Merge remote branch 'tip/auto-latest'

214 files changed, 8784 insertions, 7823 deletions

diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index b4f3fb4279e6..c8437351cc2e 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -565,6 +565,16 @@ Who:	Avi Kivity <avi@redhat.com>
 
 ----------------------------
 
+What:	xtime, wall_to_monotonic
+When:	2.6.36+
+Files:	kernel/time/timekeeping.c include/linux/time.h
+Why:	Cleaning up timekeeping internal values. Please use
+	existing timekeeping accessor functions to access
+	the equivalent functionality.
+Who:	John Stultz <johnstul@us.ibm.com>
+
+----------------------------
+
 What:	KVM kernel-allocated memory slots
 When:	July 2010
 Why:	Since 2.6.25, kvm supports user-allocated memory slots, which are
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 770700317c2c..a4a2327f5c87 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -566,6 +566,10 @@ The default_smp_affinity mask applies to all non-active IRQs, which are the
 IRQs which have not yet been allocated/activated, and hence which lack a
 /proc/irq/[0-9]* directory.
 
+The node file on an SMP system shows the node to which the device using the IRQ
+reports itself as being attached. This hardware locality information does not
+include information about any possible driver locality preference.
+
 prof_cpu_mask specifies which CPUs are to be profiled by the system wide
 profiler. Default value is ffffffff (all cpus).
 
diff --git a/Documentation/intel_txt.txt b/Documentation/intel_txt.txt
index f40a1f030019..87c8990dbbd9 100644
--- a/Documentation/intel_txt.txt
+++ b/Documentation/intel_txt.txt
@@ -161,13 +161,15 @@ o  In order to put a system into any of the sleep states after a TXT
       has been restored, it will restore the TPM PCRs and then
       transfer control back to the kernel's S3 resume vector.
       In order to preserve system integrity across S3, the kernel
-      provides tboot with a set of memory ranges (kernel
-      code/data/bss, S3 resume code, and AP trampoline) that tboot
-      will calculate a MAC (message authentication code) over and then
-      seal with the TPM.  On resume and once the measured environment
-      has been re-established, tboot will re-calculate the MAC and
-      verify it against the sealed value.  Tboot's policy determines
-      what happens if the verification fails.
+      provides tboot with a set of memory ranges (RAM and RESERVED_KERN
+      in the e820 table, but not any memory that BIOS might alter over
+      the S3 transition) that tboot will calculate a MAC (message
+      authentication code) over and then seal with the TPM. On resume
+      and once the measured environment has been re-established, tboot
+      will re-calculate the MAC and verify it against the sealed value.
+      Tboot's policy determines what happens if the verification fails.
+      Note that the c/s 194 of tboot which has the new MAC code supports
+      this.
 
 That's pretty much it for TXT support.
 
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 2f9115c0ae62..61c291cddf18 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -165,8 +165,8 @@ the user entry_handler invocation is also skipped.
 
 1.4 How Does Jump Optimization Work?
 
-If you configured your kernel with CONFIG_OPTPROBES=y (currently
-this option is supported on x86/x86-64, non-preemptive kernel) and
+If your kernel is built with CONFIG_OPTPROBES=y (currently this flag
+is automatically set 'y' on x86/x86-64, non-preemptive kernel) and
 the "debug.kprobes_optimization" kernel parameter is set to 1 (see
 sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump
 instruction instead of a breakpoint instruction at each probepoint.
@@ -271,8 +271,6 @@ tweak the kernel's execution path, you need to suppress optimization,
 using one of the following techniques:
 - Specify an empty function for the kprobe's post_handler or break_handler.
  or
-- Config CONFIG_OPTPROBES=n.
- or
 - Execute 'sysctl -w debug.kprobes_optimization=n'
 
 2. Architectures Supported
@@ -307,10 +305,6 @@ it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO),
 so you can use "objdump -d -l vmlinux" to see the source-to-object
 code mapping.
 
-If you want to reduce probing overhead, set "Kprobes jump optimization
-support" (CONFIG_OPTPROBES) to "y". You can find this option under the
-"Kprobes" line.
-
 4. API Reference
 
 The Kprobes API includes a "register" function and an "unregister"
diff --git a/Documentation/rbtree.txt b/Documentation/rbtree.txt
index aae8355d3166..221f38be98f4 100644
--- a/Documentation/rbtree.txt
+++ b/Documentation/rbtree.txt
@@ -190,3 +190,61 @@ Example:
   for (node = rb_first(&mytree); node; node = rb_next(node))
 	printk("key=%s\n", rb_entry(node, struct mytype, node)->keystring);
 
+Support for Augmented rbtrees
+-----------------------------
+
+Augmented rbtree is an rbtree with "some" additional data stored in each node.
+This data can be used to augment some new functionality to rbtree.
+Augmented rbtree is an optional feature built on top of basic rbtree
+infrastructure. rbtree user who wants this feature will have an augment
+callback function in rb_root initialized.
+
+This callback function will be called from rbtree core routines whenever
+a node has a change in one or both of its children. It is the responsibility
+of the callback function to recalculate the additional data that is in the
+rb node using new children information. Note that if this new additional
+data affects the parent node's additional data, then callback function has
+to handle it and do the recursive updates.
+
+
+Interval tree is an example of augmented rb tree. Reference -
+"Introduction to Algorithms" by Cormen, Leiserson, Rivest and Stein.
+More details about interval trees:
+
+Classical rbtree has a single key and it cannot be directly used to store
+interval ranges like [lo:hi] and do a quick lookup for any overlap with a new
+lo:hi or to find whether there is an exact match for a new lo:hi.
+
+However, rbtree can be augmented to store such interval ranges in a structured
+way making it possible to do efficient lookup and exact match.
+
+This "extra information" stored in each node is the maximum hi
+(max_hi) value among all the nodes that are its descendents. This
+information can be maintained at each node just be looking at the node
+and its immediate children. And this will be used in O(log n) lookup
+for lowest match (lowest start address among all possible matches)
+with something like:
+
+find_lowest_match(lo, hi, node)
+{
+	lowest_match = NULL;
+	while (node) {
+		if (max_hi(node->left) > lo) {
+			// Lowest overlap if any must be on left side
+			node = node->left;
+		} else if (overlap(lo, hi, node)) {
+			lowest_match = node;
+			break;
+		} else if (lo > node->lo) {
+			// Lowest overlap if any must be on right side
+			node = node->right;
+		} else {
+			break;
+		}
+	}
+	return lowest_match;
+}
+
+Finding exact match will be to first find lowest match and then to follow
+successor nodes looking for exact match, until the start of a node is beyond
+the hi value we are looking for.
diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt
index 6f33593e59e2..8239ebbcddce 100644
--- a/Documentation/scheduler/sched-design-CFS.txt
+++ b/Documentation/scheduler/sched-design-CFS.txt
@@ -211,7 +211,7 @@ provide fair CPU time to each such task group.  For example, it may be
 desirable to first provide fair CPU time to each user on the system and then to
 each task belonging to a user.
 
-CONFIG_GROUP_SCHED strives to achieve exactly that.  It lets tasks to be
+CONFIG_CGROUP_SCHED strives to achieve exactly that.  It lets tasks to be
 grouped and divides CPU time fairly among such groups.
 
 CONFIG_RT_GROUP_SCHED permits to group real-time (i.e., SCHED_FIFO and
@@ -220,38 +220,11 @@ SCHED_RR) tasks.
 CONFIG_FAIR_GROUP_SCHED permits to group CFS (i.e., SCHED_NORMAL and
 SCHED_BATCH) tasks.
 
-At present, there are two (mutually exclusive) mechanisms to group tasks for
-CPU bandwidth control purposes:
-
- - Based on user id (CONFIG_USER_SCHED)
-
-   With this option, tasks are grouped according to their user id.
-
- - Based on "cgroup" pseudo filesystem (CONFIG_CGROUP_SCHED)
-
-   This options needs CONFIG_CGROUPS to be defined, and lets the administrator
+   These options need CONFIG_CGROUPS to be defined, and let the administrator
    create arbitrary groups of tasks, using the "cgroup" pseudo filesystem.  See
    Documentation/cgroups/cgroups.txt for more information about this filesystem.
 
-Only one of these options to group tasks can be chosen and not both.
-
-When CONFIG_USER_SCHED is defined, a directory is created in sysfs for each new
-user and a "cpu_share" file is added in that directory.
-
-	# cd /sys/kernel/uids
-	# cat 512/cpu_share		# Display user 512's CPU share
-	1024
-	# echo 2048 > 512/cpu_share	# Modify user 512's CPU share
-	# cat 512/cpu_share		# Display user 512's CPU share
-	2048
-	#
-
-CPU bandwidth between two users is divided in the ratio of their CPU shares.
-For example: if you would like user "root" to get twice the bandwidth of user
-"guest," then set the cpu_share for both the users such that "root"'s cpu_share
-is twice "guest"'s cpu_share.
-
-When CONFIG_CGROUP_SCHED is defined, a "cpu.shares" file is created for each
+When CONFIG_FAIR_GROUP_SCHED is defined, a "cpu.shares" file is created for each
 group created using the pseudo filesystem.  See example steps below to create
 task groups and modify their CPU share using the "cgroups" pseudo filesystem.
 
@@ -273,24 +246,3 @@ task groups and modify their CPU share using the "cgroups" pseudo filesystem.
 
 	# #Launch gmplayer (or your favourite movie player)
 	# echo <movie_player_pid> > multimedia/tasks
-
-8. Implementation note: user namespaces
-
-User namespaces are intended to be hierarchical.  But they are currently
-only partially implemented.  Each of those has ramifications for CFS.
-
-First, since user namespaces are hierarchical, the /sys/kernel/uids
-presentation is inadequate.  Eventually we will likely want to use sysfs
-tagging to provide private views of /sys/kernel/uids within each user
-namespace.
-
-Second, the hierarchical nature is intended to support completely
-unprivileged use of user namespaces.  So if using user groups, then
-we want the users in a user namespace to be children of the user
-who created it.
-
-That is currently unimplemented.  So instead, every user in a new
-user namespace will receive 1024 shares just like any user in the
-initial user namespace.  Note that at the moment creation of a new
-user namespace requires each of CAP_SYS_ADMIN, CAP_SETUID, and
-CAP_SETGID.
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 86eabe6c3419..605b0d40329d 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -126,23 +126,12 @@ priority!
 2.3 Basis for grouping tasks
 ----------------------------
 
-There are two compile-time settings for allocating CPU bandwidth. These are
-configured using the "Basis for grouping tasks" multiple choice menu under
-General setup > Group CPU Scheduler:
-
-a. CONFIG_USER_SCHED (aka "Basis for grouping tasks" =  "user id")
-
-This lets you use the virtual files under
-"/sys/kernel/uids/<uid>/cpu_rt_runtime_us" to control he CPU time reserved for
-each user .
-
-The other option is:
-
-.o CONFIG_CGROUP_SCHED (aka "Basis for grouping tasks" = "Control groups")
+Enabling CONFIG_RT_GROUP_SCHED lets you explicitly allocate real
+CPU bandwidth to task groups.
 
 This uses the /cgroup virtual file system and
 "/cgroup/<cgroup>/cpu.rt_runtime_us" to control the CPU time reserved for each
-control group instead.
+control group.
 
 For more information on working with control groups, you should read
 Documentation/cgroups/cgroups.txt as well.
@@ -161,8 +150,7 @@ For now, this can be simplified to just the following (but see Future plans):
 ===============
 
 There is work in progress to make the scheduling period for each group
-("/sys/kernel/uids/<uid>/cpu_rt_period_us" or
-"/cgroup/<cgroup>/cpu.rt_period_us" respectively) configurable as well.
+("/cgroup/<cgroup>/cpu.rt_period_us") configurable as well.
 
 The constraint on the period is that a subgroup must have a smaller or
 equal period to its parent. But realistically its not very useful _yet_
diff --git a/MAINTAINERS b/MAINTAINERS
index 4fd4efd20c7c..7cd29885337c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2945,6 +2945,17 @@ S:	Odd Fixes
 F:	Documentation/networking/README.ipw2200
 F:	drivers/net/wireless/ipw2x00/ipw2200.*
 
+INTEL(R) TRUSTED EXECUTION TECHNOLOGY (TXT)
+M:	Joseph Cihula <joseph.cihula@intel.com>
+M:	Shane Wang <shane.wang@intel.com>
+L:	tboot-devel@lists.sourceforge.net
+W:	http://tboot.sourceforge.net
+T:	Mercurial http://www.bughost.org/repos.hg/tboot.hg
+S:	Supported
+F:	Documentation/intel_txt.txt
+F:	include/linux/tboot.h
+F:	arch/x86/kernel/tboot.c
+
 INTEL WIRELESS WIMAX CONNECTION 2400
 M:	Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
 M:	linux-wimax@intel.com
@@ -4354,13 +4365,13 @@ M:	Paul Mackerras <paulus@samba.org>
 M:	Ingo Molnar <mingo@elte.hu>
 M:	Arnaldo Carvalho de Melo <acme@redhat.com>
 S:	Supported
-F:	kernel/perf_event.c
+F:	kernel/perf_event*.c
 F:	include/linux/perf_event.h
-F:	arch/*/kernel/perf_event.c
-F:	arch/*/kernel/*/perf_event.c
-F:	arch/*/kernel/*/*/perf_event.c
+F:	arch/*/kernel/perf_event*.c
+F:	arch/*/kernel/*/perf_event*.c
+F:	arch/*/kernel/*/*/perf_event*.c
 F:	arch/*/include/asm/perf_event.h
-F:	arch/*/lib/perf_event.c
+F:	arch/*/lib/perf_event*.c
 F:	arch/*/kernel/perf_callchain.c
 F:	tools/perf/
 
diff --git a/arch/Kconfig b/arch/Kconfig
index e5eb1337a537..f06010fb4838 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -42,15 +42,10 @@ config KPROBES
 	  If in doubt, say "N".
 
 config OPTPROBES
-	bool "Kprobes jump optimization support (EXPERIMENTAL)"
-	default y
-	depends on KPROBES
+	def_bool y
+	depends on KPROBES && HAVE_OPTPROBES
 	depends on !PREEMPT
-	depends on HAVE_OPTPROBES
 	select KALLSYMS_ALL
-	help
-	  This option will allow kprobes to optimize breakpoint to
-	  a jump for reducing its overhead.
 
 config HAVE_EFFICIENT_UNALIGNED_ACCESS
 	bool
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 75291fdd379f..b7193986cbf9 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -55,6 +55,9 @@ config ARCH_USES_GETTIMEOFFSET
 	bool
 	default y
 
+config GENERIC_CMOS_UPDATE
+        def_bool y
+
 config ZONE_DMA
 	bool
 	default y
diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c
index 5d0826654c61..5465e932e568 100644
--- a/arch/alpha/kernel/time.c
+++ b/arch/alpha/kernel/time.c
@@ -75,8 +75,6 @@ static struct {
 	__u32 last_time;
 	/* ticks/cycle * 2^48 */
 	unsigned long scaled_ticks_per_cycle;
-	/* last time the CMOS clock got updated */
-	time_t last_rtc_update;
 	/* partial unused tick */
 	unsigned long partial_tick;
 } state;
@@ -91,6 +89,52 @@ static inline __u32 rpcc(void)
     return result;
 }
 
+int update_persistent_clock(struct timespec now)
+{
+	return set_rtc_mmss(now.tv_sec);
+}
+
+void read_persistent_clock(struct timespec *ts)
+{
+	unsigned int year, mon, day, hour, min, sec, epoch;
+
+	sec = CMOS_READ(RTC_SECONDS);
+	min = CMOS_READ(RTC_MINUTES);
+	hour = CMOS_READ(RTC_HOURS);
+	day = CMOS_READ(RTC_DAY_OF_MONTH);
+	mon = CMOS_READ(RTC_MONTH);
+	year = CMOS_READ(RTC_YEAR);
+
+	if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
+		sec = bcd2bin(sec);
+		min = bcd2bin(min);
+		hour = bcd2bin(hour);
+		day = bcd2bin(day);
+		mon = bcd2bin(mon);
+		year = bcd2bin(year);
+	}
+
+	/* PC-like is standard; used for year >= 70 */
+	epoch = 1900;
+	if (year < 20)
+		epoch = 2000;
+	else if (year >= 20 && year < 48)
+		/* NT epoch */
+		epoch = 1980;
+	else if (year >= 48 && year < 70)
+		/* Digital UNIX epoch */
+		epoch = 1952;
+
+	printk(KERN_INFO "Using epoch = %d\n", epoch);
+
+	if ((year += epoch) < 1970)
+		year += 100;
+
+	ts->tv_sec = mktime(year, mon, day, hour, min, sec);
+}
+
+
+
 /*
  * timer_interrupt() needs to keep up the real-time clock,
  * as well as call the "do_timer()" routine every clocktick
@@ -123,19 +167,6 @@ irqreturn_t timer_interrupt(int irq, void *dev)
 	if (nticks)
 		do_timer(nticks);
 
-	/*
-	 * If we have an externally synchronized Linux clock, then update
-	 * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be
-	 * called as close as possible to 500 ms before the new second starts.
-	 */
-	if (ntp_synced()
-	    && xtime.tv_sec > state.last_rtc_update + 660
-	    && xtime.tv_nsec >= 500000 - ((unsigned) TICK_SIZE) / 2
-	    && xtime.tv_nsec <= 500000 + ((unsigned) TICK_SIZE) / 2) {
-		int tmp = set_rtc_mmss(xtime.tv_sec);
-		state.last_rtc_update = xtime.tv_sec - (tmp ? 600 : 0);
-	}
-
 	write_sequnlock(&xtime_lock);
 
 #ifndef CONFIG_SMP
@@ -304,7 +335,7 @@ rpcc_after_update_in_progress(void)
 void __init
 time_init(void)
 {
-	unsigned int year, mon, day, hour, min, sec, cc1, cc2, epoch;
+	unsigned int cc1, cc2;
 	unsigned long cycle_freq, tolerance;
 	long diff;
 
@@ -348,43 +379,6 @@ time_init(void)
 	   bogomips yet, but this is close on a 500Mhz box.  */
 	__delay(1000000);
 
-	sec = CMOS_READ(RTC_SECONDS);
-	min = CMOS_READ(RTC_MINUTES);
-	hour = CMOS_READ(RTC_HOURS);
-	day = CMOS_READ(RTC_DAY_OF_MONTH);
-	mon = CMOS_READ(RTC_MONTH);
-	year = CMOS_READ(RTC_YEAR);
-
-	if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-		sec = bcd2bin(sec);
-		min = bcd2bin(min);
-		hour = bcd2bin(hour);
-		day = bcd2bin(day);
-		mon = bcd2bin(mon);
-		year = bcd2bin(year);
-	}
-
-	/* PC-like is standard; used for year >= 70 */
-	epoch = 1900;
-	if (year < 20)
-		epoch = 2000;
-	else if (year >= 20 && year < 48)
-		/* NT epoch */
-		epoch = 1980;
-	else if (year >= 48 && year < 70)
-		/* Digital UNIX epoch */
-		epoch = 1952;
-
-	printk(KERN_INFO "Using epoch = %d\n", epoch);
-
-	if ((year += epoch) < 1970)
-		year += 100;
-
-	xtime.tv_sec = mktime(year, mon, day, hour, min, sec);
-	xtime.tv_nsec = 0;
-
-        wall_to_monotonic.tv_sec -= xtime.tv_sec;
-        wall_to_monotonic.tv_nsec = 0;
 
 	if (HZ > (1<<16)) {
 		extern void __you_loose (void);
@@ -394,7 +388,6 @@ time_init(void)
 	state.last_time = cc1;
 	state.scaled_ticks_per_cycle
 		= ((unsigned long) HZ << FIX_SHIFT) / cycle_freq;
-	state.last_rtc_update = 0;
 	state.partial_tick = 0L;
 
 	/* Startup the timer source. */
diff --git a/arch/avr32/kernel/time.c b/arch/avr32/kernel/time.c
index f27aa3b259fa..a047d69d17e2 100644
--- a/arch/avr32/kernel/time.c
+++ b/arch/avr32/kernel/time.c
@@ -110,17 +110,17 @@ static struct clock_event_device comparator = {
 	.set_mode	= comparator_mode,
 };
 
+void read_persistent_clock(struct timespec *ts)
+{
+	ts->tv.sec = mktime(2007, 1, 1, 0, 0, 0);
+	ts->tv_nsec = 0;
+}
+
 void __init time_init(void)
 {
 	unsigned long counter_hz;
 	int ret;
 
-	xtime.tv_sec = mktime(2007, 1, 1, 0, 0, 0);
-	xtime.tv_nsec = 0;
-
-	set_normalized_timespec(&wall_to_monotonic,
-				-xtime.tv_sec, -xtime.tv_nsec);
-
 	/* figure rate for counter */
 	counter_hz = clk_get_rate(boot_cpu_data.clk);
 	counter.mult = clocksource_hz2mult(counter_hz, counter.shift);
diff --git a/arch/blackfin/kernel/time-ts.c b/arch/blackfin/kernel/time-ts.c
index cb7a01d4f009..8c9a43daf80f 100644
--- a/arch/blackfin/kernel/time-ts.c
+++ b/arch/blackfin/kernel/time-ts.c
@@ -353,9 +353,15 @@ void bfin_coretmr_clockevent_init(void)
 #endif /* CONFIG_TICKSOURCE_CORETMR */
 
 
-void __init time_init(void)
+void read_persistent_clock(struct timespec *ts)
 {
 	time_t secs_since_1970 = (365 * 37 + 9) * 24 * 60 * 60;	/* 1 Jan 2007 */
+	ts->tv_sec = secs_since_1970;
+	ts->tv_nsec = 0;
+}
+
+void __init time_init(void)
+{
 
 #ifdef CONFIG_RTC_DRV_BFIN
 	/* [#2663] hack to filter junk RTC values that would cause
@@ -368,11 +374,6 @@ void __init time_init(void)
 	}
 #endif
 
-	/* Initialize xtime. From now on, xtime is updated with timer interrupts */
-	xtime.tv_sec = secs_since_1970;
-	xtime.tv_nsec = 0;
-	set_normalized_timespec(&wall_to_monotonic, -xtime.tv_sec, -xtime.tv_nsec);
-
 	bfin_cs_cycles_init();
 	bfin_cs_gptimer0_init();
 
diff --git a/arch/blackfin/kernel/time.c b/arch/blackfin/kernel/time.c
index 13c1ee3e6408..c9113619029f 100644
--- a/arch/blackfin/kernel/time.c
+++ b/arch/blackfin/kernel/time.c
@@ -112,11 +112,6 @@ u32 arch_gettimeoffset(void)
 }
 #endif
 
-static inline int set_rtc_mmss(unsigned long nowtime)
-{
-	return 0;
-}
-
 /*
  * timer_interrupt() needs to keep up the real-time clock,
  * as well as call the "do_timer()" routine every clocktick
@@ -126,29 +121,8 @@ __attribute__((l1_text))
 #endif
 irqreturn_t timer_interrupt(int irq, void *dummy)
 {
-	/* last time the cmos clock got updated */
-	static long last_rtc_update;
-
 	write_seqlock(&xtime_lock);
 	do_timer(1);
-
-	/*
-	 * If we have an externally synchronized Linux clock, then update
-	 * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be
-	 * called as close as possible to 500 ms before the new second starts.
-	 */
-	if (ntp_synced() &&
-	    xtime.tv_sec > last_rtc_update + 660 &&
-	    (xtime.tv_nsec / NSEC_PER_USEC) >=
-	    500000 - ((unsigned)TICK_SIZE) / 2
-	    && (xtime.tv_nsec / NSEC_PER_USEC) <=
-	    500000 + ((unsigned)TICK_SIZE) / 2) {
-		if (set_rtc_mmss(xtime.tv_sec) == 0)
-			last_rtc_update = xtime.tv_sec;
-		else
-			/* Do it again in 60s. */
-			last_rtc_update = xtime.tv_sec - 600;
-	}
 	write_sequnlock(&xtime_lock);
 
 #ifdef CONFIG_IPIPE
@@ -161,10 +135,15 @@ irqreturn_t timer_interrupt(int irq, void *dummy)
 	return IRQ_HANDLED;
 }
 
-void __init time_init(void)
+void read_persistent_clock(struct timespec *ts)
 {
 	time_t secs_since_1970 = (365 * 37 + 9) * 24 * 60 * 60;	/* 1 Jan 2007 */
+	ts->tv_sec = secs_since_1970;
+	ts->tv_nsec = 0;
+}
 
+void __init time_init(void)
+{
 #ifdef CONFIG_RTC_DRV_BFIN
 	/* [#2663] hack to filter junk RTC values that would cause
 	 * userspace to have to deal with time values greater than
@@ -176,11 +155,5 @@ void __init time_init(void)
 	}
 #endif
 
-	/* Initialize xtime. From now on, xtime is updated with timer interrupts */
-	xtime.tv_sec = secs_since_1970;
-	xtime.tv_nsec = 0;
-
-	wall_to_monotonic.tv_sec = -xtime.tv_sec;
-
 	time_sched_init(timer_interrupt);
 }
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index 059eac6abda1..e25bf4440b51 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -23,6 +23,9 @@ config RWSEM_XCHGADD_ALGORITHM
 config GENERIC_TIME
 	def_bool y
 
+config GENERIC_CMOS_UPDATE
+	def_bool y
+
 config ARCH_USES_GETTIMEOFFSET
 	def_bool y
 
diff --git a/arch/cris/arch-v10/kernel/time.c b/arch/cris/arch-v10/kernel/time.c
index 31ca1418d5a7..30adae594aef 100644
--- a/arch/cris/arch-v10/kernel/time.c
+++ b/arch/cris/arch-v10/kernel/time.c
@@ -26,7 +26,6 @@
 /* it will make jiffies at 96 hz instead of 100 hz though */
 #undef USE_CASCADE_TIMERS
 
-extern void update_xtime_from_cmos(void);
 extern int set_rtc_mmss(unsigned long nowtime);
 extern int have_rtc;
 
@@ -188,8 +187,6 @@ stop_watchdog(void)
 #endif	
 }
 
-/* last time the cmos clock got updated */
-static long last_rtc_update = 0;
 
 /*
  * timer_interrupt() needs to keep up the real-time clock,
@@ -232,24 +229,6 @@ timer_interrupt(int irq, void *dev_id)
 	do_timer(1);
 	
         cris_do_profile(regs); /* Save profiling information */
-
-	/*
-	 * If we have an externally synchronized Linux clock, then update
-	 * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be
-	 * called as close as possible to 500 ms before the new second starts.
-	 *
-	 * The division here is not time critical since it will run once in 
-	 * 11 minutes
-	 */
-	if (ntp_synced() &&
-	    xtime.tv_sec > last_rtc_update + 660 &&
-	    (xtime.tv_nsec / 1000) >= 500000 - (tick_nsec / 1000) / 2 &&
-	    (xtime.tv_nsec / 1000) <= 500000 + (tick_nsec / 1000) / 2) {
-		if (set_rtc_mmss(xtime.tv_sec) == 0)
-			last_rtc_update = xtime.tv_sec;
-		else
-			last_rtc_update = xtime.tv_sec - 600; /* do it again in 60 s */
-	}
         return IRQ_HANDLED;
 }
 
@@ -274,22 +253,10 @@ time_init(void)
 	 */
 	loops_per_usec = 50;
 
-	if(RTC_INIT() < 0) {
-		/* no RTC, start at 1980 */
-		xtime.tv_sec = 0;
-		xtime.tv_nsec = 0;
+	if(RTC_INIT() < 0)
 		have_rtc = 0;
-	} else {		
-		/* get the current time */
+	else
 		have_rtc = 1;
-		update_xtime_from_cmos();
-	}
-
-	/*
-	 * Initialize wall_to_monotonic such that adding it to xtime will yield zero, the
-	 * tv_nsec field must be normalized (i.e., 0 <= nsec < NSEC_PER_SEC).
-	 */
-	set_normalized_timespec(&wall_to_monotonic, -xtime.tv_sec, -xtime.tv_nsec);
 
 	/* Setup the etrax timers
 	 * Base frequency is 25000 hz, divider 250 -> 100 HZ
diff --git a/arch/cris/arch-v32/kernel/time.c b/arch/cris/arch-v32/kernel/time.c
index b1920d8de403..1ee0e1010228 100644
--- a/arch/cris/arch-v32/kernel/time.c
+++ b/arch/cris/arch-v32/kernel/time.c
@@ -44,7 +44,6 @@ unsigned long timer_regs[NR_CPUS] =
 #endif
 };
 
-extern void update_xtime_from_cmos(void);
 extern int set_rtc_mmss(unsigned long nowtime);
 extern int have_rtc;
 
@@ -198,9 +197,6 @@ handle_watchdog_bite(struct pt_regs* regs)
 #endif
 }
 
-/* Last time the cmos clock got updated. */
-static long last_rtc_update = 0;
-
 /*
  * timer_interrupt() needs to keep up the real-time clock,
  * as well as call the "do_timer()" routine every clocktick.
@@ -238,25 +234,6 @@ timer_interrupt(int irq, void *dev_id)
 
 	/* Call the real timer interrupt handler */
 	do_timer(1);
-
-	/*
-	 * If we have an externally synchronized Linux clock, then update
-	 * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be
-	 * called as close as possible to 500 ms before the new second starts.
-	 *
-	 * The division here is not time critical since it will run once in
-	 * 11 minutes
-	 */
-	if ((time_status & STA_UNSYNC) == 0 &&
-	    xtime.tv_sec > last_rtc_update + 660 &&
-	    (xtime.tv_nsec / 1000) >= 500000 - (tick_nsec / 1000) / 2 &&
-	    (xtime.tv_nsec / 1000) <= 500000 + (tick_nsec / 1000) / 2) {
-		if (set_rtc_mmss(xtime.tv_sec) == 0)
-			last_rtc_update = xtime.tv_sec;
-		else
-			/* Do it again in 60 s */
-			last_rtc_update = xtime.tv_sec - 600;
-	}
         return IRQ_HANDLED;
 }
 
@@ -309,23 +286,10 @@ time_init(void)
 	 */
 	loops_per_usec = 50;
 
-	if(RTC_INIT() < 0) {
-		/* No RTC, start at 1980 */
-		xtime.tv_sec = 0;
-		xtime.tv_nsec = 0;
+	if(RTC_INIT() < 0)
 		have_rtc = 0;
-	} else {
-		/* Get the current time */
+	else
 		have_rtc = 1;
-		update_xtime_from_cmos();
-	}
-
-	/*
-	 * Initialize wall_to_monotonic such that adding it to
-	 * xtime will yield zero, the tv_nsec field must be normalized
-	 * (i.e., 0 <= nsec < NSEC_PER_SEC).
-	 */
-	set_normalized_timespec(&wall_to_monotonic, -xtime.tv_sec, -xtime.tv_nsec);
 
 	/* Start CPU local timer. */
 	cris_timer_init();
diff --git a/arch/cris/kernel/time.c b/arch/cris/kernel/time.c
index a05dd31f3efb..c72730d20ef6 100644
--- a/arch/cris/kernel/time.c
+++ b/arch/cris/kernel/time.c
@@ -98,6 +98,8 @@ unsigned long
 get_cmos_time(void)
 {
 	unsigned int year, mon, day, hour, min, sec;
+	if(!have_rtc)
+		return 0;
 
 	sec = CMOS_READ(RTC_SECONDS);
 	min = CMOS_READ(RTC_MINUTES);
@@ -119,19 +121,19 @@ get_cmos_time(void)
 	return mktime(year, mon, day, hour, min, sec);
 }
 
-/* update xtime from the CMOS settings. used when /dev/rtc gets a SET_TIME.
- * TODO: this doesn't reset the fancy NTP phase stuff as do_settimeofday does.
- */
 
-void
-update_xtime_from_cmos(void)
+int update_persistent_clock(struct timespec now)
 {
-	if(have_rtc) {
-		xtime.tv_sec = get_cmos_time();
-		xtime.tv_nsec = 0;
-	}
+	return set_rtc_mmss(now.tv_sec);
 }
 
+void read_persistent_clock(struct timespec *ts)
+{
+	ts->tv_sec = get_cmos_time();
+	ts->tv_nsec = 0;
+}
+
+
 extern void cris_profile_sample(struct pt_regs* regs);
 
 void
diff --git a/arch/frv/kernel/time.c b/arch/frv/kernel/time.c
index fb0ce7577225..0ddbbae83cb2 100644
--- a/arch/frv/kernel/time.c
+++ b/arch/frv/kernel/time.c
@@ -48,20 +48,12 @@ static struct irqaction timer_irq  = {
 	.name = "timer",
 };
 
-static inline int set_rtc_mmss(unsigned long nowtime)
-{
-	return -1;
-}
-
 /*
  * timer_interrupt() needs to keep up the real-time clock,
  * as well as call the "do_timer()" routine every clocktick
  */
 static irqreturn_t timer_interrupt(int irq, void *dummy)
 {
-	/* last time the cmos clock got updated */
-	static long last_rtc_update = 0;
-
 	profile_tick(CPU_PROFILING);
 	/*
 	 * Here we are in the timer irq handler. We just have irqs locally
@@ -74,22 +66,6 @@ static irqreturn_t timer_interrupt(int irq, void *dummy)
 
 	do_timer(1);
 
-	/*
-	 * If we have an externally synchronized Linux clock, then update
-	 * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be
-	 * called as close as possible to 500 ms before the new second starts.
-	 */
-	if (ntp_synced() &&
-	    xtime.tv_sec > last_rtc_update + 660 &&
-	    (xtime.tv_nsec / 1000) >= 500000 - ((unsigned) TICK_SIZE) / 2 &&
-	    (xtime.tv_nsec / 1000) <= 500000 + ((unsigned) TICK_SIZE) / 2
-	    ) {
-		if (set_rtc_mmss(xtime.tv_sec) == 0)
-			last_rtc_update = xtime.tv_sec;
-		else
-			last_rtc_update = xtime.tv_sec - 600; /* do it again in 60 s */
-	}
-
 #ifdef CONFIG_HEARTBEAT
 	static unsigned short n;
 	n++;
@@ -119,7 +95,8 @@ void time_divisor_init(void)
 	__set_TCSR_DATA(0, base >> 8);
 }
 
-void time_init(void)
+
+void read_persistent_clock(struct timespec *ts)
 {
 	unsigned int year, mon, day, hour, min, sec;
 
@@ -135,9 +112,12 @@ void time_init(void)
 
 	if ((year += 1900) < 1970)
 		year += 100;
-	xtime.tv_sec = mktime(year, mon, day, hour, min, sec);
-	xtime.tv_nsec = 0;
+	ts->tv_sec = mktime(year, mon, day, hour, min, sec);
+	ts->tv_nsec = 0;
+}
 
+void time_init(void)
+{
 	/* install scheduling interrupt handler */
 	setup_irq(IRQ_CPU_TIMER0, &timer_irq);
 
diff --git a/arch/h8300/kernel/time.c b/arch/h8300/kernel/time.c
index 7f2d6cfbb4b6..165005aff9df 100644
--- a/arch/h8300/kernel/time.c
+++ b/arch/h8300/kernel/time.c
@@ -41,7 +41,7 @@ void h8300_timer_tick(void)
 	update_process_times(user_mode(get_irq_regs()));
 }
 
-void __init time_init(void)
+void read_persistent_clock(struct timespec *ts)
 {
 	unsigned int year, mon, day, hour, min, sec;
 
@@ -56,8 +56,12 @@ void __init time_init(void)
 #endif
 	if ((year += 1900) < 1970)
 		year += 100;
-	xtime.tv_sec = mktime(year, mon, day, hour, min, sec);
-	xtime.tv_nsec = 0;
+	ts->tv_sec = mktime(year, mon, day, hour, min, sec);
+	ts->tv_nsec = 0;
+}
+
+void __init time_init(void)
+{
 
 	h8300_timer_setup();
 }
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 47a192781b0a..653b3c46ea82 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -430,18 +430,16 @@ static int __init rtc_init(void)
 }
 module_init(rtc_init);
 
+void read_persistent_clock(struct timespec *ts)
+{
+	efi_gettimeofday(ts);
+}
+
 void __init
 time_init (void)
 {
 	register_percpu_irq(IA64_TIMER_VECTOR, &timer_irqaction);
-	efi_gettimeofday(&xtime);
 	ia64_init_itm();
-
-	/*
-	 * Initialize wall_to_monotonic such that adding it to xtime will yield zero, the
-	 * tv_nsec field must be normalized (i.e., 0 <= nsec < NSEC_PER_SEC).
-	 */
-	set_normalized_timespec(&wall_to_monotonic, -xtime.tv_sec, -xtime.tv_nsec);
 }
 
 /*
diff --git a/arch/m32r/kernel/time.c b/arch/m32r/kernel/time.c
index 9cedcef11575..bda86820bffd 100644
--- a/arch/m32r/kernel/time.c
+++ b/arch/m32r/kernel/time.c
@@ -106,24 +106,6 @@ u32 arch_gettimeoffset(void)
 }
 
 /*
- * In order to set the CMOS clock precisely, set_rtc_mmss has to be
- * called 500 ms after the second nowtime has started, because when
- * nowtime is written into the registers of the CMOS clock, it will
- * jump to the next second precisely 500 ms later. Check the Motorola
- * MC146818A or Dallas DS12887 data sheet for details.
- *
- * BUG: This routine does not handle hour overflow properly; it just
- *      sets the minutes. Usually you won't notice until after reboot!
- */
-static inline int set_rtc_mmss(unsigned long nowtime)
-{
-	return 0;
-}
-
-/* last time the cmos clock got updated */
-static long last_rtc_update = 0;
-
-/*
  * timer_interrupt() needs to keep up the real-time clock,
  * as well as call the "do_timer()" routine every clocktick
  */
@@ -138,23 +120,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
 #ifndef CONFIG_SMP
 	update_process_times(user_mode(get_irq_regs()));
 #endif
-	/*
-	 * If we have an externally synchronized Linux clock, then update
-	 * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be
-	 * called as close as possible to 500 ms before the new second starts.
-	 */
-	write_seqlock(&xtime_lock);
-	if (ntp_synced()
-		&& xtime.tv_sec > last_rtc_update + 660
-		&& (xtime.tv_nsec / 1000) >= 500000 - ((unsigned)TICK_SIZE) / 2
-		&& (xtime.tv_nsec / 1000) <= 500000 + ((unsigned)TICK_SIZE) / 2)
-	{
-		if (set_rtc_mmss(xtime.tv_sec) == 0)
-			last_rtc_update = xtime.tv_sec;
-		else	/* do it again in 60 s */
-			last_rtc_update = xtime.tv_sec - 600;
-	}
-	write_sequnlock(&xtime_lock);
 	/* As we return to user mode fire off the other CPU schedulers..
 	   this is basically because we don't yet share IRQ's around.
 	   This message is rigged to be safe on the 386 - basically it's
@@ -174,7 +139,7 @@ static struct irqaction irq0 = {
 	.name = "MFT2",
 };
 
-void __init time_init(void)
+void read_persistent_clock(struct timespec *ts)
 {
 	unsigned int epoch, year, mon, day, hour, min, sec;
 
@@ -194,11 +159,13 @@ void __init time_init(void)
 		epoch = 1952;
 	year += epoch;
 
-	xtime.tv_sec = mktime(year, mon, day, hour, min, sec);
-	xtime.tv_nsec = (INITIAL_JIFFIES % HZ) * (NSEC_PER_SEC / HZ);
-	set_normalized_timespec(&wall_to_monotonic,
-		-xtime.tv_sec, -xtime.tv_nsec);
+	ts->tv_sec = mktime(year, mon, day, hour, min, sec);
+	ts->tv_nsec = (INITIAL_JIFFIES % HZ) * (NSEC_PER_SEC / HZ);
+}
 
+
+void __init time_init(void)
+{
 #if defined(CONFIG_CHIP_M32102) || defined(CONFIG_CHIP_XNUX2) \
 	|| defined(CONFIG_CHIP_VDEC2) || defined(CONFIG_CHIP_M32700) \
 	|| defined(CONFIG_CHIP_OPSP) || defined(CONFIG_CHIP_M32104)
diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c
index 17dc2a31a7ca..4926b3856c15 100644
--- a/arch/m68k/kernel/time.c
+++ b/arch/m68k/kernel/time.c
@@ -73,21 +73,24 @@ static irqreturn_t timer_interrupt(int irq, void *dummy)
 	return IRQ_HANDLED;
 }
 
-void __init time_init(void)
+void read_persistent_clock(struct timespec *ts)
 {
 	struct rtc_time time;
+	ts->tv_sec = 0;
+	ts->tv_nsec = 0;
 
 	if (mach_hwclk) {
 		mach_hwclk(0, &time);
 
 		if ((time.tm_year += 1900) < 1970)
 			time.tm_year += 100;
-		xtime.tv_sec = mktime(time.tm_year, time.tm_mon, time.tm_mday,
+		ts->tv_sec = mktime(time.tm_year, time.tm_mon, time.tm_mday,
 				      time.tm_hour, time.tm_min, time.tm_sec);
-		xtime.tv_nsec = 0;
 	}
-	wall_to_monotonic.tv_sec = -xtime.tv_sec;
+}
 
+void __init time_init(void)
+{
 	mach_sched_init(timer_interrupt);
 }
 
diff --git a/arch/mips/include/asm/i8253.h b/arch/mips/include/asm/i8253.h
index 032ca73f181b..48bb82372994 100644
--- a/arch/mips/include/asm/i8253.h
+++ b/arch/mips/include/asm/i8253.h
@@ -12,7 +12,7 @@
 #define PIT_CH0			0x40
 #define PIT_CH2			0x42
 
-extern spinlock_t i8253_lock;
+extern raw_spinlock_t i8253_lock;
 
 extern void setup_pit_timer(void);
 
diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c
index ed5c441615e4..94794062a177 100644
--- a/arch/mips/kernel/i8253.c
+++ b/arch/mips/kernel/i8253.c
@@ -15,7 +15,7 @@
 #include <asm/io.h>
 #include <asm/time.h>
 
-DEFINE_SPINLOCK(i8253_lock);
+DEFINE_RAW_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
 
 /*
@@ -26,7 +26,7 @@ EXPORT_SYMBOL(i8253_lock);
 static void init_pit_timer(enum clock_event_mode mode,
 			   struct clock_event_device *evt)
 {
-	spin_lock(&i8253_lock);
+	raw_spin_lock(&i8253_lock);
 
 	switch(mode) {
 	case CLOCK_EVT_MODE_PERIODIC:
@@ -55,7 +55,7 @@ static void init_pit_timer(enum clock_event_mode mode,
 		/* Nothing to do here */
 		break;
 	}
-	spin_unlock(&i8253_lock);
+	raw_spin_unlock(&i8253_lock);
 }
 
 /*
@@ -65,10 +65,10 @@ static void init_pit_timer(enum clock_event_mode mode,
  */
 static int pit_next_event(unsigned long delta, struct clock_event_device *evt)
 {
-	spin_lock(&i8253_lock);
+	raw_spin_lock(&i8253_lock);
 	outb_p(delta & 0xff , PIT_CH0);	/* LSB */
 	outb(delta >> 8 , PIT_CH0);	/* MSB */
-	spin_unlock(&i8253_lock);
+	raw_spin_unlock(&i8253_lock);
 
 	return 0;
 }
@@ -137,7 +137,7 @@ static cycle_t pit_read(struct clocksource *cs)
 	static int old_count;
 	static u32 old_jifs;
 
-	spin_lock_irqsave(&i8253_lock, flags);
+	raw_spin_lock_irqsave(&i8253_lock, flags);
 	/*
 	 * Although our caller may have the read side of xtime_lock,
 	 * this is now a seqlock, and we are cheating in this routine
@@ -183,7 +183,7 @@ static cycle_t pit_read(struct clocksource *cs)
 	old_count = count;
 	old_jifs = jifs;
 
-	spin_unlock_irqrestore(&i8253_lock, flags);
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
 
 	count = (LATCH - 1) - count;
 
diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig
index 89faacad5d17..1c4565a9102b 100644
--- a/arch/mn10300/Kconfig
+++ b/arch/mn10300/Kconfig
@@ -37,6 +37,9 @@ config GENERIC_HARDIRQS_NO__DO_IRQ
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
+config GENERIC_CMOS_UPDATE
+        def_bool y
+
 config GENERIC_FIND_NEXT_BIT
 	def_bool y
 
diff --git a/arch/mn10300/kernel/rtc.c b/arch/mn10300/kernel/rtc.c
index 7978470b5749..815a933aafa8 100644
--- a/arch/mn10300/kernel/rtc.c
+++ b/arch/mn10300/kernel/rtc.c
@@ -26,17 +26,15 @@ static long last_rtc_update;
 /* time for RTC to update itself in ioclks */
 static unsigned long mn10300_rtc_update_period;
 
-/*
- * read the current RTC time
- */
-unsigned long __init get_initial_rtc_time(void)
+void read_persistent_clock(struct timespec *ts)
 {
 	struct rtc_time tm;
 
 	get_rtc_time(&tm);
 
-	return mktime(tm.tm_year, tm.tm_mon, tm.tm_mday,
+	ts->tv_sec = mktime(tm.tm_year, tm.tm_mon, tm.tm_mday,
 		      tm.tm_hour, tm.tm_min, tm.tm_sec);
+	ts->tv_nsec = 0;
 }
 
 /*
@@ -110,24 +108,9 @@ static int set_rtc_mmss(unsigned long nowtime)
 	return retval;
 }
 
-void check_rtc_time(void)
+int update_persistent_clock(struct timespec now)
 {
-	/* the RTC clock just finished ticking over again this second
-	 * - if we have an externally synchronized Linux clock, then update
-	 *   RTC clock accordingly every ~11 minutes. set_rtc_mmss() has to be
-	 *   called as close as possible to 500 ms before the new second starts.
-	 */
-	if ((time_status & STA_UNSYNC) == 0 &&
-	    xtime.tv_sec > last_rtc_update + 660 &&
-	    xtime.tv_nsec / 1000 >= 500000 - ((unsigned) TICK_SIZE) / 2 &&
-	    xtime.tv_nsec / 1000 <= 500000 + ((unsigned) TICK_SIZE) / 2
-	    ) {
-		if (set_rtc_mmss(xtime.tv_sec) == 0)
-			last_rtc_update = xtime.tv_sec;
-		else
-			/* do it again in 60s */
-			last_rtc_update = xtime.tv_sec - 600;
-	}
+	return set_rtc_mms(now.tv_sec);
 }
 
 /*
diff --git a/arch/mn10300/kernel/time.c b/arch/mn10300/kernel/time.c
index 395caf01b909..8f7f6d22783d 100644
--- a/arch/mn10300/kernel/time.c
+++ b/arch/mn10300/kernel/time.c
@@ -111,7 +111,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
 		/* advance the kernel's time tracking system */
 		profile_tick(CPU_PROFILING);
 		do_timer(1);
-		check_rtc_time();
 	}
 
 	write_sequnlock(&xtime_lock);
@@ -139,9 +138,6 @@ void __init time_init(void)
 	       " (calibrated against RTC)\n",
 	       MN10300_TSCCLK / 1000000, (MN10300_TSCCLK / 10000) % 100);
 
-	xtime.tv_sec = get_initial_rtc_time();
-	xtime.tv_nsec = 0;
-
 	mn10300_last_tsc = TMTSCBC;
 
 	/* use timer 0 & 1 cascaded to tick at as close to HZ as possible */
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 9908d477ccd9..d6781ce687e2 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -75,7 +75,7 @@ config ARCH_USES_GETTIMEOFFSET
 
 config GENERIC_CMOS_UPDATE
 	bool
-	default y if SPARC64
+	default y
 
 config GENERIC_CLOCKEVENTS
 	bool
diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c
index 0d4c09b15efc..4453003032b5 100644
--- a/arch/sparc/kernel/time_32.c
+++ b/arch/sparc/kernel/time_32.c
@@ -78,6 +78,11 @@ __volatile__ unsigned int *master_l10_counter;
 
 u32 (*do_arch_gettimeoffset)(void);
 
+int update_persistent_clock(struct timespec now)
+{
+	return set_rtc_mmss(now.tv_sec);
+}
+
 /*
  * timer_interrupt() needs to keep up the real-time clock,
  * as well as call the "do_timer()" routine every clocktick
@@ -87,9 +92,6 @@ u32 (*do_arch_gettimeoffset)(void);
 
 static irqreturn_t timer_interrupt(int dummy, void *dev_id)
 {
-	/* last time the cmos clock got updated */
-	static long last_rtc_update;
-
 #ifndef CONFIG_SMP
 	profile_tick(CPU_PROFILING);
 #endif
@@ -101,16 +103,6 @@ static irqreturn_t timer_interrupt(int dummy, void *dev_id)
 
 	do_timer(1);
 
-	/* Determine when to update the Mostek clock. */
-	if (ntp_synced() &&
-	    xtime.tv_sec > last_rtc_update + 660 &&
-	    (xtime.tv_nsec / 1000) >= 500000 - ((unsigned) TICK_SIZE) / 2 &&
-	    (xtime.tv_nsec / 1000) <= 500000 + ((unsigned) TICK_SIZE) / 2) {
-	  if (set_rtc_mmss(xtime.tv_sec) == 0)
-	    last_rtc_update = xtime.tv_sec;
-	  else
-	    last_rtc_update = xtime.tv_sec - 600; /* do it again in 60 s */
-	}
 	write_sequnlock(&xtime_lock);
 
 #ifndef CONFIG_SMP
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 035edb75d74f..b769451d2f77 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -58,6 +58,9 @@ config X86
 	select HAVE_ARCH_KMEMCHECK
 	select HAVE_USER_RETURN_NOTIFIER
 
+config INSTRUCTION_DECODER
+	def_bool (KPROBES || PERF_EVENTS)
+
 config OUTPUT_FORMAT
 	string
 	default "elf32-i386" if X86_32
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index a19829374e6a..918fbb1855cc 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -502,23 +502,3 @@ config CPU_SUP_UMC_32
 	  CPU might render the kernel unbootable.
 
 	  If unsure, say N.
-
-config X86_DS
-	def_bool X86_PTRACE_BTS
-	depends on X86_DEBUGCTLMSR
-	select HAVE_HW_BRANCH_TRACER
-
-config X86_PTRACE_BTS
-	bool "Branch Trace Store"
-	default y
-	depends on X86_DEBUGCTLMSR
-	depends on BROKEN
-	---help---
-	  This adds a ptrace interface to the hardware's branch trace store.
-
-	  Debuggers may use it to collect an execution trace of the debugged
-	  application in order to answer the question 'how did I get here?'.
-	  Debuggers may trace user mode as well as kernel mode.
-
-	  Say Y unless there is no application development on this machine
-	  and you want to save a small amount of code size.
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index bc01e3ebfeb2..bd58c8abbfbd 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -174,15 +174,6 @@ config IOMMU_LEAK
 	  Add a simple leak tracer to the IOMMU code. This is useful when you
 	  are debugging a buggy device driver that leaks IOMMU mappings.
 
-config X86_DS_SELFTEST
-    bool "DS selftest"
-    default y
-    depends on DEBUG_KERNEL
-    depends on X86_DS
-	---help---
-	  Perform Debug Store selftests at boot time.
-	  If in doubt, say "N".
-
 config HAVE_MMIOTRACE_SUPPORT
 	def_bool y
 
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index b4ac2cdcb64f..1fa03e04ae44 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -373,6 +373,7 @@ extern atomic_t init_deasserted;
 extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
 #endif
 
+#ifdef CONFIG_X86_LOCAL_APIC
 static inline u32 apic_read(u32 reg)
 {
 	return apic->read(reg);
@@ -403,10 +404,19 @@ static inline u32 safe_apic_wait_icr_idle(void)
 	return apic->safe_wait_icr_idle();
 }
 
+#else /* CONFIG_X86_LOCAL_APIC */
+
+static inline u32 apic_read(u32 reg) { return 0; }
+static inline void apic_write(u32 reg, u32 val) { }
+static inline u64 apic_icr_read(void) { return 0; }
+static inline void apic_icr_write(u32 low, u32 high) { }
+static inline void apic_wait_icr_idle(void) { }
+static inline u32 safe_apic_wait_icr_idle(void) { return 0; }
+
+#endif /* CONFIG_X86_LOCAL_APIC */
 
 static inline void ack_APIC_irq(void)
 {
-#ifdef CONFIG_X86_LOCAL_APIC
 	/*
 	 * ack_APIC_irq() actually gets compiled as a single instruction
 	 * ... yummie.
@@ -414,7 +424,6 @@ static inline void ack_APIC_irq(void)
 
 	/* Docs say use 0 for future compatibility */
 	apic_write(APIC_EOI, 0);
-#endif
 }
 
 static inline unsigned default_get_apic_id(unsigned long x)
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 0cd82d068613..630e623f61e0 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -161,6 +161,7 @@
  */
 #define X86_FEATURE_IDA		(7*32+ 0) /* Intel Dynamic Acceleration */
 #define X86_FEATURE_ARAT	(7*32+ 1) /* Always Running APIC Timer */
+#define X86_FEATURE_CPB		(7*32+ 2) /* AMD Core Performance Boost */
 
 /* Virtualization flags: Linux defined */
 #define X86_FEATURE_TPR_SHADOW  (8*32+ 0) /* Intel TPR Shadow */
diff --git a/arch/x86/include/asm/ds.h b/arch/x86/include/asm/ds.h
deleted file mode 100644
index 70dac199b093..000000000000
--- a/arch/x86/include/asm/ds.h
+++ /dev/null
@@ -1,302 +0,0 @@
-/*
- * Debug Store (DS) support
- *
- * This provides a low-level interface to the hardware's Debug Store
- * feature that is used for branch trace store (BTS) and
- * precise-event based sampling (PEBS).
- *
- * It manages:
- * - DS and BTS hardware configuration
- * - buffer overflow handling (to be done)
- * - buffer access
- *
- * It does not do:
- * - security checking (is the caller allowed to trace the task)
- * - buffer allocation (memory accounting)
- *
- *
- * Copyright (C) 2007-2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
- */
-
-#ifndef _ASM_X86_DS_H
-#define _ASM_X86_DS_H
-
-
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/err.h>
-
-
-#ifdef CONFIG_X86_DS
-
-struct task_struct;
-struct ds_context;
-struct ds_tracer;
-struct bts_tracer;
-struct pebs_tracer;
-
-typedef void (*bts_ovfl_callback_t)(struct bts_tracer *);
-typedef void (*pebs_ovfl_callback_t)(struct pebs_tracer *);
-
-
-/*
- * A list of features plus corresponding macros to talk about them in
- * the ds_request function's flags parameter.
- *
- * We use the enum to index an array of corresponding control bits;
- * we use the macro to index a flags bit-vector.
- */
-enum ds_feature {
-	dsf_bts = 0,
-	dsf_bts_kernel,
-#define BTS_KERNEL (1 << dsf_bts_kernel)
-	/* trace kernel-mode branches */
-
-	dsf_bts_user,
-#define BTS_USER (1 << dsf_bts_user)
-	/* trace user-mode branches */
-
-	dsf_bts_overflow,
-	dsf_bts_max,
-	dsf_pebs = dsf_bts_max,
-
-	dsf_pebs_max,
-	dsf_ctl_max = dsf_pebs_max,
-	dsf_bts_timestamps = dsf_ctl_max,
-#define BTS_TIMESTAMPS (1 << dsf_bts_timestamps)
-	/* add timestamps into BTS trace */
-
-#define BTS_USER_FLAGS (BTS_KERNEL | BTS_USER | BTS_TIMESTAMPS)
-};
-
-
-/*
- * Request BTS or PEBS
- *
- * Due to alignement constraints, the actual buffer may be slightly
- * smaller than the requested or provided buffer.
- *
- * Returns a pointer to a tracer structure on success, or
- * ERR_PTR(errcode) on failure.
- *
- * The interrupt threshold is independent from the overflow callback
- * to allow users to use their own overflow interrupt handling mechanism.
- *
- * The function might sleep.
- *
- * task: the task to request recording for
- * cpu:  the cpu to request recording for
- * base: the base pointer for the (non-pageable) buffer;
- * size: the size of the provided buffer in bytes
- * ovfl: pointer to a function to be called on buffer overflow;
- *       NULL if cyclic buffer requested
- * th: the interrupt threshold in records from the end of the buffer;
- *     -1 if no interrupt threshold is requested.
- * flags: a bit-mask of the above flags
- */
-extern struct bts_tracer *ds_request_bts_task(struct task_struct *task,
-					      void *base, size_t size,
-					      bts_ovfl_callback_t ovfl,
-					      size_t th, unsigned int flags);
-extern struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size,
-					     bts_ovfl_callback_t ovfl,
-					     size_t th, unsigned int flags);
-extern struct pebs_tracer *ds_request_pebs_task(struct task_struct *task,
-						void *base, size_t size,
-						pebs_ovfl_callback_t ovfl,
-						size_t th, unsigned int flags);
-extern struct pebs_tracer *ds_request_pebs_cpu(int cpu,
-					       void *base, size_t size,
-					       pebs_ovfl_callback_t ovfl,
-					       size_t th, unsigned int flags);
-
-/*
- * Release BTS or PEBS resources
- * Suspend and resume BTS or PEBS tracing
- *
- * Must be called with irq's enabled.
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern void ds_release_bts(struct bts_tracer *tracer);
-extern void ds_suspend_bts(struct bts_tracer *tracer);
-extern void ds_resume_bts(struct bts_tracer *tracer);
-extern void ds_release_pebs(struct pebs_tracer *tracer);
-extern void ds_suspend_pebs(struct pebs_tracer *tracer);
-extern void ds_resume_pebs(struct pebs_tracer *tracer);
-
-/*
- * Release BTS or PEBS resources
- * Suspend and resume BTS or PEBS tracing
- *
- * Cpu tracers must call this on the traced cpu.
- * Task tracers must call ds_release_~_noirq() for themselves.
- *
- * May be called with irq's disabled.
- *
- * Returns 0 if successful;
- * -EPERM if the cpu tracer does not trace the current cpu.
- * -EPERM if the task tracer does not trace itself.
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern int ds_release_bts_noirq(struct bts_tracer *tracer);
-extern int ds_suspend_bts_noirq(struct bts_tracer *tracer);
-extern int ds_resume_bts_noirq(struct bts_tracer *tracer);
-extern int ds_release_pebs_noirq(struct pebs_tracer *tracer);
-extern int ds_suspend_pebs_noirq(struct pebs_tracer *tracer);
-extern int ds_resume_pebs_noirq(struct pebs_tracer *tracer);
-
-
-/*
- * The raw DS buffer state as it is used for BTS and PEBS recording.
- *
- * This is the low-level, arch-dependent interface for working
- * directly on the raw trace data.
- */
-struct ds_trace {
-	/* the number of bts/pebs records */
-	size_t n;
-	/* the size of a bts/pebs record in bytes */
-	size_t size;
-	/* pointers into the raw buffer:
-	   - to the first entry */
-	void *begin;
-	/* - one beyond the last entry */
-	void *end;
-	/* - one beyond the newest entry */
-	void *top;
-	/* - the interrupt threshold */
-	void *ith;
-	/* flags given on ds_request() */
-	unsigned int flags;
-};
-
-/*
- * An arch-independent view on branch trace data.
- */
-enum bts_qualifier {
-	bts_invalid,
-#define BTS_INVALID bts_invalid
-
-	bts_branch,
-#define BTS_BRANCH bts_branch
-
-	bts_task_arrives,
-#define BTS_TASK_ARRIVES bts_task_arrives
-
-	bts_task_departs,
-#define BTS_TASK_DEPARTS bts_task_departs
-
-	bts_qual_bit_size = 4,
-	bts_qual_max = (1 << bts_qual_bit_size),
-};
-
-struct bts_struct {
-	__u64 qualifier;
-	union {
-		/* BTS_BRANCH */
-		struct {
-			__u64 from;
-			__u64 to;
-		} lbr;
-		/* BTS_TASK_ARRIVES or BTS_TASK_DEPARTS */
-		struct {
-			__u64 clock;
-			pid_t pid;
-		} event;
-	} variant;
-};
-
-
-/*
- * The BTS state.
- *
- * This gives access to the raw DS state and adds functions to provide
- * an arch-independent view of the BTS data.
- */
-struct bts_trace {
-	struct ds_trace ds;
-
-	int (*read)(struct bts_tracer *tracer, const void *at,
-		    struct bts_struct *out);
-	int (*write)(struct bts_tracer *tracer, const struct bts_struct *in);
-};
-
-
-/*
- * The PEBS state.
- *
- * This gives access to the raw DS state and the PEBS-specific counter
- * reset value.
- */
-struct pebs_trace {
-	struct ds_trace ds;
-
-	/* the number of valid counters in the below array */
-	unsigned int counters;
-
-#define MAX_PEBS_COUNTERS 4
-	/* the counter reset value */
-	unsigned long long counter_reset[MAX_PEBS_COUNTERS];
-};
-
-
-/*
- * Read the BTS or PEBS trace.
- *
- * Returns a view on the trace collected for the parameter tracer.
- *
- * The view remains valid as long as the traced task is not running or
- * the tracer is suspended.
- * Writes into the trace buffer are not reflected.
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern const struct bts_trace *ds_read_bts(struct bts_tracer *tracer);
-extern const struct pebs_trace *ds_read_pebs(struct pebs_tracer *tracer);
-
-
-/*
- * Reset the write pointer of the BTS/PEBS buffer.
- *
- * Returns 0 on success; -Eerrno on error
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern int ds_reset_bts(struct bts_tracer *tracer);
-extern int ds_reset_pebs(struct pebs_tracer *tracer);
-
-/*
- * Set the PEBS counter reset value.
- *
- * Returns 0 on success; -Eerrno on error
- *
- * tracer: the tracer handle returned from ds_request_pebs()
- * counter: the index of the counter
- * value: the new counter reset value
- */
-extern int ds_set_pebs_reset(struct pebs_tracer *tracer,
-			     unsigned int counter, u64 value);
-
-/*
- * Initialization
- */
-struct cpuinfo_x86;
-extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *);
-
-/*
- * Context switch work
- */
-extern void ds_switch_to(struct task_struct *prev, struct task_struct *next);
-
-#else /* CONFIG_X86_DS */
-
-struct cpuinfo_x86;
-static inline void __cpuinit ds_init_intel(struct cpuinfo_x86 *ignored) {}
-static inline void ds_switch_to(struct task_struct *prev,
-				struct task_struct *next) {}
-
-#endif /* CONFIG_X86_DS */
-#endif /* _ASM_X86_DS_H */
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 0e22296790d3..ec8a52d14ab1 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -45,7 +45,12 @@
 #define E820_NVS	4
 #define E820_UNUSABLE	5
 
-/* reserved RAM used by kernel itself */
+/*
+ * reserved RAM used by kernel itself
+ * if CONFIG_INTEL_TXT is enabled, memory of this type will be
+ * included in the S3 integrity calculation and so should not include
+ * any memory that BIOS might alter over the S3 transition
+ */
 #define E820_RESERVED_KERN        128
 
 #ifndef __ASSEMBLY__
diff --git a/arch/x86/include/asm/i8253.h b/arch/x86/include/asm/i8253.h
index 1edbf89680fd..fc1f579fb965 100644
--- a/arch/x86/include/asm/i8253.h
+++ b/arch/x86/include/asm/i8253.h
@@ -6,7 +6,7 @@
 #define PIT_CH0			0x40
 #define PIT_CH2			0x42
 
-extern spinlock_t i8253_lock;
+extern raw_spinlock_t i8253_lock;
 
 extern struct clock_event_device *global_clock_event;
 
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 96c2e0ad04ca..88c765e16410 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -68,6 +68,8 @@ struct insn {
 	const insn_byte_t *next_byte;
 };
 
+#define MAX_INSN_SIZE	16
+
 #define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6)
 #define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3)
 #define X86_MODRM_RM(modrm) ((modrm) & 0x07)
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 4ffa345a8ccb..547882539157 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -24,6 +24,7 @@
 #include <linux/types.h>
 #include <linux/ptrace.h>
 #include <linux/percpu.h>
+#include <asm/insn.h>
 
 #define  __ARCH_WANT_KPROBES_INSN_SLOT
 
@@ -36,7 +37,6 @@ typedef u8 kprobe_opcode_t;
 #define RELATIVEJUMP_SIZE 5
 #define RELATIVECALL_OPCODE 0xe8
 #define RELATIVE_ADDR_SIZE 4
-#define MAX_INSN_SIZE 16
 #define MAX_STACK_SIZE 64
 #define MIN_STACK_SIZE(ADDR)					       \
 	(((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4604e6a54d36..bc473acfa7f9 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -71,11 +71,14 @@
 #define MSR_IA32_LASTINTTOIP		0x000001de
 
 /* DEBUGCTLMSR bits (others vary by model): */
-#define _DEBUGCTLMSR_LBR	0 /* last branch recording */
-#define _DEBUGCTLMSR_BTF	1 /* single-step on branches */
-
-#define DEBUGCTLMSR_LBR		(1UL << _DEBUGCTLMSR_LBR)
-#define DEBUGCTLMSR_BTF		(1UL << _DEBUGCTLMSR_BTF)
+#define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
+#define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
+#define DEBUGCTLMSR_TR			(1UL <<  6)
+#define DEBUGCTLMSR_BTS			(1UL <<  7)
+#define DEBUGCTLMSR_BTINT		(1UL <<  8)
+#define DEBUGCTLMSR_BTS_OFF_OS		(1UL <<  9)
+#define DEBUGCTLMSR_BTS_OFF_USR		(1UL << 10)
+#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI	(1UL << 11)
 
 #define MSR_IA32_MC0_CTL		0x00000400
 #define MSR_IA32_MC0_STATUS		0x00000401
@@ -359,6 +362,8 @@
 #define MSR_P4_U2L_ESCR0		0x000003b0
 #define MSR_P4_U2L_ESCR1		0x000003b1
 
+#define MSR_P4_PEBS_MATRIX_VERT		0x000003f2
+
 /* Intel Core-based CPU performance counters */
 #define MSR_CORE_PERF_FIXED_CTR0	0x00000309
 #define MSR_CORE_PERF_FIXED_CTR1	0x0000030a
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index db6109a885a7..f6d43dbfd8e7 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -5,7 +5,7 @@
  * Performance event hw details:
  */
 
-#define X86_PMC_MAX_GENERIC					8
+#define X86_PMC_MAX_GENERIC				       32
 #define X86_PMC_MAX_FIXED					3
 
 #define X86_PMC_IDX_GENERIC				        0
@@ -18,39 +18,31 @@
 #define MSR_ARCH_PERFMON_EVENTSEL0			     0x186
 #define MSR_ARCH_PERFMON_EVENTSEL1			     0x187
 
-#define ARCH_PERFMON_EVENTSEL_ENABLE			  (1 << 22)
-#define ARCH_PERFMON_EVENTSEL_ANY			  (1 << 21)
-#define ARCH_PERFMON_EVENTSEL_INT			  (1 << 20)
-#define ARCH_PERFMON_EVENTSEL_OS			  (1 << 17)
-#define ARCH_PERFMON_EVENTSEL_USR			  (1 << 16)
-
-/*
- * Includes eventsel and unit mask as well:
- */
-
-
-#define INTEL_ARCH_EVTSEL_MASK		0x000000FFULL
-#define INTEL_ARCH_UNIT_MASK		0x0000FF00ULL
-#define INTEL_ARCH_EDGE_MASK		0x00040000ULL
-#define INTEL_ARCH_INV_MASK		0x00800000ULL
-#define INTEL_ARCH_CNT_MASK		0xFF000000ULL
-#define INTEL_ARCH_EVENT_MASK	(INTEL_ARCH_UNIT_MASK|INTEL_ARCH_EVTSEL_MASK)
-
-/*
- * filter mask to validate fixed counter events.
- * the following filters disqualify for fixed counters:
- *  - inv
- *  - edge
- *  - cnt-mask
- *  The other filters are supported by fixed counters.
- *  The any-thread option is supported starting with v3.
- */
-#define INTEL_ARCH_FIXED_MASK \
-	(INTEL_ARCH_CNT_MASK| \
-	 INTEL_ARCH_INV_MASK| \
-	 INTEL_ARCH_EDGE_MASK|\
-	 INTEL_ARCH_UNIT_MASK|\
-	 INTEL_ARCH_EVENT_MASK)
+#define ARCH_PERFMON_EVENTSEL_EVENT			0x000000FFULL
+#define ARCH_PERFMON_EVENTSEL_UMASK			0x0000FF00ULL
+#define ARCH_PERFMON_EVENTSEL_USR			(1ULL << 16)
+#define ARCH_PERFMON_EVENTSEL_OS			(1ULL << 17)
+#define ARCH_PERFMON_EVENTSEL_EDGE			(1ULL << 18)
+#define ARCH_PERFMON_EVENTSEL_INT			(1ULL << 20)
+#define ARCH_PERFMON_EVENTSEL_ANY			(1ULL << 21)
+#define ARCH_PERFMON_EVENTSEL_ENABLE			(1ULL << 22)
+#define ARCH_PERFMON_EVENTSEL_INV			(1ULL << 23)
+#define ARCH_PERFMON_EVENTSEL_CMASK			0xFF000000ULL
+
+#define AMD64_EVENTSEL_EVENT	\
+	(ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32))
+#define INTEL_ARCH_EVENT_MASK	\
+	(ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT)
+
+#define X86_RAW_EVENT_MASK		\
+	(ARCH_PERFMON_EVENTSEL_EVENT |	\
+	 ARCH_PERFMON_EVENTSEL_UMASK |	\
+	 ARCH_PERFMON_EVENTSEL_EDGE  |	\
+	 ARCH_PERFMON_EVENTSEL_INV   |	\
+	 ARCH_PERFMON_EVENTSEL_CMASK)
+#define AMD64_RAW_EVENT_MASK		\
+	(X86_RAW_EVENT_MASK          |  \
+	 AMD64_EVENTSEL_EVENT)
 
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL		      0x3c
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK		(0x00 << 8)
@@ -67,7 +59,7 @@
 union cpuid10_eax {
 	struct {
 		unsigned int version_id:8;
-		unsigned int num_events:8;
+		unsigned int num_counters:8;
 		unsigned int bit_width:8;
 		unsigned int mask_length:8;
 	} split;
@@ -76,7 +68,7 @@ union cpuid10_eax {
 
 union cpuid10_edx {
 	struct {
-		unsigned int num_events_fixed:4;
+		unsigned int num_counters_fixed:4;
 		unsigned int reserved:28;
 	} split;
 	unsigned int full;
@@ -136,6 +128,25 @@ 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
+ * care what we do with it.
+ */
+#define PERF_EFLAGS_EXACT	(1UL << 3)
+
+#define perf_misc_flags(regs)				\
+({	int misc = 0;					\
+	if (user_mode(regs))				\
+		misc |= PERF_RECORD_MISC_USER;		\
+	else						\
+		misc |= PERF_RECORD_MISC_KERNEL;	\
+	if (regs->flags & PERF_EFLAGS_EXACT)		\
+		misc |= PERF_RECORD_MISC_EXACT;		\
+	misc; })
+
+#define perf_instruction_pointer(regs)	((regs)->ip)
+
 #else
 static inline void init_hw_perf_events(void)		{ }
 static inline void perf_events_lapic_init(void)	{ }
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
new file mode 100644
index 000000000000..b05400a542ff
--- /dev/null
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -0,0 +1,794 @@
+/*
+ * Netburst Perfomance Events (P4, old Xeon)
+ */
+
+#ifndef PERF_EVENT_P4_H
+#define PERF_EVENT_P4_H
+
+#include <linux/cpu.h>
+#include <linux/bitops.h>
+
+/*
+ * NetBurst has perfomance MSRs shared between
+ * threads if HT is turned on, ie for both logical
+ * processors (mem: in turn in Atom with HT support
+ * perf-MSRs are not shared and every thread has its
+ * own perf-MSRs set)
+ */
+#define ARCH_P4_TOTAL_ESCR	(46)
+#define ARCH_P4_RESERVED_ESCR	(2) /* IQ_ESCR(0,1) not always present */
+#define ARCH_P4_MAX_ESCR	(ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR)
+#define ARCH_P4_MAX_CCCR	(18)
+#define ARCH_P4_MAX_COUNTER	(ARCH_P4_MAX_CCCR / 2)
+
+#define P4_ESCR_EVENT_MASK	0x7e000000U
+#define P4_ESCR_EVENT_SHIFT	25
+#define P4_ESCR_EVENTMASK_MASK	0x01fffe00U
+#define P4_ESCR_EVENTMASK_SHIFT	9
+#define P4_ESCR_TAG_MASK	0x000001e0U
+#define P4_ESCR_TAG_SHIFT	5
+#define P4_ESCR_TAG_ENABLE	0x00000010U
+#define P4_ESCR_T0_OS		0x00000008U
+#define P4_ESCR_T0_USR		0x00000004U
+#define P4_ESCR_T1_OS		0x00000002U
+#define P4_ESCR_T1_USR		0x00000001U
+
+#define P4_ESCR_EVENT(v)	((v) << P4_ESCR_EVENT_SHIFT)
+#define P4_ESCR_EMASK(v)	((v) << P4_ESCR_EVENTMASK_SHIFT)
+#define P4_ESCR_TAG(v)		((v) << P4_ESCR_TAG_SHIFT)
+
+/* Non HT mask */
+#define P4_ESCR_MASK			\
+	(P4_ESCR_EVENT_MASK	|	\
+	P4_ESCR_EVENTMASK_MASK	|	\
+	P4_ESCR_TAG_MASK	|	\
+	P4_ESCR_TAG_ENABLE	|	\
+	P4_ESCR_T0_OS		|	\
+	P4_ESCR_T0_USR)
+
+/* HT mask */
+#define P4_ESCR_MASK_HT			\
+	(P4_ESCR_MASK |	P4_ESCR_T1_OS | P4_ESCR_T1_USR)
+
+#define P4_CCCR_OVF			0x80000000U
+#define P4_CCCR_CASCADE			0x40000000U
+#define P4_CCCR_OVF_PMI_T0		0x04000000U
+#define P4_CCCR_OVF_PMI_T1		0x08000000U
+#define P4_CCCR_FORCE_OVF		0x02000000U
+#define P4_CCCR_EDGE			0x01000000U
+#define P4_CCCR_THRESHOLD_MASK		0x00f00000U
+#define P4_CCCR_THRESHOLD_SHIFT		20
+#define P4_CCCR_COMPLEMENT		0x00080000U
+#define P4_CCCR_COMPARE			0x00040000U
+#define P4_CCCR_ESCR_SELECT_MASK	0x0000e000U
+#define P4_CCCR_ESCR_SELECT_SHIFT	13
+#define P4_CCCR_ENABLE			0x00001000U
+#define P4_CCCR_THREAD_SINGLE		0x00010000U
+#define P4_CCCR_THREAD_BOTH		0x00020000U
+#define P4_CCCR_THREAD_ANY		0x00030000U
+#define P4_CCCR_RESERVED		0x00000fffU
+
+#define P4_CCCR_THRESHOLD(v)		((v) << P4_CCCR_THRESHOLD_SHIFT)
+#define P4_CCCR_ESEL(v)			((v) << P4_CCCR_ESCR_SELECT_SHIFT)
+
+/* Custom bits in reerved CCCR area */
+#define P4_CCCR_CACHE_OPS_MASK		0x0000003fU
+
+
+/* Non HT mask */
+#define P4_CCCR_MASK				\
+	(P4_CCCR_OVF			|	\
+	P4_CCCR_CASCADE			|	\
+	P4_CCCR_OVF_PMI_T0		|	\
+	P4_CCCR_FORCE_OVF		|	\
+	P4_CCCR_EDGE			|	\
+	P4_CCCR_THRESHOLD_MASK		|	\
+	P4_CCCR_COMPLEMENT		|	\
+	P4_CCCR_COMPARE			|	\
+	P4_CCCR_ESCR_SELECT_MASK	|	\
+	P4_CCCR_ENABLE)
+
+/* HT mask */
+#define P4_CCCR_MASK_HT	(P4_CCCR_MASK | P4_CCCR_THREAD_ANY)
+
+#define P4_GEN_ESCR_EMASK(class, name, bit)	\
+	class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT)
+#define P4_ESCR_EMASK_BIT(class, name)		class##__##name
+
+/*
+ * config field is 64bit width and consists of
+ * HT << 63 | ESCR << 32 | CCCR
+ * where HT is HyperThreading bit (since ESCR
+ * has it reserved we may use it for own purpose)
+ *
+ * note that this is NOT the addresses of respective
+ * ESCR and CCCR but rather an only packed value should
+ * be unpacked and written to a proper addresses
+ *
+ * the base idea is to pack as much info as
+ * possible
+ */
+#define p4_config_pack_escr(v)		(((u64)(v)) << 32)
+#define p4_config_pack_cccr(v)		(((u64)(v)) & 0xffffffffULL)
+#define p4_config_unpack_escr(v)	(((u64)(v)) >> 32)
+#define p4_config_unpack_cccr(v)	(((u64)(v)) & 0xffffffffULL)
+
+#define p4_config_unpack_emask(v)			\
+	({						\
+		u32 t = p4_config_unpack_escr((v));	\
+		t = t &  P4_ESCR_EVENTMASK_MASK;	\
+		t = t >> P4_ESCR_EVENTMASK_SHIFT;	\
+		t;					\
+	})
+
+#define p4_config_unpack_event(v)			\
+	({						\
+		u32 t = p4_config_unpack_escr((v));	\
+		t = t &  P4_ESCR_EVENT_MASK;		\
+		t = t >> P4_ESCR_EVENT_SHIFT;		\
+		t;					\
+	})
+
+#define p4_config_unpack_cache_event(v)	(((u64)(v)) & P4_CCCR_CACHE_OPS_MASK)
+
+#define P4_CONFIG_HT_SHIFT		63
+#define P4_CONFIG_HT			(1ULL << P4_CONFIG_HT_SHIFT)
+
+static inline bool p4_is_event_cascaded(u64 config)
+{
+	u32 cccr = p4_config_unpack_cccr(config);
+	return !!(cccr & P4_CCCR_CASCADE);
+}
+
+static inline int p4_ht_config_thread(u64 config)
+{
+	return !!(config & P4_CONFIG_HT);
+}
+
+static inline u64 p4_set_ht_bit(u64 config)
+{
+	return config | P4_CONFIG_HT;
+}
+
+static inline u64 p4_clear_ht_bit(u64 config)
+{
+	return config & ~P4_CONFIG_HT;
+}
+
+static inline int p4_ht_active(void)
+{
+#ifdef CONFIG_SMP
+	return smp_num_siblings > 1;
+#endif
+	return 0;
+}
+
+static inline int p4_ht_thread(int cpu)
+{
+#ifdef CONFIG_SMP
+	if (smp_num_siblings == 2)
+		return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
+#endif
+	return 0;
+}
+
+static inline int p4_should_swap_ts(u64 config, int cpu)
+{
+	return p4_ht_config_thread(config) ^ p4_ht_thread(cpu);
+}
+
+static inline u32 p4_default_cccr_conf(int cpu)
+{
+	/*
+	 * Note that P4_CCCR_THREAD_ANY is "required" on
+	 * non-HT machines (on HT machines we count TS events
+	 * regardless the state of second logical processor
+	 */
+	u32 cccr = P4_CCCR_THREAD_ANY;
+
+	if (!p4_ht_thread(cpu))
+		cccr |= P4_CCCR_OVF_PMI_T0;
+	else
+		cccr |= P4_CCCR_OVF_PMI_T1;
+
+	return cccr;
+}
+
+static inline u32 p4_default_escr_conf(int cpu, int exclude_os, int exclude_usr)
+{
+	u32 escr = 0;
+
+	if (!p4_ht_thread(cpu)) {
+		if (!exclude_os)
+			escr |= P4_ESCR_T0_OS;
+		if (!exclude_usr)
+			escr |= P4_ESCR_T0_USR;
+	} else {
+		if (!exclude_os)
+			escr |= P4_ESCR_T1_OS;
+		if (!exclude_usr)
+			escr |= P4_ESCR_T1_USR;
+	}
+
+	return escr;
+}
+
+enum P4_EVENTS {
+	P4_EVENT_TC_DELIVER_MODE,
+	P4_EVENT_BPU_FETCH_REQUEST,
+	P4_EVENT_ITLB_REFERENCE,
+	P4_EVENT_MEMORY_CANCEL,
+	P4_EVENT_MEMORY_COMPLETE,
+	P4_EVENT_LOAD_PORT_REPLAY,
+	P4_EVENT_STORE_PORT_REPLAY,
+	P4_EVENT_MOB_LOAD_REPLAY,
+	P4_EVENT_PAGE_WALK_TYPE,
+	P4_EVENT_BSQ_CACHE_REFERENCE,
+	P4_EVENT_IOQ_ALLOCATION,
+	P4_EVENT_IOQ_ACTIVE_ENTRIES,
+	P4_EVENT_FSB_DATA_ACTIVITY,
+	P4_EVENT_BSQ_ALLOCATION,
+	P4_EVENT_BSQ_ACTIVE_ENTRIES,
+	P4_EVENT_SSE_INPUT_ASSIST,
+	P4_EVENT_PACKED_SP_UOP,
+	P4_EVENT_PACKED_DP_UOP,
+	P4_EVENT_SCALAR_SP_UOP,
+	P4_EVENT_SCALAR_DP_UOP,
+	P4_EVENT_64BIT_MMX_UOP,
+	P4_EVENT_128BIT_MMX_UOP,
+	P4_EVENT_X87_FP_UOP,
+	P4_EVENT_TC_MISC,
+	P4_EVENT_GLOBAL_POWER_EVENTS,
+	P4_EVENT_TC_MS_XFER,
+	P4_EVENT_UOP_QUEUE_WRITES,
+	P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE,
+	P4_EVENT_RETIRED_BRANCH_TYPE,
+	P4_EVENT_RESOURCE_STALL,
+	P4_EVENT_WC_BUFFER,
+	P4_EVENT_B2B_CYCLES,
+	P4_EVENT_BNR,
+	P4_EVENT_SNOOP,
+	P4_EVENT_RESPONSE,
+	P4_EVENT_FRONT_END_EVENT,
+	P4_EVENT_EXECUTION_EVENT,
+	P4_EVENT_REPLAY_EVENT,
+	P4_EVENT_INSTR_RETIRED,
+	P4_EVENT_UOPS_RETIRED,
+	P4_EVENT_UOP_TYPE,
+	P4_EVENT_BRANCH_RETIRED,
+	P4_EVENT_MISPRED_BRANCH_RETIRED,
+	P4_EVENT_X87_ASSIST,
+	P4_EVENT_MACHINE_CLEAR,
+	P4_EVENT_INSTR_COMPLETED,
+};
+
+#define P4_OPCODE(event)		event##_OPCODE
+#define P4_OPCODE_ESEL(opcode)		((opcode & 0x00ff) >> 0)
+#define P4_OPCODE_EVNT(opcode)		((opcode & 0xff00) >> 8)
+#define P4_OPCODE_PACK(event, sel)	(((event) << 8) | sel)
+
+/*
+ * Comments below the event represent ESCR restriction
+ * for this event and counter index per ESCR
+ *
+ * MSR_P4_IQ_ESCR0 and MSR_P4_IQ_ESCR1 are available only on early
+ * processor builds (family 0FH, models 01H-02H). These MSRs
+ * are not available on later versions, so that we don't use
+ * them completely
+ *
+ * Also note that CCCR1 do not have P4_CCCR_ENABLE bit properly
+ * working so that we should not use this CCCR and respective
+ * counter as result
+ */
+enum P4_EVENT_OPCODES {
+	P4_OPCODE(P4_EVENT_TC_DELIVER_MODE)		= P4_OPCODE_PACK(0x01, 0x01),
+	/*
+	 * MSR_P4_TC_ESCR0:	4, 5
+	 * MSR_P4_TC_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST)		= P4_OPCODE_PACK(0x03, 0x00),
+	/*
+	 * MSR_P4_BPU_ESCR0:	0, 1
+	 * MSR_P4_BPU_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_ITLB_REFERENCE)		= P4_OPCODE_PACK(0x18, 0x03),
+	/*
+	 * MSR_P4_ITLB_ESCR0:	0, 1
+	 * MSR_P4_ITLB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_MEMORY_CANCEL)		= P4_OPCODE_PACK(0x02, 0x05),
+	/*
+	 * MSR_P4_DAC_ESCR0:	8, 9
+	 * MSR_P4_DAC_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_MEMORY_COMPLETE)		= P4_OPCODE_PACK(0x08, 0x02),
+	/*
+	 * MSR_P4_SAAT_ESCR0:	8, 9
+	 * MSR_P4_SAAT_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY)		= P4_OPCODE_PACK(0x04, 0x02),
+	/*
+	 * MSR_P4_SAAT_ESCR0:	8, 9
+	 * MSR_P4_SAAT_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY)		= P4_OPCODE_PACK(0x05, 0x02),
+	/*
+	 * MSR_P4_SAAT_ESCR0:	8, 9
+	 * MSR_P4_SAAT_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY)		= P4_OPCODE_PACK(0x03, 0x02),
+	/*
+	 * MSR_P4_MOB_ESCR0:	0, 1
+	 * MSR_P4_MOB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE)		= P4_OPCODE_PACK(0x01, 0x04),
+	/*
+	 * MSR_P4_PMH_ESCR0:	0, 1
+	 * MSR_P4_PMH_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE)		= P4_OPCODE_PACK(0x0c, 0x07),
+	/*
+	 * MSR_P4_BSU_ESCR0:	0, 1
+	 * MSR_P4_BSU_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_IOQ_ALLOCATION)		= P4_OPCODE_PACK(0x03, 0x06),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES)		= P4_OPCODE_PACK(0x1a, 0x06),
+	/*
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY)		= P4_OPCODE_PACK(0x17, 0x06),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_BSQ_ALLOCATION)		= P4_OPCODE_PACK(0x05, 0x07),
+	/*
+	 * MSR_P4_BSU_ESCR0:	0, 1
+	 */
+
+	P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES)		= P4_OPCODE_PACK(0x06, 0x07),
+	/*
+	 * NOTE: no ESCR name in docs, it's guessed
+	 * MSR_P4_BSU_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST)		= P4_OPCODE_PACK(0x34, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_PACKED_SP_UOP)		= P4_OPCODE_PACK(0x08, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_PACKED_DP_UOP)		= P4_OPCODE_PACK(0x0c, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_SCALAR_SP_UOP)		= P4_OPCODE_PACK(0x0a, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_SCALAR_DP_UOP)		= P4_OPCODE_PACK(0x0e, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_64BIT_MMX_UOP)		= P4_OPCODE_PACK(0x02, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_128BIT_MMX_UOP)		= P4_OPCODE_PACK(0x1a, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_X87_FP_UOP)			= P4_OPCODE_PACK(0x04, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_TC_MISC)			= P4_OPCODE_PACK(0x06, 0x01),
+	/*
+	 * MSR_P4_TC_ESCR0:	4, 5
+	 * MSR_P4_TC_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS)		= P4_OPCODE_PACK(0x13, 0x06),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_TC_MS_XFER)			= P4_OPCODE_PACK(0x05, 0x00),
+	/*
+	 * MSR_P4_MS_ESCR0:	4, 5
+	 * MSR_P4_MS_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES)		= P4_OPCODE_PACK(0x09, 0x00),
+	/*
+	 * MSR_P4_MS_ESCR0:	4, 5
+	 * MSR_P4_MS_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE)	= P4_OPCODE_PACK(0x05, 0x02),
+	/*
+	 * MSR_P4_TBPU_ESCR0:	4, 5
+	 * MSR_P4_TBPU_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE)		= P4_OPCODE_PACK(0x04, 0x02),
+	/*
+	 * MSR_P4_TBPU_ESCR0:	4, 5
+	 * MSR_P4_TBPU_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_RESOURCE_STALL)		= P4_OPCODE_PACK(0x01, 0x01),
+	/*
+	 * MSR_P4_ALF_ESCR0:	12, 13, 16
+	 * MSR_P4_ALF_ESCR1:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_WC_BUFFER)			= P4_OPCODE_PACK(0x05, 0x05),
+	/*
+	 * MSR_P4_DAC_ESCR0:	8, 9
+	 * MSR_P4_DAC_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_B2B_CYCLES)			= P4_OPCODE_PACK(0x16, 0x03),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_BNR)				= P4_OPCODE_PACK(0x08, 0x03),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_SNOOP)			= P4_OPCODE_PACK(0x06, 0x03),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_RESPONSE)			= P4_OPCODE_PACK(0x04, 0x03),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_FRONT_END_EVENT)		= P4_OPCODE_PACK(0x08, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_EXECUTION_EVENT)		= P4_OPCODE_PACK(0x0c, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_REPLAY_EVENT)		= P4_OPCODE_PACK(0x09, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_INSTR_RETIRED)		= P4_OPCODE_PACK(0x02, 0x04),
+	/*
+	 * MSR_P4_CRU_ESCR0:	12, 13, 16
+	 * MSR_P4_CRU_ESCR1:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_UOPS_RETIRED)		= P4_OPCODE_PACK(0x01, 0x04),
+	/*
+	 * MSR_P4_CRU_ESCR0:	12, 13, 16
+	 * MSR_P4_CRU_ESCR1:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_UOP_TYPE)			= P4_OPCODE_PACK(0x02, 0x02),
+	/*
+	 * MSR_P4_RAT_ESCR0:	12, 13, 16
+	 * MSR_P4_RAT_ESCR1:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_BRANCH_RETIRED)		= P4_OPCODE_PACK(0x06, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED)	= P4_OPCODE_PACK(0x03, 0x04),
+	/*
+	 * MSR_P4_CRU_ESCR0:	12, 13, 16
+	 * MSR_P4_CRU_ESCR1:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_X87_ASSIST)			= P4_OPCODE_PACK(0x03, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_MACHINE_CLEAR)		= P4_OPCODE_PACK(0x02, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_INSTR_COMPLETED)		= P4_OPCODE_PACK(0x07, 0x04),
+	/*
+	 * MSR_P4_CRU_ESCR0:	12, 13, 16
+	 * MSR_P4_CRU_ESCR1:	14, 15, 17
+	 */
+};
+
+/*
+ * a caller should use P4_ESCR_EMASK_NAME helper to
+ * pick the EventMask needed, for example
+ *
+ *	P4_ESCR_EMASK_NAME(P4_EVENT_TC_DELIVER_MODE, DD)
+ */
+enum P4_ESCR_EMASKS {
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DD, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DB, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DI, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BD, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BB, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BI, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, ID, 6),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BPU_FETCH_REQUEST, TCMISS, 0),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, HIT, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, MISS, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, HIT_UK, 2),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_CANCEL, ST_RB_FULL, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_CANCEL, 64K_CONF, 3),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_COMPLETE, LSC, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_COMPLETE, SSC, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_LOAD_PORT_REPLAY, SPLIT_LD, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_STORE_PORT_REPLAY, SPLIT_ST, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, NO_STA, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, NO_STD, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, PARTIAL_DATA, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, UNALGN_ADDR, 5),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_PAGE_WALK_TYPE, DTMISS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_PAGE_WALK_TYPE, ITMISS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS, 10),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, DEFAULT, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, ALL_READ, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, ALL_WRITE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_UC, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WC, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WT, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WP, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WB, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, OWN, 13),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, OTHER, 14),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, PREFETCH, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, DEFAULT, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_READ, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_WRITE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_UC, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WC, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WT, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WP, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WB, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, OWN, 13),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, OTHER, 14),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, PREFETCH, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OTHER, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_DRV, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OWN, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OTHER, 5),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE0, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE1, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LEN0, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LEN1, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_IO_TYPE, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LOCK_TYPE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_CACHE_TYPE, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_SPLIT_TYPE, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_DEM_TYPE, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_ORD_TYPE, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE0, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE1, 12),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE2, 13),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE0, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE1, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN0, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN1, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_IO_TYPE, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LOCK_TYPE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_CACHE_TYPE, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_SPLIT_TYPE, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_DEM_TYPE, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_ORD_TYPE, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE0, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE1, 12),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE2, 13),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_SSE_INPUT_ASSIST, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_PACKED_SP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_PACKED_DP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_SCALAR_SP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_SCALAR_DP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_64BIT_MMX_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_128BIT_MMX_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_FP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_MISC, FLUSH, 4),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING, 0),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_MS_XFER, CISC, 0),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_BUILD, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_DELIVER, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_ROM, 2),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CONDITIONAL, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CALL, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, RETURN, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, INDIRECT, 4),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, CALL, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT, 4),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_RESOURCE_STALL, SBFULL, 5),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_WC_BUFFER, WCB_EVICTS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_WC_BUFFER, WCB_FULL_EVICTS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_FRONT_END_EVENT, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FRONT_END_EVENT, BOGUS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS0, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS1, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS2, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS3, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS0, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS1, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS2, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS3, 7),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_REPLAY_EVENT, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_REPLAY_EVENT, BOGUS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, NBOGUSTAG, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, BOGUSNTAG, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, BOGUSTAG, 3),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOPS_RETIRED, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOPS_RETIRED, BOGUS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_TYPE, TAGLOADS, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_TYPE, TAGSTORES, 2),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMNP, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMNM, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMTP, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMTM, 3),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS, 0),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, FPSU, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, FPSO, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, POAO, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, POAU, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, PREA, 4),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, CLEAR, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, MOCLEAR, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, SMCLEAR, 2),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, BOGUS, 1),
+};
+
+/* P4 PEBS: stale for a while */
+#define P4_PEBS_METRIC_MASK	0x00001fffU
+#define P4_PEBS_UOB_TAG		0x01000000U
+#define P4_PEBS_ENABLE		0x02000000U
+
+/* Replay metrics for MSR_IA32_PEBS_ENABLE and MSR_P4_PEBS_MATRIX_VERT */
+#define P4_PEBS__1stl_cache_load_miss_retired	0x3000001
+#define P4_PEBS__2ndl_cache_load_miss_retired	0x3000002
+#define P4_PEBS__dtlb_load_miss_retired		0x3000004
+#define P4_PEBS__dtlb_store_miss_retired	0x3000004
+#define P4_PEBS__dtlb_all_miss_retired		0x3000004
+#define P4_PEBS__tagged_mispred_branch		0x3018000
+#define P4_PEBS__mob_load_replay_retired	0x3000200
+#define P4_PEBS__split_load_retired		0x3000400
+#define P4_PEBS__split_store_retired		0x3000400
+
+#define P4_VERT__1stl_cache_load_miss_retired	0x0000001
+#define P4_VERT__2ndl_cache_load_miss_retired	0x0000001
+#define P4_VERT__dtlb_load_miss_retired		0x0000001
+#define P4_VERT__dtlb_store_miss_retired	0x0000002
+#define P4_VERT__dtlb_all_miss_retired		0x0000003
+#define P4_VERT__tagged_mispred_branch		0x0000010
+#define P4_VERT__mob_load_replay_retired	0x0000001
+#define P4_VERT__split_load_retired		0x0000001
+#define P4_VERT__split_store_retired		0x0000002
+
+enum P4_CACHE_EVENTS {
+	P4_CACHE__NONE,
+
+	P4_CACHE__1stl_cache_load_miss_retired,
+	P4_CACHE__2ndl_cache_load_miss_retired,
+	P4_CACHE__dtlb_load_miss_retired,
+	P4_CACHE__dtlb_store_miss_retired,
+	P4_CACHE__itlb_reference_hit,
+	P4_CACHE__itlb_reference_miss,
+
+	P4_CACHE__MAX
+};
+
+#endif /* PERF_EVENT_P4_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 543f48a058d5..04918340aa3b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -21,7 +21,6 @@ struct mm_struct;
 #include <asm/msr.h>
 #include <asm/desc_defs.h>
 #include <asm/nops.h>
-#include <asm/ds.h>
 
 #include <linux/personality.h>
 #include <linux/cpumask.h>
@@ -29,6 +28,7 @@ struct mm_struct;
 #include <linux/threads.h>
 #include <linux/math64.h>
 #include <linux/init.h>
+#include <linux/err.h>
 
 #define HBP_NUM 4
 /*
@@ -473,10 +473,6 @@ struct thread_struct {
 	unsigned long		iopl;
 	/* Max allowed port in the bitmap, in bytes: */
 	unsigned		io_bitmap_max;
-/* MSR_IA32_DEBUGCTLMSR value to switch in if TIF_DEBUGCTLMSR is set.  */
-	unsigned long	debugctlmsr;
-	/* Debug Store context; see asm/ds.h */
-	struct ds_context	*ds_ctx;
 };
 
 static inline unsigned long native_get_debugreg(int regno)
@@ -805,7 +801,7 @@ extern void cpu_init(void);
 
 static inline unsigned long get_debugctlmsr(void)
 {
-    unsigned long debugctlmsr = 0;
+	unsigned long debugctlmsr = 0;
 
 #ifndef CONFIG_X86_DEBUGCTLMSR
 	if (boot_cpu_data.x86 < 6)
@@ -813,21 +809,6 @@ static inline unsigned long get_debugctlmsr(void)
 #endif
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
 
-    return debugctlmsr;
-}
-
-static inline unsigned long get_debugctlmsr_on_cpu(int cpu)
-{
-	u64 debugctlmsr = 0;
-	u32 val1, val2;
-
-#ifndef CONFIG_X86_DEBUGCTLMSR
-	if (boot_cpu_data.x86 < 6)
-		return 0;
-#endif
-	rdmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, &val1, &val2);
-	debugctlmsr = val1 | ((u64)val2 << 32);
-
 	return debugctlmsr;
 }
 
@@ -840,18 +821,6 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr)
 	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
 }
 
-static inline void update_debugctlmsr_on_cpu(int cpu,
-					     unsigned long debugctlmsr)
-{
-#ifndef CONFIG_X86_DEBUGCTLMSR
-	if (boot_cpu_data.x86 < 6)
-		return;
-#endif
-	wrmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR,
-		     (u32)((u64)debugctlmsr),
-		     (u32)((u64)debugctlmsr >> 32));
-}
-
 /*
  * from system description table in BIOS. Mostly for MCA use, but
  * others may find it useful:
diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h
index 86723035a515..52b098a6eebb 100644
--- a/arch/x86/include/asm/ptrace-abi.h
+++ b/arch/x86/include/asm/ptrace-abi.h
@@ -82,61 +82,6 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
-
-/* configuration/status structure used in PTRACE_BTS_CONFIG and
-   PTRACE_BTS_STATUS commands.
-*/
-struct ptrace_bts_config {
-	/* requested or actual size of BTS buffer in bytes */
-	__u32 size;
-	/* bitmask of below flags */
-	__u32 flags;
-	/* buffer overflow signal */
-	__u32 signal;
-	/* actual size of bts_struct in bytes */
-	__u32 bts_size;
-};
-#endif /* __ASSEMBLY__ */
-
-#define PTRACE_BTS_O_TRACE	0x1 /* branch trace */
-#define PTRACE_BTS_O_SCHED	0x2 /* scheduling events w/ jiffies */
-#define PTRACE_BTS_O_SIGNAL     0x4 /* send SIG<signal> on buffer overflow
-				       instead of wrapping around */
-#define PTRACE_BTS_O_ALLOC	0x8 /* (re)allocate buffer */
-
-#define PTRACE_BTS_CONFIG	40
-/* Configure branch trace recording.
-   ADDR points to a struct ptrace_bts_config.
-   DATA gives the size of that buffer.
-   A new buffer is allocated, if requested in the flags.
-   An overflow signal may only be requested for new buffers.
-   Returns the number of bytes read.
-*/
-#define PTRACE_BTS_STATUS	41
-/* Return the current configuration in a struct ptrace_bts_config
-   pointed to by ADDR; DATA gives the size of that buffer.
-   Returns the number of bytes written.
-*/
-#define PTRACE_BTS_SIZE		42
-/* Return the number of available BTS records for draining.
-   DATA and ADDR are ignored.
-*/
-#define PTRACE_BTS_GET		43
-/* Get a single BTS record.
-   DATA defines the index into the BTS array, where 0 is the newest
-   entry, and higher indices refer to older entries.
-   ADDR is pointing to struct bts_struct (see asm/ds.h).
-*/
-#define PTRACE_BTS_CLEAR	44
-/* Clear the BTS buffer.
-   DATA and ADDR are ignored.
-*/
-#define PTRACE_BTS_DRAIN	45
-/* Read all available BTS records and clear the buffer.
-   ADDR points to an array of struct bts_struct.
-   DATA gives the size of that buffer.
-   BTS records are read from oldest to newest.
-   Returns number of BTS records drained.
-*/
+#endif
 
 #endif /* _ASM_X86_PTRACE_ABI_H */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 69a686a7dff0..78cd1ea94500 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -289,12 +289,6 @@ extern int do_get_thread_area(struct task_struct *p, int idx,
 extern int do_set_thread_area(struct task_struct *p, int idx,
 			      struct user_desc __user *info, int can_allocate);
 
-#ifdef CONFIG_X86_PTRACE_BTS
-extern void ptrace_bts_untrace(struct task_struct *tsk);
-
-#define arch_ptrace_untrace(tsk)	ptrace_bts_untrace(tsk)
-#endif /* CONFIG_X86_PTRACE_BTS */
-
 #endif /* __KERNEL__ */
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index e0d28901e969..d017ed5502e2 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -92,8 +92,7 @@ struct thread_info {
 #define TIF_IO_BITMAP		22	/* uses I/O bitmap */
 #define TIF_FREEZE		23	/* is freezing for suspend */
 #define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
-#define TIF_DEBUGCTLMSR		25	/* uses thread_struct.debugctlmsr */
-#define TIF_DS_AREA_MSR		26      /* uses thread_struct.ds_area_msr */
+#define TIF_BLOCKSTEP		25	/* set when we want DEBUGCTLMSR_BTF */
 #define TIF_LAZY_MMU_UPDATES	27	/* task is updating the mmu lazily */
 #define TIF_SYSCALL_TRACEPOINT	28	/* syscall tracepoint instrumentation */
 
@@ -115,8 +114,7 @@ struct thread_info {
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
 #define _TIF_FREEZE		(1 << TIF_FREEZE)
 #define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
-#define _TIF_DEBUGCTLMSR	(1 << TIF_DEBUGCTLMSR)
-#define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
+#define _TIF_BLOCKSTEP		(1 << TIF_BLOCKSTEP)
 #define _TIF_LAZY_MMU_UPDATES	(1 << TIF_LAZY_MMU_UPDATES)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 
@@ -147,7 +145,7 @@ struct thread_info {
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
-	(_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_NOTSC)
+	(_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP)
 
