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

* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (50 commits)
  perf python scripting: Add futex-contention script
  perf python scripting: Fixup cut'n'paste error in sctop script
  perf scripting: Shut up 'perf record' final status
  perf record: Remove newline character from perror() argument
  perf python scripting: Support fedora 11 (audit 1.7.17)
  perf python scripting: Improve the syscalls-by-pid script
  perf python scripting: print the syscall name on sctop
  perf python scripting: Improve the syscalls-counts script
  perf python scripting: Improve the failed-syscalls-by-pid script
  kprobes: Remove redundant text_mutex lock in optimize
  x86/oprofile: Fix uninitialized variable use in debug printk
  tracing: Fix 'faild' -> 'failed' typo
  perf probe: Fix format specified for Dwarf_Off parameter
  perf trace: Fix detection of script extension
  perf trace: Use $PERF_EXEC_PATH in canned report scripts
  perf tools: Document event modifiers
  perf tools: Remove direct slang.h include
  perf_events: Fix for transaction recovery in group_sched_in()
  perf_events: Revert: Fix transaction recovery in group_sched_in()
  perf, x86: Use NUMA aware allocations for PEBS/BTS/DS allocations
  ...

arch/x86/include/asm/msr-index.h

@@ -121,6 +121,7 @@
 #define MSR_AMD64_IBSDCLINAD		0xc0011038
 #define MSR_AMD64_IBSDCPHYSAD		0xc0011039
 #define MSR_AMD64_IBSCTL		0xc001103a
+#define MSR_AMD64_IBSBRTARGET		0xc001103b
 
 /* Fam 10h MSRs */
 #define MSR_FAM10H_MMIO_CONF_BASE	0xc0010058

arch/x86/include/asm/perf_event.h

@@ -111,17 +111,18 @@ union cpuid10_edx {
 #define X86_PMC_IDX_FIXED_BTS				(X86_PMC_IDX_FIXED + 16)
 
 /* IbsFetchCtl bits/masks */
-#define IBS_FETCH_RAND_EN		(1ULL<<57)
-#define IBS_FETCH_VAL			(1ULL<<49)
-#define IBS_FETCH_ENABLE		(1ULL<<48)
-#define IBS_FETCH_CNT			0xFFFF0000ULL
-#define IBS_FETCH_MAX_CNT		0x0000FFFFULL
+#define IBS_FETCH_RAND_EN	(1ULL<<57)
+#define IBS_FETCH_VAL		(1ULL<<49)
+#define IBS_FETCH_ENABLE	(1ULL<<48)
+#define IBS_FETCH_CNT		0xFFFF0000ULL
+#define IBS_FETCH_MAX_CNT	0x0000FFFFULL
 
 /* IbsOpCtl bits */
-#define IBS_OP_CNT_CTL			(1ULL<<19)
-#define IBS_OP_VAL			(1ULL<<18)
-#define IBS_OP_ENABLE			(1ULL<<17)
-#define IBS_OP_MAX_CNT			0x0000FFFFULL
+#define IBS_OP_CNT_CTL		(1ULL<<19)
+#define IBS_OP_VAL		(1ULL<<18)
+#define IBS_OP_ENABLE		(1ULL<<17)
+#define IBS_OP_MAX_CNT		0x0000FFFFULL
+#define IBS_OP_MAX_CNT_EXT	0x007FFFFFULL	/* not a register bit mask */
 
 #ifdef CONFIG_PERF_EVENTS
 extern void init_hw_perf_events(void);

arch/x86/kernel/cpu/perf_event.c

@@ -237,6 +237,7 @@ struct x86_pmu {
 	 * Intel DebugStore bits
 	 */
 	int		bts, pebs;
+	int		bts_active, pebs_active;
 	int		pebs_record_size;
 	void		(*drain_pebs)(struct pt_regs *regs);
 	struct event_constraint *pebs_constraints;
@@ -380,7 +381,7 @@ static void release_pmc_hardware(void) {}
 
 #endif
 
-static int reserve_ds_buffers(void);
+static void reserve_ds_buffers(void);
 static void release_ds_buffers(void);
 
 static void hw_perf_event_destroy(struct perf_event *event)
@@ -477,7 +478,7 @@ static int x86_setup_perfctr(struct perf_event *event)
 	if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
 	    (hwc->sample_period == 1)) {
 		/* BTS is not supported by this architecture. */
-		if (!x86_pmu.bts)
+		if (!x86_pmu.bts_active)
 			return -EOPNOTSUPP;
 
 		/* BTS is currently only allowed for user-mode. */
@@ -496,12 +497,13 @@ static int x86_pmu_hw_config(struct perf_event *event)
 		int precise = 0;
 
 		/* Support for constant skid */
-		if (x86_pmu.pebs)
+		if (x86_pmu.pebs_active) {
 			precise++;
 
-		/* Support for IP fixup */
-		if (x86_pmu.lbr_nr)
-			precise++;
+			/* Support for IP fixup */
+			if (x86_pmu.lbr_nr)
+				precise++;
+		}
 
 		if (event->attr.precise_ip > precise)
 			return -EOPNOTSUPP;
@@ -543,11 +545,8 @@ static int __x86_pmu_event_init(struct perf_event *event)
 		if (atomic_read(&active_events) == 0) {
 			if (!reserve_pmc_hardware())
 				err = -EBUSY;
-			else {
-				err = reserve_ds_buffers();
-				if (err)
-					release_pmc_hardware();
-			}
+			else
+				reserve_ds_buffers();
 		}
 		if (!err)
 			atomic_inc(&active_events);

arch/x86/kernel/cpu/perf_event_intel_ds.c

@@ -74,6 +74,107 @@ static void fini_debug_store_on_cpu(int cpu)
 	wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
 }
 
