Merge branch 'perf-core-for-linus' of...

Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (172 commits)
  perf_event, amd: Fix spinlock initialization
  perf_event: Fix preempt warning in perf_clock()
  perf tools: Flush maps on COMM events
  perf_events, x86: Split PMU definitions into separate files
  perf annotate: Handle samples not at objdump output addr boundaries
  perf_events, x86: Remove superflous MSR writes
  perf_events: Simplify code by removing cpu argument to hw_perf_group_sched_in()
  perf_events, x86: AMD event scheduling
  perf_events: Add new start/stop PMU callbacks
  perf_events: Report the MMAP pgoff value in bytes
  perf annotate: Defer allocating sym_priv->hist array
  perf symbols: Improve debugging information about symtab origins
  perf top: Use a macro instead of a constant variable
  perf symbols: Check the right return variable
  perf/scripts: Tag syscall_name helper as not yet available
  perf/scripts: Add perf-trace-python Documentation
  perf/scripts: Remove unnecessary PyTuple resizes
  perf/scripts: Add syscall tracing scripts
  perf/scripts: Add Python scripting engine
  perf/scripts: Remove check-perf-trace from listed scripts
  ...

Fix trivial conflict in tools/perf/util/probe-event.c

Documentation/trace/kprobetrace.txt

@@ -24,6 +24,7 @@ Synopsis of kprobe_events
 -------------------------
   p[:[GRP/]EVENT] SYMBOL[+offs]|MEMADDR [FETCHARGS]	: Set a probe
   r[:[GRP/]EVENT] SYMBOL[+0] [FETCHARGS]		: Set a return probe
+  -:[GRP/]EVENT						: Clear a probe
 
  GRP		: Group name. If omitted, use "kprobes" for it.
  EVENT		: Event name. If omitted, the event name is generated
@@ -37,15 +38,12 @@ Synopsis of kprobe_events
   @SYM[+|-offs]	: Fetch memory at SYM +|- offs (SYM should be a data symbol)
   $stackN	: Fetch Nth entry of stack (N >= 0)
   $stack	: Fetch stack address.
-  $argN		: Fetch function argument. (N >= 0)(*)
-  $retval	: Fetch return value.(**)
-  +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(***)
+  $retval	: Fetch return value.(*)
+  +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
   NAME=FETCHARG: Set NAME as the argument name of FETCHARG.
 
-  (*) aN may not correct on asmlinkaged functions and at the middle of
-      function body.
-  (**) only for return probe.
-  (***) this is useful for fetching a field of data structures.
+  (*) only for return probe.
+  (**) this is useful for fetching a field of data structures.
 
 
 Per-Probe Event Filtering
@@ -82,13 +80,16 @@ Usage examples
 To add a probe as a new event, write a new definition to kprobe_events
 as below.
 
-  echo p:myprobe do_sys_open dfd=$arg0 filename=$arg1 flags=$arg2 mode=$arg3 > /sys/kernel/debug/tracing/kprobe_events
+  echo 'p:myprobe do_sys_open dfd=%ax filename=%dx flags=%cx mode=+4($stack)' > /sys/kernel/debug/tracing/kprobe_events
 
  This sets a kprobe on the top of do_sys_open() function with recording
-1st to 4th arguments as "myprobe" event. As this example shows, users can
-choose more familiar names for each arguments.
+1st to 4th arguments as "myprobe" event. Note, which register/stack entry is
+assigned to each function argument depends on arch-specific ABI. If you unsure
+the ABI, please try to use probe subcommand of perf-tools (you can find it
+under tools/perf/).
+As this example shows, users can choose more familiar names for each arguments.
 
-  echo r:myretprobe do_sys_open $retval >> /sys/kernel/debug/tracing/kprobe_events
+  echo 'r:myretprobe do_sys_open $retval' >> /sys/kernel/debug/tracing/kprobe_events
 
  This sets a kretprobe on the return point of do_sys_open() function with
 recording return value as "myretprobe" event.
@@ -97,23 +98,24 @@ recording return value as "myretprobe" event.
 
   cat /sys/kernel/debug/tracing/events/kprobes/myprobe/format
 name: myprobe
-ID: 75
+ID: 780
 format:
-	field:unsigned short common_type;	offset:0;	size:2;
-	field:unsigned char common_flags;	offset:2;	size:1;
-	field:unsigned char common_preempt_count;	offset:3;	size:1;
-	field:int common_pid;	offset:4;	size:4;
-	field:int common_tgid;	offset:8;	size:4;
+        field:unsigned short common_type;       offset:0;       size:2; signed:0;
+        field:unsigned char common_flags;       offset:2;       size:1; signed:0;
+        field:unsigned char common_preempt_count;       offset:3; size:1;signed:0;
+        field:int common_pid;   offset:4;       size:4; signed:1;
+        field:int common_lock_depth;    offset:8;       size:4; signed:1;
 
-	field: unsigned long ip;	offset:16;tsize:8;
-	field: int nargs;	offset:24;tsize:4;
-	field: unsigned long dfd;	offset:32;tsize:8;
-	field: unsigned long filename;	offset:40;tsize:8;
-	field: unsigned long flags;	offset:48;tsize:8;
-	field: unsigned long mode;	offset:56;tsize:8;
+        field:unsigned long __probe_ip; offset:12;      size:4; signed:0;
+        field:int __probe_nargs;        offset:16;      size:4; signed:1;
+        field:unsigned long dfd;        offset:20;      size:4; signed:0;
+        field:unsigned long filename;   offset:24;      size:4; signed:0;
+        field:unsigned long flags;      offset:28;      size:4; signed:0;
+        field:unsigned long mode;       offset:32;      size:4; signed:0;
 
-print fmt: "(%lx) dfd=%lx filename=%lx flags=%lx mode=%lx", REC->ip, REC->dfd, REC->filename, REC->flags, REC->mode
 
+print fmt: "(%lx) dfd=%lx filename=%lx flags=%lx mode=%lx", REC->__probe_ip,
+REC->dfd, REC->filename, REC->flags, REC->mode
 
  You can see that the event has 4 arguments as in the expressions you specified.
 
@@ -121,6 +123,12 @@ print fmt: "(%lx) dfd=%lx filename=%lx flags=%lx mode=%lx", REC->ip, REC->dfd, R
 
  This clears all probe points.
 
+ Or,
+
+  echo -:myprobe >> kprobe_events
+
+ This clears probe points selectively.
+
  Right after definition, each event is disabled by default. For tracing these
 events, you need to enable it.
 
@@ -146,4 +154,3 @@ events, you need to enable it.
 returns from SYMBOL(e.g. "sys_open+0x1b/0x1d <- do_sys_open" means kernel
 returns from do_sys_open to sys_open+0x1b).
 
