	 *
+	 * When we actually see the EOF, we change the status to "new"
+	 * (via parse_events_restart()), so that the user can continue scanning by
+	 * just pointing parse_events_in at a new input file.
+	 */
+#define YY_BUFFER_EOF_PENDING 2
+
+	};
+#endif /* !YY_STRUCT_YY_BUFFER_STATE */
+
+/* Stack of input buffers. */
+static size_t yy_buffer_stack_top = 0; /**< index of top of stack. */
+static size_t yy_buffer_stack_max = 0; /**< capacity of stack. */
+static YY_BUFFER_STATE * yy_buffer_stack = 0; /**< Stack as an array. */
+
+/* We provide macros for accessing buffer states in case in the
+ * future we want to put the buffer states in a more general
+ * "scanner state".
+ *
+ * Returns the top of the stack, or NULL.
+ */
+#define YY_CURRENT_BUFFER ( (yy_buffer_stack) \
+                          ? (yy_buffer_stack)[(yy_buffer_stack_top)] \
+                          : NULL)
+
+/* Same as previous macro, but useful when we know that the buffer stack is not
+ * NULL or when we need an lvalue. For internal use only.
+ */
+#define YY_CURRENT_BUFFER_LVALUE (yy_buffer_stack)[(yy_buffer_stack_top)]
+
+/* yy_hold_char holds the character lost when parse_events_text is formed. */
+static char yy_hold_char;
+static int yy_n_chars;		/* number of characters read into yy_ch_buf */
+int parse_events_leng;
+
+/* Points to current character in buffer. */
+static char *yy_c_buf_p = (char *) 0;
+static int yy_init = 0;		/* whether we need to initialize */
+static int yy_start = 0;	/* start state number */
+
+/* Flag which is used to allow parse_events_wrap()'s to do buffer switches
+ * instead of setting up a fresh parse_events_in.  A bit of a hack ...
+ */
+static int yy_did_buffer_switch_on_eof;
+
+void parse_events_restart (FILE *input_file  );
+void parse_events__switch_to_buffer (YY_BUFFER_STATE new_buffer  );
+YY_BUFFER_STATE parse_events__create_buffer (FILE *file,int size  );
+void parse_events__delete_buffer (YY_BUFFER_STATE b  );
+void parse_events__flush_buffer (YY_BUFFER_STATE b  );
+void parse_events_push_buffer_state (YY_BUFFER_STATE new_buffer  );
+void parse_events_pop_buffer_state (void );
+
+static void parse_events_ensure_buffer_stack (void );
+static void parse_events__load_buffer_state (void );
+static void parse_events__init_buffer (YY_BUFFER_STATE b,FILE *file  );
+
+#define YY_FLUSH_BUFFER parse_events__flush_buffer(YY_CURRENT_BUFFER )
+
+YY_BUFFER_STATE parse_events__scan_buffer (char *base,yy_size_t size  );
+YY_BUFFER_STATE parse_events__scan_string (yyconst char *yy_str  );
+YY_BUFFER_STATE parse_events__scan_bytes (yyconst char *bytes,int len  );
+
+void *parse_events_alloc (yy_size_t  );
+void *parse_events_realloc (void *,yy_size_t  );
+void parse_events_free (void *  );
+
+#define yy_new_buffer parse_events__create_buffer
+
+#define yy_set_interactive(is_interactive) \
+	{ \
+	if ( ! YY_CURRENT_BUFFER ){ \
+        parse_events_ensure_buffer_stack (); \
+		YY_CURRENT_BUFFER_LVALUE =    \
+            parse_events__create_buffer(parse_events_in,YY_BUF_SIZE ); \
+	} \
+	YY_CURRENT_BUFFER_LVALUE->yy_is_interactive = is_interactive; \
+	}
+
+#define yy_set_bol(at_bol) \
+	{ \
+	if ( ! YY_CURRENT_BUFFER ){\
+        parse_events_ensure_buffer_stack (); \
+		YY_CURRENT_BUFFER_LVALUE =    \
+            parse_events__create_buffer(parse_events_in,YY_BUF_SIZE ); \
+	} \
+	YY_CURRENT_BUFFER_LVALUE->yy_at_bol = at_bol; \
+	}
+
+#define YY_AT_BOL() (YY_CURRENT_BUFFER_LVALUE->yy_at_bol)
+
+/* Begin user sect3 */
+
+typedef unsigned char YY_CHAR;
+
+FILE *parse_events_in = (FILE *) 0, *parse_events_out = (FILE *) 0;
+
+typedef int yy_state_type;
+
+extern int parse_events_lineno;
+
+int parse_events_lineno = 1;
+
+extern char *parse_events_text;
+#define yytext_ptr parse_events_text
+
+static yy_state_type yy_get_previous_state (void );
+static yy_state_type yy_try_NUL_trans (yy_state_type current_state  );
+static int yy_get_next_buffer (void );
+static void yy_fatal_error (yyconst char msg[]  );
+
+/* Done after the current pattern has been matched and before the
+ * corresponding action - sets up parse_events_text.
+ */
+#define YY_DO_BEFORE_ACTION \
+	(yytext_ptr) = yy_bp; \
+	parse_events_leng = (size_t) (yy_cp - yy_bp); \
+	(yy_hold_char) = *yy_cp; \
+	*yy_cp = '\0'; \
+	(yy_c_buf_p) = yy_cp;
+
+#define YY_NUM_RULES 49
+#define YY_END_OF_BUFFER 50
+/* This struct is not used in this scanner,
+   but its presence is necessary. */
+struct yy_trans_info
+	{
+	flex_int32_t yy_verify;
+	flex_int32_t yy_nxt;
+	};
+static yyconst flex_int16_t yy_accept[440] =
+    {   0,
+        0,    0,   50,   49,   43,   46,   45,   44,   39,   39,
+       47,   48,   43,   43,   43,   43,   43,   43,   43,   43,
+       43,   43,   41,   43,   43,   43,   43,   43,   41,   42,
+       43,   43,   42,   42,   43,   39,    0,   43,   43,   43,
+       21,   43,   43,   43,   43,   43,   43,   43,   43,   43,
+       43,   43,   15,   43,    0,   43,   43,   43,   41,    0,
+       43,   43,   43,   43,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   38,   38,   43,   43,   43,   43,   40,
+       43,   43,    0,   43,   43,   43,   24,   43,   43,   43,
+       43,   43,   43,    0,   43,   43,   43,   41,    0,   43,
+
+       43,   43,    0,   19,   20,   43,   43,   43,   43,   43,
+       43,   43,   30,   43,   43,   43,   38,   38,   43,   43,
+       43,   43,   43,   43,   43,    0,    0,   43,   43,   43,
+       43,    0,   43,   43,   43,    0,   43,    0,   22,   43,
+       43,   41,    0,   23,   43,   43,   19,   20,   26,   43,
+       37,   43,   43,   31,   25,   43,   43,   43,   26,   43,
+       43,   43,   43,   43,    0,   43,    0,    0,    0,    0,
+       43,   43,   43,   43,    0,   43,   43,   43,    0,    0,
+       43,   22,   43,   43,   41,   23,    0,   43,   26,   43,
+       43,   43,   43,    0,   43,   43,   43,   43,   27,    0,
+
+       27,    0,   43,    0,    0,    0,    0,   43,   43,   24,
+        0,    0,   32,   43,    0,    0,    0,    1,   43,   12,
+        0,   43,    0,   43,    0,   31,    0,   35,   43,   43,
+       43,    0,    0,   43,    0,    0,    0,   43,   43,    0,
+       43,   43,    0,    0,    0,   33,   34,   43,    0,    0,
+        0,   43,    0,   43,    0,   43,    0,    0,   43,   43,
+       43,    0,   43,    0,    0,    0,   43,   43,    0,    0,
+       43,    7,    0,    0,    0,    0,    0,    0,    0,   43,
+        0,   43,    0,   43,    0,    0,   28,   43,    0,    0,
+       43,    0,   43,    0,    0,   43,    0,    0,    0,    0,
+
+       10,    0,    0,   43,    0,   43,    0,   43,    0,    0,
+       43,   43,    0,    0,   43,    0,    0,    0,    0,   43,
+        9,    0,    0,    0,    1,    0,    0,    0,   43,    0,
+       16,    0,    0,   28,   43,    0,   11,   43,    0,    0,
+        0,    0,   36,    0,    0,    0,    0,    0,    0,   43,
+        0,    0,   12,   43,    0,    0,    0,    0,    0,    0,
+        6,    0,    0,    0,    0,    0,    4,   14,   13,    0,
+        0,    0,    0,    0,    0,    8,    0,    0,    0,    0,
+        0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
+       16,    0,    0,    0,    0,    0,    0,    0,    0,    0,
+
+        0,    0,    0,    0,    0,    0,    0,   17,    0,    5,
+       15,   18,    0,    0,   29,    0,    0,    0,    0,    0,
+        0,    0,    0,    0,    0,    0,    0,    7,    3,    0,
+        0,    0,    2,    0,    0,    0,    0,    0,    0
+    } ;
+
+static yyconst flex_int32_t yy_ec[256] =
+    {   0,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    2,    1,    3,    4,    1,    5,    6,    7,    8,
+        9,    9,    9,    9,    9,    9,    9,   10,    1,    1,
+       11,    1,    2,    1,   12,   13,   14,   15,   12,   12,
+        2,    2,   16,    2,    2,   17,    2,    2,    2,    2,
+        2,   18,    2,   19,    2,    2,    2,    2,    2,    2,
+        1,    1,    1,    1,   20,    1,   21,   22,   23,   24,
+
+       25,   26,   27,   28,   29,   30,   31,   32,   33,   34,
+       35,   36,    2,   37,   38,   39,   40,   41,   42,   43,
+       44,    2,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1
+    } ;
+
+static yyconst flex_int32_t yy_meta[45] =
+    {   0,
+        1,    2,    1,    1,    1,    3,    3,    3,    3,    1,
+        1,    3,    3,    3,    3,    2,    2,    2,    2,    2,
+        3,    3,    3,    3,    3,    3,    2,    2,    2,    2,
+        2,    2,    2,    2,    2,    2,    2,    2,    2,    2,
+        2,    2,    2,    2
+    } ;
+
+static yyconst flex_int16_t yy_base[442] =
+    {   0,
+        0,    0,  510,  511,    0,  511,  511,  511,   39,   43,
+      511,  511,  488,  474,   46,  482,   32,   20,   37,   57,
+      473,  484,   34,   64,   59,   64,  469,  467,   78,  113,
+       41,  481,  464,    0,    0,  104,    0,  461,  461,  494,
+        0,  483,  470,  472,  465,   44,  472,  470,  453,  467,
+      455,  448,    0,  464,  447,  468,  444,  443,   64,  443,
+      464,  448,  441,   67,  457,  447,  443,   52,  451,  436,
+      446,  435,  446,  445,   76,  444,   95,  430,  438,    0,
+      445,  426,  100,  439,  438,  435,    0,  427,  456,  431,
+      105,  454,  425,  424,  442,  422,  421,  112,  420,  438,
+
+      425,  410,  117,    0,    0,  424,  412,  436,  408,  409,
+      405,  417,    0,  416,  411,  413,   83,  107,  415,  405,
+      399,  404,  395,  429,  395,  126,  119,  394,  392,  395,
+      405,  404,  401,  396,  399,  100,  398,  400,    0,  400,
+      381,  123,  397,    0,  414,  380,  511,  511,  378,  378,
+      511,  393,  376,  387,    0,  407,  375,  384,  383,  367,
+      374,  380,  400,  378,  383,  361,  361,  378,  377,  359,
+      371,  357,  361,  365,  348,  387,  363,  346,   73,  359,
+      349,  511,  347,  347,    0,  511,  361,  343,    0,  378,
+      342,  376,  341,  352,  353,  337,  343,  349,  335,  349,
+
+        0,  354,  347,  348,  345,  344,  327,  331,  339,  146,
+      340,  123,  150,  323,  326,  337,  332,    0,  329,    0,
+      313,  333,  329,  325,  327,    0,  331,    0,  328,  329,
+      325,  316,  334,  307,  317,  316,  306,  319,  307,  132,
+      301,  301,  306,  308,  311,    0,    0,  331,  311,  301,
+      295,  296,  307,  290,  307,  292,  305,  285,  296,  284,
+      318,  286,  291,  294,  293,  277,  291,  276,  280,  284,
+      268,    0,  286,  272,  283,  270,  276,  281,  284,  270,
+      271,  273,  261,  266,  259,  266,  272,  267,  272,  271,
+      258,  269,  287,  252,  251,  252,  249,  248,  260,  242,
+
+      511,  245,  243,  277,  255,  244,  246,  239,  244,  236,
+      236,  232,  228,  240,  236,  230,  242,  228,  228,  240,
+      511,  239,  226,  233,  511,  232,  234,  221,  224,  218,
+        0,  217,  217,    0,  229,  230,  511,  248,  222,  229,
+      212,  223,    0,  209,  221,  206,  209,  222,  238,  203,
+      202,  201,  511,  234,  205,  217,  200,  194,  193,  194,
+      511,  197,  207,  195,  188,  142,    0,  511,  511,  130,
+      202,  209,  191,  192,  200,  511,  199,  193,  182,  187,
+      197,  180,  181,  190,  176,  200,  173,  172,  185,  184,
+      511,  169,  184,  171,  184,  183,  199,  164,  172,  162,
+
+      161,  160,  166,  162,  171,  170,  147,  511,  158,  511,
+      511,  511,  167,  152,  511,  169,  152,  154,  153,  161,
+      162,  149,  145,  158,  147,  149,  145,  511,  511,  154,
+      152,  137,  511,  138,  145,  131,   53,   54,  511,  172,
+       66
+    } ;
+
+static yyconst flex_int16_t yy_def[442] =
+    {   0,
+      439,    1,  439,  439,  440,  439,  439,  439,  439,  439,
+      439,  439,  440,  440,  440,  440,  440,  440,  440,  440,
+      440,  440,  440,  440,  440,  440,  440,  440,  440,  440,
+      440,  440,  440,  440,  440,  439,  441,  440,  440,  440,
+      440,  440,  440,  440,  440,  440,  440,  440,  440,  440,
+      440,  440,  440,  440,  439,  440,  440,  440,  440,  439,
+      440,  440,  440,  440,  440,  440,  440,  440,  440,  440,
+      440,  440,  440,   30,   30,  440,  440,  440,  440,  441,
+      440,  440,  439,  440,  440,  440,  440,  440,  440,  440,
+      440,  440,  440,  439,  440,  440,  440,  440,  439,  440,
+
+      440,  440,  439,  440,  440,  440,  440,  440,  440,  440,
+      440,  440,  440,  440,  440,  440,   30,   30,  440,  440,
+      440,  440,  440,  440,  440,  439,  439,  440,  440,  440,
+      440,  439,  440,  440,  440,  439,  440,  439,  440,  440,
+      440,  440,  439,  440,  440,  440,  439,  439,  440,  440,
+      439,  440,  440,  440,  440,  440,  440,  440,   30,  440,
+      440,  440,  440,  440,  439,  440,  439,  439,  439,  439,
+      440,  440,  440,  440,  439,  440,  440,  440,  439,  439,
+      440,  439,  440,  440,  440,  439,  439,  440,  440,  440,
+      440,  440,  440,  439,  440,  440,  440,  440,  440,  439,
+
+      440,  439,  440,  439,  439,  439,  439,  440,  440,  440,
+      439,  439,  440,  440,  439,  439,  439,  440,  440,  440,
+      439,  440,  439,  440,  439,  440,  439,  440,  440,  440,
+      440,  439,  439,  440,  439,  439,  439,  440,  440,  439,
+      440,  440,  439,  439,  439,  440,  440,  440,  439,  439,
+      439,  440,  439,  440,  439,  440,  439,  439,  440,  440,
+      440,  439,  440,  439,  439,  439,  440,  440,  439,  439,
+      440,  440,  439,  439,  439,  439,  439,  439,  439,  440,
+      439,  440,  439,  440,  439,  439,  440,  440,  439,  439,
+      440,  439,  440,  439,  439,  440,  439,  439,  439,  439,
+
+      439,  439,  439,  440,  439,  440,  439,  440,  439,  439,
+      440,  440,  439,  439,  440,  439,  439,  439,  439,  440,
+      439,  439,  439,  439,  439,  439,  439,  439,  440,  439,
+      440,  439,  439,  440,  440,  439,  439,  440,  439,  439,
+      439,  439,  440,  439,  439,  439,  439,  439,  439,  440,
+      439,  439,  439,  440,  439,  439,  439,  439,  439,  439,
+      439,  439,  439,  439,  439,  439,  440,  439,  439,  439,
+      439,  439,  439,  439,  439,  439,  439,  439,  439,  439,
+      439,  439,  439,  439,  439,  439,  439,  439,  439,  439,
+      439,  439,  439,  439,  439,  439,  439,  439,  439,  439,
+
+      439,  439,  439,  439,  439,  439,  439,  439,  439,  439,
+      439,  439,  439,  439,  439,  439,  439,  439,  439,  439,
+      439,  439,  439,  439,  439,  439,  439,  439,  439,  439,
+      439,  439,  439,  439,  439,  439,  439,  439,    0,  439,
+      439
+    } ;
+
+static yyconst flex_int16_t yy_nxt[556] =
+    {   0,
+        4,    5,    6,    7,    8,    9,   10,   10,   10,   11,
+       12,    5,    5,    5,   13,   14,   15,   16,    5,    5,
+       17,   18,   19,   20,   21,   22,    5,   23,   24,    5,
+       23,   25,   26,   27,   28,   29,   30,   31,   32,   23,
+        5,   33,   34,    5,   36,   36,   36,   36,   36,   36,
+       36,   36,   40,   41,   44,   46,   47,   50,   48,   49,
+       55,   59,   42,   45,   59,   64,   87,   60,   80,   59,
+      103,   51,   52,   59,   53,   56,   76,  433,  109,   77,
+       54,   37,   61,   87,   66,  110,  438,   62,   67,  111,
+      104,   98,   68,   65,   98,  105,  117,   63,   71,   98,
+
+       74,  118,   72,   98,  215,   59,  159,   74,   59,   36,
+       36,   36,   36,   59,   73,  120,  216,   59,   74,   74,
+       74,   74,  179,  126,   74,   74,   74,   74,  127,  121,
+      134,   74,  180,   74,   74,   74,   74,   75,   74,  142,
+      147,  169,  142,  135,  113,  148,  167,  142,  168,  240,
+      185,  142,  170,  185,  429,  244,  246,  247,  185,  245,
+      269,  383,  185,  381,  270,  241,  384,  382,  416,  437,
+      242,  436,  417,   35,   35,  435,  434,  433,  432,  431,
+      430,  429,  428,  427,  426,  425,  424,  423,  422,  421,
+      420,  419,  418,  415,  415,  414,  413,  412,  411,  410,
+
+      409,  408,  407,  406,  405,  404,  403,  402,  401,  400,
+      399,  398,  186,  397,  396,  395,  394,  393,  392,  391,
+      390,  389,  388,  387,  148,  386,  385,  380,  379,  378,
+      377,  376,  375,  374,  373,  372,  371,  370,  369,  368,
+      367,  366,  365,  364,  363,  362,  361,  360,  359,  358,
+      357,  356,  355,  354,  353,  352,  351,  350,  349,  348,
+      347,  346,  345,  344,  343,  342,  341,  340,  339,  338,
+      337,  336,  335,  334,  333,  332,  331,  330,  329,  328,
+      327,  326,  325,  324,  323,  322,  321,  320,  319,  318,
+      317,  316,  315,  314,  313,  312,  311,  310,  309,  308,
+
+      307,  306,  305,  304,  303,  302,  301,  300,  299,  298,
+      297,  296,  295,  294,  293,  113,  292,  148,  147,  291,
+      290,  289,  288,  287,  286,  285,  284,  283,  282,  281,
+      280,  279,  278,  277,  276,  275,  274,  273,  272,  271,
+      268,  267,  266,  265,  264,  263,  182,  262,  261,  260,
+      259,  258,  257,  256,  255,  254,  253,  252,  251,  250,
+      249,  248,  243,  239,  238,  237,  236,  235,  147,  234,
+      233,  232,  201,  231,  230,  229,  228,  227,  226,  225,
+      224,  223,  222,  221,  220,  219,  218,  217,  214,  213,
+      212,  211,  210,  209,  113,  208,  207,  206,  205,  204,
+
+      203,  202,  201,  200,  199,  198,  197,   74,  196,  195,
+      194,  193,  192,  191,  190,  189,  188,  187,  186,  184,
+      183,  182,  181,  178,  177,  176,  175,  174,  173,  172,
+      171,  166,  165,  164,  163,  162,  161,  160,  158,  157,
+      156,  155,  154,  153,  152,  151,  150,  149,  146,  145,
+      144,  143,  141,  140,  139,  138,  137,  136,  133,  132,
+      131,  130,  129,  128,  125,  124,  123,  122,  119,   74,
+      116,  115,  114,  113,  112,  108,  107,  106,  102,  101,
+      100,   99,   97,   96,   95,   94,   93,   92,   91,   90,
+       89,   87,   88,   86,   85,   84,   41,   83,   82,   81,
+
+       79,   78,   70,   69,   58,   57,   43,   39,   38,  439,
+        3,  439,  439,  439,  439,  439,  439,  439,  439,  439,
+      439,  439,  439,  439,  439,  439,  439,  439,  439,  439,
+      439,  439,  439,  439,  439,  439,  439,  439,  439,  439,
+      439,  439,  439,  439,  439,  439,  439,  439,  439,  439,
+      439,  439,  439,  439,  439
+    } ;
+
+static yyconst flex_int16_t yy_chk[556] =
+    {   0,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    9,    9,    9,    9,   10,   10,
+       10,   10,   15,   15,   17,   18,   18,   19,   18,   18,
+       20,   23,   15,   17,   23,   25,   46,   24,  441,   23,
+       64,   19,   19,   23,   19,   20,   31,  438,   68,   31,
+       19,    9,   24,   46,   26,   68,  437,   24,   26,   68,
+       64,   59,   26,   25,   59,   64,   75,   24,   29,   59,
+
+       75,   75,   29,   59,  179,   29,  117,  117,   29,   36,
+       36,   36,   36,   29,   29,   77,  179,   29,   30,   30,
+       30,   30,  136,   83,   30,   30,   30,   30,   83,   77,
+       91,  118,  136,   30,   30,   30,   30,   30,   30,   98,
+      103,  127,   98,   91,  118,  103,  126,   98,  126,  210,
+      142,   98,  127,  142,  436,  212,  213,  213,  142,  212,
+      240,  370,  142,  366,  240,  210,  370,  366,  407,  435,
+      210,  434,  407,  440,  440,  432,  431,  430,  427,  426,
+      425,  424,  423,  422,  421,  420,  419,  418,  417,  416,
+      414,  413,  409,  406,  405,  404,  403,  402,  401,  400,
+
+      399,  398,  397,  396,  395,  394,  393,  392,  390,  389,
+      388,  387,  386,  385,  384,  383,  382,  381,  380,  379,
+      378,  377,  375,  374,  373,  372,  371,  365,  364,  363,
+      362,  360,  359,  358,  357,  356,  355,  354,  352,  351,
+      350,  349,  348,  347,  346,  345,  344,  342,  341,  340,
+      339,  338,  336,  335,  333,  332,  330,  329,  328,  327,
+      326,  324,  323,  322,  320,  319,  318,  317,  316,  315,
+      314,  313,  312,  311,  310,  309,  308,  307,  306,  305,
+      304,  303,  302,  300,  299,  298,  297,  296,  295,  294,
+      293,  292,  291,  290,  289,  288,  287,  286,  285,  284,
+
+      283,  282,  281,  280,  279,  278,  277,  276,  275,  274,
+      273,  271,  270,  269,  268,  267,  266,  265,  264,  263,
+      262,  261,  260,  259,  258,  257,  256,  255,  254,  253,
+      252,  251,  250,  249,  248,  245,  244,  243,  242,  241,
+      239,  238,  237,  236,  235,  234,  233,  232,  231,  230,
+      229,  227,  225,  224,  223,  222,  221,  219,  217,  216,
+      215,  214,  211,  209,  208,  207,  206,  205,  204,  203,
+      202,  200,  199,  198,  197,  196,  195,  194,  193,  192,
+      191,  190,  188,  187,  184,  183,  181,  180,  178,  177,
+      176,  175,  174,  173,  172,  171,  170,  169,  168,  167,
+
+      166,  165,  164,  163,  162,  161,  160,  159,  158,  157,
+      156,  154,  153,  152,  150,  149,  146,  145,  143,  141,
+      140,  138,  137,  135,  134,  133,  132,  131,  130,  129,
+      128,  125,  124,  123,  122,  121,  120,  119,  116,  115,
+      114,  112,  111,  110,  109,  108,  107,  106,  102,  101,
+      100,   99,   97,   96,   95,   94,   93,   92,   90,   89,
+       88,   86,   85,   84,   82,   81,   79,   78,   76,   74,
+       73,   72,   71,   70,   69,   67,   66,   65,   63,   62,
+       61,   60,   58,   57,   56,   55,   54,   52,   51,   50,
+       49,   48,   47,   45,   44,   43,   42,   40,   39,   38,
+
+       33,   32,   28,   27,   22,   21,   16,   14,   13,    3,
+      439,  439,  439,  439,  439,  439,  439,  439,  439,  439,
+      439,  439,  439,  439,  439,  439,  439,  439,  439,  439,
+      439,  439,  439,  439,  439,  439,  439,  439,  439,  439,
+      439,  439,  439,  439,  439,  439,  439,  439,  439,  439,
+      439,  439,  439,  439,  439
+    } ;
+
+static yy_state_type yy_last_accepting_state;
+static char *yy_last_accepting_cpos;
+
+extern int parse_events__flex_debug;
+int parse_events__flex_debug = 0;
+
+/* The intent behind this definition is that it'll catch
+ * any uses of REJECT which flex missed.
+ */
+#define REJECT reject_used_but_not_detected
+#define yymore() yymore_used_but_not_detected
+#define YY_MORE_ADJ 0
+#define YY_RESTORE_YY_MORE_OFFSET
+char *parse_events_text;
+#line 1 "util/parse-events.l"
+#line 5 "util/parse-events.l"
+#include <errno.h>
+#include "../perf.h"
+#include "parse-events-bison.h"
+#include "parse-events.h"
+
+static int __value(char *str, int base, int token)
+{
+	long num;
+
+	errno = 0;
+	num = strtoul(str, NULL, base);
+	if (errno)
+		return PE_ERROR;
+
+	parse_events_lval.num = num;
+	return token;
+}
+
+static int value(int base)
+{
+	return __value(parse_events_text, base, PE_VALUE);
+}
+
+static int raw(void)
+{
+	return __value(parse_events_text + 1, 16, PE_RAW);
+}
+
+static int str(int token)
+{
+	parse_events_lval.str = strdup(parse_events_text);
+	return token;
+}
+
+static int sym(int type, int config)
+{
+	parse_events_lval.num = (type << 16) + config;
+	return PE_VALUE_SYM;
+}
+
+static int term(int type)
+{
+	parse_events_lval.num = type;
+	return PE_TERM;
+}
+
+#line 782 "<stdout>"
+
+#define INITIAL 0
+
+#ifndef YY_NO_UNISTD_H
+/* Special case for "unistd.h", since it is non-ANSI. We include it way
+ * down here because we want the user's section 1 to have been scanned first.
+ * The user has a chance to override it with an option.
+ */
+#include <unistd.h>
+#endif
+
+#ifndef YY_EXTRA_TYPE
+#define YY_EXTRA_TYPE void *
+#endif
+
+static int yy_init_globals (void );
+
+/* Accessor methods to globals.
+   These are made visible to non-reentrant scanners for convenience. */
+
+int parse_events_lex_destroy (void );
+
+int parse_events_get_debug (void );
+
+void parse_events_set_debug (int debug_flag  );
+
+YY_EXTRA_TYPE parse_events_get_extra (void );
+
+void parse_events_set_extra (YY_EXTRA_TYPE user_defined  );
+
+FILE *parse_events_get_in (void );
+
+void parse_events_set_in  (FILE * in_str  );
+
+FILE *parse_events_get_out (void );
+
+void parse_events_set_out  (FILE * out_str  );
+
+int parse_events_get_leng (void );
+
+char *parse_events_get_text (void );
+
+int parse_events_get_lineno (void );
+
+void parse_events_set_lineno (int line_number  );
+
+/* Macros after this point can all be overridden by user definitions in
+ * section 1.
+ */
+
+#ifndef YY_SKIP_YYWRAP
+#ifdef __cplusplus
+extern "C" int parse_events_wrap (void );
+#else
+extern int parse_events_wrap (void );
+#endif
+#endif
+
+    static void yyunput (int c,char *buf_ptr  );
+    
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char *,yyconst char *,int );
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * );
+#endif
+
+#ifndef YY_NO_INPUT
+
+#ifdef __cplusplus
+static int yyinput (void );
+#else
+static int input (void );
+#endif
+
+#endif
+
+/* Amount of stuff to slurp up with each read. */
+#ifndef YY_READ_BUF_SIZE
+#define YY_READ_BUF_SIZE 8192
+#endif
+
+/* Copy whatever the last rule matched to the standard output. */
+#ifndef ECHO
+/* This used to be an fputs(), but since the string might contain NUL's,
+ * we now use fwrite().
+ */
+#define ECHO do { if (fwrite( parse_events_text, parse_events_leng, 1, parse_events_out )) {} } while (0)
+#endif
+
+/* Gets input and stuffs it into "buf".  number of characters read, or YY_NULL,
+ * is returned in "result".
+ */
+#ifndef YY_INPUT
+#define YY_INPUT(buf,result,max_size) \
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_is_interactive ) \
+		{ \
+		int c = '*'; \
+		unsigned n; \
+		for ( n = 0; n < max_size && \
+			     (c = getc( parse_events_in )) != EOF && c != '\n'; ++n ) \
+			buf[n] = (char) c; \
+		if ( c == '\n' ) \
+			buf[n++] = (char) c; \
+		if ( c == EOF && ferror( parse_events_in ) ) \
+			YY_FATAL_ERROR( "input in flex scanner failed" ); \
+		result = n; \
+		} \
+	else \
+		{ \
+		errno=0; \
+		while ( (result = fread(buf, 1, max_size, parse_events_in))==0 && ferror(parse_events_in)) \
+			{ \
+			if( errno != EINTR) \
+				{ \
+				YY_FATAL_ERROR( "input in flex scanner failed" ); \
+				break; \
+				} \
+			errno=0; \
+			clearerr(parse_events_in); \
+			} \
+		}\
+\
+
+#endif
+
+/* No semi-colon after return; correct usage is to write "yyterminate();" -
+ * we don't want an extra ';' after the "return" because that will cause
+ * some compilers to complain about unreachable statements.
+ */
+#ifndef yyterminate
+#define yyterminate() return YY_NULL
+#endif
+
+/* Number of entries by which start-condition stack grows. */
+#ifndef YY_START_STACK_INCR
+#define YY_START_STACK_INCR 25
+#endif
+
+/* Report a fatal error. */
+#ifndef YY_FATAL_ERROR
+#define YY_FATAL_ERROR(msg) yy_fatal_error( msg )
+#endif
+
+/* end tables serialization structures and prototypes */
+
+/* Default declaration of generated scanner - a define so the user can
+ * easily add parameters.
+ */
+#ifndef YY_DECL
+#define YY_DECL_IS_OURS 1
+
+extern int parse_events_lex (void);
+
+#define YY_DECL int parse_events_lex (void)
+#endif /* !YY_DECL */
+
+/* Code executed at the beginning of each rule, after parse_events_text and parse_events_leng
+ * have been set up.
+ */
+#ifndef YY_USER_ACTION
+#define YY_USER_ACTION
+#endif
+
+/* Code executed at the end of each rule. */
+#ifndef YY_BREAK
+#define YY_BREAK break;
+#endif
+
+#define YY_RULE_SETUP \
+	YY_USER_ACTION
+
+/** The main scanner function which does all the work.
+ */
+YY_DECL
+{
+	register yy_state_type yy_current_state;
+	register char *yy_cp, *yy_bp;
+	register int yy_act;
+    
+#line 60 "util/parse-events.l"
+
+#line 966 "<stdout>"
+
+	if ( !(yy_init) )
+		{
+		(yy_init) = 1;
+
+#ifdef YY_USER_INIT
+		YY_USER_INIT;
+#endif
+
+		if ( ! (yy_start) )
+			(yy_start) = 1;	/* first start state */
+
+		if ( ! parse_events_in )
+			parse_events_in = stdin;
+
+		if ( ! parse_events_out )
+			parse_events_out = stdout;
+
+		if ( ! YY_CURRENT_BUFFER ) {
+			parse_events_ensure_buffer_stack ();
+			YY_CURRENT_BUFFER_LVALUE =
+				parse_events__create_buffer(parse_events_in,YY_BUF_SIZE );
+		}
+
+		parse_events__load_buffer_state( );
+		}
+
+	while ( 1 )		/* loops until end-of-file is reached */
+		{
+		yy_cp = (yy_c_buf_p);
+
+		/* Support of parse_events_text. */
+		*yy_cp = (yy_hold_char);
+
+		/* yy_bp points to the position in yy_ch_buf of the start of
+		 * the current run.
+		 */
+		yy_bp = yy_cp;
+
+		yy_current_state = (yy_start);
+yy_match:
+		do
+			{
+			register YY_CHAR yy_c = yy_ec[YY_SC_TO_UI(*yy_cp)];
+			if ( yy_accept[yy_current_state] )
+				{
+				(yy_last_accepting_state) = yy_current_state;
+				(yy_last_accepting_cpos) = yy_cp;
+				}
+			while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )
+				{
+				yy_current_state = (int) yy_def[yy_current_state];
+				if ( yy_current_state >= 440 )
+					yy_c = yy_meta[(unsigned int) yy_c];
+				}
+			yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];
+			++yy_cp;
+			}
+		while ( yy_base[yy_current_state] != 511 );
+
+yy_find_action:
+		yy_act = yy_accept[yy_current_state];
+		if ( yy_act == 0 )
+			{ /* have to back up */
+			yy_cp = (yy_last_accepting_cpos);
+			yy_current_state = (yy_last_accepting_state);
+			yy_act = yy_accept[yy_current_state];
+			}
+
+		YY_DO_BEFORE_ACTION;
+
+do_action:	/* This label is used only to access EOF actions. */
+
+		switch ( yy_act )
+	{ /* beginning of action switch */
+			case 0: /* must back up */
+			/* undo the effects of YY_DO_BEFORE_ACTION */
+			*yy_cp = (yy_hold_char);
+			yy_cp = (yy_last_accepting_cpos);
+			yy_current_state = (yy_last_accepting_state);
+			goto yy_find_action;
+
+case 1:
+YY_RULE_SETUP
+#line 61 "util/parse-events.l"
+{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
+	YY_BREAK
+case 2:
+YY_RULE_SETUP
+#line 62 "util/parse-events.l"
+{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
+	YY_BREAK
+case 3:
+YY_RULE_SETUP
+#line 63 "util/parse-events.l"
+{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
+	YY_BREAK
+case 4:
+YY_RULE_SETUP
+#line 64 "util/parse-events.l"
+{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); }
+	YY_BREAK
+case 5:
+YY_RULE_SETUP
+#line 65 "util/parse-events.l"
+{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); }
+	YY_BREAK
+case 6:
+YY_RULE_SETUP
+#line 66 "util/parse-events.l"
+{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); }
+	YY_BREAK
+case 7:
+YY_RULE_SETUP
+#line 67 "util/parse-events.l"
+{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
+	YY_BREAK
+case 8:
+YY_RULE_SETUP
+#line 68 "util/parse-events.l"
+{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); }
+	YY_BREAK
+case 9:
+YY_RULE_SETUP
+#line 69 "util/parse-events.l"
+{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); }
+	YY_BREAK
+case 10:
+YY_RULE_SETUP
+#line 70 "util/parse-events.l"
+{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); }
+	YY_BREAK
+case 11:
+YY_RULE_SETUP
+#line 71 "util/parse-events.l"
+{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); }
+	YY_BREAK
+case 12:
+YY_RULE_SETUP
+#line 72 "util/parse-events.l"
+{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); }
+	YY_BREAK
+case 13:
+YY_RULE_SETUP
+#line 73 "util/parse-events.l"
+{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
+	YY_BREAK
+case 14:
+YY_RULE_SETUP
+#line 74 "util/parse-events.l"
+{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
+	YY_BREAK
+case 15:
+YY_RULE_SETUP
+#line 75 "util/parse-events.l"
+{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); }
+	YY_BREAK
+case 16:
+YY_RULE_SETUP
+#line 76 "util/parse-events.l"
+{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); }
+	YY_BREAK
+case 17:
+YY_RULE_SETUP
+#line 77 "util/parse-events.l"
+{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
+	YY_BREAK
+case 18:
+YY_RULE_SETUP
+#line 78 "util/parse-events.l"
+{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
+	YY_BREAK
+case 19:
+#line 81 "util/parse-events.l"
+case 20:
+#line 82 "util/parse-events.l"
+case 21:
+#line 83 "util/parse-events.l"
+case 22:
+#line 84 "util/parse-events.l"
+case 23:
+#line 85 "util/parse-events.l"
+case 24:
+#line 86 "util/parse-events.l"
+case 25:
+YY_RULE_SETUP
+#line 86 "util/parse-events.l"
+{ return str(PE_NAME_CACHE_TYPE); }
+	YY_BREAK
+case 26:
+#line 89 "util/parse-events.l"
+case 27:
+#line 90 "util/parse-events.l"
+case 28:
+#line 91 "util/parse-events.l"
+case 29:
+#line 92 "util/parse-events.l"
+case 30:
+#line 93 "util/parse-events.l"
+case 31:
+YY_RULE_SETUP
+#line 93 "util/parse-events.l"
+{ return str(PE_NAME_CACHE_OP_RESULT); }
+	YY_BREAK
+/*
+	 * These are event config hardcoded term names to be specified
+	 * within xxx/.../ syntax. So far we dont clash with other names,
+	 * so we can put them here directly. In case the we have a conflict
+	 * in future, this needs to go into '//' condition block.
+	 */
+case 32:
+YY_RULE_SETUP
+#line 101 "util/parse-events.l"
+{ return term(PARSE_EVENTS__TERM_TYPE_CONFIG); }
+	YY_BREAK
+case 33:
+YY_RULE_SETUP
+#line 102 "util/parse-events.l"
+{ return term(PARSE_EVENTS__TERM_TYPE_CONFIG1); }
+	YY_BREAK
+case 34:
+YY_RULE_SETUP
+#line 103 "util/parse-events.l"
+{ return term(PARSE_EVENTS__TERM_TYPE_CONFIG2); }
+	YY_BREAK
+case 35:
+YY_RULE_SETUP
+#line 104 "util/parse-events.l"
+{ return term(PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
+	YY_BREAK
+case 36:
+YY_RULE_SETUP
+#line 105 "util/parse-events.l"
+{ return term(PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
+	YY_BREAK
+case 37:
+YY_RULE_SETUP
+#line 107 "util/parse-events.l"
+{ return PE_PREFIX_MEM; }
+	YY_BREAK
+case 38:
+YY_RULE_SETUP
+#line 108 "util/parse-events.l"
+{ return raw(); }
+	YY_BREAK
+case 39:
+YY_RULE_SETUP
+#line 109 "util/parse-events.l"
+{ return value(10); }
+	YY_BREAK
+case 40:
+YY_RULE_SETUP
+#line 110 "util/parse-events.l"
+{ return value(16); }
+	YY_BREAK
+case 41:
+YY_RULE_SETUP
+#line 112 "util/parse-events.l"
+{ return str(PE_MODIFIER_EVENT); }
+	YY_BREAK
+case 42:
+YY_RULE_SETUP
+#line 113 "util/parse-events.l"
+{ return str(PE_MODIFIER_BP); }
+	YY_BREAK
+case 43:
+YY_RULE_SETUP
+#line 114 "util/parse-events.l"
+{ return str(PE_NAME); }
+	YY_BREAK
+case 44:
+YY_RULE_SETUP
+#line 115 "util/parse-events.l"
+{ return '/'; }
+	YY_BREAK
+case 45:
+YY_RULE_SETUP
+#line 116 "util/parse-events.l"
+{ return '-'; }
+	YY_BREAK
+case 46:
+YY_RULE_SETUP
+#line 117 "util/parse-events.l"
+{ return ','; }
+	YY_BREAK
+case 47:
+YY_RULE_SETUP
+#line 118 "util/parse-events.l"
+{ return ':'; }
+	YY_BREAK
+case 48:
+YY_RULE_SETUP
+#line 119 "util/parse-events.l"
+{ return '='; }
+	YY_BREAK
+case 49:
+YY_RULE_SETUP
+#line 121 "util/parse-events.l"
+ECHO;
+	YY_BREAK
+#line 1267 "<stdout>"
+case YY_STATE_EOF(INITIAL):
+	yyterminate();
+
+	case YY_END_OF_BUFFER:
+		{
+		/* Amount of text matched not including the EOB char. */
+		int yy_amount_of_matched_text = (int) (yy_cp - (yytext_ptr)) - 1;
+
+		/* Undo the effects of YY_DO_BEFORE_ACTION. */
+		*yy_cp = (yy_hold_char);
+		YY_RESTORE_YY_MORE_OFFSET
+
+		if ( YY_CURRENT_BUFFER_LVALUE->yy_buffer_status == YY_BUFFER_NEW )
+			{
+			/* We're scanning a new file or input source.  It's
+			 * possible that this happened because the user
