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

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

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

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

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

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

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

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

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

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

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

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

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

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

	struct static_key key = STATIC_KEY_INIT_FALSE;

	...

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

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

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

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

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

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

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

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

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

 - 'perf bench' improvements

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

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

14 files changed, 1540 insertions, 683 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 5369059c07a..532d2e090e6 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -69,6 +69,7 @@ obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
+obj-$(CONFIG_OPTPROBES)		+= kprobes-opt.o
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault_32.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f4773f4aae3..0a44b90602b 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -5,6 +5,7 @@
 #include <linux/mm.h>
 
 #include <linux/io.h>
+#include <linux/sched.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cpu.h>
@@ -456,6 +457,8 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+		if (!check_tsc_unstable())
+			sched_clock_stable = 1;
 	}
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 5adce1040b1..0a18d16cb58 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/bitops.h>
+#include <linux/device.h>
 
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
@@ -31,6 +32,7 @@
 #include <asm/compat.h>
 #include <asm/smp.h>
 #include <asm/alternative.h>
+#include <asm/timer.h>
 
 #include "perf_event.h"
 
@@ -351,6 +353,36 @@ int x86_setup_perfctr(struct perf_event *event)
 	return 0;
 }
 
+/*
+ * check that branch_sample_type is compatible with
+ * settings needed for precise_ip > 1 which implies
+ * using the LBR to capture ALL taken branches at the
+ * priv levels of the measurement
+ */
+static inline int precise_br_compat(struct perf_event *event)
+{
+	u64 m = event->attr.branch_sample_type;
+	u64 b = 0;
+
+	/* must capture all branches */
+	if (!(m & PERF_SAMPLE_BRANCH_ANY))
+		return 0;
+
+	m &= PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_USER;
+
+	if (!event->attr.exclude_user)
+		b |= PERF_SAMPLE_BRANCH_USER;
+
+	if (!event->attr.exclude_kernel)
+		b |= PERF_SAMPLE_BRANCH_KERNEL;
+
+	/*
+	 * ignore PERF_SAMPLE_BRANCH_HV, not supported on x86
+	 */
+
+	return m == b;
+}
+
 int x86_pmu_hw_config(struct perf_event *event)
 {
 	if (event->attr.precise_ip) {
@@ -367,6 +399,36 @@ int x86_pmu_hw_config(struct perf_event *event)
 
 		if (event->attr.precise_ip > precise)
 			return -EOPNOTSUPP;
+		/*
+		 * check that PEBS LBR correction does not conflict with
+		 * whatever the user is asking with attr->branch_sample_type
+		 */
+		if (event->attr.precise_ip > 1) {
+			u64 *br_type = &event->attr.branch_sample_type;
+
+			if (has_branch_stack(event)) {
+				if (!precise_br_compat(event))
+					return -EOPNOTSUPP;
+
+				/* branch_sample_type is compatible */
+
+			} else {
+				/*
+				 * user did not specify  branch_sample_type
+				 *
+				 * For PEBS fixups, we capture all
+				 * the branches at the priv level of the
+				 * event.
+				 */
+				*br_type = PERF_SAMPLE_BRANCH_ANY;
+
+				if (!event->attr.exclude_user)
+					*br_type |= PERF_SAMPLE_BRANCH_USER;
+
+				if (!event->attr.exclude_kernel)
+					*br_type |= PERF_SAMPLE_BRANCH_KERNEL;
+			}
+		}
 	}
 
 	/*
@@ -424,6 +486,10 @@ static int __x86_pmu_event_init(struct perf_event *event)
 	/* mark unused */
 	event->hw.extra_reg.idx = EXTRA_REG_NONE;
 
+	/* mark not used */
+	event->hw.extra_reg.idx = EXTRA_REG_NONE;
+	event->hw.branch_reg.idx = EXTRA_REG_NONE;
+
 	return x86_pmu.hw_config(event);
 }
 
@@ -1210,6 +1276,8 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 		break;
 
 	case CPU_STARTING:
+		if (x86_pmu.attr_rdpmc)
+			set_in_cr4(X86_CR4_PCE);
 		if (x86_pmu.cpu_starting)
 			x86_pmu.cpu_starting(cpu);
 		break;
@@ -1319,6 +1387,8 @@ static int __init init_hw_perf_events(void)
 		}
 	}
 
+	x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
+
 	pr_info("... version:                %d\n",     x86_pmu.version);
 	pr_info("... bit width:              %d\n",     x86_pmu.cntval_bits);
 	pr_info("... generic registers:      %d\n",     x86_pmu.num_counters);
@@ -1542,23 +1612,106 @@ static int x86_pmu_event_init(struct perf_event *event)
 	return err;
 }
 
+static int x86_pmu_event_idx(struct perf_event *event)
+{
+	int idx = event->hw.idx;
+
+	if (x86_pmu.num_counters_fixed && idx >= X86_PMC_IDX_FIXED) {
+		idx -= X86_PMC_IDX_FIXED;
+		idx |= 1 << 30;
+	}
+
+	return idx + 1;
+}
+
+static ssize_t get_attr_rdpmc(struct device *cdev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	return snprintf(buf, 40, "%d\n", x86_pmu.attr_rdpmc);
+}
+
+static void change_rdpmc(void *info)
+{
+	bool enable = !!(unsigned long)info;
+
+	if (enable)
+		set_in_cr4(X86_CR4_PCE);
+	else
+		clear_in_cr4(X86_CR4_PCE);
+}
+
+static ssize_t set_attr_rdpmc(struct device *cdev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	unsigned long val = simple_strtoul(buf, NULL, 0);
+
+	if (!!val != !!x86_pmu.attr_rdpmc) {
+		x86_pmu.attr_rdpmc = !!val;
+		smp_call_function(change_rdpmc, (void *)val, 1);
+	}
+
+	return count;
+}
+
+static DEVICE_ATTR(rdpmc, S_IRUSR | S_IWUSR, get_attr_rdpmc, set_attr_rdpmc);
+
+static struct attribute *x86_pmu_attrs[] = {
+	&dev_attr_rdpmc.attr,
+	NULL,
+};
+
+static struct attribute_group x86_pmu_attr_group = {
+	.attrs = x86_pmu_attrs,
+};
+
+static const struct attribute_group *x86_pmu_attr_groups[] = {
+	&x86_pmu_attr_group,
+	NULL,
+};
+
+static void x86_pmu_flush_branch_stack(void)
+{
+	if (x86_pmu.flush_branch_stack)
+		x86_pmu.flush_branch_stack();
+}
+
 static struct pmu pmu = {
-	.pmu_enable	= x86_pmu_enable,
-	.pmu_disable	= x86_pmu_disable,
+	.pmu_enable		= x86_pmu_enable,
+	.pmu_disable		= x86_pmu_disable,
+
+	.attr_groups	= x86_pmu_attr_groups,
 
 	.event_init	= x86_pmu_event_init,
 
-	.add		= x86_pmu_add,
-	.del		= x86_pmu_del,
-	.start		= x86_pmu_start,
-	.stop		= x86_pmu_stop,
-	.read		= x86_pmu_read,
+	.add			= x86_pmu_add,
+	.del			= x86_pmu_del,
+	.start			= x86_pmu_start,
+	.stop			= x86_pmu_stop,
+	.read			= x86_pmu_read,
 
 	.start_txn	= x86_pmu_start_txn,
 	.cancel_txn	= x86_pmu_cancel_txn,
 	.commit_txn	= x86_pmu_commit_txn,
+
+	.event_idx	= x86_pmu_event_idx,
+	.flush_branch_stack	= x86_pmu_flush_branch_stack,
 };
 
+void perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)
+{
+	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+		return;
+
+	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+		return;
+
+	userpg->time_mult = this_cpu_read(cyc2ns);
+	userpg->time_shift = CYC2NS_SCALE_FACTOR;
+	userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
+}
+
 /*
  * callchain support
  */
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index c30c807ddc7..8484e77c211 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -33,6 +33,7 @@ enum extra_reg_type {
 
 	EXTRA_REG_RSP_0 = 0,	/* offcore_response_0 */
 	EXTRA_REG_RSP_1 = 1,	/* offcore_response_1 */
+	EXTRA_REG_LBR   = 2,	/* lbr_select */
 
 	EXTRA_REG_MAX		/* number of entries needed */
 };
@@ -130,6 +131,8 @@ struct cpu_hw_events {
 	void				*lbr_context;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
+	struct er_account		*lbr_sel;
+	u64				br_sel;
 
 	/*
 	 * Intel host/guest exclude bits
@@ -268,6 +271,29 @@ struct x86_pmu_quirk {
 	void (*func)(void);
 };
 
+union x86_pmu_config {
+	struct {
+		u64 event:8,
+		    umask:8,
+		    usr:1,
+		    os:1,
+		    edge:1,
+		    pc:1,
+		    interrupt:1,
+		    __reserved1:1,
+		    en:1,
+		    inv:1,
+		    cmask:8,
+		    event2:4,
+		    __reserved2:4,
+		    go:1,
+		    ho:1;
+	} bits;
+	u64 value;
+};
+
+#define X86_CONFIG(args...) ((union x86_pmu_config){.bits = {args}}).value
+
 /*
  * struct x86_pmu - generic x86 pmu
  */
@@ -309,10 +335,19 @@ struct x86_pmu {
 	struct x86_pmu_quirk *quirks;
 	int		perfctr_second_write;
 
+	/*
+	 * sysfs attrs
+	 */
+	int		attr_rdpmc;
+
+	/*
+	 * CPU Hotplug hooks
+	 */
 	int		(*cpu_prepare)(int cpu);
 	void		(*cpu_starting)(int cpu);
 	void		(*cpu_dying)(int cpu);
 	void		(*cpu_dead)(int cpu);
+	void		(*flush_branch_stack)(void);
 
 	/*
 	 * Intel Arch Perfmon v2+
@@ -334,6 +369,8 @@ struct x86_pmu {
 	 */
 	unsigned long	lbr_tos, lbr_from, lbr_to; /* MSR base regs       */
 	int		lbr_nr;			   /* hardware stack size */
+	u64		lbr_sel_mask;		   /* LBR_SELECT valid bits */
+	const int	*lbr_sel_map;		   /* lbr_select mappings */
 
 	/*
 	 * Extra registers for events
@@ -447,6 +484,15 @@ extern struct event_constraint emptyconstraint;
 
 extern struct event_constraint unconstrained;
 
+static inline bool kernel_ip(unsigned long ip)
+{
+#ifdef CONFIG_X86_32
+	return ip > PAGE_OFFSET;
+#else
+	return (long)ip < 0;
+#endif
+}
+
 #ifdef CONFIG_CPU_SUP_AMD
 
 int amd_pmu_init(void);
@@ -527,6 +573,10 @@ void intel_pmu_lbr_init_nhm(void);
 
 void intel_pmu_lbr_init_atom(void);
 
+void intel_pmu_lbr_init_snb(void);
+
+int intel_pmu_setup_lbr_filter(struct perf_event *event);
+
 int p4_pmu_init(void);
 
 int p6_pmu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 67250a52430..dd002faff7a 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -139,6 +139,9 @@ static int amd_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	if (event->attr.exclude_host && event->attr.exclude_guest)
 		/*
 		 * When HO == GO == 1 the hardware treats that as GO == HO == 0
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 61d4f79a550..6a84e7f28f0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -728,6 +728,19 @@ static __initconst const u64 atom_hw_cache_event_ids
  },
 };
 