-

arch/ia64/kernel/kprobes.c

@@ -870,7 +870,7 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 		return 1;
 
 ss_probe:
-#if !defined(CONFIG_PREEMPT) || defined(CONFIG_FREEZER)
+#if !defined(CONFIG_PREEMPT)
 	if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) {
 		/* Boost up -- we can execute copied instructions directly */
 		ia64_psr(regs)->ri = p->ainsn.slot;

arch/powerpc/kernel/perf_callchain.c

@@ -495,9 +495,6 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 
 	entry->nr = 0;
 
-	if (current->pid == 0)		/* idle task? */
-		return entry;
-
 	if (!user_mode(regs)) {
 		perf_callchain_kernel(regs, entry);
 		if (current->mm)

arch/powerpc/kernel/perf_event.c

@@ -718,10 +718,10 @@ static int collect_events(struct perf_event *group, int max_count,
 	return n;
 }
 
-static void event_sched_in(struct perf_event *event, int cpu)
+static void event_sched_in(struct perf_event *event)
 {
 	event->state = PERF_EVENT_STATE_ACTIVE;
-	event->oncpu = cpu;
+	event->oncpu = smp_processor_id();
 	event->tstamp_running += event->ctx->time - event->tstamp_stopped;
 	if (is_software_event(event))
 		event->pmu->enable(event);
@@ -735,7 +735,7 @@ static void event_sched_in(struct perf_event *event, int cpu)
  */
 int hw_perf_group_sched_in(struct perf_event *group_leader,
 	       struct perf_cpu_context *cpuctx,
-	       struct perf_event_context *ctx, int cpu)
+	       struct perf_event_context *ctx)
 {
 	struct cpu_hw_events *cpuhw;
 	long i, n, n0;
@@ -766,10 +766,10 @@ int hw_perf_group_sched_in(struct perf_event *group_leader,
 		cpuhw->event[i]->hw.config = cpuhw->events[i];
 	cpuctx->active_oncpu += n;
 	n = 1;
-	event_sched_in(group_leader, cpu);
+	event_sched_in(group_leader);
 	list_for_each_entry(sub, &group_leader->sibling_list, group_entry) {
 		if (sub->state != PERF_EVENT_STATE_OFF) {
-			event_sched_in(sub, cpu);
+			event_sched_in(sub);
 			++n;
 		}
 	}

arch/sh/kernel/perf_callchain.c

@@ -68,9 +68,6 @@ perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
 
 	is_user = user_mode(regs);
 
-	if (!current || current->pid == 0)
-		return;
-
 	if (is_user && current->state != TASK_RUNNING)
 		return;
 

arch/sparc/kernel/perf_event.c

@@ -980,10 +980,10 @@ static int collect_events(struct perf_event *group, int max_count,
 	return n;
 }
 
-static void event_sched_in(struct perf_event *event, int cpu)
+static void event_sched_in(struct perf_event *event)
 {
 	event->state = PERF_EVENT_STATE_ACTIVE;
-	event->oncpu = cpu;
+	event->oncpu = smp_processor_id();
 	event->tstamp_running += event->ctx->time - event->tstamp_stopped;
 	if (is_software_event(event))
 		event->pmu->enable(event);
@@ -991,7 +991,7 @@ static void event_sched_in(struct perf_event *event, int cpu)
 
 int hw_perf_group_sched_in(struct perf_event *group_leader,
 			   struct perf_cpu_context *cpuctx,
-			   struct perf_event_context *ctx, int cpu)
+			   struct perf_event_context *ctx)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct perf_event *sub;
@@ -1015,10 +1015,10 @@ int hw_perf_group_sched_in(struct perf_event *group_leader,
 
 	cpuctx->active_oncpu += n;
 	n = 1;
-	event_sched_in(group_leader, cpu);
+	event_sched_in(group_leader);
 	list_for_each_entry(sub, &group_leader->sibling_list, group_entry) {
 		if (sub->state != PERF_EVENT_STATE_OFF) {
-			event_sched_in(sub, cpu);
+			event_sched_in(sub);
 			n++;
 		}
 	}

arch/x86/include/asm/alternative.h

@@ -65,12 +65,17 @@ extern void alternatives_smp_module_add(struct module *mod, char *name,
 					void *text, void *text_end);
 extern void alternatives_smp_module_del(struct module *mod);
 extern void alternatives_smp_switch(int smp);
+extern int alternatives_text_reserved(void *start, void *end);
 #else
 static inline void alternatives_smp_module_add(struct module *mod, char *name,
 					       void *locks, void *locks_end,
 					       void *text, void *text_end) {}
 static inline void alternatives_smp_module_del(struct module *mod) {}
 static inline void alternatives_smp_switch(int smp) {}
+static inline int alternatives_text_reserved(void *start, void *end)
+{
+	return 0;
+}
 #endif	/* CONFIG_SMP */
 
 /* alternative assembly primitive: */

arch/x86/include/asm/debugreg.h

@@ -14,6 +14,9 @@
    which debugging register was responsible for the trap.  The other bits
    are either reserved or not of interest to us. */
 
+/* Define reserved bits in DR6 which are always set to 1 */
+#define DR6_RESERVED	(0xFFFF0FF0)
+
 #define DR_TRAP0	(0x1)		/* db0 */
 #define DR_TRAP1	(0x2)		/* db1 */
 #define DR_TRAP2	(0x4)		/* db2 */

arch/x86/include/asm/nmi.h

@@ -19,7 +19,6 @@ extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
 extern int check_nmi_watchdog(void);
 extern int nmi_watchdog_enabled;
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
-extern int avail_to_resrv_perfctr_nmi(unsigned int);
 extern int reserve_perfctr_nmi(unsigned int);
 extern void release_perfctr_nmi(unsigned int);
 extern int reserve_evntsel_nmi(unsigned int);

arch/x86/include/asm/perf_event.h

@@ -27,7 +27,14 @@
 /*
  * Includes eventsel and unit mask as well:
  */
-#define ARCH_PERFMON_EVENT_MASK				    0xffff
+
+
+#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.
@@ -38,7 +45,12 @@
  *  The other filters are supported by fixed counters.
  *  The any-thread option is supported starting with v3.
  */
-#define ARCH_PERFMON_EVENT_FILTER_MASK			0xff840000
+#define INTEL_ARCH_FIXED_MASK \
+	(INTEL_ARCH_CNT_MASK| \
+	 INTEL_ARCH_INV_MASK| \
+	 INTEL_ARCH_EDGE_MASK|\
+	 INTEL_ARCH_UNIT_MASK|\
+	 INTEL_ARCH_EVTSEL_MASK)
 
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL		      0x3c
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK		(0x00 << 8)

arch/x86/include/asm/ptrace.h

@@ -274,10 +274,6 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 		return 0;
 }
 
-/* Get Nth argument at function call */
-extern unsigned long regs_get_argument_nth(struct pt_regs *regs,
-					   unsigned int n);
-
 /*
  * These are defined as per linux/ptrace.h, which see.
  */

arch/x86/include/asm/stacktrace.h

@@ -3,8 +3,6 @@
 
 extern int kstack_depth_to_print;
 