+			 * just pointed parse_events_in at a new source and called
+			 * parse_events_lex().  If so, then we have to assure
+			 * consistency between YY_CURRENT_BUFFER and our
+			 * globals.  Here is the right place to do so, because
+			 * this is the first action (other than possibly a
+			 * back-up) that will match for the new input source.
+			 */
+			(yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_n_chars;
+			YY_CURRENT_BUFFER_LVALUE->yy_input_file = parse_events_in;
+			YY_CURRENT_BUFFER_LVALUE->yy_buffer_status = YY_BUFFER_NORMAL;
+			}
+
+		/* Note that here we test for yy_c_buf_p "<=" to the position
+		 * of the first EOB in the buffer, since yy_c_buf_p will
+		 * already have been incremented past the NUL character
+		 * (since all states make transitions on EOB to the
+		 * end-of-buffer state).  Contrast this with the test
+		 * in input().
+		 */
+		if ( (yy_c_buf_p) <= &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] )
+			{ /* This was really a NUL. */
+			yy_state_type yy_next_state;
+
+			(yy_c_buf_p) = (yytext_ptr) + yy_amount_of_matched_text;
+
+			yy_current_state = yy_get_previous_state(  );
+
+			/* Okay, we're now positioned to make the NUL
+			 * transition.  We couldn't have
+			 * yy_get_previous_state() go ahead and do it
+			 * for us because it doesn't know how to deal
+			 * with the possibility of jamming (and we don't
+			 * want to build jamming into it because then it
+			 * will run more slowly).
+			 */
+
+			yy_next_state = yy_try_NUL_trans( yy_current_state );
+
+			yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+
+			if ( yy_next_state )
+				{
+				/* Consume the NUL. */
+				yy_cp = ++(yy_c_buf_p);
+				yy_current_state = yy_next_state;
+				goto yy_match;
+				}
+
+			else
+				{
+				yy_cp = (yy_c_buf_p);
+				goto yy_find_action;
+				}
+			}
+
+		else switch ( yy_get_next_buffer(  ) )
+			{
+			case EOB_ACT_END_OF_FILE:
+				{
+				(yy_did_buffer_switch_on_eof) = 0;
+
+				if ( parse_events_wrap( ) )
+					{
+					/* Note: because we've taken care in
+					 * yy_get_next_buffer() to have set up
+					 * parse_events_text, we can now set up
+					 * yy_c_buf_p so that if some total
+					 * hoser (like flex itself) wants to
+					 * call the scanner after we return the
+					 * YY_NULL, it'll still work - another
+					 * YY_NULL will get returned.
+					 */
+					(yy_c_buf_p) = (yytext_ptr) + YY_MORE_ADJ;
+
+					yy_act = YY_STATE_EOF(YY_START);
+					goto do_action;
+					}
+
+				else
+					{
+					if ( ! (yy_did_buffer_switch_on_eof) )
+						YY_NEW_FILE;
+					}
+				break;
+				}
+
+			case EOB_ACT_CONTINUE_SCAN:
+				(yy_c_buf_p) =
+					(yytext_ptr) + yy_amount_of_matched_text;
+
+				yy_current_state = yy_get_previous_state(  );
+
+				yy_cp = (yy_c_buf_p);
+				yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+				goto yy_match;
+
+			case EOB_ACT_LAST_MATCH:
+				(yy_c_buf_p) =
+				&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)];
+
+				yy_current_state = yy_get_previous_state(  );
+
+				yy_cp = (yy_c_buf_p);
+				yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+				goto yy_find_action;
+			}
+		break;
+		}
+
+	default:
+		YY_FATAL_ERROR(
+			"fatal flex scanner internal error--no action found" );
+	} /* end of action switch */
+		} /* end of scanning one token */
+} /* end of parse_events_lex */
+
+/* yy_get_next_buffer - try to read in a new buffer
+ *
+ * Returns a code representing an action:
+ *	EOB_ACT_LAST_MATCH -
+ *	EOB_ACT_CONTINUE_SCAN - continue scanning from current position
+ *	EOB_ACT_END_OF_FILE - end of file
+ */
+static int yy_get_next_buffer (void)
+{
+    	register char *dest = YY_CURRENT_BUFFER_LVALUE->yy_ch_buf;
+	register char *source = (yytext_ptr);
+	register int number_to_move, i;
+	int ret_val;
+
+	if ( (yy_c_buf_p) > &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars) + 1] )
+		YY_FATAL_ERROR(
+		"fatal flex scanner internal error--end of buffer missed" );
+
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_fill_buffer == 0 )
+		{ /* Don't try to fill the buffer, so this is an EOF. */
+		if ( (yy_c_buf_p) - (yytext_ptr) - YY_MORE_ADJ == 1 )
+			{
+			/* We matched a single character, the EOB, so
+			 * treat this as a final EOF.
+			 */
+			return EOB_ACT_END_OF_FILE;
+			}
+
+		else
+			{
+			/* We matched some text prior to the EOB, first
+			 * process it.
+			 */
+			return EOB_ACT_LAST_MATCH;
+			}
+		}
+
+	/* Try to read more data. */
+
+	/* First move last chars to start of buffer. */
+	number_to_move = (int) ((yy_c_buf_p) - (yytext_ptr)) - 1;
+
+	for ( i = 0; i < number_to_move; ++i )
+		*(dest++) = *(source++);
+
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_buffer_status == YY_BUFFER_EOF_PENDING )
+		/* don't do the read, it's not guaranteed to return an EOF,
+		 * just force an EOF
+		 */
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars) = 0;
+
+	else
+		{
+			int num_to_read =
+			YY_CURRENT_BUFFER_LVALUE->yy_buf_size - number_to_move - 1;
+
+		while ( num_to_read <= 0 )
+			{ /* Not enough room in the buffer - grow it. */
+
+			/* just a shorter name for the current buffer */
+			YY_BUFFER_STATE b = YY_CURRENT_BUFFER;
+
+			int yy_c_buf_p_offset =
+				(int) ((yy_c_buf_p) - b->yy_ch_buf);
+
+			if ( b->yy_is_our_buffer )
+				{
+				int new_size = b->yy_buf_size * 2;
+
+				if ( new_size <= 0 )
+					b->yy_buf_size += b->yy_buf_size / 8;
+				else
+					b->yy_buf_size *= 2;
+
+				b->yy_ch_buf = (char *)
+					/* Include room in for 2 EOB chars. */
+					parse_events_realloc((void *) b->yy_ch_buf,b->yy_buf_size + 2  );
+				}
+			else
+				/* Can't grow it, we don't own it. */
+				b->yy_ch_buf = 0;
+
+			if ( ! b->yy_ch_buf )
+				YY_FATAL_ERROR(
+				"fatal error - scanner input buffer overflow" );
+
+			(yy_c_buf_p) = &b->yy_ch_buf[yy_c_buf_p_offset];
+
+			num_to_read = YY_CURRENT_BUFFER_LVALUE->yy_buf_size -
+						number_to_move - 1;
+
+			}
+
+		if ( num_to_read > YY_READ_BUF_SIZE )
+			num_to_read = YY_READ_BUF_SIZE;
+
+		/* Read in more data. */
+		YY_INPUT( (&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[number_to_move]),
+			(yy_n_chars), (size_t) num_to_read );
+
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	if ( (yy_n_chars) == 0 )
+		{
+		if ( number_to_move == YY_MORE_ADJ )
+			{
+			ret_val = EOB_ACT_END_OF_FILE;
+			parse_events_restart(parse_events_in  );
+			}
+
+		else
+			{
+			ret_val = EOB_ACT_LAST_MATCH;
+			YY_CURRENT_BUFFER_LVALUE->yy_buffer_status =
+				YY_BUFFER_EOF_PENDING;
+			}
+		}
+
+	else
+		ret_val = EOB_ACT_CONTINUE_SCAN;
+
+	if ((yy_size_t) ((yy_n_chars) + number_to_move) > YY_CURRENT_BUFFER_LVALUE->yy_buf_size) {
+		/* Extend the array by 50%, plus the number we really need. */
+		yy_size_t new_size = (yy_n_chars) + number_to_move + ((yy_n_chars) >> 1);
+		YY_CURRENT_BUFFER_LVALUE->yy_ch_buf = (char *) parse_events_realloc((void *) YY_CURRENT_BUFFER_LVALUE->yy_ch_buf,new_size  );
+		if ( ! YY_CURRENT_BUFFER_LVALUE->yy_ch_buf )
+			YY_FATAL_ERROR( "out of dynamic memory in yy_get_next_buffer()" );
+	}
+
+	(yy_n_chars) += number_to_move;
+	YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] = YY_END_OF_BUFFER_CHAR;
+	YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars) + 1] = YY_END_OF_BUFFER_CHAR;
+
+	(yytext_ptr) = &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[0];
+
+	return ret_val;
+}
+
+/* yy_get_previous_state - get the state just before the EOB char was reached */
+
+    static yy_state_type yy_get_previous_state (void)
+{
+	register yy_state_type yy_current_state;
+	register char *yy_cp;
+    
+	yy_current_state = (yy_start);
+
+	for ( yy_cp = (yytext_ptr) + YY_MORE_ADJ; yy_cp < (yy_c_buf_p); ++yy_cp )
+		{
+		register YY_CHAR yy_c = (*yy_cp ? yy_ec[YY_SC_TO_UI(*yy_cp)] : 1);
+		if ( yy_accept[yy_current_state] )
+			{
+			(yy_last_accepting_state) = yy_current_state;
+			(yy_last_accepting_cpos) = yy_cp;
+			}
+		while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )
+			{
+			yy_current_state = (int) yy_def[yy_current_state];
+			if ( yy_current_state >= 440 )
+				yy_c = yy_meta[(unsigned int) yy_c];
+			}
+		yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];
+		}
+
+	return yy_current_state;
+}
+
+/* yy_try_NUL_trans - try to make a transition on the NUL character
+ *
+ * synopsis
+ *	next_state = yy_try_NUL_trans( current_state );
+ */
+    static yy_state_type yy_try_NUL_trans  (yy_state_type yy_current_state )
+{
+	register int yy_is_jam;
+    	register char *yy_cp = (yy_c_buf_p);
+
+	register YY_CHAR yy_c = 1;
+	if ( yy_accept[yy_current_state] )
+		{
+		(yy_last_accepting_state) = yy_current_state;
+		(yy_last_accepting_cpos) = yy_cp;
+		}
+	while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )
+		{
+		yy_current_state = (int) yy_def[yy_current_state];
+		if ( yy_current_state >= 440 )
+			yy_c = yy_meta[(unsigned int) yy_c];
+		}
+	yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];
+	yy_is_jam = (yy_current_state == 439);
+
+	return yy_is_jam ? 0 : yy_current_state;
+}
+
+    static void yyunput (int c, register char * yy_bp )
+{
+	register char *yy_cp;
+    
+    yy_cp = (yy_c_buf_p);
+
+	/* undo effects of setting up parse_events_text */
+	*yy_cp = (yy_hold_char);
+
+	if ( yy_cp < YY_CURRENT_BUFFER_LVALUE->yy_ch_buf + 2 )
+		{ /* need to shift things up to make room */
+		/* +2 for EOB chars. */
+		register int number_to_move = (yy_n_chars) + 2;
+		register char *dest = &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[
+					YY_CURRENT_BUFFER_LVALUE->yy_buf_size + 2];
+		register char *source =
+				&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[number_to_move];
+
+		while ( source > YY_CURRENT_BUFFER_LVALUE->yy_ch_buf )
+			*--dest = *--source;
+
+		yy_cp += (int) (dest - source);
+		yy_bp += (int) (dest - source);
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars =
+			(yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_buf_size;
+
+		if ( yy_cp < YY_CURRENT_BUFFER_LVALUE->yy_ch_buf + 2 )
+			YY_FATAL_ERROR( "flex scanner push-back overflow" );
+		}
+
+	*--yy_cp = (char) c;
+
+	(yytext_ptr) = yy_bp;
+	(yy_hold_char) = *yy_cp;
+	(yy_c_buf_p) = yy_cp;
+}
+
+#ifndef YY_NO_INPUT
+#ifdef __cplusplus
+    static int yyinput (void)
+#else
+    static int input  (void)
+#endif
+
+{
+	int c;
+    
+	*(yy_c_buf_p) = (yy_hold_char);
+
+	if ( *(yy_c_buf_p) == YY_END_OF_BUFFER_CHAR )
+		{
+		/* yy_c_buf_p now points to the character we want to return.
+		 * If this occurs *before* the EOB characters, then it's a
+		 * valid NUL; if not, then we've hit the end of the buffer.
+		 */
+		if ( (yy_c_buf_p) < &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] )
+			/* This was really a NUL. */
+			*(yy_c_buf_p) = '\0';
+
+		else
+			{ /* need more input */
+			int offset = (yy_c_buf_p) - (yytext_ptr);
+			++(yy_c_buf_p);
+
+			switch ( yy_get_next_buffer(  ) )
+				{
+				case EOB_ACT_LAST_MATCH:
+					/* This happens because yy_g_n_b()
+					 * sees that we've accumulated a
+					 * token and flags that we need to
+					 * try matching the token before
+					 * proceeding.  But for input(),
+					 * there's no matching to consider.
+					 * So convert the EOB_ACT_LAST_MATCH
+					 * to EOB_ACT_END_OF_FILE.
+					 */
+
+					/* Reset buffer status. */
+					parse_events_restart(parse_events_in );
+
+					/*FALLTHROUGH*/
+
+				case EOB_ACT_END_OF_FILE:
+					{
+					if ( parse_events_wrap( ) )
+						return EOF;
+
+					if ( ! (yy_did_buffer_switch_on_eof) )
+						YY_NEW_FILE;
+#ifdef __cplusplus
+					return yyinput();
+#else
+					return input();
+#endif
+					}
+
+				case EOB_ACT_CONTINUE_SCAN:
+					(yy_c_buf_p) = (yytext_ptr) + offset;
+					break;
+				}
+			}
+		}
+
+	c = *(unsigned char *) (yy_c_buf_p);	/* cast for 8-bit char's */
+	*(yy_c_buf_p) = '\0';	/* preserve parse_events_text */
+	(yy_hold_char) = *++(yy_c_buf_p);
+
+	return c;
+}
+#endif	/* ifndef YY_NO_INPUT */
+
+/** Immediately switch to a different input stream.
+ * @param input_file A readable stream.
+ * 
+ * @note This function does not reset the start condition to @c INITIAL .
+ */
+    void parse_events_restart  (FILE * input_file )
+{
+    
+	if ( ! YY_CURRENT_BUFFER ){
+        parse_events_ensure_buffer_stack ();
+		YY_CURRENT_BUFFER_LVALUE =
+            parse_events__create_buffer(parse_events_in,YY_BUF_SIZE );
+	}
+
+	parse_events__init_buffer(YY_CURRENT_BUFFER,input_file );
+	parse_events__load_buffer_state( );
+}
+
+/** Switch to a different input buffer.
+ * @param new_buffer The new input buffer.
+ * 
+ */
+    void parse_events__switch_to_buffer  (YY_BUFFER_STATE  new_buffer )
+{
+    
+	/* TODO. We should be able to replace this entire function body
+	 * with
+	 *		parse_events_pop_buffer_state();
+	 *		parse_events_push_buffer_state(new_buffer);
+     */
+	parse_events_ensure_buffer_stack ();
+	if ( YY_CURRENT_BUFFER == new_buffer )
+		return;
+
+	if ( YY_CURRENT_BUFFER )
+		{
+		/* Flush out information for old buffer. */
+		*(yy_c_buf_p) = (yy_hold_char);
+		YY_CURRENT_BUFFER_LVALUE->yy_buf_pos = (yy_c_buf_p);
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	YY_CURRENT_BUFFER_LVALUE = new_buffer;
+	parse_events__load_buffer_state( );
+
+	/* We don't actually know whether we did this switch during
+	 * EOF (parse_events_wrap()) processing, but the only time this flag
+	 * is looked at is after parse_events_wrap() is called, so it's safe
+	 * to go ahead and always set it.
+	 */
+	(yy_did_buffer_switch_on_eof) = 1;
+}
+
+static void parse_events__load_buffer_state  (void)
+{
+    	(yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_n_chars;
+	(yytext_ptr) = (yy_c_buf_p) = YY_CURRENT_BUFFER_LVALUE->yy_buf_pos;
+	parse_events_in = YY_CURRENT_BUFFER_LVALUE->yy_input_file;
+	(yy_hold_char) = *(yy_c_buf_p);
+}
+
+/** Allocate and initialize an input buffer state.
+ * @param file A readable stream.
+ * @param size The character buffer size in bytes. When in doubt, use @c YY_BUF_SIZE.
+ * 
+ * @return the allocated buffer state.
+ */
+    YY_BUFFER_STATE parse_events__create_buffer  (FILE * file, int  size )
+{
+	YY_BUFFER_STATE b;
+    
+	b = (YY_BUFFER_STATE) parse_events_alloc(sizeof( struct yy_buffer_state )  );
+	if ( ! b )
+		YY_FATAL_ERROR( "out of dynamic memory in parse_events__create_buffer()" );
+
+	b->yy_buf_size = size;
+
+	/* yy_ch_buf has to be 2 characters longer than the size given because
+	 * we need to put in 2 end-of-buffer characters.
+	 */
+	b->yy_ch_buf = (char *) parse_events_alloc(b->yy_buf_size + 2  );
+	if ( ! b->yy_ch_buf )
+		YY_FATAL_ERROR( "out of dynamic memory in parse_events__create_buffer()" );
+
+	b->yy_is_our_buffer = 1;
+
+	parse_events__init_buffer(b,file );
+
+	return b;
+}
+
+/** Destroy the buffer.
+ * @param b a buffer created with parse_events__create_buffer()
+ * 
+ */
+    void parse_events__delete_buffer (YY_BUFFER_STATE  b )
+{
+    
+	if ( ! b )
+		return;
+
+	if ( b == YY_CURRENT_BUFFER ) /* Not sure if we should pop here. */
+		YY_CURRENT_BUFFER_LVALUE = (YY_BUFFER_STATE) 0;
+
+	if ( b->yy_is_our_buffer )
+		parse_events_free((void *) b->yy_ch_buf  );
+
+	parse_events_free((void *) b  );
+}
+
+#ifndef __cplusplus
+extern int isatty (int );
+#endif /* __cplusplus */
+    
+/* Initializes or reinitializes a buffer.
+ * This function is sometimes called more than once on the same buffer,
+ * such as during a parse_events_restart() or at EOF.
+ */
+    static void parse_events__init_buffer  (YY_BUFFER_STATE  b, FILE * file )
+
+{
+	int oerrno = errno;
+    
+	parse_events__flush_buffer(b );
+
+	b->yy_input_file = file;
+	b->yy_fill_buffer = 1;
+
+    /* If b is the current buffer, then parse_events__init_buffer was _probably_
+     * called from parse_events_restart() or through yy_get_next_buffer.
+     * In that case, we don't want to reset the lineno or column.
+     */
+    if (b != YY_CURRENT_BUFFER){
+        b->yy_bs_lineno = 1;
+        b->yy_bs_column = 0;
+    }
+
+        b->yy_is_interactive = file ? (isatty( fileno(file) ) > 0) : 0;
+    
+	errno = oerrno;
+}
+
+/** Discard all buffered characters. On the next scan, YY_INPUT will be called.
+ * @param b the buffer state to be flushed, usually @c YY_CURRENT_BUFFER.
+ * 
+ */
+    void parse_events__flush_buffer (YY_BUFFER_STATE  b )
+{
+    	if ( ! b )
+		return;
+
+	b->yy_n_chars = 0;
+
+	/* We always need two end-of-buffer characters.  The first causes
+	 * a transition to the end-of-buffer state.  The second causes
+	 * a jam in that state.
+	 */
+	b->yy_ch_buf[0] = YY_END_OF_BUFFER_CHAR;
+	b->yy_ch_buf[1] = YY_END_OF_BUFFER_CHAR;
+
+	b->yy_buf_pos = &b->yy_ch_buf[0];
+
+	b->yy_at_bol = 1;
+	b->yy_buffer_status = YY_BUFFER_NEW;
+
+	if ( b == YY_CURRENT_BUFFER )
+		parse_events__load_buffer_state( );
+}
+
+/** Pushes the new state onto the stack. The new state becomes
+ *  the current state. This function will allocate the stack
+ *  if necessary.
+ *  @param new_buffer The new state.
+ *  
+ */
+void parse_events_push_buffer_state (YY_BUFFER_STATE new_buffer )
+{
+    	if (new_buffer == NULL)
+		return;
+
+	parse_events_ensure_buffer_stack();
+
+	/* This block is copied from parse_events__switch_to_buffer. */
+	if ( YY_CURRENT_BUFFER )
+		{
+		/* Flush out information for old buffer. */
+		*(yy_c_buf_p) = (yy_hold_char);
+		YY_CURRENT_BUFFER_LVALUE->yy_buf_pos = (yy_c_buf_p);
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	/* Only push if top exists. Otherwise, replace top. */
+	if (YY_CURRENT_BUFFER)
+		(yy_buffer_stack_top)++;
+	YY_CURRENT_BUFFER_LVALUE = new_buffer;
+
+	/* copied from parse_events__switch_to_buffer. */
+	parse_events__load_buffer_state( );
+	(yy_did_buffer_switch_on_eof) = 1;
+}
+
+/** Removes and deletes the top of the stack, if present.
+ *  The next element becomes the new top.
+ *  
+ */
+void parse_events_pop_buffer_state (void)
+{
+    	if (!YY_CURRENT_BUFFER)
+		return;
+
+	parse_events__delete_buffer(YY_CURRENT_BUFFER );
+	YY_CURRENT_BUFFER_LVALUE = NULL;
+	if ((yy_buffer_stack_top) > 0)
+		--(yy_buffer_stack_top);
+
+	if (YY_CURRENT_BUFFER) {
+		parse_events__load_buffer_state( );
+		(yy_did_buffer_switch_on_eof) = 1;
+	}
+}
+
+/* Allocates the stack if it does not exist.
+ *  Guarantees space for at least one push.
+ */
+static void parse_events_ensure_buffer_stack (void)
+{
+	int num_to_alloc;
+    
+	if (!(yy_buffer_stack)) {
+
+		/* First allocation is just for 2 elements, since we don't know if this
+		 * scanner will even need a stack. We use 2 instead of 1 to avoid an
+		 * immediate realloc on the next call.
+         */
+		num_to_alloc = 1;
+		(yy_buffer_stack) = (struct yy_buffer_state**)parse_events_alloc
+								(num_to_alloc * sizeof(struct yy_buffer_state*)
+								);
+		if ( ! (yy_buffer_stack) )
+			YY_FATAL_ERROR( "out of dynamic memory in parse_events_ensure_buffer_stack()" );
+								  
+		memset((yy_buffer_stack), 0, num_to_alloc * sizeof(struct yy_buffer_state*));
+				
+		(yy_buffer_stack_max) = num_to_alloc;
+		(yy_buffer_stack_top) = 0;
+		return;
+	}
+
+	if ((yy_buffer_stack_top) >= ((yy_buffer_stack_max)) - 1){
+
+		/* Increase the buffer to prepare for a possible push. */
+		int grow_size = 8 /* arbitrary grow size */;
+
+		num_to_alloc = (yy_buffer_stack_max) + grow_size;
+		(yy_buffer_stack) = (struct yy_buffer_state**)parse_events_realloc
+								((yy_buffer_stack),
+								num_to_alloc * sizeof(struct yy_buffer_state*)
+								);
+		if ( ! (yy_buffer_stack) )
+			YY_FATAL_ERROR( "out of dynamic memory in parse_events_ensure_buffer_stack()" );
+
+		/* zero only the new slots.*/
+		memset((yy_buffer_stack) + (yy_buffer_stack_max), 0, grow_size * sizeof(struct yy_buffer_state*));
+		(yy_buffer_stack_max) = num_to_alloc;
+	}
+}
+
+/** Setup the input buffer state to scan directly from a user-specified character buffer.
+ * @param base the character buffer
+ * @param size the size in bytes of the character buffer
+ * 
+ * @return the newly allocated buffer state object. 
+ */
+YY_BUFFER_STATE parse_events__scan_buffer  (char * base, yy_size_t  size )
+{
+	YY_BUFFER_STATE b;
+    
+	if ( size < 2 ||
+	     base[size-2] != YY_END_OF_BUFFER_CHAR ||
+	     base[size-1] != YY_END_OF_BUFFER_CHAR )
+		/* They forgot to leave room for the EOB's. */
+		return 0;
+
+	b = (YY_BUFFER_STATE) parse_events_alloc(sizeof( struct yy_buffer_state )  );
+	if ( ! b )
+		YY_FATAL_ERROR( "out of dynamic memory in parse_events__scan_buffer()" );
+
+	b->yy_buf_size = size - 2;	/* "- 2" to take care of EOB's */
+	b->yy_buf_pos = b->yy_ch_buf = base;
+	b->yy_is_our_buffer = 0;
+	b->yy_input_file = 0;
+	b->yy_n_chars = b->yy_buf_size;
+	b->yy_is_interactive = 0;
+	b->yy_at_bol = 1;
+	b->yy_fill_buffer = 0;
+	b->yy_buffer_status = YY_BUFFER_NEW;
+
+	parse_events__switch_to_buffer(b  );
+
+	return b;
+}
+
+/** Setup the input buffer state to scan a string. The next call to parse_events_lex() will
+ * scan from a @e copy of @a str.
+ * @param yystr a NUL-terminated string to scan
+ * 
+ * @return the newly allocated buffer state object.
+ * @note If you want to scan bytes that may contain NUL values, then use
+ *       parse_events__scan_bytes() instead.
+ */
+YY_BUFFER_STATE parse_events__scan_string (yyconst char * yystr )
+{
+    
+	return parse_events__scan_bytes(yystr,strlen(yystr) );
+}
+
+/** Setup the input buffer state to scan the given bytes. The next call to parse_events_lex() will
+ * scan from a @e copy of @a bytes.
+ * @param bytes the byte buffer to scan
+ * @param len the number of bytes in the buffer pointed to by @a bytes.
+ * 
+ * @return the newly allocated buffer state object.
+ */
+YY_BUFFER_STATE parse_events__scan_bytes  (yyconst char * yybytes, int  _yybytes_len )
+{
+	YY_BUFFER_STATE b;
+	char *buf;
+	yy_size_t n;
+	int i;
+    
+	/* Get memory for full buffer, including space for trailing EOB's. */
+	n = _yybytes_len + 2;
+	buf = (char *) parse_events_alloc(n  );
+	if ( ! buf )
+		YY_FATAL_ERROR( "out of dynamic memory in parse_events__scan_bytes()" );
+
+	for ( i = 0; i < _yybytes_len; ++i )
+		buf[i] = yybytes[i];
+
+	buf[_yybytes_len] = buf[_yybytes_len+1] = YY_END_OF_BUFFER_CHAR;
+
+	b = parse_events__scan_buffer(buf,n );
+	if ( ! b )
+		YY_FATAL_ERROR( "bad buffer in parse_events__scan_bytes()" );
+
+	/* It's okay to grow etc. this buffer, and we should throw it
+	 * away when we're done.
+	 */
+	b->yy_is_our_buffer = 1;
+
+	return b;
+}
+
+#ifndef YY_EXIT_FAILURE
+#define YY_EXIT_FAILURE 2
+#endif
+
+static void yy_fatal_error (yyconst char* msg )
+{
+    	(void) fprintf( stderr, "%s\n", msg );
+	exit( YY_EXIT_FAILURE );
+}
+
+/* Redefine yyless() so it works in section 3 code. */
+
+#undef yyless
+#define yyless(n) \
+	do \
+		{ \
+		/* Undo effects of setting up parse_events_text. */ \
+        int yyless_macro_arg = (n); \
+        YY_LESS_LINENO(yyless_macro_arg);\
+		parse_events_text[parse_events_leng] = (yy_hold_char); \
+		(yy_c_buf_p) = parse_events_text + yyless_macro_arg; \
+		(yy_hold_char) = *(yy_c_buf_p); \
+		*(yy_c_buf_p) = '\0'; \
+		parse_events_leng = yyless_macro_arg; \
+		} \
+	while ( 0 )
+
+/* Accessor  methods (get/set functions) to struct members. */
+
+/** Get the current line number.
+ * 
+ */
+int parse_events_get_lineno  (void)
+{
+        
+    return parse_events_lineno;
+}
+
+/** Get the input stream.
+ * 
+ */
+FILE *parse_events_get_in  (void)
+{
+        return parse_events_in;
+}
+
+/** Get the output stream.
+ * 
+ */
+FILE *parse_events_get_out  (void)
+{
+        return parse_events_out;
+}
+
+/** Get the length of the current token.
+ * 
+ */
+int parse_events_get_leng  (void)
+{
+        return parse_events_leng;
+}
+
+/** Get the current token.
+ * 
+ */
+
+char *parse_events_get_text  (void)
+{
+        return parse_events_text;
+}
+
+/** Set the current line number.
+ * @param line_number
+ * 
+ */
+void parse_events_set_lineno (int  line_number )
+{
+    
+    parse_events_lineno = line_number;
+}
+
+/** Set the input stream. This does not discard the current
+ * input buffer.
+ * @param in_str A readable stream.
+ * 
+ * @see parse_events__switch_to_buffer
+ */
+void parse_events_set_in (FILE *  in_str )
+{
+        parse_events_in = in_str ;
+}
+
+void parse_events_set_out (FILE *  out_str )
+{
+        parse_events_out = out_str ;
+}
+
+int parse_events_get_debug  (void)
+{
+        return parse_events__flex_debug;
+}
+
+void parse_events_set_debug (int  bdebug )
+{
+        parse_events__flex_debug = bdebug ;
+}
+
+static int yy_init_globals (void)
+{
+        /* Initialization is the same as for the non-reentrant scanner.
+     * This function is called from parse_events_lex_destroy(), so don't allocate here.
+     */
+
+    (yy_buffer_stack) = 0;
+    (yy_buffer_stack_top) = 0;
+    (yy_buffer_stack_max) = 0;
+    (yy_c_buf_p) = (char *) 0;
+    (yy_init) = 0;
+    (yy_start) = 0;
+
+/* Defined in main.c */
+#ifdef YY_STDINIT
+    parse_events_in = stdin;
+    parse_events_out = stdout;
+#else
+    parse_events_in = (FILE *) 0;
+    parse_events_out = (FILE *) 0;
+#endif
+
+    /* For future reference: Set errno on error, since we are called by
+     * parse_events_lex_init()
+     */
+    return 0;
+}
+
+/* parse_events_lex_destroy is for both reentrant and non-reentrant scanners. */
+int parse_events_lex_destroy  (void)
+{
+    
+    /* Pop the buffer stack, destroying each element. */
+	while(YY_CURRENT_BUFFER){
+		parse_events__delete_buffer(YY_CURRENT_BUFFER  );
+		YY_CURRENT_BUFFER_LVALUE = NULL;
+		parse_events_pop_buffer_state();
+	}
+
+	/* Destroy the stack itself. */
+	parse_events_free((yy_buffer_stack) );
+	(yy_buffer_stack) = NULL;
+
+    /* Reset the globals. This is important in a non-reentrant scanner so the next time
+     * parse_events_lex() is called, initialization will occur. */
+    yy_init_globals( );
+
+    return 0;
+}
+
+/*
+ * Internal utility routines.
+ */
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char* s1, yyconst char * s2, int n )
+{
+	register int i;
+	for ( i = 0; i < n; ++i )
+		s1[i] = s2[i];
+}
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * s )
+{
+	register int n;
+	for ( n = 0; s[n]; ++n )
+		;
+
+	return n;
+}
+#endif
+
+void *parse_events_alloc (yy_size_t  size )
+{
+	return (void *) malloc( size );
+}
+
+void *parse_events_realloc  (void * ptr, yy_size_t  size )
+{
+	/* The cast to (char *) in the following accommodates both
+	 * implementations that use char* generic pointers, and those
+	 * that use void* generic pointers.  It works with the latter
+	 * because both ANSI C and C++ allow castless assignment from
+	 * any pointer type to void*, and deal with argument conversions
+	 * as though doing an assignment.
+	 */
+	return (void *) realloc( (char *) ptr, size );
+}
+
+void parse_events_free (void * ptr )
+{
+	free( (char *) ptr );	/* see parse_events_realloc() for (char *) cast */
+}
+
+#define YYTABLES_NAME "yytables"
+
+#line 121 "util/parse-events.l"
+
+
+
+int parse_events_wrap(void)
+{
+	return 1;
+}
+
diff --git a/tools/perf/util/parse-events-flex.h b/tools/perf/util/parse-events-flex.h
new file mode 100644
index 0000000..ceb9b20
--- /dev/null
+++ b/tools/perf/util/parse-events-flex.h
@@ -0,0 +1,316 @@
+#ifndef parse_events_HEADER_H
+#define parse_events_HEADER_H 1
+#define parse_events_IN_HEADER 1
+
+#line 6 "util/parse-events-flex.h"
+
+#define  YY_INT_ALIGNED short int
+
+/* A lexical scanner generated by flex */
+
+#define FLEX_SCANNER
+#define YY_FLEX_MAJOR_VERSION 2
+#define YY_FLEX_MINOR_VERSION 5
+#define YY_FLEX_SUBMINOR_VERSION 35
+#if YY_FLEX_SUBMINOR_VERSION > 0
+#define FLEX_BETA
+#endif
+
+/* First, we deal with  platform-specific or compiler-specific issues. */
+
+/* begin standard C headers. */
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <stdlib.h>
+
+/* end standard C headers. */
+
+/* flex integer type definitions */
+
+#ifndef FLEXINT_H
+#define FLEXINT_H
+
+/* C99 systems have <inttypes.h>. Non-C99 systems may or may not. */
+
+#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+
+/* C99 says to define __STDC_LIMIT_MACROS before including stdint.h,
+ * if you want the limit (max/min) macros for int types. 
+ */
+#ifndef __STDC_LIMIT_MACROS
+#define __STDC_LIMIT_MACROS 1
+#endif
+
+#include <inttypes.h>
+typedef int8_t flex_int8_t;
+typedef uint8_t flex_uint8_t;
+typedef int16_t flex_int16_t;
+typedef uint16_t flex_uint16_t;
+typedef int32_t flex_int32_t;
+typedef uint32_t flex_uint32_t;
+#else
+typedef signed char flex_int8_t;
+typedef short int flex_int16_t;
+typedef int flex_int32_t;
+typedef unsigned char flex_uint8_t; 
+typedef unsigned short int flex_uint16_t;
+typedef unsigned int flex_uint32_t;
+#endif /* ! C99 */
+
+/* Limits of integral types. */
+#ifndef INT8_MIN
+#define INT8_MIN               (-128)
+#endif
+#ifndef INT16_MIN
+#define INT16_MIN              (-32767-1)
+#endif
+#ifndef INT32_MIN
+#define INT32_MIN              (-2147483647-1)
+#endif
+#ifndef INT8_MAX
+#define INT8_MAX               (127)
+#endif
+#ifndef INT16_MAX
+#define INT16_MAX              (32767)
+#endif
+#ifndef INT32_MAX
+#define INT32_MAX              (2147483647)
+#endif
+#ifndef UINT8_MAX
+#define UINT8_MAX              (255U)
+#endif
+#ifndef UINT16_MAX
+#define UINT16_MAX             (65535U)
+#endif
+#ifndef UINT32_MAX
+#define UINT32_MAX             (4294967295U)
+#endif
+
+#endif /* ! FLEXINT_H */
+
+#ifdef __cplusplus
+
+/* The "const" storage-class-modifier is valid. */
+#define YY_USE_CONST
+
+#else	/* ! __cplusplus */
+
+/* C99 requires __STDC__ to be defined as 1. */
+#if defined (__STDC__)
+
+#define YY_USE_CONST
+
+#endif	/* defined (__STDC__) */
+#endif	/* ! __cplusplus */
+
+#ifdef YY_USE_CONST
+#define yyconst const
+#else
+#define yyconst
+#endif
+
+/* Size of default input buffer. */
+#ifndef YY_BUF_SIZE
+#define YY_BUF_SIZE 16384
+#endif
+
+#ifndef YY_TYPEDEF_YY_BUFFER_STATE
+#define YY_TYPEDEF_YY_BUFFER_STATE
+typedef struct yy_buffer_state *YY_BUFFER_STATE;
+#endif
+
+extern int parse_events_leng;
+
+extern FILE *parse_events_in, *parse_events_out;
+
+#ifndef YY_TYPEDEF_YY_SIZE_T
+#define YY_TYPEDEF_YY_SIZE_T
+typedef size_t yy_size_t;
+#endif
+
+#ifndef YY_STRUCT_YY_BUFFER_STATE
+#define YY_STRUCT_YY_BUFFER_STATE
+struct yy_buffer_state
+	{
+	FILE *yy_input_file;
+
+	char *yy_ch_buf;		/* input buffer */
+	char *yy_buf_pos;		/* current position in input buffer */
+
+	/* Size of input buffer in bytes, not including room for EOB
+	 * characters.
+	 */
+	yy_size_t yy_buf_size;
+
+	/* Number of characters read into yy_ch_buf, not including EOB
+	 * characters.
+	 */
+	int yy_n_chars;
+
+	/* Whether we "own" the buffer - i.e., we know we created it,
+	 * and can realloc() it to grow it, and should free() it to
+	 * delete it.
+	 */
+	int yy_is_our_buffer;
+
+	/* Whether this is an "interactive" input source; if so, and
+	 * if we're using stdio for input, then we want to use getc()
+	 * instead of fread(), to make sure we stop fetching input after
+	 * each newline.
+	 */
+	int yy_is_interactive;
+
+	/* Whether we're considered to be at the beginning of a line.
+	 * If so, '^' rules will be active on the next match, otherwise
+	 * not.
+	 */
+	int yy_at_bol;
+
+    int yy_bs_lineno; /**< The line count. */
+    int yy_bs_column; /**< The column count. */
+    
+	/* Whether to try to fill the input buffer when we reach the
+	 * end of it.
+	 */
+	int yy_fill_buffer;
+
+	int yy_buffer_status;
+
+	};
+#endif /* !YY_STRUCT_YY_BUFFER_STATE */
+
+void parse_events_restart (FILE *input_file  );
+void parse_events__switch_to_buffer (YY_BUFFER_STATE new_buffer  );
+YY_BUFFER_STATE parse_events__create_buffer (FILE *file,int size  );
+void parse_events__delete_buffer (YY_BUFFER_STATE b  );
+void parse_events__flush_buffer (YY_BUFFER_STATE b  );
+void parse_events_push_buffer_state (YY_BUFFER_STATE new_buffer  );
+void parse_events_pop_buffer_state (void );
+
+YY_BUFFER_STATE parse_events__scan_buffer (char *base,yy_size_t size  );
+YY_BUFFER_STATE parse_events__scan_string (yyconst char *yy_str  );
+YY_BUFFER_STATE parse_events__scan_bytes (yyconst char *bytes,int len  );
+
+void *parse_events_alloc (yy_size_t  );
+void *parse_events_realloc (void *,yy_size_t  );
+void parse_events_free (void *  );
+
+/* Begin user sect3 */
+
+extern int parse_events_lineno;
+
+extern char *parse_events_text;
+#define yytext_ptr parse_events_text
+
+#ifdef YY_HEADER_EXPORT_START_CONDITIONS
+#define INITIAL 0
+
+#endif
+
+#ifndef YY_NO_UNISTD_H
+/* Special case for "unistd.h", since it is non-ANSI. We include it way
+ * down here because we want the user's section 1 to have been scanned first.
+ * The user has a chance to override it with an option.
+ */
+#include <unistd.h>
+#endif
+
+#ifndef YY_EXTRA_TYPE
+#define YY_EXTRA_TYPE void *
+#endif
+
+/* Accessor methods to globals.
+   These are made visible to non-reentrant scanners for convenience. */
+
+int parse_events_lex_destroy (void );
+
+int parse_events_get_debug (void );
+
+void parse_events_set_debug (int debug_flag  );
+
+YY_EXTRA_TYPE parse_events_get_extra (void );
+
+void parse_events_set_extra (YY_EXTRA_TYPE user_defined  );
+
+FILE *parse_events_get_in (void );
+
+void parse_events_set_in  (FILE * in_str  );
+
+FILE *parse_events_get_out (void );
+
+void parse_events_set_out  (FILE * out_str  );
+
+int parse_events_get_leng (void );
+
+char *parse_events_get_text (void );
+
+int parse_events_get_lineno (void );
+
+void parse_events_set_lineno (int line_number  );
+
+/* Macros after this point can all be overridden by user definitions in
+ * section 1.
+ */
+
+#ifndef YY_SKIP_YYWRAP
+#ifdef __cplusplus
+extern "C" int parse_events_wrap (void );
+#else
+extern int parse_events_wrap (void );
+#endif
+#endif
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char *,yyconst char *,int );
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * );
+#endif
+
+#ifndef YY_NO_INPUT
+
+#endif
+
+/* Amount of stuff to slurp up with each read. */
+#ifndef YY_READ_BUF_SIZE
+#define YY_READ_BUF_SIZE 8192
+#endif
+
+/* Number of entries by which start-condition stack grows. */
+#ifndef YY_START_STACK_INCR
+#define YY_START_STACK_INCR 25
+#endif
+
+/* Default declaration of generated scanner - a define so the user can
+ * easily add parameters.
+ */
+#ifndef YY_DECL
+#define YY_DECL_IS_OURS 1
+
+extern int parse_events_lex (void);
+
+#define YY_DECL int parse_events_lex (void)
+#endif /* !YY_DECL */
+
+/* yy_get_previous_state - get the state just before the EOB char was reached */
+
+#undef YY_NEW_FILE
+#undef YY_FLUSH_BUFFER
+#undef yy_set_bol
+#undef yy_new_buffer
+#undef yy_set_interactive
+#undef YY_DO_BEFORE_ACTION
+
+#ifdef YY_DECL_IS_OURS
+#undef YY_DECL_IS_OURS
+#undef YY_DECL
+#endif
+
+#line 121 "util/parse-events.l"
+
+
+#line 315 "util/parse-events-flex.h"
+#undef parse_events_IN_HEADER
+#endif /* parse_events_HEADER_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c7a6f6f..201b40f 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -11,6 +11,10 @@
 #include "cache.h"
 #include "header.h"
 #include "debugfs.h"
+#include "parse-events-flex.h"
+#include "pmu.h"
+
+#define MAX_NAME_LEN 100
 