+static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
+{
+	/* user explicitly requested branch sampling */
+	if (has_branch_stack(event))
+		return true;
+
+	/* implicit branch sampling to correct PEBS skid */
+	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
+		return true;
+
+	return false;
+}
+
 static void intel_pmu_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -882,6 +895,13 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 
+	/*
+	 * must disable before any actual event
+	 * because any event may be combined with LBR
+	 */
+	if (intel_pmu_needs_lbr_smpl(event))
+		intel_pmu_lbr_disable(event);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
@@ -936,6 +956,12 @@ static void intel_pmu_enable_event(struct perf_event *event)
 		intel_pmu_enable_bts(hwc->config);
 		return;
 	}
+	/*
+	 * must enabled before any actual event
+	 * because any event may be combined with LBR
+	 */
+	if (intel_pmu_needs_lbr_smpl(event))
+		intel_pmu_lbr_enable(event);
 
 	if (event->attr.exclude_host)
 		cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
@@ -1058,6 +1084,9 @@ again:
 
 		data.period = event->hw.last_period;
 
+		if (has_branch_stack(event))
+			data.br_stack = &cpuc->lbr_stack;
+
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
 	}
@@ -1124,17 +1153,17 @@ static bool intel_try_alt_er(struct perf_event *event, int orig_idx)
  */
 static struct event_constraint *
 __intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc,
-				   struct perf_event *event)
+				   struct perf_event *event,
+				   struct hw_perf_event_extra *reg)
 {
 	struct event_constraint *c = &emptyconstraint;
-	struct hw_perf_event_extra *reg = &event->hw.extra_reg;
 	struct er_account *era;
 	unsigned long flags;
 	int orig_idx = reg->idx;
 
 	/* already allocated shared msr */
 	if (reg->alloc)
-		return &unconstrained;
+		return NULL; /* call x86_get_event_constraint() */
 
 again:
 	era = &cpuc->shared_regs->regs[reg->idx];
@@ -1157,14 +1186,10 @@ again:
 		reg->alloc = 1;
 
 		/*
-		 * All events using extra_reg are unconstrained.
-		 * Avoids calling x86_get_event_constraints()
-		 *
-		 * Must revisit if extra_reg controlling events
-		 * ever have constraints. Worst case we go through
-		 * the regular event constraint table.
+		 * need to call x86_get_event_constraint()
+		 * to check if associated event has constraints
 		 */
-		c = &unconstrained;
+		c = NULL;
 	} else if (intel_try_alt_er(event, orig_idx)) {
 		raw_spin_unlock_irqrestore(&era->lock, flags);
 		goto again;
@@ -1201,11 +1226,23 @@ static struct event_constraint *
 intel_shared_regs_constraints(struct cpu_hw_events *cpuc,
 			      struct perf_event *event)
 {
-	struct event_constraint *c = NULL;
-
-	if (event->hw.extra_reg.idx != EXTRA_REG_NONE)
-		c = __intel_shared_reg_get_constraints(cpuc, event);
-
+	struct event_constraint *c = NULL, *d;
+	struct hw_perf_event_extra *xreg, *breg;
+
+	xreg = &event->hw.extra_reg;
+	if (xreg->idx != EXTRA_REG_NONE) {
+		c = __intel_shared_reg_get_constraints(cpuc, event, xreg);
+		if (c == &emptyconstraint)
+			return c;
+	}
+	breg = &event->hw.branch_reg;
+	if (breg->idx != EXTRA_REG_NONE) {
+		d = __intel_shared_reg_get_constraints(cpuc, event, breg);
+		if (d == &emptyconstraint) {
+			__intel_shared_reg_put_constraints(cpuc, xreg);
+			c = d;
+		}
+	}
 	return c;
 }
 
@@ -1253,6 +1290,10 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc,
 	reg = &event->hw.extra_reg;
 	if (reg->idx != EXTRA_REG_NONE)
 		__intel_shared_reg_put_constraints(cpuc, reg);
+
+	reg = &event->hw.branch_reg;
+	if (reg->idx != EXTRA_REG_NONE)
+		__intel_shared_reg_put_constraints(cpuc, reg);
 }
 
 static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
@@ -1288,12 +1329,19 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		 *
 		 * Thereby we gain a PEBS capable cycle counter.
 		 */
-		u64 alt_config = 0x108000c0; /* INST_RETIRED.TOTAL_CYCLES */
+		u64 alt_config = X86_CONFIG(.event=0xc0, .inv=1, .cmask=16);
+
 
 		alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
 		event->hw.config = alt_config;
 	}
 
+	if (intel_pmu_needs_lbr_smpl(event)) {
+		ret = intel_pmu_setup_lbr_filter(event);
+		if (ret)
+			return ret;
+	}
+
 	if (event->attr.type != PERF_TYPE_RAW)
 		return 0;
 
@@ -1432,7 +1480,7 @@ static int intel_pmu_cpu_prepare(int cpu)
 {
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
 
-	if (!x86_pmu.extra_regs)
+	if (!(x86_pmu.extra_regs || x86_pmu.lbr_sel_map))
 		return NOTIFY_OK;
 
 	cpuc->shared_regs = allocate_shared_regs(cpu);
@@ -1454,22 +1502,28 @@ static void intel_pmu_cpu_starting(int cpu)
 	 */
 	intel_pmu_lbr_reset();
 
-	if (!cpuc->shared_regs || (x86_pmu.er_flags & ERF_NO_HT_SHARING))
+	cpuc->lbr_sel = NULL;
+
+	if (!cpuc->shared_regs)
 		return;
 
-	for_each_cpu(i, topology_thread_cpumask(cpu)) {
-		struct intel_shared_regs *pc;
+	if (!(x86_pmu.er_flags & ERF_NO_HT_SHARING)) {
+		for_each_cpu(i, topology_thread_cpumask(cpu)) {
+			struct intel_shared_regs *pc;
 
-		pc = per_cpu(cpu_hw_events, i).shared_regs;
-		if (pc && pc->core_id == core_id) {
-			cpuc->kfree_on_online = cpuc->shared_regs;
-			cpuc->shared_regs = pc;
-			break;
+			pc = per_cpu(cpu_hw_events, i).shared_regs;
+			if (pc && pc->core_id == core_id) {
+				cpuc->kfree_on_online = cpuc->shared_regs;
+				cpuc->shared_regs = pc;
+				break;
+			}
 		}
+		cpuc->shared_regs->core_id = core_id;
+		cpuc->shared_regs->refcnt++;
 	}
 
-	cpuc->shared_regs->core_id = core_id;
-	cpuc->shared_regs->refcnt++;
+	if (x86_pmu.lbr_sel_map)
+		cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR];
 }
 
 static void intel_pmu_cpu_dying(int cpu)
@@ -1487,6 +1541,18 @@ static void intel_pmu_cpu_dying(int cpu)
 	fini_debug_store_on_cpu(cpu);
 }
 
+static void intel_pmu_flush_branch_stack(void)
+{
+	/*
+	 * Intel LBR does not tag entries with the
+	 * PID of the current task, then we need to
+	 * flush it on ctxsw
+	 * For now, we simply reset it
+	 */
+	if (x86_pmu.lbr_nr)
+		intel_pmu_lbr_reset();
+}
+
 static __initconst const struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,
@@ -1514,6 +1580,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
 	.guest_get_msrs		= intel_guest_get_msrs,
+	.flush_branch_stack	= intel_pmu_flush_branch_stack,
 };
 
 static __init void intel_clovertown_quirk(void)
@@ -1690,9 +1757,11 @@ __init int intel_pmu_init(void)
 		x86_pmu.extra_regs = intel_nehalem_extra_regs;
 
 		/* UOPS_ISSUED.STALLED_CYCLES */
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
 		/* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
+			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
 		x86_add_quirk(intel_nehalem_quirk);
 
@@ -1727,9 +1796,11 @@ __init int intel_pmu_init(void)
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 
 		/* UOPS_ISSUED.STALLED_CYCLES */
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
 		/* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
+			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
 		pr_cont("Westmere events, ");
 		break;
@@ -1740,7 +1811,7 @@ __init int intel_pmu_init(void)
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
-		intel_pmu_lbr_init_nhm();
+		intel_pmu_lbr_init_snb();
 
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
@@ -1750,9 +1821,11 @@ __init int intel_pmu_init(void)
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
 
 		/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
 		/* UOPS_DISPATCHED.THREAD,c=1,i=1 to count stall cycles*/
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x18001b1;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
+			X86_CONFIG(.event=0xb1, .umask=0x01, .inv=1, .cmask=1);
 
 		pr_cont("SandyBridge events, ");
 		break;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index d6bd49faa40..7f64df19e7d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -3,6 +3,7 @@
 #include <linux/slab.h>
 
 #include <asm/perf_event.h>
+#include <asm/insn.h>
 
 #include "perf_event.h"
 
@@ -439,9 +440,6 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
-
-	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
-		intel_pmu_lbr_enable(event);
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
@@ -454,9 +452,6 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
 	hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
-
-	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
-		intel_pmu_lbr_disable(event);
 }
 
 void intel_pmu_pebs_enable_all(void)
@@ -475,17 +470,6 @@ void intel_pmu_pebs_disable_all(void)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 }
 
-#include <asm/insn.h>
-
-static inline bool kernel_ip(unsigned long ip)
-{
-#ifdef CONFIG_X86_32
-	return ip > PAGE_OFFSET;
-#else
-	return (long)ip < 0;
-#endif
-}
-
 static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -572,6 +556,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 * both formats and we don't use the other fields in this
 	 * routine.
 	 */
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct pebs_record_core *pebs = __pebs;
 	struct perf_sample_data data;
 	struct pt_regs regs;
@@ -602,6 +587,9 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	else
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 
+	if (has_branch_stack(event))
+		data.br_stack = &cpuc->lbr_stack;
+
 	if (perf_event_overflow(event, &data, &regs))
 		x86_pmu_stop(event, 0);
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 47a7e63bfe5..520b4265fcd 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -3,6 +3,7 @@
 
 #include <asm/perf_event.h>
 #include <asm/msr.h>
+#include <asm/insn.h>
 
 #include "perf_event.h"
 
@@ -14,6 +15,100 @@ enum {
 };
 
