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 while we're waiting to acquire
+ * ctx->mutex we must be careful and use the below perf_event_ctx_lock()
+ * function.
+ *
+ * Lock order:
+ *	task_struct::perf_event_mutex
+ *	  perf_event_context::mutex
+ *	    perf_event_context::lock
+ *	    perf_event::child_mutex;
+ *	    perf_event::mmap_mutex
+ *	    mmap_sem
+ */
+static struct perf_event_context *
+perf_event_ctx_lock_nested(struct perf_event *event, int nesting)
+{
+	struct perf_event_context *ctx;
+
+again:
+	rcu_read_lock();
+	ctx = ACCESS_ONCE(event->ctx);
+	if (!atomic_inc_not_zero(&ctx->refcount)) {
+		rcu_read_unlock();
+		goto again;
+	}
+	rcu_read_unlock();
+
+	mutex_lock_nested(&ctx->mutex, nesting);
+	if (event->ctx != ctx) {
+		mutex_unlock(&ctx->mutex);
+		put_ctx(ctx);
+		goto again;
+	}
+
+	return ctx;
+}
+
+static inline struct perf_event_context *
+perf_event_ctx_lock(struct perf_event *event)
+{
+	return perf_event_ctx_lock_nested(event, 0);
+}
+
+static void perf_event_ctx_unlock(struct perf_event *event,
+				  struct perf_event_context *ctx)
+{
+	mutex_unlock(&ctx->mutex);
+	put_ctx(ctx);
+}
+
+/*
  * This must be done under the ctx->lock, such as to serialize against
  * context_equiv(), therefore we cannot call put_ctx() since that might end up
  * calling scheduler related locks and ctx->lock nests inside those.
@@ -1155,8 +1243,6 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 		ctx->nr_branch_stack++;
 
 	list_add_rcu(&event->event_entry, &ctx->event_list);
-	if (!ctx->nr_events)
-		perf_pmu_rotate_start(ctx->pmu);
 	ctx->nr_events++;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat++;
@@ -1275,6 +1361,8 @@ static void perf_group_attach(struct perf_event *event)
 	if (group_leader == event)
 		return;
 
+	WARN_ON_ONCE(group_leader->ctx != event->ctx);
+
 	if (group_leader->group_flags & PERF_GROUP_SOFTWARE &&
 			!is_software_event(event))
 		group_leader->group_flags &= ~PERF_GROUP_SOFTWARE;
@@ -1296,6 +1384,10 @@ static void
 list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 {
 	struct perf_cpu_context *cpuctx;
+
+	WARN_ON_ONCE(event->ctx != ctx);
+	lockdep_assert_held(&ctx->lock);
+
 	/*
 	 * We can have double detach due to exit/hot-unplug + close.
 	 */
@@ -1380,6 +1472,8 @@ static void perf_group_detach(struct perf_event *event)
 
 		/* Inherit group flags from the previous leader */
 		sibling->group_flags = event->group_flags;
+
+		WARN_ON_ONCE(sibling->ctx != event->ctx);
 	}
 
 out:
@@ -1442,6 +1536,10 @@ event_sched_out(struct perf_event *event,
 {
 	u64 tstamp = perf_event_time(event);
 	u64 delta;
+
+	WARN_ON_ONCE(event->ctx != ctx);
+	lockdep_assert_held(&ctx->lock);
+
 	/*
 	 * An event which could not be activated because of
 	 * filter mismatch still needs to have its timings
@@ -1471,7 +1569,8 @@ event_sched_out(struct perf_event *event,
 
 	if (!is_software_event(event))
 		cpuctx->active_oncpu--;
-	ctx->nr_active--;
+	if (!--ctx->nr_active)
+		perf_event_ctx_deactivate(ctx);
 	if (event->attr.freq && event->attr.sample_freq)
 		ctx->nr_freq--;
 	if (event->attr.exclusive || !cpuctx->active_oncpu)
@@ -1654,7 +1753,7 @@ int __perf_event_disable(void *info)
  * is the current context on this CPU and preemption is disabled,
  * hence we can't get into perf_event_task_sched_out for this context.
  */
-void perf_event_disable(struct perf_event *event)
+static void _perf_event_disable(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *task = ctx->task;
@@ -1695,6 +1794,19 @@ retry:
 	}
 	raw_spin_unlock_irq(&ctx->lock);
 }
+
+/*
+ * Strictly speaking kernel users cannot create groups and therefore this
+ * interface does not need the perf_event_ctx_lock() magic.
+ */
+void perf_event_disable(struct perf_event *event)
+{
+	struct perf_event_context *ctx;
+
+	ctx = perf_event_ctx_lock(event);
+	_perf_event_disable(event);
+	perf_event_ctx_unlock(event, ctx);
+}
 EXPORT_SYMBOL_GPL(perf_event_disable);
 
 static void perf_set_shadow_time(struct perf_event *event,
@@ -1782,7 +1894,8 @@ event_sched_in(struct perf_event *event,
 
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
-	ctx->nr_active++;
+	if (!ctx->nr_active++)
+		perf_event_ctx_activate(ctx);
 	if (event->attr.freq && event->attr.sample_freq)
 		ctx->nr_freq++;
 
@@ -2158,7 +2271,7 @@ unlock:
  * perf_event_for_each_child or perf_event_for_each as described
  * for perf_event_disable.
  */
-void perf_event_enable(struct perf_event *event)
+static void _perf_event_enable(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *task = ctx->task;
@@ -2214,9 +2327,21 @@ retry:
 out:
 	raw_spin_unlock_irq(&ctx->lock);
 }
+
+/*
+ * See perf_event_disable();
+ */
+void perf_event_enable(struct perf_event *event)
+{
+	struct perf_event_context *ctx;
+
+	ctx = perf_event_ctx_lock(event);
+	_perf_event_enable(event);
+	perf_event_ctx_unlock(event, ctx);
+}
 EXPORT_SYMBOL_GPL(perf_event_enable);
 
-int perf_event_refresh(struct perf_event *event, int refresh)
+static int _perf_event_refresh(struct perf_event *event, int refresh)
 {
 	/*
 	 * not supported on inherited events
@@ -2225,10 +2350,25 @@ int perf_event_refresh(struct perf_event *event, int refresh)
 		return -EINVAL;
 
 	atomic_add(refresh, &event->event_limit);
-	perf_event_enable(event);
+	_perf_event_enable(event);
 
 	return 0;
 }
+
+/*
+ * See perf_event_disable()
+ */
+int perf_event_refresh(struct perf_event *event, int refresh)
+{
+	struct perf_event_context *ctx;
+	int ret;
+
+	ctx = perf_event_ctx_lock(event);
+	ret = _perf_event_refresh(event, refresh);
+	perf_event_ctx_unlock(event, ctx);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(perf_event_refresh);
 
 static void ctx_sched_out(struct perf_event_context *ctx,
@@ -2612,12 +2752,6 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 
 	perf_pmu_enable(ctx->pmu);
 	perf_ctx_unlock(cpuctx, ctx);
-
-	/*
-	 * Since these rotations are per-cpu, we need to ensure the
-	 * cpu-context we got scheduled on is actually rotating.
-	 */
-	perf_pmu_rotate_start(ctx->pmu);
 }
 
 /*
@@ -2905,25 +3039,18 @@ static void rotate_ctx(struct perf_event_context *ctx)
 		list_rotate_left(&ctx->flexible_groups);
 }
 
-/*
- * 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.
- */
 static int perf_rotate_context(struct perf_cpu_context *cpuctx)
 {
 	struct perf_event_context *ctx = NULL;
-	int rotate = 0, remove = 1;
+	int rotate = 0;
 
 	if (cpuctx->ctx.nr_events) {
-		remove = 0;
 		if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
 			rotate = 1;
 	}
 
 	ctx = cpuctx->task_ctx;
 	if (ctx && ctx->nr_events) {
-		remove = 0;
 		if (ctx->nr_events != ctx->nr_active)
 			rotate = 1;
 	}
@@ -2947,8 +3074,6 @@ static int perf_rotate_context(struct perf_cpu_context *cpuctx)
 	perf_pmu_enable(cpuctx->ctx.pmu);
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 done:
-	if (remove)
-		list_del_init(&cpuctx->rotation_list);
 
 	return rotate;
 }
@@ -2966,9 +3091,8 @@ bool perf_event_can_stop_tick(void)
 
 void perf_event_task_tick(void)
 {
-	struct list_head *head = this_cpu_ptr(&rotation_list);
-	struct perf_cpu_context *cpuctx, *tmp;
-	struct perf_event_context *ctx;
+	struct list_head *head = this_cpu_ptr(&active_ctx_list);
+	struct perf_event_context *ctx, *tmp;
 	int throttled;
 
 	WARN_ON(!irqs_disabled());
@@ -2976,14 +3100,8 @@ void perf_event_task_tick(void)
 	__this_cpu_inc(perf_throttled_seq);
 	throttled = __this_cpu_xchg(perf_throttled_count, 0);
 
-	list_for_each_entry_safe(cpuctx, tmp, head, rotation_list) {
-		ctx = &cpuctx->ctx;
+	list_for_each_entry_safe(ctx, tmp, head, active_ctx_list)
 		perf_adjust_freq_unthr_context(ctx, throttled);
-
-		ctx = cpuctx->task_ctx;
-		if (ctx)
-			perf_adjust_freq_unthr_context(ctx, throttled);
-	}
 }
 
 static int event_enable_on_exec(struct perf_event *event,
@@ -3142,6 +3260,7 @@ static void __perf_event_init_context(struct perf_event_context *ctx)
 {
 	raw_spin_lock_init(&ctx->lock);
 	mutex_init(&ctx->mutex);
+	INIT_LIST_HEAD(&ctx->active_ctx_list);
 	INIT_LIST_HEAD(&ctx->pinned_groups);
 	INIT_LIST_HEAD(&ctx->flexible_groups);
 	INIT_LIST_HEAD(&ctx->event_list);
@@ -3421,7 +3540,16 @@ static void perf_remove_from_owner(struct perf_event *event)
 	rcu_read_unlock();
 
 	if (owner) {
-		mutex_lock(&owner->perf_event_mutex);
+		/*
+		 * If we're here through perf_event_exit_task() we're already
+		 * holding ctx->mutex which would be an inversion wrt. the
+		 * normal lock order.
+		 *
+		 * However we can safely take this lock because its the child
+		 * ctx->mutex.
+		 */
+		mutex_lock_nested(&owner->perf_event_mutex, SINGLE_DEPTH_NESTING);
+
 		/*
 		 * We have to re-check the event->owner field, if it is cleared
 		 * we raced with perf_event_exit_task(), acquiring the mutex
@@ -3440,7 +3568,7 @@ static void perf_remove_from_owner(struct perf_event *event)
  */
 static void put_event(struct perf_event *event)
 {
-	struct perf_event_context *ctx = event->ctx;
+	struct perf_event_context *ctx;
 
 	if (!atomic_long_dec_and_test(&event->refcount))
 		return;
@@ -3448,7 +3576,6 @@ static void put_event(struct perf_event *event)
 	if (!is_kernel_event(event))
 		perf_remove_from_owner(event);
 
-	WARN_ON_ONCE(ctx->parent_ctx);
 	/*
 	 * There are two ways this annotation is useful:
 	 *
@@ -3461,7 +3588,8 @@ static void put_event(struct perf_event *event)
 	 *     the last filedesc died, so there is no possibility
 	 *     to trigger the AB-BA case.
 	 */
-	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
+	ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING);
+	WARN_ON_ONCE(ctx->parent_ctx);
 	perf_remove_from_context(event, true);
 	mutex_unlock(&ctx->mutex);
 
@@ -3547,12 +3675,13 @@ static int perf_event_read_group(struct perf_event *event,
 				   u64 read_format, char __user *buf)
 {
 	struct perf_event *leader = event->group_leader, *sub;
-	int n = 0, size = 0, ret = -EFAULT;
 	struct perf_event_context *ctx = leader->ctx;
-	u64 values[5];
+	int n = 0, size = 0, ret;
 	u64 count, enabled, running;
+	u64 values[5];
+
+	lockdep_assert_held(&ctx->mutex);
 
-	mutex_lock(&ctx->mutex);
 	count = perf_event_read_value(leader, &enabled, &running);
 
 	values[n++] = 1 + leader->nr_siblings;
@@ -3567,7 +3696,7 @@ static int perf_event_read_group(struct perf_event *event,
 	size = n * sizeof(u64);
 
 	if (copy_to_user(buf, values, size))
-		goto unlock;
+		return -EFAULT;
 
 	ret = size;
 
@@ -3581,14 +3710,11 @@ static int perf_event_read_group(struct perf_event *event,
 		size = n * sizeof(u64);
 
 		if (copy_to_user(buf + ret, values, size)) {
-			ret = -EFAULT;
-			goto unlock;
+			return -EFAULT;
 		}
 
 		ret += size;
 	}
-unlock:
-	mutex_unlock(&ctx->mutex);
 
 	return ret;
 }
@@ -3660,8 +3786,14 @@ static ssize_t
 perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 {
 	struct perf_event *event = file->private_data;
+	struct perf_event_context *ctx;
+	int ret;
 
-	return perf_read_hw(event, buf, count);
+	ctx = perf_event_ctx_lock(event);
+	ret = perf_read_hw(event, buf, count);
+	perf_event_ctx_unlock(event, ctx);
+
+	return ret;
 }
 
 static unsigned int perf_poll(struct file *file, poll_table *wait)
@@ -3687,7 +3819,7 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 	return events;
 }
 
-static void perf_event_reset(struct perf_event *event)
+static void _perf_event_reset(struct perf_event *event)
 {
 	(void)perf_event_read(event);
 	local64_set(&event->count, 0);
@@ -3706,6 +3838,7 @@ static void perf_event_for_each_child(struct perf_event *event,
 	struct perf_event *child;
 
 	WARN_ON_ONCE(event->ctx->parent_ctx);
+
 	mutex_lock(&event->child_mutex);
 	func(event);
 	list_for_each_entry(child, &event->child_list, child_list)
@@ -3719,14 +3852,13 @@ static void perf_event_for_each(struct perf_event *event,
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_event *sibling;
 
-	WARN_ON_ONCE(ctx->parent_ctx);
-	mutex_lock(&ctx->mutex);
+	lockdep_assert_held(&ctx->mutex);
+
 	event = event->group_leader;
 
 	perf_event_for_each_child(event, func);
 	list_for_each_entry(sibling, &event->sibling_list, group_entry)
 		perf_event_for_each_child(sibling, func);
-	mutex_unlock(&ctx->mutex);
 }
 
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
@@ -3796,25 +3928,24 @@ static int perf_event_set_output(struct perf_event *event,
 				 struct perf_event *output_event);
 static int perf_event_set_filter(struct perf_event *event, void __user *arg);
 
-static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned long arg)
 {
-	struct perf_event *event = file->private_data;
 	void (*func)(struct perf_event *);
 	u32 flags = arg;
 
 	switch (cmd) {
 	case PERF_EVENT_IOC_ENABLE:
-		func = perf_event_enable;
+		func = _perf_event_enable;
 		break;
 	case PERF_EVENT_IOC_DISABLE:
-		func = perf_event_disable;
+		func = _perf_event_disable;
 		break;
 	case PERF_EVENT_IOC_RESET:
-		func = perf_event_reset;
+		func = _perf_event_reset;
 		break;
 
 	case PERF_EVENT_IOC_REFRESH:
-		return perf_event_refresh(event, arg);
+		return _perf_event_refresh(event, arg);
 
 	case PERF_EVENT_IOC_PERIOD:
 		return perf_event_period(event, (u64 __user *)arg);
@@ -3861,6 +3992,19 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	return 0;
 }
 