 struct event_symbol {
 	u8		type;
@@ -19,11 +23,7 @@
 	const char	*alias;
 };
 
-enum event_result {
-	EVT_FAILED,
-	EVT_HANDLED,
-	EVT_HANDLED_ALL
-};
+int parse_events_parse(struct list_head *list, int *idx);
 
 #define CHW(x) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_##x
 #define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x
@@ -354,7 +354,24 @@
 	return "unknown";
 }
 
-static int parse_aliases(const char **str, const char *names[][MAX_ALIASES], int size)
+static int add_event(struct list_head *list, int *idx,
+		     struct perf_event_attr *attr, char *name)
+{
+	struct perf_evsel *evsel;
+
+	event_attr_init(attr);
+
+	evsel = perf_evsel__new(attr, (*idx)++);
+	if (!evsel)
+		return -ENOMEM;
+
+	list_add_tail(&evsel->node, list);
+
+	evsel->name = strdup(name);
+	return 0;
+}
+
+static int parse_aliases(char *str, const char *names[][MAX_ALIASES], int size)
 {
 	int i, j;
 	int n, longest = -1;
@@ -362,58 +379,57 @@
 	for (i = 0; i < size; i++) {
 		for (j = 0; j < MAX_ALIASES && names[i][j]; j++) {
 			n = strlen(names[i][j]);
-			if (n > longest && !strncasecmp(*str, names[i][j], n))
+			if (n > longest && !strncasecmp(str, names[i][j], n))
 				longest = n;
 		}
-		if (longest > 0) {
-			*str += longest;
+		if (longest > 0)
 			return i;
-		}
 	}
 
 	return -1;
 }
 
-static enum event_result
-parse_generic_hw_event(const char **str, struct perf_event_attr *attr)
+int parse_events_add_cache(struct list_head *list, int *idx,
+			   char *type, char *op_result1, char *op_result2)
 {
-	const char *s = *str;
+	struct perf_event_attr attr;
+	char name[MAX_NAME_LEN];
 	int cache_type = -1, cache_op = -1, cache_result = -1;
+	char *op_result[2] = { op_result1, op_result2 };
+	int i, n;
 
-	cache_type = parse_aliases(&s, hw_cache, PERF_COUNT_HW_CACHE_MAX);
 	/*
 	 * No fallback - if we cannot get a clear cache type
 	 * then bail out:
 	 */
+	cache_type = parse_aliases(type, hw_cache,
+				   PERF_COUNT_HW_CACHE_MAX);
 	if (cache_type == -1)
-		return EVT_FAILED;
+		return -EINVAL;
 
-	while ((cache_op == -1 || cache_result == -1) && *s == '-') {
-		++s;
+	n = snprintf(name, MAX_NAME_LEN, "%s", type);
+
+	for (i = 0; (i < 2) && (op_result[i]); i++) {
+		char *str = op_result[i];
+
+		snprintf(name + n, MAX_NAME_LEN - n, "-%s\n", str);
 
 		if (cache_op == -1) {
-			cache_op = parse_aliases(&s, hw_cache_op,
-						PERF_COUNT_HW_CACHE_OP_MAX);
+			cache_op = parse_aliases(str, hw_cache_op,
+						 PERF_COUNT_HW_CACHE_OP_MAX);
 			if (cache_op >= 0) {
 				if (!is_cache_op_valid(cache_type, cache_op))
-					return EVT_FAILED;
+					return -EINVAL;
 				continue;
 			}
 		}
 
 		if (cache_result == -1) {
-			cache_result = parse_aliases(&s, hw_cache_result,
+			cache_result = parse_aliases(str, hw_cache_result,
 						PERF_COUNT_HW_CACHE_RESULT_MAX);
 			if (cache_result >= 0)
 				continue;
 		}
-
-		/*
-		 * Can't parse this as a cache op or result, so back up
-		 * to the '-'.
-		 */
-		--s;
-		break;
 	}
 
 	/*
@@ -428,20 +444,17 @@
 	if (cache_result == -1)
 		cache_result = PERF_COUNT_HW_CACHE_RESULT_ACCESS;
 
-	attr->config = cache_type | (cache_op << 8) | (cache_result << 16);
-	attr->type = PERF_TYPE_HW_CACHE;
-
-	*str = s;
-	return EVT_HANDLED;
+	memset(&attr, 0, sizeof(attr));
+	attr.config = cache_type | (cache_op << 8) | (cache_result << 16);
+	attr.type = PERF_TYPE_HW_CACHE;
+	return add_event(list, idx, &attr, name);
 }
 
-static enum event_result
-parse_single_tracepoint_event(char *sys_name,
-			      const char *evt_name,
-			      unsigned int evt_length,
-			      struct perf_event_attr *attr,
-			      const char **strp)
+static int add_tracepoint(struct list_head *list, int *idx,
+			  char *sys_name, char *evt_name)
 {
+	struct perf_event_attr attr;
+	char name[MAX_NAME_LEN];
 	char evt_path[MAXPATHLEN];
 	char id_buf[4];
 	u64 id;
@@ -452,130 +465,80 @@
 
 	fd = open(evt_path, O_RDONLY);
 	if (fd < 0)
-		return EVT_FAILED;
+		return -1;
 
 	if (read(fd, id_buf, sizeof(id_buf)) < 0) {
 		close(fd);
-		return EVT_FAILED;
+		return -1;
 	}
 
 	close(fd);
 	id = atoll(id_buf);
-	attr->config = id;
-	attr->type = PERF_TYPE_TRACEPOINT;
-	*strp += strlen(sys_name) + evt_length + 1; /* + 1 for the ':' */
 
-	attr->sample_type |= PERF_SAMPLE_RAW;
-	attr->sample_type |= PERF_SAMPLE_TIME;
-	attr->sample_type |= PERF_SAMPLE_CPU;
+	memset(&attr, 0, sizeof(attr));
+	attr.config = id;
+	attr.type = PERF_TYPE_TRACEPOINT;
+	attr.sample_type |= PERF_SAMPLE_RAW;
+	attr.sample_type |= PERF_SAMPLE_TIME;
+	attr.sample_type |= PERF_SAMPLE_CPU;
+	attr.sample_period = 1;
 
-	attr->sample_period = 1;
-
-
-	return EVT_HANDLED;
+	snprintf(name, MAX_NAME_LEN, "%s:%s", sys_name, evt_name);
+	return add_event(list, idx, &attr, name);
 }
 
-/* sys + ':' + event + ':' + flags*/
-#define MAX_EVOPT_LEN	(MAX_EVENT_LENGTH * 2 + 2 + 128)
-static enum event_result
-parse_multiple_tracepoint_event(struct perf_evlist *evlist, char *sys_name,
-				const char *evt_exp, char *flags)
+static int add_tracepoint_multi(struct list_head *list, int *idx,
+				char *sys_name, char *evt_name)
 {
 	char evt_path[MAXPATHLEN];
 	struct dirent *evt_ent;
 	DIR *evt_dir;
+	int ret = 0;
 
 	snprintf(evt_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_name);
 	evt_dir = opendir(evt_path);
-
 	if (!evt_dir) {
 		perror("Can't open event dir");
-		return EVT_FAILED;
+		return -1;
 	}
 
-	while ((evt_ent = readdir(evt_dir))) {
-		char event_opt[MAX_EVOPT_LEN + 1];
-		int len;
-
+	while (!ret && (evt_ent = readdir(evt_dir))) {
 		if (!strcmp(evt_ent->d_name, ".")
 		    || !strcmp(evt_ent->d_name, "..")
 		    || !strcmp(evt_ent->d_name, "enable")
 		    || !strcmp(evt_ent->d_name, "filter"))
 			continue;
 
-		if (!strglobmatch(evt_ent->d_name, evt_exp))
+		if (!strglobmatch(evt_ent->d_name, evt_name))
 			continue;
 
-		len = snprintf(event_opt, MAX_EVOPT_LEN, "%s:%s%s%s", sys_name,
-			       evt_ent->d_name, flags ? ":" : "",
-			       flags ?: "");
-		if (len < 0)
-			return EVT_FAILED;
-
-		if (parse_events(evlist, event_opt, 0))
-			return EVT_FAILED;
+		ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name);
 	}
 
-	return EVT_HANDLED_ALL;
+	return ret;
 }
 
-static enum event_result
-parse_tracepoint_event(struct perf_evlist *evlist, const char **strp,
-		       struct perf_event_attr *attr)
+int parse_events_add_tracepoint(struct list_head *list, int *idx,
+				char *sys, char *event)
 {
-	const char *evt_name;
-	char *flags = NULL, *comma_loc;
-	char sys_name[MAX_EVENT_LENGTH];
-	unsigned int sys_length, evt_length;
+	int ret;
 
-	if (debugfs_valid_mountpoint(tracing_events_path))
-		return 0;
+	ret = debugfs_valid_mountpoint(tracing_events_path);
+	if (ret)
+		return ret;
 
-	evt_name = strchr(*strp, ':');
-	if (!evt_name)
-		return EVT_FAILED;
-
-	sys_length = evt_name - *strp;
-	if (sys_length >= MAX_EVENT_LENGTH)
-		return 0;
-
-	strncpy(sys_name, *strp, sys_length);
-	sys_name[sys_length] = '\0';
-	evt_name = evt_name + 1;
-
-	comma_loc = strchr(evt_name, ',');
-	if (comma_loc) {
-		/* take the event name up to the comma */
-		evt_name = strndup(evt_name, comma_loc - evt_name);
-	}
-	flags = strchr(evt_name, ':');
-	if (flags) {
-		/* split it out: */
-		evt_name = strndup(evt_name, flags - evt_name);
-		flags++;
-	}
-
-	evt_length = strlen(evt_name);
-	if (evt_length >= MAX_EVENT_LENGTH)
-		return EVT_FAILED;
-	if (strpbrk(evt_name, "*?")) {
-		*strp += strlen(sys_name) + evt_length + 1; /* 1 == the ':' */
-		return parse_multiple_tracepoint_event(evlist, sys_name,
-						       evt_name, flags);
-	} else {
-		return parse_single_tracepoint_event(sys_name, evt_name,
-						     evt_length, attr, strp);
-	}
+	return strpbrk(event, "*?") ?
+	       add_tracepoint_multi(list, idx, sys, event) :
+	       add_tracepoint(list, idx, sys, event);
 }
 
-static enum event_result
-parse_breakpoint_type(const char *type, const char **strp,
-		      struct perf_event_attr *attr)
+static int
+parse_breakpoint_type(const char *type, struct perf_event_attr *attr)
 {
 	int i;
 
 	for (i = 0; i < 3; i++) {
-		if (!type[i])
+		if (!type || !type[i])
 			break;
 
 		switch (type[i]) {
@@ -589,164 +552,134 @@
 			attr->bp_type |= HW_BREAKPOINT_X;
 			break;
 		default:
-			return EVT_FAILED;
+			return -EINVAL;
 		}
 	}
+
 	if (!attr->bp_type) /* Default */
 		attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W;
 
-	*strp = type + i;
-
-	return EVT_HANDLED;
+	return 0;
 }
 
-static enum event_result
-parse_breakpoint_event(const char **strp, struct perf_event_attr *attr)
+int parse_events_add_breakpoint(struct list_head *list, int *idx,
+				void *ptr, char *type)
 {
-	const char *target;
-	const char *type;
-	char *endaddr;
-	u64 addr;
-	enum event_result err;
+	struct perf_event_attr attr;
+	char name[MAX_NAME_LEN];
 
-	target = strchr(*strp, ':');
-	if (!target)
-		return EVT_FAILED;
+	memset(&attr, 0, sizeof(attr));
+	attr.bp_addr = (u64) ptr;
 
-	if (strncmp(*strp, "mem", target - *strp) != 0)
-		return EVT_FAILED;
-
-	target++;
-
-	addr = strtoull(target, &endaddr, 0);
-	if (target == endaddr)
-		return EVT_FAILED;
-
-	attr->bp_addr = addr;
-	*strp = endaddr;
-
-	type = strchr(target, ':');
-
-	/* If no type is defined, just rw as default */
-	if (!type) {
-		attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W;
-	} else {
-		err = parse_breakpoint_type(++type, strp, attr);
-		if (err == EVT_FAILED)
-			return EVT_FAILED;
-	}
+	if (parse_breakpoint_type(type, &attr))
+		return -EINVAL;
 
 	/*
 	 * We should find a nice way to override the access length
 	 * Provide some defaults for now
 	 */
-	if (attr->bp_type == HW_BREAKPOINT_X)
-		attr->bp_len = sizeof(long);
+	if (attr.bp_type == HW_BREAKPOINT_X)
+		attr.bp_len = sizeof(long);
 	else
-		attr->bp_len = HW_BREAKPOINT_LEN_4;
+		attr.bp_len = HW_BREAKPOINT_LEN_4;
 
-	attr->type = PERF_TYPE_BREAKPOINT;
+	attr.type = PERF_TYPE_BREAKPOINT;
 
-	return EVT_HANDLED;
+	snprintf(name, MAX_NAME_LEN, "mem:%p:%s", ptr, type ? type : "rw");
+	return add_event(list, idx, &attr, name);
 }
 
-static int check_events(const char *str, unsigned int i)
+static int config_term(struct perf_event_attr *attr,
+		       struct parse_events__term *term)
 {
-	int n;
-
-	n = strlen(event_symbols[i].symbol);
-	if (!strncasecmp(str, event_symbols[i].symbol, n))
-		return n;
-
-	n = strlen(event_symbols[i].alias);
-	if (n) {
-		if (!strncasecmp(str, event_symbols[i].alias, n))
-			return n;
+	switch (term->type) {
+	case PARSE_EVENTS__TERM_TYPE_CONFIG:
+		attr->config = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+		attr->config1 = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+		attr->config2 = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
+		attr->sample_period = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
+		/*
+		 * TODO uncomment when the field is available
+		 * attr->branch_sample_type = term->val.num;
+		 */
+		break;
+	default:
+		return -EINVAL;
 	}
+	return 0;
+}
+
+static int config_attr(struct perf_event_attr *attr,
+		       struct list_head *head, int fail)
+{
+	struct parse_events__term *term;
+
+	list_for_each_entry(term, head, list)
+		if (config_term(attr, term) && fail)
+			return -EINVAL;
 
 	return 0;
 }
 
-static enum event_result
-parse_symbolic_event(const char **strp, struct perf_event_attr *attr)
+int parse_events_add_numeric(struct list_head *list, int *idx,
+			     unsigned long type, unsigned long config,
+			     struct list_head *head_config)
 {
-	const char *str = *strp;
-	unsigned int i;
-	int n;
+	struct perf_event_attr attr;
 
-	for (i = 0; i < ARRAY_SIZE(event_symbols); i++) {
-		n = check_events(str, i);
-		if (n > 0) {
-			attr->type = event_symbols[i].type;
-			attr->config = event_symbols[i].config;
-			*strp = str + n;
-			return EVT_HANDLED;
-		}
-	}
-	return EVT_FAILED;
+	memset(&attr, 0, sizeof(attr));
+	attr.type = type;
+	attr.config = config;
+
+	if (head_config &&
+	    config_attr(&attr, head_config, 1))
+		return -EINVAL;
+
+	return add_event(list, idx, &attr,
+			 (char *) __event_name(type, config));
 }
 
-static enum event_result
-parse_raw_event(const char **strp, struct perf_event_attr *attr)
+int parse_events_add_pmu(struct list_head *list, int *idx,
+			 char *name, struct list_head *head_config)
 {
-	const char *str = *strp;
-	u64 config;
-	int n;
+	struct perf_event_attr attr;
+	struct perf_pmu *pmu;
 
-	if (*str != 'r')
-		return EVT_FAILED;
-	n = hex2u64(str + 1, &config);
-	if (n > 0) {
-		const char *end = str + n + 1;
-		if (*end != '\0' && *end != ',' && *end != ':')
-			return EVT_FAILED;
+	pmu = perf_pmu__find(name);
+	if (!pmu)
+		return -EINVAL;
 
-		*strp = end;
-		attr->type = PERF_TYPE_RAW;
-		attr->config = config;
-		return EVT_HANDLED;
-	}
-	return EVT_FAILED;
+	memset(&attr, 0, sizeof(attr));
+
+	/*
+	 * Configure hardcoded terms first, no need to check
+	 * return value when called with fail == 0 ;)
+	 */
+	config_attr(&attr, head_config, 0);
+
+	if (perf_pmu__config(pmu, &attr, head_config))
+		return -EINVAL;
+
+	return add_event(list, idx, &attr, (char *) "pmu");
 }
 
-static enum event_result
-parse_numeric_event(const char **strp, struct perf_event_attr *attr)
+int parse_events_modifier(struct list_head *list, char *str)
 {
-	const char *str = *strp;
-	char *endp;
-	unsigned long type;
-	u64 config;
-
-	type = strtoul(str, &endp, 0);
-	if (endp > str && type < PERF_TYPE_MAX && *endp == ':') {
-		str = endp + 1;
-		config = strtoul(str, &endp, 0);
-		if (endp > str) {
-			attr->type = type;
-			attr->config = config;
-			*strp = endp;
-			return EVT_HANDLED;
-		}
-	}
-	return EVT_FAILED;
-}
-
-static int
-parse_event_modifier(const char **strp, struct perf_event_attr *attr)
-{
-	const char *str = *strp;
+	struct perf_evsel *evsel;
 	int exclude = 0, exclude_GH = 0;
 	int eu = 0, ek = 0, eh = 0, eH = 0, eG = 0, precise = 0;
 
-	if (!*str)
+	if (str == NULL)
 		return 0;
 
-	if (*str == ',')
-		return 0;
-
-	if (*str++ != ':')
-		return -1;
-
 	while (*str) {
 		if (*str == 'u') {
 			if (!exclude)
@@ -775,111 +708,60 @@
 
 		++str;
 	}
-	if (str < *strp + 2)
-		return -1;
 
-	*strp = str;
+	/*
+	 * precise ip:
+	 *
+	 *  0 - SAMPLE_IP can have arbitrary skid
+	 *  1 - SAMPLE_IP must have constant skid
+	 *  2 - SAMPLE_IP requested to have 0 skid
+	 *  3 - SAMPLE_IP must have 0 skid
+	 *
+	 *  See also PERF_RECORD_MISC_EXACT_IP
+	 */
+	if (precise > 3)
+		return -EINVAL;
 
-	attr->exclude_user   = eu;
-	attr->exclude_kernel = ek;
-	attr->exclude_hv     = eh;
-	attr->precise_ip     = precise;
-	attr->exclude_host   = eH;
-	attr->exclude_guest  = eG;
+	list_for_each_entry(evsel, list, node) {
+		evsel->attr.exclude_user   = eu;
+		evsel->attr.exclude_kernel = ek;
+		evsel->attr.exclude_hv     = eh;
+		evsel->attr.precise_ip     = precise;
+		evsel->attr.exclude_host   = eH;
+		evsel->attr.exclude_guest  = eG;
+	}
 
 	return 0;
 }
 
-/*
- * Each event can have multiple symbolic names.
- * Symbolic names are (almost) exactly matched.
- */
-static enum event_result
-parse_event_symbols(struct perf_evlist *evlist, const char **str,
-		    struct perf_event_attr *attr)
+int parse_events(struct perf_evlist *evlist, const char *str, int unset __used)
 {
-	enum event_result ret;
+	struct perf_evsel *evsel, *h;
+	LIST_HEAD(list);
+	YY_BUFFER_STATE buffer;
+	int ret, idx = evlist->nr_entries;
 
-	ret = parse_tracepoint_event(evlist, str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	buffer = parse_events__scan_string(str);
 
-	ret = parse_raw_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	ret = parse_events_parse(&list, &idx);
 
-	ret = parse_numeric_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	parse_events__flush_buffer(buffer);
+	parse_events__delete_buffer(buffer);
 
-	ret = parse_symbolic_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	if (!ret) {
+		int entries = idx - evlist->nr_entries;
+		perf_evlist__splice_list_tail(evlist, &list, entries);
+		return 0;
+	}
 
-	ret = parse_generic_hw_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	list_for_each_entry_safe(evsel, h, &list, node)
+		perf_evsel__delete(evsel);
 
-	ret = parse_breakpoint_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
-
-	fprintf(stderr, "invalid or unsupported event: '%s'\n", *str);
+	fprintf(stderr, "invalid or unsupported event: '%s'\n", str);
 	fprintf(stderr, "Run 'perf list' for a list of valid events\n");
-	return EVT_FAILED;
-
-modifier:
-	if (parse_event_modifier(str, attr) < 0) {
-		fprintf(stderr, "invalid event modifier: '%s'\n", *str);
-		fprintf(stderr, "Run 'perf list' for a list of valid events and modifiers\n");
-
-		return EVT_FAILED;
-	}
-
 	return ret;
 }
 
-int parse_events(struct perf_evlist *evlist , const char *str, int unset __used)
-{
-	struct perf_event_attr attr;
-	enum event_result ret;
-	const char *ostr;
-
-	for (;;) {
-		ostr = str;
-		memset(&attr, 0, sizeof(attr));
-		event_attr_init(&attr);
-		ret = parse_event_symbols(evlist, &str, &attr);
-		if (ret == EVT_FAILED)
-			return -1;
-
-		if (!(*str == 0 || *str == ',' || isspace(*str)))
-			return -1;
-
-		if (ret != EVT_HANDLED_ALL) {
-			struct perf_evsel *evsel;
-			evsel = perf_evsel__new(&attr, evlist->nr_entries);
-			if (evsel == NULL)
-				return -1;
-			perf_evlist__add(evlist, evsel);
-
-			evsel->name = calloc(str - ostr + 1, 1);
-			if (!evsel->name)
-				return -1;
-			strncpy(evsel->name, ostr, str - ostr);
-		}
-
-		if (*str == 0)
-			break;
-		if (*str == ',')
-			++str;
-		while (isspace(*str))
-			++str;
-	}
-
-	return 0;
-}
-
 int parse_events_option(const struct option *opt, const char *str,
 			int unset __used)
 {
@@ -1052,8 +934,6 @@
 	return printed;
 }
 
-#define MAX_NAME_LEN 100
-
 /*
  * Print the help text for the event symbols:
  */
@@ -1102,8 +982,12 @@
 
 	printf("\n");
 	printf("  %-50s [%s]\n",
-		"rNNN (see 'perf list --help' on how to encode it)",
+	       "rNNN",
 	       event_type_descriptors[PERF_TYPE_RAW]);
+	printf("  %-50s [%s]\n",
+	       "cpu/t1=v1[,t2=v2,t3 ...]/modifier",
+	       event_type_descriptors[PERF_TYPE_RAW]);
+	printf("   (see 'perf list --help' on how to encode it)\n");
 	printf("\n");
 
 	printf("  %-50s [%s]\n",
@@ -1113,3 +997,51 @@
 
 	print_tracepoint_events(NULL, NULL);
 }
+
+int parse_events__is_hardcoded_term(struct parse_events__term *term)
+{
+	return term->type <= PARSE_EVENTS__TERM_TYPE_HARDCODED_MAX;
+}
+
+int parse_events__new_term(struct parse_events__term **_term, int type,
+			   char *config, char *str, long num)
+{
+	struct parse_events__term *term;
+
+	term = zalloc(sizeof(*term));
+	if (!term)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&term->list);
+	term->type = type;
+	term->config = config;
+
+	switch (type) {
+	case PARSE_EVENTS__TERM_TYPE_CONFIG:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+	case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
+	case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
+	case PARSE_EVENTS__TERM_TYPE_NUM:
+		term->val.num = num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_STR:
+		term->val.str = str;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*_term = term;
+	return 0;
+}
+
+void parse_events__free_terms(struct list_head *terms)
+{
+	struct parse_events__term *term, *h;
+
+	list_for_each_entry_safe(term, h, terms, list)
+		free(term);
+
+	free(terms);
+}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 7e0cbe7..6d7c74b 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -33,6 +33,52 @@
 
 #define EVENTS_HELP_MAX (128*1024)
 