 /*
+ * Intel LBR_SELECT bits
+ * Intel Vol3a, April 2011, Section 16.7 Table 16-10
+ *
+ * Hardware branch filter (not available on all CPUs)
+ */
+#define LBR_KERNEL_BIT		0 /* do not capture at ring0 */
+#define LBR_USER_BIT		1 /* do not capture at ring > 0 */
+#define LBR_JCC_BIT		2 /* do not capture conditional branches */
+#define LBR_REL_CALL_BIT	3 /* do not capture relative calls */
+#define LBR_IND_CALL_BIT	4 /* do not capture indirect calls */
+#define LBR_RETURN_BIT		5 /* do not capture near returns */
+#define LBR_IND_JMP_BIT		6 /* do not capture indirect jumps */
+#define LBR_REL_JMP_BIT		7 /* do not capture relative jumps */
+#define LBR_FAR_BIT		8 /* do not capture far branches */
+
+#define LBR_KERNEL	(1 << LBR_KERNEL_BIT)
+#define LBR_USER	(1 << LBR_USER_BIT)
+#define LBR_JCC		(1 << LBR_JCC_BIT)
+#define LBR_REL_CALL	(1 << LBR_REL_CALL_BIT)
+#define LBR_IND_CALL	(1 << LBR_IND_CALL_BIT)
+#define LBR_RETURN	(1 << LBR_RETURN_BIT)
+#define LBR_REL_JMP	(1 << LBR_REL_JMP_BIT)
+#define LBR_IND_JMP	(1 << LBR_IND_JMP_BIT)
+#define LBR_FAR		(1 << LBR_FAR_BIT)
+
+#define LBR_PLM (LBR_KERNEL | LBR_USER)
+
+#define LBR_SEL_MASK	0x1ff	/* valid bits in LBR_SELECT */
+#define LBR_NOT_SUPP	-1	/* LBR filter not supported */
+#define LBR_IGN		0	/* ignored */
+
+#define LBR_ANY		 \
+	(LBR_JCC	|\
+	 LBR_REL_CALL	|\
+	 LBR_IND_CALL	|\
+	 LBR_RETURN	|\
+	 LBR_REL_JMP	|\
+	 LBR_IND_JMP	|\
+	 LBR_FAR)
+
+#define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
+
+#define for_each_branch_sample_type(x) \
+	for ((x) = PERF_SAMPLE_BRANCH_USER; \
+	     (x) < PERF_SAMPLE_BRANCH_MAX; (x) <<= 1)
+
+/*
+ * x86control flow change classification
+ * x86control flow changes include branches, interrupts, traps, faults
+ */
+enum {
+	X86_BR_NONE     = 0,      /* unknown */
+
+	X86_BR_USER     = 1 << 0, /* branch target is user */
+	X86_BR_KERNEL   = 1 << 1, /* branch target is kernel */
+
+	X86_BR_CALL     = 1 << 2, /* call */
+	X86_BR_RET      = 1 << 3, /* return */
+	X86_BR_SYSCALL  = 1 << 4, /* syscall */
+	X86_BR_SYSRET   = 1 << 5, /* syscall return */
+	X86_BR_INT      = 1 << 6, /* sw interrupt */
+	X86_BR_IRET     = 1 << 7, /* return from interrupt */
+	X86_BR_JCC      = 1 << 8, /* conditional */
+	X86_BR_JMP      = 1 << 9, /* jump */
+	X86_BR_IRQ      = 1 << 10,/* hw interrupt or trap or fault */
+	X86_BR_IND_CALL = 1 << 11,/* indirect calls */
+};
+
+#define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
+
+#define X86_BR_ANY       \
+	(X86_BR_CALL    |\
+	 X86_BR_RET     |\
+	 X86_BR_SYSCALL |\
+	 X86_BR_SYSRET  |\
+	 X86_BR_INT     |\
+	 X86_BR_IRET    |\
+	 X86_BR_JCC     |\
+	 X86_BR_JMP	 |\
+	 X86_BR_IRQ	 |\
+	 X86_BR_IND_CALL)
+
+#define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)
+
+#define X86_BR_ANY_CALL		 \
+	(X86_BR_CALL		|\
+	 X86_BR_IND_CALL	|\
+	 X86_BR_SYSCALL		|\
+	 X86_BR_IRQ		|\
+	 X86_BR_INT)
+
+static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);
+
+/*
  * We only support LBR implementations that have FREEZE_LBRS_ON_PMI
  * otherwise it becomes near impossible to get a reliable stack.
  */
@@ -21,6 +116,10 @@ enum {
 static void __intel_pmu_lbr_enable(void)
 {
 	u64 debugctl;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (cpuc->lbr_sel)
+		wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config);
 
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 	debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
@@ -76,11 +175,11 @@ void intel_pmu_lbr_enable(struct perf_event *event)
 	 * Reset the LBR stack if we changed task context to
 	 * avoid data leaks.
 	 */
-
 	if (event->ctx->task && cpuc->lbr_context != event->ctx) {
 		intel_pmu_lbr_reset();
 		cpuc->lbr_context = event->ctx;
 	}
+	cpuc->br_sel = event->hw.branch_reg.reg;
 
 	cpuc->lbr_users++;
 }
@@ -95,8 +194,11 @@ void intel_pmu_lbr_disable(struct perf_event *event)
 	cpuc->lbr_users--;
 	WARN_ON_ONCE(cpuc->lbr_users < 0);
 
-	if (cpuc->enabled && !cpuc->lbr_users)
+	if (cpuc->enabled && !cpuc->lbr_users) {
 		__intel_pmu_lbr_disable();
+		/* avoid stale pointer */
+		cpuc->lbr_context = NULL;
+	}
 }
 
 void intel_pmu_lbr_enable_all(void)
@@ -115,6 +217,9 @@ void intel_pmu_lbr_disable_all(void)
 		__intel_pmu_lbr_disable();
 }
 
+/*
+ * TOS = most recently recorded branch
+ */
 static inline u64 intel_pmu_lbr_tos(void)
 {
 	u64 tos;
@@ -142,15 +247,15 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
 
-		cpuc->lbr_entries[i].from  = msr_lastbranch.from;
-		cpuc->lbr_entries[i].to    = msr_lastbranch.to;
-		cpuc->lbr_entries[i].flags = 0;
+		cpuc->lbr_entries[i].from	= msr_lastbranch.from;
+		cpuc->lbr_entries[i].to		= msr_lastbranch.to;
+		cpuc->lbr_entries[i].mispred	= 0;
+		cpuc->lbr_entries[i].predicted	= 0;
+		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
 }
 
-#define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
-
 /*
  * Due to lack of segmentation in Linux the effective address (offset)
  * is the same as the linear address, allowing us to merge the LIP and EIP
@@ -165,19 +270,22 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 
 	for (i = 0; i < x86_pmu.lbr_nr; i++) {
 		unsigned long lbr_idx = (tos - i) & mask;
-		u64 from, to, flags = 0;
+		u64 from, to, mis = 0, pred = 0;
 
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
 		rdmsrl(x86_pmu.lbr_to   + lbr_idx, to);
 
 		if (lbr_format == LBR_FORMAT_EIP_FLAGS) {
-			flags = !!(from & LBR_FROM_FLAG_MISPRED);
+			mis = !!(from & LBR_FROM_FLAG_MISPRED);
+			pred = !mis;
 			from = (u64)((((s64)from) << 1) >> 1);
 		}
 
-		cpuc->lbr_entries[i].from  = from;
-		cpuc->lbr_entries[i].to    = to;
-		cpuc->lbr_entries[i].flags = flags;
+		cpuc->lbr_entries[i].from	= from;
+		cpuc->lbr_entries[i].to		= to;
+		cpuc->lbr_entries[i].mispred	= mis;
+		cpuc->lbr_entries[i].predicted	= pred;
+		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
 }
@@ -193,28 +301,404 @@ void intel_pmu_lbr_read(void)
 		intel_pmu_lbr_read_32(cpuc);
 	else
 		intel_pmu_lbr_read_64(cpuc);
+
+	intel_pmu_lbr_filter(cpuc);
+}
+
+/*
+ * SW filter is used:
+ * - in case there is no HW filter
+ * - in case the HW filter has errata or limitations
+ */
+static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
+{
+	u64 br_type = event->attr.branch_sample_type;
+	int mask = 0;
+
+	if (br_type & PERF_SAMPLE_BRANCH_USER)
+		mask |= X86_BR_USER;
+
+	if (br_type & PERF_SAMPLE_BRANCH_KERNEL)
+		mask |= X86_BR_KERNEL;
+
+	/* we ignore BRANCH_HV here */
+
+	if (br_type & PERF_SAMPLE_BRANCH_ANY)
+		mask |= X86_BR_ANY;
+
+	if (br_type & PERF_SAMPLE_BRANCH_ANY_CALL)
+		mask |= X86_BR_ANY_CALL;
+
+	if (br_type & PERF_SAMPLE_BRANCH_ANY_RETURN)
+		mask |= X86_BR_RET | X86_BR_IRET | X86_BR_SYSRET;
+
+	if (br_type & PERF_SAMPLE_BRANCH_IND_CALL)
+		mask |= X86_BR_IND_CALL;
+	/*
+	 * stash actual user request into reg, it may
+	 * be used by fixup code for some CPU
+	 */
+	event->hw.branch_reg.reg = mask;
+}
+
+/*
+ * setup the HW LBR filter
+ * Used only when available, may not be enough to disambiguate
+ * all branches, may need the help of the SW filter
+ */
+static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg;
+	u64 br_type = event->attr.branch_sample_type;
+	u64 mask = 0, m;
+	u64 v;
+
+	for_each_branch_sample_type(m) {
+		if (!(br_type & m))
+			continue;
+
+		v = x86_pmu.lbr_sel_map[m];
+		if (v == LBR_NOT_SUPP)
+			return -EOPNOTSUPP;
+
+		if (v != LBR_IGN)
+			mask |= v;
+	}
+	reg = &event->hw.branch_reg;
+	reg->idx = EXTRA_REG_LBR;
+
+	/* LBR_SELECT operates in suppress mode so invert mask */
+	reg->config = ~mask & x86_pmu.lbr_sel_mask;
+
+	return 0;
+}
+
+int intel_pmu_setup_lbr_filter(struct perf_event *event)
+{
+	int ret = 0;
+
+	/*
+	 * no LBR on this PMU
+	 */
+	if (!x86_pmu.lbr_nr)
+		return -EOPNOTSUPP;
+
+	/*
+	 * setup SW LBR filter
+	 */
+	intel_pmu_setup_sw_lbr_filter(event);
+
+	/*
+	 * setup HW LBR filter, if any
+	 */
+	if (x86_pmu.lbr_sel_map)
+		ret = intel_pmu_setup_hw_lbr_filter(event);
+
+	return ret;
 }
 