+static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct perf_event *event = file->private_data;
+	struct perf_event_context *ctx;
+	long ret;
+
+	ctx = perf_event_ctx_lock(event);
+	ret = _perf_ioctl(event, cmd, arg);
+	perf_event_ctx_unlock(event, ctx);
+
+	return ret;
+}
+
 #ifdef CONFIG_COMPAT
 static long perf_compat_ioctl(struct file *file, unsigned int cmd,
 				unsigned long arg)
@@ -3883,11 +4027,15 @@ static long perf_compat_ioctl(struct file *file, unsigned int cmd,
 
 int perf_event_task_enable(void)
 {
+	struct perf_event_context *ctx;
 	struct perf_event *event;
 
 	mutex_lock(&current->perf_event_mutex);
-	list_for_each_entry(event, &current->perf_event_list, owner_entry)
-		perf_event_for_each_child(event, perf_event_enable);
+	list_for_each_entry(event, &current->perf_event_list, owner_entry) {
+		ctx = perf_event_ctx_lock(event);
+		perf_event_for_each_child(event, _perf_event_enable);
+		perf_event_ctx_unlock(event, ctx);
+	}
 	mutex_unlock(&current->perf_event_mutex);
 
 	return 0;
@@ -3895,11 +4043,15 @@ int perf_event_task_enable(void)
 
 int perf_event_task_disable(void)
 {
+	struct perf_event_context *ctx;
 	struct perf_event *event;
 
 	mutex_lock(&current->perf_event_mutex);
-	list_for_each_entry(event, &current->perf_event_list, owner_entry)
-		perf_event_for_each_child(event, perf_event_disable);
+	list_for_each_entry(event, &current->perf_event_list, owner_entry) {
+		ctx = perf_event_ctx_lock(event);
+		perf_event_for_each_child(event, _perf_event_disable);
+		perf_event_ctx_unlock(event, ctx);
+	}
 	mutex_unlock(&current->perf_event_mutex);
 
 	return 0;
@@ -5889,6 +6041,8 @@ end:
 	rcu_read_unlock();
 }
 
+DEFINE_PER_CPU(struct pt_regs, __perf_regs[4]);
+
 int perf_swevent_get_recursion_context(void)
 {
 	struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
@@ -5904,21 +6058,30 @@ inline void perf_swevent_put_recursion_context(int rctx)
 	put_recursion_context(swhash->recursion, rctx);
 }
 
-void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
+void ___perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
 {
 	struct perf_sample_data data;
-	int rctx;
 
-	preempt_disable_notrace();
-	rctx = perf_swevent_get_recursion_context();
-	if (rctx < 0)
+	if (WARN_ON_ONCE(!regs))
 		return;
 
 	perf_sample_data_init(&data, addr, 0);
-
 	do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, &data, regs);
+}
+
+void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
+{
+	int rctx;
+
+	preempt_disable_notrace();
+	rctx = perf_swevent_get_recursion_context();
+	if (unlikely(rctx < 0))
+		goto fail;
+
+	___perf_sw_event(event_id, nr, regs, addr);
 
 	perf_swevent_put_recursion_context(rctx);
+fail:
 	preempt_enable_notrace();
 }
 
@@ -6780,7 +6943,6 @@ skip_type:
 
 		__perf_cpu_hrtimer_init(cpuctx, cpu);
 
-		INIT_LIST_HEAD(&cpuctx->rotation_list);
 		cpuctx->unique_pmu = pmu;
 	}
 
@@ -6853,6 +7015,20 @@ void perf_pmu_unregister(struct pmu *pmu)
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);
 
+static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
+{
+	int ret;
+
+	if (!try_module_get(pmu->module))
+		return -ENODEV;
+	event->pmu = pmu;
+	ret = pmu->event_init(event);
+	if (ret)
+		module_put(pmu->module);
+
+	return ret;
+}
+
 struct pmu *perf_init_event(struct perf_event *event)
 {
 	struct pmu *pmu = NULL;
@@ -6865,24 +7041,14 @@ struct pmu *perf_init_event(struct perf_event *event)
 	pmu = idr_find(&pmu_idr, event->attr.type);
 	rcu_read_unlock();
 	if (pmu) {
-		if (!try_module_get(pmu->module)) {
-			pmu = ERR_PTR(-ENODEV);
-			goto unlock;
-		}
-		event->pmu = pmu;
-		ret = pmu->event_init(event);
+		ret = perf_try_init_event(pmu, event);
 		if (ret)
 			pmu = ERR_PTR(ret);
 		goto unlock;
 	}
 
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		if (!try_module_get(pmu->module)) {
-			pmu = ERR_PTR(-ENODEV);
-			goto unlock;
-		}
-		event->pmu = pmu;
-		ret = pmu->event_init(event);
+		ret = perf_try_init_event(pmu, event);
 		if (!ret)
 			goto unlock;
 
@@ -7246,6 +7412,15 @@ out:
 	return ret;
 }
 
+static void mutex_lock_double(struct mutex *a, struct mutex *b)
+{
+	if (b < a)
+		swap(a, b);
+
+	mutex_lock(a);
+	mutex_lock_nested(b, SINGLE_DEPTH_NESTING);
+}
+
 /**
  * sys_perf_event_open - open a performance event, associate it to a task/cpu
  *
@@ -7261,7 +7436,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	struct perf_event *group_leader = NULL, *output_event = NULL;
 	struct perf_event *event, *sibling;
 	struct perf_event_attr attr;
-	struct perf_event_context *ctx;
+	struct perf_event_context *ctx, *uninitialized_var(gctx);
 	struct file *event_file = NULL;
 	struct fd group = {NULL, 0};
 	struct task_struct *task = NULL;
@@ -7459,43 +7634,68 @@ SYSCALL_DEFINE5(perf_event_open,
 	}
 
 	if (move_group) {
-		struct perf_event_context *gctx = group_leader->ctx;
-
-		mutex_lock(&gctx->mutex);
-		perf_remove_from_context(group_leader, false);
+		gctx = group_leader->ctx;
 
 		/*
-		 * Removing from the context ends up with disabled
-		 * event. What we want here is event in the initial
-		 * startup state, ready to be add into new context.
+		 * See perf_event_ctx_lock() for comments on the details
+		 * of swizzling perf_event::ctx.
 		 */
-		perf_event__state_init(group_leader);
+		mutex_lock_double(&gctx->mutex, &ctx->mutex);
+
+		perf_remove_from_context(group_leader, false);
+
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
 			perf_remove_from_context(sibling, false);
-			perf_event__state_init(sibling);
 			put_ctx(gctx);
 		}
-		mutex_unlock(&gctx->mutex);
-		put_ctx(gctx);
+	} else {
+		mutex_lock(&ctx->mutex);
 	}
 
 	WARN_ON_ONCE(ctx->parent_ctx);
-	mutex_lock(&ctx->mutex);
 
 	if (move_group) {
+		/*
+		 * Wait for everybody to stop referencing the events through
+		 * the old lists, before installing it on new lists.
+		 */
 		synchronize_rcu();
-		perf_install_in_context(ctx, group_leader, group_leader->cpu);
-		get_ctx(ctx);
+
+		/*
+		 * Install the group siblings before the group leader.
+		 *
+		 * Because a group leader will try and install the entire group
+		 * (through the sibling list, which is still in-tact), we can
+		 * end up with siblings installed in the wrong context.
+		 *
+		 * By installing siblings first we NO-OP because they're not
+		 * reachable through the group lists.
+		 */
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
+			perf_event__state_init(sibling);
 			perf_install_in_context(ctx, sibling, sibling->cpu);
 			get_ctx(ctx);
 		}
+
+		/*
+		 * Removing from the context ends up with disabled
+		 * event. What we want here is event in the initial
+		 * startup state, ready to be add into new context.
+		 */
+		perf_event__state_init(group_leader);
+		perf_install_in_context(ctx, group_leader, group_leader->cpu);
+		get_ctx(ctx);
 	}
 
 	perf_install_in_context(ctx, event, event->cpu);
 	perf_unpin_context(ctx);
+
+	if (move_group) {
+		mutex_unlock(&gctx->mutex);
+		put_ctx(gctx);
+	}
 	mutex_unlock(&ctx->mutex);
 
 	put_online_cpus();
@@ -7603,7 +7803,11 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 	src_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, src_cpu)->ctx;
 	dst_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, dst_cpu)->ctx;
 
-	mutex_lock(&src_ctx->mutex);
+	/*
+	 * See perf_event_ctx_lock() for comments on the details
+	 * of swizzling perf_event::ctx.
+	 */
+	mutex_lock_double(&src_ctx->mutex, &dst_ctx->mutex);
 	list_for_each_entry_safe(event, tmp, &src_ctx->event_list,
 				 event_entry) {
 		perf_remove_from_context(event, false);
@@ -7611,11 +7815,36 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 		put_ctx(src_ctx);
 		list_add(&event->migrate_entry, &events);
 	}
-	mutex_unlock(&src_ctx->mutex);
 
+	/*
+	 * Wait for the events to quiesce before re-instating them.
+	 */
 	synchronize_rcu();
 
-	mutex_lock(&dst_ctx->mutex);
+	/*
+	 * Re-instate events in 2 passes.
+	 *
+	 * Skip over group leaders and only install siblings on this first
+	 * pass, siblings will not get enabled without a leader, however a
+	 * leader will enable its siblings, even if those are still on the old
+	 * context.
+	 */
+	list_for_each_entry_safe(event, tmp, &events, migrate_entry) {
+		if (event->group_leader == event)
+			continue;
+
+		list_del(&event->migrate_entry);
+		if (event->state >= PERF_EVENT_STATE_OFF)
+			event->state = PERF_EVENT_STATE_INACTIVE;
+		account_event_cpu(event, dst_cpu);
+		perf_install_in_context(dst_ctx, event, dst_cpu);
+		get_ctx(dst_ctx);
+	}
+
+	/*
+	 * Once all the siblings are setup properly, install the group leaders
+	 * to make it go.
+	 */
 	list_for_each_entry_safe(event, tmp, &events, migrate_entry) {
 		list_del(&event->migrate_entry);
 		if (event->state >= PERF_EVENT_STATE_OFF)
@@ -7625,6 +7854,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 		get_ctx(dst_ctx);
 	}
 	mutex_unlock(&dst_ctx->mutex);
+	mutex_unlock(&src_ctx->mutex);
 }
 EXPORT_SYMBOL_GPL(perf_pmu_migrate_context);
 
@@ -7811,14 +8041,19 @@ static void perf_free_event(struct perf_event *event,
 
 	put_event(parent);
 
+	raw_spin_lock_irq(&ctx->lock);
 	perf_group_detach(event);
 	list_del_event(event, ctx);
+	raw_spin_unlock_irq(&ctx->lock);
 	free_event(event);
 }
 
 /*
- * free an unexposed, unused context as created by inheritance by
+ * Free an unexposed, unused context as created by inheritance by
  * perf_event_init_task below, used by fork() in case of fail.
+ *
+ * Not all locks are strictly required, but take them anyway to be nice and
+ * help out with the lockdep assertions.
  */
 void perf_event_free_task(struct task_struct *task)
 {
@@ -8137,7 +8372,7 @@ static void __init perf_event_init_all_cpus(void)
 	for_each_possible_cpu(cpu) {
 		swhash = &per_cpu(swevent_htable, cpu);
 		mutex_init(&swhash->hlist_mutex);
-		INIT_LIST_HEAD(&per_cpu(rotation_list, cpu));
+		INIT_LIST_HEAD(&per_cpu(active_ctx_list, cpu));
 	}
 }
 
@@ -8158,22 +8393,11 @@ static void perf_event_init_cpu(int cpu)
 }
 
 #if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC
-static void perf_pmu_rotate_stop(struct pmu *pmu)
-{
-	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-
-	WARN_ON(!irqs_disabled());
-
-	list_del_init(&cpuctx->rotation_list);
-}
-
 static void __perf_event_exit_context(void *__info)
 {
 	struct remove_event re = { .detach_group = true };
 	struct perf_event_context *ctx = __info;
 
-	perf_pmu_rotate_stop(ctx->pmu);
-
 	rcu_read_lock();
 	list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry)
 		__perf_remove_from_context(&re);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 146a5792b1d2..eadb95ce7aac 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -13,12 +13,13 @@
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/circ_buf.h>
+#include <linux/poll.h>
 
 #include "internal.h"
 
 static void perf_output_wakeup(struct perf_output_handle *handle)
 {
-	atomic_set(&handle->rb->poll, POLL_IN);
+	atomic_set(&handle->rb->poll, POLLIN);
 
 	handle->event->pending_wakeup = 1;
 	irq_work_queue(&handle->event->pending);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5eab11d4b747..1612578a5b7a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1082,7 +1082,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 		if (p->sched_class->migrate_task_rq)
 			p->sched_class->migrate_task_rq(p, new_cpu);
 		p->se.nr_migrations++;
-		perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
+		perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
 	}
 
 	__set_task_cpu(p, new_cpu);
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 4b9c114ee9de..6fa484de2ba1 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -261,7 +261,7 @@ void perf_trace_del(struct perf_event *p_event, int flags)
 }
 
 void *perf_trace_buf_prepare(int size, unsigned short type,
-			     struct pt_regs *regs, int *rctxp)
+			     struct pt_regs **regs, int *rctxp)
 {
 	struct trace_entry *entry;
 	unsigned long flags;
@@ -280,6 +280,8 @@ void *perf_trace_buf_prepare(int size, unsigned short type,
 	if (*rctxp < 0)
 		return NULL;
 
+	if (regs)
+		*regs = this_cpu_ptr(&__perf_regs[*rctxp]);
 	raw_data = this_cpu_ptr(perf_trace_buf[*rctxp]);
 
 	/* zero the dead bytes from align to not leak stack to user */
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 5edb518be345..296079ae6583 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1148,7 +1148,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
+	entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx);
 	if (!entry)
 		return;
 
@@ -1179,7 +1179,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
+	entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx);
 	if (!entry)
 		return;
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index c6ee36fcbf90..f97f6e3a676c 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -574,7 +574,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	size -= sizeof(u32);
 
 	rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
-				sys_data->enter_event->event.type, regs, &rctx);
+				sys_data->enter_event->event.type, NULL, &rctx);
 	if (!rec)
 		return;
 
@@ -647,7 +647,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	size -= sizeof(u32);
 
 	rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
-				sys_data->exit_event->event.type, regs, &rctx);
+				sys_data->exit_event->event.type, NULL, &rctx);
 	if (!rec)
 		return;
 
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 8520acc34b18..b11441321e7a 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1111,7 +1111,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 	if (hlist_empty(head))
 		goto out;
 
