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

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

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (61 commits)
  tracing: Add __used annotation to event variable
  perf, trace: Fix !x86 build bug
  perf report: Support multiple events on the TUI
  perf annotate: Fix up usage of the build id cache
  x86/mmiotrace: Remove redundant instruction prefix checks
  perf annotate: Add TUI interface
  perf tui: Remove annotate from popup menu after failure
  perf report: Don't start the TUI if -D is used
  perf: Fix getline undeclared
  perf: Optimize perf_tp_event_match()
  perf: Remove more code from the fastpath
  perf: Optimize the !vmalloc backed buffer
  perf: Optimize perf_output_copy()
  perf: Fix wakeup storm for RO mmap()s
  perf-record: Share per-cpu buffers
  perf-record: Remove -M
  perf: Ensure that IOC_OUTPUT isn't used to create multi-writer buffers
  perf, trace: Optimize tracepoints by using per-tracepoint-per-cpu hlist to track events
  perf, trace: Optimize tracepoints by removing IRQ-disable from perf/tracepoint interaction
  perf tui: Allow disabling the TUI on a per command basis in ~/.perfconfig
  ...

arch/sparc/kernel/perf_event.c

@@ -92,6 +92,8 @@ struct cpu_hw_events {
 
 	/* Enabled/disable state.  */
 	int			enabled;
+
+	unsigned int		group_flag;
 };
 DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, };
 
@@ -981,53 +983,6 @@ static int collect_events(struct perf_event *group, int max_count,
 	return n;
 }
 
-static void event_sched_in(struct perf_event *event)
-{
-	event->state = PERF_EVENT_STATE_ACTIVE;
-	event->oncpu = smp_processor_id();
-	event->tstamp_running += event->ctx->time - event->tstamp_stopped;
-	if (is_software_event(event))
-		event->pmu->enable(event);
-}
-
-int hw_perf_group_sched_in(struct perf_event *group_leader,
-			   struct perf_cpu_context *cpuctx,
-			   struct perf_event_context *ctx)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct perf_event *sub;
-	int n0, n;
-
-	if (!sparc_pmu)
-		return 0;
-
-	n0 = cpuc->n_events;
-	n = collect_events(group_leader, perf_max_events - n0,
-			   &cpuc->event[n0], &cpuc->events[n0],
-			   &cpuc->current_idx[n0]);
-	if (n < 0)
-		return -EAGAIN;
-	if (check_excludes(cpuc->event, n0, n))
-		return -EINVAL;
-	if (sparc_check_constraints(cpuc->event, cpuc->events, n + n0))
-		return -EAGAIN;
-	cpuc->n_events = n0 + n;
-	cpuc->n_added += n;
-
-	cpuctx->active_oncpu += n;
-	n = 1;
-	event_sched_in(group_leader);
-	list_for_each_entry(sub, &group_leader->sibling_list, group_entry) {
-		if (sub->state != PERF_EVENT_STATE_OFF) {
-			event_sched_in(sub);
-			n++;
-		}
-	}
-	ctx->nr_active += n;
-
-	return 1;
-}
-
 static int sparc_pmu_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -1045,11 +1000,20 @@ static int sparc_pmu_enable(struct perf_event *event)
 	cpuc->events[n0] = event->hw.event_base;
 	cpuc->current_idx[n0] = PIC_NO_INDEX;
 
+	/*
+	 * If group events scheduling transaction was started,
+	 * skip the schedulability test here, it will be peformed
+	 * at commit time(->commit_txn) as a whole
+	 */
+	if (cpuc->group_flag & PERF_EVENT_TXN_STARTED)
+		goto nocheck;
+
 	if (check_excludes(cpuc->event, n0, 1))
 		goto out;
 	if (sparc_check_constraints(cpuc->event, cpuc->events, n0 + 1))
 		goto out;
 
+nocheck:
 	cpuc->n_events++;
 	cpuc->n_added++;
 
@@ -1129,11 +1093,61 @@ static int __hw_perf_event_init(struct perf_event *event)
 	return 0;
 }
 
+/*
+ * Start group events scheduling transaction
+ * Set the flag to make pmu::enable() not perform the
+ * schedulability test, it will be performed at commit time
+ */
+static void sparc_pmu_start_txn(const struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	cpuhw->group_flag |= PERF_EVENT_TXN_STARTED;
+}
+
+/*
+ * Stop group events scheduling transaction
+ * Clear the flag and pmu::enable() will perform the
+ * schedulability test.
+ */
+static void sparc_pmu_cancel_txn(const struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	cpuhw->group_flag &= ~PERF_EVENT_TXN_STARTED;
+}
+
+/*
+ * Commit group events scheduling transaction
+ * Perform the group schedulability test as a whole
+ * Return 0 if success
+ */
+static int sparc_pmu_commit_txn(const struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int n;
+
+	if (!sparc_pmu)
+		return -EINVAL;
+
+	cpuc = &__get_cpu_var(cpu_hw_events);
+	n = cpuc->n_events;
+	if (check_excludes(cpuc->event, 0, n))
+		return -EINVAL;
+	if (sparc_check_constraints(cpuc->event, cpuc->events, n))
+		return -EAGAIN;
+
+	return 0;
+}
+
 static const struct pmu pmu = {
 	.enable		= sparc_pmu_enable,
 	.disable	= sparc_pmu_disable,
 	.read		= sparc_pmu_read,
 	.unthrottle	= sparc_pmu_unthrottle,
+	.start_txn	= sparc_pmu_start_txn,
+	.cancel_txn	= sparc_pmu_cancel_txn,
+	.commit_txn	= sparc_pmu_commit_txn,
 };
 
 const struct pmu *hw_perf_event_init(struct perf_event *event)

arch/x86/include/asm/perf_event_p4.h

@@ -89,7 +89,8 @@
 	P4_CCCR_ENABLE)
 
 /* HT mask */
-#define P4_CCCR_MASK_HT	(P4_CCCR_MASK | P4_CCCR_THREAD_ANY)
+#define P4_CCCR_MASK_HT				\
+	(P4_CCCR_MASK | P4_CCCR_OVF_PMI_T1 | P4_CCCR_THREAD_ANY)
 
 #define P4_GEN_ESCR_EMASK(class, name, bit)	\
 	class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT)

arch/x86/kernel/cpu/perf_event.c

@@ -1717,7 +1717,11 @@ void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int ski
 	 */
 	regs->bp = rewind_frame_pointer(skip + 1);
 	regs->cs = __KERNEL_CS;
-	local_save_flags(regs->flags);
+	/*
+	 * We abuse bit 3 to pass exact information, see perf_misc_flags
+	 * and the comment with PERF_EFLAGS_EXACT.
+	 */
+	regs->flags = 0;
 }
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)

arch/x86/kernel/cpu/perf_event_p4.c

@@ -465,15 +465,21 @@ static int p4_hw_config(struct perf_event *event)
 	return rc;
 }
 
-static inline void p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
+static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
 {
-	unsigned long dummy;
+	int overflow = 0;
+	u32 low, high;
 
-	rdmsrl(hwc->config_base + hwc->idx, dummy);
-	if (dummy & P4_CCCR_OVF) {
+	rdmsr(hwc->config_base + hwc->idx, low, high);
+
+	/* we need to check high bit for unflagged overflows */
+	if ((low & P4_CCCR_OVF) || !(high & (1 << 31))) {
+		overflow = 1;
 		(void)checking_wrmsrl(hwc->config_base + hwc->idx,
-			((u64)dummy) & ~P4_CCCR_OVF);
+			((u64)low) & ~P4_CCCR_OVF);
 	}
+
+	return overflow;
 }
 
 static inline void p4_pmu_disable_event(struct perf_event *event)
@@ -584,20 +590,14 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 
 		WARN_ON_ONCE(hwc->idx != idx);
 
-		/*
-		 * FIXME: Redundant call, actually not needed
-		 * but just to check if we're screwed
-		 */
-		p4_pmu_clear_cccr_ovf(hwc);
+		/* it might be unflagged overflow */
+		handled = p4_pmu_clear_cccr_ovf(hwc);
 
 		val = x86_perf_event_update(event);
-		if (val & (1ULL << (x86_pmu.cntval_bits - 1)))
+		if (!handled && (val & (1ULL << (x86_pmu.cntval_bits - 1))))
 			continue;
 
-		/*
-		 * event overflow
-		 */
-		handled		= 1;
+		/* event overflow for sure */
 		data.period = event->hw.last_period;
 
 		if (!x86_perf_event_set_period(event))
@@ -670,7 +670,7 @@ static void p4_pmu_swap_config_ts(struct hw_perf_event *hwc, int cpu)
 
 /*
  * ESCR address hashing is tricky, ESCRs are not sequential
- * in memory but all starts from MSR_P4_BSU_ESCR0 (0x03e0) and
+ * in memory but all starts from MSR_P4_BSU_ESCR0 (0x03a0) and
  * the metric between any ESCRs is laid in range [0xa0,0xe1]
  *
  * so we make ~70% filled hashtable
@@ -736,7 +736,8 @@ static int p4_get_escr_idx(unsigned int addr)
 	unsigned int idx = P4_ESCR_MSR_IDX(addr);
 
 	if (unlikely(idx >= P4_ESCR_MSR_TABLE_SIZE	||
-			!p4_escr_table[idx])) {
+			!p4_escr_table[idx]		||
+			p4_escr_table[idx] != addr)) {
 		WARN_ONCE(1, "P4 PMU: Wrong address passed: %x\n", addr);
 		return -1;
 	}
@@ -762,7 +763,7 @@ static int p4_pmu_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign
 {
 	unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	unsigned long escr_mask[BITS_TO_LONGS(P4_ESCR_MSR_TABLE_SIZE)];
-	int cpu = raw_smp_processor_id();
+	int cpu = smp_processor_id();
 	struct hw_perf_event *hwc;
 	struct p4_event_bind *bind;
 	unsigned int i, thread, num;

arch/x86/mm/pf_in.c

@@ -34,7 +34,7 @@
 /* IA32 Manual 3, 2-1 */
 static unsigned char prefix_codes[] = {
 	0xF0, 0xF2, 0xF3, 0x2E, 0x36, 0x3E, 0x26, 0x64,
-	0x65, 0x2E, 0x3E, 0x66, 0x67
+	0x65, 0x66, 0x67
 };
 /* IA32 Manual 3, 3-432*/
 static unsigned int reg_rop[] = {

include/linux/ftrace_event.h

@@ -73,18 +73,25 @@ struct trace_iterator {
 };
 
 
+struct trace_event;
+
 typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
-					      int flags);
-struct trace_event {
-	struct hlist_node	node;
-	struct list_head	list;
-	int			type;
+				      int flags, struct trace_event *event);
+
+struct trace_event_functions {
 	trace_print_func	trace;
 	trace_print_func	raw;
 	trace_print_func	hex;
 	trace_print_func	binary;
 };
 
+struct trace_event {
+	struct hlist_node		node;
+	struct list_head		list;
+	int				type;
+	struct trace_event_functions	*funcs;
+};
+
 extern int register_ftrace_event(struct trace_event *event);
 extern int unregister_ftrace_event(struct trace_event *event);
 
@@ -116,28 +123,70 @@ void tracing_record_cmdline(struct task_struct *tsk);
 
 struct event_filter;
 
+enum trace_reg {
+	TRACE_REG_REGISTER,
+	TRACE_REG_UNREGISTER,
+	TRACE_REG_PERF_REGISTER,
+	TRACE_REG_PERF_UNREGISTER,
+};
+
+struct ftrace_event_call;
+
+struct ftrace_event_class {
+	char			*system;
+	void			*probe;
+#ifdef CONFIG_PERF_EVENTS
+	void			*perf_probe;
+#endif
+	int			(*reg)(struct ftrace_event_call *event,
+				       enum trace_reg type);
+	int			(*define_fields)(struct ftrace_event_call *);
+	struct list_head	*(*get_fields)(struct ftrace_event_call *);
+	struct list_head	fields;
+	int			(*raw_init)(struct ftrace_event_call *);
+};
+
+enum {
+	TRACE_EVENT_FL_ENABLED_BIT,
+	TRACE_EVENT_FL_FILTERED_BIT,
+};
+
+enum {
+	TRACE_EVENT_FL_ENABLED	= (1 << TRACE_EVENT_FL_ENABLED_BIT),
+	TRACE_EVENT_FL_FILTERED	= (1 << TRACE_EVENT_FL_FILTERED_BIT),
+};
+
 struct ftrace_event_call {
 	struct list_head	list;
+	struct ftrace_event_class *class;
 	char			*name;
-	char			*system;
 	struct dentry		*dir;
-	struct trace_event	*event;
-	int			enabled;
-	int			(*regfunc)(struct ftrace_event_call *);
-	void			(*unregfunc)(struct ftrace_event_call *);
-	int			id;
+	struct trace_event	event;
 	const char		*print_fmt;
-	int			(*raw_init)(struct ftrace_event_call *);
-	int			(*define_fields)(struct ftrace_event_call *);
-	struct list_head	fields;
-	int			filter_active;
 	struct event_filter	*filter;
 	void			*mod;
 	void			*data;
 