+enum {
+	PARSE_EVENTS__TERM_TYPE_CONFIG,
+	PARSE_EVENTS__TERM_TYPE_CONFIG1,
+	PARSE_EVENTS__TERM_TYPE_CONFIG2,
+	PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD,
+	PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE,
+	PARSE_EVENTS__TERM_TYPE_NUM,
+	PARSE_EVENTS__TERM_TYPE_STR,
+
+	PARSE_EVENTS__TERM_TYPE_HARDCODED_MAX =
+		PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE,
+};
+
+struct parse_events__term {
+	char *config;
+	union {
+		char *str;
+		long  num;
+	} val;
+	int type;
+
+	struct list_head list;
+};
+
+int parse_events__is_hardcoded_term(struct parse_events__term *term);
+int parse_events__new_term(struct parse_events__term **term, int type,
+			   char *config, char *str, long num);
+void parse_events__free_terms(struct list_head *terms);
+int parse_events_modifier(struct list_head *list __used, char *str __used);
+int parse_events_add_tracepoint(struct list_head *list, int *idx,
+				char *sys, char *event);
+int parse_events_add_raw(struct perf_evlist *evlist, unsigned long config,
+			 unsigned long config1, unsigned long config2,
+			 char *mod);
+int parse_events_add_numeric(struct list_head *list, int *idx,
+			     unsigned long type, unsigned long config,
+			     struct list_head *head_config);
+int parse_events_add_cache(struct list_head *list, int *idx,
+			   char *type, char *op_result1, char *op_result2);
+int parse_events_add_breakpoint(struct list_head *list, int *idx,
+				void *ptr, char *type);
+int parse_events_add_pmu(struct list_head *list, int *idx,
+			 char *pmu , struct list_head *head_config);
+void parse_events_error(struct list_head *list, int *idx,
+			char const *msg);
+
 void print_events(const char *event_glob);
 void print_events_type(u8 type);
 void print_tracepoint_events(const char *subsys_glob, const char *event_glob);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
new file mode 100644
index 0000000..ab9eca1
--- /dev/null
+++ b/tools/perf/util/parse-events.l
@@ -0,0 +1,126 @@
+
+%option prefix="parse_events_"
+
+%{
+#include <errno.h>
+#include "../perf.h"
+#include "parse-events-bison.h"
+#include "parse-events.h"
+
+static int __value(char *str, int base, int token)
+{
+	long num;
+
+	errno = 0;
+	num = strtoul(str, NULL, base);
+	if (errno)
+		return PE_ERROR;
+
+	parse_events_lval.num = num;
+	return token;
+}
+
+static int value(int base)
+{
+	return __value(parse_events_text, base, PE_VALUE);
+}
+
+static int raw(void)
+{
+	return __value(parse_events_text + 1, 16, PE_RAW);
+}
+
+static int str(int token)
+{
+	parse_events_lval.str = strdup(parse_events_text);
+	return token;
+}
+
+static int sym(int type, int config)
+{
+	parse_events_lval.num = (type << 16) + config;
+	return PE_VALUE_SYM;
+}
+
+static int term(int type)
+{
+	parse_events_lval.num = type;
+	return PE_TERM;
+}
+
+%}
+
+num_dec		[0-9]+
+num_hex		0x[a-fA-F0-9]+
+num_raw_hex	[a-fA-F0-9]+
+name		[a-zA-Z_*?][a-zA-Z0-9_*?]*
+modifier_event	[ukhp]{1,5}
+modifier_bp	[rwx]
+
+%%
+cpu-cycles|cycles				{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
+stalled-cycles-frontend|idle-cycles-frontend	{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
+stalled-cycles-backend|idle-cycles-backend	{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
+instructions					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); }
+cache-references				{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); }
+cache-misses					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); }
+branch-instructions|branches			{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
+branch-misses					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); }
+bus-cycles					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); }
+cpu-clock					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); }
+task-clock					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); }
+page-faults|faults				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); }
+minor-faults					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
+major-faults					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
+context-switches|cs				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); }
+cpu-migrations|migrations			{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); }
+alignment-faults				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
+emulation-faults				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
+
+L1-dcache|l1-d|l1d|L1-data		|
+L1-icache|l1-i|l1i|L1-instruction	|
+LLC|L2					|
+dTLB|d-tlb|Data-TLB			|
+iTLB|i-tlb|Instruction-TLB		|
+branch|branches|bpu|btb|bpc		|
+node					{ return str(PE_NAME_CACHE_TYPE); }
+
+load|loads|read				|
+store|stores|write			|
+prefetch|prefetches			|
+speculative-read|speculative-load	|
+refs|Reference|ops|access		|
+misses|miss				{ return str(PE_NAME_CACHE_OP_RESULT); }
+
+	/*
+	 * These are event config hardcoded term names to be specified
+	 * within xxx/.../ syntax. So far we dont clash with other names,
+	 * so we can put them here directly. In case the we have a conflict
+	 * in future, this needs to go into '//' condition block.
+	 */
+config			{ return term(PARSE_EVENTS__TERM_TYPE_CONFIG); }
+config1			{ return term(PARSE_EVENTS__TERM_TYPE_CONFIG1); }
+config2			{ return term(PARSE_EVENTS__TERM_TYPE_CONFIG2); }
+period			{ return term(PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
+branch_type		{ return term(PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
+
+mem:			{ return PE_PREFIX_MEM; }
+r{num_raw_hex}		{ return raw(); }
+{num_dec}		{ return value(10); }
+{num_hex}		{ return value(16); }
+
+{modifier_event}	{ return str(PE_MODIFIER_EVENT); }
+{modifier_bp}		{ return str(PE_MODIFIER_BP); }
+{name}			{ return str(PE_NAME); }
+"/"			{ return '/'; }
+-			{ return '-'; }
+,			{ return ','; }
+:			{ return ':'; }
+=			{ return '='; }
+
+%%
+
+int parse_events_wrap(void)
+{
+	return 1;
+}
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
new file mode 100644
index 0000000..3a53019
--- /dev/null
+++ b/tools/perf/util/parse-events.y
@@ -0,0 +1,217 @@
+
+%name-prefix "parse_events_"
+%parse-param {struct list_head *list}
+%parse-param {int *idx}
+
+%{
+
+#define YYDEBUG 1
+
+#include <linux/compiler.h>
+#include <linux/list.h>
+#include "types.h"
+#include "util.h"
+#include "parse-events.h"
+
+extern int parse_events_lex (void);
+
+#define ABORT_ON(val) \
+do { \
+	if (val) \
+		YYABORT; \
+} while (0)
+
+%}
+
+%token PE_VALUE PE_VALUE_SYM PE_RAW PE_TERM
+%token PE_NAME
+%token PE_MODIFIER_EVENT PE_MODIFIER_BP
+%token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT
+%token PE_PREFIX_MEM PE_PREFIX_RAW
+%token PE_ERROR
+%type <num> PE_VALUE
+%type <num> PE_VALUE_SYM
+%type <num> PE_RAW
+%type <num> PE_TERM
+%type <str> PE_NAME
+%type <str> PE_NAME_CACHE_TYPE
+%type <str> PE_NAME_CACHE_OP_RESULT
+%type <str> PE_MODIFIER_EVENT
+%type <str> PE_MODIFIER_BP
+%type <head> event_config
+%type <term> event_term
+
+%union
+{
+	char *str;
+	unsigned long num;
+	struct list_head *head;
+	struct parse_events__term *term;
+}
+%%
+
+events:
+events ',' event | event
+
+event:
+event_def PE_MODIFIER_EVENT
+{
+	ABORT_ON(parse_events_modifier(list, $2));
+}
+|
+event_def
+
+event_def: event_pmu |
+	   event_legacy_symbol |
+	   event_legacy_cache sep_dc |
+	   event_legacy_mem |
+	   event_legacy_tracepoint sep_dc |
+	   event_legacy_numeric sep_dc |
+	   event_legacy_raw sep_dc
+
+event_pmu:
+PE_NAME '/' event_config '/'
+{
+	ABORT_ON(parse_events_add_pmu(list, idx, $1, $3));
+	parse_events__free_terms($3);
+}
+
+event_legacy_symbol:
+PE_VALUE_SYM '/' event_config '/'
+{
+	int type = $1 >> 16;
+	int config = $1 & 255;
+
+	ABORT_ON(parse_events_add_numeric(list, idx, type, config, $3));
+	parse_events__free_terms($3);
+}
+|
+PE_VALUE_SYM sep_slash_dc
+{
+	int type = $1 >> 16;
+	int config = $1 & 255;
+
+	ABORT_ON(parse_events_add_numeric(list, idx, type, config, NULL));
+}
+
+event_legacy_cache:
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT
+{
+	ABORT_ON(parse_events_add_cache(list, idx, $1, $3, $5));
+}
+|
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT
+{
+	ABORT_ON(parse_events_add_cache(list, idx, $1, $3, NULL));
+}
+|
+PE_NAME_CACHE_TYPE
+{
+	ABORT_ON(parse_events_add_cache(list, idx, $1, NULL, NULL));
+}
+
+event_legacy_mem:
+PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
+{
+	ABORT_ON(parse_events_add_breakpoint(list, idx, (void *) $2, $4));
+}
+|
+PE_PREFIX_MEM PE_VALUE sep_dc
+{
+	ABORT_ON(parse_events_add_breakpoint(list, idx, (void *) $2, NULL));
+}
+
+event_legacy_tracepoint:
+PE_NAME ':' PE_NAME
+{
+	ABORT_ON(parse_events_add_tracepoint(list, idx, $1, $3));
+}
+
+event_legacy_numeric:
+PE_VALUE ':' PE_VALUE
+{
+	ABORT_ON(parse_events_add_numeric(list, idx, $1, $3, NULL));
+}
+
+event_legacy_raw:
+PE_RAW
+{
+	ABORT_ON(parse_events_add_numeric(list, idx, PERF_TYPE_RAW, $1, NULL));
+}
+
+event_config:
+event_config ',' event_term
+{
+	struct list_head *head = $1;
+	struct parse_events__term *term = $3;
+
+	ABORT_ON(!head);
+	list_add_tail(&term->list, head);
+	$$ = $1;
+}
+|
+event_term
+{
+	struct list_head *head = malloc(sizeof(*head));
+	struct parse_events__term *term = $1;
+
+	ABORT_ON(!head);
+	INIT_LIST_HEAD(head);
+	list_add_tail(&term->list, head);
+	$$ = head;
+}
+
+event_term:
+PE_NAME '=' PE_NAME
+{
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, PARSE_EVENTS__TERM_TYPE_STR,
+		 $1, $3, 0));
+	$$ = term;
+}
+|
+PE_NAME '=' PE_VALUE
+{
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, PARSE_EVENTS__TERM_TYPE_NUM,
+		 $1, NULL, $3));
+	$$ = term;
+}
+|
+PE_NAME
+{
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, PARSE_EVENTS__TERM_TYPE_NUM,
+		 $1, NULL, 1));
+	$$ = term;
+}
+|
+PE_TERM '=' PE_VALUE
+{
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, $1, NULL, NULL, $3));
+	$$ = term;
+}
+|
+PE_TERM
+{
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, $1, NULL, NULL, 1));
+	$$ = term;
+}
+
+sep_dc: ':' |
+
+sep_slash_dc: '/' | ':' |
+
+%%
+
+void parse_events_error(struct list_head *list __used, int *idx __used,
+			char const *msg __used)
+{
+}
diff --git a/tools/perf/util/pmu-bison.c b/tools/perf/util/pmu-bison.c
new file mode 100644
index 0000000..343521e
--- /dev/null
+++ b/tools/perf/util/pmu-bison.c
@@ -0,0 +1,1663 @@
+/* A Bison parser, made by GNU Bison 2.4.3.  */
+
+/* Skeleton implementation for Bison's Yacc-like parsers in C
+   
+      Copyright (C) 1984, 1989, 1990, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
+   2009, 2010 Free Software Foundation, Inc.
+   
+   This program is free software: you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation, either version 3 of the License, or
+   (at your option) any later version.
+   
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+   
+   You should have received a copy of the GNU General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
+
+/* As a special exception, you may create a larger work that contains
+   part or all of the Bison parser skeleton and distribute that work
+   under terms of your choice, so long as that work isn't itself a
+   parser generator using the skeleton or a modified version thereof
+   as a parser skeleton.  Alternatively, if you modify or redistribute
+   the parser skeleton itself, you may (at your option) remove this
+   special exception, which will cause the skeleton and the resulting
+   Bison output files to be licensed under the GNU General Public
+   License without this special exception.
+   
+   This special exception was added by the Free Software Foundation in
+   version 2.2 of Bison.  */
+
+/* C LALR(1) parser skeleton written by Richard Stallman, by
+   simplifying the original so-called "semantic" parser.  */
+
+/* All symbols defined below should begin with yy or YY, to avoid
+   infringing on user name space.  This should be done even for local
+   variables, as they might otherwise be expanded by user macros.
+   There are some unavoidable exceptions within include files to
+   define necessary library symbols; they are noted "INFRINGES ON
+   USER NAME SPACE" below.  */
+
+/* Identify Bison output.  */
+#define YYBISON 1
+
+/* Bison version.  */
+#define YYBISON_VERSION "2.4.3"
+
+/* Skeleton name.  */
+#define YYSKELETON_NAME "yacc.c"
+
+/* Pure parsers.  */
+#define YYPURE 0
+
+/* Push parsers.  */
+#define YYPUSH 0
+
+/* Pull parsers.  */
+#define YYPULL 1
+
+/* Using locations.  */
+#define YYLSP_NEEDED 0
+
+/* Substitute the variable and function names.  */
+#define yyparse         perf_pmu_parse
+#define yylex           perf_pmu_lex
+#define yyerror         perf_pmu_error
+#define yylval          perf_pmu_lval
+#define yychar          perf_pmu_char
+#define yydebug         perf_pmu_debug
+#define yynerrs         perf_pmu_nerrs
+
+
+/* Copy the first part of user declarations.  */
+
+/* Line 189 of yacc.c  */
+#line 6 "util/pmu.y"
+
+
+#include <linux/compiler.h>
+#include <linux/list.h>
+#include <linux/bitmap.h>
+#include <string.h>
+#include "pmu.h"
+
+extern int perf_pmu_lex (void);
+
+#define ABORT_ON(val) \
+do { \
+        if (val) \
+                YYABORT; \
+} while (0)
+
+
+
+/* Line 189 of yacc.c  */
+#line 99 "util/pmu-bison.c"
+
+/* Enabling traces.  */
+#ifndef YYDEBUG
+# define YYDEBUG 0
+#endif
+
+/* Enabling verbose error messages.  */
+#ifdef YYERROR_VERBOSE
+# undef YYERROR_VERBOSE
+# define YYERROR_VERBOSE 1
+#else
+# define YYERROR_VERBOSE 0
+#endif
+
+/* Enabling the token table.  */
+#ifndef YYTOKEN_TABLE
+# define YYTOKEN_TABLE 0
+#endif
+
+
+/* Tokens.  */
+#ifndef YYTOKENTYPE
+# define YYTOKENTYPE
+   /* Put the tokens into the symbol table, so that GDB and other debuggers
+      know about them.  */
+   enum yytokentype {
+     PP_CONFIG = 258,
+     PP_CONFIG1 = 259,
+     PP_CONFIG2 = 260,
+     PP_VALUE = 261,
+     PP_ERROR = 262
+   };
+#endif
+
+
+
+#if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED
+typedef union YYSTYPE
+{
+
+/* Line 214 of yacc.c  */
+#line 31 "util/pmu.y"
+
+	unsigned long num;
+	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
+
+
+
+/* Line 214 of yacc.c  */
+#line 149 "util/pmu-bison.c"
+} YYSTYPE;
+# define YYSTYPE_IS_TRIVIAL 1
+# define yystype YYSTYPE /* obsolescent; will be withdrawn */
+# define YYSTYPE_IS_DECLARED 1
+#endif
+
+
+/* Copy the second part of user declarations.  */
+
+
+/* Line 264 of yacc.c  */
+#line 161 "util/pmu-bison.c"
+
+#ifdef short
+# undef short
+#endif
+
+#ifdef YYTYPE_UINT8
+typedef YYTYPE_UINT8 yytype_uint8;
+#else
+typedef unsigned char yytype_uint8;
+#endif
+
+#ifdef YYTYPE_INT8
+typedef YYTYPE_INT8 yytype_int8;
+#elif (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+typedef signed char yytype_int8;
+#else
+typedef short int yytype_int8;
+#endif
+
+#ifdef YYTYPE_UINT16
+typedef YYTYPE_UINT16 yytype_uint16;
+#else
+typedef unsigned short int yytype_uint16;
+#endif
+
+#ifdef YYTYPE_INT16
+typedef YYTYPE_INT16 yytype_int16;
+#else
+typedef short int yytype_int16;
+#endif
+
+#ifndef YYSIZE_T
+# ifdef __SIZE_TYPE__
+#  define YYSIZE_T __SIZE_TYPE__
+# elif defined size_t
+#  define YYSIZE_T size_t
+# elif ! defined YYSIZE_T && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+#  include <stddef.h> /* INFRINGES ON USER NAME SPACE */
+#  define YYSIZE_T size_t
+# else
+#  define YYSIZE_T unsigned int
+# endif
+#endif
+
+#define YYSIZE_MAXIMUM ((YYSIZE_T) -1)
+
+#ifndef YY_
+# if defined YYENABLE_NLS && YYENABLE_NLS
+#  if ENABLE_NLS
+#   include <libintl.h> /* INFRINGES ON USER NAME SPACE */
+#   define YY_(msgid) dgettext ("bison-runtime", msgid)
+#  endif
+# endif
+# ifndef YY_
+#  define YY_(msgid) msgid
+# endif
+#endif
+
+/* Suppress unused-variable warnings by "using" E.  */
+#if ! defined lint || defined __GNUC__
+# define YYUSE(e) ((void) (e))
+#else
+# define YYUSE(e) /* empty */
+#endif
+
+/* Identity function, used to suppress warnings about constant conditions.  */
+#ifndef lint
+# define YYID(n) (n)
+#else
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static int
+YYID (int yyi)
+#else
+static int
+YYID (yyi)
+    int yyi;
+#endif
+{
+  return yyi;
+}
+#endif
+
+#if ! defined yyoverflow || YYERROR_VERBOSE
+
+/* The parser invokes alloca or malloc; define the necessary symbols.  */
+
+# ifdef YYSTACK_USE_ALLOCA
+#  if YYSTACK_USE_ALLOCA
+#   ifdef __GNUC__
+#    define YYSTACK_ALLOC __builtin_alloca
+#   elif defined __BUILTIN_VA_ARG_INCR
+#    include <alloca.h> /* INFRINGES ON USER NAME SPACE */
+#   elif defined _AIX
+#    define YYSTACK_ALLOC __alloca
+#   elif defined _MSC_VER
+#    include <malloc.h> /* INFRINGES ON USER NAME SPACE */
+#    define alloca _alloca
+#   else
+#    define YYSTACK_ALLOC alloca
+#    if ! defined _ALLOCA_H && ! defined _STDLIB_H && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+#     include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
+#     ifndef _STDLIB_H
+#      define _STDLIB_H 1
+#     endif
+#    endif
+#   endif
+#  endif
+# endif
+
+# ifdef YYSTACK_ALLOC
+   /* Pacify GCC's `empty if-body' warning.  */
+#  define YYSTACK_FREE(Ptr) do { /* empty */; } while (YYID (0))
+#  ifndef YYSTACK_ALLOC_MAXIMUM
+    /* The OS might guarantee only one guard page at the bottom of the stack,
+       and a page size can be as small as 4096 bytes.  So we cannot safely
+       invoke alloca (N) if N exceeds 4096.  Use a slightly smaller number
+       to allow for a few compiler-allocated temporary stack slots.  */
+#   define YYSTACK_ALLOC_MAXIMUM 4032 /* reasonable circa 2006 */
+#  endif
+# else
+#  define YYSTACK_ALLOC YYMALLOC
+#  define YYSTACK_FREE YYFREE
+#  ifndef YYSTACK_ALLOC_MAXIMUM
+#   define YYSTACK_ALLOC_MAXIMUM YYSIZE_MAXIMUM
+#  endif
+#  if (defined __cplusplus && ! defined _STDLIB_H \
+       && ! ((defined YYMALLOC || defined malloc) \
+	     && (defined YYFREE || defined free)))
+#   include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
+#   ifndef _STDLIB_H
+#    define _STDLIB_H 1
+#   endif
+#  endif
+#  ifndef YYMALLOC
+#   define YYMALLOC malloc
+#   if ! defined malloc && ! defined _STDLIB_H && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+void *malloc (YYSIZE_T); /* INFRINGES ON USER NAME SPACE */
+#   endif
+#  endif
+#  ifndef YYFREE
+#   define YYFREE free
+#   if ! defined free && ! defined _STDLIB_H && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+void free (void *); /* INFRINGES ON USER NAME SPACE */
+#   endif
+#  endif
+# endif
+#endif /* ! defined yyoverflow || YYERROR_VERBOSE */
+
+
+#if (! defined yyoverflow \
+     && (! defined __cplusplus \
+	 || (defined YYSTYPE_IS_TRIVIAL && YYSTYPE_IS_TRIVIAL)))
+
+/* A type that is properly aligned for any stack member.  */
+union yyalloc
+{
+  yytype_int16 yyss_alloc;
+  YYSTYPE yyvs_alloc;
+};
+
+/* The size of the maximum gap between one aligned stack and the next.  */
+# define YYSTACK_GAP_MAXIMUM (sizeof (union yyalloc) - 1)
+
+/* The size of an array large to enough to hold all stacks, each with
+   N elements.  */
+# define YYSTACK_BYTES(N) \
+     ((N) * (sizeof (yytype_int16) + sizeof (YYSTYPE)) \
+      + YYSTACK_GAP_MAXIMUM)
+
+/* Copy COUNT objects from FROM to TO.  The source and destination do
+   not overlap.  */
+# ifndef YYCOPY
+#  if defined __GNUC__ && 1 < __GNUC__
+#   define YYCOPY(To, From, Count) \
+      __builtin_memcpy (To, From, (Count) * sizeof (*(From)))
+#  else
+#   define YYCOPY(To, From, Count)		\
+      do					\
+	{					\
+	  YYSIZE_T yyi;				\
+	  for (yyi = 0; yyi < (Count); yyi++)	\
+	    (To)[yyi] = (From)[yyi];		\
+	}					\
+      while (YYID (0))
+#  endif
+# endif
+
+/* Relocate STACK from its old location to the new one.  The
+   local variables YYSIZE and YYSTACKSIZE give the old and new number of
+   elements in the stack, and YYPTR gives the new location of the
+   stack.  Advance YYPTR to a properly aligned location for the next
+   stack.  */
+# define YYSTACK_RELOCATE(Stack_alloc, Stack)				\
+    do									\
+      {									\
+	YYSIZE_T yynewbytes;						\
+	YYCOPY (&yyptr->Stack_alloc, Stack, yysize);			\
+	Stack = &yyptr->Stack_alloc;					\
+	yynewbytes = yystacksize * sizeof (*Stack) + YYSTACK_GAP_MAXIMUM; \
+	yyptr += yynewbytes / sizeof (*yyptr);				\
+      }									\
+    while (YYID (0))
+
+#endif
+
+/* YYFINAL -- State number of the termination state.  */
+#define YYFINAL  9
+/* YYLAST -- Last index in YYTABLE.  */
+#define YYLAST   17
+
+/* YYNTOKENS -- Number of terminals.  */
+#define YYNTOKENS  11
+/* YYNNTS -- Number of nonterminals.  */
+#define YYNNTS  5
+/* YYNRULES -- Number of rules.  */
+#define YYNRULES  10
+/* YYNRULES -- Number of states.  */
+#define YYNSTATES  20
+
+/* YYTRANSLATE(YYLEX) -- Bison symbol number corresponding to YYLEX.  */
+#define YYUNDEFTOK  2
+#define YYMAXUTOK   262
+
+#define YYTRANSLATE(YYX)						\
+  ((unsigned int) (YYX) <= YYMAXUTOK ? yytranslate[YYX] : YYUNDEFTOK)
+
+/* YYTRANSLATE[YYLEX] -- Bison symbol number corresponding to YYLEX.  */
+static const yytype_uint8 yytranslate[] =
+{
+       0,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     9,    10,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     8,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     1,     2,     3,     4,
+       5,     6,     7
+};
+
+#if YYDEBUG
+/* YYPRHS[YYN] -- Index of the first RHS symbol of rule number YYN in
+   YYRHS.  */
+static const yytype_uint8 yyprhs[] =
+{
+       0,     0,     3,     6,     8,    12,    16,    20,    24,    26,
+      30
+};
+
+/* YYRHS -- A `-1'-separated list of the rules' RHS.  */
+static const yytype_int8 yyrhs[] =
+{
+      12,     0,    -1,    12,    13,    -1,    13,    -1,     3,     8,
+      14,    -1,     4,     8,    14,    -1,     5,     8,    14,    -1,
+      14,     9,    15,    -1,    15,    -1,     6,    10,     6,    -1,
+       6,    -1
+};
+
+/* YYRLINE[YYN] -- source line where rule number YYN was defined.  */
+static const yytype_uint8 yyrline[] =
+{
+       0,    39,    39,    41,    44,    51,    58,    66,    71,    77,
+      82
+};
+#endif
+
+#if YYDEBUG || YYERROR_VERBOSE || YYTOKEN_TABLE
+/* YYTNAME[SYMBOL-NUM] -- String name of the symbol SYMBOL-NUM.
+   First, the terminals, then, starting at YYNTOKENS, nonterminals.  */
+static const char *const yytname[] =
+{
+  "$end", "error", "$undefined", "PP_CONFIG", "PP_CONFIG1", "PP_CONFIG2",
+  "PP_VALUE", "PP_ERROR", "':'", "','", "'-'", "$accept", "format",
+  "format_term", "bits", "bit_term", 0
+};
+#endif
+
+# ifdef YYPRINT
+/* YYTOKNUM[YYLEX-NUM] -- Internal token number corresponding to
+   token YYLEX-NUM.  */
+static const yytype_uint16 yytoknum[] =
+{
+       0,   256,   257,   258,   259,   260,   261,   262,    58,    44,
+      45
+};
+# endif
+
+/* YYR1[YYN] -- Symbol number of symbol that rule YYN derives.  */
+static const yytype_uint8 yyr1[] =
+{
+       0,    11,    12,    12,    13,    13,    13,    14,    14,    15,
+      15
+};
+
+/* YYR2[YYN] -- Number of symbols composing right hand side of rule YYN.  */
+static const yytype_uint8 yyr2[] =
+{
+       0,     2,     2,     1,     3,     3,     3,     3,     1,     3,
+       1
+};
+
+/* YYDEFACT[STATE-NAME] -- Default rule to reduce with in state
+   STATE-NUM when YYTABLE doesn't specify something else to do.  Zero
+   means the default is an error.  */
+static const yytype_uint8 yydefact[] =
+{
+       0,     0,     0,     0,     0,     3,     0,     0,     0,     1,
+       2,    10,     4,     8,     5,     6,     0,     0,     9,     7
+};
+
+/* YYDEFGOTO[NTERM-NUM].  */
+static const yytype_int8 yydefgoto[] =
+{
+      -1,     4,     5,    12,    13
+};
+
+/* YYPACT[STATE-NUM] -- Index in YYTABLE of the portion describing
+   STATE-NUM.  */
+#define YYPACT_NINF -7
+static const yytype_int8 yypact[] =
+{
+       3,     1,     2,     4,     0,    -7,     5,     5,     5,    -7,
+      -7,     6,     8,    -7,     8,     8,     7,     5,    -7,    -7
+};
+
+/* YYPGOTO[NTERM-NUM].  */
+static const yytype_int8 yypgoto[] =
+{
+      -7,    -7,    10,    -6,    -2
+};
+
+/* YYTABLE[YYPACT[STATE-NUM]].  What to do in state STATE-NUM.  If
+   positive, shift that token.  If negative, reduce the rule which
+   number is the opposite.  If zero, do what YYDEFACT says.
+   If YYTABLE_NINF, syntax error.  */
+#define YYTABLE_NINF -1
+static const yytype_uint8 yytable[] =
+{
+       9,    14,    15,     1,     2,     3,     1,     2,     3,     6,
+       7,    11,     8,    18,    10,    19,    16,    17
+};
+
+static const yytype_uint8 yycheck[] =
+{
+       0,     7,     8,     3,     4,     5,     3,     4,     5,     8,
+       8,     6,     8,     6,     4,    17,    10,     9
+};
+
+/* YYSTOS[STATE-NUM] -- The (internal number of the) accessing
+   symbol of state STATE-NUM.  */
+static const yytype_uint8 yystos[] =
+{
+       0,     3,     4,     5,    12,    13,     8,     8,     8,     0,
+      13,     6,    14,    15,    14,    14,    10,     9,     6,    15
+};
+
+#define yyerrok		(yyerrstatus = 0)
+#define yyclearin	(yychar = YYEMPTY)
+#define YYEMPTY		(-2)
+#define YYEOF		0
+
+#define YYACCEPT	goto yyacceptlab
+#define YYABORT		goto yyabortlab
+#define YYERROR		goto yyerrorlab
+
+
+/* Like YYERROR except do call yyerror.  This remains here temporarily
+   to ease the transition to the new meaning of YYERROR, for GCC.
+   Once GCC version 2 has supplanted version 1, this can go.  However,
+   YYFAIL appears to be in use.  Nevertheless, it is formally deprecated
+   in Bison 2.4.2's NEWS entry, where a plan to phase it out is
+   discussed.  */
+
+#define YYFAIL		goto yyerrlab
+#if defined YYFAIL
+  /* This is here to suppress warnings from the GCC cpp's
+     -Wunused-macros.  Normally we don't worry about that warning, but
+     some users do, and we want to make it easy for users to remove
+     YYFAIL uses, which will produce warnings from Bison 2.5.  */
+#endif
+
+#define YYRECOVERING()  (!!yyerrstatus)
+
+#define YYBACKUP(Token, Value)					\
+do								\
+  if (yychar == YYEMPTY && yylen == 1)				\
+    {								\
+      yychar = (Token);						\
+      yylval = (Value);						\
+      yytoken = YYTRANSLATE (yychar);				\
+      YYPOPSTACK (1);						\
+      goto yybackup;						\
+    }								\
+  else								\
+    {								\
+      yyerror (format, name, YY_("syntax error: cannot back up")); \
+      YYERROR;							\
+    }								\
+while (YYID (0))
+
+
+#define YYTERROR	1
+#define YYERRCODE	256
+
+
+/* YYLLOC_DEFAULT -- Set CURRENT to span from RHS[1] to RHS[N].
+   If N is 0, then set CURRENT to the empty location which ends
+   the previous symbol: RHS[0] (always defined).  */
+
+#define YYRHSLOC(Rhs, K) ((Rhs)[K])
+#ifndef YYLLOC_DEFAULT
+# define YYLLOC_DEFAULT(Current, Rhs, N)				\
+    do									\
+      if (YYID (N))                                                    \
+	{								\
+	  (Current).first_line   = YYRHSLOC (Rhs, 1).first_line;	\
+	  (Current).first_column = YYRHSLOC (Rhs, 1).first_column;	\
+	  (Current).last_line    = YYRHSLOC (Rhs, N).last_line;		\
+	  (Current).last_column  = YYRHSLOC (Rhs, N).last_column;	\
+	}								\
+      else								\
+	{								\
+	  (Current).first_line   = (Current).last_line   =		\
+	    YYRHSLOC (Rhs, 0).last_line;				\
+	  (Current).first_column = (Current).last_column =		\
+	    YYRHSLOC (Rhs, 0).last_column;				\
+	}								\
+    while (YYID (0))
+#endif
+
+
+/* YY_LOCATION_PRINT -- Print the location on the stream.
+   This macro was not mandated originally: define only if we know
+   we won't break user code: when these are the locations we know.  */
+
+#ifndef YY_LOCATION_PRINT
+# if defined YYLTYPE_IS_TRIVIAL && YYLTYPE_IS_TRIVIAL
+#  define YY_LOCATION_PRINT(File, Loc)			\
+     fprintf (File, "%d.%d-%d.%d",			\
+	      (Loc).first_line, (Loc).first_column,	\
+	      (Loc).last_line,  (Loc).last_column)
+# else
+#  define YY_LOCATION_PRINT(File, Loc) ((void) 0)
+# endif
+#endif
+
+
+/* YYLEX -- calling `yylex' with the right arguments.  */
+
+#ifdef YYLEX_PARAM
+# define YYLEX yylex (YYLEX_PARAM)
+#else
+# define YYLEX yylex ()
+#endif
+
+/* Enable debugging if requested.  */
+#if YYDEBUG
+
+# ifndef YYFPRINTF
+#  include <stdio.h> /* INFRINGES ON USER NAME SPACE */
+#  define YYFPRINTF fprintf
+# endif
+
+# define YYDPRINTF(Args)			\
+do {						\
+  if (yydebug)					\
+    YYFPRINTF Args;				\
+} while (YYID (0))
+
+# define YY_SYMBOL_PRINT(Title, Type, Value, Location)			  \
+do {									  \
+  if (yydebug)								  \
+    {									  \
+      YYFPRINTF (stderr, "%s ", Title);					  \
+      yy_symbol_print (stderr,						  \
+		  Type, Value, format, name); \
+      YYFPRINTF (stderr, "\n");						  \
+    }									  \
+} while (YYID (0))
+
+
+/*--------------------------------.
+| Print this symbol on YYOUTPUT.  |
+`--------------------------------*/
+
+/*ARGSUSED*/
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_symbol_value_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep, struct list_head *format, char *name)
+#else
+static void
+yy_symbol_value_print (yyoutput, yytype, yyvaluep, format, name)
+    FILE *yyoutput;
+    int yytype;
+    YYSTYPE const * const yyvaluep;
+    struct list_head *format;
+    char *name;
+#endif
+{
+  if (!yyvaluep)
+    return;
+  YYUSE (format);
+  YYUSE (name);
+# ifdef YYPRINT
+  if (yytype < YYNTOKENS)
+    YYPRINT (yyoutput, yytoknum[yytype], *yyvaluep);
+# else
+  YYUSE (yyoutput);
+# endif
+  switch (yytype)
+    {
+      default:
+	break;
+    }
+}
+
+
+/*--------------------------------.
+| Print this symbol on YYOUTPUT.  |
+`--------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_symbol_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep, struct list_head *format, char *name)
+#else
+static void
+yy_symbol_print (yyoutput, yytype, yyvaluep, format, name)
+    FILE *yyoutput;
+    int yytype;
+    YYSTYPE const * const yyvaluep;
+    struct list_head *format;
+    char *name;
+#endif
+{
+  if (yytype < YYNTOKENS)
+    YYFPRINTF (yyoutput, "token %s (", yytname[yytype]);
+  else
+    YYFPRINTF (yyoutput, "nterm %s (", yytname[yytype]);
+
+  yy_symbol_value_print (yyoutput, yytype, yyvaluep, format, name);
+  YYFPRINTF (yyoutput, ")");
+}
+
+/*------------------------------------------------------------------.
+| yy_stack_print -- Print the state stack from its BOTTOM up to its |
+| TOP (included).                                                   |
+`------------------------------------------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_stack_print (yytype_int16 *yybottom, yytype_int16 *yytop)
+#else
+static void
+yy_stack_print (yybottom, yytop)
+    yytype_int16 *yybottom;
+    yytype_int16 *yytop;
+#endif
+{
+  YYFPRINTF (stderr, "Stack now");
+  for (; yybottom <= yytop; yybottom++)
+    {
+      int yybot = *yybottom;
+      YYFPRINTF (stderr, " %d", yybot);
+    }
+  YYFPRINTF (stderr, "\n");
+}
+
+# define YY_STACK_PRINT(Bottom, Top)				\
+do {								\
+  if (yydebug)							\
+    yy_stack_print ((Bottom), (Top));				\
+} while (YYID (0))
+
+
+/*------------------------------------------------.
+| Report that the YYRULE is going to be reduced.  |
+`------------------------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_reduce_print (YYSTYPE *yyvsp, int yyrule, struct list_head *format, char *name)
+#else
+static void
+yy_reduce_print (yyvsp, yyrule, format, name)
+    YYSTYPE *yyvsp;
+    int yyrule;
+    struct list_head *format;
+    char *name;
+#endif
+{
+  int yynrhs = yyr2[yyrule];
+  int yyi;
+  unsigned long int yylno = yyrline[yyrule];
+  YYFPRINTF (stderr, "Reducing stack by rule %d (line %lu):\n",
+	     yyrule - 1, yylno);
+  /* The symbols being reduced.  */
+  for (yyi = 0; yyi < yynrhs; yyi++)
+    {
+      YYFPRINTF (stderr, "   $%d = ", yyi + 1);
+      yy_symbol_print (stderr, yyrhs[yyprhs[yyrule] + yyi],
+		       &(yyvsp[(yyi + 1) - (yynrhs)])
+		       		       , format, name);
+      YYFPRINTF (stderr, "\n");
+    }
+}
+
+# define YY_REDUCE_PRINT(Rule)		\
+do {					\
+  if (yydebug)				\
+    yy_reduce_print (yyvsp, Rule, format, name); \
+} while (YYID (0))
+
+/* Nonzero means print parse trace.  It is left uninitialized so that
+   multiple parsers can coexist.  */
+int yydebug;
+#else /* !YYDEBUG */
+# define YYDPRINTF(Args)
+# define YY_SYMBOL_PRINT(Title, Type, Value, Location)
+# define YY_STACK_PRINT(Bottom, Top)
+# define YY_REDUCE_PRINT(Rule)
+#endif /* !YYDEBUG */
+
+
+/* YYINITDEPTH -- initial size of the parser's stacks.  */
+#ifndef	YYINITDEPTH
+# define YYINITDEPTH 200
+#endif
+
+/* YYMAXDEPTH -- maximum size the stacks can grow to (effective only
+   if the built-in stack extension method is used).
+
+   Do not make this value too large; the results are undefined if
+   YYSTACK_ALLOC_MAXIMUM < YYSTACK_BYTES (YYMAXDEPTH)
+   evaluated with infinite-precision integer arithmetic.  */
+
+#ifndef YYMAXDEPTH
+# define YYMAXDEPTH 10000
+#endif
+
+
+
+#if YYERROR_VERBOSE
+
+# ifndef yystrlen
+#  if defined __GLIBC__ && defined _STRING_H
+#   define yystrlen strlen
+#  else
+/* Return the length of YYSTR.  */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static YYSIZE_T
+yystrlen (const char *yystr)
+#else
+static YYSIZE_T
+yystrlen (yystr)
+    const char *yystr;
+#endif
+{
+  YYSIZE_T yylen;
+  for (yylen = 0; yystr[yylen]; yylen++)
+    continue;
+  return yylen;
+}
+#  endif
+# endif
+
+# ifndef yystpcpy
+#  if defined __GLIBC__ && defined _STRING_H && defined _GNU_SOURCE
+#   define yystpcpy stpcpy
+#  else
+/* Copy YYSRC to YYDEST, returning the address of the terminating '\0' in
+   YYDEST.  */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static char *
+yystpcpy (char *yydest, const char *yysrc)
+#else
+static char *
+yystpcpy (yydest, yysrc)
+    char *yydest;
+    const char *yysrc;
+#endif
+{
+  char *yyd = yydest;
+  const char *yys = yysrc;
+
+  while ((*yyd++ = *yys++) != '\0')
+    continue;
+
+  return yyd - 1;
+}
+#  endif
+# endif
+
+# ifndef yytnamerr
+/* Copy to YYRES the contents of YYSTR after stripping away unnecessary
+   quotes and backslashes, so that it's suitable for yyerror.  The
+   heuristic is that double-quoting is unnecessary unless the string
+   contains an apostrophe, a comma, or backslash (other than
+   backslash-backslash).  YYSTR is taken from yytname.  If YYRES is
+   null, do not copy; instead, return the length of what the result
+   would have been.  */
+static YYSIZE_T
+yytnamerr (char *yyres, const char *yystr)
+{
+  if (*yystr == '"')
+    {
+      YYSIZE_T yyn = 0;
+      char const *yyp = yystr;
+
+      for (;;)
+	switch (*++yyp)
+	  {
+	  case '\'':
+	  case ',':
+	    goto do_not_strip_quotes;
+
+	  case '\\':
+	    if (*++yyp != '\\')
+	      goto do_not_strip_quotes;
+	    /* Fall through.  */
+	  default:
+	    if (yyres)
+	      yyres[yyn] = *yyp;
+	    yyn++;
+	    break;
+
+	  case '"':
+	    if (yyres)
+	      yyres[yyn] = '\0';
+	    return yyn;
+	  }
+    do_not_strip_quotes: ;
+    }
+
+  if (! yyres)
+    return yystrlen (yystr);
+
+  return yystpcpy (yyres, yystr) - yyres;
+}
+# endif
+
+/* Copy into YYRESULT an error message about the unexpected token
+   YYCHAR while in state YYSTATE.  Return the number of bytes copied,
+   including the terminating null byte.  If YYRESULT is null, do not
+   copy anything; just return the number of bytes that would be
+   copied.  As a special case, return 0 if an ordinary "syntax error"
+   message will do.  Return YYSIZE_MAXIMUM if overflow occurs during
+   size calculation.  */
+static YYSIZE_T
+yysyntax_error (char *yyresult, int yystate, int yychar)
+{
+  int yyn = yypact[yystate];
+
+  if (! (YYPACT_NINF < yyn && yyn <= YYLAST))
+    return 0;
+  else
+    {
+      int yytype = YYTRANSLATE (yychar);
+      YYSIZE_T yysize0 = yytnamerr (0, yytname[yytype]);
+      YYSIZE_T yysize = yysize0;
+      YYSIZE_T yysize1;
+      int yysize_overflow = 0;
+      enum { YYERROR_VERBOSE_ARGS_MAXIMUM = 5 };
+      char const *yyarg[YYERROR_VERBOSE_ARGS_MAXIMUM];
+      int yyx;
+
+# if 0
+      /* This is so xgettext sees the translatable formats that are
+	 constructed on the fly.  */
+      YY_("syntax error, unexpected %s");
+      YY_("syntax error, unexpected %s, expecting %s");
+      YY_("syntax error, unexpected %s, expecting %s or %s");
+      YY_("syntax error, unexpected %s, expecting %s or %s or %s");
+      YY_("syntax error, unexpected %s, expecting %s or %s or %s or %s");
+# endif
+      char *yyfmt;
+      char const *yyf;
+      static char const yyunexpected[] = "syntax error, unexpected %s";
+      static char const yyexpecting[] = ", expecting %s";
+      static char const yyor[] = " or %s";
+      char yyformat[sizeof yyunexpected
+		    + sizeof yyexpecting - 1
+		    + ((YYERROR_VERBOSE_ARGS_MAXIMUM - 2)
+		       * (sizeof yyor - 1))];
+      char const *yyprefix = yyexpecting;
+
+      /* Start YYX at -YYN if negative to avoid negative indexes in
+	 YYCHECK.  */
+      int yyxbegin = yyn < 0 ? -yyn : 0;
+
+      /* Stay within bounds of both yycheck and yytname.  */
+      int yychecklim = YYLAST - yyn + 1;
+      int yyxend = yychecklim < YYNTOKENS ? yychecklim : YYNTOKENS;
+      int yycount = 1;
+
+      yyarg[0] = yytname[yytype];
+      yyfmt = yystpcpy (yyformat, yyunexpected);
+
+      for (yyx = yyxbegin; yyx < yyxend; ++yyx)
+	if (yycheck[yyx + yyn] == yyx && yyx != YYTERROR)
+	  {
+	    if (yycount == YYERROR_VERBOSE_ARGS_MAXIMUM)
+	      {
+		yycount = 1;
+		yysize = yysize0;
+		yyformat[sizeof yyunexpected - 1] = '\0';
+		break;
+	      }
+	    yyarg[yycount++] = yytname[yyx];
+	    yysize1 = yysize + yytnamerr (0, yytname[yyx]);
+	    yysize_overflow |= (yysize1 < yysize);
+	    yysize = yysize1;
+	    yyfmt = yystpcpy (yyfmt, yyprefix);
+	    yyprefix = yyor;
+	  }
+
+      yyf = YY_(yyformat);
+      yysize1 = yysize + yystrlen (yyf);
+      yysize_overflow |= (yysize1 < yysize);
+      yysize = yysize1;
+
+      if (yysize_overflow)
+	return YYSIZE_MAXIMUM;
+
+      if (yyresult)
+	{
+	  /* Avoid sprintf, as that infringes on the user's name space.
+	     Don't have undefined behavior even if the translation
+	     produced a string with the wrong number of "%s"s.  */
+	  char *yyp = yyresult;
+	  int yyi = 0;
+	  while ((*yyp = *yyf) != '\0')
+	    {
+	      if (*yyp == '%' && yyf[1] == 's' && yyi < yycount)
+		{
+		  yyp += yytnamerr (yyp, yyarg[yyi++]);
+		  yyf += 2;
+		}
+	      else
+		{
+		  yyp++;
+		  yyf++;
+		}
+	    }
+	}
+      return yysize;
+    }
+}
+#endif /* YYERROR_VERBOSE */
+
+
+/*-----------------------------------------------.
+| Release the memory associated to this symbol.  |
+`-----------------------------------------------*/
+
+/*ARGSUSED*/
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yydestruct (const char *yymsg, int yytype, YYSTYPE *yyvaluep, struct list_head *format, char *name)
+#else
+static void
+yydestruct (yymsg, yytype, yyvaluep, format, name)
+    const char *yymsg;
+    int yytype;
+    YYSTYPE *yyvaluep;
+    struct list_head *format;
+    char *name;
+#endif
+{
+  YYUSE (yyvaluep);
+  YYUSE (format);
+  YYUSE (name);
+
+  if (!yymsg)
+    yymsg = "Deleting";
+  YY_SYMBOL_PRINT (yymsg, yytype, yyvaluep, yylocationp);
+
+  switch (yytype)
+    {
+
+      default:
+	break;
+    }
+}
+
+/* Prevent warnings from -Wmissing-prototypes.  */
+#ifdef YYPARSE_PARAM
+#if defined __STDC__ || defined __cplusplus
+int yyparse (void *YYPARSE_PARAM);
+#else
+int yyparse ();
+#endif
+#else /* ! YYPARSE_PARAM */
+#if defined __STDC__ || defined __cplusplus
+int yyparse (struct list_head *format, char *name);
+#else
+int yyparse ();
+#endif
+#endif /* ! YYPARSE_PARAM */
+
+
+/* The lookahead symbol.  */
+int yychar;
+
+/* The semantic value of the lookahead symbol.  */
+YYSTYPE yylval;
+
+/* Number of syntax errors so far.  */
+int yynerrs;
+
+
+
+/*-------------------------.
+| yyparse or yypush_parse.  |
+`-------------------------*/
+
+#ifdef YYPARSE_PARAM
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+int
+yyparse (void *YYPARSE_PARAM)
+#else
+int
+yyparse (YYPARSE_PARAM)
+    void *YYPARSE_PARAM;
+#endif
+#else /* ! YYPARSE_PARAM */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+int
+yyparse (struct list_head *format, char *name)
+#else
+int
+yyparse (format, name)
+    struct list_head *format;
+    char *name;
+#endif
+#endif
+{
+
+
+    int yystate;
+    /* Number of tokens to shift before error messages enabled.  */
+    int yyerrstatus;
+
+    /* The stacks and their tools:
+       `yyss': related to states.
+       `yyvs': related to semantic values.
+
+       Refer to the stacks thru separate pointers, to allow yyoverflow
+       to reallocate them elsewhere.  */
+
+    /* The state stack.  */
+    yytype_int16 yyssa[YYINITDEPTH];
+    yytype_int16 *yyss;
+    yytype_int16 *yyssp;
+
+    /* The semantic value stack.  */
+    YYSTYPE yyvsa[YYINITDEPTH];
+    YYSTYPE *yyvs;
+    YYSTYPE *yyvsp;
+
+    YYSIZE_T yystacksize;
+
+  int yyn;
+  int yyresult;
+  /* Lookahead token as an internal (translated) token number.  */
+  int yytoken;
+  /* The variables used to return semantic value and location from the
+     action routines.  */
+  YYSTYPE yyval;
+
+#if YYERROR_VERBOSE
+  /* Buffer for error messages, and its allocated size.  */
+  char yymsgbuf[128];
+  char *yymsg = yymsgbuf;
+  YYSIZE_T yymsg_alloc = sizeof yymsgbuf;
+#endif
+
+#define YYPOPSTACK(N)   (yyvsp -= (N), yyssp -= (N))
+
+  /* The number of symbols on the RHS of the reduced rule.
+     Keep to zero when no symbol should be popped.  */
+  int yylen = 0;
+
+  yytoken = 0;
+  yyss = yyssa;
+  yyvs = yyvsa;
+  yystacksize = YYINITDEPTH;
+
+  YYDPRINTF ((stderr, "Starting parse\n"));
+
+  yystate = 0;
+  yyerrstatus = 0;
+  yynerrs = 0;