-	entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
+	entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx);
 	if (!entry)
 		goto out;
 
diff --git a/tools/lib/api/fs/debugfs.c b/tools/lib/api/fs/debugfs.c
index 86ea2d7b8845..d2b18e887071 100644
--- a/tools/lib/api/fs/debugfs.c
+++ b/tools/lib/api/fs/debugfs.c
@@ -1,3 +1,4 @@
+#define _GNU_SOURCE
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -98,3 +99,45 @@ char *debugfs_mount(const char *mountpoint)
 out:
 	return debugfs_mountpoint;
 }
+
+int debugfs__strerror_open(int err, char *buf, size_t size, const char *filename)
+{
+	char sbuf[128];
+
+	switch (err) {
+	case ENOENT:
+		if (debugfs_found) {
+			snprintf(buf, size,
+				 "Error:\tFile %s/%s not found.\n"
+				 "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n",
+				 debugfs_mountpoint, filename);
+			break;
+		}
+		snprintf(buf, size, "%s",
+			 "Error:\tUnable to find debugfs\n"
+			 "Hint:\tWas your kernel compiled with debugfs support?\n"
+			 "Hint:\tIs the debugfs filesystem mounted?\n"
+			 "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'");
+		break;
+	case EACCES:
+		snprintf(buf, size,
+			 "Error:\tNo permissions to read %s/%s\n"
+			 "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
+			 debugfs_mountpoint, filename, debugfs_mountpoint);
+		break;
+	default:
+		snprintf(buf, size, "%s", strerror_r(err, sbuf, sizeof(sbuf)));
+		break;
+	}
+
+	return 0;
+}
+
+int debugfs__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name)
+{
+	char path[PATH_MAX];
+
+	snprintf(path, PATH_MAX, "tracing/events/%s/%s", sys, name ?: "*");
+
+	return debugfs__strerror_open(err, buf, size, path);
+}
diff --git a/tools/lib/api/fs/debugfs.h b/tools/lib/api/fs/debugfs.h
index f19d3df9609d..0739881a9897 100644
--- a/tools/lib/api/fs/debugfs.h
+++ b/tools/lib/api/fs/debugfs.h
@@ -26,4 +26,7 @@ char *debugfs_mount(const char *mountpoint);
 
 extern char debugfs_mountpoint[];
 
+int debugfs__strerror_open(int err, char *buf, size_t size, const char *filename);
+int debugfs__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name);
+
 #endif /* __API_DEBUGFS_H__ */
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index cf3a44bf1ec3..afe20ed9fac8 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -32,6 +32,7 @@
 #include <stdint.h>
 #include <limits.h>
 
+#include <netinet/ip6.h>
 #include "event-parse.h"
 #include "event-utils.h"
 
@@ -4149,6 +4150,324 @@ static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size,
 	trace_seq_printf(s, fmt, buf[0], buf[1], buf[2], buf[3], buf[4], buf[5]);
 }
 
+static void print_ip4_addr(struct trace_seq *s, char i, unsigned char *buf)
+{
+	const char *fmt;
+
+	if (i == 'i')
+		fmt = "%03d.%03d.%03d.%03d";
+	else
+		fmt = "%d.%d.%d.%d";
+
+	trace_seq_printf(s, fmt, buf[0], buf[1], buf[2], buf[3]);
+}
+
+static inline bool ipv6_addr_v4mapped(const struct in6_addr *a)
+{
+	return ((unsigned long)(a->s6_addr32[0] | a->s6_addr32[1]) |
+		(unsigned long)(a->s6_addr32[2] ^ htonl(0x0000ffff))) == 0UL;
+}
+
+static inline bool ipv6_addr_is_isatap(const struct in6_addr *addr)
+{
+	return (addr->s6_addr32[2] | htonl(0x02000000)) == htonl(0x02005EFE);
+}
+
+static void print_ip6c_addr(struct trace_seq *s, unsigned char *addr)
+{
+	int i, j, range;
+	unsigned char zerolength[8];
+	int longest = 1;
+	int colonpos = -1;
+	uint16_t word;
+	uint8_t hi, lo;
+	bool needcolon = false;
+	bool useIPv4;
+	struct in6_addr in6;
+
+	memcpy(&in6, addr, sizeof(struct in6_addr));
+
+	useIPv4 = ipv6_addr_v4mapped(&in6) || ipv6_addr_is_isatap(&in6);
+
+	memset(zerolength, 0, sizeof(zerolength));
+
+	if (useIPv4)
+		range = 6;
+	else
+		range = 8;
+
+	/* find position of longest 0 run */
+	for (i = 0; i < range; i++) {
+		for (j = i; j < range; j++) {
+			if (in6.s6_addr16[j] != 0)
+				break;
+			zerolength[i]++;
+		}
+	}
+	for (i = 0; i < range; i++) {
+		if (zerolength[i] > longest) {
+			longest = zerolength[i];
+			colonpos = i;
+		}
+	}
+	if (longest == 1)		/* don't compress a single 0 */
+		colonpos = -1;
+
+	/* emit address */
+	for (i = 0; i < range; i++) {
+		if (i == colonpos) {
+			if (needcolon || i == 0)
+				trace_seq_printf(s, ":");
+			trace_seq_printf(s, ":");
+			needcolon = false;
+			i += longest - 1;
+			continue;
+		}
+		if (needcolon) {
+			trace_seq_printf(s, ":");
+			needcolon = false;
+		}
+		/* hex u16 without leading 0s */
+		word = ntohs(in6.s6_addr16[i]);
+		hi = word >> 8;
+		lo = word & 0xff;
+		if (hi)
+			trace_seq_printf(s, "%x%02x", hi, lo);
+		else
+			trace_seq_printf(s, "%x", lo);
+
+		needcolon = true;
+	}
+
+	if (useIPv4) {
+		if (needcolon)
+			trace_seq_printf(s, ":");
+		print_ip4_addr(s, 'I', &in6.s6_addr[12]);
+	}
+
+	return;
+}
+
+static void print_ip6_addr(struct trace_seq *s, char i, unsigned char *buf)
+{
+	int j;
+
+	for (j = 0; j < 16; j += 2) {
+		trace_seq_printf(s, "%02x%02x", buf[j], buf[j+1]);
+		if (i == 'I' && j < 14)
+			trace_seq_printf(s, ":");
+	}
+}
+
+/*
+ * %pi4   print an IPv4 address with leading zeros
+ * %pI4   print an IPv4 address without leading zeros
+ * %pi6   print an IPv6 address without colons
+ * %pI6   print an IPv6 address with colons
+ * %pI6c  print an IPv6 address in compressed form with colons
+ * %pISpc print an IP address based on sockaddr; p adds port.
+ */
+static int print_ipv4_arg(struct trace_seq *s, const char *ptr, char i,
+			  void *data, int size, struct event_format *event,
+			  struct print_arg *arg)
+{
+	unsigned char *buf;
+
+	if (arg->type == PRINT_FUNC) {
+		process_defined_func(s, data, size, event, arg);
+		return 0;
+	}
+
+	if (arg->type != PRINT_FIELD) {
+		trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type);
+		return 0;
+	}
+
+	if (!arg->field.field) {
+		arg->field.field =
+			pevent_find_any_field(event, arg->field.name);
+		if (!arg->field.field) {
+			do_warning("%s: field %s not found",
+				   __func__, arg->field.name);
+			return 0;
+		}
+	}
+
+	buf = data + arg->field.field->offset;
+
+	if (arg->field.field->size != 4) {
+		trace_seq_printf(s, "INVALIDIPv4");
+		return 0;
+	}
+	print_ip4_addr(s, i, buf);
+
+	return 0;
+}
+
+static int print_ipv6_arg(struct trace_seq *s, const char *ptr, char i,
+			  void *data, int size, struct event_format *event,
+			  struct print_arg *arg)
+{
+	char have_c = 0;
+	unsigned char *buf;
+	int rc = 0;
+
+	/* pI6c */
+	if (i == 'I' && *ptr == 'c') {
+		have_c = 1;
+		ptr++;
+		rc++;
+	}
+
+	if (arg->type == PRINT_FUNC) {
+		process_defined_func(s, data, size, event, arg);
+		return rc;
+	}
+
+	if (arg->type != PRINT_FIELD) {
+		trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type);
+		return rc;
+	}
+
+	if (!arg->field.field) {
+		arg->field.field =
+			pevent_find_any_field(event, arg->field.name);
+		if (!arg->field.field) {
+			do_warning("%s: field %s not found",
+				   __func__, arg->field.name);
+			return rc;
+		}
+	}
+
+	buf = data + arg->field.field->offset;
+
+	if (arg->field.field->size != 16) {
+		trace_seq_printf(s, "INVALIDIPv6");
+		return rc;
+	}
+
+	if (have_c)
+		print_ip6c_addr(s, buf);
+	else
+		print_ip6_addr(s, i, buf);
+
+	return rc;
+}
+
+static int print_ipsa_arg(struct trace_seq *s, const char *ptr, char i,
+			  void *data, int size, struct event_format *event,
+			  struct print_arg *arg)
+{
+	char have_c = 0, have_p = 0;
+	unsigned char *buf;
+	struct sockaddr_storage *sa;
+	int rc = 0;
+
+	/* pISpc */
+	if (i == 'I') {
+		if (*ptr == 'p') {
+			have_p = 1;
+			ptr++;
+			rc++;
+		}
+		if (*ptr == 'c') {
+			have_c = 1;
+			ptr++;
+			rc++;
+		}
+	}
+
+	if (arg->type == PRINT_FUNC) {
+		process_defined_func(s, data, size, event, arg);
+		return rc;
+	}
+
+	if (arg->type != PRINT_FIELD) {
+		trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type);
+		return rc;
+	}
+
+	if (!arg->field.field) {
+		arg->field.field =
+			pevent_find_any_field(event, arg->field.name);
+		if (!arg->field.field) {
+			do_warning("%s: field %s not found",
+				   __func__, arg->field.name);
+			return rc;
+		}
+	}
+
+	sa = (struct sockaddr_storage *) (data + arg->field.field->offset);
+
+	if (sa->ss_family == AF_INET) {
+		struct sockaddr_in *sa4 = (struct sockaddr_in *) sa;
+
+		if (arg->field.field->size < sizeof(struct sockaddr_in)) {
+			trace_seq_printf(s, "INVALIDIPv4");
+			return rc;
+		}
+
+		print_ip4_addr(s, i, (unsigned char *) &sa4->sin_addr);
+		if (have_p)
+			trace_seq_printf(s, ":%d", ntohs(sa4->sin_port));
+
+
+	} else if (sa->ss_family == AF_INET6) {
+		struct sockaddr_in6 *sa6 = (struct sockaddr_in6 *) sa;
+
+		if (arg->field.field->size < sizeof(struct sockaddr_in6)) {
+			trace_seq_printf(s, "INVALIDIPv6");
+			return rc;
+		}
+
+		if (have_p)
+			trace_seq_printf(s, "[");
+
+		buf = (unsigned char *) &sa6->sin6_addr;
+		if (have_c)
+			print_ip6c_addr(s, buf);
+		else
+			print_ip6_addr(s, i, buf);
+
+		if (have_p)
+			trace_seq_printf(s, "]:%d", ntohs(sa6->sin6_port));
+	}
+
+	return rc;
+}
+
+static int print_ip_arg(struct trace_seq *s, const char *ptr,
+			void *data, int size, struct event_format *event,
+			struct print_arg *arg)
+{
+	char i = *ptr;  /* 'i' or 'I' */
+	char ver;
+	int rc = 0;
+
+	ptr++;
+	rc++;
+
+	ver = *ptr;
+	ptr++;
+	rc++;
+
+	switch (ver) {
+	case '4':
+		rc += print_ipv4_arg(s, ptr, i, data, size, event, arg);
+		break;
+	case '6':
+		rc += print_ipv6_arg(s, ptr, i, data, size, event, arg);
+		break;
+	case 'S':
+		rc += print_ipsa_arg(s, ptr, i, data, size, event, arg);
+		break;
+	default:
+		return 0;
+	}
+
+	return rc;
+}
+
 static int is_printable_array(char *p, unsigned int len)
 {
 	unsigned int i;
@@ -4337,6 +4656,15 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 					ptr++;
 					arg = arg->next;
 					break;
+				} else if (*(ptr+1) == 'I' || *(ptr+1) == 'i') {
+					int n;
+
+					n = print_ip_arg(s, ptr+1, data, size, event, arg);
+					if (n > 0) {
+						ptr += n;
+						arg = arg->next;
+						break;
+					}
 				}
 
 				/* fall through */
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index fd77d81ea748..0294c57b1f5e 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -38,7 +38,7 @@ OPTIONS
 --remove=::
         Remove specified file from the cache.
 -M::
---missing=:: 
+--missing=::
 	List missing build ids in the cache for the specified file.
 -u::
 --update::
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index cbb4f743d921..3e2aec94f806 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -89,6 +89,19 @@ raw encoding of 0x1A8 can be used:
 You should refer to the processor specific documentation for getting these
 details. Some of them are referenced in the SEE ALSO section below.
 
+PARAMETERIZED EVENTS
+--------------------
+
+Some pmu events listed by 'perf-list' will be displayed with '?' in them. For
+example:
+
+  hv_gpci/dtbp_ptitc,phys_processor_idx=?/
+
+This means that when provided as an event, a value for '?' must
+also be supplied. For example:
+
+  perf stat -C 0 -e 'hv_gpci/dtbp_ptitc,phys_processor_idx=0x2/' ...
+
 OPTIONS
 -------
 
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 1d78a4064da4..43310d8661fe 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -12,11 +12,12 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-"perf mem -t <TYPE> record" runs a command and gathers memory operation data
+"perf mem record" runs a command and gathers memory operation data
 from it, into perf.data. Perf record options are accepted and are passed through.
 
-"perf mem -t <TYPE> report" displays the result. It invokes perf report with the
-right set of options to display a memory access profile.
+"perf mem report" displays the result. It invokes perf report with the
+right set of options to display a memory access profile. By default, loads
+and stores are sampled. Use the -t option to limit to loads or stores.
 
 Note that on Intel systems the memory latency reported is the use-latency,
 not the pure load (or store latency). Use latency includes any pipeline
@@ -29,7 +30,7 @@ OPTIONS
 
 -t::
 --type=::
-	Select the memory operation type: load or store (default: load)
+	Select the memory operation type: load or store (default: load,store)
 
 -D::
 --dump-raw-samples=::
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index af9a54ece024..31e977459c51 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -33,12 +33,27 @@ OPTIONS
         - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
 	  hexadecimal event descriptor.
 
-        - a hardware breakpoint event in the form of '\mem:addr[:access]'
+	- a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where
+	  'param1', 'param2', etc are defined as formats for the PMU in
+	  /sys/bus/event_sources/devices/<pmu>/format/*.
+
+	- a symbolically formed event like 'pmu/config=M,config1=N,config3=K/'
+
+          where M, N, K are numbers (in decimal, hex, octal format). Acceptable
+          values for each of 'config', 'config1' and 'config2' are defined by
+          corresponding entries in /sys/bus/event_sources/devices/<pmu>/format/*
+          param1 and param2 are defined as formats for the PMU in:
+          /sys/bus/event_sources/devices/<pmu>/format/*
+
+        - a hardware breakpoint event in the form of '\mem:addr[/len][:access]'
           where addr is the address in memory you want to break in.
           Access is the memory access type (read, write, execute) it can
-          be passed as follows: '\mem:addr[:[r][w][x]]'.
+          be passed as follows: '\mem:addr[:[r][w][x]]'. len is the range,
+          number of bytes from specified addr, which the breakpoint will cover.
           If you want to profile read-write accesses in 0x1000, just set
           'mem:0x1000:rw'.
+          If you want to profile write accesses in [0x1000~1008), just set
+          'mem:0x1000/8:w'.
 