-int x86_is_stack_id(int id, char *name);
-
 struct thread_info;
 struct stacktrace_ops;
 

arch/x86/kernel/alternative.c

@@ -390,6 +390,24 @@ void alternatives_smp_switch(int smp)
 	mutex_unlock(&smp_alt);
 }
 
+/* Return 1 if the address range is reserved for smp-alternatives */
+int alternatives_text_reserved(void *start, void *end)
+{
+	struct smp_alt_module *mod;
+	u8 **ptr;
+	u8 *text_start = start;
+	u8 *text_end = end;
+
+	list_for_each_entry(mod, &smp_alt_modules, next) {
+		if (mod->text > text_end || mod->text_end < text_start)
+			continue;
+		for (ptr = mod->locks; ptr < mod->locks_end; ptr++)
+			if (text_start <= *ptr && text_end >= *ptr)
+				return 1;
+	}
+
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_PARAVIRT

arch/x86/kernel/cpu/perf_event_p6.c

+#ifdef CONFIG_CPU_SUP_INTEL
+
+/*
+ * Not sure about some of these
+ */
+static const u64 p6_perfmon_event_map[] =
+{
+  [PERF_COUNT_HW_CPU_CYCLES]		= 0x0079,
+  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
+  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x0f2e,
+  [PERF_COUNT_HW_CACHE_MISSES]		= 0x012e,
+  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,
+  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,
+  [PERF_COUNT_HW_BUS_CYCLES]		= 0x0062,
+};
+
+static u64 p6_pmu_event_map(int hw_event)
+{
+	return p6_perfmon_event_map[hw_event];
+}
+
+/*
+ * Event setting that is specified not to count anything.
+ * We use this to effectively disable a counter.
+ *
+ * L2_RQSTS with 0 MESI unit mask.
+ */
+#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 */
+	INTEL_EVENT_CONSTRAINT(0x10, 0x1),	/* FP_COMP_OPS_EXE */
+	INTEL_EVENT_CONSTRAINT(0x11, 0x1),	/* FP_ASSIST */
+	INTEL_EVENT_CONSTRAINT(0x12, 0x2),	/* MUL */
+	INTEL_EVENT_CONSTRAINT(0x13, 0x2),	/* DIV */
+	INTEL_EVENT_CONSTRAINT(0x14, 0x1),	/* CYCLES_DIV_BUSY */
+	EVENT_CONSTRAINT_END
+};
+
+static void p6_pmu_disable_all(void)
+{
+	u64 val;
+
+	/* p6 only has one enable register */
+	rdmsrl(MSR_P6_EVNTSEL0, val);
+	val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+	wrmsrl(MSR_P6_EVNTSEL0, val);
+}
+
+static void p6_pmu_enable_all(void)
+{
+	unsigned long val;
+
+	/* p6 only has one enable register */
+	rdmsrl(MSR_P6_EVNTSEL0, val);
+	val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+	wrmsrl(MSR_P6_EVNTSEL0, val);
+}
+
+static inline void
+p6_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	u64 val = P6_NOP_EVENT;
+
+	if (cpuc->enabled)
+		val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+
+	(void)checking_wrmsrl(hwc->config_base + idx, val);
+}
+
+static void p6_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	u64 val;
+
+	val = hwc->config;
+	if (cpuc->enabled)
+		val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+
+	(void)checking_wrmsrl(hwc->config_base + idx, val);
+}
+
+static __initconst 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,
+	.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,
+	/*
+	 * Events have 40 bits implemented. However they are designed such
+	 * that bits [32-39] are sign extensions of bit 31. As such the
+	 * effective width of a event for P6-like PMU is 32 bits only.
+	 *
+	 * See IA-32 Intel Architecture Software developer manual Vol 3B
+	 */
+	.event_bits		= 32,
+	.event_mask		= (1ULL << 32) - 1,
+	.get_event_constraints	= x86_get_event_constraints,
+	.event_constraints	= p6_event_constraints,
+};
+
+static __init int p6_pmu_init(void)
+{
+	switch (boot_cpu_data.x86_model) {
+	case 1:
+	case 3:  /* Pentium Pro */
+	case 5:
+	case 6:  /* Pentium II */
+	case 7:
+	case 8:
+	case 11: /* Pentium III */
+	case 9:
+	case 13:
+		/* Pentium M */
+		break;
+	default:
+		pr_cont("unsupported p6 CPU model %d ",
+			boot_cpu_data.x86_model);
+		return -ENODEV;
+	}
+
+	x86_pmu = p6_pmu;
+
+	return 0;
+}
+
+#endif /* CONFIG_CPU_SUP_INTEL */

arch/x86/kernel/cpu/perfctr-watchdog.c

@@ -115,17 +115,6 @@ int avail_to_resrv_perfctr_nmi_bit(unsigned int counter)
 
 	return !test_bit(counter, perfctr_nmi_owner);
 }
-
-/* checks the an msr for availability */
-int avail_to_resrv_perfctr_nmi(unsigned int msr)
-{
-	unsigned int counter;
-
-	counter = nmi_perfctr_msr_to_bit(msr);
-	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
-
-	return !test_bit(counter, perfctr_nmi_owner);
-}
 EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit);
 
 int reserve_perfctr_nmi(unsigned int msr)

arch/x86/kernel/dumpstack_32.c

@@ -18,11 +18,6 @@
 
 #include "dumpstack.h"
 
-/* Just a stub for now */
-int x86_is_stack_id(int id, char *name)
-{
-	return 0;
-}
 
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,

arch/x86/kernel/dumpstack_64.c

@@ -33,11 +33,6 @@ static char x86_stack_ids[][8] = {
 #endif
 };
 
-int x86_is_stack_id(int id, char *name)
-{
-	return x86_stack_ids[id - 1] == name;
-}
-
 static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
 					 unsigned *usedp, char **idp)
 {

arch/x86/kernel/hw_breakpoint.c

@@ -486,8 +486,6 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 		rcu_read_lock();
 
 		bp = per_cpu(bp_per_reg[i], cpu);
-		if (bp)
-			rc = NOTIFY_DONE;
 		/*
 		 * Reset the 'i'th TRAP bit in dr6 to denote completion of
 		 * exception handling
@@ -506,7 +504,13 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 
 		rcu_read_unlock();
 	}
-	if (dr6 & (~DR_TRAP_BITS))
+	/*
+	 * Further processing in do_debug() is needed for a) user-space
+	 * breakpoints (to generate signals) and b) when the system has
+	 * taken exception due to multiple causes
+	 */
+	if ((current->thread.debugreg6 & DR_TRAP_BITS) ||
+	    (dr6 & (~DR_TRAP_BITS)))
 		rc = NOTIFY_DONE;
 
 	set_debugreg(dr7, 7);

arch/x86/kernel/kprobes.c

@@ -337,6 +337,9 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p)
 