+	/*
+	 * 32 bit flags:
+	 *   bit 1:		enabled
+	 *   bit 2:		filter_active
+	 *
+	 * Changes to flags must hold the event_mutex.
+	 *
+	 * Note: Reads of flags do not hold the event_mutex since
+	 * they occur in critical sections. But the way flags
+	 * is currently used, these changes do no affect the code
+	 * except that when a change is made, it may have a slight
+	 * delay in propagating the changes to other CPUs due to
+	 * caching and such.
+	 */
+	unsigned int		flags;
+
+#ifdef CONFIG_PERF_EVENTS
 	int			perf_refcount;
-	int			(*perf_event_enable)(struct ftrace_event_call *);
-	void			(*perf_event_disable)(struct ftrace_event_call *);
+	struct hlist_head	*perf_events;
+#endif
 };
 
 #define PERF_MAX_TRACE_SIZE	2048
@@ -194,24 +243,22 @@ struct perf_event;
 
 DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
 
-extern int perf_trace_enable(int event_id);
-extern void perf_trace_disable(int event_id);
+extern int  perf_trace_init(struct perf_event *event);
+extern void perf_trace_destroy(struct perf_event *event);
+extern int  perf_trace_enable(struct perf_event *event);
+extern void perf_trace_disable(struct perf_event *event);
 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, int *rctxp,
-			 unsigned long *irq_flags);
+extern void *perf_trace_buf_prepare(int size, unsigned short type,
+				    struct pt_regs *regs, int *rctxp);
 
 static inline void
 perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
-		       u64 count, unsigned long irq_flags, struct pt_regs *regs)
+		       u64 count, struct pt_regs *regs, void *head)
 {
-	struct trace_entry *entry = raw_data;
-
-	perf_tp_event(entry->type, addr, count, raw_data, size, regs);
+	perf_tp_event(addr, count, raw_data, size, regs, head);
 	perf_swevent_put_recursion_context(rctx);
-	local_irq_restore(irq_flags);
 }
 #endif
 

include/linux/perf_event.h

@@ -485,6 +485,7 @@ struct perf_guest_info_callbacks {
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
 #include <asm/atomic.h>
+#include <asm/local.h>
 
 #define PERF_MAX_STACK_DEPTH		255
 
@@ -587,21 +588,19 @@ struct perf_mmap_data {
 	struct rcu_head			rcu_head;
 #ifdef CONFIG_PERF_USE_VMALLOC
 	struct work_struct		work;
+	int				page_order;	/* allocation order  */
 #endif
-	int				data_order;
 	int				nr_pages;	/* nr of data pages  */
 	int				writable;	/* are we writable   */
 	int				nr_locked;	/* nr pages mlocked  */
 
 	atomic_t			poll;		/* POLL_ for wakeups */
-	atomic_t			events;		/* event_id limit       */
 
-	atomic_long_t			head;		/* write position    */
-	atomic_long_t			done_head;	/* completed head    */
-
-	atomic_t			lock;		/* concurrent writes */
-	atomic_t			wakeup;		/* needs a wakeup    */
-	atomic_t			lost;		/* nr records lost   */
+	local_t				head;		/* write position    */
+	local_t				nest;		/* nested writers    */
+	local_t				events;		/* event limit       */
+	local_t				wakeup;		/* wakeup stamp      */
+	local_t				lost;		/* nr records lost   */
 
 	long				watermark;	/* wakeup watermark  */
 
@@ -728,6 +727,7 @@ struct perf_event {
 	perf_overflow_handler_t		overflow_handler;
 
 #ifdef CONFIG_EVENT_TRACING
+	struct ftrace_event_call	*tp_event;
 	struct event_filter		*filter;
 #endif
 
@@ -803,11 +803,12 @@ struct perf_cpu_context {
 struct perf_output_handle {
 	struct perf_event		*event;
 	struct perf_mmap_data		*data;
-	unsigned long			head;
-	unsigned long			offset;
+	unsigned long			wakeup;
+	unsigned long			size;
+	void				*addr;
+	int				page;
 	int				nmi;
 	int				sample;
-	int				locked;
 };
 
 #ifdef CONFIG_PERF_EVENTS
@@ -993,8 +994,9 @@ static inline bool perf_paranoid_kernel(void)
 }
 
 extern void perf_event_init(void);
-extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
-			  int entry_size, struct pt_regs *regs);
+extern void perf_tp_event(u64 addr, u64 count, void *record,
+			  int entry_size, struct pt_regs *regs,
+			  struct hlist_head *head);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags

include/linux/syscalls.h

@@ -103,22 +103,6 @@ struct perf_event_attr;
 #define __SC_TEST5(t5, a5, ...)	__SC_TEST(t5); __SC_TEST4(__VA_ARGS__)
 #define __SC_TEST6(t6, a6, ...)	__SC_TEST(t6); __SC_TEST5(__VA_ARGS__)
 
-#ifdef CONFIG_PERF_EVENTS
-
-#define TRACE_SYS_ENTER_PERF_INIT(sname)				       \
-	.perf_event_enable = perf_sysenter_enable,			       \
-	.perf_event_disable = perf_sysenter_disable,
-
-#define TRACE_SYS_EXIT_PERF_INIT(sname)					       \
-	.perf_event_enable = perf_sysexit_enable,			       \
-	.perf_event_disable = perf_sysexit_disable,
-#else
-#define TRACE_SYS_ENTER_PERF(sname)
-#define TRACE_SYS_ENTER_PERF_INIT(sname)
-#define TRACE_SYS_EXIT_PERF(sname)
-#define TRACE_SYS_EXIT_PERF_INIT(sname)
-#endif /* CONFIG_PERF_EVENTS */
-
 #ifdef CONFIG_FTRACE_SYSCALLS
 #define __SC_STR_ADECL1(t, a)		#a
 #define __SC_STR_ADECL2(t, a, ...)	#a, __SC_STR_ADECL1(__VA_ARGS__)
@@ -134,54 +118,43 @@ struct perf_event_attr;
 #define __SC_STR_TDECL5(t, a, ...)	#t, __SC_STR_TDECL4(__VA_ARGS__)
 #define __SC_STR_TDECL6(t, a, ...)	#t, __SC_STR_TDECL5(__VA_ARGS__)
 
+extern struct ftrace_event_class event_class_syscall_enter;
+extern struct ftrace_event_class event_class_syscall_exit;
+extern struct trace_event_functions enter_syscall_print_funcs;
+extern struct trace_event_functions exit_syscall_print_funcs;
+
 #define SYSCALL_TRACE_ENTER_EVENT(sname)				\
-	static const struct syscall_metadata __syscall_meta_##sname;	\
+	static struct syscall_metadata __syscall_meta_##sname;		\
 	static struct ftrace_event_call					\
 	__attribute__((__aligned__(4))) event_enter_##sname;		\
-	static struct trace_event enter_syscall_print_##sname = {	\
-		.trace                  = print_syscall_enter,		\
-	};								\
 	static struct ftrace_event_call __used				\
 	  __attribute__((__aligned__(4)))				\
 	  __attribute__((section("_ftrace_events")))			\
 	  event_enter_##sname = {					\
 		.name                   = "sys_enter"#sname,		\
-		.system                 = "syscalls",			\
-		.event                  = &enter_syscall_print_##sname,	\
-		.raw_init		= init_syscall_trace,		\
-		.define_fields		= syscall_enter_define_fields,	\
-		.regfunc		= reg_event_syscall_enter,	\
-		.unregfunc		= unreg_event_syscall_enter,	\
+		.class			= &event_class_syscall_enter,	\
+		.event.funcs            = &enter_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-		TRACE_SYS_ENTER_PERF_INIT(sname)			\
 	}
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
-	static const struct syscall_metadata __syscall_meta_##sname;	\
+	static struct syscall_metadata __syscall_meta_##sname;		\
 	static struct ftrace_event_call					\
 	__attribute__((__aligned__(4))) event_exit_##sname;		\
-	static struct trace_event exit_syscall_print_##sname = {	\
-		.trace                  = print_syscall_exit,		\
-	};								\
 	static struct ftrace_event_call __used				\
 	  __attribute__((__aligned__(4)))				\
 	  __attribute__((section("_ftrace_events")))			\
 	  event_exit_##sname = {					\
 		.name                   = "sys_exit"#sname,		\
-		.system                 = "syscalls",			\
-		.event                  = &exit_syscall_print_##sname,	\
-		.raw_init		= init_syscall_trace,		\
-		.define_fields		= syscall_exit_define_fields,	\
-		.regfunc		= reg_event_syscall_exit,	\
-		.unregfunc		= unreg_event_syscall_exit,	\
+		.class			= &event_class_syscall_exit,	\
+		.event.funcs		= &exit_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-		TRACE_SYS_EXIT_PERF_INIT(sname)			\
 	}
 
 #define SYSCALL_METADATA(sname, nb)				\
 	SYSCALL_TRACE_ENTER_EVENT(sname);			\
 	SYSCALL_TRACE_EXIT_EVENT(sname);			\
-	static const struct syscall_metadata __used		\
+	static struct syscall_metadata __used			\
 	  __attribute__((__aligned__(4)))			\
 	  __attribute__((section("__syscalls_metadata")))	\
 	  __syscall_meta_##sname = {				\
@@ -191,12 +164,14 @@ struct perf_event_attr;
 		.args		= args_##sname,			\
 		.enter_event	= &event_enter_##sname,		\
 		.exit_event	= &event_exit_##sname,		\
+		.enter_fields	= LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \
+		.exit_fields	= LIST_HEAD_INIT(__syscall_meta_##sname.exit_fields), \
 	};
 
 #define SYSCALL_DEFINE0(sname)					\
 	SYSCALL_TRACE_ENTER_EVENT(_##sname);			\
 	SYSCALL_TRACE_EXIT_EVENT(_##sname);			\
-	static const struct syscall_metadata __used		\
+	static struct syscall_metadata __used			\
 	  __attribute__((__aligned__(4)))			\
 	  __attribute__((section("__syscalls_metadata")))	\
 	  __syscall_meta__##sname = {				\
@@ -204,6 +179,8 @@ struct perf_event_attr;
 		.nb_args 	= 0,				\
 		.enter_event	= &event_enter__##sname,	\
 		.exit_event	= &event_exit__##sname,		\
+		.enter_fields	= LIST_HEAD_INIT(__syscall_meta__##sname.enter_fields), \
+		.exit_fields	= LIST_HEAD_INIT(__syscall_meta__##sname.exit_fields), \
 	};							\
 	asmlinkage long sys_##sname(void)
 #else

include/linux/tracepoint.h

@@ -20,12 +20,17 @@
 struct module;
 struct tracepoint;
 
+struct tracepoint_func {
+	void *func;
+	void *data;
+};
+
 struct tracepoint {
 	const char *name;		/* Tracepoint name */
 	int state;			/* State. */
 	void (*regfunc)(void);
 	void (*unregfunc)(void);
-	void **funcs;
+	struct tracepoint_func *funcs;
 } __attribute__((aligned(32)));		/*
 					 * Aligned on 32 bytes because it is
 					 * globally visible and gcc happily
@@ -37,16 +42,19 @@ struct tracepoint {
  * Connect a probe to a tracepoint.
  * Internal API, should not be used directly.
  */
-extern int tracepoint_probe_register(const char *name, void *probe);
+extern int tracepoint_probe_register(const char *name, void *probe, void *data);
 
 /*
  * Disconnect a probe from a tracepoint.
  * Internal API, should not be used directly.
  */
-extern int tracepoint_probe_unregister(const char *name, void *probe);
+extern int
+tracepoint_probe_unregister(const char *name, void *probe, void *data);
 
