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: (470 commits)
  x86: Fix comments of register/stack access functions
  perf tools: Replace %m with %a in sscanf
  hw-breakpoints: Keep track of user disabled breakpoints
  tracing/syscalls: Make syscall events print callbacks static
  tracing: Add DEFINE_EVENT(), DEFINE_SINGLE_EVENT() support to docbook
  perf: Don't free perf_mmap_data until work has been done
  perf_event: Fix compile error
  perf tools: Fix _GNU_SOURCE macro related strndup() build error
  trace_syscalls: Remove unused syscall_name_to_nr()
  trace_syscalls: Simplify syscall profile
  trace_syscalls: Remove duplicate init_enter_##sname()
  trace_syscalls: Add syscall_nr field to struct syscall_metadata
  trace_syscalls: Remove enter_id exit_id
  trace_syscalls: Set event_enter_##sname->data to its metadata
  trace_syscalls: Remove unused event_syscall_enter and event_syscall_exit
  perf_event: Initialize data.period in perf_swevent_hrtimer()
  perf probe: Simplify event naming
  perf probe: Add --list option for listing current probe events
  perf probe: Add argv_split() from lib/argv_split.c
  perf probe: Move probe event utility functions to probe-event.c
  ...

22 files changed, 3574 insertions, 575 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index dcf6789bf547..982c50e2ce53 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -21,6 +21,7 @@ CFLAGS_REMOVE_mutex-debug.o = -pg
 CFLAGS_REMOVE_rtmutex-debug.o = -pg
 CFLAGS_REMOVE_cgroup-debug.o = -pg
 CFLAGS_REMOVE_sched_clock.o = -pg
+CFLAGS_REMOVE_perf_event.o = -pg
 endif
 
 obj-$(CONFIG_FREEZER) += freezer.o
@@ -97,6 +98,7 @@ obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_SLOW_WORK) += slow-work.o
 obj-$(CONFIG_SLOW_WORK_DEBUG) += slow-work-debugfs.o
 obj-$(CONFIG_PERF_EVENTS) += perf_event.o
+obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/exit.c b/kernel/exit.c
index f7864ac2ecc1..3f45e3cf931d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -49,6 +49,7 @@
 #include <linux/init_task.h>
 #include <linux/perf_event.h>
 #include <trace/events/sched.h>
+#include <linux/hw_breakpoint.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -978,6 +979,10 @@ NORET_TYPE void do_exit(long code)
 	proc_exit_connector(tsk);
 
