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

Pull perf updates from Ingo Molnar:
 "Kernel side changes:

   - AMD range breakpoints support:

     Extend breakpoint tools and core to support address range through
     perf event with initial backend support for AMD extended
     breakpoints.

     The syntax is:

         perf record -e mem:addr/len:type

     For example set write breakpoint from 0x1000 to 0x1200 (0x1000 + 512)

         perf record -e mem:0x1000/512:w

   - event throttling/rotating fixes

   - various event group handling fixes, cleanups and general paranoia
     code to be more robust against bugs in the future.

    - kernel stack overhead fixes

  User-visible tooling side changes:

   - Show precise number of samples in at the end of a 'record' session,
     if processing build ids, since we will then traverse the whole
     perf.data file and see all the PERF_RECORD_SAMPLE records,
     otherwise stop showing the previous off-base heuristicly counted
     number of "samples" (Namhyung Kim).

   - Support to read compressed module from build-id cache (Namhyung
     Kim)

   - Enable sampling loads and stores simultaneously in 'perf mem'
     (Stephane Eranian)

   - 'perf diff' output improvements (Namhyung Kim)

   - Fix error reporting for evsel pgfault constructor (Arnaldo Carvalho
     de Melo)

  Tooling side infrastructure changes:

   - Cache eh/debug frame offset for dwarf unwind (Namhyung Kim)

   - Support parsing parameterized events (Cody P Schafer)

   - Add support for IP address formats in libtraceevent (David Ahern)

  Plus other misc fixes"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits)
  perf: Decouple unthrottling and rotating
  perf: Drop module reference on event init failure
  perf: Use POLLIN instead of POLL_IN for perf poll data in flag
  perf: Fix put_event() ctx lock
  perf: Fix move_group() order
  perf: Fix event->ctx locking
  perf: Add a bit of paranoia
  perf symbols: Convert lseek + read to pread
  perf tools: Use perf_data_file__fd() consistently
  perf symbols: Support to read compressed module from build-id cache
  perf evsel: Set attr.task bit for a tracking event
  perf header: Set header version correctly
  perf record: Show precise number of samples
  perf tools: Do not use __perf_session__process_events() directly
  perf callchain: Cache eh/debug frame offset for dwarf unwind
  perf tools: Provide stub for missing pthread_attr_setaffinity_np
  perf evsel: Don't rely on malloc working for sz 0
  tools lib traceevent: Add support for IP address formats
  perf ui/tui: Show fatal error message only if exists
  perf tests: Fix typo in sample-parsing.c
  ...

76 files changed, 1611 insertions, 666 deletions

diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
index 20979f8b3edb..505f080d20a1 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
@@ -52,12 +52,18 @@ Description:	Per-pmu performance monitoring events specific to the running syste
 			event=0x2abc
 			event=0x423,inv,cmask=0x3
 			domain=0x1,offset=0x8,starting_index=0xffff
+			domain=0x1,offset=0x8,core=?
 
 		Each of the assignments indicates a value to be assigned to a
 		particular set of bits (as defined by the format file
 		corresponding to the <term>) in the perf_event structure passed
 		to the perf_open syscall.
 
+		In the case of the last example, a value replacing "?" would
+		need to be provided by the user selecting the particular event.
+		This is referred to as "event parameterization". Event
+		parameters have the format 'param=?'.
+
 What: /sys/bus/event_source/devices/<pmu>/events/<event>.unit
 Date: 2014/02/24
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index aede2c347bde..90a54851aedc 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -174,6 +174,7 @@
 #define X86_FEATURE_TOPOEXT	( 6*32+22) /* topology extensions CPUID leafs */
 #define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
 #define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
+#define X86_FEATURE_BPEXT	(6*32+26) /* data breakpoint extension */
 #define X86_FEATURE_PERFCTR_L2	( 6*32+28) /* L2 performance counter extensions */
 
 /*
@@ -388,6 +389,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 #define cpu_has_cx16		boot_cpu_has(X86_FEATURE_CX16)
 #define cpu_has_eager_fpu	boot_cpu_has(X86_FEATURE_EAGER_FPU)
 #define cpu_has_topoext		boot_cpu_has(X86_FEATURE_TOPOEXT)
+#define cpu_has_bpext		boot_cpu_has(X86_FEATURE_BPEXT)
 