 #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index 2cae46c7c8a2..b2f2d2e05cec 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -1,4 +1,3 @@
-
 /*
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
@@ -15,13 +14,25 @@
 #define UV_MMR_ENABLE		(1UL << 63)
 
 /* ========================================================================= */
+/*                          UVH_BAU_DATA_BROADCAST                           */
+/* ========================================================================= */
+#define UVH_BAU_DATA_BROADCAST 0x61688UL
+#define UVH_BAU_DATA_BROADCAST_32 0x0440
+
+#define UVH_BAU_DATA_BROADCAST_ENABLE_SHFT 0
+#define UVH_BAU_DATA_BROADCAST_ENABLE_MASK 0x0000000000000001UL
+
+union uvh_bau_data_broadcast_u {
+    unsigned long	v;
+    struct uvh_bau_data_broadcast_s {
+	unsigned long	enable :  1;  /* RW */
+	unsigned long	rsvd_1_63: 63;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
 /*                           UVH_BAU_DATA_CONFIG                             */
 /* ========================================================================= */
-#define UVH_LB_BAU_MISC_CONTROL 0x320170UL
-#define UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT 15
-#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT 16
-#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x000000000bUL
-/* 1011 timebase 7 (168millisec) * 3 ticks -> 500ms */
 #define UVH_BAU_DATA_CONFIG 0x61680UL
 #define UVH_BAU_DATA_CONFIG_32 0x0438
 
@@ -604,6 +615,68 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0x0a70
 
 /* ========================================================================= */
+/*                         UVH_LB_BAU_MISC_CONTROL                           */
+/* ========================================================================= */
+#define UVH_LB_BAU_MISC_CONTROL 0x320170UL
+#define UVH_LB_BAU_MISC_CONTROL_32 0x00a10
+
+#define UVH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0
+#define UVH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL
+#define UVH_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT 8
+#define UVH_LB_BAU_MISC_CONTROL_APIC_MODE_MASK 0x0000000000000100UL
+#define UVH_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_SHFT 9
+#define UVH_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL
+#define UVH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10
+#define UVH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL
+#define UVH_LB_BAU_MISC_CONTROL_CSI_AGENT_PRESENCE_VECTOR_SHFT 11
+#define UVH_LB_BAU_MISC_CONTROL_CSI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
+#define UVH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14
+#define UVH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL
+#define UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15
+#define UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK 0x0000000000008000UL
+#define UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT 16
+#define UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK 0x00000000000f0000UL
+#define UVH_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_SHFT 20
+#define UVH_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_MASK 0x0000000000100000UL
+#define UVH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_SHFT 21
+#define UVH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_MASK 0x0000000000200000UL
+#define UVH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_SHFT 22
+#define UVH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_MASK 0x0000000000400000UL
+#define UVH_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_SHFT 23
+#define UVH_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_MASK 0x0000000000800000UL
+#define UVH_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_SHFT 24
+#define UVH_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000007000000UL
+#define UVH_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_SHFT 27
+#define UVH_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL
+#define UVH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28
+#define UVH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL
+#define UVH_LB_BAU_MISC_CONTROL_FUN_SHFT 48
+#define UVH_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL
+
+union uvh_lb_bau_misc_control_u {
+    unsigned long	v;
+    struct uvh_lb_bau_misc_control_s {
+	unsigned long	rejection_delay                    :  8;  /* RW */
+	unsigned long	apic_mode                          :  1;  /* RW */
+	unsigned long	force_broadcast                    :  1;  /* RW */
+	unsigned long	force_lock_nop                     :  1;  /* RW */
+	unsigned long	csi_agent_presence_vector          :  3;  /* RW */
+	unsigned long	descriptor_fetch_mode              :  1;  /* RW */
+	unsigned long	enable_intd_soft_ack_mode          :  1;  /* RW */
+	unsigned long	intd_soft_ack_timeout_period       :  4;  /* RW */
+	unsigned long	enable_dual_mapping_mode           :  1;  /* RW */
+	unsigned long	vga_io_port_decode_enable          :  1;  /* RW */
+	unsigned long	vga_io_port_16_bit_decode          :  1;  /* RW */
+	unsigned long	suppress_dest_registration         :  1;  /* RW */
+	unsigned long	programmed_initial_priority        :  3;  /* RW */
+	unsigned long	use_incoming_priority              :  1;  /* RW */
+	unsigned long	enable_programmed_initial_priority :  1;  /* RW */
+	unsigned long	rsvd_29_47                         : 19;  /*    */
+	unsigned long	fun                                : 16;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
 /*                     UVH_LB_BAU_SB_ACTIVATION_CONTROL                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL
@@ -681,334 +754,6 @@ union uvh_lb_bau_sb_descriptor_base_u {
 };
 
 /* ========================================================================= */
-/*                      UVH_LB_MCAST_AOERR0_RPT_ENABLE                       */
-/* ========================================================================= */
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE 0x50b20UL
-
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_OBESE_MSG_SHFT 0
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_OBESE_MSG_MASK 0x0000000000000001UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_DATA_SB_ERR_SHFT 1
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_DATA_SB_ERR_MASK 0x0000000000000002UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_NACK_BUFF_PARITY_SHFT 2
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_NACK_BUFF_PARITY_MASK 0x0000000000000004UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_TIMEOUT_SHFT 3
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_TIMEOUT_MASK 0x0000000000000008UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_INACTIVE_REPLY_SHFT 4
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_INACTIVE_REPLY_MASK 0x0000000000000010UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_UPGRADE_ERROR_SHFT 5
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_UPGRADE_ERROR_MASK 0x0000000000000020UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REG_COUNT_UNDERFLOW_SHFT 6
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REG_COUNT_UNDERFLOW_MASK 0x0000000000000040UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REP_OBESE_MSG_SHFT 7
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REP_OBESE_MSG_MASK 0x0000000000000080UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_RUNT_MSG_SHFT 8
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_RUNT_MSG_MASK 0x0000000000000100UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_OBESE_MSG_SHFT 9
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_OBESE_MSG_MASK 0x0000000000000200UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_DATA_SB_ERR_SHFT 10
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_DATA_SB_ERR_MASK 0x0000000000000400UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_RUNT_MSG_SHFT 11
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_RUNT_MSG_MASK 0x0000000000000800UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_OBESE_MSG_SHFT 12
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_OBESE_MSG_MASK 0x0000000000001000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_DATA_SB_ERR_SHFT 13
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_DATA_SB_ERR_MASK 0x0000000000002000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_COMMAND_ERR_SHFT 14
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_COMMAND_ERR_MASK 0x0000000000004000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_PEND_TIMEOUT_SHFT 15
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_PEND_TIMEOUT_MASK 0x0000000000008000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_RUNT_MSG_SHFT 16
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_RUNT_MSG_MASK 0x0000000000010000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_OBESE_MSG_SHFT 17
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_OBESE_MSG_MASK 0x0000000000020000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_DATA_SB_ERR_SHFT 18
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_DATA_SB_ERR_MASK 0x0000000000040000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_RUNT_MSG_SHFT 19
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_RUNT_MSG_MASK 0x0000000000080000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_OBESE_MSG_SHFT 20
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_OBESE_MSG_MASK 0x0000000000100000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_DATA_SB_ERR_SHFT 21
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_DATA_SB_ERR_MASK 0x0000000000200000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_AMO_TIMEOUT_SHFT 22
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_AMO_TIMEOUT_MASK 0x0000000000400000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_PUT_TIMEOUT_SHFT 23
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_PUT_TIMEOUT_MASK 0x0000000000800000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_SPURIOUS_EVENT_SHFT 24
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_SPURIOUS_EVENT_MASK 0x0000000001000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IOH_DESTINATION_TABLE_PARITY_SHFT 25
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IOH_DESTINATION_TABLE_PARITY_MASK 0x0000000002000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_HAD_ERROR_REPLY_SHFT 26
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_HAD_ERROR_REPLY_MASK 0x0000000004000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_TIMEOUT_SHFT 27
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_TIMEOUT_MASK 0x0000000008000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_LOCK_MANAGER_HAD_ERROR_REPLY_SHFT 28
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_LOCK_MANAGER_HAD_ERROR_REPLY_MASK 0x0000000010000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_HAD_ERROR_REPLY_SHFT 29
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_HAD_ERROR_REPLY_MASK 0x0000000020000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_TIMEOUT_SHFT 30
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_TIMEOUT_MASK 0x0000000040000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SB_ACTIVATION_OVERRUN_SHFT 31
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SB_ACTIVATION_OVERRUN_MASK 0x0000000080000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_HAD_ERROR_REPLY_SHFT 32
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_HAD_ERROR_REPLY_MASK 0x0000000100000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_TIMEOUT_SHFT 33
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_TIMEOUT_MASK 0x0000000200000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_0_PARITY_SHFT 34
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_0_PARITY_MASK 0x0000000400000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_1_PARITY_SHFT 35
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_1_PARITY_MASK 0x0000000800000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SOCKET_DESTINATION_TABLE_PARITY_SHFT 36
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SOCKET_DESTINATION_TABLE_PARITY_MASK 0x0000001000000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_BAU_REPLY_PAYLOAD_CORRUPTION_SHFT 37
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_BAU_REPLY_PAYLOAD_CORRUPTION_MASK 0x0000002000000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IO_PORT_DESTINATION_TABLE_PARITY_SHFT 38
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IO_PORT_DESTINATION_TABLE_PARITY_MASK 0x0000004000000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INTD_SOFT_ACK_TIMEOUT_SHFT 39
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INTD_SOFT_ACK_TIMEOUT_MASK 0x0000008000000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_OBESE_MSG_SHFT 40
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_OBESE_MSG_MASK 0x0000010000000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_COMMAND_ERR_SHFT 41
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_COMMAND_ERR_MASK 0x0000020000000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_TIMEOUT_SHFT 42
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_TIMEOUT_MASK 0x0000040000000000UL
-
-union uvh_lb_mcast_aoerr0_rpt_enable_u {
-    unsigned long	v;
-    struct uvh_lb_mcast_aoerr0_rpt_enable_s {
-	unsigned long	mcast_obese_msg                         :  1;  /* RW */
-	unsigned long	mcast_data_sb_err                       :  1;  /* RW */
-	unsigned long	mcast_nack_buff_parity                  :  1;  /* RW */
-	unsigned long	mcast_timeout                           :  1;  /* RW */
-	unsigned long	mcast_inactive_reply                    :  1;  /* RW */
-	unsigned long	mcast_upgrade_error                     :  1;  /* RW */
-	unsigned long	mcast_reg_count_underflow               :  1;  /* RW */
-	unsigned long	mcast_rep_obese_msg                     :  1;  /* RW */
-	unsigned long	ucache_req_runt_msg                     :  1;  /* RW */
-	unsigned long	ucache_req_obese_msg                    :  1;  /* RW */
-	unsigned long	ucache_req_data_sb_err                  :  1;  /* RW */
-	unsigned long	ucache_rep_runt_msg                     :  1;  /* RW */
-	unsigned long	ucache_rep_obese_msg                    :  1;  /* RW */
-	unsigned long	ucache_rep_data_sb_err                  :  1;  /* RW */
-	unsigned long	ucache_rep_command_err                  :  1;  /* RW */
-	unsigned long	ucache_pend_timeout                     :  1;  /* RW */
-	unsigned long	macc_req_runt_msg                       :  1;  /* RW */
-	unsigned long	macc_req_obese_msg                      :  1;  /* RW */
-	unsigned long	macc_req_data_sb_err                    :  1;  /* RW */
-	unsigned long	macc_rep_runt_msg                       :  1;  /* RW */
-	unsigned long	macc_rep_obese_msg                      :  1;  /* RW */
-	unsigned long	macc_rep_data_sb_err                    :  1;  /* RW */
-	unsigned long	macc_amo_timeout                        :  1;  /* RW */
-	unsigned long	macc_put_timeout                        :  1;  /* RW */
-	unsigned long	macc_spurious_event                     :  1;  /* RW */
-	unsigned long	ioh_destination_table_parity            :  1;  /* RW */
-	unsigned long	get_had_error_reply                     :  1;  /* RW */
-	unsigned long	get_timeout                             :  1;  /* RW */
-	unsigned long	lock_manager_had_error_reply            :  1;  /* RW */
-	unsigned long	put_had_error_reply                     :  1;  /* RW */
-	unsigned long	put_timeout                             :  1;  /* RW */
-	unsigned long	sb_activation_overrun                   :  1;  /* RW */
-	unsigned long	completed_gb_activation_had_error_reply :  1;  /* RW */
-	unsigned long	completed_gb_activation_timeout         :  1;  /* RW */
-	unsigned long	descriptor_buffer_0_parity              :  1;  /* RW */
-	unsigned long	descriptor_buffer_1_parity              :  1;  /* RW */
-	unsigned long	socket_destination_table_parity         :  1;  /* RW */
-	unsigned long	bau_reply_payload_corruption            :  1;  /* RW */
-	unsigned long	io_port_destination_table_parity        :  1;  /* RW */
-	unsigned long	intd_soft_ack_timeout                   :  1;  /* RW */
-	unsigned long	int_rep_obese_msg                       :  1;  /* RW */
-	unsigned long	int_rep_command_err                     :  1;  /* RW */
-	unsigned long	int_timeout                             :  1;  /* RW */
-	unsigned long	rsvd_43_63                              : 21;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                          UVH_LOCAL_INT0_CONFIG                            */
-/* ========================================================================= */
-#define UVH_LOCAL_INT0_CONFIG 0x61000UL
-
-#define UVH_LOCAL_INT0_CONFIG_VECTOR_SHFT 0
-#define UVH_LOCAL_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL
-#define UVH_LOCAL_INT0_CONFIG_DM_SHFT 8
-#define UVH_LOCAL_INT0_CONFIG_DM_MASK 0x0000000000000700UL
-#define UVH_LOCAL_INT0_CONFIG_DESTMODE_SHFT 11
-#define UVH_LOCAL_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL
-#define UVH_LOCAL_INT0_CONFIG_STATUS_SHFT 12
-#define UVH_LOCAL_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL
-#define UVH_LOCAL_INT0_CONFIG_P_SHFT 13
-#define UVH_LOCAL_INT0_CONFIG_P_MASK 0x0000000000002000UL
-#define UVH_LOCAL_INT0_CONFIG_T_SHFT 15
-#define UVH_LOCAL_INT0_CONFIG_T_MASK 0x0000000000008000UL
-#define UVH_LOCAL_INT0_CONFIG_M_SHFT 16
-#define UVH_LOCAL_INT0_CONFIG_M_MASK 0x0000000000010000UL
-#define UVH_LOCAL_INT0_CONFIG_APIC_ID_SHFT 32
-#define UVH_LOCAL_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
-
-union uvh_local_int0_config_u {
-    unsigned long	v;
-    struct uvh_local_int0_config_s {
-	unsigned long	vector_  :  8;  /* RW */
-	unsigned long	dm       :  3;  /* RW */
-	unsigned long	destmode :  1;  /* RW */
-	unsigned long	status   :  1;  /* RO */
-	unsigned long	p        :  1;  /* RO */
-	unsigned long	rsvd_14  :  1;  /*    */
-	unsigned long	t        :  1;  /* RO */
-	unsigned long	m        :  1;  /* RW */
-	unsigned long	rsvd_17_31: 15;  /*    */
-	unsigned long	apic_id  : 32;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                          UVH_LOCAL_INT0_ENABLE                            */
-/* ========================================================================= */
-#define UVH_LOCAL_INT0_ENABLE 0x65000UL
-
-#define UVH_LOCAL_INT0_ENABLE_LB_HCERR_SHFT 0
-#define UVH_LOCAL_INT0_ENABLE_LB_HCERR_MASK 0x0000000000000001UL
-#define UVH_LOCAL_INT0_ENABLE_GR0_HCERR_SHFT 1
-#define UVH_LOCAL_INT0_ENABLE_GR0_HCERR_MASK 0x0000000000000002UL
-#define UVH_LOCAL_INT0_ENABLE_GR1_HCERR_SHFT 2
-#define UVH_LOCAL_INT0_ENABLE_GR1_HCERR_MASK 0x0000000000000004UL
-#define UVH_LOCAL_INT0_ENABLE_LH_HCERR_SHFT 3
-#define UVH_LOCAL_INT0_ENABLE_LH_HCERR_MASK 0x0000000000000008UL
-#define UVH_LOCAL_INT0_ENABLE_RH_HCERR_SHFT 4
-#define UVH_LOCAL_INT0_ENABLE_RH_HCERR_MASK 0x0000000000000010UL
-#define UVH_LOCAL_INT0_ENABLE_XN_HCERR_SHFT 5
-#define UVH_LOCAL_INT0_ENABLE_XN_HCERR_MASK 0x0000000000000020UL
-#define UVH_LOCAL_INT0_ENABLE_SI_HCERR_SHFT 6
-#define UVH_LOCAL_INT0_ENABLE_SI_HCERR_MASK 0x0000000000000040UL
-#define UVH_LOCAL_INT0_ENABLE_LB_AOERR0_SHFT 7
-#define UVH_LOCAL_INT0_ENABLE_LB_AOERR0_MASK 0x0000000000000080UL
-#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR0_SHFT 8
-#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR0_MASK 0x0000000000000100UL
-#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR0_SHFT 9
-#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR0_MASK 0x0000000000000200UL
-#define UVH_LOCAL_INT0_ENABLE_LH_AOERR0_SHFT 10
-#define UVH_LOCAL_INT0_ENABLE_LH_AOERR0_MASK 0x0000000000000400UL
-#define UVH_LOCAL_INT0_ENABLE_RH_AOERR0_SHFT 11
-#define UVH_LOCAL_INT0_ENABLE_RH_AOERR0_MASK 0x0000000000000800UL
-#define UVH_LOCAL_INT0_ENABLE_XN_AOERR0_SHFT 12
-#define UVH_LOCAL_INT0_ENABLE_XN_AOERR0_MASK 0x0000000000001000UL
-#define UVH_LOCAL_INT0_ENABLE_SI_AOERR0_SHFT 13
-#define UVH_LOCAL_INT0_ENABLE_SI_AOERR0_MASK 0x0000000000002000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_AOERR1_SHFT 14
-#define UVH_LOCAL_INT0_ENABLE_LB_AOERR1_MASK 0x0000000000004000UL
-#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR1_SHFT 15
-#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR1_MASK 0x0000000000008000UL
-#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR1_SHFT 16
-#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR1_MASK 0x0000000000010000UL
-#define UVH_LOCAL_INT0_ENABLE_LH_AOERR1_SHFT 17
-#define UVH_LOCAL_INT0_ENABLE_LH_AOERR1_MASK 0x0000000000020000UL
-#define UVH_LOCAL_INT0_ENABLE_RH_AOERR1_SHFT 18
-#define UVH_LOCAL_INT0_ENABLE_RH_AOERR1_MASK 0x0000000000040000UL
-#define UVH_LOCAL_INT0_ENABLE_XN_AOERR1_SHFT 19
-#define UVH_LOCAL_INT0_ENABLE_XN_AOERR1_MASK 0x0000000000080000UL
-#define UVH_LOCAL_INT0_ENABLE_SI_AOERR1_SHFT 20
-#define UVH_LOCAL_INT0_ENABLE_SI_AOERR1_MASK 0x0000000000100000UL
-#define UVH_LOCAL_INT0_ENABLE_RH_VPI_INT_SHFT 21
-#define UVH_LOCAL_INT0_ENABLE_RH_VPI_INT_MASK 0x0000000000200000UL
-#define UVH_LOCAL_INT0_ENABLE_SYSTEM_SHUTDOWN_INT_SHFT 22
-#define UVH_LOCAL_INT0_ENABLE_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_0_SHFT 23
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_0_MASK 0x0000000000800000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_1_SHFT 24
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_1_MASK 0x0000000001000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_2_SHFT 25
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_2_MASK 0x0000000002000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_3_SHFT 26
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_3_MASK 0x0000000004000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_4_SHFT 27
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_4_MASK 0x0000000008000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_5_SHFT 28
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_5_MASK 0x0000000010000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_6_SHFT 29
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_6_MASK 0x0000000020000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_7_SHFT 30
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_7_MASK 0x0000000040000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_8_SHFT 31
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_8_MASK 0x0000000080000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_9_SHFT 32
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_9_MASK 0x0000000100000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_10_SHFT 33
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_10_MASK 0x0000000200000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_11_SHFT 34
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_11_MASK 0x0000000400000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_12_SHFT 35
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_12_MASK 0x0000000800000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_13_SHFT 36
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_13_MASK 0x0000001000000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_14_SHFT 37
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_14_MASK 0x0000002000000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_15_SHFT 38
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_15_MASK 0x0000004000000000UL
-#define UVH_LOCAL_INT0_ENABLE_L1_NMI_INT_SHFT 39
-#define UVH_LOCAL_INT0_ENABLE_L1_NMI_INT_MASK 0x0000008000000000UL
-#define UVH_LOCAL_INT0_ENABLE_STOP_CLOCK_SHFT 40
-#define UVH_LOCAL_INT0_ENABLE_STOP_CLOCK_MASK 0x0000010000000000UL
-#define UVH_LOCAL_INT0_ENABLE_ASIC_TO_L1_SHFT 41
-#define UVH_LOCAL_INT0_ENABLE_ASIC_TO_L1_MASK 0x0000020000000000UL
-#define UVH_LOCAL_INT0_ENABLE_L1_TO_ASIC_SHFT 42
-#define UVH_LOCAL_INT0_ENABLE_L1_TO_ASIC_MASK 0x0000040000000000UL
-#define UVH_LOCAL_INT0_ENABLE_LTC_INT_SHFT 43
-#define UVH_LOCAL_INT0_ENABLE_LTC_INT_MASK 0x0000080000000000UL
-#define UVH_LOCAL_INT0_ENABLE_LA_SEQ_TRIGGER_SHFT 44
-#define UVH_LOCAL_INT0_ENABLE_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL
-
-union uvh_local_int0_enable_u {
-    unsigned long	v;
-    struct uvh_local_int0_enable_s {
-	unsigned long	lb_hcerr            :  1;  /* RW */
-	unsigned long	gr0_hcerr           :  1;  /* RW */
-	unsigned long	gr1_hcerr           :  1;  /* RW */
-	unsigned long	lh_hcerr            :  1;  /* RW */
-	unsigned long	rh_hcerr            :  1;  /* RW */
-	unsigned long	xn_hcerr            :  1;  /* RW */
-	unsigned long	si_hcerr            :  1;  /* RW */
-	unsigned long	lb_aoerr0           :  1;  /* RW */
-	unsigned long	gr0_aoerr0          :  1;  /* RW */
-	unsigned long	gr1_aoerr0          :  1;  /* RW */
-	unsigned long	lh_aoerr0           :  1;  /* RW */
-	unsigned long	rh_aoerr0           :  1;  /* RW */
-	unsigned long	xn_aoerr0           :  1;  /* RW */
-	unsigned long	si_aoerr0           :  1;  /* RW */
-	unsigned long	lb_aoerr1           :  1;  /* RW */
-	unsigned long	gr0_aoerr1          :  1;  /* RW */
-	unsigned long	gr1_aoerr1          :  1;  /* RW */
-	unsigned long	lh_aoerr1           :  1;  /* RW */
-	unsigned long	rh_aoerr1           :  1;  /* RW */
-	unsigned long	xn_aoerr1           :  1;  /* RW */
-	unsigned long	si_aoerr1           :  1;  /* RW */
-	unsigned long	rh_vpi_int          :  1;  /* RW */
-	unsigned long	system_shutdown_int :  1;  /* RW */
-	unsigned long	lb_irq_int_0        :  1;  /* RW */
-	unsigned long	lb_irq_int_1        :  1;  /* RW */
-	unsigned long	lb_irq_int_2        :  1;  /* RW */
-	unsigned long	lb_irq_int_3        :  1;  /* RW */
-	unsigned long	lb_irq_int_4        :  1;  /* RW */
-	unsigned long	lb_irq_int_5        :  1;  /* RW */
-	unsigned long	lb_irq_int_6        :  1;  /* RW */
-	unsigned long	lb_irq_int_7        :  1;  /* RW */
-	unsigned long	lb_irq_int_8        :  1;  /* RW */
-	unsigned long	lb_irq_int_9        :  1;  /* RW */
-	unsigned long	lb_irq_int_10       :  1;  /* RW */
-	unsigned long	lb_irq_int_11       :  1;  /* RW */
-	unsigned long	lb_irq_int_12       :  1;  /* RW */
-	unsigned long	lb_irq_int_13       :  1;  /* RW */
-	unsigned long	lb_irq_int_14       :  1;  /* RW */
-	unsigned long	lb_irq_int_15       :  1;  /* RW */
-	unsigned long	l1_nmi_int          :  1;  /* RW */
-	unsigned long	stop_clock          :  1;  /* RW */
-	unsigned long	asic_to_l1          :  1;  /* RW */
-	unsigned long	l1_to_asic          :  1;  /* RW */
-	unsigned long	ltc_int             :  1;  /* RW */
-	unsigned long	la_seq_trigger      :  1;  /* RW */
-	unsigned long	rsvd_45_63          : 19;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
 /*                               UVH_NODE_ID                                 */
 /* ========================================================================= */
 #define UVH_NODE_ID 0x0UL
@@ -1112,26 +857,6 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
 };
 
 /* ========================================================================= */
-/*                    UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR                      */
-/* ========================================================================= */
-#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR 0x1600020UL
-
-#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_SHFT 26
-#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
-#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
-#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
-
-union uvh_rh_gam_cfg_overlay_config_mmr_u {
-    unsigned long	v;
-    struct uvh_rh_gam_cfg_overlay_config_mmr_s {
-	unsigned long	rsvd_0_25: 26;  /*    */
-	unsigned long	base   : 20;  /* RW */
-	unsigned long	rsvd_46_62: 17;  /*    */
-	unsigned long	enable :  1;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
 /*                    UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR                      */
 /* ========================================================================= */
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL
@@ -1263,101 +988,6 @@ union uvh_rtc1_int_config_u {
 };
 
 /* ========================================================================= */
-/*                           UVH_RTC2_INT_CONFIG                             */
-/* ========================================================================= */
-#define UVH_RTC2_INT_CONFIG 0x61600UL
-
-#define UVH_RTC2_INT_CONFIG_VECTOR_SHFT 0
-#define UVH_RTC2_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL
-#define UVH_RTC2_INT_CONFIG_DM_SHFT 8
-#define UVH_RTC2_INT_CONFIG_DM_MASK 0x0000000000000700UL
-#define UVH_RTC2_INT_CONFIG_DESTMODE_SHFT 11
-#define UVH_RTC2_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL
-#define UVH_RTC2_INT_CONFIG_STATUS_SHFT 12
-#define UVH_RTC2_INT_CONFIG_STATUS_MASK 0x0000000000001000UL
-#define UVH_RTC2_INT_CONFIG_P_SHFT 13
-#define UVH_RTC2_INT_CONFIG_P_MASK 0x0000000000002000UL
-#define UVH_RTC2_INT_CONFIG_T_SHFT 15
-#define UVH_RTC2_INT_CONFIG_T_MASK 0x0000000000008000UL
-#define UVH_RTC2_INT_CONFIG_M_SHFT 16
-#define UVH_RTC2_INT_CONFIG_M_MASK 0x0000000000010000UL
-#define UVH_RTC2_INT_CONFIG_APIC_ID_SHFT 32
-#define UVH_RTC2_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
-
-union uvh_rtc2_int_config_u {
-    unsigned long	v;
-    struct uvh_rtc2_int_config_s {
-	unsigned long	vector_  :  8;  /* RW */
-	unsigned long	dm       :  3;  /* RW */
-	unsigned long	destmode :  1;  /* RW */
-	unsigned long	status   :  1;  /* RO */
-	unsigned long	p        :  1;  /* RO */
-	unsigned long	rsvd_14  :  1;  /*    */
-	unsigned long	t        :  1;  /* RO */
-	unsigned long	m        :  1;  /* RW */
-	unsigned long	rsvd_17_31: 15;  /*    */
-	unsigned long	apic_id  : 32;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                           UVH_RTC3_INT_CONFIG                             */
-/* ========================================================================= */
-#define UVH_RTC3_INT_CONFIG 0x61640UL
-
-#define UVH_RTC3_INT_CONFIG_VECTOR_SHFT 0
-#define UVH_RTC3_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL
-#define UVH_RTC3_INT_CONFIG_DM_SHFT 8
-#define UVH_RTC3_INT_CONFIG_DM_MASK 0x0000000000000700UL
-#define UVH_RTC3_INT_CONFIG_DESTMODE_SHFT 11
-#define UVH_RTC3_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL
-#define UVH_RTC3_INT_CONFIG_STATUS_SHFT 12
-#define UVH_RTC3_INT_CONFIG_STATUS_MASK 0x0000000000001000UL
-#define UVH_RTC3_INT_CONFIG_P_SHFT 13
-#define UVH_RTC3_INT_CONFIG_P_MASK 0x0000000000002000UL
-#define UVH_RTC3_INT_CONFIG_T_SHFT 15
-#define UVH_RTC3_INT_CONFIG_T_MASK 0x0000000000008000UL
-#define UVH_RTC3_INT_CONFIG_M_SHFT 16
-#define UVH_RTC3_INT_CONFIG_M_MASK 0x0000000000010000UL
-#define UVH_RTC3_INT_CONFIG_APIC_ID_SHFT 32
-#define UVH_RTC3_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
-
-union uvh_rtc3_int_config_u {
-    unsigned long	v;
-    struct uvh_rtc3_int_config_s {
-	unsigned long	vector_  :  8;  /* RW */
-	unsigned long	dm       :  3;  /* RW */
-	unsigned long	destmode :  1;  /* RW */
-	unsigned long	status   :  1;  /* RO */
-	unsigned long	p        :  1;  /* RO */
-	unsigned long	rsvd_14  :  1;  /*    */
-	unsigned long	t        :  1;  /* RO */
-	unsigned long	m        :  1;  /* RW */
-	unsigned long	rsvd_17_31: 15;  /*    */
-	unsigned long	apic_id  : 32;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                            UVH_RTC_INC_RATIO                              */
-/* ========================================================================= */
-#define UVH_RTC_INC_RATIO 0x350000UL
-
-#define UVH_RTC_INC_RATIO_FRACTION_SHFT 0
-#define UVH_RTC_INC_RATIO_FRACTION_MASK 0x00000000000fffffUL
-#define UVH_RTC_INC_RATIO_RATIO_SHFT 20
-#define UVH_RTC_INC_RATIO_RATIO_MASK 0x0000000000700000UL
-
-union uvh_rtc_inc_ratio_u {
-    unsigned long	v;
-    struct uvh_rtc_inc_ratio_s {
-	unsigned long	fraction : 20;  /* RW */
-	unsigned long	ratio    :  3;  /* RW */
-	unsigned long	rsvd_23_63: 41;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
 /*                          UVH_SI_ADDR_MAP_CONFIG                           */
 /* ========================================================================= */
 #define UVH_SI_ADDR_MAP_CONFIG 0xc80000UL
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 4c58352209e0..e77b22083721 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -47,8 +47,6 @@ obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
 obj-y				+= process.o
 obj-y				+= i387.o xsave.o
 obj-y				+= ptrace.o
-obj-$(CONFIG_X86_DS)		+= ds.o
-obj-$(CONFIG_X86_DS_SELFTEST)		+= ds_selftest.o
 obj-$(CONFIG_X86_32)		+= tls.o
 obj-$(CONFIG_IA32_EMULATION)	+= tls.o
 obj-y				+= step.o
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index c085d52dbaf2..e46f98f36e31 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -735,9 +735,6 @@ void __init uv_system_init(void)
 		uv_node_to_blade[nid] = blade;
 		uv_cpu_to_blade[cpu] = blade;
 		max_pnode = max(pnode, max_pnode);
-
-		printk(KERN_DEBUG "UV: cpu %d, apicid 0x%x, pnode %d, nid %d, lcpu %d, blade %d\n",
-			cpu, apicid, pnode, nid, lcpu, blade);
 	}
 
 	/* Add blade/pnode info for nodes without cpus */
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 031aa887b0eb..c4f9182ca3ac 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1224,7 +1224,7 @@ static void reinit_timer(void)
 #ifdef INIT_TIMER_AFTER_SUSPEND
 	unsigned long flags;
 
-	spin_lock_irqsave(&i8253_lock, flags);
+	raw_spin_lock_irqsave(&i8253_lock, flags);
 	/* set the clock to HZ */
 	outb_pit(0x34, PIT_MODE);		/* binary, mode 2, LSB/MSB, ch 0 */
 	udelay(10);
@@ -1232,7 +1232,7 @@ static void reinit_timer(void)
 	udelay(10);
 	outb_pit(LATCH >> 8, PIT_CH0);	/* MSB */
 	udelay(10);
-	spin_unlock_irqrestore(&i8253_lock, flags);
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
 #endif
 }
 
diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index 97ad79cdf688..fd1fc1902a47 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -30,8 +30,9 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 	const struct cpuid_bit *cb;
 
 	static const struct cpuid_bit __cpuinitconst cpuid_bits[] = {
-		{ X86_FEATURE_IDA, CR_EAX, 1, 0x00000006 },
-		{ X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006 },
+		{ X86_FEATURE_IDA,   CR_EAX, 1, 0x00000006 },
+		{ X86_FEATURE_ARAT,  CR_EAX, 2, 0x00000006 },
+		{ X86_FEATURE_CPB,   CR_EDX, 9, 0x80000007 },
 		{ X86_FEATURE_NPT,   CR_EDX, 0, 0x8000000a },
 		{ X86_FEATURE_LBRV,  CR_EDX, 1, 0x8000000a },
 		{ X86_FEATURE_SVML,  CR_EDX, 2, 0x8000000a },
@@ -53,6 +54,14 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 		if (regs[cb->reg] & (1 << cb->bit))
 			set_cpu_cap(c, cb->feature);
 	}
+
+	/*
+	 * common AMD/Intel features
+	 */
+	if (c->cpuid_level >= 6) {
+		if (cpuid_ecx(6) & 0x1)
+			set_cpu_cap(c, X86_FEATURE_APERFMPERF);
+	}
 }
 
 /* leaf 0xb SMT level */
diff --git a/arch/x86/kernel/cpu/cpufreq/Makefile b/arch/x86/kernel/cpu/cpufreq/Makefile
index 1840c0a5170b..bd54bf67e6fb 100644
--- a/arch/x86/kernel/cpu/cpufreq/Makefile
+++ b/arch/x86/kernel/cpu/cpufreq/Makefile
@@ -2,8 +2,8 @@
 # K8 systems. ACPI is preferred to all other hardware-specific drivers.
 # speedstep-* is preferred over p4-clockmod.
 
-obj-$(CONFIG_X86_POWERNOW_K8)		+= powernow-k8.o
-obj-$(CONFIG_X86_ACPI_CPUFREQ)		+= acpi-cpufreq.o
+obj-$(CONFIG_X86_POWERNOW_K8)		+= powernow-k8.o mperf.o
+obj-$(CONFIG_X86_ACPI_CPUFREQ)		+= acpi-cpufreq.o mperf.o
 obj-$(CONFIG_X86_PCC_CPUFREQ)		+= pcc-cpufreq.o
 obj-$(CONFIG_X86_POWERNOW_K6)		+= powernow-k6.o
 obj-$(CONFIG_X86_POWERNOW_K7)		+= powernow-k7.o
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 459168083b77..1d3cddaa40ee 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -46,6 +46,7 @@
 #include <asm/msr.h>
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
+#include "mperf.h"
 
 #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
 		"acpi-cpufreq", msg)
@@ -71,8 +72,6 @@ struct acpi_cpufreq_data {
 
 static DEFINE_PER_CPU(struct acpi_cpufreq_data *, acfreq_data);
 
-static DEFINE_PER_CPU(struct aperfmperf, acfreq_old_perf);
-
 /* acpi_perf_data is a pointer to percpu data. */
 static struct acpi_processor_performance *acpi_perf_data;
 
@@ -240,45 +239,6 @@ static u32 get_cur_val(const struct cpumask *mask)
 	return cmd.val;
 }
 
-/* Called via smp_call_function_single(), on the target CPU */
-static void read_measured_perf_ctrs(void *_cur)
-{
-	struct aperfmperf *am = _cur;
-
-	get_aperfmperf(am);
-}
-
-/*
- * Return the measured active (C0) frequency on this CPU since last call
- * to this function.
- * Input: cpu number
- * Return: Average CPU frequency in terms of max frequency (zero on error)
- *
- * We use IA32_MPERF and IA32_APERF MSRs to get the measured performance
- * over a period of time, while CPU is in C0 state.
- * IA32_MPERF counts at the rate of max advertised frequency
- * IA32_APERF counts at the rate of actual CPU frequency
- * Only IA32_APERF/IA32_MPERF ratio is architecturally defined and
- * no meaning should be associated with absolute values of these MSRs.
- */
-static unsigned int get_measured_perf(struct cpufreq_policy *policy,
-				      unsigned int cpu)
-{
-	struct aperfmperf perf;
-	unsigned long ratio;
-	unsigned int retval;
-
-	if (smp_call_function_single(cpu, read_measured_perf_ctrs, &perf, 1))
-		return 0;
-
-	ratio = calc_aperfmperf_ratio(&per_cpu(acfreq_old_perf, cpu), &perf);
-	per_cpu(acfreq_old_perf, cpu) = perf;
-
-	retval = (policy->cpuinfo.max_freq * ratio) >> APERFMPERF_SHIFT;
-
-	return retval;
-}
-
 static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 {
 	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, cpu);
@@ -702,7 +662,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 	/* Check for APERF/MPERF support in hardware */
 	if (cpu_has(c, X86_FEATURE_APERFMPERF))
-		acpi_cpufreq_driver.getavg = get_measured_perf;
+		acpi_cpufreq_driver.getavg = cpufreq_get_measured_perf;
 
 	dprintk("CPU%u - ACPI performance management activated.\n", cpu);
 	for (i = 0; i < perf->state_count; i++)
diff --git a/arch/x86/kernel/cpu/cpufreq/mperf.c b/arch/x86/kernel/cpu/cpufreq/mperf.c
new file mode 100644
index 000000000000..911e193018ae
--- /dev/null
+++ b/arch/x86/kernel/cpu/cpufreq/mperf.c
@@ -0,0 +1,51 @@
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/cpufreq.h>
+#include <linux/slab.h>
+
+#include "mperf.h"
+
+static DEFINE_PER_CPU(struct aperfmperf, acfreq_old_perf);
+
+/* Called via smp_call_function_single(), on the target CPU */
+static void read_measured_perf_ctrs(void *_cur)
+{
+	struct aperfmperf *am = _cur;
+
+	get_aperfmperf(am);
+}
+
+/*
+ * Return the measured active (C0) frequency on this CPU since last call
+ * to this function.
+ * Input: cpu number
+ * Return: Average CPU frequency in terms of max frequency (zero on error)
+ *
+ * We use IA32_MPERF and IA32_APERF MSRs to get the measured performance
+ * over a period of time, while CPU is in C0 state.
+ * IA32_MPERF counts at the rate of max advertised frequency
+ * IA32_APERF counts at the rate of actual CPU frequency
+ * Only IA32_APERF/IA32_MPERF ratio is architecturally defined and
+ * no meaning should be associated with absolute values of these MSRs.
+ */
+unsigned int cpufreq_get_measured_perf(struct cpufreq_policy *policy,
+					unsigned int cpu)
+{
+	struct aperfmperf perf;
+	unsigned long ratio;
+	unsigned int retval;
+
+	if (smp_call_function_single(cpu, read_measured_perf_ctrs, &perf, 1))
+		return 0;
+
+	ratio = calc_aperfmperf_ratio(&per_cpu(acfreq_old_perf, cpu), &perf);
+	per_cpu(acfreq_old_perf, cpu) = perf;
+
+	retval = (policy->cpuinfo.max_freq * ratio) >> APERFMPERF_SHIFT;
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(cpufreq_get_measured_perf);
+MODULE_LICENSE("GPL");
diff --git a/arch/x86/kernel/cpu/cpufreq/mperf.h b/arch/x86/kernel/cpu/cpufreq/mperf.h
new file mode 100644
index 000000000000..5dbf2950dc22
--- /dev/null
+++ b/arch/x86/kernel/cpu/cpufreq/mperf.h
@@ -0,0 +1,9 @@
+/*
+ *  (c) 2010 Advanced Micro Devices, Inc.
+ *  Your use of this code is subject to the terms and conditions of the
+ *  GNU general public license version 2. See "COPYING" or
+ *  http://www.gnu.org/licenses/gpl.html
+ */
+
+unsigned int cpufreq_get_measured_perf(struct cpufreq_policy *policy,
+					unsigned int cpu);
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 062f56223bed..a267dbd64b8e 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1,6 +1,5 @@
-
 /*
- *   (c) 2003-2006 Advanced Micro Devices, Inc.
+ *   (c) 2003-2010 Advanced Micro Devices, Inc.
  *  Your use of this code is subject to the terms and conditions of the
  *  GNU general public license version 2. See "COPYING" or
  *  http://www.gnu.org/licenses/gpl.html
@@ -46,6 +45,7 @@
 #define PFX "powernow-k8: "
 #define VERSION "version 2.20.00"
 #include "powernow-k8.h"
+#include "mperf.h"
 
 /* serialize freq changes  */
 static DEFINE_MUTEX(fidvid_mutex);
@@ -54,6 +54,12 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
 
 static int cpu_family = CPU_OPTERON;
 
+/* core performance boost */
+static bool cpb_capable, cpb_enabled;
+static struct msr __percpu *msrs;
+
+static struct cpufreq_driver cpufreq_amd64_driver;
+
 #ifndef CONFIG_SMP
 static inline const struct cpumask *cpu_core_mask(int cpu)
 {
@@ -931,7 +937,8 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data,
 		powernow_table[i].index = index;
 
 		/* Frequency may be rounded for these */
-		if (boot_cpu_data.x86 == 0x10 || boot_cpu_data.x86 == 0x11) {
+		if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10)
+				 || boot_cpu_data.x86 == 0x11) {
 			powernow_table[i].frequency =
 				freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7);
 		} else
@@ -1250,6 +1257,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 	struct powernow_k8_data *data;
 	struct init_on_cpu init_on_cpu;
 	int rc;
+	struct cpuinfo_x86 *c = &cpu_data(pol->cpu);
 
 	if (!cpu_online(pol->cpu))
 		return -ENODEV;
@@ -1324,6 +1332,10 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 		return -EINVAL;
 	}
 
+	/* Check for APERF/MPERF support in hardware */
+	if (cpu_has(c, X86_FEATURE_APERFMPERF))
+		cpufreq_amd64_driver.getavg = cpufreq_get_measured_perf;
+
 	cpufreq_frequency_table_get_attr(data->powernow_table, pol->cpu);
 
 	if (cpu_family == CPU_HW_PSTATE)
@@ -1395,8 +1407,77 @@ out:
 	return khz;
 }
 
+static void _cpb_toggle_msrs(bool t)
+{
+	int cpu;
+
+	get_online_cpus();
+
+	rdmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs);
+
+	for_each_cpu(cpu, cpu_online_mask) {
+		struct msr *reg = per_cpu_ptr(msrs, cpu);
+		if (t)
+			reg->l &= ~BIT(25);
+		else
+			reg->l |= BIT(25);
+	}
+	wrmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs);
+
+	put_online_cpus();
+}
+
+/*
+ * Switch on/off core performance boosting.
+ *
+ * 0=disable
+ * 1=enable.
+ */
+static void cpb_toggle(bool t)
+{
+	if (!cpb_capable)
+		return;
+
+	if (t && !cpb_enabled) {
+		cpb_enabled = true;
+		_cpb_toggle_msrs(t);
+		printk(KERN_INFO PFX "Core Boosting enabled.\n");
+	} else if (!t && cpb_enabled) {
+		cpb_enabled = false;
+		_cpb_toggle_msrs(t);
+		printk(KERN_INFO PFX "Core Boosting disabled.\n");
+	}
+}
+
+static ssize_t store_cpb(struct cpufreq_policy *policy, const char *buf,
+				 size_t count)
+{
+	int ret = -EINVAL;
+	unsigned long val = 0;
+
+	ret = strict_strtoul(buf, 10, &val);
+	if (!ret && (val == 0 || val == 1) && cpb_capable)
+		cpb_toggle(val);
+	else
+		return -EINVAL;
+
+	return count;
+}
+
+static ssize_t show_cpb(struct cpufreq_policy *policy, char *buf)
+{
+	return sprintf(buf, "%u\n", cpb_enabled);
+}
+
+#define define_one_rw(_name) \
+static struct freq_attr _name = \
+__ATTR(_name, 0644, show_##_name, store_##_name)
+
+define_one_rw(cpb);
+
 static struct freq_attr *powernow_k8_attr[] = {
 	&cpufreq_freq_attr_scaling_available_freqs,
+	&cpb,
 	NULL,
 };
 
@@ -1412,10 +1493,51 @@ static struct cpufreq_driver cpufreq_amd64_driver = {
 	.attr		= powernow_k8_attr,
 };
 
+/*
+ * Clear the boost-disable flag on the CPU_DOWN path so that this cpu
+ * cannot block the remaining ones from boosting. On the CPU_UP path we
+ * simply keep the boost-disable flag in sync with the current global
+ * state.
+ */
+static int __cpuinit cpb_notify(struct notifier_block *nb, unsigned long action,
+				void *hcpu)
+{
+	unsigned cpu = (long)hcpu;
+	u32 lo, hi;
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+
+		if (!cpb_enabled) {
+			rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi);
+			lo |= BIT(25);
+			wrmsr_on_cpu(cpu, MSR_K7_HWCR, lo, hi);
+		}
+		break;
+
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+		rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi);
+		lo &= ~BIT(25);
+		wrmsr_on_cpu(cpu, MSR_K7_HWCR, lo, hi);
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata cpb_nb = {
+	.notifier_call		= cpb_notify,
+};
+
 /* driver entry point for init */
 static int __cpuinit powernowk8_init(void)
 {
-	unsigned int i, supported_cpus = 0;
+	unsigned int i, supported_cpus = 0, cpu;
 
 	for_each_online_cpu(i) {
 		int rc;
@@ -1424,15 +1546,36 @@ static int __cpuinit powernowk8_init(void)
 			supported_cpus++;
 	}
 
-	if (supported_cpus == num_online_cpus()) {
-		printk(KERN_INFO PFX "Found %d %s "
-			"processors (%d cpu cores) (" VERSION ")\n",
-			num_online_nodes(),
-			boot_cpu_data.x86_model_id, supported_cpus);
-		return cpufreq_register_driver(&cpufreq_amd64_driver);
+	if (supported_cpus != num_online_cpus())
+		return -ENODEV;
+
+	printk(KERN_INFO PFX "Found %d %s (%d cpu cores) (" VERSION ")\n",
+		num_online_nodes(), boot_cpu_data.x86_model_id, supported_cpus);
+
+	if (boot_cpu_has(X86_FEATURE_CPB)) {
+
+		cpb_capable = true;
+
+		register_cpu_notifier(&cpb_nb);
+
+		msrs = msrs_alloc();
+		if (!msrs) {
+			printk(KERN_ERR "%s: Error allocating msrs!\n", __func__);
+			return -ENOMEM;
+		}
+
+		rdmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs);
+
+		for_each_cpu(cpu, cpu_online_mask) {
+			struct msr *reg = per_cpu_ptr(msrs, cpu);
+			cpb_enabled |= !(!!(reg->l & BIT(25)));
+		}
+
+		printk(KERN_INFO PFX "Core Performance Boosting: %s.\n",
+			(cpb_enabled ? "on" : "off"));
 	}
 
-	return -ENODEV;
+	return cpufreq_register_driver(&cpufreq_amd64_driver);
 }
 
 /* driver entry point for term */
@@ -1440,6 +1583,13 @@ static void __exit powernowk8_exit(void)
 {
 	dprintk("exit\n");
 
+	if (boot_cpu_has(X86_FEATURE_CPB)) {
+		msrs_free(msrs);
+		msrs = NULL;
+
+		unregister_cpu_notifier(&cpb_nb);
+	}
+
 	cpufreq_unregister_driver(&cpufreq_amd64_driver);
 }
 
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
index 02ce824073cb..df3529b1c02d 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
@@ -5,7 +5,6 @@
  *  http://www.gnu.org/licenses/gpl.html
  */
 
-
 enum pstate {
 	HW_PSTATE_INVALID = 0xff,
 	HW_PSTATE_0 = 0,
@@ -55,7 +54,6 @@ struct powernow_k8_data {
 	struct cpumask *available_cores;
 };
 
-
 /* processor's cpuid instruction support */
 #define CPUID_PROCESSOR_SIGNATURE	1	/* function 1 */
 #define CPUID_XFAM			0x0ff00000	/* extended family */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 7e1cca13af35..8b2265732ce8 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -12,7 +12,6 @@
 #include <asm/processor.h>
 #include <asm/pgtable.h>
 #include <asm/msr.h>
-#include <asm/ds.h>
 #include <asm/bugs.h>
 #include <asm/cpu.h>
 
@@ -352,12 +351,6 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
 	}
 
-	if (c->cpuid_level > 6) {
-		unsigned ecx = cpuid_ecx(6);
-		if (ecx & 0x01)
-			set_cpu_cap(c, X86_FEATURE_APERFMPERF);
-	}
-
 	if (cpu_has_xmm2)
 		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
 	if (cpu_has_ds) {
@@ -367,7 +360,6 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_BTS);
 		if (!(l1 & (1<<12)))
 			set_cpu_cap(c, X86_FEATURE_PEBS);
-		ds_init_intel(c);
 	}
 
 	if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index db5bdc8addf8..626154a9f535 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -31,46 +31,51 @@
 #include <asm/nmi.h>
 #include <asm/compat.h>
 
-static u64 perf_event_mask __read_mostly;
+#if 0
+#undef wrmsrl
+#define wrmsrl(msr, val) 					\
+do {								\
+	trace_printk("wrmsrl(%lx, %lx)\n", (unsigned long)(msr),\
+			(unsigned long)(val));			\
+	native_write_msr((msr), (u32)((u64)(val)), 		\
+			(u32)((u64)(val) >> 32));		\
+} while (0)
+#endif
 
-/* The maximal number of PEBS events: */
-#define MAX_PEBS_EVENTS	4
+/*
+ * best effort, GUP based copy_from_user() that assumes IRQ or NMI context
+ */
+static unsigned long
+copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
+{
+	unsigned long offset, addr = (unsigned long)from;
+	int type = in_nmi() ? KM_NMI : KM_IRQ0;
+	unsigned long size, len = 0;
+	struct page *page;
+	void *map;
+	int ret;
 
-/* The size of a BTS record in bytes: */
-#define BTS_RECORD_SIZE		24
+	do {
+		ret = __get_user_pages_fast(addr, 1, 0, &page);
+		if (!ret)
+			break;
 
-/* The size of a per-cpu BTS buffer in bytes: */
-#define BTS_BUFFER_SIZE		(BTS_RECORD_SIZE * 2048)
+		offset = addr & (PAGE_SIZE - 1);
+		size = min(PAGE_SIZE - offset, n - len);
 
-/* The BTS overflow threshold in bytes from the end of the buffer: */
-#define BTS_OVFL_TH		(BTS_RECORD_SIZE * 128)
+		map = kmap_atomic(page, type);
+		memcpy(to, map+offset, size);
+		kunmap_atomic(map, type);
+		put_page(page);
 
+		len  += size;
+		to   += size;
+		addr += size;
 
-/*
- * Bits in the debugctlmsr controlling branch tracing.
- */
-#define X86_DEBUGCTL_TR			(1 << 6)
-#define X86_DEBUGCTL_BTS		(1 << 7)
-#define X86_DEBUGCTL_BTINT		(1 << 8)
-#define X86_DEBUGCTL_BTS_OFF_OS		(1 << 9)
-#define X86_DEBUGCTL_BTS_OFF_USR	(1 << 10)
+	} while (len < n);
 
-/*
- * A debug store configuration.
- *
- * We only support architectures that use 64bit fields.
- */
-struct debug_store {
-	u64	bts_buffer_base;
-	u64	bts_index;
-	u64	bts_absolute_maximum;
-	u64	bts_interrupt_threshold;
-	u64	pebs_buffer_base;
-	u64	pebs_index;
-	u64	pebs_absolute_maximum;
-	u64	pebs_interrupt_threshold;
-	u64	pebs_event_reset[MAX_PEBS_EVENTS];
-};
+	return len;
+}
 
 struct event_constraint {
 	union {
@@ -89,18 +94,39 @@ struct amd_nb {
 	struct event_constraint event_constraints[X86_PMC_IDX_MAX];
 };
 
+#define MAX_LBR_ENTRIES		16
+
 struct cpu_hw_events {
+	/*
+	 * Generic x86 PMC bits
+	 */
 	struct perf_event	*events[X86_PMC_IDX_MAX]; /* in counter order */
 	unsigned long		active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
-	unsigned long		interrupts;
 	int			enabled;
-	struct debug_store	*ds;
 
 	int			n_events;
 	int			n_added;
 	int			assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
 	u64			tags[X86_PMC_IDX_MAX];
 	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */
+
+	/*
+	 * Intel DebugStore bits
+	 */
+	struct debug_store	*ds;
+	u64			pebs_enabled;
+
+	/*
+	 * Intel LBR bits
+	 */
+	int				lbr_users;
+	void				*lbr_context;
+	struct perf_branch_stack	lbr_stack;
+	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
+
+	/*
+	 * AMD specific bits
+	 */
 	struct amd_nb		*amd_nb;
 };
 
@@ -114,11 +140,31 @@ struct cpu_hw_events {
 #define EVENT_CONSTRAINT(c, n, m)	\
 	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n))
 
+/*
+ * Constraint on the Event code.
+ */
 #define INTEL_EVENT_CONSTRAINT(c, n)	\
-	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVTSEL_MASK)
+	EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
 
+/*
+ * Constraint on the Event code + UMask + fixed-mask
+ *
+ * filter mask to validate fixed counter events.
+ * the following filters disqualify for fixed counters:
+ *  - inv
+ *  - edge
+ *  - cnt-mask
+ *  The other filters are supported by fixed counters.
+ *  The any-thread option is supported starting with v3.
+ */
 #define FIXED_EVENT_CONSTRAINT(c, n)	\
-	EVENT_CONSTRAINT(c, (1ULL << (32+n)), INTEL_ARCH_FIXED_MASK)
+	EVENT_CONSTRAINT(c, (1ULL << (32+n)), X86_RAW_EVENT_MASK)
+
+/*
+ * Constraint on the Event code + UMask
+ */
+#define PEBS_EVENT_CONSTRAINT(c, n)	\
+	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
 
 #define EVENT_CONSTRAINT_END		\
 	EVENT_CONSTRAINT(0, 0, 0)
@@ -126,32 +172,43 @@ struct cpu_hw_events {
 #define for_each_event_constraint(e, c)	\
 	for ((e) = (c); (e)->cmask; (e)++)
 
+union perf_capabilities {
+	struct {
+		u64	lbr_format    : 6;
+		u64	pebs_trap     : 1;
+		u64	pebs_arch_reg : 1;
+		u64	pebs_format   : 4;
+		u64	smm_freeze    : 1;
+	};
+	u64	capabilities;
+};
+
 /*
  * struct x86_pmu - generic x86 pmu
  */
 struct x86_pmu {
+	/*
+	 * Generic x86 PMC bits
+	 */
 	const char	*name;
 	int		version;
 	int		(*handle_irq)(struct pt_regs *);
 	void		(*disable_all)(void);
-	void		(*enable_all)(void);
+	void		(*enable_all)(int added);
 	void		(*enable)(struct perf_event *);
 	void		(*disable)(struct perf_event *);
+	int		(*hw_config)(struct perf_event *event);
+	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
 	unsigned	eventsel;
 	unsigned	perfctr;
 	u64		(*event_map)(int);
-	u64		(*raw_event)(u64);
 	int		max_events;
-	int		num_events;
-	int		num_events_fixed;
-	int		event_bits;
-	u64		event_mask;
+	int		num_counters;
+	int		num_counters_fixed;
+	int		cntval_bits;
+	u64		cntval_mask;
 	int		apic;
 	u64		max_period;
-	u64		intel_ctrl;
-	void		(*enable_bts)(u64 config);
-	void		(*disable_bts)(void);
-
 	struct event_constraint *
 			(*get_event_constraints)(struct cpu_hw_events *cpuc,
 						 struct perf_event *event);
@@ -159,11 +216,32 @@ struct x86_pmu {
 	void		(*put_event_constraints)(struct cpu_hw_events *cpuc,
 						 struct perf_event *event);
 	struct event_constraint *event_constraints;
+	void		(*quirks)(void);
 
 	int		(*cpu_prepare)(int cpu);
 	void		(*cpu_starting)(int cpu);
 	void		(*cpu_dying)(int cpu);
 	void		(*cpu_dead)(int cpu);
+
+	/*
+	 * Intel Arch Perfmon v2+
+	 */
+	u64			intel_ctrl;
+	union perf_capabilities intel_cap;
+
+	/*
+	 * Intel DebugStore bits
+	 */
+	int		bts, pebs;
+	int		pebs_record_size;
+	void		(*drain_pebs)(struct pt_regs *regs);
+	struct event_constraint *pebs_constraints;
+
+	/*
+	 * Intel LBR
+	 */
+	unsigned long	lbr_tos, lbr_from, lbr_to; /* MSR base regs       */
+	int		lbr_nr;			   /* hardware stack size */
 };
 
 static struct x86_pmu x86_pmu __read_mostly;
@@ -198,7 +276,7 @@ static u64
 x86_perf_event_update(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	int shift = 64 - x86_pmu.event_bits;
+	int shift = 64 - x86_pmu.cntval_bits;
 	u64 prev_raw_count, new_raw_count;
 	int idx = hwc->idx;
 	s64 delta;
@@ -241,33 +319,32 @@ again:
 static atomic_t active_events;
 static DEFINE_MUTEX(pmc_reserve_mutex);
 
+#ifdef CONFIG_X86_LOCAL_APIC
+
 static bool reserve_pmc_hardware(void)
 {
-#ifdef CONFIG_X86_LOCAL_APIC
 	int i;
 
 	if (nmi_watchdog == NMI_LOCAL_APIC)
 		disable_lapic_nmi_watchdog();
 
-	for (i = 0; i < x86_pmu.num_events; i++) {
+	for (i = 0; i < x86_pmu.num_counters; i++) {
 		if (!reserve_perfctr_nmi(x86_pmu.perfctr + i))
 			goto perfctr_fail;
 	}
 
-	for (i = 0; i < x86_pmu.num_events; i++) {
+	for (i = 0; i < x86_pmu.num_counters; i++) {
 		if (!reserve_evntsel_nmi(x86_pmu.eventsel + i))
 			goto eventsel_fail;
 	}
-#endif
 
 	return true;
 
-#ifdef CONFIG_X86_LOCAL_APIC
 eventsel_fail:
 	for (i--; i >= 0; i--)
 		release_evntsel_nmi(x86_pmu.eventsel + i);
 
-	i = x86_pmu.num_events;
+	i = x86_pmu.num_counters;
 
 perfctr_fail:
 	for (i--; i >= 0; i--)
@@ -277,128 +354,36 @@ perfctr_fail:
 		enable_lapic_nmi_watchdog();
 
 	return false;
-#endif
 }
 
 static void release_pmc_hardware(void)
 {
-#ifdef CONFIG_X86_LOCAL_APIC
 	int i;
 
-	for (i = 0; i < x86_pmu.num_events; i++) {
+	for (i = 0; i < x86_pmu.num_counters; i++) {
 		release_perfctr_nmi(x86_pmu.perfctr + i);
 		release_evntsel_nmi(x86_pmu.eventsel + i);
 	}
 
 	if (nmi_watchdog == NMI_LOCAL_APIC)
 		enable_lapic_nmi_watchdog();
-#endif
-}
-
-static inline bool bts_available(void)
-{
-	return x86_pmu.enable_bts != NULL;
-}
-
-static void init_debug_store_on_cpu(int cpu)
-{
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-
-	if (!ds)
-		return;
-
-	wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA,
-		     (u32)((u64)(unsigned long)ds),
-		     (u32)((u64)(unsigned long)ds >> 32));
-}
-
-static void fini_debug_store_on_cpu(int cpu)
-{
-	if (!per_cpu(cpu_hw_events, cpu).ds)
-		return;
-
-	wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
-}
-
-static void release_bts_hardware(void)
-{
-	int cpu;
-
-	if (!bts_available())
-		return;
-
-	get_online_cpus();
-
-	for_each_online_cpu(cpu)
-		fini_debug_store_on_cpu(cpu);
-
-	for_each_possible_cpu(cpu) {
-		struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-
-		if (!ds)
-			continue;
-
-		per_cpu(cpu_hw_events, cpu).ds = NULL;
-
-		kfree((void *)(unsigned long)ds->bts_buffer_base);
-		kfree(ds);
-	}
-
-	put_online_cpus();
 }
 
-static int reserve_bts_hardware(void)
-{
-	int cpu, err = 0;
-
-	if (!bts_available())
-		return 0;
-
-	get_online_cpus();
-
-	for_each_possible_cpu(cpu) {
-		struct debug_store *ds;
-		void *buffer;
-
-		err = -ENOMEM;
-		buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL);
-		if (unlikely(!buffer))
-			break;
-
-		ds = kzalloc(sizeof(*ds), GFP_KERNEL);
-		if (unlikely(!ds)) {
-			kfree(buffer);
-			break;
-		}
-
-		ds->bts_buffer_base = (u64)(unsigned long)buffer;
-		ds->bts_index = ds->bts_buffer_base;
-		ds->bts_absolute_maximum =
-			ds->bts_buffer_base + BTS_BUFFER_SIZE;
-		ds->bts_interrupt_threshold =
-			ds->bts_absolute_maximum - BTS_OVFL_TH;
+#else
 
-		per_cpu(cpu_hw_events, cpu).ds = ds;
-		err = 0;
-	}
+static bool reserve_pmc_hardware(void) { return true; }
+static void release_pmc_hardware(void) {}
 
-	if (err)
-		release_bts_hardware();
-	else {
-		for_each_online_cpu(cpu)
-			init_debug_store_on_cpu(cpu);
-	}
-
-	put_online_cpus();
+#endif
 
-	return err;
-}
+static int reserve_ds_buffers(void);
+static void release_ds_buffers(void);
 
 static void hw_perf_event_destroy(struct perf_event *event)
 {
 	if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) {
 		release_pmc_hardware();
-		release_bts_hardware();
+		release_ds_buffers();
 		mutex_unlock(&pmc_reserve_mutex);
 	}
 }
@@ -441,6 +426,28 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr)
 	return 0;
 }
 
+static int x86_pmu_hw_config(struct perf_event *event)
+{
+	/*
+	 * Generate PMC IRQs:
+	 * (keep 'enabled' bit clear for now)
+	 */
+	event->hw.config = ARCH_PERFMON_EVENTSEL_INT;
+
+	/*
+	 * Count user and OS events unless requested not to
+	 */
+	if (!event->attr.exclude_user)
+		event->hw.config |= ARCH_PERFMON_EVENTSEL_USR;
+	if (!event->attr.exclude_kernel)
+		event->hw.config |= ARCH_PERFMON_EVENTSEL_OS;
+
+	if (event->attr.type == PERF_TYPE_RAW)
+		event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK;
+
+	return 0;
+}
+
 /*
  * Setup the hardware configuration for a given attr_type
  */
@@ -460,8 +467,11 @@ static int __hw_perf_event_init(struct perf_event *event)
 		if (atomic_read(&active_events) == 0) {
 			if (!reserve_pmc_hardware())
 				err = -EBUSY;
-			else
-				err = reserve_bts_hardware();
+			else {
+				err = reserve_ds_buffers();
+				if (err)
+					release_pmc_hardware();
+			}
 		}
 		if (!err)
 			atomic_inc(&active_events);
@@ -472,23 +482,14 @@ static int __hw_perf_event_init(struct perf_event *event)
 
 	event->destroy = hw_perf_event_destroy;
 
-	/*
-	 * Generate PMC IRQs:
-	 * (keep 'enabled' bit clear for now)
-	 */
-	hwc->config = ARCH_PERFMON_EVENTSEL_INT;
-
 	hwc->idx = -1;
 	hwc->last_cpu = -1;
 	hwc->last_tag = ~0ULL;
 
-	/*
-	 * Count user and OS events unless requested not to.
-	 */
-	if (!attr->exclude_user)
-		hwc->config |= ARCH_PERFMON_EVENTSEL_USR;
-	if (!attr->exclude_kernel)
-		hwc->config |= ARCH_PERFMON_EVENTSEL_OS;
+	/* Processor specifics */
+	err = x86_pmu.hw_config(event);
+	if (err)
+		return err;
 
 	if (!hwc->sample_period) {
 		hwc->sample_period = x86_pmu.max_period;
@@ -505,16 +506,8 @@ static int __hw_perf_event_init(struct perf_event *event)
 			return -EOPNOTSUPP;
 	}
 
-	/*
-	 * Raw hw_event type provide the config in the hw_event structure
-	 */
-	if (attr->type == PERF_TYPE_RAW) {
-		hwc->config |= x86_pmu.raw_event(attr->config);
-		if ((hwc->config & ARCH_PERFMON_EVENTSEL_ANY) &&
-		    perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
-			return -EACCES;
+	if (attr->type == PERF_TYPE_RAW)
 		return 0;
-	}
 
 	if (attr->type == PERF_TYPE_HW_CACHE)
 		return set_ext_hw_attr(hwc, attr);
@@ -539,11 +532,11 @@ static int __hw_perf_event_init(struct perf_event *event)
 	if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
 	    (hwc->sample_period == 1)) {
 		/* BTS is not supported by this architecture. */
-		if (!bts_available())
+		if (!x86_pmu.bts)
 			return -EOPNOTSUPP;
 
 		/* BTS is currently only allowed for user-mode. */
-		if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
+		if (!attr->exclude_kernel)
 			return -EOPNOTSUPP;
 	}
 
@@ -557,7 +550,7 @@ static void x86_pmu_disable_all(void)
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_events; idx++) {
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		u64 val;
 
 		if (!test_bit(idx, cpuc->active_mask))
@@ -587,12 +580,12 @@ void hw_perf_disable(void)
 	x86_pmu.disable_all();
 }
 
-static void x86_pmu_enable_all(void)
+static void x86_pmu_enable_all(int added)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_events; idx++) {
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		struct perf_event *event = cpuc->events[idx];
 		u64 val;
 
@@ -667,14 +660,14 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 	 * assign events to counters starting with most
 	 * constrained events.
 	 */
-	wmax = x86_pmu.num_events;
+	wmax = x86_pmu.num_counters;
 
 	/*
 	 * when fixed event counters are present,
 	 * wmax is incremented by 1 to account
 	 * for one more choice
 	 */
-	if (x86_pmu.num_events_fixed)
+	if (x86_pmu.num_counters_fixed)
 		wmax++;
 
 	for (w = 1, num = n; num && w <= wmax; w++) {
@@ -724,7 +717,7 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
 	struct perf_event *event;
 	int n, max_count;
 
-	max_count = x86_pmu.num_events + x86_pmu.num_events_fixed;
+	max_count = x86_pmu.num_counters + x86_pmu.num_counters_fixed;
 
 	/* current number of events already accepted */
 	n = cpuc->n_events;
@@ -795,7 +788,7 @@ void hw_perf_enable(void)
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
-	int i;
+	int i, added = cpuc->n_added;
 
 	if (!x86_pmu_initialized())
 		return;
@@ -847,19 +840,20 @@ void hw_perf_enable(void)
 	cpuc->enabled = 1;
 	barrier();
 
-	x86_pmu.enable_all();
+	x86_pmu.enable_all(added);
 }
 
 static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc)
 {
-	(void)checking_wrmsrl(hwc->config_base + hwc->idx,
+	wrmsrl(hwc->config_base + hwc->idx,
 			      hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
 static inline void x86_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	(void)checking_wrmsrl(hwc->config_base + hwc->idx, hwc->config);
+
+	wrmsrl(hwc->config_base + hwc->idx, hwc->config);
 }
 
 static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
@@ -874,7 +868,7 @@ x86_perf_event_set_period(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	s64 left = atomic64_read(&hwc->period_left);
 	s64 period = hwc->sample_period;
-	int err, ret = 0, idx = hwc->idx;
+	int ret = 0, idx = hwc->idx;
 
 	if (idx == X86_PMC_IDX_FIXED_BTS)
 		return 0;
@@ -912,8 +906,8 @@ x86_perf_event_set_period(struct perf_event *event)
 	 */
 	atomic64_set(&hwc->prev_count, (u64)-left);
 
-	err = checking_wrmsrl(hwc->event_base + idx,
-			     (u64)(-left) & x86_pmu.event_mask);
+	wrmsrl(hwc->event_base + idx,
+			(u64)(-left) & x86_pmu.cntval_mask);
 
 	perf_event_update_userpage(event);
 
@@ -950,7 +944,7 @@ static int x86_pmu_enable(struct perf_event *event)
 	if (n < 0)
 		return n;
 
-	ret = x86_schedule_events(cpuc, n, assign);
+	ret = x86_pmu.schedule_events(cpuc, n, assign);
 	if (ret)
 		return ret;
 	/*
@@ -991,11 +985,12 @@ static void x86_pmu_unthrottle(struct perf_event *event)
 void perf_event_print_debug(void)
 {
 	u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed;
+	u64 pebs;
 	struct cpu_hw_events *cpuc;
 	unsigned long flags;
 	int cpu, idx;
 
-	if (!x86_pmu.num_events)
+	if (!x86_pmu.num_counters)
 		return;
 
 	local_irq_save(flags);
@@ -1008,16 +1003,18 @@ void perf_event_print_debug(void)
 		rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
 		rdmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow);
 		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed);
+		rdmsrl(MSR_IA32_PEBS_ENABLE, pebs);
 
 		pr_info("\n");
 		pr_info("CPU#%d: ctrl:       %016llx\n", cpu, ctrl);
 		pr_info("CPU#%d: status:     %016llx\n", cpu, status);
 		pr_info("CPU#%d: overflow:   %016llx\n", cpu, overflow);
 		pr_info("CPU#%d: fixed:      %016llx\n", cpu, fixed);
+		pr_info("CPU#%d: pebs:       %016llx\n", cpu, pebs);
 	}
-	pr_info("CPU#%d: active:       %016llx\n", cpu, *(u64 *)cpuc->active_mask);
+	pr_info("CPU#%d: active:     %016llx\n", cpu, *(u64 *)cpuc->active_mask);
 
-	for (idx = 0; idx < x86_pmu.num_events; idx++) {
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl);
 		rdmsrl(x86_pmu.perfctr  + idx, pmc_count);
 
@@ -1030,7 +1027,7 @@ void perf_event_print_debug(void)
 		pr_info("CPU#%d:   gen-PMC%d left:  %016llx\n",
 			cpu, idx, prev_left);
 	}
-	for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) {
+	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
 		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
 
 		pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
@@ -1095,7 +1092,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
-	for (idx = 0; idx < x86_pmu.num_events; idx++) {
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
 
@@ -1103,7 +1100,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 		hwc = &event->hw;
 
 		val = x86_perf_event_update(event);
-		if (val & (1ULL << (x86_pmu.event_bits - 1)))
+		if (val & (1ULL << (x86_pmu.cntval_bits - 1)))
 			continue;
 
 		/*
@@ -1146,7 +1143,6 @@ void set_perf_event_pending(void)
 
 void perf_events_lapic_init(void)
 {
-#ifdef CONFIG_X86_LOCAL_APIC
 	if (!x86_pmu.apic || !x86_pmu_initialized())
 		return;
 
@@ -1154,7 +1150,6 @@ void perf_events_lapic_init(void)
 	 * Always use NMI for PMU
 	 */
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
-#endif
 }
 
 static int __kprobes
@@ -1178,9 +1173,7 @@ perf_event_nmi_handler(struct notifier_block *self,
 
 	regs = args->regs;
 
-#ifdef CONFIG_X86_LOCAL_APIC
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
-#endif
 	/*
 	 * Can't rely on the handled return value to say it was our NMI, two
 	 * events could trigger 'simultaneously' raising two back-to-back NMIs.
@@ -1274,12 +1267,15 @@ int hw_perf_group_sched_in(struct perf_event *leader,
 	int assign[X86_PMC_IDX_MAX];
 	int n0, n1, ret;
 
+	if (!x86_pmu_initialized())
+		return 0;
+
 	/* n0 = total number of events */
 	n0 = collect_events(cpuc, leader, true);
 	if (n0 < 0)
 		return n0;
 
-	ret = x86_schedule_events(cpuc, n0, assign);
+	ret = x86_pmu.schedule_events(cpuc, n0, assign);
 	if (ret)
 		return ret;
 
@@ -1329,6 +1325,9 @@ undo:
 
 #include "perf_event_amd.c"
 #include "perf_event_p6.c"
+#include "perf_event_p4.c"
+#include "perf_event_intel_lbr.c"
+#include "perf_event_intel_ds.c"
 #include "perf_event_intel.c"
 
 static int __cpuinit
@@ -1402,48 +1401,50 @@ void __init init_hw_perf_events(void)
 
 	pr_cont("%s PMU driver.\n", x86_pmu.name);
 
-	if (x86_pmu.num_events > X86_PMC_MAX_GENERIC) {
+	if (x86_pmu.quirks)
+		x86_pmu.quirks();
+
+	if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) {
 		WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
-		     x86_pmu.num_events, X86_PMC_MAX_GENERIC);
-		x86_pmu.num_events = X86_PMC_MAX_GENERIC;
+		     x86_pmu.num_counters, X86_PMC_MAX_GENERIC);
+		x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
 	}
-	perf_event_mask = (1 << x86_pmu.num_events) - 1;
-	perf_max_events = x86_pmu.num_events;
+	x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
+	perf_max_events = x86_pmu.num_counters;
 
-	if (x86_pmu.num_events_fixed > X86_PMC_MAX_FIXED) {
+	if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) {
 		WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
-		     x86_pmu.num_events_fixed, X86_PMC_MAX_FIXED);
-		x86_pmu.num_events_fixed = X86_PMC_MAX_FIXED;
+		     x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED);
+		x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
 	}
 
-	perf_event_mask |=
-		((1LL << x86_pmu.num_events_fixed)-1) << X86_PMC_IDX_FIXED;
-	x86_pmu.intel_ctrl = perf_event_mask;
+	x86_pmu.intel_ctrl |=
+		((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED;
 
 	perf_events_lapic_init();
 	register_die_notifier(&perf_event_nmi_notifier);
 
 	unconstrained = (struct event_constraint)
-		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_events) - 1,
-				   0, x86_pmu.num_events);
+		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
+				   0, x86_pmu.num_counters);
 
 	if (x86_pmu.event_constraints) {
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			if (c->cmask != INTEL_ARCH_FIXED_MASK)
+			if (c->cmask != X86_RAW_EVENT_MASK)
 				continue;
 
-			c->idxmsk64 |= (1ULL << x86_pmu.num_events) - 1;
-			c->weight += x86_pmu.num_events;
+			c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
+			c->weight += x86_pmu.num_counters;
 		}
 	}
 
 	pr_info("... version:                %d\n",     x86_pmu.version);
-	pr_info("... bit width:              %d\n",     x86_pmu.event_bits);
-	pr_info("... generic registers:      %d\n",     x86_pmu.num_events);
-	pr_info("... value mask:             %016Lx\n", x86_pmu.event_mask);
+	pr_info("... bit width:              %d\n",     x86_pmu.cntval_bits);
+	pr_info("... generic registers:      %d\n",     x86_pmu.num_counters);
+	pr_info("... value mask:             %016Lx\n", x86_pmu.cntval_mask);
 	pr_info("... max period:             %016Lx\n", x86_pmu.max_period);
-	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_events_fixed);
-	pr_info("... event mask:             %016Lx\n", perf_event_mask);
+	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_counters_fixed);
+	pr_info("... event mask:             %016Lx\n", x86_pmu.intel_ctrl);
 
 	perf_cpu_notifier(x86_pmu_notifier);
 }
@@ -1463,6 +1464,32 @@ static const struct pmu pmu = {
 };
 
 /*
+ * validate that we can schedule this event
+ */
+static int validate_event(struct perf_event *event)
+{
+	struct cpu_hw_events *fake_cpuc;
+	struct event_constraint *c;
+	int ret = 0;
+
+	fake_cpuc = kmalloc(sizeof(*fake_cpuc), GFP_KERNEL | __GFP_ZERO);
+	if (!fake_cpuc)
+		return -ENOMEM;
+
+	c = x86_pmu.get_event_constraints(fake_cpuc, event);
+
+	if (!c || !c->weight)
+		ret = -ENOSPC;
+
+	if (x86_pmu.put_event_constraints)
+		x86_pmu.put_event_constraints(fake_cpuc, event);
+
+	kfree(fake_cpuc);
+
+	return ret;
+}
+
+/*
  * validate a single event group
  *
  * validation include:
@@ -1502,7 +1529,7 @@ static int validate_group(struct perf_event *event)
 
 	fake_cpuc->n_events = n;
 
-	ret = x86_schedule_events(fake_cpuc, n, NULL);
+	ret = x86_pmu.schedule_events(fake_cpuc, n, NULL);
 
 out_free:
 	kfree(fake_cpuc);
@@ -1527,6 +1554,8 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 
 		if (event->group_leader != event)
 			err = validate_group(event);
+		else
+			err = validate_event(event);
 
 		event->pmu = tmp;
 	}
@@ -1574,8 +1603,7 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
 {
 	struct perf_callchain_entry *entry = data;
 
-	if (reliable)
-		callchain_store(entry, addr);
+	callchain_store(entry, addr);
 }
 
 static const struct stacktrace_ops backtrace_ops = {
@@ -1597,41 +1625,6 @@ perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
 	dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
 }
 
-/*
- * best effort, GUP based copy_from_user() that assumes IRQ or NMI context
- */
-static unsigned long
-copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
-{
-	unsigned long offset, addr = (unsigned long)from;
-	int type = in_nmi() ? KM_NMI : KM_IRQ0;
-	unsigned long size, len = 0;
-	struct page *page;
-	void *map;
-	int ret;
-
-	do {
-		ret = __get_user_pages_fast(addr, 1, 0, &page);
-		if (!ret)
-			break;
-
-		offset = addr & (PAGE_SIZE - 1);
-		size = min(PAGE_SIZE - offset, n - len);
-
-		map = kmap_atomic(page, type);
-		memcpy(to, map+offset, size);
-		kunmap_atomic(map, type);
-		put_page(page);
-
-		len  += size;
-		to   += size;
-		addr += size;
-
-	} while (len < n);
-
-	return len;
-}
-
 #ifdef CONFIG_COMPAT
 static inline int
 perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index db6f7d4056e1..611df11ba15e 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -2,7 +2,7 @@
 
 static DEFINE_RAW_SPINLOCK(amd_nb_lock);
 
-static __initconst u64 amd_hw_cache_event_ids
+static __initconst const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -111,22 +111,19 @@ static u64 amd_pmu_event_map(int hw_event)
 	return amd_perfmon_event_map[hw_event];
 }
 
-static u64 amd_pmu_raw_event(u64 hw_event)
+static int amd_pmu_hw_config(struct perf_event *event)
 {
-#define K7_EVNTSEL_EVENT_MASK	0xF000000FFULL
-#define K7_EVNTSEL_UNIT_MASK	0x00000FF00ULL
-#define K7_EVNTSEL_EDGE_MASK	0x000040000ULL
-#define K7_EVNTSEL_INV_MASK	0x000800000ULL
-#define K7_EVNTSEL_REG_MASK	0x0FF000000ULL
-
-#define K7_EVNTSEL_MASK			\
-	(K7_EVNTSEL_EVENT_MASK |	\
-	 K7_EVNTSEL_UNIT_MASK  |	\
-	 K7_EVNTSEL_EDGE_MASK  |	\
-	 K7_EVNTSEL_INV_MASK   |	\
-	 K7_EVNTSEL_REG_MASK)
-
-	return hw_event & K7_EVNTSEL_MASK;
+	int ret = x86_pmu_hw_config(event);
+
+	if (ret)
+		return ret;
+
+	if (event->attr.type != PERF_TYPE_RAW)
+		return 0;
+
+	event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK;
+
+	return 0;
 }
 
 /*
@@ -165,7 +162,7 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
 	 * be removed on one CPU at a time AND PMU is disabled
 	 * when we come here
 	 */
-	for (i = 0; i < x86_pmu.num_events; i++) {
+	for (i = 0; i < x86_pmu.num_counters; i++) {
 		if (nb->owners[i] == event) {
 			cmpxchg(nb->owners+i, event, NULL);
 			break;
@@ -215,7 +212,7 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	struct amd_nb *nb = cpuc->amd_nb;
 	struct perf_event *old = NULL;
-	int max = x86_pmu.num_events;
+	int max = x86_pmu.num_counters;
 	int i, j, k = -1;
 
 	/*
@@ -293,7 +290,7 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 	/*
 	 * initialize all possible NB constraints
 	 */
-	for (i = 0; i < x86_pmu.num_events; i++) {
+	for (i = 0; i < x86_pmu.num_counters; i++) {
 		__set_bit(i, nb->event_constraints[i].idxmsk);
 		nb->event_constraints[i].weight = 1;
 	}
@@ -371,21 +368,22 @@ static void amd_pmu_cpu_dead(int cpu)
 	raw_spin_unlock(&amd_nb_lock);
 }
 
-static __initconst struct x86_pmu amd_pmu = {
+static __initconst const struct x86_pmu amd_pmu = {
 	.name			= "AMD",
 	.handle_irq		= x86_pmu_handle_irq,
 	.disable_all		= x86_pmu_disable_all,
 	.enable_all		= x86_pmu_enable_all,
 	.enable			= x86_pmu_enable_event,
 	.disable		= x86_pmu_disable_event,
+	.hw_config		= amd_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_K7_EVNTSEL0,
 	.perfctr		= MSR_K7_PERFCTR0,
 	.event_map		= amd_pmu_event_map,
-	.raw_event		= amd_pmu_raw_event,
 	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
-	.num_events		= 4,
-	.event_bits		= 48,
-	.event_mask		= (1ULL << 48) - 1,
+	.num_counters		= 4,
+	.cntval_bits		= 48,
+	.cntval_mask		= (1ULL << 48) - 1,
 	.apic			= 1,
 	/* use highest bit to detect overflow */
 	.max_period		= (1ULL << 47) - 1,
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 9c794ac87837..a099df96f916 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -88,7 +88,7 @@ static u64 intel_pmu_event_map(int hw_event)
 	return intel_perfmon_event_map[hw_event];
 }
 
-static __initconst u64 westmere_hw_cache_event_ids
+static __initconst const u64 westmere_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -179,7 +179,7 @@ static __initconst u64 westmere_hw_cache_event_ids
  },
 };
 
-static __initconst u64 nehalem_hw_cache_event_ids
+static __initconst const u64 nehalem_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -270,7 +270,7 @@ static __initconst u64 nehalem_hw_cache_event_ids
  },
 };
 
-static __initconst u64 core2_hw_cache_event_ids
+static __initconst const u64 core2_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -361,7 +361,7 @@ static __initconst u64 core2_hw_cache_event_ids
  },
 };
 
-static __initconst u64 atom_hw_cache_event_ids
+static __initconst const u64 atom_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -452,60 +452,6 @@ static __initconst u64 atom_hw_cache_event_ids
  },
 };
 
-static u64 intel_pmu_raw_event(u64 hw_event)
-{
-#define CORE_EVNTSEL_EVENT_MASK		0x000000FFULL
-#define CORE_EVNTSEL_UNIT_MASK		0x0000FF00ULL
-#define CORE_EVNTSEL_EDGE_MASK		0x00040000ULL
-#define CORE_EVNTSEL_INV_MASK		0x00800000ULL
-#define CORE_EVNTSEL_REG_MASK		0xFF000000ULL
-
-#define CORE_EVNTSEL_MASK		\
-	(INTEL_ARCH_EVTSEL_MASK |	\
-	 INTEL_ARCH_UNIT_MASK   |	\
-	 INTEL_ARCH_EDGE_MASK   |	\
-	 INTEL_ARCH_INV_MASK    |	\
-	 INTEL_ARCH_CNT_MASK)
-
-	return hw_event & CORE_EVNTSEL_MASK;
-}
-
-static void intel_pmu_enable_bts(u64 config)
-{
-	unsigned long debugctlmsr;
-
-	debugctlmsr = get_debugctlmsr();
-
-	debugctlmsr |= X86_DEBUGCTL_TR;
-	debugctlmsr |= X86_DEBUGCTL_BTS;
-	debugctlmsr |= X86_DEBUGCTL_BTINT;
-
-	if (!(config & ARCH_PERFMON_EVENTSEL_OS))
-		debugctlmsr |= X86_DEBUGCTL_BTS_OFF_OS;
-
-	if (!(config & ARCH_PERFMON_EVENTSEL_USR))
-		debugctlmsr |= X86_DEBUGCTL_BTS_OFF_USR;
-
-	update_debugctlmsr(debugctlmsr);
-}
-
-static void intel_pmu_disable_bts(void)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	unsigned long debugctlmsr;
-
-	if (!cpuc->ds)
-		return;
-
-	debugctlmsr = get_debugctlmsr();
-
-	debugctlmsr &=
-		~(X86_DEBUGCTL_TR | X86_DEBUGCTL_BTS | X86_DEBUGCTL_BTINT |
-		  X86_DEBUGCTL_BTS_OFF_OS | X86_DEBUGCTL_BTS_OFF_USR);
-
-	update_debugctlmsr(debugctlmsr);
-}
-
 static void intel_pmu_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -514,12 +460,17 @@ static void intel_pmu_disable_all(void)
 
 	if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask))
 		intel_pmu_disable_bts();
+
+	intel_pmu_pebs_disable_all();
+	intel_pmu_lbr_disable_all();
 }
 
-static void intel_pmu_enable_all(void)
+static void intel_pmu_enable_all(int added)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
+	intel_pmu_pebs_enable_all();
+	intel_pmu_lbr_enable_all();
 	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
 
 	if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
@@ -533,6 +484,41 @@ static void intel_pmu_enable_all(void)
 	}
 }
 
+/*
+ * Workaround for:
+ *   Intel Errata AAK100 (model 26)
+ *   Intel Errata AAP53  (model 30)
+ *   Intel Errata BD53   (model 44)
+ *
+ * These chips need to be 'reset' when adding counters by programming
+ * the magic three (non counting) events 0x4300D2, 0x4300B1 and 0x4300B5
+ * either in sequence on the same PMC or on different PMCs.
+ */
+static void intel_pmu_nhm_enable_all(int added)
+{
+	if (added) {
+		struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+		int i;
+
+		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 0, 0x4300D2);
+		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x4300B1);
+		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x4300B5);
+
+		wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x3);
+		wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x0);
+
+		for (i = 0; i < 3; i++) {
+			struct perf_event *event = cpuc->events[i];
+
+			if (!event)
+				continue;
+
+			__x86_pmu_enable_event(&event->hw);
+		}
+	}
+	intel_pmu_enable_all(added);
+}
+
 static inline u64 intel_pmu_get_status(void)
 {
 	u64 status;
@@ -547,8 +533,7 @@ static inline void intel_pmu_ack_status(u64 ack)
 	wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
 }
 
-static inline void
-intel_pmu_disable_fixed(struct hw_perf_event *hwc)
+static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
 {
 	int idx = hwc->idx - X86_PMC_IDX_FIXED;
 	u64 ctrl_val, mask;
@@ -557,71 +542,10 @@ intel_pmu_disable_fixed(struct hw_perf_event *hwc)
 
 	rdmsrl(hwc->config_base, ctrl_val);
 	ctrl_val &= ~mask;
-	(void)checking_wrmsrl(hwc->config_base, ctrl_val);
-}
-
-static void intel_pmu_drain_bts_buffer(void)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct debug_store *ds = cpuc->ds;
-	struct bts_record {
-		u64	from;
-		u64	to;
-		u64	flags;
-	};
-	struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS];
-	struct bts_record *at, *top;
-	struct perf_output_handle handle;
-	struct perf_event_header header;
-	struct perf_sample_data data;
-	struct pt_regs regs;
-
-	if (!event)
-		return;
-
-	if (!ds)
-		return;
-
-	at  = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
-	top = (struct bts_record *)(unsigned long)ds->bts_index;
-
-	if (top <= at)
-		return;
-
-	ds->bts_index = ds->bts_buffer_base;
-
-	perf_sample_data_init(&data, 0);
-
-	data.period	= event->hw.last_period;
-	regs.ip		= 0;
-
-	/*
-	 * Prepare a generic sample, i.e. fill in the invariant fields.
-	 * We will overwrite the from and to address before we output
-	 * the sample.
-	 */
-	perf_prepare_sample(&header, &data, event, &regs);
-
-	if (perf_output_begin(&handle, event,
-			      header.size * (top - at), 1, 1))
-		return;
-
-	for (; at < top; at++) {
-		data.ip		= at->from;
-		data.addr	= at->to;
-
-		perf_output_sample(&handle, &header, &data, event);
-	}
-
-	perf_output_end(&handle);
-
-	/* There's new data available. */
-	event->hw.interrupts++;
-	event->pending_kill = POLL_IN;
+	wrmsrl(hwc->config_base, ctrl_val);
 }
 
-static inline void
-intel_pmu_disable_event(struct perf_event *event)
+static void intel_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
@@ -637,14 +561,15 @@ intel_pmu_disable_event(struct perf_event *event)
 	}
 
 	x86_pmu_disable_event(event);
+
+	if (unlikely(event->attr.precise))
+		intel_pmu_pebs_disable(event);
 }
 
-static inline void
-intel_pmu_enable_fixed(struct hw_perf_event *hwc)
+static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
 {
 	int idx = hwc->idx - X86_PMC_IDX_FIXED;
 	u64 ctrl_val, bits, mask;
-	int err;
 
 	/*
 	 * Enable IRQ generation (0x8),
@@ -669,7 +594,7 @@ intel_pmu_enable_fixed(struct hw_perf_event *hwc)
 	rdmsrl(hwc->config_base, ctrl_val);
 	ctrl_val &= ~mask;
 	ctrl_val |= bits;
-	err = checking_wrmsrl(hwc->config_base, ctrl_val);
+	wrmsrl(hwc->config_base, ctrl_val);
 }
 
 static void intel_pmu_enable_event(struct perf_event *event)
@@ -689,6 +614,9 @@ static void intel_pmu_enable_event(struct perf_event *event)
 		return;
 	}
 
+	if (unlikely(event->attr.precise))
+		intel_pmu_pebs_enable(event);
+
 	__x86_pmu_enable_event(hwc);
 }
 
@@ -708,20 +636,20 @@ static void intel_pmu_reset(void)
 	unsigned long flags;
 	int idx;
 
-	if (!x86_pmu.num_events)
+	if (!x86_pmu.num_counters)
 		return;
 
 	local_irq_save(flags);
 
 	printk("clearing PMU state on CPU#%d\n", smp_processor_id());
 
-	for (idx = 0; idx < x86_pmu.num_events; idx++) {
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		checking_wrmsrl(x86_pmu.eventsel + idx, 0ull);
 		checking_wrmsrl(x86_pmu.perfctr  + idx, 0ull);
 	}
-	for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) {
+	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++)
 		checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
-	}
+
 	if (ds)
 		ds->bts_index = ds->bts_buffer_base;
 
@@ -747,7 +675,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	intel_pmu_drain_bts_buffer();
 	status = intel_pmu_get_status();
 	if (!status) {
-		intel_pmu_enable_all();
+		intel_pmu_enable_all(0);
 		return 0;
 	}
 
@@ -762,6 +690,15 @@ again:
 
 	inc_irq_stat(apic_perf_irqs);
 	ack = status;
+
+	intel_pmu_lbr_read();
+
+	/*
+	 * PEBS overflow sets bit 62 in the global status register
+	 */
+	if (__test_and_clear_bit(62, (unsigned long *)&status))
+		x86_pmu.drain_pebs(regs);
+
 	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[bit];
 
@@ -787,26 +724,22 @@ again:
 		goto again;
 
 done:
-	intel_pmu_enable_all();
+	intel_pmu_enable_all(0);
 	return 1;
 }
 
-static struct event_constraint bts_constraint =
-	EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0);
-
 static struct event_constraint *
-intel_special_constraints(struct perf_event *event)
+intel_bts_constraints(struct perf_event *event)
 {
-	unsigned int hw_event;
-
-	hw_event = event->hw.config & INTEL_ARCH_EVENT_MASK;
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned int hw_event, bts_event;
 
-	if (unlikely((hw_event ==
-		      x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)) &&
-		     (event->hw.sample_period == 1))) {
+	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
+	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
 
+	if (unlikely(hw_event == bts_event && hwc->sample_period == 1))
 		return &bts_constraint;
-	}
+
 	return NULL;
 }
 
@@ -815,24 +748,53 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event
 {
 	struct event_constraint *c;
 
-	c = intel_special_constraints(event);
+	c = intel_bts_constraints(event);
+	if (c)
+		return c;
+
+	c = intel_pebs_constraints(event);
 	if (c)
 		return c;
 
 	return x86_get_event_constraints(cpuc, event);
 }
 
-static __initconst struct x86_pmu core_pmu = {
+static int intel_pmu_hw_config(struct perf_event *event)
+{
+	int ret = x86_pmu_hw_config(event);
+
+	if (ret)
+		return ret;
+
+	if (event->attr.type != PERF_TYPE_RAW)
+		return 0;
+
+	if (!(event->attr.config & ARCH_PERFMON_EVENTSEL_ANY))
+		return 0;
+
+	if (x86_pmu.version < 3)
+		return -EINVAL;
+
+	if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	event->hw.config |= ARCH_PERFMON_EVENTSEL_ANY;
+
+	return 0;
+}
+
+static __initconst const struct x86_pmu core_pmu = {
 	.name			= "core",
 	.handle_irq		= x86_pmu_handle_irq,
 	.disable_all		= x86_pmu_disable_all,
 	.enable_all		= x86_pmu_enable_all,
 	.enable			= x86_pmu_enable_event,
 	.disable		= x86_pmu_disable_event,
+	.hw_config		= x86_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
 	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
 	.event_map		= intel_pmu_event_map,
-	.raw_event		= intel_pmu_raw_event,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
 	/*
@@ -845,17 +807,32 @@ static __initconst struct x86_pmu core_pmu = {
 	.event_constraints	= intel_core_event_constraints,
 };
 
-static __initconst struct x86_pmu intel_pmu = {
+static void intel_pmu_cpu_starting(int cpu)
+{
+	init_debug_store_on_cpu(cpu);
+	/*
+	 * Deal with CPUs that don't clear their LBRs on power-up.
+	 */
+	intel_pmu_lbr_reset();
+}
+
+static void intel_pmu_cpu_dying(int cpu)
+{
+	fini_debug_store_on_cpu(cpu);
+}
+
+static __initconst const struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,
 	.disable_all		= intel_pmu_disable_all,
 	.enable_all		= intel_pmu_enable_all,
 	.enable			= intel_pmu_enable_event,
 	.disable		= intel_pmu_disable_event,
+	.hw_config		= intel_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
 	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
 	.event_map		= intel_pmu_event_map,
-	.raw_event		= intel_pmu_raw_event,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
 	/*
@@ -864,14 +841,38 @@ static __initconst struct x86_pmu intel_pmu = {
 	 * the generic event period:
 	 */
 	.max_period		= (1ULL << 31) - 1,
-	.enable_bts		= intel_pmu_enable_bts,
-	.disable_bts		= intel_pmu_disable_bts,
 	.get_event_constraints	= intel_get_event_constraints,
 
-	.cpu_starting		= init_debug_store_on_cpu,
-	.cpu_dying		= fini_debug_store_on_cpu,
+	.cpu_starting		= intel_pmu_cpu_starting,
+	.cpu_dying		= intel_pmu_cpu_dying,
 };
 
+static void intel_clovertown_quirks(void)
+{
+	/*
+	 * PEBS is unreliable due to:
+	 *
+	 *   AJ67  - PEBS may experience CPL leaks
+	 *   AJ68  - PEBS PMI may be delayed by one event
+	 *   AJ69  - GLOBAL_STATUS[62] will only be set when DEBUGCTL[12]
+	 *   AJ106 - FREEZE_LBRS_ON_PMI doesn't work in combination with PEBS
+	 *
+	 * AJ67 could be worked around by restricting the OS/USR flags.
+	 * AJ69 could be worked around by setting PMU_FREEZE_ON_PMI.
+	 *
+	 * AJ106 could possibly be worked around by not allowing LBR
+	 *       usage from PEBS, including the fixup.
+	 * AJ68  could possibly be worked around by always programming
+	 * 	 a pebs_event_reset[0] value and coping with the lost events.
+	 *
+	 * But taken together it might just make sense to not enable PEBS on
+	 * these chips.
+	 */
+	printk(KERN_WARNING "PEBS disabled due to CPU errata.\n");
+	x86_pmu.pebs = 0;
+	x86_pmu.pebs_constraints = NULL;
+}
+
 static __init int intel_pmu_init(void)
 {
 	union cpuid10_edx edx;
@@ -881,12 +882,13 @@ static __init int intel_pmu_init(void)
 	int version;
 
 	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
-		/* check for P6 processor family */
-	   if (boot_cpu_data.x86 == 6) {
-		return p6_pmu_init();
-	   } else {
+		switch (boot_cpu_data.x86) {
+		case 0x6:
+			return p6_pmu_init();
+		case 0xf:
+			return p4_pmu_init();
+		}
 		return -ENODEV;
-	   }
 	}
 
 	/*
@@ -904,16 +906,28 @@ static __init int intel_pmu_init(void)
 		x86_pmu = intel_pmu;
 
 	x86_pmu.version			= version;
-	x86_pmu.num_events		= eax.split.num_events;
-	x86_pmu.event_bits		= eax.split.bit_width;
-	x86_pmu.event_mask		= (1ULL << eax.split.bit_width) - 1;
+	x86_pmu.num_counters		= eax.split.num_counters;
+	x86_pmu.cntval_bits		= eax.split.bit_width;
+	x86_pmu.cntval_mask		= (1ULL << eax.split.bit_width) - 1;
 
 	/*
 	 * Quirk: v2 perfmon does not report fixed-purpose events, so
 	 * assume at least 3 events:
 	 */
 	if (version > 1)
-		x86_pmu.num_events_fixed = max((int)edx.split.num_events_fixed, 3);
+		x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3);
+
+	/*
+	 * v2 and above have a perf capabilities MSR
+	 */
+	if (version > 1) {
+		u64 capabilities;
+
+		rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities);
+		x86_pmu.intel_cap.capabilities = capabilities;
+	}
+
+	intel_ds_init();
 