 	/*
+	 * FIXME: do that only when needed, using sched_exit tracepoint
+	 */
+	flush_ptrace_hw_breakpoint(tsk);
+	/*
 	 * Flush inherited counters to the parent - before the parent
 	 * gets woken up by child-exit notifications.
 	 */
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
new file mode 100644
index 000000000000..cf5ee1628411
--- /dev/null
+++ b/kernel/hw_breakpoint.c
@@ -0,0 +1,423 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) 2007 Alan Stern
+ * Copyright (C) IBM Corporation, 2009
+ * Copyright (C) 2009, Frederic Weisbecker <fweisbec@gmail.com>
+ *
+ * Thanks to Ingo Molnar for his many suggestions.
+ *
+ * Authors: Alan Stern <stern@rowland.harvard.edu>
+ *          K.Prasad <prasad@linux.vnet.ibm.com>
+ *          Frederic Weisbecker <fweisbec@gmail.com>
+ */
+
+/*
+ * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility,
+ * using the CPU's debug registers.
+ * This file contains the arch-independent routines.
+ */
+
+#include <linux/irqflags.h>
+#include <linux/kallsyms.h>
+#include <linux/notifier.h>
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+
+#include <linux/hw_breakpoint.h>
+
+/*
+ * Constraints data
+ */
+
+/* Number of pinned cpu breakpoints in a cpu */
+static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned);
+
+/* Number of pinned task breakpoints in a cpu */
+static DEFINE_PER_CPU(unsigned int, task_bp_pinned[HBP_NUM]);
+
+/* Number of non-pinned cpu/task breakpoints in a cpu */
+static DEFINE_PER_CPU(unsigned int, nr_bp_flexible);
+
+/* Gather the number of total pinned and un-pinned bp in a cpuset */
+struct bp_busy_slots {
+	unsigned int pinned;
+	unsigned int flexible;
+};
+
+/* Serialize accesses to the above constraints */
+static DEFINE_MUTEX(nr_bp_mutex);
+
+/*
+ * Report the maximum number of pinned breakpoints a task
+ * have in this cpu
+ */
+static unsigned int max_task_bp_pinned(int cpu)
+{
+	int i;
+	unsigned int *tsk_pinned = per_cpu(task_bp_pinned, cpu);
+
+	for (i = HBP_NUM -1; i >= 0; i--) {
+		if (tsk_pinned[i] > 0)
+			return i + 1;
+	}
+
+	return 0;
+}
+
+/*
+ * Report the number of pinned/un-pinned breakpoints we have in
+ * a given cpu (cpu > -1) or in all of them (cpu = -1).
+ */
+static void fetch_bp_busy_slots(struct bp_busy_slots *slots, int cpu)
+{
+	if (cpu >= 0) {
+		slots->pinned = per_cpu(nr_cpu_bp_pinned, cpu);
+		slots->pinned += max_task_bp_pinned(cpu);
+		slots->flexible = per_cpu(nr_bp_flexible, cpu);
+
+		return;
+	}
+
+	for_each_online_cpu(cpu) {
+		unsigned int nr;
+
+		nr = per_cpu(nr_cpu_bp_pinned, cpu);
+		nr += max_task_bp_pinned(cpu);
+
+		if (nr > slots->pinned)
+			slots->pinned = nr;
+
+		nr = per_cpu(nr_bp_flexible, cpu);
+
+		if (nr > slots->flexible)
+			slots->flexible = nr;
+	}
+}
+
+/*
+ * Add a pinned breakpoint for the given task in our constraint table
+ */
+static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable)
+{
+	int count = 0;
+	struct perf_event *bp;
+	struct perf_event_context *ctx = tsk->perf_event_ctxp;
+	unsigned int *tsk_pinned;
+	struct list_head *list;
+	unsigned long flags;
+
+	if (WARN_ONCE(!ctx, "No perf context for this task"))
+		return;
+
+	list = &ctx->event_list;
+
+	spin_lock_irqsave(&ctx->lock, flags);
+
+	/*
+	 * The current breakpoint counter is not included in the list
+	 * at the open() callback time
+	 */
+	list_for_each_entry(bp, list, event_entry) {
+		if (bp->attr.type == PERF_TYPE_BREAKPOINT)
+			count++;
+	}
+
+	spin_unlock_irqrestore(&ctx->lock, flags);
+
+	if (WARN_ONCE(count < 0, "No breakpoint counter found in the counter list"))
+		return;
+
+	tsk_pinned = per_cpu(task_bp_pinned, cpu);
+	if (enable) {
+		tsk_pinned[count]++;
+		if (count > 0)
+			tsk_pinned[count-1]--;
+	} else {
+		tsk_pinned[count]--;
+		if (count > 0)
+			tsk_pinned[count-1]++;
+	}
+}
+
+/*
+ * Add/remove the given breakpoint in our constraint table
+ */
+static void toggle_bp_slot(struct perf_event *bp, bool enable)
+{
+	int cpu = bp->cpu;
+	struct task_struct *tsk = bp->ctx->task;
+
+	/* Pinned counter task profiling */
+	if (tsk) {
+		if (cpu >= 0) {
+			toggle_bp_task_slot(tsk, cpu, enable);
+			return;
+		}
+
+		for_each_online_cpu(cpu)
+			toggle_bp_task_slot(tsk, cpu, enable);
+		return;
+	}
+
+	/* Pinned counter cpu profiling */
+	if (enable)
+		per_cpu(nr_cpu_bp_pinned, bp->cpu)++;
+	else
+		per_cpu(nr_cpu_bp_pinned, bp->cpu)--;
+}
+
+/*
+ * Contraints to check before allowing this new breakpoint counter:
+ *
+ *  == Non-pinned counter == (Considered as pinned for now)
+ *
+ *   - If attached to a single cpu, check:
+ *
+ *       (per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ *           + max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
+ *
+ *       -> If there are already non-pinned counters in this cpu, it means
+ *          there is already a free slot for them.
+ *          Otherwise, we check that the maximum number of per task
+ *          breakpoints (for this cpu) plus the number of per cpu breakpoint
+ *          (for this cpu) doesn't cover every registers.
+ *
+ *   - If attached to every cpus, check:
+ *
+ *       (per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ *           + max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
+ *
+ *       -> This is roughly the same, except we check the number of per cpu
+ *          bp for every cpu and we keep the max one. Same for the per tasks
+ *          breakpoints.
+ *
+ *
+ * == Pinned counter ==
+ *
+ *   - If attached to a single cpu, check:
+ *
+ *       ((per_cpu(nr_bp_flexible, cpu) > 1) + per_cpu(nr_cpu_bp_pinned, cpu)
+ *            + max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
+ *