-extern int tracepoint_probe_register_noupdate(const char *name, void *probe);
-extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe);
+extern int tracepoint_probe_register_noupdate(const char *name, void *probe,
+					      void *data);
+extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe,
+						void *data);
 extern void tracepoint_probe_update_all(void);
 
 struct tracepoint_iter {
@@ -102,17 +110,27 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 /*
  * it_func[0] is never NULL because there is at least one element in the array
  * when the array itself is non NULL.
+ *
+ * Note, the proto and args passed in includes "__data" as the first parameter.
+ * The reason for this is to handle the "void" prototype. If a tracepoint
+ * has a "void" prototype, then it is invalid to declare a function
+ * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just
+ * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto".
  */
 #define __DO_TRACE(tp, proto, args)					\
 	do {								\
-		void **it_func;						\
+		struct tracepoint_func *it_func_ptr;			\
+		void *it_func;						\
+		void *__data;						\
 									\
 		rcu_read_lock_sched_notrace();				\
-		it_func = rcu_dereference_sched((tp)->funcs);		\
-		if (it_func) {						\
+		it_func_ptr = rcu_dereference_sched((tp)->funcs);	\
+		if (it_func_ptr) {					\
 			do {						\
-				((void(*)(proto))(*it_func))(args);	\
-			} while (*(++it_func));				\
+				it_func = (it_func_ptr)->func;		\
+				__data = (it_func_ptr)->data;		\
+				((void(*)(proto))(it_func))(args);	\
+			} while ((++it_func_ptr)->func);		\
 		}							\
 		rcu_read_unlock_sched_notrace();			\
 	} while (0)
@@ -122,24 +140,32 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
  * not add unwanted padding between the beginning of the section and the
  * structure. Force alignment to the same alignment as the section start.
  */
-#define DECLARE_TRACE(name, proto, args)				\
+#define __DECLARE_TRACE(name, proto, args, data_proto, data_args)	\
 	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
 		if (unlikely(__tracepoint_##name.state))		\
 			__DO_TRACE(&__tracepoint_##name,		\
-				TP_PROTO(proto), TP_ARGS(args));	\
+				TP_PROTO(data_proto),			\
+				TP_ARGS(data_args));			\
+	}								\
+	static inline int						\
+	register_trace_##name(void (*probe)(data_proto), void *data)	\
+	{								\
+		return tracepoint_probe_register(#name, (void *)probe,	\
+						 data);			\
 	}								\
-	static inline int register_trace_##name(void (*probe)(proto))	\
+	static inline int						\
+	unregister_trace_##name(void (*probe)(data_proto), void *data)	\
 	{								\
-		return tracepoint_probe_register(#name, (void *)probe);	\
+		return tracepoint_probe_unregister(#name, (void *)probe, \
+						   data);		\
 	}								\
-	static inline int unregister_trace_##name(void (*probe)(proto))	\
+	static inline void						\
+	check_trace_callback_type_##name(void (*cb)(data_proto))	\
 	{								\
-		return tracepoint_probe_unregister(#name, (void *)probe);\
 	}
 
-
 #define DEFINE_TRACE_FN(name, reg, unreg)				\
 	static const char __tpstrtab_##name[]				\
 	__attribute__((section("__tracepoints_strings"))) = #name;	\
@@ -156,18 +182,23 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 	EXPORT_SYMBOL(__tracepoint_##name)
 
 #else /* !CONFIG_TRACEPOINTS */
-#define DECLARE_TRACE(name, proto, args)				\
-	static inline void _do_trace_##name(struct tracepoint *tp, proto) \
-	{ }								\
+#define __DECLARE_TRACE(name, proto, args, data_proto, data_args)	\
 	static inline void trace_##name(proto)				\
 	{ }								\
-	static inline int register_trace_##name(void (*probe)(proto))	\
+	static inline int						\
+	register_trace_##name(void (*probe)(data_proto),		\
+			      void *data)				\
 	{								\
 		return -ENOSYS;						\
 	}								\
-	static inline int unregister_trace_##name(void (*probe)(proto))	\
+	static inline int						\
+	unregister_trace_##name(void (*probe)(data_proto),		\
+				void *data)				\
 	{								\
 		return -ENOSYS;						\
+	}								\
+	static inline void check_trace_callback_type_##name(void (*cb)(data_proto)) \
+	{								\
 	}
 
 #define DEFINE_TRACE_FN(name, reg, unreg)
@@ -176,6 +207,29 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 #define EXPORT_TRACEPOINT_SYMBOL(name)
 
 #endif /* CONFIG_TRACEPOINTS */
+
+/*
+ * The need for the DECLARE_TRACE_NOARGS() is to handle the prototype
+ * (void). "void" is a special value in a function prototype and can
+ * not be combined with other arguments. Since the DECLARE_TRACE()
+ * macro adds a data element at the beginning of the prototype,
+ * we need a way to differentiate "(void *data, proto)" from
+ * "(void *data, void)". The second prototype is invalid.
+ *
+ * DECLARE_TRACE_NOARGS() passes "void" as the tracepoint prototype
+ * and "void *__data" as the callback prototype.
+ *
+ * DECLARE_TRACE() passes "proto" as the tracepoint protoype and
+ * "void *__data, proto" as the callback prototype.
+ */
+#define DECLARE_TRACE_NOARGS(name)					\
+		__DECLARE_TRACE(name, void, , void *__data, __data)
+
+#define DECLARE_TRACE(name, proto, args)				\
+		__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args),	\
+				PARAMS(void *__data, proto),		\
+				PARAMS(__data, args))
+
 #endif /* DECLARE_TRACE */
 
 #ifndef TRACE_EVENT

include/trace/syscall.h

@@ -25,6 +25,8 @@ struct syscall_metadata {
 	int		nb_args;
 	const char	**types;
 	const char	**args;
+	struct list_head enter_fields;
+	struct list_head exit_fields;
 
 	struct ftrace_event_call *enter_event;
 	struct ftrace_event_call *exit_event;
@@ -34,16 +36,16 @@ struct syscall_metadata {
 extern unsigned long arch_syscall_addr(int nr);
 extern int init_syscall_trace(struct ftrace_event_call *call);
 
-extern int syscall_enter_define_fields(struct ftrace_event_call *call);
-extern int syscall_exit_define_fields(struct ftrace_event_call *call);
 extern int reg_event_syscall_enter(struct ftrace_event_call *call);
 extern void unreg_event_syscall_enter(struct ftrace_event_call *call);
 extern int reg_event_syscall_exit(struct ftrace_event_call *call);
 extern void unreg_event_syscall_exit(struct ftrace_event_call *call);
 extern int
 ftrace_format_syscall(struct ftrace_event_call *call, struct trace_seq *s);
-enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags);
-enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags);
+enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags,
+				      struct trace_event *event);
+enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags,
+				     struct trace_event *event);
 #endif
 
 #ifdef CONFIG_PERF_EVENTS

kernel/trace/ftrace.c

@@ -3234,7 +3234,8 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 }
 
 static void
-ftrace_graph_probe_sched_switch(struct task_struct *prev, struct task_struct *next)
+ftrace_graph_probe_sched_switch(void *ignore,
+			struct task_struct *prev, struct task_struct *next)
 {
 	unsigned long long timestamp;
 	int index;
@@ -3288,7 +3289,7 @@ static int start_graph_tracing(void)
 	} while (ret == -EAGAIN);
 
 	if (!ret) {
-		ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch);
+		ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
 		if (ret)
 			pr_info("ftrace_graph: Couldn't activate tracepoint"
 				" probe to kernel_sched_switch\n");
@@ -3364,7 +3365,7 @@ void unregister_ftrace_graph(void)
 	ftrace_graph_entry = ftrace_graph_entry_stub;
 	ftrace_shutdown(FTRACE_STOP_FUNC_RET);
 	unregister_pm_notifier(&ftrace_suspend_notifier);
-	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
+	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
 
  out:
 	mutex_unlock(&ftrace_lock);

kernel/trace/kmemtrace.c

@@ -95,7 +95,8 @@ static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
 	trace_wake_up();
 }
 
-static void kmemtrace_kmalloc(unsigned long call_site,
+static void kmemtrace_kmalloc(void *ignore,
+			      unsigned long call_site,
 			      const void *ptr,
 			      size_t bytes_req,
 			      size_t bytes_alloc,
@@ -105,7 +106,8 @@ static void kmemtrace_kmalloc(unsigned long call_site,
 			bytes_req, bytes_alloc, gfp_flags, -1);
 }
 
-static void kmemtrace_kmem_cache_alloc(unsigned long call_site,
+static void kmemtrace_kmem_cache_alloc(void *ignore,
+				       unsigned long call_site,
 				       const void *ptr,
 				       size_t bytes_req,
 				       size_t bytes_alloc,
@@ -115,7 +117,8 @@ static void kmemtrace_kmem_cache_alloc(unsigned long call_site,
 			bytes_req, bytes_alloc, gfp_flags, -1);
 }
 
-static void kmemtrace_kmalloc_node(unsigned long call_site,
+static void kmemtrace_kmalloc_node(void *ignore,
+				   unsigned long call_site,
 				   const void *ptr,
 				   size_t bytes_req,
 				   size_t bytes_alloc,
@@ -126,7 +129,8 @@ static void kmemtrace_kmalloc_node(unsigned long call_site,
 			bytes_req, bytes_alloc, gfp_flags, node);
 }
 
-static void kmemtrace_kmem_cache_alloc_node(unsigned long call_site,
+static void kmemtrace_kmem_cache_alloc_node(void *ignore,
+					    unsigned long call_site,
 					    const void *ptr,
 					    size_t bytes_req,
 					    size_t bytes_alloc,
@@ -137,12 +141,14 @@ static void kmemtrace_kmem_cache_alloc_node(unsigned long call_site,
 			bytes_req, bytes_alloc, gfp_flags, node);
 }
 
-static void kmemtrace_kfree(unsigned long call_site, const void *ptr)
+static void
+kmemtrace_kfree(void *ignore, unsigned long call_site, const void *ptr)
 {
 	kmemtrace_free(KMEMTRACE_TYPE_KMALLOC, call_site, ptr);
 }
 
-static void kmemtrace_kmem_cache_free(unsigned long call_site, const void *ptr)
+static void kmemtrace_kmem_cache_free(void *ignore,
+				      unsigned long call_site, const void *ptr)
 {
 	kmemtrace_free(KMEMTRACE_TYPE_CACHE, call_site, ptr);
 }
@@ -151,34 +157,34 @@ static int kmemtrace_start_probes(void)
 {
 	int err;
 
-	err = register_trace_kmalloc(kmemtrace_kmalloc);
+	err = register_trace_kmalloc(kmemtrace_kmalloc, NULL);
 	if (err)
 		return err;
-	err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
+	err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL);
 	if (err)
 		return err;
-	err = register_trace_kmalloc_node(kmemtrace_kmalloc_node);
+	err = register_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL);
 	if (err)
 		return err;
-	err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
+	err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL);
 	if (err)
 		return err;
-	err = register_trace_kfree(kmemtrace_kfree);
+	err = register_trace_kfree(kmemtrace_kfree, NULL);
 	if (err)
 		return err;
-	err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+	err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL);
 
 	return err;
 }
 
 static void kmemtrace_stop_probes(void)
 {
-	unregister_trace_kmalloc(kmemtrace_kmalloc);
-	unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
-	unregister_trace_kmalloc_node(kmemtrace_kmalloc_node);
-	unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
-	unregister_trace_kfree(kmemtrace_kfree);
-	unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+	unregister_trace_kmalloc(kmemtrace_kmalloc, NULL);
+	unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL);
+	unregister_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL);
+	unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL);
+	unregister_trace_kfree(kmemtrace_kfree, NULL);
+	unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL);
 }
 
 static int kmem_trace_init(struct trace_array *tr)
@@ -237,7 +243,8 @@ struct kmemtrace_user_event_alloc {
 };
 
 static enum print_line_t
-kmemtrace_print_alloc(struct trace_iterator *iter, int flags)
+kmemtrace_print_alloc(struct trace_iterator *iter, int flags,
+		      struct trace_event *event)
 {
 	struct trace_seq *s = &iter->seq;
 	struct kmemtrace_alloc_entry *entry;
@@ -257,7 +264,8 @@ kmemtrace_print_alloc(struct trace_iterator *iter, int flags)
 }
 
 static enum print_line_t
-kmemtrace_print_free(struct trace_iterator *iter, int flags)
+kmemtrace_print_free(struct trace_iterator *iter, int flags,
+		     struct trace_event *event)
 {
 	struct trace_seq *s = &iter->seq;
 	struct kmemtrace_free_entry *entry;
@@ -275,7 +283,8 @@ kmemtrace_print_free(struct trace_iterator *iter, int flags)
 }
 
 static enum print_line_t
-kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags)
+kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags,
+			   struct trace_event *event)
 {
 	struct trace_seq *s = &iter->seq;
 	struct kmemtrace_alloc_entry *entry;
@@ -309,7 +318,8 @@ kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags)
 }
 
 static enum print_line_t
-kmemtrace_print_free_user(struct trace_iterator *iter, int flags)
+kmemtrace_print_free_user(struct trace_iterator *iter, int flags,
+			  struct trace_event *event)
 {
 	struct trace_seq *s = &iter->seq;
 	struct kmemtrace_free_entry *entry;
@@ -463,18 +473,26 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
 	}
 }
 
-static struct trace_event kmem_trace_alloc = {
-	.type			= TRACE_KMEM_ALLOC,
+static struct trace_event_functions kmem_trace_alloc_funcs = {
 	.trace			= kmemtrace_print_alloc,
 	.binary			= kmemtrace_print_alloc_user,
 };
 
-static struct trace_event kmem_trace_free = {
-	.type			= TRACE_KMEM_FREE,
+static struct trace_event kmem_trace_alloc = {
+	.type			= TRACE_KMEM_ALLOC,
+	.funcs			= &kmem_trace_alloc_funcs,
+};
+
+static struct trace_event_functions kmem_trace_free_funcs = {
 	.trace			= kmemtrace_print_free,
 	.binary			= kmemtrace_print_free_user,
 };
 