 --filter=<filter>::
         Event filter.
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 21494806c0ab..a21eec05bc42 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -125,46 +125,46 @@ OPTIONS
 	is equivalent to:
 
 		perf script -f trace:<fields> -f sw:<fields> -f hw:<fields>
-    
+
 	i.e., the specified fields apply to all event types if the type string
 	is not given.
-    
+
 	The arguments are processed in the order received. A later usage can
 	reset a prior request. e.g.:
-    
+
 		-f trace: -f comm,tid,time,ip,sym
-    
+
 	The first -f suppresses trace events (field list is ""), but then the
 	second invocation sets the fields to comm,tid,time,ip,sym. In this case a
 	warning is given to the user:
-    
+
 		"Overriding previous field request for all events."
-    
+
 	Alternatively, consider the order:
-    
+
 		-f comm,tid,time,ip,sym -f trace:
-    
+
 	The first -f sets the fields for all events and the second -f
 	suppresses trace events. The user is given a warning message about
 	the override, and the result of the above is that only S/W and H/W
 	events are displayed with the given fields.
-    
+
 	For the 'wildcard' option if a user selected field is invalid for an
 	event type, a message is displayed to the user that the option is
 	ignored for that type. For example:
-    
+
 		$ perf script -f comm,tid,trace
 		'trace' not valid for hardware events. Ignoring.
 		'trace' not valid for software events. Ignoring.
-    
+
 	Alternatively, if the type is given an invalid field is specified it
 	is an error. For example:
-    
+
         perf script -v -f sw:comm,tid,trace
         'trace' not valid for software events.
-    
+
 	At this point usage is displayed, and perf-script exits.
-    
+
 	Finally, a user may not set fields to none for all event types.
 	i.e., -f "" is not allowed.
 
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 29ee857c09c6..04e150d83e7d 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -25,10 +25,22 @@ OPTIONS
 
 -e::
 --event=::
-	Select the PMU event. Selection can be a symbolic event name
-	(use 'perf list' to list all events) or a raw PMU
-	event (eventsel+umask) in the form of rNNN where NNN is a
-	 hexadecimal event descriptor.
+	Select the PMU event. Selection can be:
+
+	- a symbolic event name (use 'perf list' to list all events)
+
+	- a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
+	  hexadecimal event descriptor.
+
+	- a symbolically formed event like 'pmu/param1=0x3,param2/' where
+	  param1 and param2 are defined as formats for the PMU in
+	  /sys/bus/event_sources/devices/<pmu>/format/*
+
+	- a symbolically formed event like 'pmu/config=M,config1=N,config2=K/'
+	  where M, N, K are numbers (in decimal, hex, octal format).
+	  Acceptable values for each of 'config', 'config1' and 'config2'
+	  parameters are defined by corresponding entries in
+	  /sys/bus/event_sources/devices/<pmu>/format/*
 
 -i::
 --no-inherit::
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index 71f2844cf97f..7ed22ff1e1ac 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -68,4 +68,17 @@ futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wak
 		 val, opflags);
 }
 
+#ifndef HAVE_PTHREAD_ATTR_SETAFFINITY_NP
+#include <pthread.h>
+static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr,
+					      size_t cpusetsize,
+					      cpu_set_t *cpuset)
+{
+	attr = attr;
+	cpusetsize = cpusetsize;
+	cpuset = cpuset;
+	return 0;
+}
+#endif
+
 #endif /* _FUTEX_H */
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 77d5cae54c6a..50e6b66aea1f 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -236,10 +236,10 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
 		if (errno == ENOENT)
 			return false;
 
-		pr_warning("Problems with %s file, consider removing it from the cache\n", 
+		pr_warning("Problems with %s file, consider removing it from the cache\n",
 			   filename);
 	} else if (memcmp(dso->build_id, build_id, sizeof(dso->build_id))) {
-		pr_warning("Problems with %s file, consider removing it from the cache\n", 
+		pr_warning("Problems with %s file, consider removing it from the cache\n",
 			   filename);
 	}
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 1fd96c13f199..74aada554b12 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -390,6 +390,15 @@ static void perf_evlist__collapse_resort(struct perf_evlist *evlist)
 	}
 }
 
+static struct data__file *fmt_to_data_file(struct perf_hpp_fmt *fmt)
+{
+	struct diff_hpp_fmt *dfmt = container_of(fmt, struct diff_hpp_fmt, fmt);
+	void *ptr = dfmt - dfmt->idx;
+	struct data__file *d = container_of(ptr, struct data__file, fmt);
+
+	return d;
+}
+
 static struct hist_entry*
 get_pair_data(struct hist_entry *he, struct data__file *d)
 {
@@ -407,8 +416,7 @@ get_pair_data(struct hist_entry *he, struct data__file *d)
 static struct hist_entry*
 get_pair_fmt(struct hist_entry *he, struct diff_hpp_fmt *dfmt)
 {
-	void *ptr = dfmt - dfmt->idx;
-	struct data__file *d = container_of(ptr, struct data__file, fmt);
+	struct data__file *d = fmt_to_data_file(&dfmt->fmt);
 
 	return get_pair_data(he, d);
 }
@@ -430,7 +438,7 @@ static void hists__baseline_only(struct hists *hists)
 		next = rb_next(&he->rb_node_in);
 		if (!hist_entry__next_pair(he)) {
 			rb_erase(&he->rb_node_in, root);
-			hist_entry__free(he);
+			hist_entry__delete(he);
 		}
 	}
 }
@@ -448,26 +456,30 @@ static void hists__precompute(struct hists *hists)
 	next = rb_first(root);
 	while (next != NULL) {
 		struct hist_entry *he, *pair;
+		struct data__file *d;
+		int i;
 
 		he   = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&he->rb_node_in);
 
-		pair = get_pair_data(he, &data__files[sort_compute]);
-		if (!pair)
-			continue;
+		data__for_each_file_new(i, d) {
+			pair = get_pair_data(he, d);
+			if (!pair)
+				continue;
 
-		switch (compute) {
-		case COMPUTE_DELTA:
-			compute_delta(he, pair);
-			break;
-		case COMPUTE_RATIO:
-			compute_ratio(he, pair);
-			break;
-		case COMPUTE_WEIGHTED_DIFF:
-			compute_wdiff(he, pair);
-			break;
-		default:
-			BUG_ON(1);
+			switch (compute) {
+			case COMPUTE_DELTA:
+				compute_delta(he, pair);
+				break;
+			case COMPUTE_RATIO:
+				compute_ratio(he, pair);
+				break;
+			case COMPUTE_WEIGHTED_DIFF:
+				compute_wdiff(he, pair);
+				break;
+			default:
+				BUG_ON(1);
+			}
 		}
 	}
 }
@@ -517,7 +529,7 @@ __hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
 
 static int64_t
 hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
-			int c)
+			int c, int sort_idx)
 {
 	bool pairs_left  = hist_entry__has_pairs(left);
 	bool pairs_right = hist_entry__has_pairs(right);
@@ -529,8 +541,8 @@ hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
 	if (!pairs_left || !pairs_right)
 		return pairs_left ? -1 : 1;
 
-	p_left  = get_pair_data(left,  &data__files[sort_compute]);
-	p_right = get_pair_data(right, &data__files[sort_compute]);
+	p_left  = get_pair_data(left,  &data__files[sort_idx]);
+	p_right = get_pair_data(right, &data__files[sort_idx]);
 
 	if (!p_left && !p_right)
 		return 0;
@@ -546,90 +558,102 @@ hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
 }
 
 static int64_t
-hist_entry__cmp_nop(struct hist_entry *left __maybe_unused,
+hist_entry__cmp_compute_idx(struct hist_entry *left, struct hist_entry *right,
+			    int c, int sort_idx)
+{
+	struct hist_entry *p_right, *p_left;
+
+	p_left  = get_pair_data(left,  &data__files[sort_idx]);
+	p_right = get_pair_data(right, &data__files[sort_idx]);
+
+	if (!p_left && !p_right)
+		return 0;
+
+	if (!p_left || !p_right)
+		return p_left ? -1 : 1;
+
+	if (c != COMPUTE_DELTA) {
+		/*
+		 * The delta can be computed without the baseline, but
+		 * others are not.  Put those entries which have no
+		 * values below.
+		 */
+		if (left->dummy && right->dummy)
+			return 0;
+
+		if (left->dummy || right->dummy)
+			return left->dummy ? 1 : -1;
+	}
+
+	return __hist_entry__cmp_compute(p_left, p_right, c);
+}
+
+static int64_t
+hist_entry__cmp_nop(struct perf_hpp_fmt *fmt __maybe_unused,
+		    struct hist_entry *left __maybe_unused,
 		    struct hist_entry *right __maybe_unused)
 {
 	return 0;
 }
 
 static int64_t
-hist_entry__cmp_baseline(struct hist_entry *left, struct hist_entry *right)
+hist_entry__cmp_baseline(struct perf_hpp_fmt *fmt __maybe_unused,
+			 struct hist_entry *left, struct hist_entry *right)
 {
-	if (sort_compute)
-		return 0;
-
 	if (left->stat.period == right->stat.period)
 		return 0;
 	return left->stat.period > right->stat.period ? 1 : -1;
 }
 
 static int64_t
-hist_entry__cmp_delta(struct hist_entry *left, struct hist_entry *right)
+hist_entry__cmp_delta(struct perf_hpp_fmt *fmt,
+		      struct hist_entry *left, struct hist_entry *right)
 {
-	return hist_entry__cmp_compute(right, left, COMPUTE_DELTA);
+	struct data__file *d = fmt_to_data_file(fmt);
+
+	return hist_entry__cmp_compute(right, left, COMPUTE_DELTA, d->idx);
 }
 
 static int64_t
-hist_entry__cmp_ratio(struct hist_entry *left, struct hist_entry *right)
+hist_entry__cmp_ratio(struct perf_hpp_fmt *fmt,
+		      struct hist_entry *left, struct hist_entry *right)
 {
-	return hist_entry__cmp_compute(right, left, COMPUTE_RATIO);
+	struct data__file *d = fmt_to_data_file(fmt);
+
+	return hist_entry__cmp_compute(right, left, COMPUTE_RATIO, d->idx);
 }
 
 static int64_t
-hist_entry__cmp_wdiff(struct hist_entry *left, struct hist_entry *right)
+hist_entry__cmp_wdiff(struct perf_hpp_fmt *fmt,
+		      struct hist_entry *left, struct hist_entry *right)
 {
-	return hist_entry__cmp_compute(right, left, COMPUTE_WEIGHTED_DIFF);
+	struct data__file *d = fmt_to_data_file(fmt);
+
+	return hist_entry__cmp_compute(right, left, COMPUTE_WEIGHTED_DIFF, d->idx);
 }
 
-static void insert_hist_entry_by_compute(struct rb_root *root,
-					 struct hist_entry *he,
-					 int c)
+static int64_t
+hist_entry__cmp_delta_idx(struct perf_hpp_fmt *fmt __maybe_unused,
+			  struct hist_entry *left, struct hist_entry *right)
 {
-	struct rb_node **p = &root->rb_node;
-	struct rb_node *parent = NULL;
-	struct hist_entry *iter;
-
-	while (*p != NULL) {
-		parent = *p;
-		iter = rb_entry(parent, struct hist_entry, rb_node);
-		if (hist_entry__cmp_compute(he, iter, c) < 0)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
-
-	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, root);
+	return hist_entry__cmp_compute_idx(right, left, COMPUTE_DELTA,
+					   sort_compute);
 }
 
-static void hists__compute_resort(struct hists *hists)
+static int64_t
+hist_entry__cmp_ratio_idx(struct perf_hpp_fmt *fmt __maybe_unused,
+			  struct hist_entry *left, struct hist_entry *right)
 {
-	struct rb_root *root;
-	struct rb_node *next;
-
-	if (sort__need_collapse)
-		root = &hists->entries_collapsed;
-	else
-		root = hists->entries_in;
-
-	hists->entries = RB_ROOT;
-	next = rb_first(root);
-
-	hists__reset_stats(hists);
-	hists__reset_col_len(hists);
-
-	while (next != NULL) {
-		struct hist_entry *he;
-
-		he = rb_entry(next, struct hist_entry, rb_node_in);
-		next = rb_next(&he->rb_node_in);
-
-		insert_hist_entry_by_compute(&hists->entries, he, compute);
-		hists__inc_stats(hists, he);
+	return hist_entry__cmp_compute_idx(right, left, COMPUTE_RATIO,
+					   sort_compute);
+}
 
-		if (!he->filtered)
-			hists__calc_col_len(hists, he);
-	}
+static int64_t
+hist_entry__cmp_wdiff_idx(struct perf_hpp_fmt *fmt __maybe_unused,
+			  struct hist_entry *left, struct hist_entry *right)
+{
+	return hist_entry__cmp_compute_idx(right, left, COMPUTE_WEIGHTED_DIFF,
+					   sort_compute);
 }
 
 static void hists__process(struct hists *hists)
@@ -637,12 +661,8 @@ static void hists__process(struct hists *hists)
 	if (show_baseline_only)
 		hists__baseline_only(hists);
 
-	if (sort_compute) {
-		hists__precompute(hists);
-		hists__compute_resort(hists);
-	} else {
-		hists__output_resort(hists, NULL);
-	}
+	hists__precompute(hists);
+	hists__output_resort(hists, NULL);
 
 	hists__fprintf(hists, true, 0, 0, 0, stdout);
 }
@@ -841,7 +861,7 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
 	char pfmt[20] = " ";
 
 	if (!pair)
-		goto dummy_print;
+		goto no_print;
 
 	switch (comparison_method) {
 	case COMPUTE_DELTA:
@@ -850,8 +870,6 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
 		else
 			diff = compute_delta(he, pair);
 
-		if (fabs(diff) < 0.01)
-			goto dummy_print;
 		scnprintf(pfmt, 20, "%%%+d.2f%%%%", dfmt->header_width - 1);
 		return percent_color_snprintf(hpp->buf, hpp->size,
 					pfmt, diff);
@@ -883,6 +901,9 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
 	}
 dummy_print:
 	return scnprintf(hpp->buf, hpp->size, "%*s",
+			dfmt->header_width, "N/A");
+no_print:
+	return scnprintf(hpp->buf, hpp->size, "%*s",
 			dfmt->header_width, pfmt);
 }
 
@@ -932,14 +953,15 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair,
 		else
 			diff = compute_delta(he, pair);
 