+ *       -> Same checks as before. But now the nr_bp_flexible, if any, must keep
+ *          one register at least (or they will never be fed).
+ *
+ *   - If attached to every cpus, check:
+ *
+ *       ((per_cpu(nr_bp_flexible, *) > 1) + max(per_cpu(nr_cpu_bp_pinned, *))
+ *            + max(per_cpu(task_bp_pinned, *))) < HBP_NUM
+ */
+int reserve_bp_slot(struct perf_event *bp)
+{
+	struct bp_busy_slots slots = {0};
+	int ret = 0;
+
+	mutex_lock(&nr_bp_mutex);
+
+	fetch_bp_busy_slots(&slots, bp->cpu);
+
+	/* Flexible counters need to keep at least one slot */
+	if (slots.pinned + (!!slots.flexible) == HBP_NUM) {
+		ret = -ENOSPC;
+		goto end;
+	}
+
+	toggle_bp_slot(bp, true);
+
+end:
+	mutex_unlock(&nr_bp_mutex);
+
+	return ret;
+}
+
+void release_bp_slot(struct perf_event *bp)
+{
+	mutex_lock(&nr_bp_mutex);
+
+	toggle_bp_slot(bp, false);
+
+	mutex_unlock(&nr_bp_mutex);
+}
+
+
+int __register_perf_hw_breakpoint(struct perf_event *bp)
+{
+	int ret;
+
+	ret = reserve_bp_slot(bp);
+	if (ret)
+		return ret;
+
+	/*
+	 * Ptrace breakpoints can be temporary perf events only
+	 * meant to reserve a slot. In this case, it is created disabled and
+	 * we don't want to check the params right now (as we put a null addr)
+	 * But perf tools create events as disabled and we want to check
+	 * the params for them.
+	 * This is a quick hack that will be removed soon, once we remove
+	 * the tmp breakpoints from ptrace
+	 */
+	if (!bp->attr.disabled || bp->callback == perf_bp_event)
+		ret = arch_validate_hwbkpt_settings(bp, bp->ctx->task);
+
+	return ret;
+}
+
+int register_perf_hw_breakpoint(struct perf_event *bp)
+{
+	bp->callback = perf_bp_event;
+
+	return __register_perf_hw_breakpoint(bp);
+}
+
+/**
+ * register_user_hw_breakpoint - register a hardware breakpoint for user space
+ * @attr: breakpoint attributes
+ * @triggered: callback to trigger when we hit the breakpoint
+ * @tsk: pointer to 'task_struct' of the process to which the address belongs
+ */
+struct perf_event *
+register_user_hw_breakpoint(struct perf_event_attr *attr,
+			    perf_callback_t triggered,
+			    struct task_struct *tsk)
+{
+	return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered);
+}
+EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
+
+/**
+ * modify_user_hw_breakpoint - modify a user-space hardware breakpoint
+ * @bp: the breakpoint structure to modify
+ * @attr: new breakpoint attributes
+ * @triggered: callback to trigger when we hit the breakpoint
+ * @tsk: pointer to 'task_struct' of the process to which the address belongs
+ */
+struct perf_event *
+modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr,
+			  perf_callback_t triggered,
+			  struct task_struct *tsk)
+{
+	/*
+	 * FIXME: do it without unregistering
+	 * - We don't want to lose our slot
+	 * - If the new bp is incorrect, don't lose the older one
+	 */
+	unregister_hw_breakpoint(bp);
+
+	return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered);
+}
+EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);
+
+/**
+ * unregister_hw_breakpoint - unregister a user-space hardware breakpoint
+ * @bp: the breakpoint structure to unregister
+ */
+void unregister_hw_breakpoint(struct perf_event *bp)
+{
+	if (!bp)
+		return;
+	perf_event_release_kernel(bp);
+}
+EXPORT_SYMBOL_GPL(unregister_hw_breakpoint);
+
+/**
+ * register_wide_hw_breakpoint - register a wide breakpoint in the kernel
+ * @attr: breakpoint attributes
+ * @triggered: callback to trigger when we hit the breakpoint
+ *
+ * @return a set of per_cpu pointers to perf events
+ */
+struct perf_event **
+register_wide_hw_breakpoint(struct perf_event_attr *attr,
+			    perf_callback_t triggered)
+{
+	struct perf_event **cpu_events, **pevent, *bp;
+	long err;
+	int cpu;
+
+	cpu_events = alloc_percpu(typeof(*cpu_events));
+	if (!cpu_events)
+		return ERR_PTR(-ENOMEM);
+
+	for_each_possible_cpu(cpu) {
+		pevent = per_cpu_ptr(cpu_events, cpu);
+		bp = perf_event_create_kernel_counter(attr, cpu, -1, triggered);
+
+		*pevent = bp;
+
+		if (IS_ERR(bp)) {
+			err = PTR_ERR(bp);
+			goto fail;
+		}
+	}
+
+	return cpu_events;
+
+fail:
+	for_each_possible_cpu(cpu) {
+		pevent = per_cpu_ptr(cpu_events, cpu);
+		if (IS_ERR(*pevent))
+			break;
+		unregister_hw_breakpoint(*pevent);
+	}
+	free_percpu(cpu_events);
+	/* return the error if any */
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint);
+
+/**
+ * unregister_wide_hw_breakpoint - unregister a wide breakpoint in the kernel
+ * @cpu_events: the per cpu set of events to unregister
+ */
+void unregister_wide_hw_breakpoint(struct perf_event **cpu_events)
+{
+	int cpu;
+	struct perf_event **pevent;
+
+	for_each_possible_cpu(cpu) {
+		pevent = per_cpu_ptr(cpu_events, cpu);
+		unregister_hw_breakpoint(*pevent);
+	}
+	free_percpu(cpu_events);
+}
+EXPORT_SYMBOL_GPL(unregister_wide_hw_breakpoint);
+
+static struct notifier_block hw_breakpoint_exceptions_nb = {
+	.notifier_call = hw_breakpoint_exceptions_notify,
+	/* we need to be notified first */
+	.priority = 0x7fffffff
+};
+
+static int __init init_hw_breakpoint(void)
+{
+	return register_die_notifier(&hw_breakpoint_exceptions_nb);
+}
+core_initcall(init_hw_breakpoint);
+
+
+struct pmu perf_ops_bp = {
+	.enable		= arch_install_hw_breakpoint,
+	.disable	= arch_uninstall_hw_breakpoint,
+	.read		= hw_breakpoint_pmu_read,
+	.unthrottle	= hw_breakpoint_pmu_unthrottle
+};
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 8b6b8b697c68..8e5288a8a355 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -181,6 +181,7 @@ unsigned long kallsyms_lookup_name(const char *name)
 	}
 	return module_kallsyms_lookup_name(name);
 }
+EXPORT_SYMBOL_GPL(kallsyms_lookup_name);
 