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
 {
+	if (alternatives_text_reserved(p->addr, p->addr))
+		return -EINVAL;
+
 	if (!can_probe((unsigned long)p->addr))
 		return -EILSEQ;
 	/* insn: must be on special executable page on x86. */
@@ -429,7 +432,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs,
 				       struct kprobe_ctlblk *kcb)
 {
-#if !defined(CONFIG_PREEMPT) || defined(CONFIG_FREEZER)
+#if !defined(CONFIG_PREEMPT)
 	if (p->ainsn.boostable == 1 && !p->post_handler) {
 		/* Boost up -- we can execute copied instructions directly */
 		reset_current_kprobe();

arch/x86/kernel/ptrace.c

@@ -140,30 +140,6 @@ static const int arg_offs_table[] = {
 #endif
 };
 
-/**
- * regs_get_argument_nth() - get Nth argument at function call
- * @regs:	pt_regs which contains registers at function entry.
- * @n:		argument number.
- *
- * regs_get_argument_nth() returns @n th argument of a function call.
- * Since usually the kernel stack will be changed right after function entry,
- * you must use this at function entry. If the @n th entry is NOT in the
- * kernel stack or pt_regs, this returns 0.
- */
-unsigned long regs_get_argument_nth(struct pt_regs *regs, unsigned int n)
-{
-	if (n < ARRAY_SIZE(arg_offs_table))
-		return *(unsigned long *)((char *)regs + arg_offs_table[n]);
-	else {
-		/*
-		 * The typical case: arg n is on the stack.
-		 * (Note: stack[0] = return address, so skip it)
-		 */
-		n -= ARRAY_SIZE(arg_offs_table);
-		return regs_get_kernel_stack_nth(regs, 1 + n);
-	}
-}
-
 /*
  * does not yet catch signals sent when the child dies.
  * in exit.c or in signal.c.

arch/x86/kernel/traps.c

@@ -534,6 +534,9 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 
 	get_debugreg(dr6, 6);
 
+	/* Filter out all the reserved bits which are preset to 1 */
+	dr6 &= ~DR6_RESERVED;
+
 	/* Catch kmemcheck conditions first of all! */
 	if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
 		return;

include/linux/bitops.h

@@ -45,6 +45,31 @@ static inline unsigned long hweight_long(unsigned long w)
 	return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
 }
 
+/*
+ * Clearly slow versions of the hweightN() functions, their benefit is
+ * of course compile time evaluation of constant arguments.
+ */
+#define HWEIGHT8(w)					\
+      (	BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) +	\
+	(!!((w) & (1ULL << 0))) +			\
+	(!!((w) & (1ULL << 1))) +			\
+	(!!((w) & (1ULL << 2))) +			\
+	(!!((w) & (1ULL << 3))) +			\
+	(!!((w) & (1ULL << 4))) +			\
+	(!!((w) & (1ULL << 5))) +			\
+	(!!((w) & (1ULL << 6))) +			\
+	(!!((w) & (1ULL << 7)))	)
+
+#define HWEIGHT16(w) (HWEIGHT8(w)  + HWEIGHT8((w) >> 8))
+#define HWEIGHT32(w) (HWEIGHT16(w) + HWEIGHT16((w) >> 16))
+#define HWEIGHT64(w) (HWEIGHT32(w) + HWEIGHT32((w) >> 32))
+
+/*
+ * Type invariant version that simply casts things to the
+ * largest type.
+ */
+#define HWEIGHT(w)   HWEIGHT64((u64)(w))
+
 /**
  * rol32 - rotate a 32-bit value left
  * @word: value to rotate

include/linux/ftrace.h

@@ -134,6 +134,8 @@ extern void
 unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops);
 extern void unregister_ftrace_function_probe_all(char *glob);
 
+extern int ftrace_text_reserved(void *start, void *end);
+
 enum {
 	FTRACE_FL_FREE		= (1 << 0),
 	FTRACE_FL_FAILED	= (1 << 1),
@@ -141,7 +143,6 @@ enum {
 	FTRACE_FL_ENABLED	= (1 << 3),
 	FTRACE_FL_NOTRACE	= (1 << 4),
 	FTRACE_FL_CONVERTED	= (1 << 5),
-	FTRACE_FL_FROZEN	= (1 << 6),
 };
 
 struct dyn_ftrace {
@@ -250,6 +251,10 @@ static inline int unregister_ftrace_command(char *cmd_name)
 {
 	return -EINVAL;
 }
+static inline int ftrace_text_reserved(void *start, void *end)
+{
+	return 0;
+}
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 /* totally disable ftrace - can not re-enable after this */

include/linux/ftrace_event.h

@@ -5,6 +5,7 @@
 #include <linux/trace_seq.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
+#include <linux/perf_event.h>
 
 struct trace_array;
 struct tracer;
@@ -137,9 +138,6 @@ struct ftrace_event_call {
 
 #define FTRACE_MAX_PROFILE_SIZE	2048
 
-extern char *perf_trace_buf;
-extern char *perf_trace_buf_nmi;
-
 #define MAX_FILTER_PRED		32
 #define MAX_FILTER_STR_VAL	256	/* Should handle KSYM_SYMBOL_LEN */
 
@@ -187,13 +185,27 @@ do {									\
 		__trace_printk(ip, fmt, ##args);			\
 } while (0)
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
 struct perf_event;
 extern int ftrace_profile_enable(int event_id);
 extern void ftrace_profile_disable(int event_id);
 extern int ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);
+extern void *
+ftrace_perf_buf_prepare(int size, unsigned short type, int *rctxp,
+			 unsigned long *irq_flags);
+
+static inline void
+ftrace_perf_buf_submit(void *raw_data, int size, int rctx, u64 addr,
+		       u64 count, unsigned long irq_flags)
+{
+	struct trace_entry *entry = raw_data;
+
+	perf_tp_event(entry->type, addr, count, raw_data, size);
+	perf_swevent_put_recursion_context(rctx);
+	local_irq_restore(irq_flags);
+}
 #endif
 
 #endif /* _LINUX_FTRACE_EVENT_H */

include/linux/list.h

@@ -205,6 +205,20 @@ static inline int list_empty_careful(const struct list_head *head)
 	return (next == head) && (next == head->prev);
 }
 
+/**
+ * list_rotate_left - rotate the list to the left
+ * @head: the head of the list
+ */
+static inline void list_rotate_left(struct list_head *head)
+{
+	struct list_head *first;
+
+	if (!list_empty(head)) {
+		first = head->next;
+		list_move_tail(first, head);
+	}
+}
+
 /**
  * list_is_singular - tests whether a list has just one entry.
  * @head: the list to test.

include/linux/perf_event.h

@@ -476,9 +476,11 @@ struct hw_perf_event {
 	union {
 		struct { /* hardware */
 			u64		config;
+			u64		last_tag;
 			unsigned long	config_base;
 			unsigned long	event_base;
 			int		idx;
+			int		last_cpu;
 		};
 		struct { /* software */
 			s64		remaining;
@@ -496,9 +498,8 @@ struct hw_perf_event {
 	atomic64_t			period_left;
 	u64				interrupts;
 
-	u64				freq_count;
-	u64				freq_interrupts;
-	u64				freq_stamp;
+	u64				freq_time_stamp;
+	u64				freq_count_stamp;
 #endif
 };
 