+static int alloc_pebs_buffer(int cpu)
+{
+	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+	int node = cpu_to_node(cpu);
+	int max, thresh = 1; /* always use a single PEBS record */
+	void *buffer;
+
+	if (!x86_pmu.pebs)
+		return 0;
+
+	buffer = kmalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node);
+	if (unlikely(!buffer))
+		return -ENOMEM;
+
+	max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
+
+	ds->pebs_buffer_base = (u64)(unsigned long)buffer;
+	ds->pebs_index = ds->pebs_buffer_base;
+	ds->pebs_absolute_maximum = ds->pebs_buffer_base +
+		max * x86_pmu.pebs_record_size;
+
+	ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
+		thresh * x86_pmu.pebs_record_size;
+
+	return 0;
+}
+
+static void release_pebs_buffer(int cpu)
+{
+	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+
+	if (!ds || !x86_pmu.pebs)
+		return;
+
+	kfree((void *)(unsigned long)ds->pebs_buffer_base);
+	ds->pebs_buffer_base = 0;
+}
+
+static int alloc_bts_buffer(int cpu)
+{
+	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+	int node = cpu_to_node(cpu);
+	int max, thresh;
+	void *buffer;
+
+	if (!x86_pmu.bts)
+		return 0;
+
+	buffer = kmalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node);
+	if (unlikely(!buffer))
+		return -ENOMEM;
+
+	max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
+	thresh = max / 16;
+
+	ds->bts_buffer_base = (u64)(unsigned long)buffer;
+	ds->bts_index = ds->bts_buffer_base;
+	ds->bts_absolute_maximum = ds->bts_buffer_base +
+		max * BTS_RECORD_SIZE;
+	ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
+		thresh * BTS_RECORD_SIZE;
+
+	return 0;
+}
+
+static void release_bts_buffer(int cpu)
+{
+	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+
+	if (!ds || !x86_pmu.bts)
+		return;
+
+	kfree((void *)(unsigned long)ds->bts_buffer_base);
+	ds->bts_buffer_base = 0;
+}
+
+static int alloc_ds_buffer(int cpu)
+{
+	int node = cpu_to_node(cpu);
+	struct debug_store *ds;
+
+	ds = kmalloc_node(sizeof(*ds), GFP_KERNEL | __GFP_ZERO, node);
+	if (unlikely(!ds))
+		return -ENOMEM;
+
+	per_cpu(cpu_hw_events, cpu).ds = ds;
+
+	return 0;
+}
+
+static void release_ds_buffer(int cpu)
+{
+	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+
+	if (!ds)
+		return;
+
+	per_cpu(cpu_hw_events, cpu).ds = NULL;
+	kfree(ds);
+}
+
 static void release_ds_buffers(void)
 {
 	int cpu;
@@ -82,93 +183,77 @@ static void release_ds_buffers(void)
 		return;
 
 	get_online_cpus();
-
 	for_each_online_cpu(cpu)
 		fini_debug_store_on_cpu(cpu);
 
 	for_each_possible_cpu(cpu) {
-		struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-
-		if (!ds)
-			continue;
-
-		per_cpu(cpu_hw_events, cpu).ds = NULL;
-
-		kfree((void *)(unsigned long)ds->pebs_buffer_base);
-		kfree((void *)(unsigned long)ds->bts_buffer_base);
-		kfree(ds);
+		release_pebs_buffer(cpu);
+		release_bts_buffer(cpu);
+		release_ds_buffer(cpu);
 	}
-
 	put_online_cpus();
 }
 
-static int reserve_ds_buffers(void)
+static void reserve_ds_buffers(void)
 {
-	int cpu, err = 0;
+	int bts_err = 0, pebs_err = 0;
+	int cpu;
+
+	x86_pmu.bts_active = 0;
+	x86_pmu.pebs_active = 0;
 
 	if (!x86_pmu.bts && !x86_pmu.pebs)
-		return 0;
+		return;
+
+	if (!x86_pmu.bts)
+		bts_err = 1;
+
+	if (!x86_pmu.pebs)
+		pebs_err = 1;
 
 	get_online_cpus();
 
 	for_each_possible_cpu(cpu) {
-		struct debug_store *ds;
-		void *buffer;
-		int max, thresh;
+		if (alloc_ds_buffer(cpu)) {
+			bts_err = 1;
+			pebs_err = 1;
+		}
 
-		err = -ENOMEM;
-		ds = kzalloc(sizeof(*ds), GFP_KERNEL);
-		if (unlikely(!ds))
+		if (!bts_err && alloc_bts_buffer(cpu))
+			bts_err = 1;
+
+		if (!pebs_err && alloc_pebs_buffer(cpu))
+			pebs_err = 1;
+
+		if (bts_err && pebs_err)
 			break;
-		per_cpu(cpu_hw_events, cpu).ds = ds;
-
-		if (x86_pmu.bts) {
-			buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL);
-			if (unlikely(!buffer))
-				break;
-
-			max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
-			thresh = max / 16;
-
-			ds->bts_buffer_base = (u64)(unsigned long)buffer;
-			ds->bts_index = ds->bts_buffer_base;
-			ds->bts_absolute_maximum = ds->bts_buffer_base +
-				max * BTS_RECORD_SIZE;
-			ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
-				thresh * BTS_RECORD_SIZE;
-		}
-
-		if (x86_pmu.pebs) {
-			buffer = kzalloc(PEBS_BUFFER_SIZE, GFP_KERNEL);
-			if (unlikely(!buffer))
-				break;
-
-			max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
-
-			ds->pebs_buffer_base = (u64)(unsigned long)buffer;
-			ds->pebs_index = ds->pebs_buffer_base;
-			ds->pebs_absolute_maximum = ds->pebs_buffer_base +
-				max * x86_pmu.pebs_record_size;
-			/*
-			 * Always use single record PEBS
-			 */
-			ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
-				x86_pmu.pebs_record_size;
-		}
-
-		err = 0;
 	}
 
-	if (err)
-		release_ds_buffers();
-	else {
+	if (bts_err) {
+		for_each_possible_cpu(cpu)
+			release_bts_buffer(cpu);
+	}
+
+	if (pebs_err) {
+		for_each_possible_cpu(cpu)
+			release_pebs_buffer(cpu);
+	}
+
+	if (bts_err && pebs_err) {
+		for_each_possible_cpu(cpu)
+			release_ds_buffer(cpu);
+	} else {
+		if (x86_pmu.bts && !bts_err)
+			x86_pmu.bts_active = 1;
+
+		if (x86_pmu.pebs && !pebs_err)
+			x86_pmu.pebs_active = 1;
+
 		for_each_online_cpu(cpu)
 			init_debug_store_on_cpu(cpu);
 	}
 
 	put_online_cpus();
-
-	return err;
 }
 
 /*
@@ -233,7 +318,7 @@ static int intel_pmu_drain_bts_buffer(void)
 	if (!event)
 		return 0;
 
-	if (!ds)
+	if (!x86_pmu.bts_active)
 		return 0;
 
 	at  = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
@@ -503,7 +588,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 	struct pebs_record_core *at, *top;
 	int n;
 