 int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
 				      unsigned long),
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 1494e85b35f2..e5342a344c43 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -90,6 +90,9 @@ static spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
  */
 static struct kprobe_blackpoint kprobe_blacklist[] = {
 	{"preempt_schedule",},
+	{"native_get_debugreg",},
+	{"irq_entries_start",},
+	{"common_interrupt",},
 	{NULL}    /* Terminator */
 };
 
@@ -673,6 +676,40 @@ static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p)
 	return (kprobe_opcode_t *)(((char *)addr) + p->offset);
 }
 
+/* Check passed kprobe is valid and return kprobe in kprobe_table. */
+static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p)
+{
+	struct kprobe *old_p, *list_p;
+
+	old_p = get_kprobe(p->addr);
+	if (unlikely(!old_p))
+		return NULL;
+
+	if (p != old_p) {
+		list_for_each_entry_rcu(list_p, &old_p->list, list)
+			if (list_p == p)
+			/* kprobe p is a valid probe */
+				goto valid;
+		return NULL;
+	}
+valid:
+	return old_p;
+}
+
+/* Return error if the kprobe is being re-registered */
+static inline int check_kprobe_rereg(struct kprobe *p)
+{
+	int ret = 0;
+	struct kprobe *old_p;
+
+	mutex_lock(&kprobe_mutex);
+	old_p = __get_valid_kprobe(p);
+	if (old_p)
+		ret = -EINVAL;
+	mutex_unlock(&kprobe_mutex);
+	return ret;
+}
+
 int __kprobes register_kprobe(struct kprobe *p)
 {
 	int ret = 0;
@@ -685,6 +722,10 @@ int __kprobes register_kprobe(struct kprobe *p)
 		return -EINVAL;
 	p->addr = addr;
 