+/*
+ * return the type of control flow change at address "from"
+ * intruction is not necessarily a branch (in case of interrupt).
+ *
+ * The branch type returned also includes the priv level of the
+ * target of the control flow change (X86_BR_USER, X86_BR_KERNEL).
+ *
+ * If a branch type is unknown OR the instruction cannot be
+ * decoded (e.g., text page not present), then X86_BR_NONE is
+ * returned.
+ */
+static int branch_type(unsigned long from, unsigned long to)
+{
+	struct insn insn;
+	void *addr;
+	int bytes, size = MAX_INSN_SIZE;
+	int ret = X86_BR_NONE;
+	int ext, to_plm, from_plm;
+	u8 buf[MAX_INSN_SIZE];
+	int is64 = 0;
+
+	to_plm = kernel_ip(to) ? X86_BR_KERNEL : X86_BR_USER;
+	from_plm = kernel_ip(from) ? X86_BR_KERNEL : X86_BR_USER;
+
+	/*
+	 * maybe zero if lbr did not fill up after a reset by the time
+	 * we get a PMU interrupt
+	 */
+	if (from == 0 || to == 0)
+		return X86_BR_NONE;
+
+	if (from_plm == X86_BR_USER) {
+		/*
+		 * can happen if measuring at the user level only
+		 * and we interrupt in a kernel thread, e.g., idle.
+		 */
+		if (!current->mm)
+			return X86_BR_NONE;
+
+		/* may fail if text not present */
+		bytes = copy_from_user_nmi(buf, (void __user *)from, size);
+		if (bytes != size)
+			return X86_BR_NONE;
+
+		addr = buf;
+	} else
+		addr = (void *)from;
+
+	/*
+	 * decoder needs to know the ABI especially
+	 * on 64-bit systems running 32-bit apps
+	 */
+#ifdef CONFIG_X86_64
+	is64 = kernel_ip((unsigned long)addr) || !test_thread_flag(TIF_IA32);
+#endif
+	insn_init(&insn, addr, is64);
+	insn_get_opcode(&insn);
+
+	switch (insn.opcode.bytes[0]) {
+	case 0xf:
+		switch (insn.opcode.bytes[1]) {
+		case 0x05: /* syscall */
+		case 0x34: /* sysenter */
+			ret = X86_BR_SYSCALL;
+			break;
+		case 0x07: /* sysret */
+		case 0x35: /* sysexit */
+			ret = X86_BR_SYSRET;
+			break;
+		case 0x80 ... 0x8f: /* conditional */
+			ret = X86_BR_JCC;
+			break;
+		default:
+			ret = X86_BR_NONE;
+		}
+		break;
+	case 0x70 ... 0x7f: /* conditional */
+		ret = X86_BR_JCC;
+		break;
+	case 0xc2: /* near ret */
+	case 0xc3: /* near ret */
+	case 0xca: /* far ret */
+	case 0xcb: /* far ret */
+		ret = X86_BR_RET;
+		break;
+	case 0xcf: /* iret */
+		ret = X86_BR_IRET;
+		break;
+	case 0xcc ... 0xce: /* int */
+		ret = X86_BR_INT;
+		break;
+	case 0xe8: /* call near rel */
+	case 0x9a: /* call far absolute */
+		ret = X86_BR_CALL;
+		break;
+	case 0xe0 ... 0xe3: /* loop jmp */
+		ret = X86_BR_JCC;
+		break;
+	case 0xe9 ... 0xeb: /* jmp */
+		ret = X86_BR_JMP;
+		break;
+	case 0xff: /* call near absolute, call far absolute ind */
+		insn_get_modrm(&insn);
+		ext = (insn.modrm.bytes[0] >> 3) & 0x7;
+		switch (ext) {
+		case 2: /* near ind call */
+		case 3: /* far ind call */
+			ret = X86_BR_IND_CALL;
+			break;
+		case 4:
+		case 5:
+			ret = X86_BR_JMP;
+			break;
+		}
+		break;
+	default:
+		ret = X86_BR_NONE;
+	}
+	/*
+	 * interrupts, traps, faults (and thus ring transition) may
+	 * occur on any instructions. Thus, to classify them correctly,
+	 * we need to first look at the from and to priv levels. If they
+	 * are different and to is in the kernel, then it indicates
+	 * a ring transition. If the from instruction is not a ring
+	 * transition instr (syscall, systenter, int), then it means
+	 * it was a irq, trap or fault.
+	 *
+	 * we have no way of detecting kernel to kernel faults.
+	 */
+	if (from_plm == X86_BR_USER && to_plm == X86_BR_KERNEL
+	    && ret != X86_BR_SYSCALL && ret != X86_BR_INT)
+		ret = X86_BR_IRQ;
+
+	/*
+	 * branch priv level determined by target as
+	 * is done by HW when LBR_SELECT is implemented
+	 */
+	if (ret != X86_BR_NONE)
+		ret |= to_plm;
+
+	return ret;
+}
+
+/*
+ * implement actual branch filter based on user demand.
+ * Hardware may not exactly satisfy that request, thus
+ * we need to inspect opcodes. Mismatched branches are
+ * discarded. Therefore, the number of branches returned
+ * in PERF_SAMPLE_BRANCH_STACK sample may vary.
+ */
+static void
+intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
+{
+	u64 from, to;
+	int br_sel = cpuc->br_sel;
+	int i, j, type;
+	bool compress = false;
+
+	/* if sampling all branches, then nothing to filter */
+	if ((br_sel & X86_BR_ALL) == X86_BR_ALL)
+		return;
+
+	for (i = 0; i < cpuc->lbr_stack.nr; i++) {
+
+		from = cpuc->lbr_entries[i].from;
+		to = cpuc->lbr_entries[i].to;
+
+		type = branch_type(from, to);
+
+		/* if type does not correspond, then discard */
+		if (type == X86_BR_NONE || (br_sel & type) != type) {
+			cpuc->lbr_entries[i].from = 0;
+			compress = true;
+		}
+	}
+
+	if (!compress)
+		return;
+
+	/* remove all entries with from=0 */
+	for (i = 0; i < cpuc->lbr_stack.nr; ) {
+		if (!cpuc->lbr_entries[i].from) {
+			j = i;
+			while (++j < cpuc->lbr_stack.nr)
+				cpuc->lbr_entries[j-1] = cpuc->lbr_entries[j];
+			cpuc->lbr_stack.nr--;
+			if (!cpuc->lbr_entries[i].from)
+				continue;
+		}
+		i++;
+	}
+}
+
+/*
+ * Map interface branch filters onto LBR filters
+ */
+static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
+	[PERF_SAMPLE_BRANCH_ANY]	= LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER]	= LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL]	= LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN]	= LBR_RETURN | LBR_REL_JMP
+					| LBR_IND_JMP | LBR_FAR,
+	/*
+	 * NHM/WSM erratum: must include REL_JMP+IND_JMP to get CALL branches
+	 */
+	[PERF_SAMPLE_BRANCH_ANY_CALL] =
+	 LBR_REL_CALL | LBR_IND_CALL | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR,
+	/*
+	 * NHM/WSM erratum: must include IND_JMP to capture IND_CALL
+	 */
+	[PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP,
+};
+
+static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
+	[PERF_SAMPLE_BRANCH_ANY]	= LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER]	= LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL]	= LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN]	= LBR_RETURN | LBR_FAR,
+	[PERF_SAMPLE_BRANCH_ANY_CALL]	= LBR_REL_CALL | LBR_IND_CALL
+					| LBR_FAR,
+	[PERF_SAMPLE_BRANCH_IND_CALL]	= LBR_IND_CALL,
+};
+
+/* core */
 void intel_pmu_lbr_init_core(void)
 {
 	x86_pmu.lbr_nr     = 4;
-	x86_pmu.lbr_tos    = 0x01c9;
-	x86_pmu.lbr_from   = 0x40;
-	x86_pmu.lbr_to     = 0x60;
+	x86_pmu.lbr_tos    = MSR_LBR_TOS;
+	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
+	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
+
+	/*
+	 * SW branch filter usage:
+	 * - compensate for lack of HW filter
+	 */
+	pr_cont("4-deep LBR, ");
 }
 
+/* nehalem/westmere */
 void intel_pmu_lbr_init_nhm(void)
 {
 	x86_pmu.lbr_nr     = 16;
-	x86_pmu.lbr_tos    = 0x01c9;
-	x86_pmu.lbr_from   = 0x680;
-	x86_pmu.lbr_to     = 0x6c0;
+	x86_pmu.lbr_tos    = MSR_LBR_TOS;
+	x86_pmu.lbr_from   = MSR_LBR_NHM_FROM;
+	x86_pmu.lbr_to     = MSR_LBR_NHM_TO;
+
+	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
+	x86_pmu.lbr_sel_map  = nhm_lbr_sel_map;
+
+	/*
+	 * SW branch filter usage:
+	 * - workaround LBR_SEL errata (see above)
+	 * - support syscall, sysret capture.
+	 *   That requires LBR_FAR but that means far
+	 *   jmp need to be filtered out
+	 */
+	pr_cont("16-deep LBR, ");
+}
+
+/* sandy bridge */
+void intel_pmu_lbr_init_snb(void)
+{
+	x86_pmu.lbr_nr	 = 16;
+	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
+	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
+	x86_pmu.lbr_to   = MSR_LBR_NHM_TO;
+
+	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
+	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;
+
+	/*
+	 * SW branch filter usage:
+	 * - support syscall, sysret capture.
+	 *   That requires LBR_FAR but that means far
+	 *   jmp need to be filtered out
+	 */
+	pr_cont("16-deep LBR, ");
 }
 