@@ -510,6 +511,8 @@ struct perf_event;
 struct pmu {
 	int (*enable)			(struct perf_event *event);
 	void (*disable)			(struct perf_event *event);
+	int (*start)			(struct perf_event *event);
+	void (*stop)			(struct perf_event *event);
 	void (*read)			(struct perf_event *event);
 	void (*unthrottle)		(struct perf_event *event);
 };
@@ -563,6 +566,10 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *, int,
 					struct perf_sample_data *,
 					struct pt_regs *regs);
 
+enum perf_group_flag {
+	PERF_GROUP_SOFTWARE = 0x1,
+};
+
 /**
  * struct perf_event - performance event kernel representation:
  */
@@ -572,6 +579,7 @@ struct perf_event {
 	struct list_head		event_entry;
 	struct list_head		sibling_list;
 	int				nr_siblings;
+	int				group_flags;
 	struct perf_event		*group_leader;
 	struct perf_event		*output;
 	const struct pmu		*pmu;
@@ -656,7 +664,7 @@ struct perf_event {
 
 	perf_overflow_handler_t		overflow_handler;
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_EVENT_TRACING
 	struct event_filter		*filter;
 #endif
 
@@ -681,7 +689,8 @@ struct perf_event_context {
 	 */
 	struct mutex			mutex;
 
-	struct list_head		group_list;
+	struct list_head		pinned_groups;
+	struct list_head		flexible_groups;
 	struct list_head		event_list;
 	int				nr_events;
 	int				nr_active;
@@ -744,10 +753,9 @@ extern int perf_max_events;
 
 extern const struct pmu *hw_perf_event_init(struct perf_event *event);
 
-extern void perf_event_task_sched_in(struct task_struct *task, int cpu);
-extern void perf_event_task_sched_out(struct task_struct *task,
-					struct task_struct *next, int cpu);
-extern void perf_event_task_tick(struct task_struct *task, int cpu);
+extern void perf_event_task_sched_in(struct task_struct *task);
+extern void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next);
+extern void perf_event_task_tick(struct task_struct *task);
 extern int perf_event_init_task(struct task_struct *child);
 extern void perf_event_exit_task(struct task_struct *child);
 extern void perf_event_free_task(struct task_struct *task);
@@ -762,7 +770,7 @@ extern int perf_event_task_disable(void);
 extern int perf_event_task_enable(void);
 extern int hw_perf_group_sched_in(struct perf_event *group_leader,
 	       struct perf_cpu_context *cpuctx,
-	       struct perf_event_context *ctx, int cpu);
+	       struct perf_event_context *ctx);
 extern void perf_event_update_userpage(struct perf_event *event);
 extern int perf_event_release_kernel(struct perf_event *event);
 extern struct perf_event *
@@ -851,8 +859,7 @@ extern int sysctl_perf_event_mlock;
 extern int sysctl_perf_event_sample_rate;
 
 extern void perf_event_init(void);
-extern void perf_tp_event(int event_id, u64 addr, u64 count,
-				 void *record, int entry_size);
+extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
@@ -873,12 +880,12 @@ extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
 #else
 static inline void
-perf_event_task_sched_in(struct task_struct *task, int cpu)		{ }
+perf_event_task_sched_in(struct task_struct *task)			{ }
 static inline void
 perf_event_task_sched_out(struct task_struct *task,
-			    struct task_struct *next, int cpu)		{ }
+			    struct task_struct *next)			{ }
 static inline void
-perf_event_task_tick(struct task_struct *task, int cpu)			{ }
+perf_event_task_tick(struct task_struct *task)				{ }
 static inline int perf_event_init_task(struct task_struct *child)	{ return 0; }
 static inline void perf_event_exit_task(struct task_struct *child)	{ }
 static inline void perf_event_free_task(struct task_struct *task)	{ }

include/linux/syscalls.h

@@ -99,7 +99,7 @@ struct perf_event_attr;
 #define __SC_TEST5(t5, a5, ...)	__SC_TEST(t5); __SC_TEST4(__VA_ARGS__)
 #define __SC_TEST6(t6, a6, ...)	__SC_TEST(t6); __SC_TEST5(__VA_ARGS__)
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
 
 #define TRACE_SYS_ENTER_PROFILE_INIT(sname)				       \
 	.profile_enable = prof_sysenter_enable,				       \
@@ -113,7 +113,7 @@ struct perf_event_attr;
 #define TRACE_SYS_ENTER_PROFILE_INIT(sname)
 #define TRACE_SYS_EXIT_PROFILE(sname)
 #define TRACE_SYS_EXIT_PROFILE_INIT(sname)
-#endif
+#endif /* CONFIG_PERF_EVENTS */
 
 #ifdef CONFIG_FTRACE_SYSCALLS
 #define __SC_STR_ADECL1(t, a)		#a

include/trace/events/lock.h

@@ -20,14 +20,17 @@ TRACE_EVENT(lock_acquire,
 	TP_STRUCT__entry(
 		__field(unsigned int, flags)
 		__string(name, lock->name)
+		__field(void *, lockdep_addr)
 	),
 
 	TP_fast_assign(
 		__entry->flags = (trylock ? 1 : 0) | (read ? 2 : 0);
 		__assign_str(name, lock->name);
+		__entry->lockdep_addr = lock;
 	),
 
-	TP_printk("%s%s%s", (__entry->flags & 1) ? "try " : "",
+	TP_printk("%p %s%s%s", __entry->lockdep_addr,
+		  (__entry->flags & 1) ? "try " : "",
 		  (__entry->flags & 2) ? "read " : "",
 		  __get_str(name))
 );
@@ -40,13 +43,16 @@ TRACE_EVENT(lock_release,
 
 	TP_STRUCT__entry(
 		__string(name, lock->name)
+		__field(void *, lockdep_addr)
 	),
 
 	TP_fast_assign(
 		__assign_str(name, lock->name);
+		__entry->lockdep_addr = lock;
 	),
 
-	TP_printk("%s", __get_str(name))
+	TP_printk("%p %s",
+		  __entry->lockdep_addr, __get_str(name))
 );
 
 #ifdef CONFIG_LOCK_STAT
@@ -59,13 +65,16 @@ TRACE_EVENT(lock_contended,
 
 	TP_STRUCT__entry(
 		__string(name, lock->name)
+		__field(void *, lockdep_addr)
 	),
 
 	TP_fast_assign(
 		__assign_str(name, lock->name);
+		__entry->lockdep_addr = lock;
 	),
 
-	TP_printk("%s", __get_str(name))
+	TP_printk("%p %s",
+		  __entry->lockdep_addr, __get_str(name))
 );
 