 	/*
 	 * Install the hw-cache-events table:
@@ -924,12 +938,15 @@ static __init int intel_pmu_init(void)
 		break;
 
 	case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
+		x86_pmu.quirks = intel_clovertown_quirks;
 	case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
 	case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
 	case 29: /* six-core 45 nm xeon "Dunnington" */
 		memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
+		intel_pmu_lbr_init_core();
+
 		x86_pmu.event_constraints = intel_core2_event_constraints;
 		pr_cont("Core2 events, ");
 		break;
@@ -940,13 +957,19 @@ static __init int intel_pmu_init(void)
 		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
+		intel_pmu_lbr_init_nhm();
+
 		x86_pmu.event_constraints = intel_nehalem_event_constraints;
-		pr_cont("Nehalem/Corei7 events, ");
+		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
+		pr_cont("Nehalem events, ");
 		break;
+
 	case 28: /* Atom */
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
+		intel_pmu_lbr_init_atom();
+
 		x86_pmu.event_constraints = intel_gen_event_constraints;
 		pr_cont("Atom events, ");
 		break;
@@ -956,7 +979,10 @@ static __init int intel_pmu_init(void)
 		memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
+		intel_pmu_lbr_init_nhm();
+
 		x86_pmu.event_constraints = intel_westmere_event_constraints;
+		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
 		pr_cont("Westmere events, ");
 		break;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
new file mode 100644
index 000000000000..ec8b2e12e104
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -0,0 +1,664 @@
+#ifdef CONFIG_CPU_SUP_INTEL
+
+/* The maximal number of PEBS events: */
+#define MAX_PEBS_EVENTS		4
+
+/* The size of a BTS record in bytes: */
+#define BTS_RECORD_SIZE		24
+
+#define BTS_BUFFER_SIZE		(PAGE_SIZE << 4)
+#define PEBS_BUFFER_SIZE	PAGE_SIZE
+
+/*
+ * pebs_record_32 for p4 and core not supported
+
+struct pebs_record_32 {
+	u32 flags, ip;
+	u32 ax, bc, cx, dx;
+	u32 si, di, bp, sp;
+};
+
+ */
+
+struct pebs_record_core {
+	u64 flags, ip;
+	u64 ax, bx, cx, dx;
+	u64 si, di, bp, sp;
+	u64 r8,  r9,  r10, r11;
+	u64 r12, r13, r14, r15;
+};
+
+struct pebs_record_nhm {
+	u64 flags, ip;
+	u64 ax, bx, cx, dx;
+	u64 si, di, bp, sp;
+	u64 r8,  r9,  r10, r11;
+	u64 r12, r13, r14, r15;
+	u64 status, dla, dse, lat;
+};
+
+/*
+ * A debug store configuration.
+ *
+ * We only support architectures that use 64bit fields.
+ */
+struct debug_store {
+	u64	bts_buffer_base;
+	u64	bts_index;
+	u64	bts_absolute_maximum;
+	u64	bts_interrupt_threshold;
+	u64	pebs_buffer_base;
+	u64	pebs_index;
+	u64	pebs_absolute_maximum;
+	u64	pebs_interrupt_threshold;
+	u64	pebs_event_reset[MAX_PEBS_EVENTS];
+};
+
+static void init_debug_store_on_cpu(int cpu)
+{
+	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+
+	if (!ds)
+		return;
+
+	wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA,
+		     (u32)((u64)(unsigned long)ds),
+		     (u32)((u64)(unsigned long)ds >> 32));
+}
+
+static void fini_debug_store_on_cpu(int cpu)
+{
+	if (!per_cpu(cpu_hw_events, cpu).ds)
+		return;
+
+	wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
+}
+
+static void release_ds_buffers(void)
+{
+	int cpu;
+
+	if (!x86_pmu.bts && !x86_pmu.pebs)
+		return;
+
+	get_online_cpus();
+
+	for_each_online_cpu(cpu)
+		fini_debug_store_on_cpu(cpu);
+
+	for_each_possible_cpu(cpu) {
+		struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+
+		if (!ds)
+			continue;
+
+		per_cpu(cpu_hw_events, cpu).ds = NULL;
+
+		kfree((void *)(unsigned long)ds->pebs_buffer_base);
+		kfree((void *)(unsigned long)ds->bts_buffer_base);
+		kfree(ds);
+	}
+
+	put_online_cpus();
+}
+
+static int reserve_ds_buffers(void)
+{
+	int cpu, err = 0;
+
+	if (!x86_pmu.bts && !x86_pmu.pebs)
+		return 0;
+
+	get_online_cpus();
+
+	for_each_possible_cpu(cpu) {
+		struct debug_store *ds;
+		void *buffer;
+		int max, thresh;
+
+		err = -ENOMEM;
+		ds = kzalloc(sizeof(*ds), GFP_KERNEL);
+		if (unlikely(!ds))
+			break;
+		per_cpu(cpu_hw_events, cpu).ds = ds;
+
+		if (x86_pmu.bts) {
+			buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL);
+			if (unlikely(!buffer))
+				break;
+
+			max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
+			thresh = max / 16;
+
+			ds->bts_buffer_base = (u64)(unsigned long)buffer;
+			ds->bts_index = ds->bts_buffer_base;
+			ds->bts_absolute_maximum = ds->bts_buffer_base +
+				max * BTS_RECORD_SIZE;
+			ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
+				thresh * BTS_RECORD_SIZE;
+		}
+
+		if (x86_pmu.pebs) {
+			buffer = kzalloc(PEBS_BUFFER_SIZE, GFP_KERNEL);
+			if (unlikely(!buffer))
+				break;
+
+			max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
+
+			ds->pebs_buffer_base = (u64)(unsigned long)buffer;
+			ds->pebs_index = ds->pebs_buffer_base;
+			ds->pebs_absolute_maximum = ds->pebs_buffer_base +
+				max * x86_pmu.pebs_record_size;
+			/*
+			 * Always use single record PEBS
+			 */
+			ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
+				x86_pmu.pebs_record_size;
+		}
+
+		err = 0;
+	}
+
+	if (err)
+		release_ds_buffers();
+	else {
+		for_each_online_cpu(cpu)
+			init_debug_store_on_cpu(cpu);
+	}
+
+	put_online_cpus();
+
+	return err;
+}
+
+/*
+ * BTS
+ */
+
+static struct event_constraint bts_constraint =
+	EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0);
+
+static void intel_pmu_enable_bts(u64 config)
+{
+	unsigned long debugctlmsr;
+
+	debugctlmsr = get_debugctlmsr();
+
+	debugctlmsr |= DEBUGCTLMSR_TR;
+	debugctlmsr |= DEBUGCTLMSR_BTS;
+	debugctlmsr |= DEBUGCTLMSR_BTINT;
+
+	if (!(config & ARCH_PERFMON_EVENTSEL_OS))
+		debugctlmsr |= DEBUGCTLMSR_BTS_OFF_OS;
+
+	if (!(config & ARCH_PERFMON_EVENTSEL_USR))
+		debugctlmsr |= DEBUGCTLMSR_BTS_OFF_USR;
+
+	update_debugctlmsr(debugctlmsr);
+}
+
+static void intel_pmu_disable_bts(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	unsigned long debugctlmsr;
+
+	if (!cpuc->ds)
+		return;
+
+	debugctlmsr = get_debugctlmsr();
+
+	debugctlmsr &=
+		~(DEBUGCTLMSR_TR | DEBUGCTLMSR_BTS | DEBUGCTLMSR_BTINT |
+		  DEBUGCTLMSR_BTS_OFF_OS | DEBUGCTLMSR_BTS_OFF_USR);
+
+	update_debugctlmsr(debugctlmsr);
+}
+
+static void intel_pmu_drain_bts_buffer(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct debug_store *ds = cpuc->ds;
+	struct bts_record {
+		u64	from;
+		u64	to;
+		u64	flags;
+	};
+	struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS];
+	struct bts_record *at, *top;
+	struct perf_output_handle handle;
+	struct perf_event_header header;
+	struct perf_sample_data data;
+	struct pt_regs regs;
+
+	if (!event)
+		return;
+
+	if (!ds)
+		return;
+
+	at  = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
+	top = (struct bts_record *)(unsigned long)ds->bts_index;
+
+	if (top <= at)
+		return;
+
+	ds->bts_index = ds->bts_buffer_base;
+
+	perf_sample_data_init(&data, 0);
+	data.period = event->hw.last_period;
+	regs.ip     = 0;
+
+	/*
+	 * Prepare a generic sample, i.e. fill in the invariant fields.
+	 * We will overwrite the from and to address before we output
+	 * the sample.
+	 */
+	perf_prepare_sample(&header, &data, event, &regs);
+
+	if (perf_output_begin(&handle, event, header.size * (top - at), 1, 1))
+		return;
+
+	for (; at < top; at++) {
+		data.ip		= at->from;
+		data.addr	= at->to;
+
+		perf_output_sample(&handle, &header, &data, event);
+	}
+
+	perf_output_end(&handle);
+
+	/* There's new data available. */
+	event->hw.interrupts++;
+	event->pending_kill = POLL_IN;
+}
+
+/*
+ * PEBS
+ */
+
+static struct event_constraint intel_core_pebs_events[] = {
+	PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INSTR_RETIRED.ANY */
+	PEBS_EVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
+	PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
+	PEBS_EVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
+	PEBS_EVENT_CONSTRAINT(0x01cb, 0x1), /* MEM_LOAD_RETIRED.L1D_MISS */
+	PEBS_EVENT_CONSTRAINT(0x02cb, 0x1), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
+	PEBS_EVENT_CONSTRAINT(0x04cb, 0x1), /* MEM_LOAD_RETIRED.L2_MISS */
+	PEBS_EVENT_CONSTRAINT(0x08cb, 0x1), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
+	PEBS_EVENT_CONSTRAINT(0x10cb, 0x1), /* MEM_LOAD_RETIRED.DTLB_MISS */
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_nehalem_pebs_events[] = {
+	PEBS_EVENT_CONSTRAINT(0x00c0, 0xf), /* INSTR_RETIRED.ANY */
+	PEBS_EVENT_CONSTRAINT(0xfec1, 0xf), /* X87_OPS_RETIRED.ANY */
+	PEBS_EVENT_CONSTRAINT(0x00c5, 0xf), /* BR_INST_RETIRED.MISPRED */
+	PEBS_EVENT_CONSTRAINT(0x1fc7, 0xf), /* SIMD_INST_RETURED.ANY */
+	PEBS_EVENT_CONSTRAINT(0x01cb, 0xf), /* MEM_LOAD_RETIRED.L1D_MISS */
+	PEBS_EVENT_CONSTRAINT(0x02cb, 0xf), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
+	PEBS_EVENT_CONSTRAINT(0x04cb, 0xf), /* MEM_LOAD_RETIRED.L2_MISS */
+	PEBS_EVENT_CONSTRAINT(0x08cb, 0xf), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
+	PEBS_EVENT_CONSTRAINT(0x10cb, 0xf), /* MEM_LOAD_RETIRED.DTLB_MISS */
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint *
+intel_pebs_constraints(struct perf_event *event)
+{
+	struct event_constraint *c;
+
+	if (!event->attr.precise)
+		return NULL;
+
+	if (x86_pmu.pebs_constraints) {
+		for_each_event_constraint(c, x86_pmu.pebs_constraints) {
+			if ((event->hw.config & c->cmask) == c->code)
+				return c;
+		}
+	}
+
+	return &emptyconstraint;
+}
+
+static void intel_pmu_pebs_enable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
+
+	cpuc->pebs_enabled |= 1ULL << hwc->idx;
+	WARN_ON_ONCE(cpuc->enabled);
+
+	if (x86_pmu.intel_cap.pebs_trap)
+		intel_pmu_lbr_enable(event);
+}
+
+static void intel_pmu_pebs_disable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
+	if (cpuc->enabled)
+		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+
+	hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
+
+	if (x86_pmu.intel_cap.pebs_trap)
+		intel_pmu_lbr_disable(event);
+}
+
+static void intel_pmu_pebs_enable_all(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (cpuc->pebs_enabled)
+		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+}
+
+static void intel_pmu_pebs_disable_all(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (cpuc->pebs_enabled)
+		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);
+	unsigned long from = cpuc->lbr_entries[0].from;
+	unsigned long old_to, to = cpuc->lbr_entries[0].to;
+	unsigned long ip = regs->ip;
+
+	/*
+	 * We don't need to fixup if the PEBS assist is fault like
+	 */
+	if (!x86_pmu.intel_cap.pebs_trap)
+		return 1;
+
+	/*
+	 * No LBR entry, no basic block, no rewinding
+	 */
+	if (!cpuc->lbr_stack.nr || !from || !to)
+		return 0;
+
+	/*
+	 * Basic blocks should never cross user/kernel boundaries
+	 */
+	if (kernel_ip(ip) != kernel_ip(to))
+		return 0;
+
+	/*
+	 * unsigned math, either ip is before the start (impossible) or
+	 * the basic block is larger than 1 page (sanity)
+	 */
+	if ((ip - to) > PAGE_SIZE)
+		return 0;
+
+	/*
+	 * We sampled a branch insn, rewind using the LBR stack
+	 */
+	if (ip == to) {
+		regs->ip = from;
+		return 1;
+	}
+
+	do {
+		struct insn insn;
+		u8 buf[MAX_INSN_SIZE];
+		void *kaddr;
+
+		old_to = to;
+		if (!kernel_ip(ip)) {
+			int bytes, size = MAX_INSN_SIZE;
+
+			bytes = copy_from_user_nmi(buf, (void __user *)to, size);
+			if (bytes != size)
+				return 0;
+
+			kaddr = buf;
+		} else
+			kaddr = (void *)to;
+
+		kernel_insn_init(&insn, kaddr);
+		insn_get_length(&insn);
+		to += insn.length;
+	} while (to < ip);
+
+	if (to == ip) {
+		regs->ip = old_to;
+		return 1;
+	}
+
+	/*
+	 * Even though we decoded the basic block, the instruction stream
+	 * never matched the given IP, either the TO or the IP got corrupted.
+	 */
+	return 0;
+}
+
+static int intel_pmu_save_and_restart(struct perf_event *event);
+
+static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct debug_store *ds = cpuc->ds;
+	struct perf_event *event = cpuc->events[0]; /* PMC0 only */
+	struct pebs_record_core *at, *top;
+	struct perf_sample_data data;
+	struct perf_raw_record raw;
+	struct pt_regs regs;
+	int n;
+
+	if (!ds || !x86_pmu.pebs)
+		return;
+
+	at  = (struct pebs_record_core *)(unsigned long)ds->pebs_buffer_base;
+	top = (struct pebs_record_core *)(unsigned long)ds->pebs_index;
+
+	/*
+	 * Whatever else happens, drain the thing
+	 */
+	ds->pebs_index = ds->pebs_buffer_base;
+
+	if (!test_bit(0, cpuc->active_mask))
+		return;
+
+	WARN_ON_ONCE(!event);
+
+	if (!event->attr.precise)
+		return;
+
+	n = top - at;
+	if (n <= 0)
+		return;
+
+	if (!intel_pmu_save_and_restart(event))
+		return;
+
+	/*
+	 * Should not happen, we program the threshold at 1 and do not
+	 * set a reset value.
+	 */
+	WARN_ON_ONCE(n > 1);
+	at += n - 1;
+
+	perf_sample_data_init(&data, 0);
+	data.period = event->hw.last_period;
+
+	if (event->attr.sample_type & PERF_SAMPLE_RAW) {
+		raw.size = x86_pmu.pebs_record_size;
+		raw.data = at;
+		data.raw = &raw;
+	}
+
+	/*
+	 * We use the interrupt regs as a base because the PEBS record
+	 * does not contain a full regs set, specifically it seems to
+	 * lack segment descriptors, which get used by things like
+	 * user_mode().
+	 *
+	 * In the simple case fix up only the IP and BP,SP regs, for
+	 * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly.
+	 * A possible PERF_SAMPLE_REGS will have to transfer all regs.
+	 */
+	regs = *iregs;
+	regs.ip = at->ip;
+	regs.bp = at->bp;
+	regs.sp = at->sp;
+
+	if (intel_pmu_pebs_fixup_ip(&regs))
+		regs.flags |= PERF_EFLAGS_EXACT;
+	else
+		regs.flags &= ~PERF_EFLAGS_EXACT;
+
+	if (perf_event_overflow(event, 1, &data, &regs))
+		x86_pmu_stop(event);
+}
+
+static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct debug_store *ds = cpuc->ds;
+	struct pebs_record_nhm *at, *top;
+	struct perf_sample_data data;
+	struct perf_event *event = NULL;
+	struct perf_raw_record raw;
+	struct pt_regs regs;
+	u64 status = 0;
+	int bit, n;
+
+	if (!ds || !x86_pmu.pebs)
+		return;
+
+	at  = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
+	top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
+
+	ds->pebs_index = ds->pebs_buffer_base;
+
+	n = top - at;
+	if (n <= 0)
+		return;
+
+	/*
+	 * Should not happen, we program the threshold at 1 and do not
+	 * set a reset value.
+	 */
+	WARN_ON_ONCE(n > MAX_PEBS_EVENTS);
+
+	for ( ; at < top; at++) {
+		for_each_set_bit(bit, (unsigned long *)&at->status, MAX_PEBS_EVENTS) {
+			event = cpuc->events[bit];
+			if (!test_bit(bit, cpuc->active_mask))
+				continue;
+
+			WARN_ON_ONCE(!event);
+
+			if (!event->attr.precise)
+				continue;
+
+			if (__test_and_set_bit(bit, (unsigned long *)&status))
+				continue;
+
+			break;
+		}
+
+		if (!event || bit >= MAX_PEBS_EVENTS)
+			continue;
+
+		if (!intel_pmu_save_and_restart(event))
+			continue;
+
+		perf_sample_data_init(&data, 0);
+		data.period = event->hw.last_period;
+
+		if (event->attr.sample_type & PERF_SAMPLE_RAW) {
+			raw.size = x86_pmu.pebs_record_size;
+			raw.data = at;
+			data.raw = &raw;
+		}
+
+		/*
+		 * See the comment in intel_pmu_drain_pebs_core()
+		 */
+		regs = *iregs;
+		regs.ip = at->ip;
+		regs.bp = at->bp;
+		regs.sp = at->sp;
+
+		if (intel_pmu_pebs_fixup_ip(&regs))
+			regs.flags |= PERF_EFLAGS_EXACT;
+		else
+			regs.flags &= ~PERF_EFLAGS_EXACT;
+
+		if (perf_event_overflow(event, 1, &data, &regs))
+			x86_pmu_stop(event);
+	}
+}
+
+/*
+ * BTS, PEBS probe and setup
+ */
+
+static void intel_ds_init(void)
+{
+	/*
+	 * No support for 32bit formats
+	 */
+	if (!boot_cpu_has(X86_FEATURE_DTES64))
+		return;
+
+	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
+	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
+	if (x86_pmu.pebs) {
+		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
+		int format = x86_pmu.intel_cap.pebs_format;
+
+		switch (format) {
+		case 0:
+			printk(KERN_CONT "PEBS fmt0%c, ", pebs_type);
+			x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
+			x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
+			x86_pmu.pebs_constraints = intel_core_pebs_events;
+			break;
+
+		case 1:
+			printk(KERN_CONT "PEBS fmt1%c, ", pebs_type);
+			x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm);
+			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
+			x86_pmu.pebs_constraints = intel_nehalem_pebs_events;
+			break;
+
+		default:
+			printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type);
+			x86_pmu.pebs = 0;
+			break;
+		}
+	}
+}
+
+#else /* CONFIG_CPU_SUP_INTEL */
+
+static int reserve_ds_buffers(void)
+{
+	return 0;
+}
+
+static void release_ds_buffers(void)
+{
+}
+
+#endif /* CONFIG_CPU_SUP_INTEL */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
new file mode 100644
index 000000000000..d202c1bece1a
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -0,0 +1,218 @@
+#ifdef CONFIG_CPU_SUP_INTEL
+
+enum {
+	LBR_FORMAT_32		= 0x00,
+	LBR_FORMAT_LIP		= 0x01,
+	LBR_FORMAT_EIP		= 0x02,
+	LBR_FORMAT_EIP_FLAGS	= 0x03,
+};
+
+/*
+ * We only support LBR implementations that have FREEZE_LBRS_ON_PMI
+ * otherwise it becomes near impossible to get a reliable stack.
+ */
+
+static void __intel_pmu_lbr_enable(void)
+{
+	u64 debugctl;
+
+	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+	debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+}
+
+static void __intel_pmu_lbr_disable(void)
+{
+	u64 debugctl;
+
+	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+	debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+}
+
+static void intel_pmu_lbr_reset_32(void)
+{
+	int i;
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++)
+		wrmsrl(x86_pmu.lbr_from + i, 0);
+}
+
+static void intel_pmu_lbr_reset_64(void)
+{
+	int i;
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		wrmsrl(x86_pmu.lbr_from + i, 0);
+		wrmsrl(x86_pmu.lbr_to   + i, 0);
+	}
+}
+
+static void intel_pmu_lbr_reset(void)
+{
+	if (!x86_pmu.lbr_nr)
+		return;
+
+	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
+		intel_pmu_lbr_reset_32();
+	else
+		intel_pmu_lbr_reset_64();
+}
+
+static void intel_pmu_lbr_enable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (!x86_pmu.lbr_nr)
+		return;
+
+	WARN_ON_ONCE(cpuc->enabled);
+
+	/*
+	 * 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->lbr_users++;
+}
+
+static void intel_pmu_lbr_disable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (!x86_pmu.lbr_nr)
+		return;
+
+	cpuc->lbr_users--;
+	WARN_ON_ONCE(cpuc->lbr_users < 0);
+
+	if (cpuc->enabled && !cpuc->lbr_users)
+		__intel_pmu_lbr_disable();
+}
+
+static void intel_pmu_lbr_enable_all(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (cpuc->lbr_users)
+		__intel_pmu_lbr_enable();
+}
+
+static void intel_pmu_lbr_disable_all(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (cpuc->lbr_users)
+		__intel_pmu_lbr_disable();
+}
+
+static inline u64 intel_pmu_lbr_tos(void)
+{
+	u64 tos;
+
+	rdmsrl(x86_pmu.lbr_tos, tos);
+
+	return tos;
+}
+
+static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
+{
+	unsigned long mask = x86_pmu.lbr_nr - 1;
+	u64 tos = intel_pmu_lbr_tos();
+	int i;
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		unsigned long lbr_idx = (tos - i) & mask;
+		union {
+			struct {
+				u32 from;
+				u32 to;
+			};
+			u64     lbr;
+		} msr_lastbranch;
+
+		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_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
+ * LBR formats.
+ */
+static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
+{
+	unsigned long mask = x86_pmu.lbr_nr - 1;
+	int lbr_format = x86_pmu.intel_cap.lbr_format;
+	u64 tos = intel_pmu_lbr_tos();
+	int i;
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		unsigned long lbr_idx = (tos - i) & mask;
+		u64 from, to, flags = 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);
+			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_stack.nr = i;
+}
+
+static void intel_pmu_lbr_read(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (!cpuc->lbr_users)
+		return;
+
+	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
+		intel_pmu_lbr_read_32(cpuc);
+	else
+		intel_pmu_lbr_read_64(cpuc);
+}
+
+static 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;
+}
+
+static 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;
+}
+
+static void intel_pmu_lbr_init_atom(void)
+{
+	x86_pmu.lbr_nr	   = 8;
+	x86_pmu.lbr_tos    = 0x01c9;
+	x86_pmu.lbr_from   = 0x40;
+	x86_pmu.lbr_to     = 0x60;
+}
+
+#endif /* CONFIG_CPU_SUP_INTEL */
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
new file mode 100644
index 000000000000..15367cce66bd
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -0,0 +1,834 @@
+/*
+ * Netburst Perfomance Events (P4, old Xeon)
+ *
+ *  Copyright (C) 2010 Parallels, Inc., Cyrill Gorcunov <gorcunov@openvz.org>
+ *  Copyright (C) 2010 Intel Corporation, Lin Ming <ming.m.lin@intel.com>
+ *
+ *  For licencing details see kernel-base/COPYING
+ */
+
+#ifdef CONFIG_CPU_SUP_INTEL
+
+#include <asm/perf_event_p4.h>
+
+#define P4_CNTR_LIMIT 3
+/*
+ * array indices: 0,1 - HT threads, used with HT enabled cpu
+ */
+struct p4_event_bind {
+	unsigned int opcode;			/* Event code and ESCR selector */
+	unsigned int escr_msr[2];		/* ESCR MSR for this event */
+	unsigned char cntr[2][P4_CNTR_LIMIT];	/* counter index (offset), -1 on abscence */
+};
+
+struct p4_cache_event_bind {
+	unsigned int metric_pebs;
+	unsigned int metric_vert;
+};
+
+#define P4_GEN_CACHE_EVENT_BIND(name)		\
+	[P4_CACHE__##name] = {			\
+		.metric_pebs = P4_PEBS__##name,	\
+		.metric_vert = P4_VERT__##name,	\
+	}
+
+static struct p4_cache_event_bind p4_cache_event_bind_map[] = {
+	P4_GEN_CACHE_EVENT_BIND(1stl_cache_load_miss_retired),
+	P4_GEN_CACHE_EVENT_BIND(2ndl_cache_load_miss_retired),
+	P4_GEN_CACHE_EVENT_BIND(dtlb_load_miss_retired),
+	P4_GEN_CACHE_EVENT_BIND(dtlb_store_miss_retired),
+};
+
+/*
+ * Note that we don't use CCCR1 here, there is an
+ * exception for P4_BSQ_ALLOCATION but we just have
+ * no workaround
+ *
+ * consider this binding as resources which particular
+ * event may borrow, it doesn't contain EventMask,
+ * Tags and friends -- they are left to a caller
+ */
+static struct p4_event_bind p4_event_bind_map[] = {
+	[P4_EVENT_TC_DELIVER_MODE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_TC_DELIVER_MODE),
+		.escr_msr	= { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_BPU_FETCH_REQUEST] = {
+		.opcode		= P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST),
+		.escr_msr	= { MSR_P4_BPU_ESCR0, MSR_P4_BPU_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_ITLB_REFERENCE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_ITLB_REFERENCE),
+		.escr_msr	= { MSR_P4_ITLB_ESCR0, MSR_P4_ITLB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_MEMORY_CANCEL] = {
+		.opcode		= P4_OPCODE(P4_EVENT_MEMORY_CANCEL),
+		.escr_msr	= { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_MEMORY_COMPLETE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_MEMORY_COMPLETE),
+		.escr_msr	= { MSR_P4_SAAT_ESCR0 , MSR_P4_SAAT_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_LOAD_PORT_REPLAY] = {
+		.opcode		= P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY),
+		.escr_msr	= { MSR_P4_SAAT_ESCR0, MSR_P4_SAAT_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_STORE_PORT_REPLAY] = {
+		.opcode		= P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY),
+		.escr_msr	= { MSR_P4_SAAT_ESCR0 ,  MSR_P4_SAAT_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_MOB_LOAD_REPLAY] = {
+		.opcode		= P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY),
+		.escr_msr	= { MSR_P4_MOB_ESCR0, MSR_P4_MOB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_PAGE_WALK_TYPE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE),
+		.escr_msr	= { MSR_P4_PMH_ESCR0, MSR_P4_PMH_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_BSQ_CACHE_REFERENCE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE),
+		.escr_msr	= { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_IOQ_ALLOCATION] = {
+		.opcode		= P4_OPCODE(P4_EVENT_IOQ_ALLOCATION),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_IOQ_ACTIVE_ENTRIES] = {	/* shared ESCR */
+		.opcode		= P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES),
+		.escr_msr	= { MSR_P4_FSB_ESCR1,  MSR_P4_FSB_ESCR1 },
+		.cntr		= { {2, -1, -1}, {3, -1, -1} },
+	},
+	[P4_EVENT_FSB_DATA_ACTIVITY] = {
+		.opcode		= P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_BSQ_ALLOCATION] = {		/* shared ESCR, broken CCCR1 */
+		.opcode		= P4_OPCODE(P4_EVENT_BSQ_ALLOCATION),
+		.escr_msr	= { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR0 },
+		.cntr		= { {0, -1, -1}, {1, -1, -1} },
+	},
+	[P4_EVENT_BSQ_ACTIVE_ENTRIES] = {	/* shared ESCR */
+		.opcode		= P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES),
+		.escr_msr	= { MSR_P4_BSU_ESCR1 , MSR_P4_BSU_ESCR1 },
+		.cntr		= { {2, -1, -1}, {3, -1, -1} },
+	},
+	[P4_EVENT_SSE_INPUT_ASSIST] = {
+		.opcode		= P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_PACKED_SP_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_PACKED_SP_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_PACKED_DP_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_PACKED_DP_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_SCALAR_SP_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_SCALAR_SP_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_SCALAR_DP_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_SCALAR_DP_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_64BIT_MMX_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_64BIT_MMX_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_128BIT_MMX_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_128BIT_MMX_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_X87_FP_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_X87_FP_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_TC_MISC] = {
+		.opcode		= P4_OPCODE(P4_EVENT_TC_MISC),
+		.escr_msr	= { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_GLOBAL_POWER_EVENTS] = {
+		.opcode		= P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_TC_MS_XFER] = {
+		.opcode		= P4_OPCODE(P4_EVENT_TC_MS_XFER),
+		.escr_msr	= { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_UOP_QUEUE_WRITES] = {
+		.opcode		= P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES),
+		.escr_msr	= { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE),
+		.escr_msr	= { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR0 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_RETIRED_BRANCH_TYPE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE),
+		.escr_msr	= { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR1 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_RESOURCE_STALL] = {
+		.opcode		= P4_OPCODE(P4_EVENT_RESOURCE_STALL),
+		.escr_msr	= { MSR_P4_ALF_ESCR0, MSR_P4_ALF_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_WC_BUFFER] = {
+		.opcode		= P4_OPCODE(P4_EVENT_WC_BUFFER),
+		.escr_msr	= { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_B2B_CYCLES] = {
+		.opcode		= P4_OPCODE(P4_EVENT_B2B_CYCLES),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_BNR] = {
+		.opcode		= P4_OPCODE(P4_EVENT_BNR),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_SNOOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_SNOOP),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_RESPONSE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_RESPONSE),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_FRONT_END_EVENT] = {
+		.opcode		= P4_OPCODE(P4_EVENT_FRONT_END_EVENT),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_EXECUTION_EVENT] = {
+		.opcode		= P4_OPCODE(P4_EVENT_EXECUTION_EVENT),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_REPLAY_EVENT] = {
+		.opcode		= P4_OPCODE(P4_EVENT_REPLAY_EVENT),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_INSTR_RETIRED] = {
+		.opcode		= P4_OPCODE(P4_EVENT_INSTR_RETIRED),
+		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_UOPS_RETIRED] = {
+		.opcode		= P4_OPCODE(P4_EVENT_UOPS_RETIRED),
+		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_UOP_TYPE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_UOP_TYPE),
+		.escr_msr	= { MSR_P4_RAT_ESCR0, MSR_P4_RAT_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_BRANCH_RETIRED] = {
+		.opcode		= P4_OPCODE(P4_EVENT_BRANCH_RETIRED),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_MISPRED_BRANCH_RETIRED] = {
+		.opcode		= P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED),
+		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_X87_ASSIST] = {
+		.opcode		= P4_OPCODE(P4_EVENT_X87_ASSIST),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_MACHINE_CLEAR] = {
+		.opcode		= P4_OPCODE(P4_EVENT_MACHINE_CLEAR),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_INSTR_COMPLETED] = {
+		.opcode		= P4_OPCODE(P4_EVENT_INSTR_COMPLETED),
+		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+};
+
+#define P4_GEN_CACHE_EVENT(event, bit, cache_event)			  \
+	p4_config_pack_escr(P4_ESCR_EVENT(event)			| \
+			    P4_ESCR_EMASK_BIT(event, bit))		| \
+	p4_config_pack_cccr(cache_event					| \
+			    P4_CCCR_ESEL(P4_OPCODE_ESEL(P4_OPCODE(event))))
+
+static __initconst const u64 p4_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS,
+						P4_CACHE__1stl_cache_load_miss_retired),
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS,
+						P4_CACHE__2ndl_cache_load_miss_retired),
+	},
+},
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS,
+						P4_CACHE__dtlb_load_miss_retired),
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS,
+						P4_CACHE__dtlb_store_miss_retired),
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_ITLB_REFERENCE, HIT,
+						P4_CACHE__itlb_reference_hit),
+		[ C(RESULT_MISS)   ] = P4_GEN_CACHE_EVENT(P4_EVENT_ITLB_REFERENCE, MISS,
+						P4_CACHE__itlb_reference_miss),
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static u64 p4_general_events[PERF_COUNT_HW_MAX] = {
+  /* non-halted CPU clocks */
+  [PERF_COUNT_HW_CPU_CYCLES] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_GLOBAL_POWER_EVENTS)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING)),
+
+  /*
+   * retired instructions
+   * in a sake of simplicity we don't use the FSB tagging
+   */
+  [PERF_COUNT_HW_INSTRUCTIONS] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_INSTR_RETIRED)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, BOGUSNTAG)),
+
+  /* cache hits */
+  [PERF_COUNT_HW_CACHE_REFERENCES] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_BSQ_CACHE_REFERENCE)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM)),
+
+  /* cache misses */
+  [PERF_COUNT_HW_CACHE_MISSES] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_BSQ_CACHE_REFERENCE)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS)),
+
+  /* branch instructions retired */
+  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_RETIRED_BRANCH_TYPE)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CALL)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT)),
+
+  /* mispredicted branches retired */
+  [PERF_COUNT_HW_BRANCH_MISSES]	=
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_MISPRED_BRANCH_RETIRED)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS)),
+
+  /* bus ready clocks (cpu is driving #DRDY_DRV\#DRDY_OWN):  */
+  [PERF_COUNT_HW_BUS_CYCLES] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_FSB_DATA_ACTIVITY)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN))	|
+	p4_config_pack_cccr(P4_CCCR_EDGE | P4_CCCR_COMPARE),
+};
+
+static struct p4_event_bind *p4_config_get_bind(u64 config)
+{
+	unsigned int evnt = p4_config_unpack_event(config);
+	struct p4_event_bind *bind = NULL;
+
+	if (evnt < ARRAY_SIZE(p4_event_bind_map))
+		bind = &p4_event_bind_map[evnt];
+
+	return bind;
+}
+
+static u64 p4_pmu_event_map(int hw_event)
+{
+	struct p4_event_bind *bind;
+	unsigned int esel;
+	u64 config;
+
+	if (hw_event > ARRAY_SIZE(p4_general_events)) {
+		printk_once(KERN_ERR "P4 PMU: Bad index: %i\n", hw_event);
+		return 0;
+	}
+
+	config = p4_general_events[hw_event];
+	bind = p4_config_get_bind(config);
+	esel = P4_OPCODE_ESEL(bind->opcode);
+	config |= p4_config_pack_cccr(P4_CCCR_ESEL(esel));
+
+	return config;
+}
+
+static int p4_hw_config(struct perf_event *event)
+{
+	int cpu = raw_smp_processor_id();
+	u32 escr, cccr;
+
+	/*
+	 * the reason we use cpu that early is that: if we get scheduled
+	 * first time on the same cpu -- we will not need swap thread
+	 * specific flags in config (and will save some cpu cycles)
+	 */
+
+	cccr = p4_default_cccr_conf(cpu);
+	escr = p4_default_escr_conf(cpu, event->attr.exclude_kernel,
+					 event->attr.exclude_user);
+	event->hw.config = p4_config_pack_escr(escr) |
+			   p4_config_pack_cccr(cccr);
+
+	if (p4_ht_active() && p4_ht_thread(cpu))
+		event->hw.config = p4_set_ht_bit(event->hw.config);
+
+	if (event->attr.type != PERF_TYPE_RAW)
+		return 0;
+
+	/*
+	 * We don't control raw events so it's up to the caller
+	 * to pass sane values (and we don't count the thread number
+	 * on HT machine but allow HT-compatible specifics to be
+	 * passed on)
+	 *
+	 * XXX: HT wide things should check perf_paranoid_cpu() &&
+	 *      CAP_SYS_ADMIN
+	 */
+	event->hw.config |= event->attr.config &
+		(p4_config_pack_escr(P4_ESCR_MASK_HT) |
+		 p4_config_pack_cccr(P4_CCCR_MASK_HT));
+
+	return 0;
+}
+
+static inline void p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
+{
+	unsigned long dummy;
+
+	rdmsrl(hwc->config_base + hwc->idx, dummy);
+	if (dummy & P4_CCCR_OVF) {
+		(void)checking_wrmsrl(hwc->config_base + hwc->idx,
+			((u64)dummy) & ~P4_CCCR_OVF);
+	}
+}
+
+static inline void p4_pmu_disable_event(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/*
+	 * If event gets disabled while counter is in overflowed
+	 * state we need to clear P4_CCCR_OVF, otherwise interrupt get
+	 * asserted again and again
+	 */
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx,
+		(u64)(p4_config_unpack_cccr(hwc->config)) &
+			~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED);
+}
+
+static void p4_pmu_disable_all(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int idx;
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		struct perf_event *event = cpuc->events[idx];
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+		p4_pmu_disable_event(event);
+	}
+}
+
+static void p4_pmu_enable_event(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int thread = p4_ht_config_thread(hwc->config);
+	u64 escr_conf = p4_config_unpack_escr(p4_clear_ht_bit(hwc->config));
+	unsigned int idx = p4_config_unpack_event(hwc->config);
+	unsigned int idx_cache = p4_config_unpack_cache_event(hwc->config);
+	struct p4_event_bind *bind;
+	struct p4_cache_event_bind *bind_cache;
+	u64 escr_addr, cccr;
+
+	bind = &p4_event_bind_map[idx];
+	escr_addr = (u64)bind->escr_msr[thread];
+
+	/*
+	 * - we dont support cascaded counters yet
+	 * - and counter 1 is broken (erratum)
+	 */
+	WARN_ON_ONCE(p4_is_event_cascaded(hwc->config));
+	WARN_ON_ONCE(hwc->idx == 1);
+
+	/* we need a real Event value */
+	escr_conf &= ~P4_ESCR_EVENT_MASK;
+	escr_conf |= P4_ESCR_EVENT(P4_OPCODE_EVNT(bind->opcode));
+
+	cccr = p4_config_unpack_cccr(hwc->config);
+
+	/*
+	 * it could be Cache event so that we need to
+	 * set metrics into additional MSRs
+	 */
+	BUILD_BUG_ON(P4_CACHE__MAX > P4_CCCR_CACHE_OPS_MASK);
+	if (idx_cache > P4_CACHE__NONE &&
+		idx_cache < ARRAY_SIZE(p4_cache_event_bind_map)) {
+		bind_cache = &p4_cache_event_bind_map[idx_cache];
+		(void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)bind_cache->metric_pebs);
+		(void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)bind_cache->metric_vert);
+	}
+
+	(void)checking_wrmsrl(escr_addr, escr_conf);
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx,
+				(cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE);
+}
+
+static void p4_pmu_enable_all(int added)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int idx;
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		struct perf_event *event = cpuc->events[idx];
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+		p4_pmu_enable_event(event);
+	}
+}
+
+static int p4_pmu_handle_irq(struct pt_regs *regs)
+{
+	struct perf_sample_data data;
+	struct cpu_hw_events *cpuc;
+	struct perf_event *event;
+	struct hw_perf_event *hwc;
+	int idx, handled = 0;
+	u64 val;
+
+	data.addr = 0;
+	data.raw = NULL;
+
+	cpuc = &__get_cpu_var(cpu_hw_events);
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+
+		event = cpuc->events[idx];
+		hwc = &event->hw;
+
+		WARN_ON_ONCE(hwc->idx != idx);
+
+		/*
+		 * FIXME: Redundant call, actually not needed
+		 * but just to check if we're screwed
+		 */
+		p4_pmu_clear_cccr_ovf(hwc);
+
+		val = x86_perf_event_update(event);
+		if (val & (1ULL << (x86_pmu.cntval_bits - 1)))
+			continue;
+
+		/*
+		 * event overflow
+		 */
+		handled		= 1;
+		data.period	= event->hw.last_period;
+
+		if (!x86_perf_event_set_period(event))
+			continue;
+		if (perf_event_overflow(event, 1, &data, regs))
+			p4_pmu_disable_event(event);
+	}
+
+	if (handled) {
+		/* p4 quirk: unmask it again */
+		apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED);
+		inc_irq_stat(apic_perf_irqs);
+	}
+
+	return handled;
+}
+
+/*
+ * swap thread specific fields according to a thread
+ * we are going to run on
+ */
+static void p4_pmu_swap_config_ts(struct hw_perf_event *hwc, int cpu)
+{
+	u32 escr, cccr;
+
+	/*
+	 * we either lucky and continue on same cpu or no HT support
+	 */
+	if (!p4_should_swap_ts(hwc->config, cpu))
+		return;
+
+	/*
+	 * the event is migrated from an another logical
+	 * cpu, so we need to swap thread specific flags
+	 */
+
+	escr = p4_config_unpack_escr(hwc->config);
+	cccr = p4_config_unpack_cccr(hwc->config);
+
+	if (p4_ht_thread(cpu)) {
+		cccr &= ~P4_CCCR_OVF_PMI_T0;
+		cccr |= P4_CCCR_OVF_PMI_T1;
+		if (escr & P4_ESCR_T0_OS) {
+			escr &= ~P4_ESCR_T0_OS;
+			escr |= P4_ESCR_T1_OS;
+		}
+		if (escr & P4_ESCR_T0_USR) {
+			escr &= ~P4_ESCR_T0_USR;
+			escr |= P4_ESCR_T1_USR;
+		}
+		hwc->config  = p4_config_pack_escr(escr);
+		hwc->config |= p4_config_pack_cccr(cccr);
+		hwc->config |= P4_CONFIG_HT;
+	} else {
+		cccr &= ~P4_CCCR_OVF_PMI_T1;
+		cccr |= P4_CCCR_OVF_PMI_T0;
+		if (escr & P4_ESCR_T1_OS) {
+			escr &= ~P4_ESCR_T1_OS;
+			escr |= P4_ESCR_T0_OS;
+		}
+		if (escr & P4_ESCR_T1_USR) {
+			escr &= ~P4_ESCR_T1_USR;
+			escr |= P4_ESCR_T0_USR;
+		}
+		hwc->config  = p4_config_pack_escr(escr);
+		hwc->config |= p4_config_pack_cccr(cccr);
+		hwc->config &= ~P4_CONFIG_HT;
+	}
+}
+
+/* ESCRs are not sequential in memory so we need a map */
+static const unsigned int p4_escr_map[ARCH_P4_TOTAL_ESCR] = {
+	MSR_P4_ALF_ESCR0,	/*  0 */
+	MSR_P4_ALF_ESCR1,	/*  1 */
+	MSR_P4_BPU_ESCR0,	/*  2 */
+	MSR_P4_BPU_ESCR1,	/*  3 */
+	MSR_P4_BSU_ESCR0,	/*  4 */
+	MSR_P4_BSU_ESCR1,	/*  5 */
+	MSR_P4_CRU_ESCR0,	/*  6 */
+	MSR_P4_CRU_ESCR1,	/*  7 */
+	MSR_P4_CRU_ESCR2,	/*  8 */
+	MSR_P4_CRU_ESCR3,	/*  9 */
+	MSR_P4_CRU_ESCR4,	/* 10 */
+	MSR_P4_CRU_ESCR5,	/* 11 */
+	MSR_P4_DAC_ESCR0,	/* 12 */
+	MSR_P4_DAC_ESCR1,	/* 13 */
+	MSR_P4_FIRM_ESCR0,	/* 14 */
+	MSR_P4_FIRM_ESCR1,	/* 15 */
+	MSR_P4_FLAME_ESCR0,	/* 16 */
+	MSR_P4_FLAME_ESCR1,	/* 17 */
+	MSR_P4_FSB_ESCR0,	/* 18 */
+	MSR_P4_FSB_ESCR1,	/* 19 */
+	MSR_P4_IQ_ESCR0,	/* 20 */
+	MSR_P4_IQ_ESCR1,	/* 21 */
+	MSR_P4_IS_ESCR0,	/* 22 */
+	MSR_P4_IS_ESCR1,	/* 23 */
+	MSR_P4_ITLB_ESCR0,	/* 24 */
+	MSR_P4_ITLB_ESCR1,	/* 25 */
+	MSR_P4_IX_ESCR0,	/* 26 */
+	MSR_P4_IX_ESCR1,	/* 27 */
+	MSR_P4_MOB_ESCR0,	/* 28 */
+	MSR_P4_MOB_ESCR1,	/* 29 */
+	MSR_P4_MS_ESCR0,	/* 30 */
+	MSR_P4_MS_ESCR1,	/* 31 */
+	MSR_P4_PMH_ESCR0,	/* 32 */
+	MSR_P4_PMH_ESCR1,	/* 33 */
+	MSR_P4_RAT_ESCR0,	/* 34 */
+	MSR_P4_RAT_ESCR1,	/* 35 */
+	MSR_P4_SAAT_ESCR0,	/* 36 */
+	MSR_P4_SAAT_ESCR1,	/* 37 */
+	MSR_P4_SSU_ESCR0,	/* 38 */
+	MSR_P4_SSU_ESCR1,	/* 39 */
+	MSR_P4_TBPU_ESCR0,	/* 40 */
+	MSR_P4_TBPU_ESCR1,	/* 41 */
+	MSR_P4_TC_ESCR0,	/* 42 */
+	MSR_P4_TC_ESCR1,	/* 43 */
+	MSR_P4_U2L_ESCR0,	/* 44 */
+	MSR_P4_U2L_ESCR1,	/* 45 */
+};
+
+static int p4_get_escr_idx(unsigned int addr)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(p4_escr_map); i++) {
+		if (addr == p4_escr_map[i])
+			return i;
+	}
+
+	return -1;
+}
+
+static int p4_next_cntr(int thread, unsigned long *used_mask,
+			struct p4_event_bind *bind)
+{
+	int i = 0, j;
+
+	for (i = 0; i < P4_CNTR_LIMIT; i++) {
+		j = bind->cntr[thread][i++];
+		if (j == -1 || !test_bit(j, used_mask))
+			return j;
+	}
+
+	return -1;
+}
+
+static int p4_pmu_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
+{
+	unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	unsigned long escr_mask[BITS_TO_LONGS(ARCH_P4_TOTAL_ESCR)];
+	int cpu = raw_smp_processor_id();
+	struct hw_perf_event *hwc;
+	struct p4_event_bind *bind;
+	unsigned int i, thread, num;
+	int cntr_idx, escr_idx;
+
+	bitmap_zero(used_mask, X86_PMC_IDX_MAX);
+	bitmap_zero(escr_mask, ARCH_P4_TOTAL_ESCR);
+
+	for (i = 0, num = n; i < n; i++, num--) {
+
+		hwc = &cpuc->event_list[i]->hw;
+		thread = p4_ht_thread(cpu);
+		bind = p4_config_get_bind(hwc->config);
+		escr_idx = p4_get_escr_idx(bind->escr_msr[thread]);
+
+		if (hwc->idx != -1 && !p4_should_swap_ts(hwc->config, cpu)) {
+			cntr_idx = hwc->idx;
+			if (assign)
+				assign[i] = hwc->idx;
+			goto reserve;
+		}
+
+		cntr_idx = p4_next_cntr(thread, used_mask, bind);
+		if (cntr_idx == -1 || test_bit(escr_idx, escr_mask))
+			goto done;
+
+		p4_pmu_swap_config_ts(hwc, cpu);
+		if (assign)
+			assign[i] = cntr_idx;
+reserve:
+		set_bit(cntr_idx, used_mask);
+		set_bit(escr_idx, escr_mask);
+	}
+
+done:
+	return num ? -ENOSPC : 0;
+}
+
+static __initconst const struct x86_pmu p4_pmu = {
+	.name			= "Netburst P4/Xeon",
+	.handle_irq		= p4_pmu_handle_irq,
+	.disable_all		= p4_pmu_disable_all,
+	.enable_all		= p4_pmu_enable_all,
+	.enable			= p4_pmu_enable_event,
+	.disable		= p4_pmu_disable_event,
+	.eventsel		= MSR_P4_BPU_CCCR0,
+	.perfctr		= MSR_P4_BPU_PERFCTR0,
+	.event_map		= p4_pmu_event_map,
+	.max_events		= ARRAY_SIZE(p4_general_events),
+	.get_event_constraints	= x86_get_event_constraints,
+	/*
+	 * IF HT disabled we may need to use all
+	 * ARCH_P4_MAX_CCCR counters simulaneously
+	 * though leave it restricted at moment assuming
+	 * HT is on
+	 */
+	.num_counters		= ARCH_P4_MAX_CCCR,
+	.apic			= 1,
+	.cntval_bits		= 40,
+	.cntval_mask		= (1ULL << 40) - 1,
+	.max_period		= (1ULL << 39) - 1,
+	.hw_config		= p4_hw_config,
+	.schedule_events	= p4_pmu_schedule_events,
+};
+
+static __init int p4_pmu_init(void)
+{
+	unsigned int low, high;
+
+	/* If we get stripped -- indexig fails */
+	BUILD_BUG_ON(ARCH_P4_MAX_CCCR > X86_PMC_MAX_GENERIC);
+
+	rdmsr(MSR_IA32_MISC_ENABLE, low, high);
+	if (!(low & (1 << 7))) {
+		pr_cont("unsupported Netburst CPU model %d ",
+			boot_cpu_data.x86_model);
+		return -ENODEV;
+	}
+
+	memcpy(hw_cache_event_ids, p4_hw_cache_event_ids,
+		sizeof(hw_cache_event_ids));
+
+	pr_cont("Netburst events, ");
+
+	x86_pmu = p4_pmu;
+
+	return 0;
+}
+
+#endif /* CONFIG_CPU_SUP_INTEL */
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index a330485d14da..34ba07be2cda 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -27,24 +27,6 @@ static u64 p6_pmu_event_map(int hw_event)
  */
 #define P6_NOP_EVENT			0x0000002EULL
 
-static u64 p6_pmu_raw_event(u64 hw_event)
-{
-#define P6_EVNTSEL_EVENT_MASK		0x000000FFULL
-#define P6_EVNTSEL_UNIT_MASK		0x0000FF00ULL
-#define P6_EVNTSEL_EDGE_MASK		0x00040000ULL
-#define P6_EVNTSEL_INV_MASK		0x00800000ULL
-#define P6_EVNTSEL_REG_MASK		0xFF000000ULL
-
-#define P6_EVNTSEL_MASK			\
-	(P6_EVNTSEL_EVENT_MASK |	\
-	 P6_EVNTSEL_UNIT_MASK  |	\
-	 P6_EVNTSEL_EDGE_MASK  |	\
-	 P6_EVNTSEL_INV_MASK   |	\
-	 P6_EVNTSEL_REG_MASK)
-
-	return hw_event & P6_EVNTSEL_MASK;
-}
-
 static struct event_constraint p6_event_constraints[] =
 {
 	INTEL_EVENT_CONSTRAINT(0xc1, 0x1),	/* FLOPS */
@@ -66,7 +48,7 @@ static void p6_pmu_disable_all(void)
 	wrmsrl(MSR_P6_EVNTSEL0, val);
 }
 
-static void p6_pmu_enable_all(void)
+static void p6_pmu_enable_all(int added)
 {
 	unsigned long val;
 
@@ -102,22 +84,23 @@ static void p6_pmu_enable_event(struct perf_event *event)
 	(void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
 }
 
-static __initconst struct x86_pmu p6_pmu = {
+static __initconst const struct x86_pmu p6_pmu = {
 	.name			= "p6",
 	.handle_irq		= x86_pmu_handle_irq,
 	.disable_all		= p6_pmu_disable_all,
 	.enable_all		= p6_pmu_enable_all,
 	.enable			= p6_pmu_enable_event,
 	.disable		= p6_pmu_disable_event,
+	.hw_config		= x86_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_P6_EVNTSEL0,
 	.perfctr		= MSR_P6_PERFCTR0,
 	.event_map		= p6_pmu_event_map,
-	.raw_event		= p6_pmu_raw_event,
 	.max_events		= ARRAY_SIZE(p6_perfmon_event_map),
 	.apic			= 1,
 	.max_period		= (1ULL << 31) - 1,
 	.version		= 0,
-	.num_events		= 2,
+	.num_counters		= 2,
 	/*
 	 * Events have 40 bits implemented. However they are designed such
 	 * that bits [32-39] are sign extensions of bit 31. As such the
@@ -125,8 +108,8 @@ static __initconst struct x86_pmu p6_pmu = {
 	 *
 	 * See IA-32 Intel Architecture Software developer manual Vol 3B
 	 */
-	.event_bits		= 32,
-	.event_mask		= (1ULL << 32) - 1,
+	.cntval_bits		= 32,
+	.cntval_mask		= (1ULL << 32) - 1,
 	.get_event_constraints	= x86_get_event_constraints,
 	.event_constraints	= p6_event_constraints,
 };
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
deleted file mode 100644
index 1c47390dd0e5..000000000000
--- a/arch/x86/kernel/ds.c
+++ /dev/null
@@ -1,1437 +0,0 @@
-/*
- * Debug Store support
- *
- * This provides a low-level interface to the hardware's Debug Store
- * feature that is used for branch trace store (BTS) and
- * precise-event based sampling (PEBS).
- *
- * It manages:
- * - DS and BTS hardware configuration
- * - buffer overflow handling (to be done)
- * - buffer access
- *
- * It does not do:
- * - security checking (is the caller allowed to trace the task)
- * - buffer allocation (memory accounting)
- *
- *
- * Copyright (C) 2007-2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
- */
-
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/mm.h>
-#include <linux/trace_clock.h>
-
-#include <asm/ds.h>
-
-#include "ds_selftest.h"
-
-/*
- * The configuration for a particular DS hardware implementation:
- */
-struct ds_configuration {
-	/* The name of the configuration: */
-	const char		*name;
-
-	/* The size of pointer-typed fields in DS, BTS, and PEBS: */
-	unsigned char		sizeof_ptr_field;
-
-	/* The size of a BTS/PEBS record in bytes: */
-	unsigned char		sizeof_rec[2];
-
-	/* The number of pebs counter reset values in the DS structure. */
-	unsigned char		nr_counter_reset;
-
-	/* Control bit-masks indexed by enum ds_feature: */
-	unsigned long		ctl[dsf_ctl_max];
-};
-static struct ds_configuration ds_cfg __read_mostly;
-
-
-/* Maximal size of a DS configuration: */
-#define MAX_SIZEOF_DS		0x80
-
-/* Maximal size of a BTS record: */
-#define MAX_SIZEOF_BTS		(3 * 8)
-
-/* BTS and PEBS buffer alignment: */
-#define DS_ALIGNMENT		(1 << 3)
-
-/* Number of buffer pointers in DS: */
-#define NUM_DS_PTR_FIELDS	8
-
-/* Size of a pebs reset value in DS: */
-#define PEBS_RESET_FIELD_SIZE	8
-
-/* Mask of control bits in the DS MSR register: */
-#define BTS_CONTROL				  \
-	( ds_cfg.ctl[dsf_bts]			| \
-	  ds_cfg.ctl[dsf_bts_kernel]		| \
-	  ds_cfg.ctl[dsf_bts_user]		| \
-	  ds_cfg.ctl[dsf_bts_overflow] )
-
-/*
- * A BTS or PEBS tracer.
- *
- * This holds the configuration of the tracer and serves as a handle
- * to identify tracers.
- */
-struct ds_tracer {
-	/* The DS context (partially) owned by this tracer. */
-	struct ds_context	*context;
-	/* The buffer provided on ds_request() and its size in bytes. */
-	void			*buffer;
-	size_t			size;
-};
-
-struct bts_tracer {
-	/* The common DS part: */
-	struct ds_tracer	ds;
-
-	/* The trace including the DS configuration: */
-	struct bts_trace	trace;
-
-	/* Buffer overflow notification function: */
-	bts_ovfl_callback_t	ovfl;
-
-	/* Active flags affecting trace collection. */
-	unsigned int		flags;
-};
-
-struct pebs_tracer {
-	/* The common DS part: */
-	struct ds_tracer	ds;
-
-	/* The trace including the DS configuration: */
-	struct pebs_trace	trace;
-
-	/* Buffer overflow notification function: */
-	pebs_ovfl_callback_t	ovfl;
-};
-
-/*
- * Debug Store (DS) save area configuration (see Intel64 and IA32
- * Architectures Software Developer's Manual, section 18.5)
- *
- * The DS configuration consists of the following fields; different
- * architetures vary in the size of those fields.
- *
- * - double-word aligned base linear address of the BTS buffer
- * - write pointer into the BTS buffer
- * - end linear address of the BTS buffer (one byte beyond the end of
- *   the buffer)
- * - interrupt pointer into BTS buffer
- *   (interrupt occurs when write pointer passes interrupt pointer)
- * - double-word aligned base linear address of the PEBS buffer
- * - write pointer into the PEBS buffer
- * - end linear address of the PEBS buffer (one byte beyond the end of
- *   the buffer)
- * - interrupt pointer into PEBS buffer
- *   (interrupt occurs when write pointer passes interrupt pointer)
- * - value to which counter is reset following counter overflow
- *
- * Later architectures use 64bit pointers throughout, whereas earlier
- * architectures use 32bit pointers in 32bit mode.
- *
- *
- * We compute the base address for the first 8 fields based on:
- * - the field size stored in the DS configuration
- * - the relative field position
- * - an offset giving the start of the respective region
- *
- * This offset is further used to index various arrays holding
- * information for BTS and PEBS at the respective index.
- *
- * On later 32bit processors, we only access the lower 32bit of the
- * 64bit pointer fields. The upper halves will be zeroed out.
- */
-
-enum ds_field {
-	ds_buffer_base = 0,
-	ds_index,
-	ds_absolute_maximum,
-	ds_interrupt_threshold,
-};
-
-enum ds_qualifier {
-	ds_bts = 0,
-	ds_pebs
-};
-
-static inline unsigned long
-ds_get(const unsigned char *base, enum ds_qualifier qual, enum ds_field field)
-{
-	base += (ds_cfg.sizeof_ptr_field * (field + (4 * qual)));
-	return *(unsigned long *)base;
-}
-
-static inline void
-ds_set(unsigned char *base, enum ds_qualifier qual, enum ds_field field,
-       unsigned long value)
-{
-	base += (ds_cfg.sizeof_ptr_field * (field + (4 * qual)));
-	(*(unsigned long *)base) = value;
-}
-
-
-/*
- * Locking is done only for allocating BTS or PEBS resources.
- */
-static DEFINE_SPINLOCK(ds_lock);
-
-/*
- * We either support (system-wide) per-cpu or per-thread allocation.
- * We distinguish the two based on the task_struct pointer, where a
- * NULL pointer indicates per-cpu allocation for the current cpu.
- *
- * Allocations are use-counted. As soon as resources are allocated,
- * further allocations must be of the same type (per-cpu or
- * per-thread). We model this by counting allocations (i.e. the number
- * of tracers of a certain type) for one type negatively:
- *   =0  no tracers
- *   >0  number of per-thread tracers
- *   <0  number of per-cpu tracers
- *
- * Tracers essentially gives the number of ds contexts for a certain
- * type of allocation.
- */
-static atomic_t tracers = ATOMIC_INIT(0);
-
-static inline int get_tracer(struct task_struct *task)
-{
-	int error;
-
-	spin_lock_irq(&ds_lock);
-
-	if (task) {
-		error = -EPERM;
-		if (atomic_read(&tracers) < 0)
-			goto out;
-		atomic_inc(&tracers);
-	} else {
-		error = -EPERM;
-		if (atomic_read(&tracers) > 0)
-			goto out;
-		atomic_dec(&tracers);
-	}
-
-	error = 0;
-out:
-	spin_unlock_irq(&ds_lock);
-	return error;
-}
-
-static inline void put_tracer(struct task_struct *task)
-{
-	if (task)
-		atomic_dec(&tracers);
-	else
-		atomic_inc(&tracers);
-}
-
-/*
- * The DS context is either attached to a thread or to a cpu:
- * - in the former case, the thread_struct contains a pointer to the
- *   attached context.
- * - in the latter case, we use a static array of per-cpu context
- *   pointers.
- *
- * Contexts are use-counted. They are allocated on first access and
- * deallocated when the last user puts the context.
- */
-struct ds_context {
-	/* The DS configuration; goes into MSR_IA32_DS_AREA: */
-	unsigned char		ds[MAX_SIZEOF_DS];
-
-	/* The owner of the BTS and PEBS configuration, respectively: */
-	struct bts_tracer	*bts_master;
-	struct pebs_tracer	*pebs_master;
-
-	/* Use count: */
-	unsigned long		count;
-
-	/* Pointer to the context pointer field: */
-	struct ds_context	**this;
-
-	/* The traced task; NULL for cpu tracing: */
-	struct task_struct	*task;
-
-	/* The traced cpu; only valid if task is NULL: */
-	int			cpu;
-};
-
-static DEFINE_PER_CPU(struct ds_context *, cpu_ds_context);
-
-
-static struct ds_context *ds_get_context(struct task_struct *task, int cpu)
-{
-	struct ds_context **p_context =
-		(task ? &task->thread.ds_ctx : &per_cpu(cpu_ds_context, cpu));
-	struct ds_context *context = NULL;
-	struct ds_context *new_context = NULL;
-
-	/* Chances are small that we already have a context. */
-	new_context = kzalloc(sizeof(*new_context), GFP_KERNEL);
-	if (!new_context)
-		return NULL;
-
-	spin_lock_irq(&ds_lock);
-
-	context = *p_context;
-	if (likely(!context)) {
-		context = new_context;
-
-		context->this = p_context;
-		context->task = task;
-		context->cpu = cpu;
-		context->count = 0;
-
-		*p_context = context;
-	}
-
-	context->count++;
-
-	spin_unlock_irq(&ds_lock);
-
-	if (context != new_context)
-		kfree(new_context);
-
-	return context;
-}
-
-static void ds_put_context(struct ds_context *context)
-{
-	struct task_struct *task;
-	unsigned long irq;
-
-	if (!context)
-		return;
-
-	spin_lock_irqsave(&ds_lock, irq);
-
-	if (--context->count) {
-		spin_unlock_irqrestore(&ds_lock, irq);
-		return;
-	}
-
-	*(context->this) = NULL;
-
-	task = context->task;
-
-	if (task)
-		clear_tsk_thread_flag(task, TIF_DS_AREA_MSR);
-
-	/*
-	 * We leave the (now dangling) pointer to the DS configuration in
-	 * the DS_AREA msr. This is as good or as bad as replacing it with
-	 * NULL - the hardware would crash if we enabled tracing.
-	 *
-	 * This saves us some problems with having to write an msr on a
-	 * different cpu while preventing others from doing the same for the
-	 * next context for that same cpu.
-	 */
-
-	spin_unlock_irqrestore(&ds_lock, irq);
-
-	/* The context might still be in use for context switching. */
-	if (task && (task != current))
-		wait_task_context_switch(task);
-
-	kfree(context);
-}
-
-static void ds_install_ds_area(struct ds_context *context)
-{
-	unsigned long ds;
-
-	ds = (unsigned long)context->ds;
-
-	/*
-	 * There is a race between the bts master and the pebs master.
-	 *
-	 * The thread/cpu access is synchronized via get/put_cpu() for
-	 * task tracing and via wrmsr_on_cpu for cpu tracing.
-	 *
-	 * If bts and pebs are collected for the same task or same cpu,
-	 * the same confiuration is written twice.
-	 */
-	if (context->task) {
-		get_cpu();
-		if (context->task == current)
-			wrmsrl(MSR_IA32_DS_AREA, ds);
-		set_tsk_thread_flag(context->task, TIF_DS_AREA_MSR);
-		put_cpu();
-	} else
-		wrmsr_on_cpu(context->cpu, MSR_IA32_DS_AREA,
-			     (u32)((u64)ds), (u32)((u64)ds >> 32));
-}
-
-/*
- * Call the tracer's callback on a buffer overflow.
- *
- * context: the ds context
- * qual: the buffer type
- */
-static void ds_overflow(struct ds_context *context, enum ds_qualifier qual)
-{
-	switch (qual) {
-	case ds_bts:
-		if (context->bts_master &&
-		    context->bts_master->ovfl)
-			context->bts_master->ovfl(context->bts_master);
-		break;
-	case ds_pebs:
-		if (context->pebs_master &&
-		    context->pebs_master->ovfl)
-			context->pebs_master->ovfl(context->pebs_master);
-		break;
-	}
-}
-
-
-/*
- * Write raw data into the BTS or PEBS buffer.
- *
- * The remainder of any partially written record is zeroed out.
- *
- * context: the DS context
- * qual:    the buffer type
- * record:  the data to write
- * size:    the size of the data
- */
-static int ds_write(struct ds_context *context, enum ds_qualifier qual,
-		    const void *record, size_t size)
-{
-	int bytes_written = 0;
-
-	if (!record)
-		return -EINVAL;
-
-	while (size) {
-		unsigned long base, index, end, write_end, int_th;
-		unsigned long write_size, adj_write_size;
-
-		/*
-		 * Write as much as possible without producing an
-		 * overflow interrupt.
-		 *
-		 * Interrupt_threshold must either be
-		 * - bigger than absolute_maximum or
-		 * - point to a record between buffer_base and absolute_maximum
-		 *
-		 * Index points to a valid record.
-		 */
-		base   = ds_get(context->ds, qual, ds_buffer_base);
-		index  = ds_get(context->ds, qual, ds_index);
-		end    = ds_get(context->ds, qual, ds_absolute_maximum);
-		int_th = ds_get(context->ds, qual, ds_interrupt_threshold);
-
-		write_end = min(end, int_th);
-
-		/*
-		 * If we are already beyond the interrupt threshold,
-		 * we fill the entire buffer.
-		 */
-		if (write_end <= index)
-			write_end = end;
-
-		if (write_end <= index)
-			break;
-
-		write_size = min((unsigned long) size, write_end - index);
-		memcpy((void *)index, record, write_size);
-
-		record = (const char *)record + write_size;
-		size -= write_size;
-		bytes_written += write_size;
-
-		adj_write_size = write_size / ds_cfg.sizeof_rec[qual];
-		adj_write_size *= ds_cfg.sizeof_rec[qual];
-
-		/* Zero out trailing bytes. */
-		memset((char *)index + write_size, 0,
-		       adj_write_size - write_size);
-		index += adj_write_size;
-
-		if (index >= end)
-			index = base;
-		ds_set(context->ds, qual, ds_index, index);
-
-		if (index >= int_th)
-			ds_overflow(context, qual);
-	}
-
-	return bytes_written;
-}
-
-
-/*
- * Branch Trace Store (BTS) uses the following format. Different
- * architectures vary in the size of those fields.
- * - source linear address
- * - destination linear address
- * - flags
- *
- * Later architectures use 64bit pointers throughout, whereas earlier
- * architectures use 32bit pointers in 32bit mode.
- *
- * We compute the base address for the fields based on:
- * - the field size stored in the DS configuration
- * - the relative field position
- *
- * In order to store additional information in the BTS buffer, we use
- * a special source address to indicate that the record requires
- * special interpretation.
- *
- * Netburst indicated via a bit in the flags field whether the branch
- * was predicted; this is ignored.
- *
- * We use two levels of abstraction:
- * - the raw data level defined here
- * - an arch-independent level defined in ds.h
- */
-
-enum bts_field {
-	bts_from,
-	bts_to,
-	bts_flags,
-
-	bts_qual		= bts_from,
-	bts_clock		= bts_to,
-	bts_pid			= bts_flags,
-
-	bts_qual_mask		= (bts_qual_max - 1),
-	bts_escape		= ((unsigned long)-1 & ~bts_qual_mask)
-};
-
-static inline unsigned long bts_get(const char *base, unsigned long field)
-{
-	base += (ds_cfg.sizeof_ptr_field * field);
-	return *(unsigned long *)base;
-}
-
-static inline void bts_set(char *base, unsigned long field, unsigned long val)
-{
-	base += (ds_cfg.sizeof_ptr_field * field);
-	(*(unsigned long *)base) = val;
-}
-
-
-/*
- * The raw BTS data is architecture dependent.
- *
- * For higher-level users, we give an arch-independent view.
- * - ds.h defines struct bts_struct
- * - bts_read translates one raw bts record into a bts_struct
- * - bts_write translates one bts_struct into the raw format and
- *   writes it into the top of the parameter tracer's buffer.
- *
- * return: bytes read/written on success; -Eerrno, otherwise
- */
-static int
-bts_read(struct bts_tracer *tracer, const void *at, struct bts_struct *out)
-{
-	if (!tracer)
-		return -EINVAL;
-
-	if (at < tracer->trace.ds.begin)
-		return -EINVAL;
-
-	if (tracer->trace.ds.end < (at + tracer->trace.ds.size))
-		return -EINVAL;
-
-	memset(out, 0, sizeof(*out));
-	if ((bts_get(at, bts_qual) & ~bts_qual_mask) == bts_escape) {
-		out->qualifier = (bts_get(at, bts_qual) & bts_qual_mask);
-		out->variant.event.clock = bts_get(at, bts_clock);
-		out->variant.event.pid = bts_get(at, bts_pid);
-	} else {
-		out->qualifier = bts_branch;
-		out->variant.lbr.from = bts_get(at, bts_from);
-		out->variant.lbr.to   = bts_get(at, bts_to);
-
-		if (!out->variant.lbr.from && !out->variant.lbr.to)
-			out->qualifier = bts_invalid;
-	}
-
-	return ds_cfg.sizeof_rec[ds_bts];
-}
-
-static int bts_write(struct bts_tracer *tracer, const struct bts_struct *in)
-{
-	unsigned char raw[MAX_SIZEOF_BTS];
-
-	if (!tracer)
-		return -EINVAL;
-
-	if (MAX_SIZEOF_BTS < ds_cfg.sizeof_rec[ds_bts])
-		return -EOVERFLOW;
-
-	switch (in->qualifier) {
-	case bts_invalid:
-		bts_set(raw, bts_from, 0);
-		bts_set(raw, bts_to, 0);
-		bts_set(raw, bts_flags, 0);
-		break;
-	case bts_branch:
-		bts_set(raw, bts_from, in->variant.lbr.from);
-		bts_set(raw, bts_to,   in->variant.lbr.to);
-		bts_set(raw, bts_flags, 0);
-		break;
-	case bts_task_arrives:
-	case bts_task_departs:
-		bts_set(raw, bts_qual, (bts_escape | in->qualifier));
-		bts_set(raw, bts_clock, in->variant.event.clock);
-		bts_set(raw, bts_pid, in->variant.event.pid);
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return ds_write(tracer->ds.context, ds_bts, raw,
-			ds_cfg.sizeof_rec[ds_bts]);
-}
-
-
-static void ds_write_config(struct ds_context *context,
-			    struct ds_trace *cfg, enum ds_qualifier qual)
-{
-	unsigned char *ds = context->ds;
-
-	ds_set(ds, qual, ds_buffer_base, (unsigned long)cfg->begin);
-	ds_set(ds, qual, ds_index, (unsigned long)cfg->top);
-	ds_set(ds, qual, ds_absolute_maximum, (unsigned long)cfg->end);
-	ds_set(ds, qual, ds_interrupt_threshold, (unsigned long)cfg->ith);
-}
-
-static void ds_read_config(struct ds_context *context,
-			   struct ds_trace *cfg, enum ds_qualifier qual)
-{
-	unsigned char *ds = context->ds;
-
-	cfg->begin = (void *)ds_get(ds, qual, ds_buffer_base);
-	cfg->top = (void *)ds_get(ds, qual, ds_index);
-	cfg->end = (void *)ds_get(ds, qual, ds_absolute_maximum);
-	cfg->ith = (void *)ds_get(ds, qual, ds_interrupt_threshold);
-}
-
-static void ds_init_ds_trace(struct ds_trace *trace, enum ds_qualifier qual,
-			     void *base, size_t size, size_t ith,
-			     unsigned int flags) {
-	unsigned long buffer, adj;
-
-	/*
-	 * Adjust the buffer address and size to meet alignment
-	 * constraints:
-	 * - buffer is double-word aligned
-	 * - size is multiple of record size
-	 *
-	 * We checked the size at the very beginning; we have enough
-	 * space to do the adjustment.
-	 */
-	buffer = (unsigned long)base;
-
-	adj = ALIGN(buffer, DS_ALIGNMENT) - buffer;
-	buffer += adj;
-	size   -= adj;
-
-	trace->n = size / ds_cfg.sizeof_rec[qual];
-	trace->size = ds_cfg.sizeof_rec[qual];
-
-	size = (trace->n * trace->size);
-
-	trace->begin = (void *)buffer;
-	trace->top = trace->begin;
-	trace->end = (void *)(buffer + size);
-	/*
-	 * The value for 'no threshold' is -1, which will set the
-	 * threshold outside of the buffer, just like we want it.
-	 */
-	ith *= ds_cfg.sizeof_rec[qual];
-	trace->ith = (void *)(buffer + size - ith);
-
-	trace->flags = flags;
-}
-
-
-static int ds_request(struct ds_tracer *tracer, struct ds_trace *trace,
-		      enum ds_qualifier qual, struct task_struct *task,
-		      int cpu, void *base, size_t size, size_t th)
-{
-	struct ds_context *context;
-	int error;
-	size_t req_size;
-
-	error = -EOPNOTSUPP;
-	if (!ds_cfg.sizeof_rec[qual])
-		goto out;
-
-	error = -EINVAL;
-	if (!base)
-		goto out;
-
-	req_size = ds_cfg.sizeof_rec[qual];
-	/* We might need space for alignment adjustments. */
-	if (!IS_ALIGNED((unsigned long)base, DS_ALIGNMENT))
-		req_size += DS_ALIGNMENT;
-
-	error = -EINVAL;
-	if (size < req_size)
-		goto out;
-
-	if (th != (size_t)-1) {
-		th *= ds_cfg.sizeof_rec[qual];
-
-		error = -EINVAL;
-		if (size <= th)
-			goto out;
-	}
-
-	tracer->buffer = base;
-	tracer->size = size;
-
-	error = -ENOMEM;
-	context = ds_get_context(task, cpu);
-	if (!context)
-		goto out;
-	tracer->context = context;
-
-	/*
-	 * Defer any tracer-specific initialization work for the context until
-	 * context ownership has been clarified.
-	 */
-
-	error = 0;
- out:
-	return error;
-}
-
-static struct bts_tracer *ds_request_bts(struct task_struct *task, int cpu,
-					 void *base, size_t size,
-					 bts_ovfl_callback_t ovfl, size_t th,
-					 unsigned int flags)
-{
-	struct bts_tracer *tracer;
-	int error;
-
-	/* Buffer overflow notification is not yet implemented. */
-	error = -EOPNOTSUPP;
-	if (ovfl)
-		goto out;
-
-	error = get_tracer(task);
-	if (error < 0)
-		goto out;
-
-	error = -ENOMEM;
-	tracer = kzalloc(sizeof(*tracer), GFP_KERNEL);
-	if (!tracer)
-		goto out_put_tracer;
-	tracer->ovfl = ovfl;
-
-	/* Do some more error checking and acquire a tracing context. */
-	error = ds_request(&tracer->ds, &tracer->trace.ds,
-			   ds_bts, task, cpu, base, size, th);
-	if (error < 0)
-		goto out_tracer;
-
-	/* Claim the bts part of the tracing context we acquired above. */
-	spin_lock_irq(&ds_lock);
-
-	error = -EPERM;
-	if (tracer->ds.context->bts_master)
-		goto out_unlock;
-	tracer->ds.context->bts_master = tracer;
-
-	spin_unlock_irq(&ds_lock);
-
-	/*
-	 * Now that we own the bts part of the context, let's complete the
-	 * initialization for that part.
-	 */
-	ds_init_ds_trace(&tracer->trace.ds, ds_bts, base, size, th, flags);
-	ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts);
-	ds_install_ds_area(tracer->ds.context);
-
-	tracer->trace.read  = bts_read;
-	tracer->trace.write = bts_write;
-
-	/* Start tracing. */
-	ds_resume_bts(tracer);
-
-	return tracer;
-
- out_unlock:
-	spin_unlock_irq(&ds_lock);
-	ds_put_context(tracer->ds.context);
- out_tracer:
-	kfree(tracer);
- out_put_tracer:
-	put_tracer(task);
- out:
-	return ERR_PTR(error);
-}
-
-struct bts_tracer *ds_request_bts_task(struct task_struct *task,
-				       void *base, size_t size,
-				       bts_ovfl_callback_t ovfl,
-				       size_t th, unsigned int flags)
-{
-	return ds_request_bts(task, 0, base, size, ovfl, th, flags);
-}
-
-struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size,
-				      bts_ovfl_callback_t ovfl,
-				      size_t th, unsigned int flags)
-{
-	return ds_request_bts(NULL, cpu, base, size, ovfl, th, flags);
-}
-
-static struct pebs_tracer *ds_request_pebs(struct task_struct *task, int cpu,
-					   void *base, size_t size,
-					   pebs_ovfl_callback_t ovfl, size_t th,
-					   unsigned int flags)
-{
-	struct pebs_tracer *tracer;
-	int error;
-
-	/* Buffer overflow notification is not yet implemented. */
-	error = -EOPNOTSUPP;
-	if (ovfl)
-		goto out;
-
-	error = get_tracer(task);
-	if (error < 0)
-		goto out;
-
-	error = -ENOMEM;
-	tracer = kzalloc(sizeof(*tracer), GFP_KERNEL);
-	if (!tracer)
-		goto out_put_tracer;
-	tracer->ovfl = ovfl;
-
-	/* Do some more error checking and acquire a tracing context. */
-	error = ds_request(&tracer->ds, &tracer->trace.ds,
-			   ds_pebs, task, cpu, base, size, th);
-	if (error < 0)
-		goto out_tracer;
-
-	/* Claim the pebs part of the tracing context we acquired above. */
-	spin_lock_irq(&ds_lock);
-
-	error = -EPERM;
-	if (tracer->ds.context->pebs_master)
-		goto out_unlock;
-	tracer->ds.context->pebs_master = tracer;
-
-	spin_unlock_irq(&ds_lock);
-
-	/*
-	 * Now that we own the pebs part of the context, let's complete the
-	 * initialization for that part.
-	 */
-	ds_init_ds_trace(&tracer->trace.ds, ds_pebs, base, size, th, flags);
-	ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_pebs);
-	ds_install_ds_area(tracer->ds.context);
-
-	/* Start tracing. */
-	ds_resume_pebs(tracer);
-
-	return tracer;
-
- out_unlock:
-	spin_unlock_irq(&ds_lock);
-	ds_put_context(tracer->ds.context);
- out_tracer:
-	kfree(tracer);
- out_put_tracer:
-	put_tracer(task);
- out:
-	return ERR_PTR(error);
-}
-
-struct pebs_tracer *ds_request_pebs_task(struct task_struct *task,
-					 void *base, size_t size,
-					 pebs_ovfl_callback_t ovfl,
-					 size_t th, unsigned int flags)
-{
-	return ds_request_pebs(task, 0, base, size, ovfl, th, flags);
-}
-
-struct pebs_tracer *ds_request_pebs_cpu(int cpu, void *base, size_t size,
-					pebs_ovfl_callback_t ovfl,
-					size_t th, unsigned int flags)
-{
-	return ds_request_pebs(NULL, cpu, base, size, ovfl, th, flags);
-}
-
-static void ds_free_bts(struct bts_tracer *tracer)
-{
-	struct task_struct *task;
-
-	task = tracer->ds.context->task;
-
-	WARN_ON_ONCE(tracer->ds.context->bts_master != tracer);
-	tracer->ds.context->bts_master = NULL;
-
-	/* Make sure tracing stopped and the tracer is not in use. */
-	if (task && (task != current))
-		wait_task_context_switch(task);
-
-	ds_put_context(tracer->ds.context);
-	put_tracer(task);
-
-	kfree(tracer);
-}
-
-void ds_release_bts(struct bts_tracer *tracer)
-{
-	might_sleep();
-
-	if (!tracer)
-		return;
-
-	ds_suspend_bts(tracer);
-	ds_free_bts(tracer);
-}
-
-int ds_release_bts_noirq(struct bts_tracer *tracer)
-{
-	struct task_struct *task;
-	unsigned long irq;
-	int error;
-
-	if (!tracer)
-		return 0;
-
-	task = tracer->ds.context->task;
-
-	local_irq_save(irq);
-
-	error = -EPERM;
-	if (!task &&
-	    (tracer->ds.context->cpu != smp_processor_id()))
-		goto out;
-
-	error = -EPERM;
-	if (task && (task != current))
-		goto out;
-
-	ds_suspend_bts_noirq(tracer);
-	ds_free_bts(tracer);
-
-	error = 0;
- out:
-	local_irq_restore(irq);
-	return error;
-}
-
-static void update_task_debugctlmsr(struct task_struct *task,
-				    unsigned long debugctlmsr)
-{
-	task->thread.debugctlmsr = debugctlmsr;
-
-	get_cpu();
-	if (task == current)
-		update_debugctlmsr(debugctlmsr);
-	put_cpu();
-}
-
-void ds_suspend_bts(struct bts_tracer *tracer)
-{
-	struct task_struct *task;
-	unsigned long debugctlmsr;
-	int cpu;
-
-	if (!tracer)
-		return;
-
-	tracer->flags = 0;
-
-	task = tracer->ds.context->task;
-	cpu  = tracer->ds.context->cpu;
-
-	WARN_ON(!task && irqs_disabled());
-
-	debugctlmsr = (task ?
-		       task->thread.debugctlmsr :
-		       get_debugctlmsr_on_cpu(cpu));
-	debugctlmsr &= ~BTS_CONTROL;
-
-	if (task)
-		update_task_debugctlmsr(task, debugctlmsr);
-	else
-		update_debugctlmsr_on_cpu(cpu, debugctlmsr);
-}
-
-int ds_suspend_bts_noirq(struct bts_tracer *tracer)
-{
-	struct task_struct *task;
-	unsigned long debugctlmsr, irq;
-	int cpu, error = 0;
-
-	if (!tracer)
-		return 0;
-
-	tracer->flags = 0;
-
-	task = tracer->ds.context->task;
-	cpu  = tracer->ds.context->cpu;
-
-	local_irq_save(irq);
-
-	error = -EPERM;
-	if (!task && (cpu != smp_processor_id()))
-		goto out;
-
-	debugctlmsr = (task ?
-		       task->thread.debugctlmsr :
-		       get_debugctlmsr());
-	debugctlmsr &= ~BTS_CONTROL;
-
-	if (task)
-		update_task_debugctlmsr(task, debugctlmsr);
-	else
-		update_debugctlmsr(debugctlmsr);
-
-	error = 0;
- out:
-	local_irq_restore(irq);
-	return error;
-}
-
-static unsigned long ds_bts_control(struct bts_tracer *tracer)
-{
-	unsigned long control;
-
-	control = ds_cfg.ctl[dsf_bts];
-	if (!(tracer->trace.ds.flags & BTS_KERNEL))
-		control |= ds_cfg.ctl[dsf_bts_kernel];
-	if (!(tracer->trace.ds.flags & BTS_USER))
-		control |= ds_cfg.ctl[dsf_bts_user];
-
-	return control;
-}
-
-void ds_resume_bts(struct bts_tracer *tracer)
-{
-	struct task_struct *task;
-	unsigned long debugctlmsr;
-	int cpu;
-
-	if (!tracer)
-		return;
-
-	tracer->flags = tracer->trace.ds.flags;
-
-	task = tracer->ds.context->task;
-	cpu  = tracer->ds.context->cpu;
-
-	WARN_ON(!task && irqs_disabled());
-
-	debugctlmsr = (task ?
-		       task->thread.debugctlmsr :
-		       get_debugctlmsr_on_cpu(cpu));
-	debugctlmsr |= ds_bts_control(tracer);
-
-	if (task)
-		update_task_debugctlmsr(task, debugctlmsr);
-	else
-		update_debugctlmsr_on_cpu(cpu, debugctlmsr);
-}
-
-int ds_resume_bts_noirq(struct bts_tracer *tracer)
-{
-	struct task_struct *task;
-	unsigned long debugctlmsr, irq;
-	int cpu, error = 0;
-
-	if (!tracer)
-		return 0;
-
-	tracer->flags = tracer->trace.ds.flags;
-
-	task = tracer->ds.context->task;
-	cpu  = tracer->ds.context->cpu;
-
-	local_irq_save(irq);
-
-	error = -EPERM;
-	if (!task && (cpu != smp_processor_id()))
-		goto out;
-
-	debugctlmsr = (task ?
-		       task->thread.debugctlmsr :
-		       get_debugctlmsr());
-	debugctlmsr |= ds_bts_control(tracer);
-
-	if (task)
-		update_task_debugctlmsr(task, debugctlmsr);
-	else
-		update_debugctlmsr(debugctlmsr);
-
-	error = 0;
- out:
-	local_irq_restore(irq);
-	return error;
-}
-
-static void ds_free_pebs(struct pebs_tracer *tracer)
-{
-	struct task_struct *task;
-
-	task = tracer->ds.context->task;
-
-	WARN_ON_ONCE(tracer->ds.context->pebs_master != tracer);
-	tracer->ds.context->pebs_master = NULL;
-
-	ds_put_context(tracer->ds.context);
-	put_tracer(task);
-
-	kfree(tracer);
-}
-
-void ds_release_pebs(struct pebs_tracer *tracer)
-{
-	might_sleep();
-
-	if (!tracer)
-		return;
-
-	ds_suspend_pebs(tracer);
-	ds_free_pebs(tracer);
-}
-
-int ds_release_pebs_noirq(struct pebs_tracer *tracer)
-{
-	struct task_struct *task;
-	unsigned long irq;
-	int error;
-
-	if (!tracer)
-		return 0;
-
-	task = tracer->ds.context->task;
-
-	local_irq_save(irq);
-
-	error = -EPERM;
-	if (!task &&
-	    (tracer->ds.context->cpu != smp_processor_id()))
-		goto out;
-
-	error = -EPERM;
-	if (task && (task != current))
-		goto out;
-
-	ds_suspend_pebs_noirq(tracer);
-	ds_free_pebs(tracer);
-
-	error = 0;
- out:
-	local_irq_restore(irq);
-	return error;
-}
-
-void ds_suspend_pebs(struct pebs_tracer *tracer)
-{
-
-}
-
-int ds_suspend_pebs_noirq(struct pebs_tracer *tracer)
-{
-	return 0;
-}
-
-void ds_resume_pebs(struct pebs_tracer *tracer)
-{
-
-}
-
-int ds_resume_pebs_noirq(struct pebs_tracer *tracer)
-{
-	return 0;
-}
-
-const struct bts_trace *ds_read_bts(struct bts_tracer *tracer)
-{
-	if (!tracer)
-		return NULL;
-
-	ds_read_config(tracer->ds.context, &tracer->trace.ds, ds_bts);
-	return &tracer->trace;
-}
-
-const struct pebs_trace *ds_read_pebs(struct pebs_tracer *tracer)
-{
-	if (!tracer)
-		return NULL;
-
-	ds_read_config(tracer->ds.context, &tracer->trace.ds, ds_pebs);
-
-	tracer->trace.counters = ds_cfg.nr_counter_reset;
-	memcpy(tracer->trace.counter_reset,
-	       tracer->ds.context->ds +
-	       (NUM_DS_PTR_FIELDS * ds_cfg.sizeof_ptr_field),
-	       ds_cfg.nr_counter_reset * PEBS_RESET_FIELD_SIZE);
-
-	return &tracer->trace;
-}
-
-int ds_reset_bts(struct bts_tracer *tracer)
-{
-	if (!tracer)
-		return -EINVAL;
-
-	tracer->trace.ds.top = tracer->trace.ds.begin;
-
-	ds_set(tracer->ds.context->ds, ds_bts, ds_index,
-	       (unsigned long)tracer->trace.ds.top);
-
-	return 0;
-}
-
-int ds_reset_pebs(struct pebs_tracer *tracer)
-{
-	if (!tracer)
-		return -EINVAL;
-
-	tracer->trace.ds.top = tracer->trace.ds.begin;
-
-	ds_set(tracer->ds.context->ds, ds_pebs, ds_index,
-	       (unsigned long)tracer->trace.ds.top);
-
-	return 0;
-}
-
-int ds_set_pebs_reset(struct pebs_tracer *tracer,
-		      unsigned int counter, u64 value)
-{
-	if (!tracer)
-		return -EINVAL;
-
-	if (ds_cfg.nr_counter_reset < counter)
-		return -EINVAL;
-
-	*(u64 *)(tracer->ds.context->ds +
-		 (NUM_DS_PTR_FIELDS * ds_cfg.sizeof_ptr_field) +
-		 (counter * PEBS_RESET_FIELD_SIZE)) = value;
-
-	return 0;
-}
-
-static const struct ds_configuration ds_cfg_netburst = {
-	.name = "Netburst",
-	.ctl[dsf_bts]		= (1 << 2) | (1 << 3),
-	.ctl[dsf_bts_kernel]	= (1 << 5),
-	.ctl[dsf_bts_user]	= (1 << 6),
-	.nr_counter_reset	= 1,
-};
-static const struct ds_configuration ds_cfg_pentium_m = {
-	.name = "Pentium M",
-	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
-	.nr_counter_reset	= 1,
-};
-static const struct ds_configuration ds_cfg_core2_atom = {
-	.name = "Core 2/Atom",
-	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
-	.ctl[dsf_bts_kernel]	= (1 << 9),
-	.ctl[dsf_bts_user]	= (1 << 10),
-	.nr_counter_reset	= 1,
-};
-static const struct ds_configuration ds_cfg_core_i7 = {
-	.name = "Core i7",
-	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
-	.ctl[dsf_bts_kernel]	= (1 << 9),
-	.ctl[dsf_bts_user]	= (1 << 10),
-	.nr_counter_reset	= 4,
-};
-
-static void
-ds_configure(const struct ds_configuration *cfg,
-	     struct cpuinfo_x86 *cpu)
-{
-	unsigned long nr_pebs_fields = 0;
-
-	printk(KERN_INFO "[ds] using %s configuration\n", cfg->name);
-
-#ifdef __i386__
-	nr_pebs_fields = 10;
-#else
-	nr_pebs_fields = 18;
-#endif
-
-	/*
-	 * Starting with version 2, architectural performance
-	 * monitoring supports a format specifier.
-	 */
-	if ((cpuid_eax(0xa) & 0xff) > 1) {
-		unsigned long perf_capabilities, format;
-
-		rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_capabilities);
-
-		format = (perf_capabilities >> 8) & 0xf;
-
-		switch (format) {
-		case 0:
-			nr_pebs_fields = 18;
-			break;
-		case 1:
-			nr_pebs_fields = 22;
-			break;
-		default:
-			printk(KERN_INFO
-			       "[ds] unknown PEBS format: %lu\n", format);
-			nr_pebs_fields = 0;
-			break;
-		}
-	}
-
-	memset(&ds_cfg, 0, sizeof(ds_cfg));
-	ds_cfg = *cfg;
-
-	ds_cfg.sizeof_ptr_field =
-		(cpu_has(cpu, X86_FEATURE_DTES64) ? 8 : 4);
-
-	ds_cfg.sizeof_rec[ds_bts]  = ds_cfg.sizeof_ptr_field * 3;
-	ds_cfg.sizeof_rec[ds_pebs] = ds_cfg.sizeof_ptr_field * nr_pebs_fields;
-
-	if (!cpu_has(cpu, X86_FEATURE_BTS)) {
-		ds_cfg.sizeof_rec[ds_bts] = 0;
-		printk(KERN_INFO "[ds] bts not available\n");
-	}
-	if (!cpu_has(cpu, X86_FEATURE_PEBS)) {
-		ds_cfg.sizeof_rec[ds_pebs] = 0;
-		printk(KERN_INFO "[ds] pebs not available\n");
-	}
-
-	printk(KERN_INFO "[ds] sizes: address: %u bit, ",
-	       8 * ds_cfg.sizeof_ptr_field);
-	printk("bts/pebs record: %u/%u bytes\n",
-	       ds_cfg.sizeof_rec[ds_bts], ds_cfg.sizeof_rec[ds_pebs]);
-
-	WARN_ON_ONCE(MAX_PEBS_COUNTERS < ds_cfg.nr_counter_reset);
-}
-
-void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
-{
-	/* Only configure the first cpu. Others are identical. */
-	if (ds_cfg.name)
-		return;
-
-	switch (c->x86) {
-	case 0x6:
-		switch (c->x86_model) {
-		case 0x9:
-		case 0xd: /* Pentium M */
-			ds_configure(&ds_cfg_pentium_m, c);
-			break;
-		case 0xf:
-		case 0x17: /* Core2 */
-		case 0x1c: /* Atom */
-			ds_configure(&ds_cfg_core2_atom, c);
-			break;
-		case 0x1a: /* Core i7 */
-			ds_configure(&ds_cfg_core_i7, c);
-			break;
-		default:
-			/* Sorry, don't know about them. */
-			break;
-		}
-		break;
-	case 0xf:
-		switch (c->x86_model) {
-		case 0x0:
-		case 0x1:
-		case 0x2: /* Netburst */
-			ds_configure(&ds_cfg_netburst, c);
-			break;
-		default:
-			/* Sorry, don't know about them. */
-			break;
-		}
-		break;
-	default:
-		/* Sorry, don't know about them. */
-		break;
-	}
-}
-
-static inline void ds_take_timestamp(struct ds_context *context,
-				     enum bts_qualifier qualifier,
-				     struct task_struct *task)
-{
-	struct bts_tracer *tracer = context->bts_master;
-	struct bts_struct ts;
-
-	/* Prevent compilers from reading the tracer pointer twice. */
-	barrier();
-
-	if (!tracer || !(tracer->flags & BTS_TIMESTAMPS))
-		return;
-
-	memset(&ts, 0, sizeof(ts));
-	ts.qualifier		= qualifier;
-	ts.variant.event.clock	= trace_clock_global();
-	ts.variant.event.pid	= task->pid;
-
-	bts_write(tracer, &ts);
-}
-
-/*
- * Change the DS configuration from tracing prev to tracing next.
- */
-void ds_switch_to(struct task_struct *prev, struct task_struct *next)
-{
-	struct ds_context *prev_ctx	= prev->thread.ds_ctx;
-	struct ds_context *next_ctx	= next->thread.ds_ctx;
-	unsigned long debugctlmsr	= next->thread.debugctlmsr;
-
-	/* Make sure all data is read before we start. */
-	barrier();
-
-	if (prev_ctx) {
-		update_debugctlmsr(0);
-
-		ds_take_timestamp(prev_ctx, bts_task_departs, prev);
-	}
-
-	if (next_ctx) {
-		ds_take_timestamp(next_ctx, bts_task_arrives, next);
-
-		wrmsrl(MSR_IA32_DS_AREA, (unsigned long)next_ctx->ds);
-	}
-
-	update_debugctlmsr(debugctlmsr);
-}
-
-static __init int ds_selftest(void)
-{
-	if (ds_cfg.sizeof_rec[ds_bts]) {
-		int error;
-
-		error = ds_selftest_bts();
-		if (error) {
-			WARN(1, "[ds] selftest failed. disabling bts.\n");
-			ds_cfg.sizeof_rec[ds_bts] = 0;
-		}
-	}
-
-	if (ds_cfg.sizeof_rec[ds_pebs]) {
-		int error;
-
-		error = ds_selftest_pebs();
-		if (error) {
-			WARN(1, "[ds] selftest failed. disabling pebs.\n");
-			ds_cfg.sizeof_rec[ds_pebs] = 0;
-		}
-	}
-
-	return 0;
-}
-device_initcall(ds_selftest);
diff --git a/arch/x86/kernel/ds_selftest.c b/arch/x86/kernel/ds_selftest.c
deleted file mode 100644
index 6bc7c199ab99..000000000000
--- a/arch/x86/kernel/ds_selftest.c
+++ /dev/null
@@ -1,408 +0,0 @@
-/*
- * Debug Store support - selftest
- *
- *
- * Copyright (C) 2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2009
- */
-
-#include "ds_selftest.h"
-
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/smp.h>
-#include <linux/cpu.h>
-
-#include <asm/ds.h>
-
-
-#define BUFFER_SIZE		521	/* Intentionally chose an odd size. */
-#define SMALL_BUFFER_SIZE	24	/* A single bts entry. */
-
-struct ds_selftest_bts_conf {
-	struct bts_tracer *tracer;
-	int error;
-	int (*suspend)(struct bts_tracer *);
-	int (*resume)(struct bts_tracer *);
-};
-
-static int ds_selftest_bts_consistency(const struct bts_trace *trace)
-{
-	int error = 0;
-
-	if (!trace) {
-		printk(KERN_CONT "failed to access trace...");
-		/* Bail out. Other tests are pointless. */
-		return -1;
-	}
-
-	if (!trace->read) {
-		printk(KERN_CONT "bts read not available...");
-		error = -1;
-	}
-
-	/* Do some sanity checks on the trace configuration. */
-	if (!trace->ds.n) {
-		printk(KERN_CONT "empty bts buffer...");
-		error = -1;
-	}
-	if (!trace->ds.size) {
-		printk(KERN_CONT "bad bts trace setup...");
-		error = -1;
-	}
-	if (trace->ds.end !=
-	    (char *)trace->ds.begin + (trace->ds.n * trace->ds.size)) {
-		printk(KERN_CONT "bad bts buffer setup...");
-		error = -1;
-	}
-	/*
-	 * We allow top in [begin; end], since its not clear when the
-	 * overflow adjustment happens: after the increment or before the
-	 * write.
-	 */
-	if ((trace->ds.top < trace->ds.begin) ||
-	    (trace->ds.end < trace->ds.top)) {
-		printk(KERN_CONT "bts top out of bounds...");
-		error = -1;
-	}
-
-	return error;
-}
-
-static int ds_selftest_bts_read(struct bts_tracer *tracer,
-				const struct bts_trace *trace,
-				const void *from, const void *to)
-{
-	const unsigned char *at;
-
-	/*
-	 * Check a few things which do not belong to this test.
-	 * They should be covered by other tests.
-	 */
-	if (!trace)
-		return -1;
-
-	if (!trace->read)
-		return -1;
-
-	if (to < from)
-		return -1;
-
-	if (from < trace->ds.begin)
-		return -1;
-
-	if (trace->ds.end < to)
-		return -1;
-
-	if (!trace->ds.size)
-		return -1;
-
-	/* Now to the test itself. */
-	for (at = from; (void *)at < to; at += trace->ds.size) {
-		struct bts_struct bts;
-		unsigned long index;
-		int error;
-
-		if (((void *)at - trace->ds.begin) % trace->ds.size) {
-			printk(KERN_CONT
-			       "read from non-integer index...");
-			return -1;
-		}
-		index = ((void *)at - trace->ds.begin) / trace->ds.size;
-
-		memset(&bts, 0, sizeof(bts));
-		error = trace->read(tracer, at, &bts);
-		if (error < 0) {
-			printk(KERN_CONT
-			       "error reading bts trace at [%lu] (0x%p)...",
-			       index, at);
-			return error;
-		}
-
-		switch (bts.qualifier) {
-		case BTS_BRANCH:
-			break;
-		default:
-			printk(KERN_CONT
-			       "unexpected bts entry %llu at [%lu] (0x%p)...",
-			       bts.qualifier, index, at);
-			return -1;
-		}
-	}
-
-	return 0;
-}
-
-static void ds_selftest_bts_cpu(void *arg)
-{
-	struct ds_selftest_bts_conf *conf = arg;
-	const struct bts_trace *trace;
-	void *top;
-
-	if (IS_ERR(conf->tracer)) {
-		conf->error = PTR_ERR(conf->tracer);
-		conf->tracer = NULL;
-
-		printk(KERN_CONT
-		       "initialization failed (err: %d)...", conf->error);
-		return;
-	}
-
-	/* We should meanwhile have enough trace. */
-	conf->error = conf->suspend(conf->tracer);
-	if (conf->error < 0)
-		return;
-
-	/* Let's see if we can access the trace. */
-	trace = ds_read_bts(conf->tracer);
-
-	conf->error = ds_selftest_bts_consistency(trace);
-	if (conf->error < 0)
-		return;
-
-	/* If everything went well, we should have a few trace entries. */
-	if (trace->ds.top == trace->ds.begin) {
-		/*
-		 * It is possible but highly unlikely that we got a
-		 * buffer overflow and end up at exactly the same
-		 * position we started from.
-		 * Let's issue a warning, but continue.
-		 */
-		printk(KERN_CONT "no trace/overflow...");
-	}
-
-	/* Let's try to read the trace we collected. */
-	conf->error =
-		ds_selftest_bts_read(conf->tracer, trace,
-				     trace->ds.begin, trace->ds.top);
-	if (conf->error < 0)
-		return;
-
-	/*
-	 * Let's read the trace again.
-	 * Since we suspended tracing, we should get the same result.
-	 */
-	top = trace->ds.top;
-
-	trace = ds_read_bts(conf->tracer);
-	conf->error = ds_selftest_bts_consistency(trace);
-	if (conf->error < 0)
-		return;
-
-	if (top != trace->ds.top) {
-		printk(KERN_CONT "suspend not working...");
-		conf->error = -1;
-		return;
-	}
-
-	/* Let's collect some more trace - see if resume is working. */
-	conf->error = conf->resume(conf->tracer);
-	if (conf->error < 0)
-		return;
-
-	conf->error = conf->suspend(conf->tracer);
-	if (conf->error < 0)
-		return;
-
-	trace = ds_read_bts(conf->tracer);
-
-	conf->error = ds_selftest_bts_consistency(trace);
-	if (conf->error < 0)
-		return;
-
-	if (trace->ds.top == top) {
-		/*
-		 * It is possible but highly unlikely that we got a
-		 * buffer overflow and end up at exactly the same
-		 * position we started from.
-		 * Let's issue a warning and check the full trace.
-		 */
-		printk(KERN_CONT
-		       "no resume progress/overflow...");
-
-		conf->error =
-			ds_selftest_bts_read(conf->tracer, trace,
-					     trace->ds.begin, trace->ds.end);
-	} else if (trace->ds.top < top) {
-		/*
-		 * We had a buffer overflow - the entire buffer should
-		 * contain trace records.
-		 */
-		conf->error =
-			ds_selftest_bts_read(conf->tracer, trace,
-					     trace->ds.begin, trace->ds.end);
-	} else {
-		/*
-		 * It is quite likely that the buffer did not overflow.
-		 * Let's just check the delta trace.
-		 */
-		conf->error =
-			ds_selftest_bts_read(conf->tracer, trace, top,
-					     trace->ds.top);
-	}
-	if (conf->error < 0)
-		return;
-
-	conf->error = 0;
-}
-
-static int ds_suspend_bts_wrap(struct bts_tracer *tracer)
-{
-	ds_suspend_bts(tracer);
-	return 0;
-}
-
-static int ds_resume_bts_wrap(struct bts_tracer *tracer)
-{
-	ds_resume_bts(tracer);
-	return 0;
-}
-
-static void ds_release_bts_noirq_wrap(void *tracer)
-{
-	(void)ds_release_bts_noirq(tracer);
-}
-
-static int ds_selftest_bts_bad_release_noirq(int cpu,
-					     struct bts_tracer *tracer)
-{
-	int error = -EPERM;
-
-	/* Try to release the tracer on the wrong cpu. */
-	get_cpu();
-	if (cpu != smp_processor_id()) {
-		error = ds_release_bts_noirq(tracer);
-		if (error != -EPERM)
-			printk(KERN_CONT "release on wrong cpu...");
-	}
-	put_cpu();
-
-	return error ? 0 : -1;
-}
-
-static int ds_selftest_bts_bad_request_cpu(int cpu, void *buffer)
-{
-	struct bts_tracer *tracer;
-	int error;
-
-	/* Try to request cpu tracing while task tracing is active. */
-	tracer = ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE, NULL,
-				    (size_t)-1, BTS_KERNEL);
-	error = PTR_ERR(tracer);
-	if (!IS_ERR(tracer)) {
-		ds_release_bts(tracer);
-		error = 0;
-	}
-
-	if (error != -EPERM)
-		printk(KERN_CONT "cpu/task tracing overlap...");
-
-	return error ? 0 : -1;
-}
-
-static int ds_selftest_bts_bad_request_task(void *buffer)
-{
-	struct bts_tracer *tracer;
-	int error;
-
-	/* Try to request cpu tracing while task tracing is active. */
-	tracer = ds_request_bts_task(current, buffer, BUFFER_SIZE, NULL,
-				    (size_t)-1, BTS_KERNEL);
-	error = PTR_ERR(tracer);
-	if (!IS_ERR(tracer)) {
-		error = 0;
-		ds_release_bts(tracer);
-	}
-
-	if (error != -EPERM)
-		printk(KERN_CONT "task/cpu tracing overlap...");
-
-	return error ? 0 : -1;
-}
-
-int ds_selftest_bts(void)
-{
-	struct ds_selftest_bts_conf conf;
-	unsigned char buffer[BUFFER_SIZE], *small_buffer;
-	unsigned long irq;
-	int cpu;
-
-	printk(KERN_INFO "[ds] bts selftest...");
-	conf.error = 0;
-
-	small_buffer = (unsigned char *)ALIGN((unsigned long)buffer, 8) + 8;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu) {
-		conf.suspend = ds_suspend_bts_wrap;
-		conf.resume = ds_resume_bts_wrap;
-		conf.tracer =
-			ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE,
-					   NULL, (size_t)-1, BTS_KERNEL);
-		ds_selftest_bts_cpu(&conf);
-		if (conf.error >= 0)
-			conf.error = ds_selftest_bts_bad_request_task(buffer);
-		ds_release_bts(conf.tracer);
-		if (conf.error < 0)
-			goto out;
-
-		conf.suspend = ds_suspend_bts_noirq;
-		conf.resume = ds_resume_bts_noirq;
-		conf.tracer =
-			ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE,
-					   NULL, (size_t)-1, BTS_KERNEL);
-		smp_call_function_single(cpu, ds_selftest_bts_cpu, &conf, 1);
-		if (conf.error >= 0) {
-			conf.error =
-				ds_selftest_bts_bad_release_noirq(cpu,
-								  conf.tracer);
-			/* We must not release the tracer twice. */
-			if (conf.error < 0)
-				conf.tracer = NULL;
-		}
-		if (conf.error >= 0)
-			conf.error = ds_selftest_bts_bad_request_task(buffer);
-		smp_call_function_single(cpu, ds_release_bts_noirq_wrap,
-					 conf.tracer, 1);
-		if (conf.error < 0)
-			goto out;
-	}
-
-	conf.suspend = ds_suspend_bts_wrap;
-	conf.resume = ds_resume_bts_wrap;
-	conf.tracer =
-		ds_request_bts_task(current, buffer, BUFFER_SIZE,
-				    NULL, (size_t)-1, BTS_KERNEL);
-	ds_selftest_bts_cpu(&conf);
-	if (conf.error >= 0)
-		conf.error = ds_selftest_bts_bad_request_cpu(0, buffer);
-	ds_release_bts(conf.tracer);
-	if (conf.error < 0)
-		goto out;
-
-	conf.suspend = ds_suspend_bts_noirq;
-	conf.resume = ds_resume_bts_noirq;
-	conf.tracer =
-		ds_request_bts_task(current, small_buffer, SMALL_BUFFER_SIZE,
-				   NULL, (size_t)-1, BTS_KERNEL);
-	local_irq_save(irq);
-	ds_selftest_bts_cpu(&conf);
-	if (conf.error >= 0)
-		conf.error = ds_selftest_bts_bad_request_cpu(0, buffer);
-	ds_release_bts_noirq(conf.tracer);
-	local_irq_restore(irq);
-	if (conf.error < 0)
-		goto out;
-
-	conf.error = 0;
- out:
-	put_online_cpus();
-	printk(KERN_CONT "%s.\n", (conf.error ? "failed" : "passed"));
-
-	return conf.error;
-}
-
-int ds_selftest_pebs(void)
-{
-	return 0;
-}
diff --git a/arch/x86/kernel/ds_selftest.h b/arch/x86/kernel/ds_selftest.h
deleted file mode 100644
index 2ba8745c6663..000000000000
--- a/arch/x86/kernel/ds_selftest.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Debug Store support - selftest
- *
- *
- * Copyright (C) 2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2009
- */
-
-#ifdef CONFIG_X86_DS_SELFTEST
-extern int ds_selftest_bts(void);
-extern int ds_selftest_pebs(void);
-#else
-static inline int ds_selftest_bts(void) { return 0; }
-static inline int ds_selftest_pebs(void) { return 0; }
-#endif
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 6d817554780a..c89a386930b7 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -224,11 +224,6 @@ unsigned __kprobes long oops_begin(void)
 	int cpu;
 	unsigned long flags;
 