 #if __GNUC__ >= 4
 extern void warn_pre_alternatives(void);
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 61fd18b83b6c..12cb66f6d3a5 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -114,5 +114,10 @@ static inline void debug_stack_usage_inc(void) { }
 static inline void debug_stack_usage_dec(void) { }
 #endif /* X86_64 */
 
+#ifdef CONFIG_CPU_SUP_AMD
+extern void set_dr_addr_mask(unsigned long mask, int dr);
+#else
+static inline void set_dr_addr_mask(unsigned long mask, int dr) { }
+#endif
 
 #endif /* _ASM_X86_DEBUGREG_H */
diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index ef1c4d2d41ec..6c98be864a75 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -12,6 +12,7 @@
  */
 struct arch_hw_breakpoint {
 	unsigned long	address;
+	unsigned long	mask;
 	u8		len;
 	u8		type;
 };
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index c8aa65d56027..d979e5abae55 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -251,6 +251,10 @@
 /* Fam 16h MSRs */
 #define MSR_F16H_L2I_PERF_CTL		0xc0010230
 #define MSR_F16H_L2I_PERF_CTR		0xc0010231
+#define MSR_F16H_DR1_ADDR_MASK		0xc0011019
+#define MSR_F16H_DR2_ADDR_MASK		0xc001101a
+#define MSR_F16H_DR3_ADDR_MASK		0xc001101b
+#define MSR_F16H_DR0_ADDR_MASK		0xc0011027
 
 /* Fam 15h MSRs */
 #define MSR_F15H_PERF_CTL		0xc0010200
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 15c5df92f74e..a220239cea65 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -869,3 +869,22 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 
 	return false;
 }
+
+void set_dr_addr_mask(unsigned long mask, int dr)
+{
+	if (!cpu_has_bpext)
+		return;
+
+	switch (dr) {
+	case 0:
+		wrmsr(MSR_F16H_DR0_ADDR_MASK, mask, 0);
+		break;
+	case 1:
+	case 2:
+	case 3:
+		wrmsr(MSR_F16H_DR1_ADDR_MASK - 1 + dr, mask, 0);
+		break;
+	default:
+		break;
+	}
+}
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 3d5fb509bdeb..7114ba220fd4 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -126,6 +126,8 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 	*dr7 |= encode_dr7(i, info->len, info->type);
 
 	set_debugreg(*dr7, 7);
+	if (info->mask)
+		set_dr_addr_mask(info->mask, i);
 
 	return 0;
 }
@@ -161,29 +163,8 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	*dr7 &= ~__encode_dr7(i, info->len, info->type);
 
 	set_debugreg(*dr7, 7);
-}
-
-static int get_hbp_len(u8 hbp_len)
-{
-	unsigned int len_in_bytes = 0;
-
-	switch (hbp_len) {
-	case X86_BREAKPOINT_LEN_1:
-		len_in_bytes = 1;
-		break;
-	case X86_BREAKPOINT_LEN_2:
-		len_in_bytes = 2;
-		break;
-	case X86_BREAKPOINT_LEN_4:
-		len_in_bytes = 4;
-		break;
-#ifdef CONFIG_X86_64
-	case X86_BREAKPOINT_LEN_8:
-		len_in_bytes = 8;
-		break;
-#endif
-	}
-	return len_in_bytes;
+	if (info->mask)
+		set_dr_addr_mask(0, i);
 }
 
 /*
@@ -196,7 +177,7 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
 	va = info->address;
-	len = get_hbp_len(info->len);
+	len = bp->attr.bp_len;
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -277,6 +258,8 @@ static int arch_build_bp_info(struct perf_event *bp)
 	}
 