+/* atom */
 void intel_pmu_lbr_init_atom(void)
 {
+	/*
+	 * only models starting at stepping 10 seems
+	 * to have an operational LBR which can freeze
+	 * on PMU interrupt
+	 */
+	if (boot_cpu_data.x86_mask < 10) {
+		pr_cont("LBR disabled due to erratum");
+		return;
+	}
+
 	x86_pmu.lbr_nr	   = 8;
-	x86_pmu.lbr_tos    = 0x01c9;
-	x86_pmu.lbr_from   = 0x40;
-	x86_pmu.lbr_to     = 0x60;
+	x86_pmu.lbr_tos    = MSR_LBR_TOS;
+	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
+	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
+
+	/*
+	 * SW branch filter usage:
+	 * - compensate for lack of HW filter
+	 */
+	pr_cont("8-deep LBR, ");
 }
diff --git a/arch/x86/kernel/kprobes-common.h b/arch/x86/kernel/kprobes-common.h
new file mode 100644
index 00000000000..3230b68ef29
--- /dev/null
+++ b/arch/x86/kernel/kprobes-common.h
@@ -0,0 +1,102 @@
+#ifndef __X86_KERNEL_KPROBES_COMMON_H
+#define __X86_KERNEL_KPROBES_COMMON_H
+
+/* Kprobes and Optprobes common header */
+
+#ifdef CONFIG_X86_64
+#define SAVE_REGS_STRING			\
+	/* Skip cs, ip, orig_ax. */		\
+	"	subq $24, %rsp\n"		\
+	"	pushq %rdi\n"			\
+	"	pushq %rsi\n"			\
+	"	pushq %rdx\n"			\
+	"	pushq %rcx\n"			\
+	"	pushq %rax\n"			\
+	"	pushq %r8\n"			\
+	"	pushq %r9\n"			\
+	"	pushq %r10\n"			\
+	"	pushq %r11\n"			\
+	"	pushq %rbx\n"			\
+	"	pushq %rbp\n"			\
+	"	pushq %r12\n"			\
+	"	pushq %r13\n"			\
+	"	pushq %r14\n"			\
+	"	pushq %r15\n"
+#define RESTORE_REGS_STRING			\
+	"	popq %r15\n"			\
+	"	popq %r14\n"			\
+	"	popq %r13\n"			\
+	"	popq %r12\n"			\
+	"	popq %rbp\n"			\
+	"	popq %rbx\n"			\
+	"	popq %r11\n"			\
+	"	popq %r10\n"			\
+	"	popq %r9\n"			\
+	"	popq %r8\n"			\
+	"	popq %rax\n"			\
+	"	popq %rcx\n"			\
+	"	popq %rdx\n"			\
+	"	popq %rsi\n"			\
+	"	popq %rdi\n"			\
+	/* Skip orig_ax, ip, cs */		\
+	"	addq $24, %rsp\n"
+#else
+#define SAVE_REGS_STRING			\
+	/* Skip cs, ip, orig_ax and gs. */	\
+	"	subl $16, %esp\n"		\
+	"	pushl %fs\n"			\
+	"	pushl %es\n"			\
+	"	pushl %ds\n"			\
+	"	pushl %eax\n"			\
+	"	pushl %ebp\n"			\
+	"	pushl %edi\n"			\
+	"	pushl %esi\n"			\
+	"	pushl %edx\n"			\
+	"	pushl %ecx\n"			\
+	"	pushl %ebx\n"
+#define RESTORE_REGS_STRING			\
+	"	popl %ebx\n"			\
+	"	popl %ecx\n"			\
+	"	popl %edx\n"			\
+	"	popl %esi\n"			\
+	"	popl %edi\n"			\
+	"	popl %ebp\n"			\
+	"	popl %eax\n"			\
+	/* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\
+	"	addl $24, %esp\n"
+#endif
+
+/* Ensure if the instruction can be boostable */
+extern int can_boost(kprobe_opcode_t *instruction);
+/* Recover instruction if given address is probed */
+extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
+					 unsigned long addr);
+/*
+ * Copy an instruction and adjust the displacement if the instruction
+ * uses the %rip-relative addressing mode.
+ */
+extern int __copy_instruction(u8 *dest, u8 *src);
+
+/* Generate a relative-jump/call instruction */
+extern void synthesize_reljump(void *from, void *to);
+extern void synthesize_relcall(void *from, void *to);
+
+#ifdef	CONFIG_OPTPROBES
+extern int arch_init_optprobes(void);
+extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter);
+extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr);
+#else	/* !CONFIG_OPTPROBES */
+static inline int arch_init_optprobes(void)
+{
+	return 0;
+}
+static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
+{
+	return 0;
+}
+static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
+{
+	return addr;
+}
+#endif
+#endif
diff --git a/arch/x86/kernel/kprobes-opt.c b/arch/x86/kernel/kprobes-opt.c
new file mode 100644
index 00000000000..c5e410eed40
--- /dev/null
+++ b/arch/x86/kernel/kprobes-opt.c
@@ -0,0 +1,512 @@
+/*
+ *  Kernel Probes Jump Optimization (Optprobes)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2002, 2004
+ * Copyright (C) Hitachi Ltd., 2012
+ */
+#include <linux/kprobes.h>
+#include <linux/ptrace.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/hardirq.h>
+#include <linux/preempt.h>
+#include <linux/module.h>
+#include <linux/kdebug.h>
+#include <linux/kallsyms.h>
+#include <linux/ftrace.h>
+
+#include <asm/cacheflush.h>
+#include <asm/desc.h>
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+#include <asm/alternative.h>
+#include <asm/insn.h>
+#include <asm/debugreg.h>
+
+#include "kprobes-common.h"
+
+unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
+{
+	struct optimized_kprobe *op;
+	struct kprobe *kp;
+	long offs;
+	int i;
+
+	for (i = 0; i < RELATIVEJUMP_SIZE; i++) {
+		kp = get_kprobe((void *)addr - i);
+		/* This function only handles jump-optimized kprobe */
+		if (kp && kprobe_optimized(kp)) {
+			op = container_of(kp, struct optimized_kprobe, kp);
+			/* If op->list is not empty, op is under optimizing */
+			if (list_empty(&op->list))
+				goto found;
+		}
+	}
+
+	return addr;
+found:
+	/*
+	 * If the kprobe can be optimized, original bytes which can be
+	 * overwritten by jump destination address. In this case, original
+	 * bytes must be recovered from op->optinsn.copied_insn buffer.
+	 */
+	memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+	if (addr == (unsigned long)kp->addr) {
+		buf[0] = kp->opcode;
+		memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+	} else {
+		offs = addr - (unsigned long)kp->addr - 1;
+		memcpy(buf, op->optinsn.copied_insn + offs, RELATIVE_ADDR_SIZE - offs);
+	}
+
+	return (unsigned long)buf;
+}
+
+/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */
+static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val)
+{
+#ifdef CONFIG_X86_64
+	*addr++ = 0x48;
+	*addr++ = 0xbf;
+#else
+	*addr++ = 0xb8;
+#endif
+	*(unsigned long *)addr = val;
+}
+
+static void __used __kprobes kprobes_optinsn_template_holder(void)
+{
+	asm volatile (
+			".global optprobe_template_entry\n"
+			"optprobe_template_entry:\n"
+#ifdef CONFIG_X86_64
+			/* We don't bother saving the ss register */
+			"	pushq %rsp\n"
+			"	pushfq\n"
+			SAVE_REGS_STRING
+			"	movq %rsp, %rsi\n"
+			".global optprobe_template_val\n"
+			"optprobe_template_val:\n"
+			ASM_NOP5
+			ASM_NOP5
+			".global optprobe_template_call\n"
+			"optprobe_template_call:\n"
+			ASM_NOP5
+			/* Move flags to rsp */
+			"	movq 144(%rsp), %rdx\n"
+			"	movq %rdx, 152(%rsp)\n"
+			RESTORE_REGS_STRING
+			/* Skip flags entry */
+			"	addq $8, %rsp\n"
+			"	popfq\n"
+#else /* CONFIG_X86_32 */
+			"	pushf\n"
+			SAVE_REGS_STRING
+			"	movl %esp, %edx\n"
+			".global optprobe_template_val\n"
+			"optprobe_template_val:\n"
+			ASM_NOP5
+			".global optprobe_template_call\n"
+			"optprobe_template_call:\n"
+			ASM_NOP5
+			RESTORE_REGS_STRING
+			"	addl $4, %esp\n"	/* skip cs */
+			"	popf\n"
+#endif
+			".global optprobe_template_end\n"
+			"optprobe_template_end:\n");
+}
+
+#define TMPL_MOVE_IDX \
+	((long)&optprobe_template_val - (long)&optprobe_template_entry)
+#define TMPL_CALL_IDX \
+	((long)&optprobe_template_call - (long)&optprobe_template_entry)
+#define TMPL_END_IDX \
+	((long)&optprobe_template_end - (long)&optprobe_template_entry)
+
+#define INT3_SIZE sizeof(kprobe_opcode_t)
+
+/* Optimized kprobe call back function: called from optinsn */
+static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	unsigned long flags;
+
+	/* This is possible if op is under delayed unoptimizing */
+	if (kprobe_disabled(&op->kp))
+		return;
+
+	local_irq_save(flags);
+	if (kprobe_running()) {
+		kprobes_inc_nmissed_count(&op->kp);
+	} else {
+		/* Save skipped registers */
+#ifdef CONFIG_X86_64
+		regs->cs = __KERNEL_CS;
+#else
+		regs->cs = __KERNEL_CS | get_kernel_rpl();
+		regs->gs = 0;
+#endif
+		regs->ip = (unsigned long)op->kp.addr + INT3_SIZE;
+		regs->orig_ax = ~0UL;
+
+		__this_cpu_write(current_kprobe, &op->kp);
+		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+		opt_pre_handler(&op->kp, regs);
+		__this_cpu_write(current_kprobe, NULL);
+	}
+	local_irq_restore(flags);
+}
+
+static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
+{
+	int len = 0, ret;
+
+	while (len < RELATIVEJUMP_SIZE) {
+		ret = __copy_instruction(dest + len, src + len);
+		if (!ret || !can_boost(dest + len))
+			return -EINVAL;
+		len += ret;
+	}
+	/* Check whether the address range is reserved */
+	if (ftrace_text_reserved(src, src + len - 1) ||
+	    alternatives_text_reserved(src, src + len - 1) ||
+	    jump_label_text_reserved(src, src + len - 1))
+		return -EBUSY;
+
+	return len;
+}
+
+/* Check whether insn is indirect jump */
+static int __kprobes insn_is_indirect_jump(struct insn *insn)
+{
+	return ((insn->opcode.bytes[0] == 0xff &&
+		(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
+		insn->opcode.bytes[0] == 0xea);	/* Segment based jump */
+}
+
+/* Check whether insn jumps into specified address range */
+static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
+{
+	unsigned long target = 0;
+
+	switch (insn->opcode.bytes[0]) {
+	case 0xe0:	/* loopne */
+	case 0xe1:	/* loope */
+	case 0xe2:	/* loop */
+	case 0xe3:	/* jcxz */
+	case 0xe9:	/* near relative jump */
+	case 0xeb:	/* short relative jump */
+		break;
+	case 0x0f:
+		if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */
+			break;
+		return 0;
+	default:
+		if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */
+			break;
+		return 0;
+	}
+	target = (unsigned long)insn->next_byte + insn->immediate.value;
+
+	return (start <= target && target <= start + len);
+}
+
+/* Decode whole function to ensure any instructions don't jump into target */
+static int __kprobes can_optimize(unsigned long paddr)
+{
+	unsigned long addr, size = 0, offset = 0;
+	struct insn insn;
+	kprobe_opcode_t buf[MAX_INSN_SIZE];
+
+	/* Lookup symbol including addr */
+	if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
+		return 0;
+
+	/*
+	 * Do not optimize in the entry code due to the unstable
+	 * stack handling.
+	 */
+	if ((paddr >= (unsigned long)__entry_text_start) &&
+	    (paddr <  (unsigned long)__entry_text_end))
+		return 0;
+
+	/* Check there is enough space for a relative jump. */
+	if (size - offset < RELATIVEJUMP_SIZE)
+		return 0;
+
+	/* Decode instructions */
+	addr = paddr - offset;
+	while (addr < paddr - offset + size) { /* Decode until function end */
+		if (search_exception_tables(addr))
+			/*
+			 * Since some fixup code will jumps into this function,
+			 * we can't optimize kprobe in this function.
+			 */
+			return 0;
+		kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, addr));
+		insn_get_length(&insn);
+		/* Another subsystem puts a breakpoint */
+		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
+			return 0;
+		/* Recover address */
+		insn.kaddr = (void *)addr;
+		insn.next_byte = (void *)(addr + insn.length);
+		/* Check any instructions don't jump into target */
+		if (insn_is_indirect_jump(&insn) ||
+		    insn_jump_into_range(&insn, paddr + INT3_SIZE,
+					 RELATIVE_ADDR_SIZE))
+			return 0;
+		addr += insn.length;
+	}
+
+	return 1;
+}
+
+/* Check optimized_kprobe can actually be optimized. */
+int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op)
+{
+	int i;
+	struct kprobe *p;
+
+	for (i = 1; i < op->optinsn.size; i++) {
+		p = get_kprobe(op->kp.addr + i);
+		if (p && !kprobe_disabled(p))
+			return -EEXIST;
+	}
+
+	return 0;
+}
+
+/* Check the addr is within the optimized instructions. */
+int __kprobes
+arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr)
+{
+	return ((unsigned long)op->kp.addr <= addr &&
+		(unsigned long)op->kp.addr + op->optinsn.size > addr);
+}
+
+/* Free optimized instruction slot */
+static __kprobes
+void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
+{
+	if (op->optinsn.insn) {
+		free_optinsn_slot(op->optinsn.insn, dirty);
+		op->optinsn.insn = NULL;
+		op->optinsn.size = 0;
+	}
+}
+
+void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op)
+{
+	__arch_remove_optimized_kprobe(op, 1);
+}
+
+/*
+ * Copy replacing target instructions
+ * Target instructions MUST be relocatable (checked inside)
+ * This is called when new aggr(opt)probe is allocated or reused.
+ */
+int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
+{
+	u8 *buf;
+	int ret;
+	long rel;
+
+	if (!can_optimize((unsigned long)op->kp.addr))
+		return -EILSEQ;
+
+	op->optinsn.insn = get_optinsn_slot();
+	if (!op->optinsn.insn)
+		return -ENOMEM;
+
+	/*
+	 * Verify if the address gap is in 2GB range, because this uses
+	 * a relative jump.
+	 */
+	rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE;
+	if (abs(rel) > 0x7fffffff)
+		return -ERANGE;
+
+	buf = (u8 *)op->optinsn.insn;
+
+	/* Copy instructions into the out-of-line buffer */
+	ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr);
+	if (ret < 0) {
+		__arch_remove_optimized_kprobe(op, 0);
+		return ret;
+	}
+	op->optinsn.size = ret;
+
+	/* Copy arch-dep-instance from template */
+	memcpy(buf, &optprobe_template_entry, TMPL_END_IDX);
+
+	/* Set probe information */
+	synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op);
+
+	/* Set probe function call */
+	synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback);
+
+	/* Set returning jmp instruction at the tail of out-of-line buffer */
+	synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size,
+			   (u8 *)op->kp.addr + op->optinsn.size);
+
+	flush_icache_range((unsigned long) buf,
+			   (unsigned long) buf + TMPL_END_IDX +
+			   op->optinsn.size + RELATIVEJUMP_SIZE);
+	return 0;
+}
+
+#define MAX_OPTIMIZE_PROBES 256
+static struct text_poke_param *jump_poke_params;
+static struct jump_poke_buffer {
+	u8 buf[RELATIVEJUMP_SIZE];
+} *jump_poke_bufs;
+
+static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
+					    u8 *insn_buf,
+					    struct optimized_kprobe *op)
+{
+	s32 rel = (s32)((long)op->optinsn.insn -
+			((long)op->kp.addr + RELATIVEJUMP_SIZE));
+
+	/* Backup instructions which will be replaced by jump address */
+	memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
+	       RELATIVE_ADDR_SIZE);
+
+	insn_buf[0] = RELATIVEJUMP_OPCODE;
+	*(s32 *)(&insn_buf[1]) = rel;
+
+	tprm->addr = op->kp.addr;
+	tprm->opcode = insn_buf;
+	tprm->len = RELATIVEJUMP_SIZE;
+}
+
+/*
+ * Replace breakpoints (int3) with relative jumps.
+ * Caller must call with locking kprobe_mutex and text_mutex.
+ */
+void __kprobes arch_optimize_kprobes(struct list_head *oplist)
+{
+	struct optimized_kprobe *op, *tmp;
+	int c = 0;
+
+	list_for_each_entry_safe(op, tmp, oplist, list) {
+		WARN_ON(kprobe_disabled(&op->kp));
+		/* Setup param */
+		setup_optimize_kprobe(&jump_poke_params[c],
+				      jump_poke_bufs[c].buf, op);
+		list_del_init(&op->list);
+		if (++c >= MAX_OPTIMIZE_PROBES)
+			break;
+	}
+
+	/*
+	 * text_poke_smp doesn't support NMI/MCE code modifying.
+	 * However, since kprobes itself also doesn't support NMI/MCE
+	 * code probing, it's not a problem.
+	 */
+	text_poke_smp_batch(jump_poke_params, c);
+}
+
+static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm,
+					      u8 *insn_buf,
+					      struct optimized_kprobe *op)
+{
+	/* Set int3 to first byte for kprobes */
+	insn_buf[0] = BREAKPOINT_INSTRUCTION;
+	memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+
+	tprm->addr = op->kp.addr;
+	tprm->opcode = insn_buf;
+	tprm->len = RELATIVEJUMP_SIZE;
+}
+
+/*
+ * Recover original instructions and breakpoints from relative jumps.
+ * Caller must call with locking kprobe_mutex.
+ */
+extern void arch_unoptimize_kprobes(struct list_head *oplist,
+				    struct list_head *done_list)
+{
+	struct optimized_kprobe *op, *tmp;
+	int c = 0;
+
+	list_for_each_entry_safe(op, tmp, oplist, list) {
+		/* Setup param */
+		setup_unoptimize_kprobe(&jump_poke_params[c],
+					jump_poke_bufs[c].buf, op);
+		list_move(&op->list, done_list);
+		if (++c >= MAX_OPTIMIZE_PROBES)
+			break;
+	}
+
+	/*
+	 * text_poke_smp doesn't support NMI/MCE code modifying.
+	 * However, since kprobes itself also doesn't support NMI/MCE
+	 * code probing, it's not a problem.
+	 */
+	text_poke_smp_batch(jump_poke_params, c);
+}
+
+/* Replace a relative jump with a breakpoint (int3).  */
+void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
+{
+	u8 buf[RELATIVEJUMP_SIZE];
+
+	/* Set int3 to first byte for kprobes */
+	buf[0] = BREAKPOINT_INSTRUCTION;
+	memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+	text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE);
+}
+
+int  __kprobes
+setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
+{
+	struct optimized_kprobe *op;
+
+	if (p->flags & KPROBE_FLAG_OPTIMIZED) {
+		/* This kprobe is really able to run optimized path. */
+		op = container_of(p, struct optimized_kprobe, kp);
+		/* Detour through copied instructions */
+		regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX;
+		if (!reenter)
+			reset_current_kprobe();
+		preempt_enable_no_resched();
+		return 1;
+	}
+	return 0;
+}
+
+int __kprobes arch_init_optprobes(void)
+{
+	/* Allocate code buffer and parameter array */
+	jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) *
+				 MAX_OPTIMIZE_PROBES, GFP_KERNEL);
+	if (!jump_poke_bufs)
+		return -ENOMEM;
+
+	jump_poke_params = kmalloc(sizeof(struct text_poke_param) *
+				   MAX_OPTIMIZE_PROBES, GFP_KERNEL);
+	if (!jump_poke_params) {
+		kfree(jump_poke_bufs);
+		jump_poke_bufs = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 7da647d8b64..e213fc8408d 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -30,16 +30,15 @@
  *		<jkenisto@us.ibm.com> and Prasanna S Panchamukhi
  *		<prasanna@in.ibm.com> added function-return probes.
  * 2005-May	Rusty Lynch <rusty.lynch@intel.com>
- * 		Added function return probes functionality
+ *		Added function return probes functionality
  * 2006-Feb	Masami Hiramatsu <hiramatu@sdl.hitachi.co.jp> added
- * 		kprobe-booster and kretprobe-booster for i386.
+ *		kprobe-booster and kretprobe-booster for i386.
  * 2007-Dec	Masami Hiramatsu <mhiramat@redhat.com> added kprobe-booster
- * 		and kretprobe-booster for x86-64
+ *		and kretprobe-booster for x86-64
  * 2007-Dec	Masami Hiramatsu <mhiramat@redhat.com>, Arjan van de Ven
- * 		<arjan@infradead.org> and Jim Keniston <jkenisto@us.ibm.com>
- * 		unified x86 kprobes code.
+ *		<arjan@infradead.org> and Jim Keniston <jkenisto@us.ibm.com>
+ *		unified x86 kprobes code.
  */
-
 #include <linux/kprobes.h>
 #include <linux/ptrace.h>
 #include <linux/string.h>
@@ -59,6 +58,8 @@
 #include <asm/insn.h>
 #include <asm/debugreg.h>
 