-	if (!ds || !x86_pmu.pebs)
+	if (!x86_pmu.pebs_active)
 		return;
 
 	at  = (struct pebs_record_core *)(unsigned long)ds->pebs_buffer_base;
@@ -545,7 +630,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 	u64 status = 0;
 	int bit, n;
 
-	if (!ds || !x86_pmu.pebs)
+	if (!x86_pmu.pebs_active)
 		return;
 
 	at  = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
@@ -630,9 +715,8 @@ static void intel_ds_init(void)
 
 #else /* CONFIG_CPU_SUP_INTEL */
 
-static int reserve_ds_buffers(void)
+static void reserve_ds_buffers(void)
 {
-	return 0;
 }
 
 static void release_ds_buffers(void)

arch/x86/oprofile/nmi_int.c

@@ -726,6 +726,12 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 		case 0x11:
 			cpu_type = "x86-64/family11h";
 			break;
+		case 0x12:
+			cpu_type = "x86-64/family12h";
+			break;
+		case 0x14:
+			cpu_type = "x86-64/family14h";
+			break;
 		default:
 			return -ENODEV;
 		}

arch/x86/oprofile/op_model_amd.c

@@ -48,17 +48,24 @@ static unsigned long reset_value[NUM_VIRT_COUNTERS];
 
 static u32 ibs_caps;
 
-struct op_ibs_config {
+struct ibs_config {
 	unsigned long op_enabled;
 	unsigned long fetch_enabled;
 	unsigned long max_cnt_fetch;
 	unsigned long max_cnt_op;
 	unsigned long rand_en;
 	unsigned long dispatched_ops;
+	unsigned long branch_target;
 };
 
-static struct op_ibs_config ibs_config;
-static u64 ibs_op_ctl;
+struct ibs_state {
+	u64		ibs_op_ctl;
+	int		branch_target;
+	unsigned long	sample_size;
+};
+
+static struct ibs_config ibs_config;
+static struct ibs_state ibs_state;
 
 /*
  * IBS cpuid feature detection
@@ -71,8 +78,16 @@ static u64 ibs_op_ctl;
  * bit 0 is used to indicate the existence of IBS.
  */
 #define IBS_CAPS_AVAIL			(1U<<0)
+#define IBS_CAPS_FETCHSAM		(1U<<1)
+#define IBS_CAPS_OPSAM			(1U<<2)
 #define IBS_CAPS_RDWROPCNT		(1U<<3)
 #define IBS_CAPS_OPCNT			(1U<<4)
+#define IBS_CAPS_BRNTRGT		(1U<<5)
+#define IBS_CAPS_OPCNTEXT		(1U<<6)
+
+#define IBS_CAPS_DEFAULT		(IBS_CAPS_AVAIL		\
+					 | IBS_CAPS_FETCHSAM	\
+					 | IBS_CAPS_OPSAM)
 
 /*
  * IBS APIC setup
@@ -99,12 +114,12 @@ static u32 get_ibs_caps(void)
 	/* check IBS cpuid feature flags */
 	max_level = cpuid_eax(0x80000000);
 	if (max_level < IBS_CPUID_FEATURES)
-		return IBS_CAPS_AVAIL;
+		return IBS_CAPS_DEFAULT;
 
 	ibs_caps = cpuid_eax(IBS_CPUID_FEATURES);
 	if (!(ibs_caps & IBS_CAPS_AVAIL))
 		/* cpuid flags not valid */
-		return IBS_CAPS_AVAIL;
+		return IBS_CAPS_DEFAULT;
 
 	return ibs_caps;
 }
@@ -197,8 +212,8 @@ op_amd_handle_ibs(struct pt_regs * const regs,
 		rdmsrl(MSR_AMD64_IBSOPCTL, ctl);
 		if (ctl & IBS_OP_VAL) {
 			rdmsrl(MSR_AMD64_IBSOPRIP, val);
-			oprofile_write_reserve(&entry, regs, val,
-					       IBS_OP_CODE, IBS_OP_SIZE);
+			oprofile_write_reserve(&entry, regs, val, IBS_OP_CODE,
+					       ibs_state.sample_size);
 			oprofile_add_data64(&entry, val);
 			rdmsrl(MSR_AMD64_IBSOPDATA, val);
 			oprofile_add_data64(&entry, val);
@@ -210,10 +225,14 @@ op_amd_handle_ibs(struct pt_regs * const regs,
 			oprofile_add_data64(&entry, val);
 			rdmsrl(MSR_AMD64_IBSDCPHYSAD, val);
 			oprofile_add_data64(&entry, val);
+			if (ibs_state.branch_target) {
+				rdmsrl(MSR_AMD64_IBSBRTARGET, val);
+				oprofile_add_data(&entry, (unsigned long)val);
+			}
 			oprofile_write_commit(&entry);
 
 			/* reenable the IRQ */
-			ctl = op_amd_randomize_ibs_op(ibs_op_ctl);
+			ctl = op_amd_randomize_ibs_op(ibs_state.ibs_op_ctl);
 			wrmsrl(MSR_AMD64_IBSOPCTL, ctl);
 		}
 	}
@@ -226,21 +245,32 @@ static inline void op_amd_start_ibs(void)
 	if (!ibs_caps)
 		return;
 
+	memset(&ibs_state, 0, sizeof(ibs_state));
+
+	/*
+	 * Note: Since the max count settings may out of range we
+	 * write back the actual used values so that userland can read
+	 * it.
+	 */
+
 	if (ibs_config.fetch_enabled) {
-		val = (ibs_config.max_cnt_fetch >> 4) & IBS_FETCH_MAX_CNT;
+		val = ibs_config.max_cnt_fetch >> 4;
+		val = min(val, IBS_FETCH_MAX_CNT);
+		ibs_config.max_cnt_fetch = val << 4;
 		val |= ibs_config.rand_en ? IBS_FETCH_RAND_EN : 0;
 		val |= IBS_FETCH_ENABLE;
 		wrmsrl(MSR_AMD64_IBSFETCHCTL, val);
 	}
 