 	/* Len */
+	info->mask = 0;
+
 	switch (bp->attr.bp_len) {
 	case HW_BREAKPOINT_LEN_1:
 		info->len = X86_BREAKPOINT_LEN_1;
@@ -293,11 +276,17 @@ static int arch_build_bp_info(struct perf_event *bp)
 		break;
 #endif
 	default:
-		return -EINVAL;
+		if (!is_power_of_2(bp->attr.bp_len))
+			return -EINVAL;
+		if (!cpu_has_bpext)
+			return -EOPNOTSUPP;
+		info->mask = bp->attr.bp_len - 1;
+		info->len = X86_BREAKPOINT_LEN_1;
 	}
 
 	return 0;
 }
+
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
@@ -312,11 +301,11 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	if (ret)
 		return ret;
 
-	ret = -EINVAL;
-
 	switch (info->len) {
 	case X86_BREAKPOINT_LEN_1:
 		align = 0;
+		if (info->mask)
+			align = info->mask;
 		break;
 	case X86_BREAKPOINT_LEN_2:
 		align = 1;
@@ -330,7 +319,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		break;
 #endif
 	default:
-		return ret;
+		WARN_ON_ONCE(1);
 	}
 
 	/*
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 0bebb5c348b8..d36f68b08acc 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -595,7 +595,7 @@ 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 *perf_trace_buf_prepare(int size, unsigned short type,
-				    struct pt_regs *regs, int *rctxp);
+				    struct pt_regs **regs, int *rctxp);
 
 static inline void
 perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 664de5a4ec46..5cad0e6f3552 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -469,6 +469,7 @@ struct perf_event_context {
 	 */
 	struct mutex			mutex;
 
+	struct list_head		active_ctx_list;
 	struct list_head		pinned_groups;
 	struct list_head		flexible_groups;
 	struct list_head		event_list;
@@ -519,7 +520,6 @@ struct perf_cpu_context {
 	int				exclusive;
 	struct hrtimer			hrtimer;
 	ktime_t				hrtimer_interval;
-	struct list_head		rotation_list;
 	struct pmu			*unique_pmu;
 	struct perf_cgroup		*cgrp;
 };
@@ -659,6 +659,7 @@ static inline int is_software_event(struct perf_event *event)
 
 extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
+extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64);
 extern void __perf_sw_event(u32, u64, struct pt_regs *, u64);
 
 #ifndef perf_arch_fetch_caller_regs
@@ -683,14 +684,25 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 static __always_inline void
 perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
 {
-	struct pt_regs hot_regs;
+	if (static_key_false(&perf_swevent_enabled[event_id]))
+		__perf_sw_event(event_id, nr, regs, addr);
+}
+
+DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]);
 
+/*
+ * 'Special' version for the scheduler, it hard assumes no recursion,
+ * which is guaranteed by us not actually scheduling inside other swevents
+ * because those disable preemption.
+ */
+static __always_inline void
+perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)
+{
 	if (static_key_false(&perf_swevent_enabled[event_id])) {
-		if (!regs) {
-			perf_fetch_caller_regs(&hot_regs);
-			regs = &hot_regs;
-		}
-		__perf_sw_event(event_id, nr, regs, addr);
+		struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
+
+		perf_fetch_caller_regs(regs);
+		___perf_sw_event(event_id, nr, regs, addr);
 	}
 }
 
@@ -706,7 +718,7 @@ static inline void perf_event_task_sched_in(struct task_struct *prev,
 static inline void perf_event_task_sched_out(struct task_struct *prev,
 					     struct task_struct *next)
 {
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
+	perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0);
 
 	if (static_key_false(&perf_sched_events.key))
 		__perf_event_task_sched_out(prev, next);
@@ -817,6 +829,8 @@ static inline int perf_event_refresh(struct perf_event *event, int refresh)
 static inline void
 perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)	{ }
 static inline void
+perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)			{ }
+static inline void
 perf_bp_event(struct perf_event *event, void *data)			{ }
 