-		if (fabs(diff) >= 0.01)
-			scnprintf(buf, size, "%+4.2F%%", diff);
+		scnprintf(buf, size, "%+4.2F%%", diff);
 		break;
 
 	case PERF_HPP_DIFF__RATIO:
 		/* No point for ratio number if we are dummy.. */
-		if (he->dummy)
+		if (he->dummy) {
+			scnprintf(buf, size, "N/A");
 			break;
+		}
 
 		if (pair->diff.computed)
 			ratio = pair->diff.period_ratio;
@@ -952,8 +974,10 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair,
 
 	case PERF_HPP_DIFF__WEIGHTED_DIFF:
 		/* No point for wdiff number if we are dummy.. */
-		if (he->dummy)
+		if (he->dummy) {
+			scnprintf(buf, size, "N/A");
 			break;
+		}
 
 		if (pair->diff.computed)
 			wdiff = pair->diff.wdiff;
@@ -1105,9 +1129,10 @@ static void data__hpp_register(struct data__file *d, int idx)
 	perf_hpp__register_sort_field(fmt);
 }
 
-static void ui_init(void)
+static int ui_init(void)
 {
 	struct data__file *d;
+	struct perf_hpp_fmt *fmt;
 	int i;
 
 	data__for_each_file(i, d) {
@@ -1137,6 +1162,46 @@ static void ui_init(void)
 			data__hpp_register(d, i ? PERF_HPP_DIFF__PERIOD :
 						  PERF_HPP_DIFF__PERIOD_BASELINE);
 	}
+
+	if (!sort_compute)
+		return 0;
+
+	/*
+	 * Prepend an fmt to sort on columns at 'sort_compute' first.
+	 * This fmt is added only to the sort list but not to the
+	 * output fields list.
+	 *
+	 * Note that this column (data) can be compared twice - one
+	 * for this 'sort_compute' fmt and another for the normal
+	 * diff_hpp_fmt.  But it shouldn't a problem as most entries
+	 * will be sorted out by first try or baseline and comparing
+	 * is not a costly operation.
+	 */
+	fmt = zalloc(sizeof(*fmt));
+	if (fmt == NULL) {
+		pr_err("Memory allocation failed\n");
+		return -1;
+	}
+
+	fmt->cmp      = hist_entry__cmp_nop;
+	fmt->collapse = hist_entry__cmp_nop;
+
+	switch (compute) {
+	case COMPUTE_DELTA:
+		fmt->sort = hist_entry__cmp_delta_idx;
+		break;
+	case COMPUTE_RATIO:
+		fmt->sort = hist_entry__cmp_ratio_idx;
+		break;
+	case COMPUTE_WEIGHTED_DIFF:
+		fmt->sort = hist_entry__cmp_wdiff_idx;
+		break;
+	default:
+		BUG_ON(1);
+	}
+
+	list_add(&fmt->sort_list, &perf_hpp__sort_list);
+	return 0;
 }
 
 static int data_init(int argc, const char **argv)
@@ -1202,7 +1267,8 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (data_init(argc, argv) < 0)
 		return -1;
 
-	ui_init();
+	if (ui_init() < 0)
+		return -1;
 
 	sort__mode = SORT_MODE__DIFF;
 
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 84df2deed988..a13641e066f5 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -343,6 +343,7 @@ static int __cmd_inject(struct perf_inject *inject)
 	int ret = -EINVAL;
 	struct perf_session *session = inject->session;
 	struct perf_data_file *file_out = &inject->output;
+	int fd = perf_data_file__fd(file_out);
 
 	signal(SIGINT, sig_handler);
 
@@ -376,7 +377,7 @@ static int __cmd_inject(struct perf_inject *inject)
 	}
 
 	if (!file_out->is_pipe)
-		lseek(file_out->fd, session->header.data_offset, SEEK_SET);
+		lseek(fd, session->header.data_offset, SEEK_SET);
 
 	ret = perf_session__process_events(session, &inject->tool);
 
@@ -385,7 +386,7 @@ static int __cmd_inject(struct perf_inject *inject)
 			perf_header__set_feat(&session->header,
 					      HEADER_BUILD_ID);
 		session->header.data_size = inject->bytes_written;
-		perf_session__write_header(session, session->evlist, file_out->fd, true);
+		perf_session__write_header(session, session->evlist, fd, true);
 	}
 
 	return ret;
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 24db6ffe2957..9b5663950a4d 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -7,44 +7,47 @@
 #include "util/session.h"
 #include "util/data.h"
 
-#define MEM_OPERATION_LOAD	"load"
-#define MEM_OPERATION_STORE	"store"
-
-static const char	*mem_operation		= MEM_OPERATION_LOAD;
+#define MEM_OPERATION_LOAD	0x1
+#define MEM_OPERATION_STORE	0x2
 
 struct perf_mem {
 	struct perf_tool	tool;
 	char const		*input_name;
 	bool			hide_unresolved;
 	bool			dump_raw;
+	int			operation;
 	const char		*cpu_list;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
-static int __cmd_record(int argc, const char **argv)
+static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 {
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
-	char event[64];
 	int ret;
 
-	rec_argc = argc + 4;
+	rec_argc = argc + 7; /* max number of arguments */
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 	if (!rec_argv)
 		return -1;
 
-	rec_argv[i++] = strdup("record");
-	if (!strcmp(mem_operation, MEM_OPERATION_LOAD))
-		rec_argv[i++] = strdup("-W");
-	rec_argv[i++] = strdup("-d");
-	rec_argv[i++] = strdup("-e");
+	rec_argv[i++] = "record";
 
-	if (strcmp(mem_operation, MEM_OPERATION_LOAD))
-		sprintf(event, "cpu/mem-stores/pp");
-	else
-		sprintf(event, "cpu/mem-loads/pp");
+	if (mem->operation & MEM_OPERATION_LOAD)
+		rec_argv[i++] = "-W";
+
+	rec_argv[i++] = "-d";
+
+	if (mem->operation & MEM_OPERATION_LOAD) {
+		rec_argv[i++] = "-e";
+		rec_argv[i++] = "cpu/mem-loads/pp";
+	}
+
+	if (mem->operation & MEM_OPERATION_STORE) {
+		rec_argv[i++] = "-e";
+		rec_argv[i++] = "cpu/mem-stores/pp";
+	}
 
-	rec_argv[i++] = strdup(event);
 	for (j = 1; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
 
@@ -162,17 +165,17 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
 	if (!rep_argv)
 		return -1;
 
-	rep_argv[i++] = strdup("report");
-	rep_argv[i++] = strdup("--mem-mode");
-	rep_argv[i++] = strdup("-n"); /* display number of samples */
+	rep_argv[i++] = "report";
+	rep_argv[i++] = "--mem-mode";
+	rep_argv[i++] = "-n"; /* display number of samples */
 
 	/*
 	 * there is no weight (cost) associated with stores, so don't print
 	 * the column
 	 */
-	if (strcmp(mem_operation, MEM_OPERATION_LOAD))
-		rep_argv[i++] = strdup("--sort=mem,sym,dso,symbol_daddr,"
-				       "dso_daddr,tlb,locked");
+	if (!(mem->operation & MEM_OPERATION_LOAD))
+		rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
+				"dso_daddr,tlb,locked";
 
 	for (j = 1; j < argc; j++, i++)
 		rep_argv[i] = argv[j];
@@ -182,6 +185,75 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
 	return ret;
 }
 
+struct mem_mode {
+	const char *name;
+	int mode;
+};
+
+#define MEM_OPT(n, m) \
+	{ .name = n, .mode = (m) }
+
+#define MEM_END { .name = NULL }
+
+static const struct mem_mode mem_modes[]={
+	MEM_OPT("load", MEM_OPERATION_LOAD),
+	MEM_OPT("store", MEM_OPERATION_STORE),
+	MEM_END
+};
+
+static int
+parse_mem_ops(const struct option *opt, const char *str, int unset)
+{
+	int *mode = (int *)opt->value;
+	const struct mem_mode *m;
+	char *s, *os = NULL, *p;
+	int ret = -1;
+
+	if (unset)
+		return 0;
+
+	/* str may be NULL in case no arg is passed to -t */
+	if (str) {
+		/* because str is read-only */
+		s = os = strdup(str);
+		if (!s)
+			return -1;
+
+		/* reset mode */
+		*mode = 0;
+
+		for (;;) {
+			p = strchr(s, ',');
+			if (p)
+				*p = '\0';
+
+			for (m = mem_modes; m->name; m++) {
+				if (!strcasecmp(s, m->name))
+					break;
+			}
+			if (!m->name) {
+				fprintf(stderr, "unknown sampling op %s,"
+					    " check man page\n", s);
+				goto error;
+			}
+
+			*mode |= m->mode;
+
+			if (!p)
+				break;
+
+			s = p + 1;
+		}
+	}
+	ret = 0;
+
+	if (*mode == 0)
+		*mode = MEM_OPERATION_LOAD;
+error:
+	free(os);
+	return ret;
+}
+
 int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	struct stat st;
@@ -197,10 +269,15 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 			.ordered_events	= true,
 		},
 		.input_name		 = "perf.data",
+		/*
+		 * default to both load an store sampling
+		 */
+		.operation		 = MEM_OPERATION_LOAD | MEM_OPERATION_STORE,
 	};
 	const struct option mem_options[] = {
-	OPT_STRING('t', "type", &mem_operation,
-		   "type", "memory operations(load/store)"),
+	OPT_CALLBACK('t', "type", &mem.operation,
+		   "type", "memory operations(load,store) Default load,store",
+		    parse_mem_ops),
 	OPT_BOOLEAN('D', "dump-raw-samples", &mem.dump_raw,
 		    "dump raw samples in ASCII"),
 	OPT_BOOLEAN('U', "hide-unresolved", &mem.hide_unresolved,
@@ -225,7 +302,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 	argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
 					mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
 
-	if (!argc || !(strncmp(argv[0], "rec", 3) || mem_operation))
+	if (!argc || !(strncmp(argv[0], "rec", 3) || mem.operation))
 		usage_with_options(mem_usage, mem_options);
 
 	if (!mem.input_name || !strlen(mem.input_name)) {
@@ -236,7 +313,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 	}
 
 	if (!strncmp(argv[0], "rec", 3))
-		return __cmd_record(argc, argv);
+		return __cmd_record(argc, argv, &mem);
 	else if (!strncmp(argv[0], "rep", 3))
 		return report_events(argc, argv, &mem);
 	else
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 8648c6d3003d..404ab3434052 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -190,16 +190,30 @@ out:
 	return rc;
 }
 
+static int process_sample_event(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
+{
+	struct record *rec = container_of(tool, struct record, tool);
+
+	rec->samples++;
+
+	return build_id__mark_dso_hit(tool, event, sample, evsel, machine);
+}
+
 static int process_buildids(struct record *rec)
 {
 	struct perf_data_file *file  = &rec->file;
 	struct perf_session *session = rec->session;
-	u64 start = session->header.data_offset;
 
-	u64 size = lseek(file->fd, 0, SEEK_CUR);
+	u64 size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
 	if (size == 0)
 		return 0;
 
+	file->size = size;
+
 	/*
 	 * During this process, it'll load kernel map and replace the
 	 * dso->long_name to a real pathname it found.  In this case
@@ -211,9 +225,7 @@ static int process_buildids(struct record *rec)
 	 */
 	symbol_conf.ignore_vmlinux_buildid = true;
 
-	return __perf_session__process_events(session, start,
-					      size - start,
-					      size, &build_id__mark_dso_hit_ops);
+	return perf_session__process_events(session, &rec->tool);
 }
 
 static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
@@ -322,6 +334,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	struct perf_data_file *file = &rec->file;
 	struct perf_session *session;
 	bool disabled = false, draining = false;
+	int fd;
 
 	rec->progname = argv[0];
 
@@ -336,6 +349,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		return -1;
 	}
 
+	fd = perf_data_file__fd(file);
 	rec->session = session;
 
 	record__init_features(rec);
@@ -360,12 +374,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
 
 	if (file->is_pipe) {
-		err = perf_header__write_pipe(file->fd);
+		err = perf_header__write_pipe(fd);
 		if (err < 0)
 			goto out_child;
 	} else {
-		err = perf_session__write_header(session, rec->evlist,
-						 file->fd, false);
+		err = perf_session__write_header(session, rec->evlist, fd, false);
 		if (err < 0)
 			goto out_child;
 	}
@@ -397,7 +410,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 			 * return this more properly and also
 			 * propagate errors that now are calling die()
 			 */
-			err = perf_event__synthesize_tracing_data(tool, file->fd, rec->evlist,
+			err = perf_event__synthesize_tracing_data(tool,	fd, rec->evlist,
 								  process_synthesized_event);
 			if (err <= 0) {
 				pr_err("Couldn't record tracing data.\n");
@@ -504,19 +517,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		goto out_child;
 	}
 
-	if (!quiet) {
+	if (!quiet)
 		fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
 
-		/*
-		 * Approximate RIP event size: 24 bytes.
-		 */
-		fprintf(stderr,
-			"[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n",
-			(double)rec->bytes_written / 1024.0 / 1024.0,
-			file->path,
-			rec->bytes_written / 24);
-	}
-
 out_child:
 	if (forks) {
 		int exit_status;
@@ -535,13 +538,29 @@ out_child:
 	} else
 		status = err;
 
+	/* this will be recalculated during process_buildids() */
+	rec->samples = 0;
+
 	if (!err && !file->is_pipe) {
 		rec->session->header.data_size += rec->bytes_written;
 
 		if (!rec->no_buildid)
 			process_buildids(rec);
-		perf_session__write_header(rec->session, rec->evlist,
-					   file->fd, true);
+		perf_session__write_header(rec->session, rec->evlist, fd, true);
+	}
+
+	if (!err && !quiet) {
+		char samples[128];
+
+		if (rec->samples)
+			scnprintf(samples, sizeof(samples),
+				  " (%" PRIu64 " samples)", rec->samples);
+		else
+			samples[0] = '\0';
+
+		fprintf(stderr,	"[ perf record: Captured and wrote %.3f MB %s%s ]\n",
+			perf_data_file__size(file) / 1024.0 / 1024.0,
+			file->path, samples);
 	}
 
 out_delete_session:
@@ -720,6 +739,13 @@ static struct record record = {
 			.default_per_cpu = true,
 		},
 	},
+	.tool = {
+		.sample		= process_sample_event,
+		.fork		= perf_event__process_fork,
+		.comm		= perf_event__process_comm,
+		.mmap		= perf_event__process_mmap,
+		.mmap2		= perf_event__process_mmap2,
+	},
 };
 
 #define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: "
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 072ae8ad67fc..2f91094e228b 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -86,17 +86,6 @@ static int report__config(const char *var, const char *value, void *cb)
 	return perf_default_config(var, value, cb);
 }
 
-static void report__inc_stats(struct report *rep, struct hist_entry *he)
-{
-	/*
-	 * The @he is either of a newly created one or an existing one
-	 * merging current sample.  We only want to count a new one so
-	 * checking ->nr_events being 1.
-	 */
-	if (he->stat.nr_events == 1)
-		rep->nr_entries++;
-}
-
 static int hist_iter__report_callback(struct hist_entry_iter *iter,
 				      struct addr_location *al, bool single,
 				      void *arg)
@@ -108,8 +97,6 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter,
 	struct mem_info *mi;
 	struct branch_info *bi;
 
-	report__inc_stats(rep, he);
-
 	if (!ui__has_annotation())
 		return 0;
 
@@ -499,6 +486,9 @@ static int __cmd_report(struct report *rep)
 
 	report__warn_kptr_restrict(rep);
 