 TRACE_EVENT(lock_acquired,
@@ -75,16 +84,18 @@ TRACE_EVENT(lock_acquired,
 
 	TP_STRUCT__entry(
 		__string(name, lock->name)
-		__field(unsigned long, wait_usec)
-		__field(unsigned long, wait_nsec_rem)
+		__field(s64, wait_nsec)
+		__field(void *, lockdep_addr)
 	),
+
 	TP_fast_assign(
 		__assign_str(name, lock->name);
-		__entry->wait_nsec_rem = do_div(waittime, NSEC_PER_USEC);
-		__entry->wait_usec = (unsigned long) waittime;
+		__entry->wait_nsec = waittime;
+		__entry->lockdep_addr = lock;
 	),
-	TP_printk("%s (%lu.%03lu us)", __get_str(name), __entry->wait_usec,
-				       __entry->wait_nsec_rem)
+	TP_printk("%p %s (%llu ns)", __entry->lockdep_addr,
+		  __get_str(name),
+		  __entry->wait_nsec)
 );
 
 #endif

include/trace/ftrace.h

@@ -376,7 +376,7 @@ static inline notrace int ftrace_get_offsets_##call(			\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
 
 /*
  * Generate the functions needed for tracepoint perf_event support.
@@ -421,7 +421,7 @@ ftrace_profile_disable_##name(struct ftrace_event_call *unused)		\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#endif
+#endif /* CONFIG_PERF_EVENTS */
 
 /*
  * Stage 4 of the trace events.
@@ -505,7 +505,7 @@ ftrace_profile_disable_##name(struct ftrace_event_call *unused)		\
  *
  */
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
 
 #define _TRACE_PROFILE_INIT(call)					\
 	.profile_enable = ftrace_profile_enable_##call,			\
@@ -513,7 +513,7 @@ ftrace_profile_disable_##name(struct ftrace_event_call *unused)		\
 
 #else
 #define _TRACE_PROFILE_INIT(call)
-#endif
+#endif /* CONFIG_PERF_EVENTS */
 
 #undef __entry
 #define __entry entry
@@ -736,7 +736,7 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
  * }
  */
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
 
 #undef __entry
 #define __entry entry
@@ -761,22 +761,12 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
 			    proto)					\
 {									\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
-	extern int perf_swevent_get_recursion_context(void);		\
-	extern void perf_swevent_put_recursion_context(int rctx);	\
-	extern void perf_tp_event(int, u64, u64, void *, int);		\
 	struct ftrace_raw_##call *entry;				\
 	u64 __addr = 0, __count = 1;					\
 	unsigned long irq_flags;					\
-	struct trace_entry *ent;					\
 	int __entry_size;						\
 	int __data_size;						\
-	char *trace_buf;						\
-	char *raw_data;							\
-	int __cpu;							\
 	int rctx;							\
-	int pc;								\
-									\
-	pc = preempt_count();						\
 									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
 	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
@@ -786,42 +776,16 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
 	if (WARN_ONCE(__entry_size > FTRACE_MAX_PROFILE_SIZE,		\
 		      "profile buffer not large enough"))		\
 		return;							\
-									\
-	local_irq_save(irq_flags);					\
-									\
-	rctx = perf_swevent_get_recursion_context();			\
-	if (rctx < 0)							\
-		goto end_recursion;					\
-									\
-	__cpu = smp_processor_id();					\
-									\
-	if (in_nmi())							\
-		trace_buf = rcu_dereference(perf_trace_buf_nmi);	\
-	else								\
-		trace_buf = rcu_dereference(perf_trace_buf);		\
-									\
-	if (!trace_buf)							\
-		goto end;						\
-									\
-	raw_data = per_cpu_ptr(trace_buf, __cpu);			\
-									\
-	*(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;		\
-	entry = (struct ftrace_raw_##call *)raw_data;			\
-	ent = &entry->ent;						\
-	tracing_generic_entry_update(ent, irq_flags, pc);		\
-	ent->type = event_call->id;					\
-									\
+	entry = (struct ftrace_raw_##call *)ftrace_perf_buf_prepare(	\
+		__entry_size, event_call->id, &rctx, &irq_flags);	\
+	if (!entry)							\
+		return;							\
 	tstruct								\
 									\
 	{ assign; }							\
 									\
-	perf_tp_event(event_call->id, __addr, __count, entry,		\
-			     __entry_size);				\
-									\
-end:									\
-	perf_swevent_put_recursion_context(rctx);			\
-end_recursion:								\
-	local_irq_restore(irq_flags);					\
+	ftrace_perf_buf_submit(entry, __entry_size, rctx, __addr,	\
+			       __count, irq_flags);			\
 }
 
 #undef DEFINE_EVENT
@@ -838,7 +802,7 @@ static notrace void ftrace_profile_##call(proto)		\
 	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
-#endif /* CONFIG_EVENT_PROFILE */
+#endif /* CONFIG_PERF_EVENTS */
 
 #undef _TRACE_PROFILE_INIT
 

include/trace/syscall.h

@@ -45,12 +45,12 @@ ftrace_format_syscall(struct ftrace_event_call *call, struct trace_seq *s);
 enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags);
 enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags);
 #endif
-#ifdef CONFIG_EVENT_PROFILE
+
+#ifdef CONFIG_PERF_EVENTS
 int prof_sysenter_enable(struct ftrace_event_call *call);
 void prof_sysenter_disable(struct ftrace_event_call *call);
 int prof_sysexit_enable(struct ftrace_event_call *call);
 void prof_sysexit_disable(struct ftrace_event_call *call);
-
 #endif
 
 #endif /* _TRACE_SYSCALL_H */

init/Kconfig

@@ -992,19 +992,6 @@ config PERF_EVENTS
 
 	  Say Y if unsure.
 
-config EVENT_PROFILE
-	bool "Tracepoint profiling sources"
-	depends on PERF_EVENTS && EVENT_TRACING
-	default y
-	help
-	 Allow the use of tracepoints as software performance events.
-
-	 When this is enabled, you can create perf events based on
-	 tracepoints using PERF_TYPE_TRACEPOINT and the tracepoint ID
-	 found in debugfs://tracing/events/*/*/id. (The -e/--events
-	 option to the perf tool can parse and interpret symbolic
-	 tracepoints, in the subsystem:tracepoint_name format.)
-
 config PERF_COUNTERS
 	bool "Kernel performance counters (old config option)"
 	depends on HAVE_PERF_EVENTS

kernel/kprobes.c

@@ -44,6 +44,7 @@
 #include <linux/debugfs.h>
 #include <linux/kdebug.h>
 #include <linux/memory.h>
+#include <linux/ftrace.h>
 
 #include <asm-generic/sections.h>
 #include <asm/cacheflush.h>
@@ -125,30 +126,6 @@ static LIST_HEAD(kprobe_insn_pages);
 static int kprobe_garbage_slots;
 static int collect_garbage_slots(void);
 