+static struct trace_event kmem_trace_free = {
+	.type			= TRACE_KMEM_FREE,
+	.funcs			= &kmem_trace_free_funcs,
+};
+
 static struct tracer kmem_tracer __read_mostly = {
 	.name			= "kmemtrace",
 	.init			= kmem_trace_init,

kernel/trace/trace.c

@@ -1936,7 +1936,7 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
 	}
 
 	if (event)
-		return event->trace(iter, sym_flags);
+		return event->funcs->trace(iter, sym_flags, event);
 
 	if (!trace_seq_printf(s, "Unknown type %d\n", entry->type))
 		goto partial;
@@ -1962,7 +1962,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
 
 	event = ftrace_find_event(entry->type);
 	if (event)
-		return event->raw(iter, 0);
+		return event->funcs->raw(iter, 0, event);
 
 	if (!trace_seq_printf(s, "%d ?\n", entry->type))
 		goto partial;
@@ -1989,7 +1989,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 
 	event = ftrace_find_event(entry->type);
 	if (event) {
-		enum print_line_t ret = event->hex(iter, 0);
+		enum print_line_t ret = event->funcs->hex(iter, 0, event);
 		if (ret != TRACE_TYPE_HANDLED)
 			return ret;
 	}
@@ -2014,7 +2014,8 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
 	}
 
 	event = ftrace_find_event(entry->type);
-	return event ? event->binary(iter, 0) : TRACE_TYPE_HANDLED;
+	return event ? event->funcs->binary(iter, 0, event) :
+		TRACE_TYPE_HANDLED;
 }
 
 int trace_empty(struct trace_iterator *iter)

kernel/trace/trace.h

@@ -405,12 +405,12 @@ void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
 		   int pc);
 #else
-static inline void ftrace_trace_stack(struct trace_array *tr,
+static inline void ftrace_trace_stack(struct ring_buffer *buffer,
 				      unsigned long flags, int skip, int pc)
 {
 }
 
-static inline void ftrace_trace_userstack(struct trace_array *tr,
+static inline void ftrace_trace_userstack(struct ring_buffer *buffer,
 					  unsigned long flags, int pc)
 {
 }
@@ -778,12 +778,15 @@ extern void print_subsystem_event_filter(struct event_subsystem *system,
 					 struct trace_seq *s);
 extern int filter_assign_type(const char *type);
 
+struct list_head *
+trace_get_fields(struct ftrace_event_call *event_call);
+
 static inline int
 filter_check_discard(struct ftrace_event_call *call, void *rec,
 		     struct ring_buffer *buffer,
 		     struct ring_buffer_event *event)
 {
-	if (unlikely(call->filter_active) &&
+	if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
 	    !filter_match_preds(call->filter, rec)) {
 		ring_buffer_discard_commit(buffer, event);
 		return 1;

kernel/trace/trace_branch.c

@@ -143,7 +143,7 @@ static void branch_trace_reset(struct trace_array *tr)
 }
 
 static enum print_line_t trace_branch_print(struct trace_iterator *iter,
-					    int flags)
+					    int flags, struct trace_event *event)
 {
 	struct trace_branch *field;
 
@@ -167,9 +167,13 @@ static void branch_print_header(struct seq_file *s)
 		"    |\n");
 }
 
+static struct trace_event_functions trace_branch_funcs = {
+	.trace		= trace_branch_print,
+};
+
 static struct trace_event trace_branch_event = {
 	.type		= TRACE_BRANCH,
-	.trace		= trace_branch_print,
+	.funcs		= &trace_branch_funcs,
 };
 
 static struct tracer branch_trace __read_mostly =

kernel/trace/trace_event_perf.c

@@ -9,13 +9,9 @@
 #include <linux/kprobes.h>
 #include "trace.h"
 
-DEFINE_PER_CPU(struct pt_regs, perf_trace_regs);
-EXPORT_PER_CPU_SYMBOL_GPL(perf_trace_regs);
-
 EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs);
 
-static char *perf_trace_buf;
-static char *perf_trace_buf_nmi;
+static char *perf_trace_buf[4];
 
 /*
  * Force it to be aligned to unsigned long to avoid misaligned accesses
@@ -27,57 +23,82 @@ typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
 /* Count the events in use (per event id, not per instance) */
 static int	total_ref_count;
 
-static int perf_trace_event_enable(struct ftrace_event_call *event)
+static int perf_trace_event_init(struct ftrace_event_call *tp_event,
+				 struct perf_event *p_event)
 {
-	char *buf;
+	struct hlist_head *list;
 	int ret = -ENOMEM;
+	int cpu;
 
-	if (event->perf_refcount++ > 0)
+	p_event->tp_event = tp_event;
+	if (tp_event->perf_refcount++ > 0)
 		return 0;
 
-	if (!total_ref_count) {
-		buf = (char *)alloc_percpu(perf_trace_t);
-		if (!buf)
-			goto fail_buf;
+	list = alloc_percpu(struct hlist_head);
+	if (!list)
+		goto fail;
+
+	for_each_possible_cpu(cpu)
+		INIT_HLIST_HEAD(per_cpu_ptr(list, cpu));
 
-		rcu_assign_pointer(perf_trace_buf, buf);
+	tp_event->perf_events = list;
 
+	if (!total_ref_count) {
+		char *buf;
+		int i;
+
+		for (i = 0; i < 4; i++) {
 			buf = (char *)alloc_percpu(perf_trace_t);
 			if (!buf)
-			goto fail_buf_nmi;
+				goto fail;
 
-		rcu_assign_pointer(perf_trace_buf_nmi, buf);
+			perf_trace_buf[i] = buf;
 		}
+	}
+
+	if (tp_event->class->reg)
+		ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER);
+	else
+		ret = tracepoint_probe_register(tp_event->name,
+						tp_event->class->perf_probe,
+						tp_event);
+
+	if (ret)
+		goto fail;
 
-	ret = event->perf_event_enable(event);
-	if (!ret) {
 	total_ref_count++;
 	return 0;
-	}
 
-fail_buf_nmi:
+fail:
 	if (!total_ref_count) {
-		free_percpu(perf_trace_buf_nmi);
-		free_percpu(perf_trace_buf);
-		perf_trace_buf_nmi = NULL;
-		perf_trace_buf = NULL;
+		int i;
+
+		for (i = 0; i < 4; i++) {
+			free_percpu(perf_trace_buf[i]);
+			perf_trace_buf[i] = NULL;
+		}
+	}
+
+	if (!--tp_event->perf_refcount) {
+		free_percpu(tp_event->perf_events);
+		tp_event->perf_events = NULL;
 	}
-fail_buf:
-	event->perf_refcount--;
 
 	return ret;
 }
 
-int perf_trace_enable(int event_id)
+int perf_trace_init(struct perf_event *p_event)
 {
-	struct ftrace_event_call *event;
+	struct ftrace_event_call *tp_event;
+	int event_id = p_event->attr.config;
 	int ret = -EINVAL;
 
 	mutex_lock(&event_mutex);
-	list_for_each_entry(event, &ftrace_events, list) {
-		if (event->id == event_id && event->perf_event_enable &&
-		    try_module_get(event->mod)) {
-			ret = perf_trace_event_enable(event);
+	list_for_each_entry(tp_event, &ftrace_events, list) {
+		if (tp_event->event.type == event_id &&
+		    tp_event->class && tp_event->class->perf_probe &&
+		    try_module_get(tp_event->mod)) {
+			ret = perf_trace_event_init(tp_event, p_event);
 			break;
 		}
 	}
@@ -86,90 +107,78 @@ int perf_trace_enable(int event_id)
 	return ret;
 }
 
-static void perf_trace_event_disable(struct ftrace_event_call *event)
+int perf_trace_enable(struct perf_event *p_event)
 {
-	char *buf, *nmi_buf;
-
-	if (--event->perf_refcount > 0)
-		return;
+	struct ftrace_event_call *tp_event = p_event->tp_event;
+	struct hlist_head *list;
 
-	event->perf_event_disable(event);
-
-	if (!--total_ref_count) {
-		buf = perf_trace_buf;
-		rcu_assign_pointer(perf_trace_buf, NULL);
+	list = tp_event->perf_events;
+	if (WARN_ON_ONCE(!list))
+		return -EINVAL;
 
-		nmi_buf = perf_trace_buf_nmi;
-		rcu_assign_pointer(perf_trace_buf_nmi, NULL);
+	list = per_cpu_ptr(list, smp_processor_id());
+	hlist_add_head_rcu(&p_event->hlist_entry, list);
 
-		/*
-		 * Ensure every events in profiling have finished before
-		 * releasing the buffers
-		 */
-		synchronize_sched();
+	return 0;
+}
 
-		free_percpu(buf);
-		free_percpu(nmi_buf);
-	}
+void perf_trace_disable(struct perf_event *p_event)
+{
+	hlist_del_rcu(&p_event->hlist_entry);
 }
 
-void perf_trace_disable(int event_id)
+void perf_trace_destroy(struct perf_event *p_event)
 {
-	struct ftrace_event_call *event;
+	struct ftrace_event_call *tp_event = p_event->tp_event;
+	int i;
 
-	mutex_lock(&event_mutex);
-	list_for_each_entry(event, &ftrace_events, list) {
-		if (event->id == event_id) {
-			perf_trace_event_disable(event);
-			module_put(event->mod);
-			break;
+	if (--tp_event->perf_refcount > 0)
+		return;
+
+	if (tp_event->class->reg)
+		tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
+	else
+		tracepoint_probe_unregister(tp_event->name,
+					    tp_event->class->perf_probe,
+					    tp_event);
+
+	free_percpu(tp_event->perf_events);
+	tp_event->perf_events = NULL;
+
+	if (!--total_ref_count) {
+		for (i = 0; i < 4; i++) {
+			free_percpu(perf_trace_buf[i]);
+			perf_trace_buf[i] = NULL;
 		}
 	}
-	mutex_unlock(&event_mutex);
 }
 
 __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
-				       int *rctxp, unsigned long *irq_flags)
+				       struct pt_regs *regs, int *rctxp)
 {
 	struct trace_entry *entry;
-	char *trace_buf, *raw_data;
-	int pc, cpu;
+	unsigned long flags;
+	char *raw_data;
+	int pc;
 
 	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
 
 	pc = preempt_count();
 
-	/* Protect the per cpu buffer, begin the rcu read side */
-	local_irq_save(*irq_flags);
-
 	*rctxp = perf_swevent_get_recursion_context();
 	if (*rctxp < 0)
-		goto err_recursion;
-
-	cpu = smp_processor_id();
-
-	if (in_nmi())
-		trace_buf = rcu_dereference_sched(perf_trace_buf_nmi);
-	else
-		trace_buf = rcu_dereference_sched(perf_trace_buf);
-
-	if (!trace_buf)
-		goto err;
+		return NULL;
 
-	raw_data = per_cpu_ptr(trace_buf, cpu);
+	raw_data = per_cpu_ptr(perf_trace_buf[*rctxp], smp_processor_id());
 
 	/* zero the dead bytes from align to not leak stack to user */
 	memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
 
 	entry = (struct trace_entry *)raw_data;
-	tracing_generic_entry_update(entry, *irq_flags, pc);
+	local_save_flags(flags);
+	tracing_generic_entry_update(entry, flags, pc);
 	entry->type = type;
 
 	return raw_data;
-err:
-	perf_swevent_put_recursion_context(*rctxp);
-err_recursion:
-	local_irq_restore(*irq_flags);
-	return NULL;
 }
 EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);

kernel/trace/trace_events_filter.c

@@ -500,8 +500,10 @@ static struct ftrace_event_field *
 find_event_field(struct ftrace_event_call *call, char *name)
 {
 	struct ftrace_event_field *field;
+	struct list_head *head;
 
-	list_for_each_entry(field, &call->fields, link) {
+	head = trace_get_fields(call);
+	list_for_each_entry(field, head, link) {
 		if (!strcmp(field->name, name))
 			return field;
 	}
@@ -545,7 +547,7 @@ static void filter_disable_preds(struct ftrace_event_call *call)
 	struct event_filter *filter = call->filter;
 	int i;
 
-	call->filter_active = 0;
+	call->flags &= ~TRACE_EVENT_FL_FILTERED;
 	filter->n_preds = 0;
 
 	for (i = 0; i < MAX_FILTER_PRED; i++)
@@ -572,7 +574,7 @@ void destroy_preds(struct ftrace_event_call *call)
 {
 	__free_preds(call->filter);
 	call->filter = NULL;
-	call->filter_active = 0;
+	call->flags &= ~TRACE_EVENT_FL_FILTERED;
 }
 
 static struct event_filter *__alloc_preds(void)
@@ -611,7 +613,7 @@ static int init_preds(struct ftrace_event_call *call)
 	if (call->filter)
 		return 0;
 