+	evlist__for_each(session->evlist, pos)
+		rep->nr_entries += evsel__hists(pos)->nr_entries;
+
 	if (use_browser == 0) {
 		if (verbose > 3)
 			perf_session__fprintf(session, stdout);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 891086376381..e598e4e98170 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1730,7 +1730,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "detailed run - start a lot of events"),
 	OPT_BOOLEAN('S', "sync", &sync_run,
 		    "call sync() before starting a run"),
-	OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, 
+	OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL,
 			   "print large numbers with thousands\' separators",
 			   stat__set_big_num),
 	OPT_STRING('C', "cpu", &target.cpu_list, "cpu",
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 616f0fcb4701..c4c7eac69de4 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -165,7 +165,7 @@ static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip)
 		    err ? "[unknown]" : uts.release, perf_version_string);
 	if (use_browser <= 0)
 		sleep(5);
-	
+
 	map->erange_warned = true;
 }
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index badfabc6a01f..7e935f1083ec 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -929,66 +929,66 @@ static struct syscall_fmt {
 	  .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
 	{ .name     = "clock_gettime",  .errmsg = true, STRARRAY(0, clk_id, clockid), },
 	{ .name	    = "close",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, },
 	{ .name	    = "connect",    .errmsg = true, },
 	{ .name	    = "dup",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "dup2",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "dup3",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "epoll_ctl",  .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), },
 	{ .name	    = "eventfd2",   .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, },
 	{ .name	    = "faccessat",  .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
 	{ .name	    = "fadvise64",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "fallocate",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "fchdir",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "fchmod",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "fchmodat",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
 	{ .name	    = "fchown",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "fchownat",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
 	{ .name	    = "fcntl",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
 			     [1] = SCA_STRARRAY, /* cmd */ },
 	  .arg_parm	 = { [1] = &strarray__fcntl_cmds, /* cmd */ }, },
 	{ .name	    = "fdatasync",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "flock",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
 			     [1] = SCA_FLOCK, /* cmd */ }, },
 	{ .name	    = "fsetxattr",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "fstat",	    .errmsg = true, .alias = "newfstat",
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "fstatat",    .errmsg = true, .alias = "newfstatat",
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
 	{ .name	    = "fstatfs",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "fsync",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "ftruncate", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "futex",	    .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
 	{ .name	    = "futimesat", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
 	{ .name	    = "getdents",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "getdents64", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "getitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
 	{ .name	    = "getrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
 	{ .name	    = "ioctl",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
 #if defined(__i386__) || defined(__x86_64__)
 /*
  * FIXME: Make this available to all arches.
@@ -1002,7 +1002,7 @@ static struct syscall_fmt {
 	{ .name	    = "kill",	    .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
 	{ .name	    = "linkat",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
 	{ .name	    = "lseek",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
 			     [2] = SCA_STRARRAY, /* whence */ },
@@ -1012,9 +1012,9 @@ static struct syscall_fmt {
 	  .arg_scnprintf = { [0] = SCA_HEX,	 /* start */
 			     [2] = SCA_MADV_BHV, /* behavior */ }, },
 	{ .name	    = "mkdirat",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
 	{ .name	    = "mknodat",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
 	{ .name	    = "mlock",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
 	{ .name	    = "mlockall",   .errmsg = true,
@@ -1036,9 +1036,9 @@ static struct syscall_fmt {
 	{ .name	    = "munmap",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
 	{ .name	    = "name_to_handle_at", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
 	{ .name	    = "newfstatat", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
 	{ .name	    = "open",	    .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
 	{ .name	    = "open_by_handle_at", .errmsg = true,
@@ -1052,20 +1052,20 @@ static struct syscall_fmt {
 	{ .name	    = "poll",	    .errmsg = true, .timeout = true, },
 	{ .name	    = "ppoll",	    .errmsg = true, .timeout = true, },
 	{ .name	    = "pread",	    .errmsg = true, .alias = "pread64",
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "preadv",	    .errmsg = true, .alias = "pread",
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "prlimit64",  .errmsg = true, STRARRAY(1, resource, rlimit_resources), },
 	{ .name	    = "pwrite",	    .errmsg = true, .alias = "pwrite64",
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "pwritev",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "read",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "readlinkat", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
 	{ .name	    = "readv",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "recvfrom",   .errmsg = true,
 	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
 	{ .name	    = "recvmmsg",   .errmsg = true,
@@ -1073,7 +1073,7 @@ static struct syscall_fmt {
 	{ .name	    = "recvmsg",    .errmsg = true,
 	  .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
 	{ .name	    = "renameat",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
 	{ .name	    = "rt_sigaction", .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, },
 	{ .name	    = "rt_sigprocmask",  .errmsg = true, STRARRAY(0, how, sighow), },
@@ -1091,7 +1091,7 @@ static struct syscall_fmt {
 	{ .name	    = "setitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
 	{ .name	    = "setrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
 	{ .name	    = "shutdown",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "socket",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
 			     [1] = SCA_SK_TYPE, /* type */ },
@@ -1102,7 +1102,7 @@ static struct syscall_fmt {
 	  .arg_parm	 = { [0] = &strarray__socket_families, /* family */ }, },
 	{ .name	    = "stat",	    .errmsg = true, .alias = "newstat", },
 	{ .name	    = "symlinkat",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
 	{ .name	    = "tgkill",	    .errmsg = true,
 	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
 	{ .name	    = "tkill",	    .errmsg = true,
@@ -1113,9 +1113,9 @@ static struct syscall_fmt {
 	{ .name	    = "utimensat",  .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, },
 	{ .name	    = "write",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 	{ .name	    = "writev",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
 };
 
 static int syscall_fmt__cmp(const void *name, const void *fmtp)
@@ -1191,7 +1191,7 @@ static struct thread_trace *thread__trace(struct thread *thread, FILE *fp)
 
 	if (thread__priv(thread) == NULL)
 		thread__set_priv(thread, thread_trace__new());
-		
+
 	if (thread__priv(thread) == NULL)
 		goto fail;
 
@@ -2056,23 +2056,24 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (trace->trace_syscalls &&
 	    perf_evlist__add_syscall_newtp(evlist, trace__sys_enter,
 					   trace__sys_exit))
-		goto out_error_tp;
+		goto out_error_raw_syscalls;
 
 	if (trace->trace_syscalls)
 		perf_evlist__add_vfs_getname(evlist);
 
 	if ((trace->trace_pgfaults & TRACE_PFMAJ) &&
-	    perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MAJ))
-		goto out_error_tp;
+	    perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MAJ)) {
+		goto out_error_mem;
+	}
 
 	if ((trace->trace_pgfaults & TRACE_PFMIN) &&
 	    perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MIN))
-		goto out_error_tp;
+		goto out_error_mem;
 
 	if (trace->sched &&
-		perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
-				trace__sched_stat_runtime))
-		goto out_error_tp;
+	    perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
+				   trace__sched_stat_runtime))
+		goto out_error_sched_stat_runtime;
 
 	err = perf_evlist__create_maps(evlist, &trace->opts.target);
 	if (err < 0) {
@@ -2202,8 +2203,12 @@ out:
 {
 	char errbuf[BUFSIZ];
 
-out_error_tp:
-	perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf));
+out_error_sched_stat_runtime:
+	debugfs__strerror_open_tp(errno, errbuf, sizeof(errbuf), "sched", "sched_stat_runtime");
+	goto out_error;
+
+out_error_raw_syscalls:
+	debugfs__strerror_open_tp(errno, errbuf, sizeof(errbuf), "raw_syscalls", "sys_(enter|exit)");
 	goto out_error;
 
 out_error_mmap:
@@ -2217,6 +2222,9 @@ out_error:
 	fprintf(trace->output, "%s\n", errbuf);
 	goto out_delete_evlist;
 }
+out_error_mem:
+	fprintf(trace->output, "Not enough memory to run!\n");
+	goto out_delete_evlist;
 }
 
 static int trace__replay(struct trace *trace)
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 648e31ff4021..cc224080b525 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -198,6 +198,7 @@ CORE_FEATURE_TESTS =			\
 	libpython-version		\
 	libslang			\
 	libunwind			\
+	pthread-attr-setaffinity-np	\
 	stackprotector-all		\
 	timerfd				\
 	libdw-dwarf-unwind		\
@@ -226,6 +227,7 @@ VF_FEATURE_TESTS =			\
 	libelf-getphdrnum		\
 	libelf-mmap			\
 	libpython-version		\
+	pthread-attr-setaffinity-np	\
 	stackprotector-all		\
 	timerfd				\
 	libunwind-debug-frame		\
@@ -301,6 +303,10 @@ ifeq ($(feature-sync-compare-and-swap), 1)
   CFLAGS += -DHAVE_SYNC_COMPARE_AND_SWAP_SUPPORT
 endif
 
+ifeq ($(feature-pthread-attr-setaffinity-np), 1)
+  CFLAGS += -DHAVE_PTHREAD_ATTR_SETAFFINITY_NP
+endif
+
 ifndef NO_BIONIC
   $(call feature_check,bionic)
   ifeq ($(feature-bionic), 1)
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 53f19b5dbc37..42ac05aaf8ac 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -25,6 +25,7 @@ FILES=					\
 	test-libslang.bin		\
 	test-libunwind.bin		\
 	test-libunwind-debug-frame.bin	\
+	test-pthread-attr-setaffinity-np.bin	\
 	test-stackprotector-all.bin	\
 	test-timerfd.bin		\
 	test-libdw-dwarf-unwind.bin	\
@@ -47,6 +48,9 @@ test-all.bin:
 test-hello.bin:
 	$(BUILD)
 
+test-pthread-attr-setaffinity-np.bin:
+	$(BUILD) -Werror -lpthread
+
 test-stackprotector-all.bin:
 	$(BUILD) -Werror -fstack-protector-all
 
diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c
index 652e0098eba6..6d4d09323922 100644
--- a/tools/perf/config/feature-checks/test-all.c
+++ b/tools/perf/config/feature-checks/test-all.c
@@ -97,6 +97,10 @@
 # include "test-zlib.c"
 #undef main
 
+#define main main_test_pthread_attr_setaffinity_np
+# include "test-pthread_attr_setaffinity_np.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -121,6 +125,7 @@ int main(int argc, char *argv[])
 	main_test_libdw_dwarf_unwind();
 	main_test_sync_compare_and_swap(argc, argv);
 	main_test_zlib();
+	main_test_pthread_attr_setaffinity_np();
 
 	return 0;
 }
diff --git a/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c b/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c
new file mode 100644
index 000000000000..0a0d3ecb4e8a
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c
@@ -0,0 +1,14 @@
+#include <stdint.h>
+#include <pthread.h>
+
+int main(void)
+{
+	int ret = 0;
+	pthread_attr_t thread_attr;
+
+	pthread_attr_init(&thread_attr);
+	/* don't care abt exact args, just the API itself in libpthread */
+	ret = pthread_attr_setaffinity_np(&thread_attr, 0, NULL);
+
+	return ret;
+}
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
index c9b4b6269b51..1091bd47adfd 100644
--- a/tools/perf/tests/attr.py
+++ b/tools/perf/tests/attr.py
@@ -104,7 +104,6 @@ class Event(dict):
                 continue
             if not self.compare_data(self[t], other[t]):
 		log.warning("expected %s=%s, got %s" % (t, self[t], other[t]))
-                
 
 # Test file description needs to have following sections:
 # [config]
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 8d110dec393e..18619966454c 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -140,7 +140,7 @@ static void del_hist_entries(struct hists *hists)
 		he = rb_entry(node, struct hist_entry, rb_node);
 		rb_erase(node, root_out);
 		rb_erase(&he->rb_node_in, root_in);
-		hist_entry__free(he);
+		hist_entry__delete(he);
 	}
 }
 
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index f5547610da02..b52c9faea224 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -106,7 +106,7 @@ static void del_hist_entries(struct hists *hists)
 		he = rb_entry(node, struct hist_entry, rb_node);
 		rb_erase(node, root_out);
 		rb_erase(&he->rb_node_in, root_in);
-		hist_entry__free(he);
+		hist_entry__delete(he);
 	}
 }
 
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 69a71ff84e01..75709d2b17b4 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -222,7 +222,6 @@ tarpkg:
 	@cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \
 	echo "- $@: $$cmd" && echo $$cmd > $@ && \
 	( eval $$cmd ) >> $@ 2>&1
-	
 
 all: $(run) $(run_O) tarpkg
 	@echo OK
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 7f2f51f93619..1cdab0ce00e2 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1145,6 +1145,49 @@ static int test__pinned_group(struct perf_evlist *evlist)
 	return 0;
 }
 
+static int test__checkevent_breakpoint_len(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type", (HW_BREAKPOINT_R | HW_BREAKPOINT_W) ==
+					 evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_1 ==
+					evsel->attr.bp_len);
+
+	return 0;
+}
+
+static int test__checkevent_breakpoint_len_w(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type", HW_BREAKPOINT_W ==
+					 evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_2 ==
+					evsel->attr.bp_len);
+
+	return 0;
+}
+
+static int
+test__checkevent_breakpoint_len_rw_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	return test__checkevent_breakpoint_rw(evlist);
+}
+
 static int count_tracepoints(void)
 {
 	char events_path[PATH_MAX];
@@ -1420,6 +1463,21 @@ static struct evlist_test test__events[] = {
 		.check = test__pinned_group,
 		.id    = 41,
 	},
+	{
+		.name  = "mem:0/1",
+		.check = test__checkevent_breakpoint_len,
+		.id    = 42,
+	},
+	{
+		.name  = "mem:0/2:w",
+		.check = test__checkevent_breakpoint_len_w,
+		.id    = 43,
+	},
+	{
+		.name  = "mem:0/4:rw:u",
+		.check = test__checkevent_breakpoint_len_rw_modifier,
+		.id    = 44
+	},
 #if defined(__s390x__)
 	{
 		.name  = "kvm-s390:kvm_s390_create_vm",
@@ -1471,7 +1529,7 @@ static int test_event(struct evlist_test *e)
 	} else {
 		ret = e->check(evlist);
 	}
-	
+
 	perf_evlist__delete(evlist);
 
 	return ret;
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 4908c648a597..30c02181e78b 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -110,7 +110,7 @@ static bool samples_same(const struct perf_sample *s1,
 
 	if (type & PERF_SAMPLE_STACK_USER) {
 		COMP(user_stack.size);
-		if (memcmp(s1->user_stack.data, s1->user_stack.data,
+		if (memcmp(s1->user_stack.data, s2->user_stack.data,
 			   s1->user_stack.size)) {
 			pr_debug("Samples differ at 'user_stack'\n");
 			return false;
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 1e0a2fd80115..9d32e3c0cfee 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -517,7 +517,7 @@ static bool annotate_browser__jump(struct annotate_browser *browser)
 	}
 
 	annotate_browser__set_top(browser, dl, idx);
-	
+
 	return true;
 }
 
@@ -867,7 +867,6 @@ static void annotate_browser__mark_jump_targets(struct annotate_browser *browser
 
 		++browser->nr_jumps;
 	}
-		
 }
 
 static inline int width_jumps(int n)
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 482adae3cc44..25d608394d74 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -285,7 +285,8 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 }
 
 #define __HPP_SORT_FN(_type, _field)						\
-static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b)	\
+static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, 	\
+				 struct hist_entry *a, struct hist_entry *b) 	\
 {										\
 	return __hpp__sort(a, b, he_get_##_field);				\
 }
@@ -312,7 +313,8 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 }
 