-	/* notify the hw-branch tracer so it may disable tracing and
-	   add the last trace to the trace buffer -
-	   the earlier this happens, the more useful the trace. */
-	trace_hw_branch_oops();
-
 	oops_enter();
 
 	/* racy, but better than risking deadlock. */
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 23c167925a5c..2dfd31597443 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -16,7 +16,7 @@
 #include <asm/hpet.h>
 #include <asm/smp.h>
 
-DEFINE_SPINLOCK(i8253_lock);
+DEFINE_RAW_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
 
 /*
@@ -33,7 +33,7 @@ struct clock_event_device *global_clock_event;
 static void init_pit_timer(enum clock_event_mode mode,
 			   struct clock_event_device *evt)
 {
-	spin_lock(&i8253_lock);
+	raw_spin_lock(&i8253_lock);
 
 	switch (mode) {
 	case CLOCK_EVT_MODE_PERIODIC:
@@ -62,7 +62,7 @@ static void init_pit_timer(enum clock_event_mode mode,
 		/* Nothing to do here */
 		break;
 	}
-	spin_unlock(&i8253_lock);
+	raw_spin_unlock(&i8253_lock);
 }
 
 /*
@@ -72,10 +72,10 @@ static void init_pit_timer(enum clock_event_mode mode,
  */
 static int pit_next_event(unsigned long delta, struct clock_event_device *evt)
 {
-	spin_lock(&i8253_lock);
+	raw_spin_lock(&i8253_lock);
 	outb_pit(delta & 0xff , PIT_CH0);	/* LSB */
 	outb_pit(delta >> 8 , PIT_CH0);		/* MSB */
-	spin_unlock(&i8253_lock);
+	raw_spin_unlock(&i8253_lock);
 
 	return 0;
 }
@@ -130,7 +130,7 @@ static cycle_t pit_read(struct clocksource *cs)
 	int count;
 	u32 jifs;
 
-	spin_lock_irqsave(&i8253_lock, flags);
+	raw_spin_lock_irqsave(&i8253_lock, flags);
 	/*
 	 * Although our caller may have the read side of xtime_lock,
 	 * this is now a seqlock, and we are cheating in this routine
@@ -176,7 +176,7 @@ static cycle_t pit_read(struct clocksource *cs)
 	old_count = count;
 	old_jifs = jifs;
 
-	spin_unlock_irqrestore(&i8253_lock, flags);
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
 
 	count = (LATCH - 1) - count;
 
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index b43bbaebe2c0..f2f56c0967b6 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -422,14 +422,22 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 
 static void __kprobes clear_btf(void)
 {
-	if (test_thread_flag(TIF_DEBUGCTLMSR))
-		update_debugctlmsr(0);
+	if (test_thread_flag(TIF_BLOCKSTEP)) {
+		unsigned long debugctl = get_debugctlmsr();
+
+		debugctl &= ~DEBUGCTLMSR_BTF;
+		update_debugctlmsr(debugctl);
+	}
 }
 
 static void __kprobes restore_btf(void)
 {
-	if (test_thread_flag(TIF_DEBUGCTLMSR))
-		update_debugctlmsr(current->thread.debugctlmsr);
+	if (test_thread_flag(TIF_BLOCKSTEP)) {
+		unsigned long debugctl = get_debugctlmsr();
+
+		debugctl |= DEBUGCTLMSR_BTF;
+		update_debugctlmsr(debugctl);
+	}
 }
 
 void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 85a343e28937..356170262a93 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -343,10 +343,11 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 				int (*get_ucode_data)(void *, const void *, size_t))
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	u8 *ucode_ptr = data, *new_mc = NULL, *mc;
+	u8 *ucode_ptr = data, *new_mc = NULL, *mc = NULL;
 	int new_rev = uci->cpu_sig.rev;
 	unsigned int leftover = size;
 	enum ucode_state state = UCODE_OK;
+	unsigned int curr_mc_size = 0;
 
 	while (leftover) {
 		struct microcode_header_intel mc_header;
@@ -361,9 +362,15 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 			break;
 		}
 
-		mc = vmalloc(mc_size);
-		if (!mc)
-			break;
+		/* For performance reasons, reuse mc area when possible */
+		if (!mc || mc_size > curr_mc_size) {
+			if (mc)
+				vfree(mc);
+			mc = vmalloc(mc_size);
+			if (!mc)
+				break;
+			curr_mc_size = mc_size;
+		}
 
 		if (get_ucode_data(mc, ucode_ptr, mc_size) ||
 		    microcode_sanity_check(mc) < 0) {
@@ -376,13 +383,16 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 				vfree(new_mc);
 			new_rev = mc_header.rev;
 			new_mc  = mc;
-		} else
-			vfree(mc);
+			mc = NULL;	/* trigger new vmalloc */
+		}
 
 		ucode_ptr += mc_size;
 		leftover  -= mc_size;
 	}
 
+	if (mc)
+		vfree(mc);
+
 	if (leftover) {
 		if (new_mc)
 			vfree(new_mc);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 28ad9f4d8b94..eccdb57094e3 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -20,7 +20,6 @@
 #include <asm/idle.h>
 #include <asm/uaccess.h>
 #include <asm/i387.h>
-#include <asm/ds.h>
 #include <asm/debugreg.h>
 
 unsigned long idle_halt;
@@ -50,8 +49,6 @@ void free_thread_xstate(struct task_struct *tsk)
 		kmem_cache_free(task_xstate_cachep, tsk->thread.xstate);
 		tsk->thread.xstate = NULL;
 	}
-
-	WARN(tsk->thread.ds_ctx, "leaking DS context\n");
 }
 
 void free_thread_info(struct thread_info *ti)
@@ -198,11 +195,16 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 	prev = &prev_p->thread;
 	next = &next_p->thread;
 
-	if (test_tsk_thread_flag(next_p, TIF_DS_AREA_MSR) ||
-	    test_tsk_thread_flag(prev_p, TIF_DS_AREA_MSR))
-		ds_switch_to(prev_p, next_p);
-	else if (next->debugctlmsr != prev->debugctlmsr)
-		update_debugctlmsr(next->debugctlmsr);
+	if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^
+	    test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) {
+		unsigned long debugctl = get_debugctlmsr();
+
+		debugctl &= ~DEBUGCTLMSR_BTF;
+		if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP))
+			debugctl |= DEBUGCTLMSR_BTF;
+
+		update_debugctlmsr(debugctl);
+	}
 
 	if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^
 	    test_tsk_thread_flag(next_p, TIF_NOTSC)) {
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index f6c62667e30c..75090c589b7a 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -55,7 +55,6 @@
 #include <asm/cpu.h>
 #include <asm/idle.h>
 #include <asm/syscalls.h>
-#include <asm/ds.h>
 #include <asm/debugreg.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
@@ -238,13 +237,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 		kfree(p->thread.io_bitmap_ptr);
 		p->thread.io_bitmap_max = 0;
 	}
-
-	clear_tsk_thread_flag(p, TIF_DS_AREA_MSR);
-	p->thread.ds_ctx = NULL;
-
-	clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR);
-	p->thread.debugctlmsr = 0;
-
 	return err;
 }
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index dc9690b4c4cc..cc4258f2beb5 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -49,7 +49,6 @@
 #include <asm/ia32.h>
 #include <asm/idle.h>
 #include <asm/syscalls.h>
-#include <asm/ds.h>
 #include <asm/debugreg.h>
 
 asmlinkage extern void ret_from_fork(void);
@@ -313,13 +312,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 		if (err)
 			goto out;
 	}
-
-	clear_tsk_thread_flag(p, TIF_DS_AREA_MSR);
-	p->thread.ds_ctx = NULL;
-
-	clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR);
-	p->thread.debugctlmsr = 0;
-
 	err = 0;
 out:
 	if (err && p->thread.io_bitmap_ptr) {
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 2e9b55027b7e..055be0afd330 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -2,9 +2,6 @@
 /*
  * Pentium III FXSR, SSE support
  *	Gareth Hughes <gareth@valinux.com>, May 2000
- *
- * BTS tracing
- *	Markus Metzger <markus.t.metzger@intel.com>, Dec 2007
  */
 
 #include <linux/kernel.h>
@@ -22,7 +19,6 @@
 #include <linux/audit.h>
 #include <linux/seccomp.h>
 #include <linux/signal.h>
-#include <linux/workqueue.h>
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
 
@@ -36,7 +32,6 @@
 #include <asm/desc.h>
 #include <asm/prctl.h>
 #include <asm/proto.h>
-#include <asm/ds.h>
 #include <asm/hw_breakpoint.h>
 
 #include "tls.h"
@@ -789,342 +784,6 @@ static int ioperm_get(struct task_struct *target,
 				   0, IO_BITMAP_BYTES);
 }
 
-#ifdef CONFIG_X86_PTRACE_BTS
-/*
- * A branch trace store context.
- *
- * Contexts may only be installed by ptrace_bts_config() and only for
- * ptraced tasks.
- *
- * Contexts are destroyed when the tracee is detached from the tracer.
- * The actual destruction work requires interrupts enabled, so the
- * work is deferred and will be scheduled during __ptrace_unlink().
- *
- * Contexts hold an additional task_struct reference on the traced
- * task, as well as a reference on the tracer's mm.
- *
- * Ptrace already holds a task_struct for the duration of ptrace operations,
- * but since destruction is deferred, it may be executed after both
- * tracer and tracee exited.
- */
-struct bts_context {
-	/* The branch trace handle. */
-	struct bts_tracer	*tracer;
-
-	/* The buffer used to store the branch trace and its size. */
-	void			*buffer;
-	unsigned int		size;
-
-	/* The mm that paid for the above buffer. */
-	struct mm_struct	*mm;
-
-	/* The task this context belongs to. */
-	struct task_struct	*task;
-
-	/* The signal to send on a bts buffer overflow. */
-	unsigned int		bts_ovfl_signal;
-
-	/* The work struct to destroy a context. */
-	struct work_struct	work;
-};
-
-static int alloc_bts_buffer(struct bts_context *context, unsigned int size)
-{
-	void *buffer = NULL;
-	int err = -ENOMEM;
-
-	err = account_locked_memory(current->mm, current->signal->rlim, size);
-	if (err < 0)
-		return err;
-
-	buffer = kzalloc(size, GFP_KERNEL);
-	if (!buffer)
-		goto out_refund;
-
-	context->buffer = buffer;
-	context->size = size;
-	context->mm = get_task_mm(current);
-
-	return 0;
-
- out_refund:
-	refund_locked_memory(current->mm, size);
-	return err;
-}
-
-static inline void free_bts_buffer(struct bts_context *context)
-{
-	if (!context->buffer)
-		return;
-
-	kfree(context->buffer);
-	context->buffer = NULL;
-
-	refund_locked_memory(context->mm, context->size);
-	context->size = 0;
-
-	mmput(context->mm);
-	context->mm = NULL;
-}
-
-static void free_bts_context_work(struct work_struct *w)
-{
-	struct bts_context *context;
-
-	context = container_of(w, struct bts_context, work);
-
-	ds_release_bts(context->tracer);
-	put_task_struct(context->task);
-	free_bts_buffer(context);
-	kfree(context);
-}
-
-static inline void free_bts_context(struct bts_context *context)
-{
-	INIT_WORK(&context->work, free_bts_context_work);
-	schedule_work(&context->work);
-}
-
-static inline struct bts_context *alloc_bts_context(struct task_struct *task)
-{
-	struct bts_context *context = kzalloc(sizeof(*context), GFP_KERNEL);
-	if (context) {
-		context->task = task;
-		task->bts = context;
-
-		get_task_struct(task);
-	}
-
-	return context;
-}
-
-static int ptrace_bts_read_record(struct task_struct *child, size_t index,
-				  struct bts_struct __user *out)
-{
-	struct bts_context *context;
-	const struct bts_trace *trace;
-	struct bts_struct bts;
-	const unsigned char *at;
-	int error;
-
-	context = child->bts;
-	if (!context)
-		return -ESRCH;
-
-	trace = ds_read_bts(context->tracer);
-	if (!trace)
-		return -ESRCH;
-
-	at = trace->ds.top - ((index + 1) * trace->ds.size);
-	if ((void *)at < trace->ds.begin)
-		at += (trace->ds.n * trace->ds.size);
-
-	if (!trace->read)
-		return -EOPNOTSUPP;
-
-	error = trace->read(context->tracer, at, &bts);
-	if (error < 0)
-		return error;
-
-	if (copy_to_user(out, &bts, sizeof(bts)))
-		return -EFAULT;
-
-	return sizeof(bts);
-}
-
-static int ptrace_bts_drain(struct task_struct *child,
-			    long size,
-			    struct bts_struct __user *out)
-{
-	struct bts_context *context;
-	const struct bts_trace *trace;
-	const unsigned char *at;
-	int error, drained = 0;
-
-	context = child->bts;
-	if (!context)
-		return -ESRCH;
-
-	trace = ds_read_bts(context->tracer);
-	if (!trace)
-		return -ESRCH;
-
-	if (!trace->read)
-		return -EOPNOTSUPP;
-
-	if (size < (trace->ds.top - trace->ds.begin))
-		return -EIO;
-
-	for (at = trace->ds.begin; (void *)at < trace->ds.top;
-	     out++, drained++, at += trace->ds.size) {
-		struct bts_struct bts;
-
-		error = trace->read(context->tracer, at, &bts);
-		if (error < 0)
-			return error;
-
-		if (copy_to_user(out, &bts, sizeof(bts)))
-			return -EFAULT;
-	}
-
-	memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
-
-	error = ds_reset_bts(context->tracer);
-	if (error < 0)
-		return error;
-
-	return drained;
-}
-
-static int ptrace_bts_config(struct task_struct *child,
-			     long cfg_size,
-			     const struct ptrace_bts_config __user *ucfg)
-{
-	struct bts_context *context;
-	struct ptrace_bts_config cfg;
-	unsigned int flags = 0;
-
-	if (cfg_size < sizeof(cfg))
-		return -EIO;
-
-	if (copy_from_user(&cfg, ucfg, sizeof(cfg)))
-		return -EFAULT;
-
-	context = child->bts;
-	if (!context)
-		context = alloc_bts_context(child);
-	if (!context)
-		return -ENOMEM;
-
-	if (cfg.flags & PTRACE_BTS_O_SIGNAL) {
-		if (!cfg.signal)
-			return -EINVAL;
-
-		return -EOPNOTSUPP;
-		context->bts_ovfl_signal = cfg.signal;
-	}
-
-	ds_release_bts(context->tracer);
-	context->tracer = NULL;
-
-	if ((cfg.flags & PTRACE_BTS_O_ALLOC) && (cfg.size != context->size)) {
-		int err;
-
-		free_bts_buffer(context);
-		if (!cfg.size)
-			return 0;
-
-		err = alloc_bts_buffer(context, cfg.size);
-		if (err < 0)
-			return err;
-	}
-
-	if (cfg.flags & PTRACE_BTS_O_TRACE)
-		flags |= BTS_USER;
-
-	if (cfg.flags & PTRACE_BTS_O_SCHED)
-		flags |= BTS_TIMESTAMPS;
-
-	context->tracer =
-		ds_request_bts_task(child, context->buffer, context->size,
-				    NULL, (size_t)-1, flags);
-	if (unlikely(IS_ERR(context->tracer))) {
-		int error = PTR_ERR(context->tracer);
-
-		free_bts_buffer(context);
-		context->tracer = NULL;
-		return error;
-	}
-
-	return sizeof(cfg);
-}
-
-static int ptrace_bts_status(struct task_struct *child,
-			     long cfg_size,
-			     struct ptrace_bts_config __user *ucfg)
-{
-	struct bts_context *context;
-	const struct bts_trace *trace;
-	struct ptrace_bts_config cfg;
-
-	context = child->bts;
-	if (!context)
-		return -ESRCH;
-
-	if (cfg_size < sizeof(cfg))
-		return -EIO;
-
-	trace = ds_read_bts(context->tracer);
-	if (!trace)
-		return -ESRCH;
-
-	memset(&cfg, 0, sizeof(cfg));
-	cfg.size	= trace->ds.end - trace->ds.begin;
-	cfg.signal	= context->bts_ovfl_signal;
-	cfg.bts_size	= sizeof(struct bts_struct);
-
-	if (cfg.signal)
-		cfg.flags |= PTRACE_BTS_O_SIGNAL;
-
-	if (trace->ds.flags & BTS_USER)
-		cfg.flags |= PTRACE_BTS_O_TRACE;
-
-	if (trace->ds.flags & BTS_TIMESTAMPS)
-		cfg.flags |= PTRACE_BTS_O_SCHED;
-
-	if (copy_to_user(ucfg, &cfg, sizeof(cfg)))
-		return -EFAULT;
-
-	return sizeof(cfg);
-}
-
-static int ptrace_bts_clear(struct task_struct *child)
-{
-	struct bts_context *context;
-	const struct bts_trace *trace;
-
-	context = child->bts;
-	if (!context)
-		return -ESRCH;
-
-	trace = ds_read_bts(context->tracer);
-	if (!trace)
-		return -ESRCH;
-
-	memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
-
-	return ds_reset_bts(context->tracer);
-}
-
-static int ptrace_bts_size(struct task_struct *child)
-{
-	struct bts_context *context;
-	const struct bts_trace *trace;
-
-	context = child->bts;
-	if (!context)
-		return -ESRCH;
-
-	trace = ds_read_bts(context->tracer);
-	if (!trace)
-		return -ESRCH;
-
-	return (trace->ds.top - trace->ds.begin) / trace->ds.size;
-}
-
-/*
- * Called from __ptrace_unlink() after the child has been moved back
- * to its original parent.
- */
-void ptrace_bts_untrace(struct task_struct *child)
-{
-	if (unlikely(child->bts)) {
-		free_bts_context(child->bts);
-		child->bts = NULL;
-	}
-}
-#endif /* CONFIG_X86_PTRACE_BTS */
-
 /*
  * Called by kernel/ptrace.c when detaching..
  *
@@ -1252,39 +911,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 		break;
 #endif
 
-	/*
-	 * These bits need more cooking - not enabled yet:
-	 */
-#ifdef CONFIG_X86_PTRACE_BTS
-	case PTRACE_BTS_CONFIG:
-		ret = ptrace_bts_config
-			(child, data, (struct ptrace_bts_config __user *)addr);
-		break;
-
-	case PTRACE_BTS_STATUS:
-		ret = ptrace_bts_status
-			(child, data, (struct ptrace_bts_config __user *)addr);
-		break;
-
-	case PTRACE_BTS_SIZE:
-		ret = ptrace_bts_size(child);
-		break;
-
-	case PTRACE_BTS_GET:
-		ret = ptrace_bts_read_record
-			(child, data, (struct bts_struct __user *) addr);
-		break;
-
-	case PTRACE_BTS_CLEAR:
-		ret = ptrace_bts_clear(child);
-		break;
-
-	case PTRACE_BTS_DRAIN:
-		ret = ptrace_bts_drain
-			(child, data, (struct bts_struct __user *) addr);
-		break;
-#endif /* CONFIG_X86_PTRACE_BTS */
-
 	default:
 		ret = ptrace_request(child, request, addr, data);
 		break;
@@ -1544,14 +1170,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 
 	case PTRACE_GET_THREAD_AREA:
 	case PTRACE_SET_THREAD_AREA:
-#ifdef CONFIG_X86_PTRACE_BTS
-	case PTRACE_BTS_CONFIG:
-	case PTRACE_BTS_STATUS:
-	case PTRACE_BTS_SIZE:
-	case PTRACE_BTS_GET:
-	case PTRACE_BTS_CLEAR:
-	case PTRACE_BTS_DRAIN:
-#endif /* CONFIG_X86_PTRACE_BTS */
 		return arch_ptrace(child, request, addr, data);
 
 	default:
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 3149032ff107..58de45ee08b6 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -158,22 +158,6 @@ static int enable_single_step(struct task_struct *child)
 }
 
 /*
- * Install this value in MSR_IA32_DEBUGCTLMSR whenever child is running.
- */
-static void write_debugctlmsr(struct task_struct *child, unsigned long val)
-{
-	if (child->thread.debugctlmsr == val)
-		return;
-
-	child->thread.debugctlmsr = val;
-
-	if (child != current)
-		return;
-
-	update_debugctlmsr(val);
-}
-
-/*
  * Enable single or block step.
  */
 static void enable_step(struct task_struct *child, bool block)
@@ -186,15 +170,17 @@ static void enable_step(struct task_struct *child, bool block)
 	 * that uses user-mode single stepping itself.
 	 */
 	if (enable_single_step(child) && block) {
-		set_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
-		write_debugctlmsr(child,
-				  child->thread.debugctlmsr | DEBUGCTLMSR_BTF);
-	} else {
-		write_debugctlmsr(child,
-				  child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF);
-
-		if (!child->thread.debugctlmsr)
-			clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
+		unsigned long debugctl = get_debugctlmsr();
+
+		debugctl |= DEBUGCTLMSR_BTF;
+		update_debugctlmsr(debugctl);
+		set_tsk_thread_flag(child, TIF_BLOCKSTEP);
+	} else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) {
+		unsigned long debugctl = get_debugctlmsr();
+
+		debugctl &= ~DEBUGCTLMSR_BTF;
+		update_debugctlmsr(debugctl);
+		clear_tsk_thread_flag(child, TIF_BLOCKSTEP);
 	}
 }
 
@@ -213,11 +199,13 @@ void user_disable_single_step(struct task_struct *child)
 	/*
 	 * Make sure block stepping (BTF) is disabled.
 	 */
-	write_debugctlmsr(child,
-			  child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF);
+	if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) {
+		unsigned long debugctl = get_debugctlmsr();
 
-	if (!child->thread.debugctlmsr)
-		clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
+		debugctl &= ~DEBUGCTLMSR_BTF;
+		update_debugctlmsr(debugctl);
+		clear_tsk_thread_flag(child, TIF_BLOCKSTEP);
+	}
 
 	/* Always clear TIF_SINGLESTEP... */
 	clear_tsk_thread_flag(child, TIF_SINGLESTEP);
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 86c9f91b48ae..cc2c60474fd0 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -175,6 +175,9 @@ static void add_mac_region(phys_addr_t start, unsigned long size)
 	struct tboot_mac_region *mr;
 	phys_addr_t end = start + size;
 
+	if (tboot->num_mac_regions >= MAX_TB_MAC_REGIONS)
+		panic("tboot: Too many MAC regions\n");
+
 	if (start && size) {
 		mr = &tboot->mac_regions[tboot->num_mac_regions++];
 		mr->start = round_down(start, PAGE_SIZE);
@@ -184,18 +187,17 @@ static void add_mac_region(phys_addr_t start, unsigned long size)
 
 static int tboot_setup_sleep(void)
 {
+	int i;
+
 	tboot->num_mac_regions = 0;
 
-	/* S3 resume code */
-	add_mac_region(acpi_wakeup_address, WAKEUP_SIZE);
+	for (i = 0; i < e820.nr_map; i++) {
+		if ((e820.map[i].type != E820_RAM)
+		 && (e820.map[i].type != E820_RESERVED_KERN))
+			continue;
 
-#ifdef CONFIG_X86_TRAMPOLINE
-	/* AP trampoline code */
-	add_mac_region(virt_to_phys(trampoline_base), TRAMPOLINE_SIZE);
-#endif
-
-	/* kernel code + data + bss */
-	add_mac_region(virt_to_phys(_text), _end - _text);
+		add_mac_region(e820.map[i].addr, e820.map[i].size);
+	}
 
 	tboot->acpi_sinfo.kernel_s3_resume_vector = acpi_wakeup_address;
 
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 17b03dd3a6b5..a108164d7bf1 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -21,6 +21,8 @@
 #include <asm/tsc.h>
 #include <asm/irq_vectors.h>
 
+#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD	0x000000000bUL
+
 static struct bau_control	**uv_bau_table_bases __read_mostly;
 static int			uv_bau_retry_limit __read_mostly;
 
@@ -479,16 +481,16 @@ static void uv_enable_timeouts(void)
 		 * To program the period, the SOFT_ACK_MODE must be off.
 		 */
 		mmr_image &= ~((unsigned long)1 <<
-			       UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT);
+		    UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT);
 		uv_write_global_mmr64
 		    (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
 		/*
 		 * Set the 4-bit period.
 		 */
 		mmr_image &= ~((unsigned long)0xf <<
-			UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT);
+		     UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT);
 		mmr_image |= (UV_INTD_SOFT_ACK_TIMEOUT_PERIOD <<
-			     UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT);
+		     UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT);
 		uv_write_global_mmr64
 		    (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
 		/*
@@ -497,7 +499,7 @@ static void uv_enable_timeouts(void)
 		 * indicated in bits 2:0 (7 causes all of them to timeout).
 		 */
 		mmr_image |= ((unsigned long)1 <<
-			      UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT);
+		    UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT);
 		uv_write_global_mmr64
 		    (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
 	}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 94b604b76e5c..c87de84d1eef 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -549,11 +549,11 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 
 	/* DR6 may or may not be cleared by the CPU */
 	set_debugreg(0, 6);
+
 	/*
 	 * The processor cleared BTF, so don't mark that we need it set.
 	 */
-	clear_tsk_thread_flag(tsk, TIF_DEBUGCTLMSR);
-	tsk->thread.debugctlmsr = 0;
+	clear_tsk_thread_flag(tsk, TIF_BLOCKSTEP);
 
 	/* Store the virtualized DR6 value */
 	tsk->thread.debugreg6 = dr6;
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 419386c24b82..cbaf8f2b83df 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -20,7 +20,7 @@ lib-y := delay.o
 lib-y += thunk_$(BITS).o
 lib-y += usercopy_$(BITS).o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
-lib-$(CONFIG_KPROBES) += insn.o inat.o
+lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o
 
 obj-y += msr.o msr-reg.o msr-reg-export.o
 
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 06630d26e56d..a4c768397baa 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -6,6 +6,7 @@ nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_physaddr.o		:= $(nostackp)
 CFLAGS_setup_nx.o		:= $(nostackp)
 
+obj-$(CONFIG_X86_PAT)		+= pat_rbtree.o
 obj-$(CONFIG_SMP)		+= tlb.o
 
 obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index edc8b95afc1a..931e5b753e77 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -30,6 +30,8 @@
 #include <asm/pat.h>
 #include <asm/io.h>
 
+#include "pat_internal.h"
+
 #ifdef CONFIG_X86_PAT
 int __read_mostly pat_enabled = 1;
 
@@ -53,19 +55,15 @@ static inline void pat_disable(const char *reason)
 #endif
 
 
-static int debug_enable;
+int pat_debug_enable;
 
 static int __init pat_debug_setup(char *str)
 {
-	debug_enable = 1;
+	pat_debug_enable = 1;
 	return 0;
 }
 __setup("debugpat", pat_debug_setup);
 
-#define dprintk(fmt, arg...) \
-	do { if (debug_enable) printk(KERN_INFO fmt, ##arg); } while (0)
-
-
 static u64 __read_mostly boot_pat_state;
 
 enum {
@@ -132,84 +130,7 @@ void pat_init(void)
 
 #undef PAT
 
-static char *cattr_name(unsigned long flags)
-{
-	switch (flags & _PAGE_CACHE_MASK) {
-	case _PAGE_CACHE_UC:		return "uncached";
-	case _PAGE_CACHE_UC_MINUS:	return "uncached-minus";
-	case _PAGE_CACHE_WB:		return "write-back";
-	case _PAGE_CACHE_WC:		return "write-combining";
-	default:			return "broken";
-	}
-}
-
-/*
- * The global memtype list keeps track of memory type for specific
- * physical memory areas. Conflicting memory types in different
- * mappings can cause CPU cache corruption. To avoid this we keep track.
- *
- * The list is sorted based on starting address and can contain multiple
- * entries for each address (this allows reference counting for overlapping
- * areas). All the aliases have the same cache attributes of course.
- * Zero attributes are represented as holes.
- *
- * The data structure is a list that is also organized as an rbtree
- * sorted on the start address of memtype range.
- *
- * memtype_lock protects both the linear list and rbtree.
- */
-
-struct memtype {
-	u64			start;
-	u64			end;
-	unsigned long		type;
-	struct list_head	nd;
-	struct rb_node		rb;
-};
-
-static struct rb_root memtype_rbroot = RB_ROOT;
-static LIST_HEAD(memtype_list);
-static DEFINE_SPINLOCK(memtype_lock);	/* protects memtype list */
-
-static struct memtype *memtype_rb_search(struct rb_root *root, u64 start)
-{
-	struct rb_node *node = root->rb_node;
-	struct memtype *last_lower = NULL;
-
-	while (node) {
-		struct memtype *data = container_of(node, struct memtype, rb);
-
-		if (data->start < start) {
-			last_lower = data;
-			node = node->rb_right;
-		} else if (data->start > start) {
-			node = node->rb_left;
-		} else
-			return data;
-	}
-
-	/* Will return NULL if there is no entry with its start <= start */
-	return last_lower;
-}
-
-static void memtype_rb_insert(struct rb_root *root, struct memtype *data)
-{
-	struct rb_node **new = &(root->rb_node);
-	struct rb_node *parent = NULL;
-
-	while (*new) {
-		struct memtype *this = container_of(*new, struct memtype, rb);
-
-		parent = *new;
-		if (data->start <= this->start)
-			new = &((*new)->rb_left);
-		else if (data->start > this->start)
-			new = &((*new)->rb_right);
-	}
-
-	rb_link_node(&data->rb, parent, new);
-	rb_insert_color(&data->rb, root);
-}
+static DEFINE_SPINLOCK(memtype_lock);	/* protects memtype accesses */
 
 /*
  * Does intersection of PAT memory type and MTRR memory type and returns
@@ -237,33 +158,6 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type)
 	return req_type;
 }
 
-static int
-chk_conflict(struct memtype *new, struct memtype *entry, unsigned long *type)
-{
-	if (new->type != entry->type) {
-		if (type) {
-			new->type = entry->type;
-			*type = entry->type;
-		} else
-			goto conflict;
-	}
-
-	 /* check overlaps with more than one entry in the list */
-	list_for_each_entry_continue(entry, &memtype_list, nd) {
-		if (new->end <= entry->start)
-			break;
-		else if (new->type != entry->type)
-			goto conflict;
-	}
-	return 0;
-
- conflict:
-	printk(KERN_INFO "%s:%d conflicting memory types "
-	       "%Lx-%Lx %s<->%s\n", current->comm, current->pid, new->start,
-	       new->end, cattr_name(new->type), cattr_name(entry->type));
-	return -EBUSY;
-}
-
 static int pat_pagerange_is_ram(unsigned long start, unsigned long end)
 {
 	int ram_page = 0, not_rampage = 0;
@@ -364,9 +258,8 @@ static int free_ram_pages_type(u64 start, u64 end)
 int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 		    unsigned long *new_type)
 {
-	struct memtype *new, *entry;
+	struct memtype *new;
 	unsigned long actual_type;
-	struct list_head *where;
 	int is_range_ram;
 	int err = 0;
 
@@ -423,42 +316,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 
 	spin_lock(&memtype_lock);
 
-	/* Search for existing mapping that overlaps the current range */
-	where = NULL;
-	list_for_each_entry(entry, &memtype_list, nd) {
-		if (end <= entry->start) {
-			where = entry->nd.prev;
-			break;
-		} else if (start <= entry->start) { /* end > entry->start */
-			err = chk_conflict(new, entry, new_type);
-			if (!err) {
-				dprintk("Overlap at 0x%Lx-0x%Lx\n",
-					entry->start, entry->end);
-				where = entry->nd.prev;
-			}
-			break;
-		} else if (start < entry->end) { /* start > entry->start */
-			err = chk_conflict(new, entry, new_type);
-			if (!err) {
-				dprintk("Overlap at 0x%Lx-0x%Lx\n",
-					entry->start, entry->end);
-
-				/*
-				 * Move to right position in the linked
-				 * list to add this new entry
-				 */
-				list_for_each_entry_continue(entry,
-							&memtype_list, nd) {
-					if (start <= entry->start) {
-						where = entry->nd.prev;
-						break;
-					}
-				}
-			}
-			break;
-		}
-	}
-
+	err = rbt_memtype_check_insert(new, new_type);
 	if (err) {
 		printk(KERN_INFO "reserve_memtype failed 0x%Lx-0x%Lx, "
 		       "track %s, req %s\n",
@@ -469,13 +327,6 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 		return err;
 	}
 
-	if (where)
-		list_add(&new->nd, where);
-	else
-		list_add_tail(&new->nd, &memtype_list);
-
-	memtype_rb_insert(&memtype_rbroot, new);
-
 	spin_unlock(&memtype_lock);
 
 	dprintk("reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s, ret %s\n",
@@ -487,7 +338,6 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 
 int free_memtype(u64 start, u64 end)
 {
-	struct memtype *entry, *saved_entry;
 	int err = -EINVAL;
 	int is_range_ram;
 
@@ -511,46 +361,7 @@ int free_memtype(u64 start, u64 end)
 	}
 
 	spin_lock(&memtype_lock);
-
-	entry = memtype_rb_search(&memtype_rbroot, start);
-	if (unlikely(entry == NULL))
-		goto unlock_ret;
-
-	/*
-	 * Saved entry points to an entry with start same or less than what
-	 * we searched for. Now go through the list in both directions to look
-	 * for the entry that matches with both start and end, with list stored
-	 * in sorted start address
-	 */
-	saved_entry = entry;
-	list_for_each_entry_from(entry, &memtype_list, nd) {
-		if (entry->start == start && entry->end == end) {
-			rb_erase(&entry->rb, &memtype_rbroot);
-			list_del(&entry->nd);
-			kfree(entry);
-			err = 0;
-			break;
-		} else if (entry->start > start) {
-			break;
-		}
-	}
-
-	if (!err)
-		goto unlock_ret;
-
-	entry = saved_entry;
-	list_for_each_entry_reverse(entry, &memtype_list, nd) {
-		if (entry->start == start && entry->end == end) {
-			rb_erase(&entry->rb, &memtype_rbroot);
-			list_del(&entry->nd);
-			kfree(entry);
-			err = 0;
-			break;
-		} else if (entry->start < start) {
-			break;
-		}
-	}
-unlock_ret:
+	err = rbt_memtype_erase(start, end);
 	spin_unlock(&memtype_lock);
 
 	if (err) {
@@ -599,7 +410,7 @@ static unsigned long lookup_memtype(u64 paddr)
 
 	spin_lock(&memtype_lock);
 
-	entry = memtype_rb_search(&memtype_rbroot, paddr);
+	entry = rbt_memtype_lookup(paddr);
 	if (entry != NULL)
 		rettype = entry->type;
 	else
@@ -936,29 +747,25 @@ EXPORT_SYMBOL_GPL(pgprot_writecombine);
 
 #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)
 
-/* get Nth element of the linked list */
 static struct memtype *memtype_get_idx(loff_t pos)
 {
-	struct memtype *list_node, *print_entry;
-	int i = 1;
+	struct memtype *print_entry;
+	int ret;
 
-	print_entry  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
+	print_entry  = kzalloc(sizeof(struct memtype), GFP_KERNEL);
 	if (!print_entry)
 		return NULL;
 
 	spin_lock(&memtype_lock);
-	list_for_each_entry(list_node, &memtype_list, nd) {
-		if (pos == i) {
-			*print_entry = *list_node;
-			spin_unlock(&memtype_lock);
-			return print_entry;
-		}
-		++i;
-	}
+	ret = rbt_memtype_copy_nth_element(print_entry, pos);
 	spin_unlock(&memtype_lock);
-	kfree(print_entry);
 
-	return NULL;
+	if (!ret) {
+		return print_entry;
+	} else {
+		kfree(print_entry);
+		return NULL;
+	}
 }
 
 static void *memtype_seq_start(struct seq_file *seq, loff_t *pos)
diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h
new file mode 100644
index 000000000000..4f39eefa3e61
--- /dev/null
+++ b/arch/x86/mm/pat_internal.h
@@ -0,0 +1,46 @@
+#ifndef __PAT_INTERNAL_H_
+#define __PAT_INTERNAL_H_
+
+extern int pat_debug_enable;
+
+#define dprintk(fmt, arg...) \
+	do { if (pat_debug_enable) printk(KERN_INFO fmt, ##arg); } while (0)
+
+struct memtype {
+	u64			start;
+	u64			end;
+	u64			subtree_max_end;
+	unsigned long		type;
+	struct rb_node		rb;
+};
+
+static inline char *cattr_name(unsigned long flags)
+{
+	switch (flags & _PAGE_CACHE_MASK) {
+	case _PAGE_CACHE_UC:		return "uncached";
+	case _PAGE_CACHE_UC_MINUS:	return "uncached-minus";
+	case _PAGE_CACHE_WB:		return "write-back";
+	case _PAGE_CACHE_WC:		return "write-combining";
+	default:			return "broken";
+	}
+}
+
+#ifdef CONFIG_X86_PAT
+extern int rbt_memtype_check_insert(struct memtype *new,
+					unsigned long *new_type);
+extern int rbt_memtype_erase(u64 start, u64 end);
+extern struct memtype *rbt_memtype_lookup(u64 addr);
+extern int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos);
+#else
+static inline int rbt_memtype_check_insert(struct memtype *new,
+					unsigned long *new_type)
+{ return 0; }
+static inline int rbt_memtype_erase(u64 start, u64 end)
+{ return 0; }
+static inline struct memtype *rbt_memtype_lookup(u64 addr)
+{ return NULL; }
+static inline int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos)
+{ return 0; }
+#endif
+
+#endif /* __PAT_INTERNAL_H_ */
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
new file mode 100644
index 000000000000..07de4cb8cc30
--- /dev/null
+++ b/arch/x86/mm/pat_rbtree.c
@@ -0,0 +1,273 @@
+/*
+ * Handle caching attributes in page tables (PAT)
+ *
+ * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
+ *          Suresh B Siddha <suresh.b.siddha@intel.com>
+ *
+ * Interval tree (augmented rbtree) used to store the PAT memory type
+ * reservations.
+ */
+
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/rbtree.h>
+#include <linux/sched.h>
+#include <linux/gfp.h>
+
+#include <asm/pgtable.h>
+#include <asm/pat.h>
+
+#include "pat_internal.h"
+
+/*
+ * The memtype tree keeps track of memory type for specific
+ * physical memory areas. Without proper tracking, conflicting memory
+ * types in different mappings can cause CPU cache corruption.
+ *
+ * The tree is an interval tree (augmented rbtree) with tree ordered
+ * on starting address. Tree can contain multiple entries for
+ * different regions which overlap. All the aliases have the same
+ * cache attributes of course.
+ *
+ * memtype_lock protects the rbtree.
+ */
+
+static void memtype_rb_augment_cb(struct rb_node *node);
+static struct rb_root memtype_rbroot = RB_AUGMENT_ROOT(&memtype_rb_augment_cb);
+
+static int is_node_overlap(struct memtype *node, u64 start, u64 end)
+{
+	if (node->start >= end || node->end <= start)
+		return 0;
+
+	return 1;
+}
+
+static u64 get_subtree_max_end(struct rb_node *node)
+{
+	u64 ret = 0;
+	if (node) {
+		struct memtype *data = container_of(node, struct memtype, rb);
+		ret = data->subtree_max_end;
+	}
+	return ret;
+}
+
+/* Update 'subtree_max_end' for a node, based on node and its children */
+static void update_node_max_end(struct rb_node *node)
+{
+	struct memtype *data;
+	u64 max_end, child_max_end;
+
+	if (!node)
+		return;
+
+	data = container_of(node, struct memtype, rb);
+	max_end = data->end;
+
+	child_max_end = get_subtree_max_end(node->rb_right);
+	if (child_max_end > max_end)
+		max_end = child_max_end;
+
+	child_max_end = get_subtree_max_end(node->rb_left);
+	if (child_max_end > max_end)
+		max_end = child_max_end;
+
+	data->subtree_max_end = max_end;
+}
+
+/* Update 'subtree_max_end' for a node and all its ancestors */
+static void update_path_max_end(struct rb_node *node)
+{
+	u64 old_max_end, new_max_end;
+
+	while (node) {
+		struct memtype *data = container_of(node, struct memtype, rb);
+
+		old_max_end = data->subtree_max_end;
+		update_node_max_end(node);
+		new_max_end = data->subtree_max_end;
+
+		if (new_max_end == old_max_end)
+			break;
+
+		node = rb_parent(node);
+	}
+}
+
+/* Find the first (lowest start addr) overlapping range from rb tree */
+static struct memtype *memtype_rb_lowest_match(struct rb_root *root,
+				u64 start, u64 end)
+{
+	struct rb_node *node = root->rb_node;
+	struct memtype *last_lower = NULL;
+
+	while (node) {
+		struct memtype *data = container_of(node, struct memtype, rb);
+
+		if (get_subtree_max_end(node->rb_left) > start) {
+			/* Lowest overlap if any must be on left side */
+			node = node->rb_left;
+		} else if (is_node_overlap(data, start, end)) {
+			last_lower = data;
+			break;
+		} else if (start >= data->start) {
+			/* Lowest overlap if any must be on right side */
+			node = node->rb_right;
+		} else {
+			break;
+		}
+	}
+	return last_lower; /* Returns NULL if there is no overlap */
+}
+
+static struct memtype *memtype_rb_exact_match(struct rb_root *root,
+				u64 start, u64 end)
+{
+	struct memtype *match;
+
+	match = memtype_rb_lowest_match(root, start, end);
+	while (match != NULL && match->start < end) {
+		struct rb_node *node;
+
+		if (match->start == start && match->end == end)
+			return match;
+
+		node = rb_next(&match->rb);
+		if (node)
+			match = container_of(node, struct memtype, rb);
+		else
+			match = NULL;
+	}
+
+	return NULL; /* Returns NULL if there is no exact match */
+}
+
+static int memtype_rb_check_conflict(struct rb_root *root,
+				u64 start, u64 end,
+				unsigned long reqtype, unsigned long *newtype)
+{
+	struct rb_node *node;
+	struct memtype *match;
+	int found_type = reqtype;
+
+	match = memtype_rb_lowest_match(&memtype_rbroot, start, end);
+	if (match == NULL)
+		goto success;
+
+	if (match->type != found_type && newtype == NULL)
+		goto failure;
+
+	dprintk("Overlap at 0x%Lx-0x%Lx\n", match->start, match->end);
+	found_type = match->type;
+
+	node = rb_next(&match->rb);
+	while (node) {
+		match = container_of(node, struct memtype, rb);
+
+		if (match->start >= end) /* Checked all possible matches */
+			goto success;
+
+		if (is_node_overlap(match, start, end) &&
+		    match->type != found_type) {
+			goto failure;
+		}
+
+		node = rb_next(&match->rb);
+	}
+success:
+	if (newtype)
+		*newtype = found_type;
+
+	return 0;
+
+failure:
+	printk(KERN_INFO "%s:%d conflicting memory types "
+		"%Lx-%Lx %s<->%s\n", current->comm, current->pid, start,
+		end, cattr_name(found_type), cattr_name(match->type));
+	return -EBUSY;
+}
+
+static void memtype_rb_augment_cb(struct rb_node *node)
+{
+	if (node)
+		update_path_max_end(node);
+}
+
+static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata)
+{
+	struct rb_node **node = &(root->rb_node);
+	struct rb_node *parent = NULL;
+
+	while (*node) {
+		struct memtype *data = container_of(*node, struct memtype, rb);
+
+		parent = *node;
+		if (newdata->start <= data->start)
+			node = &((*node)->rb_left);
+		else if (newdata->start > data->start)
+			node = &((*node)->rb_right);
+	}
+
+	rb_link_node(&newdata->rb, parent, node);
+	rb_insert_color(&newdata->rb, root);
+}
+
+int rbt_memtype_check_insert(struct memtype *new, unsigned long *ret_type)
+{
+	int err = 0;
+
+	err = memtype_rb_check_conflict(&memtype_rbroot, new->start, new->end,
+						new->type, ret_type);
+
+	if (!err) {
+		if (ret_type)
+			new->type = *ret_type;
+
+		memtype_rb_insert(&memtype_rbroot, new);
+	}
+	return err;
+}
+
+int rbt_memtype_erase(u64 start, u64 end)
+{
+	struct memtype *data;
+
+	data = memtype_rb_exact_match(&memtype_rbroot, start, end);
+	if (!data)
+		return -EINVAL;
+
+	rb_erase(&data->rb, &memtype_rbroot);
+	return 0;
+}
+
+struct memtype *rbt_memtype_lookup(u64 addr)
+{
+	struct memtype *data;
+	data = memtype_rb_lowest_match(&memtype_rbroot, addr, addr + PAGE_SIZE);
+	return data;
+}
+
+#if defined(CONFIG_DEBUG_FS)
+int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos)
+{
+	struct rb_node *node;
+	int i = 1;
+
+	node = rb_first(&memtype_rbroot);
+	while (node && pos != i) {
+		node = rb_next(node);
+		i++;
+	}
+
+	if (node) { /* pos == i */
+		struct memtype *this = container_of(node, struct memtype, rb);
+		*out = *this;
+		return 0;
+	} else {
+		return 1;
+	}
+}
+#endif
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index 2bf90fafa7b5..c8abc4d1bf35 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -239,11 +239,11 @@ static void arch_perfmon_setup_counters(void)
 	if (eax.split.version_id == 0 && current_cpu_data.x86 == 6 &&
 		current_cpu_data.x86_model == 15) {
 		eax.split.version_id = 2;
-		eax.split.num_events = 2;
+		eax.split.num_counters = 2;
 		eax.split.bit_width = 40;
 	}
 
-	num_counters = eax.split.num_events;
+	num_counters = eax.split.num_counters;
 
 	op_arch_perfmon_spec.num_counters = num_counters;
 	op_arch_perfmon_spec.num_controls = num_counters;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 32764b8880b5..b3c6c59ed302 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -476,6 +476,7 @@ void xen_timer_resume(void)
 __init void xen_time_init(void)
 {
 	int cpu = smp_processor_id();
+	struct timespec tp;
 
 	clocksource_register(&xen_clocksource);
 
@@ -487,9 +488,8 @@ __init void xen_time_init(void)
 	}
 
 	/* Set initial system time with full resolution */
-	xen_read_wallclock(&xtime);
-	set_normalized_timespec(&wall_to_monotonic,
-				-xtime.tv_sec, -xtime.tv_nsec);
+	xen_read_wallclock(&tp);
+	do_settimeofday(&tp);
 
 	setup_force_cpu_cap(X86_FEATURE_TSC);
 
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index 19f7df30937f..19df764f6399 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -60,11 +60,6 @@ static struct irqaction timer_irqaction = {
 
 void __init time_init(void)
 {
-	/* FIXME: xtime&wall_to_monotonic are set in timekeeping_init. */
-	read_persistent_clock(&xtime);
-	set_normalized_timespec(&wall_to_monotonic,
-		-xtime.tv_sec, -xtime.tv_nsec);
-
 #ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT
 	printk("Calibrating CPU frequency ");
 	platform_calibrate_ccount();
diff --git a/drivers/block/hd.c b/drivers/block/hd.c
index 034e6dfc878c..81c78b3ce2df 100644
--- a/drivers/block/hd.c
+++ b/drivers/block/hd.c
@@ -164,12 +164,12 @@ unsigned long read_timer(void)
 	unsigned long t, flags;
 	int i;
 
-	spin_lock_irqsave(&i8253_lock, flags);
+	raw_spin_lock_irqsave(&i8253_lock, flags);
 	t = jiffies * 11932;
 	outb_p(0, 0x43);
 	i = inb_p(0x40);
 	i |= inb(0x40) << 8;
-	spin_unlock_irqrestore(&i8253_lock, flags);
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
 	return(t - i);
 }
 #endif
diff --git a/drivers/clocksource/cs5535-clockevt.c b/drivers/clocksource/cs5535-clockevt.c
index b314a999aabe..d7be69f13154 100644
--- a/drivers/clocksource/cs5535-clockevt.c
+++ b/drivers/clocksource/cs5535-clockevt.c
@@ -154,14 +154,14 @@ static int __init cs5535_mfgpt_init(void)
 	if (cs5535_mfgpt_setup_irq(timer, MFGPT_CMP2, &timer_irq)) {
 		printk(KERN_ERR DRV_NAME ": Could not set up IRQ %d\n",
 				timer_irq);
-		return -EIO;
+		goto err_timer;
 	}
 
 	/* And register it with the kernel */
 	ret = setup_irq(timer_irq, &mfgptirq);
 	if (ret) {
 		printk(KERN_ERR DRV_NAME ": Unable to set up the interrupt.\n");
-		goto err;
+		goto err_irq;
 	}
 
 	/* Set the clock scale and enable the event mode for CMP2 */
@@ -184,8 +184,10 @@ static int __init cs5535_mfgpt_init(void)
 
 	return 0;
 
-err:
+err_irq:
 	cs5535_mfgpt_release_irq(cs5535_event_clock, MFGPT_CMP2, &timer_irq);
+err_timer:
+	cs5535_mfgpt_free_timer(cs5535_event_clock);
 	printk(KERN_ERR DRV_NAME ": Unable to set up the MFGPT clock source\n");
 	return -EIO;
 }
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 16e478fc10de..6ba37c10700d 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -658,32 +658,20 @@ static ssize_t show_bios_limit(struct cpufreq_policy *policy, char *buf)
 	return sprintf(buf, "%u\n", policy->cpuinfo.max_freq);
 }
 
-#define define_one_ro(_name) \
-static struct freq_attr _name = \
-__ATTR(_name, 0444, show_##_name, NULL)
-
-#define define_one_ro0400(_name) \
-static struct freq_attr _name = \
-__ATTR(_name, 0400, show_##_name, NULL)
-
-#define define_one_rw(_name) \
-static struct freq_attr _name = \
-__ATTR(_name, 0644, show_##_name, store_##_name)
-
-define_one_ro0400(cpuinfo_cur_freq);
-define_one_ro(cpuinfo_min_freq);
-define_one_ro(cpuinfo_max_freq);
-define_one_ro(cpuinfo_transition_latency);
-define_one_ro(scaling_available_governors);
-define_one_ro(scaling_driver);
-define_one_ro(scaling_cur_freq);
-define_one_ro(bios_limit);
-define_one_ro(related_cpus);
-define_one_ro(affected_cpus);
-define_one_rw(scaling_min_freq);
-define_one_rw(scaling_max_freq);
-define_one_rw(scaling_governor);
-define_one_rw(scaling_setspeed);
+cpufreq_freq_attr_ro_perm(cpuinfo_cur_freq, 0400);
+cpufreq_freq_attr_ro(cpuinfo_min_freq);
+cpufreq_freq_attr_ro(cpuinfo_max_freq);
+cpufreq_freq_attr_ro(cpuinfo_transition_latency);
+cpufreq_freq_attr_ro(scaling_available_governors);
+cpufreq_freq_attr_ro(scaling_driver);
+cpufreq_freq_attr_ro(scaling_cur_freq);
+cpufreq_freq_attr_ro(bios_limit);
+cpufreq_freq_attr_ro(related_cpus);
+cpufreq_freq_attr_ro(affected_cpus);
+cpufreq_freq_attr_rw(scaling_min_freq);
+cpufreq_freq_attr_rw(scaling_max_freq);
+cpufreq_freq_attr_rw(scaling_governor);
+cpufreq_freq_attr_rw(scaling_setspeed);
 
 static struct attribute *default_attrs[] = {
 	&cpuinfo_min_freq.attr,
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 3a147874a465..526bfbf69611 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -178,12 +178,8 @@ static ssize_t show_sampling_rate_min(struct kobject *kobj,
 	return sprintf(buf, "%u\n", min_sampling_rate);
 }
 
-#define define_one_ro(_name)		\
-static struct global_attr _name =	\
-__ATTR(_name, 0444, show_##_name, NULL)
-
-define_one_ro(sampling_rate_max);
-define_one_ro(sampling_rate_min);
+define_one_global_ro(sampling_rate_max);
+define_one_global_ro(sampling_rate_min);
 
 /* cpufreq_conservative Governor Tunables */
 #define show_one(file_name, object)					\
@@ -221,12 +217,8 @@ show_one_old(freq_step);
 show_one_old(sampling_rate_min);
 show_one_old(sampling_rate_max);
 
-#define define_one_ro_old(object, _name)	\
-static struct freq_attr object =		\
-__ATTR(_name, 0444, show_##_name##_old, NULL)
-
-define_one_ro_old(sampling_rate_min_old, sampling_rate_min);
-define_one_ro_old(sampling_rate_max_old, sampling_rate_max);
+cpufreq_freq_attr_ro_old(sampling_rate_min);
+cpufreq_freq_attr_ro_old(sampling_rate_max);
 
 /*** delete after deprecation time ***/
 
@@ -364,16 +356,12 @@ static ssize_t store_freq_step(struct kobject *a, struct attribute *b,
 	return count;
 }
 
-#define define_one_rw(_name) \
-static struct global_attr _name = \
-__ATTR(_name, 0644, show_##_name, store_##_name)
-
-define_one_rw(sampling_rate);
-define_one_rw(sampling_down_factor);
-define_one_rw(up_threshold);
-define_one_rw(down_threshold);
-define_one_rw(ignore_nice_load);
-define_one_rw(freq_step);
+define_one_global_rw(sampling_rate);
+define_one_global_rw(sampling_down_factor);
+define_one_global_rw(up_threshold);
+define_one_global_rw(down_threshold);
+define_one_global_rw(ignore_nice_load);
+define_one_global_rw(freq_step);
 
 static struct attribute *dbs_attributes[] = {
 	&sampling_rate_max.attr,
@@ -409,16 +397,12 @@ write_one_old(down_threshold);
 write_one_old(ignore_nice_load);
 write_one_old(freq_step);
 
-#define define_one_rw_old(object, _name)	\
-static struct freq_attr object =		\
-__ATTR(_name, 0644, show_##_name##_old, store_##_name##_old)
-
-define_one_rw_old(sampling_rate_old, sampling_rate);
-define_one_rw_old(sampling_down_factor_old, sampling_down_factor);
-define_one_rw_old(up_threshold_old, up_threshold);
-define_one_rw_old(down_threshold_old, down_threshold);
-define_one_rw_old(ignore_nice_load_old, ignore_nice_load);
-define_one_rw_old(freq_step_old, freq_step);
+cpufreq_freq_attr_rw_old(sampling_rate);
+cpufreq_freq_attr_rw_old(sampling_down_factor);
+cpufreq_freq_attr_rw_old(up_threshold);
+cpufreq_freq_attr_rw_old(down_threshold);
+cpufreq_freq_attr_rw_old(ignore_nice_load);
+cpufreq_freq_attr_rw_old(freq_step);
 
 static struct attribute *dbs_attributes_old[] = {
 	&sampling_rate_max_old.attr,
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index 4b63dbc555fc..508e70739643 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -234,12 +234,8 @@ static ssize_t show_sampling_rate_min(struct kobject *kobj,
 	return sprintf(buf, "%u\n", min_sampling_rate);
 }
 
-#define define_one_ro(_name)		\
-static struct global_attr _name =	\
-__ATTR(_name, 0444, show_##_name, NULL)
-
-define_one_ro(sampling_rate_max);
-define_one_ro(sampling_rate_min);
+define_one_global_ro(sampling_rate_max);
+define_one_global_ro(sampling_rate_min);
 
 /* cpufreq_ondemand Governor Tunables */
 #define show_one(file_name, object)					\
@@ -274,12 +270,8 @@ show_one_old(powersave_bias);
 show_one_old(sampling_rate_min);
 show_one_old(sampling_rate_max);
 
-#define define_one_ro_old(object, _name)       \
-static struct freq_attr object =               \
-__ATTR(_name, 0444, show_##_name##_old, NULL)
-
-define_one_ro_old(sampling_rate_min_old, sampling_rate_min);
-define_one_ro_old(sampling_rate_max_old, sampling_rate_max);
+cpufreq_freq_attr_ro_old(sampling_rate_min);
+cpufreq_freq_attr_ro_old(sampling_rate_max);
 
 /*** delete after deprecation time ***/
 
@@ -376,14 +368,10 @@ static ssize_t store_powersave_bias(struct kobject *a, struct attribute *b,
 	return count;
 }
 
-#define define_one_rw(_name) \
-static struct global_attr _name = \
-__ATTR(_name, 0644, show_##_name, store_##_name)
-
-define_one_rw(sampling_rate);
-define_one_rw(up_threshold);
-define_one_rw(ignore_nice_load);
-define_one_rw(powersave_bias);
+define_one_global_rw(sampling_rate);
+define_one_global_rw(up_threshold);
+define_one_global_rw(ignore_nice_load);
+define_one_global_rw(powersave_bias);
 
 static struct attribute *dbs_attributes[] = {
 	&sampling_rate_max.attr,
@@ -415,14 +403,10 @@ write_one_old(up_threshold);
 write_one_old(ignore_nice_load);
 write_one_old(powersave_bias);
 
-#define define_one_rw_old(object, _name)       \
-static struct freq_attr object =               \
-__ATTR(_name, 0644, show_##_name##_old, store_##_name##_old)
-
-define_one_rw_old(sampling_rate_old, sampling_rate);
-define_one_rw_old(up_threshold_old, up_threshold);
-define_one_rw_old(ignore_nice_load_old, ignore_nice_load);
-define_one_rw_old(powersave_bias_old, powersave_bias);
+cpufreq_freq_attr_rw_old(sampling_rate);
+cpufreq_freq_attr_rw_old(up_threshold);
+cpufreq_freq_attr_rw_old(ignore_nice_load);
+cpufreq_freq_attr_rw_old(powersave_bias);
 
 static struct attribute *dbs_attributes_old[] = {
        &sampling_rate_max_old.attr,
diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c
index 7e18bcf05a66..46239e47a260 100644
--- a/drivers/input/gameport/gameport.c
+++ b/drivers/input/gameport/gameport.c
@@ -59,11 +59,11 @@ static unsigned int get_time_pit(void)
 	unsigned long flags;
 	unsigned int count;
 
-	spin_lock_irqsave(&i8253_lock, flags);
+	raw_spin_lock_irqsave(&i8253_lock, flags);
 	outb_p(0x00, 0x43);
 	count = inb_p(0x40);
 	count |= inb_p(0x40) << 8;
-	spin_unlock_irqrestore(&i8253_lock, flags);
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
 
 	return count;
 }
diff --git a/drivers/input/joystick/analog.c b/drivers/input/joystick/analog.c
index 1c0b529c06aa..4afe0a3b4884 100644
--- a/drivers/input/joystick/analog.c
+++ b/drivers/input/joystick/analog.c
@@ -146,11 +146,11 @@ static unsigned int get_time_pit(void)
         unsigned long flags;
         unsigned int count;
 
-        spin_lock_irqsave(&i8253_lock, flags);
+        raw_spin_lock_irqsave(&i8253_lock, flags);
         outb_p(0x00, 0x43);
         count = inb_p(0x40);
         count |= inb_p(0x40) << 8;
-        spin_unlock_irqrestore(&i8253_lock, flags);
+        raw_spin_unlock_irqrestore(&i8253_lock, flags);
 
         return count;
 }
diff --git a/drivers/input/misc/pcspkr.c b/drivers/input/misc/pcspkr.c
index ea4e1fd12651..f080dd31499b 100644
--- a/drivers/input/misc/pcspkr.c
+++ b/drivers/input/misc/pcspkr.c
@@ -30,7 +30,7 @@ MODULE_ALIAS("platform:pcspkr");
 #include <asm/i8253.h>
 #else
 #include <asm/8253pit.h>
-static DEFINE_SPINLOCK(i8253_lock);
+static DEFINE_RAW_SPINLOCK(i8253_lock);
 #endif
 
 static int pcspkr_event(struct input_dev *dev, unsigned int type, unsigned int code, int value)
@@ -50,7 +50,7 @@ static int pcspkr_event(struct input_dev *dev, unsigned int type, unsigned int c
 	if (value > 20 && value < 32767)
 		count = PIT_TICK_RATE / value;
 
-	spin_lock_irqsave(&i8253_lock, flags);
+	raw_spin_lock_irqsave(&i8253_lock, flags);
 
 	if (count) {
 		/* set command for counter 2, 2 byte write */
@@ -65,7 +65,7 @@ static int pcspkr_event(struct input_dev *dev, unsigned int type, unsigned int c
 		outb(inb_p(0x61) & 0xFC, 0x61);
 	}
 
-	spin_unlock_irqrestore(&i8253_lock, flags);
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
 
 	return 0;
 }
diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index 166b67ea622f..7581dbe456da 100644
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -186,14 +186,14 @@ int op_cpu_buffer_write_commit(struct op_entry *entry)
 struct op_sample *op_cpu_buffer_read_entry(struct op_entry *entry, int cpu)
 {
 	struct ring_buffer_event *e;
-	e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL);
+	e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL, NULL);
 	if (e)
 		goto event;
 	if (ring_buffer_swap_cpu(op_ring_buffer_read,
 				 op_ring_buffer_write,
 				 cpu))
 		return NULL;
-	e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL);
+	e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL, NULL);
 	if (e)
 		goto event;
 	return NULL;
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 7a4a5ff681fd..c3e9de8321c6 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -273,6 +273,27 @@ struct freq_attr {
 	ssize_t (*store)(struct cpufreq_policy *, const char *, size_t count);
 };
 
+#define cpufreq_freq_attr_ro(_name)		\
+static struct freq_attr _name =			\
+__ATTR(_name, 0444, show_##_name, NULL)
+
+#define cpufreq_freq_attr_ro_perm(_name, _perm)	\
+static struct freq_attr _name =			\
+__ATTR(_name, _perm, show_##_name, NULL)
+
+#define cpufreq_freq_attr_ro_old(_name)		\
+static struct freq_attr _name##_old =		\
+__ATTR(_name, 0444, show_##_name##_old, NULL)
+
+#define cpufreq_freq_attr_rw(_name)		\
+static struct freq_attr _name =			\
+__ATTR(_name, 0644, show_##_name, store_##_name)
+
+#define cpufreq_freq_attr_rw_old(_name)		\
+static struct freq_attr _name##_old =		\
+__ATTR(_name, 0644, show_##_name##_old, store_##_name##_old)
+
+
 struct global_attr {
 	struct attribute attr;
 	ssize_t (*show)(struct kobject *kobj,
@@ -281,6 +302,15 @@ struct global_attr {
 			 const char *c, size_t count);
 };
 
+#define define_one_global_ro(_name)		\
+static struct global_attr _name =		\
+__ATTR(_name, 0444, show_##_name, NULL)
+
+#define define_one_global_rw(_name)		\
+static struct global_attr _name =		\
+__ATTR(_name, 0644, show_##_name, store_##_name)
+
+
 /*********************************************************************
  *                        CPUFREQ 2.6. INTERFACE                     *
  *********************************************************************/
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index a5740fc4d04b..a73454aec333 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -21,8 +21,7 @@ extern int number_of_cpusets;	/* How many cpusets are defined in system? */
 extern int cpuset_init(void);
 extern void cpuset_init_smp(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
-extern void cpuset_cpus_allowed_locked(struct task_struct *p,
-				       struct cpumask *mask);
+extern int cpuset_cpus_allowed_fallback(struct task_struct *p);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
 #define cpuset_current_mems_allowed (current->mems_allowed)
 void cpuset_init_current_mems_allowed(void);
@@ -69,9 +68,6 @@ struct seq_file;
 extern void cpuset_task_status_allowed(struct seq_file *m,
 					struct task_struct *task);
 
-extern void cpuset_lock(void);
-extern void cpuset_unlock(void);
-
 extern int cpuset_mem_spread_node(void);
 
 static inline int cpuset_do_page_mem_spread(void)
@@ -105,10 +101,11 @@ static inline void cpuset_cpus_allowed(struct task_struct *p,
 {
 	cpumask_copy(mask, cpu_possible_mask);
 }
-static inline void cpuset_cpus_allowed_locked(struct task_struct *p,
-					      struct cpumask *mask)
+
+static inline int cpuset_cpus_allowed_fallback(struct task_struct *p)
 {
-	cpumask_copy(mask, cpu_possible_mask);
+	cpumask_copy(&p->cpus_allowed, cpu_possible_mask);
+	return cpumask_any(cpu_active_mask);
 }
 
 static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
@@ -157,9 +154,6 @@ static inline void cpuset_task_status_allowed(struct seq_file *m,
 {
 }
 
-static inline void cpuset_lock(void) {}
-static inline void cpuset_unlock(void) {}
-
 static inline int cpuset_mem_spread_node(void)
 {
 	return 0;
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 01e6adea07ec..cc12b3c556b3 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -504,18 +504,6 @@ extern int ftrace_dump_on_oops;
 #define INIT_TRACE_RECURSION
 #endif
 
-#ifdef CONFIG_HW_BRANCH_TRACER
-
-void trace_hw_branch(u64 from, u64 to);
-void trace_hw_branch_oops(void);
-
-#else /* CONFIG_HW_BRANCH_TRACER */
-
-static inline void trace_hw_branch(u64 from, u64 to) {}
-static inline void trace_hw_branch_oops(void) {}
-
-#endif /* CONFIG_HW_BRANCH_TRACER */
-
 #ifdef CONFIG_FTRACE_SYSCALLS
 
 unsigned long arch_syscall_addr(int nr);
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index c0f4b364c711..39e71b0a3bfd 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -58,6 +58,7 @@ struct trace_iterator {
 	/* The below is zeroed out in pipe_read */
 	struct trace_seq	seq;
 	struct trace_entry	*ent;
+	unsigned long		lost_events;
 	int			leftover;
 	int			cpu;
 	u64			ts;
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 5d86fb2309d2..fd0c1b857d3d 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -422,6 +422,8 @@ extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
 
 extern int schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
 						const enum hrtimer_mode mode);
+extern int schedule_hrtimeout_range_clock(ktime_t *expires,
+		unsigned long delta, const enum hrtimer_mode mode, int clock);
 extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
 
 /* Soft interrupt function to run the hrtimer queues: */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 462acaf36f3a..fb19bb92b809 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -19,7 +19,6 @@ struct anon_vma;
 struct file_ra_state;
 struct user_struct;
 struct writeback_control;
-struct rlimit;
 
 #ifndef CONFIG_DISCONTIGMEM          /* Don't use mapnrs, do it properly */
 extern unsigned long max_mapnr;
@@ -1449,9 +1448,6 @@ int vmemmap_populate_basepages(struct page *start_page,
 int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
 void vmemmap_populate_print_last(void);
 
-extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
-				 size_t size);
-extern void refund_locked_memory(struct mm_struct *mm, size_t size);
 
 enum mf_flags {
 	MF_COUNT_INCREASED = 1 << 0,
diff --git a/include/linux/module.h b/include/linux/module.h
index 515d53ae6a79..6914fcad4673 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -465,8 +465,7 @@ static inline void __module_get(struct module *module)
 	if (module) {
 		preempt_disable();
 		__this_cpu_inc(module->refptr->incs);
-		trace_module_get(module, _THIS_IP_,
-				 __this_cpu_read(module->refptr->incs));
+		trace_module_get(module, _THIS_IP_);
 		preempt_enable();
 	}
 }
@@ -480,8 +479,7 @@ static inline int try_module_get(struct module *module)
 
 		if (likely(module_is_live(module))) {
 			__this_cpu_inc(module->refptr->incs);
-			trace_module_get(module, _THIS_IP_,
-				__this_cpu_read(module->refptr->incs));
+			trace_module_get(module, _THIS_IP_);
 		} else
 			ret = 0;
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c8e375440403..6e96cc8225d4 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -203,8 +203,9 @@ struct perf_event_attr {
 				enable_on_exec :  1, /* next exec enables     */
 				task           :  1, /* trace fork/exit       */
 				watermark      :  1, /* wakeup_watermark      */
+				precise        :  1, /* OoO invariant counter */
 
-				__reserved_1   : 49;
+				__reserved_1   : 48;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -293,6 +294,12 @@ struct perf_event_mmap_page {
 #define PERF_RECORD_MISC_USER			(2 << 0)
 #define PERF_RECORD_MISC_HYPERVISOR		(3 << 0)
 
+#define PERF_RECORD_MISC_EXACT			(1 << 14)
+/*
+ * Reserve the last bit to indicate some extended misc field
+ */
+#define PERF_RECORD_MISC_EXT_RESERVED		(1 << 15)
+
 struct perf_event_header {
 	__u32	type;
 	__u16	misc;
@@ -468,6 +475,17 @@ struct perf_raw_record {
 	void				*data;
 };
 
+struct perf_branch_entry {
+	__u64				from;
+	__u64				to;
+	__u64				flags;
+};
+
+struct perf_branch_stack {
+	__u64				nr;
+	struct perf_branch_entry	entries[0];
+};
+
 struct task_struct;
 
 /**
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index e1fb60729979..4272521e29e9 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -345,18 +345,6 @@ static inline void user_single_step_siginfo(struct task_struct *tsk,
 #define arch_ptrace_stop(code, info)		do { } while (0)
 #endif
 
-#ifndef arch_ptrace_untrace
-/*
- * Do machine-specific work before untracing child.
- *
- * This is called for a normal detach as well as from ptrace_exit()
- * when the tracing task dies.
- *
- * Called with write_lock(&tasklist_lock) held.
- */
-#define arch_ptrace_untrace(task)		do { } while (0)
-#endif
-
 extern int task_current_syscall(struct task_struct *target, long *callno,
 				unsigned long args[6], unsigned int maxargs,
 				unsigned long *sp, unsigned long *pc);
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index 5210a5c60877..fe1872e5b37e 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -110,6 +110,7 @@ struct rb_node
 struct rb_root
 {
 	struct rb_node *rb_node;
+	void (*augment_cb)(struct rb_node *node);
 };
 
 
@@ -129,7 +130,9 @@ static inline void rb_set_color(struct rb_node *rb, int color)
 	rb->rb_parent_color = (rb->rb_parent_color & ~1) | color;
 }
 
-#define RB_ROOT	(struct rb_root) { NULL, }
+#define RB_ROOT	(struct rb_root) { NULL, NULL, }
+#define RB_AUGMENT_ROOT(x)	(struct rb_root) { NULL, x}
+
 #define	rb_entry(ptr, type, member) container_of(ptr, type, member)
 
 #define RB_EMPTY_ROOT(root)	((root)->rb_node == NULL)
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 5fcc31ed5771..c8297761e414 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -120,9 +120,11 @@ int ring_buffer_write(struct ring_buffer *buffer,
 		      unsigned long length, void *data);
 
 struct ring_buffer_event *
-ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts);
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts,
+		 unsigned long *lost_events);
 struct ring_buffer_event *
-ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts);
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts,
+		    unsigned long *lost_events);
 
 struct ring_buffer_iter *
 ring_buffer_read_start(struct ring_buffer *buffer, int cpu);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index dad7f668ebf7..c46b6e5ad685 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -99,7 +99,6 @@ struct futex_pi_state;
 struct robust_list_head;
 struct bio_list;
 struct fs_struct;
-struct bts_context;
 struct perf_event_context;
 
 /*
@@ -275,11 +274,17 @@ extern cpumask_var_t nohz_cpu_mask;
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
 extern int select_nohz_load_balancer(int cpu);
 extern int get_nohz_load_balancer(void);
+extern int nohz_ratelimit(int cpu);
 #else
 static inline int select_nohz_load_balancer(int cpu)
 {
 	return 0;
 }
+
+static inline int nohz_ratelimit(int cpu)
+{
+	return 0;
+}
 #endif
 
 /*
@@ -1026,12 +1031,17 @@ struct sched_domain;
 #define WF_SYNC		0x01		/* waker goes to sleep after wakup */
 #define WF_FORK		0x02		/* child wakeup after fork */
 
+#define ENQUEUE_WAKEUP		1
+#define ENQUEUE_WAKING		2
+#define ENQUEUE_HEAD		4
+
+#define DEQUEUE_SLEEP		1
+
 struct sched_class {
 	const struct sched_class *next;
 
-	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup,
-			      bool head);
-	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
+	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
+	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*yield_task) (struct rq *rq);
 
 	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
@@ -1040,7 +1050,8 @@ struct sched_class {
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
-	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
+	int  (*select_task_rq)(struct rq *rq, struct task_struct *p,
+			       int sd_flag, int flags);
 
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
 	void (*post_schedule) (struct rq *this_rq);
@@ -1077,36 +1088,8 @@ struct load_weight {
 	unsigned long weight, inv_weight;
 };
 
-/*
- * CFS stats for a schedulable entity (task, task-group etc)
- *
- * Current field usage histogram:
- *
- *     4 se->block_start
- *     4 se->run_node
- *     4 se->sleep_start
- *     6 se->load.weight
- */
-struct sched_entity {
-	struct load_weight	load;		/* for load-balancing */
-	struct rb_node		run_node;
-	struct list_head	group_node;
-	unsigned int		on_rq;
-
-	u64			exec_start;
-	u64			sum_exec_runtime;
-	u64			vruntime;
-	u64			prev_sum_exec_runtime;
-
-	u64			last_wakeup;
-	u64			avg_overlap;
-
-	u64			nr_migrations;
-
-	u64			start_runtime;
-	u64			avg_wakeup;
-
 #ifdef CONFIG_SCHEDSTATS
+struct sched_statistics {
 	u64			wait_start;
 	u64			wait_max;
 	u64			wait_count;
@@ -1138,6 +1121,24 @@ struct sched_entity {
 	u64			nr_wakeups_affine_attempts;
 	u64			nr_wakeups_passive;
 	u64			nr_wakeups_idle;
+};
+#endif
+
+struct sched_entity {
+	struct load_weight	load;		/* for load-balancing */
+	struct rb_node		run_node;
+	struct list_head	group_node;
+	unsigned int		on_rq;
+
+	u64			exec_start;
+	u64			sum_exec_runtime;
+	u64			vruntime;
+	u64			prev_sum_exec_runtime;
+
+	u64			nr_migrations;
+
+#ifdef CONFIG_SCHEDSTATS
+	struct sched_statistics statistics;
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1272,12 +1273,6 @@ struct task_struct {
 	struct list_head ptraced;
 	struct list_head ptrace_entry;
 
-	/*
-	 * This is the tracer handle for the ptrace BTS extension.
-	 * This field actually belongs to the ptracer task.
-	 */
-	struct bts_context *bts;
-
 	/* PID/PID hash table linkage. */
 	struct pid_link pids[PIDTYPE_MAX];
 	struct list_head thread_group;
@@ -1847,6 +1842,7 @@ extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
 
 #ifdef CONFIG_HOTPLUG_CPU
+extern void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p);
 extern void idle_task_exit(void);
 #else
 static inline void idle_task_exit(void) {}
@@ -2123,10 +2119,8 @@ extern void set_task_comm(struct task_struct *tsk, char *from);
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
-extern void wait_task_context_switch(struct task_struct *p);
 extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
-static inline void wait_task_context_switch(struct task_struct *p) {}
 static inline unsigned long wait_task_inactive(struct task_struct *p,
 					       long match_state)
 {
diff --git a/include/linux/timer.h b/include/linux/timer.h
index a2d1eb6cb3f0..ea965b857a50 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -10,13 +10,19 @@
 struct tvec_base;
 
 struct timer_list {
+	/*
+	 * All fields that change during normal runtime grouped to the
+	 * same cacheline
+	 */
 	struct list_head entry;
 	unsigned long expires;
+	struct tvec_base *base;
 
 	void (*function)(unsigned long);
 	unsigned long data;
 
-	struct tvec_base *base;
+	int slack;
+
 #ifdef CONFIG_TIMER_STATS
 	void *start_site;
 	char start_comm[16];
@@ -165,6 +171,8 @@ extern int mod_timer(struct timer_list *timer, unsigned long expires);
 extern int mod_timer_pending(struct timer_list *timer, unsigned long expires);
 extern int mod_timer_pinned(struct timer_list *timer, unsigned long expires);
 
+extern void set_timer_slack(struct timer_list *time, int slack_hz);
+
 #define TIMER_NOT_PINNED	0
 #define TIMER_PINNED		1
 /*
diff --git a/include/linux/timex.h b/include/linux/timex.h
index 7a082b32d8e1..32d852f8cbe4 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -232,13 +232,11 @@ struct timex {
  */
 extern unsigned long tick_usec;		/* USER_HZ period (usec) */
 extern unsigned long tick_nsec;		/* ACTHZ          period (nsec) */
-extern int tickadj;			/* amount of adjustment per tick */
 
 /*
  * phase-lock loop variables
  */
 extern int time_status;		/* clock synchronization status bits */
-extern long time_adjust;	/* The amount of adjtime left */
 
 extern void ntp_init(void);
 extern void ntp_clear(void);
@@ -271,9 +269,6 @@ extern void second_overflow(void);
 extern void update_ntp_one_tick(void);
 extern int do_adjtimex(struct timex *);
 
-/* Don't use! Compatibility define for existing users. */
-#define tickadj	(500/HZ ? : 1)
-
 int read_current_timer(unsigned long *timer_val);
 
 /* The clock frequency of the i8253/i8254 PIT */
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index 4b0f48ba16a6..c7bb2f0482fe 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -51,11 +51,14 @@ TRACE_EVENT(module_free,
 	TP_printk("%s", __get_str(name))
 );
 
+#ifdef CONFIG_MODULE_UNLOAD
+/* trace_module_get/put are only used if CONFIG_MODULE_UNLOAD is defined */
+
 DECLARE_EVENT_CLASS(module_refcnt,
 
-	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+	TP_PROTO(struct module *mod, unsigned long ip),
 
-	TP_ARGS(mod, ip, refcnt),
+	TP_ARGS(mod, ip),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	ip		)
@@ -65,7 +68,7 @@ DECLARE_EVENT_CLASS(module_refcnt,
 
 	TP_fast_assign(
 		__entry->ip	= ip;
-		__entry->refcnt	= refcnt;
+		__entry->refcnt	= __this_cpu_read(mod->refptr->incs) + __this_cpu_read(mod->refptr->decs);
 		__assign_str(name, mod->name);
 	),
 
@@ -75,17 +78,18 @@ DECLARE_EVENT_CLASS(module_refcnt,
 
 DEFINE_EVENT(module_refcnt, module_get,
 
-	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+	TP_PROTO(struct module *mod, unsigned long ip),
 
-	TP_ARGS(mod, ip, refcnt)
+	TP_ARGS(mod, ip)
 );
 
 DEFINE_EVENT(module_refcnt, module_put,
 
-	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+	TP_PROTO(struct module *mod, unsigned long ip),
 
-	TP_ARGS(mod, ip, refcnt)
+	TP_ARGS(mod, ip)
 );
+#endif /* CONFIG_MODULE_UNLOAD */
 
 TRACE_EVENT(module_request,
 
diff --git a/include/trace/events/signal.h b/include/trace/events/signal.h
index a510b75ac304..814566c99d29 100644
--- a/include/trace/events/signal.h
+++ b/include/trace/events/signal.h
@@ -100,18 +100,7 @@ TRACE_EVENT(signal_deliver,
 		  __entry->sa_handler, __entry->sa_flags)
 );
 
-/**
- * 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.
- */
-TRACE_EVENT(signal_overflow_fail,
+DECLARE_EVENT_CLASS(signal_queue_overflow,
 
 	TP_PROTO(int sig, int group, struct siginfo *info),
 
@@ -135,6 +124,24 @@ TRACE_EVENT(signal_overflow_fail,
 );
 
 /**
+ * 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)
@@ -145,28 +152,13 @@ TRACE_EVENT(signal_overflow_fail,
  * 'group' is not 0 if the signal will be sent to a process group.
  * 'sig' is always one of non-RT signals.
  */
-TRACE_EVENT(signal_lose_info,
+DEFINE_EVENT(signal_queue_overflow, signal_lose_info,
 
 	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)
+	TP_ARGS(sig, group, info)
 );
+
 #endif /* _TRACE_SIGNAL_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index ea6f9d4a20e9..16253db38d73 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -154,9 +154,11 @@
  *
  *	field = (typeof(field))entry;
  *
- *	p = get_cpu_var(ftrace_event_seq);
+ *	p = &get_cpu_var(ftrace_event_seq);
  *	trace_seq_init(p);
- *	ret = trace_seq_printf(s, <TP_printk> "\n");
+ *	ret = trace_seq_printf(s, "%s: ", <call>);
+ *	if (ret)
+ *		ret = trace_seq_printf(s, <TP_printk> "\n");
  *	put_cpu();
  *	if (!ret)
  *		return TRACE_TYPE_PARTIAL_LINE;
@@ -450,38 +452,38 @@ perf_trace_disable_##name(struct ftrace_event_call *unused)		\
  *
  * static void ftrace_raw_event_<call>(proto)
  * {
+ *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
  *	struct ring_buffer_event *event;
  *	struct ftrace_raw_<call> *entry; <-- defined in stage 1
  *	struct ring_buffer *buffer;
  *	unsigned long irq_flags;
+ *	int __data_size;
  *	int pc;
  *
  *	local_save_flags(irq_flags);
  *	pc = preempt_count();
  *
+ *	__data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
+ *
  *	event = trace_current_buffer_lock_reserve(&buffer,
  *				  event_<call>.id,
- *				  sizeof(struct ftrace_raw_<call>),
+ *				  sizeof(*entry) + __data_size,
  *				  irq_flags, pc);
  *	if (!event)
  *		return;
  *	entry	= ring_buffer_event_data(event);
  *
- *	<assign>;  <-- Here we assign the entries by the __field and
- *			__array macros.
+ *	{ <assign>; }  <-- Here we assign the entries by the __field and
+ *			   __array macros.
  *
- *	trace_current_buffer_unlock_commit(buffer, event, irq_flags, pc);
+ *	if (!filter_current_check_discard(buffer, event_call, entry, event))
+ *		trace_current_buffer_unlock_commit(buffer,
+ *						   event, irq_flags, pc);
  * }
  *
  * static int ftrace_raw_reg_event_<call>(struct ftrace_event_call *unused)
  * {
- *	int ret;
- *
- *	ret = register_trace_<call>(ftrace_raw_event_<call>);
- *	if (!ret)
- *		pr_info("event trace: Could not activate trace point "
- *			"probe to <call>");
- *	return ret;
+ *	return register_trace_<call>(ftrace_raw_event_<call>);
  * }
  *
  * static void ftrace_unreg_event_<call>(struct ftrace_event_call *unused)
@@ -493,6 +495,8 @@ perf_trace_disable_##name(struct ftrace_event_call *unused)		\
  *	.trace			= ftrace_raw_output_<call>, <-- stage 2
  * };
  *
+ * static const char print_fmt_<call>[] = <TP_printk>;
+ *
  * static struct ftrace_event_call __used
  * __attribute__((__aligned__(4)))
  * __attribute__((section("_ftrace_events"))) event_<call> = {
@@ -501,6 +505,8 @@ perf_trace_disable_##name(struct ftrace_event_call *unused)		\
  *	.raw_init		= trace_event_raw_init,
  *	.regfunc		= ftrace_reg_event_<call>,
  *	.unregfunc		= ftrace_unreg_event_<call>,
+ *	.print_fmt		= print_fmt_<call>,
+ *	.define_fields		= ftrace_define_fields_<call>,
  * }
  *
  */
@@ -569,7 +575,6 @@ ftrace_raw_event_id_##call(struct ftrace_event_call *event_call,	\
 		return;							\
 	entry	= ring_buffer_event_data(event);			\
 									\
-									\
 	tstruct								\
 									\
 	{ assign; }							\
@@ -758,13 +763,12 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 static notrace void							\
 perf_trace_templ_##call(struct ftrace_event_call *event_call,		\
-			    proto)					\
+			struct pt_regs *__regs, proto)			\
 {									\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
 	struct ftrace_raw_##call *entry;				\
 	u64 __addr = 0, __count = 1;					\
 	unsigned long irq_flags;					\
-	struct pt_regs *__regs;						\
 	int __entry_size;						\
 	int __data_size;						\
 	int rctx;							\
@@ -785,20 +789,22 @@ perf_trace_templ_##call(struct ftrace_event_call *event_call,		\
 									\
 	{ assign; }							\
 									\
-	__regs = &__get_cpu_var(perf_trace_regs);			\
-	perf_fetch_caller_regs(__regs, 2);				\
-									\
 	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
 			       __count, irq_flags, __regs);		\
 }
 
 #undef DEFINE_EVENT
-#define DEFINE_EVENT(template, call, proto, args)		\
-static notrace void perf_trace_##call(proto)			\
-{								\
-	struct ftrace_event_call *event_call = &event_##call;	\
-								\
-	perf_trace_templ_##template(event_call, args);		\
+#define DEFINE_EVENT(template, call, proto, args)			\
+static notrace void perf_trace_##call(proto)				\
+{									\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	struct pt_regs *__regs = &get_cpu_var(perf_trace_regs);		\
+									\
+	perf_fetch_caller_regs(__regs, 1);				\
+									\
+	perf_trace_templ_##template(event_call, __regs, args);		\
+									\
+	put_cpu_var(perf_trace_regs);					\
 }
 
 #undef DEFINE_EVENT_PRINT
diff --git a/init/Kconfig b/init/Kconfig
index cb6069ec6f5f..8daa66cb166b 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -616,8 +616,7 @@ config RT_GROUP_SCHED
 	default n
 	help
 	  This feature lets you explicitly allocate real CPU bandwidth
-	  to users or control groups (depending on the "Basis for grouping tasks"
-	  setting below. If enabled, it will also make it impossible to
+	  to task groups. If enabled, it will also make it impossible to
 	  schedule realtime tasks for non-root users until you allocate
 	  realtime bandwidth for them.
 	  See Documentation/scheduler/sched-rt-group.txt for more information.
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 722b0130aa94..d6c09c46ad06 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -429,7 +429,7 @@ static void wq_add(struct mqueue_inode_info *info, int sr,
  * sr: SEND or RECV
  */
 static int wq_sleep(struct mqueue_inode_info *info, int sr,
-			long timeout, struct ext_wait_queue *ewp)
+		    ktime_t *timeout, struct ext_wait_queue *ewp)
 {
 	int retval;
 	signed long time;
@@ -440,7 +440,8 @@ static int wq_sleep(struct mqueue_inode_info *info, int sr,
 		set_current_state(TASK_INTERRUPTIBLE);
 
 		spin_unlock(&info->lock);
-		time = schedule_timeout(timeout);
+		time = schedule_hrtimeout_range_clock(timeout,
+		    HRTIMER_MODE_ABS, 0, CLOCK_REALTIME);
 
 		while (ewp->state == STATE_PENDING)
 			cpu_relax();
@@ -552,31 +553,16 @@ static void __do_notify(struct mqueue_inode_info *info)
 	wake_up(&info->wait_q);
 }
 
-static long prepare_timeout(struct timespec *p)
+static int prepare_timeout(const struct timespec __user *u_abs_timeout,
+			   ktime_t *expires, struct timespec *ts)
 {
-	struct timespec nowts;
-	long timeout;
-
-	if (p) {
-		if (unlikely(p->tv_nsec < 0 || p->tv_sec < 0
-			|| p->tv_nsec >= NSEC_PER_SEC))
-			return -EINVAL;
-		nowts = CURRENT_TIME;
-		/* first subtract as jiffies can't be too big */
-		p->tv_sec -= nowts.tv_sec;
-		if (p->tv_nsec < nowts.tv_nsec) {
-			p->tv_nsec += NSEC_PER_SEC;
-			p->tv_sec--;
-		}
-		p->tv_nsec -= nowts.tv_nsec;
-		if (p->tv_sec < 0)
-			return 0;
-
-		timeout = timespec_to_jiffies(p) + 1;
-	} else
-		return MAX_SCHEDULE_TIMEOUT;
+	if (copy_from_user(ts, u_abs_timeout, sizeof(struct timespec)))
+		return -EFAULT;
+	if (!timespec_valid(ts))
+		return -EINVAL;
 
-	return timeout;
+	*expires = timespec_to_ktime(*ts);
+	return 0;
 }
 
 static void remove_notification(struct mqueue_inode_info *info)
@@ -862,22 +848,21 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
 	struct ext_wait_queue *receiver;
 	struct msg_msg *msg_ptr;
 	struct mqueue_inode_info *info;
-	struct timespec ts, *p = NULL;
-	long timeout;
+	ktime_t expires, *timeout = NULL;
+	struct timespec ts;
 	int ret;
 
 	if (u_abs_timeout) {
-		if (copy_from_user(&ts, u_abs_timeout, 
-					sizeof(struct timespec)))
-			return -EFAULT;
-		p = &ts;
+		int res = prepare_timeout(u_abs_timeout, &expires, &ts);
+		if (res)
+			return res;
+		timeout = &expires;
 	}
 
 	if (unlikely(msg_prio >= (unsigned long) MQ_PRIO_MAX))
 		return -EINVAL;
 
-	audit_mq_sendrecv(mqdes, msg_len, msg_prio, p);
-	timeout = prepare_timeout(p);
+	audit_mq_sendrecv(mqdes, msg_len, msg_prio, timeout ? &ts : NULL);
 
 	filp = fget(mqdes);
 	if (unlikely(!filp)) {
@@ -919,9 +904,6 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
 		if (filp->f_flags & O_NONBLOCK) {
 			spin_unlock(&info->lock);
 			ret = -EAGAIN;
-		} else if (unlikely(timeout < 0)) {
-			spin_unlock(&info->lock);
-			ret = timeout;
 		} else {
 			wait.task = current;
 			wait.msg = (void *) msg_ptr;
@@ -954,24 +936,23 @@ SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
 		size_t, msg_len, unsigned int __user *, u_msg_prio,
 		const struct timespec __user *, u_abs_timeout)
 {
-	long timeout;
 	ssize_t ret;
 	struct msg_msg *msg_ptr;
 	struct file *filp;
 	struct inode *inode;
 	struct mqueue_inode_info *info;
 	struct ext_wait_queue wait;
-	struct timespec ts, *p = NULL;
+	ktime_t expires, *timeout = NULL;
+	struct timespec ts;
 
 	if (u_abs_timeout) {
-		if (copy_from_user(&ts, u_abs_timeout, 
-					sizeof(struct timespec)))
-			return -EFAULT;
-		p = &ts;
+		int res = prepare_timeout(u_abs_timeout, &expires, &ts);
+		if (res)
+			return res;
+		timeout = &expires;
 	}
 
-	audit_mq_sendrecv(mqdes, msg_len, 0, p);
-	timeout = prepare_timeout(p);
+	audit_mq_sendrecv(mqdes, msg_len, 0, timeout ? &ts : NULL);
 
 	filp = fget(mqdes);
 	if (unlikely(!filp)) {
@@ -1003,11 +984,6 @@ SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
 		if (filp->f_flags & O_NONBLOCK) {
 			spin_unlock(&info->lock);
 			ret = -EAGAIN;
-			msg_ptr = NULL;
-		} else if (unlikely(timeout < 0)) {
-			spin_unlock(&info->lock);
-			ret = timeout;
-			msg_ptr = NULL;
 		} else {
 			wait.task = current;
 			wait.state = STATE_NONE;
diff --git a/kernel/capability.c b/kernel/capability.c
index 9e4697e9b276..2f05303715a5 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -15,7 +15,6 @@
 #include <linux/syscalls.h>
 #include <linux/pid_namespace.h>
 #include <asm/uaccess.h>
-#include "cred-internals.h"
 
 /*
  * Leveraged for setting/resetting capabilities
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 25bba73b1be3..914aedcde849 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -164,6 +164,7 @@ static inline void check_for_tasks(int cpu)
 }
 
 struct take_cpu_down_param {
+	struct task_struct *caller;
 	unsigned long mod;
 	void *hcpu;
 };
@@ -172,6 +173,7 @@ struct take_cpu_down_param {
 static int __ref take_cpu_down(void *_param)
 {
 	struct take_cpu_down_param *param = _param;
+	unsigned int cpu = (unsigned long)param->hcpu;
 	int err;
 
 	/* Ensure this CPU doesn't handle any more interrupts. */
@@ -182,6 +184,8 @@ static int __ref take_cpu_down(void *_param)
 	raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
 				param->hcpu);
 
+	if (task_cpu(param->caller) == cpu)
+		move_task_off_dead_cpu(cpu, param->caller);
 	/* Force idle task to run as soon as we yield: it should
 	   immediately notice cpu is offline and die quickly. */
 	sched_idle_next();
@@ -192,10 +196,10 @@ static int __ref take_cpu_down(void *_param)
 static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 {
 	int err, nr_calls = 0;
-	cpumask_var_t old_allowed;
 	void *hcpu = (void *)(long)cpu;
 	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
 	struct take_cpu_down_param tcd_param = {
+		.caller = current,
 		.mod = mod,
 		.hcpu = hcpu,
 	};
@@ -206,9 +210,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	if (!cpu_online(cpu))
 		return -EINVAL;
 
-	if (!alloc_cpumask_var(&old_allowed, GFP_KERNEL))
-		return -ENOMEM;
-
 	cpu_hotplug_begin();
 	set_cpu_active(cpu, false);
 	err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
@@ -225,10 +226,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 		goto out_release;
 	}
 
-	/* Ensure that we are not runnable on dying cpu */
-	cpumask_copy(old_allowed, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current, cpu_active_mask);
-
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		set_cpu_active(cpu, true);
@@ -237,7 +234,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 					    hcpu) == NOTIFY_BAD)
 			BUG();
 
-		goto out_allowed;
+		goto out_release;
 	}
 	BUG_ON(cpu_online(cpu));
 
@@ -255,8 +252,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 
 	check_for_tasks(cpu);
 
-out_allowed:
-	set_cpus_allowed_ptr(current, old_allowed);
 out_release:
 	cpu_hotplug_done();
 	if (!err) {
@@ -264,7 +259,6 @@ out_release:
 					    hcpu) == NOTIFY_BAD)
 			BUG();
 	}
-	free_cpumask_var(old_allowed);
 	return err;
 }
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index d10946748ec2..9a50c5f6e727 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2182,19 +2182,52 @@ void __init cpuset_init_smp(void)
 void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 {
 	mutex_lock(&callback_mutex);
-	cpuset_cpus_allowed_locked(tsk, pmask);
+	task_lock(tsk);
+	guarantee_online_cpus(task_cs(tsk), pmask);
+	task_unlock(tsk);
 	mutex_unlock(&callback_mutex);
 }
 
-/**
- * cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset.
- * Must be called with callback_mutex held.
- **/
-void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask)
+int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 {
-	task_lock(tsk);
-	guarantee_online_cpus(task_cs(tsk), pmask);
-	task_unlock(tsk);
+	const struct cpuset *cs;
+	int cpu;
+
+	rcu_read_lock();
+	cs = task_cs(tsk);
+	if (cs)
+		cpumask_copy(&tsk->cpus_allowed, cs->cpus_allowed);
+	rcu_read_unlock();
+
+	/*
+	 * We own tsk->cpus_allowed, nobody can change it under us.
+	 *
+	 * But we used cs && cs->cpus_allowed lockless and thus can
+	 * race with cgroup_attach_task() or update_cpumask() and get
+	 * the wrong tsk->cpus_allowed. However, both cases imply the
+	 * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr()
+	 * which takes task_rq_lock().
+	 *
+	 * If we are called after it dropped the lock we must see all
+	 * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary
+	 * set any mask even if it is not right from task_cs() pov,
+	 * the pending set_cpus_allowed_ptr() will fix things.
+	 */
+
+	cpu = cpumask_any_and(&tsk->cpus_allowed, cpu_active_mask);
+	if (cpu >= nr_cpu_ids) {
+		/*
+		 * Either tsk->cpus_allowed is wrong (see above) or it
+		 * is actually empty. The latter case is only possible
+		 * if we are racing with remove_tasks_in_empty_cpuset().
+		 * Like above we can temporary set any mask and rely on
+		 * set_cpus_allowed_ptr() as synchronization point.
+		 */
+		cpumask_copy(&tsk->cpus_allowed, cpu_possible_mask);
+		cpu = cpumask_any(cpu_active_mask);
+	}
+
+	return cpu;
 }
 
 void cpuset_init_current_mems_allowed(void)
@@ -2383,22 +2416,6 @@ int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
 }
 
 /**
- * cpuset_lock - lock out any changes to cpuset structures
- *
- * The out of memory (oom) code needs to mutex_lock cpusets
- * from being changed while it scans the tasklist looking for a
- * task in an overlapping cpuset.  Expose callback_mutex via this
- * cpuset_lock() routine, so the oom code can lock it, before
- * locking the task list.  The tasklist_lock is a spinlock, so
- * must be taken inside callback_mutex.
- */
-
-void cpuset_lock(void)
-{
-	mutex_lock(&callback_mutex);
-}
-
-/**
  * cpuset_unlock - release lock on cpuset changes
  *
  * Undo the lock taken in a previous cpuset_lock() call.
diff --git a/kernel/cred-internals.h b/kernel/cred-internals.h
deleted file mode 100644
index 2dc4fc2d0bf1..000000000000
--- a/kernel/cred-internals.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* Internal credentials stuff
- *
- * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-/*
- * user.c
- */
-static inline void sched_switch_user(struct task_struct *p)
-{
-#ifdef CONFIG_USER_SCHED
-	sched_move_task(p);
-#endif	/* CONFIG_USER_SCHED */
-}
-
diff --git a/kernel/cred.c b/kernel/cred.c
index ec767ac9d41b..031232506fb7 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -17,7 +17,6 @@
 #include <linux/init_task.h>
 #include <linux/security.h>
 #include <linux/cn_proc.h>
-#include "cred-internals.h"
 
 #if 0
 #define kdebug(FMT, ...) \
@@ -556,8 +555,6 @@ int commit_creds(struct cred *new)
 		atomic_dec(&old->user->processes);
 	alter_cred_subscribers(old, -2);
 
-	sched_switch_user(task);
-
 	/* send notifications */
 	if (new->uid   != old->uid  ||
 	    new->euid  != old->euid ||
diff --git a/kernel/exit.c b/kernel/exit.c
index 7f2683a10ac4..eabca5a73a85 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -55,7 +55,6 @@
 #include <asm/unistd.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
-#include "cred-internals.h"
 
 static void exit_mm(struct task_struct * tsk);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 44b0791b0a2e..5d3592deaf71 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1111,9 +1111,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->memcg_batch.do_batch = 0;
 	p->memcg_batch.memcg = NULL;
 #endif
-
-	p->bts = NULL;
-
 	p->stack_start = stack_start;
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 0086628b6e97..b9b134b35088 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1749,35 +1749,15 @@ void __init hrtimers_init(void)
 }
 
 /**
- * schedule_hrtimeout_range - sleep until timeout
+ * schedule_hrtimeout_range_clock - sleep until timeout
  * @expires:	timeout value (ktime_t)
  * @delta:	slack in expires timeout (ktime_t)
  * @mode:	timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
- *
- * Make the current task sleep until the given expiry time has
- * elapsed. The routine will return immediately unless
- * the current task state has been set (see set_current_state()).
- *
- * The @delta argument gives the kernel the freedom to schedule the
- * actual wakeup to a time that is both power and performance friendly.
- * The kernel give the normal best effort behavior for "@expires+@delta",
- * but may decide to fire the timer earlier, but no earlier than @expires.
- *
- * You can set the task state as follows -
- *
- * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
- * pass before the routine returns.
- *
- * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
- * delivered to the current task.
- *
- * The current task state is guaranteed to be TASK_RUNNING when this
- * routine returns.
- *
- * Returns 0 when the timer has expired otherwise -EINTR
+ * @clock:	timer clock, CLOCK_MONOTONIC or CLOCK_REALTIME
  */
-int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
-			       const enum hrtimer_mode mode)
+int __sched
+schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
+			       const enum hrtimer_mode mode, int clock)
 {
 	struct hrtimer_sleeper t;
 