 	if (ibs_config.op_enabled) {
-		ibs_op_ctl = ibs_config.max_cnt_op >> 4;
+		val = ibs_config.max_cnt_op >> 4;
 		if (!(ibs_caps & IBS_CAPS_RDWROPCNT)) {
 			/*
 			 * IbsOpCurCnt not supported.  See
 			 * op_amd_randomize_ibs_op() for details.
 			 */
-			ibs_op_ctl = clamp(ibs_op_ctl, 0x0081ULL, 0xFF80ULL);
+			val = clamp(val, 0x0081ULL, 0xFF80ULL);
+			ibs_config.max_cnt_op = val << 4;
 		} else {
 			/*
 			 * The start value is randomized with a
@@ -248,13 +278,24 @@ static inline void op_amd_start_ibs(void)
 			 * with the half of the randomized range. Also
 			 * avoid underflows.
 			 */
-			ibs_op_ctl = min(ibs_op_ctl + IBS_RANDOM_MAXCNT_OFFSET,
-					 IBS_OP_MAX_CNT);
+			val += IBS_RANDOM_MAXCNT_OFFSET;
+			if (ibs_caps & IBS_CAPS_OPCNTEXT)
+				val = min(val, IBS_OP_MAX_CNT_EXT);
+			else
+				val = min(val, IBS_OP_MAX_CNT);
+			ibs_config.max_cnt_op =
+				(val - IBS_RANDOM_MAXCNT_OFFSET) << 4;
 		}
-		if (ibs_caps & IBS_CAPS_OPCNT && ibs_config.dispatched_ops)
-			ibs_op_ctl |= IBS_OP_CNT_CTL;
-		ibs_op_ctl |= IBS_OP_ENABLE;
-		val = op_amd_randomize_ibs_op(ibs_op_ctl);
+		val = ((val & ~IBS_OP_MAX_CNT) << 4) | (val & IBS_OP_MAX_CNT);
+		val |= ibs_config.dispatched_ops ? IBS_OP_CNT_CTL : 0;
+		val |= IBS_OP_ENABLE;
+		ibs_state.ibs_op_ctl = val;
+		ibs_state.sample_size = IBS_OP_SIZE;
+		if (ibs_config.branch_target) {
+			ibs_state.branch_target = 1;
+			ibs_state.sample_size++;
+		}
+		val = op_amd_randomize_ibs_op(ibs_state.ibs_op_ctl);
 		wrmsrl(MSR_AMD64_IBSOPCTL, val);
 	}
 }
@@ -281,29 +322,25 @@ static inline int eilvt_is_available(int offset)
 
 static inline int ibs_eilvt_valid(void)
 {
-	u64 val;
 	int offset;
+	u64 val;
 
 	rdmsrl(MSR_AMD64_IBSCTL, val);
+	offset = val & IBSCTL_LVT_OFFSET_MASK;
+
 	if (!(val & IBSCTL_LVT_OFFSET_VALID)) {
-		pr_err(FW_BUG "cpu %d, invalid IBS "
-		       "interrupt offset %d (MSR%08X=0x%016llx)",
-		       smp_processor_id(), offset,
-		       MSR_AMD64_IBSCTL, val);
+		pr_err(FW_BUG "cpu %d, invalid IBS interrupt offset %d (MSR%08X=0x%016llx)\n",
+		       smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
 		return 0;
 	}
 
-	offset = val & IBSCTL_LVT_OFFSET_MASK;
+	if (!eilvt_is_available(offset)) {
+		pr_err(FW_BUG "cpu %d, IBS interrupt offset %d not available (MSR%08X=0x%016llx)\n",
+		       smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
+		return 0;
+	}
 
-	if (eilvt_is_available(offset))
-		return !0;
-
-	pr_err(FW_BUG "cpu %d, IBS interrupt offset %d "
-	       "not available (MSR%08X=0x%016llx)",
-	       smp_processor_id(), offset,
-	       MSR_AMD64_IBSCTL, val);
-
-	return 0;
+	return 1;
 }
 
 static inline int get_ibs_offset(void)
@@ -630,28 +667,33 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root)
 	/* model specific files */
 
 	/* setup some reasonable defaults */
+	memset(&ibs_config, 0, sizeof(ibs_config));
 	ibs_config.max_cnt_fetch = 250000;
-	ibs_config.fetch_enabled = 0;
 	ibs_config.max_cnt_op = 250000;
-	ibs_config.op_enabled = 0;
-	ibs_config.dispatched_ops = 0;
 
-	dir = oprofilefs_mkdir(sb, root, "ibs_fetch");
-	oprofilefs_create_ulong(sb, dir, "enable",
-				&ibs_config.fetch_enabled);
-	oprofilefs_create_ulong(sb, dir, "max_count",
-				&ibs_config.max_cnt_fetch);
-	oprofilefs_create_ulong(sb, dir, "rand_enable",
-				&ibs_config.rand_en);
+	if (ibs_caps & IBS_CAPS_FETCHSAM) {
+		dir = oprofilefs_mkdir(sb, root, "ibs_fetch");
+		oprofilefs_create_ulong(sb, dir, "enable",
+					&ibs_config.fetch_enabled);
+		oprofilefs_create_ulong(sb, dir, "max_count",
+					&ibs_config.max_cnt_fetch);
+		oprofilefs_create_ulong(sb, dir, "rand_enable",
+					&ibs_config.rand_en);
+	}
 
-	dir = oprofilefs_mkdir(sb, root, "ibs_op");
-	oprofilefs_create_ulong(sb, dir, "enable",
-				&ibs_config.op_enabled);
-	oprofilefs_create_ulong(sb, dir, "max_count",
-				&ibs_config.max_cnt_op);
-	if (ibs_caps & IBS_CAPS_OPCNT)
-		oprofilefs_create_ulong(sb, dir, "dispatched_ops",
-					&ibs_config.dispatched_ops);
+	if (ibs_caps & IBS_CAPS_OPSAM) {
+		dir = oprofilefs_mkdir(sb, root, "ibs_op");
+		oprofilefs_create_ulong(sb, dir, "enable",
+					&ibs_config.op_enabled);
+		oprofilefs_create_ulong(sb, dir, "max_count",
+					&ibs_config.max_cnt_op);
+		if (ibs_caps & IBS_CAPS_OPCNT)
+			oprofilefs_create_ulong(sb, dir, "dispatched_ops",
+						&ibs_config.dispatched_ops);
+		if (ibs_caps & IBS_CAPS_BRNTRGT)
+			oprofilefs_create_ulong(sb, dir, "branch_target",
+						&ibs_config.branch_target);
+	}
 
 	return 0;
 }

include/linux/interrupt.h

@@ -410,7 +410,7 @@ extern void open_softirq(int nr, void (*action)(struct softirq_action *));
 extern void softirq_init(void);
 static inline void __raise_softirq_irqoff(unsigned int nr)
 {
-	trace_softirq_raise((struct softirq_action *)(unsigned long)nr, NULL);
+	trace_softirq_raise(nr);
 	or_softirq_pending(1UL << nr);
 }
 

include/linux/ring_buffer.h

@@ -62,18 +62,6 @@ enum ring_buffer_type {
 unsigned ring_buffer_event_length(struct ring_buffer_event *event);
 void *ring_buffer_event_data(struct ring_buffer_event *event);
 