+#include "kprobes-common.h"
+
 void jprobe_return_end(void);
 
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
@@ -108,6 +109,7 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = {
 			      doesn't switch kernel stack.*/
 	{NULL, NULL}	/* Terminator */
 };
+
 const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist);
 
 static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op)
@@ -123,11 +125,17 @@ static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op)
 }
 
 /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/
-static void __kprobes synthesize_reljump(void *from, void *to)
+void __kprobes synthesize_reljump(void *from, void *to)
 {
 	__synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE);
 }
 
+/* Insert a call instruction at address 'from', which calls address 'to'.*/
+void __kprobes synthesize_relcall(void *from, void *to)
+{
+	__synthesize_relative_insn(from, to, RELATIVECALL_OPCODE);
+}
+
 /*
  * Skip the prefixes of the instruction.
  */
@@ -151,7 +159,7 @@ static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn)
  * Returns non-zero if opcode is boostable.
  * RIP relative instructions are adjusted at copying time in 64 bits mode
  */
-static int __kprobes can_boost(kprobe_opcode_t *opcodes)
+int __kprobes can_boost(kprobe_opcode_t *opcodes)
 {
 	kprobe_opcode_t opcode;
 	kprobe_opcode_t *orig_opcodes = opcodes;
@@ -207,13 +215,15 @@ retry:
 	}
 }
 
-/* Recover the probed instruction at addr for further analysis. */
-static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
+static unsigned long
+__recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
 {
 	struct kprobe *kp;
+
 	kp = get_kprobe((void *)addr);
+	/* There is no probe, return original address */
 	if (!kp)
-		return -EINVAL;
+		return addr;
 
 	/*
 	 *  Basically, kp->ainsn.insn has an original instruction.
@@ -230,14 +240,29 @@ static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
 	 */
 	memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
 	buf[0] = kp->opcode;
-	return 0;
+	return (unsigned long)buf;
+}
+
+/*
+ * Recover the probed instruction at addr for further analysis.
+ * Caller must lock kprobes by kprobe_mutex, or disable preemption
+ * for preventing to release referencing kprobes.
+ */
+unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
+{
+	unsigned long __addr;
+
+	__addr = __recover_optprobed_insn(buf, addr);
+	if (__addr != addr)
+		return __addr;
+
+	return __recover_probed_insn(buf, addr);
 }
 
 /* Check if paddr is at an instruction boundary */
 static int __kprobes can_probe(unsigned long paddr)
 {
-	int ret;
-	unsigned long addr, offset = 0;
+	unsigned long addr, __addr, offset = 0;
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
 
@@ -247,26 +272,24 @@ static int __kprobes can_probe(unsigned long paddr)
 	/* Decode instructions */
 	addr = paddr - offset;
 	while (addr < paddr) {
-		kernel_insn_init(&insn, (void *)addr);
-		insn_get_opcode(&insn);
-
 		/*
 		 * Check if the instruction has been modified by another
 		 * kprobe, in which case we replace the breakpoint by the
 		 * original instruction in our buffer.
+		 * Also, jump optimization will change the breakpoint to
+		 * relative-jump. Since the relative-jump itself is
+		 * normally used, we just go through if there is no kprobe.
 		 */
-		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) {
-			ret = recover_probed_instruction(buf, addr);
-			if (ret)
-				/*
-				 * Another debugging subsystem might insert
-				 * this breakpoint. In that case, we can't
-				 * recover it.
-				 */
-				return 0;
-			kernel_insn_init(&insn, buf);
-		}
+		__addr = recover_probed_instruction(buf, addr);
+		kernel_insn_init(&insn, (void *)__addr);
 		insn_get_length(&insn);
+
+		/*
+		 * Another debugging subsystem might insert this breakpoint.
+		 * In that case, we can't recover it.
+		 */
+		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
+			return 0;
 		addr += insn.length;
 	}
 
@@ -299,24 +322,16 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn)
  * If not, return null.
  * Only applicable to 64-bit x86.
  */
-static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover)
+int __kprobes __copy_instruction(u8 *dest, u8 *src)
 {
 	struct insn insn;
-	int ret;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
 
-	kernel_insn_init(&insn, src);
-	if (recover) {
-		insn_get_opcode(&insn);
-		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) {
-			ret = recover_probed_instruction(buf,
-							 (unsigned long)src);
-			if (ret)
-				return 0;
-			kernel_insn_init(&insn, buf);
-		}
-	}
+	kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src));
 	insn_get_length(&insn);
+	/* Another subsystem puts a breakpoint, failed to recover */
+	if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
+		return 0;
 	memcpy(dest, insn.kaddr, insn.length);
 