-	call->filter_active = 0;
+	call->flags &= ~TRACE_EVENT_FL_FILTERED;
 	call->filter = __alloc_preds();
 	if (IS_ERR(call->filter))
 		return PTR_ERR(call->filter);
@@ -625,10 +627,10 @@ static int init_subsystem_preds(struct event_subsystem *system)
 	int err;
 
 	list_for_each_entry(call, &ftrace_events, list) {
-		if (!call->define_fields)
+		if (!call->class || !call->class->define_fields)
 			continue;
 
-		if (strcmp(call->system, system->name) != 0)
+		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
 		err = init_preds(call);
@@ -644,10 +646,10 @@ static void filter_free_subsystem_preds(struct event_subsystem *system)
 	struct ftrace_event_call *call;
 
 	list_for_each_entry(call, &ftrace_events, list) {
-		if (!call->define_fields)
+		if (!call->class || !call->class->define_fields)
 			continue;
 
-		if (strcmp(call->system, system->name) != 0)
+		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
 		filter_disable_preds(call);
@@ -1249,10 +1251,10 @@ static int replace_system_preds(struct event_subsystem *system,
 	list_for_each_entry(call, &ftrace_events, list) {
 		struct event_filter *filter = call->filter;
 
-		if (!call->define_fields)
+		if (!call->class || !call->class->define_fields)
 			continue;
 
-		if (strcmp(call->system, system->name) != 0)
+		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
 		/* try to see if the filter can be applied */
@@ -1266,7 +1268,7 @@ static int replace_system_preds(struct event_subsystem *system,
 		if (err)
 			filter_disable_preds(call);
 		else {
-			call->filter_active = 1;
+			call->flags |= TRACE_EVENT_FL_FILTERED;
 			replace_filter_string(filter, filter_string);
 		}
 		fail = false;
@@ -1315,7 +1317,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 	if (err)
 		append_filter_err(ps, call->filter);
 	else
-		call->filter_active = 1;
+		call->flags |= TRACE_EVENT_FL_FILTERED;
 out:
 	filter_opstack_clear(ps);
 	postfix_clear(ps);
@@ -1393,7 +1395,7 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
 	mutex_lock(&event_mutex);
 
 	list_for_each_entry(call, &ftrace_events, list) {
-		if (call->id == event_id)
+		if (call->event.type == event_id)
 			break;
 	}
 

kernel/trace/trace_export.c

@@ -127,7 +127,7 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 
 static int ftrace_raw_init_event(struct ftrace_event_call *call)
 {
-	INIT_LIST_HEAD(&call->fields);
+	INIT_LIST_HEAD(&call->class->fields);
 	return 0;
 }
 
@@ -153,17 +153,21 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call)
 #define F_printk(fmt, args...) #fmt ", "  __stringify(args)
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(call, struct_name, type, tstruct, print)		\
+#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print)		\
+									\
+struct ftrace_event_class event_class_ftrace_##call = {			\
+	.system			= __stringify(TRACE_SYSTEM),		\
+	.define_fields		= ftrace_define_fields_##call,		\
+	.raw_init		= ftrace_raw_init_event,		\
+};									\
 									\
 struct ftrace_event_call __used						\
 __attribute__((__aligned__(4)))						\
 __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.name			= #call,				\
-	.id			= type,					\
-	.system			= __stringify(TRACE_SYSTEM),		\
-	.raw_init		= ftrace_raw_init_event,		\
+	.event.type		= etype,				\
+	.class			= &event_class_ftrace_##call,		\
 	.print_fmt		= print,				\
-	.define_fields		= ftrace_define_fields_##call,		\
 };									\
 
 #include "trace_entries.h"

kernel/trace/trace_functions_graph.c

@@ -1025,7 +1025,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
 		if (!event)
 			return TRACE_TYPE_UNHANDLED;
 
-		ret = event->trace(iter, sym_flags);
+		ret = event->funcs->trace(iter, sym_flags, event);
 		if (ret != TRACE_TYPE_HANDLED)
 			return ret;
 	}
@@ -1112,7 +1112,8 @@ print_graph_function(struct trace_iterator *iter)
 }
 
 static enum print_line_t
-print_graph_function_event(struct trace_iterator *iter, int flags)
+print_graph_function_event(struct trace_iterator *iter, int flags,
+			   struct trace_event *event)
 {
 	return print_graph_function(iter);
 }
@@ -1225,14 +1226,18 @@ void graph_trace_close(struct trace_iterator *iter)
 	}
 }
 
+static struct trace_event_functions graph_functions = {
+	.trace		= print_graph_function_event,
+};
+
 static struct trace_event graph_trace_entry_event = {
 	.type		= TRACE_GRAPH_ENT,
-	.trace		= print_graph_function_event,
+	.funcs		= &graph_functions,
 };
 
 static struct trace_event graph_trace_ret_event = {
 	.type		= TRACE_GRAPH_RET,
-	.trace		= print_graph_function_event,
+	.funcs		= &graph_functions
 };
 
 static struct tracer graph_trace __read_mostly = {

kernel/trace/trace_kprobe.c

@@ -324,8 +324,8 @@ struct trace_probe {
 	unsigned long 		nhit;
 	unsigned int		flags;	/* For TP_FLAG_* */
 	const char		*symbol;	/* symbol name */
+	struct ftrace_event_class	class;
 	struct ftrace_event_call	call;
-	struct trace_event		event;
 	ssize_t			size;		/* trace entry size */
 	unsigned int		nr_args;
 	struct probe_arg	args[];
@@ -404,6 +404,7 @@ static struct trace_probe *alloc_trace_probe(const char *group,
 		goto error;
 	}
 
+	tp->call.class = &tp->class;
 	tp->call.name = kstrdup(event, GFP_KERNEL);
 	if (!tp->call.name)
 		goto error;
@@ -413,8 +414,8 @@ static struct trace_probe *alloc_trace_probe(const char *group,
 		goto error;
 	}
 
-	tp->call.system = kstrdup(group, GFP_KERNEL);
-	if (!tp->call.system)
+	tp->class.system = kstrdup(group, GFP_KERNEL);
+	if (!tp->class.system)
 		goto error;
 
 	INIT_LIST_HEAD(&tp->list);
@@ -443,7 +444,7 @@ static void free_trace_probe(struct trace_probe *tp)
 	for (i = 0; i < tp->nr_args; i++)
 		free_probe_arg(&tp->args[i]);
 
-	kfree(tp->call.system);
+	kfree(tp->call.class->system);
 	kfree(tp->call.name);
 	kfree(tp->symbol);
 	kfree(tp);
@@ -456,7 +457,7 @@ static struct trace_probe *find_probe_event(const char *event,
 
 	list_for_each_entry(tp, &probe_list, list)
 		if (strcmp(tp->call.name, event) == 0 &&
-		    strcmp(tp->call.system, group) == 0)
+		    strcmp(tp->call.class->system, group) == 0)
 			return tp;
 	return NULL;
 }
@@ -481,7 +482,7 @@ static int register_trace_probe(struct trace_probe *tp)
 	mutex_lock(&probe_lock);
 
 	/* register as an event */
-	old_tp = find_probe_event(tp->call.name, tp->call.system);
+	old_tp = find_probe_event(tp->call.name, tp->call.class->system);
 	if (old_tp) {
 		/* delete old event */
 		unregister_trace_probe(old_tp);
@@ -904,7 +905,7 @@ static int probes_seq_show(struct seq_file *m, void *v)
 	int i;
 
 	seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
-	seq_printf(m, ":%s/%s", tp->call.system, tp->call.name);
+	seq_printf(m, ":%s/%s", tp->call.class->system, tp->call.name);
 
 	if (!tp->symbol)
 		seq_printf(m, " 0x%p", tp->rp.kp.addr);
@@ -1061,8 +1062,8 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
 
 	size = sizeof(*entry) + tp->size;
 
-	event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
-						  irq_flags, pc);
+	event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
+						  size, irq_flags, pc);
 	if (!event)
 		return;
 
@@ -1094,8 +1095,8 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
 
 	size = sizeof(*entry) + tp->size;
 
-	event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
-						  irq_flags, pc);
+	event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
+						  size, irq_flags, pc);
 	if (!event)
 		return;
 
@@ -1112,18 +1113,17 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
 
 /* Event entry printers */
 enum print_line_t
-print_kprobe_event(struct trace_iterator *iter, int flags)
+print_kprobe_event(struct trace_iterator *iter, int flags,
+		   struct trace_event *event)
 {
 	struct kprobe_trace_entry_head *field;
 	struct trace_seq *s = &iter->seq;
-	struct trace_event *event;
 	struct trace_probe *tp;
 	u8 *data;
 	int i;
 
 	field = (struct kprobe_trace_entry_head *)iter->ent;
-	event = ftrace_find_event(field->ent.type);
-	tp = container_of(event, struct trace_probe, event);
+	tp = container_of(event, struct trace_probe, call.event);
 
 	if (!trace_seq_printf(s, "%s: (", tp->call.name))
 		goto partial;
@@ -1149,18 +1149,17 @@ print_kprobe_event(struct trace_iterator *iter, int flags)
 }
 
 enum print_line_t
-print_kretprobe_event(struct trace_iterator *iter, int flags)
+print_kretprobe_event(struct trace_iterator *iter, int flags,
+		      struct trace_event *event)
 {
 	struct kretprobe_trace_entry_head *field;
 	struct trace_seq *s = &iter->seq;
-	struct trace_event *event;
 	struct trace_probe *tp;
 	u8 *data;
 	int i;
 
 	field = (struct kretprobe_trace_entry_head *)iter->ent;
-	event = ftrace_find_event(field->ent.type);
-	tp = container_of(event, struct trace_probe, event);
+	tp = container_of(event, struct trace_probe, call.event);
 
 	if (!trace_seq_printf(s, "%s: (", tp->call.name))
 		goto partial;
@@ -1217,8 +1216,6 @@ static void probe_event_disable(struct ftrace_event_call *call)
 
 static int probe_event_raw_init(struct ftrace_event_call *event_call)
 {
-	INIT_LIST_HEAD(&event_call->fields);
-
 	return 0;
 }
 
@@ -1341,9 +1338,9 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp,
 	struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
 	struct ftrace_event_call *call = &tp->call;
 	struct kprobe_trace_entry_head *entry;
+	struct hlist_head *head;
 	u8 *data;
 	int size, __size, i;
-	unsigned long irq_flags;
 	int rctx;
 
 	__size = sizeof(*entry) + tp->size;
@@ -1353,7 +1350,7 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp,
 		     "profile buffer not large enough"))
 		return;
 
-	entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
+	entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
 	if (!entry)
 		return;
 
@@ -1362,7 +1359,8 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp,
 	for (i = 0; i < tp->nr_args; i++)
 		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
-	perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs);
+	head = per_cpu_ptr(call->perf_events, smp_processor_id());
+	perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head);
 }
 
 /* Kretprobe profile handler */
@@ -1372,9 +1370,9 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
 	struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
 	struct ftrace_event_call *call = &tp->call;
 	struct kretprobe_trace_entry_head *entry;
+	struct hlist_head *head;
 	u8 *data;
 	int size, __size, i;
-	unsigned long irq_flags;
 	int rctx;
 
 	__size = sizeof(*entry) + tp->size;
@@ -1384,7 +1382,7 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
 		     "profile buffer not large enough"))
 		return;
 
-	entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
+	entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
 	if (!entry)
 		return;
 
@@ -1394,8 +1392,8 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
 	for (i = 0; i < tp->nr_args; i++)
 		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
-	perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1,
-			       irq_flags, regs);
+	head = per_cpu_ptr(call->perf_events, smp_processor_id());
+	perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head);
 }
 
 static int probe_perf_enable(struct ftrace_event_call *call)
@@ -1425,6 +1423,26 @@ static void probe_perf_disable(struct ftrace_event_call *call)
 }
 #endif	/* CONFIG_PERF_EVENTS */
 
+static __kprobes
+int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
+{
+	switch (type) {
+	case TRACE_REG_REGISTER:
+		return probe_event_enable(event);
+	case TRACE_REG_UNREGISTER:
+		probe_event_disable(event);
+		return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+	case TRACE_REG_PERF_REGISTER:
+		return probe_perf_enable(event);
+	case TRACE_REG_PERF_UNREGISTER:
+		probe_perf_disable(event);
+		return 0;
+#endif
+	}
+	return 0;
+}
 
 static __kprobes
 int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
@@ -1454,6 +1472,14 @@ int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
 	return 0;	/* We don't tweek kernel, so just return 0 */
 }
 
+static struct trace_event_functions kretprobe_funcs = {
+	.trace		= print_kretprobe_event
+};
+
+static struct trace_event_functions kprobe_funcs = {
+	.trace		= print_kprobe_event
+};
+
 static int register_probe_event(struct trace_probe *tp)
 {
 	struct ftrace_event_call *call = &tp->call;
@@ -1461,36 +1487,31 @@ static int register_probe_event(struct trace_probe *tp)
 