-/**
- * ring_buffer_event_time_delta - return the delta timestamp of the event
- * @event: the event to get the delta timestamp of
- *
- * The delta timestamp is the 27 bit timestamp since the last event.
- */
-static inline unsigned
-ring_buffer_event_time_delta(struct ring_buffer_event *event)
-{
-	return event->time_delta;
-}
-
 /*
  * ring_buffer_discard_commit will remove an event that has not
  *   ben committed yet. If this is used, then ring_buffer_unlock_commit

include/trace/events/irq.h

@@ -86,76 +86,62 @@ TRACE_EVENT(irq_handler_exit,
 
 DECLARE_EVENT_CLASS(softirq,
 
-	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+	TP_PROTO(unsigned int vec_nr),
 
-	TP_ARGS(h, vec),
+	TP_ARGS(vec_nr),
 
 	TP_STRUCT__entry(
-		__field(	int,	vec			)
+		__field(	unsigned int,	vec	)
 	),
 
 	TP_fast_assign(
-		if (vec)
-			__entry->vec = (int)(h - vec);
-		else
-			__entry->vec = (int)(long)h;
+		__entry->vec = vec_nr;
 	),
 
-	TP_printk("vec=%d [action=%s]", __entry->vec,
+	TP_printk("vec=%u [action=%s]", __entry->vec,
 		  show_softirq_name(__entry->vec))
 );
 
 /**
  * softirq_entry - called immediately before the softirq handler
- * @h: pointer to struct softirq_action
- * @vec: pointer to first struct softirq_action in softirq_vec array
+ * @vec_nr:  softirq vector number
  *
- * The @h parameter, contains a pointer to the struct softirq_action
- * which has a pointer to the action handler that is called. By subtracting
- * the @vec pointer from the @h pointer, we can determine the softirq
- * number. Also, when used in combination with the softirq_exit tracepoint
- * we can determine the softirq latency.
+ * When used in combination with the softirq_exit tracepoint
+ * we can determine the softirq handler runtine.
  */
 DEFINE_EVENT(softirq, softirq_entry,
 
-	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+	TP_PROTO(unsigned int vec_nr),
 
-	TP_ARGS(h, vec)
+	TP_ARGS(vec_nr)
 );
 
 /**
  * softirq_exit - called immediately after the softirq handler returns
- * @h: pointer to struct softirq_action
- * @vec: pointer to first struct softirq_action in softirq_vec array
+ * @vec_nr:  softirq vector number
  *
- * The @h parameter contains a pointer to the struct softirq_action
- * that has handled the softirq. By subtracting the @vec pointer from
- * the @h pointer, we can determine the softirq number. Also, when used in
- * combination with the softirq_entry tracepoint we can determine the softirq
- * latency.
+ * When used in combination with the softirq_entry tracepoint
+ * we can determine the softirq handler runtine.
  */
 DEFINE_EVENT(softirq, softirq_exit,
 
-	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+	TP_PROTO(unsigned int vec_nr),
 
-	TP_ARGS(h, vec)
+	TP_ARGS(vec_nr)
 );
 
 /**
  * softirq_raise - called immediately when a softirq is raised
- * @h: pointer to struct softirq_action
- * @vec: pointer to first struct softirq_action in softirq_vec array
+ * @vec_nr:  softirq vector number
  *
- * The @h parameter contains a pointer to the softirq vector number which is
- * raised. @vec is NULL and it means @h includes vector number not
- * softirq_action. When used in combination with the softirq_entry tracepoint
- * we can determine the softirq raise latency.
+ * When used in combination with the softirq_entry tracepoint
+ * we can determine the softirq raise to run latency.
  */
 DEFINE_EVENT(softirq, softirq_raise,
 
-	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+	TP_PROTO(unsigned int vec_nr),
 
-	TP_ARGS(h, vec)
+	TP_ARGS(vec_nr)
 );
 
 #endif /*  _TRACE_IRQ_H */

kernel/kprobes.c

@@ -74,7 +74,8 @@ static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
 /* NOTE: change this value only with kprobe_mutex held */
 static bool kprobes_all_disarmed;
 
-static DEFINE_MUTEX(kprobe_mutex);	/* Protects kprobe_table */
+/* This protects kprobe_table and optimizing_list */
+static DEFINE_MUTEX(kprobe_mutex);
 static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
 static struct {
 	spinlock_t lock ____cacheline_aligned_in_smp;
@@ -595,6 +596,7 @@ static __kprobes void try_to_optimize_kprobe(struct kprobe *p)
 }
 
 #ifdef CONFIG_SYSCTL
+/* This should be called with kprobe_mutex locked */
 static void __kprobes optimize_all_kprobes(void)
 {
 	struct hlist_head *head;
@@ -607,17 +609,16 @@ static void __kprobes optimize_all_kprobes(void)
 		return;
 
 	kprobes_allow_optimization = true;
-	mutex_lock(&text_mutex);
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
 		hlist_for_each_entry_rcu(p, node, head, hlist)
 			if (!kprobe_disabled(p))
 				optimize_kprobe(p);
 	}
-	mutex_unlock(&text_mutex);
 	printk(KERN_INFO "Kprobes globally optimized\n");
 }
 
+/* This should be called with kprobe_mutex locked */
 static void __kprobes unoptimize_all_kprobes(void)
 {
 	struct hlist_head *head;

kernel/perf_event.c

@@ -417,8 +417,8 @@ event_filter_match(struct perf_event *event)
 	return event->cpu == -1 || event->cpu == smp_processor_id();
 }
 