 #ifdef CONFIG_X86_64
@@ -337,8 +352,7 @@ static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover)
 		 * extension of the original signed 32-bit displacement would
 		 * have given.
 		 */
-		newdisp = (u8 *) src + (s64) insn.displacement.value -
-			  (u8 *) dest;
+		newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest;
 		BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check.  */
 		disp = (u8 *) dest + insn_offset_displacement(&insn);
 		*(s32 *) disp = (s32) newdisp;
@@ -349,18 +363,20 @@ static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover)
 
 static void __kprobes arch_copy_kprobe(struct kprobe *p)
 {
+	/* Copy an instruction with recovering if other optprobe modifies it.*/
+	__copy_instruction(p->ainsn.insn, p->addr);
+
 	/*
-	 * Copy an instruction without recovering int3, because it will be
-	 * put by another subsystem.
+	 * __copy_instruction can modify the displacement of the instruction,
+	 * but it doesn't affect boostable check.
 	 */
-	__copy_instruction(p->ainsn.insn, p->addr, 0);
-
-	if (can_boost(p->addr))
+	if (can_boost(p->ainsn.insn))
 		p->ainsn.boostable = 0;
 	else
 		p->ainsn.boostable = -1;
 
-	p->opcode = *p->addr;
+	/* Also, displacement change doesn't affect the first byte */
+	p->opcode = p->ainsn.insn[0];
 }
 
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
@@ -442,8 +458,8 @@ static void __kprobes restore_btf(void)
 	}
 }
 
-void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
-				      struct pt_regs *regs)
+void __kprobes
+arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	unsigned long *sara = stack_addr(regs);
 
@@ -453,16 +469,8 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 	*sara = (unsigned long) &kretprobe_trampoline;
 }
 
-#ifdef CONFIG_OPTPROBES
-static int  __kprobes setup_detour_execution(struct kprobe *p,
-					     struct pt_regs *regs,
-					     int reenter);
-#else
-#define setup_detour_execution(p, regs, reenter) (0)
-#endif
-
-static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs,
-				       struct kprobe_ctlblk *kcb, int reenter)
+static void __kprobes
+setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, int reenter)
 {
 	if (setup_detour_execution(p, regs, reenter))
 		return;
@@ -504,8 +512,8 @@ static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs,
  * within the handler. We save the original kprobes variables and just single
  * step on the instruction of the new probe without calling any user handlers.
  */
-static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs,
-				    struct kprobe_ctlblk *kcb)
+static int __kprobes
+reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
 {
 	switch (kcb->kprobe_status) {
 	case KPROBE_HIT_SSDONE:
@@ -600,69 +608,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	return 0;
 }
 
-#ifdef CONFIG_X86_64
-#define SAVE_REGS_STRING		\
-	/* Skip cs, ip, orig_ax. */	\
-	"	subq $24, %rsp\n"	\
-	"	pushq %rdi\n"		\
-	"	pushq %rsi\n"		\
-	"	pushq %rdx\n"		\
-	"	pushq %rcx\n"		\
-	"	pushq %rax\n"		\
-	"	pushq %r8\n"		\
-	"	pushq %r9\n"		\
-	"	pushq %r10\n"		\
-	"	pushq %r11\n"		\
-	"	pushq %rbx\n"		\
-	"	pushq %rbp\n"		\
-	"	pushq %r12\n"		\
-	"	pushq %r13\n"		\
-	"	pushq %r14\n"		\
-	"	pushq %r15\n"
-#define RESTORE_REGS_STRING		\
-	"	popq %r15\n"		\
-	"	popq %r14\n"		\
-	"	popq %r13\n"		\
-	"	popq %r12\n"		\
-	"	popq %rbp\n"		\
-	"	popq %rbx\n"		\
-	"	popq %r11\n"		\
-	"	popq %r10\n"		\
-	"	popq %r9\n"		\
-	"	popq %r8\n"		\
-	"	popq %rax\n"		\
-	"	popq %rcx\n"		\
-	"	popq %rdx\n"		\
-	"	popq %rsi\n"		\
-	"	popq %rdi\n"		\
-	/* Skip orig_ax, ip, cs */	\
-	"	addq $24, %rsp\n"
-#else
-#define SAVE_REGS_STRING		\
-	/* Skip cs, ip, orig_ax and gs. */	\
-	"	subl $16, %esp\n"	\
-	"	pushl %fs\n"		\
-	"	pushl %es\n"		\
-	"	pushl %ds\n"		\
-	"	pushl %eax\n"		\
-	"	pushl %ebp\n"		\
-	"	pushl %edi\n"		\
-	"	pushl %esi\n"		\
-	"	pushl %edx\n"		\
-	"	pushl %ecx\n"		\
-	"	pushl %ebx\n"
-#define RESTORE_REGS_STRING		\
-	"	popl %ebx\n"		\
-	"	popl %ecx\n"		\
-	"	popl %edx\n"		\
-	"	popl %esi\n"		\
-	"	popl %edi\n"		\
-	"	popl %ebp\n"		\
-	"	popl %eax\n"		\
-	/* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\
-	"	addl $24, %esp\n"
-#endif
-
 /*
  * When a retprobed function returns, this code saves registers and
  * calls trampoline_handler() runs, which calls the kretprobe's handler.
@@ -816,8 +761,8 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
  * jump instruction after the copied instruction, that jumps to the next
  * instruction after the probepoint.
  */
-static void __kprobes resume_execution(struct kprobe *p,
-		struct pt_regs *regs, struct kprobe_ctlblk *kcb)
+static void __kprobes
+resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
 {
 	unsigned long *tos = stack_addr(regs);
 	unsigned long copy_ip = (unsigned long)p->ainsn.insn;
@@ -996,8 +941,8 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 /*
  * Wrapper routine for handling exceptions.
  */
-int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
-				       unsigned long val, void *data)
+int __kprobes
+kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data)
 {
 	struct die_args *args = data;
 	int ret = NOTIFY_DONE;
@@ -1107,466 +1052,9 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	return 0;
 }
 