-static int __kprobes check_safety(void)
-{
-	int ret = 0;
-#if defined(CONFIG_PREEMPT) && defined(CONFIG_FREEZER)
-	ret = freeze_processes();
-	if (ret == 0) {
-		struct task_struct *p, *q;
-		do_each_thread(p, q) {
-			if (p != current && p->state == TASK_RUNNING &&
-			    p->pid != 0) {
-				printk("Check failed: %s is running\n",p->comm);
-				ret = -1;
-				goto loop_end;
-			}
-		} while_each_thread(p, q);
-	}
-loop_end:
-	thaw_processes();
-#else
-	synchronize_sched();
-#endif
-	return ret;
-}
-
 /**
  * __get_insn_slot() - Find a slot on an executable page for an instruction.
  * We allocate an executable page if there's no room on existing ones.
@@ -236,9 +213,8 @@ static int __kprobes collect_garbage_slots(void)
 {
 	struct kprobe_insn_page *kip, *next;
 
-	/* Ensure no-one is preepmted on the garbages */
-	if (check_safety())
-		return -EAGAIN;
+	/* Ensure no-one is interrupted on the garbages */
+	synchronize_sched();
 
 	list_for_each_entry_safe(kip, next, &kprobe_insn_pages, list) {
 		int i;
@@ -729,7 +705,8 @@ int __kprobes register_kprobe(struct kprobe *p)
 
 	preempt_disable();
 	if (!kernel_text_address((unsigned long) p->addr) ||
-	    in_kprobes_functions((unsigned long) p->addr)) {
+	    in_kprobes_functions((unsigned long) p->addr) ||
+	    ftrace_text_reserved(p->addr, p->addr)) {
 		preempt_enable();
 		return -EINVAL;
 	}

kernel/sched.c

@@ -2799,7 +2799,13 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	 */
 	prev_state = prev->state;
 	finish_arch_switch(prev);
-	perf_event_task_sched_in(current, cpu_of(rq));
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+	local_irq_disable();
+#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
+	perf_event_task_sched_in(current);
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+	local_irq_enable();
+#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
 	finish_lock_switch(rq, prev);
 
 	fire_sched_in_preempt_notifiers(current);
@@ -5314,7 +5320,7 @@ void scheduler_tick(void)
 	curr->sched_class->task_tick(rq, curr, 0);
 	raw_spin_unlock(&rq->lock);
 
-	perf_event_task_tick(curr, cpu);
+	perf_event_task_tick(curr);
 
 #ifdef CONFIG_SMP
 	rq->idle_at_tick = idle_cpu(cpu);
@@ -5528,7 +5534,7 @@ asmlinkage void __sched schedule(void)
 
 	if (likely(prev != next)) {
 		sched_info_switch(prev, next);
-		perf_event_task_sched_out(prev, next, cpu);
+		perf_event_task_sched_out(prev, next);
 
 		rq->nr_switches++;
 		rq->curr = next;

kernel/trace/Makefile

@@ -51,7 +51,9 @@ endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events.o
 obj-$(CONFIG_EVENT_TRACING) += trace_export.o
 obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
-obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
+ifeq ($(CONFIG_PERF_EVENTS),y)
+obj-$(CONFIG_EVENT_TRACING) += trace_event_profile.o
+endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
 obj-$(CONFIG_KSYM_TRACER) += trace_ksym.o

kernel/trace/ftrace.c

@@ -22,7 +22,6 @@
 #include <linux/hardirq.h>
 #include <linux/kthread.h>
 #include <linux/uaccess.h>
-#include <linux/kprobes.h>
 #include <linux/ftrace.h>
 #include <linux/sysctl.h>
 #include <linux/ctype.h>
@@ -898,36 +897,6 @@ static struct dyn_ftrace *ftrace_free_records;
 		}				\
 	}
 
-#ifdef CONFIG_KPROBES
-
-static int frozen_record_count;
-
-static inline void freeze_record(struct dyn_ftrace *rec)
-{
-	if (!(rec->flags & FTRACE_FL_FROZEN)) {
-		rec->flags |= FTRACE_FL_FROZEN;
-		frozen_record_count++;
-	}
-}
-
-static inline void unfreeze_record(struct dyn_ftrace *rec)
-{
-	if (rec->flags & FTRACE_FL_FROZEN) {
-		rec->flags &= ~FTRACE_FL_FROZEN;
-		frozen_record_count--;
-	}
-}
-
-static inline int record_frozen(struct dyn_ftrace *rec)
-{
-	return rec->flags & FTRACE_FL_FROZEN;
-}
-#else
-# define freeze_record(rec)			({ 0; })
-# define unfreeze_record(rec)			({ 0; })
-# define record_frozen(rec)			({ 0; })
-#endif /* CONFIG_KPROBES */
-
 static void ftrace_free_rec(struct dyn_ftrace *rec)
 {
 	rec->freelist = ftrace_free_records;
@@ -1025,6 +994,21 @@ static void ftrace_bug(int failed, unsigned long ip)
 }
 
 
+/* Return 1 if the address range is reserved for ftrace */
+int ftrace_text_reserved(void *start, void *end)
+{
+	struct dyn_ftrace *rec;
+	struct ftrace_page *pg;
+
+	do_for_each_ftrace_rec(pg, rec) {
+		if (rec->ip <= (unsigned long)end &&
+		    rec->ip + MCOUNT_INSN_SIZE > (unsigned long)start)
+			return 1;
+	} while_for_each_ftrace_rec();
+	return 0;
+}
+
+
 static int
 __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 {
@@ -1076,14 +1060,6 @@ static void ftrace_replace_code(int enable)
 		    !(rec->flags & FTRACE_FL_CONVERTED))
 			continue;
 
-		/* ignore updates to this record's mcount site */
-		if (get_kprobe((void *)rec->ip)) {
-			freeze_record(rec);
-			continue;
-		} else {
-			unfreeze_record(rec);
-		}
-
 		failed = __ftrace_replace_code(rec, enable);
 		if (failed) {
 			rec->flags |= FTRACE_FL_FAILED;

kernel/trace/trace_event_profile.c

@@ -6,14 +6,12 @@
  */
 
 #include <linux/module.h>
+#include <linux/kprobes.h>
 #include "trace.h"
 
 
-char *perf_trace_buf;
-EXPORT_SYMBOL_GPL(perf_trace_buf);
-
-char *perf_trace_buf_nmi;
-EXPORT_SYMBOL_GPL(perf_trace_buf_nmi);
+static char *perf_trace_buf;
+static char *perf_trace_buf_nmi;
 
 typedef typeof(char [FTRACE_MAX_PROFILE_SIZE]) perf_trace_t ;
 