@@ -1799,7 +1779,7 @@ int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
 		return -EINTR;
 	}
 
-	hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode);
+	hrtimer_init_on_stack(&t.timer, clock, mode);
 	hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
 
 	hrtimer_init_sleeper(&t, current);
@@ -1818,6 +1798,41 @@ int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
 
 	return !t.task ? 0 : -EINTR;
 }
+
+/**
+ * schedule_hrtimeout_range - sleep until timeout
+ * @expires:	timeout value (ktime_t)
+ * @delta:	slack in expires timeout (ktime_t)
+ * @mode:	timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ *
+ * Make the current task sleep until the given expiry time has
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * The @delta argument gives the kernel the freedom to schedule the
+ * actual wakeup to a time that is both power and performance friendly.
+ * The kernel give the normal best effort behavior for "@expires+@delta",
+ * but may decide to fire the timer earlier, but no earlier than @expires.
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
+ * pass before the routine returns.
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task.
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Returns 0 when the timer has expired otherwise -EINTR
+ */
+int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
+				     const enum hrtimer_mode mode)
+{
+	return schedule_hrtimeout_range_clock(expires, delta, mode,
+					      CLOCK_MONOTONIC);
+}
 EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);
 
 /**
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 7a6eb04ef6b5..fe92dc5190dd 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -147,6 +147,26 @@ static const struct file_operations default_affinity_proc_fops = {
 	.release	= single_release,
 	.write		= default_affinity_write,
 };
+
+static int irq_node_proc_show(struct seq_file *m, void *v)
+{
+	struct irq_desc *desc = irq_to_desc((long) m->private);
+
+	seq_printf(m, "%d\n", desc->node);
+	return 0;
+}
+
+static int irq_node_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, irq_node_proc_show, PDE(inode)->data);
+}
+
+static const struct file_operations irq_node_proc_fops = {
+	.open		= irq_node_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
 #endif
 
 static int irq_spurious_proc_show(struct seq_file *m, void *v)
@@ -231,6 +251,9 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 	/* create /proc/irq/<irq>/smp_affinity */
 	proc_create_data("smp_affinity", 0600, desc->dir,
 			 &irq_affinity_proc_fops, (void *)(long)irq);
+
+	proc_create_data("node", 0444, desc->dir,
+			 &irq_node_proc_fops, (void *)(long)irq);
 #endif
 
 	proc_create_data("spurious", 0444, desc->dir,
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 2594e1ce41cb..78325f8f1139 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -431,20 +431,7 @@ static struct stack_trace lockdep_init_trace = {
 /*
  * Various lockdep statistics:
  */
-atomic_t chain_lookup_hits;
-atomic_t chain_lookup_misses;
-atomic_t hardirqs_on_events;
-atomic_t hardirqs_off_events;
-atomic_t redundant_hardirqs_on;
-atomic_t redundant_hardirqs_off;
-atomic_t softirqs_on_events;
-atomic_t softirqs_off_events;
-atomic_t redundant_softirqs_on;
-atomic_t redundant_softirqs_off;
-atomic_t nr_unused_locks;
-atomic_t nr_cyclic_checks;
-atomic_t nr_find_usage_forwards_checks;
-atomic_t nr_find_usage_backwards_checks;
+DEFINE_PER_CPU(struct lockdep_stats, lockdep_stats);
 #endif
 
 /*
@@ -748,7 +735,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 		return NULL;
 	}
 	class = lock_classes + nr_lock_classes++;
-	debug_atomic_inc(&nr_unused_locks);
+	debug_atomic_inc(nr_unused_locks);
 	class->key = key;
 	class->name = lock->name;
 	class->subclass = subclass;
@@ -1205,7 +1192,7 @@ check_noncircular(struct lock_list *root, struct lock_class *target,
 {
 	int result;
 
-	debug_atomic_inc(&nr_cyclic_checks);
+	debug_atomic_inc(nr_cyclic_checks);
 
 	result = __bfs_forwards(root, target, class_equal, target_entry);
 
@@ -1242,7 +1229,7 @@ find_usage_forwards(struct lock_list *root, enum lock_usage_bit bit,
 {
 	int result;
 
-	debug_atomic_inc(&nr_find_usage_forwards_checks);
+	debug_atomic_inc(nr_find_usage_forwards_checks);
 
 	result = __bfs_forwards(root, (void *)bit, usage_match, target_entry);
 
@@ -1265,7 +1252,7 @@ find_usage_backwards(struct lock_list *root, enum lock_usage_bit bit,
 {
 	int result;
 
-	debug_atomic_inc(&nr_find_usage_backwards_checks);
+	debug_atomic_inc(nr_find_usage_backwards_checks);
 
 	result = __bfs_backwards(root, (void *)bit, usage_match, target_entry);
 
@@ -1825,7 +1812,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 	list_for_each_entry(chain, hash_head, entry) {
 		if (chain->chain_key == chain_key) {
 cache_hit:
-			debug_atomic_inc(&chain_lookup_hits);
+			debug_atomic_inc(chain_lookup_hits);
 			if (very_verbose(class))
 				printk("\nhash chain already cached, key: "
 					"%016Lx tail class: [%p] %s\n",
@@ -1890,7 +1877,7 @@ cache_hit:
 		chain_hlocks[chain->base + j] = class - lock_classes;
 	}
 	list_add_tail_rcu(&chain->entry, hash_head);
-	debug_atomic_inc(&chain_lookup_misses);
+	debug_atomic_inc(chain_lookup_misses);
 	inc_chains();
 
 	return 1;
@@ -2311,7 +2298,7 @@ void trace_hardirqs_on_caller(unsigned long ip)
 		return;
 
 	if (unlikely(curr->hardirqs_enabled)) {
-		debug_atomic_inc(&redundant_hardirqs_on);
+		debug_atomic_inc(redundant_hardirqs_on);
 		return;
 	}
 	/* we'll do an OFF -> ON transition: */
@@ -2338,7 +2325,7 @@ void trace_hardirqs_on_caller(unsigned long ip)
 
 	curr->hardirq_enable_ip = ip;
 	curr->hardirq_enable_event = ++curr->irq_events;
-	debug_atomic_inc(&hardirqs_on_events);
+	debug_atomic_inc(hardirqs_on_events);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
 
@@ -2370,9 +2357,9 @@ void trace_hardirqs_off_caller(unsigned long ip)
 		curr->hardirqs_enabled = 0;
 		curr->hardirq_disable_ip = ip;
 		curr->hardirq_disable_event = ++curr->irq_events;
-		debug_atomic_inc(&hardirqs_off_events);
+		debug_atomic_inc(hardirqs_off_events);
 	} else
-		debug_atomic_inc(&redundant_hardirqs_off);
+		debug_atomic_inc(redundant_hardirqs_off);
 }
 EXPORT_SYMBOL(trace_hardirqs_off_caller);
 
@@ -2396,7 +2383,7 @@ void trace_softirqs_on(unsigned long ip)
 		return;
 
 	if (curr->softirqs_enabled) {
-		debug_atomic_inc(&redundant_softirqs_on);
+		debug_atomic_inc(redundant_softirqs_on);
 		return;
 	}
 
@@ -2406,7 +2393,7 @@ void trace_softirqs_on(unsigned long ip)
 	curr->softirqs_enabled = 1;
 	curr->softirq_enable_ip = ip;
 	curr->softirq_enable_event = ++curr->irq_events;
-	debug_atomic_inc(&softirqs_on_events);
+	debug_atomic_inc(softirqs_on_events);
 	/*
 	 * We are going to turn softirqs on, so set the
 	 * usage bit for all held locks, if hardirqs are
@@ -2436,10 +2423,10 @@ void trace_softirqs_off(unsigned long ip)
 		curr->softirqs_enabled = 0;
 		curr->softirq_disable_ip = ip;
 		curr->softirq_disable_event = ++curr->irq_events;
-		debug_atomic_inc(&softirqs_off_events);
+		debug_atomic_inc(softirqs_off_events);
 		DEBUG_LOCKS_WARN_ON(!softirq_count());
 	} else
-		debug_atomic_inc(&redundant_softirqs_off);
+		debug_atomic_inc(redundant_softirqs_off);
 }
 
 static void __lockdep_trace_alloc(gfp_t gfp_mask, unsigned long flags)
@@ -2644,7 +2631,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			return 0;
 		break;
 	case LOCK_USED:
-		debug_atomic_dec(&nr_unused_locks);
+		debug_atomic_dec(nr_unused_locks);
 		break;
 	default:
 		if (!debug_locks_off_graph_unlock())
@@ -2750,7 +2737,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 		if (!class)
 			return 0;
 	}
-	debug_atomic_inc((atomic_t *)&class->ops);
+	atomic_inc((atomic_t *)&class->ops);
 	if (very_verbose(class)) {
 		printk("\nacquire class [%p] %s", class->key, class->name);
 		if (class->name_version > 1)
diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h
index a2ee95ad1313..8d7d4b6c741a 100644
--- a/kernel/lockdep_internals.h
+++ b/kernel/lockdep_internals.h
@@ -110,29 +110,61 @@ lockdep_count_backward_deps(struct lock_class *class)
 #endif
 
 #ifdef CONFIG_DEBUG_LOCKDEP
+
+#include <asm/local.h>
 /*
- * Various lockdep statistics:
+ * Various lockdep statistics.
+ * We want them per cpu as they are often accessed in fast path
+ * and we want to avoid too much cache bouncing.
  */
-extern atomic_t chain_lookup_hits;
-extern atomic_t chain_lookup_misses;
-extern atomic_t hardirqs_on_events;
-extern atomic_t hardirqs_off_events;
-extern atomic_t redundant_hardirqs_on;
-extern atomic_t redundant_hardirqs_off;
-extern atomic_t softirqs_on_events;
-extern atomic_t softirqs_off_events;
-extern atomic_t redundant_softirqs_on;
-extern atomic_t redundant_softirqs_off;
-extern atomic_t nr_unused_locks;
-extern atomic_t nr_cyclic_checks;
-extern atomic_t nr_cyclic_check_recursions;
-extern atomic_t nr_find_usage_forwards_checks;
-extern atomic_t nr_find_usage_forwards_recursions;
-extern atomic_t nr_find_usage_backwards_checks;
-extern atomic_t nr_find_usage_backwards_recursions;
-# define debug_atomic_inc(ptr)		atomic_inc(ptr)
-# define debug_atomic_dec(ptr)		atomic_dec(ptr)
-# define debug_atomic_read(ptr)		atomic_read(ptr)
+struct lockdep_stats {
+	int	chain_lookup_hits;
+	int	chain_lookup_misses;
+	int	hardirqs_on_events;
+	int	hardirqs_off_events;
+	int	redundant_hardirqs_on;
+	int	redundant_hardirqs_off;
+	int	softirqs_on_events;
+	int	softirqs_off_events;
+	int	redundant_softirqs_on;
+	int	redundant_softirqs_off;
+	int	nr_unused_locks;
+	int	nr_cyclic_checks;
+	int	nr_cyclic_check_recursions;
+	int	nr_find_usage_forwards_checks;
+	int	nr_find_usage_forwards_recursions;
+	int	nr_find_usage_backwards_checks;
+	int	nr_find_usage_backwards_recursions;
+};
+
+DECLARE_PER_CPU(struct lockdep_stats, lockdep_stats);
+
+#define debug_atomic_inc(ptr)			{		\
+	struct lockdep_stats *__cpu_lockdep_stats;		\
+								\
+	WARN_ON_ONCE(!irqs_disabled());				\
+	__cpu_lockdep_stats = &__get_cpu_var(lockdep_stats);	\
+	__cpu_lockdep_stats->ptr++;				\
+}
+
+#define debug_atomic_dec(ptr)			{		\
+	struct lockdep_stats *__cpu_lockdep_stats;		\
+								\
+	WARN_ON_ONCE(!irqs_disabled());				\
+	__cpu_lockdep_stats = &__get_cpu_var(lockdep_stats);	\
+	__cpu_lockdep_stats->ptr--;				\
+}
+
+#define debug_atomic_read(ptr)		({				\
+	struct lockdep_stats *__cpu_lockdep_stats;			\
+	unsigned long long __total = 0;					\
+	int __cpu;							\
+	for_each_possible_cpu(__cpu) {					\
+		__cpu_lockdep_stats = &per_cpu(lockdep_stats, __cpu);	\
+		__total += __cpu_lockdep_stats->ptr;			\
+	}								\
+	__total;							\
+})
 #else
 # define debug_atomic_inc(ptr)		do { } while (0)
 # define debug_atomic_dec(ptr)		do { } while (0)
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index d4aba4f3584c..59b76c8ce9d7 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -184,34 +184,34 @@ static const struct file_operations proc_lockdep_chains_operations = {
 static void lockdep_stats_debug_show(struct seq_file *m)
 {
 #ifdef CONFIG_DEBUG_LOCKDEP
-	unsigned int hi1 = debug_atomic_read(&hardirqs_on_events),
-		     hi2 = debug_atomic_read(&hardirqs_off_events),
-		     hr1 = debug_atomic_read(&redundant_hardirqs_on),
-		     hr2 = debug_atomic_read(&redundant_hardirqs_off),
-		     si1 = debug_atomic_read(&softirqs_on_events),
-		     si2 = debug_atomic_read(&softirqs_off_events),
-		     sr1 = debug_atomic_read(&redundant_softirqs_on),
-		     sr2 = debug_atomic_read(&redundant_softirqs_off);
-
-	seq_printf(m, " chain lookup misses:           %11u\n",
-		debug_atomic_read(&chain_lookup_misses));
-	seq_printf(m, " chain lookup hits:             %11u\n",
-		debug_atomic_read(&chain_lookup_hits));
-	seq_printf(m, " cyclic checks:                 %11u\n",
-		debug_atomic_read(&nr_cyclic_checks));
-	seq_printf(m, " find-mask forwards checks:     %11u\n",
-		debug_atomic_read(&nr_find_usage_forwards_checks));
-	seq_printf(m, " find-mask backwards checks:    %11u\n",
-		debug_atomic_read(&nr_find_usage_backwards_checks));
-
-	seq_printf(m, " hardirq on events:             %11u\n", hi1);
-	seq_printf(m, " hardirq off events:            %11u\n", hi2);
-	seq_printf(m, " redundant hardirq ons:         %11u\n", hr1);
-	seq_printf(m, " redundant hardirq offs:        %11u\n", hr2);
-	seq_printf(m, " softirq on events:             %11u\n", si1);
-	seq_printf(m, " softirq off events:            %11u\n", si2);
-	seq_printf(m, " redundant softirq ons:         %11u\n", sr1);
-	seq_printf(m, " redundant softirq offs:        %11u\n", sr2);
+	unsigned long long hi1 = debug_atomic_read(hardirqs_on_events),
+			   hi2 = debug_atomic_read(hardirqs_off_events),
+			   hr1 = debug_atomic_read(redundant_hardirqs_on),
+			   hr2 = debug_atomic_read(redundant_hardirqs_off),
+			   si1 = debug_atomic_read(softirqs_on_events),
+			   si2 = debug_atomic_read(softirqs_off_events),
+			   sr1 = debug_atomic_read(redundant_softirqs_on),
+			   sr2 = debug_atomic_read(redundant_softirqs_off);
+
+	seq_printf(m, " chain lookup misses:           %11llu\n",
+		debug_atomic_read(chain_lookup_misses));
+	seq_printf(m, " chain lookup hits:             %11llu\n",
+		debug_atomic_read(chain_lookup_hits));
+	seq_printf(m, " cyclic checks:                 %11llu\n",
+		debug_atomic_read(nr_cyclic_checks));
+	seq_printf(m, " find-mask forwards checks:     %11llu\n",
+		debug_atomic_read(nr_find_usage_forwards_checks));
+	seq_printf(m, " find-mask backwards checks:    %11llu\n",
+		debug_atomic_read(nr_find_usage_backwards_checks));
+
+	seq_printf(m, " hardirq on events:             %11llu\n", hi1);
+	seq_printf(m, " hardirq off events:            %11llu\n", hi2);
+	seq_printf(m, " redundant hardirq ons:         %11llu\n", hr1);
+	seq_printf(m, " redundant hardirq offs:        %11llu\n", hr2);
+	seq_printf(m, " softirq on events:             %11llu\n", si1);
+	seq_printf(m, " softirq off events:            %11llu\n", si2);
+	seq_printf(m, " redundant softirq ons:         %11llu\n", sr1);
+	seq_printf(m, " redundant softirq offs:        %11llu\n", sr2);
 #endif
 }
 
@@ -263,7 +263,7 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 #endif
 	}
 #ifdef CONFIG_DEBUG_LOCKDEP
-	DEBUG_LOCKS_WARN_ON(debug_atomic_read(&nr_unused_locks) != nr_unused);
+	DEBUG_LOCKS_WARN_ON(debug_atomic_read(nr_unused_locks) != nr_unused);
 #endif
 	seq_printf(m, " lock-classes:                  %11lu [max: %lu]\n",
 			nr_lock_classes, MAX_LOCKDEP_KEYS);
diff --git a/kernel/module.c b/kernel/module.c
index aced6720b0e9..8ae93db591a6 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -59,8 +59,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/module.h>
 
-EXPORT_TRACEPOINT_SYMBOL(module_get);
-
 #if 0
 #define DEBUGP printk
 #else
@@ -519,6 +517,9 @@ MODINFO_ATTR(srcversion);
 static char last_unloaded_module[MODULE_NAME_LEN+1];
 
 #ifdef CONFIG_MODULE_UNLOAD
+
+EXPORT_TRACEPOINT_SYMBOL(module_get);
+
 /* Init the unload section of the module. */
 static void module_unload_init(struct module *mod)
 {
@@ -864,8 +865,7 @@ void module_put(struct module *module)
 		smp_wmb(); /* see comment in module_refcount */
 		__this_cpu_inc(module->refptr->decs);
 
-		trace_module_put(module, _RET_IP_,
-				 __this_cpu_read(module->refptr->decs));
+		trace_module_put(module, _RET_IP_);
 		/* Maybe they're waiting for us to drop reference? */
 		if (unlikely(!module_is_live(module)))
 			wake_up_process(module->waiter);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 2f3fbf84215a..fcf42dcd6089 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1367,6 +1367,8 @@ void perf_event_task_sched_in(struct task_struct *task)
 	if (cpuctx->task_ctx == ctx)
 		return;
 
+	perf_disable();
+
 	/*
 	 * We want to keep the following priority order:
 	 * cpu pinned (that don't need to move), task pinned,
@@ -1379,6 +1381,8 @@ void perf_event_task_sched_in(struct task_struct *task)
 	ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE);
 
 	cpuctx->task_ctx = ctx;
+
+	perf_enable();
 }
 
 #define MAX_INTERRUPTS (~0ULL)
@@ -2642,6 +2646,7 @@ static int perf_fasync(int fd, struct file *filp, int on)
 }
 
 static const struct file_operations perf_fops = {
+	.llseek			= no_llseek,
 	.release		= perf_release,
 	.read			= perf_read,
 	.poll			= perf_poll,
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index bc7704b3a443..799f360d1475 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -11,19 +11,18 @@
 #include <trace/events/timer.h>
 
 /*
- * Called after updating RLIMIT_CPU to set timer expiration if necessary.
+ * Called after updating RLIMIT_CPU to run cpu timer and update
+ * tsk->signal->cputime_expires expiration cache if necessary. Needs
+ * siglock protection since other code may update expiration cache as
+ * well.
  */
 void update_rlimit_cpu(unsigned long rlim_new)
 {
 	cputime_t cputime = secs_to_cputime(rlim_new);
-	struct signal_struct *const sig = current->signal;
 
-	if (cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) ||
-	    cputime_gt(sig->it[CPUCLOCK_PROF].expires, cputime)) {
-		spin_lock_irq(&current->sighand->siglock);
-		set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
-		spin_unlock_irq(&current->sighand->siglock);
-	}
+	spin_lock_irq(&current->sighand->siglock);
+	set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
+	spin_unlock_irq(&current->sighand->siglock);
 }
 
 static int check_clock(const clockid_t which_clock)
@@ -548,111 +547,62 @@ static inline int expires_gt(cputime_t expires, cputime_t new_exp)
 	       cputime_gt(expires, new_exp);
 }
 
-static inline int expires_le(cputime_t expires, cputime_t new_exp)
-{
-	return !cputime_eq(expires, cputime_zero) &&
-	       cputime_le(expires, new_exp);
-}
 /*
  * Insert the timer on the appropriate list before any timers that
  * expire later.  This must be called with the tasklist_lock held
- * for reading, and interrupts disabled.
+ * for reading, interrupts disabled and p->sighand->siglock taken.
  */
-static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
+static void arm_timer(struct k_itimer *timer)
 {
 	struct task_struct *p = timer->it.cpu.task;
 	struct list_head *head, *listpos;
+	struct task_cputime *cputime_expires;
 	struct cpu_timer_list *const nt = &timer->it.cpu;
 	struct cpu_timer_list *next;
-	unsigned long i;
 
-	head = (CPUCLOCK_PERTHREAD(timer->it_clock) ?
-		p->cpu_timers : p->signal->cpu_timers);
+	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+		head = p->cpu_timers;
+		cputime_expires = &p->cputime_expires;
+	} else {
+		head = p->signal->cpu_timers;
+		cputime_expires = &p->signal->cputime_expires;
+	}
 	head += CPUCLOCK_WHICH(timer->it_clock);
 
-	BUG_ON(!irqs_disabled());
-	spin_lock(&p->sighand->siglock);
-
 	listpos = head;
-	if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) {
-		list_for_each_entry(next, head, entry) {
-			if (next->expires.sched > nt->expires.sched)
-				break;
-			listpos = &next->entry;
-		}
-	} else {
-		list_for_each_entry(next, head, entry) {
-			if (cputime_gt(next->expires.cpu, nt->expires.cpu))
-				break;
-			listpos = &next->entry;
-		}
+	list_for_each_entry(next, head, entry) {
+		if (cpu_time_before(timer->it_clock, nt->expires, next->expires))
+			break;
+		listpos = &next->entry;
 	}
 	list_add(&nt->entry, listpos);
 
 	if (listpos == head) {
+		union cpu_time_count *exp = &nt->expires;
+
 		/*
-		 * We are the new earliest-expiring timer.
-		 * If we are a thread timer, there can always
-		 * be a process timer telling us to stop earlier.
+		 * We are the new earliest-expiring POSIX 1.b timer, hence
+		 * need to update expiration cache. Take into account that
+		 * for process timers we share expiration cache with itimers
+		 * and RLIMIT_CPU and for thread timers with RLIMIT_RTTIME.
 		 */
 
-		if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
-			union cpu_time_count *exp = &nt->expires;
-
-			switch (CPUCLOCK_WHICH(timer->it_clock)) {
-			default:
-				BUG();
-			case CPUCLOCK_PROF:
-				if (expires_gt(p->cputime_expires.prof_exp,
-					       exp->cpu))
-					p->cputime_expires.prof_exp = exp->cpu;
-				break;
-			case CPUCLOCK_VIRT:
-				if (expires_gt(p->cputime_expires.virt_exp,
-					       exp->cpu))
-					p->cputime_expires.virt_exp = exp->cpu;
-				break;
-			case CPUCLOCK_SCHED:
-				if (p->cputime_expires.sched_exp == 0 ||
-				    p->cputime_expires.sched_exp > exp->sched)
-					p->cputime_expires.sched_exp =
-								exp->sched;
-				break;
-			}
-		} else {
-			struct signal_struct *const sig = p->signal;
-			union cpu_time_count *exp = &timer->it.cpu.expires;
-
-			/*
-			 * For a process timer, set the cached expiration time.
-			 */
-			switch (CPUCLOCK_WHICH(timer->it_clock)) {
-			default:
-				BUG();
-			case CPUCLOCK_VIRT:
-				if (expires_le(sig->it[CPUCLOCK_VIRT].expires,
-					       exp->cpu))
-					break;
-				sig->cputime_expires.virt_exp = exp->cpu;
-				break;
-			case CPUCLOCK_PROF:
-				if (expires_le(sig->it[CPUCLOCK_PROF].expires,
-					       exp->cpu))
-					break;
-				i = sig->rlim[RLIMIT_CPU].rlim_cur;
-				if (i != RLIM_INFINITY &&
-				    i <= cputime_to_secs(exp->cpu))
-					break;
-				sig->cputime_expires.prof_exp = exp->cpu;
-				break;
-			case CPUCLOCK_SCHED:
-				sig->cputime_expires.sched_exp = exp->sched;
-				break;
-			}
+		switch (CPUCLOCK_WHICH(timer->it_clock)) {
+		case CPUCLOCK_PROF:
+			if (expires_gt(cputime_expires->prof_exp, exp->cpu))
+				cputime_expires->prof_exp = exp->cpu;
+			break;
+		case CPUCLOCK_VIRT:
+			if (expires_gt(cputime_expires->virt_exp, exp->cpu))
+				cputime_expires->virt_exp = exp->cpu;
+			break;
+		case CPUCLOCK_SCHED:
+			if (cputime_expires->sched_exp == 0 ||
+			    cputime_expires->sched_exp > exp->sched)
+				cputime_expires->sched_exp = exp->sched;
+			break;
 		}
 	}
-
-	spin_unlock(&p->sighand->siglock);
 }
 
 /*
@@ -660,7 +610,12 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
  */
 static void cpu_timer_fire(struct k_itimer *timer)
 {
-	if (unlikely(timer->sigq == NULL)) {
+	if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) {
+		/*
+		 * User don't want any signal.
+		 */
+		timer->it.cpu.expires.sched = 0;
+	} else if (unlikely(timer->sigq == NULL)) {
 		/*
 		 * This a special case for clock_nanosleep,
 		 * not a normal timer from sys_timer_create.
@@ -721,7 +676,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 			struct itimerspec *new, struct itimerspec *old)
 {
 	struct task_struct *p = timer->it.cpu.task;
-	union cpu_time_count old_expires, new_expires, val;
+	union cpu_time_count old_expires, new_expires, old_incr, val;
 	int ret;
 
 	if (unlikely(p == NULL)) {
@@ -752,6 +707,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	BUG_ON(!irqs_disabled());
 
 	ret = 0;
+	old_incr = timer->it.cpu.incr;
 	spin_lock(&p->sighand->siglock);
 	old_expires = timer->it.cpu.expires;
 	if (unlikely(timer->it.cpu.firing)) {
@@ -759,7 +715,6 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 		ret = TIMER_RETRY;
 	} else
 		list_del_init(&timer->it.cpu.entry);
-	spin_unlock(&p->sighand->siglock);
 
 	/*
 	 * We need to sample the current value to convert the new
@@ -813,6 +768,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 		 * disable this firing since we are already reporting
 		 * it as an overrun (thanks to bump_cpu_timer above).
 		 */
+		spin_unlock(&p->sighand->siglock);
 		read_unlock(&tasklist_lock);
 		goto out;
 	}
@@ -828,11 +784,11 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	 */
 	timer->it.cpu.expires = new_expires;
 	if (new_expires.sched != 0 &&
-	    (timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE &&
 	    cpu_time_before(timer->it_clock, val, new_expires)) {
-		arm_timer(timer, val);
+		arm_timer(timer);
 	}
 
+	spin_unlock(&p->sighand->siglock);
 	read_unlock(&tasklist_lock);
 
 	/*
@@ -853,7 +809,6 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	timer->it_overrun = -1;
 
 	if (new_expires.sched != 0 &&
-	    (timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE &&
 	    !cpu_time_before(timer->it_clock, val, new_expires)) {
 		/*
 		 * The designated time already passed, so we notify
@@ -867,7 +822,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
  out:
 	if (old) {
 		sample_to_timespec(timer->it_clock,
-				   timer->it.cpu.incr, &old->it_interval);
+				   old_incr, &old->it_interval);
 	}
 	return ret;
 }
@@ -927,25 +882,6 @@ void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 		read_unlock(&tasklist_lock);
 	}
 
-	if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) {
-		if (timer->it.cpu.incr.sched == 0 &&
-		    cpu_time_before(timer->it_clock,
-				    timer->it.cpu.expires, now)) {
-			/*
-			 * Do-nothing timer expired and has no reload,
-			 * so it's as if it was never set.
-			 */
-			timer->it.cpu.expires.sched = 0;
-			itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
-			return;
-		}
-		/*
-		 * Account for any expirations and reloads that should
-		 * have happened.
-		 */
-		bump_cpu_timer(timer, now);
-	}
-
 	if (unlikely(clear_dead)) {
 		/*
 		 * We've noticed that the thread is dead, but
@@ -1270,6 +1206,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 			goto out;
 		}
 		read_lock(&tasklist_lock); /* arm_timer needs it.  */
+		spin_lock(&p->sighand->siglock);
 	} else {
 		read_lock(&tasklist_lock);
 		if (unlikely(p->signal == NULL)) {
@@ -1290,6 +1227,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 			clear_dead_task(timer, now);
 			goto out_unlock;
 		}
+		spin_lock(&p->sighand->siglock);
 		cpu_timer_sample_group(timer->it_clock, p, &now);
 		bump_cpu_timer(timer, now);
 		/* Leave the tasklist_lock locked for the call below.  */
@@ -1298,7 +1236,9 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	/*
 	 * Now re-arm for the new expiry time.
 	 */
-	arm_timer(timer, now);
+	BUG_ON(!irqs_disabled());
+	arm_timer(timer);
+	spin_unlock(&p->sighand->siglock);
 
 out_unlock:
 	read_unlock(&tasklist_lock);
@@ -1390,7 +1330,7 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
 			return 1;
 	}
 
-	return sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY;
+	return 0;
 }
 
 /*
@@ -1456,21 +1396,23 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 }
 
 /*
- * Set one of the process-wide special case CPU timers.
+ * Set one of the process-wide special case CPU timers or RLIMIT_CPU.
  * The tsk->sighand->siglock must be held by the caller.
- * The *newval argument is relative and we update it to be absolute, *oldval
- * is absolute and we update it to be relative.
  */
 void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 			   cputime_t *newval, cputime_t *oldval)
 {
 	union cpu_time_count now;
-	struct list_head *head;
 
 	BUG_ON(clock_idx == CPUCLOCK_SCHED);
 	cpu_timer_sample_group(clock_idx, tsk, &now);
 
 	if (oldval) {
+		/*
+		 * We are setting itimer. The *oldval is absolute and we update
+		 * it to be relative, *newval argument is relative and we update
+		 * it to be absolute.
+		 */
 		if (!cputime_eq(*oldval, cputime_zero)) {
 			if (cputime_le(*oldval, now.cpu)) {
 				/* Just about to fire. */
@@ -1483,33 +1425,21 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 		if (cputime_eq(*newval, cputime_zero))
 			return;
 		*newval = cputime_add(*newval, now.cpu);
-
-		/*
-		 * If the RLIMIT_CPU timer will expire before the
-		 * ITIMER_PROF timer, we have nothing else to do.
-		 */
-		if (tsk->signal->rlim[RLIMIT_CPU].rlim_cur
-		    < cputime_to_secs(*newval))
-			return;
 	}
 
 	/*
-	 * Check whether there are any process timers already set to fire
-	 * before this one.  If so, we don't have anything more to do.
+	 * Update expiration cache if we are the earliest timer, or eventually
+	 * RLIMIT_CPU limit is earlier than prof_exp cpu timer expire.
 	 */
-	head = &tsk->signal->cpu_timers[clock_idx];
-	if (list_empty(head) ||
-	    cputime_ge(list_first_entry(head,
-				  struct cpu_timer_list, entry)->expires.cpu,
-		       *newval)) {
-		switch (clock_idx) {
-		case CPUCLOCK_PROF:
+	switch (clock_idx) {
+	case CPUCLOCK_PROF:
+		if (expires_gt(tsk->signal->cputime_expires.prof_exp, *newval))
 			tsk->signal->cputime_expires.prof_exp = *newval;
-			break;
-		case CPUCLOCK_VIRT:
+		break;
+	case CPUCLOCK_VIRT:
+		if (expires_gt(tsk->signal->cputime_expires.virt_exp, *newval))
 			tsk->signal->cputime_expires.virt_exp = *newval;
-			break;
-		}
+		break;
 	}
 }
 
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 42ad8ae729a0..9fb51237b18c 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -76,7 +76,6 @@ void __ptrace_unlink(struct task_struct *child)
 	child->parent = child->real_parent;
 	list_del_init(&child->ptrace_entry);
 
-	arch_ptrace_untrace(child);
 	if (task_is_traced(child))
 		ptrace_untrace(child);
 }
diff --git a/kernel/sched.c b/kernel/sched.c
index eadb6ab0a219..1204388b762f 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -493,8 +493,11 @@ struct rq {
 	#define CPU_LOAD_IDX_MAX 5
 	unsigned long cpu_load[CPU_LOAD_IDX_MAX];
 #ifdef CONFIG_NO_HZ
+	u64 nohz_stamp;
 	unsigned char in_nohz_recently;
 #endif
+	unsigned int skip_clock_update;
+
 	/* capture load from *all* tasks on this cpu: */
 	struct load_weight load;
 	unsigned long nr_load_updates;
@@ -592,6 +595,13 @@ static inline
 void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 {
 	rq->curr->sched_class->check_preempt_curr(rq, p, flags);
+
+	/*
+	 * A queue event has occurred, and we're going to schedule.  In
+	 * this case, we can save a useless back to back clock update.
+	 */
+	if (test_tsk_need_resched(p))
+		rq->skip_clock_update = 1;
 }
 
 static inline int cpu_of(struct rq *rq)
@@ -626,7 +636,8 @@ static inline int cpu_of(struct rq *rq)
 
 inline void update_rq_clock(struct rq *rq)
 {
-	rq->clock = sched_clock_cpu(cpu_of(rq));
+	if (!rq->skip_clock_update)
+		rq->clock = sched_clock_cpu(cpu_of(rq));
 }
 
 /*
@@ -904,16 +915,12 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 #endif /* __ARCH_WANT_UNLOCKED_CTXSW */
 
 /*
- * Check whether the task is waking, we use this to synchronize against
- * ttwu() so that task_cpu() reports a stable number.
- *
- * We need to make an exception for PF_STARTING tasks because the fork
- * path might require task_rq_lock() to work, eg. it can call
- * set_cpus_allowed_ptr() from the cpuset clone_ns code.
+ * Check whether the task is waking, we use this to synchronize ->cpus_allowed
+ * against ttwu().
  */
 static inline int task_is_waking(struct task_struct *p)
 {
-	return unlikely((p->state == TASK_WAKING) && !(p->flags & PF_STARTING));
+	return unlikely(p->state == TASK_WAKING);
 }
 
 /*
@@ -926,11 +933,9 @@ static inline struct rq *__task_rq_lock(struct task_struct *p)
 	struct rq *rq;
 
 	for (;;) {
-		while (task_is_waking(p))
-			cpu_relax();
 		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p) && !task_is_waking(p)))
+		if (likely(rq == task_rq(p)))
 			return rq;
 		raw_spin_unlock(&rq->lock);
 	}
@@ -947,12 +952,10 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
 	struct rq *rq;
 
 	for (;;) {
-		while (task_is_waking(p))
-			cpu_relax();
 		local_irq_save(*flags);
 		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p) && !task_is_waking(p)))
+		if (likely(rq == task_rq(p)))
 			return rq;
 		raw_spin_unlock_irqrestore(&rq->lock, *flags);
 	}
@@ -1229,6 +1232,17 @@ void wake_up_idle_cpu(int cpu)
 	if (!tsk_is_polling(rq->idle))
 		smp_send_reschedule(cpu);
 }
+
+int nohz_ratelimit(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	u64 diff = rq->clock - rq->nohz_stamp;
+
+	rq->nohz_stamp = rq->clock;
+
+	return diff < (NSEC_PER_SEC / HZ) >> 1;
+}
+
 #endif /* CONFIG_NO_HZ */
 
 static u64 sched_avg_period(void)
@@ -1771,8 +1785,6 @@ static void double_rq_lock(struct rq *rq1, struct rq *rq2)
 			raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
 		}
 	}
-	update_rq_clock(rq1);
-	update_rq_clock(rq2);
 }
 
 /*
@@ -1866,56 +1878,43 @@ static void update_avg(u64 *avg, u64 sample)
 	*avg += diff >> 3;
 }
 
-static void
-enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head)
+static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	if (wakeup)
-		p->se.start_runtime = p->se.sum_exec_runtime;
-
+	update_rq_clock(rq);
 	sched_info_queued(p);
-	p->sched_class->enqueue_task(rq, p, wakeup, head);
+	p->sched_class->enqueue_task(rq, p, flags);
 	p->se.on_rq = 1;
 }
 
-static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
+static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	if (sleep) {
-		if (p->se.last_wakeup) {
-			update_avg(&p->se.avg_overlap,
-				p->se.sum_exec_runtime - p->se.last_wakeup);
-			p->se.last_wakeup = 0;
-		} else {
-			update_avg(&p->se.avg_wakeup,
-				sysctl_sched_wakeup_granularity);
-		}
-	}
-
+	update_rq_clock(rq);
 	sched_info_dequeued(p);
-	p->sched_class->dequeue_task(rq, p, sleep);
+	p->sched_class->dequeue_task(rq, p, flags);
 	p->se.on_rq = 0;
 }
 
 /*
  * activate_task - move a task to the runqueue.
  */
-static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
+static void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (task_contributes_to_load(p))
 		rq->nr_uninterruptible--;
 
-	enqueue_task(rq, p, wakeup, false);
+	enqueue_task(rq, p, flags);
 	inc_nr_running(rq);
 }
 
 /*
  * deactivate_task - remove a task from the runqueue.
  */
-static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
+static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (task_contributes_to_load(p))
 		rq->nr_uninterruptible++;
 
-	dequeue_task(rq, p, sleep);
+	dequeue_task(rq, p, flags);
 	dec_nr_running(rq);
 }
 
@@ -2078,49 +2077,6 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
 }
 
 /*
- * wait_task_context_switch -	wait for a thread to complete at least one
- *				context switch.
- *
- * @p must not be current.
- */
-void wait_task_context_switch(struct task_struct *p)
-{
-	unsigned long nvcsw, nivcsw, flags;
-	int running;
-	struct rq *rq;
-
-	nvcsw	= p->nvcsw;
-	nivcsw	= p->nivcsw;
-	for (;;) {
-		/*
-		 * The runqueue is assigned before the actual context
-		 * switch. We need to take the runqueue lock.
-		 *
-		 * We could check initially without the lock but it is
-		 * very likely that we need to take the lock in every
-		 * iteration.
-		 */
-		rq = task_rq_lock(p, &flags);
-		running = task_running(rq, p);
-		task_rq_unlock(rq, &flags);
-
-		if (likely(!running))
-			break;
-		/*
-		 * The switch count is incremented before the actual
-		 * context switch. We thus wait for two switches to be
-		 * sure at least one completed.
-		 */
-		if ((p->nvcsw - nvcsw) > 1)
-			break;
-		if ((p->nivcsw - nivcsw) > 1)
-			break;
-
-		cpu_relax();
-	}
-}
-
-/*
  * wait_task_inactive - wait for a thread to unschedule.
  *
  * If @match_state is nonzero, it's the @p->state value just checked and
@@ -2273,6 +2229,9 @@ void task_oncpu_function_call(struct task_struct *p,
 }
 
 #ifdef CONFIG_SMP
+/*
+ * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held.
+ */
 static int select_fallback_rq(int cpu, struct task_struct *p)
 {
 	int dest_cpu;
@@ -2289,12 +2248,8 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 		return dest_cpu;
 
 	/* No more Mr. Nice Guy. */
-	if (dest_cpu >= nr_cpu_ids) {
-		rcu_read_lock();
-		cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
-		rcu_read_unlock();
-		dest_cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
-
+	if (unlikely(dest_cpu >= nr_cpu_ids)) {
+		dest_cpu = cpuset_cpus_allowed_fallback(p);
 		/*
 		 * Don't tell them about moving exiting tasks or
 		 * kernel threads (both mm NULL), since they never
@@ -2311,17 +2266,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 }
 
 /*
- * Gets called from 3 sites (exec, fork, wakeup), since it is called without
- * holding rq->lock we need to ensure ->cpus_allowed is stable, this is done
- * by:
- *
- *  exec:           is unstable, retry loop
- *  fork & wake-up: serialize ->cpus_allowed against TASK_WAKING
+ * The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable.
  */
 static inline
-int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
+int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags)
 {
-	int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);
+	int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags);
 
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need
@@ -2360,16 +2310,13 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 {
 	int cpu, orig_cpu, this_cpu, success = 0;
 	unsigned long flags;
+	unsigned long en_flags = ENQUEUE_WAKEUP;
 	struct rq *rq;
 
-	if (!sched_feat(SYNC_WAKEUPS))
-		wake_flags &= ~WF_SYNC;
-
 	this_cpu = get_cpu();
 
 	smp_wmb();
 	rq = task_rq_lock(p, &flags);
-	update_rq_clock(rq);
 	if (!(p->state & state))
 		goto out;
 
@@ -2389,28 +2336,26 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 	 *
 	 * First fix up the nr_uninterruptible count:
 	 */
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible--;
+	if (task_contributes_to_load(p)) {
+		if (likely(cpu_online(orig_cpu)))
+			rq->nr_uninterruptible--;
+		else
+			this_rq()->nr_uninterruptible--;
+	}
 	p->state = TASK_WAKING;
 
-	if (p->sched_class->task_waking)
+	if (p->sched_class->task_waking) {
 		p->sched_class->task_waking(rq, p);
+		en_flags |= ENQUEUE_WAKING;
+	}
 
-	__task_rq_unlock(rq);
-
-	cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
-	if (cpu != orig_cpu) {
-		/*
-		 * Since we migrate the task without holding any rq->lock,
-		 * we need to be careful with task_rq_lock(), since that
-		 * might end up locking an invalid rq.
-		 */
+	cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags);
+	if (cpu != orig_cpu)
 		set_task_cpu(p, cpu);
-	}
+	__task_rq_unlock(rq);
 
 	rq = cpu_rq(cpu);
 	raw_spin_lock(&rq->lock);
-	update_rq_clock(rq);
 
 	/*
 	 * We migrated the task without holding either rq->lock, however
@@ -2438,34 +2383,18 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 
 out_activate:
 #endif /* CONFIG_SMP */
-	schedstat_inc(p, se.nr_wakeups);
+	schedstat_inc(p, se.statistics.nr_wakeups);
 	if (wake_flags & WF_SYNC)
-		schedstat_inc(p, se.nr_wakeups_sync);
+		schedstat_inc(p, se.statistics.nr_wakeups_sync);
 	if (orig_cpu != cpu)
-		schedstat_inc(p, se.nr_wakeups_migrate);
+		schedstat_inc(p, se.statistics.nr_wakeups_migrate);
 	if (cpu == this_cpu)
-		schedstat_inc(p, se.nr_wakeups_local);
+		schedstat_inc(p, se.statistics.nr_wakeups_local);
 	else
-		schedstat_inc(p, se.nr_wakeups_remote);
-	activate_task(rq, p, 1);
+		schedstat_inc(p, se.statistics.nr_wakeups_remote);
+	activate_task(rq, p, en_flags);
 	success = 1;
 
-	/*
-	 * Only attribute actual wakeups done by this task.
-	 */
-	if (!in_interrupt()) {
-		struct sched_entity *se = &current->se;
-		u64 sample = se->sum_exec_runtime;
-
-		if (se->last_wakeup)
-			sample -= se->last_wakeup;
-		else
-			sample -= se->start_runtime;
-		update_avg(&se->avg_wakeup, sample);
-
-		se->last_wakeup = se->sum_exec_runtime;
-	}
-
 out_running:
 	trace_sched_wakeup(rq, p, success);
 	check_preempt_curr(rq, p, wake_flags);
@@ -2527,42 +2456,9 @@ static void __sched_fork(struct task_struct *p)
 	p->se.sum_exec_runtime		= 0;
 	p->se.prev_sum_exec_runtime	= 0;
 	p->se.nr_migrations		= 0;
-	p->se.last_wakeup		= 0;
-	p->se.avg_overlap		= 0;
-	p->se.start_runtime		= 0;
-	p->se.avg_wakeup		= sysctl_sched_wakeup_granularity;
 
 #ifdef CONFIG_SCHEDSTATS
-	p->se.wait_start			= 0;
-	p->se.wait_max				= 0;
-	p->se.wait_count			= 0;
-	p->se.wait_sum				= 0;
-
-	p->se.sleep_start			= 0;
-	p->se.sleep_max				= 0;
-	p->se.sum_sleep_runtime			= 0;
-
-	p->se.block_start			= 0;
-	p->se.block_max				= 0;
-	p->se.exec_max				= 0;
-	p->se.slice_max				= 0;
-
-	p->se.nr_migrations_cold		= 0;
-	p->se.nr_failed_migrations_affine	= 0;
-	p->se.nr_failed_migrations_running	= 0;
-	p->se.nr_failed_migrations_hot		= 0;
-	p->se.nr_forced_migrations		= 0;
-
-	p->se.nr_wakeups			= 0;
-	p->se.nr_wakeups_sync			= 0;
-	p->se.nr_wakeups_migrate		= 0;
-	p->se.nr_wakeups_local			= 0;
-	p->se.nr_wakeups_remote			= 0;
-	p->se.nr_wakeups_affine			= 0;
-	p->se.nr_wakeups_affine_attempts	= 0;
-	p->se.nr_wakeups_passive		= 0;
-	p->se.nr_wakeups_idle			= 0;
-
+	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 
 	INIT_LIST_HEAD(&p->rt.run_list);
@@ -2583,11 +2479,11 @@ void sched_fork(struct task_struct *p, int clone_flags)
 
 	__sched_fork(p);
 	/*
-	 * We mark the process as waking here. This guarantees that
+	 * We mark the process as running here. This guarantees that
 	 * nobody will actually run it, and a signal or other external
 	 * event cannot wake it up and insert it on the runqueue either.
 	 */
-	p->state = TASK_WAKING;
+	p->state = TASK_RUNNING;
 
 	/*
 	 * Revert to default priority/policy on fork if requested.
@@ -2654,29 +2550,25 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 	int cpu __maybe_unused = get_cpu();
 
 #ifdef CONFIG_SMP
+	rq = task_rq_lock(p, &flags);
+	p->state = TASK_WAKING;
+
 	/*
 	 * Fork balancing, do it here and not earlier because:
 	 *  - cpus_allowed can change in the fork path
 	 *  - any previously selected cpu might disappear through hotplug
 	 *
-	 * We still have TASK_WAKING but PF_STARTING is gone now, meaning
-	 * ->cpus_allowed is stable, we have preemption disabled, meaning
-	 * cpu_online_mask is stable.
+	 * We set TASK_WAKING so that select_task_rq() can drop rq->lock
+	 * without people poking at ->cpus_allowed.
 	 */
-	cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
+	cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0);
 	set_task_cpu(p, cpu);
-#endif
 
-	/*
-	 * Since the task is not on the rq and we still have TASK_WAKING set
-	 * nobody else will migrate this task.
-	 */
-	rq = cpu_rq(cpu);
-	raw_spin_lock_irqsave(&rq->lock, flags);
-
-	BUG_ON(p->state != TASK_WAKING);
 	p->state = TASK_RUNNING;
-	update_rq_clock(rq);
+	task_rq_unlock(rq, &flags);
+#endif
+
+	rq = task_rq_lock(p, &flags);
 	activate_task(rq, p, 0);
 	trace_sched_wakeup_new(rq, p, 1);
 	check_preempt_curr(rq, p, WF_FORK);
@@ -3122,32 +3014,21 @@ void sched_exec(void)
 {
 	struct task_struct *p = current;
 	struct migration_req req;
-	int dest_cpu, this_cpu;
 	unsigned long flags;
 	struct rq *rq;
-
-again:
-	this_cpu = get_cpu();
-	dest_cpu = select_task_rq(p, SD_BALANCE_EXEC, 0);
-	if (dest_cpu == this_cpu) {
-		put_cpu();
-		return;
-	}
+	int dest_cpu;
 
 	rq = task_rq_lock(p, &flags);
-	put_cpu();
+	dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0);
+	if (dest_cpu == smp_processor_id())
+		goto unlock;
 
 	/*
 	 * select_task_rq() can race against ->cpus_allowed
 	 */
-	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)
-	    || unlikely(!cpu_active(dest_cpu))) {
-		task_rq_unlock(rq, &flags);
-		goto again;
-	}
-
-	/* force the process onto the specified CPU */
-	if (migrate_task(p, dest_cpu, &req)) {
+	if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) &&
+	    likely(cpu_active(dest_cpu)) &&
+	    migrate_task(p, dest_cpu, &req)) {
 		/* Need to wait for migration thread (might exit: take ref). */
 		struct task_struct *mt = rq->migration_thread;
 
@@ -3159,6 +3040,7 @@ again:
 
 		return;
 	}
+unlock:
 	task_rq_unlock(rq, &flags);
 }
 
@@ -3630,23 +3512,9 @@ static inline void schedule_debug(struct task_struct *prev)
 
 static void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
-	if (prev->state == TASK_RUNNING) {
-		u64 runtime = prev->se.sum_exec_runtime;
-
-		runtime -= prev->se.prev_sum_exec_runtime;
-		runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
-
-		/*
-		 * In order to avoid avg_overlap growing stale when we are
-		 * indeed overlapping and hence not getting put to sleep, grow
-		 * the avg_overlap on preemption.
-		 *
-		 * We use the average preemption runtime because that
-		 * correlates to the amount of cache footprint a task can
-		 * build up.
-		 */
-		update_avg(&prev->se.avg_overlap, runtime);
-	}
+	if (prev->se.on_rq)
+		update_rq_clock(rq);
+	rq->skip_clock_update = 0;
 	prev->sched_class->put_prev_task(rq, prev);
 }
 
@@ -3709,14 +3577,13 @@ need_resched_nonpreemptible:
 		hrtick_clear(rq);
 
 	raw_spin_lock_irq(&rq->lock);
-	update_rq_clock(rq);
 	clear_tsk_need_resched(prev);
 
 	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
 		if (unlikely(signal_pending_state(prev->state, prev)))
 			prev->state = TASK_RUNNING;
 		else
-			deactivate_task(rq, prev, 1);
+			deactivate_task(rq, prev, DEQUEUE_SLEEP);
 		switch_count = &prev->nvcsw;
 	}
 
@@ -4266,7 +4133,6 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	BUG_ON(prio < 0 || prio > MAX_PRIO);
 
 	rq = task_rq_lock(p, &flags);
-	update_rq_clock(rq);
 
 	oldprio = p->prio;
 	prev_class = p->sched_class;
@@ -4287,7 +4153,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (on_rq) {
-		enqueue_task(rq, p, 0, oldprio < prio);
+		enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
 
 		check_class_changed(rq, p, prev_class, oldprio, running);
 	}
@@ -4309,7 +4175,6 @@ void set_user_nice(struct task_struct *p, long nice)
 	 * the task might be in the middle of scheduling on another CPU.
 	 */
 	rq = task_rq_lock(p, &flags);
-	update_rq_clock(rq);
 	/*
 	 * The RT priorities are set via sched_setscheduler(), but we still
 	 * allow the 'normal' nice value to be set - but as expected
@@ -4331,7 +4196,7 @@ void set_user_nice(struct task_struct *p, long nice)
 	delta = p->prio - old_prio;
 
 	if (on_rq) {
-		enqueue_task(rq, p, 0, false);
+		enqueue_task(rq, p, 0);
 		/*
 		 * If the task increased its priority or is running and
 		 * lowered its priority, then reschedule its CPU:
@@ -4592,7 +4457,6 @@ recheck:
 		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 		goto recheck;
 	}
-	update_rq_clock(rq);
 	on_rq = p->se.on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
@@ -5358,7 +5222,18 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 	struct rq *rq;
 	int ret = 0;
 
+	/*
+	 * Serialize against TASK_WAKING so that ttwu() and wunt() can
+	 * drop the rq->lock and still rely on ->cpus_allowed.
+	 */
+again:
+	while (task_is_waking(p))
+		cpu_relax();
 	rq = task_rq_lock(p, &flags);
+	if (task_is_waking(p)) {
+		task_rq_unlock(rq, &flags);
+		goto again;
+	}
 
 	if (!cpumask_intersects(new_mask, cpu_active_mask)) {
 		ret = -EINVAL;
@@ -5516,30 +5391,29 @@ static int migration_thread(void *data)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-
-static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu)
-{
-	int ret;
-
-	local_irq_disable();
-	ret = __migrate_task(p, src_cpu, dest_cpu);
-	local_irq_enable();
-	return ret;
-}
-
 /*
  * Figure out where task on dead CPU should go, use force if necessary.
  */
-static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
+void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
 {
-	int dest_cpu;
+	struct rq *rq = cpu_rq(dead_cpu);
+	int needs_cpu, uninitialized_var(dest_cpu);
+	unsigned long flags;
 
-again:
-	dest_cpu = select_fallback_rq(dead_cpu, p);
+	local_irq_save(flags);
 
-	/* It can have affinity changed while we were choosing. */
-	if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu)))
-		goto again;
+	raw_spin_lock(&rq->lock);
+	needs_cpu = (task_cpu(p) == dead_cpu) && (p->state != TASK_WAKING);
+	if (needs_cpu)
+		dest_cpu = select_fallback_rq(dead_cpu, p);
+	raw_spin_unlock(&rq->lock);
+	/*
+	 * It can only fail if we race with set_cpus_allowed(),
+	 * in the racer should migrate the task anyway.
+	 */
+	if (needs_cpu)
+		__migrate_task(p, dead_cpu, dest_cpu);
+	local_irq_restore(flags);
 }
 
 /*
@@ -5603,7 +5477,6 @@ void sched_idle_next(void)
 
 	__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
 
-	update_rq_clock(rq);
 	activate_task(rq, p, 0);
 
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
@@ -5658,7 +5531,6 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
 	for ( ; ; ) {
 		if (!rq->nr_running)
 			break;
-		update_rq_clock(rq);
 		next = pick_next_task(rq);
 		if (!next)
 			break;
@@ -5934,7 +5806,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		cpuset_lock(); /* around calls to cpuset_cpus_allowed_lock() */
 		migrate_live_tasks(cpu);
 		rq = cpu_rq(cpu);
 		kthread_stop(rq->migration_thread);
@@ -5942,13 +5813,11 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		rq->migration_thread = NULL;
 		/* Idle task back to normal (off runqueue, low prio) */
 		raw_spin_lock_irq(&rq->lock);
-		update_rq_clock(rq);
 		deactivate_task(rq, rq->idle, 0);
 		__setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
 		rq->idle->sched_class = &idle_sched_class;
 		migrate_dead_tasks(cpu);
 		raw_spin_unlock_irq(&rq->lock);
-		cpuset_unlock();
 		migrate_nr_uninterruptible(rq);
 		BUG_ON(rq->nr_running != 0);
 		calc_global_load_remove(rq);
@@ -7892,7 +7761,6 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
 {
 	int on_rq;
 
-	update_rq_clock(rq);
 	on_rq = p->se.on_rq;
 	if (on_rq)
 		deactivate_task(rq, p, 0);
@@ -7919,9 +7787,9 @@ void normalize_rt_tasks(void)
 
 		p->se.exec_start		= 0;
 #ifdef CONFIG_SCHEDSTATS
-		p->se.wait_start		= 0;
-		p->se.sleep_start		= 0;
-		p->se.block_start		= 0;
+		p->se.statistics.wait_start	= 0;
+		p->se.statistics.sleep_start	= 0;
+		p->se.statistics.block_start	= 0;
 #endif
 
 		if (!rt_task(p)) {
@@ -8257,8 +8125,6 @@ void sched_move_task(struct task_struct *tsk)
 
 	rq = task_rq_lock(tsk, &flags);
 
-	update_rq_clock(rq);
-
 	running = task_current(rq, tsk);
 	on_rq = tsk->se.on_rq;
 
@@ -8277,7 +8143,7 @@ void sched_move_task(struct task_struct *tsk)
 	if (unlikely(running))
 		tsk->sched_class->set_curr_task(rq);
 	if (on_rq)
-		enqueue_task(rq, tsk, 0, false);
+		enqueue_task(rq, tsk, 0);
 
 	task_rq_unlock(rq, &flags);
 }
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 9b49db144037..9cf1baf6616a 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -70,16 +70,16 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu,
 	PN(se->vruntime);
 	PN(se->sum_exec_runtime);
 #ifdef CONFIG_SCHEDSTATS
-	PN(se->wait_start);
-	PN(se->sleep_start);
-	PN(se->block_start);
-	PN(se->sleep_max);
-	PN(se->block_max);
-	PN(se->exec_max);
-	PN(se->slice_max);
-	PN(se->wait_max);
-	PN(se->wait_sum);
-	P(se->wait_count);
+	PN(se->statistics.wait_start);
+	PN(se->statistics.sleep_start);
+	PN(se->statistics.block_start);
+	PN(se->statistics.sleep_max);
+	PN(se->statistics.block_max);
+	PN(se->statistics.exec_max);
+	PN(se->statistics.slice_max);
+	PN(se->statistics.wait_max);
+	PN(se->statistics.wait_sum);
+	P(se->statistics.wait_count);
 #endif
 	P(se->load.weight);
 #undef PN
@@ -104,7 +104,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
 		SPLIT_NS(p->se.vruntime),
 		SPLIT_NS(p->se.sum_exec_runtime),
-		SPLIT_NS(p->se.sum_sleep_runtime));
+		SPLIT_NS(p->se.statistics.sum_sleep_runtime));
 #else
 	SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld",
 		0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
@@ -173,11 +173,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	task_group_path(tg, path, sizeof(path));
 
 	SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path);
-#elif defined(CONFIG_USER_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
-	{
-		uid_t uid = cfs_rq->tg->uid;
-		SEQ_printf(m, "\ncfs_rq[%d] for UID: %u\n", cpu, uid);
-	}
 #else
 	SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
 #endif
@@ -407,40 +402,38 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	PN(se.exec_start);
 	PN(se.vruntime);
 	PN(se.sum_exec_runtime);
-	PN(se.avg_overlap);
-	PN(se.avg_wakeup);
 
 	nr_switches = p->nvcsw + p->nivcsw;
 
 #ifdef CONFIG_SCHEDSTATS
-	PN(se.wait_start);
-	PN(se.sleep_start);
-	PN(se.block_start);
-	PN(se.sleep_max);
-	PN(se.block_max);
-	PN(se.exec_max);
-	PN(se.slice_max);
-	PN(se.wait_max);
-	PN(se.wait_sum);
-	P(se.wait_count);
-	PN(se.iowait_sum);
-	P(se.iowait_count);
+	PN(se.statistics.wait_start);
+	PN(se.statistics.sleep_start);
+	PN(se.statistics.block_start);
+	PN(se.statistics.sleep_max);
+	PN(se.statistics.block_max);
+	PN(se.statistics.exec_max);
+	PN(se.statistics.slice_max);
+	PN(se.statistics.wait_max);
+	PN(se.statistics.wait_sum);
+	P(se.statistics.wait_count);
+	PN(se.statistics.iowait_sum);
+	P(se.statistics.iowait_count);
 	P(sched_info.bkl_count);
 	P(se.nr_migrations);
-	P(se.nr_migrations_cold);
-	P(se.nr_failed_migrations_affine);
-	P(se.nr_failed_migrations_running);
-	P(se.nr_failed_migrations_hot);
-	P(se.nr_forced_migrations);
-	P(se.nr_wakeups);
-	P(se.nr_wakeups_sync);
-	P(se.nr_wakeups_migrate);
-	P(se.nr_wakeups_local);
-	P(se.nr_wakeups_remote);
-	P(se.nr_wakeups_affine);
-	P(se.nr_wakeups_affine_attempts);
-	P(se.nr_wakeups_passive);
-	P(se.nr_wakeups_idle);
+	P(se.statistics.nr_migrations_cold);
+	P(se.statistics.nr_failed_migrations_affine);
+	P(se.statistics.nr_failed_migrations_running);
+	P(se.statistics.nr_failed_migrations_hot);
+	P(se.statistics.nr_forced_migrations);
+	P(se.statistics.nr_wakeups);
+	P(se.statistics.nr_wakeups_sync);
+	P(se.statistics.nr_wakeups_migrate);
+	P(se.statistics.nr_wakeups_local);
+	P(se.statistics.nr_wakeups_remote);
+	P(se.statistics.nr_wakeups_affine);
+	P(se.statistics.nr_wakeups_affine_attempts);
+	P(se.statistics.nr_wakeups_passive);
+	P(se.statistics.nr_wakeups_idle);
 
 	{
 		u64 avg_atom, avg_per_cpu;
@@ -491,31 +484,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 void proc_sched_set_task(struct task_struct *p)
 {
 #ifdef CONFIG_SCHEDSTATS
-	p->se.wait_max				= 0;
-	p->se.wait_sum				= 0;
-	p->se.wait_count			= 0;
-	p->se.iowait_sum			= 0;
-	p->se.iowait_count			= 0;
-	p->se.sleep_max				= 0;
-	p->se.sum_sleep_runtime			= 0;
-	p->se.block_max				= 0;
-	p->se.exec_max				= 0;
-	p->se.slice_max				= 0;
-	p->se.nr_migrations			= 0;
-	p->se.nr_migrations_cold		= 0;
-	p->se.nr_failed_migrations_affine	= 0;
-	p->se.nr_failed_migrations_running	= 0;
-	p->se.nr_failed_migrations_hot		= 0;
-	p->se.nr_forced_migrations		= 0;
-	p->se.nr_wakeups			= 0;
-	p->se.nr_wakeups_sync			= 0;
-	p->se.nr_wakeups_migrate		= 0;
-	p->se.nr_wakeups_local			= 0;
-	p->se.nr_wakeups_remote			= 0;
-	p->se.nr_wakeups_affine			= 0;
-	p->se.nr_wakeups_affine_attempts	= 0;
-	p->se.nr_wakeups_passive		= 0;
-	p->se.nr_wakeups_idle			= 0;
-	p->sched_info.bkl_count			= 0;
+	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 }
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5a5ea2cd924f..88d3053ac7c2 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -35,8 +35,8 @@
  * (to see the precise effective timeslice length of your workload,
  *  run vmstat and monitor the context-switches (cs) field)
  */
-unsigned int sysctl_sched_latency = 5000000ULL;
-unsigned int normalized_sysctl_sched_latency = 5000000ULL;
+unsigned int sysctl_sched_latency = 6000000ULL;
+unsigned int normalized_sysctl_sched_latency = 6000000ULL;
 
 /*
  * The initial- and re-scaling of tunables is configurable
@@ -52,15 +52,15 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling
 
 /*
  * Minimal preemption granularity for CPU-bound tasks:
- * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 2 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-unsigned int sysctl_sched_min_granularity = 1000000ULL;
-unsigned int normalized_sysctl_sched_min_granularity = 1000000ULL;
+unsigned int sysctl_sched_min_granularity = 2000000ULL;
+unsigned int normalized_sysctl_sched_min_granularity = 2000000ULL;
 
 /*
  * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
  */
-static unsigned int sched_nr_latency = 5;
+static unsigned int sched_nr_latency = 3;
 
 /*
  * After fork, child runs first. If set to 0 (default) then
@@ -505,7 +505,8 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 {
 	unsigned long delta_exec_weighted;
 
-	schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
+	schedstat_set(curr->statistics.exec_max,
+		      max((u64)delta_exec, curr->statistics.exec_max));
 
 	curr->sum_exec_runtime += delta_exec;
 	schedstat_add(cfs_rq, exec_clock, delta_exec);
@@ -548,7 +549,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	schedstat_set(se->wait_start, rq_of(cfs_rq)->clock);
+	schedstat_set(se->statistics.wait_start, rq_of(cfs_rq)->clock);
 }
 
 /*
@@ -567,18 +568,18 @@ static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static void
 update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	schedstat_set(se->wait_max, max(se->wait_max,
-			rq_of(cfs_rq)->clock - se->wait_start));
-	schedstat_set(se->wait_count, se->wait_count + 1);
-	schedstat_set(se->wait_sum, se->wait_sum +
-			rq_of(cfs_rq)->clock - se->wait_start);
+	schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max,
+			rq_of(cfs_rq)->clock - se->statistics.wait_start));
+	schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1);
+	schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum +
+			rq_of(cfs_rq)->clock - se->statistics.wait_start);
 #ifdef CONFIG_SCHEDSTATS
 	if (entity_is_task(se)) {
 		trace_sched_stat_wait(task_of(se),
-			rq_of(cfs_rq)->clock - se->wait_start);
+			rq_of(cfs_rq)->clock - se->statistics.wait_start);
 	}
 #endif
-	schedstat_set(se->wait_start, 0);
+	schedstat_set(se->statistics.wait_start, 0);
 }
 
 static inline void
@@ -657,39 +658,39 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	if (entity_is_task(se))
 		tsk = task_of(se);
 
-	if (se->sleep_start) {
-		u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
+	if (se->statistics.sleep_start) {
+		u64 delta = rq_of(cfs_rq)->clock - se->statistics.sleep_start;
 
 		if ((s64)delta < 0)
 			delta = 0;
 
-		if (unlikely(delta > se->sleep_max))
-			se->sleep_max = delta;
+		if (unlikely(delta > se->statistics.sleep_max))
+			se->statistics.sleep_max = delta;
 
-		se->sleep_start = 0;
-		se->sum_sleep_runtime += delta;
+		se->statistics.sleep_start = 0;
+		se->statistics.sum_sleep_runtime += delta;
 
 		if (tsk) {
 			account_scheduler_latency(tsk, delta >> 10, 1);
 			trace_sched_stat_sleep(tsk, delta);
 		}
 	}
-	if (se->block_start) {
-		u64 delta = rq_of(cfs_rq)->clock - se->block_start;
+	if (se->statistics.block_start) {
+		u64 delta = rq_of(cfs_rq)->clock - se->statistics.block_start;
 
 		if ((s64)delta < 0)
 			delta = 0;
 
-		if (unlikely(delta > se->block_max))
-			se->block_max = delta;
+		if (unlikely(delta > se->statistics.block_max))
+			se->statistics.block_max = delta;
 
-		se->block_start = 0;
-		se->sum_sleep_runtime += delta;
+		se->statistics.block_start = 0;
+		se->statistics.sum_sleep_runtime += delta;
 
 		if (tsk) {
 			if (tsk->in_iowait) {
-				se->iowait_sum += delta;
-				se->iowait_count++;
+				se->statistics.iowait_sum += delta;
+				se->statistics.iowait_count++;
 				trace_sched_stat_iowait(tsk, delta);
 			}
 
@@ -737,20 +738,10 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 		vruntime += sched_vslice(cfs_rq, se);
 
 	/* sleeps up to a single latency don't count. */
-	if (!initial && sched_feat(FAIR_SLEEPERS)) {
+	if (!initial) {
 		unsigned long thresh = sysctl_sched_latency;
 
 		/*
-		 * Convert the sleeper threshold into virtual time.
-		 * SCHED_IDLE is a special sub-class.  We care about
-		 * fairness only relative to other SCHED_IDLE tasks,
-		 * all of which have the same weight.
-		 */
-		if (sched_feat(NORMALIZED_SLEEPER) && (!entity_is_task(se) ||
-				 task_of(se)->policy != SCHED_IDLE))
-			thresh = calc_delta_fair(thresh, se);
-
-		/*
 		 * Halve their sleep time's effect, to allow
 		 * for a gentler effect of sleepers:
 		 */
@@ -766,9 +757,6 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 	se->vruntime = vruntime;
 }
 
-#define ENQUEUE_WAKEUP	1
-#define ENQUEUE_MIGRATE 2
-
 static void
 enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
@@ -776,7 +764,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Update the normalized vruntime before updating min_vruntime
 	 * through callig update_curr().
 	 */
-	if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_MIGRATE))
+	if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING))
 		se->vruntime += cfs_rq->min_vruntime;
 
 	/*
@@ -812,7 +800,7 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 static void
-dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
+dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	/*
 	 * Update run-time statistics of the 'current'.
@@ -820,15 +808,15 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 	update_curr(cfs_rq);
 
 	update_stats_dequeue(cfs_rq, se);
-	if (sleep) {
+	if (flags & DEQUEUE_SLEEP) {
 #ifdef CONFIG_SCHEDSTATS
 		if (entity_is_task(se)) {
 			struct task_struct *tsk = task_of(se);
 
 			if (tsk->state & TASK_INTERRUPTIBLE)
-				se->sleep_start = rq_of(cfs_rq)->clock;
+				se->statistics.sleep_start = rq_of(cfs_rq)->clock;
 			if (tsk->state & TASK_UNINTERRUPTIBLE)
-				se->block_start = rq_of(cfs_rq)->clock;
+				se->statistics.block_start = rq_of(cfs_rq)->clock;
 		}
 #endif
 	}
@@ -845,7 +833,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 	 * update can refer to the ->curr item and we need to reflect this
 	 * movement in our normalized position.
 	 */
-	if (!sleep)
+	if (!(flags & DEQUEUE_SLEEP))
 		se->vruntime -= cfs_rq->min_vruntime;
 }
 
@@ -912,7 +900,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 * when there are only lesser-weight tasks around):
 	 */
 	if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
-		se->slice_max = max(se->slice_max,
+		se->statistics.slice_max = max(se->statistics.slice_max,
 			se->sum_exec_runtime - se->prev_sum_exec_runtime);
 	}
 #endif
@@ -1054,16 +1042,10 @@ static inline void hrtick_update(struct rq *rq)
  * then put the task into the rbtree:
  */
 static void
-enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, bool head)
+enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
-	int flags = 0;
-
-	if (wakeup)
-		flags |= ENQUEUE_WAKEUP;
-	if (p->state == TASK_WAKING)
-		flags |= ENQUEUE_MIGRATE;
 
 	for_each_sched_entity(se) {
 		if (se->on_rq)
@@ -1081,18 +1063,18 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, bool head)
  * decreased. We remove the task from the rbtree and
  * update the fair scheduling stats:
  */
-static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
+static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		dequeue_entity(cfs_rq, se, sleep);
+		dequeue_entity(cfs_rq, se, flags);
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight)
 			break;
-		sleep = 1;
+		flags |= DEQUEUE_SLEEP;
 	}
 
 	hrtick_update(rq);
@@ -1240,7 +1222,6 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu,
 
 static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 {
-	struct task_struct *curr = current;
 	unsigned long this_load, load;
 	int idx, this_cpu, prev_cpu;
 	unsigned long tl_per_task;
@@ -1255,18 +1236,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 	load	  = source_load(prev_cpu, idx);
 	this_load = target_load(this_cpu, idx);
 
-	if (sync) {
-	       if (sched_feat(SYNC_LESS) &&
-		   (curr->se.avg_overlap > sysctl_sched_migration_cost ||
-		    p->se.avg_overlap > sysctl_sched_migration_cost))
-		       sync = 0;
-	} else {
-		if (sched_feat(SYNC_MORE) &&
-		    (curr->se.avg_overlap < sysctl_sched_migration_cost &&
-		     p->se.avg_overlap < sysctl_sched_migration_cost))
-			sync = 1;
-	}
-
 	/*
 	 * If sync wakeup then subtract the (maximum possible)
 	 * effect of the currently running task from the load
@@ -1306,7 +1275,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 	if (sync && balanced)
 		return 1;
 
-	schedstat_inc(p, se.nr_wakeups_affine_attempts);
+	schedstat_inc(p, se.statistics.nr_wakeups_affine_attempts);
 	tl_per_task = cpu_avg_load_per_task(this_cpu);
 
 	if (balanced ||
@@ -1318,7 +1287,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 		 * there is no bad imbalance.
 		 */
 		schedstat_inc(sd, ttwu_move_affine);
-		schedstat_inc(p, se.nr_wakeups_affine);
+		schedstat_inc(p, se.statistics.nr_wakeups_affine);
 
 		return 1;
 	}
@@ -1445,19 +1414,19 @@ select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
  *
  * preempt must be disabled.
  */
-static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
+static int
+select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags)
 {
 	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
 	int cpu = smp_processor_id();
 	int prev_cpu = task_cpu(p);
 	int new_cpu = cpu;
-	int want_affine = 0;
+	int want_affine = 0, cpu_idle = !current->pid;
 	int want_sd = 1;
 	int sync = wake_flags & WF_SYNC;
 
 	if (sd_flag & SD_BALANCE_WAKE) {
-		if (sched_feat(AFFINE_WAKEUPS) &&
-		    cpumask_test_cpu(cpu, &p->cpus_allowed))
+		if (cpumask_test_cpu(cpu, &p->cpus_allowed))
 			want_affine = 1;
 		new_cpu = prev_cpu;
 	}
@@ -1509,13 +1478,15 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 			 * If there's an idle sibling in this domain, make that
 			 * the wake_affine target instead of the current cpu.
 			 */
-			if (tmp->flags & SD_SHARE_PKG_RESOURCES)
+			if (!cpu_idle && tmp->flags & SD_SHARE_PKG_RESOURCES)
 				target = select_idle_sibling(p, tmp, target);
 
 			if (target >= 0) {
 				if (tmp->flags & SD_WAKE_AFFINE) {
 					affine_sd = tmp;
 					want_affine = 0;
+					if (target != cpu)
+						cpu_idle = 1;
 				}
 				cpu = target;
 			}
@@ -1531,6 +1502,7 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 			sd = tmp;
 	}
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
 	if (sched_feat(LB_SHARES_UPDATE)) {
 		/*
 		 * Pick the largest domain to update shares over
@@ -1541,12 +1513,18 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 				  cpumask_weight(sched_domain_span(sd))))
 			tmp = affine_sd;
 
-		if (tmp)
+		if (tmp) {
+			raw_spin_unlock(&rq->lock);
 			update_shares(tmp);
+			raw_spin_lock(&rq->lock);
+		}
 	}
+#endif
 
-	if (affine_sd && wake_affine(affine_sd, p, sync))
-		return cpu;
+	if (affine_sd) {
+		if (cpu_idle || cpu == prev_cpu || wake_affine(affine_sd, p, sync))
+			return cpu;
+	}
 
 	while (sd) {
 		int load_idx = sd->forkexec_idx;
@@ -1591,63 +1569,26 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 }
 #endif /* CONFIG_SMP */
 
-/*
- * Adaptive granularity
- *
- * se->avg_wakeup gives the average time a task runs until it does a wakeup,
- * with the limit of wakeup_gran -- when it never does a wakeup.
- *
- * So the smaller avg_wakeup is the faster we want this task to preempt,
- * but we don't want to treat the preemptee unfairly and therefore allow it
- * to run for at least the amount of time we'd like to run.
- *
- * NOTE: we use 2*avg_wakeup to increase the probability of actually doing one
- *
- * NOTE: we use *nr_running to scale with load, this nicely matches the
- *       degrading latency on load.
- */
-static unsigned long
-adaptive_gran(struct sched_entity *curr, struct sched_entity *se)
-{
-	u64 this_run = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
-	u64 expected_wakeup = 2*se->avg_wakeup * cfs_rq_of(se)->nr_running;
-	u64 gran = 0;
-
-	if (this_run < expected_wakeup)
-		gran = expected_wakeup - this_run;
-
-	return min_t(s64, gran, sysctl_sched_wakeup_granularity);
-}
-
 static unsigned long
 wakeup_gran(struct sched_entity *curr, struct sched_entity *se)
 {
 	unsigned long gran = sysctl_sched_wakeup_granularity;
 
-	if (cfs_rq_of(curr)->curr && sched_feat(ADAPTIVE_GRAN))
-		gran = adaptive_gran(curr, se);
-
 	/*
 	 * Since its curr running now, convert the gran from real-time
 	 * to virtual-time in his units.
+	 *
+	 * By using 'se' instead of 'curr' we penalize light tasks, so
+	 * they get preempted easier. That is, if 'se' < 'curr' then
+	 * the resulting gran will be larger, therefore penalizing the
+	 * lighter, if otoh 'se' > 'curr' then the resulting gran will
+	 * be smaller, again penalizing the lighter task.
+	 *
+	 * This is especially important for buddies when the leftmost
+	 * task is higher priority than the buddy.
 	 */
-	if (sched_feat(ASYM_GRAN)) {
-		/*
-		 * By using 'se' instead of 'curr' we penalize light tasks, so
-		 * they get preempted easier. That is, if 'se' < 'curr' then
-		 * the resulting gran will be larger, therefore penalizing the
-		 * lighter, if otoh 'se' > 'curr' then the resulting gran will
-		 * be smaller, again penalizing the lighter task.
-		 *
-		 * This is especially important for buddies when the leftmost
-		 * task is higher priority than the buddy.
-		 */
-		if (unlikely(se->load.weight != NICE_0_LOAD))
-			gran = calc_delta_fair(gran, se);
-	} else {
-		if (unlikely(curr->load.weight != NICE_0_LOAD))
-			gran = calc_delta_fair(gran, curr);
-	}
+	if (unlikely(se->load.weight != NICE_0_LOAD))
+		gran = calc_delta_fair(gran, se);
 
 	return gran;
 }
@@ -1705,7 +1646,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	struct task_struct *curr = rq->curr;
 	struct sched_entity *se = &curr->se, *pse = &p->se;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
-	int sync = wake_flags & WF_SYNC;
 	int scale = cfs_rq->nr_running >= sched_nr_latency;
 
 	if (unlikely(rt_prio(p->prio)))
@@ -1738,14 +1678,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	if (unlikely(curr->policy == SCHED_IDLE))
 		goto preempt;
 
-	if (sched_feat(WAKEUP_SYNC) && sync)
-		goto preempt;
-
-	if (sched_feat(WAKEUP_OVERLAP) &&
-			se->avg_overlap < sysctl_sched_migration_cost &&
-			pse->avg_overlap < sysctl_sched_migration_cost)
-		goto preempt;
-
 	if (!sched_feat(WAKEUP_PREEMPT))
 		return;
 
@@ -1844,13 +1776,13 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 	 * 3) are cache-hot on their current CPU.
 	 */
 	if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) {
-		schedstat_inc(p, se.nr_failed_migrations_affine);
+		schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
 		return 0;
 	}
 	*all_pinned = 0;
 
 	if (task_running(rq, p)) {
-		schedstat_inc(p, se.nr_failed_migrations_running);
+		schedstat_inc(p, se.statistics.nr_failed_migrations_running);
 		return 0;
 	}
 
@@ -1866,14 +1798,14 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 #ifdef CONFIG_SCHEDSTATS
 		if (tsk_cache_hot) {
 			schedstat_inc(sd, lb_hot_gained[idle]);
-			schedstat_inc(p, se.nr_forced_migrations);
+			schedstat_inc(p, se.statistics.nr_forced_migrations);
 		}
 #endif
 		return 1;
 	}
 
 	if (tsk_cache_hot) {
-		schedstat_inc(p, se.nr_failed_migrations_hot);
+		schedstat_inc(p, se.statistics.nr_failed_migrations_hot);
 		return 0;
 	}
 	return 1;
@@ -3112,8 +3044,6 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
 
 	/* move a task from busiest_rq to target_rq */
 	double_lock_balance(busiest_rq, target_rq);
-	update_rq_clock(busiest_rq);
-	update_rq_clock(target_rq);
 
 	/* Search for an sd spanning us and the target CPU. */
 	for_each_domain(target_cpu, sd) {
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index d5059fd761d9..83c66e8ad3ee 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -1,11 +1,4 @@
 /*
- * Disregards a certain amount of sleep time (sched_latency_ns) and
- * considers the task to be running during that period. This gives it
- * a service deficit on wakeup, allowing it to run sooner.
- */
-SCHED_FEAT(FAIR_SLEEPERS, 1)
-
-/*
  * Only give sleepers 50% of their service deficit. This allows
  * them to run sooner, but does not allow tons of sleepers to
  * rip the spread apart.
@@ -13,13 +6,6 @@ SCHED_FEAT(FAIR_SLEEPERS, 1)
 SCHED_FEAT(GENTLE_FAIR_SLEEPERS, 1)
 
 /*
- * By not normalizing the sleep time, heavy tasks get an effective
- * longer period, and lighter task an effective shorter period they
- * are considered running.
- */
-SCHED_FEAT(NORMALIZED_SLEEPER, 0)
-
-/*
  * Place new tasks ahead so that they do not starve already running
  * tasks
  */
@@ -31,37 +17,6 @@ SCHED_FEAT(START_DEBIT, 1)
 SCHED_FEAT(WAKEUP_PREEMPT, 1)
 
 /*
- * Compute wakeup_gran based on task behaviour, clipped to
- *  [0, sched_wakeup_gran_ns]
- */
-SCHED_FEAT(ADAPTIVE_GRAN, 1)
-
-/*
- * When converting the wakeup granularity to virtual time, do it such
- * that heavier tasks preempting a lighter task have an edge.
- */
-SCHED_FEAT(ASYM_GRAN, 1)
-
-/*
- * Always wakeup-preempt SYNC wakeups, see SYNC_WAKEUPS.
- */
-SCHED_FEAT(WAKEUP_SYNC, 0)
-
-/*
- * Wakeup preempt based on task behaviour. Tasks that do not overlap
- * don't get preempted.
- */
-SCHED_FEAT(WAKEUP_OVERLAP, 0)
-
-/*
- * Use the SYNC wakeup hint, pipes and the likes use this to indicate
- * the remote end is likely to consume the data we just wrote, and
- * therefore has cache benefit from being placed on the same cpu, see
- * also AFFINE_WAKEUPS.
- */
-SCHED_FEAT(SYNC_WAKEUPS, 1)
-
-/*
  * Based on load and program behaviour, see if it makes sense to place
  * a newly woken task on the same cpu as the task that woke it --
  * improve cache locality. Typically used with SYNC wakeups as
@@ -70,16 +25,6 @@ SCHED_FEAT(SYNC_WAKEUPS, 1)
 SCHED_FEAT(AFFINE_WAKEUPS, 1)
 
 /*
- * Weaken SYNC hint based on overlap
- */
-SCHED_FEAT(SYNC_LESS, 1)
-
-/*
- * Add SYNC hint based on overlap
- */
-SCHED_FEAT(SYNC_MORE, 0)
-
-/*
  * Prefer to schedule the task we woke last (assuming it failed
  * wakeup-preemption), since its likely going to consume data we
  * touched, increases cache locality.
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index a8a6d8a50947..bea2b8f12024 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -6,7 +6,8 @@
  */
 
 #ifdef CONFIG_SMP
-static int select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
+static int
+select_task_rq_idle(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
@@ -32,7 +33,7 @@ static struct task_struct *pick_next_task_idle(struct rq *rq)
  * message if some code attempts to do it:
  */
 static void
-dequeue_task_idle(struct rq *rq, struct task_struct *p, int sleep)
+dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
 {
 	raw_spin_unlock_irq(&rq->lock);
 	printk(KERN_ERR "bad: scheduling from the idle thread!\n");
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index b5b920ae2ea7..8afb953e31c6 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -613,7 +613,7 @@ static void update_curr_rt(struct rq *rq)
 	if (unlikely((s64)delta_exec < 0))
 		delta_exec = 0;
 
-	schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec));
+	schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec));
 
 	curr->se.sum_exec_runtime += delta_exec;
 	account_group_exec_runtime(curr, delta_exec);
@@ -888,20 +888,20 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
  * Adding/removing a task to/from a priority array:
  */
 static void
-enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup, bool head)
+enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
 
-	if (wakeup)
+	if (flags & ENQUEUE_WAKEUP)
 		rt_se->timeout = 0;
 
-	enqueue_rt_entity(rt_se, head);
+	enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
 
 	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
 }
 
-static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
+static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
 
@@ -948,10 +948,9 @@ static void yield_task_rt(struct rq *rq)
 #ifdef CONFIG_SMP
 static int find_lowest_rq(struct task_struct *task);
 
-static int select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
+static int
+select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
 {
-	struct rq *rq = task_rq(p);
-
 	if (sd_flag != SD_BALANCE_WAKE)
 		return smp_processor_id();
 
diff --git a/kernel/time.c b/kernel/time.c
index 656dccfe1cbb..50612faa9baf 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -132,12 +132,11 @@ SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv,
  */
 static inline void warp_clock(void)
 {
-	write_seqlock_irq(&xtime_lock);
-	wall_to_monotonic.tv_sec -= sys_tz.tz_minuteswest * 60;
-	xtime.tv_sec += sys_tz.tz_minuteswest * 60;
-	update_xtime_cache(0);
-	write_sequnlock_irq(&xtime_lock);
-	clock_was_set();
+	struct timespec delta, adjust;
+	delta.tv_sec = sys_tz.tz_minuteswest * 60;
+	delta.tv_nsec = 0;
+	adjust = timespec_add_safe(current_kernel_time(), delta);
+	do_settimeofday(&adjust);
 }
 
 /*
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 7c0f180d6e9d..c63116863a80 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -69,7 +69,7 @@ static s64			time_freq;
 /* time at last adjustment (secs):					*/
 static long			time_reftime;
 
-long				time_adjust;
+static long			time_adjust;
 
 /* constant (boot-param configurable) NTP tick adjustment (upscaled)	*/
 static s64			ntp_tick_adj;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index f992762d7f51..f25735a767af 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -262,6 +262,9 @@ void tick_nohz_stop_sched_tick(int inidle)
 		goto end;
 	}
 
+	if (nohz_ratelimit(cpu))
+		goto end;
+
 	ts->idle_calls++;
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
diff --git a/kernel/timer.c b/kernel/timer.c
index aeb6a54f2771..9199f3c52215 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -319,6 +319,24 @@ unsigned long round_jiffies_up_relative(unsigned long j)
 }
 EXPORT_SYMBOL_GPL(round_jiffies_up_relative);
 
+/**
+ * set_timer_slack - set the allowed slack for a timer
+ * @slack_hz: the amount of time (in jiffies) allowed for rounding
+ *
+ * Set the amount of time, in jiffies, that a certain timer has
+ * in terms of slack. By setting this value, the timer subsystem
+ * will schedule the actual timer somewhere between
+ * the time mod_timer() asks for, and that time plus the slack.
+ *
+ * By setting the slack to -1, a percentage of the delay is used
+ * instead.
+ */
+void set_timer_slack(struct timer_list *timer, int slack_hz)
+{
+	timer->slack = slack_hz;
+}
+EXPORT_SYMBOL_GPL(set_timer_slack);
+
 
 static inline void set_running_timer(struct tvec_base *base,
 					struct timer_list *timer)
@@ -550,6 +568,7 @@ static void __init_timer(struct timer_list *timer,
 {
 	timer->entry.next = NULL;
 	timer->base = __raw_get_cpu_var(tvec_bases);
+	timer->slack = -1;
 #ifdef CONFIG_TIMER_STATS
 	timer->start_site = NULL;
 	timer->start_pid = -1;
@@ -715,6 +734,41 @@ int mod_timer_pending(struct timer_list *timer, unsigned long expires)
 }
 EXPORT_SYMBOL(mod_timer_pending);
 
+/*
+ * Decide where to put the timer while taking the slack into account
+ *
+ * Algorithm:
+ *   1) calculate the maximum (absolute) time
+ *   2) calculate the highest bit where the expires and new max are different
+ *   3) use this bit to make a mask
+ *   4) use the bitmask to round down the maximum time, so that all last
+ *      bits are zeros
+ */
+static inline
+unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
+{
+	unsigned long expires_limit, mask;
+	int bit;
+
+	expires_limit = expires + timer->slack;
+
+	if (timer->slack < 0) /* auto slack: use 0.4% */
+		expires_limit = expires + (expires - jiffies)/256;
+
+	mask = expires ^ expires_limit;
+
+	if (mask == 0)
+		return expires;
+
+	bit = find_last_bit(&mask, BITS_PER_LONG);
+
+	mask = (1 << bit) - 1;
+
+	expires_limit = expires_limit & ~(mask);
+
+	return expires_limit;
+}
+
 /**
  * mod_timer - modify a timer's timeout
  * @timer: the timer to be modified
@@ -745,6 +799,8 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
 	if (timer_pending(timer) && timer->expires == expires)
 		return 1;
 
+	expires = apply_slack(timer, expires);
+
 	return __mod_timer(timer, expires, false, TIMER_NOT_PINNED);
 }
 EXPORT_SYMBOL(mod_timer);
@@ -955,6 +1011,47 @@ static int cascade(struct tvec_base *base, struct tvec *tv, int index)
 	return index;
 }
 
+static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long),
+			  unsigned long data)
+{
+	int preempt_count = preempt_count();
+
+#ifdef CONFIG_LOCKDEP
+	/*
+	 * It is permissible to free the timer from inside the
+	 * function that is called from it, this we need to take into
+	 * account for lockdep too. To avoid bogus "held lock freed"
+	 * warnings as well as problems when looking into
+	 * timer->lockdep_map, make a copy and use that here.
+	 */
+	struct lockdep_map lockdep_map = timer->lockdep_map;
+#endif
+	/*
+	 * Couple the lock chain with the lock chain at
+	 * del_timer_sync() by acquiring the lock_map around the fn()
+	 * call here and in del_timer_sync().
+	 */
+	lock_map_acquire(&lockdep_map);
+
+	trace_timer_expire_entry(timer);
+	fn(data);
+	trace_timer_expire_exit(timer);
+
+	lock_map_release(&lockdep_map);
+
+	if (preempt_count != preempt_count()) {
+		WARN_ONCE(1, "timer: %pF preempt leak: %08x -> %08x\n",
+			  fn, preempt_count, preempt_count());
+		/*
+		 * Restore the preempt count. That gives us a decent
+		 * chance to survive and extract information. If the
+		 * callback kept a lock held, bad luck, but not worse
+		 * than the BUG() we had.
+		 */
+		preempt_count() = preempt_count;
+	}
+}
+
 #define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK)
 
 /**
@@ -998,45 +1095,7 @@ static inline void __run_timers(struct tvec_base *base)
 			detach_timer(timer, 1);
 
 			spin_unlock_irq(&base->lock);
-			{
-				int preempt_count = preempt_count();
-
-#ifdef CONFIG_LOCKDEP
-				/*
-				 * It is permissible to free the timer from
-				 * inside the function that is called from
-				 * it, this we need to take into account for
-				 * lockdep too. To avoid bogus "held lock
-				 * freed" warnings as well as problems when
-				 * looking into timer->lockdep_map, make a
-				 * copy and use that here.
-				 */
-				struct lockdep_map lockdep_map =
-					timer->lockdep_map;
-#endif
-				/*
-				 * Couple the lock chain with the lock chain at
-				 * del_timer_sync() by acquiring the lock_map
-				 * around the fn() call here and in
-				 * del_timer_sync().
-				 */
-				lock_map_acquire(&lockdep_map);
-
-				trace_timer_expire_entry(timer);
-				fn(data);
-				trace_timer_expire_exit(timer);
-
-				lock_map_release(&lockdep_map);
-
-				if (preempt_count != preempt_count()) {
-					printk(KERN_ERR "huh, entered %p "
-					       "with preempt_count %08x, exited"
-					       " with %08x?\n",
-					       fn, preempt_count,
-					       preempt_count());
-					BUG();
-				}
-			}
+			call_timer_fn(timer, fn, data);
 			spin_lock_irq(&base->lock);
 		}
 	}
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 13e13d428cd3..8b1797c4545b 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -44,9 +44,6 @@ config HAVE_FTRACE_MCOUNT_RECORD
 	help
 	  See Documentation/trace/ftrace-design.txt
 
-config HAVE_HW_BRANCH_TRACER
-	bool
-
 config HAVE_SYSCALL_TRACEPOINTS
 	bool
 	help
@@ -374,14 +371,6 @@ config STACK_TRACER
 
 	  Say N if unsure.
 