-static int
-__event_sched_out(struct perf_event *event,
+static void
+event_sched_out(struct perf_event *event,
 		  struct perf_cpu_context *cpuctx,
 		  struct perf_event_context *ctx)
 {
@@ -437,13 +437,14 @@ __event_sched_out(struct perf_event *event,
 	}
 
 	if (event->state != PERF_EVENT_STATE_ACTIVE)
-		return 0;
+		return;
 
 	event->state = PERF_EVENT_STATE_INACTIVE;
 	if (event->pending_disable) {
 		event->pending_disable = 0;
 		event->state = PERF_EVENT_STATE_OFF;
 	}
+	event->tstamp_stopped = ctx->time;
 	event->pmu->del(event, 0);
 	event->oncpu = -1;
 
@@ -452,19 +453,6 @@ __event_sched_out(struct perf_event *event,
 	ctx->nr_active--;
 	if (event->attr.exclusive || !cpuctx->active_oncpu)
 		cpuctx->exclusive = 0;
-	return 1;
-}
-
-static void
-event_sched_out(struct perf_event *event,
-		  struct perf_cpu_context *cpuctx,
-		  struct perf_event_context *ctx)
-{
-	int ret;
-
-	ret = __event_sched_out(event, cpuctx, ctx);
-	if (ret)
-		event->tstamp_stopped = ctx->time;
 }
 
 static void
@@ -664,7 +652,7 @@ retry:
 }
 
 static int
-__event_sched_in(struct perf_event *event,
+event_sched_in(struct perf_event *event,
 		 struct perf_cpu_context *cpuctx,
 		 struct perf_event_context *ctx)
 {
@@ -684,6 +672,8 @@ __event_sched_in(struct perf_event *event,
 		return -EAGAIN;
 	}
 
+	event->tstamp_running += ctx->time - event->tstamp_stopped;
+
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
 	ctx->nr_active++;
@@ -694,35 +684,6 @@ __event_sched_in(struct perf_event *event,
 	return 0;
 }
 
-static inline int
-event_sched_in(struct perf_event *event,
-		 struct perf_cpu_context *cpuctx,
-		 struct perf_event_context *ctx)
-{
-	int ret = __event_sched_in(event, cpuctx, ctx);
-	if (ret)
-		return ret;
-	event->tstamp_running += ctx->time - event->tstamp_stopped;
-	return 0;
-}
-
-static void
-group_commit_event_sched_in(struct perf_event *group_event,
-	       struct perf_cpu_context *cpuctx,
-	       struct perf_event_context *ctx)
-{
-	struct perf_event *event;
-	u64 now = ctx->time;
-
-	group_event->tstamp_running += now - group_event->tstamp_stopped;
-	/*
-	 * Schedule in siblings as one group (if any):
-	 */
-	list_for_each_entry(event, &group_event->sibling_list, group_entry) {
-		event->tstamp_running += now - event->tstamp_stopped;
-	}
-}
-
 static int
 group_sched_in(struct perf_event *group_event,
 	       struct perf_cpu_context *cpuctx,
@@ -730,19 +691,15 @@ group_sched_in(struct perf_event *group_event,
 {
 	struct perf_event *event, *partial_group = NULL;
 	struct pmu *pmu = group_event->pmu;
+	u64 now = ctx->time;
+	bool simulate = false;
 
 	if (group_event->state == PERF_EVENT_STATE_OFF)
 		return 0;
 
 	pmu->start_txn(pmu);
 
-	/*
-	 * use __event_sched_in() to delay updating tstamp_running
-	 * until the transaction is committed. In case of failure
-	 * we will keep an unmodified tstamp_running which is a
-	 * requirement to get correct timing information
-	 */
-	if (__event_sched_in(group_event, cpuctx, ctx)) {
+	if (event_sched_in(group_event, cpuctx, ctx)) {
 		pmu->cancel_txn(pmu);
 		return -EAGAIN;
 	}
@@ -751,31 +708,42 @@ group_sched_in(struct perf_event *group_event,
 	 * Schedule in siblings as one group (if any):
 	 */
 	list_for_each_entry(event, &group_event->sibling_list, group_entry) {
-		if (__event_sched_in(event, cpuctx, ctx)) {
+		if (event_sched_in(event, cpuctx, ctx)) {
 			partial_group = event;
 			goto group_error;
 		}
 	}
 
-	if (!pmu->commit_txn(pmu)) {
-		/* commit tstamp_running */
-		group_commit_event_sched_in(group_event, cpuctx, ctx);
+	if (!pmu->commit_txn(pmu))
 		return 0;
-	}
+
 group_error:
 	/*
 	 * Groups can be scheduled in as one unit only, so undo any
 	 * partial group before returning:
+	 * The events up to the failed event are scheduled out normally,
+	 * tstamp_stopped will be updated.
 	 *
-	 * use __event_sched_out() to avoid updating tstamp_stopped
-	 * because the event never actually ran
+	 * The failed events and the remaining siblings need to have
+	 * their timings updated as if they had gone thru event_sched_in()
+	 * and event_sched_out(). This is required to get consistent timings
+	 * across the group. This also takes care of the case where the group
+	 * could never be scheduled by ensuring tstamp_stopped is set to mark
+	 * the time the event was actually stopped, such that time delta
+	 * calculation in update_event_times() is correct.
 	 */
 	list_for_each_entry(event, &group_event->sibling_list, group_entry) {
 		if (event == partial_group)
-			break;
-		__event_sched_out(event, cpuctx, ctx);
+			simulate = true;
+
+		if (simulate) {
+			event->tstamp_running += now - event->tstamp_stopped;
+			event->tstamp_stopped = now;
+		} else {
+			event_sched_out(event, cpuctx, ctx);
+		}
 	}
-	__event_sched_out(group_event, cpuctx, ctx);
+	event_sched_out(group_event, cpuctx, ctx);
 
 	pmu->cancel_txn(pmu);
 

kernel/softirq.c

@@ -229,18 +229,20 @@ restart:
 
 	do {
 		if (pending & 1) {
+			unsigned int vec_nr = h - softirq_vec;
 			int prev_count = preempt_count();
-			kstat_incr_softirqs_this_cpu(h - softirq_vec);
 