+  yychar = YYEMPTY; /* Cause a token to be read.  */
+
+  /* Initialize stack pointers.
+     Waste one element of value and location stack
+     so that they stay on the same level as the state stack.
+     The wasted elements are never initialized.  */
+  yyssp = yyss;
+  yyvsp = yyvs;
+
+  goto yysetstate;
+
+/*------------------------------------------------------------.
+| yynewstate -- Push a new state, which is found in yystate.  |
+`------------------------------------------------------------*/
+ yynewstate:
+  /* In all cases, when you get here, the value and location stacks
+     have just been pushed.  So pushing a state here evens the stacks.  */
+  yyssp++;
+
+ yysetstate:
+  *yyssp = yystate;
+
+  if (yyss + yystacksize - 1 <= yyssp)
+    {
+      /* Get the current used size of the three stacks, in elements.  */
+      YYSIZE_T yysize = yyssp - yyss + 1;
+
+#ifdef yyoverflow
+      {
+	/* Give user a chance to reallocate the stack.  Use copies of
+	   these so that the &'s don't force the real ones into
+	   memory.  */
+	YYSTYPE *yyvs1 = yyvs;
+	yytype_int16 *yyss1 = yyss;
+
+	/* Each stack pointer address is followed by the size of the
+	   data in use in that stack, in bytes.  This used to be a
+	   conditional around just the two extra args, but that might
+	   be undefined if yyoverflow is a macro.  */
+	yyoverflow (YY_("memory exhausted"),
+		    &yyss1, yysize * sizeof (*yyssp),
+		    &yyvs1, yysize * sizeof (*yyvsp),
+		    &yystacksize);
+
+	yyss = yyss1;
+	yyvs = yyvs1;
+      }
+#else /* no yyoverflow */
+# ifndef YYSTACK_RELOCATE
+      goto yyexhaustedlab;
+# else
+      /* Extend the stack our own way.  */
+      if (YYMAXDEPTH <= yystacksize)
+	goto yyexhaustedlab;
+      yystacksize *= 2;
+      if (YYMAXDEPTH < yystacksize)
+	yystacksize = YYMAXDEPTH;
+
+      {
+	yytype_int16 *yyss1 = yyss;
+	union yyalloc *yyptr =
+	  (union yyalloc *) YYSTACK_ALLOC (YYSTACK_BYTES (yystacksize));
+	if (! yyptr)
+	  goto yyexhaustedlab;
+	YYSTACK_RELOCATE (yyss_alloc, yyss);
+	YYSTACK_RELOCATE (yyvs_alloc, yyvs);
+#  undef YYSTACK_RELOCATE
+	if (yyss1 != yyssa)
+	  YYSTACK_FREE (yyss1);
+      }
+# endif
+#endif /* no yyoverflow */
+
+      yyssp = yyss + yysize - 1;
+      yyvsp = yyvs + yysize - 1;
+
+      YYDPRINTF ((stderr, "Stack size increased to %lu\n",
+		  (unsigned long int) yystacksize));
+
+      if (yyss + yystacksize - 1 <= yyssp)
+	YYABORT;
+    }
+
+  YYDPRINTF ((stderr, "Entering state %d\n", yystate));
+
+  if (yystate == YYFINAL)
+    YYACCEPT;
+
+  goto yybackup;
+
+/*-----------.
+| yybackup.  |
+`-----------*/
+yybackup:
+
+  /* Do appropriate processing given the current state.  Read a
+     lookahead token if we need one and don't already have one.  */
+
+  /* First try to decide what to do without reference to lookahead token.  */
+  yyn = yypact[yystate];
+  if (yyn == YYPACT_NINF)
+    goto yydefault;
+
+  /* Not known => get a lookahead token if don't already have one.  */
+
+  /* YYCHAR is either YYEMPTY or YYEOF or a valid lookahead symbol.  */
+  if (yychar == YYEMPTY)
+    {
+      YYDPRINTF ((stderr, "Reading a token: "));
+      yychar = YYLEX;
+    }
+
+  if (yychar <= YYEOF)
+    {
+      yychar = yytoken = YYEOF;
+      YYDPRINTF ((stderr, "Now at end of input.\n"));
+    }
+  else
+    {
+      yytoken = YYTRANSLATE (yychar);
+      YY_SYMBOL_PRINT ("Next token is", yytoken, &yylval, &yylloc);
+    }
+
+  /* If the proper action on seeing token YYTOKEN is to reduce or to
+     detect an error, take that action.  */
+  yyn += yytoken;
+  if (yyn < 0 || YYLAST < yyn || yycheck[yyn] != yytoken)
+    goto yydefault;
+  yyn = yytable[yyn];
+  if (yyn <= 0)
+    {
+      if (yyn == 0 || yyn == YYTABLE_NINF)
+	goto yyerrlab;
+      yyn = -yyn;
+      goto yyreduce;
+    }
+
+  /* Count tokens shifted since error; after three, turn off error
+     status.  */
+  if (yyerrstatus)
+    yyerrstatus--;
+
+  /* Shift the lookahead token.  */
+  YY_SYMBOL_PRINT ("Shifting", yytoken, &yylval, &yylloc);
+
+  /* Discard the shifted token.  */
+  yychar = YYEMPTY;
+
+  yystate = yyn;
+  *++yyvsp = yylval;
+
+  goto yynewstate;
+
+
+/*-----------------------------------------------------------.
+| yydefault -- do the default action for the current state.  |
+`-----------------------------------------------------------*/
+yydefault:
+  yyn = yydefact[yystate];
+  if (yyn == 0)
+    goto yyerrlab;
+  goto yyreduce;
+
+
+/*-----------------------------.
+| yyreduce -- Do a reduction.  |
+`-----------------------------*/
+yyreduce:
+  /* yyn is the number of a rule to reduce with.  */
+  yylen = yyr2[yyn];
+
+  /* If YYLEN is nonzero, implement the default value of the action:
+     `$$ = $1'.
+
+     Otherwise, the following line sets YYVAL to garbage.
+     This behavior is undocumented and Bison
+     users should not rely upon it.  Assigning to YYVAL
+     unconditionally makes the parser a bit smaller, and it avoids a
+     GCC warning that YYVAL may be used uninitialized.  */
+  yyval = yyvsp[1-yylen];
+
+
+  YY_REDUCE_PRINT (yyn);
+  switch (yyn)
+    {
+        case 4:
+
+/* Line 1464 of yacc.c  */
+#line 45 "util/pmu.y"
+    {
+	ABORT_ON(perf_pmu__new_format(format, name,
+				      PERF_PMU_FORMAT_VALUE_CONFIG,
+				      (yyvsp[(3) - (3)].bits)));
+;}
+    break;
+
+  case 5:
+
+/* Line 1464 of yacc.c  */
+#line 52 "util/pmu.y"
+    {
+	ABORT_ON(perf_pmu__new_format(format, name,
+				      PERF_PMU_FORMAT_VALUE_CONFIG1,
+				      (yyvsp[(3) - (3)].bits)));
+;}
+    break;
+
+  case 6:
+
+/* Line 1464 of yacc.c  */
+#line 59 "util/pmu.y"
+    {
+	ABORT_ON(perf_pmu__new_format(format, name,
+				      PERF_PMU_FORMAT_VALUE_CONFIG2,
+				      (yyvsp[(3) - (3)].bits)));
+;}
+    break;
+
+  case 7:
+
+/* Line 1464 of yacc.c  */
+#line 67 "util/pmu.y"
+    {
+	bitmap_or((yyval.bits), (yyvsp[(1) - (3)].bits), (yyvsp[(3) - (3)].bits), 64);
+;}
+    break;
+
+  case 8:
+
+/* Line 1464 of yacc.c  */
+#line 72 "util/pmu.y"
+    {
+	memcpy((yyval.bits), (yyvsp[(1) - (1)].bits), sizeof((yyvsp[(1) - (1)].bits)));
+;}
+    break;
+
+  case 9:
+
+/* Line 1464 of yacc.c  */
+#line 78 "util/pmu.y"
+    {
+	perf_pmu__set_format((yyval.bits), (yyvsp[(1) - (3)].num), (yyvsp[(3) - (3)].num));
+;}
+    break;
+
+  case 10:
+
+/* Line 1464 of yacc.c  */
+#line 83 "util/pmu.y"
+    {
+	perf_pmu__set_format((yyval.bits), (yyvsp[(1) - (1)].num), 0);
+;}
+    break;
+
+
+
+/* Line 1464 of yacc.c  */
+#line 1444 "util/pmu-bison.c"
+      default: break;
+    }
+  YY_SYMBOL_PRINT ("-> $$ =", yyr1[yyn], &yyval, &yyloc);
+
+  YYPOPSTACK (yylen);
+  yylen = 0;
+  YY_STACK_PRINT (yyss, yyssp);
+
+  *++yyvsp = yyval;
+
+  /* Now `shift' the result of the reduction.  Determine what state
+     that goes to, based on the state we popped back to and the rule
+     number reduced by.  */
+
+  yyn = yyr1[yyn];
+
+  yystate = yypgoto[yyn - YYNTOKENS] + *yyssp;
+  if (0 <= yystate && yystate <= YYLAST && yycheck[yystate] == *yyssp)
+    yystate = yytable[yystate];
+  else
+    yystate = yydefgoto[yyn - YYNTOKENS];
+
+  goto yynewstate;
+
+
+/*------------------------------------.
+| yyerrlab -- here on detecting error |
+`------------------------------------*/
+yyerrlab:
+  /* If not already recovering from an error, report this error.  */
+  if (!yyerrstatus)
+    {
+      ++yynerrs;
+#if ! YYERROR_VERBOSE
+      yyerror (format, name, YY_("syntax error"));
+#else
+      {
+	YYSIZE_T yysize = yysyntax_error (0, yystate, yychar);
+	if (yymsg_alloc < yysize && yymsg_alloc < YYSTACK_ALLOC_MAXIMUM)
+	  {
+	    YYSIZE_T yyalloc = 2 * yysize;
+	    if (! (yysize <= yyalloc && yyalloc <= YYSTACK_ALLOC_MAXIMUM))
+	      yyalloc = YYSTACK_ALLOC_MAXIMUM;
+	    if (yymsg != yymsgbuf)
+	      YYSTACK_FREE (yymsg);
+	    yymsg = (char *) YYSTACK_ALLOC (yyalloc);
+	    if (yymsg)
+	      yymsg_alloc = yyalloc;
+	    else
+	      {
+		yymsg = yymsgbuf;
+		yymsg_alloc = sizeof yymsgbuf;
+	      }
+	  }
+
+	if (0 < yysize && yysize <= yymsg_alloc)
+	  {
+	    (void) yysyntax_error (yymsg, yystate, yychar);
+	    yyerror (format, name, yymsg);
+	  }
+	else
+	  {
+	    yyerror (format, name, YY_("syntax error"));
+	    if (yysize != 0)
+	      goto yyexhaustedlab;
+	  }
+      }
+#endif
+    }
+
+
+
+  if (yyerrstatus == 3)
+    {
+      /* If just tried and failed to reuse lookahead token after an
+	 error, discard it.  */
+
+      if (yychar <= YYEOF)
+	{
+	  /* Return failure if at end of input.  */
+	  if (yychar == YYEOF)
+	    YYABORT;
+	}
+      else
+	{
+	  yydestruct ("Error: discarding",
+		      yytoken, &yylval, format, name);
+	  yychar = YYEMPTY;
+	}
+    }
+
+  /* Else will try to reuse lookahead token after shifting the error
+     token.  */
+  goto yyerrlab1;
+
+
+/*---------------------------------------------------.
+| yyerrorlab -- error raised explicitly by YYERROR.  |
+`---------------------------------------------------*/
+yyerrorlab:
+
+  /* Pacify compilers like GCC when the user code never invokes
+     YYERROR and the label yyerrorlab therefore never appears in user
+     code.  */
+  if (/*CONSTCOND*/ 0)
+     goto yyerrorlab;
+
+  /* Do not reclaim the symbols of the rule which action triggered
+     this YYERROR.  */
+  YYPOPSTACK (yylen);
+  yylen = 0;
+  YY_STACK_PRINT (yyss, yyssp);
+  yystate = *yyssp;
+  goto yyerrlab1;
+
+
+/*-------------------------------------------------------------.
+| yyerrlab1 -- common code for both syntax error and YYERROR.  |
+`-------------------------------------------------------------*/
+yyerrlab1:
+  yyerrstatus = 3;	/* Each real token shifted decrements this.  */
+
+  for (;;)
+    {
+      yyn = yypact[yystate];
+      if (yyn != YYPACT_NINF)
+	{
+	  yyn += YYTERROR;
+	  if (0 <= yyn && yyn <= YYLAST && yycheck[yyn] == YYTERROR)
+	    {
+	      yyn = yytable[yyn];
+	      if (0 < yyn)
+		break;
+	    }
+	}
+
+      /* Pop the current state because it cannot handle the error token.  */
+      if (yyssp == yyss)
+	YYABORT;
+
+
+      yydestruct ("Error: popping",
+		  yystos[yystate], yyvsp, format, name);
+      YYPOPSTACK (1);
+      yystate = *yyssp;
+      YY_STACK_PRINT (yyss, yyssp);
+    }
+
+  *++yyvsp = yylval;
+
+
+  /* Shift the error token.  */
+  YY_SYMBOL_PRINT ("Shifting", yystos[yyn], yyvsp, yylsp);
+
+  yystate = yyn;
+  goto yynewstate;
+
+
+/*-------------------------------------.
+| yyacceptlab -- YYACCEPT comes here.  |
+`-------------------------------------*/
+yyacceptlab:
+  yyresult = 0;
+  goto yyreturn;
+
+/*-----------------------------------.
+| yyabortlab -- YYABORT comes here.  |
+`-----------------------------------*/
+yyabortlab:
+  yyresult = 1;
+  goto yyreturn;
+
+#if !defined(yyoverflow) || YYERROR_VERBOSE
+/*-------------------------------------------------.
+| yyexhaustedlab -- memory exhaustion comes here.  |
+`-------------------------------------------------*/
+yyexhaustedlab:
+  yyerror (format, name, YY_("memory exhausted"));
+  yyresult = 2;
+  /* Fall through.  */
+#endif
+
+yyreturn:
+  if (yychar != YYEMPTY)
+     yydestruct ("Cleanup: discarding lookahead",
+		 yytoken, &yylval, format, name);
+  /* Do not reclaim the symbols of the rule which action triggered
+     this YYABORT or YYACCEPT.  */
+  YYPOPSTACK (yylen);
+  YY_STACK_PRINT (yyss, yyssp);
+  while (yyssp != yyss)
+    {
+      yydestruct ("Cleanup: popping",
+		  yystos[*yyssp], yyvsp, format, name);
+      YYPOPSTACK (1);
+    }
+#ifndef yyoverflow
+  if (yyss != yyssa)
+    YYSTACK_FREE (yyss);
+#endif
+#if YYERROR_VERBOSE
+  if (yymsg != yymsgbuf)
+    YYSTACK_FREE (yymsg);
+#endif
+  /* Make sure YYID is used.  */
+  return YYID (yyresult);
+}
+
+
+
+/* Line 1684 of yacc.c  */
+#line 87 "util/pmu.y"
+
+
+void perf_pmu_error(struct list_head *list __used,
+		    char *name __used,
+		    char const *msg __used)
+{
+}
+
diff --git a/tools/perf/util/pmu-bison.h b/tools/perf/util/pmu-bison.h
new file mode 100644
index 0000000..54f4a0d
--- /dev/null
+++ b/tools/perf/util/pmu-bison.h
@@ -0,0 +1,73 @@
+/* A Bison parser, made by GNU Bison 2.4.3.  */
+
+/* Skeleton interface for Bison's Yacc-like parsers in C
+   
+      Copyright (C) 1984, 1989, 1990, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
+   2009, 2010 Free Software Foundation, Inc.
+   
+   This program is free software: you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation, either version 3 of the License, or
+   (at your option) any later version.
+   
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+   
+   You should have received a copy of the GNU General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
+
+/* As a special exception, you may create a larger work that contains
+   part or all of the Bison parser skeleton and distribute that work
+   under terms of your choice, so long as that work isn't itself a
+   parser generator using the skeleton or a modified version thereof
+   as a parser skeleton.  Alternatively, if you modify or redistribute
+   the parser skeleton itself, you may (at your option) remove this
+   special exception, which will cause the skeleton and the resulting
+   Bison output files to be licensed under the GNU General Public
+   License without this special exception.
+   
+   This special exception was added by the Free Software Foundation in
+   version 2.2 of Bison.  */
+
+
+/* Tokens.  */
+#ifndef YYTOKENTYPE
+# define YYTOKENTYPE
+   /* Put the tokens into the symbol table, so that GDB and other debuggers
+      know about them.  */
+   enum yytokentype {
+     PP_CONFIG = 258,
+     PP_CONFIG1 = 259,
+     PP_CONFIG2 = 260,
+     PP_VALUE = 261,
+     PP_ERROR = 262
+   };
+#endif
+
+
+
+#if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED
+typedef union YYSTYPE
+{
+
+/* Line 1685 of yacc.c  */
+#line 31 "util/pmu.y"
+
+	unsigned long num;
+	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
+
+
+
+/* Line 1685 of yacc.c  */
+#line 65 "util/pmu-bison.h"
+} YYSTYPE;
+# define YYSTYPE_IS_TRIVIAL 1
+# define yystype YYSTYPE /* obsolescent; will be withdrawn */
+# define YYSTYPE_IS_DECLARED 1
+#endif
+
+extern YYSTYPE perf_pmu_lval;
+
+
diff --git a/tools/perf/util/pmu-flex.c b/tools/perf/util/pmu-flex.c
new file mode 100644
index 0000000..5a8c159
--- /dev/null
+++ b/tools/perf/util/pmu-flex.c
@@ -0,0 +1,1821 @@
+
+#line 3 "<stdout>"
+
+#define  YY_INT_ALIGNED short int
+
+/* A lexical scanner generated by flex */
+
+#define yy_create_buffer perf_pmu__create_buffer
+#define yy_delete_buffer perf_pmu__delete_buffer
+#define yy_flex_debug perf_pmu__flex_debug
+#define yy_init_buffer perf_pmu__init_buffer
+#define yy_flush_buffer perf_pmu__flush_buffer
+#define yy_load_buffer_state perf_pmu__load_buffer_state
+#define yy_switch_to_buffer perf_pmu__switch_to_buffer
+#define yyin perf_pmu_in
+#define yyleng perf_pmu_leng
+#define yylex perf_pmu_lex
+#define yylineno perf_pmu_lineno
+#define yyout perf_pmu_out
+#define yyrestart perf_pmu_restart
+#define yytext perf_pmu_text
+#define yywrap perf_pmu_wrap
+#define yyalloc perf_pmu_alloc
+#define yyrealloc perf_pmu_realloc
+#define yyfree perf_pmu_free
+
+#define FLEX_SCANNER
+#define YY_FLEX_MAJOR_VERSION 2
+#define YY_FLEX_MINOR_VERSION 5
+#define YY_FLEX_SUBMINOR_VERSION 35
+#if YY_FLEX_SUBMINOR_VERSION > 0
+#define FLEX_BETA
+#endif
+
+/* First, we deal with  platform-specific or compiler-specific issues. */
+
+/* begin standard C headers. */
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <stdlib.h>
+
+/* end standard C headers. */
+
+/* flex integer type definitions */
+
+#ifndef FLEXINT_H
+#define FLEXINT_H
+
+/* C99 systems have <inttypes.h>. Non-C99 systems may or may not. */
+
+#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+
+/* C99 says to define __STDC_LIMIT_MACROS before including stdint.h,
+ * if you want the limit (max/min) macros for int types. 
+ */
+#ifndef __STDC_LIMIT_MACROS
+#define __STDC_LIMIT_MACROS 1
+#endif
+
+#include <inttypes.h>
+typedef int8_t flex_int8_t;
+typedef uint8_t flex_uint8_t;
+typedef int16_t flex_int16_t;
+typedef uint16_t flex_uint16_t;
+typedef int32_t flex_int32_t;
+typedef uint32_t flex_uint32_t;
+#else
+typedef signed char flex_int8_t;
+typedef short int flex_int16_t;
+typedef int flex_int32_t;
+typedef unsigned char flex_uint8_t; 
+typedef unsigned short int flex_uint16_t;
+typedef unsigned int flex_uint32_t;
+#endif /* ! C99 */
+
+/* Limits of integral types. */
+#ifndef INT8_MIN
+#define INT8_MIN               (-128)
+#endif
+#ifndef INT16_MIN
+#define INT16_MIN              (-32767-1)
+#endif
+#ifndef INT32_MIN
+#define INT32_MIN              (-2147483647-1)
+#endif
+#ifndef INT8_MAX
+#define INT8_MAX               (127)
+#endif
+#ifndef INT16_MAX
+#define INT16_MAX              (32767)
+#endif
+#ifndef INT32_MAX
+#define INT32_MAX              (2147483647)
+#endif
+#ifndef UINT8_MAX
+#define UINT8_MAX              (255U)
+#endif
+#ifndef UINT16_MAX
+#define UINT16_MAX             (65535U)
+#endif
+#ifndef UINT32_MAX
+#define UINT32_MAX             (4294967295U)
+#endif
+
+#endif /* ! FLEXINT_H */
+
+#ifdef __cplusplus
+
+/* The "const" storage-class-modifier is valid. */
+#define YY_USE_CONST
+
+#else	/* ! __cplusplus */
+
+/* C99 requires __STDC__ to be defined as 1. */
+#if defined (__STDC__)
+
+#define YY_USE_CONST
+
+#endif	/* defined (__STDC__) */
+#endif	/* ! __cplusplus */
+
+#ifdef YY_USE_CONST
+#define yyconst const
+#else
+#define yyconst
+#endif
+
+/* Returned upon end-of-file. */
+#define YY_NULL 0
+
+/* Promotes a possibly negative, possibly signed char to an unsigned
+ * integer for use as an array index.  If the signed char is negative,
+ * we want to instead treat it as an 8-bit unsigned char, hence the
+ * double cast.
+ */
+#define YY_SC_TO_UI(c) ((unsigned int) (unsigned char) c)
+
+/* Enter a start condition.  This macro really ought to take a parameter,
+ * but we do it the disgusting crufty way forced on us by the ()-less
+ * definition of BEGIN.
+ */
+#define BEGIN (yy_start) = 1 + 2 *
+
+/* Translate the current start state into a value that can be later handed
+ * to BEGIN to return to the state.  The YYSTATE alias is for lex
+ * compatibility.
+ */
+#define YY_START (((yy_start) - 1) / 2)
+#define YYSTATE YY_START
+
+/* Action number for EOF rule of a given start state. */
+#define YY_STATE_EOF(state) (YY_END_OF_BUFFER + state + 1)
+
+/* Special action meaning "start processing a new file". */
+#define YY_NEW_FILE perf_pmu_restart(perf_pmu_in  )
+
+#define YY_END_OF_BUFFER_CHAR 0
+
+/* Size of default input buffer. */
+#ifndef YY_BUF_SIZE
+#define YY_BUF_SIZE 16384
+#endif
+
+/* The state buf must be large enough to hold one state per character in the main buffer.
+ */
+#define YY_STATE_BUF_SIZE   ((YY_BUF_SIZE + 2) * sizeof(yy_state_type))
+
+#ifndef YY_TYPEDEF_YY_BUFFER_STATE
+#define YY_TYPEDEF_YY_BUFFER_STATE
+typedef struct yy_buffer_state *YY_BUFFER_STATE;
+#endif
+
+extern int perf_pmu_leng;
+
+extern FILE *perf_pmu_in, *perf_pmu_out;
+
+#define EOB_ACT_CONTINUE_SCAN 0
+#define EOB_ACT_END_OF_FILE 1
+#define EOB_ACT_LAST_MATCH 2
+
+    #define YY_LESS_LINENO(n)
+    
+/* Return all but the first "n" matched characters back to the input stream. */
+#define yyless(n) \
+	do \
+		{ \
+		/* Undo effects of setting up perf_pmu_text. */ \
+        int yyless_macro_arg = (n); \
+        YY_LESS_LINENO(yyless_macro_arg);\
+		*yy_cp = (yy_hold_char); \
+		YY_RESTORE_YY_MORE_OFFSET \
+		(yy_c_buf_p) = yy_cp = yy_bp + yyless_macro_arg - YY_MORE_ADJ; \
+		YY_DO_BEFORE_ACTION; /* set up perf_pmu_text again */ \
+		} \
+	while ( 0 )
+
+#define unput(c) yyunput( c, (yytext_ptr)  )
+
+#ifndef YY_TYPEDEF_YY_SIZE_T
+#define YY_TYPEDEF_YY_SIZE_T
+typedef size_t yy_size_t;
+#endif
+
+#ifndef YY_STRUCT_YY_BUFFER_STATE
+#define YY_STRUCT_YY_BUFFER_STATE
+struct yy_buffer_state
+	{
+	FILE *yy_input_file;
+
+	char *yy_ch_buf;		/* input buffer */
+	char *yy_buf_pos;		/* current position in input buffer */
+
+	/* Size of input buffer in bytes, not including room for EOB
+	 * characters.
+	 */
+	yy_size_t yy_buf_size;
+
+	/* Number of characters read into yy_ch_buf, not including EOB
+	 * characters.
+	 */
+	int yy_n_chars;
+
+	/* Whether we "own" the buffer - i.e., we know we created it,
+	 * and can realloc() it to grow it, and should free() it to
+	 * delete it.
+	 */
+	int yy_is_our_buffer;
+
+	/* Whether this is an "interactive" input source; if so, and
+	 * if we're using stdio for input, then we want to use getc()
+	 * instead of fread(), to make sure we stop fetching input after
+	 * each newline.
+	 */
+	int yy_is_interactive;
+
+	/* Whether we're considered to be at the beginning of a line.
+	 * If so, '^' rules will be active on the next match, otherwise
+	 * not.
+	 */
+	int yy_at_bol;
+
+    int yy_bs_lineno; /**< The line count. */
+    int yy_bs_column; /**< The column count. */
+    
+	/* Whether to try to fill the input buffer when we reach the
+	 * end of it.
+	 */
+	int yy_fill_buffer;
+
+	int yy_buffer_status;
+
+#define YY_BUFFER_NEW 0
+#define YY_BUFFER_NORMAL 1
+	/* When an EOF's been seen but there's still some text to process
+	 * then we mark the buffer as YY_EOF_PENDING, to indicate that we
+	 * shouldn't try reading from the input source any more.  We might
+	 * still have a bunch of tokens to match, though, because of
+	 * possible backing-up.
+	 *
+	 * When we actually see the EOF, we change the status to "new"
+	 * (via perf_pmu_restart()), so that the user can continue scanning by
+	 * just pointing perf_pmu_in at a new input file.
+	 */
+#define YY_BUFFER_EOF_PENDING 2
+
+	};
+#endif /* !YY_STRUCT_YY_BUFFER_STATE */
+
+/* Stack of input buffers. */
+static size_t yy_buffer_stack_top = 0; /**< index of top of stack. */
+static size_t yy_buffer_stack_max = 0; /**< capacity of stack. */
+static YY_BUFFER_STATE * yy_buffer_stack = 0; /**< Stack as an array. */
+
+/* We provide macros for accessing buffer states in case in the
+ * future we want to put the buffer states in a more general
+ * "scanner state".
+ *
+ * Returns the top of the stack, or NULL.
+ */
+#define YY_CURRENT_BUFFER ( (yy_buffer_stack) \
+                          ? (yy_buffer_stack)[(yy_buffer_stack_top)] \
+                          : NULL)
+
+/* Same as previous macro, but useful when we know that the buffer stack is not
+ * NULL or when we need an lvalue. For internal use only.
+ */
+#define YY_CURRENT_BUFFER_LVALUE (yy_buffer_stack)[(yy_buffer_stack_top)]
+
+/* yy_hold_char holds the character lost when perf_pmu_text is formed. */
+static char yy_hold_char;
+static int yy_n_chars;		/* number of characters read into yy_ch_buf */
+int perf_pmu_leng;
+
+/* Points to current character in buffer. */
+static char *yy_c_buf_p = (char *) 0;
+static int yy_init = 0;		/* whether we need to initialize */
+static int yy_start = 0;	/* start state number */
+
+/* Flag which is used to allow perf_pmu_wrap()'s to do buffer switches
+ * instead of setting up a fresh perf_pmu_in.  A bit of a hack ...
+ */
+static int yy_did_buffer_switch_on_eof;
+
+void perf_pmu_restart (FILE *input_file  );
+void perf_pmu__switch_to_buffer (YY_BUFFER_STATE new_buffer  );
+YY_BUFFER_STATE perf_pmu__create_buffer (FILE *file,int size  );
+void perf_pmu__delete_buffer (YY_BUFFER_STATE b  );
+void perf_pmu__flush_buffer (YY_BUFFER_STATE b  );
+void perf_pmu_push_buffer_state (YY_BUFFER_STATE new_buffer  );
+void perf_pmu_pop_buffer_state (void );
+
+static void perf_pmu_ensure_buffer_stack (void );
+static void perf_pmu__load_buffer_state (void );
+static void perf_pmu__init_buffer (YY_BUFFER_STATE b,FILE *file  );
+
+#define YY_FLUSH_BUFFER perf_pmu__flush_buffer(YY_CURRENT_BUFFER )
+
+YY_BUFFER_STATE perf_pmu__scan_buffer (char *base,yy_size_t size  );
+YY_BUFFER_STATE perf_pmu__scan_string (yyconst char *yy_str  );
+YY_BUFFER_STATE perf_pmu__scan_bytes (yyconst char *bytes,int len  );
+
+void *perf_pmu_alloc (yy_size_t  );
+void *perf_pmu_realloc (void *,yy_size_t  );
+void perf_pmu_free (void *  );
+
+#define yy_new_buffer perf_pmu__create_buffer
+
+#define yy_set_interactive(is_interactive) \
+	{ \
+	if ( ! YY_CURRENT_BUFFER ){ \
+        perf_pmu_ensure_buffer_stack (); \
+		YY_CURRENT_BUFFER_LVALUE =    \
+            perf_pmu__create_buffer(perf_pmu_in,YY_BUF_SIZE ); \
+	} \
+	YY_CURRENT_BUFFER_LVALUE->yy_is_interactive = is_interactive; \
+	}
+
+#define yy_set_bol(at_bol) \
+	{ \
+	if ( ! YY_CURRENT_BUFFER ){\
+        perf_pmu_ensure_buffer_stack (); \
+		YY_CURRENT_BUFFER_LVALUE =    \
+            perf_pmu__create_buffer(perf_pmu_in,YY_BUF_SIZE ); \
+	} \
+	YY_CURRENT_BUFFER_LVALUE->yy_at_bol = at_bol; \
+	}
+
+#define YY_AT_BOL() (YY_CURRENT_BUFFER_LVALUE->yy_at_bol)
+
+/* Begin user sect3 */
+
+typedef unsigned char YY_CHAR;
+
+FILE *perf_pmu_in = (FILE *) 0, *perf_pmu_out = (FILE *) 0;
+
+typedef int yy_state_type;
+
+extern int perf_pmu_lineno;
+
+int perf_pmu_lineno = 1;
+
+extern char *perf_pmu_text;
+#define yytext_ptr perf_pmu_text
+
+static yy_state_type yy_get_previous_state (void );
+static yy_state_type yy_try_NUL_trans (yy_state_type current_state  );
+static int yy_get_next_buffer (void );
+static void yy_fatal_error (yyconst char msg[]  );
+
+/* Done after the current pattern has been matched and before the
+ * corresponding action - sets up perf_pmu_text.
+ */
+#define YY_DO_BEFORE_ACTION \
+	(yytext_ptr) = yy_bp; \
+	perf_pmu_leng = (size_t) (yy_cp - yy_bp); \
+	(yy_hold_char) = *yy_cp; \
+	*yy_cp = '\0'; \
+	(yy_c_buf_p) = yy_cp;
+
+#define YY_NUM_RULES 10
+#define YY_END_OF_BUFFER 11
+/* This struct is not used in this scanner,
+   but its presence is necessary. */
+struct yy_trans_info
+	{
+	flex_int32_t yy_verify;
+	flex_int32_t yy_nxt;
+	};
+static yyconst flex_int16_t yy_accept[20] =
+    {   0,
+        0,    0,   11,    8,    9,    7,    5,    1,    6,    8,
+        1,    0,    0,    0,    0,    2,    3,    4,    0
+    } ;
+
+static yyconst flex_int32_t yy_ec[256] =
+    {   0,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    2,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    3,    4,    1,    1,    5,    6,    7,
+        5,    5,    5,    5,    5,    5,    5,    8,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    9,    1,
+
+        1,   10,   11,    1,   12,    1,    1,    1,    1,   13,
+       14,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1
+    } ;
+
+static yyconst flex_int32_t yy_meta[15] =
+    {   0,
+        1,    1,    1,    1,    2,    2,    2,    1,    1,    1,
+        1,    1,    1,    1
+    } ;
+
+static yyconst flex_int16_t yy_base[21] =
+    {   0,
+        0,    0,   23,   24,   24,   24,   24,    0,   24,    8,
+        0,    8,   10,    7,    7,    9,   24,   24,   24,   15
+    } ;
+
+static yyconst flex_int16_t yy_def[21] =
+    {   0,
+       19,    1,   19,   19,   19,   19,   19,   20,   19,   19,
+       20,   19,   19,   19,   19,   19,   19,   19,    0,   19
+    } ;
+
+static yyconst flex_int16_t yy_nxt[39] =
+    {   0,
+        4,    5,    6,    7,    8,    8,    8,    9,   10,    4,
+        4,    4,    4,    4,   17,   18,   11,   16,   15,   14,
+       13,   12,   19,    3,   19,   19,   19,   19,   19,   19,
+       19,   19,   19,   19,   19,   19,   19,   19
+    } ;
+
+static yyconst flex_int16_t yy_chk[39] =
+    {   0,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,   16,   16,   20,   15,   14,   13,
+       12,   10,    3,   19,   19,   19,   19,   19,   19,   19,
+       19,   19,   19,   19,   19,   19,   19,   19
+    } ;
+
+static yy_state_type yy_last_accepting_state;
+static char *yy_last_accepting_cpos;
+
+extern int perf_pmu__flex_debug;
+int perf_pmu__flex_debug = 0;
+
+/* The intent behind this definition is that it'll catch
+ * any uses of REJECT which flex missed.
+ */
+#define REJECT reject_used_but_not_detected
+#define yymore() yymore_used_but_not_detected
+#define YY_MORE_ADJ 0
+#define YY_RESTORE_YY_MORE_OFFSET
+char *perf_pmu_text;
+#line 1 "util/pmu.l"
+#line 4 "util/pmu.l"
+#include <stdlib.h>
+#include <linux/bitops.h>
+#include "pmu.h"
+#include "pmu-bison.h"
+
+static int value(int base)
+{
+	long num;
+
+	errno = 0;
+	num = strtoul(perf_pmu_text, NULL, base);
+	if (errno)
+		return PP_ERROR;
+
+	perf_pmu_lval.num = num;
+	return PP_VALUE;
+}
+
+#line 497 "<stdout>"
+
+#define INITIAL 0
+
+#ifndef YY_NO_UNISTD_H
+/* Special case for "unistd.h", since it is non-ANSI. We include it way
+ * down here because we want the user's section 1 to have been scanned first.
+ * The user has a chance to override it with an option.
+ */
+#include <unistd.h>
+#endif
+
+#ifndef YY_EXTRA_TYPE
+#define YY_EXTRA_TYPE void *
+#endif
+
+static int yy_init_globals (void );
+
+/* Accessor methods to globals.
+   These are made visible to non-reentrant scanners for convenience. */
+
+int perf_pmu_lex_destroy (void );
+
+int perf_pmu_get_debug (void );
+
+void perf_pmu_set_debug (int debug_flag  );
+
+YY_EXTRA_TYPE perf_pmu_get_extra (void );
+
+void perf_pmu_set_extra (YY_EXTRA_TYPE user_defined  );
+
+FILE *perf_pmu_get_in (void );
+
+void perf_pmu_set_in  (FILE * in_str  );
+
+FILE *perf_pmu_get_out (void );
+
+void perf_pmu_set_out  (FILE * out_str  );
+
+int perf_pmu_get_leng (void );
+
+char *perf_pmu_get_text (void );
+
+int perf_pmu_get_lineno (void );
+
+void perf_pmu_set_lineno (int line_number  );
+
+/* Macros after this point can all be overridden by user definitions in
+ * section 1.
+ */
+
+#ifndef YY_SKIP_YYWRAP
+#ifdef __cplusplus
+extern "C" int perf_pmu_wrap (void );
+#else
+extern int perf_pmu_wrap (void );
+#endif
+#endif
+
+    static void yyunput (int c,char *buf_ptr  );
+    
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char *,yyconst char *,int );
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * );
+#endif
+
+#ifndef YY_NO_INPUT
+
+#ifdef __cplusplus
+static int yyinput (void );
+#else
+static int input (void );
+#endif
+
+#endif
+
+/* Amount of stuff to slurp up with each read. */
+#ifndef YY_READ_BUF_SIZE
+#define YY_READ_BUF_SIZE 8192
+#endif
+
+/* Copy whatever the last rule matched to the standard output. */
+#ifndef ECHO
+/* This used to be an fputs(), but since the string might contain NUL's,
+ * we now use fwrite().
+ */
+#define ECHO do { if (fwrite( perf_pmu_text, perf_pmu_leng, 1, perf_pmu_out )) {} } while (0)
+#endif
+
+/* Gets input and stuffs it into "buf".  number of characters read, or YY_NULL,
+ * is returned in "result".
+ */
+#ifndef YY_INPUT
+#define YY_INPUT(buf,result,max_size) \
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_is_interactive ) \
+		{ \
+		int c = '*'; \
+		unsigned n; \
+		for ( n = 0; n < max_size && \
+			     (c = getc( perf_pmu_in )) != EOF && c != '\n'; ++n ) \
+			buf[n] = (char) c; \
+		if ( c == '\n' ) \
+			buf[n++] = (char) c; \
+		if ( c == EOF && ferror( perf_pmu_in ) ) \
+			YY_FATAL_ERROR( "input in flex scanner failed" ); \
+		result = n; \
+		} \
+	else \
+		{ \
+		errno=0; \
+		while ( (result = fread(buf, 1, max_size, perf_pmu_in))==0 && ferror(perf_pmu_in)) \
+			{ \
+			if( errno != EINTR) \
+				{ \
+				YY_FATAL_ERROR( "input in flex scanner failed" ); \
+				break; \
+				} \
+			errno=0; \
+			clearerr(perf_pmu_in); \
+			} \
+		}\
+\
+
+#endif
+
+/* No semi-colon after return; correct usage is to write "yyterminate();" -
+ * we don't want an extra ';' after the "return" because that will cause
+ * some compilers to complain about unreachable statements.
+ */
+#ifndef yyterminate
+#define yyterminate() return YY_NULL
+#endif
+
+/* Number of entries by which start-condition stack grows. */
+#ifndef YY_START_STACK_INCR
+#define YY_START_STACK_INCR 25
+#endif
+
+/* Report a fatal error. */
+#ifndef YY_FATAL_ERROR
+#define YY_FATAL_ERROR(msg) yy_fatal_error( msg )
+#endif
+
+/* end tables serialization structures and prototypes */
+
+/* Default declaration of generated scanner - a define so the user can
+ * easily add parameters.
+ */
+#ifndef YY_DECL
+#define YY_DECL_IS_OURS 1
+
+extern int perf_pmu_lex (void);
+
+#define YY_DECL int perf_pmu_lex (void)
+#endif /* !YY_DECL */
+
+/* Code executed at the beginning of each rule, after perf_pmu_text and perf_pmu_leng
+ * have been set up.
+ */
+#ifndef YY_USER_ACTION
+#define YY_USER_ACTION
+#endif
+
+/* Code executed at the end of each rule. */
+#ifndef YY_BREAK
+#define YY_BREAK break;
+#endif
+
+#define YY_RULE_SETUP \
+	YY_USER_ACTION
+
+/** The main scanner function which does all the work.
+ */
+YY_DECL
+{
+	register yy_state_type yy_current_state;
+	register char *yy_cp, *yy_bp;
+	register int yy_act;
+    
+#line 26 "util/pmu.l"
+
+
+#line 682 "<stdout>"
+
+	if ( !(yy_init) )
+		{
+		(yy_init) = 1;
+
+#ifdef YY_USER_INIT
+		YY_USER_INIT;
+#endif
+
+		if ( ! (yy_start) )
+			(yy_start) = 1;	/* first start state */
+
+		if ( ! perf_pmu_in )
+			perf_pmu_in = stdin;
+
+		if ( ! perf_pmu_out )
+			perf_pmu_out = stdout;
+
+		if ( ! YY_CURRENT_BUFFER ) {
+			perf_pmu_ensure_buffer_stack ();
+			YY_CURRENT_BUFFER_LVALUE =
+				perf_pmu__create_buffer(perf_pmu_in,YY_BUF_SIZE );
+		}
+
+		perf_pmu__load_buffer_state( );
+		}
+
+	while ( 1 )		/* loops until end-of-file is reached */
+		{
+		yy_cp = (yy_c_buf_p);
+
+		/* Support of perf_pmu_text. */
+		*yy_cp = (yy_hold_char);
+
+		/* yy_bp points to the position in yy_ch_buf of the start of
+		 * the current run.
+		 */
+		yy_bp = yy_cp;
+
+		yy_current_state = (yy_start);
+yy_match:
+		do
+			{
+			register YY_CHAR yy_c = yy_ec[YY_SC_TO_UI(*yy_cp)];
+			if ( yy_accept[yy_current_state] )
+				{
+				(yy_last_accepting_state) = yy_current_state;
+				(yy_last_accepting_cpos) = yy_cp;
+				}
+			while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )
+				{
+				yy_current_state = (int) yy_def[yy_current_state];
+				if ( yy_current_state >= 20 )
+					yy_c = yy_meta[(unsigned int) yy_c];
+				}
+			yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];
+			++yy_cp;
+			}
+		while ( yy_base[yy_current_state] != 24 );
+
+yy_find_action:
+		yy_act = yy_accept[yy_current_state];
+		if ( yy_act == 0 )
+			{ /* have to back up */
+			yy_cp = (yy_last_accepting_cpos);
+			yy_current_state = (yy_last_accepting_state);
+			yy_act = yy_accept[yy_current_state];
+			}
+
+		YY_DO_BEFORE_ACTION;
+
+do_action:	/* This label is used only to access EOF actions. */
+
+		switch ( yy_act )
+	{ /* beginning of action switch */
+			case 0: /* must back up */
+			/* undo the effects of YY_DO_BEFORE_ACTION */
+			*yy_cp = (yy_hold_char);
+			yy_cp = (yy_last_accepting_cpos);
+			yy_current_state = (yy_last_accepting_state);
+			goto yy_find_action;
+
+case 1:
+YY_RULE_SETUP
+#line 28 "util/pmu.l"
+{ return value(10); }
+	YY_BREAK
+case 2:
+YY_RULE_SETUP
+#line 29 "util/pmu.l"
+{ return PP_CONFIG; }
+	YY_BREAK
+case 3:
+YY_RULE_SETUP
+#line 30 "util/pmu.l"
+{ return PP_CONFIG1; }
+	YY_BREAK
+case 4:
+YY_RULE_SETUP
+#line 31 "util/pmu.l"
+{ return PP_CONFIG2; }
+	YY_BREAK
+case 5:
+YY_RULE_SETUP
+#line 32 "util/pmu.l"
+{ return '-'; }
+	YY_BREAK
+case 6:
+YY_RULE_SETUP
+#line 33 "util/pmu.l"
+{ return ':'; }
+	YY_BREAK
+case 7:
+YY_RULE_SETUP
+#line 34 "util/pmu.l"
+{ return ','; }
+	YY_BREAK
+case 8:
+YY_RULE_SETUP
+#line 35 "util/pmu.l"
+{ ; }
+	YY_BREAK
+case 9:
+/* rule 9 can match eol */
+YY_RULE_SETUP
+#line 36 "util/pmu.l"
+{ ; }
+	YY_BREAK
+case 10:
+YY_RULE_SETUP
+#line 38 "util/pmu.l"
+ECHO;
+	YY_BREAK
+#line 816 "<stdout>"
+case YY_STATE_EOF(INITIAL):
+	yyterminate();
+
+	case YY_END_OF_BUFFER:
+		{
+		/* Amount of text matched not including the EOB char. */
+		int yy_amount_of_matched_text = (int) (yy_cp - (yytext_ptr)) - 1;
+
+		/* Undo the effects of YY_DO_BEFORE_ACTION. */
+		*yy_cp = (yy_hold_char);
+		YY_RESTORE_YY_MORE_OFFSET
+
+		if ( YY_CURRENT_BUFFER_LVALUE->yy_buffer_status == YY_BUFFER_NEW )
+			{
+			/* We're scanning a new file or input source.  It's
+			 * possible that this happened because the user
+			 * just pointed perf_pmu_in at a new source and called
+			 * perf_pmu_lex().  If so, then we have to assure
+			 * consistency between YY_CURRENT_BUFFER and our
+			 * globals.  Here is the right place to do so, because
+			 * this is the first action (other than possibly a
+			 * back-up) that will match for the new input source.
+			 */
+			(yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_n_chars;
+			YY_CURRENT_BUFFER_LVALUE->yy_input_file = perf_pmu_in;
+			YY_CURRENT_BUFFER_LVALUE->yy_buffer_status = YY_BUFFER_NORMAL;
+			}
+
+		/* Note that here we test for yy_c_buf_p "<=" to the position
+		 * of the first EOB in the buffer, since yy_c_buf_p will
+		 * already have been incremented past the NUL character
+		 * (since all states make transitions on EOB to the
+		 * end-of-buffer state).  Contrast this with the test
+		 * in input().
+		 */
+		if ( (yy_c_buf_p) <= &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] )
+			{ /* This was really a NUL. */
+			yy_state_type yy_next_state;
+
+			(yy_c_buf_p) = (yytext_ptr) + yy_amount_of_matched_text;
+
+			yy_current_state = yy_get_previous_state(  );
+
+			/* Okay, we're now positioned to make the NUL
+			 * transition.  We couldn't have
+			 * yy_get_previous_state() go ahead and do it
+			 * for us because it doesn't know how to deal
+			 * with the possibility of jamming (and we don't
+			 * want to build jamming into it because then it
+			 * will run more slowly).
+			 */
+
+			yy_next_state = yy_try_NUL_trans( yy_current_state );
+
+			yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+
+			if ( yy_next_state )
+				{
+				/* Consume the NUL. */
+				yy_cp = ++(yy_c_buf_p);
+				yy_current_state = yy_next_state;
+				goto yy_match;
+				}
+
+			else
+				{
+				yy_cp = (yy_c_buf_p);
+				goto yy_find_action;
+				}
+			}
+
+		else switch ( yy_get_next_buffer(  ) )
+			{
+			case EOB_ACT_END_OF_FILE:
+				{
+				(yy_did_buffer_switch_on_eof) = 0;
+
+				if ( perf_pmu_wrap( ) )
+					{
+					/* Note: because we've taken care in
+					 * yy_get_next_buffer() to have set up
+					 * perf_pmu_text, we can now set up
+					 * yy_c_buf_p so that if some total
+					 * hoser (like flex itself) wants to
+					 * call the scanner after we return the
+					 * YY_NULL, it'll still work - another
+					 * YY_NULL will get returned.
+					 */
+					(yy_c_buf_p) = (yytext_ptr) + YY_MORE_ADJ;
+
+					yy_act = YY_STATE_EOF(YY_START);
+					goto do_action;
+					}
+
+				else
+					{
+					if ( ! (yy_did_buffer_switch_on_eof) )
+						YY_NEW_FILE;
+					}
+				break;
+				}
+
+			case EOB_ACT_CONTINUE_SCAN:
+				(yy_c_buf_p) =
+					(yytext_ptr) + yy_amount_of_matched_text;
+
+				yy_current_state = yy_get_previous_state(  );
+
+				yy_cp = (yy_c_buf_p);
+				yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+				goto yy_match;
+
+			case EOB_ACT_LAST_MATCH:
+				(yy_c_buf_p) =
+				&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)];
+
+				yy_current_state = yy_get_previous_state(  );
+
+				yy_cp = (yy_c_buf_p);
+				yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+				goto yy_find_action;
+			}
+		break;
+		}
+
+	default:
+		YY_FATAL_ERROR(
+			"fatal flex scanner internal error--no action found" );
+	} /* end of action switch */
+		} /* end of scanning one token */
+} /* end of perf_pmu_lex */
+
+/* yy_get_next_buffer - try to read in a new buffer
+ *
+ * Returns a code representing an action:
+ *	EOB_ACT_LAST_MATCH -
+ *	EOB_ACT_CONTINUE_SCAN - continue scanning from current position
+ *	EOB_ACT_END_OF_FILE - end of file
+ */
+static int yy_get_next_buffer (void)
+{
+    	register char *dest = YY_CURRENT_BUFFER_LVALUE->yy_ch_buf;
+	register char *source = (yytext_ptr);
+	register int number_to_move, i;
+	int ret_val;
+
+	if ( (yy_c_buf_p) > &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars) + 1] )
+		YY_FATAL_ERROR(
+		"fatal flex scanner internal error--end of buffer missed" );
+
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_fill_buffer == 0 )
+		{ /* Don't try to fill the buffer, so this is an EOF. */
+		if ( (yy_c_buf_p) - (yytext_ptr) - YY_MORE_ADJ == 1 )
+			{
+			/* We matched a single character, the EOB, so
+			 * treat this as a final EOF.
+			 */
+			return EOB_ACT_END_OF_FILE;
+			}
+
+		else
+			{
+			/* We matched some text prior to the EOB, first
+			 * process it.
+			 */
+			return EOB_ACT_LAST_MATCH;
+			}
+		}
+
+	/* Try to read more data. */
+
+	/* First move last chars to start of buffer. */
+	number_to_move = (int) ((yy_c_buf_p) - (yytext_ptr)) - 1;
+
+	for ( i = 0; i < number_to_move; ++i )
+		*(dest++) = *(source++);
+
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_buffer_status == YY_BUFFER_EOF_PENDING )
+		/* don't do the read, it's not guaranteed to return an EOF,
+		 * just force an EOF
+		 */
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars) = 0;
+
+	else
+		{
+			int num_to_read =
+			YY_CURRENT_BUFFER_LVALUE->yy_buf_size - number_to_move - 1;
+
+		while ( num_to_read <= 0 )
+			{ /* Not enough room in the buffer - grow it. */
+
+			/* just a shorter name for the current buffer */
+			YY_BUFFER_STATE b = YY_CURRENT_BUFFER;
+
+			int yy_c_buf_p_offset =
+				(int) ((yy_c_buf_p) - b->yy_ch_buf);
+
+			if ( b->yy_is_our_buffer )
+				{
+				int new_size = b->yy_buf_size * 2;
+
+				if ( new_size <= 0 )
+					b->yy_buf_size += b->yy_buf_size / 8;
+				else
+					b->yy_buf_size *= 2;
+
+				b->yy_ch_buf = (char *)
+					/* Include room in for 2 EOB chars. */
+					perf_pmu_realloc((void *) b->yy_ch_buf,b->yy_buf_size + 2  );
+				}
+			else
+				/* Can't grow it, we don't own it. */
+				b->yy_ch_buf = 0;
+
+			if ( ! b->yy_ch_buf )
+				YY_FATAL_ERROR(
+				"fatal error - scanner input buffer overflow" );
+
+			(yy_c_buf_p) = &b->yy_ch_buf[yy_c_buf_p_offset];
+