 	/* Initialize ftrace_event_call */
 	if (probe_is_return(tp)) {
-		tp->event.trace = print_kretprobe_event;
-		call->raw_init = probe_event_raw_init;
-		call->define_fields = kretprobe_event_define_fields;
+		INIT_LIST_HEAD(&call->class->fields);
+		call->event.funcs = &kretprobe_funcs;
+		call->class->raw_init = probe_event_raw_init;
+		call->class->define_fields = kretprobe_event_define_fields;
 	} else {
-		tp->event.trace = print_kprobe_event;
-		call->raw_init = probe_event_raw_init;
-		call->define_fields = kprobe_event_define_fields;
+		INIT_LIST_HEAD(&call->class->fields);
+		call->event.funcs = &kprobe_funcs;
+		call->class->raw_init = probe_event_raw_init;
+		call->class->define_fields = kprobe_event_define_fields;
 	}
 	if (set_print_fmt(tp) < 0)
 		return -ENOMEM;
-	call->event = &tp->event;
-	call->id = register_ftrace_event(&tp->event);
-	if (!call->id) {
+	ret = register_ftrace_event(&call->event);
+	if (!ret) {
 		kfree(call->print_fmt);
 		return -ENODEV;
 	}
-	call->enabled = 0;
-	call->regfunc = probe_event_enable;
-	call->unregfunc = probe_event_disable;
-
-#ifdef CONFIG_PERF_EVENTS
-	call->perf_event_enable = probe_perf_enable;
-	call->perf_event_disable = probe_perf_disable;
-#endif
+	call->flags = 0;
+	call->class->reg = kprobe_register;
 	call->data = tp;
 	ret = trace_add_event_call(call);
 	if (ret) {
 		pr_info("Failed to register kprobe event: %s\n", call->name);
 		kfree(call->print_fmt);
-		unregister_ftrace_event(&tp->event);
+		unregister_ftrace_event(&call->event);
 	}
 	return ret;
 }

kernel/trace/trace_output.h

@@ -25,7 +25,7 @@ extern void trace_event_read_unlock(void);
 extern struct trace_event *ftrace_find_event(int type);
 
 extern enum print_line_t trace_nop_print(struct trace_iterator *iter,
-					 int flags);
+					 int flags, struct trace_event *event);
 extern int
 trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry);
 

kernel/trace/trace_sched_switch.c

@@ -50,7 +50,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
 }
 
 static void
-probe_sched_switch(struct task_struct *prev, struct task_struct *next)
+probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *next)
 {
 	struct trace_array_cpu *data;
 	unsigned long flags;
@@ -108,7 +108,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 }
 
 static void
-probe_sched_wakeup(struct task_struct *wakee, int success)
+probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success)
 {
 	struct trace_array_cpu *data;
 	unsigned long flags;
@@ -138,21 +138,21 @@ static int tracing_sched_register(void)
 {
 	int ret;
 
-	ret = register_trace_sched_wakeup(probe_sched_wakeup);
+	ret = register_trace_sched_wakeup(probe_sched_wakeup, NULL);
 	if (ret) {
 		pr_info("wakeup trace: Couldn't activate tracepoint"
 			" probe to kernel_sched_wakeup\n");
 		return ret;
 	}
 
-	ret = register_trace_sched_wakeup_new(probe_sched_wakeup);
+	ret = register_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
 	if (ret) {
 		pr_info("wakeup trace: Couldn't activate tracepoint"
 			" probe to kernel_sched_wakeup_new\n");
 		goto fail_deprobe;
 	}
 
-	ret = register_trace_sched_switch(probe_sched_switch);
+	ret = register_trace_sched_switch(probe_sched_switch, NULL);
 	if (ret) {
 		pr_info("sched trace: Couldn't activate tracepoint"
 			" probe to kernel_sched_switch\n");
@@ -161,17 +161,17 @@ static int tracing_sched_register(void)
 
 	return ret;
 fail_deprobe_wake_new:
-	unregister_trace_sched_wakeup_new(probe_sched_wakeup);
+	unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
 fail_deprobe:
-	unregister_trace_sched_wakeup(probe_sched_wakeup);
+	unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
 	return ret;
 }
 
 static void tracing_sched_unregister(void)
 {
-	unregister_trace_sched_switch(probe_sched_switch);
-	unregister_trace_sched_wakeup_new(probe_sched_wakeup);
-	unregister_trace_sched_wakeup(probe_sched_wakeup);
+	unregister_trace_sched_switch(probe_sched_switch, NULL);
+	unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
+	unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
 }
 
 static void tracing_start_sched_switch(void)

kernel/trace/trace_sched_wakeup.c

@@ -98,7 +98,8 @@ static int report_latency(cycle_t delta)
 	return 1;
 }
 
-static void probe_wakeup_migrate_task(struct task_struct *task, int cpu)
+static void
+probe_wakeup_migrate_task(void *ignore, struct task_struct *task, int cpu)
 {
 	if (task != wakeup_task)
 		return;
@@ -107,7 +108,8 @@ static void probe_wakeup_migrate_task(struct task_struct *task, int cpu)
 }
 
 static void notrace
-probe_wakeup_sched_switch(struct task_struct *prev, struct task_struct *next)
+probe_wakeup_sched_switch(void *ignore,
+			  struct task_struct *prev, struct task_struct *next)
 {
 	struct trace_array_cpu *data;
 	cycle_t T0, T1, delta;
@@ -199,7 +201,7 @@ static void wakeup_reset(struct trace_array *tr)
 }
 
 static void
-probe_wakeup(struct task_struct *p, int success)
+probe_wakeup(void *ignore, struct task_struct *p, int success)
 {
 	struct trace_array_cpu *data;
 	int cpu = smp_processor_id();
@@ -263,28 +265,28 @@ static void start_wakeup_tracer(struct trace_array *tr)
 {
 	int ret;
 
-	ret = register_trace_sched_wakeup(probe_wakeup);
+	ret = register_trace_sched_wakeup(probe_wakeup, NULL);
 	if (ret) {
 		pr_info("wakeup trace: Couldn't activate tracepoint"
 			" probe to kernel_sched_wakeup\n");
 		return;
 	}
 
-	ret = register_trace_sched_wakeup_new(probe_wakeup);
+	ret = register_trace_sched_wakeup_new(probe_wakeup, NULL);
 	if (ret) {
 		pr_info("wakeup trace: Couldn't activate tracepoint"
 			" probe to kernel_sched_wakeup_new\n");
 		goto fail_deprobe;
 	}
 
-	ret = register_trace_sched_switch(probe_wakeup_sched_switch);
+	ret = register_trace_sched_switch(probe_wakeup_sched_switch, NULL);
 	if (ret) {
 		pr_info("sched trace: Couldn't activate tracepoint"
 			" probe to kernel_sched_switch\n");
 		goto fail_deprobe_wake_new;
 	}
 
-	ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task);
+	ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
 	if (ret) {
 		pr_info("wakeup trace: Couldn't activate tracepoint"
 			" probe to kernel_sched_migrate_task\n");
@@ -311,19 +313,19 @@ static void start_wakeup_tracer(struct trace_array *tr)
 
 	return;
 fail_deprobe_wake_new:
-	unregister_trace_sched_wakeup_new(probe_wakeup);
+	unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
 fail_deprobe:
-	unregister_trace_sched_wakeup(probe_wakeup);
+	unregister_trace_sched_wakeup(probe_wakeup, NULL);
 }
 
 static void stop_wakeup_tracer(struct trace_array *tr)
 {
 	tracer_enabled = 0;
 	unregister_ftrace_function(&trace_ops);
-	unregister_trace_sched_switch(probe_wakeup_sched_switch);
-	unregister_trace_sched_wakeup_new(probe_wakeup);
-	unregister_trace_sched_wakeup(probe_wakeup);
-	unregister_trace_sched_migrate_task(probe_wakeup_migrate_task);
+	unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
+	unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
+	unregister_trace_sched_wakeup(probe_wakeup, NULL);
+	unregister_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
 }
 
 static int __wakeup_tracer_init(struct trace_array *tr)

kernel/trace/trace_workqueue.c

@@ -49,7 +49,8 @@ static void cpu_workqueue_stat_free(struct kref *kref)
 
 /* Insertion of a work */
 static void
-probe_workqueue_insertion(struct task_struct *wq_thread,
+probe_workqueue_insertion(void *ignore,
+			  struct task_struct *wq_thread,
 			  struct work_struct *work)
 {
 	int cpu = cpumask_first(&wq_thread->cpus_allowed);
@@ -70,7 +71,8 @@ probe_workqueue_insertion(struct task_struct *wq_thread,
 
 /* Execution of a work */
 static void
-probe_workqueue_execution(struct task_struct *wq_thread,
+probe_workqueue_execution(void *ignore,
+			  struct task_struct *wq_thread,
 			  struct work_struct *work)
 {
 	int cpu = cpumask_first(&wq_thread->cpus_allowed);
@@ -90,7 +92,8 @@ probe_workqueue_execution(struct task_struct *wq_thread,
 }
 
 /* Creation of a cpu workqueue thread */
-static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
+static void probe_workqueue_creation(void *ignore,
+				     struct task_struct *wq_thread, int cpu)
 {
 	struct cpu_workqueue_stats *cws;
 	unsigned long flags;
@@ -114,7 +117,8 @@ static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
 }
 
 /* Destruction of a cpu workqueue thread */
-static void probe_workqueue_destruction(struct task_struct *wq_thread)
+static void
+probe_workqueue_destruction(void *ignore, struct task_struct *wq_thread)
 {
 	/* Workqueue only execute on one cpu */
 	int cpu = cpumask_first(&wq_thread->cpus_allowed);
@@ -259,19 +263,19 @@ int __init trace_workqueue_early_init(void)
 {
 	int ret, cpu;
 
-	ret = register_trace_workqueue_insertion(probe_workqueue_insertion);
+	ret = register_trace_workqueue_insertion(probe_workqueue_insertion, NULL);
 	if (ret)
 		goto out;
 
-	ret = register_trace_workqueue_execution(probe_workqueue_execution);
+	ret = register_trace_workqueue_execution(probe_workqueue_execution, NULL);
 	if (ret)
 		goto no_insertion;
 
-	ret = register_trace_workqueue_creation(probe_workqueue_creation);
+	ret = register_trace_workqueue_creation(probe_workqueue_creation, NULL);
 	if (ret)
 		goto no_execution;
 
-	ret = register_trace_workqueue_destruction(probe_workqueue_destruction);
+	ret = register_trace_workqueue_destruction(probe_workqueue_destruction, NULL);
 	if (ret)
 		goto no_creation;
 
@@ -283,11 +287,11 @@ int __init trace_workqueue_early_init(void)
 	return 0;
 
 no_creation:
-	unregister_trace_workqueue_creation(probe_workqueue_creation);
+	unregister_trace_workqueue_creation(probe_workqueue_creation, NULL);
 no_execution:
-	unregister_trace_workqueue_execution(probe_workqueue_execution);
+	unregister_trace_workqueue_execution(probe_workqueue_execution, NULL);
 no_insertion:
-	unregister_trace_workqueue_insertion(probe_workqueue_insertion);
+	unregister_trace_workqueue_insertion(probe_workqueue_insertion, NULL);
 out:
 	pr_warning("trace_workqueue: unable to trace workqueues\n");
 

kernel/tracepoint.c

@@ -54,7 +54,7 @@ static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE];
  */
 struct tracepoint_entry {
 	struct hlist_node hlist;
-	void **funcs;
+	struct tracepoint_func *funcs;
 	int refcount;	/* Number of times armed. 0 if disarmed. */
 	char name[0];
 };
@@ -64,12 +64,12 @@ struct tp_probes {
 		struct rcu_head rcu;
 		struct list_head list;
 	} u;
-	void *probes[0];
+	struct tracepoint_func probes[0];
 };
 
 static inline void *allocate_probes(int count)
 {
-	struct tp_probes *p  = kmalloc(count * sizeof(void *)
+	struct tp_probes *p  = kmalloc(count * sizeof(struct tracepoint_func)
 			+ sizeof(struct tp_probes), GFP_KERNEL);
 	return p == NULL ? NULL : p->probes;
 }
@@ -79,7 +79,7 @@ static void rcu_free_old_probes(struct rcu_head *head)
 	kfree(container_of(head, struct tp_probes, u.rcu));
 }
 
-static inline void release_probes(void *old)
+static inline void release_probes(struct tracepoint_func *old)
 {
 	if (old) {
 		struct tp_probes *tp_probes = container_of(old,
@@ -95,15 +95,16 @@ static void debug_print_probes(struct tracepoint_entry *entry)
 	if (!tracepoint_debug || !entry->funcs)
 		return;
 