-			trace_softirq_entry(h, softirq_vec);
+			kstat_incr_softirqs_this_cpu(vec_nr);
+
+			trace_softirq_entry(vec_nr);
 			h->action(h);
-			trace_softirq_exit(h, softirq_vec);
+			trace_softirq_exit(vec_nr);
 			if (unlikely(prev_count != preempt_count())) {
-				printk(KERN_ERR "huh, entered softirq %td %s %p"
+				printk(KERN_ERR "huh, entered softirq %u %s %p"
 				       "with preempt_count %08x,"
-				       " exited with %08x?\n", h - softirq_vec,
-				       softirq_to_name[h - softirq_vec],
-				       h->action, prev_count, preempt_count());
+				       " exited with %08x?\n", vec_nr,
+				       softirq_to_name[vec_nr], h->action,
+				       prev_count, preempt_count());
 				preempt_count() = prev_count;
 			}
 

kernel/trace/trace.c

@@ -3996,13 +3996,9 @@ static void tracing_init_debugfs_percpu(long cpu)
 {
 	struct dentry *d_percpu = tracing_dentry_percpu();
 	struct dentry *d_cpu;
-	/* strlen(cpu) + MAX(log10(cpu)) + '\0' */
-	char cpu_dir[7];
+	char cpu_dir[30]; /* 30 characters should be more than enough */
 
-	if (cpu > 999 || cpu < 0)
-		return;
-
-	sprintf(cpu_dir, "cpu%ld", cpu);
+	snprintf(cpu_dir, 30, "cpu%ld", cpu);
 	d_cpu = debugfs_create_dir(cpu_dir, d_percpu);
 	if (!d_cpu) {
 		pr_warning("Could not create debugfs '%s' entry\n", cpu_dir);

tools/perf/Documentation/perf-list.txt

@@ -15,6 +15,23 @@ DESCRIPTION
 This command displays the symbolic event types which can be selected in the
 various perf commands with the -e option.
 
+EVENT MODIFIERS
+---------------
+
+Events can optionally have a modifer by appending a colon and one or
+more modifiers.  Modifiers allow the user to restrict when events are
+counted with 'u' for user-space, 'k' for kernel, 'h' for hypervisor.
+
+The 'p' modifier can be used for specifying how precise the instruction
+address should be. The 'p' modifier is currently only implemented for
+Intel PEBS and can be specified multiple times:
+  0 - SAMPLE_IP can have arbitrary skid
+  1 - SAMPLE_IP must have constant skid
+  2 - SAMPLE_IP requested to have 0 skid
+  3 - SAMPLE_IP must have 0 skid
+
+The PEBS implementation now supports up to 2.
+
 RAW HARDWARE EVENT DESCRIPTOR
 -----------------------------
 Even when an event is not available in a symbolic form within perf right now,

tools/perf/Documentation/perf-probe.txt

@@ -16,7 +16,9 @@ or
 or
 'perf probe' --list
 or
-'perf probe' --line='FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]'
+'perf probe' [options] --line='FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]'
+or
+'perf probe' [options] --vars='PROBEPOINT'
 
 DESCRIPTION
 -----------
@@ -31,6 +33,11 @@ OPTIONS
 --vmlinux=PATH::
 	Specify vmlinux path which has debuginfo (Dwarf binary).
 
+-m::
+--module=MODNAME::
+	Specify module name in which perf-probe searches probe points
+	or lines.
+
 -s::
 --source=PATH::
 	Specify path to kernel source.
@@ -57,6 +64,15 @@ OPTIONS
 	Show source code lines which can be probed. This needs an argument
 	which specifies a range of the source code. (see LINE SYNTAX for detail)
 
+-V::
+--vars=::
+	Show available local variables at given probe point. The argument
+	syntax is same as PROBE SYNTAX, but NO ARGs.
+
+--externs::
+	(Only for --vars) Show external defined variables in addition to local
+	variables.
+
 -f::
 --force::
 	Forcibly add events with existing name.

tools/perf/Documentation/perf-record.txt

@@ -83,6 +83,10 @@ OPTIONS
 --call-graph::
 	Do call-graph (stack chain/backtrace) recording.
 
+-q::
+--quiet::
+	Don't print any message, useful for scripting.
+
 -v::
 --verbose::
 	Be more verbose (show counter open errors, etc).

tools/perf/builtin-probe.c

@@ -50,14 +50,17 @@ static struct {
 	bool list_events;
 	bool force_add;
 	bool show_lines;
+	bool show_vars;
+	bool show_ext_vars;
+	bool mod_events;
 	int nevents;
 	struct perf_probe_event events[MAX_PROBES];
 	struct strlist *dellist;
 	struct line_range line_range;
+	const char *target_module;
 	int max_probe_points;
 } params;
 
-
 /* Parse an event definition. Note that any error must die. */
 static int parse_probe_event(const char *str)
 {
@@ -92,6 +95,7 @@ static int parse_probe_event_argv(int argc, const char **argv)
 	len = 0;
 	for (i = 0; i < argc; i++)
 		len += sprintf(&buf[len], "%s ", argv[i]);
+	params.mod_events = true;
 	ret = parse_probe_event(buf);
 	free(buf);
 	return ret;
@@ -100,9 +104,10 @@ static int parse_probe_event_argv(int argc, const char **argv)
 static int opt_add_probe_event(const struct option *opt __used,
 			      const char *str, int unset __used)
 {
-	if (str)
+	if (str) {
+		params.mod_events = true;
 		return parse_probe_event(str);
-	else
+	} else
 		return 0;
 }
 
@@ -110,6 +115,7 @@ static int opt_del_probe_event(const struct option *opt __used,
 			       const char *str, int unset __used)
 {
 	if (str) {
+		params.mod_events = true;
 		if (!params.dellist)
 			params.dellist = strlist__new(true, NULL);
 		strlist__add(params.dellist, str);
@@ -130,6 +136,25 @@ static int opt_show_lines(const struct option *opt __used,
 
 	return ret;
 }
+
+static int opt_show_vars(const struct option *opt __used,
+			 const char *str, int unset __used)
+{
+	struct perf_probe_event *pev = &params.events[params.nevents];
+	int ret;
+
+	if (!str)
+		return 0;
+
+	ret = parse_probe_event(str);
+	if (!ret && pev->nargs != 0) {
+		pr_err("  Error: '--vars' doesn't accept arguments.\n");
+		return -EINVAL;
+	}
+	params.show_vars = true;
+
+	return ret;
+}
 #endif
 