 static inline int perf_register_guest_info_callbacks
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 139b5067345b..27609dfcce25 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -763,7 +763,7 @@ perf_trace_##call(void *__data, proto)					\
 	struct ftrace_event_call *event_call = __data;			\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
 	struct ftrace_raw_##call *entry;				\
-	struct pt_regs __regs;						\
+	struct pt_regs *__regs;						\
 	u64 __addr = 0, __count = 1;					\
 	struct task_struct *__task = NULL;				\
 	struct hlist_head *head;					\
@@ -782,18 +782,19 @@ perf_trace_##call(void *__data, proto)					\
 			     sizeof(u64));				\
 	__entry_size -= sizeof(u32);					\
 									\
-	perf_fetch_caller_regs(&__regs);				\
 	entry = perf_trace_buf_prepare(__entry_size,			\
 			event_call->event.type, &__regs, &rctx);	\
 	if (!entry)							\
 		return;							\
 									\
+	perf_fetch_caller_regs(__regs);					\
+									\
 	tstruct								\
 									\
 	{ assign; }							\
 									\
 	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
-		__count, &__regs, head, __task);			\
+		__count, __regs, head, __task);				\
 }
 
 /*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 19efcf13375a..7f2fbb8b5069 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -872,22 +872,32 @@ void perf_pmu_enable(struct pmu *pmu)
 		pmu->pmu_enable(pmu);
 }
 
-static DEFINE_PER_CPU(struct list_head, rotation_list);
+static DEFINE_PER_CPU(struct list_head, active_ctx_list);
 
 /*
- * perf_pmu_rotate_start() and perf_rotate_context() are fully serialized
- * because they're strictly cpu affine and rotate_start is called with IRQs
- * disabled, while rotate_context is called from IRQ context.
+ * perf_event_ctx_activate(), perf_event_ctx_deactivate(), and
+ * perf_event_task_tick() are fully serialized because they're strictly cpu
+ * affine and perf_event_ctx{activate,deactivate} are called with IRQs
+ * disabled, while perf_event_task_tick is called from IRQ context.
  */
-static void perf_pmu_rotate_start(struct pmu *pmu)
+static void perf_event_ctx_activate(struct perf_event_context *ctx)
 {
-	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-	struct list_head *head = this_cpu_ptr(&rotation_list);
+	struct list_head *head = this_cpu_ptr(&active_ctx_list);
 
 	WARN_ON(!irqs_disabled());
 
-	if (list_empty(&cpuctx->rotation_list))
-		list_add(&cpuctx->rotation_list, head);
+	WARN_ON(!list_empty(&ctx->active_ctx_list));
+
+	list_add(&ctx->active_ctx_list, head);
+}
+
+static void perf_event_ctx_deactivate(struct perf_event_context *ctx)
+{
+	WARN_ON(!irqs_disabled());
+
+	WARN_ON(list_empty(&ctx->active_ctx_list));
+
+	list_del_init(&ctx->active_ctx_list);
 }
 
 static void get_ctx(struct perf_event_context *ctx)
@@ -907,6 +917,84 @@ static void put_ctx(struct perf_event_context *ctx)
 }
 
 /*
+ * Because of perf_event::ctx migration in sys_perf_event_open::move_group and
+ * perf_pmu_migrate_context() we need some magic.
+ *
+ * Those places that change perf_event::ctx will hold both
+ * perf_event_ctx::mutex of the 'old' and 'new' ctx value.
+ *
+ * Lock ordering is by mutex address. There is one other site where
+ * perf_event_context::mutex nests and that is put_event(). But remember that
+ * that is a parent<->child context relation, and migration does not affect
+ * children, therefore these two orderings should not interact.
+ *
+ * The change in perf_event::ctx does not affect children (as claimed above)
+ * because the sys_perf_event_open() case will install a new event and break
+ * the ctx parent<->child relation, and perf_pmu_migrate_context() is only
+ * concerned with cpuctx and that doesn't have children.
+ *
+ * The places that change perf_event::ctx will issue:
+ *
+ *   perf_remove_from_context();
+ *   synchronize_rcu();
+ *   perf_install_in_context();
+ *
+ * to affect the change. The remove_from_context() + synchronize_rcu() should
+ * quiesce the event, after which we can install it in the new location. This
+ * means that only external vectors (perf_fops, prctl) can perturb the event
+ * while in transit. Therefore all such accessors should also acquire
+ * perf_event_context::mutex to serialize against this.
+ *
+ * However; because event->ctx can change