-config HW_BRANCH_TRACER
-	depends on HAVE_HW_BRANCH_TRACER
-	bool "Trace hw branches"
-	select GENERIC_TRACER
-	help
-	  This tracer records all branches on the system in a circular
-	  buffer, giving access to the last N branches for each cpu.
-
 config KMEMTRACE
 	bool "Trace SLAB allocations"
 	select GENERIC_TRACER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 78edc6490038..ffb1a5b0550e 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -41,7 +41,6 @@ obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
 obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
-obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
 obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
 obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
 obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 41ca394feb22..5885cdfc41f3 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -319,6 +319,11 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
 #define TS_MASK		((1ULL << TS_SHIFT) - 1)
 #define TS_DELTA_TEST	(~TS_MASK)
 
+/* Flag when events were overwritten */
+#define RB_MISSED_EVENTS	(1 << 31)
+/* Missed count stored at end */
+#define RB_MISSED_STORED	(1 << 30)
+
 struct buffer_data_page {
 	u64		 time_stamp;	/* page time stamp */
 	local_t		 commit;	/* write committed index */
@@ -338,6 +343,7 @@ struct buffer_page {
 	local_t		 write;		/* index for next write */
 	unsigned	 read;		/* index for next read */
 	local_t		 entries;	/* entries on this page */
+	unsigned long	 real_end;	/* real end of data */
 	struct buffer_data_page *page;	/* Actual data page */
 };
 
@@ -417,6 +423,12 @@ int ring_buffer_print_page_header(struct trace_seq *s)
 			       (unsigned int)sizeof(field.commit),
 			       (unsigned int)is_signed_type(long));
 
+	ret = trace_seq_printf(s, "\tfield: int overwrite;\t"
+			       "offset:%u;\tsize:%u;\tsigned:%u;\n",
+			       (unsigned int)offsetof(typeof(field), commit),
+			       1,
+			       (unsigned int)is_signed_type(long));
+
 	ret = trace_seq_printf(s, "\tfield: char data;\t"
 			       "offset:%u;\tsize:%u;\tsigned:%u;\n",
 			       (unsigned int)offsetof(typeof(field), data),
@@ -440,6 +452,8 @@ struct ring_buffer_per_cpu {
 	struct buffer_page		*tail_page;	/* write to tail */
 	struct buffer_page		*commit_page;	/* committed pages */
 	struct buffer_page		*reader_page;
+	unsigned long			lost_events;
+	unsigned long			last_overrun;
 	local_t				commit_overrun;
 	local_t				overrun;
 	local_t				entries;
@@ -1762,6 +1776,13 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	kmemcheck_annotate_bitfield(event, bitfield);
 
 	/*
+	 * Save the original length to the meta data.
+	 * This will be used by the reader to add lost event
+	 * counter.
+	 */
+	tail_page->real_end = tail;
+
+	/*
 	 * If this event is bigger than the minimum size, then
 	 * we need to be careful that we don't subtract the
 	 * write counter enough to allow another writer to slip
@@ -2838,6 +2859,7 @@ static struct buffer_page *
 rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct buffer_page *reader = NULL;
+	unsigned long overwrite;
 	unsigned long flags;
 	int nr_loops = 0;
 	int ret;
@@ -2879,6 +2901,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	local_set(&cpu_buffer->reader_page->write, 0);
 	local_set(&cpu_buffer->reader_page->entries, 0);
 	local_set(&cpu_buffer->reader_page->page->commit, 0);
+	cpu_buffer->reader_page->real_end = 0;
 
  spin:
 	/*
@@ -2899,6 +2922,18 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	rb_set_list_to_head(cpu_buffer, &cpu_buffer->reader_page->list);
 
 	/*
+	 * We want to make sure we read the overruns after we set up our
+	 * pointers to the next object. The writer side does a
+	 * cmpxchg to cross pages which acts as the mb on the writer
+	 * side. Note, the reader will constantly fail the swap
+	 * while the writer is updating the pointers, so this
+	 * guarantees that the overwrite recorded here is the one we
+	 * want to compare with the last_overrun.
+	 */
+	smp_mb();
+	overwrite = local_read(&(cpu_buffer->overrun));
+
+	/*
 	 * Here's the tricky part.
 	 *
 	 * We need to move the pointer past the header page.
@@ -2929,6 +2964,11 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->reader_page = reader;
 	rb_reset_reader_page(cpu_buffer);
 
+	if (overwrite != cpu_buffer->last_overrun) {
+		cpu_buffer->lost_events = overwrite - cpu_buffer->last_overrun;
+		cpu_buffer->last_overrun = overwrite;
+	}
+
 	goto again;
 
  out:
@@ -3005,8 +3045,14 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 		rb_advance_iter(iter);
 }
 
+static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	return cpu_buffer->lost_events;
+}
+
 static struct ring_buffer_event *
-rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
+rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
+	       unsigned long *lost_events)
 {
 	struct ring_buffer_event *event;
 	struct buffer_page *reader;
@@ -3058,6 +3104,8 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
 			ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
 							 cpu_buffer->cpu, ts);
 		}
+		if (lost_events)
+			*lost_events = rb_lost_events(cpu_buffer);
 		return event;
 
 	default:
@@ -3168,12 +3216,14 @@ static inline int rb_ok_to_lock(void)
  * @buffer: The ring buffer to read
  * @cpu: The cpu to peak at
  * @ts: The timestamp counter of this event.
+ * @lost_events: a variable to store if events were lost (may be NULL)
  *
  * This will return the event that will be read next, but does
  * not consume the data.
  */
 struct ring_buffer_event *
-ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts,
+		 unsigned long *lost_events)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct ring_buffer_event *event;
@@ -3188,7 +3238,7 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	local_irq_save(flags);
 	if (dolock)
 		spin_lock(&cpu_buffer->reader_lock);
-	event = rb_buffer_peek(cpu_buffer, ts);
+	event = rb_buffer_peek(cpu_buffer, ts, lost_events);
 	if (event && event->type_len == RINGBUF_TYPE_PADDING)
 		rb_advance_reader(cpu_buffer);
 	if (dolock)
@@ -3230,13 +3280,17 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 /**
  * ring_buffer_consume - return an event and consume it
  * @buffer: The ring buffer to get the next event from
+ * @cpu: the cpu to read the buffer from
+ * @ts: a variable to store the timestamp (may be NULL)
+ * @lost_events: a variable to store if events were lost (may be NULL)
  *
  * Returns the next event in the ring buffer, and that event is consumed.
  * Meaning, that sequential reads will keep returning a different event,
  * and eventually empty the ring buffer if the producer is slower.
  */
 struct ring_buffer_event *
-ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts,
+		    unsigned long *lost_events)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event = NULL;
@@ -3257,9 +3311,11 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 	if (dolock)
 		spin_lock(&cpu_buffer->reader_lock);
 
-	event = rb_buffer_peek(cpu_buffer, ts);
-	if (event)
+	event = rb_buffer_peek(cpu_buffer, ts, lost_events);
+	if (event) {
+		cpu_buffer->lost_events = 0;
 		rb_advance_reader(cpu_buffer);
+	}
 
 	if (dolock)
 		spin_unlock(&cpu_buffer->reader_lock);
@@ -3408,6 +3464,9 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->write_stamp = 0;
 	cpu_buffer->read_stamp = 0;
 
+	cpu_buffer->lost_events = 0;
+	cpu_buffer->last_overrun = 0;
+
 	rb_head_page_activate(cpu_buffer);
 }
 
@@ -3683,6 +3742,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 	struct ring_buffer_event *event;
 	struct buffer_data_page *bpage;
 	struct buffer_page *reader;
+	unsigned long missed_events;
 	unsigned long flags;
 	unsigned int commit;
 	unsigned int read;
@@ -3719,6 +3779,9 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 	read = reader->read;
 	commit = rb_page_commit(reader);
 
+	/* Check if any events were dropped */
+	missed_events = cpu_buffer->lost_events;
+
 	/*
 	 * If this page has been partially read or
 	 * if len is not big enough to read the rest of the page or
@@ -3779,9 +3842,35 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 		local_set(&reader->entries, 0);
 		reader->read = 0;
 		*data_page = bpage;
+
+		/*
+		 * Use the real_end for the data size,
+		 * This gives us a chance to store the lost events
+		 * on the page.
+		 */
+		if (reader->real_end)
+			local_set(&bpage->commit, reader->real_end);
 	}
 	ret = read;
 
+	cpu_buffer->lost_events = 0;
+	/*
+	 * Set a flag in the commit field if we lost events
+	 */
+	if (missed_events) {
+		commit = local_read(&bpage->commit);
+
+		/* If there is room at the end of the page to save the
+		 * missed events, then record it there.
+		 */
+		if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) {
+			memcpy(&bpage->data[commit], &missed_events,
+			       sizeof(missed_events));
+			local_add(RB_MISSED_STORED, &bpage->commit);
+		}
+		local_add(RB_MISSED_EVENTS, &bpage->commit);
+	}
+
  out_unlock:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index df74c7982255..dc56556b55a2 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -81,7 +81,7 @@ static enum event_status read_event(int cpu)
 	int *entry;
 	u64 ts;
 
-	event = ring_buffer_consume(buffer, cpu, &ts);
+	event = ring_buffer_consume(buffer, cpu, &ts, NULL);
 	if (!event)
 		return EVENT_DROPPED;
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 44f916a04065..60f3b6289731 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1545,7 +1545,8 @@ static void trace_iterator_increment(struct trace_iterator *iter)
 }
 
 static struct trace_entry *
-peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
+peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
+		unsigned long *lost_events)
 {
 	struct ring_buffer_event *event;
 	struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];
@@ -1556,7 +1557,8 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
 	if (buf_iter)
 		event = ring_buffer_iter_peek(buf_iter, ts);
 	else
-		event = ring_buffer_peek(iter->tr->buffer, cpu, ts);
+		event = ring_buffer_peek(iter->tr->buffer, cpu, ts,
+					 lost_events);
 
 	ftrace_enable_cpu();
 
@@ -1564,10 +1566,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
 }
 
 static struct trace_entry *
-__find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
+__find_next_entry(struct trace_iterator *iter, int *ent_cpu,
+		  unsigned long *missing_events, u64 *ent_ts)
 {
 	struct ring_buffer *buffer = iter->tr->buffer;
 	struct trace_entry *ent, *next = NULL;
+	unsigned long lost_events, next_lost = 0;
 	int cpu_file = iter->cpu_file;
 	u64 next_ts = 0, ts;
 	int next_cpu = -1;
@@ -1580,7 +1584,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 	if (cpu_file > TRACE_PIPE_ALL_CPU) {
 		if (ring_buffer_empty_cpu(buffer, cpu_file))
 			return NULL;
-		ent = peek_next_entry(iter, cpu_file, ent_ts);
+		ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events);
 		if (ent_cpu)
 			*ent_cpu = cpu_file;
 
@@ -1592,7 +1596,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 		if (ring_buffer_empty_cpu(buffer, cpu))
 			continue;
 
-		ent = peek_next_entry(iter, cpu, &ts);
+		ent = peek_next_entry(iter, cpu, &ts, &lost_events);
 
 		/*
 		 * Pick the entry with the smallest timestamp:
@@ -1601,6 +1605,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 			next = ent;
 			next_cpu = cpu;
 			next_ts = ts;
+			next_lost = lost_events;
 		}
 	}
 
@@ -1610,6 +1615,9 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 	if (ent_ts)
 		*ent_ts = next_ts;
 
+	if (missing_events)
+		*missing_events = next_lost;
+
 	return next;
 }
 
@@ -1617,13 +1625,14 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 					  int *ent_cpu, u64 *ent_ts)
 {
-	return __find_next_entry(iter, ent_cpu, ent_ts);
+	return __find_next_entry(iter, ent_cpu, NULL, ent_ts);
 }
 
 /* Find the next real entry, and increment the iterator to the next entry */
 static void *find_next_entry_inc(struct trace_iterator *iter)
 {
-	iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts);
+	iter->ent = __find_next_entry(iter, &iter->cpu,
+				      &iter->lost_events, &iter->ts);
 
 	if (iter->ent)
 		trace_iterator_increment(iter);
@@ -1635,7 +1644,8 @@ static void trace_consume(struct trace_iterator *iter)
 {
 	/* Don't allow ftrace to trace into the ring buffers */
 	ftrace_disable_cpu();
-	ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts);
+	ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts,
+			    &iter->lost_events);
 	ftrace_enable_cpu();
 }
 
@@ -2030,6 +2040,10 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
 {
 	enum print_line_t ret;
 
+	if (iter->lost_events)
+		trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
+				 iter->cpu, iter->lost_events);
+
 	if (iter->trace && iter->trace->print_line) {
 		ret = iter->trace->print_line(iter);
 		if (ret != TRACE_TYPE_UNHANDLED)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 2825ef2c0b15..bec2c973ff0c 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -34,7 +34,6 @@ enum trace_type {
 	TRACE_GRAPH_RET,
 	TRACE_GRAPH_ENT,
 	TRACE_USER_STACK,
-	TRACE_HW_BRANCHES,
 	TRACE_KMEM_ALLOC,
 	TRACE_KMEM_FREE,
 	TRACE_BLK,
@@ -229,7 +228,6 @@ extern void __ftrace_bad_type(void);
 			  TRACE_GRAPH_ENT);		\
 		IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry,	\
 			  TRACE_GRAPH_RET);		\
-		IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\
 		IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry,	\
 			  TRACE_KMEM_ALLOC);	\
 		IF_ASSIGN(var, ent, struct kmemtrace_free_entry,	\
@@ -467,8 +465,6 @@ extern int trace_selftest_startup_sysprof(struct tracer *trace,
 					       struct trace_array *tr);
 extern int trace_selftest_startup_branch(struct tracer *trace,
 					 struct trace_array *tr);
-extern int trace_selftest_startup_hw_branches(struct tracer *trace,
-					      struct trace_array *tr);
 extern int trace_selftest_startup_ksym(struct tracer *trace,
 					 struct trace_array *tr);
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index c16a08f399df..dc008c1240da 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -318,18 +318,6 @@ FTRACE_ENTRY(branch, trace_branch,
 		 __entry->func, __entry->file, __entry->correct)
 );
 
-FTRACE_ENTRY(hw_branch, hw_branch_entry,
-
-	TRACE_HW_BRANCHES,
-
-	F_STRUCT(
-		__field(	u64,	from	)
-		__field(	u64,	to	)
-	),
-
-	F_printk("from: %llx to: %llx", __entry->from, __entry->to)
-);
-
 FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry,
 
 	TRACE_KMEM_ALLOC,
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 9aed1a5cf553..669b9c31861d 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -490,9 +490,10 @@ get_return_for_leaf(struct trace_iterator *iter,
 			 * We need to consume the current entry to see
 			 * the next one.
 			 */
-			ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
+			ring_buffer_consume(iter->tr->buffer, iter->cpu,
+					    NULL, NULL);
 			event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
-						 NULL);
+						 NULL, NULL);
 		}
 
 		if (!event)
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
deleted file mode 100644
index 7b97000745f5..000000000000
--- a/kernel/trace/trace_hw_branches.c
+++ /dev/null
@@ -1,312 +0,0 @@
-/*
- * h/w branch tracer for x86 based on BTS
- *
- * Copyright (C) 2008-2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@gmail.com>, 2008-2009
- */
-#include <linux/kallsyms.h>
-#include <linux/debugfs.h>
-#include <linux/ftrace.h>
-#include <linux/module.h>
-#include <linux/cpu.h>
-#include <linux/smp.h>
-#include <linux/fs.h>
-
-#include <asm/ds.h>
-
-#include "trace_output.h"
-#include "trace.h"
-
-
-#define BTS_BUFFER_SIZE (1 << 13)
-
-static DEFINE_PER_CPU(struct bts_tracer *, hwb_tracer);
-static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], hwb_buffer);
-
-#define this_tracer per_cpu(hwb_tracer, smp_processor_id())
-
-static int trace_hw_branches_enabled __read_mostly;
-static int trace_hw_branches_suspended __read_mostly;
-static struct trace_array *hw_branch_trace __read_mostly;
-
-
-static void bts_trace_init_cpu(int cpu)
-{
-	per_cpu(hwb_tracer, cpu) =
-		ds_request_bts_cpu(cpu, per_cpu(hwb_buffer, cpu),
-				   BTS_BUFFER_SIZE, NULL, (size_t)-1,
-				   BTS_KERNEL);
-
-	if (IS_ERR(per_cpu(hwb_tracer, cpu)))
-		per_cpu(hwb_tracer, cpu) = NULL;
-}
-
-static int bts_trace_init(struct trace_array *tr)
-{
-	int cpu;
-
-	hw_branch_trace = tr;
-	trace_hw_branches_enabled = 0;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu) {
-		bts_trace_init_cpu(cpu);
-
-		if (likely(per_cpu(hwb_tracer, cpu)))
-			trace_hw_branches_enabled = 1;
-	}
-	trace_hw_branches_suspended = 0;
-	put_online_cpus();
-
-	/* If we could not enable tracing on a single cpu, we fail. */
-	return trace_hw_branches_enabled ? 0 : -EOPNOTSUPP;
-}
-
-static void bts_trace_reset(struct trace_array *tr)
-{
-	int cpu;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu) {
-		if (likely(per_cpu(hwb_tracer, cpu))) {
-			ds_release_bts(per_cpu(hwb_tracer, cpu));
-			per_cpu(hwb_tracer, cpu) = NULL;
-		}
-	}
-	trace_hw_branches_enabled = 0;
-	trace_hw_branches_suspended = 0;
-	put_online_cpus();
-}
-
-static void bts_trace_start(struct trace_array *tr)
-{
-	int cpu;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu)
-		if (likely(per_cpu(hwb_tracer, cpu)))
-			ds_resume_bts(per_cpu(hwb_tracer, cpu));
-	trace_hw_branches_suspended = 0;
-	put_online_cpus();
-}
-
-static void bts_trace_stop(struct trace_array *tr)
-{
-	int cpu;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu)
-		if (likely(per_cpu(hwb_tracer, cpu)))
-			ds_suspend_bts(per_cpu(hwb_tracer, cpu));
-	trace_hw_branches_suspended = 1;
-	put_online_cpus();
-}
-
-static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb,
-				     unsigned long action, void *hcpu)
-{
-	int cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_DOWN_FAILED:
-		/* The notification is sent with interrupts enabled. */
-		if (trace_hw_branches_enabled) {
-			bts_trace_init_cpu(cpu);
-
-			if (trace_hw_branches_suspended &&
-			    likely(per_cpu(hwb_tracer, cpu)))
-				ds_suspend_bts(per_cpu(hwb_tracer, cpu));
-		}
-		break;
-
-	case CPU_DOWN_PREPARE:
-		/* The notification is sent with interrupts enabled. */
-		if (likely(per_cpu(hwb_tracer, cpu))) {
-			ds_release_bts(per_cpu(hwb_tracer, cpu));
-			per_cpu(hwb_tracer, cpu) = NULL;
-		}
-	}
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block bts_hotcpu_notifier __cpuinitdata = {
-	.notifier_call = bts_hotcpu_handler
-};
-
-static void bts_trace_print_header(struct seq_file *m)
-{
-	seq_puts(m, "# CPU#        TO  <-  FROM\n");
-}
-
-static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
-{
-	unsigned long symflags = TRACE_ITER_SYM_OFFSET;
-	struct trace_entry *entry = iter->ent;
-	struct trace_seq *seq = &iter->seq;
-	struct hw_branch_entry *it;
-
-	trace_assign_type(it, entry);
-
-	if (entry->type == TRACE_HW_BRANCHES) {
-		if (trace_seq_printf(seq, "%4d  ", iter->cpu) &&
-		    seq_print_ip_sym(seq, it->to, symflags) &&
-		    trace_seq_printf(seq, "\t  <-  ") &&
-		    seq_print_ip_sym(seq, it->from, symflags) &&
-		    trace_seq_printf(seq, "\n"))
-			return TRACE_TYPE_HANDLED;
-		return TRACE_TYPE_PARTIAL_LINE;
-	}
-	return TRACE_TYPE_UNHANDLED;
-}
-
-void trace_hw_branch(u64 from, u64 to)
-{
-	struct ftrace_event_call *call = &event_hw_branch;
-	struct trace_array *tr = hw_branch_trace;
-	struct ring_buffer_event *event;
-	struct ring_buffer *buf;
-	struct hw_branch_entry *entry;
-	unsigned long irq1;
-	int cpu;
-
-	if (unlikely(!tr))
-		return;
-
-	if (unlikely(!trace_hw_branches_enabled))
-		return;
-
-	local_irq_save(irq1);
-	cpu = raw_smp_processor_id();
-	if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
-		goto out;
-
-	buf = tr->buffer;
-	event = trace_buffer_lock_reserve(buf, TRACE_HW_BRANCHES,
-					  sizeof(*entry), 0, 0);
-	if (!event)
-		goto out;
-	entry	= ring_buffer_event_data(event);
-	tracing_generic_entry_update(&entry->ent, 0, from);
-	entry->ent.type = TRACE_HW_BRANCHES;
-	entry->from = from;
-	entry->to   = to;
-	if (!filter_check_discard(call, entry, buf, event))
-		trace_buffer_unlock_commit(buf, event, 0, 0);
-
- out:
-	atomic_dec(&tr->data[cpu]->disabled);
-	local_irq_restore(irq1);
-}
-
-static void trace_bts_at(const struct bts_trace *trace, void *at)
-{
-	struct bts_struct bts;
-	int err = 0;
-
-	WARN_ON_ONCE(!trace->read);
-	if (!trace->read)
-		return;
-
-	err = trace->read(this_tracer, at, &bts);
-	if (err < 0)
-		return;
-
-	switch (bts.qualifier) {
-	case BTS_BRANCH:
-		trace_hw_branch(bts.variant.lbr.from, bts.variant.lbr.to);
-		break;
-	}
-}
-
-/*
- * Collect the trace on the current cpu and write it into the ftrace buffer.
- *
- * pre: tracing must be suspended on the current cpu
- */
-static void trace_bts_cpu(void *arg)
-{
-	struct trace_array *tr = (struct trace_array *)arg;
-	const struct bts_trace *trace;
-	unsigned char *at;
-
-	if (unlikely(!tr))
-		return;
-
-	if (unlikely(atomic_read(&tr->data[raw_smp_processor_id()]->disabled)))
-		return;
-
-	if (unlikely(!this_tracer))
-		return;
-
-	trace = ds_read_bts(this_tracer);
-	if (!trace)
-		return;
-
-	for (at = trace->ds.top; (void *)at < trace->ds.end;
-	     at += trace->ds.size)
-		trace_bts_at(trace, at);
-
-	for (at = trace->ds.begin; (void *)at < trace->ds.top;
-	     at += trace->ds.size)
-		trace_bts_at(trace, at);
-}
-
-static void trace_bts_prepare(struct trace_iterator *iter)
-{
-	int cpu;
-
-	get_online_cpus();
-	for_each_online_cpu(cpu)
-		if (likely(per_cpu(hwb_tracer, cpu)))
-			ds_suspend_bts(per_cpu(hwb_tracer, cpu));
-	/*
-	 * We need to collect the trace on the respective cpu since ftrace
-	 * implicitly adds the record for the current cpu.
-	 * Once that is more flexible, we could collect the data from any cpu.
-	 */
-	on_each_cpu(trace_bts_cpu, iter->tr, 1);
-
-	for_each_online_cpu(cpu)
-		if (likely(per_cpu(hwb_tracer, cpu)))
-			ds_resume_bts(per_cpu(hwb_tracer, cpu));
-	put_online_cpus();
-}
-
-static void trace_bts_close(struct trace_iterator *iter)
-{
-	tracing_reset_online_cpus(iter->tr);
-}
-
-void trace_hw_branch_oops(void)
-{
-	if (this_tracer) {
-		ds_suspend_bts_noirq(this_tracer);
-		trace_bts_cpu(hw_branch_trace);
-		ds_resume_bts_noirq(this_tracer);
-	}
-}
-
-struct tracer bts_tracer __read_mostly =
-{
-	.name		= "hw-branch-tracer",
-	.init		= bts_trace_init,
-	.reset		= bts_trace_reset,
-	.print_header	= bts_trace_print_header,
-	.print_line	= bts_trace_print_line,
-	.start		= bts_trace_start,
-	.stop		= bts_trace_stop,
-	.open		= trace_bts_prepare,
-	.close		= trace_bts_close,
-#ifdef CONFIG_FTRACE_SELFTEST
-	.selftest	= trace_selftest_startup_hw_branches,
-#endif /* CONFIG_FTRACE_SELFTEST */
-};
-
-__init static int init_bts_trace(void)
-{
-	register_hotcpu_notifier(&bts_hotcpu_notifier);
-	return register_tracer(&bts_tracer);
-}
-device_initcall(init_bts_trace);
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 81003b4d617f..71fa771ee4d7 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -17,7 +17,6 @@ static inline int trace_valid_entry(struct trace_entry *entry)
 	case TRACE_BRANCH:
 	case TRACE_GRAPH_ENT:
 	case TRACE_GRAPH_RET:
-	case TRACE_HW_BRANCHES:
 	case TRACE_KSYM:
 		return 1;
 	}
@@ -30,7 +29,7 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
 	struct trace_entry *entry;
 	unsigned int loops = 0;
 
-	while ((event = ring_buffer_consume(tr->buffer, cpu, NULL))) {
+	while ((event = ring_buffer_consume(tr->buffer, cpu, NULL, NULL))) {
 		entry = ring_buffer_event_data(event);
 
 		/*
@@ -755,62 +754,6 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
 }
 #endif /* CONFIG_BRANCH_TRACER */
 
-#ifdef CONFIG_HW_BRANCH_TRACER
-int
-trace_selftest_startup_hw_branches(struct tracer *trace,
-				   struct trace_array *tr)
-{
-	struct trace_iterator *iter;
-	struct tracer tracer;
-	unsigned long count;
-	int ret;
-
-	if (!trace->open) {
-		printk(KERN_CONT "missing open function...");
-		return -1;
-	}
-
-	ret = tracer_init(trace, tr);
-	if (ret) {
-		warn_failed_init_tracer(trace, ret);
-		return ret;
-	}
-
-	/*
-	 * The hw-branch tracer needs to collect the trace from the various
-	 * cpu trace buffers - before tracing is stopped.
-	 */
-	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
-	if (!iter)
-		return -ENOMEM;
-
-	memcpy(&tracer, trace, sizeof(tracer));
-
-	iter->trace = &tracer;
-	iter->tr = tr;
-	iter->pos = -1;
-	mutex_init(&iter->mutex);
-
-	trace->open(iter);
-
-	mutex_destroy(&iter->mutex);
-	kfree(iter);
-
-	tracing_stop();
-
-	ret = trace_test_buffer(tr, &count);
-	trace->reset(tr);
-	tracing_start();
-
-	if (!ret && !count) {
-		printk(KERN_CONT "no entries found..");
-		ret = -1;
-	}
-
-	return ret;
-}
-#endif /* CONFIG_HW_BRANCH_TRACER */
-
 #ifdef CONFIG_KSYM_TRACER
 static int ksym_selftest_dummy;
 
diff --git a/kernel/user.c b/kernel/user.c
index 766467b3bcb7..8e1c8c0a496c 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -16,7 +16,6 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/user_namespace.h>
-#include "cred-internals.h"
 
 struct user_namespace init_user_ns = {
 	.kref = {
@@ -137,9 +136,7 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 	struct hlist_head *hashent = uidhashentry(ns, uid);
 	struct user_struct *up, *new;
 
-	/* Make uid_hash_find() + uids_user_create() + uid_hash_insert()
-	 * atomic.
-	 */
+	/* Make uid_hash_find() + uid_hash_insert() atomic. */
 	spin_lock_irq(&uidhash_lock);
 	up = uid_hash_find(uid, hashent);
 	spin_unlock_irq(&uidhash_lock);
@@ -161,11 +158,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 		spin_lock_irq(&uidhash_lock);
 		up = uid_hash_find(uid, hashent);
 		if (up) {
-			/* This case is not possible when CONFIG_USER_SCHED
-			 * is defined, since we serialize alloc_uid() using
-			 * uids_mutex. Hence no need to call
-			 * sched_destroy_user() or remove_user_sysfs_dir().
-			 */
 			key_put(new->uid_keyring);
 			key_put(new->session_keyring);
 			kmem_cache_free(uid_cachep, new);
@@ -178,8 +170,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 
 	return up;
 
-	put_user_ns(new->user_ns);
-	kmem_cache_free(uid_cachep, new);
 out_unlock:
 	return NULL;
 }
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index b862b30369ff..bf007a43c053 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -774,7 +774,7 @@ static int __init fixup_free(void *addr, enum debug_obj_state state)
 	}
 }
 
-static int
+static int __init
 check_results(void *addr, enum debug_obj_state state, int fixups, int warnings)
 {
 	struct debug_bucket *db;
@@ -917,7 +917,7 @@ void __init debug_objects_early_init(void)
 /*
  * Convert the statically allocated objects to dynamic ones:
  */
-static int debug_objects_replace_static_objects(void)
+static int __init debug_objects_replace_static_objects(void)
 {
 	struct debug_bucket *db = obj_hash;
 	struct hlist_node *node, *tmp;
diff --git a/lib/rbtree.c b/lib/rbtree.c
index e2aa3be29858..15e10b1afdd2 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -44,6 +44,11 @@ static void __rb_rotate_left(struct rb_node *node, struct rb_root *root)
 	else
 		root->rb_node = right;
 	rb_set_parent(node, right);
+
+	if (root->augment_cb) {
+		root->augment_cb(node);
+		root->augment_cb(right);
+	}
 }
 
 static void __rb_rotate_right(struct rb_node *node, struct rb_root *root)
@@ -67,12 +72,20 @@ static void __rb_rotate_right(struct rb_node *node, struct rb_root *root)
 	else
 		root->rb_node = left;
 	rb_set_parent(node, left);
+
+	if (root->augment_cb) {
+		root->augment_cb(node);
+		root->augment_cb(left);
+	}
 }
 
 void rb_insert_color(struct rb_node *node, struct rb_root *root)
 {
 	struct rb_node *parent, *gparent;
 
+	if (root->augment_cb)
+		root->augment_cb(node);
+
 	while ((parent = rb_parent(node)) && rb_is_red(parent))
 	{
 		gparent = rb_parent(parent);
@@ -227,12 +240,15 @@ void rb_erase(struct rb_node *node, struct rb_root *root)
 	else
 	{
 		struct rb_node *old = node, *left;
+		int old_parent_cb = 0;
+		int successor_parent_cb = 0;
 
 		node = node->rb_right;
 		while ((left = node->rb_left) != NULL)
 			node = left;
 
 		if (rb_parent(old)) {
+			old_parent_cb = 1;
 			if (rb_parent(old)->rb_left == old)
 				rb_parent(old)->rb_left = node;
 			else
@@ -247,8 +263,10 @@ void rb_erase(struct rb_node *node, struct rb_root *root)
 		if (parent == old) {
 			parent = node;
 		} else {
+			successor_parent_cb = 1;
 			if (child)
 				rb_set_parent(child, parent);
+
 			parent->rb_left = child;
 
 			node->rb_right = old->rb_right;
@@ -259,6 +277,24 @@ void rb_erase(struct rb_node *node, struct rb_root *root)
 		node->rb_left = old->rb_left;
 		rb_set_parent(old->rb_left, node);
 
+		if (root->augment_cb) {
+			/*
+			 * Here, three different nodes can have new children.
+			 * The parent of the successor node that was selected
+			 * to replace the node to be erased.
+			 * The node that is getting erased and is now replaced
+			 * by its successor.
+			 * The parent of the node getting erased-replaced.
+			 */
+			if (successor_parent_cb)
+				root->augment_cb(parent);
+
+			root->augment_cb(node);
+
+			if (old_parent_cb)
+				root->augment_cb(rb_parent(old));
+		}
+
 		goto color;
 	}
 
@@ -267,15 +303,19 @@ void rb_erase(struct rb_node *node, struct rb_root *root)
 
 	if (child)
 		rb_set_parent(child, parent);
-	if (parent)
-	{
+
+	if (parent) {
 		if (parent->rb_left == node)
 			parent->rb_left = child;
 		else
 			parent->rb_right = child;
-	}
-	else
+
+		if (root->augment_cb)
+			root->augment_cb(parent);
+
+	} else {
 		root->rb_node = child;
+	}
 
  color:
 	if (color == RB_BLACK)
diff --git a/mm/mlock.c b/mm/mlock.c
index 8f4e2dfceec1..3f82720e0515 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -607,44 +607,3 @@ void user_shm_unlock(size_t size, struct user_struct *user)
 	spin_unlock(&shmlock_user_lock);
 	free_uid(user);
 }
-
-int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
-			  size_t size)
-{
-	unsigned long lim, vm, pgsz;
-	int error = -ENOMEM;
-
-	pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-	down_write(&mm->mmap_sem);
-
-	lim = ACCESS_ONCE(rlim[RLIMIT_AS].rlim_cur) >> PAGE_SHIFT;
-	vm   = mm->total_vm + pgsz;
-	if (lim < vm)
-		goto out;
-
-	lim = ACCESS_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur) >> PAGE_SHIFT;
-	vm   = mm->locked_vm + pgsz;
-	if (lim < vm)
-		goto out;
-
-	mm->total_vm  += pgsz;
-	mm->locked_vm += pgsz;
-
-	error = 0;
- out:
-	up_write(&mm->mmap_sem);
-	return error;
-}
-
-void refund_locked_memory(struct mm_struct *mm, size_t size)
-{
-	unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-	down_write(&mm->mmap_sem);
-
-	mm->total_vm  -= pgsz;
-	mm->locked_vm -= pgsz;
-
-	up_write(&mm->mmap_sem);
-}
diff --git a/sound/drivers/pcsp/pcsp.h b/sound/drivers/pcsp/pcsp.h
index 1e123077923d..4ff6c8cc5077 100644
--- a/sound/drivers/pcsp/pcsp.h
+++ b/sound/drivers/pcsp/pcsp.h
@@ -16,7 +16,7 @@
 #include <asm/i8253.h>
 #else
 #include <asm/8253pit.h>
-static DEFINE_SPINLOCK(i8253_lock);
+static DEFINE_RAW_SPINLOCK(i8253_lock);
 #endif
 
 #define PCSP_SOUND_VERSION 0x400	/* read 4.00 */
diff --git a/sound/drivers/pcsp/pcsp_input.c b/sound/drivers/pcsp/pcsp_input.c
index 0444cdeb4bec..b5e2b54c2604 100644
--- a/sound/drivers/pcsp/pcsp_input.c
+++ b/sound/drivers/pcsp/pcsp_input.c
@@ -21,7 +21,7 @@ static void pcspkr_do_sound(unsigned int count)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&i8253_lock, flags);
+	raw_spin_lock_irqsave(&i8253_lock, flags);
 
 	if (count) {
 		/* set command for counter 2, 2 byte write */
@@ -36,7 +36,7 @@ static void pcspkr_do_sound(unsigned int count)
 		outb(inb_p(0x61) & 0xFC, 0x61);
 	}
 
-	spin_unlock_irqrestore(&i8253_lock, flags);
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
 }
 
 void pcspkr_stop_sound(void)
diff --git a/sound/drivers/pcsp/pcsp_lib.c b/sound/drivers/pcsp/pcsp_lib.c
index d77ffa9a9387..ce9e7d170c0d 100644
--- a/sound/drivers/pcsp/pcsp_lib.c
+++ b/sound/drivers/pcsp/pcsp_lib.c
@@ -66,7 +66,7 @@ static u64 pcsp_timer_update(struct snd_pcsp *chip)
 	timer_cnt = val * CUR_DIV() / 256;
 
 	if (timer_cnt && chip->enable) {
-		spin_lock_irqsave(&i8253_lock, flags);
+		raw_spin_lock_irqsave(&i8253_lock, flags);
 		if (!nforce_wa) {
 			outb_p(chip->val61, 0x61);
 			outb_p(timer_cnt, 0x42);
@@ -75,7 +75,7 @@ static u64 pcsp_timer_update(struct snd_pcsp *chip)
 			outb(chip->val61 ^ 2, 0x61);
 			chip->thalf = 1;
 		}
-		spin_unlock_irqrestore(&i8253_lock, flags);
+		raw_spin_unlock_irqrestore(&i8253_lock, flags);
 	}
 
 	chip->ns_rem = PCSP_PERIOD_NS();
@@ -159,10 +159,10 @@ static int pcsp_start_playing(struct snd_pcsp *chip)
 		return -EIO;
 	}
 
-	spin_lock(&i8253_lock);
+	raw_spin_lock(&i8253_lock);
 	chip->val61 = inb(0x61) | 0x03;
 	outb_p(0x92, 0x43);	/* binary, mode 1, LSB only, ch 2 */
-	spin_unlock(&i8253_lock);
+	raw_spin_unlock(&i8253_lock);
 	atomic_set(&chip->timer_active, 1);
 	chip->thalf = 0;
 
@@ -179,11 +179,11 @@ static void pcsp_stop_playing(struct snd_pcsp *chip)
 		return;
 
 	atomic_set(&chip->timer_active, 0);
-	spin_lock(&i8253_lock);
+	raw_spin_lock(&i8253_lock);
 	/* restore the timer */
 	outb_p(0xb6, 0x43);	/* binary, mode 3, LSB/MSB, ch 2 */
 	outb(chip->val61 & 0xFC, 0x61);
-	spin_unlock(&i8253_lock);
+	raw_spin_unlock(&i8253_lock);
 }
 
 /*
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index ae525ac5a2ce..0181dddf6b61 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -19,12 +19,12 @@ COMMON OPTIONS
 -f::
 --format=::
 Specify format style.
-Current available format styles are,
+Current available format styles are:
 
 'default'::
 Default style. This is mainly for human reading.
 ---------------------
-% perf bench sched pipe                      # with no style specify
+% perf bench sched pipe                      # with no style specified
 (executing 1000000 pipe operations between two tasks)
         Total time:5.855 sec
                 5.855061 usecs/op
@@ -79,7 +79,7 @@ options (20 sender and receiver processes per group)
 
       Total time:0.308 sec
 
-% perf bench sched messaging -t -g 20        # be multi-thread,with 20 groups
+% perf bench sched messaging -t -g 20        # be multi-thread, with 20 groups
 (20 sender and receiver threads per group)
 (20 groups == 800 threads run)
 
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 34202b1be0bb..bb671b346774 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -57,6 +57,11 @@ OPTIONS
 --force::
 	Forcibly add events with existing name.
 
+-n::
+--dry-run::
+	Dry run. With this option, --add and --del doesn't execute actual
+	adding and removal operations.
+
 PROBE SYNTAX
 ------------
 Probe points are defined by following syntax.
@@ -80,7 +85,7 @@ LINE SYNTAX
 -----------
 Line range is descripted by following syntax.
 
- "FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]"
+ "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]"
 
 FUNC specifies the function name of showing lines. 'RLN' is the start line
 number from function entry line, and 'RLN2' is the end line number. As same as
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 1ce79198997b..8417644a6166 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -12,7 +12,7 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-There's four variants of perf sched:
+There are four variants of perf sched:
 
   'perf sched record <command>' to record the scheduling events
   of an arbitrary workload.
@@ -27,7 +27,7 @@ There's four variants of perf sched:
   via perf sched record. (this is done by starting up mockup threads
   that mimic the workload based on the events in the trace. These
   threads can then replay the timings (CPU runtime and sleep patterns)
-  of the workload as it occured when it was recorded - and can repeat
+  of the workload as it occurred when it was recorded - and can repeat
   it a number of times, measuring its performance.)
 
 OPTIONS
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index bc0f670a8338..57b3569716dd 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -1,3 +1,7 @@
+ifeq ("$(origin O)", "command line")
+	OUTPUT := $(O)/
+endif
+
 # The default target of this Makefile is...
 all::
 
@@ -150,10 +154,17 @@ all::
 # Define LDFLAGS=-static to build a static binary.
 #
 # Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds.
+#
+# Define NO_DWARF if you do not want debug-info analysis feature at all.
 
-PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
-	@$(SHELL_PATH) util/PERF-VERSION-GEN
--include PERF-VERSION-FILE
+$(shell sh -c 'mkdir -p $(OUTPUT)scripts/python/Perf-Trace-Util/' 2> /dev/null)
+$(shell sh -c 'mkdir -p $(OUTPUT)scripts/perl/Perf-Trace-Util/' 2> /dev/null)
+$(shell sh -c 'mkdir -p $(OUTPUT)util/scripting-engines/' 2> /dev/null)
+$(shell sh -c 'mkdir $(OUTPUT)bench' 2> /dev/null)
+
+$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
+	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
+-include $(OUTPUT)PERF-VERSION-FILE
 
 uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not')
 uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not')
@@ -308,7 +319,7 @@ PROGRAMS += $(EXTRA_PROGRAMS)
 #
 # Single 'perf' binary right now:
 #
-PROGRAMS += perf
+PROGRAMS += $(OUTPUT)perf
 
 # List built-in command $C whose implementation cmd_$C() is not in
 # builtin-$C.o but is linked in as part of some other command.
@@ -318,7 +329,7 @@ PROGRAMS += perf
 ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
 
 # what 'all' will build but not install in perfexecdir
-OTHER_PROGRAMS = perf$X
+OTHER_PROGRAMS = $(OUTPUT)perf$X
 
 # Set paths to tools early so that they can be used for version tests.
 ifndef SHELL_PATH
@@ -330,7 +341,7 @@ endif
 
 export PERL_PATH
 
-LIB_FILE=libperf.a
+LIB_FILE=$(OUTPUT)libperf.a
 
 LIB_H += ../../include/linux/perf_event.h
 LIB_H += ../../include/linux/rbtree.h
@@ -375,7 +386,6 @@ LIB_H += util/header.h
 LIB_H += util/help.h
 LIB_H += util/session.h
 LIB_H += util/strbuf.h
-LIB_H += util/string.h
 LIB_H += util/strlist.h
 LIB_H += util/svghelper.h
 LIB_H += util/run-command.h
@@ -391,77 +401,77 @@ LIB_H += util/probe-finder.h
 LIB_H += util/probe-event.h
 LIB_H += util/cpumap.h
 
-LIB_OBJS += util/abspath.o
-LIB_OBJS += util/alias.o
-LIB_OBJS += util/build-id.o
-LIB_OBJS += util/config.o
-LIB_OBJS += util/ctype.o
-LIB_OBJS += util/debugfs.o
-LIB_OBJS += util/environment.o
-LIB_OBJS += util/event.o
-LIB_OBJS += util/exec_cmd.o
-LIB_OBJS += util/help.o
-LIB_OBJS += util/levenshtein.o
-LIB_OBJS += util/parse-options.o
-LIB_OBJS += util/parse-events.o
-LIB_OBJS += util/path.o
-LIB_OBJS += util/rbtree.o
-LIB_OBJS += util/bitmap.o
-LIB_OBJS += util/hweight.o
-LIB_OBJS += util/find_next_bit.o
-LIB_OBJS += util/run-command.o
-LIB_OBJS += util/quote.o
-LIB_OBJS += util/strbuf.o
-LIB_OBJS += util/string.o
-LIB_OBJS += util/strlist.o
-LIB_OBJS += util/usage.o
-LIB_OBJS += util/wrapper.o
-LIB_OBJS += util/sigchain.o
-LIB_OBJS += util/symbol.o
-LIB_OBJS += util/color.o
-LIB_OBJS += util/pager.o
-LIB_OBJS += util/header.o
-LIB_OBJS += util/callchain.o
-LIB_OBJS += util/values.o
-LIB_OBJS += util/debug.o
-LIB_OBJS += util/map.o
-LIB_OBJS += util/session.o
-LIB_OBJS += util/thread.o
-LIB_OBJS += util/trace-event-parse.o
-LIB_OBJS += util/trace-event-read.o
-LIB_OBJS += util/trace-event-info.o
-LIB_OBJS += util/trace-event-scripting.o
-LIB_OBJS += util/svghelper.o
-LIB_OBJS += util/sort.o
-LIB_OBJS += util/hist.o
-LIB_OBJS += util/probe-event.o
-LIB_OBJS += util/util.o
-LIB_OBJS += util/cpumap.o
-
-BUILTIN_OBJS += builtin-annotate.o
-
-BUILTIN_OBJS += builtin-bench.o
+LIB_OBJS += $(OUTPUT)util/abspath.o
+LIB_OBJS += $(OUTPUT)util/alias.o
+LIB_OBJS += $(OUTPUT)util/build-id.o
+LIB_OBJS += $(OUTPUT)util/config.o
+LIB_OBJS += $(OUTPUT)util/ctype.o
+LIB_OBJS += $(OUTPUT)util/debugfs.o
+LIB_OBJS += $(OUTPUT)util/environment.o
+LIB_OBJS += $(OUTPUT)util/event.o
+LIB_OBJS += $(OUTPUT)util/exec_cmd.o
+LIB_OBJS += $(OUTPUT)util/help.o
+LIB_OBJS += $(OUTPUT)util/levenshtein.o
+LIB_OBJS += $(OUTPUT)util/parse-options.o
+LIB_OBJS += $(OUTPUT)util/parse-events.o
+LIB_OBJS += $(OUTPUT)util/path.o
+LIB_OBJS += $(OUTPUT)util/rbtree.o
+LIB_OBJS += $(OUTPUT)util/bitmap.o
+LIB_OBJS += $(OUTPUT)util/hweight.o
+LIB_OBJS += $(OUTPUT)util/find_next_bit.o
+LIB_OBJS += $(OUTPUT)util/run-command.o
+LIB_OBJS += $(OUTPUT)util/quote.o
+LIB_OBJS += $(OUTPUT)util/strbuf.o
+LIB_OBJS += $(OUTPUT)util/string.o
+LIB_OBJS += $(OUTPUT)util/strlist.o
+LIB_OBJS += $(OUTPUT)util/usage.o
+LIB_OBJS += $(OUTPUT)util/wrapper.o
+LIB_OBJS += $(OUTPUT)util/sigchain.o
+LIB_OBJS += $(OUTPUT)util/symbol.o
+LIB_OBJS += $(OUTPUT)util/color.o
+LIB_OBJS += $(OUTPUT)util/pager.o
+LIB_OBJS += $(OUTPUT)util/header.o
+LIB_OBJS += $(OUTPUT)util/callchain.o
+LIB_OBJS += $(OUTPUT)util/values.o
+LIB_OBJS += $(OUTPUT)util/debug.o
+LIB_OBJS += $(OUTPUT)util/map.o
+LIB_OBJS += $(OUTPUT)util/session.o
+LIB_OBJS += $(OUTPUT)util/thread.o
+LIB_OBJS += $(OUTPUT)util/trace-event-parse.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
+LIB_OBJS += $(OUTPUT)util/svghelper.o
+LIB_OBJS += $(OUTPUT)util/sort.o
+LIB_OBJS += $(OUTPUT)util/hist.o
+LIB_OBJS += $(OUTPUT)util/probe-event.o
+LIB_OBJS += $(OUTPUT)util/util.o
+LIB_OBJS += $(OUTPUT)util/cpumap.o
+
+BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
+
+BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
 
 # Benchmark modules
-BUILTIN_OBJS += bench/sched-messaging.o
-BUILTIN_OBJS += bench/sched-pipe.o
-BUILTIN_OBJS += bench/mem-memcpy.o
-
-BUILTIN_OBJS += builtin-diff.o
-BUILTIN_OBJS += builtin-help.o
-BUILTIN_OBJS += builtin-sched.o
-BUILTIN_OBJS += builtin-buildid-list.o
-BUILTIN_OBJS += builtin-buildid-cache.o
-BUILTIN_OBJS += builtin-list.o
-BUILTIN_OBJS += builtin-record.o
-BUILTIN_OBJS += builtin-report.o
-BUILTIN_OBJS += builtin-stat.o
-BUILTIN_OBJS += builtin-timechart.o
-BUILTIN_OBJS += builtin-top.o
-BUILTIN_OBJS += builtin-trace.o
-BUILTIN_OBJS += builtin-probe.o
-BUILTIN_OBJS += builtin-kmem.o
-BUILTIN_OBJS += builtin-lock.o
+BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
+BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
+
+BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
+BUILTIN_OBJS += $(OUTPUT)builtin-help.o
+BUILTIN_OBJS += $(OUTPUT)builtin-sched.o
+BUILTIN_OBJS += $(OUTPUT)builtin-buildid-list.o
+BUILTIN_OBJS += $(OUTPUT)builtin-buildid-cache.o
+BUILTIN_OBJS += $(OUTPUT)builtin-list.o
+BUILTIN_OBJS += $(OUTPUT)builtin-record.o
+BUILTIN_OBJS += $(OUTPUT)builtin-report.o
+BUILTIN_OBJS += $(OUTPUT)builtin-stat.o
+BUILTIN_OBJS += $(OUTPUT)builtin-timechart.o
+BUILTIN_OBJS += $(OUTPUT)builtin-top.o
+BUILTIN_OBJS += $(OUTPUT)builtin-trace.o
+BUILTIN_OBJS += $(OUTPUT)builtin-probe.o
+BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o
+BUILTIN_OBJS += $(OUTPUT)builtin-lock.o
 
 PERFLIBS = $(LIB_FILE)
 
@@ -492,6 +502,10 @@ ifeq ($(uname_S),Darwin)
 	PTHREAD_LIBS =
 endif
 
+ifneq ($(OUTPUT),)
+	BASIC_CFLAGS += -I$(OUTPUT)
+endif
+
 ifeq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
 ifneq ($(shell sh -c "(echo '\#include <gnu/libc-version.h>'; echo 'int main(void) { const char * version = gnu_get_libc_version(); return (long)version; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
 	msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
@@ -506,11 +520,20 @@ endif
 
 ifneq ($(shell sh -c "(echo '\#include <dwarf.h>'; echo '\#include <libdw.h>'; echo 'int main(void) { Dwarf *dbg; dbg = dwarf_begin(0, DWARF_C_READ); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -I/usr/include/elfutils -ldw -lelf -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
 	msg := $(warning No libdw.h found or old libdw.h found, disables dwarf support. Please install elfutils-devel/elfutils-dev);
-	BASIC_CFLAGS += -DNO_DWARF_SUPPORT
 else
-	BASIC_CFLAGS += -I/usr/include/elfutils
+ifndef NO_DWARF
+	BASIC_CFLAGS += -I/usr/include/elfutils -DDWARF_SUPPORT
 	EXTLIBS += -lelf -ldw
-	LIB_OBJS += util/probe-finder.o
+	LIB_OBJS += $(OUTPUT)util/probe-finder.o
+endif
+endif
+
+ifneq ($(shell sh -c "(echo '\#include <newt.h>'; echo 'int main(void) { newtInit(); newtCls(); return newtFinished(); }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -lnewt -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+	msg := $(warning newt not found, disables TUI support. Please install newt-devel or libnewt-dev);
+	BASIC_CFLAGS += -DNO_NEWT_SUPPORT
+else
+	EXTLIBS += -lnewt
+	LIB_OBJS += $(OUTPUT)util/newt.o
 endif
 
 ifndef NO_LIBPERL
@@ -522,8 +545,8 @@ ifneq ($(shell sh -c "(echo '\#include <EXTERN.h>'; echo '\#include <perl.h>'; e
 	BASIC_CFLAGS += -DNO_LIBPERL
 else
 	ALL_LDFLAGS += $(PERL_EMBED_LDOPTS)
-	LIB_OBJS += util/scripting-engines/trace-event-perl.o
-	LIB_OBJS += scripts/perl/Perf-Trace-Util/Context.o
+	LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o
+	LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o
 endif
 
 ifndef NO_LIBPYTHON
@@ -531,12 +554,12 @@ PYTHON_EMBED_LDOPTS = `python-config --ldflags 2>/dev/null`
 PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null`
 endif
 
-ifneq ($(shell sh -c "(echo '\#include <Python.h>'; echo 'int main(void) { Py_Initialize(); return 0; }') | $(CC) -x c - $(PYTHON_EMBED_CCOPTS) -o /dev/null $(PYTHON_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y)
+ifneq ($(shell sh -c "(echo '\#include <Python.h>'; echo 'int main(void) { Py_Initialize(); return 0; }') | $(CC) -x c - $(PYTHON_EMBED_CCOPTS) -o $(BITBUCKET) $(PYTHON_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y)
 	BASIC_CFLAGS += -DNO_LIBPYTHON
 else
 	ALL_LDFLAGS += $(PYTHON_EMBED_LDOPTS)
-	LIB_OBJS += util/scripting-engines/trace-event-python.o
-	LIB_OBJS += scripts/python/Perf-Trace-Util/Context.o
+	LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
+	LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
 endif
 
 ifdef NO_DEMANGLE
@@ -607,53 +630,53 @@ ifdef NO_C99_FORMAT
 endif
 ifdef SNPRINTF_RETURNS_BOGUS
 	COMPAT_CFLAGS += -DSNPRINTF_RETURNS_BOGUS
-	COMPAT_OBJS += compat/snprintf.o
+	COMPAT_OBJS += $(OUTPUT)compat/snprintf.o
 endif
 ifdef FREAD_READS_DIRECTORIES
 	COMPAT_CFLAGS += -DFREAD_READS_DIRECTORIES
-	COMPAT_OBJS += compat/fopen.o
+	COMPAT_OBJS += $(OUTPUT)compat/fopen.o
 endif
 ifdef NO_SYMLINK_HEAD
 	BASIC_CFLAGS += -DNO_SYMLINK_HEAD
 endif
 ifdef NO_STRCASESTR
 	COMPAT_CFLAGS += -DNO_STRCASESTR
-	COMPAT_OBJS += compat/strcasestr.o
+	COMPAT_OBJS += $(OUTPUT)compat/strcasestr.o
 endif
 ifdef NO_STRTOUMAX
 	COMPAT_CFLAGS += -DNO_STRTOUMAX
-	COMPAT_OBJS += compat/strtoumax.o
+	COMPAT_OBJS += $(OUTPUT)compat/strtoumax.o
 endif
 ifdef NO_STRTOULL
 	COMPAT_CFLAGS += -DNO_STRTOULL
 endif
 ifdef NO_SETENV
 	COMPAT_CFLAGS += -DNO_SETENV
-	COMPAT_OBJS += compat/setenv.o
+	COMPAT_OBJS += $(OUTPUT)compat/setenv.o
 endif
 ifdef NO_MKDTEMP
 	COMPAT_CFLAGS += -DNO_MKDTEMP
-	COMPAT_OBJS += compat/mkdtemp.o
+	COMPAT_OBJS += $(OUTPUT)compat/mkdtemp.o
 endif
 ifdef NO_UNSETENV
 	COMPAT_CFLAGS += -DNO_UNSETENV
-	COMPAT_OBJS += compat/unsetenv.o
+	COMPAT_OBJS += $(OUTPUT)compat/unsetenv.o
 endif
 ifdef NO_SYS_SELECT_H
 	BASIC_CFLAGS += -DNO_SYS_SELECT_H
 endif
 ifdef NO_MMAP
 	COMPAT_CFLAGS += -DNO_MMAP
-	COMPAT_OBJS += compat/mmap.o
+	COMPAT_OBJS += $(OUTPUT)compat/mmap.o
 else
 	ifdef USE_WIN32_MMAP
 		COMPAT_CFLAGS += -DUSE_WIN32_MMAP
-		COMPAT_OBJS += compat/win32mmap.o
+		COMPAT_OBJS += $(OUTPUT)compat/win32mmap.o
 	endif
 endif
 ifdef NO_PREAD
 	COMPAT_CFLAGS += -DNO_PREAD
-	COMPAT_OBJS += compat/pread.o
+	COMPAT_OBJS += $(OUTPUT)compat/pread.o
 endif
 ifdef NO_FAST_WORKING_DIRECTORY
 	BASIC_CFLAGS += -DNO_FAST_WORKING_DIRECTORY
@@ -675,10 +698,10 @@ else
 endif
 endif
 ifdef NO_INET_NTOP
-	LIB_OBJS += compat/inet_ntop.o
+	LIB_OBJS += $(OUTPUT)compat/inet_ntop.o
 endif
 ifdef NO_INET_PTON
-	LIB_OBJS += compat/inet_pton.o
+	LIB_OBJS += $(OUTPUT)compat/inet_pton.o
 endif
 
 ifdef NO_ICONV
@@ -695,15 +718,15 @@ endif
 
 ifdef PPC_SHA1
 	SHA1_HEADER = "ppc/sha1.h"
-	LIB_OBJS += ppc/sha1.o ppc/sha1ppc.o
+	LIB_OBJS += $(OUTPUT)ppc/sha1.o ppc/sha1ppc.o
 else
 ifdef ARM_SHA1
 	SHA1_HEADER = "arm/sha1.h"
-	LIB_OBJS += arm/sha1.o arm/sha1_arm.o
+	LIB_OBJS += $(OUTPUT)arm/sha1.o $(OUTPUT)arm/sha1_arm.o
 else
 ifdef MOZILLA_SHA1
 	SHA1_HEADER = "mozilla-sha1/sha1.h"
-	LIB_OBJS += mozilla-sha1/sha1.o
+	LIB_OBJS += $(OUTPUT)mozilla-sha1/sha1.o
 else
 	SHA1_HEADER = <openssl/sha.h>
 	EXTLIBS += $(LIB_4_CRYPTO)
@@ -715,15 +738,15 @@ ifdef NO_PERL_MAKEMAKER
 endif
 ifdef NO_HSTRERROR
 	COMPAT_CFLAGS += -DNO_HSTRERROR
-	COMPAT_OBJS += compat/hstrerror.o
+	COMPAT_OBJS += $(OUTPUT)compat/hstrerror.o
 endif
 ifdef NO_MEMMEM
 	COMPAT_CFLAGS += -DNO_MEMMEM
-	COMPAT_OBJS += compat/memmem.o
+	COMPAT_OBJS += $(OUTPUT)compat/memmem.o
 endif
 ifdef INTERNAL_QSORT
 	COMPAT_CFLAGS += -DINTERNAL_QSORT
-	COMPAT_OBJS += compat/qsort.o
+	COMPAT_OBJS += $(OUTPUT)compat/qsort.o
 endif
 ifdef RUNTIME_PREFIX
 	COMPAT_CFLAGS += -DRUNTIME_PREFIX
@@ -803,7 +826,7 @@ export TAR INSTALL DESTDIR SHELL_PATH
 
 SHELL = $(SHELL_PATH)
 
-all:: .perf.dev.null shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) PERF-BUILD-OPTIONS
+all:: .perf.dev.null shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) $(OUTPUT)PERF-BUILD-OPTIONS
 ifneq (,$X)
 	$(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), test '$p' -ef '$p$X' || $(RM) '$p';)
 endif
@@ -815,39 +838,39 @@ please_set_SHELL_PATH_to_a_more_modern_shell:
 
 shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell
 
-strip: $(PROGRAMS) perf$X
-	$(STRIP) $(STRIP_OPTS) $(PROGRAMS) perf$X
+strip: $(PROGRAMS) $(OUTPUT)perf$X
+	$(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf$X
 
-perf.o: perf.c common-cmds.h PERF-CFLAGS
+$(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -DPERF_VERSION='"$(PERF_VERSION)"' \
 		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
-		$(ALL_CFLAGS) -c $(filter %.c,$^)
+		$(ALL_CFLAGS) -c $(filter %.c,$^) -o $@
 
-perf$X: perf.o $(BUILTIN_OBJS) $(PERFLIBS)
-	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ perf.o \
+$(OUTPUT)perf$X: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
+	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(OUTPUT)perf.o \
 		$(BUILTIN_OBJS) $(ALL_LDFLAGS) $(LIBS)
 
-builtin-help.o: builtin-help.c common-cmds.h PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) \
+$(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
 		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
 		'-DPERF_MAN_PATH="$(mandir_SQ)"' \
 		'-DPERF_INFO_PATH="$(infodir_SQ)"' $<
 
-builtin-timechart.o: builtin-timechart.c common-cmds.h PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) \
+$(OUTPUT)builtin-timechart.o: builtin-timechart.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
 		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
 		'-DPERF_MAN_PATH="$(mandir_SQ)"' \
 		'-DPERF_INFO_PATH="$(infodir_SQ)"' $<
 
-$(BUILT_INS): perf$X
+$(BUILT_INS): $(OUTPUT)perf$X
 	$(QUIET_BUILT_IN)$(RM) $@ && \
 	ln perf$X $@ 2>/dev/null || \
 	ln -s perf$X $@ 2>/dev/null || \
 	cp perf$X $@
 
-common-cmds.h: util/generate-cmdlist.sh command-list.txt
+$(OUTPUT)common-cmds.h: util/generate-cmdlist.sh command-list.txt
 
-common-cmds.h: $(wildcard Documentation/perf-*.txt)
+$(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
 	$(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@
 
 $(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh
@@ -859,7 +882,7 @@ $(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh
 	    -e 's/@@NO_CURL@@/$(NO_CURL)/g' \
 	    $@.sh >$@+ && \
 	chmod +x $@+ && \
-	mv $@+ $@
+	mv $@+ $(OUTPUT)$@
 
 configure: configure.ac
 	$(QUIET_GEN)$(RM) $@ $<+ && \
@@ -869,60 +892,60 @@ configure: configure.ac
 	$(RM) $<+
 
 # These can record PERF_VERSION
-perf.o perf.spec \
+$(OUTPUT)perf.o perf.spec \
 	$(patsubst %.sh,%,$(SCRIPT_SH)) \
 	$(patsubst %.perl,%,$(SCRIPT_PERL)) \
-	: PERF-VERSION-FILE
+	: $(OUTPUT)PERF-VERSION-FILE
 
-%.o: %.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) $<
-%.s: %.c PERF-CFLAGS
+$(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+$(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $<
-%.o: %.S
-	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) $<
+$(OUTPUT)%.o: %.S
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
 
-util/exec_cmd.o: util/exec_cmd.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) \
+$(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
 		'-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \
 		'-DBINDIR="$(bindir_relative_SQ)"' \
 		'-DPREFIX="$(prefix_SQ)"' \
 		$<
 
-builtin-init-db.o: builtin-init-db.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) -DDEFAULT_PERF_TEMPLATE_DIR='"$(template_dir_SQ)"' $<
+$(OUTPUT)builtin-init-db.o: builtin-init-db.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DDEFAULT_PERF_TEMPLATE_DIR='"$(template_dir_SQ)"' $<
 
-util/config.o: util/config.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+$(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
-util/rbtree.o: ../../lib/rbtree.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o util/rbtree.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
 # some perf warning policies can't fit to lib/bitmap.c, eg: it warns about variable shadowing
 # from <string.h> that comes from kernel headers wrapping.
 KBITMAP_FLAGS=`echo $(ALL_CFLAGS) | sed s/-Wshadow// | sed s/-Wswitch-default// | sed s/-Wextra//`
 
-util/bitmap.o: ../../lib/bitmap.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o util/bitmap.o -c $(KBITMAP_FLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+$(OUTPUT)util/bitmap.o: ../../lib/bitmap.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(KBITMAP_FLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
-util/hweight.o: ../../lib/hweight.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o util/hweight.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+$(OUTPUT)util/hweight.o: ../../lib/hweight.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
-util/find_next_bit.o: ../../lib/find_next_bit.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o util/find_next_bit.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+$(OUTPUT)util/find_next_bit.o: ../../lib/find_next_bit.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
-util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o util/scripting-engines/trace-event-perl.o -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
+$(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 $<
 
-scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o scripts/perl/Perf-Trace-Util/Context.o -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
+$(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
 
-util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o util/scripting-engines/trace-event-python.o -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
+$(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
 
-scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o scripts/python/Perf-Trace-Util/Context.o -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
+$(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
 
-perf-%$X: %.o $(PERFLIBS)
+$(OUTPUT)perf-%$X: %.o $(PERFLIBS)
 	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
 
 $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
@@ -963,17 +986,17 @@ cscope:
 TRACK_CFLAGS = $(subst ','\'',$(ALL_CFLAGS)):\
              $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ)
 
-PERF-CFLAGS: .FORCE-PERF-CFLAGS
+$(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS
 	@FLAGS='$(TRACK_CFLAGS)'; \
-	    if test x"$$FLAGS" != x"`cat PERF-CFLAGS 2>/dev/null`" ; then \
+	    if test x"$$FLAGS" != x"`cat $(OUTPUT)PERF-CFLAGS 2>/dev/null`" ; then \
 		echo 1>&2 "    * new build flags or prefix"; \
-		echo "$$FLAGS" >PERF-CFLAGS; \
+		echo "$$FLAGS" >$(OUTPUT)PERF-CFLAGS; \
             fi
 
 # We need to apply sq twice, once to protect from the shell
-# that runs PERF-BUILD-OPTIONS, and then again to protect it
+# that runs $(OUTPUT)PERF-BUILD-OPTIONS, and then again to protect it
 # and the first level quoting from the shell that runs "echo".
-PERF-BUILD-OPTIONS: .FORCE-PERF-BUILD-OPTIONS
+$(OUTPUT)PERF-BUILD-OPTIONS: .FORCE-PERF-BUILD-OPTIONS
 	@echo SHELL_PATH=\''$(subst ','\'',$(SHELL_PATH_SQ))'\' >$@
 	@echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@
 	@echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@
@@ -994,7 +1017,7 @@ all:: $(TEST_PROGRAMS)
 
 export NO_SVN_TESTS
 
-check: common-cmds.h
+check: $(OUTPUT)common-cmds.h
 	if sparse; \
 	then \
 		for i in *.c */*.c; \
@@ -1028,10 +1051,10 @@ export perfexec_instdir
 
 install: all
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
-	$(INSTALL) perf$X '$(DESTDIR_SQ)$(bindir_SQ)'
+	$(INSTALL) $(OUTPUT)perf$X '$(DESTDIR_SQ)$(bindir_SQ)'
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
-	$(INSTALL) perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+	$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
 	$(INSTALL) scripts/perl/*.pl -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'
 	$(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
@@ -1045,7 +1068,7 @@ ifdef BUILT_INS
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(INSTALL) $(BUILT_INS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 ifneq (,$X)
-	$(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), $(RM) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$p';)
+	$(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) $(OUTPUT)perf$X)), $(RM) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$p';)
 endif
 endif
 
@@ -1129,14 +1152,14 @@ clean:
 	$(RM) *.o */*.o */*/*.o */*/*/*.o $(LIB_FILE)
 	$(RM) $(ALL_PROGRAMS) $(BUILT_INS) perf$X
 	$(RM) $(TEST_PROGRAMS)
-	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo common-cmds.h TAGS tags cscope*
+	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
 	$(RM) -r autom4te.cache
 	$(RM) config.log config.mak.autogen config.mak.append config.status config.cache
 	$(RM) -r $(PERF_TARNAME) .doc-tmp-dir
 	$(RM) $(PERF_TARNAME).tar.gz perf-core_$(PERF_VERSION)-*.tar.gz
 	$(RM) $(htmldocs).tar.gz $(manpages).tar.gz
 	$(MAKE) -C Documentation/ clean
-	$(RM) PERF-VERSION-FILE PERF-CFLAGS PERF-BUILD-OPTIONS
+	$(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-BUILD-OPTIONS
 
 .PHONY: all install clean strip
 .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 89773178e894..52e646e3e873 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -10,7 +10,6 @@
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/parse-options.h"
-#include "../util/string.h"
 #include "../util/header.h"
 #include "bench.h"
 
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 4f77c7c27640..d9ab3ce446ac 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -93,7 +93,7 @@ int bench_sched_pipe(int argc, const char **argv,
 
 	switch (bench_format) {
 	case BENCH_FORMAT_DEFAULT:
-		printf("# Extecuted %d pipe operations between two tasks\n\n",
+		printf("# Executed %d pipe operations between two tasks\n\n",
 			loops);
 
 		result_usec = diff.tv_sec * 1000000;
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 6ad7148451c5..ee0d91726991 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -14,7 +14,6 @@
 #include "util/cache.h"
 #include <linux/rbtree.h>
 #include "util/symbol.h"
-#include "util/string.h"
 
 #include "perf.h"
 #include "util/debug.h"
@@ -69,13 +68,13 @@ static int sym__alloc_hist(struct symbol *self)
 static int annotate__hist_hit(struct hist_entry *he, u64 ip)
 {
 	unsigned int sym_size, offset;
-	struct symbol *sym = he->sym;
+	struct symbol *sym = he->ms.sym;
 	struct sym_priv *priv;
 	struct sym_hist *h;
 
 	he->count++;
 
-	if (!sym || !he->map)
+	if (!sym || !he->ms.map)
 		return 0;
 
 	priv = symbol__priv(sym);
@@ -85,7 +84,7 @@ static int annotate__hist_hit(struct hist_entry *he, u64 ip)
 	sym_size = sym->end - sym->start;
 	offset = ip - sym->start;
 
-	pr_debug3("%s: ip=%#Lx\n", __func__, he->map->unmap_ip(he->map, ip));
+	pr_debug3("%s: ip=%#Lx\n", __func__, he->ms.map->unmap_ip(he->ms.map, ip));
 
 	if (offset >= sym_size)
 		return 0;
@@ -94,8 +93,8 @@ static int annotate__hist_hit(struct hist_entry *he, u64 ip)
 	h->sum++;
 	h->ip[offset]++;
 
-	pr_debug3("%#Lx %s: count++ [ip: %#Lx, %#Lx] => %Ld\n", he->sym->start,
-		  he->sym->name, ip, ip - he->sym->start, h->ip[offset]);
+	pr_debug3("%#Lx %s: count++ [ip: %#Lx, %#Lx] => %Ld\n", he->ms.sym->start,
+		  he->ms.sym->name, ip, ip - he->ms.sym->start, h->ip[offset]);
 	return 0;
 }
 
@@ -187,7 +186,7 @@ static struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
 static int parse_line(FILE *file, struct hist_entry *he,
 		      struct list_head *head)
 {
-	struct symbol *sym = he->sym;
+	struct symbol *sym = he->ms.sym;
 	struct objdump_line *objdump_line;
 	char *line = NULL, *tmp, *tmp2;
 	size_t line_len;
@@ -226,7 +225,7 @@ static int parse_line(FILE *file, struct hist_entry *he,
 	}
 
 	if (line_ip != -1) {
-		u64 start = map__rip_2objdump(he->map, sym->start);
+		u64 start = map__rip_2objdump(he->ms.map, sym->start);
 		offset = line_ip - start;
 	}
 
@@ -244,7 +243,7 @@ static int objdump_line__print(struct objdump_line *self,
 			       struct list_head *head,
 			       struct hist_entry *he, u64 len)
 {
-	struct symbol *sym = he->sym;
+	struct symbol *sym = he->ms.sym;
 	static const char *prev_line;
 	static const char *prev_color;
 
@@ -327,7 +326,7 @@ static void insert_source_line(struct sym_ext *sym_ext)
 
 static void free_source_line(struct hist_entry *he, int len)
 {
-	struct sym_priv *priv = symbol__priv(he->sym);
+	struct sym_priv *priv = symbol__priv(he->ms.sym);
 	struct sym_ext *sym_ext = priv->ext;
 	int i;
 
@@ -346,7 +345,7 @@ static void free_source_line(struct hist_entry *he, int len)
 static void
 get_source_line(struct hist_entry *he, int len, const char *filename)
 {
-	struct symbol *sym = he->sym;
+	struct symbol *sym = he->ms.sym;
 	u64 start;
 	int i;
 	char cmd[PATH_MAX * 2];
@@ -361,7 +360,7 @@ get_source_line(struct hist_entry *he, int len, const char *filename)
 	if (!priv->ext)
 		return;
 
-	start = he->map->unmap_ip(he->map, sym->start);
+	start = he->ms.map->unmap_ip(he->ms.map, sym->start);
 
 	for (i = 0; i < len; i++) {
 		char *path = NULL;
@@ -425,7 +424,7 @@ static void print_summary(const char *filename)
 
 static void hist_entry__print_hits(struct hist_entry *self)
 {
-	struct symbol *sym = self->sym;
+	struct symbol *sym = self->ms.sym;
 	struct sym_priv *priv = symbol__priv(sym);
 	struct sym_hist *h = priv->hist;
 	u64 len = sym->end - sym->start, offset;
@@ -439,9 +438,9 @@ static void hist_entry__print_hits(struct hist_entry *self)
 
 static void annotate_sym(struct hist_entry *he)
 {
-	struct map *map = he->map;
+	struct map *map = he->ms.map;
 	struct dso *dso = map->dso;
-	struct symbol *sym = he->sym;
+	struct symbol *sym = he->ms.sym;
 	const char *filename = dso->long_name, *d_filename;
 	u64 len;
 	char command[PATH_MAX*2];
@@ -452,6 +451,16 @@ static void annotate_sym(struct hist_entry *he)
 	if (!filename)
 		return;
 
+	if (dso->origin == DSO__ORIG_KERNEL) {
+		if (dso->annotate_warned)
+			return;
+		dso->annotate_warned = 1;
+		pr_err("Can't annotate %s: No vmlinux file was found in the "
+		       "path:\n", sym->name);
+		vmlinux_path__fprintf(stderr);
+		return;
+	}
+
 	pr_debug("%s: filename=%s, sym=%s, start=%#Lx, end=%#Lx\n", __func__,
 		 filename, sym->name, map->unmap_ip(map, sym->start),
 		 map->unmap_ip(map, sym->end));
@@ -516,17 +525,17 @@ static void perf_session__find_annotations(struct perf_session *self)
 		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
 		struct sym_priv *priv;
 
-		if (he->sym == NULL)
+		if (he->ms.sym == NULL)
 			continue;
 
-		priv = symbol__priv(he->sym);
+		priv = symbol__priv(he->ms.sym);
 		if (priv->hist == NULL)
 			continue;
 
 		annotate_sym(he);
 		/*
 		 * Since we have a hist_entry per IP for the same symbol, free
-		 * he->sym->hist to signal we already processed this symbol.
+		 * he->ms.sym->hist to signal we already processed this symbol.
 		 */
 		free(priv->hist);
 		priv->hist = NULL;
@@ -581,6 +590,8 @@ static const char * const annotate_usage[] = {
 static const struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
+	OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
+		   "only consider symbols in these dsos"),
 	OPT_STRING('s', "symbol", &sym_hist_filter, "symbol",
 		    "symbol to annotate"),
 	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 924a9518931a..513aa8a55db6 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -363,19 +363,21 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 		struct alloc_stat *data = rb_entry(next, struct alloc_stat,
 						   node);
 		struct symbol *sym = NULL;
+		struct map *map;
 		char buf[BUFSIZ];
 		u64 addr;
 
 		if (is_caller) {
 			addr = data->call_site;
 			if (!raw_ip)
-				sym = map_groups__find_function(&session->kmaps, addr, NULL);
+				sym = map_groups__find_function(&session->kmaps,
+								addr, &map, NULL);
 		} else
 			addr = data->ptr;
 
 		if (sym != NULL)
 			snprintf(buf, sizeof(buf), "%s+%Lx", sym->name,
-				 addr - sym->start);
+				 addr - map->unmap_ip(map, sym->start));
 		else
 			snprintf(buf, sizeof(buf), "%#Lx", addr);
 		printf(" %-34s |", buf);
@@ -488,6 +490,9 @@ static int __cmd_kmem(void)
 	if (session == NULL)
 		return -ENOMEM;
 
+	if (perf_session__create_kernel_maps(session) < 0)
+		goto out_delete;
+
 	if (!perf_session__has_traces(session, "kmem record"))
 		goto out_delete;
 
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 152d6c9b1fa4..b3ba25a910fa 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -36,11 +36,9 @@
 #include "builtin.h"
 #include "util/util.h"
 #include "util/strlist.h"
-#include "util/event.h"
+#include "util/symbol.h"
 #include "util/debug.h"
 #include "util/debugfs.h"
-#include "util/symbol.h"
-#include "util/thread.h"
 #include "util/parse-options.h"
 #include "util/parse-events.h"	/* For debugfs_path */
 #include "util/probe-finder.h"
@@ -50,32 +48,29 @@
 
 /* Session management structure */
 static struct {
-	bool need_dwarf;
 	bool list_events;
 	bool force_add;
 	bool show_lines;
-	int nr_probe;
-	struct probe_point probes[MAX_PROBES];
+	int nevents;
+	struct perf_probe_event events[MAX_PROBES];
 	struct strlist *dellist;
-	struct map_groups kmap_groups;
-	struct map *kmaps[MAP__NR_TYPES];
 	struct line_range line_range;
-} session;
+} params;
 
 
 /* Parse an event definition. Note that any error must die. */
 static void parse_probe_event(const char *str)
 {
-	struct probe_point *pp = &session.probes[session.nr_probe];
+	struct perf_probe_event *pev = &params.events[params.nevents];
 
-	pr_debug("probe-definition(%d): %s\n", session.nr_probe, str);
-	if (++session.nr_probe == MAX_PROBES)
+	pr_debug("probe-definition(%d): %s\n", params.nevents, str);
+	if (++params.nevents == MAX_PROBES)
 		die("Too many probes (> %d) are specified.", MAX_PROBES);
 
-	/* Parse perf-probe event into probe_point */
-	parse_perf_probe_event(str, pp, &session.need_dwarf);
+	/* Parse a perf-probe command into event */
+	parse_perf_probe_command(str, pev);
 
-	pr_debug("%d arguments\n", pp->nr_args);
+	pr_debug("%d arguments\n", pev->nargs);
 }
 
 static void parse_probe_event_argv(int argc, const char **argv)
@@ -87,9 +82,7 @@ static void parse_probe_event_argv(int argc, const char **argv)
 	len = 0;
 	for (i = 0; i < argc; i++)
 		len += strlen(argv[i]) + 1;
-	buf = zalloc(len + 1);
-	if (!buf)
-		die("Failed to allocate memory for binding arguments.");
+	buf = xzalloc(len + 1);
 	len = 0;
 	for (i = 0; i < argc; i++)
 		len += sprintf(&buf[len], "%s ", argv[i]);
@@ -109,43 +102,21 @@ static int opt_del_probe_event(const struct option *opt __used,
 			       const char *str, int unset __used)
 {
 	if (str) {
-		if (!session.dellist)
-			session.dellist = strlist__new(true, NULL);
-		strlist__add(session.dellist, str);
+		if (!params.dellist)
+			params.dellist = strlist__new(true, NULL);
+		strlist__add(params.dellist, str);
 	}
 	return 0;
 }
 
-/* Currently just checking function name from symbol map */
-static void evaluate_probe_point(struct probe_point *pp)
-{
-	struct symbol *sym;
-	sym = map__find_symbol_by_name(session.kmaps[MAP__FUNCTION],
-				       pp->function, NULL);
-	if (!sym)
-		die("Kernel symbol \'%s\' not found - probe not added.",
-		    pp->function);
-}
-
-#ifndef NO_DWARF_SUPPORT
-static int open_vmlinux(void)
-{
-	if (map__load(session.kmaps[MAP__FUNCTION], NULL) < 0) {
-		pr_debug("Failed to load kernel map.\n");
-		return -EINVAL;
-	}
-	pr_debug("Try to open %s\n",
-		 session.kmaps[MAP__FUNCTION]->dso->long_name);
-	return open(session.kmaps[MAP__FUNCTION]->dso->long_name, O_RDONLY);
-}
-
+#ifdef DWARF_SUPPORT
 static int opt_show_lines(const struct option *opt __used,
 			  const char *str, int unset __used)
 {
 	if (str)
-		parse_line_range_desc(str, &session.line_range);
-	INIT_LIST_HEAD(&session.line_range.line_list);
-	session.show_lines = true;
+		parse_line_range_desc(str, &params.line_range);
+	INIT_LIST_HEAD(&params.line_range.line_list);
+	params.show_lines = true;
 	return 0;
 }
 #endif
@@ -155,7 +126,7 @@ static const char * const probe_usage[] = {
 	"perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
 	"perf probe [<options>] --del '[GROUP:]EVENT' ...",
 	"perf probe --list",
-#ifndef NO_DWARF_SUPPORT
+#ifdef DWARF_SUPPORT
 	"perf probe --line 'LINEDESC'",
 #endif
 	NULL
@@ -164,20 +135,16 @@ static const char * const probe_usage[] = {
 static const struct option options[] = {
 	OPT_BOOLEAN('v', "verbose", &verbose,
 		    "be more verbose (show parsed arguments, etc)"),
-#ifndef NO_DWARF_SUPPORT
-	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
-		   "file", "vmlinux pathname"),
-#endif
-	OPT_BOOLEAN('l', "list", &session.list_events,
+	OPT_BOOLEAN('l', "list", &params.list_events,
 		    "list up current probe events"),
 	OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.",
 		opt_del_probe_event),
 	OPT_CALLBACK('a', "add", NULL,
-#ifdef NO_DWARF_SUPPORT
-		"[EVENT=]FUNC[+OFF|%return] [ARG ...]",
-#else
+#ifdef DWARF_SUPPORT
 		"[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT"
 		" [ARG ...]",
+#else
+		"[EVENT=]FUNC[+OFF|%return] [ARG ...]",
 #endif
 		"probe point definition, where\n"
 		"\t\tGROUP:\tGroup name (optional)\n"
@@ -185,52 +152,32 @@ static const struct option options[] = {
 		"\t\tFUNC:\tFunction name\n"
 		"\t\tOFF:\tOffset from function entry (in byte)\n"
 		"\t\t%return:\tPut the probe at function return\n"
-#ifdef NO_DWARF_SUPPORT
-		"\t\tARG:\tProbe argument (only \n"
-#else
+#ifdef DWARF_SUPPORT
 		"\t\tSRC:\tSource code path\n"
 		"\t\tRL:\tRelative line number from function entry.\n"
 		"\t\tAL:\tAbsolute line number in file.\n"
 		"\t\tPT:\tLazy expression of line code.\n"
 		"\t\tARG:\tProbe argument (local variable name or\n"
-#endif
 		"\t\t\tkprobe-tracer argument format.)\n",
+#else
+		"\t\tARG:\tProbe argument (kprobe-tracer argument format.)\n",
+#endif
 		opt_add_probe_event),
-	OPT_BOOLEAN('f', "force", &session.force_add, "forcibly add events"
+	OPT_BOOLEAN('f', "force", &params.force_add, "forcibly add events"
 		    " with existing name"),
-#ifndef NO_DWARF_SUPPORT
+#ifdef DWARF_SUPPORT
 	OPT_CALLBACK('L', "line", NULL,
-		     "FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]",
+		     "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]",
 		     "Show source code lines.", opt_show_lines),
+	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
+		   "file", "vmlinux pathname"),
 #endif
+	OPT__DRY_RUN(&probe_event_dry_run),
 	OPT_END()
 };
 
-/* Initialize symbol maps for vmlinux */
-static void init_vmlinux(void)
-{
-	symbol_conf.sort_by_name = true;
-	if (symbol_conf.vmlinux_name == NULL)
-		symbol_conf.try_vmlinux_path = true;
-	else
-		pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name);
-	if (symbol__init() < 0)
-		die("Failed to init symbol map.");
-
-	map_groups__init(&session.kmap_groups);
-	if (map_groups__create_kernel_maps(&session.kmap_groups,
-					   session.kmaps) < 0)
-		die("Failed to create kernel maps.");
-}
-
 int cmd_probe(int argc, const char **argv, const char *prefix __used)
 {
-	int i, ret;
-#ifndef NO_DWARF_SUPPORT
-	int fd;
-#endif
-	struct probe_point *pp;
-
 	argc = parse_options(argc, argv, options, probe_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 	if (argc > 0) {
@@ -241,20 +188,20 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 		parse_probe_event_argv(argc, argv);
 	}
 
-	if ((!session.nr_probe && !session.dellist && !session.list_events &&
-	     !session.show_lines))
+	if ((!params.nevents && !params.dellist && !params.list_events &&
+	     !params.show_lines))
 		usage_with_options(probe_usage, options);
 
 	if (debugfs_valid_mountpoint(debugfs_path) < 0)
 		die("Failed to find debugfs path.");
 
-	if (session.list_events) {
-		if (session.nr_probe != 0 || session.dellist) {
+	if (params.list_events) {
+		if (params.nevents != 0 || params.dellist) {
 			pr_warning("  Error: Don't use --list with"
 				   " --add/--del.\n");
 			usage_with_options(probe_usage, options);
 		}
-		if (session.show_lines) {
+		if (params.show_lines) {
 			pr_warning("  Error: Don't use --list with --line.\n");
 			usage_with_options(probe_usage, options);
 		}
@@ -262,99 +209,27 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 		return 0;
 	}
 
-#ifndef NO_DWARF_SUPPORT
-	if (session.show_lines) {
-		if (session.nr_probe != 0 || session.dellist) {
+#ifdef DWARF_SUPPORT
+	if (params.show_lines) {
+		if (params.nevents != 0 || params.dellist) {
 			pr_warning("  Error: Don't use --line with"
 				   " --add/--del.\n");
 			usage_with_options(probe_usage, options);
 		}
-		init_vmlinux();
-		fd = open_vmlinux();
-		if (fd < 0)
-			die("Could not open debuginfo file.");
-		ret = find_line_range(fd, &session.line_range);
-		if (ret <= 0)
-			die("Source line is not found.\n");
-		close(fd);
-		show_line_range(&session.line_range);
+
+		show_line_range(&params.line_range);
 		return 0;
 	}
 #endif
 
-	if (session.dellist) {
-		del_trace_kprobe_events(session.dellist);
-		strlist__delete(session.dellist);
-		if (session.nr_probe == 0)
+	if (params.dellist) {
+		del_perf_probe_events(params.dellist);
+		strlist__delete(params.dellist);
+		if (params.nevents == 0)
 			return 0;
 	}
 
-	/* Add probes */
-	init_vmlinux();
-
-	if (session.need_dwarf)
-#ifdef NO_DWARF_SUPPORT
-		die("Debuginfo-analysis is not supported");
-#else	/* !NO_DWARF_SUPPORT */
-		pr_debug("Some probes require debuginfo.\n");
-
-	fd = open_vmlinux();
-	if (fd < 0) {
-		if (session.need_dwarf)
-			die("Could not open debuginfo file.");
-
-		pr_debug("Could not open vmlinux/module file."
-			 " Try to use symbols.\n");
-		goto end_dwarf;
-	}
-
-	/* Searching probe points */
-	for (i = 0; i < session.nr_probe; i++) {
-		pp = &session.probes[i];
-		if (pp->found)
-			continue;
-
-		lseek(fd, SEEK_SET, 0);
-		ret = find_probe_point(fd, pp);
-		if (ret > 0)
-			continue;
-		if (ret == 0) {	/* No error but failed to find probe point. */
-			synthesize_perf_probe_point(pp);
-			die("Probe point '%s' not found. - probe not added.",
-			    pp->probes[0]);
-		}
-		/* Error path */
-		if (session.need_dwarf) {
-			if (ret == -ENOENT)
-				pr_warning("No dwarf info found in the vmlinux - please rebuild with CONFIG_DEBUG_INFO=y.\n");
-			die("Could not analyze debuginfo.");
-		}
-		pr_debug("An error occurred in debuginfo analysis."
-			 " Try to use symbols.\n");
-		break;
-	}
-	close(fd);
-
-end_dwarf:
-#endif /* !NO_DWARF_SUPPORT */
-
-	/* Synthesize probes without dwarf */
-	for (i = 0; i < session.nr_probe; i++) {
-		pp = &session.probes[i];
-		if (pp->found)	/* This probe is already found. */
-			continue;
-
-		evaluate_probe_point(pp);
-		ret = synthesize_trace_kprobe_event(pp);
-		if (ret == -E2BIG)
-			die("probe point definition becomes too long.");
-		else if (ret < 0)
-			die("Failed to synthesize a probe point.");
-	}
-
-	/* Settng up probe points */
-	add_trace_kprobe_events(session.probes, session.nr_probe,
-				session.force_add);
+	add_perf_probe_events(params.events, params.nevents, params.force_add);
 	return 0;
 }
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3b8b6387c47c..dc61f1b68b40 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -15,7 +15,6 @@
 #include "util/util.h"
 #include "util/parse-options.h"
 #include "util/parse-events.h"
-#include "util/string.h"
 
 #include "util/header.h"
 #include "util/event.h"
@@ -27,7 +26,7 @@
 #include <unistd.h>
 #include <sched.h>
 
-static int			fd[MAX_NR_CPUS][MAX_COUNTERS];
+static int			*fd[MAX_NR_CPUS][MAX_COUNTERS];
 
 static long			default_interval		=      0;
 
@@ -43,6 +42,9 @@ static int			raw_samples			=      0;
 static int			system_wide			=      0;
 static int			profile_cpu			=     -1;
 static pid_t			target_pid			=     -1;
+static pid_t			target_tid			=     -1;
+static pid_t			*all_tids			=      NULL;
+static int			thread_num			=      0;
 static pid_t			child_pid			=     -1;
 static int			inherit				=      1;
 static int			force				=      0;
@@ -60,7 +62,7 @@ static struct timeval		this_read;
 
 static u64			bytes_written			=      0;
 
-static struct pollfd		event_array[MAX_NR_CPUS * MAX_COUNTERS];
+static struct pollfd		*event_array;
 
 static int			nr_poll				=      0;
 static int			nr_cpu				=      0;
@@ -77,7 +79,7 @@ struct mmap_data {
 	unsigned int		prev;
 };
 
-static struct mmap_data		mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
+static struct mmap_data		*mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
 
 static unsigned long mmap_read_head(struct mmap_data *md)
 {
@@ -225,12 +227,13 @@ static struct perf_header_attr *get_header_attr(struct perf_event_attr *a, int n
 	return h_attr;
 }
 
-static void create_counter(int counter, int cpu, pid_t pid)
+static void create_counter(int counter, int cpu)
 {
 	char *filter = filters[counter];
 	struct perf_event_attr *attr = attrs + counter;
 	struct perf_header_attr *h_attr;
 	int track = !counter; /* only the first counter needs these */
+	int thread_index;
 	int ret;
 	struct {
 		u64 count;
@@ -275,118 +278,129 @@ static void create_counter(int counter, int cpu, pid_t pid)
 	attr->mmap		= track;
 	attr->comm		= track;
 	attr->inherit		= inherit;
-	attr->disabled		= 1;
+	if (target_pid == -1 && !system_wide) {
+		attr->disabled = 1;
+		attr->enable_on_exec = 1;
+	}
 
+	for (thread_index = 0; thread_index < thread_num; thread_index++) {
 try_again:
-	fd[nr_cpu][counter] = sys_perf_event_open(attr, pid, cpu, group_fd, 0);
-
-	if (fd[nr_cpu][counter] < 0) {
-		int err = errno;
-
-		if (err == EPERM || err == EACCES)
-			die("Permission error - are you root?\n");
-		else if (err ==  ENODEV && profile_cpu != -1)
-			die("No such device - did you specify an out-of-range profile CPU?\n");
+		fd[nr_cpu][counter][thread_index] = sys_perf_event_open(attr,
+				all_tids[thread_index], cpu, group_fd, 0);
+
+		if (fd[nr_cpu][counter][thread_index] < 0) {
+			int err = errno;
+
+			if (err == EPERM || err == EACCES)
+				die("Permission error - are you root?\n"
+					"\t Consider tweaking"
+					" /proc/sys/kernel/perf_event_paranoid.\n");
+			else if (err ==  ENODEV && profile_cpu != -1) {
+				die("No such device - did you specify"
+					" an out-of-range profile CPU?\n");
+			}
 
-		/*
-		 * If it's cycles then fall back to hrtimer
-		 * based cpu-clock-tick sw counter, which
-		 * is always available even if no PMU support:
-		 */
-		if (attr->type == PERF_TYPE_HARDWARE
-			&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
-
-			if (verbose)
-				warning(" ... trying to fall back to cpu-clock-ticks\n");
-			attr->type = PERF_TYPE_SOFTWARE;
-			attr->config = PERF_COUNT_SW_CPU_CLOCK;
-			goto try_again;
-		}
-		printf("\n");
-		error("perfcounter syscall returned with %d (%s)\n",
-			fd[nr_cpu][counter], strerror(err));
+			/*
+			 * If it's cycles then fall back to hrtimer
+			 * based cpu-clock-tick sw counter, which
+			 * is always available even if no PMU support:
+			 */
+			if (attr->type == PERF_TYPE_HARDWARE
+					&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+
+				if (verbose)
+					warning(" ... trying to fall back to cpu-clock-ticks\n");
+				attr->type = PERF_TYPE_SOFTWARE;
+				attr->config = PERF_COUNT_SW_CPU_CLOCK;
+				goto try_again;
+			}
+			printf("\n");
+			error("perfcounter syscall returned with %d (%s)\n",
+					fd[nr_cpu][counter][thread_index], strerror(err));
 
 #if defined(__i386__) || defined(__x86_64__)
-		if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP)
-			die("No hardware sampling interrupt available. No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.\n");
+			if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP)
+				die("No hardware sampling interrupt available."
+				    " No APIC? If so then you can boot the kernel"
+				    " with the \"lapic\" boot parameter to"
+				    " force-enable it.\n");
 #endif
 
-		die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-		exit(-1);
-	}
+			die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
+			exit(-1);
+		}
 
-	h_attr = get_header_attr(attr, counter);
-	if (h_attr == NULL)
-		die("nomem\n");
+		h_attr = get_header_attr(attr, counter);
+		if (h_attr == NULL)
+			die("nomem\n");
 
-	if (!file_new) {
-		if (memcmp(&h_attr->attr, attr, sizeof(*attr))) {
-			fprintf(stderr, "incompatible append\n");
-			exit(-1);
+		if (!file_new) {
+			if (memcmp(&h_attr->attr, attr, sizeof(*attr))) {
+				fprintf(stderr, "incompatible append\n");
+				exit(-1);
+			}
 		}
-	}
 
-	if (read(fd[nr_cpu][counter], &read_data, sizeof(read_data)) == -1) {
-		perror("Unable to read perf file descriptor\n");
-		exit(-1);
-	}
+		if (read(fd[nr_cpu][counter][thread_index], &read_data, sizeof(read_data)) == -1) {
+			perror("Unable to read perf file descriptor\n");
+			exit(-1);
+		}
 
-	if (perf_header_attr__add_id(h_attr, read_data.id) < 0) {
-		pr_warning("Not enough memory to add id\n");
-		exit(-1);
-	}
+		if (perf_header_attr__add_id(h_attr, read_data.id) < 0) {
+			pr_warning("Not enough memory to add id\n");
+			exit(-1);
+		}
 
-	assert(fd[nr_cpu][counter] >= 0);
-	fcntl(fd[nr_cpu][counter], F_SETFL, O_NONBLOCK);
+		assert(fd[nr_cpu][counter][thread_index] >= 0);
+		fcntl(fd[nr_cpu][counter][thread_index], F_SETFL, O_NONBLOCK);
 
-	/*
-	 * First counter acts as the group leader:
-	 */
-	if (group && group_fd == -1)
-		group_fd = fd[nr_cpu][counter];
-	if (multiplex && multiplex_fd == -1)
-		multiplex_fd = fd[nr_cpu][counter];
+		/*
+		 * First counter acts as the group leader:
+		 */
+		if (group && group_fd == -1)
+			group_fd = fd[nr_cpu][counter][thread_index];
+		if (multiplex && multiplex_fd == -1)
+			multiplex_fd = fd[nr_cpu][counter][thread_index];
 
-	if (multiplex && fd[nr_cpu][counter] != multiplex_fd) {
+		if (multiplex && fd[nr_cpu][counter][thread_index] != multiplex_fd) {
 
-		ret = ioctl(fd[nr_cpu][counter], PERF_EVENT_IOC_SET_OUTPUT, multiplex_fd);
-		assert(ret != -1);
-	} else {
-		event_array[nr_poll].fd = fd[nr_cpu][counter];
-		event_array[nr_poll].events = POLLIN;
-		nr_poll++;
-
-		mmap_array[nr_cpu][counter].counter = counter;
-		mmap_array[nr_cpu][counter].prev = 0;
-		mmap_array[nr_cpu][counter].mask = mmap_pages*page_size - 1;
-		mmap_array[nr_cpu][counter].base = mmap(NULL, (mmap_pages+1)*page_size,
-				PROT_READ|PROT_WRITE, MAP_SHARED, fd[nr_cpu][counter], 0);
-		if (mmap_array[nr_cpu][counter].base == MAP_FAILED) {
-			error("failed to mmap with %d (%s)\n", errno, strerror(errno));
-			exit(-1);
+			ret = ioctl(fd[nr_cpu][counter][thread_index], PERF_EVENT_IOC_SET_OUTPUT, multiplex_fd);
+			assert(ret != -1);
+		} else {
+			event_array[nr_poll].fd = fd[nr_cpu][counter][thread_index];
+			event_array[nr_poll].events = POLLIN;
+			nr_poll++;
+
+			mmap_array[nr_cpu][counter][thread_index].counter = counter;
+			mmap_array[nr_cpu][counter][thread_index].prev = 0;
+			mmap_array[nr_cpu][counter][thread_index].mask = mmap_pages*page_size - 1;
+			mmap_array[nr_cpu][counter][thread_index].base = mmap(NULL, (mmap_pages+1)*page_size,
+				PROT_READ|PROT_WRITE, MAP_SHARED, fd[nr_cpu][counter][thread_index], 0);
+			if (mmap_array[nr_cpu][counter][thread_index].base == MAP_FAILED) {
+				error("failed to mmap with %d (%s)\n", errno, strerror(errno));
+				exit(-1);
+			}
 		}
-	}
 
-	if (filter != NULL) {
-		ret = ioctl(fd[nr_cpu][counter],
-			    PERF_EVENT_IOC_SET_FILTER, filter);
-		if (ret) {
-			error("failed to set filter with %d (%s)\n", errno,
-			      strerror(errno));
-			exit(-1);
+		if (filter != NULL) {
+			ret = ioctl(fd[nr_cpu][counter][thread_index],
+					PERF_EVENT_IOC_SET_FILTER, filter);
+			if (ret) {
+				error("failed to set filter with %d (%s)\n", errno,
+						strerror(errno));
+				exit(-1);
+			}
 		}
 	}
-
-	ioctl(fd[nr_cpu][counter], PERF_EVENT_IOC_ENABLE);
 }
 
-static void open_counters(int cpu, pid_t pid)
+static void open_counters(int cpu)
 {
 	int counter;
 
 	group_fd = -1;
 	for (counter = 0; counter < nr_counters; counter++)
-		create_counter(counter, cpu, pid);
+		create_counter(counter, cpu);
 
 	nr_cpu++;
 }
@@ -421,7 +435,7 @@ static int __cmd_record(int argc, const char **argv)
 	int err;
 	unsigned long waking = 0;
 	int child_ready_pipe[2], go_pipe[2];
-	const bool forks = target_pid == -1 && argc > 0;
+	const bool forks = argc > 0;
 	char buf;
 
 	page_size = sysconf(_SC_PAGE_SIZE);
@@ -492,13 +506,13 @@ static int __cmd_record(int argc, const char **argv)
 	atexit(atexit_header);
 
 	if (forks) {
-		pid = fork();
+		child_pid = fork();
 		if (pid < 0) {
 			perror("failed to fork");
 			exit(-1);
 		}
 
-		if (!pid) {
+		if (!child_pid) {
 			close(child_ready_pipe[0]);
 			close(go_pipe[1]);
 			fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
@@ -527,10 +541,8 @@ static int __cmd_record(int argc, const char **argv)
 			exit(-1);
 		}
 
-		child_pid = pid;
-
-		if (!system_wide)
-			target_pid = pid;
+		if (!system_wide && target_tid == -1 && target_pid == -1)
+			all_tids[0] = child_pid;
 
 		close(child_ready_pipe[1]);
 		close(go_pipe[0]);
@@ -544,13 +556,12 @@ static int __cmd_record(int argc, const char **argv)
 		close(child_ready_pipe[0]);
 	}
 
-
 	if ((!system_wide && !inherit) || profile_cpu != -1) {
-		open_counters(profile_cpu, target_pid);
+		open_counters(profile_cpu);
 	} else {
 		nr_cpus = read_cpu_map();
 		for (i = 0; i < nr_cpus; i++)
-			open_counters(cpumap[i], target_pid);
+			open_counters(cpumap[i]);
 	}
 
 	if (file_new) {
@@ -563,6 +574,9 @@ static int __cmd_record(int argc, const char **argv)
 
 	err = event__synthesize_kernel_mmap(process_synthesized_event,
 					    session, "_text");
+	if (err < 0)
+		err = event__synthesize_kernel_mmap(process_synthesized_event,
+						    session, "_stext");
 	if (err < 0) {
 		pr_err("Couldn't record kernel reference relocation symbol.\n");
 		return err;
@@ -575,7 +589,7 @@ static int __cmd_record(int argc, const char **argv)
 	}
 
 	if (!system_wide && profile_cpu == -1)
-		event__synthesize_thread(target_pid, process_synthesized_event,
+		event__synthesize_thread(target_tid, process_synthesized_event,
 					 session);
 	else
 		event__synthesize_threads(process_synthesized_event, session);
@@ -598,11 +612,16 @@ static int __cmd_record(int argc, const char **argv)
 
 	for (;;) {
 		int hits = samples;
+		int thread;
 
 		for (i = 0; i < nr_cpu; i++) {
 			for (counter = 0; counter < nr_counters; counter++) {
-				if (mmap_array[i][counter].base)
-					mmap_read(&mmap_array[i][counter]);
+				for (thread = 0;
+					thread < thread_num; thread++) {
+					if (mmap_array[i][counter][thread].base)
+						mmap_read(&mmap_array[i][counter][thread]);
+				}
+
 			}
 		}
 
@@ -615,8 +634,15 @@ static int __cmd_record(int argc, const char **argv)
 
 		if (done) {
 			for (i = 0; i < nr_cpu; i++) {
-				for (counter = 0; counter < nr_counters; counter++)
-					ioctl(fd[i][counter], PERF_EVENT_IOC_DISABLE);
+				for (counter = 0;
+					counter < nr_counters;
+					counter++) {
+					for (thread = 0;
+						thread < thread_num;
+						thread++)
+						ioctl(fd[i][counter][thread],
+							PERF_EVENT_IOC_DISABLE);
+				}
 			}
 		}
 	}
@@ -648,7 +674,9 @@ static const struct option options[] = {
 	OPT_CALLBACK(0, "filter", NULL, "filter",
 		     "event filter", parse_filter),
 	OPT_INTEGER('p', "pid", &target_pid,
-		    "record events on existing pid"),
+		    "record events on existing process id"),
+	OPT_INTEGER('t', "tid", &target_tid,
+		    "record events on existing thread id"),
 	OPT_INTEGER('r', "realtime", &realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
 	OPT_BOOLEAN('R', "raw-samples", &raw_samples,
@@ -689,10 +717,12 @@ static const struct option options[] = {
 int cmd_record(int argc, const char **argv, const char *prefix __used)
 {
 	int counter;
+	int i,j;
 
 	argc = parse_options(argc, argv, options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc && target_pid == -1 && !system_wide && profile_cpu == -1)
+	if (!argc && target_pid == -1 && target_tid == -1 &&
+		!system_wide && profile_cpu == -1)
 		usage_with_options(record_usage, options);
 
 	symbol__init();
@@ -703,6 +733,37 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 		attrs[0].config = PERF_COUNT_HW_CPU_CYCLES;
 	}
 
+	if (target_pid != -1) {
+		target_tid = target_pid;
+		thread_num = find_all_tid(target_pid, &all_tids);
+		if (thread_num <= 0) {
+			fprintf(stderr, "Can't find all threads of pid %d\n",
+					target_pid);
+			usage_with_options(record_usage, options);
+		}
+	} else {
+		all_tids=malloc(sizeof(pid_t));
+		if (!all_tids)
+			return -ENOMEM;
+
+		all_tids[0] = target_tid;
+		thread_num = 1;
+	}
+
+	for (i = 0; i < MAX_NR_CPUS; i++) {
+		for (j = 0; j < MAX_COUNTERS; j++) {
+			fd[i][j] = malloc(sizeof(int)*thread_num);
+			mmap_array[i][j] = zalloc(
+				sizeof(struct mmap_data)*thread_num);
+			if (!fd[i][j] || !mmap_array[i][j])
+				return -ENOMEM;
+		}
+	}
+	event_array = malloc(
+		sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num);
+	if (!event_array)
+		return -ENOMEM;
+
 	/*
 	 * User specified count overrides default frequency.
 	 */
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index f815de25d0fc..e93c69a8e720 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -14,7 +14,6 @@
 #include "util/cache.h"
 #include <linux/rbtree.h>
 #include "util/symbol.h"
-#include "util/string.h"
 #include "util/callchain.h"
 #include "util/strlist.h"
 #include "util/values.h"
@@ -81,15 +80,20 @@ static int perf_session__add_hist_entry(struct perf_session *self,
 					struct addr_location *al,
 					struct sample_data *data)
 {
-	struct symbol **syms = NULL, *parent = NULL;
+	struct map_symbol *syms = NULL;
+	struct symbol *parent = NULL;
 	bool hit;
+	int err;
 	struct hist_entry *he;
 	struct event_stat_id *stats;
 	struct perf_event_attr *attr;
 
-	if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain)
+	if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain) {
 		syms = perf_session__resolve_callchain(self, al->thread,
 						       data->callchain, &parent);
+		if (syms == NULL)
+			return -ENOMEM;
+	}
 
 	attr = perf_header__find_attr(data->id, &self->header);
 	if (attr)
@@ -108,9 +112,12 @@ static int perf_session__add_hist_entry(struct perf_session *self,
 
 	if (symbol_conf.use_callchain) {
 		if (!hit)
-			callchain_init(&he->callchain);
-		append_chain(&he->callchain, data->callchain, syms);
+			callchain_init(he->callchain);
+		err = append_chain(he->callchain, data->callchain, syms);
 		free(syms);
+
+		if (err)
+			return err;
 	}
 
 	return 0;
@@ -267,6 +274,7 @@ static int __cmd_report(void)
 	int ret = -EINVAL;
 	struct perf_session *session;
 	struct rb_node *next;
+	const char *help = "For a higher level overview, try: perf report --sort comm,dso";
 
 	session = perf_session__new(input_name, O_RDONLY, force);
 	if (session == NULL)
@@ -297,34 +305,44 @@ static int __cmd_report(void)
 	next = rb_first(&session->stats_by_id);
 	while (next) {
 		struct event_stat_id *stats;
+		u64 nr_hists;
 
 		stats = rb_entry(next, struct event_stat_id, rb_node);
 		perf_session__collapse_resort(&stats->hists);
-		perf_session__output_resort(&stats->hists, stats->stats.total);
-		if (rb_first(&session->stats_by_id) ==
-		    rb_last(&session->stats_by_id))
-			fprintf(stdout, "# Samples: %Ld\n#\n",
-				stats->stats.total);
-		else
-			fprintf(stdout, "# Samples: %Ld %s\n#\n",
-				stats->stats.total,
-				__event_name(stats->type, stats->config));
-
-		perf_session__fprintf_hists(&stats->hists, NULL, false, stdout,
+		nr_hists = perf_session__output_resort(&stats->hists,
+						       stats->stats.total);
+		if (use_browser)
+			perf_session__browse_hists(&stats->hists, nr_hists,
+						   stats->stats.total, help,
+						   input_name);
+		else {
+			if (rb_first(&session->stats_by_id) ==
+			    rb_last(&session->stats_by_id))
+				fprintf(stdout, "# Samples: %Ld\n#\n",
+					stats->stats.total);
+			else
+				fprintf(stdout, "# Samples: %Ld %s\n#\n",
+					stats->stats.total,
+					__event_name(stats->type, stats->config));
+
+			perf_session__fprintf_hists(&stats->hists, NULL, false, stdout,
 					    stats->stats.total);
-		fprintf(stdout, "\n\n");
+			fprintf(stdout, "\n\n");
+		}
+
 		next = rb_next(&stats->rb_node);
 	}
 
-	if (sort_order == default_sort_order &&
-	    parent_pattern == default_parent_pattern)
-		fprintf(stdout, "#\n# (For a higher level overview, try: perf report --sort comm,dso)\n#\n");
+	if (!use_browser && sort_order == default_sort_order &&
+	    parent_pattern == default_parent_pattern) {
+		fprintf(stdout, "#\n# (%s)\n#\n", help);
 
-	if (show_threads) {
-		bool raw_printing_style = !strcmp(pretty_printing_style, "raw");
-		perf_read_values_display(stdout, &show_threads_values,
-					 raw_printing_style);
-		perf_read_values_destroy(&show_threads_values);
+		if (show_threads) {
+			bool style = !strcmp(pretty_printing_style, "raw");
+			perf_read_values_display(stdout, &show_threads_values,
+						 style);
+			perf_read_values_destroy(&show_threads_values);
+		}
 	}
 out_delete:
 	perf_session__delete(session);
@@ -447,7 +465,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 {
 	argc = parse_options(argc, argv, options, report_usage, 0);
 
-	setup_pager();
+	setup_browser();
 
 	if (symbol__init() < 0)
 		return -1;
@@ -455,7 +473,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	setup_sorting(report_usage, options);
 
 	if (parent_pattern != default_parent_pattern) {
-		sort_dimension__add("parent");
+		if (sort_dimension__add("parent") < 0)
+			return -1;
 		sort_parent.elide = 1;
 	} else
 		symbol_conf.exclude_other = false;
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 4f5a03e43444..5e59c0c40c40 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -68,10 +68,10 @@ enum sched_event_type {
 
 struct sched_atom {
 	enum sched_event_type	type;
+	int			specific_wait;
 	u64			timestamp;
 	u64			duration;
 	unsigned long		nr;
-	int			specific_wait;
 	sem_t			*wait_sem;
 	struct task_desc	*wakee;
 };
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 95db31cff6fd..1036ca739e6f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -46,6 +46,7 @@
 #include "util/debug.h"
 #include "util/header.h"
 #include "util/cpumap.h"
+#include "util/thread.h"
 
 #include <sys/prctl.h>
 #include <math.h>
@@ -74,10 +75,13 @@ static int			run_count			=  1;
 static int			inherit				=  1;
 static int			scale				=  1;
 static pid_t			target_pid			= -1;
+static pid_t			target_tid			= -1;
+static pid_t			*all_tids			=  NULL;
+static int			thread_num			=  0;
 static pid_t			child_pid			= -1;
 static int			null_run			=  0;
 
-static int			fd[MAX_NR_CPUS][MAX_COUNTERS];
+static int			*fd[MAX_NR_CPUS][MAX_COUNTERS];
 
 static int			event_scaled[MAX_COUNTERS];
 
@@ -140,9 +144,11 @@ struct stats			runtime_branches_stats;
 #define ERR_PERF_OPEN \
 "Error: counter %d, sys_perf_event_open() syscall returned with %d (%s)\n"
 
-static void create_perf_stat_counter(int counter, int pid)
+static int create_perf_stat_counter(int counter)
 {
 	struct perf_event_attr *attr = attrs + counter;
+	int thread;
+	int ncreated = 0;
 
 	if (scale)
 		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
@@ -152,21 +158,33 @@ static void create_perf_stat_counter(int counter, int pid)
 		unsigned int cpu;
 
 		for (cpu = 0; cpu < nr_cpus; cpu++) {
-			fd[cpu][counter] = sys_perf_event_open(attr, -1, cpumap[cpu], -1, 0);
-			if (fd[cpu][counter] < 0 && verbose)
-				fprintf(stderr, ERR_PERF_OPEN, counter,
-					fd[cpu][counter], strerror(errno));
+			fd[cpu][counter][0] = sys_perf_event_open(attr,
+					-1, cpumap[cpu], -1, 0);
+			if (fd[cpu][counter][0] < 0)
+				pr_debug(ERR_PERF_OPEN, counter,
+					 fd[cpu][counter][0], strerror(errno));
+			else
+				++ncreated;
 		}
 	} else {
 		attr->inherit	     = inherit;
-		attr->disabled	     = 1;
-		attr->enable_on_exec = 1;
-
-		fd[0][counter] = sys_perf_event_open(attr, pid, -1, -1, 0);
-		if (fd[0][counter] < 0 && verbose)
-			fprintf(stderr, ERR_PERF_OPEN, counter,
-				fd[0][counter], strerror(errno));
+		if (target_pid == -1) {
+			attr->disabled = 1;
+			attr->enable_on_exec = 1;
+		}
+		for (thread = 0; thread < thread_num; thread++) {
+			fd[0][counter][thread] = sys_perf_event_open(attr,
+				all_tids[thread], -1, -1, 0);
+			if (fd[0][counter][thread] < 0)
+				pr_debug(ERR_PERF_OPEN, counter,
+					 fd[0][counter][thread],
+					 strerror(errno));
+			else
+				++ncreated;
+		}
 	}
+
+	return ncreated;
 }
 