-
-#ifdef CONFIG_OPTPROBES
-
-/* Insert a call instruction at address 'from', which calls address 'to'.*/
-static void __kprobes synthesize_relcall(void *from, void *to)
-{
-	__synthesize_relative_insn(from, to, RELATIVECALL_OPCODE);
-}
-
-/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */
-static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr,
-					  unsigned long val)
-{
-#ifdef CONFIG_X86_64
-	*addr++ = 0x48;
-	*addr++ = 0xbf;
-#else
-	*addr++ = 0xb8;
-#endif
-	*(unsigned long *)addr = val;
-}
-
-static void __used __kprobes kprobes_optinsn_template_holder(void)
-{
-	asm volatile (
-			".global optprobe_template_entry\n"
-			"optprobe_template_entry: \n"
-#ifdef CONFIG_X86_64
-			/* We don't bother saving the ss register */
-			"	pushq %rsp\n"
-			"	pushfq\n"
-			SAVE_REGS_STRING
-			"	movq %rsp, %rsi\n"
-			".global optprobe_template_val\n"
-			"optprobe_template_val: \n"
-			ASM_NOP5
-			ASM_NOP5
-			".global optprobe_template_call\n"
-			"optprobe_template_call: \n"
-			ASM_NOP5
-			/* Move flags to rsp */
-			"	movq 144(%rsp), %rdx\n"
-			"	movq %rdx, 152(%rsp)\n"
-			RESTORE_REGS_STRING
-			/* Skip flags entry */
-			"	addq $8, %rsp\n"
-			"	popfq\n"
-#else /* CONFIG_X86_32 */
-			"	pushf\n"
-			SAVE_REGS_STRING
-			"	movl %esp, %edx\n"
-			".global optprobe_template_val\n"
-			"optprobe_template_val: \n"
-			ASM_NOP5
-			".global optprobe_template_call\n"
-			"optprobe_template_call: \n"
-			ASM_NOP5
-			RESTORE_REGS_STRING
-			"	addl $4, %esp\n"	/* skip cs */
-			"	popf\n"
-#endif
-			".global optprobe_template_end\n"
-			"optprobe_template_end: \n");
-}
-
-#define TMPL_MOVE_IDX \
-	((long)&optprobe_template_val - (long)&optprobe_template_entry)
-#define TMPL_CALL_IDX \
-	((long)&optprobe_template_call - (long)&optprobe_template_entry)
-#define TMPL_END_IDX \
-	((long)&optprobe_template_end - (long)&optprobe_template_entry)
-
-#define INT3_SIZE sizeof(kprobe_opcode_t)
-
-/* Optimized kprobe call back function: called from optinsn */
-static void __kprobes optimized_callback(struct optimized_kprobe *op,
-					 struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long flags;
-
-	/* This is possible if op is under delayed unoptimizing */
-	if (kprobe_disabled(&op->kp))
-		return;
-
-	local_irq_save(flags);
-	if (kprobe_running()) {
-		kprobes_inc_nmissed_count(&op->kp);
-	} else {
-		/* Save skipped registers */
-#ifdef CONFIG_X86_64
-		regs->cs = __KERNEL_CS;
-#else
-		regs->cs = __KERNEL_CS | get_kernel_rpl();
-		regs->gs = 0;
-#endif
-		regs->ip = (unsigned long)op->kp.addr + INT3_SIZE;
-		regs->orig_ax = ~0UL;
-
-		__this_cpu_write(current_kprobe, &op->kp);
-		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-		opt_pre_handler(&op->kp, regs);
-		__this_cpu_write(current_kprobe, NULL);
-	}
-	local_irq_restore(flags);
-}
-
-static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
-{
-	int len = 0, ret;
-
-	while (len < RELATIVEJUMP_SIZE) {
-		ret = __copy_instruction(dest + len, src + len, 1);
-		if (!ret || !can_boost(dest + len))
-			return -EINVAL;
-		len += ret;
-	}
-	/* Check whether the address range is reserved */
-	if (ftrace_text_reserved(src, src + len - 1) ||
-	    alternatives_text_reserved(src, src + len - 1) ||
-	    jump_label_text_reserved(src, src + len - 1))
-		return -EBUSY;
-
-	return len;
-}
-
-/* Check whether insn is indirect jump */
-static int __kprobes insn_is_indirect_jump(struct insn *insn)
-{
-	return ((insn->opcode.bytes[0] == 0xff &&
-		(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
-		insn->opcode.bytes[0] == 0xea);	/* Segment based jump */
-}
-
-/* Check whether insn jumps into specified address range */
-static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
-{
-	unsigned long target = 0;
-
-	switch (insn->opcode.bytes[0]) {
-	case 0xe0:	/* loopne */
-	case 0xe1:	/* loope */
-	case 0xe2:	/* loop */
-	case 0xe3:	/* jcxz */
-	case 0xe9:	/* near relative jump */
-	case 0xeb:	/* short relative jump */
-		break;
-	case 0x0f:
-		if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */
-			break;
-		return 0;
-	default:
-		if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */
-			break;
-		return 0;
-	}
-	target = (unsigned long)insn->next_byte + insn->immediate.value;
-
-	return (start <= target && target <= start + len);
-}
-
-/* Decode whole function to ensure any instructions don't jump into target */
-static int __kprobes can_optimize(unsigned long paddr)
-{
-	int ret;
-	unsigned long addr, size = 0, offset = 0;
-	struct insn insn;
-	kprobe_opcode_t buf[MAX_INSN_SIZE];
-
-	/* Lookup symbol including addr */
-	if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
-		return 0;
-
-	/*
-	 * Do not optimize in the entry code due to the unstable
-	 * stack handling.
-	 */
-	if ((paddr >= (unsigned long )__entry_text_start) &&
-	    (paddr <  (unsigned long )__entry_text_end))
-		return 0;
-
-	/* Check there is enough space for a relative jump. */
-	if (size - offset < RELATIVEJUMP_SIZE)
-		return 0;
-
-	/* Decode instructions */
-	addr = paddr - offset;
-	while (addr < paddr - offset + size) { /* Decode until function end */
-		if (search_exception_tables(addr))
-			/*
-			 * Since some fixup code will jumps into this function,
-			 * we can't optimize kprobe in this function.
-			 */
-			return 0;
-		kernel_insn_init(&insn, (void *)addr);
-		insn_get_opcode(&insn);
-		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) {
-			ret = recover_probed_instruction(buf, addr);
-			if (ret)
-				return 0;
-			kernel_insn_init(&insn, buf);
-		}
-		insn_get_length(&insn);
-		/* Recover address */
-		insn.kaddr = (void *)addr;
-		insn.next_byte = (void *)(addr + insn.length);
-		/* Check any instructions don't jump into target */
-		if (insn_is_indirect_jump(&insn) ||
-		    insn_jump_into_range(&insn, paddr + INT3_SIZE,
-					 RELATIVE_ADDR_SIZE))
-			return 0;
-		addr += insn.length;
-	}
-
-	return 1;
-}
-
-/* Check optimized_kprobe can actually be optimized. */
-int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op)
-{
-	int i;
-	struct kprobe *p;
-
-	for (i = 1; i < op->optinsn.size; i++) {
-		p = get_kprobe(op->kp.addr + i);
-		if (p && !kprobe_disabled(p))
-			return -EEXIST;
-	}
-
-	return 0;
-}
-
-/* Check the addr is within the optimized instructions. */
-int __kprobes arch_within_optimized_kprobe(struct optimized_kprobe *op,
-					   unsigned long addr)
-{
-	return ((unsigned long)op->kp.addr <= addr &&
-		(unsigned long)op->kp.addr + op->optinsn.size > addr);
-}
-
-/* Free optimized instruction slot */
-static __kprobes
-void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
-{
-	if (op->optinsn.insn) {
-		free_optinsn_slot(op->optinsn.insn, dirty);
-		op->optinsn.insn = NULL;
-		op->optinsn.size = 0;
-	}
-}
-
-void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op)
-{
-	__arch_remove_optimized_kprobe(op, 1);
-}
-
-/*
- * Copy replacing target instructions
- * Target instructions MUST be relocatable (checked inside)
- */
-int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
-{
-	u8 *buf;
-	int ret;
-	long rel;
-
-	if (!can_optimize((unsigned long)op->kp.addr))
-		return -EILSEQ;
-
-	op->optinsn.insn = get_optinsn_slot();
-	if (!op->optinsn.insn)
-		return -ENOMEM;
-
-	/*
-	 * Verify if the address gap is in 2GB range, because this uses
-	 * a relative jump.
-	 */
-	rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE;
-	if (abs(rel) > 0x7fffffff)
-		return -ERANGE;
-
-	buf = (u8 *)op->optinsn.insn;
-
-	/* Copy instructions into the out-of-line buffer */
-	ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr);
-	if (ret < 0) {
-		__arch_remove_optimized_kprobe(op, 0);
-		return ret;
-	}
-	op->optinsn.size = ret;
-
-	/* Copy arch-dep-instance from template */
-	memcpy(buf, &optprobe_template_entry, TMPL_END_IDX);
-
-	/* Set probe information */
-	synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op);
-
-	/* Set probe function call */
-	synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback);
-
-	/* Set returning jmp instruction at the tail of out-of-line buffer */
-	synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size,
-			   (u8 *)op->kp.addr + op->optinsn.size);
-
-	flush_icache_range((unsigned long) buf,
-			   (unsigned long) buf + TMPL_END_IDX +
-			   op->optinsn.size + RELATIVEJUMP_SIZE);
-	return 0;
-}
-
-#define MAX_OPTIMIZE_PROBES 256
-static struct text_poke_param *jump_poke_params;
-static struct jump_poke_buffer {
-	u8 buf[RELATIVEJUMP_SIZE];
-} *jump_poke_bufs;
-
-static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
-					    u8 *insn_buf,
-					    struct optimized_kprobe *op)
-{
-	s32 rel = (s32)((long)op->optinsn.insn -
-			((long)op->kp.addr + RELATIVEJUMP_SIZE));
-
-	/* Backup instructions which will be replaced by jump address */
-	memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
-	       RELATIVE_ADDR_SIZE);
-
-	insn_buf[0] = RELATIVEJUMP_OPCODE;
-	*(s32 *)(&insn_buf[1]) = rel;
-
-	tprm->addr = op->kp.addr;
-	tprm->opcode = insn_buf;
-	tprm->len = RELATIVEJUMP_SIZE;
-}
-
-/*
- * Replace breakpoints (int3) with relative jumps.
- * Caller must call with locking kprobe_mutex and text_mutex.
- */
-void __kprobes arch_optimize_kprobes(struct list_head *oplist)
-{
-	struct optimized_kprobe *op, *tmp;
-	int c = 0;
-
-	list_for_each_entry_safe(op, tmp, oplist, list) {
-		WARN_ON(kprobe_disabled(&op->kp));
-		/* Setup param */
-		setup_optimize_kprobe(&jump_poke_params[c],
-				      jump_poke_bufs[c].buf, op);
-		list_del_init(&op->list);
-		if (++c >= MAX_OPTIMIZE_PROBES)
-			break;
-	}
-
-	/*
-	 * text_poke_smp doesn't support NMI/MCE code modifying.
-	 * However, since kprobes itself also doesn't support NMI/MCE
-	 * code probing, it's not a problem.
-	 */
-	text_poke_smp_batch(jump_poke_params, c);
-}
-
-static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm,
-					      u8 *insn_buf,
-					      struct optimized_kprobe *op)
-{
-	/* Set int3 to first byte for kprobes */
-	insn_buf[0] = BREAKPOINT_INSTRUCTION;
-	memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
-
-	tprm->addr = op->kp.addr;
-	tprm->opcode = insn_buf;
-	tprm->len = RELATIVEJUMP_SIZE;
-}
-
-/*
- * Recover original instructions and breakpoints from relative jumps.
- * Caller must call with locking kprobe_mutex.
- */
-extern void arch_unoptimize_kprobes(struct list_head *oplist,
-				    struct list_head *done_list)
-{
-	struct optimized_kprobe *op, *tmp;
-	int c = 0;
-
-	list_for_each_entry_safe(op, tmp, oplist, list) {
-		/* Setup param */
-		setup_unoptimize_kprobe(&jump_poke_params[c],
-					jump_poke_bufs[c].buf, op);
-		list_move(&op->list, done_list);
-		if (++c >= MAX_OPTIMIZE_PROBES)
-			break;
-	}
-
-	/*
-	 * text_poke_smp doesn't support NMI/MCE code modifying.
-	 * However, since kprobes itself also doesn't support NMI/MCE
-	 * code probing, it's not a problem.
-	 */
-	text_poke_smp_batch(jump_poke_params, c);
-}
-
-/* Replace a relative jump with a breakpoint (int3).  */
-void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
-{
-	u8 buf[RELATIVEJUMP_SIZE];
-
-	/* Set int3 to first byte for kprobes */
-	buf[0] = BREAKPOINT_INSTRUCTION;
-	memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
-	text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE);
-}
-
-static int  __kprobes setup_detour_execution(struct kprobe *p,
-					     struct pt_regs *regs,
-					     int reenter)
-{
-	struct optimized_kprobe *op;
-
-	if (p->flags & KPROBE_FLAG_OPTIMIZED) {
-		/* This kprobe is really able to run optimized path. */
-		op = container_of(p, struct optimized_kprobe, kp);
-		/* Detour through copied instructions */
-		regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX;
-		if (!reenter)
-			reset_current_kprobe();
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-
-static int __kprobes init_poke_params(void)
-{
-	/* Allocate code buffer and parameter array */
-	jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) *
-				 MAX_OPTIMIZE_PROBES, GFP_KERNEL);
-	if (!jump_poke_bufs)
-		return -ENOMEM;
-
-	jump_poke_params = kmalloc(sizeof(struct text_poke_param) *
-				   MAX_OPTIMIZE_PROBES, GFP_KERNEL);
-	if (!jump_poke_params) {
-		kfree(jump_poke_bufs);
-		jump_poke_bufs = NULL;
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-#else	/* !CONFIG_OPTPROBES */
-static int __kprobes init_poke_params(void)
-{
-	return 0;
-}
-#endif
-
 int __init arch_init_kprobes(void)
 {
-	return init_poke_params();
+	return arch_init_optprobes();
 }
 
 int __kprobes arch_trampoline_kprobe(struct kprobe *p)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index f0c6fd6f176..694d801bf60 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -438,9 +438,9 @@ void __init kvm_guest_init(void)
 static __init int activate_jump_labels(void)
 {
 	if (has_steal_clock) {
-		jump_label_inc(&paravirt_steal_enabled);
+		static_key_slow_inc(&paravirt_steal_enabled);
 		if (steal_acc)
-			jump_label_inc(&paravirt_steal_rq_enabled);
+			static_key_slow_inc(&paravirt_steal_rq_enabled);
 	}
 
 	return 0;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index d90272e6bc4..ada2f99388d 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -202,8 +202,8 @@ static void native_flush_tlb_single(unsigned long addr)
 	__native_flush_tlb_single(addr);
 }
 
-struct jump_label_key paravirt_steal_enabled;
-struct jump_label_key paravirt_steal_rq_enabled;
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
 
 static u64 native_steal_clock(int cpu)
 {
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 15763af7bfe..44eefde9210 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -377,8 +377,8 @@ static inline int hlt_use_halt(void)
 void default_idle(void)
 {
 	if (hlt_use_halt()) {
-		trace_power_start(POWER_CSTATE, 1, smp_processor_id());
-		trace_cpu_idle(1, smp_processor_id());
+		trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id());
+		trace_cpu_idle_rcuidle(1, smp_processor_id());
 		current_thread_info()->status &= ~TS_POLLING;
 		/*
 		 * TS_POLLING-cleared state must be visible before we
@@ -391,8 +391,8 @@ void default_idle(void)
 		else
 			local_irq_enable();
 		current_thread_info()->status |= TS_POLLING;
-		trace_power_end(smp_processor_id());
-		trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
+		trace_power_end_rcuidle(smp_processor_id());
+		trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	} else {
 		local_irq_enable();
 		/* loop is done by the caller */
@@ -450,8 +450,8 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait);
 static void mwait_idle(void)
 {
 	if (!need_resched()) {
-		trace_power_start(POWER_CSTATE, 1, smp_processor_id());
-		trace_cpu_idle(1, smp_processor_id());
+		trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id());
+		trace_cpu_idle_rcuidle(1, smp_processor_id());
 		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
 			clflush((void *)&current_thread_info()->flags);
 
@@ -461,8 +461,8 @@ static void mwait_idle(void)
 			__sti_mwait(0, 0);
 		else
 			local_irq_enable();
-		trace_power_end(smp_processor_id());
-		trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
+		trace_power_end_rcuidle(smp_processor_id());
+		trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	} else
 		local_irq_enable();
 }
@@ -474,13 +474,13 @@ static void mwait_idle(void)
  */
 static void poll_idle(void)
 {
-	trace_power_start(POWER_CSTATE, 0, smp_processor_id());
-	trace_cpu_idle(0, smp_processor_id());
+	trace_power_start_rcuidle(POWER_CSTATE, 0, smp_processor_id());
+	trace_cpu_idle_rcuidle(0, smp_processor_id());
 	local_irq_enable();
 	while (!need_resched())
 		cpu_relax();
-	trace_power_end(smp_processor_id());
-	trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
+	trace_power_end_rcuidle(smp_processor_id());
+	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 }
 
 /*