-	for (i = 0; entry->funcs[i]; i++)
-		printk(KERN_DEBUG "Probe %d : %p\n", i, entry->funcs[i]);
+	for (i = 0; entry->funcs[i].func; i++)
+		printk(KERN_DEBUG "Probe %d : %p\n", i, entry->funcs[i].func);
 }
 
-static void *
-tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
+static struct tracepoint_func *
+tracepoint_entry_add_probe(struct tracepoint_entry *entry,
+			   void *probe, void *data)
 {
 	int nr_probes = 0;
-	void **old, **new;
+	struct tracepoint_func *old, *new;
 
 	WARN_ON(!probe);
 
@@ -111,8 +112,9 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
 	old = entry->funcs;
 	if (old) {
 		/* (N -> N+1), (N != 0, 1) probes */
-		for (nr_probes = 0; old[nr_probes]; nr_probes++)
-			if (old[nr_probes] == probe)
+		for (nr_probes = 0; old[nr_probes].func; nr_probes++)
+			if (old[nr_probes].func == probe &&
+			    old[nr_probes].data == data)
 				return ERR_PTR(-EEXIST);
 	}
 	/* + 2 : one for new probe, one for NULL func */
@@ -120,9 +122,10 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
 	if (new == NULL)
 		return ERR_PTR(-ENOMEM);
 	if (old)
-		memcpy(new, old, nr_probes * sizeof(void *));
-	new[nr_probes] = probe;
-	new[nr_probes + 1] = NULL;
+		memcpy(new, old, nr_probes * sizeof(struct tracepoint_func));
+	new[nr_probes].func = probe;
+	new[nr_probes].data = data;
+	new[nr_probes + 1].func = NULL;
 	entry->refcount = nr_probes + 1;
 	entry->funcs = new;
 	debug_print_probes(entry);
@@ -130,10 +133,11 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
 }
 
 static void *
-tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe)
+tracepoint_entry_remove_probe(struct tracepoint_entry *entry,
+			      void *probe, void *data)
 {
 	int nr_probes = 0, nr_del = 0, i;
-	void **old, **new;
+	struct tracepoint_func *old, *new;
 
 	old = entry->funcs;
 
@@ -142,8 +146,10 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe)
 
 	debug_print_probes(entry);
 	/* (N -> M), (N > 1, M >= 0) probes */
-	for (nr_probes = 0; old[nr_probes]; nr_probes++) {
-		if ((!probe || old[nr_probes] == probe))
+	for (nr_probes = 0; old[nr_probes].func; nr_probes++) {
+		if (!probe ||
+		    (old[nr_probes].func == probe &&
+		     old[nr_probes].data == data))
 			nr_del++;
 	}
 
@@ -160,10 +166,11 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe)
 		new = allocate_probes(nr_probes - nr_del + 1);
 		if (new == NULL)
 			return ERR_PTR(-ENOMEM);
-		for (i = 0; old[i]; i++)
-			if ((probe && old[i] != probe))
+		for (i = 0; old[i].func; i++)
+			if (probe &&
+			    (old[i].func != probe || old[i].data != data))
 				new[j++] = old[i];
-		new[nr_probes - nr_del] = NULL;
+		new[nr_probes - nr_del].func = NULL;
 		entry->refcount = nr_probes - nr_del;
 		entry->funcs = new;
 	}
@@ -315,18 +322,19 @@ static void tracepoint_update_probes(void)
 	module_update_tracepoints();
 }
 
-static void *tracepoint_add_probe(const char *name, void *probe)
+static struct tracepoint_func *
+tracepoint_add_probe(const char *name, void *probe, void *data)
 {
 	struct tracepoint_entry *entry;
-	void *old;
+	struct tracepoint_func *old;
 
 	entry = get_tracepoint(name);
 	if (!entry) {
 		entry = add_tracepoint(name);
 		if (IS_ERR(entry))
-			return entry;
+			return (struct tracepoint_func *)entry;
 	}
-	old = tracepoint_entry_add_probe(entry, probe);
+	old = tracepoint_entry_add_probe(entry, probe, data);
 	if (IS_ERR(old) && !entry->refcount)
 		remove_tracepoint(entry);
 	return old;
@@ -340,12 +348,12 @@ static void *tracepoint_add_probe(const char *name, void *probe)
  * Returns 0 if ok, error value on error.
  * The probe address must at least be aligned on the architecture pointer size.
  */
-int tracepoint_probe_register(const char *name, void *probe)
+int tracepoint_probe_register(const char *name, void *probe, void *data)
 {
-	void *old;
+	struct tracepoint_func *old;
 
 	mutex_lock(&tracepoints_mutex);
-	old = tracepoint_add_probe(name, probe);
+	old = tracepoint_add_probe(name, probe, data);
 	mutex_unlock(&tracepoints_mutex);
 	if (IS_ERR(old))
 		return PTR_ERR(old);
@@ -356,15 +364,16 @@ int tracepoint_probe_register(const char *name, void *probe)
 }
 EXPORT_SYMBOL_GPL(tracepoint_probe_register);
 
-static void *tracepoint_remove_probe(const char *name, void *probe)
+static struct tracepoint_func *
+tracepoint_remove_probe(const char *name, void *probe, void *data)
 {
 	struct tracepoint_entry *entry;
-	void *old;
+	struct tracepoint_func *old;
 
 	entry = get_tracepoint(name);
 	if (!entry)
 		return ERR_PTR(-ENOENT);
-	old = tracepoint_entry_remove_probe(entry, probe);
+	old = tracepoint_entry_remove_probe(entry, probe, data);
 	if (IS_ERR(old))
 		return old;
 	if (!entry->refcount)
@@ -382,12 +391,12 @@ static void *tracepoint_remove_probe(const char *name, void *probe)
  * itself uses stop_machine(), which insures that every preempt disabled section
  * have finished.
  */
-int tracepoint_probe_unregister(const char *name, void *probe)
+int tracepoint_probe_unregister(const char *name, void *probe, void *data)
 {
-	void *old;
+	struct tracepoint_func *old;
 
 	mutex_lock(&tracepoints_mutex);
-	old = tracepoint_remove_probe(name, probe);
+	old = tracepoint_remove_probe(name, probe, data);
 	mutex_unlock(&tracepoints_mutex);
 	if (IS_ERR(old))
 		return PTR_ERR(old);
@@ -418,12 +427,13 @@ static void tracepoint_add_old_probes(void *old)
  *
  * caller must call tracepoint_probe_update_all()
  */
-int tracepoint_probe_register_noupdate(const char *name, void *probe)
+int tracepoint_probe_register_noupdate(const char *name, void *probe,
+				       void *data)
 {
-	void *old;
+	struct tracepoint_func *old;
 
 	mutex_lock(&tracepoints_mutex);
-	old = tracepoint_add_probe(name, probe);
+	old = tracepoint_add_probe(name, probe, data);
 	if (IS_ERR(old)) {
 		mutex_unlock(&tracepoints_mutex);
 		return PTR_ERR(old);
@@ -441,12 +451,13 @@ EXPORT_SYMBOL_GPL(tracepoint_probe_register_noupdate);
  *
  * caller must call tracepoint_probe_update_all()
  */
-int tracepoint_probe_unregister_noupdate(const char *name, void *probe)
+int tracepoint_probe_unregister_noupdate(const char *name, void *probe,
+					 void *data)
 {
-	void *old;
+	struct tracepoint_func *old;
 
 	mutex_lock(&tracepoints_mutex);
-	old = tracepoint_remove_probe(name, probe);
+	old = tracepoint_remove_probe(name, probe, data);
 	if (IS_ERR(old)) {
 		mutex_unlock(&tracepoints_mutex);
 		return PTR_ERR(old);

net/core/drop_monitor.c

@@ -172,12 +172,12 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 	return;
 }
 
-static void trace_kfree_skb_hit(struct sk_buff *skb, void *location)
+static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location)
 {
 	trace_drop_common(skb, location);
 }
 
-static void trace_napi_poll_hit(struct napi_struct *napi)
+static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi)
 {
 	struct dm_hw_stat_delta *new_stat;
 
@@ -225,12 +225,12 @@ static int set_all_monitor_traces(int state)
 
 	switch (state) {
 	case TRACE_ON:
-		rc |= register_trace_kfree_skb(trace_kfree_skb_hit);
-		rc |= register_trace_napi_poll(trace_napi_poll_hit);
+		rc |= register_trace_kfree_skb(trace_kfree_skb_hit, NULL);
+		rc |= register_trace_napi_poll(trace_napi_poll_hit, NULL);
 		break;
 	case TRACE_OFF:
-		rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit);
-		rc |= unregister_trace_napi_poll(trace_napi_poll_hit);
+		rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit, NULL);
+		rc |= unregister_trace_napi_poll(trace_napi_poll_hit, NULL);
 
 		tracepoint_synchronize_unregister();
 

samples/tracepoints/tp-samples-trace.h

@@ -7,7 +7,5 @@
 DECLARE_TRACE(subsys_event,
 	TP_PROTO(struct inode *inode, struct file *file),
 	TP_ARGS(inode, file));
-DECLARE_TRACE(subsys_eventb,
-	TP_PROTO(void),
-	TP_ARGS());
+DECLARE_TRACE_NOARGS(subsys_eventb);
 #endif

samples/tracepoints/tracepoint-probe-sample.c

@@ -13,7 +13,8 @@
  * Here the caller only guarantees locking for struct file and struct inode.
  * Locking must therefore be done in the probe to use the dentry.
  */
-static void probe_subsys_event(struct inode *inode, struct file *file)
+static void probe_subsys_event(void *ignore,
+			       struct inode *inode, struct file *file)
 {
 	path_get(&file->f_path);
 	dget(file->f_path.dentry);
@@ -23,7 +24,7 @@ static void probe_subsys_event(struct inode *inode, struct file *file)
 	path_put(&file->f_path);
 }
 
-static void probe_subsys_eventb(void)
+static void probe_subsys_eventb(void *ignore)
 {
 	printk(KERN_INFO "Event B is encountered\n");
 }
@@ -32,9 +33,9 @@ static int __init tp_sample_trace_init(void)
 {
 	int ret;
 
-	ret = register_trace_subsys_event(probe_subsys_event);
+	ret = register_trace_subsys_event(probe_subsys_event, NULL);
 	WARN_ON(ret);
-	ret = register_trace_subsys_eventb(probe_subsys_eventb);
+	ret = register_trace_subsys_eventb(probe_subsys_eventb, NULL);
 	WARN_ON(ret);
 
 	return 0;
@@ -44,8 +45,8 @@ module_init(tp_sample_trace_init);
 
 static void __exit tp_sample_trace_exit(void)
 {
-	unregister_trace_subsys_eventb(probe_subsys_eventb);
-	unregister_trace_subsys_event(probe_subsys_event);
+	unregister_trace_subsys_eventb(probe_subsys_eventb, NULL);
+	unregister_trace_subsys_event(probe_subsys_event, NULL);
 	tracepoint_synchronize_unregister();
 }
 

samples/tracepoints/tracepoint-probe-sample2.c

@@ -12,7 +12,8 @@
  * Here the caller only guarantees locking for struct file and struct inode.
  * Locking must therefore be done in the probe to use the dentry.
  */
-static void probe_subsys_event(struct inode *inode, struct file *file)
+static void probe_subsys_event(void *ignore,
+			       struct inode *inode, struct file *file)
 {
 	printk(KERN_INFO "Event is encountered with inode number %lu\n",
 		inode->i_ino);
@@ -22,7 +23,7 @@ static int __init tp_sample_trace_init(void)
 {
 	int ret;
 
-	ret = register_trace_subsys_event(probe_subsys_event);
+	ret = register_trace_subsys_event(probe_subsys_event, NULL);
 	WARN_ON(ret);
 
 	return 0;
@@ -32,7 +33,7 @@ module_init(tp_sample_trace_init);
 
 static void __exit tp_sample_trace_exit(void)
 {
-	unregister_trace_subsys_event(probe_subsys_event);
+	unregister_trace_subsys_event(probe_subsys_event, NULL);
 	tracepoint_synchronize_unregister();
 }
 

tools/perf/Documentation/perf-stat.txt

@@ -43,6 +43,9 @@ OPTIONS
 -c::
         scale counter values
 
+-B::
+        print large numbers with thousands' separators according to locale
+
 EXAMPLES
 --------
 

tools/perf/builtin-annotate.c

@@ -277,7 +277,7 @@ static void hist_entry__print_hits(struct hist_entry *self)
 	printf("%*s: %Lu\n", BITS_PER_LONG / 2, "h->sum", h->sum);
 }
 
-static void annotate_sym(struct hist_entry *he)
+static int hist_entry__tty_annotate(struct hist_entry *he)
 {
 	struct map *map = he->ms.map;
 	struct dso *dso = map->dso;
@@ -288,7 +288,7 @@ static void annotate_sym(struct hist_entry *he)
 	struct objdump_line *pos, *n;
 
 	if (hist_entry__annotate(he, &head) < 0)
-		return;
+		return -1;
 
 	if (full_paths)
 		d_filename = filename;
@@ -317,31 +317,60 @@ static void annotate_sym(struct hist_entry *he)
 
 	if (print_line)
 		free_source_line(he, len);
+
+	return 0;
 }
 
 static void hists__find_annotations(struct hists *self)
 {
-	struct rb_node *nd;
+	struct rb_node *first = rb_first(&self->entries), *nd = first;
+	int key = KEY_RIGHT;
 