 /*
@@ -190,25 +208,28 @@ static void read_counter(int counter)
 	unsigned int cpu;
 	size_t res, nv;
 	int scaled;
-	int i;
+	int i, thread;
 
 	count[0] = count[1] = count[2] = 0;
 
 	nv = scale ? 3 : 1;
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		if (fd[cpu][counter] < 0)
-			continue;
-
-		res = read(fd[cpu][counter], single_count, nv * sizeof(u64));
-		assert(res == nv * sizeof(u64));
-
-		close(fd[cpu][counter]);
-		fd[cpu][counter] = -1;
-
-		count[0] += single_count[0];
-		if (scale) {
-			count[1] += single_count[1];
-			count[2] += single_count[2];
+		for (thread = 0; thread < thread_num; thread++) {
+			if (fd[cpu][counter][thread] < 0)
+				continue;
+
+			res = read(fd[cpu][counter][thread],
+					single_count, nv * sizeof(u64));
+			assert(res == nv * sizeof(u64));
+
+			close(fd[cpu][counter][thread]);
+			fd[cpu][counter][thread] = -1;
+
+			count[0] += single_count[0];
+			if (scale) {
+				count[1] += single_count[1];
+				count[2] += single_count[2];
+			}
 		}
 	}
 
@@ -250,10 +271,9 @@ static int run_perf_stat(int argc __used, const char **argv)
 {
 	unsigned long long t0, t1;
 	int status = 0;
-	int counter;
-	int pid = target_pid;
+	int counter, ncreated = 0;
 	int child_ready_pipe[2], go_pipe[2];
-	const bool forks = (target_pid == -1 && argc > 0);
+	const bool forks = (argc > 0);
 	char buf;
 
 	if (!system_wide)
@@ -265,10 +285,10 @@ static int run_perf_stat(int argc __used, const char **argv)
 	}
 
 	if (forks) {
-		if ((pid = fork()) < 0)
+		if ((child_pid = fork()) < 0)
 			perror("failed to fork");
 
-		if (!pid) {
+		if (!child_pid) {
 			close(child_ready_pipe[0]);
 			close(go_pipe[1]);
 			fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
@@ -297,7 +317,8 @@ static int run_perf_stat(int argc __used, const char **argv)
 			exit(-1);
 		}
 
-		child_pid = pid;
+		if (target_tid == -1 && target_pid == -1 && !system_wide)
+			all_tids[0] = child_pid;
 
 		/*
 		 * Wait for the child to be ready to exec.
@@ -310,7 +331,16 @@ static int run_perf_stat(int argc __used, const char **argv)
 	}
 
 	for (counter = 0; counter < nr_counters; counter++)
-		create_perf_stat_counter(counter, pid);
+		ncreated += create_perf_stat_counter(counter);
+
+	if (ncreated == 0) {
+		pr_err("No permission to collect %sstats.\n"
+		       "Consider tweaking /proc/sys/kernel/perf_event_paranoid.\n",
+		       system_wide ? "system-wide " : "");
+		if (child_pid != -1)
+			kill(child_pid, SIGTERM);
+		return -1;
+	}
 
 	/*
 	 * Enable counters and exec the command:
@@ -321,7 +351,7 @@ static int run_perf_stat(int argc __used, const char **argv)
 		close(go_pipe[1]);
 		wait(&status);
 	} else {
-		while(!done);
+		while(!done) sleep(1);
 	}
 
 	t1 = rdclock();
@@ -429,12 +459,14 @@ static void print_stat(int argc, const char **argv)
 
 	fprintf(stderr, "\n");
 	fprintf(stderr, " Performance counter stats for ");
-	if(target_pid == -1) {
+	if(target_pid == -1 && target_tid == -1) {
 		fprintf(stderr, "\'%s", argv[0]);
 		for (i = 1; i < argc; i++)
 			fprintf(stderr, " %s", argv[i]);
-	}else
-		fprintf(stderr, "task pid \'%d", target_pid);
+	} else if (target_pid != -1)
+		fprintf(stderr, "process id \'%d", target_pid);
+	else
+		fprintf(stderr, "thread id \'%d", target_tid);
 
 	fprintf(stderr, "\'");
 	if (run_count > 1)
@@ -459,7 +491,7 @@ static volatile int signr = -1;
 
 static void skip_signal(int signo)
 {
-	if(target_pid != -1)
+	if(child_pid == -1)
 		done = 1;
 
 	signr = signo;
@@ -489,7 +521,9 @@ static const struct option options[] = {
 	OPT_BOOLEAN('i', "inherit", &inherit,
 		    "child tasks inherit counters"),
 	OPT_INTEGER('p', "pid", &target_pid,
-		    "stat events on existing pid"),
+		    "stat events on existing process id"),
+	OPT_INTEGER('t', "tid", &target_tid,
+		    "stat events on existing thread id"),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_BOOLEAN('c', "scale", &scale,
@@ -506,10 +540,11 @@ static const struct option options[] = {
 int cmd_stat(int argc, const char **argv, const char *prefix __used)
 {
 	int status;
+	int i,j;
 
 	argc = parse_options(argc, argv, options, stat_usage,
 		PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc && target_pid == -1)
+	if (!argc && target_pid == -1 && target_tid == -1)
 		usage_with_options(stat_usage, options);
 	if (run_count <= 0)
 		usage_with_options(stat_usage, options);
@@ -525,6 +560,31 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 	else
 		nr_cpus = 1;
 
+	if (target_pid != -1) {
+		target_tid = target_pid;
+		thread_num = find_all_tid(target_pid, &all_tids);
+		if (thread_num <= 0) {
+			fprintf(stderr, "Can't find all threads of pid %d\n",
+					target_pid);
+			usage_with_options(stat_usage, options);
+		}
+	} else {
+		all_tids=malloc(sizeof(pid_t));
+		if (!all_tids)
+			return -ENOMEM;
+
+		all_tids[0] = target_tid;
+		thread_num = 1;
+	}
+
+	for (i = 0; i < MAX_NR_CPUS; i++) {
+		for (j = 0; j < MAX_COUNTERS; j++) {
+			fd[i][j] = malloc(sizeof(int)*thread_num);
+			if (!fd[i][j])
+				return -ENOMEM;
+		}
+	}
+
 	/*
 	 * We dont want to block the signals - that would cause
 	 * child tasks to inherit that and Ctrl-C would not work.
@@ -543,7 +603,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 		status = run_perf_stat(argc, argv);
 	}
 
-	print_stat(argc, argv);
+	if (status != -1)
+		print_stat(argc, argv);
 
 	return status;
 }
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 0d4d8ff7914b..369c1b490a9e 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -21,7 +21,6 @@
 #include "util/cache.h"
 #include <linux/rbtree.h>
 #include "util/symbol.h"
-#include "util/string.h"
 #include "util/callchain.h"
 #include "util/strlist.h"
 
@@ -78,8 +77,6 @@ struct per_pid {
 
 	struct per_pidcomm *all;
 	struct per_pidcomm *current;
-
-	int painted;
 };
 
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1f529321607e..4abdd9b646b3 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -55,7 +55,7 @@
 #include <linux/unistd.h>
 #include <linux/types.h>
 
-static int			fd[MAX_NR_CPUS][MAX_COUNTERS];
+static int			*fd[MAX_NR_CPUS][MAX_COUNTERS];
 
 static int			system_wide			=      0;
 
@@ -65,6 +65,9 @@ static int			count_filter			=      5;
 static int			print_entries;
 
 static int			target_pid			=     -1;
+static int			target_tid			=     -1;
+static pid_t			*all_tids			=      NULL;
+static int			thread_num			=      0;
 static int			inherit				=      0;
 static int			profile_cpu			=     -1;
 static int			nr_cpus				=      0;
@@ -133,7 +136,7 @@ static inline struct symbol *sym_entry__symbol(struct sym_entry *self)
        return ((void *)self) + symbol_conf.priv_size;
 }
 
-static void get_term_dimensions(struct winsize *ws)
+void get_term_dimensions(struct winsize *ws)
 {
 	char *s = getenv("LINES");
 
@@ -169,7 +172,7 @@ static void sig_winch_handler(int sig __used)
 	update_print_entries(&winsize);
 }
 
-static void parse_source(struct sym_entry *syme)
+static int parse_source(struct sym_entry *syme)
 {
 	struct symbol *sym;
 	struct sym_entry_source *source;
@@ -180,12 +183,21 @@ static void parse_source(struct sym_entry *syme)
 	u64 len;
 
 	if (!syme)
-		return;
+		return -1;
+
+	sym = sym_entry__symbol(syme);
+	map = syme->map;
+
+	/*
+	 * We can't annotate with just /proc/kallsyms
+	 */
+	if (map->dso->origin == DSO__ORIG_KERNEL)
+		return -1;
 
 	if (syme->src == NULL) {
 		syme->src = zalloc(sizeof(*source));
 		if (syme->src == NULL)
-			return;
+			return -1;
 		pthread_mutex_init(&syme->src->lock, NULL);
 	}
 
@@ -195,9 +207,6 @@ static void parse_source(struct sym_entry *syme)
 		pthread_mutex_lock(&source->lock);
 		goto out_assign;
 	}
-
-	sym = sym_entry__symbol(syme);
-	map = syme->map;
 	path = map->dso->long_name;
 
 	len = sym->end - sym->start;
@@ -209,7 +218,7 @@ static void parse_source(struct sym_entry *syme)
 
 	file = popen(command, "r");
 	if (!file)
-		return;
+		return -1;
 
 	pthread_mutex_lock(&source->lock);
 	source->lines_tail = &source->lines;
@@ -245,6 +254,7 @@ static void parse_source(struct sym_entry *syme)
 out_assign:
 	sym_filter_entry = syme;
 	pthread_mutex_unlock(&source->lock);
+	return 0;
 }
 
 static void __zero_source_counters(struct sym_entry *syme)
@@ -411,6 +421,7 @@ static double sym_weight(const struct sym_entry *sym)
 
 static long			samples;
 static long			userspace_samples;
+static long			exact_samples;
 static const char		CONSOLE_CLEAR[] = "";
 
 static void __list_insert_active_sym(struct sym_entry *syme)
@@ -451,6 +462,7 @@ static void print_sym_table(void)
 	int counter, snap = !display_weighted ? sym_counter : 0;
 	float samples_per_sec = samples/delay_secs;
 	float ksamples_per_sec = (samples-userspace_samples)/delay_secs;
+	float esamples_percent = (100.0*exact_samples)/samples;
 	float sum_ksamples = 0.0;
 	struct sym_entry *syme, *n;
 	struct rb_root tmp = RB_ROOT;
@@ -458,7 +470,7 @@ static void print_sym_table(void)
 	int sym_width = 0, dso_width = 0, dso_short_width = 0;
 	const int win_width = winsize.ws_col - 1;
 
-	samples = userspace_samples = 0;
+	samples = userspace_samples = exact_samples = 0;
 
 	/* Sort the active symbols */
 	pthread_mutex_lock(&active_symbols_lock);
@@ -489,9 +501,10 @@ static void print_sym_table(void)
 	puts(CONSOLE_CLEAR);
 
 	printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
-	printf( "   PerfTop:%8.0f irqs/sec  kernel:%4.1f%% [",
+	printf( "   PerfTop:%8.0f irqs/sec  kernel:%4.1f%%  exact: %4.1f%% [",
 		samples_per_sec,
-		100.0 - (100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec)));
+		100.0 - (100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec)),
+		esamples_percent);
 
 	if (nr_counters == 1 || !display_weighted) {
 		printf("%Ld", (u64)attrs[0].sample_period);
@@ -514,13 +527,15 @@ static void print_sym_table(void)
 
 	if (target_pid != -1)
 		printf(" (target_pid: %d", target_pid);
+	else if (target_tid != -1)
+		printf(" (target_tid: %d", target_tid);
 	else
 		printf(" (all");
 
 	if (profile_cpu != -1)
 		printf(", cpu: %d)\n", profile_cpu);
 	else {
-		if (target_pid != -1)
+		if (target_tid != -1)
 			printf(")\n");
 		else
 			printf(", %d CPUs)\n", nr_cpus);
@@ -960,6 +975,9 @@ static void event__process_sample(const event_t *self,
 		return;
 	}
 
+	if (self->header.misc & PERF_RECORD_MISC_EXACT)
+		exact_samples++;
+
 	if (event__preprocess_sample(self, session, &al, symbol_filter) < 0 ||
 	    al.filtered)
 		return;
@@ -990,7 +1008,17 @@ static void event__process_sample(const event_t *self,
 	if (sym_filter_entry_sched) {
 		sym_filter_entry = sym_filter_entry_sched;
 		sym_filter_entry_sched = NULL;
-		parse_source(sym_filter_entry);
+		if (parse_source(sym_filter_entry) < 0) {
+			struct symbol *sym = sym_entry__symbol(sym_filter_entry);
+
+			pr_err("Can't annotate %s", sym->name);
+			if (sym_filter_entry->map->dso->origin == DSO__ORIG_KERNEL) {
+				pr_err(": No vmlinux file was found in the path:\n");
+				vmlinux_path__fprintf(stderr);
+			} else
+				pr_err(".\n");
+			exit(1);
+		}
 	}
 
 	syme = symbol__priv(al.sym);
@@ -1106,16 +1134,21 @@ static void perf_session__mmap_read_counter(struct perf_session *self,
 	md->prev = old;
 }
 
-static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS];
-static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
+static struct pollfd *event_array;
+static struct mmap_data *mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
 
 static void perf_session__mmap_read(struct perf_session *self)
 {
-	int i, counter;
+	int i, counter, thread_index;
 
 	for (i = 0; i < nr_cpus; i++) {
 		for (counter = 0; counter < nr_counters; counter++)
-			perf_session__mmap_read_counter(self, &mmap_array[i][counter]);
+			for (thread_index = 0;
+				thread_index < thread_num;
+				thread_index++) {
+				perf_session__mmap_read_counter(self,
+					&mmap_array[i][counter][thread_index]);
+			}
 	}
 }
 
@@ -1126,9 +1159,10 @@ static void start_counter(int i, int counter)
 {
 	struct perf_event_attr *attr;
 	int cpu;
+	int thread_index;
 
 	cpu = profile_cpu;
-	if (target_pid == -1 && profile_cpu == -1)
+	if (target_tid == -1 && profile_cpu == -1)
 		cpu = cpumap[i];
 
 	attr = attrs + counter;
@@ -1144,55 +1178,58 @@ static void start_counter(int i, int counter)
 	attr->inherit		= (cpu < 0) && inherit;
 	attr->mmap		= 1;
 
+	for (thread_index = 0; thread_index < thread_num; thread_index++) {
 try_again:
-	fd[i][counter] = sys_perf_event_open(attr, target_pid, cpu, group_fd, 0);
-
-	if (fd[i][counter] < 0) {
-		int err = errno;
+		fd[i][counter][thread_index] = sys_perf_event_open(attr,
+				all_tids[thread_index], cpu, group_fd, 0);
+
+		if (fd[i][counter][thread_index] < 0) {
+			int err = errno;
+
+			if (err == EPERM || err == EACCES)
+				die("No permission - are you root?\n");
+			/*
+			 * If it's cycles then fall back to hrtimer
+			 * based cpu-clock-tick sw counter, which
+			 * is always available even if no PMU support:
+			 */
+			if (attr->type == PERF_TYPE_HARDWARE
+					&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+
+				if (verbose)
+					warning(" ... trying to fall back to cpu-clock-ticks\n");
+
+				attr->type = PERF_TYPE_SOFTWARE;
+				attr->config = PERF_COUNT_SW_CPU_CLOCK;
+				goto try_again;
+			}
+			printf("\n");
+			error("perfcounter syscall returned with %d (%s)\n",
+					fd[i][counter][thread_index], strerror(err));
+			die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
+			exit(-1);
+		}
+		assert(fd[i][counter][thread_index] >= 0);
+		fcntl(fd[i][counter][thread_index], F_SETFL, O_NONBLOCK);
 
-		if (err == EPERM || err == EACCES)
-			die("No permission - are you root?\n");
 		/*
-		 * If it's cycles then fall back to hrtimer
-		 * based cpu-clock-tick sw counter, which
-		 * is always available even if no PMU support:
+		 * First counter acts as the group leader:
 		 */
-		if (attr->type == PERF_TYPE_HARDWARE
-			&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
-
-			if (verbose)
-				warning(" ... trying to fall back to cpu-clock-ticks\n");
-
-			attr->type = PERF_TYPE_SOFTWARE;
-			attr->config = PERF_COUNT_SW_CPU_CLOCK;
-			goto try_again;
-		}
-		printf("\n");
-		error("perfcounter syscall returned with %d (%s)\n",
-			fd[i][counter], strerror(err));
-		die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-		exit(-1);
+		if (group && group_fd == -1)
+			group_fd = fd[i][counter][thread_index];
+
+		event_array[nr_poll].fd = fd[i][counter][thread_index];
+		event_array[nr_poll].events = POLLIN;
+		nr_poll++;
+
+		mmap_array[i][counter][thread_index].counter = counter;
+		mmap_array[i][counter][thread_index].prev = 0;
+		mmap_array[i][counter][thread_index].mask = mmap_pages*page_size - 1;
+		mmap_array[i][counter][thread_index].base = mmap(NULL, (mmap_pages+1)*page_size,
+				PROT_READ, MAP_SHARED, fd[i][counter][thread_index], 0);
+		if (mmap_array[i][counter][thread_index].base == MAP_FAILED)
+			die("failed to mmap with %d (%s)\n", errno, strerror(errno));
 	}
-	assert(fd[i][counter] >= 0);
-	fcntl(fd[i][counter], F_SETFL, O_NONBLOCK);
-
-	/*
-	 * First counter acts as the group leader:
-	 */
-	if (group && group_fd == -1)
-		group_fd = fd[i][counter];
-
-	event_array[nr_poll].fd = fd[i][counter];
-	event_array[nr_poll].events = POLLIN;
-	nr_poll++;
-
-	mmap_array[i][counter].counter = counter;
-	mmap_array[i][counter].prev = 0;
-	mmap_array[i][counter].mask = mmap_pages*page_size - 1;
-	mmap_array[i][counter].base = mmap(NULL, (mmap_pages+1)*page_size,
-			PROT_READ, MAP_SHARED, fd[i][counter], 0);
-	if (mmap_array[i][counter].base == MAP_FAILED)
-		die("failed to mmap with %d (%s)\n", errno, strerror(errno));
 }
 
 static int __cmd_top(void)
@@ -1208,8 +1245,8 @@ static int __cmd_top(void)
 	if (session == NULL)
 		return -ENOMEM;
 
-	if (target_pid != -1)
-		event__synthesize_thread(target_pid, event__process, session);
+	if (target_tid != -1)
+		event__synthesize_thread(target_tid, event__process, session);
 	else
 		event__synthesize_threads(event__process, session);
 
@@ -1220,7 +1257,7 @@ static int __cmd_top(void)
 	}
 
 	/* Wait for a minimal set of events before starting the snapshot */
-	poll(event_array, nr_poll, 100);
+	poll(&event_array[0], nr_poll, 100);
 
 	perf_session__mmap_read(session);
 
@@ -1263,7 +1300,9 @@ static const struct option options[] = {
 	OPT_INTEGER('c', "count", &default_interval,
 		    "event period to sample"),
 	OPT_INTEGER('p', "pid", &target_pid,
-		    "profile events on existing pid"),
+		    "profile events on existing process id"),
+	OPT_INTEGER('t', "tid", &target_tid,
+		    "profile events on existing thread id"),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 			    "system-wide collection from all CPUs"),
 	OPT_INTEGER('C', "CPU", &profile_cpu,
@@ -1304,6 +1343,7 @@ static const struct option options[] = {
 int cmd_top(int argc, const char **argv, const char *prefix __used)
 {
 	int counter;
+	int i,j;
 
 	page_size = sysconf(_SC_PAGE_SIZE);
 
@@ -1311,8 +1351,39 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 	if (argc)
 		usage_with_options(top_usage, options);
 
+	if (target_pid != -1) {
+		target_tid = target_pid;
+		thread_num = find_all_tid(target_pid, &all_tids);
+		if (thread_num <= 0) {
+			fprintf(stderr, "Can't find all threads of pid %d\n",
+				target_pid);
+			usage_with_options(top_usage, options);
+		}
+	} else {
+		all_tids=malloc(sizeof(pid_t));
+		if (!all_tids)
+			return -ENOMEM;
+
+		all_tids[0] = target_tid;
+		thread_num = 1;
+	}
+
+	for (i = 0; i < MAX_NR_CPUS; i++) {
+		for (j = 0; j < MAX_COUNTERS; j++) {
+			fd[i][j] = malloc(sizeof(int)*thread_num);
+			mmap_array[i][j] = zalloc(
+				sizeof(struct mmap_data)*thread_num);
+			if (!fd[i][j] || !mmap_array[i][j])
+				return -ENOMEM;
+		}
+	}
+	event_array = malloc(
+		sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num);
+	if (!event_array)
+		return -ENOMEM;
+
 	/* CPU and PID are mutually exclusive */
-	if (target_pid != -1 && profile_cpu != -1) {
+	if (target_tid > 0 && profile_cpu != -1) {
 		printf("WARNING: PID switch overriding CPU\n");
 		sleep(1);
 		profile_cpu = -1;
@@ -1353,7 +1424,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 		attrs[counter].sample_period = default_interval;
 	}
 
-	if (target_pid != -1 || profile_cpu != -1)
+	if (target_tid != -1 || profile_cpu != -1)
 		nr_cpus = 1;
 	else
 		nr_cpus = read_cpu_map();
diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
index 910468e6e01c..2e7a4f417e20 100644
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -30,4 +30,7 @@ done
 
 tar cfj $PERF_DATA.tar.bz2 -C $DEBUGDIR -T $MANIFEST
 rm -f $MANIFEST $BUILDIDS
+echo -e "Now please run:\n"
+echo -e "$ tar xvf $PERF_DATA.tar.bz2 -C ~/.debug\n"
+echo "wherever you need to run 'perf report' on."
 exit 0
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index cd32c200cdb3..d4be55b6cd34 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -13,9 +13,10 @@
 #include "util/quote.h"
 #include "util/run-command.h"
 #include "util/parse-events.h"
-#include "util/string.h"
 #include "util/debugfs.h"
 
+bool use_browser;
+
 const char perf_usage_string[] =
 	"perf [--version] [--help] COMMAND [ARGS]";
 
@@ -262,6 +263,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	set_debugfs_path();
 
 	status = p->fn(argc, argv, prefix);
+	exit_browser(status);
+
 	if (status)
 		return status & 0xff;
 
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 6fb379bc1d1f..ec212748d651 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -1,6 +1,10 @@
 #ifndef _PERF_PERF_H
 #define _PERF_PERF_H
 
+struct winsize;
+
+void get_term_dimensions(struct winsize *ws);
+
 #if defined(__i386__)
 #include "../../arch/x86/include/asm/unistd.h"
 #define rmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
@@ -102,8 +106,6 @@ static inline unsigned long long rdclock(void)
 #define __user
 #define asmlinkage
 
-#define __used		__attribute__((__unused__))
-
 #define unlikely(x)	__builtin_expect(!!(x), 0)
 #define min(x, y) ({				\
 	typeof(x) _min1 = (x);			\
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 54552a00a117..49ece7921914 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -1,6 +1,10 @@
 #!/bin/sh
 
-GVF=PERF-VERSION-FILE
+if [ $# -eq 1 ]  ; then
+	OUTPUT=$1
+fi
+
+GVF=${OUTPUT}PERF-VERSION-FILE
 DEF_VER=v0.0.2.PERF
 
 LF='
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 918eb376abe3..4b9aab7f0405 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_CACHE_H
 #define __PERF_CACHE_H
 
+#include <stdbool.h>
 #include "util.h"
 #include "strbuf.h"
 #include "../perf.h"
@@ -69,6 +70,19 @@ extern const char *pager_program;
 extern int pager_in_use(void);
 extern int pager_use_color;
 
+extern bool use_browser;
+
+#ifdef NO_NEWT_SUPPORT
+static inline void setup_browser(void)
+{
+	setup_pager();
+}
+static inline void exit_browser(bool wait_for_ok __used) {}
+#else
+void setup_browser(void);
+void exit_browser(bool wait_for_ok);
+#endif
+
 extern const char *editor_program;
 extern const char *excludes_file;
 
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index b3b71258272a..db628af6d20d 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2009, Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2009-2010, Frederic Weisbecker <fweisbec@gmail.com>
  *
  * Handle the callchains from the stream in an ad-hoc radix tree and then
  * sort them in an rbtree.
@@ -183,12 +183,23 @@ create_child(struct callchain_node *parent, bool inherit_children)
 	return new;
 }
 
+
+struct resolved_ip {
+	u64		  ip;
+	struct map_symbol ms;
+};
+
+struct resolved_chain {
+	u64			nr;
+	struct resolved_ip	ips[0];
+};
+
+
 /*
  * Fill the node with callchain values
  */
 static void
-fill_node(struct callchain_node *node, struct ip_callchain *chain,
-	  int start, struct symbol **syms)
+fill_node(struct callchain_node *node, struct resolved_chain *chain, int start)
 {
 	unsigned int i;
 
@@ -200,8 +211,8 @@ fill_node(struct callchain_node *node, struct ip_callchain *chain,
 			perror("not enough memory for the code path tree");
 			return;
 		}
-		call->ip = chain->ips[i];
-		call->sym = syms[i];
+		call->ip = chain->ips[i].ip;
+		call->ms = chain->ips[i].ms;
 		list_add_tail(&call->list, &node->val);
 	}
 	node->val_nr = chain->nr - start;
@@ -210,13 +221,13 @@ fill_node(struct callchain_node *node, struct ip_callchain *chain,
 }
 
 static void
-add_child(struct callchain_node *parent, struct ip_callchain *chain,
-	  int start, struct symbol **syms)
+add_child(struct callchain_node *parent, struct resolved_chain *chain,
+	  int start)
 {
 	struct callchain_node *new;
 
 	new = create_child(parent, false);
-	fill_node(new, chain, start, syms);
+	fill_node(new, chain, start);
 
 	new->children_hit = 0;
 	new->hit = 1;
@@ -228,9 +239,8 @@ add_child(struct callchain_node *parent, struct ip_callchain *chain,
  * Then create another child to host the given callchain of new branch
  */
 static void
-split_add_child(struct callchain_node *parent, struct ip_callchain *chain,
-		struct callchain_list *to_split, int idx_parents, int idx_local,
-		struct symbol **syms)
+split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
+		struct callchain_list *to_split, int idx_parents, int idx_local)
 {
 	struct callchain_node *new;
 	struct list_head *old_tail;
@@ -257,7 +267,7 @@ split_add_child(struct callchain_node *parent, struct ip_callchain *chain,
 	/* create a new child for the new branch if any */
 	if (idx_total < chain->nr) {
 		parent->hit = 0;
-		add_child(parent, chain, idx_total, syms);
+		add_child(parent, chain, idx_total);
 		parent->children_hit++;
 	} else {
 		parent->hit = 1;
@@ -265,32 +275,33 @@ split_add_child(struct callchain_node *parent, struct ip_callchain *chain,
 }
 
 static int
-__append_chain(struct callchain_node *root, struct ip_callchain *chain,
-	       unsigned int start, struct symbol **syms);
+__append_chain(struct callchain_node *root, struct resolved_chain *chain,
+	       unsigned int start);
 
 static void
-__append_chain_children(struct callchain_node *root, struct ip_callchain *chain,
-			struct symbol **syms, unsigned int start)
+__append_chain_children(struct callchain_node *root,
+			struct resolved_chain *chain,
+			unsigned int start)
 {
 	struct callchain_node *rnode;
 
 	/* lookup in childrens */
 	chain_for_each_child(rnode, root) {
-		unsigned int ret = __append_chain(rnode, chain, start, syms);
+		unsigned int ret = __append_chain(rnode, chain, start);
 
 		if (!ret)
 			goto inc_children_hit;
 	}
 	/* nothing in children, add to the current node */
-	add_child(root, chain, start, syms);
+	add_child(root, chain, start);
 
 inc_children_hit:
 	root->children_hit++;
 }
 
 static int
-__append_chain(struct callchain_node *root, struct ip_callchain *chain,
-	       unsigned int start, struct symbol **syms)
+__append_chain(struct callchain_node *root, struct resolved_chain *chain,
+	       unsigned int start)
 {
 	struct callchain_list *cnode;
 	unsigned int i = start;
@@ -302,13 +313,19 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain,
 	 * anywhere inside a function.
 	 */
 	list_for_each_entry(cnode, &root->val, list) {
+		struct symbol *sym;
+
 		if (i == chain->nr)
 			break;
-		if (cnode->sym && syms[i]) {
-			if (cnode->sym->start != syms[i]->start)
+
+		sym = chain->ips[i].ms.sym;
+
+		if (cnode->ms.sym && sym) {
+			if (cnode->ms.sym->start != sym->start)
 				break;
-		} else if (cnode->ip != chain->ips[i])
+		} else if (cnode->ip != chain->ips[i].ip)
 			break;
+
 		if (!found)
 			found = true;
 		i++;
@@ -320,7 +337,7 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain,
 
 	/* we match only a part of the node. Split it and add the new chain */
 	if (i - start < root->val_nr) {
-		split_add_child(root, chain, cnode, start, i - start, syms);
+		split_add_child(root, chain, cnode, start, i - start);
 		return 0;
 	}
 
@@ -331,15 +348,50 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain,
 	}
 
 	/* We match the node and still have a part remaining */
-	__append_chain_children(root, chain, syms, i);
+	__append_chain_children(root, chain, i);
 
 	return 0;
 }
 
-void append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		  struct symbol **syms)
+static void filter_context(struct ip_callchain *old, struct resolved_chain *new,
+			   struct map_symbol *syms)
+{
+	int i, j = 0;
+
+	for (i = 0; i < (int)old->nr; i++) {
+		if (old->ips[i] >= PERF_CONTEXT_MAX)
+			continue;
+
+		new->ips[j].ip = old->ips[i];
+		new->ips[j].ms = syms[i];
+		j++;
+	}
+
+	new->nr = j;
+}
+
+
+int append_chain(struct callchain_node *root, struct ip_callchain *chain,
+		 struct map_symbol *syms)
 {
+	struct resolved_chain *filtered;
+
 	if (!chain->nr)
-		return;
-	__append_chain_children(root, chain, syms, 0);
+		return 0;
+
+	filtered = malloc(sizeof(*filtered) +
+			  chain->nr * sizeof(struct resolved_ip));
+	if (!filtered)
+		return -ENOMEM;
+
+	filter_context(chain, filtered, syms);
+
+	if (!filtered->nr)
+		goto end;
+
+	__append_chain_children(root, filtered, 0);
+end:
+	free(filtered);
+
+	return 0;
 }
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index ad4626de4c2b..8a7e8bbd0fda 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -39,7 +39,7 @@ struct callchain_param {
 
 struct callchain_list {
 	u64			ip;
-	struct symbol		*sym;
+	struct map_symbol	ms;
 	struct list_head	list;
 };
 
@@ -56,6 +56,6 @@ static inline u64 cumul_hits(struct callchain_node *node)
 }
 
 int register_callchain_param(struct callchain_param *param);
-void append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		  struct symbol **syms);
+int append_chain(struct callchain_node *root, struct ip_callchain *chain,
+		 struct map_symbol *syms);
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index e88bca55a599..e191eb9a667f 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -166,6 +166,31 @@ int perf_color_default_config(const char *var, const char *value, void *cb)
 	return perf_default_config(var, value, cb);
 }
 
+static int __color_vsnprintf(char *bf, size_t size, const char *color,
+			     const char *fmt, va_list args, const char *trail)
+{
+	int r = 0;
+
+	/*
+	 * Auto-detect:
+	 */
+	if (perf_use_color_default < 0) {
+		if (isatty(1) || pager_in_use())
+			perf_use_color_default = 1;
+		else
+			perf_use_color_default = 0;
+	}
+
+	if (perf_use_color_default && *color)
+		r += snprintf(bf, size, "%s", color);
+	r += vsnprintf(bf + r, size - r, fmt, args);
+	if (perf_use_color_default && *color)
+		r += snprintf(bf + r, size - r, "%s", PERF_COLOR_RESET);
+	if (trail)
+		r += snprintf(bf + r, size - r, "%s", trail);
+	return r;
+}
+
 static int __color_vfprintf(FILE *fp, const char *color, const char *fmt,
 		va_list args, const char *trail)
 {
@@ -191,11 +216,28 @@ static int __color_vfprintf(FILE *fp, const char *color, const char *fmt,
 	return r;
 }
 
+int color_vsnprintf(char *bf, size_t size, const char *color,
+		    const char *fmt, va_list args)
+{
+	return __color_vsnprintf(bf, size, color, fmt, args, NULL);
+}
+
 int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args)
 {
 	return __color_vfprintf(fp, color, fmt, args, NULL);
 }
 
+int color_snprintf(char *bf, size_t size, const char *color,
+		   const char *fmt, ...)
+{
+	va_list args;
+	int r;
+
+	va_start(args, fmt);
+	r = color_vsnprintf(bf, size, color, fmt, args);
+	va_end(args);
+	return r;
+}
 
 int color_fprintf(FILE *fp, const char *color, const char *fmt, ...)
 {
@@ -274,3 +316,9 @@ int percent_color_fprintf(FILE *fp, const char *fmt, double percent)
 
 	return r;
 }
+
+int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent)
+{
+	const char *color = get_percent_color(percent);
+	return color_snprintf(bf, size, color, fmt, percent);
+}
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index 24e8809210bb..dea082b79602 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -32,10 +32,14 @@ int perf_color_default_config(const char *var, const char *value, void *cb);
 int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty);
 void color_parse(const char *value, const char *var, char *dst);
 void color_parse_mem(const char *value, int len, const char *var, char *dst);
+int color_vsnprintf(char *bf, size_t size, const char *color,
+		    const char *fmt, va_list args);
 int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args);
 int color_fprintf(FILE *fp, const char *color, const char *fmt, ...);
+int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...);
 int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
 int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
+int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent);
 int percent_color_fprintf(FILE *fp, const char *fmt, double percent);
 const char *get_percent_color(double percent);
 
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 0905600c3851..033d66db863a 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -6,6 +6,7 @@
 #include <stdarg.h>
 #include <stdio.h>
 
+#include "cache.h"
 #include "color.h"
 #include "event.h"
 #include "debug.h"
@@ -21,7 +22,10 @@ int eprintf(int level, const char *fmt, ...)
 
 	if (verbose >= level) {
 		va_start(args, fmt);
-		ret = vfprintf(stderr, fmt, args);
+		if (use_browser)
+			ret = browser__show_help(fmt, args);
+		else
+			ret = vfprintf(stderr, fmt, args);
 		va_end(args);
 	}
 
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index c6c24c522dea..5cb0a1b1401a 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -7,9 +7,32 @@
 extern int verbose;
 extern int dump_trace;
 
-int eprintf(int level,
-	    const char *fmt, ...) __attribute__((format(printf, 2, 3)));
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(event_t *event);
 
+struct ui_progress;
+
+#ifdef NO_NEWT_SUPPORT
+static inline int browser__show_help(const char *format __used, va_list ap __used)
+{
+	return 0;
+}
+
+static inline struct ui_progress *ui_progress__new(const char *title __used,
+						   u64 total __used)
+{
+	return (struct ui_progress *)1;
+}
+
+static inline void ui_progress__update(struct ui_progress *self __used,
+				       u64 curr __used) {}
+
+static inline void ui_progress__delete(struct ui_progress *self __used) {}
+#else
+int browser__show_help(const char *format, va_list ap);
+struct ui_progress *ui_progress__new(const char *title, u64 total);
+void ui_progress__update(struct ui_progress *self, u64 curr);
+void ui_progress__delete(struct ui_progress *self);
+#endif
+
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 705ec63548b4..571fb25f7eb9 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -130,6 +130,7 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
 			continue;
 		pbf += n + 3;
 		if (*pbf == 'x') { /* vm_exec */
+			u64 vm_pgoff;
 			char *execname = strchr(bf, '/');
 
 			/* Catch VDSO */
@@ -139,6 +140,14 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
 			if (execname == NULL)
 				continue;
 
+			pbf += 3;
+			n = hex2u64(pbf, &vm_pgoff);
+			/* pgoff is in bytes, not pages */
+			if (n >= 0)
+				ev.mmap.pgoff = vm_pgoff << getpagesize();
+			else
+				ev.mmap.pgoff = 0;
+
 			size = strlen(execname);
 			execname[size - 1] = '\0'; /* Remove \n */
 			memcpy(ev.mmap.filename, execname, size);
@@ -393,7 +402,8 @@ int event__process_mmap(event_t *self, struct perf_session *session)
 	}
 
 	thread = perf_session__findnew(session, self->mmap.pid);
-	map = map__new(&self->mmap, MAP__FUNCTION,
+	map = map__new(self->mmap.start, self->mmap.len, self->mmap.pgoff,
+		       self->mmap.pid, self->mmap.filename, MAP__FUNCTION,
 		       session->cwd, session->cwdlen);
 
 	if (thread == NULL || map == NULL)
@@ -513,24 +523,32 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session,
 
 	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
 
-	thread__find_addr_location(thread, session, cpumode, MAP__FUNCTION,
-				   self->ip.ip, al, filter);
+	thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
+			      self->ip.ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
-	/*
-	 * We have to do this here as we may have a dso with no symbol hit that
-	 * has a name longer than the ones with symbols sampled.
-	 */
-	if (al->map && !sort_dso.elide && !al->map->dso->slen_calculated)
-		dso__calc_col_width(al->map->dso);
-
-	if (symbol_conf.dso_list &&
-	    (!al->map || !al->map->dso ||
-	     !(strlist__has_entry(symbol_conf.dso_list, al->map->dso->short_name) ||
-	       (al->map->dso->short_name != al->map->dso->long_name &&
-		strlist__has_entry(symbol_conf.dso_list, al->map->dso->long_name)))))
-		goto out_filtered;
+	al->sym = NULL;
+
+	if (al->map) {
+		if (symbol_conf.dso_list &&
+		    (!al->map || !al->map->dso ||
+		     !(strlist__has_entry(symbol_conf.dso_list,
+					  al->map->dso->short_name) ||
+		       (al->map->dso->short_name != al->map->dso->long_name &&
+			strlist__has_entry(symbol_conf.dso_list,
+					   al->map->dso->long_name)))))
+			goto out_filtered;
+		/*
+		 * We have to do this here as we may have a dso with no symbol
+		 * hit that has a name longer than the ones with symbols
+		 * sampled.
+		 */
+		if (!sort_dso.elide && !al->map->dso->slen_calculated)
+			dso__calc_col_width(al->map->dso);
+
+		al->sym = map__find_symbol(al->map, al->addr, filter);
+	}
 
 	if (symbol_conf.sym_list && al->sym &&
 	    !strlist__has_entry(symbol_conf.sym_list, al->sym->name))
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index a33b94952e34..7f7cf8539cfe 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -68,11 +68,11 @@ struct sample_data {
 	u64 addr;
 	u64 id;
 	u64 stream_id;
-	u32 cpu;
 	u64 period;
-	struct ip_callchain *callchain;
+	u32 cpu;
 	u32 raw_size;
 	void *raw_data;
+	struct ip_callchain *callchain;
 };
 
 #define BUILD_ID_SIZE 20
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 82a6af72d4cc..c059f08cf877 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -47,13 +47,13 @@ int perf_file_header__read(struct perf_file_header *self,
 struct perf_header {
 	int			frozen;
 	int			attrs, size;
+	bool			needs_swap;
 	struct perf_header_attr **attr;
 	s64			attr_offset;
 	u64			data_offset;
 	u64			data_size;
 	u64			event_offset;
 	u64			event_size;
-	bool			needs_swap;
 	DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
 };
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 2be33c7dbf03..18cf8b321608 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -22,8 +22,10 @@ struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
 	struct hist_entry *he;
 	struct hist_entry entry = {
 		.thread	= al->thread,
-		.map	= al->map,
-		.sym	= al->sym,
+		.ms = {
+			.map	= al->map,
+			.sym	= al->sym,
+		},
 		.ip	= al->addr,
 		.level	= al->level,
 		.count	= count,
@@ -48,7 +50,8 @@ struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
 			p = &(*p)->rb_right;
 	}
 
-	he = malloc(sizeof(*he));
+	he = malloc(sizeof(*he) + (symbol_conf.use_callchain ?
+				    sizeof(struct callchain_node) : 0));
 	if (!he)
 		return NULL;
 	*he = entry;
@@ -166,7 +169,7 @@ static void perf_session__insert_output_hist_entry(struct rb_root *root,
 	struct hist_entry *iter;
 
 	if (symbol_conf.use_callchain)
-		callchain_param.sort(&he->sorted_chain, &he->callchain,
+		callchain_param.sort(&he->sorted_chain, he->callchain,
 				      min_callchain_hits, &callchain_param);
 
 	while (*p != NULL) {
@@ -183,12 +186,13 @@ static void perf_session__insert_output_hist_entry(struct rb_root *root,
 	rb_insert_color(&he->rb_node, root);
 }
 
-void perf_session__output_resort(struct rb_root *hists, u64 total_samples)
+u64 perf_session__output_resort(struct rb_root *hists, u64 total_samples)
 {
 	struct rb_root tmp;
 	struct rb_node *next;
 	struct hist_entry *n;
 	u64 min_callchain_hits;
+	u64 nr_hists = 0;
 
 	min_callchain_hits =
 		total_samples * (callchain_param.min_percent / 100);
@@ -203,9 +207,11 @@ void perf_session__output_resort(struct rb_root *hists, u64 total_samples)
 		rb_erase(&n->rb_node, hists);
 		perf_session__insert_output_hist_entry(&tmp, n,
 						       min_callchain_hits);
+		++nr_hists;
 	}
 
 	*hists = tmp;
+	return nr_hists;
 }
 
 static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
@@ -258,8 +264,8 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
 		} else
 			ret += fprintf(fp, "%s", "          ");
 	}
-	if (chain->sym)
-		ret += fprintf(fp, "%s\n", chain->sym->name);
+	if (chain->ms.sym)
+		ret += fprintf(fp, "%s\n", chain->ms.sym->name);
 	else
 		ret += fprintf(fp, "%p\n", (void *)(long)chain->ip);
 
@@ -278,7 +284,7 @@ static void init_rem_hits(void)
 	}
 
 	strcpy(rem_sq_bracket->name, "[...]");
-	rem_hits.sym = rem_sq_bracket;
+	rem_hits.ms.sym = rem_sq_bracket;
 }
 
 static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
@@ -328,8 +334,6 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 						   left_margin);
 		i = 0;
 		list_for_each_entry(chain, &child->val, list) {
-			if (chain->ip >= PERF_CONTEXT_MAX)
-				continue;
 			ret += ipchain__fprintf_graph(fp, chain, depth,
 						      new_depth_mask, i++,
 						      new_total,
@@ -368,9 +372,6 @@ static size_t callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	int ret = 0;
 
 	list_for_each_entry(chain, &self->val, list) {
-		if (chain->ip >= PERF_CONTEXT_MAX)
-			continue;
-
 		if (!i++ && sort__first_dimension == SORT_SYM)
 			continue;
 
@@ -385,8 +386,8 @@ static size_t callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 		} else
 			ret += callchain__fprintf_left_margin(fp, left_margin);
 
-		if (chain->sym)
-			ret += fprintf(fp, " %s\n", chain->sym->name);
+		if (chain->ms.sym)
+			ret += fprintf(fp, " %s\n", chain->ms.sym->name);
 		else
 			ret += fprintf(fp, " %p\n", (void *)(long)chain->ip);
 	}
@@ -411,8 +412,8 @@ static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self,
 	list_for_each_entry(chain, &self->val, list) {
 		if (chain->ip >= PERF_CONTEXT_MAX)
 			continue;
-		if (chain->sym)
-			ret += fprintf(fp, "                %s\n", chain->sym->name);
+		if (chain->ms.sym)
+			ret += fprintf(fp, "                %s\n", chain->ms.sym->name);
 		else
 			ret += fprintf(fp, "                %p\n",
 					(void *)(long)chain->ip);
@@ -455,16 +456,17 @@ static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self,
 	return ret;
 }
 
-static size_t hist_entry__fprintf(struct hist_entry *self,
-				  struct perf_session *pair_session,
-				  bool show_displacement,
-				  long displacement, FILE *fp,
-				  u64 session_total)
+int hist_entry__snprintf(struct hist_entry *self,
+			   char *s, size_t size,
+			   struct perf_session *pair_session,
+			   bool show_displacement,
+			   long displacement, bool color,
+			   u64 session_total)
 {
 	struct sort_entry *se;
 	u64 count, total;
 	const char *sep = symbol_conf.field_sep;
-	size_t ret;
+	int ret;
 
 	if (symbol_conf.exclude_other && !self->parent)
 		return 0;
@@ -477,17 +479,22 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
 		total = session_total;
 	}
 
-	if (total)
-		ret = percent_color_fprintf(fp, sep ? "%.2f" : "   %6.2f%%",
-					    (count * 100.0) / total);
-	else
-		ret = fprintf(fp, sep ? "%lld" : "%12lld ", count);
+	if (total) {
+		if (color)
+			ret = percent_color_snprintf(s, size,
+						     sep ? "%.2f" : "   %6.2f%%",
+						     (count * 100.0) / total);
+		else
+			ret = snprintf(s, size, sep ? "%.2f" : "   %6.2f%%",
+				       (count * 100.0) / total);
+	} else
+		ret = snprintf(s, size, sep ? "%lld" : "%12lld ", count);
 
 	if (symbol_conf.show_nr_samples) {
 		if (sep)
-			fprintf(fp, "%c%lld", *sep, count);
+			ret += snprintf(s + ret, size - ret, "%c%lld", *sep, count);
 		else
-			fprintf(fp, "%11lld", count);
+			ret += snprintf(s + ret, size - ret, "%11lld", count);
 	}
 
 	if (pair_session) {
@@ -507,9 +514,9 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
 			snprintf(bf, sizeof(bf), " ");
 
 		if (sep)
-			ret += fprintf(fp, "%c%s", *sep, bf);
+			ret += snprintf(s + ret, size - ret, "%c%s", *sep, bf);
 		else
-			ret += fprintf(fp, "%11.11s", bf);
+			ret += snprintf(s + ret, size - ret, "%11.11s", bf);
 
 		if (show_displacement) {
 			if (displacement)
@@ -518,9 +525,9 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
 				snprintf(bf, sizeof(bf), " ");
 
 			if (sep)
-				fprintf(fp, "%c%s", *sep, bf);
+				ret += snprintf(s + ret, size - ret, "%c%s", *sep, bf);
 			else
-				fprintf(fp, "%6.6s", bf);
+				ret += snprintf(s + ret, size - ret, "%6.6s", bf);
 		}
 	}
 
@@ -528,27 +535,41 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
 		if (se->elide)
 			continue;
 
-		fprintf(fp, "%s", sep ?: "  ");
-		ret += se->print(fp, self, se->width ? *se->width : 0);
+		ret += snprintf(s + ret, size - ret, "%s", sep ?: "  ");
+		ret += se->snprintf(self, s + ret, size - ret,
+				    se->width ? *se->width : 0);
 	}
 
-	ret += fprintf(fp, "\n");
+	return ret;
+}
 
-	if (symbol_conf.use_callchain) {
-		int left_margin = 0;
+int hist_entry__fprintf(struct hist_entry *self,
+			struct perf_session *pair_session,
+			bool show_displacement,
+			long displacement, FILE *fp,
+			u64 session_total)
+{
+	char bf[512];
+	hist_entry__snprintf(self, bf, sizeof(bf), pair_session,
+			     show_displacement, displacement,
+			     true, session_total);
+	return fprintf(fp, "%s\n", bf);
+}
 
-		if (sort__first_dimension == SORT_COMM) {
-			se = list_first_entry(&hist_entry__sort_list, typeof(*se),
-						list);
-			left_margin = se->width ? *se->width : 0;
-			left_margin -= thread__comm_len(self->thread);
-		}
+static size_t hist_entry__fprintf_callchain(struct hist_entry *self, FILE *fp,
+					    u64 session_total)
+{
+	int left_margin = 0;
 
-		hist_entry_callchain__fprintf(fp, self, session_total,
-					      left_margin);
+	if (sort__first_dimension == SORT_COMM) {
+		struct sort_entry *se = list_first_entry(&hist_entry__sort_list,
+							 typeof(*se), list);
+		left_margin = se->width ? *se->width : 0;
+		left_margin -= thread__comm_len(self->thread);
 	}
 
-	return ret;
+	return hist_entry_callchain__fprintf(fp, self, session_total,
+					     left_margin);
 }
 
 size_t perf_session__fprintf_hists(struct rb_root *hists,
@@ -655,9 +676,13 @@ print_entries:
 		}
 		ret += hist_entry__fprintf(h, pair, show_displacement,
 					   displacement, fp, session_total);
-		if (h->map == NULL && verbose > 1) {
+
+		if (symbol_conf.use_callchain)
+			ret += hist_entry__fprintf_callchain(h, fp, session_total);
+
+		if (h->ms.map == NULL && verbose > 1) {
 			__map_groups__fprintf_maps(&h->thread->mg,
-						   MAP__FUNCTION, fp);
+						   MAP__FUNCTION, verbose, fp);
 			fprintf(fp, "%.10s end\n", graph_dotted_line);
 		}
 	}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 16f360cce5bf..ad17f0ad798b 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -18,9 +18,19 @@ struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
 						  u64 count, bool *hit);
 extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *);
 extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *);
+int hist_entry__fprintf(struct hist_entry *self,
+			   struct perf_session *pair_session,
+			   bool show_displacement,
+			   long displacement, FILE *fp,
+			   u64 session_total);
+int hist_entry__snprintf(struct hist_entry *self,
+			 char *bf, size_t size,
+			 struct perf_session *pair_session,
+			 bool show_displacement, long displacement,
+			 bool color, u64 session_total);
 void hist_entry__free(struct hist_entry *);
 
-void perf_session__output_resort(struct rb_root *hists, u64 total_samples);
+u64 perf_session__output_resort(struct rb_root *hists, u64 total_samples);
 void perf_session__collapse_resort(struct rb_root *hists);
 size_t perf_session__fprintf_hists(struct rb_root *hists,
 				   struct perf_session *pair,
diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h
index dfb0713ed47f..791f9dd27ebf 100644
--- a/tools/perf/util/include/linux/compiler.h
+++ b/tools/perf/util/include/linux/compiler.h
@@ -7,4 +7,6 @@
 #define __user
 #define __attribute_const__
 
+#define __used		__attribute__((__unused__))
+
 #endif
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index f2611655ab51..388ab1bfd114 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/perf/util/include/linux/kernel.h
@@ -85,16 +85,19 @@ simple_strtoul(const char *nptr, char **endptr, int base)
 	return strtoul(nptr, endptr, base);
 }
 
+int eprintf(int level,
+	    const char *fmt, ...) __attribute__((format(printf, 2, 3)));
+
 #ifndef pr_fmt
 #define pr_fmt(fmt) fmt
 #endif
 
 #define pr_err(fmt, ...) \
-	do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0)
+	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_warning(fmt, ...) \
-	do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0)
+	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_info(fmt, ...) \
-	do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0)
+	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_debug(fmt, ...) \
 	eprintf(1, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_debugN(n, fmt, ...) \
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index e509cd59c67d..37913b241bdf 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -1,9 +1,10 @@
-#include "event.h"
 #include "symbol.h"
+#include <errno.h>
+#include <limits.h>
 #include <stdlib.h>
 #include <string.h>
 #include <stdio.h>
-#include "debug.h"
+#include "map.h"
 
 const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__FUNCTION] = "Functions",
@@ -38,13 +39,12 @@ void map__init(struct map *self, enum map_type type,
 	RB_CLEAR_NODE(&self->rb_node);
 }
 
-struct map *map__new(struct mmap_event *event, enum map_type type,
-		     char *cwd, int cwdlen)
+struct map *map__new(u64 start, u64 len, u64 pgoff, u32 pid, char *filename,
+		     enum map_type type, char *cwd, int cwdlen)
 {
 	struct map *self = malloc(sizeof(*self));
 
 	if (self != NULL) {
-		const char *filename = event->filename;
 		char newfilename[PATH_MAX];
 		struct dso *dso;
 		int anon;
@@ -62,7 +62,7 @@ struct map *map__new(struct mmap_event *event, enum map_type type,
 		anon = is_anon_memory(filename);
 
 		if (anon) {
-			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", event->pid);
+			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
 			filename = newfilename;
 		}
 
@@ -70,8 +70,7 @@ struct map *map__new(struct mmap_event *event, enum map_type type,
 		if (dso == NULL)
 			goto out_delete;
 
-		map__init(self, type, event->start, event->start + event->len,
-			  event->pgoff, dso);
+		map__init(self, type, start, start + len, pgoff, dso);
 
 		if (anon) {
 set_identity:
@@ -235,3 +234,277 @@ u64 map__objdump_2ip(struct map *map, u64 addr)
 			map->unmap_ip(map, addr);	/* RIP -> IP */
 	return ip;
 }
+
+void map_groups__init(struct map_groups *self)
+{
+	int i;
+	for (i = 0; i < MAP__NR_TYPES; ++i) {
+		self->maps[i] = RB_ROOT;
+		INIT_LIST_HEAD(&self->removed_maps[i]);
+	}
+}
+
+void map_groups__flush(struct map_groups *self)
+{
+	int type;
+
+	for (type = 0; type < MAP__NR_TYPES; type++) {
+		struct rb_root *root = &self->maps[type];
+		struct rb_node *next = rb_first(root);
+
+		while (next) {
+			struct map *pos = rb_entry(next, struct map, rb_node);
+			next = rb_next(&pos->rb_node);
+			rb_erase(&pos->rb_node, root);
+			/*
+			 * We may have references to this map, for
+			 * instance in some hist_entry instances, so
+			 * just move them to a separate list.
+			 */
+			list_add_tail(&pos->node, &self->removed_maps[pos->type]);
+		}
+	}
+}
+
+struct symbol *map_groups__find_symbol(struct map_groups *self,
+				       enum map_type type, u64 addr,
+				       struct map **mapp,
+				       symbol_filter_t filter)
+{
+	struct map *map = map_groups__find(self, type, addr);
+
+	if (map != NULL) {
+		if (mapp != NULL)
+			*mapp = map;
+		return map__find_symbol(map, map->map_ip(map, addr), filter);
+	}
+
+	return NULL;
+}
+
+struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
+					       enum map_type type,
+					       const char *name,
+					       struct map **mapp,
+					       symbol_filter_t filter)
+{
+	struct rb_node *nd;
+
+	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+		struct map *pos = rb_entry(nd, struct map, rb_node);
+		struct symbol *sym = map__find_symbol_by_name(pos, name, filter);
+
+		if (sym == NULL)
+			continue;
+		if (mapp != NULL)
+			*mapp = pos;
+		return sym;
+	}
+
+	return NULL;
+}
+
+size_t __map_groups__fprintf_maps(struct map_groups *self,
+				  enum map_type type, int verbose, FILE *fp)
+{
+	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
+	struct rb_node *nd;
+
+	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+		struct map *pos = rb_entry(nd, struct map, rb_node);
+		printed += fprintf(fp, "Map:");
+		printed += map__fprintf(pos, fp);
+		if (verbose > 2) {
+			printed += dso__fprintf(pos->dso, type, fp);
+			printed += fprintf(fp, "--\n");
+		}
+	}
+
+	return printed;
+}
+
+size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp)
+{
+	size_t printed = 0, i;
+	for (i = 0; i < MAP__NR_TYPES; ++i)
+		printed += __map_groups__fprintf_maps(self, i, verbose, fp);
+	return printed;
+}
+
+static size_t __map_groups__fprintf_removed_maps(struct map_groups *self,
+						 enum map_type type,
+						 int verbose, FILE *fp)
+{
+	struct map *pos;
+	size_t printed = 0;
+
+	list_for_each_entry(pos, &self->removed_maps[type], node) {
+		printed += fprintf(fp, "Map:");
+		printed += map__fprintf(pos, fp);
+		if (verbose > 1) {
+			printed += dso__fprintf(pos->dso, type, fp);
+			printed += fprintf(fp, "--\n");
+		}
+	}
+	return printed;
+}
+
+static size_t map_groups__fprintf_removed_maps(struct map_groups *self,
+					       int verbose, FILE *fp)
+{
+	size_t printed = 0, i;
+	for (i = 0; i < MAP__NR_TYPES; ++i)
+		printed += __map_groups__fprintf_removed_maps(self, i, verbose, fp);
+	return printed;
+}
+
+size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp)
+{
+	size_t printed = map_groups__fprintf_maps(self, verbose, fp);
+	printed += fprintf(fp, "Removed maps:\n");
+	return printed + map_groups__fprintf_removed_maps(self, verbose, fp);
+}
+
+int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
+				   int verbose, FILE *fp)
+{
+	struct rb_root *root = &self->maps[map->type];
+	struct rb_node *next = rb_first(root);
+
+	while (next) {
+		struct map *pos = rb_entry(next, struct map, rb_node);
+		next = rb_next(&pos->rb_node);
+
+		if (!map__overlap(pos, map))
+			continue;
+
+		if (verbose >= 2) {
+			fputs("overlapping maps:\n", fp);
+			map__fprintf(map, fp);
+			map__fprintf(pos, fp);
+		}
+
+		rb_erase(&pos->rb_node, root);
+		/*
+		 * We may have references to this map, for instance in some
+		 * hist_entry instances, so just move them to a separate
+		 * list.
+		 */
+		list_add_tail(&pos->node, &self->removed_maps[map->type]);
+		/*
+		 * Now check if we need to create new maps for areas not
+		 * overlapped by the new map:
+		 */
+		if (map->start > pos->start) {
+			struct map *before = map__clone(pos);
+
+			if (before == NULL)
+				return -ENOMEM;
+
+			before->end = map->start - 1;
+			map_groups__insert(self, before);
+			if (verbose >= 2)
+				map__fprintf(before, fp);
+		}
+
+		if (map->end < pos->end) {
+			struct map *after = map__clone(pos);
+
+			if (after == NULL)
+				return -ENOMEM;
+
+			after->start = map->end + 1;
+			map_groups__insert(self, after);
+			if (verbose >= 2)
+				map__fprintf(after, fp);
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * XXX This should not really _copy_ te maps, but refcount them.
+ */
+int map_groups__clone(struct map_groups *self,
+		      struct map_groups *parent, enum map_type type)
+{
+	struct rb_node *nd;
+	for (nd = rb_first(&parent->maps[type]); nd; nd = rb_next(nd)) {
+		struct map *map = rb_entry(nd, struct map, rb_node);
+		struct map *new = map__clone(map);
+		if (new == NULL)
+			return -ENOMEM;
+		map_groups__insert(self, new);
+	}
+	return 0;
+}
+
+static u64 map__reloc_map_ip(struct map *map, u64 ip)
+{
+	return ip + (s64)map->pgoff;
+}
+
+static u64 map__reloc_unmap_ip(struct map *map, u64 ip)
+{
+	return ip - (s64)map->pgoff;
+}
+
+void map__reloc_vmlinux(struct map *self)
+{
+	struct kmap *kmap = map__kmap(self);
+	s64 reloc;
+
+	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr)
+		return;
+
+	reloc = (kmap->ref_reloc_sym->unrelocated_addr -
+		 kmap->ref_reloc_sym->addr);
+
+	if (!reloc)
+		return;
+
+	self->map_ip   = map__reloc_map_ip;
+	self->unmap_ip = map__reloc_unmap_ip;
+	self->pgoff    = reloc;
+}
+
+void maps__insert(struct rb_root *maps, struct map *map)
+{
+	struct rb_node **p = &maps->rb_node;
+	struct rb_node *parent = NULL;
+	const u64 ip = map->start;
+	struct map *m;
+
+	while (*p != NULL) {
+		parent = *p;
+		m = rb_entry(parent, struct map, rb_node);
+		if (ip < m->start)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&map->rb_node, parent, p);
+	rb_insert_color(&map->rb_node, maps);
+}
+
+struct map *maps__find(struct rb_root *maps, u64 ip)
+{
+	struct rb_node **p = &maps->rb_node;
+	struct rb_node *parent = NULL;
+	struct map *m;
+
+	while (*p != NULL) {
+		parent = *p;
+		m = rb_entry(parent, struct map, rb_node);
+		if (ip < m->start)
+			p = &(*p)->rb_left;
+		else if (ip > m->end)
+			p = &(*p)->rb_right;
+		else
+			return m;
+	}
+
+	return NULL;
+}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index b756368076c6..2031278cc06a 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -4,7 +4,8 @@
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
-#include <linux/types.h>
+#include <stdio.h>
+#include "types.h"
 
 enum map_type {
 	MAP__FUNCTION = 0,
@@ -68,14 +69,13 @@ u64 map__rip_2objdump(struct map *map, u64 rip);
 u64 map__objdump_2ip(struct map *map, u64 addr);
 
 struct symbol;
-struct mmap_event;
 
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
 void map__init(struct map *self, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
-struct map *map__new(struct mmap_event *event, enum map_type,
-		     char *cwd, int cwdlen);
+struct map *map__new(u64 start, u64 len, u64 pgoff, u32 pid, char *filename,
+		     enum map_type type, char *cwd, int cwdlen);
 void map__delete(struct map *self);
 struct map *map__clone(struct map *self);
 int map__overlap(struct map *l, struct map *r);
@@ -91,4 +91,70 @@ void map__fixup_end(struct map *self);
 
 void map__reloc_vmlinux(struct map *self);
 
+struct map_groups {
+	struct rb_root		maps[MAP__NR_TYPES];
+	struct list_head	removed_maps[MAP__NR_TYPES];
+};
+
+size_t __map_groups__fprintf_maps(struct map_groups *self,
+				  enum map_type type, int verbose, FILE *fp);
+void maps__insert(struct rb_root *maps, struct map *map);
+struct map *maps__find(struct rb_root *maps, u64 addr);
+void map_groups__init(struct map_groups *self);
+int map_groups__clone(struct map_groups *self,
+		      struct map_groups *parent, enum map_type type);
+size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp);
+size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp);
+
+static inline void map_groups__insert(struct map_groups *self, struct map *map)
+{
+	 maps__insert(&self->maps[map->type], map);
+}
+
+static inline struct map *map_groups__find(struct map_groups *self,
+					   enum map_type type, u64 addr)
+{
+	return maps__find(&self->maps[type], addr);
+}
+
+struct symbol *map_groups__find_symbol(struct map_groups *self,
+				       enum map_type type, u64 addr,
+				       struct map **mapp,
+				       symbol_filter_t filter);
+
+struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
+					       enum map_type type,
+					       const char *name,
+					       struct map **mapp,
+					       symbol_filter_t filter);
+
+static inline
+struct symbol *map_groups__find_function(struct map_groups *self, u64 addr,
+					 struct map **mapp, symbol_filter_t filter)
+{
+	return map_groups__find_symbol(self, MAP__FUNCTION, addr, mapp, filter);
+}
+
+static inline
+struct symbol *map_groups__find_function_by_name(struct map_groups *self,
+						 const char *name, struct map **mapp,
+						 symbol_filter_t filter)
+{
+	return map_groups__find_symbol_by_name(self, MAP__FUNCTION, name, mapp, filter);
+}
+
+int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
+				   int verbose, FILE *fp);
+
+struct map *map_groups__find_by_name(struct map_groups *self,
+				     enum map_type type, const char *name);
+int __map_groups__create_kernel_maps(struct map_groups *self,
+				     struct map *vmlinux_maps[MAP__NR_TYPES],
+				     struct dso *kernel);
+int map_groups__create_kernel_maps(struct map_groups *self,
+				   struct map *vmlinux_maps[MAP__NR_TYPES]);
+struct map *map_groups__new_module(struct map_groups *self, u64 start,
+				   const char *filename);
+void map_groups__flush(struct map_groups *self);
+
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/newt.c b/tools/perf/util/newt.c
new file mode 100644
index 000000000000..7a123a94e3fc
--- /dev/null
+++ b/tools/perf/util/newt.c
@@ -0,0 +1,725 @@
+#define _GNU_SOURCE
+#include <stdio.h>
+#undef _GNU_SOURCE
+
+#include <stdlib.h>
+#include <newt.h>
+#include <sys/ttydefaults.h>
+
+#include "cache.h"
+#include "hist.h"
+#include "session.h"
+#include "sort.h"
+#include "symbol.h"
+
+struct ui_progress {
+	newtComponent form, scale;
+};
+
+struct ui_progress *ui_progress__new(const char *title, u64 total)
+{
+	struct ui_progress *self = malloc(sizeof(*self));
+
+	if (self != NULL) {
+		int cols;
+		newtGetScreenSize(&cols, NULL);
+		cols -= 4;
+		newtCenteredWindow(cols, 1, title);
+		self->form  = newtForm(NULL, NULL, 0);
+		if (self->form == NULL)
+			goto out_free_self;
+		self->scale = newtScale(0, 0, cols, total);
+		if (self->scale == NULL)
+			goto out_free_form;
+		newtFormAddComponents(self->form, self->scale, NULL);
+		newtRefresh();
+	}
+
+	return self;
+
+out_free_form:
+	newtFormDestroy(self->form);
+out_free_self:
+	free(self);
+	return NULL;
+}
+
+void ui_progress__update(struct ui_progress *self, u64 curr)
+{
+	newtScaleSet(self->scale, curr);
+	newtRefresh();
+}
+
+void ui_progress__delete(struct ui_progress *self)
+{
+	newtFormDestroy(self->form);
+	newtPopWindow();
+	free(self);
+}
+
+static char browser__last_msg[1024];
+
+int browser__show_help(const char *format, va_list ap)
+{
+	int ret;
+	static int backlog;
+
+        ret = vsnprintf(browser__last_msg + backlog,
+			sizeof(browser__last_msg) - backlog, format, ap);
+	backlog += ret;
+
+	if (browser__last_msg[backlog - 1] == '\n') {
+		newtPopHelpLine();
+		newtPushHelpLine(browser__last_msg);
+		newtRefresh();
+		backlog = 0;
+	}
+
+	return ret;
+}
+
+static void newt_form__set_exit_keys(newtComponent self)
+{
+	newtFormAddHotKey(self, NEWT_KEY_ESCAPE);
+	newtFormAddHotKey(self, 'Q');
+	newtFormAddHotKey(self, 'q');
+	newtFormAddHotKey(self, CTRL('c'));
+}
+
+static newtComponent newt_form__new(void)
+{
+	newtComponent self = newtForm(NULL, NULL, 0);
+	if (self)
+		newt_form__set_exit_keys(self);
+	return self;
+}
+
+static int popup_menu(int argc, char * const argv[])
+{
+	struct newtExitStruct es;
+	int i, rc = -1, max_len = 5;
+	newtComponent listbox, form = newt_form__new();
+
+	if (form == NULL)
+		return -1;
+
+	listbox = newtListbox(0, 0, argc, NEWT_FLAG_RETURNEXIT);
+	if (listbox == NULL)
+		goto out_destroy_form;
+
+	newtFormAddComponents(form, listbox, NULL);
+
+	for (i = 0; i < argc; ++i) {
+		int len = strlen(argv[i]);
+		if (len > max_len)
+			max_len = len;
+		if (newtListboxAddEntry(listbox, argv[i], (void *)(long)i))
+			goto out_destroy_form;
+	}
+
+	newtCenteredWindow(max_len, argc, NULL);
+	newtFormRun(form, &es);
+	rc = newtListboxGetCurrent(listbox) - NULL;
+	if (es.reason == NEWT_EXIT_HOTKEY)
+		rc = -1;
+	newtPopWindow();
+out_destroy_form:
+	newtFormDestroy(form);
+	return rc;
+}
+
+static bool dialog_yesno(const char *msg)
+{
+	/* newtWinChoice should really be accepting const char pointers... */
+	char yes[] = "Yes", no[] = "No";
+	return newtWinChoice(NULL, yes, no, (char *)msg) == 1;
+}
+
+/*
+ * When debugging newt problems it was useful to be able to "unroll"
+ * the calls to newtCheckBoxTreeAdd{Array,Item}, so that we can generate
+ * a source file with the sequence of calls to these methods, to then
+ * tweak the arrays to get the intended results, so I'm keeping this code
+ * here, may be useful again in the future.
+ */
+#undef NEWT_DEBUG
+
+static void newt_checkbox_tree__add(newtComponent tree, const char *str,
+				    void *priv, int *indexes)
+{
+#ifdef NEWT_DEBUG
+	/* Print the newtCheckboxTreeAddArray to tinker with its index arrays */
+	int i = 0, len = 40 - strlen(str);
+
+	fprintf(stderr,
+		"\tnewtCheckboxTreeAddItem(tree, %*.*s\"%s\", (void *)%p, 0, ",
+		len, len, " ", str, priv);
+	while (indexes[i] != NEWT_ARG_LAST) {
+		if (indexes[i] != NEWT_ARG_APPEND)
+			fprintf(stderr, " %d,", indexes[i]);
+		else
+			fprintf(stderr, " %s,", "NEWT_ARG_APPEND");
+		++i;
+	}
+	fprintf(stderr, " %s", " NEWT_ARG_LAST);\n");
+	fflush(stderr);
+#endif
+	newtCheckboxTreeAddArray(tree, str, priv, 0, indexes);
+}
+
+static char *callchain_list__sym_name(struct callchain_list *self,
+				      char *bf, size_t bfsize)
+{
+	if (self->ms.sym)
+		return self->ms.sym->name;
+
+	snprintf(bf, bfsize, "%#Lx", self->ip);
+	return bf;
+}
+
+static void __callchain__append_graph_browser(struct callchain_node *self,
+					      newtComponent tree, u64 total,
+					      int *indexes, int depth)
+{
+	struct rb_node *node;
+	u64 new_total, remaining;
+	int idx = 0;
+
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		new_total = self->children_hit;
+	else
+		new_total = total;
+
+	remaining = new_total;
+	node = rb_first(&self->rb_root);
+	while (node) {
+		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
+		struct rb_node *next = rb_next(node);
+		u64 cumul = cumul_hits(child);
+		struct callchain_list *chain;
+		int first = true, printed = 0;
+		int chain_idx = -1;
+		remaining -= cumul;
+
+		indexes[depth] = NEWT_ARG_APPEND;
+		indexes[depth + 1] = NEWT_ARG_LAST;
+
+		list_for_each_entry(chain, &child->val, list) {
+			char ipstr[BITS_PER_LONG / 4 + 1],
+			     *alloc_str = NULL;
+			const char *str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
+
+			if (first) {
+				double percent = cumul * 100.0 / new_total;
+
+				first = false;
+				if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
+					str = "Not enough memory!";
+				else
+					str = alloc_str;
+			} else {
+				indexes[depth] = idx;
+				indexes[depth + 1] = NEWT_ARG_APPEND;
+				indexes[depth + 2] = NEWT_ARG_LAST;
+				++chain_idx;
+			}
+			newt_checkbox_tree__add(tree, str, &chain->ms, indexes);
+			free(alloc_str);
+			++printed;
+		}
+
+		indexes[depth] = idx;
+		if (chain_idx != -1)
+			indexes[depth + 1] = chain_idx;
+		if (printed != 0)
+			++idx;
+		__callchain__append_graph_browser(child, tree, new_total, indexes,
+						  depth + (chain_idx != -1 ? 2 : 1));
+		node = next;
+	}
+}
+
+static void callchain__append_graph_browser(struct callchain_node *self,
+					    newtComponent tree, u64 total,
+					    int *indexes, int parent_idx)
+{
+	struct callchain_list *chain;
+	int i = 0;
+
+	indexes[1] = NEWT_ARG_APPEND;
+	indexes[2] = NEWT_ARG_LAST;
+
+	list_for_each_entry(chain, &self->val, list) {
+		char ipstr[BITS_PER_LONG / 4 + 1], *str;
+
+		if (chain->ip >= PERF_CONTEXT_MAX)
+			continue;
+
+		if (!i++ && sort__first_dimension == SORT_SYM)
+			continue;
+
+		str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
+		newt_checkbox_tree__add(tree, str, &chain->ms, indexes);
+	}
+
+	indexes[1] = parent_idx;
+	indexes[2] = NEWT_ARG_APPEND;
+	indexes[3] = NEWT_ARG_LAST;
+	__callchain__append_graph_browser(self, tree, total, indexes, 2);
+}
+
+static void hist_entry__append_callchain_browser(struct hist_entry *self,
+						 newtComponent tree, u64 total, int parent_idx)
+{
+	struct rb_node *rb_node;
+	int indexes[1024] = { [0] = parent_idx, };
+	int idx = 0;
+	struct callchain_node *chain;
+
+	rb_node = rb_first(&self->sorted_chain);
+	while (rb_node) {
+		chain = rb_entry(rb_node, struct callchain_node, rb_node);
+		switch (callchain_param.mode) {
+		case CHAIN_FLAT:
+			break;
+		case CHAIN_GRAPH_ABS: /* falldown */
+		case CHAIN_GRAPH_REL:
+			callchain__append_graph_browser(chain, tree, total, indexes, idx++);
+			break;
+		case CHAIN_NONE:
+		default:
+			break;
+		}
+		rb_node = rb_next(rb_node);
+	}
+}
+
+static size_t hist_entry__append_browser(struct hist_entry *self,
+					 newtComponent tree, u64 total)
+{
+	char s[256];
+	size_t ret;
+
+	if (symbol_conf.exclude_other && !self->parent)
+		return 0;
+
+	ret = hist_entry__snprintf(self, s, sizeof(s), NULL,
+				   false, 0, false, total);
+	if (symbol_conf.use_callchain) {
+		int indexes[2];
+
+		indexes[0] = NEWT_ARG_APPEND;
+		indexes[1] = NEWT_ARG_LAST;
+		newt_checkbox_tree__add(tree, s, &self->ms, indexes);
+	} else
+		newtListboxAppendEntry(tree, s, &self->ms);
+
+	return ret;
+}
+
+static void map_symbol__annotate_browser(const struct map_symbol *self,
+					 const char *input_name)
+{
+	FILE *fp;
+	int cols, rows;
+	newtComponent form, tree;
+	struct newtExitStruct es;
+	char *str;
+	size_t line_len, max_line_len = 0;
+	size_t max_usable_width;
+	char *line = NULL;
+
+	if (self->sym == NULL)
+		return;
+
+	if (asprintf(&str, "perf annotate -i \"%s\" -d \"%s\" %s 2>&1 | expand",
+		     input_name, self->map->dso->name, self->sym->name) < 0)
+		return;
+
+	fp = popen(str, "r");
+	if (fp == NULL)
+		goto out_free_str;
+
+	newtPushHelpLine("Press ESC to exit");
+	newtGetScreenSize(&cols, &rows);
+	tree = newtListbox(0, 0, rows - 5, NEWT_FLAG_SCROLL);
+
+	while (!feof(fp)) {
+		if (getline(&line, &line_len, fp) < 0 || !line_len)
+			break;
+		while (line_len != 0 && isspace(line[line_len - 1]))
+			line[--line_len] = '\0';
+
+		if (line_len > max_line_len)
+			max_line_len = line_len;
+		newtListboxAppendEntry(tree, line, NULL);
+	}
+	fclose(fp);
+	free(line);
+
+	max_usable_width = cols - 22;
+	if (max_line_len > max_usable_width)
+		max_line_len = max_usable_width;
+
+	newtListboxSetWidth(tree, max_line_len);
+
+	newtCenteredWindow(max_line_len + 2, rows - 5, self->sym->name);
+	form = newt_form__new();
+	newtFormAddComponents(form, tree, NULL);
+
+	newtFormRun(form, &es);
+	newtFormDestroy(form);
+	newtPopWindow();
+	newtPopHelpLine();
+out_free_str:
+	free(str);
+}
+
+static const void *newt__symbol_tree_get_current(newtComponent self)
+{
+	if (symbol_conf.use_callchain)
+		return newtCheckboxTreeGetCurrent(self);
+	return newtListboxGetCurrent(self);
+}
+
+static void hist_browser__selection(newtComponent self, void *data)
+{
+	const struct map_symbol **symbol_ptr = data;
+	*symbol_ptr = newt__symbol_tree_get_current(self);
+}
+
+struct hist_browser {
+	newtComponent		form, tree;
+	const struct map_symbol *selection;
+};
+
+static struct hist_browser *hist_browser__new(void)
+{
+	struct hist_browser *self = malloc(sizeof(*self));
+
+	if (self != NULL)
+		self->form = NULL;
+
+	return self;
+}
+
+static void hist_browser__delete(struct hist_browser *self)
+{
+	newtFormDestroy(self->form);
+	newtPopWindow();
+	free(self);
+}
+
+static int hist_browser__populate(struct hist_browser *self, struct rb_root *hists,
+				  u64 nr_hists, u64 session_total, const char *title)
+{
+	int max_len = 0, idx, cols, rows;
+	struct ui_progress *progress;
+	struct rb_node *nd;
+	u64 curr_hist = 0;
+	char seq[] = ".";
+	char str[256];
+
+	if (self->form) {
+		newtFormDestroy(self->form);
+		newtPopWindow();
+	}
+
+	snprintf(str, sizeof(str), "Samples: %Ld                            ",
+		 session_total);
+	newtDrawRootText(0, 0, str);
+
+	newtGetScreenSize(NULL, &rows);
+
+	if (symbol_conf.use_callchain)
+		self->tree = newtCheckboxTreeMulti(0, 0, rows - 5, seq,
+						   NEWT_FLAG_SCROLL);
+	else
+		self->tree = newtListbox(0, 0, rows - 5,
+					(NEWT_FLAG_SCROLL |
+					 NEWT_FLAG_RETURNEXIT));
+
+	newtComponentAddCallback(self->tree, hist_browser__selection,
+				 &self->selection);
+
+	progress = ui_progress__new("Adding entries to the browser...", nr_hists);
+	if (progress == NULL)
+		return -1;
+
+	idx = 0;
+	for (nd = rb_first(hists); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		int len;
+
+		if (h->filtered)
+			continue;
+
+		len = hist_entry__append_browser(h, self->tree, session_total);
+		if (len > max_len)
+			max_len = len;
+		if (symbol_conf.use_callchain)
+			hist_entry__append_callchain_browser(h, self->tree,
+							     session_total, idx++);
+		++curr_hist;
+		if (curr_hist % 5)
+			ui_progress__update(progress, curr_hist);
+	}
+
+	ui_progress__delete(progress);
+
+	newtGetScreenSize(&cols, &rows);
+
+	if (max_len > cols)
+		max_len = cols - 3;
+
+	if (!symbol_conf.use_callchain)
+		newtListboxSetWidth(self->tree, max_len);
+
+	newtCenteredWindow(max_len + (symbol_conf.use_callchain ? 5 : 0),
+			   rows - 5, title);
+	self->form = newt_form__new();
+	if (self->form == NULL)
+		return -1;
+
+	newtFormAddHotKey(self->form, 'A');
+	newtFormAddHotKey(self->form, 'a');
+	newtFormAddHotKey(self->form, NEWT_KEY_RIGHT);
+	newtFormAddComponents(self->form, self->tree, NULL);
+	self->selection = newt__symbol_tree_get_current(self->tree);
+
+	return 0;
+}
+
+enum hist_filter {
+	HIST_FILTER__DSO,
+	HIST_FILTER__THREAD,
+};
+
+static u64 hists__filter_by_dso(struct rb_root *hists, const struct dso *dso,
+				u64 *session_total)
+{
+	struct rb_node *nd;
+	u64 nr_hists = 0;
+
+	*session_total = 0;
+
+	for (nd = rb_first(hists); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		if (dso != NULL && (h->ms.map == NULL || h->ms.map->dso != dso)) {
+			h->filtered |= (1 << HIST_FILTER__DSO);
+			continue;
+		}
+		h->filtered &= ~(1 << HIST_FILTER__DSO);
+		++nr_hists;
+		*session_total += h->count;
+	}
+
+	return nr_hists;
+}
+
+static u64 hists__filter_by_thread(struct rb_root *hists, const struct thread *thread,
+				   u64 *session_total)
+{
+	struct rb_node *nd;
+	u64 nr_hists = 0;
+
+	*session_total = 0;
+
+	for (nd = rb_first(hists); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		if (thread != NULL && h->thread != thread) {
+			h->filtered |= (1 << HIST_FILTER__THREAD);
+			continue;
+		}
+		h->filtered &= ~(1 << HIST_FILTER__THREAD);
+		++nr_hists;
+		*session_total += h->count;
+	}
+
+	return nr_hists;
+}
+
+static struct thread *hist_browser__selected_thread(struct hist_browser *self)
+{
+	int *indexes;
+
+	if (!symbol_conf.use_callchain)
+		goto out;
+
+	indexes = newtCheckboxTreeFindItem(self->tree, (void *)self->selection);
+	if (indexes) {
+		bool is_hist_entry = indexes[1] == NEWT_ARG_LAST;
+		free(indexes);
+		if (is_hist_entry)
+			goto out;
+	}
+	return NULL;
+out:
+	return *(struct thread **)(self->selection + 1);
+}
+
+static int hist_browser__title(char *bf, size_t size, const char *input_name,
+			       const struct dso *dso, const struct thread *thread)
+{
+	int printed = 0;
+
+	if (thread)
+		printed += snprintf(bf + printed, size - printed,
+				    "Thread: %s(%d)",
+				    (thread->comm_set ?  thread->comm : ""),
+				    thread->pid);
+	if (dso)
+		printed += snprintf(bf + printed, size - printed,
+				    "%sDSO: %s", thread ? " " : "",
+				    dso->short_name);
+	return printed ?: snprintf(bf, size, "Report: %s", input_name);
+}
+
+int perf_session__browse_hists(struct rb_root *hists, u64 nr_hists,
+			       u64 session_total, const char *helpline,
+			       const char *input_name)
+{
+	struct hist_browser *browser = hist_browser__new();
+	const struct thread *thread_filter = NULL;
+	const struct dso *dso_filter = NULL;
+	struct newtExitStruct es;
+	char msg[160];
+	int err = -1;
+
+	if (browser == NULL)
+		return -1;
+
+	newtPushHelpLine(helpline);
+
+	hist_browser__title(msg, sizeof(msg), input_name,
+			    dso_filter, thread_filter);
+	if (hist_browser__populate(browser, hists, nr_hists, session_total, msg) < 0)
+		goto out;
+
+	while (1) {
+		const struct thread *thread;
+		const struct dso *dso;
+		char *options[16];
+		int nr_options = 0, choice = 0, i,
+		    annotate = -2, zoom_dso = -2, zoom_thread = -2;
+
+		newtFormRun(browser->form, &es);
+		if (es.reason == NEWT_EXIT_HOTKEY) {
+			if (toupper(es.u.key) == 'A')
+				goto do_annotate;
+			if (es.u.key == NEWT_KEY_ESCAPE ||
+			    toupper(es.u.key) == 'Q' ||
+			    es.u.key == CTRL('c')) {
+				if (dialog_yesno("Do you really want to exit?"))
+					break;
+				else
+					continue;
+			}
+		}
+
+		if (browser->selection->sym != NULL &&
+		    asprintf(&options[nr_options], "Annotate %s",
+			     browser->selection->sym->name) > 0)
+			annotate = nr_options++;
+
+		thread = hist_browser__selected_thread(browser);
+		if (thread != NULL &&
+		    asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
+			     (thread_filter ? "out of" : "into"),
+			     (thread->comm_set ? thread->comm : ""),
+			     thread->pid) > 0)
+			zoom_thread = nr_options++;
+
+		dso = browser->selection->map ? browser->selection->map->dso : NULL;
+		if (dso != NULL &&
+		    asprintf(&options[nr_options], "Zoom %s %s DSO",
+			     (dso_filter ? "out of" : "into"),
+			     (dso->kernel ? "the Kernel" : dso->short_name)) > 0)
+			zoom_dso = nr_options++;
+
+		options[nr_options++] = (char *)"Exit";
+
+		choice = 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)
+			continue;
+do_annotate:
+		if (choice == annotate) {
+			if (browser->selection->map->dso->origin == DSO__ORIG_KERNEL) {
+				newtPopHelpLine();
+				newtPushHelpLine("No vmlinux file found, can't "
+						 "annotate with just a "
+						 "kallsyms file");
+				continue;
+			}
+			map_symbol__annotate_browser(browser->selection, input_name);
+		} else if (choice == zoom_dso) {
+			if (dso_filter) {
+				newtPopHelpLine();
+				dso_filter = NULL;
+			} else {
+				snprintf(msg, sizeof(msg),
+					 "To zoom out press -> + \"Zoom out of %s DSO\"",
+					 dso->kernel ? "the Kernel" : dso->short_name);
+				newtPushHelpLine(msg);
+				dso_filter = dso;
+			}
+			nr_hists = hists__filter_by_dso(hists, dso_filter, &session_total);
+			hist_browser__title(msg, sizeof(msg), input_name,
+					    dso_filter, thread_filter);
+			if (hist_browser__populate(browser, hists, nr_hists, session_total, msg) < 0)
+				goto out;
+		} else if (choice == zoom_thread) {
+			if (thread_filter) {
+				newtPopHelpLine();
+				thread_filter = NULL;
+			} else {
+				snprintf(msg, sizeof(msg),
+					 "To zoom out press -> + \"Zoom out of %s(%d) thread\"",
+					 (thread->comm_set ? thread->comm : ""),
+					 thread->pid);
+				newtPushHelpLine(msg);
+				thread_filter = thread;
+			}
+			nr_hists = hists__filter_by_thread(hists, thread_filter, &session_total);
+			hist_browser__title(msg, sizeof(msg), input_name,
+					    dso_filter, thread_filter);
+			if (hist_browser__populate(browser, hists, nr_hists, session_total, msg) < 0)
+				goto out;
+		}
+	}
+	err = 0;
+out:
+	hist_browser__delete(browser);
+	return err;
+}
+
+void setup_browser(void)
+{
+	if (!isatty(1))
+		return;
+
+	use_browser = true;
+	newtInit();
+	newtCls();
+	newtPushHelpLine(" ");
+}
+
+void exit_browser(bool wait_for_ok)
+{
+	if (use_browser) {
+		if (wait_for_ok) {
+			char title[] = "Fatal Error", ok[] = "Ok";
+			newtWinMessage(title, ok, browser__last_msg);
+		}
+		newtFinished();
+	}
+}
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 05d0c5c2030c..435781e0c205 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -5,6 +5,7 @@
 #include "parse-events.h"
 #include "exec_cmd.h"
 #include "string.h"
+#include "symbol.h"
 #include "cache.h"
 #include "header.h"
 #include "debugfs.h"
@@ -656,6 +657,10 @@ parse_raw_event(const char **strp, struct perf_event_attr *attr)
 		return EVT_FAILED;
 	n = hex2u64(str + 1, &config);
 	if (n > 0) {
+		if (str[n+1] == 'p') {
+			attr->precise = 1;
+			n++;
+		}
 		*strp = str + n + 1;
 		attr->type = PERF_TYPE_RAW;
 		attr->config = config;
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index efebd5b476b3..79dfa0c34b3c 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -500,6 +500,7 @@ int usage_with_options_internal(const char * const *usagestr,
 void usage_with_options(const char * const *usagestr,
 			const struct option *opts)
 {
+	exit_browser(false);
 	usage_with_options_internal(usagestr, opts, 0);
 	exit(129);
 }
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 7c004b6ef24f..3fc0be741b8e 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -33,19 +33,26 @@
 #include <limits.h>
 
 #undef _GNU_SOURCE
+#include "util.h"
 #include "event.h"
 #include "string.h"
 #include "strlist.h"
 #include "debug.h"
 #include "cache.h"
 #include "color.h"
-#include "parse-events.h"  /* For debugfs_path */
+#include "symbol.h"
+#include "thread.h"
+#include "trace-event.h"	/* For __unused */
+#include "parse-events.h"	/* For debugfs_path */
 #include "probe-event.h"
+#include "probe-finder.h"
 
 #define MAX_CMDLEN 256
 #define MAX_PROBE_ARGS 128
 #define PERFPROBE_GROUP "probe"
 
+bool probe_event_dry_run;	/* Dry run flag */
+
 #define semantic_error(msg ...) die("Semantic error :" msg)
 
 /* If there is no space to write, returns -E2BIG. */
@@ -64,6 +71,208 @@ static int e_snprintf(char *str, size_t size, const char *format, ...)
 	return ret;
 }
 
+static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
+static struct map_groups kmap_groups;
+static struct map *kmaps[MAP__NR_TYPES];
+
+/* Initialize symbol maps and path of vmlinux */
+static void init_vmlinux(void)
+{
+	symbol_conf.sort_by_name = true;
+	if (symbol_conf.vmlinux_name == NULL)
+		symbol_conf.try_vmlinux_path = true;
+	else
+		pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name);
+	if (symbol__init() < 0)
+		die("Failed to init symbol map.");
+
+	map_groups__init(&kmap_groups);
+	if (map_groups__create_kernel_maps(&kmap_groups, kmaps) < 0)
+		die("Failed to create kernel maps.");
+}
+
+#ifdef DWARF_SUPPORT
+static int open_vmlinux(void)
+{
+	if (map__load(kmaps[MAP__FUNCTION], NULL) < 0) {
+		pr_debug("Failed to load kernel map.\n");
+		return -EINVAL;
+	}
+	pr_debug("Try to open %s\n", kmaps[MAP__FUNCTION]->dso->long_name);
+	return open(kmaps[MAP__FUNCTION]->dso->long_name, O_RDONLY);
+}
+
+static void convert_to_perf_probe_point(struct kprobe_trace_point *tp,
+					struct perf_probe_point *pp)
+{
+	struct symbol *sym;
+	int fd, ret = 0;
+
+	sym = map__find_symbol_by_name(kmaps[MAP__FUNCTION],
+				       tp->symbol, NULL);
+	if (sym) {
+		fd = open_vmlinux();
+		ret = find_perf_probe_point(fd, sym->start + tp->offset, pp);
+		close(fd);
+	}
+	if (ret <= 0) {
+		pp->function = xstrdup(tp->symbol);
+		pp->offset = tp->offset;
+	}
+	pp->retprobe = tp->retprobe;
+}
+
+/* Try to find perf_probe_event with debuginfo */
+static int try_to_find_kprobe_trace_events(struct perf_probe_event *pev,
+					   struct kprobe_trace_event **tevs)
+{
+	bool need_dwarf = perf_probe_event_need_dwarf(pev);
+	int fd, ntevs;
+
+	fd = open_vmlinux();
+	if (fd < 0) {
+		if (need_dwarf)
+			die("Could not open debuginfo file.");
+
+		pr_debug("Could not open vmlinux. Try to use symbols.\n");
+		return 0;
+	}
+
+	/* Searching trace events corresponding to probe event */
+	ntevs = find_kprobe_trace_events(fd, pev, tevs);
+	close(fd);
+
+	if (ntevs > 0)	/* Succeeded to find trace events */
+		return ntevs;
+
+	if (ntevs == 0)	/* No error but failed to find probe point. */
+		die("Probe point '%s' not found. - probe not added.",
+		    synthesize_perf_probe_point(&pev->point));
+
+	/* Error path */
+	if (need_dwarf) {
+		if (ntevs == -ENOENT)
+			pr_warning("No dwarf info found in the vmlinux - "
+				"please rebuild with CONFIG_DEBUG_INFO=y.\n");
+		die("Could not analyze debuginfo.");
+	}
+	pr_debug("An error occurred in debuginfo analysis."
+		 " Try to use symbols.\n");
+	return 0;
+
+}
+
+#define LINEBUF_SIZE 256
+#define NR_ADDITIONAL_LINES 2
+
+static void show_one_line(FILE *fp, unsigned int l, bool skip, bool show_num)
+{
+	char buf[LINEBUF_SIZE];
+	const char *color = PERF_COLOR_BLUE;
+
+	if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
+		goto error;
+	if (!skip) {
+		if (show_num)
+			fprintf(stdout, "%7u  %s", l, buf);
+		else
+			color_fprintf(stdout, color, "         %s", buf);
+	}
+
+	while (strlen(buf) == LINEBUF_SIZE - 1 &&
+	       buf[LINEBUF_SIZE - 2] != '\n') {
+		if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
+			goto error;
+		if (!skip) {
+			if (show_num)
+				fprintf(stdout, "%s", buf);
+			else
+				color_fprintf(stdout, color, "%s", buf);
+		}
+	}
+	return;
+error:
+	if (feof(fp))
+		die("Source file is shorter than expected.");
+	else
+		die("File read error: %s", strerror(errno));
+}
+
+/*
+ * Show line-range always requires debuginfo to find source file and
+ * line number.
+ */
+void show_line_range(struct line_range *lr)
+{
+	unsigned int l = 1;
+	struct line_node *ln;
+	FILE *fp;
+	int fd, ret;
+
+	/* Search a line range */
+	init_vmlinux();
+	fd = open_vmlinux();
+	if (fd < 0)
+		die("Could not open debuginfo file.");
+	ret = find_line_range(fd, lr);
+	if (ret <= 0)
+		die("Source line is not found.\n");
+	close(fd);
+
+	setup_pager();
+
+	if (lr->function)
+		fprintf(stdout, "<%s:%d>\n", lr->function,
+			lr->start - lr->offset);
+	else
+		fprintf(stdout, "<%s:%d>\n", lr->file, lr->start);
+
+	fp = fopen(lr->path, "r");
+	if (fp == NULL)
+		die("Failed to open %s: %s", lr->path, strerror(errno));
+	/* Skip to starting line number */
+	while (l < lr->start)
+		show_one_line(fp, l++, true, false);
+
+	list_for_each_entry(ln, &lr->line_list, list) {
+		while (ln->line > l)
+			show_one_line(fp, (l++) - lr->offset, false, false);
+		show_one_line(fp, (l++) - lr->offset, false, true);
+	}
+
+	if (lr->end == INT_MAX)
+		lr->end = l + NR_ADDITIONAL_LINES;
+	while (l < lr->end && !feof(fp))
+		show_one_line(fp, (l++) - lr->offset, false, false);
+
+	fclose(fp);
+}
+
+#else	/* !DWARF_SUPPORT */
+
+static void convert_to_perf_probe_point(struct kprobe_trace_point *tp,
+					struct perf_probe_point *pp)
+{
+	pp->function = xstrdup(tp->symbol);
+	pp->offset = tp->offset;
+	pp->retprobe = tp->retprobe;
+}
+
+static int try_to_find_kprobe_trace_events(struct perf_probe_event *pev,
+				struct kprobe_trace_event **tevs __unused)
+{
+	if (perf_probe_event_need_dwarf(pev))
+		die("Debuginfo-analysis is not supported");
+	return 0;
+}
+
+void show_line_range(struct line_range *lr __unused)
+{
+	die("Debuginfo-analysis is not supported");
+}
+
+#endif
+
 void parse_line_range_desc(const char *arg, struct line_range *lr)
 {
 	const char *ptr;
@@ -90,9 +299,9 @@ void parse_line_range_desc(const char *arg, struct line_range *lr)
 		if (*tmp != '\0')
 			semantic_error("Tailing with invalid character '%d'.",
 				       *tmp);
-		tmp = strndup(arg, (ptr - arg));
+		tmp = xstrndup(arg, (ptr - arg));
 	} else
-		tmp = strdup(arg);
+		tmp = xstrdup(arg);
 
 	if (strchr(tmp, '.'))
 		lr->file = tmp;
@@ -113,8 +322,9 @@ static bool check_event_name(const char *name)
 }
 
 /* Parse probepoint definition. */
-static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
+static void parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 {
+	struct perf_probe_point *pp = &pev->point;
 	char *ptr, *tmp;
 	char c, nc = 0;
 	/*
@@ -135,7 +345,8 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 		if (!check_event_name(arg))
 			semantic_error("%s is bad for event name -it must "
 				       "follow C symbol-naming rule.", arg);
-		pp->event = strdup(arg);
+		pev->event = xstrdup(arg);
+		pev->group = NULL;
 		arg = tmp;
 	}
 
@@ -147,17 +358,16 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 
 	/* Check arg is function or file and copy it */
 	if (strchr(arg, '.'))	/* File */
-		pp->file = strdup(arg);
+		pp->file = xstrdup(arg);
 	else			/* Function */
-		pp->function = strdup(arg);
-	DIE_IF(pp->file == NULL && pp->function == NULL);
+		pp->function = xstrdup(arg);
 
 	/* Parse other options */
 	while (ptr) {
 		arg = ptr;
 		c = nc;
 		if (c == ';') {	/* Lazy pattern must be the last part */
-			pp->lazy_line = strdup(arg);
+			pp->lazy_line = xstrdup(arg);
 			break;
 		}
 		ptr = strpbrk(arg, ";:+@%");
@@ -181,8 +391,7 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 		case '@':	/* File name */
 			if (pp->file)
 				semantic_error("SRC@SRC is not allowed.");
-			pp->file = strdup(arg);
-			DIE_IF(pp->file == NULL);
+			pp->file = xstrdup(arg);
 			break;
 		case '%':	/* Probe places */
 			if (strcmp(arg, "return") == 0) {
@@ -220,59 +429,108 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 		semantic_error("Offset/Line/Lazy pattern can't be used with "
 			       "return probe.");
 
-	pr_debug("symbol:%s file:%s line:%d offset:%d return:%d lazy:%s\n",
+	pr_debug("symbol:%s file:%s line:%d offset:%lu return:%d lazy:%s\n",
 		 pp->function, pp->file, pp->line, pp->offset, pp->retprobe,
 		 pp->lazy_line);
 }
 
-/* Parse perf-probe event definition */
-void parse_perf_probe_event(const char *str, struct probe_point *pp,
-			    bool *need_dwarf)
+/* Parse perf-probe event argument */
+static void parse_perf_probe_arg(const char *str, struct perf_probe_arg *arg)
+{
+	const char *tmp;
+	struct perf_probe_arg_field **fieldp;
+
+	pr_debug("parsing arg: %s into ", str);
+
+	tmp = strpbrk(str, "-.");
+	if (!is_c_varname(str) || !tmp) {
+		/* A variable, register, symbol or special value */
+		arg->name = xstrdup(str);
+		pr_debug("%s\n", arg->name);
+		return;
+	}
+
+	/* Structure fields */
+	arg->name = xstrndup(str, tmp - str);
+	pr_debug("%s, ", arg->name);
+	fieldp = &arg->field;
+
+	do {
+		*fieldp = xzalloc(sizeof(struct perf_probe_arg_field));
+		if (*tmp == '.') {
+			str = tmp + 1;
+			(*fieldp)->ref = false;
+		} else if (tmp[1] == '>') {
+			str = tmp + 2;
+			(*fieldp)->ref = true;
+		} else
+			semantic_error("Argument parse error: %s", str);
+
+		tmp = strpbrk(str, "-.");
+		if (tmp) {
+			(*fieldp)->name = xstrndup(str, tmp - str);
+			pr_debug("%s(%d), ", (*fieldp)->name, (*fieldp)->ref);
+			fieldp = &(*fieldp)->next;
+		}
+	} while (tmp);
+	(*fieldp)->name = xstrdup(str);
+	pr_debug("%s(%d)\n", (*fieldp)->name, (*fieldp)->ref);
+}
+
+/* Parse perf-probe event command */
+void parse_perf_probe_command(const char *cmd, struct perf_probe_event *pev)
 {
 	char **argv;
 	int argc, i;
 
-	*need_dwarf = false;
-
-	argv = argv_split(str, &argc);
+	argv = argv_split(cmd, &argc);
 	if (!argv)
 		die("argv_split failed.");
 	if (argc > MAX_PROBE_ARGS + 1)
 		semantic_error("Too many arguments");
 
 	/* Parse probe point */
-	parse_perf_probe_probepoint(argv[0], pp);
-	if (pp->file || pp->line || pp->lazy_line)
-		*need_dwarf = true;
+	parse_perf_probe_point(argv[0], pev);
 
 	/* Copy arguments and ensure return probe has no C argument */
-	pp->nr_args = argc - 1;
-	pp->args = zalloc(sizeof(char *) * pp->nr_args);
-	for (i = 0; i < pp->nr_args; i++) {
-		pp->args[i] = strdup(argv[i + 1]);
-		if (!pp->args[i])
-			die("Failed to copy argument.");
-		if (is_c_varname(pp->args[i])) {
-			if (pp->retprobe)
-				semantic_error("You can't specify local"
-						" variable for kretprobe");
-			*need_dwarf = true;
-		}
+	pev->nargs = argc - 1;
+	pev->args = xzalloc(sizeof(struct perf_probe_arg) * pev->nargs);
+	for (i = 0; i < pev->nargs; i++) {
+		parse_perf_probe_arg(argv[i + 1], &pev->args[i]);
+		if (is_c_varname(pev->args[i].name) && pev->point.retprobe)
+			semantic_error("You can't specify local variable for"
+				       " kretprobe");
 	}
 
 	argv_free(argv);
 }
 
+/* Return true if this perf_probe_event requires debuginfo */
+bool perf_probe_event_need_dwarf(struct perf_probe_event *pev)
+{
+	int i;
+
+	if (pev->point.file || pev->point.line || pev->point.lazy_line)
+		return true;
+
+	for (i = 0; i < pev->nargs; i++)
+		if (is_c_varname(pev->args[i].name))
+			return true;
+
+	return false;
+}
+
 /* Parse kprobe_events event into struct probe_point */
-void parse_trace_kprobe_event(const char *str, struct probe_point *pp)
+void parse_kprobe_trace_command(const char *cmd, struct kprobe_trace_event *tev)
 {
+	struct kprobe_trace_point *tp = &tev->point;
 	char pr;
 	char *p;
 	int ret, i, argc;
 	char **argv;
 
-	pr_debug("Parsing kprobe_events: %s\n", str);
-	argv = argv_split(str, &argc);
+	pr_debug("Parsing kprobe_events: %s\n", cmd);
+	argv = argv_split(cmd, &argc);
 	if (!argv)
 		die("argv_split failed.");
 	if (argc < 2)
@@ -280,132 +538,314 @@ void parse_trace_kprobe_event(const char *str, struct probe_point *pp)
 
 	/* Scan event and group name. */
 	ret = sscanf(argv[0], "%c:%a[^/ \t]/%a[^ \t]",
-		     &pr, (float *)(void *)&pp->group,
-		     (float *)(void *)&pp->event);
+		     &pr, (float *)(void *)&tev->group,
+		     (float *)(void *)&tev->event);
 	if (ret != 3)
 		semantic_error("Failed to parse event name: %s", argv[0]);
-	pr_debug("Group:%s Event:%s probe:%c\n", pp->group, pp->event, pr);
+	pr_debug("Group:%s Event:%s probe:%c\n", tev->group, tev->event, pr);
 
-	pp->retprobe = (pr == 'r');
+	tp->retprobe = (pr == 'r');
 