 #define __HPP_SORT_ACC_FN(_type, _field)					\
-static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b)	\
+static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, 	\
+				 struct hist_entry *a, struct hist_entry *b) 	\
 {										\
 	return __hpp__sort_acc(a, b, he_get_acc_##_field);			\
 }
@@ -331,7 +333,8 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 }
 
 #define __HPP_SORT_RAW_FN(_type, _field)					\
-static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b)	\
+static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, 	\
+				 struct hist_entry *a, struct hist_entry *b) 	\
 {										\
 	return __hpp__sort(a, b, he_get_raw_##_field);				\
 }
@@ -361,7 +364,8 @@ HPP_PERCENT_ACC_FNS(overhead_acc, period)
 HPP_RAW_FNS(samples, nr_events)
 HPP_RAW_FNS(period, period)
 
-static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused,
+static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+			    struct hist_entry *a __maybe_unused,
 			    struct hist_entry *b __maybe_unused)
 {
 	return 0;
diff --git a/tools/perf/ui/progress.h b/tools/perf/ui/progress.h
index f34f89eb607c..717d39d3052b 100644
--- a/tools/perf/ui/progress.h
+++ b/tools/perf/ui/progress.h
@@ -4,12 +4,12 @@
 #include <linux/types.h>
 
 void ui_progress__finish(void);
- 
+
 struct ui_progress {
 	const char *title;
 	u64 curr, next, step, total;
 };
- 
+
 void ui_progress__init(struct ui_progress *p, u64 total, const char *title);
 void ui_progress__update(struct ui_progress *p, u64 adv);
 
diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c
index 1c8b9afd5d6e..88f5143a5981 100644
--- a/tools/perf/ui/tui/helpline.c
+++ b/tools/perf/ui/tui/helpline.c
@@ -9,6 +9,7 @@
 #include "../libslang.h"
 
 char ui_helpline__last_msg[1024];
+bool tui_helpline__set;
 
 static void tui_helpline__pop(void)
 {
@@ -35,6 +36,8 @@ static int tui_helpline__show(const char *format, va_list ap)
 			sizeof(ui_helpline__last_msg) - backlog, format, ap);
 	backlog += ret;
 
+	tui_helpline__set = true;
+
 	if (ui_helpline__last_msg[backlog - 1] == '\n') {
 		ui_helpline__puts(ui_helpline__last_msg);
 		SLsmg_refresh();
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 3c38f25b1695..b77e1d771363 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -17,6 +17,7 @@
 static volatile int ui__need_resize;
 
 extern struct perf_error_ops perf_tui_eops;
+extern bool tui_helpline__set;
 
 extern void hist_browser__init_hpp(void);
 
@@ -159,7 +160,7 @@ out:
 
 void ui__exit(bool wait_for_ok)
 {
-	if (wait_for_ok)
+	if (wait_for_ok && tui_helpline__set)
 		ui__question_window("Fatal Error",
 				    ui_helpline__last_msg,
 				    "Press any key...", 0);
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 01bc4e23a2cf..61bf9128e1f2 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -239,7 +239,7 @@ static int mov__parse(struct ins_operands *ops)
 	*s = '\0';
 	ops->source.raw = strdup(ops->raw);
 	*s = ',';
-	
+
 	if (ops->source.raw == NULL)
 		return -1;
 
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index f4654183d391..55355b3d4f85 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -5,132 +5,6 @@
 
 int perf_use_color_default = -1;
 
-static int parse_color(const char *name, int len)
-{
-	static const char * const color_names[] = {
-		"normal", "black", "red", "green", "yellow",
-		"blue", "magenta", "cyan", "white"
-	};
-	char *end;
-	int i;
-
-	for (i = 0; i < (int)ARRAY_SIZE(color_names); i++) {
-		const char *str = color_names[i];
-		if (!strncasecmp(name, str, len) && !str[len])
-			return i - 1;
-	}
-	i = strtol(name, &end, 10);
-	if (end - name == len && i >= -1 && i <= 255)
-		return i;
-	return -2;
-}
-
-static int parse_attr(const char *name, int len)
-{
-	static const int attr_values[] = { 1, 2, 4, 5, 7 };
-	static const char * const attr_names[] = {
-		"bold", "dim", "ul", "blink", "reverse"
-	};
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(attr_names); i++) {
-		const char *str = attr_names[i];
-		if (!strncasecmp(name, str, len) && !str[len])
-			return attr_values[i];
-	}
-	return -1;
-}
-
-void color_parse(const char *value, const char *var, char *dst)
-{
-	color_parse_mem(value, strlen(value), var, dst);
-}
-
-void color_parse_mem(const char *value, int value_len, const char *var,
-		char *dst)
-{
-	const char *ptr = value;
-	int len = value_len;
-	int attr = -1;
-	int fg = -2;
-	int bg = -2;
-
-	if (!strncasecmp(value, "reset", len)) {
-		strcpy(dst, PERF_COLOR_RESET);
-		return;
-	}
-
-	/* [fg [bg]] [attr] */
-	while (len > 0) {
-		const char *word = ptr;
-		int val, wordlen = 0;
-
-		while (len > 0 && !isspace(word[wordlen])) {
-			wordlen++;
-			len--;
-		}
-
-		ptr = word + wordlen;
-		while (len > 0 && isspace(*ptr)) {
-			ptr++;
-			len--;
-		}
-
-		val = parse_color(word, wordlen);
-		if (val >= -1) {
-			if (fg == -2) {
-				fg = val;
-				continue;
-			}
-			if (bg == -2) {
-				bg = val;
-				continue;
-			}
-			goto bad;
-		}
-		val = parse_attr(word, wordlen);
-		if (val < 0 || attr != -1)
-			goto bad;
-		attr = val;
-	}
-
-	if (attr >= 0 || fg >= 0 || bg >= 0) {
-		int sep = 0;
-
-		*dst++ = '\033';
-		*dst++ = '[';
-		if (attr >= 0) {
-			*dst++ = '0' + attr;
-			sep++;
-		}
-		if (fg >= 0) {
-			if (sep++)
-				*dst++ = ';';
-			if (fg < 8) {
-				*dst++ = '3';
-				*dst++ = '0' + fg;
-			} else {
-				dst += sprintf(dst, "38;5;%d", fg);
-			}
-		}
-		if (bg >= 0) {
-			if (sep++)
-				*dst++ = ';';
-			if (bg < 8) {
-				*dst++ = '4';
-				*dst++ = '0' + bg;
-			} else {
-				dst += sprintf(dst, "48;5;%d", bg);
-			}
-		}
-		*dst++ = 'm';
-	}
-	*dst = 0;
-	return;
-bad:
-	die("bad color value '%.*s' for variable '%s'", value_len, value, var);
-}
-
 int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty)
 {
 	if (value) {
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index 0a594b8a0c26..38146f922c54 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -30,8 +30,6 @@ extern int perf_use_color_default;
 int perf_color_default_config(const char *var, const char *value, void *cb);
 
 int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty);
-void color_parse(const char *value, const char *var, char *dst);
-void color_parse_mem(const char *value, int len, const char *var, char *dst);
 int color_vsnprintf(char *bf, size_t size, const char *color,
 		    const char *fmt, va_list args);
 int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args);
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 45be944d450a..c2f7d3b90966 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -532,12 +532,8 @@ dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 			break;
 
 		cache_offset = offset & DSO__DATA_CACHE_MASK;
-		ret = -EINVAL;
 
-		if (-1 == lseek(dso->data.fd, cache_offset, SEEK_SET))
-			break;
-
-		ret = read(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE);
+		ret = pread(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE, cache_offset);
 		if (ret <= 0)
 			break;
 
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 3782c82c6e44..ced92841ff97 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -139,6 +139,7 @@ struct dso {
 		u32		 status_seen;
 		size_t		 file_size;
 		struct list_head open_entry;
+		u64		 frame_offset;
 	} data;
 
 	union { /* Tool specific area */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 2e507b5025a3..28b8ce86bf12 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1436,33 +1436,6 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
 	return printed + fprintf(fp, "\n");
 }
 
-int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused,
-			     int err, char *buf, size_t size)
-{
-	char sbuf[128];
-
-	switch (err) {
-	case ENOENT:
-		scnprintf(buf, size, "%s",
-			  "Error:\tUnable to find debugfs\n"
-			  "Hint:\tWas your kernel compiled with debugfs support?\n"
-			  "Hint:\tIs the debugfs filesystem mounted?\n"
-			  "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'");
-		break;
-	case EACCES:
-		scnprintf(buf, size,
-			  "Error:\tNo permissions to read %s/tracing/events/raw_syscalls\n"
-			  "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
-			  debugfs_mountpoint, debugfs_mountpoint);
-		break;
-	default:
-		scnprintf(buf, size, "%s", strerror_r(err, sbuf, sizeof(sbuf)));
-		break;
-	}
-
-	return 0;
-}
-
 int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 			       int err, char *buf, size_t size)
 {
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 0ba93f67ab94..c94a9e03ecf1 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -183,7 +183,6 @@ static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist)
 
 size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp);
 
-int perf_evlist__strerror_tp(struct perf_evlist *evlist, int err, char *buf, size_t size);
 int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size);
 int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1e90c8557ede..ea51a90e20a0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -709,6 +709,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (opts->sample_weight)
 		perf_evsel__set_sample_bit(evsel, WEIGHT);
 
+	attr->task  = track;
 	attr->mmap  = track;
 	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
@@ -797,6 +798,9 @@ int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads)
 
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
+	if (ncpus == 0 || nthreads == 0)
+		return 0;
+
 	if (evsel->system_wide)
 		nthreads = 1;
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index b20e40c74468..1f407f7352a7 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2237,6 +2237,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz,
 	 * - unique number to identify actual perf.data files
 	 * - encode endianness of file
 	 */
+	ph->version = PERF_HEADER_VERSION_2;
 
 	/* check magic number with one endianness */
 	if (magic == __perf_magic2)
@@ -2247,7 +2248,6 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz,
 		return -1;
 
 	ph->needs_swap = true;
-	ph->version = PERF_HEADER_VERSION_2;
 
 	return 0;
 }
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 182395546ddc..70b48a65064c 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -241,6 +241,20 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 	return he->stat.period == 0;
 }
 
+static void hists__delete_entry(struct hists *hists, struct hist_entry *he)
+{
+	rb_erase(&he->rb_node, &hists->entries);
+
+	if (sort__need_collapse)
+		rb_erase(&he->rb_node_in, &hists->entries_collapsed);
+
+	--hists->nr_entries;
+	if (!he->filtered)
+		--hists->nr_non_filtered_entries;
+
+	hist_entry__delete(he);
+}
+
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
 {
 	struct rb_node *next = rb_first(&hists->entries);
@@ -258,16 +272,7 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
 		     (zap_kernel && n->level != '.') ||
 		     hists__decay_entry(hists, n)) &&
 		    !n->used) {
-			rb_erase(&n->rb_node, &hists->entries);
-
-			if (sort__need_collapse)
-				rb_erase(&n->rb_node_in, &hists->entries_collapsed);
-
-			--hists->nr_entries;
-			if (!n->filtered)
-				--hists->nr_non_filtered_entries;
-
-			hist_entry__free(n);
+			hists__delete_entry(hists, n);
 		}
 	}
 }
@@ -281,16 +286,7 @@ void hists__delete_entries(struct hists *hists)
 		n = rb_entry(next, struct hist_entry, rb_node);
 		next = rb_next(&n->rb_node);
 
-		rb_erase(&n->rb_node, &hists->entries);
-
-		if (sort__need_collapse)
-			rb_erase(&n->rb_node_in, &hists->entries_collapsed);
-
-		--hists->nr_entries;
-		if (!n->filtered)
-			--hists->nr_non_filtered_entries;
-
-		hist_entry__free(n);
+		hists__delete_entry(hists, n);
 	}
 }
 
@@ -433,6 +429,8 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 	if (!he)
 		return NULL;
 
+	hists->nr_entries++;
+
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, hists->entries_in);
 out:
@@ -915,7 +913,7 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 		if (perf_hpp__should_skip(fmt))
 			continue;
 
-		cmp = fmt->cmp(left, right);
+		cmp = fmt->cmp(fmt, left, right);
 		if (cmp)
 			break;
 	}
@@ -933,7 +931,7 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 		if (perf_hpp__should_skip(fmt))
 			continue;
 
-		cmp = fmt->collapse(left, right);
+		cmp = fmt->collapse(fmt, left, right);
 		if (cmp)
 			break;
 	}
@@ -941,7 +939,7 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 	return cmp;
 }
 
-void hist_entry__free(struct hist_entry *he)
+void hist_entry__delete(struct hist_entry *he)
 {
 	zfree(&he->branch_info);
 	zfree(&he->mem_info);
@@ -981,7 +979,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 						iter->callchain,
 						he->callchain);
 			}
-			hist_entry__free(he);
+			hist_entry__delete(he);
 			return false;
 		}
 
@@ -1063,7 +1061,7 @@ static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
 		if (perf_hpp__should_skip(fmt))
 			continue;
 
-		cmp = fmt->sort(a, b);
+		cmp = fmt->sort(fmt, a, b);
 		if (cmp)
 			break;
 	}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 46bd50344f85..2b690d028907 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -119,7 +119,7 @@ int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
 int hist_entry__transaction_len(void);
 int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size,
 			      struct hists *hists);
-void hist_entry__free(struct hist_entry *);
+void hist_entry__delete(struct hist_entry *he);
 
 void hists__output_resort(struct hists *hists, struct ui_progress *prog);
 void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
@@ -195,9 +195,12 @@ struct perf_hpp_fmt {
 		     struct hist_entry *he);
 	int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		     struct hist_entry *he);
-	int64_t (*cmp)(struct hist_entry *a, struct hist_entry *b);
-	int64_t (*collapse)(struct hist_entry *a, struct hist_entry *b);
-	int64_t (*sort)(struct hist_entry *a, struct hist_entry *b);
+	int64_t (*cmp)(struct perf_hpp_fmt *fmt,
+		       struct hist_entry *a, struct hist_entry *b);
+	int64_t (*collapse)(struct perf_hpp_fmt *fmt,
+			    struct hist_entry *a, struct hist_entry *b);
+	int64_t (*sort)(struct perf_hpp_fmt *fmt,
+			struct hist_entry *a, struct hist_entry *b);
 
 	struct list_head list;
 	struct list_head sort_list;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 77b43fe43d55..7f8ec6ce2823 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -526,7 +526,7 @@ do {					\
 }
 
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
-				void *ptr, char *type)
+				void *ptr, char *type, u64 len)
 {
 	struct perf_event_attr attr;
 
@@ -536,14 +536,15 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
 	if (parse_breakpoint_type(type, &attr))
 		return -EINVAL;
 
-	/*
-	 * We should find a nice way to override the access length
-	 * Provide some defaults for now
-	 */
-	if (attr.bp_type == HW_BREAKPOINT_X)
-		attr.bp_len = sizeof(long);
-	else
-		attr.bp_len = HW_BREAKPOINT_LEN_4;
+	/* Provide some defaults if len is not specified */
+	if (!len) {
+		if (attr.bp_type == HW_BREAKPOINT_X)
+			len = sizeof(long);
+		else
+			len = HW_BREAKPOINT_LEN_4;
+	}
+
+	attr.bp_len = len;
 
 	attr.type = PERF_TYPE_BREAKPOINT;
 	attr.sample_period = 1;
@@ -1121,7 +1122,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 		return;
 