-	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
+	while (nd) {
 		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
 		struct sym_priv *priv;
 
-		if (he->ms.sym == NULL)
-			continue;
+		if (he->ms.sym == NULL || he->ms.map->dso->annotate_warned)
+			goto find_next;
 
 		priv = symbol__priv(he->ms.sym);
-		if (priv->hist == NULL)
+		if (priv->hist == NULL) {
+find_next:
+			if (key == KEY_LEFT)
+				nd = rb_prev(nd);
+			else
+				nd = rb_next(nd);
 			continue;
+		}
 
-		annotate_sym(he);
+		if (use_browser) {
+			key = hist_entry__tui_annotate(he);
+			if (is_exit_key(key))
+				break;
+			switch (key) {
+			case KEY_RIGHT:
+			case '\t':
+				nd = rb_next(nd);
+				break;
+			case KEY_LEFT:
+				if (nd == first)
+					continue;
+				nd = rb_prev(nd);
+			default:
+				break;
+			}
+		} else {
+			hist_entry__tty_annotate(he);
+			nd = rb_next(nd);
 			/*
-		 * Since we have a hist_entry per IP for the same symbol, free
-		 * he->ms.sym->hist to signal we already processed this symbol.
+			 * Since we have a hist_entry per IP for the same
+			 * symbol, free he->ms.sym->hist to signal we already
+			 * processed this symbol.
 			 */
 			free(priv->hist);
 			priv->hist = NULL;
 		}
+	}
 }
 
 static struct perf_event_ops event_ops = {
@@ -416,6 +445,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __used)
 {
 	argc = parse_options(argc, argv, options, annotate_usage, 0);
 
+	setup_browser();
+
 	symbol_conf.priv_size = sizeof(struct sym_priv);
 	symbol_conf.try_vmlinux_path = true;
 
@@ -435,8 +466,6 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __used)
 		sym_hist_filter = argv[0];
 	}
 
-	setup_pager();
-
 	if (field_sep && *field_sep == '.') {
 		pr_err("'.' is the only non valid --field-separator argument\n");
 		return -1;

tools/perf/builtin-probe.c

@@ -65,8 +65,10 @@ static int parse_probe_event(const char *str)
 	int ret;
 
 	pr_debug("probe-definition(%d): %s\n", params.nevents, str);
-	if (++params.nevents == MAX_PROBES)
-		die("Too many probes (> %d) are specified.", MAX_PROBES);
+	if (++params.nevents == MAX_PROBES) {
+		pr_err("Too many probes (> %d) were specified.", MAX_PROBES);
+		return -1;
+	}
 
 	/* Parse a perf-probe command into event */
 	ret = parse_perf_probe_command(str, pev);
@@ -84,7 +86,9 @@ static int parse_probe_event_argv(int argc, const char **argv)
 	len = 0;
 	for (i = 0; i < argc; i++)
 		len += strlen(argv[i]) + 1;
-	buf = xzalloc(len + 1);
+	buf = zalloc(len + 1);
+	if (buf == NULL)
+		return -ENOMEM;
 	len = 0;
 	for (i = 0; i < argc; i++)
 		len += sprintf(&buf[len], "%s ", argv[i]);

tools/perf/builtin-record.c

@@ -25,6 +25,7 @@
 
 #include <unistd.h>
 #include <sched.h>
+#include <sys/mman.h>
 
 enum write_mode_t {
 	WRITE_FORCE,
@@ -60,13 +61,8 @@ static bool			call_graph			=  false;
 static bool			inherit_stat			=  false;
 static bool			no_samples			=  false;
 static bool			sample_address			=  false;
-static bool			multiplex			=  false;
-static int			multiplex_fd			=     -1;
 
 static long			samples				=      0;
-static struct timeval		last_read;
-static struct timeval		this_read;
-
 static u64			bytes_written			=      0;
 
 static struct pollfd		*event_array;
@@ -86,7 +82,7 @@ struct mmap_data {
 	unsigned int		prev;
 };
 
-static struct mmap_data		*mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
+static struct mmap_data		mmap_array[MAX_NR_CPUS];
 
 static unsigned long mmap_read_head(struct mmap_data *md)
 {
@@ -146,8 +142,6 @@ static void mmap_read(struct mmap_data *md)
 	void *buf;
 	int diff;
 
-	gettimeofday(&this_read, NULL);
-
 	/*
 	 * If we're further behind than half the buffer, there's a chance
 	 * the writer will bite our tail and mess up the samples under us.
@@ -158,23 +152,13 @@ static void mmap_read(struct mmap_data *md)
 	 */
 	diff = head - old;
 	if (diff < 0) {
-		struct timeval iv;
-		unsigned long msecs;
-
-		timersub(&this_read, &last_read, &iv);
-		msecs = iv.tv_sec*1000 + iv.tv_usec/1000;
-
-		fprintf(stderr, "WARNING: failed to keep up with mmap data."
-				"  Last read %lu msecs ago.\n", msecs);
-
+		fprintf(stderr, "WARNING: failed to keep up with mmap data\n");
 		/*
 		 * head points to a known good entry, start there.
 		 */
 		old = head;
 	}
 
-	last_read = this_read;
-
 	if (old != head)
 		samples++;
 
@@ -380,27 +364,30 @@ static void create_counter(int counter, int cpu)
 		 */
 		if (group && group_fd == -1)
 			group_fd = fd[nr_cpu][counter][thread_index];
-		if (multiplex && multiplex_fd == -1)
-			multiplex_fd = fd[nr_cpu][counter][thread_index];
 
-		if (multiplex && fd[nr_cpu][counter][thread_index] != multiplex_fd) {
-
-			ret = ioctl(fd[nr_cpu][counter][thread_index], PERF_EVENT_IOC_SET_OUTPUT, multiplex_fd);
-			assert(ret != -1);
+		if (counter || thread_index) {
+			ret = ioctl(fd[nr_cpu][counter][thread_index],
+					PERF_EVENT_IOC_SET_OUTPUT,
+					fd[nr_cpu][0][0]);
+			if (ret) {
+				error("failed to set output: %d (%s)\n", errno,
+						strerror(errno));
+				exit(-1);
+			}
 		} else {
-			event_array[nr_poll].fd = fd[nr_cpu][counter][thread_index];
-			event_array[nr_poll].events = POLLIN;
-			nr_poll++;
-
-			mmap_array[nr_cpu][counter][thread_index].counter = counter;
-			mmap_array[nr_cpu][counter][thread_index].prev = 0;
-			mmap_array[nr_cpu][counter][thread_index].mask = mmap_pages*page_size - 1;
-			mmap_array[nr_cpu][counter][thread_index].base = mmap(NULL, (mmap_pages+1)*page_size,
+			mmap_array[nr_cpu].counter = counter;
+			mmap_array[nr_cpu].prev = 0;
+			mmap_array[nr_cpu].mask = mmap_pages*page_size - 1;
+			mmap_array[nr_cpu].base = mmap(NULL, (mmap_pages+1)*page_size,
 				PROT_READ|PROT_WRITE, MAP_SHARED, fd[nr_cpu][counter][thread_index], 0);
-			if (mmap_array[nr_cpu][counter][thread_index].base == MAP_FAILED) {
+			if (mmap_array[nr_cpu].base == MAP_FAILED) {
 				error("failed to mmap with %d (%s)\n", errno, strerror(errno));
 				exit(-1);
 			}
+
+			event_array[nr_poll].fd = fd[nr_cpu][counter][thread_index];
+			event_array[nr_poll].events = POLLIN;
+			nr_poll++;
 		}
 
 		if (filter != NULL) {
@@ -501,16 +488,11 @@ static struct perf_event_header finished_round_event = {
 
 static void mmap_read_all(void)
 {
-	int i, counter, thread;
+	int i;
 
 	for (i = 0; i < nr_cpu; i++) {
-		for (counter = 0; counter < nr_counters; counter++) {
-			for (thread = 0; thread < thread_num; thread++) {
-				if (mmap_array[i][counter][thread].base)
-					mmap_read(&mmap_array[i][counter][thread]);
-			}
-
-		}
+		if (mmap_array[i].base)
+			mmap_read(&mmap_array[i]);
 	}
 
 	if (perf_header__has_feat(&session->header, HEADER_TRACE_INFO))
@@ -834,8 +816,6 @@ static const struct option options[] = {
 		    "Sample addresses"),
 	OPT_BOOLEAN('n', "no-samples", &no_samples,
 		    "don't sample"),
-	OPT_BOOLEAN('M', "multiplex", &multiplex,
-		    "multiplex counter output in a single channel"),
 	OPT_END()
 };
 
@@ -887,9 +867,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 	for (i = 0; i < MAX_NR_CPUS; i++) {
 		for (j = 0; j < MAX_COUNTERS; j++) {
 			fd[i][j] = malloc(sizeof(int)*thread_num);
-			mmap_array[i][j] = zalloc(
-				sizeof(struct mmap_data)*thread_num);
-			if (!fd[i][j] || !mmap_array[i][j])
+			if (!fd[i][j])
 				return -ENOMEM;
 		}
 	}

tools/perf/builtin-stat.c

@@ -50,6 +50,7 @@
 
 #include <sys/prctl.h>
 #include <math.h>
+#include <locale.h>
 
 static struct perf_event_attr default_attrs[] = {
 
@@ -80,6 +81,8 @@ static pid_t			*all_tids			=  NULL;
 static int			thread_num			=  0;
 static pid_t			child_pid			= -1;
 static bool			null_run			=  false;
+static bool			big_num				=  false;
+
 
 static int			*fd[MAX_NR_CPUS][MAX_COUNTERS];
 
@@ -377,7 +380,7 @@ static void nsec_printout(int counter, double avg)
 {
 	double msecs = avg / 1e6;
 
-	fprintf(stderr, " %14.6f  %-24s", msecs, event_name(counter));
+	fprintf(stderr, " %18.6f  %-24s", msecs, event_name(counter));
 
 	if (MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter)) {
 		fprintf(stderr, " # %10.3f CPUs ",
@@ -389,7 +392,10 @@ static void abs_printout(int counter, double avg)
 {
 	double total, ratio = 0.0;
 
-	fprintf(stderr, " %14.0f  %-24s", avg, event_name(counter));
+	if (big_num)
+		fprintf(stderr, " %'18.0f  %-24s", avg, event_name(counter));
+	else
+		fprintf(stderr, " %18.0f  %-24s", avg, event_name(counter));
 
 	if (MATCH_EVENT(HARDWARE, HW_INSTRUCTIONS, counter)) {
 		total = avg_stats(&runtime_cycles_stats);
@@ -426,7 +432,7 @@ static void print_counter(int counter)
 	int scaled = event_scaled[counter];
 
 	if (scaled == -1) {
-		fprintf(stderr, " %14s  %-24s\n",
+		fprintf(stderr, " %18s  %-24s\n",
 			"<not counted>", event_name(counter));
 		return;
 	}
@@ -477,7 +483,7 @@ static void print_stat(int argc, const char **argv)
 		print_counter(counter);
 
 	fprintf(stderr, "\n");
-	fprintf(stderr, " %14.9f  seconds time elapsed",
+	fprintf(stderr, " %18.9f  seconds time elapsed",
 			avg_stats(&walltime_nsecs_stats)/1e9);
 	if (run_count > 1) {
 		fprintf(stderr, "   ( +- %7.3f%% )",
@@ -534,6 +540,8 @@ static const struct option options[] = {
 		    "repeat command and print average + stddev (max: 100)"),
 	OPT_BOOLEAN('n', "null", &null_run,
 		    "null run - dont start any counters"),
+	OPT_BOOLEAN('B', "big-num", &big_num,
+		    "print large numbers with thousands\' separators"),
 	OPT_END()
 };
 
@@ -542,6 +550,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 	int status;
 	int i,j;
 
+	setlocale(LC_ALL, "");
+
 	argc = parse_options(argc, argv, options, stat_usage,
 		PARSE_OPT_STOP_AT_NON_OPTION);
 	if (!argc && target_pid == -1 && target_tid == -1)

tools/perf/util/build-id.h

@@ -5,4 +5,6 @@
 
 extern struct perf_event_ops build_id__mark_dso_hit_ops;
 
+char *dso__build_id_filename(struct dso *self, char *bf, size_t size);
+
 #endif

tools/perf/util/callchain.c

@@ -15,6 +15,7 @@
 #include <errno.h>
 #include <math.h>
 
+#include "util.h"
 #include "callchain.h"
 
 bool ip_callchain__valid(struct ip_callchain *chain, event_t *event)