 	/* Scan function name and offset */
-	ret = sscanf(argv[1], "%a[^+]+%d", (float *)(void *)&pp->function,
-		     &pp->offset);
+	ret = sscanf(argv[1], "%a[^+]+%lu", (float *)(void *)&tp->symbol,
+		     &tp->offset);
 	if (ret == 1)
-		pp->offset = 0;
-
-	/* kprobe_events doesn't have this information */
-	pp->line = 0;
-	pp->file = NULL;
+		tp->offset = 0;
 
-	pp->nr_args = argc - 2;
-	pp->args = zalloc(sizeof(char *) * pp->nr_args);
-	for (i = 0; i < pp->nr_args; i++) {
+	tev->nargs = argc - 2;
+	tev->args = xzalloc(sizeof(struct kprobe_trace_arg) * tev->nargs);
+	for (i = 0; i < tev->nargs; i++) {
 		p = strchr(argv[i + 2], '=');
 		if (p)	/* We don't need which register is assigned. */
-			*p = '\0';
-		pp->args[i] = strdup(argv[i + 2]);
-		if (!pp->args[i])
-			die("Failed to copy argument.");
+			*p++ = '\0';
+		else
+			p = argv[i + 2];
+		tev->args[i].name = xstrdup(argv[i + 2]);
+		/* TODO: parse regs and offset */
+		tev->args[i].value = xstrdup(p);
 	}
 
 	argv_free(argv);
 }
 
-/* Synthesize only probe point (not argument) */
-int synthesize_perf_probe_point(struct probe_point *pp)
+/* Compose only probe arg */
+int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len)
 {
-	char *buf;
-	char offs[64] = "", line[64] = "";
+	struct perf_probe_arg_field *field = pa->field;
 	int ret;
+	char *tmp = buf;
 
-	pp->probes[0] = buf = zalloc(MAX_CMDLEN);
-	pp->found = 1;
-	if (!buf)
-		die("Failed to allocate memory by zalloc.");
+	ret = e_snprintf(tmp, len, "%s", pa->name);
+	if (ret <= 0)
+		goto error;
+	tmp += ret;
+	len -= ret;
+
+	while (field) {
+		ret = e_snprintf(tmp, len, "%s%s", field->ref ? "->" : ".",
+				 field->name);
+		if (ret <= 0)
+			goto error;
+		tmp += ret;
+		len -= ret;
+		field = field->next;
+	}
+	return tmp - buf;
+error:
+	die("Failed to synthesize perf probe argument: %s", strerror(-ret));
+}
+
+/* Compose only probe point (not argument) */
+static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
+{
+	char *buf, *tmp;
+	char offs[32] = "", line[32] = "", file[32] = "";
+	int ret, len;
+
+	buf = xzalloc(MAX_CMDLEN);
 	if (pp->offset) {
-		ret = e_snprintf(offs, 64, "+%d", pp->offset);
+		ret = e_snprintf(offs, 32, "+%lu", pp->offset);
 		if (ret <= 0)
 			goto error;
 	}
 	if (pp->line) {
-		ret = e_snprintf(line, 64, ":%d", pp->line);
+		ret = e_snprintf(line, 32, ":%d", pp->line);
+		if (ret <= 0)
+			goto error;
+	}
+	if (pp->file) {
+		len = strlen(pp->file) - 32;
+		if (len < 0)
+			len = 0;
+		tmp = strchr(pp->file + len, '/');
+		if (!tmp)
+			tmp = pp->file + len - 1;
+		ret = e_snprintf(file, 32, "@%s", tmp + 1);
 		if (ret <= 0)
 			goto error;
 	}
 
 	if (pp->function)
-		ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s", pp->function,
-				 offs, pp->retprobe ? "%return" : "", line);
+		ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s%s", pp->function,
+				 offs, pp->retprobe ? "%return" : "", line,
+				 file);
 	else
-		ret = e_snprintf(buf, MAX_CMDLEN, "%s%s", pp->file, line);
-	if (ret <= 0) {
+		ret = e_snprintf(buf, MAX_CMDLEN, "%s%s", file, line);
+	if (ret <= 0)
+		goto error;
+
+	return buf;
 error:
-		free(pp->probes[0]);
-		pp->probes[0] = NULL;
-		pp->found = 0;
-	}
-	return ret;
+	die("Failed to synthesize perf probe point: %s", strerror(-ret));
 }
 
-int synthesize_perf_probe_event(struct probe_point *pp)
+#if 0
+char *synthesize_perf_probe_command(struct perf_probe_event *pev)
 {
 	char *buf;
 	int i, len, ret;
 
-	len = synthesize_perf_probe_point(pp);
-	if (len < 0)
-		return 0;
+	buf = synthesize_perf_probe_point(&pev->point);
+	if (!buf)
+		return NULL;
 
-	buf = pp->probes[0];
-	for (i = 0; i < pp->nr_args; i++) {
+	len = strlen(buf);
+	for (i = 0; i < pev->nargs; i++) {
 		ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s",
-				 pp->args[i]);
-		if (ret <= 0)
-			goto error;
+				 pev->args[i].name);
+		if (ret <= 0) {
+			free(buf);
+			return NULL;
+		}
 		len += ret;
 	}
-	pp->found = 1;
 
-	return pp->found;
-error:
-	free(pp->probes[0]);
-	pp->probes[0] = NULL;
+	return buf;
+}
+#endif
 
-	return ret;
+static int __synthesize_kprobe_trace_arg_ref(struct kprobe_trace_arg_ref *ref,
+					     char **buf, size_t *buflen,
+					     int depth)
+{
+	int ret;
+	if (ref->next) {
+		depth = __synthesize_kprobe_trace_arg_ref(ref->next, buf,
+							 buflen, depth + 1);
+		if (depth < 0)
+			goto out;
+	}
+
+	ret = e_snprintf(*buf, *buflen, "%+ld(", ref->offset);
+	if (ret < 0)
+		depth = ret;
+	else {
+		*buf += ret;
+		*buflen -= ret;
+	}
+out:
+	return depth;
+
+}
+
+static int synthesize_kprobe_trace_arg(struct kprobe_trace_arg *arg,
+				       char *buf, size_t buflen)
+{
+	int ret, depth = 0;
+	char *tmp = buf;
+
+	/* Argument name or separator */
+	if (arg->name)
+		ret = e_snprintf(buf, buflen, " %s=", arg->name);
+	else
+		ret = e_snprintf(buf, buflen, " ");
+	if (ret < 0)
+		return ret;
+	buf += ret;
+	buflen -= ret;
+
+	/* Dereferencing arguments */
+	if (arg->ref) {
+		depth = __synthesize_kprobe_trace_arg_ref(arg->ref, &buf,
+							  &buflen, 1);
+		if (depth < 0)
+			return depth;
+	}
+
+	/* Print argument value */
+	ret = e_snprintf(buf, buflen, "%s", arg->value);
+	if (ret < 0)
+		return ret;
+	buf += ret;
+	buflen -= ret;
+
+	/* Closing */
+	while (depth--) {
+		ret = e_snprintf(buf, buflen, ")");
+		if (ret < 0)
+			return ret;
+		buf += ret;
+		buflen -= ret;
+	}
+
+	return buf - tmp;
 }
 
-int synthesize_trace_kprobe_event(struct probe_point *pp)
+char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev)
 {
+	struct kprobe_trace_point *tp = &tev->point;
 	char *buf;
 	int i, len, ret;
 
-	pp->probes[0] = buf = zalloc(MAX_CMDLEN);
-	if (!buf)
-		die("Failed to allocate memory by zalloc.");
-	ret = e_snprintf(buf, MAX_CMDLEN, "%s+%d", pp->function, pp->offset);
-	if (ret <= 0)
+	buf = xzalloc(MAX_CMDLEN);
+	len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s+%lu",
+			 tp->retprobe ? 'r' : 'p',
+			 tev->group, tev->event,
+			 tp->symbol, tp->offset);
+	if (len <= 0)
 		goto error;
-	len = ret;
 
-	for (i = 0; i < pp->nr_args; i++) {
-		ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s",
-				 pp->args[i]);
+	for (i = 0; i < tev->nargs; i++) {
+		ret = synthesize_kprobe_trace_arg(&tev->args[i], buf + len,
+						  MAX_CMDLEN - len);
 		if (ret <= 0)
 			goto error;
 		len += ret;
 	}
-	pp->found = 1;
 
-	return pp->found;
+	return buf;
 error:
-	free(pp->probes[0]);
-	pp->probes[0] = NULL;
+	free(buf);
+	return NULL;
+}
 
-	return ret;
+void convert_to_perf_probe_event(struct kprobe_trace_event *tev,
+				 struct perf_probe_event *pev)
+{
+	char buf[64];
+	int i;
+
+	/* Convert event/group name */
+	pev->event = xstrdup(tev->event);
+	pev->group = xstrdup(tev->group);
+
+	/* Convert trace_point to probe_point */
+	convert_to_perf_probe_point(&tev->point, &pev->point);
+
+	/* Convert trace_arg to probe_arg */
+	pev->nargs = tev->nargs;
+	pev->args = xzalloc(sizeof(struct perf_probe_arg) * pev->nargs);
+	for (i = 0; i < tev->nargs; i++)
+		if (tev->args[i].name)
+			pev->args[i].name = xstrdup(tev->args[i].name);
+		else {
+			synthesize_kprobe_trace_arg(&tev->args[i], buf, 64);
+			pev->args[i].name = xstrdup(buf);
+		}
+}
+
+void clear_perf_probe_event(struct perf_probe_event *pev)
+{
+	struct perf_probe_point *pp = &pev->point;
+	struct perf_probe_arg_field *field, *next;
+	int i;
+
+	if (pev->event)
+		free(pev->event);
+	if (pev->group)
+		free(pev->group);
+	if (pp->file)
+		free(pp->file);
+	if (pp->function)
+		free(pp->function);
+	if (pp->lazy_line)
+		free(pp->lazy_line);
+	for (i = 0; i < pev->nargs; i++) {
+		if (pev->args[i].name)
+			free(pev->args[i].name);
+		field = pev->args[i].field;
+		while (field) {
+			next = field->next;
+			if (field->name)
+				free(field->name);
+			free(field);
+			field = next;
+		}
+	}
+	if (pev->args)
+		free(pev->args);
+	memset(pev, 0, sizeof(*pev));
 }
 
-static int open_kprobe_events(int flags, int mode)
+void clear_kprobe_trace_event(struct kprobe_trace_event *tev)
+{
+	struct kprobe_trace_arg_ref *ref, *next;
+	int i;
+
+	if (tev->event)
+		free(tev->event);
+	if (tev->group)
+		free(tev->group);
+	if (tev->point.symbol)
+		free(tev->point.symbol);
+	for (i = 0; i < tev->nargs; i++) {
+		if (tev->args[i].name)
+			free(tev->args[i].name);
+		if (tev->args[i].value)
+			free(tev->args[i].value);
+		ref = tev->args[i].ref;
+		while (ref) {
+			next = ref->next;
+			free(ref);
+			ref = next;
+		}
+	}
+	if (tev->args)
+		free(tev->args);
+	memset(tev, 0, sizeof(*tev));
+}
+
+static int open_kprobe_events(bool readwrite)
 {
 	char buf[PATH_MAX];
 	int ret;
@@ -414,7 +854,11 @@ static int open_kprobe_events(int flags, int mode)
 	if (ret < 0)
 		die("Failed to make kprobe_events path.");
 
-	ret = open(buf, flags, mode);
+	if (readwrite && !probe_event_dry_run)
+		ret = open(buf, O_RDWR, O_APPEND);
+	else
+		ret = open(buf, O_RDONLY, 0);
+
 	if (ret < 0) {
 		if (errno == ENOENT)
 			die("kprobe_events file does not exist -"
@@ -427,7 +871,7 @@ static int open_kprobe_events(int flags, int mode)
 }
 
 /* Get raw string list of current kprobe_events */
-static struct strlist *get_trace_kprobe_event_rawlist(int fd)
+static struct strlist *get_kprobe_trace_command_rawlist(int fd)
 {
 	int ret, idx;
 	FILE *fp;
@@ -455,99 +899,85 @@ static struct strlist *get_trace_kprobe_event_rawlist(int fd)
 	return sl;
 }
 
-/* Free and zero clear probe_point */
-static void clear_probe_point(struct probe_point *pp)
-{
-	int i;
-
-	if (pp->event)
-		free(pp->event);
-	if (pp->group)
-		free(pp->group);
-	if (pp->function)
-		free(pp->function);
-	if (pp->file)
-		free(pp->file);
-	if (pp->lazy_line)
-		free(pp->lazy_line);
-	for (i = 0; i < pp->nr_args; i++)
-		free(pp->args[i]);
-	if (pp->args)
-		free(pp->args);
-	for (i = 0; i < pp->found; i++)
-		free(pp->probes[i]);
-	memset(pp, 0, sizeof(*pp));
-}
-
 /* Show an event */
-static void show_perf_probe_event(const char *event, const char *place,
-				  struct probe_point *pp)
+static void show_perf_probe_event(struct perf_probe_event *pev)
 {
 	int i, ret;
 	char buf[128];
+	char *place;
 
-	ret = e_snprintf(buf, 128, "%s:%s", pp->group, event);
+	/* Synthesize only event probe point */
+	place = synthesize_perf_probe_point(&pev->point);
+
+	ret = e_snprintf(buf, 128, "%s:%s", pev->group, pev->event);
 	if (ret < 0)
 		die("Failed to copy event: %s", strerror(-ret));
-	printf("  %-40s (on %s", buf, place);
+	printf("  %-20s (on %s", buf, place);
 
-	if (pp->nr_args > 0) {
+	if (pev->nargs > 0) {
 		printf(" with");
-		for (i = 0; i < pp->nr_args; i++)
-			printf(" %s", pp->args[i]);
+		for (i = 0; i < pev->nargs; i++) {
+			synthesize_perf_probe_arg(&pev->args[i], buf, 128);
+			printf(" %s", buf);
+		}
 	}
 	printf(")\n");
+	free(place);
 }
 
 /* List up current perf-probe events */
 void show_perf_probe_events(void)
 {
 	int fd;
-	struct probe_point pp;
+	struct kprobe_trace_event tev;
+	struct perf_probe_event pev;
 	struct strlist *rawlist;
 	struct str_node *ent;
 
 	setup_pager();
-	memset(&pp, 0, sizeof(pp));
+	init_vmlinux();
+
+	memset(&tev, 0, sizeof(tev));
+	memset(&pev, 0, sizeof(pev));
 
-	fd = open_kprobe_events(O_RDONLY, 0);
-	rawlist = get_trace_kprobe_event_rawlist(fd);
+	fd = open_kprobe_events(false);
+	rawlist = get_kprobe_trace_command_rawlist(fd);
 	close(fd);
 
 	strlist__for_each(ent, rawlist) {
-		parse_trace_kprobe_event(ent->s, &pp);
-		/* Synthesize only event probe point */
-		synthesize_perf_probe_point(&pp);
+		parse_kprobe_trace_command(ent->s, &tev);
+		convert_to_perf_probe_event(&tev, &pev);
 		/* Show an event */
-		show_perf_probe_event(pp.event, pp.probes[0], &pp);
-		clear_probe_point(&pp);
+		show_perf_probe_event(&pev);
+		clear_perf_probe_event(&pev);
+		clear_kprobe_trace_event(&tev);
 	}
 
 	strlist__delete(rawlist);
 }
 
 /* Get current perf-probe event names */
-static struct strlist *get_perf_event_names(int fd, bool include_group)
+static struct strlist *get_kprobe_trace_event_names(int fd, bool include_group)
 {
 	char buf[128];
 	struct strlist *sl, *rawlist;
 	struct str_node *ent;
-	struct probe_point pp;
+	struct kprobe_trace_event tev;
 
-	memset(&pp, 0, sizeof(pp));
-	rawlist = get_trace_kprobe_event_rawlist(fd);
+	memset(&tev, 0, sizeof(tev));
 
+	rawlist = get_kprobe_trace_command_rawlist(fd);
 	sl = strlist__new(true, NULL);
 	strlist__for_each(ent, rawlist) {
-		parse_trace_kprobe_event(ent->s, &pp);
+		parse_kprobe_trace_command(ent->s, &tev);
 		if (include_group) {
-			if (e_snprintf(buf, 128, "%s:%s", pp.group,
-				       pp.event) < 0)
+			if (e_snprintf(buf, 128, "%s:%s", tev.group,
+				       tev.event) < 0)
 				die("Failed to copy group:event name.");
 			strlist__add(sl, buf);
 		} else
-			strlist__add(sl, pp.event);
-		clear_probe_point(&pp);
+			strlist__add(sl, tev.event);
+		clear_kprobe_trace_event(&tev);
 	}
 
 	strlist__delete(rawlist);
@@ -555,14 +985,18 @@ static struct strlist *get_perf_event_names(int fd, bool include_group)
 	return sl;
 }
 
-static void write_trace_kprobe_event(int fd, const char *buf)
+static void write_kprobe_trace_event(int fd, struct kprobe_trace_event *tev)
 {
 	int ret;
+	char *buf = synthesize_kprobe_trace_command(tev);
 
 	pr_debug("Writing event: %s\n", buf);
-	ret = write(fd, buf, strlen(buf));
-	if (ret <= 0)
-		die("Failed to write event: %s", strerror(errno));
+	if (!probe_event_dry_run) {
+		ret = write(fd, buf, strlen(buf));
+		if (ret <= 0)
+			die("Failed to write event: %s", strerror(errno));
+	}
+	free(buf);
 }
 
 static void get_new_event_name(char *buf, size_t len, const char *base,
@@ -595,65 +1029,145 @@ static void get_new_event_name(char *buf, size_t len, const char *base,
 		die("Too many events are on the same function.");
 }
 
-void add_trace_kprobe_events(struct probe_point *probes, int nr_probes,
-			     bool force_add)
+static void __add_kprobe_trace_events(struct perf_probe_event *pev,
+				      struct kprobe_trace_event *tevs,
+				      int ntevs, bool allow_suffix)
 {
-	int i, j, fd;
-	struct probe_point *pp;
-	char buf[MAX_CMDLEN];
-	char event[64];
+	int i, fd;
+	struct kprobe_trace_event *tev = NULL;
+	char buf[64];
+	const char *event, *group;
 	struct strlist *namelist;
-	bool allow_suffix;
 
-	fd = open_kprobe_events(O_RDWR, O_APPEND);
+	fd = open_kprobe_events(true);
 	/* Get current event names */
-	namelist = get_perf_event_names(fd, false);
-
-	for (j = 0; j < nr_probes; j++) {
-		pp = probes + j;
-		if (!pp->event)
-			pp->event = strdup(pp->function);
-		if (!pp->group)
-			pp->group = strdup(PERFPROBE_GROUP);
-		DIE_IF(!pp->event || !pp->group);
-		/* If force_add is true, suffix search is allowed */
-		allow_suffix = force_add;
-		for (i = 0; i < pp->found; i++) {
-			/* Get an unused new event name */
-			get_new_event_name(event, 64, pp->event, namelist,
-					   allow_suffix);
-			snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s\n",
-				 pp->retprobe ? 'r' : 'p',
-				 pp->group, event,
-				 pp->probes[i]);
-			write_trace_kprobe_event(fd, buf);
-			printf("Added new event:\n");
-			/* Get the first parameter (probe-point) */
-			sscanf(pp->probes[i], "%s", buf);
-			show_perf_probe_event(event, buf, pp);
-			/* Add added event name to namelist */
-			strlist__add(namelist, event);
-			/*
-			 * Probes after the first probe which comes from same
-			 * user input are always allowed to add suffix, because
-			 * there might be several addresses corresponding to
-			 * one code line.
-			 */
-			allow_suffix = true;
-		}
+	namelist = get_kprobe_trace_event_names(fd, false);
+
+	printf("Add new event%s\n", (ntevs > 1) ? "s:" : ":");
+	for (i = 0; i < ntevs; i++) {
+		tev = &tevs[i];
+		if (pev->event)
+			event = pev->event;
+		else
+			if (pev->point.function)
+				event = pev->point.function;
+			else
+				event = tev->point.symbol;
+		if (pev->group)
+			group = pev->group;
+		else
+			group = PERFPROBE_GROUP;
+
+		/* Get an unused new event name */
+		get_new_event_name(buf, 64, event, namelist, allow_suffix);
+		event = buf;
+
+		tev->event = xstrdup(event);
+		tev->group = xstrdup(group);
+		write_kprobe_trace_event(fd, tev);
+		/* Add added event name to namelist */
+		strlist__add(namelist, event);
+
+		/* Trick here - save current event/group */
+		event = pev->event;
+		group = pev->group;
+		pev->event = tev->event;
+		pev->group = tev->group;
+		show_perf_probe_event(pev);
+		/* Trick here - restore current event/group */
+		pev->event = (char *)event;
+		pev->group = (char *)group;
+
+		/*
+		 * Probes after the first probe which comes from same
+		 * user input are always allowed to add suffix, because
+		 * there might be several addresses corresponding to
+		 * one code line.
+		 */
+		allow_suffix = true;
 	}
 	/* Show how to use the event. */
 	printf("\nYou can now use it on all perf tools, such as:\n\n");
-	printf("\tperf record -e %s:%s -a sleep 1\n\n", PERFPROBE_GROUP, event);
+	printf("\tperf record -e %s:%s -a sleep 1\n\n", tev->group, tev->event);
 
 	strlist__delete(namelist);
 	close(fd);
 }
 
+static int convert_to_kprobe_trace_events(struct perf_probe_event *pev,
+					  struct kprobe_trace_event **tevs)
+{
+	struct symbol *sym;
+	int ntevs = 0, i;
+	struct kprobe_trace_event *tev;
+
+	/* Convert perf_probe_event with debuginfo */
+	ntevs = try_to_find_kprobe_trace_events(pev, tevs);
+	if (ntevs > 0)
+		return ntevs;
+
+	/* Allocate trace event buffer */
+	ntevs = 1;
+	tev = *tevs = xzalloc(sizeof(struct kprobe_trace_event));
+
+	/* Copy parameters */
+	tev->point.symbol = xstrdup(pev->point.function);
+	tev->point.offset = pev->point.offset;
+	tev->nargs = pev->nargs;
+	if (tev->nargs) {
+		tev->args = xzalloc(sizeof(struct kprobe_trace_arg)
+				    * tev->nargs);
+		for (i = 0; i < tev->nargs; i++)
+			tev->args[i].value = xstrdup(pev->args[i].name);
+	}
+
+	/* Currently just checking function name from symbol map */
+	sym = map__find_symbol_by_name(kmaps[MAP__FUNCTION],
+				       tev->point.symbol, NULL);
+	if (!sym)
+		die("Kernel symbol \'%s\' not found - probe not added.",
+		    tev->point.symbol);
+
+	return ntevs;
+}
+
+struct __event_package {
+	struct perf_probe_event		*pev;
+	struct kprobe_trace_event	*tevs;
+	int				ntevs;
+};
+
+void add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
+			   bool force_add)
+{
+	int i;
+	struct __event_package *pkgs;
+
+	pkgs = xzalloc(sizeof(struct __event_package) * npevs);
+
+	/* Init vmlinux path */
+	init_vmlinux();
+
+	/* Loop 1: convert all events */
+	for (i = 0; i < npevs; i++) {
+		pkgs[i].pev = &pevs[i];
+		/* Convert with or without debuginfo */
+		pkgs[i].ntevs = convert_to_kprobe_trace_events(pkgs[i].pev,
+							       &pkgs[i].tevs);
+	}
+
+	/* Loop 2: add all events */
+	for (i = 0; i < npevs; i++)
+		__add_kprobe_trace_events(pkgs[i].pev, pkgs[i].tevs,
+					  pkgs[i].ntevs, force_add);
+	/* TODO: cleanup all trace events? */
+}
+
 static void __del_trace_kprobe_event(int fd, struct str_node *ent)
 {
 	char *p;
 	char buf[128];
+	int ret;
 
 	/* Convert from perf-probe event to trace-kprobe event */
 	if (e_snprintf(buf, 128, "-:%s", ent->s) < 0)
@@ -663,7 +1177,10 @@ static void __del_trace_kprobe_event(int fd, struct str_node *ent)
 		die("Internal error: %s should have ':' but not.", ent->s);
 	*p = '/';
 
-	write_trace_kprobe_event(fd, buf);
+	pr_debug("Writing event: %s\n", buf);
+	ret = write(fd, buf, strlen(buf));
+	if (ret <= 0)
+		die("Failed to write event: %s", strerror(errno));
 	printf("Remove event: %s\n", ent->s);
 }
 
@@ -696,7 +1213,7 @@ static void del_trace_kprobe_event(int fd, const char *group,
 		pr_info("Info: event \"%s\" does not exist, could not remove it.\n", buf);
 }
 
-void del_trace_kprobe_events(struct strlist *dellist)
+void del_perf_probe_events(struct strlist *dellist)
 {
 	int fd;
 	const char *group, *event;
@@ -704,14 +1221,12 @@ void del_trace_kprobe_events(struct strlist *dellist)
 	struct str_node *ent;
 	struct strlist *namelist;
 
-	fd = open_kprobe_events(O_RDWR, O_APPEND);
+	fd = open_kprobe_events(true);
 	/* Get current event names */
-	namelist = get_perf_event_names(fd, true);
+	namelist = get_kprobe_trace_event_names(fd, true);
 
 	strlist__for_each(ent, dellist) {
-		str = strdup(ent->s);
-		if (!str)
-			die("Failed to copy event.");
+		str = xstrdup(ent->s);
 		pr_debug("Parsing: %s\n", str);
 		p = strchr(str, ':');
 		if (p) {
@@ -730,73 +1245,3 @@ void del_trace_kprobe_events(struct strlist *dellist)
 	close(fd);
 }
 
-#define LINEBUF_SIZE 256
-#define NR_ADDITIONAL_LINES 2
-
-static void show_one_line(FILE *fp, unsigned int l, bool skip, bool show_num)
-{
-	char buf[LINEBUF_SIZE];
-	const char *color = PERF_COLOR_BLUE;
-
-	if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
-		goto error;
-	if (!skip) {
-		if (show_num)
-			fprintf(stdout, "%7u  %s", l, buf);
-		else
-			color_fprintf(stdout, color, "         %s", buf);
-	}
-
-	while (strlen(buf) == LINEBUF_SIZE - 1 &&
-	       buf[LINEBUF_SIZE - 2] != '\n') {
-		if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
-			goto error;
-		if (!skip) {
-			if (show_num)
-				fprintf(stdout, "%s", buf);
-			else
-				color_fprintf(stdout, color, "%s", buf);
-		}
-	}
-	return;
-error:
-	if (feof(fp))
-		die("Source file is shorter than expected.");
-	else
-		die("File read error: %s", strerror(errno));
-}
-
-void show_line_range(struct line_range *lr)
-{
-	unsigned int l = 1;
-	struct line_node *ln;
-	FILE *fp;
-
-	setup_pager();
-
-	if (lr->function)
-		fprintf(stdout, "<%s:%d>\n", lr->function,
-			lr->start - lr->offset);
-	else
-		fprintf(stdout, "<%s:%d>\n", lr->file, lr->start);
-
-	fp = fopen(lr->path, "r");
-	if (fp == NULL)
-		die("Failed to open %s: %s", lr->path, strerror(errno));
-	/* Skip to starting line number */
-	while (l < lr->start)
-		show_one_line(fp, l++, true, false);
-
-	list_for_each_entry(ln, &lr->line_list, list) {
-		while (ln->line > l)
-			show_one_line(fp, (l++) - lr->offset, false, false);
-		show_one_line(fp, (l++) - lr->offset, false, true);
-	}
-
-	if (lr->end == INT_MAX)
-		lr->end = l + NR_ADDITIONAL_LINES;
-	while (l < lr->end && !feof(fp))
-		show_one_line(fp, (l++) - lr->offset, false, false);
-
-	fclose(fp);
-}
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 711287d4baea..9d99fc24c4fc 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -2,22 +2,123 @@
 #define _PROBE_EVENT_H
 
 #include <stdbool.h>
-#include "probe-finder.h"
 #include "strlist.h"
 
-extern void parse_line_range_desc(const char *arg, struct line_range *lr);
-extern void parse_perf_probe_event(const char *str, struct probe_point *pp,
-				   bool *need_dwarf);
-extern int synthesize_perf_probe_point(struct probe_point *pp);
-extern int synthesize_perf_probe_event(struct probe_point *pp);
-extern void parse_trace_kprobe_event(const char *str, struct probe_point *pp);
-extern int synthesize_trace_kprobe_event(struct probe_point *pp);
-extern void add_trace_kprobe_events(struct probe_point *probes, int nr_probes,
-				    bool force_add);
-extern void del_trace_kprobe_events(struct strlist *dellist);
+extern bool probe_event_dry_run;
+
+/* kprobe-tracer tracing point */
+struct kprobe_trace_point {
+	char		*symbol;	/* Base symbol */
+	unsigned long	offset;		/* Offset from symbol */
+	bool		retprobe;	/* Return probe flag */
+};
+
+/* kprobe-tracer tracing argument referencing offset */
+struct kprobe_trace_arg_ref {
+	struct kprobe_trace_arg_ref	*next;	/* Next reference */
+	long				offset;	/* Offset value */
+};
+
+/* kprobe-tracer tracing argument */
+struct kprobe_trace_arg {
+	char				*name;	/* Argument name */
+	char				*value;	/* Base value */
+	struct kprobe_trace_arg_ref	*ref;	/* Referencing offset */
+};
+
+/* kprobe-tracer tracing event (point + arg) */
+struct kprobe_trace_event {
+	char				*event;	/* Event name */
+	char				*group;	/* Group name */
+	struct kprobe_trace_point	point;	/* Trace point */
+	int				nargs;	/* Number of args */
+	struct kprobe_trace_arg		*args;	/* Arguments */
+};
+
+/* Perf probe probing point */
+struct perf_probe_point {
+	char		*file;		/* File path */
+	char		*function;	/* Function name */
+	int		line;		/* Line number */
+	bool		retprobe;	/* Return probe flag */
+	char		*lazy_line;	/* Lazy matching pattern */
+	unsigned long	offset;		/* Offset from function entry */
+};
+
+/* Perf probe probing argument field chain */
+struct perf_probe_arg_field {
+	struct perf_probe_arg_field	*next;	/* Next field */
+	char				*name;	/* Name of the field */
+	bool				ref;	/* Referencing flag */
+};
+
+/* Perf probe probing argument */
+struct perf_probe_arg {
+	char				*name;	/* Argument name */
+	struct perf_probe_arg_field	*field;	/* Structure fields */
+};
+
+/* Perf probe probing event (point + arg) */
+struct perf_probe_event {
+	char			*event;	/* Event name */
+	char			*group;	/* Group name */
+	struct perf_probe_point	point;	/* Probe point */
+	int			nargs;	/* Number of arguments */
+	struct perf_probe_arg	*args;	/* Arguments */
+};
+
+
+/* Line number container */
+struct line_node {
+	struct list_head	list;
+	unsigned int		line;
+};
+
+/* Line range */
+struct line_range {
+	char			*file;		/* File name */
+	char			*function;	/* Function name */
+	unsigned int		start;		/* Start line number */
+	unsigned int		end;		/* End line number */
+	int			offset;		/* Start line offset */
+	char			*path;		/* Real path name */
+	struct list_head	line_list;	/* Visible lines */
+};
+
+/* Command string to events */
+extern void parse_perf_probe_command(const char *cmd,
+				     struct perf_probe_event *pev);
+extern void parse_kprobe_trace_command(const char *cmd,
+				       struct kprobe_trace_event *tev);
+
+/* Events to command string */
+extern char *synthesize_perf_probe_command(struct perf_probe_event *pev);
+extern char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev);
+extern int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf,
+				     size_t len);
+
+/* Check the perf_probe_event needs debuginfo */
+extern bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
+
+/* Convert from kprobe_trace_event to perf_probe_event */
+extern void convert_to_perf_probe_event(struct kprobe_trace_event *tev,
+					struct perf_probe_event *pev);
+
+/* Release event contents */
+extern void clear_perf_probe_event(struct perf_probe_event *pev);
+extern void clear_kprobe_trace_event(struct kprobe_trace_event *tev);
+
+/* Command string to line-range */
+extern void parse_line_range_desc(const char *cmd, struct line_range *lr);
+
+
+extern void add_perf_probe_events(struct perf_probe_event *pevs, int ntevs,
+				  bool force_add);
+extern void del_perf_probe_events(struct strlist *dellist);
 extern void show_perf_probe_events(void);
 extern void show_line_range(struct line_range *lr);
 
+
 /* Maximum index number of event-name postfix */
 #define MAX_EVENT_INDEX	1024
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index c171a243d05b..a8513772df08 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -125,8 +125,7 @@ static void line_list__add_line(struct list_head *head, unsigned int line)
 	p = head;
 found:
 	pr_debug("line list: add a line %u\n", line);
-	ln = zalloc(sizeof(struct line_node));
-	DIE_IF(ln == NULL);
+	ln = xzalloc(sizeof(struct line_node));
 	ln->line = line;
 	INIT_LIST_HEAD(&ln->list);
 	list_add(&ln->list, p);
@@ -184,9 +183,89 @@ static const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname)
 		if (strtailcmp(src, fname) == 0)
 			break;
 	}
+	if (i == nfiles)
+		return NULL;
 	return src;
 }
 
+/* Compare diename and tname */
+static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
+{
+	const char *name;
+	name = dwarf_diename(dw_die);
+	DIE_IF(name == NULL);
+	return strcmp(tname, name);
+}
+
+/* Get entry pc(or low pc, 1st entry of ranges)  of the die */
+static Dwarf_Addr die_get_entrypc(Dwarf_Die *dw_die)
+{
+	Dwarf_Addr epc;
+	int ret;
+
+	ret = dwarf_entrypc(dw_die, &epc);
+	DIE_IF(ret == -1);
+	return epc;
+}
+
+/* Get type die, but skip qualifiers and typedef */
+static Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem)
+{
+	Dwarf_Attribute attr;
+	int tag;
+
+	do {
+		if (dwarf_attr(vr_die, DW_AT_type, &attr) == NULL ||
+		    dwarf_formref_die(&attr, die_mem) == NULL)
+			return NULL;
+
+		tag = dwarf_tag(die_mem);
+		vr_die = die_mem;
+	} while (tag == DW_TAG_const_type ||
+		 tag == DW_TAG_restrict_type ||
+		 tag == DW_TAG_volatile_type ||
+		 tag == DW_TAG_shared_type ||
+		 tag == DW_TAG_typedef);
+
+	return die_mem;
+}
+
+/* Return values for die_find callbacks */
+enum {
+	DIE_FIND_CB_FOUND = 0,		/* End of Search */
+	DIE_FIND_CB_CHILD = 1,		/* Search only children */
+	DIE_FIND_CB_SIBLING = 2,	/* Search only siblings */
+	DIE_FIND_CB_CONTINUE = 3,	/* Search children and siblings */
+};
+
+/* Search a child die */
+static Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
+				 int (*callback)(Dwarf_Die *, void *),
+				 void *data, Dwarf_Die *die_mem)
+{
+	Dwarf_Die child_die;
+	int ret;
+
+	ret = dwarf_child(rt_die, die_mem);
+	if (ret != 0)
+		return NULL;
+
+	do {
+		ret = callback(die_mem, data);
+		if (ret == DIE_FIND_CB_FOUND)
+			return die_mem;
+
+		if ((ret & DIE_FIND_CB_CHILD) &&
+		    die_find_child(die_mem, callback, data, &child_die)) {
+			memcpy(die_mem, &child_die, sizeof(Dwarf_Die));
+			return die_mem;
+		}
+	} while ((ret & DIE_FIND_CB_SIBLING) &&
+		 dwarf_siblingof(die_mem, die_mem) == 0);
+
+	return NULL;
+}
+
 struct __addr_die_search_param {
 	Dwarf_Addr	addr;
 	Dwarf_Die	*die_mem;
@@ -205,8 +284,8 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
 }
 
 /* Search a real subprogram including this line, */
-static Dwarf_Die *die_get_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr,
-					  Dwarf_Die *die_mem)
+static Dwarf_Die *die_find_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr,
+					   Dwarf_Die *die_mem)
 {
 	struct __addr_die_search_param ad;
 	ad.addr = addr;
@@ -218,77 +297,64 @@ static Dwarf_Die *die_get_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr,
 		return die_mem;
 }
 
-/* Similar to dwarf_getfuncs, but returns inlined_subroutine if exists. */
-static Dwarf_Die *die_get_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
-				     Dwarf_Die *die_mem)
+/* die_find callback for inline function search */
+static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data)
 {
-	Dwarf_Die child_die;
-	int ret;
-
-	ret = dwarf_child(sp_die, die_mem);
-	if (ret != 0)
-		return NULL;
+	Dwarf_Addr *addr = data;
 
-	do {
-		if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine &&
-		    dwarf_haspc(die_mem, addr))
-			return die_mem;
+	if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine &&
+	    dwarf_haspc(die_mem, *addr))
+		return DIE_FIND_CB_FOUND;
 
-		if (die_get_inlinefunc(die_mem, addr, &child_die)) {
-			memcpy(die_mem, &child_die, sizeof(Dwarf_Die));
-			return die_mem;
-		}
-	} while (dwarf_siblingof(die_mem, die_mem) == 0);
-
-	return NULL;
+	return DIE_FIND_CB_CONTINUE;
 }
 
-/* Compare diename and tname */
-static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
+/* Similar to dwarf_getfuncs, but returns inlined_subroutine if exists. */
+static Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+				      Dwarf_Die *die_mem)
 {
-	const char *name;
-	name = dwarf_diename(dw_die);
-	DIE_IF(name == NULL);
-	return strcmp(tname, name);
+	return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
 }
 
-/* Get entry pc(or low pc, 1st entry of ranges)  of the die */
-static Dwarf_Addr die_get_entrypc(Dwarf_Die *dw_die)
+static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data)
 {
-	Dwarf_Addr epc;
-	int ret;
+	const char *name = data;
+	int tag;
 
-	ret = dwarf_entrypc(dw_die, &epc);
-	DIE_IF(ret == -1);
-	return epc;
+	tag = dwarf_tag(die_mem);
+	if ((tag == DW_TAG_formal_parameter ||
+	     tag == DW_TAG_variable) &&
+	    (die_compare_name(die_mem, name) == 0))
+		return DIE_FIND_CB_FOUND;
+
+	return DIE_FIND_CB_CONTINUE;
 }
 
-/* Get a variable die */
+/* Find a variable called 'name' */
 static Dwarf_Die *die_find_variable(Dwarf_Die *sp_die, const char *name,
 				    Dwarf_Die *die_mem)
 {
-	Dwarf_Die child_die;
-	int tag;
-	int ret;
+	return die_find_child(sp_die, __die_find_variable_cb, (void *)name,
+			      die_mem);
+}
 
-	ret = dwarf_child(sp_die, die_mem);
-	if (ret != 0)
-		return NULL;
+static int __die_find_member_cb(Dwarf_Die *die_mem, void *data)
+{
+	const char *name = data;
 
-	do {
-		tag = dwarf_tag(die_mem);
-		if ((tag == DW_TAG_formal_parameter ||
-		     tag == DW_TAG_variable) &&
-		    (die_compare_name(die_mem, name) == 0))
-			return die_mem;
+	if ((dwarf_tag(die_mem) == DW_TAG_member) &&
+	    (die_compare_name(die_mem, name) == 0))
+		return DIE_FIND_CB_FOUND;
 
-		if (die_find_variable(die_mem, name, &child_die)) {
-			memcpy(die_mem, &child_die, sizeof(Dwarf_Die));
-			return die_mem;
-		}
-	} while (dwarf_siblingof(die_mem, die_mem) == 0);
+	return DIE_FIND_CB_SIBLING;
+}
 
-	return NULL;
+/* Find a member called 'name' */
+static Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
+				  Dwarf_Die *die_mem)
+{
+	return die_find_child(st_die, __die_find_member_cb, (void *)name,
+			      die_mem);
 }
 
 /*
@@ -296,19 +362,20 @@ static Dwarf_Die *die_find_variable(Dwarf_Die *sp_die, const char *name,
  */
 
 /* Show a location */
-static void show_location(Dwarf_Op *op, struct probe_finder *pf)
+static void convert_location(Dwarf_Op *op, struct probe_finder *pf)
 {
 	unsigned int regn;
 	Dwarf_Word offs = 0;
-	int deref = 0, ret;
+	bool ref = false;
 	const char *regs;
+	struct kprobe_trace_arg *tvar = pf->tvar;
 
 	/* TODO: support CFA */
 	/* If this is based on frame buffer, set the offset */
 	if (op->atom == DW_OP_fbreg) {
 		if (pf->fb_ops == NULL)
 			die("The attribute of frame base is not supported.\n");
-		deref = 1;
+		ref = true;
 		offs = op->number;
 		op = &pf->fb_ops[0];
 	}
@@ -316,13 +383,13 @@ static void show_location(Dwarf_Op *op, struct probe_finder *pf)
 	if (op->atom >= DW_OP_breg0 && op->atom <= DW_OP_breg31) {
 		regn = op->atom - DW_OP_breg0;
 		offs += op->number;
-		deref = 1;
+		ref = true;
 	} else if (op->atom >= DW_OP_reg0 && op->atom <= DW_OP_reg31) {
 		regn = op->atom - DW_OP_reg0;
 	} else if (op->atom == DW_OP_bregx) {
 		regn = op->number;
 		offs += op->number2;
-		deref = 1;
+		ref = true;
 	} else if (op->atom == DW_OP_regx) {
 		regn = op->number;
 	} else
@@ -332,17 +399,75 @@ static void show_location(Dwarf_Op *op, struct probe_finder *pf)
 	if (!regs)
 		die("%u exceeds max register number.", regn);
 
-	if (deref)
-		ret = snprintf(pf->buf, pf->len, " %s=%+jd(%s)",
-			       pf->var, (intmax_t)offs, regs);
-	else
-		ret = snprintf(pf->buf, pf->len, " %s=%s", pf->var, regs);
-	DIE_IF(ret < 0);
-	DIE_IF(ret >= pf->len);
+	tvar->value = xstrdup(regs);
+	if (ref) {
+		tvar->ref = xzalloc(sizeof(struct kprobe_trace_arg_ref));
+		tvar->ref->offset = (long)offs;
+	}
+}
+
+static void convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
+				    struct perf_probe_arg_field *field,
+				    struct kprobe_trace_arg_ref **ref_ptr)
+{
+	struct kprobe_trace_arg_ref *ref = *ref_ptr;
+	Dwarf_Attribute attr;
+	Dwarf_Die member;
+	Dwarf_Die type;
+	Dwarf_Word offs;
+
+	pr_debug("converting %s in %s\n", field->name, varname);
+	if (die_get_real_type(vr_die, &type) == NULL)
+		die("Failed to get a type information of %s.", varname);
+
+	/* Check the pointer and dereference */
+	if (dwarf_tag(&type) == DW_TAG_pointer_type) {
+		if (!field->ref)
+			die("Semantic error: %s must be referred by '->'",
+			    field->name);
+		/* Get the type pointed by this pointer */
+		if (die_get_real_type(&type, &type) == NULL)
+			die("Failed to get a type information of %s.", varname);
+
+		/* Verify it is a data structure  */
+		if (dwarf_tag(&type) != DW_TAG_structure_type)
+			die("%s is not a data structure.", varname);
+
+		ref = xzalloc(sizeof(struct kprobe_trace_arg_ref));
+		if (*ref_ptr)
+			(*ref_ptr)->next = ref;
+		else
+			*ref_ptr = ref;
+	} else {
+		/* Verify it is a data structure  */
+		if (dwarf_tag(&type) != DW_TAG_structure_type)
+			die("%s is not a data structure.", varname);
+
+		if (field->ref)
+			die("Semantic error: %s must be referred by '.'",
+			    field->name);
+		if (!ref)
+			die("Structure on a register is not supported yet.");
+	}
+
+	if (die_find_member(&type, field->name, &member) == NULL)
+		die("%s(tyep:%s) has no member %s.", varname,
+		    dwarf_diename(&type), field->name);
+
+	/* Get the offset of the field */
+	if (dwarf_attr(&member, DW_AT_data_member_location, &attr) == NULL ||
+	    dwarf_formudata(&attr, &offs) != 0)
+		die("Failed to get the offset of %s.", field->name);
+	ref->offset += (long)offs;
+
+	/* Converting next field */
+	if (field->next)
+		convert_variable_fields(&member, field->name, field->next,
+					&ref);
 }
 
 /* Show a variables in kprobe event format */
-static void show_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
+static void convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 {
 	Dwarf_Attribute attr;
 	Dwarf_Op *expr;
@@ -356,83 +481,77 @@ static void show_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 	if (ret <= 0 || nexpr == 0)
 		goto error;
 
-	show_location(expr, pf);
+	convert_location(expr, pf);
+
+	if (pf->pvar->field)
+		convert_variable_fields(vr_die, pf->pvar->name,
+					pf->pvar->field, &pf->tvar->ref);
 	/* *expr will be cached in libdw. Don't free it. */
 	return ;
 error:
 	/* TODO: Support const_value */
 	die("Failed to find the location of %s at this address.\n"
-	    " Perhaps, it has been optimized out.", pf->var);
+	    " Perhaps, it has been optimized out.", pf->pvar->name);
 }
 
 /* Find a variable in a subprogram die */
 static void find_variable(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
-	int ret;
 	Dwarf_Die vr_die;
+	char buf[128];
 
 	/* TODO: Support struct members and arrays */
-	if (!is_c_varname(pf->var)) {
-		/* Output raw parameters */
-		ret = snprintf(pf->buf, pf->len, " %s", pf->var);
-		DIE_IF(ret < 0);
-		DIE_IF(ret >= pf->len);
-		return ;
+	if (!is_c_varname(pf->pvar->name)) {
+		/* Copy raw parameters */
+		pf->tvar->value = xstrdup(pf->pvar->name);
+	} else {
+		synthesize_perf_probe_arg(pf->pvar, buf, 128);
+		pf->tvar->name = xstrdup(buf);
+		pr_debug("Searching '%s' variable in context.\n",
+			 pf->pvar->name);
+		/* Search child die for local variables and parameters. */
+		if (!die_find_variable(sp_die, pf->pvar->name, &vr_die))
+			die("Failed to find '%s' in this function.",
+			    pf->pvar->name);
+		convert_variable(&vr_die, pf);
 	}
-
-	pr_debug("Searching '%s' variable in context.\n", pf->var);
-	/* Search child die for local variables and parameters. */
-	if (!die_find_variable(sp_die, pf->var, &vr_die))
-		die("Failed to find '%s' in this function.", pf->var);
-
-	show_variable(&vr_die, pf);
 }
 
 /* Show a probe point to output buffer */
-static void show_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
+static void convert_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
-	struct probe_point *pp = pf->pp;
+	struct kprobe_trace_event *tev;
 	Dwarf_Addr eaddr;
 	Dwarf_Die die_mem;
 	const char *name;
-	char tmp[MAX_PROBE_BUFFER];
-	int ret, i, len;
+	int ret, i;
 	Dwarf_Attribute fb_attr;
 	size_t nops;
 
+	if (pf->ntevs == MAX_PROBES)
+		die("Too many( > %d) probe point found.\n", MAX_PROBES);
+	tev = &pf->tevs[pf->ntevs++];
+
 	/* If no real subprogram, find a real one */
 	if (!sp_die || dwarf_tag(sp_die) != DW_TAG_subprogram) {
-		sp_die = die_get_real_subprogram(&pf->cu_die,
+		sp_die = die_find_real_subprogram(&pf->cu_die,
 						 pf->addr, &die_mem);
 		if (!sp_die)
 			die("Probe point is not found in subprograms.");
 	}
 
-	/* Output name of probe point */
+	/* Copy the name of probe point */
 	name = dwarf_diename(sp_die);
 	if (name) {
 		dwarf_entrypc(sp_die, &eaddr);
-		ret = snprintf(tmp, MAX_PROBE_BUFFER, "%s+%lu", name,
-				(unsigned long)(pf->addr - eaddr));
-		/* Copy the function name if possible */
-		if (!pp->function) {
-			pp->function = strdup(name);
-			pp->offset = (size_t)(pf->addr - eaddr);
-		}
-	} else {
+		tev->point.symbol = xstrdup(name);
+		tev->point.offset = (unsigned long)(pf->addr - eaddr);
+	} else
 		/* This function has no name. */
-		ret = snprintf(tmp, MAX_PROBE_BUFFER, "0x%jx",
-			       (uintmax_t)pf->addr);
-		if (!pp->function) {
-			/* TODO: Use _stext */
-			pp->function = strdup("");
-			pp->offset = (size_t)pf->addr;
-		}
-	}
-	DIE_IF(ret < 0);
-	DIE_IF(ret >= MAX_PROBE_BUFFER);
-	len = ret;
-	pr_debug("Probe point found: %s\n", tmp);
+		tev->point.offset = (unsigned long)pf->addr;
+
+	pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
+		 tev->point.offset);
 
 	/* Get the frame base attribute/ops */
 	dwarf_attr(sp_die, DW_AT_frame_base, &fb_attr);
@@ -442,22 +561,16 @@ static void show_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
 
 	/* Find each argument */
 	/* TODO: use dwarf_cfi_addrframe */
-	for (i = 0; i < pp->nr_args; i++) {
-		pf->var = pp->args[i];
-		pf->buf = &tmp[len];
-		pf->len = MAX_PROBE_BUFFER - len;
+	tev->nargs = pf->pev->nargs;
+	tev->args = xzalloc(sizeof(struct kprobe_trace_arg) * tev->nargs);
+	for (i = 0; i < pf->pev->nargs; i++) {
+		pf->pvar = &pf->pev->args[i];
+		pf->tvar = &tev->args[i];
 		find_variable(sp_die, pf);
-		len += strlen(pf->buf);
 	}
 
 	/* *pf->fb_ops will be cached in libdw. Don't free it. */
 	pf->fb_ops = NULL;
-
-	if (pp->found == MAX_PROBES)
-		die("Too many( > %d) probe point found.\n", MAX_PROBES);
-
-	pp->probes[pp->found] = strdup(tmp);
-	pp->found++;
 }
 
 /* Find probe point from its line number */
@@ -489,7 +602,7 @@ static void find_probe_point_by_line(struct probe_finder *pf)
 			 (int)i, lineno, (uintmax_t)addr);
 		pf->addr = addr;
 
-		show_probe_point(NULL, pf);
+		convert_probe_point(NULL, pf);
 		/* Continuing, because target line might be inlined. */
 	}
 }
@@ -506,8 +619,7 @@ static int find_lazy_match_lines(struct list_head *head,
 	if (fd < 0)
 		die("failed to open %s", fname);
 	DIE_IF(fstat(fd, &st) < 0);
-	fbuf = malloc(st.st_size + 2);
-	DIE_IF(fbuf == NULL);
+	fbuf = xmalloc(st.st_size + 2);
 	DIE_IF(read(fd, fbuf, st.st_size) < 0);
 	close(fd);
 	fbuf[st.st_size] = '\n';	/* Dummy line */
@@ -541,7 +653,7 @@ static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 	if (list_empty(&pf->lcache)) {
 		/* Matching lazy line pattern */
 		ret = find_lazy_match_lines(&pf->lcache, pf->fname,
-					    pf->pp->lazy_line);
+					    pf->pev->point.lazy_line);
 		if (ret <= 0)
 			die("No matched lines found in %s.", pf->fname);
 	}
@@ -566,7 +678,7 @@ static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 			if (!dwarf_haspc(sp_die, addr))
 				continue;
 			/* Address filtering 2: No child include addr? */
-			if (die_get_inlinefunc(sp_die, addr, &die_mem))
+			if (die_find_inlinefunc(sp_die, addr, &die_mem))
 				continue;
 		}
 
@@ -574,7 +686,7 @@ static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 			 (int)i, lineno, (unsigned long long)addr);
 		pf->addr = addr;
 
-		show_probe_point(sp_die, pf);
+		convert_probe_point(sp_die, pf);
 		/* Continuing, because target line might be inlined. */
 	}
 	/* TODO: deallocate lines, but how? */
@@ -583,7 +695,7 @@ static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
 {
 	struct probe_finder *pf = (struct probe_finder *)data;
-	struct probe_point *pp = pf->pp;
+	struct perf_probe_point *pp = &pf->pev->point;
 
 	if (pp->lazy_line)
 		find_probe_point_lazy(in_die, pf);
@@ -594,7 +706,7 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
 		pr_debug("found inline addr: 0x%jx\n",
 			 (uintmax_t)pf->addr);
 
-		show_probe_point(in_die, pf);
+		convert_probe_point(in_die, pf);
 	}
 
 	return DWARF_CB_OK;
@@ -604,7 +716,7 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
 static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 {
 	struct probe_finder *pf = (struct probe_finder *)data;
-	struct probe_point *pp = pf->pp;
+	struct perf_probe_point *pp = &pf->pev->point;
 
 	/* Check tag and diename */
 	if (dwarf_tag(sp_die) != DW_TAG_subprogram ||
@@ -624,7 +736,7 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 			pf->addr = die_get_entrypc(sp_die);
 			pf->addr += pp->offset;
 			/* TODO: Check the address in this function */
-			show_probe_point(sp_die, pf);
+			convert_probe_point(sp_die, pf);
 		}
 	} else
 		/* Inlined function: search instances */
@@ -638,20 +750,25 @@ static void find_probe_point_by_func(struct probe_finder *pf)
 	dwarf_getfuncs(&pf->cu_die, probe_point_search_cb, pf, 0);
 }
 
-/* Find a probe point */
-int find_probe_point(int fd, struct probe_point *pp)
+/* Find kprobe_trace_events specified by perf_probe_event from debuginfo */
+int find_kprobe_trace_events(int fd, struct perf_probe_event *pev,
+			     struct kprobe_trace_event **tevs)
 {
-	struct probe_finder pf = {.pp = pp};
+	struct probe_finder pf = {.pev = pev};
+	struct perf_probe_point *pp = &pev->point;
 	Dwarf_Off off, noff;
 	size_t cuhl;
 	Dwarf_Die *diep;
 	Dwarf *dbg;
 
+	pf.tevs = xzalloc(sizeof(struct kprobe_trace_event) * MAX_PROBES);
+	*tevs = pf.tevs;
+	pf.ntevs = 0;
+
 	dbg = dwarf_begin(fd, DWARF_C_READ);
 	if (!dbg)
 		return -ENOENT;
 
-	pp->found = 0;
 	off = 0;
 	line_list__init(&pf.lcache);
 	/* Loop on CUs (Compilation Unit) */
@@ -682,9 +799,81 @@ int find_probe_point(int fd, struct probe_point *pp)
 	line_list__free(&pf.lcache);
 	dwarf_end(dbg);
 
-	return pp->found;
+	return pf.ntevs;
+}
+
+/* Reverse search */
+int find_perf_probe_point(int fd, unsigned long addr,
+			  struct perf_probe_point *ppt)
+{
+	Dwarf_Die cudie, spdie, indie;
+	Dwarf *dbg;
+	Dwarf_Line *line;
+	Dwarf_Addr laddr, eaddr;
+	const char *tmp;
+	int lineno, ret = 0;
+
+	dbg = dwarf_begin(fd, DWARF_C_READ);
+	if (!dbg)
+		return -ENOENT;
+
+	/* Find cu die */
+	if (!dwarf_addrdie(dbg, (Dwarf_Addr)addr, &cudie)) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	/* Find a corresponding line */
+	line = dwarf_getsrc_die(&cudie, (Dwarf_Addr)addr);
+	if (line) {
+		dwarf_lineaddr(line, &laddr);
+		if ((Dwarf_Addr)addr == laddr) {
+			dwarf_lineno(line, &lineno);
+			ppt->line = lineno;
+
+			tmp = dwarf_linesrc(line, NULL, NULL);
+			DIE_IF(!tmp);
+			ppt->file = xstrdup(tmp);
+			ret = 1;
+		}
+	}
+
+	/* Find a corresponding function */
+	if (die_find_real_subprogram(&cudie, (Dwarf_Addr)addr, &spdie)) {
+		tmp = dwarf_diename(&spdie);
+		if (!tmp)
+			goto end;
+
+		dwarf_entrypc(&spdie, &eaddr);
+		if (!lineno) {
+			/* We don't have a line number, let's use offset */
+			ppt->function = xstrdup(tmp);
+			ppt->offset = addr - (unsigned long)eaddr;
+			ret = 1;
+			goto end;
+		}
+		if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr, &indie)) {
+			/* addr in an inline function */
+			tmp = dwarf_diename(&indie);
+			if (!tmp)
+				goto end;
+			dwarf_decl_line(&indie, &lineno);
+		} else {
+			if (eaddr == addr)	/* No offset: function entry */
+				lineno = ppt->line;
+			else
+				dwarf_decl_line(&spdie, &lineno);
+		}
+		ppt->function = xstrdup(tmp);
+		ppt->line -= lineno;	/* Make a relative line number */
+	}
+
+end:
+	dwarf_end(dbg);
+	return ret;
 }
 
+
 /* Find line range from its line number */
 static void find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 {
@@ -716,7 +905,7 @@ static void find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 				continue;
 
 			/* Address filtering 2: No child include addr? */
-			if (die_get_inlinefunc(sp_die, addr, &die_mem))
+			if (die_find_inlinefunc(sp_die, addr, &die_mem))
 				continue;
 		}
 
@@ -727,7 +916,7 @@ static void find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 
 		/* Copy real path */
 		if (!lf->lr->path)
-			lf->lr->path = strdup(src);
+			lf->lr->path = xstrdup(src);
 		line_list__add_line(&lf->lr->line_list, (unsigned int)lineno);
 	}
 	/* Update status */
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 21f7354397b4..2a271321944f 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -3,6 +3,7 @@
 
 #include <stdbool.h>
 #include "util.h"
+#include "probe-event.h"
 
 #define MAX_PATH_LEN		 256
 #define MAX_PROBE_BUFFER	1024
@@ -14,67 +15,36 @@ static inline int is_c_varname(const char *name)
 	return isalpha(name[0]) || name[0] == '_';
 }
 
-struct probe_point {
-	char			*event;			/* Event name */
-	char			*group;			/* Event group */
+#ifdef DWARF_SUPPORT
+/* Find kprobe_trace_events specified by perf_probe_event from debuginfo */
+extern int find_kprobe_trace_events(int fd, struct perf_probe_event *pev,
+				    struct kprobe_trace_event **tevs);
 
-	/* Inputs */
-	char			*file;			/* File name */
-	int			line;			/* Line number */
-	char			*lazy_line;		/* Lazy line pattern */
+/* Find a perf_probe_point from debuginfo */
+extern int find_perf_probe_point(int fd, unsigned long addr,
+				 struct perf_probe_point *ppt);
 
-	char			*function;		/* Function name */
-	int			offset;			/* Offset bytes */
-
-	int			nr_args;		/* Number of arguments */
-	char			**args;			/* Arguments */
-
-	int			retprobe;		/* Return probe */
-
-	/* Output */
-	int			found;			/* Number of found probe points */
-	char			*probes[MAX_PROBES];	/* Output buffers (will be allocated)*/
-};
-
-/* Line number container */
-struct line_node {
-	struct list_head	list;
-	unsigned int		line;
-};
-
-/* Line range */
-struct line_range {
-	char			*file;			/* File name */
-	char			*function;		/* Function name */
-	unsigned int		start;			/* Start line number */
-	unsigned int		end;			/* End line number */
-	int			offset;			/* Start line offset */
-	char			*path;			/* Real path name */
-	struct list_head	line_list;		/* Visible lines */
-};
-
-#ifndef NO_DWARF_SUPPORT
-extern int find_probe_point(int fd, struct probe_point *pp);
 extern int find_line_range(int fd, struct line_range *lr);
 
 #include <dwarf.h>
 #include <libdw.h>
 
 struct probe_finder {
-	struct probe_point	*pp;		/* Target probe point */
+	struct perf_probe_event	*pev;		/* Target probe event */
+	struct kprobe_trace_event *tevs;	/* Result trace events */
+	int			ntevs;		/* number of trace events */
 
 	/* For function searching */
-	Dwarf_Addr		addr;		/* Address */
-	const char		*fname;		/* File name */
 	int			lno;		/* Line number */
+	Dwarf_Addr		addr;		/* Address */
+	const char		*fname;		/* Real file name */
 	Dwarf_Die		cu_die;		/* Current CU */
+	struct list_head	lcache;		/* Line cache for lazy match */
 
 	/* For variable searching */
 	Dwarf_Op		*fb_ops;	/* Frame base attribute */
-	const char		*var;		/* Current variable name */
-	char			*buf;		/* Current output buffer */
-	int			len;		/* Length of output buffer */
-	struct list_head	lcache;		/* Line cache for lazy match */
+	struct perf_probe_arg	*pvar;		/* Current target variable */
+	struct kprobe_trace_arg	*tvar;		/* Current result variable */
 };
 
 struct line_finder {
@@ -87,6 +57,6 @@ struct line_finder {
 	int			found;
 };
 
-#endif /* NO_DWARF_SUPPORT */
+#endif /* DWARF_SUPPORT */
 
 #endif /*_PROBE_FINDER_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index eed1cb889008..ddf288fca3eb 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -52,11 +52,6 @@ out_close:
 	return -1;
 }
 
-static inline int perf_session__create_kernel_maps(struct perf_session *self)
-{
-	return map_groups__create_kernel_maps(&self->kmaps, self->vmlinux_maps);
-}
-
 struct perf_session *perf_session__new(const char *filename, int mode, bool force)
 {
 	size_t len = filename ? strlen(filename) + 1 : 0;
@@ -117,22 +112,17 @@ static bool symbol__match_parent_regex(struct symbol *sym)
 	return 0;
 }
 
-struct symbol **perf_session__resolve_callchain(struct perf_session *self,
-						struct thread *thread,
-						struct ip_callchain *chain,
-						struct symbol **parent)
+struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
+						   struct thread *thread,
+						   struct ip_callchain *chain,
+						   struct symbol **parent)
 {
 	u8 cpumode = PERF_RECORD_MISC_USER;
-	struct symbol **syms = NULL;
 	unsigned int i;
+	struct map_symbol *syms = calloc(chain->nr, sizeof(*syms));
 
-	if (symbol_conf.use_callchain) {
-		syms = calloc(chain->nr, sizeof(*syms));
-		if (!syms) {
-			fprintf(stderr, "Can't allocate memory for symbols\n");
-			exit(-1);
-		}
-	}
+	if (!syms)
+		return NULL;
 
 	for (i = 0; i < chain->nr; i++) {
 		u64 ip = chain->ips[i];
@@ -160,7 +150,8 @@ struct symbol **perf_session__resolve_callchain(struct perf_session *self,
 				*parent = al.sym;
 			if (!symbol_conf.use_callchain)
 				break;
-			syms[i] = al.sym;
+			syms[i].map = al.map;
+			syms[i].sym = al.sym;
 		}
 	}
 
@@ -396,6 +387,10 @@ int __perf_session__process_events(struct perf_session *self,
 	event_t *event;
 	uint32_t size;
 	char *buf;
+	struct ui_progress *progress = ui_progress__new("Processing events...",
+							self->size);
+	if (progress == NULL)
+		return -1;
 
 	perf_event_ops__fill_defaults(ops);
 
@@ -424,6 +419,7 @@ remap:
 
 more:
 	event = (event_t *)(buf + head);
+	ui_progress__update(progress, offset);
 
 	if (self->header.needs_swap)
 		perf_event_header__bswap(&event->header);
@@ -474,6 +470,7 @@ more:
 done:
 	err = 0;
 out_err:
+	ui_progress__delete(progress);
 	return err;
 }
 
@@ -543,32 +540,3 @@ int perf_session__set_kallsyms_ref_reloc_sym(struct perf_session *self,
 
 	return 0;
 }
-
-static u64 map__reloc_map_ip(struct map *map, u64 ip)
-{
-	return ip + (s64)map->pgoff;
-}
-
-static u64 map__reloc_unmap_ip(struct map *map, u64 ip)
-{
-	return ip - (s64)map->pgoff;
-}
-
-void map__reloc_vmlinux(struct map *self)
-{
-	struct kmap *kmap = map__kmap(self);
-	s64 reloc;
-
-	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr)
-		return;
-
-	reloc = (kmap->ref_reloc_sym->unrelocated_addr -
-		 kmap->ref_reloc_sym->addr);
-
-	if (!reloc)
-		return;
-
-	self->map_ip   = map__reloc_map_ip;
-	self->unmap_ip = map__reloc_unmap_ip;
-	self->pgoff    = reloc;
-}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 5c33417eebb3..27f4c2dc715b 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -57,10 +57,10 @@ int __perf_session__process_events(struct perf_session *self,
 int perf_session__process_events(struct perf_session *self,
 				 struct perf_event_ops *event_ops);
 
-struct symbol **perf_session__resolve_callchain(struct perf_session *self,
-						struct thread *thread,
-						struct ip_callchain *chain,
-						struct symbol **parent);
+struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
+						   struct thread *thread,
+						   struct ip_callchain *chain,
+						   struct symbol **parent);
 
 bool perf_session__has_traces(struct perf_session *self, const char *msg);
 
@@ -80,10 +80,30 @@ static inline int __perf_session__create_kernel_maps(struct perf_session *self,
 						self->vmlinux_maps, kernel);
 }
 
+static inline int perf_session__create_kernel_maps(struct perf_session *self)
+{
+	return map_groups__create_kernel_maps(&self->kmaps, self->vmlinux_maps);
+}
+
 static inline struct map *
 	perf_session__new_module_map(struct perf_session *self,
 				     u64 start, const char *filename)
 {
 	return map_groups__new_module(&self->kmaps, start, filename);
 }
+
+#ifdef NO_NEWT_SUPPORT
+static inline int perf_session__browse_hists(struct rb_root *hists __used,
+					      u64 nr_hists __used,
+					      u64 session_total __used,
+					     const char *helpline __used,
+					     const char *input_name __used)
+{
+	return 0;
+}
+#else
+int perf_session__browse_hists(struct rb_root *hists, u64 nr_hists,
+			       u64 session_total, const char *helpline,
+			       const char *input_name);
+#endif
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index cb0f327de9e8..9d24d4b2c8fb 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -18,10 +18,21 @@ char * field_sep;
 
 LIST_HEAD(hist_entry__sort_list);
 
+static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
+				       size_t size, unsigned int width);
+static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
+				     size_t size, unsigned int width);
+static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width);
+static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width);
+static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
+				       size_t size, unsigned int width);
+
 struct sort_entry sort_thread = {
 	.header = "Command:  Pid",
 	.cmp	= sort__thread_cmp,
-	.print	= sort__thread_print,
+	.snprintf = hist_entry__thread_snprintf,
 	.width	= &threads__col_width,
 };
 
@@ -29,27 +40,27 @@ struct sort_entry sort_comm = {
 	.header		= "Command",
 	.cmp		= sort__comm_cmp,
 	.collapse	= sort__comm_collapse,
-	.print		= sort__comm_print,
+	.snprintf	= hist_entry__comm_snprintf,
 	.width		= &comms__col_width,
 };
 
 struct sort_entry sort_dso = {
 	.header = "Shared Object",
 	.cmp	= sort__dso_cmp,
-	.print	= sort__dso_print,
+	.snprintf = hist_entry__dso_snprintf,
 	.width	= &dsos__col_width,
 };
 
 struct sort_entry sort_sym = {
 	.header = "Symbol",
 	.cmp	= sort__sym_cmp,
-	.print	= sort__sym_print,
+	.snprintf = hist_entry__sym_snprintf,
 };
 
 struct sort_entry sort_parent = {
 	.header = "Parent symbol",
 	.cmp	= sort__parent_cmp,
-	.print	= sort__parent_print,
+	.snprintf = hist_entry__parent_snprintf,
 	.width	= &parent_symbol__col_width,
 };
 
@@ -85,45 +96,38 @@ sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
 	return right->thread->pid - left->thread->pid;
 }
 
-int repsep_fprintf(FILE *fp, const char *fmt, ...)
+static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
 {
 	int n;
 	va_list ap;
 
 	va_start(ap, fmt);
-	if (!field_sep)
-		n = vfprintf(fp, fmt, ap);
-	else {
-		char *bf = NULL;
-		n = vasprintf(&bf, fmt, ap);
-		if (n > 0) {
-			char *sep = bf;
-
-			while (1) {
-				sep = strchr(sep, *field_sep);
-				if (sep == NULL)
-					break;
-				*sep = '.';
-			}
+	n = vsnprintf(bf, size, fmt, ap);
+	if (field_sep && n > 0) {
+		char *sep = bf;
+
+		while (1) {
+			sep = strchr(sep, *field_sep);
+			if (sep == NULL)
+				break;
+			*sep = '.';
 		}
-		fputs(bf, fp);
-		free(bf);
 	}
 	va_end(ap);
 	return n;
 }
 
-size_t
-sort__thread_print(FILE *fp, struct hist_entry *self, unsigned int width)
+static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
+				       size_t size, unsigned int width)
 {
-	return repsep_fprintf(fp, "%*s:%5d", width - 6,
+	return repsep_snprintf(bf, size, "%*s:%5d", width,
 			      self->thread->comm ?: "", self->thread->pid);
 }
 
-size_t
-sort__comm_print(FILE *fp, struct hist_entry *self, unsigned int width)
+static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
+				     size_t size, unsigned int width)
 {
-	return repsep_fprintf(fp, "%*s", width, self->thread->comm);
+	return repsep_snprintf(bf, size, "%*s", width, self->thread->comm);
 }
 
 /* --sort dso */
@@ -131,8 +135,8 @@ sort__comm_print(FILE *fp, struct hist_entry *self, unsigned int width)
 int64_t
 sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	struct dso *dso_l = left->map ? left->map->dso : NULL;
-	struct dso *dso_r = right->map ? right->map->dso : NULL;
+	struct dso *dso_l = left->ms.map ? left->ms.map->dso : NULL;
+	struct dso *dso_r = right->ms.map ? right->ms.map->dso : NULL;
 	const char *dso_name_l, *dso_name_r;
 
 	if (!dso_l || !dso_r)
@@ -149,16 +153,16 @@ sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
 	return strcmp(dso_name_l, dso_name_r);
 }
 
-size_t
-sort__dso_print(FILE *fp, struct hist_entry *self, unsigned int width)
+static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width)
 {
-	if (self->map && self->map->dso) {
-		const char *dso_name = !verbose ? self->map->dso->short_name :
-						  self->map->dso->long_name;
-		return repsep_fprintf(fp, "%-*s", width, dso_name);
+	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 repsep_snprintf(bf, size, "%-*s", width, dso_name);
 	}
 
-	return repsep_fprintf(fp, "%*llx", width, (u64)self->ip);
+	return repsep_snprintf(bf, size, "%*Lx", width, self->ip);
 }
 
 /* --sort symbol */
@@ -168,31 +172,31 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	u64 ip_l, ip_r;
 
-	if (left->sym == right->sym)
+	if (left->ms.sym == right->ms.sym)
 		return 0;
 
-	ip_l = left->sym ? left->sym->start : left->ip;
-	ip_r = right->sym ? right->sym->start : right->ip;
+	ip_l = left->ms.sym ? left->ms.sym->start : left->ip;
+	ip_r = right->ms.sym ? right->ms.sym->start : right->ip;
 
 	return (int64_t)(ip_r - ip_l);
 }
 
-
-size_t
-sort__sym_print(FILE *fp, struct hist_entry *self, unsigned int width __used)
+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->map ? dso__symtab_origin(self->map->dso) : '!';
-		ret += repsep_fprintf(fp, "%#018llx %c ", (u64)self->ip, o);
+		char o = self->ms.map ? dso__symtab_origin(self->ms.map->dso) : '!';
+		ret += repsep_snprintf(bf, size, "%#018llx %c ", self->ip, o);
 	}
 
-	ret += repsep_fprintf(fp, "[%c] ", self->level);
-	if (self->sym)
-		ret += repsep_fprintf(fp, "%s", self->sym->name);
+	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_fprintf(fp, "%#016llx", (u64)self->ip);
+		ret += repsep_snprintf(bf + ret, size - ret, "%#016llx", self->ip);
 
 	return ret;
 }
@@ -231,10 +235,10 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
 	return strcmp(sym_l->name, sym_r->name);
 }
 
-size_t
-sort__parent_print(FILE *fp, struct hist_entry *self, unsigned int width)
+static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
+				       size_t size, unsigned int width)
 {
-	return repsep_fprintf(fp, "%-*s", width,
+	return repsep_snprintf(bf, size, "%-*s", width,
 			      self->parent ? self->parent->name : "[other]");
 }
 
@@ -260,9 +264,8 @@ int sort_dimension__add(const char *tok)
 				char err[BUFSIZ];
 
 				regerror(ret, &parent_regex, err, sizeof(err));
-				fprintf(stderr, "Invalid regex: %s\n%s",
-					parent_pattern, err);
-				exit(-1);
+				pr_err("Invalid regex: %s\n%s", parent_pattern, err);
+				return -EINVAL;
 			}
 			sort__has_parent = 1;
 		}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 753f9ea99fb0..6d7b4be70609 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -44,18 +44,23 @@ extern enum sort_type sort__first_dimension;
 struct hist_entry {
 	struct rb_node		rb_node;
 	u64			count;
+	/*
+	 * XXX WARNING!
+	 * thread _has_ to come after ms, see
+	 * hist_browser__selected_thread in util/newt.c
+	 */
+	struct map_symbol	ms;
 	struct thread		*thread;
-	struct map		*map;
-	struct symbol		*sym;
 	u64			ip;
 	char			level;
-	struct symbol	  *parent;
-	struct callchain_node	callchain;
+	u8			filtered;
+	struct symbol		*parent;
 	union {
 		unsigned long	  position;
 		struct hist_entry *pair;
 		struct rb_root	  sorted_chain;
 	};
+	struct callchain_node	callchain[0];
 };
 
 enum sort_type {
@@ -77,7 +82,8 @@ struct sort_entry {
 
 	int64_t (*cmp)(struct hist_entry *, struct hist_entry *);
 	int64_t (*collapse)(struct hist_entry *, struct hist_entry *);
-	size_t	(*print)(FILE *fp, struct hist_entry *, unsigned int width);
+	int	(*snprintf)(struct hist_entry *self, char *bf, size_t size,
+			    unsigned int width);
 	unsigned int *width;
 	bool	elide;
 };
@@ -87,7 +93,6 @@ extern struct list_head hist_entry__sort_list;
 
 void setup_sorting(const char * const usagestr[], const struct option *opts);
 
-extern int repsep_fprintf(FILE *fp, const char *fmt, ...);
 extern size_t sort__thread_print(FILE *, struct hist_entry *, unsigned int);
 extern size_t sort__comm_print(FILE *, struct hist_entry *, unsigned int);
 extern size_t sort__dso_print(FILE *, struct hist_entry *, unsigned int);
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index a175949ed216..0409fc7c0058 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -1,48 +1,5 @@
-#include "string.h"
 #include "util.h"
-
-static int hex(char ch)
-{
-	if ((ch >= '0') && (ch <= '9'))
-		return ch - '0';
-	if ((ch >= 'a') && (ch <= 'f'))
-		return ch - 'a' + 10;
-	if ((ch >= 'A') && (ch <= 'F'))
-		return ch - 'A' + 10;
-	return -1;
-}
-
-/*
- * While we find nice hex chars, build a long_val.
- * Return number of chars processed.
- */
-int hex2u64(const char *ptr, u64 *long_val)
-{
-	const char *p = ptr;
-	*long_val = 0;
-
-	while (*p) {
-		const int hex_val = hex(*p);
-
-		if (hex_val < 0)
-			break;
-
-		*long_val = (*long_val << 4) | hex_val;
-		p++;
-	}
-
-	return p - ptr;
-}
-
-char *strxfrchar(char *s, char from, char to)
-{
-	char *p = s;
-
-	while ((p = strchr(p, from)) != NULL)
-		*p++ = to;
-
-	return s;
-}
+#include "string.h"
 
 #define K 1024LL
 /*
diff --git a/tools/perf/util/string.h b/tools/perf/util/string.h
deleted file mode 100644
index 542e44de3719..000000000000
--- a/tools/perf/util/string.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef __PERF_STRING_H_
-#define __PERF_STRING_H_
-
-#include <stdbool.h>
-#include "types.h"
-
-int hex2u64(const char *ptr, u64 *val);
-char *strxfrchar(char *s, char from, char to);
-s64 perf_atoll(const char *str);
-char **argv_split(const char *str, int *argcp);
-void argv_free(char **argv);
-bool strglobmatch(const char *str, const char *pat);
-bool strlazymatch(const char *str, const char *pat);
-
-#define _STR(x) #x
-#define STR(x) _STR(x)
-
-#endif /* __PERF_STRING_H */
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index c458c4a371d1..f3d4151e46a1 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1,13 +1,19 @@
-#include "util.h"
-#include "../perf.h"
-#include "sort.h"
-#include "string.h"
+#define _GNU_SOURCE
+#include <ctype.h>
+#include <dirent.h>
+#include <errno.h>
+#include <libgen.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/param.h>
+#include <fcntl.h>
+#include <unistd.h>
 #include "symbol.h"
-#include "thread.h"
+#include "strlist.h"
 
-#include "debug.h"
-
-#include <asm/bug.h>
 #include <libelf.h>
 #include <gelf.h>
 #include <elf.h>
@@ -18,18 +24,6 @@
 #define NT_GNU_BUILD_ID 3
 #endif
 
-enum dso_origin {
-	DSO__ORIG_KERNEL = 0,
-	DSO__ORIG_JAVA_JIT,
-	DSO__ORIG_BUILD_ID_CACHE,
-	DSO__ORIG_FEDORA,
-	DSO__ORIG_UBUNTU,
-	DSO__ORIG_BUILDID,
-	DSO__ORIG_DSO,
-	DSO__ORIG_KMODULE,
-	DSO__ORIG_NOT_FOUND,
-};
-
 static void dsos__add(struct list_head *head, struct dso *dso);
 static struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
 static int dso__load_kernel_sym(struct dso *self, struct map *map,
@@ -126,8 +120,8 @@ static void map_groups__fixup_end(struct map_groups *self)
 static struct symbol *symbol__new(u64 start, u64 len, const char *name)
 {
 	size_t namelen = strlen(name) + 1;
-	struct symbol *self = zalloc(symbol_conf.priv_size +
-				     sizeof(*self) + namelen);
+	struct symbol *self = calloc(1, (symbol_conf.priv_size +
+					 sizeof(*self) + namelen));
 	if (self == NULL)
 		return NULL;
 
@@ -178,7 +172,7 @@ static void dso__set_basename(struct dso *self)
 
 struct dso *dso__new(const char *name)
 {
-	struct dso *self = zalloc(sizeof(*self) + strlen(name) + 1);
+	struct dso *self = calloc(1, sizeof(*self) + strlen(name) + 1);
 
 	if (self != NULL) {
 		int i;
@@ -870,8 +864,8 @@ out_close:
 	if (err == 0)
 		return nr;
 out:
-	pr_warning("%s: problems reading %s PLT info.\n",
-		   __func__, self->long_name);
+	pr_debug("%s: problems reading %s PLT info.\n",
+		 __func__, self->long_name);
 	return 0;
 }
 
@@ -1025,7 +1019,7 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 				}
 				curr_map->map_ip = identity__map_ip;
 				curr_map->unmap_ip = identity__map_ip;
-				curr_dso->origin = DSO__ORIG_KERNEL;
+				curr_dso->origin = self->origin;
 				map_groups__insert(kmap->kmaps, curr_map);
 				dsos__add(&dsos__kernel, curr_dso);
 				dso__set_loaded(curr_dso, map->type);
@@ -1394,13 +1388,13 @@ static int dso__kernel_module_get_build_id(struct dso *self)
 	return 0;
 }
 
-static int map_groups__set_modules_path_dir(struct map_groups *self, char *dirname)
+static int map_groups__set_modules_path_dir(struct map_groups *self, char *dir_name)
 {
 	struct dirent *dent;
-	DIR *dir = opendir(dirname);
+	DIR *dir = opendir(dir_name);
 
 	if (!dir) {
-		pr_debug("%s: cannot open %s dir\n", __func__, dirname);
+		pr_debug("%s: cannot open %s dir\n", __func__, dir_name);
 		return -1;
 	}
 
@@ -1413,7 +1407,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *self, char *dirna
 				continue;
 
 			snprintf(path, sizeof(path), "%s/%s",
-				 dirname, dent->d_name);
+				 dir_name, dent->d_name);
 			if (map_groups__set_modules_path_dir(self, path) < 0)
 				goto failure;
 		} else {
@@ -1433,7 +1427,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *self, char *dirna
 				continue;
 
 			snprintf(path, sizeof(path), "%s/%s",
-				 dirname, dent->d_name);
+				 dir_name, dent->d_name);
 
 			long_name = strdup(path);
 			if (long_name == NULL)
@@ -1470,8 +1464,8 @@ static int map_groups__set_modules_path(struct map_groups *self)
  */
 static struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 {
-	struct map *self = zalloc(sizeof(*self) +
-				  (dso->kernel ? sizeof(struct kmap) : 0));
+	struct map *self = calloc(1, (sizeof(*self) +
+				      (dso->kernel ? sizeof(struct kmap) : 0)));
 	if (self != NULL) {
 		/*
 		 * ->end will be filled after we load all the symbols
@@ -1895,6 +1889,17 @@ out_fail:
 	return -1;
 }
 
+size_t vmlinux_path__fprintf(FILE *fp)
+{
+	int i;
+	size_t printed = 0;
+
+	for (i = 0; i < vmlinux_path__nr_entries; ++i)
+		printed += fprintf(fp, "[%d] %s\n", i, vmlinux_path[i]);
+
+	return printed;
+}
+
 static int setup_list(struct strlist **list, const char *list_str,
 		      const char *list_name)
 {
@@ -1964,3 +1969,46 @@ int map_groups__create_kernel_maps(struct map_groups *self,
 	map_groups__fixup_end(self);
 	return 0;
 }
+
+static int hex(char ch)
+{
+	if ((ch >= '0') && (ch <= '9'))
+		return ch - '0';
+	if ((ch >= 'a') && (ch <= 'f'))
+		return ch - 'a' + 10;
+	if ((ch >= 'A') && (ch <= 'F'))
+		return ch - 'A' + 10;
+	return -1;
+}
+
+/*
+ * While we find nice hex chars, build a long_val.
+ * Return number of chars processed.
+ */
+int hex2u64(const char *ptr, u64 *long_val)
+{
+	const char *p = ptr;
+	*long_val = 0;
+
+	while (*p) {
+		const int hex_val = hex(*p);
+
+		if (hex_val < 0)
+			break;
+
+		*long_val = (*long_val << 4) | hex_val;
+		p++;
+	}
+
+	return p - ptr;
+}
+
+char *strxfrchar(char *s, char from, char to)
+{
+	char *p = s;
+
+	while ((p = strchr(p, from)) != NULL)
+		*p++ = to;
+
+	return s;
+}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index f30a37428919..757fae3f5ee0 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -3,10 +3,11 @@
 
 #include <linux/types.h>
 #include <stdbool.h>
-#include "types.h"
+#include <stdint.h>
+#include "map.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
-#include "event.h"
+#include <stdio.h>
 
 #define DEBUG_CACHE_DIR ".debug"
 
@@ -29,6 +30,9 @@ static inline char *bfd_demangle(void __used *v, const char __used *c,
 #endif
 #endif
 
+int hex2u64(const char *ptr, u64 *val);
+char *strxfrchar(char *s, char from, char to);
+
 /*
  * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP;
  * for newer versions we can use mmap to reduce memory usage:
@@ -44,6 +48,8 @@ static inline char *bfd_demangle(void __used *v, const char __used *c,
 #define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
 #endif
 
+#define BUILD_ID_SIZE 20
+
 struct symbol {
 	struct rb_node	rb_node;
 	u64		start;
@@ -88,6 +94,11 @@ struct ref_reloc_sym {
 	u64		unrelocated_addr;
 };
 
+struct map_symbol {
+	struct map    *map;
+	struct symbol *sym;
+};
+
 struct addr_location {
 	struct thread *thread;
 	struct map    *map;
@@ -106,6 +117,7 @@ struct dso {
 	u8		 has_build_id:1;
 	u8		 kernel:1;
 	u8		 hit:1;
+	u8		 annotate_warned:1;
 	unsigned char	 origin;
 	u8		 sorted_by_name;
 	u8		 loaded;
@@ -150,6 +162,19 @@ size_t dsos__fprintf_buildid(FILE *fp, bool with_hits);
 
 size_t dso__fprintf_buildid(struct dso *self, FILE *fp);
 size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp);
+
+enum dso_origin {
+	DSO__ORIG_KERNEL = 0,
+	DSO__ORIG_JAVA_JIT,
+	DSO__ORIG_BUILD_ID_CACHE,
+	DSO__ORIG_FEDORA,
+	DSO__ORIG_UBUNTU,
+	DSO__ORIG_BUILDID,
+	DSO__ORIG_DSO,
+	DSO__ORIG_KMODULE,
+	DSO__ORIG_NOT_FOUND,
+};
+
 char dso__symtab_origin(const struct dso *self);
 void dso__set_long_name(struct dso *self, char *name);
 void dso__set_build_id(struct dso *self, void *build_id);
@@ -169,4 +194,6 @@ int kallsyms__parse(const char *filename, void *arg,
 int symbol__init(void);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
+size_t vmlinux_path__fprintf(FILE *fp);
+
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index fa968312ee7d..1f7ecd47f499 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,13 +7,35 @@
 #include "util.h"
 #include "debug.h"
 
-void map_groups__init(struct map_groups *self)
+int find_all_tid(int pid, pid_t ** all_tid)
 {
+	char name[256];
+	int items;
+	struct dirent **namelist = NULL;
+	int ret = 0;
 	int i;
-	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		self->maps[i] = RB_ROOT;
-		INIT_LIST_HEAD(&self->removed_maps[i]);
+
+	sprintf(name, "/proc/%d/task", pid);
+	items = scandir(name, &namelist, NULL, NULL);
+	if (items <= 0)
+                return -ENOENT;
+	*all_tid = malloc(sizeof(pid_t) * items);
+	if (!*all_tid) {
+		ret = -ENOMEM;
+		goto failure;
 	}
+
+	for (i = 0; i < items; i++)
+		(*all_tid)[i] = atoi(namelist[i]->d_name);
+
+	ret = items;
+
+failure:
+	for (i=0; i<items; i++)
+		free(namelist[i]);
+	free(namelist);
+
+	return ret;
 }
 
 static struct thread *thread__new(pid_t pid)
@@ -31,28 +53,6 @@ static struct thread *thread__new(pid_t pid)
 	return self;
 }
 
-static void map_groups__flush(struct map_groups *self)
-{
-	int type;
-
-	for (type = 0; type < MAP__NR_TYPES; type++) {
-		struct rb_root *root = &self->maps[type];
-		struct rb_node *next = rb_first(root);
-
-		while (next) {
-			struct map *pos = rb_entry(next, struct map, rb_node);
-			next = rb_next(&pos->rb_node);
-			rb_erase(&pos->rb_node, root);
-			/*
-			 * We may have references to this map, for
-			 * instance in some hist_entry instances, so
-			 * just move them to a separate list.
-			 */
-			list_add_tail(&pos->node, &self->removed_maps[pos->type]);
-		}
-	}
-}
-
 int thread__set_comm(struct thread *self, const char *comm)
 {
 	int err;
@@ -79,69 +79,10 @@ int thread__comm_len(struct thread *self)
 	return self->comm_len;
 }
 
-size_t __map_groups__fprintf_maps(struct map_groups *self,
-				  enum map_type type, FILE *fp)
-{
-	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
-	struct rb_node *nd;
-
-	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node);
-		printed += fprintf(fp, "Map:");
-		printed += map__fprintf(pos, fp);
-		if (verbose > 2) {
-			printed += dso__fprintf(pos->dso, type, fp);
-			printed += fprintf(fp, "--\n");
-		}
-	}
-
-	return printed;
-}
-
-size_t map_groups__fprintf_maps(struct map_groups *self, FILE *fp)
-{
-	size_t printed = 0, i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_maps(self, i, fp);
-	return printed;
-}
-
-static size_t __map_groups__fprintf_removed_maps(struct map_groups *self,
-						 enum map_type type, FILE *fp)
-{
-	struct map *pos;
-	size_t printed = 0;
-
-	list_for_each_entry(pos, &self->removed_maps[type], node) {
-		printed += fprintf(fp, "Map:");
-		printed += map__fprintf(pos, fp);
-		if (verbose > 1) {
-			printed += dso__fprintf(pos->dso, type, fp);
-			printed += fprintf(fp, "--\n");
-		}
-	}
-	return printed;
-}
-
-static size_t map_groups__fprintf_removed_maps(struct map_groups *self, FILE *fp)
-{
-	size_t printed = 0, i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_removed_maps(self, i, fp);
-	return printed;
-}
-
-static size_t map_groups__fprintf(struct map_groups *self, FILE *fp)
-{
-	size_t printed = map_groups__fprintf_maps(self, fp);
-	printed += fprintf(fp, "Removed maps:\n");
-	return printed + map_groups__fprintf_removed_maps(self, fp);
-}
-
 static size_t thread__fprintf(struct thread *self, FILE *fp)
 {
 	return fprintf(fp, "Thread %d %s\n", self->pid, self->comm) +
-	       map_groups__fprintf(&self->mg, fp);
+	       map_groups__fprintf(&self->mg, verbose, fp);
 }
 
 struct thread *perf_session__findnew(struct perf_session *self, pid_t pid)
@@ -183,127 +124,12 @@ struct thread *perf_session__findnew(struct perf_session *self, pid_t pid)
 	return th;
 }
 
-static int map_groups__fixup_overlappings(struct map_groups *self,
-					  struct map *map)
-{
-	struct rb_root *root = &self->maps[map->type];
-	struct rb_node *next = rb_first(root);
-
-	while (next) {
-		struct map *pos = rb_entry(next, struct map, rb_node);
-		next = rb_next(&pos->rb_node);
-
-		if (!map__overlap(pos, map))
-			continue;
-
-		if (verbose >= 2) {
-			fputs("overlapping maps:\n", stderr);
-			map__fprintf(map, stderr);
-			map__fprintf(pos, stderr);
-		}
-
-		rb_erase(&pos->rb_node, root);
-		/*
-		 * We may have references to this map, for instance in some
-		 * hist_entry instances, so just move them to a separate
-		 * list.
-		 */
-		list_add_tail(&pos->node, &self->removed_maps[map->type]);
-		/*
-		 * Now check if we need to create new maps for areas not
-		 * overlapped by the new map:
-		 */
-		if (map->start > pos->start) {
-			struct map *before = map__clone(pos);
-
-			if (before == NULL)
-				return -ENOMEM;
-
-			before->end = map->start - 1;
-			map_groups__insert(self, before);
-			if (verbose >= 2)
-				map__fprintf(before, stderr);
-		}
-
-		if (map->end < pos->end) {
-			struct map *after = map__clone(pos);
-
-			if (after == NULL)
-				return -ENOMEM;
-
-			after->start = map->end + 1;
-			map_groups__insert(self, after);
-			if (verbose >= 2)
-				map__fprintf(after, stderr);
-		}
-	}
-
-	return 0;
-}
-
-void maps__insert(struct rb_root *maps, struct map *map)
-{
-	struct rb_node **p = &maps->rb_node;
-	struct rb_node *parent = NULL;
-	const u64 ip = map->start;
-	struct map *m;
-
-	while (*p != NULL) {
-		parent = *p;
-		m = rb_entry(parent, struct map, rb_node);
-		if (ip < m->start)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
-
-	rb_link_node(&map->rb_node, parent, p);
-	rb_insert_color(&map->rb_node, maps);
-}
-
-struct map *maps__find(struct rb_root *maps, u64 ip)
-{
-	struct rb_node **p = &maps->rb_node;
-	struct rb_node *parent = NULL;
-	struct map *m;
-
-	while (*p != NULL) {
-		parent = *p;
-		m = rb_entry(parent, struct map, rb_node);
-		if (ip < m->start)
-			p = &(*p)->rb_left;
-		else if (ip > m->end)
-			p = &(*p)->rb_right;
-		else
-			return m;
-	}
-
-	return NULL;
-}
-
 void thread__insert_map(struct thread *self, struct map *map)
 {
-	map_groups__fixup_overlappings(&self->mg, map);
+	map_groups__fixup_overlappings(&self->mg, map, verbose, stderr);
 	map_groups__insert(&self->mg, map);
 }
 
-/*
- * XXX This should not really _copy_ te maps, but refcount them.
- */
-static int map_groups__clone(struct map_groups *self,
-			     struct map_groups *parent, enum map_type type)
-{
-	struct rb_node *nd;
-	for (nd = rb_first(&parent->maps[type]); nd; nd = rb_next(nd)) {
-		struct map *map = rb_entry(nd, struct map, rb_node);
-		struct map *new = map__clone(map);
-		if (new == NULL)
-			return -ENOMEM;
-		map_groups__insert(self, new);
-	}
-	return 0;
-}
-
 int thread__fork(struct thread *self, struct thread *parent)
 {
 	int i;
@@ -336,15 +162,3 @@ size_t perf_session__fprintf(struct perf_session *self, FILE *fp)
 
 	return ret;
 }
-
-struct symbol *map_groups__find_symbol(struct map_groups *self,
-				       enum map_type type, u64 addr,
-				       symbol_filter_t filter)
-{
-	struct map *map = map_groups__find(self, type, addr);
-
-	if (map != NULL)
-		return map__find_symbol(map, map->map_ip(map, addr), filter);
-
-	return NULL;
-}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index dcf70303e58e..9c488fcadec9 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -5,14 +5,6 @@
 #include <unistd.h>
 #include "symbol.h"
 
-struct map_groups {
-	struct rb_root		maps[MAP__NR_TYPES];
-	struct list_head	removed_maps[MAP__NR_TYPES];
-};
-
-size_t __map_groups__fprintf_maps(struct map_groups *self,
-				  enum map_type type, FILE *fp);
-
 struct thread {
 	struct rb_node		rb_node;
 	struct map_groups	mg;
@@ -23,29 +15,16 @@ struct thread {
 	int			comm_len;
 };
 
-void map_groups__init(struct map_groups *self);
+struct perf_session;
+
+int find_all_tid(int pid, pid_t ** all_tid);
 int thread__set_comm(struct thread *self, const char *comm);
 int thread__comm_len(struct thread *self);
 struct thread *perf_session__findnew(struct perf_session *self, pid_t pid);
 void thread__insert_map(struct thread *self, struct map *map);
 int thread__fork(struct thread *self, struct thread *parent);
-size_t map_groups__fprintf_maps(struct map_groups *self, FILE *fp);
 size_t perf_session__fprintf(struct perf_session *self, FILE *fp);
 
-void maps__insert(struct rb_root *maps, struct map *map);
-struct map *maps__find(struct rb_root *maps, u64 addr);
-
-static inline void map_groups__insert(struct map_groups *self, struct map *map)
-{
-	 maps__insert(&self->maps[map->type], map);
-}
-
-static inline struct map *map_groups__find(struct map_groups *self,
-					   enum map_type type, u64 addr)
-{
-	return maps__find(&self->maps[type], addr);
-}
-
 static inline struct map *thread__find_map(struct thread *self,
 					   enum map_type type, u64 addr)
 {
@@ -62,26 +41,4 @@ void thread__find_addr_location(struct thread *self,
 				enum map_type type, u64 addr,
 				struct addr_location *al,
 				symbol_filter_t filter);
-struct symbol *map_groups__find_symbol(struct map_groups *self,
-				       enum map_type type, u64 addr,
-				       symbol_filter_t filter);
-
-static inline struct symbol *map_groups__find_function(struct map_groups *self,
-						       u64 addr,
-						       symbol_filter_t filter)
-{
-	return map_groups__find_symbol(self, MAP__FUNCTION, addr, filter);
-}
-
-struct map *map_groups__find_by_name(struct map_groups *self,
-				     enum map_type type, const char *name);
-
-int __map_groups__create_kernel_maps(struct map_groups *self,
-				     struct map *vmlinux_maps[MAP__NR_TYPES],
-				     struct dso *kernel);
-int map_groups__create_kernel_maps(struct map_groups *self,
-				   struct map *vmlinux_maps[MAP__NR_TYPES]);
-
-struct map *map_groups__new_module(struct map_groups *self, u64 start,
-				   const char *filename);
 #endif	/* __PERF_THREAD_H */
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 9b3c20f42f98..3b81250ffedb 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -37,6 +37,8 @@ int header_page_ts_offset;
 int header_page_ts_size;
 int header_page_size_offset;
 int header_page_size_size;
+int header_page_overwrite_offset;
+int header_page_overwrite_size;
 int header_page_data_offset;
 int header_page_data_size;
 
@@ -628,23 +630,32 @@ static int test_type(enum event_type type, enum event_type expect)
 	return 0;
 }
 
-static int test_type_token(enum event_type type, char *token,
-		    enum event_type expect, const char *expect_tok)
+static int __test_type_token(enum event_type type, char *token,
+			     enum event_type expect, const char *expect_tok,
+			     bool warn)
 {
 	if (type != expect) {
-		warning("Error: expected type %d but read %d",
-		    expect, type);
+		if (warn)
+			warning("Error: expected type %d but read %d",
+				expect, type);
 		return -1;
 	}
 
 	if (strcmp(token, expect_tok) != 0) {
-		warning("Error: expected '%s' but read '%s'",
-		    expect_tok, token);
+		if (warn)
+			warning("Error: expected '%s' but read '%s'",
+				expect_tok, token);
 		return -1;
 	}
 	return 0;
 }
 
+static int test_type_token(enum event_type type, char *token,
+			   enum event_type expect, const char *expect_tok)
+{
+	return __test_type_token(type, token, expect, expect_tok, true);
+}
+
 static int __read_expect_type(enum event_type expect, char **tok, int newline_ok)
 {
 	enum event_type type;
@@ -661,7 +672,8 @@ static int read_expect_type(enum event_type expect, char **tok)
 	return __read_expect_type(expect, tok, 1);
 }
 
-static int __read_expected(enum event_type expect, const char *str, int newline_ok)
+static int __read_expected(enum event_type expect, const char *str,
+			   int newline_ok, bool warn)
 {
 	enum event_type type;
 	char *token;
@@ -672,21 +684,26 @@ static int __read_expected(enum event_type expect, const char *str, int newline_
 	else
 		type = read_token_item(&token);
 
-	ret = test_type_token(type, token, expect, str);
+	ret = __test_type_token(type, token, expect, str, warn);
 
 	free_token(token);
 
 	return ret;
 }
 
+static int read_expected_warn(enum event_type expect, const char *str, bool warn)
+{
+	return __read_expected(expect, str, 1, warn);
+}
+
 static int read_expected(enum event_type expect, const char *str)
 {
-	return __read_expected(expect, str, 1);
+	return __read_expected(expect, str, 1, true);
 }
 
 static int read_expected_item(enum event_type expect, const char *str)
 {
-	return __read_expected(expect, str, 0);
+	return __read_expected(expect, str, 0, true);
 }
 
 static char *event_read_name(void)
@@ -3088,7 +3105,7 @@ static void print_args(struct print_arg *args)
 }
 
 static void parse_header_field(const char *field,
-			       int *offset, int *size)
+			       int *offset, int *size, bool warn)
 {
 	char *token;
 	int type;
@@ -3103,7 +3120,7 @@ static void parse_header_field(const char *field,
 		goto fail;
 	free_token(token);
 
-	if (read_expected(EVENT_ITEM, field) < 0)
+	if (read_expected_warn(EVENT_ITEM, field, warn) < 0)
 		return;
 	if (read_expected(EVENT_OP, ";") < 0)
 		return;
@@ -3160,11 +3177,13 @@ int parse_header_page(char *buf, unsigned long size)
 	init_input_buf(buf, size);
 
 	parse_header_field("timestamp", &header_page_ts_offset,
-			   &header_page_ts_size);
+			   &header_page_ts_size, true);
 	parse_header_field("commit", &header_page_size_offset,
-			   &header_page_size_size);
+			   &header_page_size_size, true);
+	parse_header_field("overwrite", &header_page_overwrite_offset,
+			   &header_page_overwrite_size, false);
 	parse_header_field("data", &header_page_data_offset,
-			   &header_page_data_size);
+			   &header_page_data_size, true);
 
 	return 0;
 }
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 0f5b2a6f1080..fbf45d1b26f7 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -42,12 +42,14 @@
 #define _ALL_SOURCE 1
 #define _GNU_SOURCE 1
 #define _BSD_SOURCE 1
+#define HAS_BOOL
 
 #include <unistd.h>
 #include <stdio.h>
 #include <sys/stat.h>
 #include <sys/statfs.h>
 #include <fcntl.h>
+#include <stdbool.h>
 #include <stddef.h>
 #include <stdlib.h>
 #include <stdarg.h>
@@ -78,6 +80,7 @@
 #include <pwd.h>
 #include <inttypes.h>
 #include "../../../include/linux/magic.h"
+#include "types.h"
 
 
 #ifndef NO_ICONV
@@ -295,6 +298,13 @@ extern void *xmemdupz(const void *data, size_t len);
 extern char *xstrndup(const char *str, size_t len);
 extern void *xrealloc(void *ptr, size_t size) __attribute__((weak));
 
+static inline void *xzalloc(size_t size)
+{
+	void *buf = xmalloc(size);
+
+	return memset(buf, 0, size);
+}
+
 static inline void *zalloc(size_t size)
 {
 	return calloc(1, size);
@@ -309,6 +319,7 @@ static inline int has_extension(const char *filename, const char *ext)
 {
 	size_t len = strlen(filename);
 	size_t extlen = strlen(ext);
+
 	return len > extlen && !memcmp(filename + len - extlen, ext, extlen);
 }
 
@@ -322,6 +333,7 @@ static inline int has_extension(const char *filename, const char *ext)
 #undef isalnum
 #undef tolower
 #undef toupper
+
 extern unsigned char sane_ctype[256];
 #define GIT_SPACE		0x01
 #define GIT_DIGIT		0x02
@@ -406,4 +418,13 @@ void git_qsort(void *base, size_t nmemb, size_t size,
 int mkdir_p(char *path, mode_t mode);
 int copyfile(const char *from, const char *to);
 
+s64 perf_atoll(const char *str);
+char **argv_split(const char *str, int *argcp);
+void argv_free(char **argv);
+bool strglobmatch(const char *str, const char *pat);
+bool strlazymatch(const char *str, const char *pat);
+
+#define _STR(x) #x
+#define STR(x) _STR(x)
+
 #endif