@@ -120,3 +118,47 @@ void ftrace_profile_disable(int event_id)
 	}
 	mutex_unlock(&event_mutex);
 }
+
+__kprobes void *ftrace_perf_buf_prepare(int size, unsigned short type,
+					int *rctxp, unsigned long *irq_flags)
+{
+	struct trace_entry *entry;
+	char *trace_buf, *raw_data;
+	int pc, cpu;
+
+	pc = preempt_count();
+
+	/* Protect the per cpu buffer, begin the rcu read side */
+	local_irq_save(*irq_flags);
+
+	*rctxp = perf_swevent_get_recursion_context();
+	if (*rctxp < 0)
+		goto err_recursion;
+
+	cpu = smp_processor_id();
+
+	if (in_nmi())
+		trace_buf = rcu_dereference(perf_trace_buf_nmi);
+	else
+		trace_buf = rcu_dereference(perf_trace_buf);
+
+	if (!trace_buf)
+		goto err;
+
+	raw_data = per_cpu_ptr(trace_buf, cpu);
+
+	/* zero the dead bytes from align to not leak stack to user */
+	*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+
+	entry = (struct trace_entry *)raw_data;
+	tracing_generic_entry_update(entry, *irq_flags, pc);
+	entry->type = type;
+
+	return raw_data;
+err:
+	perf_swevent_put_recursion_context(*rctxp);
+err_recursion:
+	local_irq_restore(*irq_flags);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(ftrace_perf_buf_prepare);

kernel/trace/trace_events_filter.c

@@ -1371,7 +1371,7 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 	return err;
 }
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
 
 void ftrace_profile_free_filter(struct perf_event *event)
 {
@@ -1439,5 +1439,5 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
 	return err;
 }
 
-#endif /* CONFIG_EVENT_PROFILE */
+#endif /* CONFIG_PERF_EVENTS */
 

kernel/trace/trace_syscalls.c

@@ -426,7 +426,7 @@ int __init init_ftrace_syscalls(void)
 }
 core_initcall(init_ftrace_syscalls);
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
 
 static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls);
 static DECLARE_BITMAP(enabled_prof_exit_syscalls, NR_syscalls);
@@ -438,12 +438,9 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_enter *rec;
 	unsigned long flags;
-	char *trace_buf;
-	char *raw_data;
 	int syscall_nr;
 	int rctx;
 	int size;
-	int cpu;
 
 	syscall_nr = syscall_get_nr(current, regs);
 	if (!test_bit(syscall_nr, enabled_prof_enter_syscalls))
@@ -462,37 +459,15 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
 		      "profile buffer not large enough"))
 		return;
 
-	/* Protect the per cpu buffer, begin the rcu read side */
-	local_irq_save(flags);
-
-	rctx = perf_swevent_get_recursion_context();
-	if (rctx < 0)
-		goto end_recursion;
-
-	cpu = smp_processor_id();
-
-	trace_buf = rcu_dereference(perf_trace_buf);
-
-	if (!trace_buf)
-		goto end;
-
-	raw_data = per_cpu_ptr(trace_buf, cpu);
-
-	/* zero the dead bytes from align to not leak stack to user */
-	*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+	rec = (struct syscall_trace_enter *)ftrace_perf_buf_prepare(size,
+				sys_data->enter_event->id, &rctx, &flags);
+	if (!rec)
+		return;
 
-	rec = (struct syscall_trace_enter *) raw_data;
-	tracing_generic_entry_update(&rec->ent, 0, 0);
-	rec->ent.type = sys_data->enter_event->id;
 	rec->nr = syscall_nr;
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
 			       (unsigned long *)&rec->args);
-	perf_tp_event(sys_data->enter_event->id, 0, 1, rec, size);
-
-end:
-	perf_swevent_put_recursion_context(rctx);
-end_recursion:
-	local_irq_restore(flags);
+	ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags);
 }
 
 int prof_sysenter_enable(struct ftrace_event_call *call)
@@ -536,11 +511,8 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
 	struct syscall_trace_exit *rec;
 	unsigned long flags;
 	int syscall_nr;
-	char *trace_buf;
-	char *raw_data;
 	int rctx;
 	int size;
-	int cpu;
 
 	syscall_nr = syscall_get_nr(current, regs);
 	if (!test_bit(syscall_nr, enabled_prof_exit_syscalls))
@@ -562,38 +534,15 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
 		"exit event has grown above profile buffer size"))
 		return;
 
-	/* Protect the per cpu buffer, begin the rcu read side */
-	local_irq_save(flags);
-
-	rctx = perf_swevent_get_recursion_context();
-	if (rctx < 0)
-		goto end_recursion;
-
-	cpu = smp_processor_id();
-
-	trace_buf = rcu_dereference(perf_trace_buf);
-
-	if (!trace_buf)
-		goto end;
-
-	raw_data = per_cpu_ptr(trace_buf, cpu);
-
-	/* zero the dead bytes from align to not leak stack to user */
-	*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
-
-	rec = (struct syscall_trace_exit *)raw_data;
+	rec = (struct syscall_trace_exit *)ftrace_perf_buf_prepare(size,
+				sys_data->exit_event->id, &rctx, &flags);
+	if (!rec)
+		return;
 
-	tracing_generic_entry_update(&rec->ent, 0, 0);
-	rec->ent.type = sys_data->exit_event->id;
 	rec->nr = syscall_nr;
 	rec->ret = syscall_get_return_value(current, regs);
 
-	perf_tp_event(sys_data->exit_event->id, 0, 1, rec, size);
-
-end:
-	perf_swevent_put_recursion_context(rctx);
-end_recursion:
-	local_irq_restore(flags);
+	ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags);
 }
 
 int prof_sysexit_enable(struct ftrace_event_call *call)
@@ -631,6 +580,5 @@ void prof_sysexit_disable(struct ftrace_event_call *call)
 	mutex_unlock(&syscall_trace_lock);
 }
 
-#endif
-
+#endif /* CONFIG_PERF_EVENTS */
 

tools/perf/.gitignore

@@ -14,6 +14,7 @@ perf*.html
 common-cmds.h
 perf.data
 perf.data.old
+perf-archive
 tags
 TAGS
 cscope*

tools/perf/Documentation/perf-archive.txt

+perf-archive(1)
+===============
+
+NAME
+----
+perf-archive - Create archive with object files with build-ids found in perf.data file
+
+SYNOPSIS
+--------
+[verse]
+'perf archive' [file]
+
+DESCRIPTION
+-----------
+This command runs runs perf-buildid-list --with-hits, and collects the files
+with the buildids found so that analisys of perf.data contents can be possible
+on another machine.
+
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-buildid-list[1], linkperf:perf-report[1]

tools/perf/Documentation/perf-top.txt

@@ -74,7 +74,7 @@ OPTIONS
 
 -s <symbol>::
 --sym-annotate=<symbol>::
-        Annotate this symbol.  Requires -k option.
+        Annotate this symbol.
 
 -v::
 --verbose::

tools/perf/Documentation/perf-trace-perl.txt

@@ -8,7 +8,7 @@ perf-trace-perl - Process trace data with a Perl script
 SYNOPSIS
 --------
 [verse]
-'perf trace' [-s [lang]:script[.ext] ]
+'perf trace' [-s [Perl]:script[.pl] ]
 
 DESCRIPTION
 -----------

tools/perf/Documentation/perf.txt

@@ -12,7 +12,7 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-Performance counters for Linux are are a new kernel-based subsystem
+Performance counters for Linux are a new kernel-based subsystem
 that provide a framework for all things performance analysis. It
 covers hardware level (CPU/PMU, Performance Monitoring Unit) features
 and software features (software counters, tracepoints) as well.