 static const char * const probe_usage[] = {
@@ -138,7 +163,8 @@ static const char * const probe_usage[] = {
 	"perf probe [<options>] --del '[GROUP:]EVENT' ...",
 	"perf probe --list",
 #ifdef DWARF_SUPPORT
-	"perf probe --line 'LINEDESC'",
+	"perf probe [<options>] --line 'LINEDESC'",
+	"perf probe [<options>] --vars 'PROBEPOINT'",
 #endif
 	NULL
 };
@@ -180,10 +206,17 @@ static const struct option options[] = {
 	OPT_CALLBACK('L', "line", NULL,
 		     "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]",
 		     "Show source code lines.", opt_show_lines),
+	OPT_CALLBACK('V', "vars", NULL,
+		     "FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT",
+		     "Show accessible variables on PROBEDEF", opt_show_vars),
+	OPT_BOOLEAN('\0', "externs", &params.show_ext_vars,
+		    "Show external variables too (with --vars only)"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
 	OPT_STRING('s', "source", &symbol_conf.source_prefix,
 		   "directory", "path to kernel source"),
+	OPT_STRING('m', "module", &params.target_module,
+		   "modname", "target module name"),
 #endif
 	OPT__DRY_RUN(&probe_event_dry_run),
 	OPT_INTEGER('\0', "max-probes", &params.max_probe_points,
@@ -217,7 +250,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 		usage_with_options(probe_usage, options);
 
 	if (params.list_events) {
-		if (params.nevents != 0 || params.dellist) {
+		if (params.mod_events) {
 			pr_err("  Error: Don't use --list with --add/--del.\n");
 			usage_with_options(probe_usage, options);
 		}
@@ -225,6 +258,10 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 			pr_err("  Error: Don't use --list with --line.\n");
 			usage_with_options(probe_usage, options);
 		}
+		if (params.show_vars) {
+			pr_err(" Error: Don't use --list with --vars.\n");
+			usage_with_options(probe_usage, options);
+		}
 		ret = show_perf_probe_events();
 		if (ret < 0)
 			pr_err("  Error: Failed to show event list. (%d)\n",
@@ -234,17 +271,35 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 
 #ifdef DWARF_SUPPORT
 	if (params.show_lines) {
-		if (params.nevents != 0 || params.dellist) {
-			pr_warning("  Error: Don't use --line with"
-				   " --add/--del.\n");
+		if (params.mod_events) {
+			pr_err("  Error: Don't use --line with"
+			       " --add/--del.\n");
+			usage_with_options(probe_usage, options);
+		}
+		if (params.show_vars) {
+			pr_err(" Error: Don't use --line with --vars.\n");
 			usage_with_options(probe_usage, options);
 		}
 
-		ret = show_line_range(&params.line_range);
+		ret = show_line_range(&params.line_range, params.target_module);
 		if (ret < 0)
 			pr_err("  Error: Failed to show lines. (%d)\n", ret);
 		return ret;
 	}
+	if (params.show_vars) {
+		if (params.mod_events) {
+			pr_err("  Error: Don't use --vars with"
+			       " --add/--del.\n");
+			usage_with_options(probe_usage, options);
+		}
+		ret = show_available_vars(params.events, params.nevents,
+					  params.max_probe_points,
+					  params.target_module,
+					  params.show_ext_vars);
+		if (ret < 0)
+			pr_err("  Error: Failed to show vars. (%d)\n", ret);
+		return ret;
+	}
 #endif
 
 	if (params.dellist) {
@@ -258,8 +313,9 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 
 	if (params.nevents) {
 		ret = add_perf_probe_events(params.events, params.nevents,
-					    params.force_add,
-					    params.max_probe_points);
+					    params.max_probe_points,
+					    params.target_module,
+					    params.force_add);
 		if (ret < 0) {
 			pr_err("  Error: Failed to add events. (%d)\n", ret);
 			return ret;

tools/perf/builtin-record.c

@@ -353,7 +353,7 @@ try_again:
 		}
 
 		if (read(fd[nr_cpu][counter][thread_index], &read_data, sizeof(read_data)) == -1) {
-			perror("Unable to read perf file descriptor\n");
+			perror("Unable to read perf file descriptor");
 			exit(-1);
 		}
 
@@ -626,7 +626,7 @@ static int __cmd_record(int argc, const char **argv)
 
 	nr_cpus = read_cpu_map(cpu_list);
 	if (nr_cpus < 1) {
-		perror("failed to collect number of CPUs\n");
+		perror("failed to collect number of CPUs");
 		return -1;
 	}
 
@@ -761,6 +761,9 @@ static int __cmd_record(int argc, const char **argv)
 		}
 	}
 
+	if (quiet)
+		return 0;
+
 	fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
 
 	/*
@@ -820,6 +823,7 @@ static const struct option options[] = {
 		    "do call-graph (stack chain/backtrace) recording"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
+	OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
 	OPT_BOOLEAN('s', "stat", &inherit_stat,
 		    "per thread counts"),
 	OPT_BOOLEAN('d', "data", &sample_address,

tools/perf/builtin-trace.c

@@ -46,9 +46,6 @@ static struct scripting_ops	*scripting_ops;
 
 static void setup_scripting(void)
 {
-	/* make sure PERF_EXEC_PATH is set for scripts */
-	perf_set_argv_exec_path(perf_exec_path());
-
 	setup_perl_scripting();
 	setup_python_scripting();
 
@@ -285,7 +282,7 @@ static int parse_scriptname(const struct option *opt __used,
 		script++;
 	} else {
 		script = str;
-		ext = strchr(script, '.');
+		ext = strrchr(script, '.');
 		if (!ext) {
 			fprintf(stderr, "invalid script extension");
 			return -1;
@@ -593,6 +590,9 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
 		suffix = REPORT_SUFFIX;
 	}
 
+	/* make sure PERF_EXEC_PATH is set for scripts */
+	perf_set_argv_exec_path(perf_exec_path());
+
 	if (!suffix && argc >= 2 && strncmp(argv[1], "-", strlen("-")) != 0) {
 		char *record_script_path, *report_script_path;
 		int live_pipe[2];
@@ -625,12 +625,13 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
 			dup2(live_pipe[1], 1);
 			close(live_pipe[0]);
 
-			__argv = malloc(5 * sizeof(const char *));
+			__argv = malloc(6 * sizeof(const char *));
 			__argv[0] = "/bin/sh";
 			__argv[1] = record_script_path;
-			__argv[2] = "-o";
-			__argv[3] = "-";
-			__argv[4] = NULL;
+			__argv[2] = "-q";
+			__argv[3] = "-o";
+			__argv[4] = "-";
+			__argv[5] = NULL;
 
 			execvp("/bin/sh", (char **)__argv);
 			exit(-1);