+			num_to_read = YY_CURRENT_BUFFER_LVALUE->yy_buf_size -
+						number_to_move - 1;
+
+			}
+
+		if ( num_to_read > YY_READ_BUF_SIZE )
+			num_to_read = YY_READ_BUF_SIZE;
+
+		/* Read in more data. */
+		YY_INPUT( (&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[number_to_move]),
+			(yy_n_chars), (size_t) num_to_read );
+
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	if ( (yy_n_chars) == 0 )
+		{
+		if ( number_to_move == YY_MORE_ADJ )
+			{
+			ret_val = EOB_ACT_END_OF_FILE;
+			perf_pmu_restart(perf_pmu_in  );
+			}
+
+		else
+			{
+			ret_val = EOB_ACT_LAST_MATCH;
+			YY_CURRENT_BUFFER_LVALUE->yy_buffer_status =
+				YY_BUFFER_EOF_PENDING;
+			}
+		}
+
+	else
+		ret_val = EOB_ACT_CONTINUE_SCAN;
+
+	if ((yy_size_t) ((yy_n_chars) + number_to_move) > YY_CURRENT_BUFFER_LVALUE->yy_buf_size) {
+		/* Extend the array by 50%, plus the number we really need. */
+		yy_size_t new_size = (yy_n_chars) + number_to_move + ((yy_n_chars) >> 1);
+		YY_CURRENT_BUFFER_LVALUE->yy_ch_buf = (char *) perf_pmu_realloc((void *) YY_CURRENT_BUFFER_LVALUE->yy_ch_buf,new_size  );
+		if ( ! YY_CURRENT_BUFFER_LVALUE->yy_ch_buf )
+			YY_FATAL_ERROR( "out of dynamic memory in yy_get_next_buffer()" );
+	}
+
+	(yy_n_chars) += number_to_move;
+	YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] = YY_END_OF_BUFFER_CHAR;
+	YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars) + 1] = YY_END_OF_BUFFER_CHAR;
+
+	(yytext_ptr) = &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[0];
+
+	return ret_val;
+}
+
+/* yy_get_previous_state - get the state just before the EOB char was reached */
+
+    static yy_state_type yy_get_previous_state (void)
+{
+	register yy_state_type yy_current_state;
+	register char *yy_cp;
+    
+	yy_current_state = (yy_start);
+
+	for ( yy_cp = (yytext_ptr) + YY_MORE_ADJ; yy_cp < (yy_c_buf_p); ++yy_cp )
+		{
+		register YY_CHAR yy_c = (*yy_cp ? yy_ec[YY_SC_TO_UI(*yy_cp)] : 1);
+		if ( yy_accept[yy_current_state] )
+			{
+			(yy_last_accepting_state) = yy_current_state;
+			(yy_last_accepting_cpos) = yy_cp;
+			}
+		while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )
+			{
+			yy_current_state = (int) yy_def[yy_current_state];
+			if ( yy_current_state >= 20 )
+				yy_c = yy_meta[(unsigned int) yy_c];
+			}
+		yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];
+		}
+
+	return yy_current_state;
+}
+
+/* yy_try_NUL_trans - try to make a transition on the NUL character
+ *
+ * synopsis
+ *	next_state = yy_try_NUL_trans( current_state );
+ */
+    static yy_state_type yy_try_NUL_trans  (yy_state_type yy_current_state )
+{
+	register int yy_is_jam;
+    	register char *yy_cp = (yy_c_buf_p);
+
+	register YY_CHAR yy_c = 1;
+	if ( yy_accept[yy_current_state] )
+		{
+		(yy_last_accepting_state) = yy_current_state;
+		(yy_last_accepting_cpos) = yy_cp;
+		}
+	while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )
+		{
+		yy_current_state = (int) yy_def[yy_current_state];
+		if ( yy_current_state >= 20 )
+			yy_c = yy_meta[(unsigned int) yy_c];
+		}
+	yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];
+	yy_is_jam = (yy_current_state == 19);
+
+	return yy_is_jam ? 0 : yy_current_state;
+}
+
+    static void yyunput (int c, register char * yy_bp )
+{
+	register char *yy_cp;
+    
+    yy_cp = (yy_c_buf_p);
+
+	/* undo effects of setting up perf_pmu_text */
+	*yy_cp = (yy_hold_char);
+
+	if ( yy_cp < YY_CURRENT_BUFFER_LVALUE->yy_ch_buf + 2 )
+		{ /* need to shift things up to make room */
+		/* +2 for EOB chars. */
+		register int number_to_move = (yy_n_chars) + 2;
+		register char *dest = &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[
+					YY_CURRENT_BUFFER_LVALUE->yy_buf_size + 2];
+		register char *source =
+				&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[number_to_move];
+
+		while ( source > YY_CURRENT_BUFFER_LVALUE->yy_ch_buf )
+			*--dest = *--source;
+
+		yy_cp += (int) (dest - source);
+		yy_bp += (int) (dest - source);
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars =
+			(yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_buf_size;
+
+		if ( yy_cp < YY_CURRENT_BUFFER_LVALUE->yy_ch_buf + 2 )
+			YY_FATAL_ERROR( "flex scanner push-back overflow" );
+		}
+
+	*--yy_cp = (char) c;
+
+	(yytext_ptr) = yy_bp;
+	(yy_hold_char) = *yy_cp;
+	(yy_c_buf_p) = yy_cp;
+}
+
+#ifndef YY_NO_INPUT
+#ifdef __cplusplus
+    static int yyinput (void)
+#else
+    static int input  (void)
+#endif
+
+{
+	int c;
+    
+	*(yy_c_buf_p) = (yy_hold_char);
+
+	if ( *(yy_c_buf_p) == YY_END_OF_BUFFER_CHAR )
+		{
+		/* yy_c_buf_p now points to the character we want to return.
+		 * If this occurs *before* the EOB characters, then it's a
+		 * valid NUL; if not, then we've hit the end of the buffer.
+		 */
+		if ( (yy_c_buf_p) < &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] )
+			/* This was really a NUL. */
+			*(yy_c_buf_p) = '\0';
+
+		else
+			{ /* need more input */
+			int offset = (yy_c_buf_p) - (yytext_ptr);
+			++(yy_c_buf_p);
+
+			switch ( yy_get_next_buffer(  ) )
+				{
+				case EOB_ACT_LAST_MATCH:
+					/* This happens because yy_g_n_b()
+					 * sees that we've accumulated a
+					 * token and flags that we need to
+					 * try matching the token before
+					 * proceeding.  But for input(),
+					 * there's no matching to consider.
+					 * So convert the EOB_ACT_LAST_MATCH
+					 * to EOB_ACT_END_OF_FILE.
+					 */
+
+					/* Reset buffer status. */
+					perf_pmu_restart(perf_pmu_in );
+
+					/*FALLTHROUGH*/
+
+				case EOB_ACT_END_OF_FILE:
+					{
+					if ( perf_pmu_wrap( ) )
+						return EOF;
+
+					if ( ! (yy_did_buffer_switch_on_eof) )
+						YY_NEW_FILE;
+#ifdef __cplusplus
+					return yyinput();
+#else
+					return input();
+#endif
+					}
+
+				case EOB_ACT_CONTINUE_SCAN:
+					(yy_c_buf_p) = (yytext_ptr) + offset;
+					break;
+				}
+			}
+		}
+
+	c = *(unsigned char *) (yy_c_buf_p);	/* cast for 8-bit char's */
+	*(yy_c_buf_p) = '\0';	/* preserve perf_pmu_text */
+	(yy_hold_char) = *++(yy_c_buf_p);
+
+	return c;
+}
+#endif	/* ifndef YY_NO_INPUT */
+
+/** Immediately switch to a different input stream.
+ * @param input_file A readable stream.
+ * 
+ * @note This function does not reset the start condition to @c INITIAL .
+ */
+    void perf_pmu_restart  (FILE * input_file )
+{
+    
+	if ( ! YY_CURRENT_BUFFER ){
+        perf_pmu_ensure_buffer_stack ();
+		YY_CURRENT_BUFFER_LVALUE =
+            perf_pmu__create_buffer(perf_pmu_in,YY_BUF_SIZE );
+	}
+
+	perf_pmu__init_buffer(YY_CURRENT_BUFFER,input_file );
+	perf_pmu__load_buffer_state( );
+}
+
+/** Switch to a different input buffer.
+ * @param new_buffer The new input buffer.
+ * 
+ */
+    void perf_pmu__switch_to_buffer  (YY_BUFFER_STATE  new_buffer )
+{
+    
+	/* TODO. We should be able to replace this entire function body
+	 * with
+	 *		perf_pmu_pop_buffer_state();
+	 *		perf_pmu_push_buffer_state(new_buffer);
+     */
+	perf_pmu_ensure_buffer_stack ();
+	if ( YY_CURRENT_BUFFER == new_buffer )
+		return;
+
+	if ( YY_CURRENT_BUFFER )
+		{
+		/* Flush out information for old buffer. */
+		*(yy_c_buf_p) = (yy_hold_char);
+		YY_CURRENT_BUFFER_LVALUE->yy_buf_pos = (yy_c_buf_p);
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	YY_CURRENT_BUFFER_LVALUE = new_buffer;
+	perf_pmu__load_buffer_state( );
+
+	/* We don't actually know whether we did this switch during
+	 * EOF (perf_pmu_wrap()) processing, but the only time this flag
+	 * is looked at is after perf_pmu_wrap() is called, so it's safe
+	 * to go ahead and always set it.
+	 */
+	(yy_did_buffer_switch_on_eof) = 1;
+}
+
+static void perf_pmu__load_buffer_state  (void)
+{
+    	(yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_n_chars;
+	(yytext_ptr) = (yy_c_buf_p) = YY_CURRENT_BUFFER_LVALUE->yy_buf_pos;
+	perf_pmu_in = YY_CURRENT_BUFFER_LVALUE->yy_input_file;
+	(yy_hold_char) = *(yy_c_buf_p);
+}
+
+/** Allocate and initialize an input buffer state.
+ * @param file A readable stream.
+ * @param size The character buffer size in bytes. When in doubt, use @c YY_BUF_SIZE.
+ * 
+ * @return the allocated buffer state.
+ */
+    YY_BUFFER_STATE perf_pmu__create_buffer  (FILE * file, int  size )
+{
+	YY_BUFFER_STATE b;
+    
+	b = (YY_BUFFER_STATE) perf_pmu_alloc(sizeof( struct yy_buffer_state )  );
+	if ( ! b )
+		YY_FATAL_ERROR( "out of dynamic memory in perf_pmu__create_buffer()" );
+
+	b->yy_buf_size = size;
+
+	/* yy_ch_buf has to be 2 characters longer than the size given because
+	 * we need to put in 2 end-of-buffer characters.
+	 */
+	b->yy_ch_buf = (char *) perf_pmu_alloc(b->yy_buf_size + 2  );
+	if ( ! b->yy_ch_buf )
+		YY_FATAL_ERROR( "out of dynamic memory in perf_pmu__create_buffer()" );
+
+	b->yy_is_our_buffer = 1;
+
+	perf_pmu__init_buffer(b,file );
+
+	return b;
+}
+
+/** Destroy the buffer.
+ * @param b a buffer created with perf_pmu__create_buffer()
+ * 
+ */
+    void perf_pmu__delete_buffer (YY_BUFFER_STATE  b )
+{
+    
+	if ( ! b )
+		return;
+
+	if ( b == YY_CURRENT_BUFFER ) /* Not sure if we should pop here. */
+		YY_CURRENT_BUFFER_LVALUE = (YY_BUFFER_STATE) 0;
+
+	if ( b->yy_is_our_buffer )
+		perf_pmu_free((void *) b->yy_ch_buf  );
+
+	perf_pmu_free((void *) b  );
+}
+
+#ifndef __cplusplus
+extern int isatty (int );
+#endif /* __cplusplus */
+    
+/* Initializes or reinitializes a buffer.
+ * This function is sometimes called more than once on the same buffer,
+ * such as during a perf_pmu_restart() or at EOF.
+ */
+    static void perf_pmu__init_buffer  (YY_BUFFER_STATE  b, FILE * file )
+
+{
+	int oerrno = errno;
+    
+	perf_pmu__flush_buffer(b );
+
+	b->yy_input_file = file;
+	b->yy_fill_buffer = 1;
+
+    /* If b is the current buffer, then perf_pmu__init_buffer was _probably_
+     * called from perf_pmu_restart() or through yy_get_next_buffer.
+     * In that case, we don't want to reset the lineno or column.
+     */
+    if (b != YY_CURRENT_BUFFER){
+        b->yy_bs_lineno = 1;
+        b->yy_bs_column = 0;
+    }
+
+        b->yy_is_interactive = file ? (isatty( fileno(file) ) > 0) : 0;
+    
+	errno = oerrno;
+}
+
+/** Discard all buffered characters. On the next scan, YY_INPUT will be called.
+ * @param b the buffer state to be flushed, usually @c YY_CURRENT_BUFFER.
+ * 
+ */
+    void perf_pmu__flush_buffer (YY_BUFFER_STATE  b )
+{
+    	if ( ! b )
+		return;
+
+	b->yy_n_chars = 0;
+
+	/* We always need two end-of-buffer characters.  The first causes
+	 * a transition to the end-of-buffer state.  The second causes
+	 * a jam in that state.
+	 */
+	b->yy_ch_buf[0] = YY_END_OF_BUFFER_CHAR;
+	b->yy_ch_buf[1] = YY_END_OF_BUFFER_CHAR;
+
+	b->yy_buf_pos = &b->yy_ch_buf[0];
+
+	b->yy_at_bol = 1;
+	b->yy_buffer_status = YY_BUFFER_NEW;
+
+	if ( b == YY_CURRENT_BUFFER )
+		perf_pmu__load_buffer_state( );
+}
+
+/** Pushes the new state onto the stack. The new state becomes
+ *  the current state. This function will allocate the stack
+ *  if necessary.
+ *  @param new_buffer The new state.
+ *  
+ */
+void perf_pmu_push_buffer_state (YY_BUFFER_STATE new_buffer )
+{
+    	if (new_buffer == NULL)
+		return;
+
+	perf_pmu_ensure_buffer_stack();
+
+	/* This block is copied from perf_pmu__switch_to_buffer. */
+	if ( YY_CURRENT_BUFFER )
+		{
+		/* Flush out information for old buffer. */
+		*(yy_c_buf_p) = (yy_hold_char);
+		YY_CURRENT_BUFFER_LVALUE->yy_buf_pos = (yy_c_buf_p);
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	/* Only push if top exists. Otherwise, replace top. */
+	if (YY_CURRENT_BUFFER)
+		(yy_buffer_stack_top)++;
+	YY_CURRENT_BUFFER_LVALUE = new_buffer;
+
+	/* copied from perf_pmu__switch_to_buffer. */
+	perf_pmu__load_buffer_state( );
+	(yy_did_buffer_switch_on_eof) = 1;
+}
+
+/** Removes and deletes the top of the stack, if present.
+ *  The next element becomes the new top.
+ *  
+ */
+void perf_pmu_pop_buffer_state (void)
+{
+    	if (!YY_CURRENT_BUFFER)
+		return;
+
+	perf_pmu__delete_buffer(YY_CURRENT_BUFFER );
+	YY_CURRENT_BUFFER_LVALUE = NULL;
+	if ((yy_buffer_stack_top) > 0)
+		--(yy_buffer_stack_top);
+
+	if (YY_CURRENT_BUFFER) {
+		perf_pmu__load_buffer_state( );
+		(yy_did_buffer_switch_on_eof) = 1;
+	}
+}
+
+/* Allocates the stack if it does not exist.
+ *  Guarantees space for at least one push.
+ */
+static void perf_pmu_ensure_buffer_stack (void)
+{
+	int num_to_alloc;
+    
+	if (!(yy_buffer_stack)) {
+
+		/* First allocation is just for 2 elements, since we don't know if this
+		 * scanner will even need a stack. We use 2 instead of 1 to avoid an
+		 * immediate realloc on the next call.
+         */
+		num_to_alloc = 1;
+		(yy_buffer_stack) = (struct yy_buffer_state**)perf_pmu_alloc
+								(num_to_alloc * sizeof(struct yy_buffer_state*)
+								);
+		if ( ! (yy_buffer_stack) )
+			YY_FATAL_ERROR( "out of dynamic memory in perf_pmu_ensure_buffer_stack()" );
+								  
+		memset((yy_buffer_stack), 0, num_to_alloc * sizeof(struct yy_buffer_state*));
+				
+		(yy_buffer_stack_max) = num_to_alloc;
+		(yy_buffer_stack_top) = 0;
+		return;
+	}
+
+	if ((yy_buffer_stack_top) >= ((yy_buffer_stack_max)) - 1){
+
+		/* Increase the buffer to prepare for a possible push. */
+		int grow_size = 8 /* arbitrary grow size */;
+
+		num_to_alloc = (yy_buffer_stack_max) + grow_size;
+		(yy_buffer_stack) = (struct yy_buffer_state**)perf_pmu_realloc
+								((yy_buffer_stack),
+								num_to_alloc * sizeof(struct yy_buffer_state*)
+								);
+		if ( ! (yy_buffer_stack) )
+			YY_FATAL_ERROR( "out of dynamic memory in perf_pmu_ensure_buffer_stack()" );
+
+		/* zero only the new slots.*/
+		memset((yy_buffer_stack) + (yy_buffer_stack_max), 0, grow_size * sizeof(struct yy_buffer_state*));
+		(yy_buffer_stack_max) = num_to_alloc;
+	}
+}
+
+/** Setup the input buffer state to scan directly from a user-specified character buffer.
+ * @param base the character buffer
+ * @param size the size in bytes of the character buffer
+ * 
+ * @return the newly allocated buffer state object. 
+ */
+YY_BUFFER_STATE perf_pmu__scan_buffer  (char * base, yy_size_t  size )
+{
+	YY_BUFFER_STATE b;
+    
+	if ( size < 2 ||
+	     base[size-2] != YY_END_OF_BUFFER_CHAR ||
+	     base[size-1] != YY_END_OF_BUFFER_CHAR )
+		/* They forgot to leave room for the EOB's. */
+		return 0;
+
+	b = (YY_BUFFER_STATE) perf_pmu_alloc(sizeof( struct yy_buffer_state )  );
+	if ( ! b )
+		YY_FATAL_ERROR( "out of dynamic memory in perf_pmu__scan_buffer()" );
+
+	b->yy_buf_size = size - 2;	/* "- 2" to take care of EOB's */
+	b->yy_buf_pos = b->yy_ch_buf = base;
+	b->yy_is_our_buffer = 0;
+	b->yy_input_file = 0;
+	b->yy_n_chars = b->yy_buf_size;
+	b->yy_is_interactive = 0;
+	b->yy_at_bol = 1;
+	b->yy_fill_buffer = 0;
+	b->yy_buffer_status = YY_BUFFER_NEW;
+
+	perf_pmu__switch_to_buffer(b  );
+
+	return b;
+}
+
+/** Setup the input buffer state to scan a string. The next call to perf_pmu_lex() will
+ * scan from a @e copy of @a str.
+ * @param yystr a NUL-terminated string to scan
+ * 
+ * @return the newly allocated buffer state object.
+ * @note If you want to scan bytes that may contain NUL values, then use
+ *       perf_pmu__scan_bytes() instead.
+ */
+YY_BUFFER_STATE perf_pmu__scan_string (yyconst char * yystr )
+{
+    
+	return perf_pmu__scan_bytes(yystr,strlen(yystr) );
+}
+
+/** Setup the input buffer state to scan the given bytes. The next call to perf_pmu_lex() will
+ * scan from a @e copy of @a bytes.
+ * @param bytes the byte buffer to scan
+ * @param len the number of bytes in the buffer pointed to by @a bytes.
+ * 
+ * @return the newly allocated buffer state object.
+ */
+YY_BUFFER_STATE perf_pmu__scan_bytes  (yyconst char * yybytes, int  _yybytes_len )
+{
+	YY_BUFFER_STATE b;
+	char *buf;
+	yy_size_t n;
+	int i;
+    
+	/* Get memory for full buffer, including space for trailing EOB's. */
+	n = _yybytes_len + 2;
+	buf = (char *) perf_pmu_alloc(n  );
+	if ( ! buf )
+		YY_FATAL_ERROR( "out of dynamic memory in perf_pmu__scan_bytes()" );
+
+	for ( i = 0; i < _yybytes_len; ++i )
+		buf[i] = yybytes[i];
+
+	buf[_yybytes_len] = buf[_yybytes_len+1] = YY_END_OF_BUFFER_CHAR;
+
+	b = perf_pmu__scan_buffer(buf,n );
+	if ( ! b )
+		YY_FATAL_ERROR( "bad buffer in perf_pmu__scan_bytes()" );
+
+	/* It's okay to grow etc. this buffer, and we should throw it
+	 * away when we're done.
+	 */
+	b->yy_is_our_buffer = 1;
+
+	return b;
+}
+
+#ifndef YY_EXIT_FAILURE
+#define YY_EXIT_FAILURE 2
+#endif
+
+static void yy_fatal_error (yyconst char* msg )
+{
+    	(void) fprintf( stderr, "%s\n", msg );
+	exit( YY_EXIT_FAILURE );
+}
+
+/* Redefine yyless() so it works in section 3 code. */
+
+#undef yyless
+#define yyless(n) \
+	do \
+		{ \
+		/* Undo effects of setting up perf_pmu_text. */ \
+        int yyless_macro_arg = (n); \
+        YY_LESS_LINENO(yyless_macro_arg);\
+		perf_pmu_text[perf_pmu_leng] = (yy_hold_char); \
+		(yy_c_buf_p) = perf_pmu_text + yyless_macro_arg; \
+		(yy_hold_char) = *(yy_c_buf_p); \
+		*(yy_c_buf_p) = '\0'; \
+		perf_pmu_leng = yyless_macro_arg; \
+		} \
+	while ( 0 )
+
+/* Accessor  methods (get/set functions) to struct members. */
+
+/** Get the current line number.
+ * 
+ */
+int perf_pmu_get_lineno  (void)
+{
+        
+    return perf_pmu_lineno;
+}
+
+/** Get the input stream.
+ * 
+ */
+FILE *perf_pmu_get_in  (void)
+{
+        return perf_pmu_in;
+}
+
+/** Get the output stream.
+ * 
+ */
+FILE *perf_pmu_get_out  (void)
+{
+        return perf_pmu_out;
+}
+
+/** Get the length of the current token.
+ * 
+ */
+int perf_pmu_get_leng  (void)
+{
+        return perf_pmu_leng;
+}
+
+/** Get the current token.
+ * 
+ */
+
+char *perf_pmu_get_text  (void)
+{
+        return perf_pmu_text;
+}
+
+/** Set the current line number.
+ * @param line_number
+ * 
+ */
+void perf_pmu_set_lineno (int  line_number )
+{
+    
+    perf_pmu_lineno = line_number;
+}
+
+/** Set the input stream. This does not discard the current
+ * input buffer.
+ * @param in_str A readable stream.
+ * 
+ * @see perf_pmu__switch_to_buffer
+ */
+void perf_pmu_set_in (FILE *  in_str )
+{
+        perf_pmu_in = in_str ;
+}
+
+void perf_pmu_set_out (FILE *  out_str )
+{
+        perf_pmu_out = out_str ;
+}
+
+int perf_pmu_get_debug  (void)
+{
+        return perf_pmu__flex_debug;
+}
+
+void perf_pmu_set_debug (int  bdebug )
+{
+        perf_pmu__flex_debug = bdebug ;
+}
+
+static int yy_init_globals (void)
+{
+        /* Initialization is the same as for the non-reentrant scanner.
+     * This function is called from perf_pmu_lex_destroy(), so don't allocate here.
+     */
+
+    (yy_buffer_stack) = 0;
+    (yy_buffer_stack_top) = 0;
+    (yy_buffer_stack_max) = 0;
+    (yy_c_buf_p) = (char *) 0;
+    (yy_init) = 0;
+    (yy_start) = 0;
+
+/* Defined in main.c */
+#ifdef YY_STDINIT
+    perf_pmu_in = stdin;
+    perf_pmu_out = stdout;
+#else
+    perf_pmu_in = (FILE *) 0;
+    perf_pmu_out = (FILE *) 0;
+#endif
+
+    /* For future reference: Set errno on error, since we are called by
+     * perf_pmu_lex_init()
+     */
+    return 0;
+}
+
+/* perf_pmu_lex_destroy is for both reentrant and non-reentrant scanners. */
+int perf_pmu_lex_destroy  (void)
+{
+    
+    /* Pop the buffer stack, destroying each element. */
+	while(YY_CURRENT_BUFFER){
+		perf_pmu__delete_buffer(YY_CURRENT_BUFFER  );
+		YY_CURRENT_BUFFER_LVALUE = NULL;
+		perf_pmu_pop_buffer_state();
+	}
+
+	/* Destroy the stack itself. */
+	perf_pmu_free((yy_buffer_stack) );
+	(yy_buffer_stack) = NULL;
+
+    /* Reset the globals. This is important in a non-reentrant scanner so the next time
+     * perf_pmu_lex() is called, initialization will occur. */
+    yy_init_globals( );
+
+    return 0;
+}
+
+/*
+ * Internal utility routines.
+ */
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char* s1, yyconst char * s2, int n )
+{
+	register int i;
+	for ( i = 0; i < n; ++i )
+		s1[i] = s2[i];
+}
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * s )
+{
+	register int n;
+	for ( n = 0; s[n]; ++n )
+		;
+
+	return n;
+}
+#endif
+
+void *perf_pmu_alloc (yy_size_t  size )
+{
+	return (void *) malloc( size );
+}
+
+void *perf_pmu_realloc  (void * ptr, yy_size_t  size )
+{
+	/* The cast to (char *) in the following accommodates both
+	 * implementations that use char* generic pointers, and those
+	 * that use void* generic pointers.  It works with the latter
+	 * because both ANSI C and C++ allow castless assignment from
+	 * any pointer type to void*, and deal with argument conversions
+	 * as though doing an assignment.
+	 */
+	return (void *) realloc( (char *) ptr, size );
+}
+
+void perf_pmu_free (void * ptr )
+{
+	free( (char *) ptr );	/* see perf_pmu_realloc() for (char *) cast */
+}
+
+#define YYTABLES_NAME "yytables"
+
+#line 38 "util/pmu.l"
+
+
+
+int perf_pmu_wrap(void)
+{
+	return 1;
+}
+
diff --git a/tools/perf/util/pmu-flex.h b/tools/perf/util/pmu-flex.h
new file mode 100644
index 0000000..0a29c8a
--- /dev/null
+++ b/tools/perf/util/pmu-flex.h
@@ -0,0 +1,316 @@
+#ifndef perf_pmu_HEADER_H
+#define perf_pmu_HEADER_H 1
+#define perf_pmu_IN_HEADER 1
+
+#line 6 "util/pmu-flex.h"
+
+#define  YY_INT_ALIGNED short int
+
+/* A lexical scanner generated by flex */
+
+#define FLEX_SCANNER
+#define YY_FLEX_MAJOR_VERSION 2
+#define YY_FLEX_MINOR_VERSION 5
+#define YY_FLEX_SUBMINOR_VERSION 35
+#if YY_FLEX_SUBMINOR_VERSION > 0
+#define FLEX_BETA
+#endif
+
+/* First, we deal with  platform-specific or compiler-specific issues. */
+
+/* begin standard C headers. */
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <stdlib.h>
+
+/* end standard C headers. */
+
+/* flex integer type definitions */
+
+#ifndef FLEXINT_H
+#define FLEXINT_H
+
+/* C99 systems have <inttypes.h>. Non-C99 systems may or may not. */
+
+#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+
+/* C99 says to define __STDC_LIMIT_MACROS before including stdint.h,
+ * if you want the limit (max/min) macros for int types. 
+ */
+#ifndef __STDC_LIMIT_MACROS
+#define __STDC_LIMIT_MACROS 1
+#endif
+
+#include <inttypes.h>
+typedef int8_t flex_int8_t;
+typedef uint8_t flex_uint8_t;
+typedef int16_t flex_int16_t;
+typedef uint16_t flex_uint16_t;
+typedef int32_t flex_int32_t;
+typedef uint32_t flex_uint32_t;
+#else
+typedef signed char flex_int8_t;
+typedef short int flex_int16_t;
+typedef int flex_int32_t;
+typedef unsigned char flex_uint8_t; 
+typedef unsigned short int flex_uint16_t;
+typedef unsigned int flex_uint32_t;
+#endif /* ! C99 */
+
+/* Limits of integral types. */
+#ifndef INT8_MIN
+#define INT8_MIN               (-128)
+#endif
+#ifndef INT16_MIN
+#define INT16_MIN              (-32767-1)
+#endif
+#ifndef INT32_MIN
+#define INT32_MIN              (-2147483647-1)
+#endif
+#ifndef INT8_MAX
+#define INT8_MAX               (127)
+#endif
+#ifndef INT16_MAX
+#define INT16_MAX              (32767)
+#endif
+#ifndef INT32_MAX
+#define INT32_MAX              (2147483647)
+#endif
+#ifndef UINT8_MAX
+#define UINT8_MAX              (255U)
+#endif
+#ifndef UINT16_MAX
+#define UINT16_MAX             (65535U)
+#endif
+#ifndef UINT32_MAX
+#define UINT32_MAX             (4294967295U)
+#endif
+
+#endif /* ! FLEXINT_H */
+
+#ifdef __cplusplus
+
+/* The "const" storage-class-modifier is valid. */
+#define YY_USE_CONST
+
+#else	/* ! __cplusplus */
+
+/* C99 requires __STDC__ to be defined as 1. */
+#if defined (__STDC__)
+
+#define YY_USE_CONST
+
+#endif	/* defined (__STDC__) */
+#endif	/* ! __cplusplus */
+
+#ifdef YY_USE_CONST
+#define yyconst const
+#else
+#define yyconst
+#endif
+
+/* Size of default input buffer. */
+#ifndef YY_BUF_SIZE
+#define YY_BUF_SIZE 16384
+#endif
+
+#ifndef YY_TYPEDEF_YY_BUFFER_STATE
+#define YY_TYPEDEF_YY_BUFFER_STATE
+typedef struct yy_buffer_state *YY_BUFFER_STATE;
+#endif
+
+extern int perf_pmu_leng;
+
+extern FILE *perf_pmu_in, *perf_pmu_out;
+
+#ifndef YY_TYPEDEF_YY_SIZE_T
+#define YY_TYPEDEF_YY_SIZE_T
+typedef size_t yy_size_t;
+#endif
+
+#ifndef YY_STRUCT_YY_BUFFER_STATE
+#define YY_STRUCT_YY_BUFFER_STATE
+struct yy_buffer_state
+	{
+	FILE *yy_input_file;
+
+	char *yy_ch_buf;		/* input buffer */
+	char *yy_buf_pos;		/* current position in input buffer */
+
+	/* Size of input buffer in bytes, not including room for EOB
+	 * characters.
+	 */
+	yy_size_t yy_buf_size;
+
+	/* Number of characters read into yy_ch_buf, not including EOB
+	 * characters.
+	 */
+	int yy_n_chars;
+
+	/* Whether we "own" the buffer - i.e., we know we created it,
+	 * and can realloc() it to grow it, and should free() it to
+	 * delete it.
+	 */
+	int yy_is_our_buffer;
+
+	/* Whether this is an "interactive" input source; if so, and
+	 * if we're using stdio for input, then we want to use getc()
+	 * instead of fread(), to make sure we stop fetching input after
+	 * each newline.
+	 */
+	int yy_is_interactive;
+
+	/* Whether we're considered to be at the beginning of a line.
+	 * If so, '^' rules will be active on the next match, otherwise
+	 * not.
+	 */
+	int yy_at_bol;
+
+    int yy_bs_lineno; /**< The line count. */
+    int yy_bs_column; /**< The column count. */
+    
+	/* Whether to try to fill the input buffer when we reach the
+	 * end of it.
+	 */
+	int yy_fill_buffer;
+
+	int yy_buffer_status;
+
+	};
+#endif /* !YY_STRUCT_YY_BUFFER_STATE */
+
+void perf_pmu_restart (FILE *input_file  );
+void perf_pmu__switch_to_buffer (YY_BUFFER_STATE new_buffer  );
+YY_BUFFER_STATE perf_pmu__create_buffer (FILE *file,int size  );
+void perf_pmu__delete_buffer (YY_BUFFER_STATE b  );
+void perf_pmu__flush_buffer (YY_BUFFER_STATE b  );
+void perf_pmu_push_buffer_state (YY_BUFFER_STATE new_buffer  );
+void perf_pmu_pop_buffer_state (void );
+
+YY_BUFFER_STATE perf_pmu__scan_buffer (char *base,yy_size_t size  );
+YY_BUFFER_STATE perf_pmu__scan_string (yyconst char *yy_str  );
+YY_BUFFER_STATE perf_pmu__scan_bytes (yyconst char *bytes,int len  );
+
+void *perf_pmu_alloc (yy_size_t  );
+void *perf_pmu_realloc (void *,yy_size_t  );
+void perf_pmu_free (void *  );
+
+/* Begin user sect3 */
+
+extern int perf_pmu_lineno;
+
+extern char *perf_pmu_text;
+#define yytext_ptr perf_pmu_text
+
+#ifdef YY_HEADER_EXPORT_START_CONDITIONS
+#define INITIAL 0
+
+#endif
+
+#ifndef YY_NO_UNISTD_H
+/* Special case for "unistd.h", since it is non-ANSI. We include it way
+ * down here because we want the user's section 1 to have been scanned first.
+ * The user has a chance to override it with an option.
+ */
+#include <unistd.h>
+#endif
+
+#ifndef YY_EXTRA_TYPE
+#define YY_EXTRA_TYPE void *
+#endif
+
+/* Accessor methods to globals.
+   These are made visible to non-reentrant scanners for convenience. */
+
+int perf_pmu_lex_destroy (void );
+
+int perf_pmu_get_debug (void );
+
+void perf_pmu_set_debug (int debug_flag  );
+
+YY_EXTRA_TYPE perf_pmu_get_extra (void );
+
+void perf_pmu_set_extra (YY_EXTRA_TYPE user_defined  );
+
+FILE *perf_pmu_get_in (void );
+
+void perf_pmu_set_in  (FILE * in_str  );
+
+FILE *perf_pmu_get_out (void );
+
+void perf_pmu_set_out  (FILE * out_str  );
+
+int perf_pmu_get_leng (void );
+
+char *perf_pmu_get_text (void );
+
+int perf_pmu_get_lineno (void );
+
+void perf_pmu_set_lineno (int line_number  );
+
+/* Macros after this point can all be overridden by user definitions in
+ * section 1.
+ */
+
+#ifndef YY_SKIP_YYWRAP
+#ifdef __cplusplus
+extern "C" int perf_pmu_wrap (void );
+#else
+extern int perf_pmu_wrap (void );
+#endif
+#endif
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char *,yyconst char *,int );
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * );
+#endif
+
+#ifndef YY_NO_INPUT
+
+#endif
+
+/* Amount of stuff to slurp up with each read. */
+#ifndef YY_READ_BUF_SIZE
+#define YY_READ_BUF_SIZE 8192
+#endif
+
+/* Number of entries by which start-condition stack grows. */
+#ifndef YY_START_STACK_INCR
+#define YY_START_STACK_INCR 25
+#endif
+
+/* Default declaration of generated scanner - a define so the user can
+ * easily add parameters.
+ */
+#ifndef YY_DECL
+#define YY_DECL_IS_OURS 1
+
+extern int perf_pmu_lex (void);
+
+#define YY_DECL int perf_pmu_lex (void)
+#endif /* !YY_DECL */
+
+/* yy_get_previous_state - get the state just before the EOB char was reached */
+
+#undef YY_NEW_FILE
+#undef YY_FLUSH_BUFFER
+#undef yy_set_bol
+#undef yy_new_buffer
+#undef yy_set_interactive
+#undef YY_DO_BEFORE_ACTION
+
+#ifdef YY_DECL_IS_OURS
+#undef YY_DECL_IS_OURS
+#undef YY_DECL
+#endif
+
+#line 38 "util/pmu.l"
+
+
+#line 315 "util/pmu-flex.h"
+#undef perf_pmu_IN_HEADER
+#endif /* perf_pmu_HEADER_H */
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
new file mode 100644
index 0000000..cb08a11
--- /dev/null
+++ b/tools/perf/util/pmu.c
@@ -0,0 +1,469 @@
+
+#include <linux/list.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <dirent.h>
+#include "sysfs.h"
+#include "util.h"
+#include "pmu.h"
+#include "parse-events.h"
+
+int perf_pmu_parse(struct list_head *list, char *name);
+extern FILE *perf_pmu_in;
+
+static LIST_HEAD(pmus);
+
+/*
+ * Parse & process all the sysfs attributes located under
+ * the directory specified in 'dir' parameter.
+ */
+static int pmu_format_parse(char *dir, struct list_head *head)
+{
+	struct dirent *evt_ent;
+	DIR *format_dir;
+	int ret = 0;
+
+	format_dir = opendir(dir);
+	if (!format_dir)
+		return -EINVAL;
+
+	while (!ret && (evt_ent = readdir(format_dir))) {
+		char path[PATH_MAX];
+		char *name = evt_ent->d_name;
+		FILE *file;
+
+		if (!strcmp(name, ".") || !strcmp(name, ".."))
+			continue;
+
+		snprintf(path, PATH_MAX, "%s/%s", dir, name);
+
+		ret = -EINVAL;
+		file = fopen(path, "r");
+		if (!file)
+			break;
+
+		perf_pmu_in = file;
+		ret = perf_pmu_parse(head, name);
+		fclose(file);
+	}
+
+	closedir(format_dir);
+	return ret;
+}
+
+/*
+ * Reading/parsing the default pmu format definition, which should be
+ * located at:
+ * /sys/bus/event_source/devices/<dev>/format as sysfs group attributes.
+ */
+static int pmu_format(char *name, struct list_head *format)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs;
+
+	sysfs = sysfs_find_mountpoint();
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, PATH_MAX,
+		 "%s/bus/event_source/devices/%s/format", sysfs, name);
+
+	if (stat(path, &st) < 0)
+		return -1;
+
+	if (pmu_format_parse(path, format))
+		return -1;
+
+	return 0;
+}
+
+/*
+ * Reading/parsing the default pmu type value, which should be
+ * located at:
+ * /sys/bus/event_source/devices/<dev>/type as sysfs attribute.
+ */
+static int pmu_type(char *name, __u32 *type)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs;
+	FILE *file;
+	int ret = 0;
+
+	sysfs = sysfs_find_mountpoint();
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, PATH_MAX,
+		 "%s/bus/event_source/devices/%s/type", sysfs, name);
+
+	if (stat(path, &st) < 0)
+		return -1;
+
+	file = fopen(path, "r");
+	if (!file)
+		return -EINVAL;
+
+	if (1 != fscanf(file, "%u", type))
+		ret = -1;
+
+	fclose(file);
+	return ret;
+}
+
+static struct perf_pmu *pmu_lookup(char *name)
+{
+	struct perf_pmu *pmu;
+	LIST_HEAD(format);
+	__u32 type;
+
+	/*
+	 * The pmu data we store & need consists of the pmu
+	 * type value and format definitions. Load both right
+	 * now.
+	 */
+	if (pmu_format(name, &format))
+		return NULL;
+
+	if (pmu_type(name, &type))
+		return NULL;
+
+	pmu = zalloc(sizeof(*pmu));
+	if (!pmu)
+		return NULL;
+
+	INIT_LIST_HEAD(&pmu->format);
+	list_splice(&format, &pmu->format);
+	pmu->name = strdup(name);
+	pmu->type = type;
+	return pmu;
+}
+
+static struct perf_pmu *pmu_find(char *name)
+{
+	struct perf_pmu *pmu;
+
+	list_for_each_entry(pmu, &pmus, list)
+		if (!strcmp(pmu->name, name))
+			return pmu;
+
+	return NULL;
+}
+
+struct perf_pmu *perf_pmu__find(char *name)
+{
+	struct perf_pmu *pmu;
+
+	/*
+	 * Once PMU is loaded it stays in the list,
+	 * so we keep us from multiple reading/parsing
+	 * the pmu format definitions.
+	 */
+	pmu = pmu_find(name);
+	if (pmu)
+		return pmu;
+
+	return pmu_lookup(name);
+}
+
+static struct perf_pmu__format*
+pmu_find_format(struct list_head *formats, char *name)
+{
+	struct perf_pmu__format *format;
+
+	list_for_each_entry(format, formats, list)
+		if (!strcmp(format->name, name))
+			return format;
+
+	return NULL;
+}
+
+/*
+ * Returns value based on the format definition (format parameter)
+ * and unformated value (value parameter).
+ *
+ * TODO maybe optimize a little ;)
+ */
+static __u64 pmu_format_value(unsigned long *format, __u64 value)
+{
+	unsigned long fbit, vbit;
+	__u64 v = 0;
+
+	for (fbit = 0, vbit = 0; fbit < PERF_PMU_FORMAT_BITS; fbit++) {
+
+		if (!test_bit(fbit, format))
+			continue;
+
+		if (!(value & (1llu << vbit++)))
+			continue;
+
+		v |= (1llu << fbit);
+	}
+
+	return v;
+}
+
+/*
+ * Setup one of config[12] attr members based on the
+ * user input data - temr parameter.
+ */
+static int pmu_config_term(struct list_head *formats,
+			   struct perf_event_attr *attr,
+			   struct parse_events__term *term)
+{
+	struct perf_pmu__format *format;
+	__u64 *vp;
+
+	/*
+	 * Support only for hardcoded and numnerial terms.
+	 * Hardcoded terms should be already in, so nothing
+	 * to be done for them.
+	 */
+	if (parse_events__is_hardcoded_term(term))
+		return 0;
+
+	if (term->type != PARSE_EVENTS__TERM_TYPE_NUM)
+		return -EINVAL;
+
+	format = pmu_find_format(formats, term->config);
+	if (!format)
+		return -EINVAL;
+
+	switch (format->value) {
+	case PERF_PMU_FORMAT_VALUE_CONFIG:
+		vp = &attr->config;
+		break;
+	case PERF_PMU_FORMAT_VALUE_CONFIG1:
+		vp = &attr->config1;
+		break;
+	case PERF_PMU_FORMAT_VALUE_CONFIG2:
+		vp = &attr->config2;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*vp |= pmu_format_value(format->bits, term->val.num);
+	return 0;
+}
+
+static int pmu_config(struct list_head *formats, struct perf_event_attr *attr,
+		      struct list_head *head_terms)
+{
+	struct parse_events__term *term, *h;
+
+	list_for_each_entry_safe(term, h, head_terms, list)
+		if (pmu_config_term(formats, attr, term))
+			return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * Configures event's 'attr' parameter based on the:
+ * 1) users input - specified in terms parameter
+ * 2) pmu format definitions - specified by pmu parameter
+ */
+int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
+		     struct list_head *head_terms)
+{
+	attr->type = pmu->type;
+	return pmu_config(&pmu->format, attr, head_terms);
+}
+
+int perf_pmu__new_format(struct list_head *list, char *name,
+			 int config, unsigned long *bits)
+{
+	struct perf_pmu__format *format;
+
+	format = zalloc(sizeof(*format));
+	if (!format)
+		return -ENOMEM;
+
+	format->name = strdup(name);
+	format->value = config;
+	memcpy(format->bits, bits, sizeof(format->bits));
+
+	list_add_tail(&format->list, list);
+	return 0;
+}
+
+void perf_pmu__set_format(unsigned long *bits, long from, long to)
+{
+	long b;
+
+	if (!to)
+		to = from;
+
+	memset(bits, 0, BITS_TO_LONGS(PERF_PMU_FORMAT_BITS));
+	for (b = from; b <= to; b++)
+		set_bit(b, bits);
+}
+
+/* Simulated format definitions. */
+static struct test_format {
+	const char *name;
+	const char *value;
+} test_formats[] = {
+	{ "krava01", "config:0-1,62-63\n", },
+	{ "krava02", "config:10-17\n", },
+	{ "krava03", "config:5\n", },
+	{ "krava11", "config1:0,2,4,6,8,20-28\n", },
+	{ "krava12", "config1:63\n", },
+	{ "krava13", "config1:45-47\n", },
+	{ "krava21", "config2:0-3,10-13,20-23,30-33,40-43,50-53,60-63\n", },
+	{ "krava22", "config2:8,18,48,58\n", },
+	{ "krava23", "config2:28-29,38\n", },
+};
+
+#define TEST_FORMATS_CNT (sizeof(test_formats) / sizeof(struct test_format))
+
+/* Simulated users input. */
+static struct parse_events__term test_terms[] = {
+	{
+		.config  = (char *) "krava01",
+		.val.num = 15,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava02",
+		.val.num = 170,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava03",
+		.val.num = 1,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava11",
+		.val.num = 27,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava12",
+		.val.num = 1,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava13",
+		.val.num = 2,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava21",
+		.val.num = 119,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava22",
+		.val.num = 11,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava23",
+		.val.num = 2,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+};
+#define TERMS_CNT (sizeof(test_terms) / sizeof(struct parse_events__term))
+
+/*
+ * Prepare format directory data, exported by kernel
+ * at /sys/bus/event_source/devices/<dev>/format.
+ */
+static char *test_format_dir_get(void)
+{
+	static char dir[PATH_MAX];
+	unsigned int i;
+
+	snprintf(dir, PATH_MAX, "/tmp/perf-pmu-test-format-XXXXXX");
+	if (!mkdtemp(dir))
+		return NULL;
+
+	for (i = 0; i < TEST_FORMATS_CNT; i++) {
+		static char name[PATH_MAX];
+		struct test_format *format = &test_formats[i];
+		FILE *file;
+
+		snprintf(name, PATH_MAX, "%s/%s", dir, format->name);
+
+		file = fopen(name, "w");
+		if (!file)
+			return NULL;
+
+		if (1 != fwrite(format->value, strlen(format->value), 1, file))
+			break;
+
+		fclose(file);
+	}
+
+	return dir;
+}
+
+/* Cleanup format directory. */
+static int test_format_dir_put(char *dir)
+{
+	char buf[PATH_MAX];
+	snprintf(buf, PATH_MAX, "rm -f %s/*\n", dir);
+	if (system(buf))
+		return -1;
+
+	snprintf(buf, PATH_MAX, "rmdir %s\n", dir);
+	return system(buf);
+}
+
+static struct list_head *test_terms_list(void)
+{
+	static LIST_HEAD(terms);
+	unsigned int i;
+
+	for (i = 0; i < TERMS_CNT; i++)
+		list_add_tail(&test_terms[i].list, &terms);
+
+	return &terms;
+}
+
+#undef TERMS_CNT
+
+int perf_pmu__test(void)
+{
+	char *format = test_format_dir_get();
+	LIST_HEAD(formats);
+	struct list_head *terms = test_terms_list();
+	int ret;
+
+	if (!format)
+		return -EINVAL;
+
+	do {
+		struct perf_event_attr attr;
+
+		memset(&attr, 0, sizeof(attr));
+
+		ret = pmu_format_parse(format, &formats);
+		if (ret)
+			break;
+
+		ret = pmu_config(&formats, &attr, terms);
+		if (ret)
+			break;
+
+		ret = -EINVAL;
+
+		if (attr.config  != 0xc00000000002a823)
+			break;
+		if (attr.config1 != 0x8000400000000145)
+			break;
+		if (attr.config2 != 0x0400000020041d07)
+			break;
+
+		ret = 0;
+	} while (0);
+
+	test_format_dir_put(format);
+	return ret;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
new file mode 100644
index 0000000..68c0db9
--- /dev/null
+++ b/tools/perf/util/pmu.h
@@ -0,0 +1,41 @@
+#ifndef __PMU_H
+#define __PMU_H
+
+#include <linux/bitops.h>
+#include "../../../include/linux/perf_event.h"
+
+enum {
+	PERF_PMU_FORMAT_VALUE_CONFIG,
+	PERF_PMU_FORMAT_VALUE_CONFIG1,
+	PERF_PMU_FORMAT_VALUE_CONFIG2,
+};
+
+#define PERF_PMU_FORMAT_BITS 64
+
+struct perf_pmu__format {
+	char *name;
+	int value;
+	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
+	struct list_head list;
+};
+
+struct perf_pmu {
+	char *name;
+	__u32 type;
+	struct list_head format;
+	struct list_head list;
+};
+
+struct perf_pmu *perf_pmu__find(char *name);
+int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
+		     struct list_head *head_terms);
+
+int perf_pmu_wrap(void);
+void perf_pmu_error(struct list_head *list, char *name, char const *msg);
+
+int perf_pmu__new_format(struct list_head *list, char *name,
+			 int config, unsigned long *bits);
+void perf_pmu__set_format(unsigned long *bits, long from, long to);
+
+int perf_pmu__test(void);
+#endif /* __PMU_H */
diff --git a/tools/perf/util/pmu.l b/tools/perf/util/pmu.l
new file mode 100644
index 0000000..a15d9fb
--- /dev/null
+++ b/tools/perf/util/pmu.l
@@ -0,0 +1,43 @@
+%option prefix="perf_pmu_"
+
+%{
+#include <stdlib.h>
+#include <linux/bitops.h>
+#include "pmu.h"
+#include "pmu-bison.h"
+
+static int value(int base)
+{
+	long num;
+
+	errno = 0;
+	num = strtoul(perf_pmu_text, NULL, base);
+	if (errno)
+		return PP_ERROR;
+
+	perf_pmu_lval.num = num;
+	return PP_VALUE;
+}
+
+%}
+
+num_dec         [0-9]+
+
+%%
+
+{num_dec}	{ return value(10); }
+config		{ return PP_CONFIG; }
+config1		{ return PP_CONFIG1; }
+config2		{ return PP_CONFIG2; }
+-		{ return '-'; }
+:		{ return ':'; }
+,		{ return ','; }
+.		{ ; }
+\n		{ ; }
+
+%%
+
+int perf_pmu_wrap(void)
+{
+	return 1;
+}
diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y
new file mode 100644
index 0000000..20ea77e
--- /dev/null
+++ b/tools/perf/util/pmu.y
@@ -0,0 +1,93 @@
+
+%name-prefix "perf_pmu_"
+%parse-param {struct list_head *format}
+%parse-param {char *name}
+
+%{
+
+#include <linux/compiler.h>
+#include <linux/list.h>
+#include <linux/bitmap.h>
+#include <string.h>
+#include "pmu.h"
+
+extern int perf_pmu_lex (void);
+
+#define ABORT_ON(val) \
+do { \
+        if (val) \
+                YYABORT; \
+} while (0)
+
+%}
+
+%token PP_CONFIG PP_CONFIG1 PP_CONFIG2
+%token PP_VALUE PP_ERROR
+%type <num> PP_VALUE
+%type <bits> bit_term
+%type <bits> bits
+
+%union
+{
+	unsigned long num;
+	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
+}
+
+%%
+
+format:
+format format_term
+|
+format_term
+
+format_term:
+PP_CONFIG ':' bits
+{
+	ABORT_ON(perf_pmu__new_format(format, name,
+				      PERF_PMU_FORMAT_VALUE_CONFIG,
+				      $3));
+}
+|
+PP_CONFIG1 ':' bits
+{
+	ABORT_ON(perf_pmu__new_format(format, name,
+				      PERF_PMU_FORMAT_VALUE_CONFIG1,
+				      $3));
+}
+|
+PP_CONFIG2 ':' bits
+{
+	ABORT_ON(perf_pmu__new_format(format, name,
+				      PERF_PMU_FORMAT_VALUE_CONFIG2,
+				      $3));
+}
+
+bits:
+bits ',' bit_term
+{
+	bitmap_or($$, $1, $3, 64);
+}
+|
+bit_term
+{
+	memcpy($$, $1, sizeof($1));
+}
+
+bit_term:
+PP_VALUE '-' PP_VALUE
+{
+	perf_pmu__set_format($$, $1, $3);
+}
+|
+PP_VALUE
+{
+	perf_pmu__set_format($$, $1, 0);
+}
+
+%%
+
+void perf_pmu_error(struct list_head *list __used,
+		    char *name __used,
+		    char const *msg __used)
+{
+}
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index e33554a..8a8ee64 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -34,7 +34,6 @@
 