 	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
-		if (subsys_glob != NULL && 
+		if (subsys_glob != NULL &&
 		    !strglobmatch(sys_dirent.d_name, subsys_glob))
 			continue;
 
@@ -1132,7 +1133,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			continue;
 
 		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
-			if (event_glob != NULL && 
+			if (event_glob != NULL &&
 			    !strglobmatch(evt_dirent.d_name, event_glob))
 				continue;
 
@@ -1305,7 +1306,7 @@ static void print_symbol_events(const char *event_glob, unsigned type,
 
 	for (i = 0; i < max; i++, syms++) {
 
-		if (event_glob != NULL && 
+		if (event_glob != NULL &&
 		    !(strglobmatch(syms->symbol, event_glob) ||
 		      (syms->alias && strglobmatch(syms->alias, event_glob))))
 			continue;
@@ -1366,7 +1367,7 @@ void print_events(const char *event_glob, bool name_only)
 		printf("\n");
 
 		printf("  %-50s [%s]\n",
-		       "mem:<addr>[:access]",
+		       "mem:<addr>[/len][:access]",
 			event_type_descriptors[PERF_TYPE_BREAKPOINT]);
 		printf("\n");
 	}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index db2cf78ff0f3..ff6e1fa4111e 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -71,6 +71,7 @@ struct parse_events_term {
 	int type_val;
 	int type_term;
 	struct list_head list;
+	bool used;
 };
 
 struct parse_events_evlist {
@@ -104,7 +105,7 @@ int parse_events_add_numeric(struct list_head *list, int *idx,
 int parse_events_add_cache(struct list_head *list, int *idx,
 			   char *type, char *op_result1, char *op_result2);
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
-				void *ptr, char *type);
+				void *ptr, char *type, u64 len);
 int parse_events_add_pmu(struct list_head *list, int *idx,
 			 char *pmu , struct list_head *head_config);
 enum perf_pmu_event_symbol_type
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 906630bbf8eb..94eacb6c1ef7 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -159,6 +159,7 @@ branch_type		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE
 <mem>{
 {modifier_bp}		{ return str(yyscanner, PE_MODIFIER_BP); }
 :			{ return ':'; }
+"/"			{ return '/'; }
 {num_dec}		{ return value(yyscanner, 10); }
 {num_hex}		{ return value(yyscanner, 16); }
 	/*
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 93c4c9fbc922..72def077dbbf 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -326,6 +326,28 @@ PE_NAME_CACHE_TYPE
 }
 
 event_legacy_mem:
+PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+					     (void *) $2, $6, $4));
+	$$ = list;
+}
+|
+PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+					     (void *) $2, NULL, $4));
+	$$ = list;
+}
+|
 PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
 {
 	struct parse_events_evlist *data = _data;
@@ -333,7 +355,7 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
 
 	ALLOC_LIST(list);
 	ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
-					     (void *) $2, $4));
+					     (void *) $2, $4, 0));
 	$$ = list;
 }
 |
@@ -344,7 +366,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc
 
 	ALLOC_LIST(list);
 	ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
-					     (void *) $2, NULL));
+					     (void *) $2, NULL, 0));
 	$$ = list;
 }
 
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index f62dee7bd924..4a015f77e2b5 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -46,7 +46,7 @@ static int get_value(struct parse_opt_ctx_t *p,
 		return opterror(opt, "is not usable", flags);
 
 	if (opt->flags & PARSE_OPT_EXCLUSIVE) {
-		if (p->excl_opt) {
+		if (p->excl_opt && p->excl_opt != opt) {
 			char msg[128];
 
 			if (((flags & OPT_SHORT) && p->excl_opt->short_name) ||
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 5c9c4947cfb4..48411674da0f 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -551,31 +551,68 @@ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v,
 }
 
 /*
+ * Term is a string term, and might be a param-term. Try to look up it's value
+ * in the remaining terms.
+ * - We have a term like "base-or-format-term=param-term",
+ * - We need to find the value supplied for "param-term" (with param-term named
+ *   in a config string) later on in the term list.
+ */
+static int pmu_resolve_param_term(struct parse_events_term *term,
+				  struct list_head *head_terms,
+				  __u64 *value)
+{
+	struct parse_events_term *t;
+
+	list_for_each_entry(t, head_terms, list) {
+		if (t->type_val == PARSE_EVENTS__TERM_TYPE_NUM) {
+			if (!strcmp(t->config, term->config)) {
+				t->used = true;
+				*value = t->val.num;
+				return 0;
+			}
+		}
+	}
+
+	if (verbose)
+		printf("Required parameter '%s' not specified\n", term->config);
+
+	return -1;
+}
+
+/*
  * Setup one of config[12] attr members based on the
  * user input data - term parameter.
  */
 static int pmu_config_term(struct list_head *formats,
 			   struct perf_event_attr *attr,
 			   struct parse_events_term *term,
+			   struct list_head *head_terms,
 			   bool zero)
 {
 	struct perf_pmu_format *format;
 	__u64 *vp;
+	__u64 val;
+
+	/*
+	 * If this is a parameter we've already used for parameterized-eval,
+	 * skip it in normal eval.
+	 */
+	if (term->used)
+		return 0;
 
 	/*
-	 * Support only for hardcoded and numnerial terms.
 	 * Hardcoded terms should be already in, so nothing
 	 * to be done for them.
 	 */
 	if (parse_events__is_hardcoded_term(term))
 		return 0;
 
-	if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM)
-		return -EINVAL;
-
 	format = pmu_find_format(formats, term->config);
-	if (!format)
+	if (!format) {
+		if (verbose)
+			printf("Invalid event/parameter '%s'\n", term->config);
 		return -EINVAL;
+	}
 
 	switch (format->value) {
 	case PERF_PMU_FORMAT_VALUE_CONFIG:
@@ -592,11 +629,25 @@ static int pmu_config_term(struct list_head *formats,
 	}
 
 	/*
-	 * XXX If we ever decide to go with string values for
-	 * non-hardcoded terms, here's the place to translate
-	 * them into value.
+	 * Either directly use a numeric term, or try to translate string terms
+	 * using event parameters.
 	 */
-	pmu_format_value(format->bits, term->val.num, vp, zero);
+	if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+		val = term->val.num;
+	else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
+		if (strcmp(term->val.str, "?")) {
+			if (verbose)
+				pr_info("Invalid sysfs entry %s=%s\n",
+						term->config, term->val.str);
+			return -EINVAL;
+		}
+
+		if (pmu_resolve_param_term(term, head_terms, &val))
+			return -EINVAL;
+	} else
+		return -EINVAL;
+
+	pmu_format_value(format->bits, val, vp, zero);
 	return 0;
 }
 
@@ -607,9 +658,10 @@ int perf_pmu__config_terms(struct list_head *formats,
 {
 	struct parse_events_term *term;
 
-	list_for_each_entry(term, head_terms, list)
-		if (pmu_config_term(formats, attr, term, zero))
+	list_for_each_entry(term, head_terms, list) {
+		if (pmu_config_term(formats, attr, term, head_terms, zero))
 			return -EINVAL;
+	}
 
 	return 0;
 }
@@ -767,10 +819,36 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to)
 		set_bit(b, bits);
 }
 
+static int sub_non_neg(int a, int b)
+{
+	if (b > a)
+		return 0;
+	return a - b;
+}
+
 static char *format_alias(char *buf, int len, struct perf_pmu *pmu,
 			  struct perf_pmu_alias *alias)
 {
-	snprintf(buf, len, "%s/%s/", pmu->name, alias->name);
+	struct parse_events_term *term;
+	int used = snprintf(buf, len, "%s/%s", pmu->name, alias->name);
+
+	list_for_each_entry(term, &alias->terms, list) {
+		if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
+			used += snprintf(buf + used, sub_non_neg(len, used),
+					",%s=%s", term->config,
+					term->val.str);
+	}
+
+	if (sub_non_neg(len, used) > 0) {
+		buf[used] = '/';
+		used++;
+	}
+	if (sub_non_neg(len, used) > 0) {
+		buf[used] = '\0';
+		used++;
+	} else
+		buf[len - 1] = '\0';
+
 	return buf;
 }
 
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 3dda85ca50c1..d906d0ad5d40 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -768,7 +768,7 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist,
 			Py_DECREF(file);
 			goto free_list;
 		}
-			
+
 		Py_DECREF(file);
 	}
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index d808a328f4dc..0c815a40a6e8 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -89,7 +89,7 @@ static void handler_call_die(const char *handler_name)
 
 /*
  * Insert val into into the dictionary and decrement the reference counter.
- * This is necessary for dictionaries since PyDict_SetItemString() does not 
+ * This is necessary for dictionaries since PyDict_SetItemString() does not
  * steal a reference, as opposed to PyTuple_SetItem().
  */
 static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObject *val)
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 5f0e05a76c05..0baf75f12b7c 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -274,7 +274,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	if (tool->id_index == NULL)
 		tool->id_index = process_id_index_stub;
 }
- 
+
 static void swap_sample_id_all(union perf_event *event, void *data)
 {
 	void *end = (void *) event + event->header.size;
@@ -1251,9 +1251,9 @@ fetch_mmaped_event(struct perf_session *session,
 #define NUM_MMAPS 128
 #endif
 
-int __perf_session__process_events(struct perf_session *session,
-				   u64 data_offset, u64 data_size,
-				   u64 file_size, struct perf_tool *tool)
+static int __perf_session__process_events(struct perf_session *session,
+					  u64 data_offset, u64 data_size,
+					  u64 file_size, struct perf_tool *tool)
 {
 	int fd = perf_data_file__fd(session->file);
 	u64 head, page_offset, file_offset, file_pos, size;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index dc26ebf60fe4..6d663dc76404 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -49,9 +49,6 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 			     union perf_event **event_ptr,
 			     struct perf_sample *sample);
 
-int __perf_session__process_events(struct perf_session *session,
-				   u64 data_offset, u64 data_size, u64 size,
-				   struct perf_tool *tool);
 int perf_session__process_events(struct perf_session *session,
 				 struct perf_tool *tool);
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 9139dda9f9a3..7a39c1ed8d37 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1304,6 +1304,37 @@ static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	return hse->se->se_snprintf(he, hpp->buf, hpp->size, len);
 }
 
+static int64_t __sort__hpp_cmp(struct perf_hpp_fmt *fmt,
+			       struct hist_entry *a, struct hist_entry *b)
+{
+	struct hpp_sort_entry *hse;
+
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);
+	return hse->se->se_cmp(a, b);
+}
+
+static int64_t __sort__hpp_collapse(struct perf_hpp_fmt *fmt,
+				    struct hist_entry *a, struct hist_entry *b)
+{
+	struct hpp_sort_entry *hse;
+	int64_t (*collapse_fn)(struct hist_entry *, struct hist_entry *);
+
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);
+	collapse_fn = hse->se->se_collapse ?: hse->se->se_cmp;
+	return collapse_fn(a, b);
+}
+
+static int64_t __sort__hpp_sort(struct perf_hpp_fmt *fmt,
+				struct hist_entry *a, struct hist_entry *b)
+{
+	struct hpp_sort_entry *hse;
+	int64_t (*sort_fn)(struct hist_entry *, struct hist_entry *);
+
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);
+	sort_fn = hse->se->se_sort ?: hse->se->se_cmp;
+	return sort_fn(a, b);
+}
+
 static struct hpp_sort_entry *
 __sort_dimension__alloc_hpp(struct sort_dimension *sd)
 {
@@ -1322,9 +1353,9 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
 	hse->hpp.entry = __sort__hpp_entry;
 	hse->hpp.color = NULL;
 
-	hse->hpp.cmp = sd->entry->se_cmp;
-	hse->hpp.collapse = sd->entry->se_collapse ? : sd->entry->se_cmp;
-	hse->hpp.sort = sd->entry->se_sort ? : hse->hpp.collapse;
+	hse->hpp.cmp = __sort__hpp_cmp;
+	hse->hpp.collapse = __sort__hpp_collapse;
+	hse->hpp.sort = __sort__hpp_sort;
 
 	INIT_LIST_HEAD(&hse->hpp.list);
 	INIT_LIST_HEAD(&hse->hpp.sort_list);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 06fcd1bf98b6..b24f9d8727a8 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -574,13 +574,16 @@ static int decompress_kmodule(struct dso *dso, const char *name,
 	const char *ext = strrchr(name, '.');
 	char tmpbuf[] = "/tmp/perf-kmod-XXXXXX";
 
-	if ((type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP &&
-	     type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP) ||
-	    type != dso->symtab_type)
+	if (type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP &&
+	    type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP &&
+	    type != DSO_BINARY_TYPE__BUILD_ID_CACHE)
 		return -1;
 
-	if (!ext || !is_supported_compression(ext + 1))
-		return -1;
+	if (!ext || !is_supported_compression(ext + 1)) {
+		ext = strrchr(dso->name, '.');
+		if (!ext || !is_supported_compression(ext + 1))
+			return -1;
+	}
 
 	fd = mkstemp(tmpbuf);
 	if (fd < 0)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index a194702a0a2f..a69066865a55 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -685,7 +685,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta,
 	struct machine *machine = kmaps->machine;
 	struct map *curr_map = map;
 	struct symbol *pos;
-	int count = 0, moved = 0;	
+	int count = 0, moved = 0;
 	struct rb_root *root = &dso->symbols[map->type];
 	struct rb_node *next = rb_first(root);
 	int kernel_range = 0;
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 6edf535f65c2..e3c40a520a25 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -266,14 +266,17 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
 				     u64 *fde_count)
 {
 	int ret = -EINVAL, fd;
-	u64 offset;
+	u64 offset = dso->data.frame_offset;
 
-	fd = dso__data_fd(dso, machine);
-	if (fd < 0)
-		return -EINVAL;
+	if (offset == 0) {
+		fd = dso__data_fd(dso, machine);
+		if (fd < 0)
+			return -EINVAL;
 
-	/* Check the .eh_frame section for unwinding info */
-	offset = elf_section_offset(fd, ".eh_frame_hdr");
+		/* Check the .eh_frame section for unwinding info */
+		offset = elf_section_offset(fd, ".eh_frame_hdr");
+		dso->data.frame_offset = offset;
+	}
 
 	if (offset)
 		ret = unwind_spec_ehframe(dso, machine, offset,
@@ -287,14 +290,20 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
 static int read_unwind_spec_debug_frame(struct dso *dso,
 					struct machine *machine, u64 *offset)
 {
-	int fd = dso__data_fd(dso, machine);
+	int fd;
+	u64 ofs = dso->data.frame_offset;
 
-	if (fd < 0)
-		return -EINVAL;
+	if (ofs == 0) {
+		fd = dso__data_fd(dso, machine);
+		if (fd < 0)
+			return -EINVAL;
 
-	/* Check the .debug_frame section for unwinding info */
-	*offset = elf_section_offset(fd, ".debug_frame");
+		/* Check the .debug_frame section for unwinding info */
+		ofs = elf_section_offset(fd, ".debug_frame");
+		dso->data.frame_offset = ofs;
+	}
 
+	*offset = ofs;
 	if (*offset)
 		return 0;