 #include "util.h"
 #include "event.h"
-#include "string.h"
 #include "strlist.h"
 #include "debug.h"
 #include "cache.h"
@@ -273,10 +272,10 @@
 /* Try to find perf_probe_event with debuginfo */
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 					  struct probe_trace_event **tevs,
-					  int max_tevs, const char *module)
+					  int max_tevs, const char *target)
 {
 	bool need_dwarf = perf_probe_event_need_dwarf(pev);
-	struct debuginfo *dinfo = open_debuginfo(module);
+	struct debuginfo *dinfo = open_debuginfo(target);
 	int ntevs, ret = 0;
 
 	if (!dinfo) {
@@ -295,9 +294,9 @@
 
 	if (ntevs > 0) {	/* Succeeded to find trace events */
 		pr_debug("find %d probe_trace_events.\n", ntevs);
-		if (module)
+		if (target)
 			ret = add_module_to_probe_trace_events(*tevs, ntevs,
-							       module);
+							       target);
 		return ret < 0 ? ret : ntevs;
 	}
 
@@ -1729,7 +1728,7 @@
 	}
 
 	ret = 0;
-	printf("Add new event%s\n", (ntevs > 1) ? "s:" : ":");
+	printf("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
 	for (i = 0; i < ntevs; i++) {
 		tev = &tevs[i];
 		if (pev->event)
@@ -1784,7 +1783,7 @@
 
 	if (ret >= 0) {
 		/* Show how to use the event. */
-		printf("\nYou can now use it on all perf tools, such as:\n\n");
+		printf("\nYou can now use it in all perf tools, such as:\n\n");
 		printf("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group,
 			 tev->event);
 	}
@@ -1796,14 +1795,14 @@
 
 static int convert_to_probe_trace_events(struct perf_probe_event *pev,
 					  struct probe_trace_event **tevs,
-					  int max_tevs, const char *module)
+					  int max_tevs, const char *target)
 {
 	struct symbol *sym;
 	int ret = 0, i;
 	struct probe_trace_event *tev;
 
 	/* Convert perf_probe_event with debuginfo */
-	ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, module);
+	ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target);
 	if (ret != 0)
 		return ret;	/* Found in debuginfo or got an error */
 
@@ -1819,8 +1818,8 @@
 		goto error;
 	}
 
-	if (module) {
-		tev->point.module = strdup(module);
+	if (target) {
+		tev->point.module = strdup(target);
 		if (tev->point.module == NULL) {
 			ret = -ENOMEM;
 			goto error;
@@ -1890,7 +1889,7 @@
 };
 
 int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
-			  int max_tevs, const char *module, bool force_add)
+			  int max_tevs, const char *target, bool force_add)
 {
 	int i, j, ret;
 	struct __event_package *pkgs;
@@ -1913,7 +1912,7 @@
 		ret  = convert_to_probe_trace_events(pkgs[i].pev,
 						     &pkgs[i].tevs,
 						     max_tevs,
-						     module);
+						     target);
 		if (ret < 0)
 			goto end;
 		pkgs[i].ntevs = ret;
@@ -1965,7 +1964,7 @@
 		goto error;
 	}
 
-	printf("Remove event: %s\n", ent->s);
+	printf("Removed event: %s\n", ent->s);
 	return 0;
 error:
 	pr_warning("Failed to delete event: %s\n", strerror(-ret));
@@ -2069,7 +2068,7 @@
 	return 1;
 }
 
-int show_available_funcs(const char *module, struct strfilter *_filter)
+int show_available_funcs(const char *target, struct strfilter *_filter)
 {
 	struct map *map;
 	int ret;
@@ -2080,9 +2079,9 @@
 	if (ret < 0)
 		return ret;
 
-	map = kernel_get_module_map(module);
+	map = kernel_get_module_map(target);
 	if (!map) {
-		pr_err("Failed to find %s map.\n", (module) ? : "kernel");
+		pr_err("Failed to find %s map.\n", (target) ? : "kernel");
 		return -EINVAL;
 	}
 	available_func_filter = _filter;
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 74bd2e6..2cc162d 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -30,7 +30,6 @@
 #include <stdlib.h>
 #include <string.h>
 #include <stdarg.h>
-#include <ctype.h>
 #include <dwarf-regs.h>
 
 #include <linux/bitops.h>
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
new file mode 100644
index 0000000..2884e67
--- /dev/null
+++ b/tools/perf/util/python-ext-sources
@@ -0,0 +1,19 @@
+#
+# List of files needed by perf python extention
+#
+# Each source file must be placed on its own line so that it can be
+# processed by Makefile and util/setup.py accordingly.
+#
+
+util/python.c
+util/ctype.c
+util/evlist.c
+util/evsel.c
+util/cpumap.c
+util/thread_map.c
+util/util.c
+util/xyarray.c
+util/cgroup.c
+util/debugfs.c
+util/strlist.c
+../../lib/rbtree.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 9dd47a4..e03b58a 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -425,14 +425,14 @@
 static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads,
 				 PyObject *args, PyObject *kwargs)
 {
-	static char *kwlist[] = { "pid", "tid", NULL };
-	int pid = -1, tid = -1;
+	static char *kwlist[] = { "pid", "tid", "uid", NULL };
+	int pid = -1, tid = -1, uid = UINT_MAX;
 
-	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ii",
-					 kwlist, &pid, &tid))
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|iii",
+					 kwlist, &pid, &tid, &uid))
 		return -1;
 
-	pthreads->threads = thread_map__new(pid, tid);
+	pthreads->threads = thread_map__new(pid, tid, uid);
 	if (pthreads->threads == NULL)
 		return -1;
 	return 0;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 0b2a487..c2623c6 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -24,7 +24,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <ctype.h>
 #include <errno.h>
 
 #include "../../perf.h"
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b5ca255..002ebbf 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -24,7 +24,7 @@
 		self->fd = STDIN_FILENO;
 
 		if (perf_session__read_header(self, self->fd) < 0)
-			pr_err("incompatible file format");
+			pr_err("incompatible file format (rerun with -v to learn more)");
 
 		return 0;
 	}
@@ -56,7 +56,7 @@
 	}
 
 	if (perf_session__read_header(self, self->fd) < 0) {
-		pr_err("incompatible file format");
+		pr_err("incompatible file format (rerun with -v to learn more)");
 		goto out_close;
 	}
 
@@ -229,6 +229,64 @@
 	return 0;
 }
 
+static const u8 cpumodes[] = {
+	PERF_RECORD_MISC_USER,
+	PERF_RECORD_MISC_KERNEL,
+	PERF_RECORD_MISC_GUEST_USER,
+	PERF_RECORD_MISC_GUEST_KERNEL
+};
+#define NCPUMODES (sizeof(cpumodes)/sizeof(u8))
+
+static void ip__resolve_ams(struct machine *self, struct thread *thread,
+			    struct addr_map_symbol *ams,
+			    u64 ip)
+{
+	struct addr_location al;
+	size_t i;
+	u8 m;
+
+	memset(&al, 0, sizeof(al));
+
+	for (i = 0; i < NCPUMODES; i++) {
+		m = cpumodes[i];
+		/*
+		 * We cannot use the header.misc hint to determine whether a
+		 * branch stack address is user, kernel, guest, hypervisor.
+		 * Branches may straddle the kernel/user/hypervisor boundaries.
+		 * Thus, we have to try consecutively until we find a match
+		 * or else, the symbol is unknown
+		 */
+		thread__find_addr_location(thread, self, m, MAP__FUNCTION,
+				ip, &al, NULL);
+		if (al.sym)
+			goto found;
+	}
+found:
+	ams->addr = ip;
+	ams->al_addr = al.addr;
+	ams->sym = al.sym;
+	ams->map = al.map;
+}
+
+struct branch_info *machine__resolve_bstack(struct machine *self,
+					    struct thread *thr,
+					    struct branch_stack *bs)
+{
+	struct branch_info *bi;
+	unsigned int i;
+
+	bi = calloc(bs->nr, sizeof(struct branch_info));
+	if (!bi)
+		return NULL;
+
+	for (i = 0; i < bs->nr; i++) {
+		ip__resolve_ams(self, thr, &bi[i].to, bs->entries[i].to);
+		ip__resolve_ams(self, thr, &bi[i].from, bs->entries[i].from);
+		bi[i].flags = bs->entries[i].flags;
+	}
+	return bi;
+}
+
 int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
 			       struct thread *thread,
 			       struct ip_callchain *chain,
@@ -697,6 +755,18 @@
 		       i, sample->callchain->ips[i]);
 }
 
+static void branch_stack__printf(struct perf_sample *sample)
+{
+	uint64_t i;
+
+	printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr);
+
+	for (i = 0; i < sample->branch_stack->nr; i++)
+		printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 "\n",
+			i, sample->branch_stack->entries[i].from,
+			sample->branch_stack->entries[i].to);
+}
+
 static void perf_session__print_tstamp(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_sample *sample)
@@ -744,6 +814,9 @@
 
 	if (session->sample_type & PERF_SAMPLE_CALLCHAIN)
 		callchain__printf(sample);
+
+	if (session->sample_type & PERF_SAMPLE_BRANCH_STACK)
+		branch_stack__printf(sample);
 }
 
 static struct machine *
@@ -796,6 +869,10 @@
 			++session->hists.stats.nr_unknown_id;
 			return -1;
 		}
+		if (machine == NULL) {
+			++session->hists.stats.nr_unprocessable_samples;
+			return -1;
+		}
 		return tool->sample(tool, event, sample, evsel, machine);
 	case PERF_RECORD_MMAP:
 		return tool->mmap(tool, event, sample, machine);
@@ -964,6 +1041,12 @@
  			    session->hists.stats.nr_invalid_chains,
  			    session->hists.stats.nr_events[PERF_RECORD_SAMPLE]);
  	}
+
+	if (session->hists.stats.nr_unprocessable_samples != 0) {
+		ui__warning("%u unprocessable samples recorded.\n"
+			    "Do you have a KVM guest running and not using 'perf kvm'?\n",
+			    session->hists.stats.nr_unprocessable_samples);
+	}
 }
 
 #define session_done()	(*(volatile int *)(&session_done))
@@ -1293,10 +1376,9 @@
 
 void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
 			  struct machine *machine, struct perf_evsel *evsel,
-			  int print_sym, int print_dso)
+			  int print_sym, int print_dso, int print_symoffset)
 {
 	struct addr_location al;
-	const char *symname, *dsoname;
 	struct callchain_cursor *cursor = &evsel->hists.callchain_cursor;
 	struct callchain_cursor_node *node;
 
@@ -1324,20 +1406,13 @@
 
 			printf("\t%16" PRIx64, node->ip);
 			if (print_sym) {
-				if (node->sym && node->sym->name)
-					symname = node->sym->name;
-				else
-					symname = "";
-
-				printf(" %s", symname);
+				printf(" ");
+				symbol__fprintf_symname(node->sym, stdout);
 			}
 			if (print_dso) {
-				if (node->map && node->map->dso && node->map->dso->name)
-					dsoname = node->map->dso->name;
-				else
-					dsoname = "";
-
-				printf(" (%s)", dsoname);
+				printf(" (");
+				map__fprintf_dsoname(al.map, stdout);
+				printf(")");
 			}
 			printf("\n");
 
@@ -1347,21 +1422,18 @@
 	} else {
 		printf("%16" PRIx64, sample->ip);
 		if (print_sym) {
-			if (al.sym && al.sym->name)
-				symname = al.sym->name;
+			printf(" ");
+			if (print_symoffset)
+				symbol__fprintf_symname_offs(al.sym, &al,
+							     stdout);
 			else
-				symname = "";
-
-			printf(" %s", symname);
+				symbol__fprintf_symname(al.sym, stdout);
 		}
 
 		if (print_dso) {
-			if (al.map && al.map->dso && al.map->dso->name)
-				dsoname = al.map->dso->name;
-			else
-				dsoname = "";
-
-			printf(" (%s)", dsoname);
+			printf(" (");
+			map__fprintf_dsoname(al.map, stdout);
+			printf(")");
 		}
 	}
 }
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 37bc383..7a5434c 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -73,6 +73,10 @@
 				    struct ip_callchain *chain,
 				    struct symbol **parent);
 
+struct branch_info *machine__resolve_bstack(struct machine *self,
+					    struct thread *thread,
+					    struct branch_stack *bs);
+
 bool perf_session__has_traces(struct perf_session *self, const char *msg);
 
 void mem_bswap_64(void *src, int byte_size);
@@ -147,7 +151,7 @@
 
 void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
 			  struct machine *machine, struct perf_evsel *evsel,
-			  int print_sym, int print_dso);
+			  int print_sym, int print_dso, int print_symoffset);
 
 int perf_session__cpu_bitmap(struct perf_session *session,
 			     const char *cpu_list, unsigned long *cpu_bitmap);
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 36d4c56..d0f9f29 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -24,11 +24,11 @@
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
 
+ext_sources = [f.strip() for f in file('util/python-ext-sources')
+				if len(f.strip()) > 0 and f[0] != '#']
+
 perf = Extension('perf',
-		  sources = ['util/python.c', 'util/ctype.c', 'util/evlist.c',
-			     'util/evsel.c', 'util/cpumap.c', 'util/thread_map.c',
-			     'util/util.c', 'util/xyarray.c', 'util/cgroup.c',
-			     'util/debugfs.c'],
+		  sources = ext_sources,
 		  include_dirs = ['util/include'],
 		  extra_compile_args = cflags,
                  )
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 076c9d4..a272374 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -8,6 +8,7 @@
 const char	*sort_order = default_sort_order;
 int		sort__need_collapse = 0;
 int		sort__has_parent = 0;
+int		sort__branch_mode = -1; /* -1 = means not set */
 
 enum sort_type	sort__first_dimension;
 
@@ -97,21 +98,10 @@
 	return repsep_snprintf(bf, size, "%*s", width, self->thread->comm);
 }
 
-struct sort_entry sort_comm = {
-	.se_header	= "Command",
-	.se_cmp		= sort__comm_cmp,
-	.se_collapse	= sort__comm_collapse,
-	.se_snprintf	= hist_entry__comm_snprintf,
-	.se_width_idx	= HISTC_COMM,
-};
-
-/* --sort dso */
-
-static int64_t
-sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
+static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r)
 {
-	struct dso *dso_l = left->ms.map ? left->ms.map->dso : NULL;
-	struct dso *dso_r = right->ms.map ? right->ms.map->dso : NULL;
+	struct dso *dso_l = map_l ? map_l->dso : NULL;
+	struct dso *dso_r = map_r ? map_r->dso : NULL;
 	const char *dso_name_l, *dso_name_r;
 
 	if (!dso_l || !dso_r)
@@ -128,18 +118,87 @@
 	return strcmp(dso_name_l, dso_name_r);
 }
 
-static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
-				    size_t size, unsigned int width)
+struct sort_entry sort_comm = {
+	.se_header	= "Command",
+	.se_cmp		= sort__comm_cmp,
+	.se_collapse	= sort__comm_collapse,
+	.se_snprintf	= hist_entry__comm_snprintf,
+	.se_width_idx	= HISTC_COMM,
+};
+
+/* --sort dso */
+
+static int64_t
+sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	if (self->ms.map && self->ms.map->dso) {
-		const char *dso_name = !verbose ? self->ms.map->dso->short_name :
-						  self->ms.map->dso->long_name;
+	return _sort__dso_cmp(left->ms.map, right->ms.map);
+}
+
+
+static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r,
+			      u64 ip_l, u64 ip_r)
+{
+	if (!sym_l || !sym_r)
+		return cmp_null(sym_l, sym_r);
+
+	if (sym_l == sym_r)
+		return 0;
+
+	if (sym_l)
+		ip_l = sym_l->start;
+	if (sym_r)
+		ip_r = sym_r->start;
+
+	return (int64_t)(ip_r - ip_l);
+}
+
+static int _hist_entry__dso_snprintf(struct map *map, char *bf,
+				     size_t size, unsigned int width)
+{
+	if (map && map->dso) {
+		const char *dso_name = !verbose ? map->dso->short_name :
+			map->dso->long_name;
 		return repsep_snprintf(bf, size, "%-*s", width, dso_name);
 	}
 
 	return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
 }
 
+static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width)
+{
+	return _hist_entry__dso_snprintf(self->ms.map, bf, size, width);
+}
+
+static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
+				     u64 ip, char level, char *bf, size_t size,
+				     unsigned int width __used)
+{
+	size_t ret = 0;
+
+	if (verbose) {
+		char o = map ? dso__symtab_origin(map->dso) : '!';
+		ret += repsep_snprintf(bf, size, "%-#*llx %c ",
+				       BITS_PER_LONG / 4, ip, o);
+	}
+
+	ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
+	if (sym)
+		ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
+				       width - ret,
+				       sym->name);
+	else {
+		size_t len = BITS_PER_LONG / 4;
+		ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx",
+				       len, ip);
+		ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
+				       width - ret, "");
+	}
+
+	return ret;
+}
+
+
 struct sort_entry sort_dso = {
 	.se_header	= "Shared Object",
 	.se_cmp		= sort__dso_cmp,
@@ -147,8 +206,14 @@
 	.se_width_idx	= HISTC_DSO,
 };
 
-/* --sort symbol */
+static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width __used)
+{
+	return _hist_entry__sym_snprintf(self->ms.map, self->ms.sym, self->ip,
+					 self->level, bf, size, width);
+}
 
+/* --sort symbol */
 static int64_t
 sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -166,31 +231,7 @@
 	ip_l = left->ms.sym->start;
 	ip_r = right->ms.sym->start;
 
-	return (int64_t)(ip_r - ip_l);
-}
-
-static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
-				    size_t size, unsigned int width __used)
-{
-	size_t ret = 0;
-
-	if (verbose) {
-		char o = self->ms.map ? dso__symtab_origin(self->ms.map->dso) : '!';
-		ret += repsep_snprintf(bf, size, "%-#*llx %c ",
-				       BITS_PER_LONG / 4, self->ip, o);
-	}
-
-	if (!sort_dso.elide)
-		ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level);
-
-	if (self->ms.sym)
-		ret += repsep_snprintf(bf + ret, size - ret, "%s",
-				       self->ms.sym->name);
-	else
-		ret += repsep_snprintf(bf + ret, size - ret, "%-#*llx",
-				       BITS_PER_LONG / 4, self->ip);
-
-	return ret;
+	return _sort__sym_cmp(left->ms.sym, right->ms.sym, ip_l, ip_r);
 }
 
 struct sort_entry sort_sym = {
@@ -249,19 +290,155 @@
 	.se_width_idx	= HISTC_CPU,
 };
 
+static int64_t
+sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return _sort__dso_cmp(left->branch_info->from.map,
+			      right->branch_info->from.map);
+}
+
+static int hist_entry__dso_from_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width)
+{
+	return _hist_entry__dso_snprintf(self->branch_info->from.map,
+					 bf, size, width);
+}
+
+struct sort_entry sort_dso_from = {
+	.se_header	= "Source Shared Object",
+	.se_cmp		= sort__dso_from_cmp,
+	.se_snprintf	= hist_entry__dso_from_snprintf,
+	.se_width_idx	= HISTC_DSO_FROM,
+};
+
+static int64_t
+sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return _sort__dso_cmp(left->branch_info->to.map,
+			      right->branch_info->to.map);
+}
+
+static int hist_entry__dso_to_snprintf(struct hist_entry *self, char *bf,
+				       size_t size, unsigned int width)
+{
+	return _hist_entry__dso_snprintf(self->branch_info->to.map,
+					 bf, size, width);
+}
+
+static int64_t
+sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct addr_map_symbol *from_l = &left->branch_info->from;
+	struct addr_map_symbol *from_r = &right->branch_info->from;
+
+	if (!from_l->sym && !from_r->sym)
+		return right->level - left->level;
+
+	return _sort__sym_cmp(from_l->sym, from_r->sym, from_l->addr,
+			     from_r->addr);
+}
+
+static int64_t
+sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct addr_map_symbol *to_l = &left->branch_info->to;
+	struct addr_map_symbol *to_r = &right->branch_info->to;
+
+	if (!to_l->sym && !to_r->sym)
+		return right->level - left->level;
+
+	return _sort__sym_cmp(to_l->sym, to_r->sym, to_l->addr, to_r->addr);
+}
+
+static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width __used)
+{
+	struct addr_map_symbol *from = &self->branch_info->from;
+	return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
+					 self->level, bf, size, width);
+
+}
+
+static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width __used)
+{
+	struct addr_map_symbol *to = &self->branch_info->to;
+	return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
+					 self->level, bf, size, width);
+
+}
+
+struct sort_entry sort_dso_to = {
+	.se_header	= "Target Shared Object",
+	.se_cmp		= sort__dso_to_cmp,
+	.se_snprintf	= hist_entry__dso_to_snprintf,
+	.se_width_idx	= HISTC_DSO_TO,
+};
+
+struct sort_entry sort_sym_from = {
+	.se_header	= "Source Symbol",
+	.se_cmp		= sort__sym_from_cmp,
+	.se_snprintf	= hist_entry__sym_from_snprintf,
+	.se_width_idx	= HISTC_SYMBOL_FROM,
+};
+
+struct sort_entry sort_sym_to = {
+	.se_header	= "Target Symbol",
+	.se_cmp		= sort__sym_to_cmp,
+	.se_snprintf	= hist_entry__sym_to_snprintf,
+	.se_width_idx	= HISTC_SYMBOL_TO,
+};
+
+static int64_t
+sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	const unsigned char mp = left->branch_info->flags.mispred !=
+					right->branch_info->flags.mispred;
+	const unsigned char p = left->branch_info->flags.predicted !=
+					right->branch_info->flags.predicted;
+
+	return mp || p;
+}
+
+static int hist_entry__mispredict_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width){
+	static const char *out = "N/A";
+
+	if (self->branch_info->flags.predicted)
+		out = "N";
+	else if (self->branch_info->flags.mispred)
+		out = "Y";
+
+	return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
+struct sort_entry sort_mispredict = {
+	.se_header	= "Branch Mispredicted",
+	.se_cmp		= sort__mispredict_cmp,
+	.se_snprintf	= hist_entry__mispredict_snprintf,
+	.se_width_idx	= HISTC_MISPREDICT,
+};
+
 struct sort_dimension {
 	const char		*name;
 	struct sort_entry	*entry;
 	int			taken;
 };
 
+#define DIM(d, n, func) [d] = { .name = n, .entry = &(func) }
+
 static struct sort_dimension sort_dimensions[] = {
-	{ .name = "pid",	.entry = &sort_thread,	},
-	{ .name = "comm",	.entry = &sort_comm,	},
-	{ .name = "dso",	.entry = &sort_dso,	},
-	{ .name = "symbol",	.entry = &sort_sym,	},
-	{ .name = "parent",	.entry = &sort_parent,	},
-	{ .name = "cpu",	.entry = &sort_cpu,	},
+	DIM(SORT_PID, "pid", sort_thread),
+	DIM(SORT_COMM, "comm", sort_comm),
+	DIM(SORT_DSO, "dso", sort_dso),
+	DIM(SORT_DSO_FROM, "dso_from", sort_dso_from),
+	DIM(SORT_DSO_TO, "dso_to", sort_dso_to),
+	DIM(SORT_SYM, "symbol", sort_sym),
+	DIM(SORT_SYM_TO, "symbol_from", sort_sym_from),
+	DIM(SORT_SYM_FROM, "symbol_to", sort_sym_to),
+	DIM(SORT_PARENT, "parent", sort_parent),
+	DIM(SORT_CPU, "cpu", sort_cpu),
+	DIM(SORT_MISPREDICT, "mispredict", sort_mispredict),
 };
 
 int sort_dimension__add(const char *tok)
@@ -273,7 +450,6 @@
 
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
-
 		if (sd->entry == &sort_parent) {
 			int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED);
 			if (ret) {
@@ -305,6 +481,16 @@
 				sort__first_dimension = SORT_PARENT;
 			else if (!strcmp(sd->name, "cpu"))
 				sort__first_dimension = SORT_CPU;
+			else if (!strcmp(sd->name, "symbol_from"))
+				sort__first_dimension = SORT_SYM_FROM;
+			else if (!strcmp(sd->name, "symbol_to"))
+				sort__first_dimension = SORT_SYM_TO;
+			else if (!strcmp(sd->name, "dso_from"))
+				sort__first_dimension = SORT_DSO_FROM;
+			else if (!strcmp(sd->name, "dso_to"))
+				sort__first_dimension = SORT_DSO_TO;
+			else if (!strcmp(sd->name, "mispredict"))
+				sort__first_dimension = SORT_MISPREDICT;
 		}
 
 		list_add_tail(&sd->entry->list, &hist_entry__sort_list);
@@ -312,7 +498,6 @@
 
 		return 0;
 	}
-
 	return -ESRCH;
 }
 
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 3f67ae3..472aa5a 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -31,11 +31,16 @@
 extern const char default_sort_order[];
 extern int sort__need_collapse;
 extern int sort__has_parent;
+extern int sort__branch_mode;
 extern char *field_sep;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;
 extern struct sort_entry sort_sym;
 extern struct sort_entry sort_parent;
+extern struct sort_entry sort_dso_from;
+extern struct sort_entry sort_dso_to;
+extern struct sort_entry sort_sym_from;
+extern struct sort_entry sort_sym_to;
 extern enum sort_type sort__first_dimension;
 
 /**
@@ -72,6 +77,7 @@
 		struct hist_entry *pair;
 		struct rb_root	  sorted_chain;
 	};
+	struct branch_info	*branch_info;
 	struct callchain_root	callchain[0];
 };
 
@@ -82,6 +88,11 @@
 	SORT_SYM,
 	SORT_PARENT,
 	SORT_CPU,
+	SORT_DSO_FROM,
+	SORT_DSO_TO,
+	SORT_SYM_FROM,
+	SORT_SYM_TO,
+	SORT_MISPREDICT,
 };
 
 /*
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 0975438..5dd83c3 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1,4 +1,3 @@
-#include <ctype.h>
 #include <dirent.h>
 #include <errno.h>
 #include <libgen.h>
@@ -12,6 +11,7 @@
 #include <unistd.h>
 #include <inttypes.h>
 #include "build-id.h"
+#include "util.h"
 #include "debug.h"
 #include "symbol.h"
 #include "strlist.h"
@@ -263,6 +263,28 @@
 		       sym->name);
 }
 
+size_t symbol__fprintf_symname_offs(const struct symbol *sym,
+				    const struct addr_location *al, FILE *fp)
+{
+	unsigned long offset;
+	size_t length;
+
+	if (sym && sym->name) {
+		length = fprintf(fp, "%s", sym->name);
+		if (al) {
+			offset = al->addr - sym->start;
+			length += fprintf(fp, "+0x%lx", offset);
+		}
+		return length;
+	} else
+		return fprintf(fp, "[unknown]");
+}
+
+size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp)
+{
+	return symbol__fprintf_symname_offs(sym, NULL, fp);
+}
+
 void dso__set_long_name(struct dso *dso, char *name)
 {
 	if (name == NULL)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 123c2e1..ac49ef2 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -5,6 +5,7 @@
 #include <stdbool.h>
 #include <stdint.h>
 #include "map.h"
+#include "../perf.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <stdio.h>
@@ -70,6 +71,7 @@
 	unsigned short	priv_size;
 	unsigned short	nr_events;
 	bool		try_vmlinux_path,
+			show_kernel_path,
 			use_modules,
 			sort_by_name,
 			show_nr_samples,
@@ -95,7 +97,11 @@
 			*col_width_list_str;
        struct strlist	*dso_list,
 			*comm_list,
-			*sym_list;
+			*sym_list,
+			*dso_from_list,
+			*dso_to_list,
+			*sym_from_list,
+			*sym_to_list;
 	const char	*symfs;
 };
 
@@ -119,6 +125,19 @@
 	bool	      has_children;
 };
 
+struct addr_map_symbol {
+	struct map    *map;
+	struct symbol *sym;
+	u64	      addr;
+	u64	      al_addr;
+};
+
+struct branch_info {
+	struct addr_map_symbol from;
+	struct addr_map_symbol to;
+	struct branch_flags flags;
+};
+
 struct addr_location {
 	struct thread *thread;
 	struct map    *map;
@@ -241,6 +260,9 @@
 
 int symbol__init(void);
 void symbol__exit(void);
+size_t symbol__fprintf_symname_offs(const struct symbol *sym,
+				    const struct addr_location *al, FILE *fp);
+size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
 size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
diff --git a/tools/perf/util/sysfs.c b/tools/perf/util/sysfs.c
new file mode 100644
index 0000000..48c6902
--- /dev/null
+++ b/tools/perf/util/sysfs.c
@@ -0,0 +1,60 @@
+
+#include "util.h"
+#include "sysfs.h"
+
+static const char * const sysfs_known_mountpoints[] = {
+	"/sys",
+	0,
+};
+
+static int sysfs_found;
+char sysfs_mountpoint[PATH_MAX];
+
+static int sysfs_valid_mountpoint(const char *sysfs)
+{
+	struct statfs st_fs;
+
+	if (statfs(sysfs, &st_fs) < 0)
+		return -ENOENT;
+	else if (st_fs.f_type != (long) SYSFS_MAGIC)
+		return -ENOENT;
+
+	return 0;
+}
+
+const char *sysfs_find_mountpoint(void)
+{
+	const char * const *ptr;
+	char type[100];
+	FILE *fp;
+
+	if (sysfs_found)
+		return (const char *) sysfs_mountpoint;
+
+	ptr = sysfs_known_mountpoints;
+	while (*ptr) {
+		if (sysfs_valid_mountpoint(*ptr) == 0) {
+			sysfs_found = 1;
+			strcpy(sysfs_mountpoint, *ptr);
+			return sysfs_mountpoint;
+		}
+		ptr++;
+	}
+
+	/* give up and parse /proc/mounts */
+	fp = fopen("/proc/mounts", "r");
+	if (fp == NULL)
+		return NULL;
+
+	while (!sysfs_found &&
+	       fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n",
+		      sysfs_mountpoint, type) == 2) {
+
+		if (strcmp(type, "sysfs") == 0)
+			sysfs_found = 1;
+	}
+
+	fclose(fp);
+
+	return sysfs_found ? sysfs_mountpoint : NULL;
+}
diff --git a/tools/perf/util/sysfs.h b/tools/perf/util/sysfs.h
new file mode 100644
index 0000000..a813b72
--- /dev/null
+++ b/tools/perf/util/sysfs.h
@@ -0,0 +1,6 @@
+#ifndef __SYSFS_H__
+#define __SYSFS_H__
+
+const char *sysfs_find_mountpoint(void);
+
+#endif /* __DEBUGFS_H__ */
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index a5df131..84d9bd78 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -1,6 +1,13 @@
 #include <dirent.h>
+#include <limits.h>
+#include <stdbool.h>
 #include <stdlib.h>
 #include <stdio.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include "strlist.h"
+#include <string.h>
 #include "thread_map.h"
 
 /* Skip "." and ".." directories */
@@ -23,7 +30,7 @@
 	sprintf(name, "/proc/%d/task", pid);
 	items = scandir(name, &namelist, filter, NULL);
 	if (items <= 0)
-                return NULL;
+		return NULL;
 
 	threads = malloc(sizeof(*threads) + sizeof(pid_t) * items);
 	if (threads != NULL) {
@@ -51,14 +58,240 @@
 	return threads;
 }
 
-struct thread_map *thread_map__new(pid_t pid, pid_t tid)
+struct thread_map *thread_map__new_by_uid(uid_t uid)
+{
+	DIR *proc;
+	int max_threads = 32, items, i;
+	char path[256];
+	struct dirent dirent, *next, **namelist = NULL;
+	struct thread_map *threads = malloc(sizeof(*threads) +
+					    max_threads * sizeof(pid_t));
+	if (threads == NULL)
+		goto out;
+
+	proc = opendir("/proc");
+	if (proc == NULL)
+		goto out_free_threads;
+
+	threads->nr = 0;
+
+	while (!readdir_r(proc, &dirent, &next) && next) {
+		char *end;
+		bool grow = false;
+		struct stat st;
+		pid_t pid = strtol(dirent.d_name, &end, 10);
+
+		if (*end) /* only interested in proper numerical dirents */
+			continue;
+
+		snprintf(path, sizeof(path), "/proc/%s", dirent.d_name);
+
+		if (stat(path, &st) != 0)
+			continue;
+
+		if (st.st_uid != uid)
+			continue;
+
+		snprintf(path, sizeof(path), "/proc/%d/task", pid);
+		items = scandir(path, &namelist, filter, NULL);
+		if (items <= 0)
+			goto out_free_closedir;
+
+		while (threads->nr + items >= max_threads) {
+			max_threads *= 2;
+			grow = true;
+		}
+
+		if (grow) {
+			struct thread_map *tmp;
+
+			tmp = realloc(threads, (sizeof(*threads) +
+						max_threads * sizeof(pid_t)));
+			if (tmp == NULL)
+				goto out_free_namelist;
+
+			threads = tmp;
+		}
+
+		for (i = 0; i < items; i++)
+			threads->map[threads->nr + i] = atoi(namelist[i]->d_name);
+
+		for (i = 0; i < items; i++)
+			free(namelist[i]);
+		free(namelist);
+
+		threads->nr += items;
+	}
+
+out_closedir:
+	closedir(proc);
+out:
+	return threads;
+
+out_free_threads:
+	free(threads);
+	return NULL;
+
+out_free_namelist:
+	for (i = 0; i < items; i++)
+		free(namelist[i]);
+	free(namelist);
+
+out_free_closedir:
+	free(threads);
+	threads = NULL;
+	goto out_closedir;
+}
+
+struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid)
 {
 	if (pid != -1)
 		return thread_map__new_by_pid(pid);
+
+	if (tid == -1 && uid != UINT_MAX)
+		return thread_map__new_by_uid(uid);
+
 	return thread_map__new_by_tid(tid);
 }
 
+static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
+{
+	struct thread_map *threads = NULL, *nt;
+	char name[256];
+	int items, total_tasks = 0;
+	struct dirent **namelist = NULL;
+	int i, j = 0;
+	pid_t pid, prev_pid = INT_MAX;
+	char *end_ptr;
+	struct str_node *pos;
+	struct strlist *slist = strlist__new(false, pid_str);
+
+	if (!slist)
+		return NULL;
+
+	strlist__for_each(pos, slist) {
+		pid = strtol(pos->s, &end_ptr, 10);
+
+		if (pid == INT_MIN || pid == INT_MAX ||
+		    (*end_ptr != '\0' && *end_ptr != ','))
+			goto out_free_threads;
+
+		if (pid == prev_pid)
+			continue;
+
+		sprintf(name, "/proc/%d/task", pid);
+		items = scandir(name, &namelist, filter, NULL);
+		if (items <= 0)
+			goto out_free_threads;
+
+		total_tasks += items;
+		nt = realloc(threads, (sizeof(*threads) +
+				       sizeof(pid_t) * total_tasks));
+		if (nt == NULL)
+			goto out_free_threads;
+
+		threads = nt;
+
+		if (threads) {
+			for (i = 0; i < items; i++)
+				threads->map[j++] = atoi(namelist[i]->d_name);
+			threads->nr = total_tasks;
+		}
+
+		for (i = 0; i < items; i++)
+			free(namelist[i]);
+		free(namelist);
+
+		if (!threads)
+			break;
+	}
+
+out:
+	strlist__delete(slist);
+	return threads;
+
+out_free_threads:
+	free(threads);
+	threads = NULL;
+	goto out;
+}
+
+static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
+{
+	struct thread_map *threads = NULL, *nt;
+	int ntasks = 0;
+	pid_t tid, prev_tid = INT_MAX;
+	char *end_ptr;
+	struct str_node *pos;
+	struct strlist *slist;
+
+	/* perf-stat expects threads to be generated even if tid not given */
+	if (!tid_str) {
+		threads = malloc(sizeof(*threads) + sizeof(pid_t));
+		if (threads != NULL) {
+			threads->map[0] = -1;
+			threads->nr	= 1;
+		}
+		return threads;
+	}
+
+	slist = strlist__new(false, tid_str);
+	if (!slist)
+		return NULL;
+
+	strlist__for_each(pos, slist) {
+		tid = strtol(pos->s, &end_ptr, 10);
+
+		if (tid == INT_MIN || tid == INT_MAX ||
+		    (*end_ptr != '\0' && *end_ptr != ','))
+			goto out_free_threads;
+
+		if (tid == prev_tid)
+			continue;
+
+		ntasks++;
+		nt = realloc(threads, sizeof(*threads) + sizeof(pid_t) * ntasks);
+
+		if (nt == NULL)
+			goto out_free_threads;
+
+		threads = nt;
+		threads->map[ntasks - 1] = tid;
+		threads->nr		 = ntasks;
+	}
+out:
+	return threads;
+
+out_free_threads:
+	free(threads);
+	threads = NULL;
+	goto out;
+}
+
+struct thread_map *thread_map__new_str(const char *pid, const char *tid,
+				       uid_t uid)
+{
+	if (pid)
+		return thread_map__new_by_pid_str(pid);
+
+	if (!tid && uid != UINT_MAX)
+		return thread_map__new_by_uid(uid);
+
+	return thread_map__new_by_tid_str(tid);
+}
+
 void thread_map__delete(struct thread_map *threads)
 {
 	free(threads);
 }
+
+size_t thread_map__fprintf(struct thread_map *threads, FILE *fp)
+{
+	int i;
+	size_t printed = fprintf(fp, "%d thread%s: ",
+				 threads->nr, threads->nr > 1 ? "s" : "");
+	for (i = 0; i < threads->nr; ++i)
+		printed += fprintf(fp, "%s%d", i ? ", " : "", threads->map[i]);
+
+	return printed + fprintf(fp, "\n");
+}
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 3cb9073..7da80f1 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -2,6 +2,7 @@
 #define __PERF_THREAD_MAP_H
 
 #include <sys/types.h>
+#include <stdio.h>
 
 struct thread_map {
 	int nr;
@@ -10,6 +11,14 @@
 
 struct thread_map *thread_map__new_by_pid(pid_t pid);
 struct thread_map *thread_map__new_by_tid(pid_t tid);
-struct thread_map *thread_map__new(pid_t pid, pid_t tid);
+struct thread_map *thread_map__new_by_uid(uid_t uid);
+struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
+
+struct thread_map *thread_map__new_str(const char *pid,
+		const char *tid, uid_t uid);
+
 void thread_map__delete(struct thread_map *threads);
+
+size_t thread_map__fprintf(struct thread_map *threads, FILE *fp);
+
 #endif	/* __PERF_THREAD_MAP_H */
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index 500471d..09fe579 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -69,12 +69,15 @@
 
 	ret += SNPRINTF(bf + ret, size - ret, "], ");
 
-	if (top->target_pid != -1)
-		ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %d",
+	if (top->target_pid)
+		ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %s",
 				top->target_pid);
-	else if (top->target_tid != -1)
-		ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %d",
+	else if (top->target_tid)
+		ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %s",
 				top->target_tid);
+	else if (top->uid_str != NULL)
+		ret += SNPRINTF(bf + ret, size - ret, " (uid: %s",
+				top->uid_str);
 	else
 		ret += SNPRINTF(bf + ret, size - ret, " (all");
 
@@ -82,7 +85,7 @@
 		ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
 				top->evlist->cpus->nr > 1 ? "s" : "", top->cpu_list);
 	else {
-		if (top->target_tid != -1)
+		if (top->target_tid)
 			ret += SNPRINTF(bf + ret, size - ret, ")");
 		else
 			ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index f2eab81..ce61cb2 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -23,7 +23,8 @@
 	u64		   guest_us_samples, guest_kernel_samples;
 	int		   print_entries, count_filter, delay_secs;
 	int		   freq;
-	pid_t		   target_pid, target_tid;
+	const char	   *target_pid, *target_tid;
+	uid_t		   uid;
 	bool		   hide_kernel_symbols, hide_user_symbols, zero;
 	bool		   system_wide;
 	bool		   use_tui, use_stdio;
@@ -33,7 +34,7 @@
 	bool		   vmlinux_warned;
 	bool		   inherit;
 	bool		   group;
-	bool		   sample_id_all_avail;
+	bool		   sample_id_all_missing;
 	bool		   exclude_guest_missing;
 	bool		   dump_symtab;
 	const char	   *cpu_list;
@@ -46,6 +47,7 @@
 	int		   realtime_prio;
 	int		   sym_pcnt_filter;
 	const char	   *sym_filter;
+	const char	   *uid_str;
 };
 
 size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size);
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 1a8d4dc..a4088ce 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -25,7 +25,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <ctype.h>
 #include <errno.h>
 
 #include "../perf.h"
@@ -1424,6 +1423,11 @@
 				die("unknown op '%s'", arg->op.op);
 			}
 			break;
+		case '+':
+			left = arg_num_eval(arg->op.left);
+			right = arg_num_eval(arg->op.right);
+			val = left + right;
+			break;
 		default:
 			die("unknown op '%s'", arg->op.op);
 		}
@@ -1484,6 +1488,13 @@
 
 		free_token(token);
 		type = process_arg(event, arg, &token);
+
+		if (type == EVENT_OP)
+			type = process_op(event, arg, &token);
+
+		if (type == EVENT_ERROR)
+			goto out_free;
+
 		if (test_type_token(type, token, EVENT_DELIM, ","))
 			goto out_free;
 
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index f55cc3a..b9592e0 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -33,7 +33,6 @@
 #include <pthread.h>
 #include <fcntl.h>
 #include <unistd.h>
-#include <ctype.h>
 #include <errno.h>
 
 #include "../perf.h"
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index a3fdf55..18ae6c1 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -22,7 +22,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <ctype.h>
 #include <errno.h>
 
 #include "../perf.h"
diff --git a/tools/perf/util/ui/browser.h b/tools/perf/util/ui/browser.h
index 84d761b..6ee82f6 100644
--- a/tools/perf/util/ui/browser.h
+++ b/tools/perf/util/ui/browser.h
@@ -49,6 +49,8 @@
 			const char *format, ...);
 int ui_browser__help_window(struct ui_browser *browser, const char *text);
 bool ui_browser__dialog_yesno(struct ui_browser *browser, const char *text);
+int ui_browser__input_window(const char *title, const char *text, char *input,
+			     const char *exit_msg, int delay_sec);
 
 void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence);
 unsigned int ui_browser__argv_refresh(struct ui_browser *browser);
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index 295a9c9..57a4c6e 100644
--- a/tools/perf/util/ui/browsers/annotate.c
+++ b/tools/perf/util/ui/browsers/annotate.c
@@ -69,14 +69,17 @@
 	if (!self->navkeypressed)
 		width += 1;
 
+	if (!ab->hide_src_code && ol->offset != -1)
+		if (!current_entry || (self->use_navkeypressed &&
+				       !self->navkeypressed))
+			ui_browser__set_color(self, HE_COLORSET_CODE);
+
 	if (!*ol->line)
 		slsmg_write_nstring(" ", width - 18);
 	else
 		slsmg_write_nstring(ol->line, width - 18);
 
-	if (!current_entry)
-		ui_browser__set_color(self, HE_COLORSET_CODE);
-	else
+	if (current_entry)
 		ab->selection = ol;
 }
 
@@ -230,9 +233,9 @@
 	struct rb_node *nd = NULL;
 	struct map_symbol *ms = self->b.priv;
 	struct symbol *sym = ms->sym;
-	const char *help = "<-, ESC: exit, TAB/shift+TAB: cycle hottest lines, "
-			   "H: Hottest, -> Line action, S -> Toggle source "
-			   "code view";
+	const char *help = "<-/ESC: Exit, TAB/shift+TAB: Cycle hot lines, "
+			   "H: Go to hottest line, ->/ENTER: Line action, "
+			   "S: Toggle source code view";
 	int key;
 
 	if (ui_browser__show(&self->b, sym->name, help) < 0)
@@ -284,9 +287,11 @@
 				nd = self->curr_hot;
 			break;
 		case 'H':
+		case 'h':
 			nd = self->curr_hot;
 			break;
 		case 'S':
+		case 's':
 			if (annotate_browser__toggle_source(self))
 				ui_helpline__puts(help);
 			continue;
@@ -338,6 +343,7 @@
 				pthread_mutex_unlock(&notes->lock);
 				symbol__tui_annotate(target, ms->map, evidx,
 						     timer, arg, delay_secs);
+				ui_browser__show_title(&self->b, sym->name);
 			}
 			continue;
 		case K_LEFT:
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index bb9197c..d7a1c4a 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -805,8 +805,11 @@
 		self->hists = hists;
 		self->b.refresh = hist_browser__refresh;
 		self->b.seek = ui_browser__hists_seek;
-		self->b.use_navkeypressed = true,
-		self->has_symbols = sort_sym.list.next != NULL;
+		self->b.use_navkeypressed = true;
+		if (sort__branch_mode == 1)
+			self->has_symbols = sort_sym_from.list.next != NULL;
+		else
+			self->has_symbols = sort_sym.list.next != NULL;
 	}
 
 	return self;
@@ -839,6 +842,9 @@
 	nr_events = convert_unit(nr_events, &unit);
 	printed = scnprintf(bf, size, "Events: %lu%c %s", nr_events, unit, ev_name);
 
+	if (self->uid_filter_str)
+		printed += snprintf(bf + printed, size - printed,
+				    ", UID: %s", self->uid_filter_str);
 	if (thread)
 		printed += scnprintf(bf + printed, size - printed,
 				    ", Thread: %s(%d)",
@@ -850,6 +856,16 @@
 	return printed;
 }
 
+static inline void free_popup_options(char **options, int n)
+{
+	int i;
+
+	for (i = 0; i < n; ++i) {
+		free(options[i]);
+		options[i] = NULL;
+	}
+}
+
 static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 				    const char *helpline, const char *ev_name,
 				    bool left_exits,
@@ -858,8 +874,12 @@
 {
 	struct hists *self = &evsel->hists;
 	struct hist_browser *browser = hist_browser__new(self);
+	struct branch_info *bi;
 	struct pstack *fstack;
+	char *options[16];
+	int nr_options = 0;
 	int key = -1;
+	char buf[64];
 
 	if (browser == NULL)
 		return -1;
@@ -870,13 +890,16 @@
 
 	ui_helpline__push(helpline);
 
+	memset(options, 0, sizeof(options));
+
 	while (1) {
 		const struct thread *thread = NULL;
 		const struct dso *dso = NULL;
-		char *options[16];
-		int nr_options = 0, choice = 0, i,
+		int choice = 0,
 		    annotate = -2, zoom_dso = -2, zoom_thread = -2,
-		    browse_map = -2;
+		    annotate_f = -2, annotate_t = -2, browse_map = -2;
+
+		nr_options = 0;
 
 		key = hist_browser__run(browser, ev_name, timer, arg, delay_secs);
 
@@ -884,7 +907,6 @@
 			thread = hist_browser__selected_thread(browser);
 			dso = browser->selection->map ? browser->selection->map->dso : NULL;
 		}
-
 		switch (key) {
 		case K_TAB:
 		case K_UNTAB:
@@ -899,7 +921,7 @@
 			if (!browser->has_symbols) {
 				ui_browser__warning(&browser->b, delay_secs * 2,
 			"Annotation is only available for symbolic views, "
-			"include \"sym\" in --sort to use it.");
+			"include \"sym*\" in --sort to use it.");
 				continue;
 			}
 
@@ -912,6 +934,16 @@
 			goto zoom_dso;
 		case 't':
 			goto zoom_thread;
+		case 's':
+			if (ui_browser__input_window("Symbol to show",
+					"Please enter the name of symbol you want to see",
+					buf, "ENTER: OK, ESC: Cancel",
+					delay_secs * 2) == K_ENTER) {
+				self->symbol_filter_str = *buf ? buf : NULL;
+				hists__filter_by_symbol(self);
+				hist_browser__reset(browser);
+			}
+			continue;
 		case K_F1:
 		case 'h':
 		case '?':
@@ -929,7 +961,8 @@
 					"C             Collapse all callchains\n"
 					"E             Expand all callchains\n"
 					"d             Zoom into current DSO\n"
-					"t             Zoom into current Thread");
+					"t             Zoom into current Thread\n"
+					"s             Filter symbol by name");
 			continue;
 		case K_ENTER:
 		case K_RIGHT:
@@ -969,12 +1002,34 @@
 		if (!browser->has_symbols)
 			goto add_exit_option;
 
-		if (browser->selection != NULL &&
-		    browser->selection->sym != NULL &&
-		    !browser->selection->map->dso->annotate_warned &&
-		    asprintf(&options[nr_options], "Annotate %s",
-			     browser->selection->sym->name) > 0)
-			annotate = nr_options++;
+		if (sort__branch_mode == 1) {
+			bi = browser->he_selection->branch_info;
+			if (browser->selection != NULL &&
+			    bi &&
+			    bi->from.sym != NULL &&
+			    !bi->from.map->dso->annotate_warned &&
+				asprintf(&options[nr_options], "Annotate %s",
+					 bi->from.sym->name) > 0)
+				annotate_f = nr_options++;
+
+			if (browser->selection != NULL &&
+			    bi &&
+			    bi->to.sym != NULL &&
+			    !bi->to.map->dso->annotate_warned &&
+			    (bi->to.sym != bi->from.sym ||
+			     bi->to.map->dso != bi->from.map->dso) &&
+				asprintf(&options[nr_options], "Annotate %s",
+					 bi->to.sym->name) > 0)
+				annotate_t = nr_options++;
+		} else {
+
+			if (browser->selection != NULL &&
+			    browser->selection->sym != NULL &&
+			    !browser->selection->map->dso->annotate_warned &&
+				asprintf(&options[nr_options], "Annotate %s",
+					 browser->selection->sym->name) > 0)
+				annotate = nr_options++;
+		}
 
 		if (thread != NULL &&
 		    asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
@@ -995,25 +1050,39 @@
 			browse_map = nr_options++;
 add_exit_option:
 		options[nr_options++] = (char *)"Exit";
-
+retry_popup_menu:
 		choice = ui__popup_menu(nr_options, options);
 
-		for (i = 0; i < nr_options - 1; ++i)
-			free(options[i]);
-
 		if (choice == nr_options - 1)
 			break;
 
-		if (choice == -1)
+		if (choice == -1) {
+			free_popup_options(options, nr_options - 1);
 			continue;
+		}
 
-		if (choice == annotate) {
+		if (choice == annotate || choice == annotate_t || choice == annotate_f) {
 			struct hist_entry *he;
 			int err;
 do_annotate:
 			he = hist_browser__selected_entry(browser);
 			if (he == NULL)
 				continue;
+
+			/*
+			 * we stash the branch_info symbol + map into the
+			 * the ms so we don't have to rewrite all the annotation
+			 * code to use branch_info.
+			 * in branch mode, the ms struct is not used
+			 */
+			if (choice == annotate_f) {
+				he->ms.sym = he->branch_info->from.sym;
+				he->ms.map = he->branch_info->from.map;
+			}  else if (choice == annotate_t) {
+				he->ms.sym = he->branch_info->to.sym;
+				he->ms.map = he->branch_info->to.map;
+			}
+
 			/*
 			 * Don't let this be freed, say, by hists__decay_entry.
 			 */
@@ -1021,9 +1090,18 @@
 			err = hist_entry__tui_annotate(he, evsel->idx,
 						       timer, arg, delay_secs);
 			he->used = false;
+			/*
+			 * offer option to annotate the other branch source or target
+			 * (if they exists) when returning from annotate
+			 */
+			if ((err == 'q' || err == CTRL('c'))
+			    && annotate_t != -2 && annotate_f != -2)
+				goto retry_popup_menu;
+
 			ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
 			if (err)
 				ui_browser__handle_resize(&browser->b);
+
 		} else if (choice == browse_map)
 			map__browse(browser->selection->map);
 		else if (choice == zoom_dso) {
@@ -1069,6 +1147,7 @@
 	pstack__delete(fstack);
 out:
 	hist_browser__delete(browser);
+	free_popup_options(options, nr_options - 1);
 	return key;
 }
 
diff --git a/tools/perf/util/ui/browsers/map.c b/tools/perf/util/ui/browsers/map.c
index 6905bcc..eca6575 100644
--- a/tools/perf/util/ui/browsers/map.c
+++ b/tools/perf/util/ui/browsers/map.c
@@ -3,9 +3,9 @@
 #include <newt.h>
 #include <inttypes.h>
 #include <sys/ttydefaults.h>
-#include <ctype.h>
 #include <string.h>
 #include <linux/bitops.h>
+#include "../../util.h"
 #include "../../debug.h"
 #include "../../symbol.h"
 #include "../browser.h"
diff --git a/tools/perf/util/ui/keysyms.h b/tools/perf/util/ui/keysyms.h
index 3458b19..809eca5 100644
--- a/tools/perf/util/ui/keysyms.h
+++ b/tools/perf/util/ui/keysyms.h
@@ -16,6 +16,8 @@
 #define K_TAB	'\t'
 #define K_UNTAB	SL_KEY_UNTAB
 #define K_UP	SL_KEY_UP
+#define K_BKSPC 0x7f
+#define K_DEL	SL_KEY_DELETE
 
 /* Not really keys */
 #define K_TIMER	 -1
diff --git a/tools/perf/util/ui/util.c b/tools/perf/util/ui/util.c
index 45daa7c..ad4374a 100644
--- a/tools/perf/util/ui/util.c
+++ b/tools/perf/util/ui/util.c
@@ -69,6 +69,88 @@
 	return popup_menu__run(&menu);
 }
 
+int ui_browser__input_window(const char *title, const char *text, char *input,
+			     const char *exit_msg, int delay_secs)
+{
+	int x, y, len, key;
+	int max_len = 60, nr_lines = 0;
+	static char buf[50];
+	const char *t;
+
+	t = text;
+	while (1) {
+		const char *sep = strchr(t, '\n');
+
+		if (sep == NULL)
+			sep = strchr(t, '\0');
+		len = sep - t;
+		if (max_len < len)
+			max_len = len;
+		++nr_lines;
+		if (*sep == '\0')
+			break;
+		t = sep + 1;
+	}
+
+	max_len += 2;
+	nr_lines += 8;
+	y = SLtt_Screen_Rows / 2 - nr_lines / 2;
+	x = SLtt_Screen_Cols / 2 - max_len / 2;
+
+	SLsmg_set_color(0);
+	SLsmg_draw_box(y, x++, nr_lines, max_len);
+	if (title) {
+		SLsmg_gotorc(y, x + 1);
+		SLsmg_write_string((char *)title);
+	}
+	SLsmg_gotorc(++y, x);
+	nr_lines -= 7;
+	max_len -= 2;
+	SLsmg_write_wrapped_string((unsigned char *)text, y, x,
+				   nr_lines, max_len, 1);
+	y += nr_lines;
+	len = 5;
+	while (len--) {
+		SLsmg_gotorc(y + len - 1, x);
+		SLsmg_write_nstring((char *)" ", max_len);
+	}
+	SLsmg_draw_box(y++, x + 1, 3, max_len - 2);
+
+	SLsmg_gotorc(y + 3, x);
+	SLsmg_write_nstring((char *)exit_msg, max_len);
+	SLsmg_refresh();
+
+	x += 2;
+	len = 0;
+	key = ui__getch(delay_secs);
+	while (key != K_TIMER && key != K_ENTER && key != K_ESC) {
+		if (key == K_BKSPC) {
+			if (len == 0)
+				goto next_key;
+			SLsmg_gotorc(y, x + --len);
+			SLsmg_write_char(' ');
+		} else {
+			buf[len] = key;
+			SLsmg_gotorc(y, x + len++);
+			SLsmg_write_char(key);
+		}
+		SLsmg_refresh();
+
+		/* XXX more graceful overflow handling needed */
+		if (len == sizeof(buf) - 1) {
+			ui_helpline__push("maximum size of symbol name reached!");
+			key = K_ENTER;
+			break;
+		}
+next_key:
+		key = ui__getch(delay_secs);
+	}
+
+	buf[len] = '\0';
+	strncpy(input, buf, len+1);
+	return key;
+}
+
 int ui__question_window(const char *title, const char *text,
 			const char *exit_msg, int delay_secs)
 {
diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c
index d76d1c0..52bb07c 100644
--- a/tools/perf/util/usage.c
+++ b/tools/perf/util/usage.c
@@ -7,6 +7,7 @@
  * Copyright (C) Linus Torvalds, 2005
  */
 #include "util.h"
+#include "debug.h"
 
 static void report(const char *prefix, const char *err, va_list params)
 {
@@ -81,3 +82,41 @@
 	warn_routine(warn, params);
 	va_end(params);
 }
+
+uid_t parse_target_uid(const char *str, const char *tid, const char *pid)
+{
+	struct passwd pwd, *result;
+	char buf[1024];
+
+	if (str == NULL)
+		return UINT_MAX;
+
+	/* UID and PID are mutually exclusive */
+	if (tid || pid) {
+		ui__warning("PID/TID switch overriding UID\n");
+		sleep(1);
+		return UINT_MAX;
+	}
+
+	getpwnam_r(str, &pwd, buf, sizeof(buf), &result);
+
+	if (result == NULL) {
+		char *endptr;
+		int uid = strtol(str, &endptr, 10);
+
+		if (*endptr != '\0') {
+			ui__error("Invalid user %s\n", str);
+			return UINT_MAX - 1;
+		}
+
+		getpwuid_r(uid, &pwd, buf, sizeof(buf), &result);
+
+		if (result == NULL) {
+			ui__error("Problems obtaining information for user %s\n",
+				  str);
+			return UINT_MAX - 1;
+		}
+	}
+
+	return result->pw_uid;
+}
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index fb25d13..8109a90 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -14,6 +14,8 @@
 		attr->exclude_host  = 1;
 	if (!perf_guest)
 		attr->exclude_guest = 1;
+	/* to capture ABI version */
+	attr->size = sizeof(*attr);
 }
 
 int mkdir_p(char *path, mode_t mode)
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index ecf9898..0f99f39 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -199,6 +199,8 @@
 #undef isalpha
 #undef isprint
 #undef isalnum
+#undef islower
+#undef isupper
 #undef tolower
 #undef toupper
 
@@ -219,6 +221,8 @@
 #define isalpha(x) sane_istest(x,GIT_ALPHA)
 #define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT)
 #define isprint(x) sane_istest(x,GIT_PRINT)
+#define islower(x) (sane_istest(x,GIT_ALPHA) && sane_istest(x,0x20))
+#define isupper(x) (sane_istest(x,GIT_ALPHA) && !sane_istest(x,0x20))
 #define tolower(x) sane_case((unsigned char)(x), 0x20)
 #define toupper(x) sane_case((unsigned char)(x), 0)
 
@@ -245,6 +249,8 @@
 
 void event_attr_init(struct perf_event_attr *attr);
 
+uid_t parse_target_uid(const char *str, const char *tid, const char *pid);
+
 #define _STR(x) #x
 #define STR(x) _STR(x)