+	ret = check_kprobe_rereg(p);
+	if (ret)
+		return ret;
+
 	preempt_disable();
 	if (!kernel_text_address((unsigned long) p->addr) ||
 	    in_kprobes_functions((unsigned long) p->addr)) {
@@ -754,26 +795,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(register_kprobe);
 
-/* Check passed kprobe is valid and return kprobe in kprobe_table. */
-static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p)
-{
-	struct kprobe *old_p, *list_p;
-
-	old_p = get_kprobe(p->addr);
-	if (unlikely(!old_p))
-		return NULL;
-
-	if (p != old_p) {
-		list_for_each_entry_rcu(list_p, &old_p->list, list)
-			if (list_p == p)
-			/* kprobe p is a valid probe */
-				goto valid;
-		return NULL;
-	}
-valid:
-	return old_p;
-}
-
 /*
  * Unregister a kprobe without a scheduler synchronization.
  */
@@ -1141,6 +1162,13 @@ static void __kprobes kill_kprobe(struct kprobe *p)
 	arch_remove_kprobe(p);
 }
 
+void __kprobes dump_kprobe(struct kprobe *kp)
+{
+	printk(KERN_WARNING "Dumping kprobe:\n");
+	printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n",
+	       kp->symbol_name, kp->addr, kp->offset);
+}
+
 /* Module notifier call back, checking kprobes on the module */
 static int __kprobes kprobes_module_callback(struct notifier_block *nb,
 					     unsigned long val, void *data)
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 9af56723c096..f5dcd36d3151 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -49,7 +49,7 @@
 #include "lockdep_internals.h"
 
 #define CREATE_TRACE_POINTS
-#include <trace/events/lockdep.h>
+#include <trace/events/lock.h>
 
 #ifdef CONFIG_PROVE_LOCKING
 int prove_locking = 1;
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 61d5aa5eced3..acd24e7643eb 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -558,7 +558,7 @@ EXPORT_SYMBOL(unregister_reboot_notifier);
 
 static ATOMIC_NOTIFIER_HEAD(die_chain);
 
-int notrace notify_die(enum die_val val, const char *str,
+int notrace __kprobes notify_die(enum die_val val, const char *str,
 	       struct pt_regs *regs, long err, int trap, int sig)
 {
 	struct die_args args = {
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 7f29643c8985..6b7ddba1dd64 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -28,6 +28,8 @@
 #include <linux/anon_inodes.h>
 #include <linux/kernel_stat.h>
 #include <linux/perf_event.h>
+#include <linux/ftrace_event.h>
+#include <linux/hw_breakpoint.h>
 
 #include <asm/irq_regs.h>
 
@@ -244,6 +246,49 @@ static void perf_unpin_context(struct perf_event_context *ctx)
 	put_ctx(ctx);
 }
 
+static inline u64 perf_clock(void)
+{
+	return cpu_clock(smp_processor_id());
+}
+
+/*
+ * Update the record of the current time in a context.
+ */
+static void update_context_time(struct perf_event_context *ctx)
+{
+	u64 now = perf_clock();
+
+	ctx->time += now - ctx->timestamp;
+	ctx->timestamp = now;
+}
+
+/*
+ * Update the total_time_enabled and total_time_running fields for a event.
+ */
+static void update_event_times(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+	u64 run_end;
+
+	if (event->state < PERF_EVENT_STATE_INACTIVE ||
+	    event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
+		return;
+
+	if (ctx->is_active)
+		run_end = ctx->time;
+	else
+		run_end = event->tstamp_stopped;
+
+	event->total_time_enabled = run_end - event->tstamp_enabled;
+
+	if (event->state == PERF_EVENT_STATE_INACTIVE)
+		run_end = event->tstamp_stopped;
+	else
+		run_end = ctx->time;
+
+	event->total_time_running = run_end - event->tstamp_running;
+}
+
 /*
  * Add a event from the lists for its context.
  * Must be called with ctx->mutex and ctx->lock held.
@@ -292,6 +337,18 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 	if (event->group_leader != event)
 		event->group_leader->nr_siblings--;
 
+	update_event_times(event);
+
+	/*
+	 * If event was in error state, then keep it
+	 * that way, otherwise bogus counts will be
+	 * returned on read(). The only way to get out
+	 * of error state is by explicit re-enabling
+	 * of the event
+	 */
+	if (event->state > PERF_EVENT_STATE_OFF)
+		event->state = PERF_EVENT_STATE_OFF;
+
 	/*
 	 * If this was a group event with sibling events then
 	 * upgrade the siblings to singleton events by adding them
@@ -445,50 +502,11 @@ retry:
 	 * can remove the event safely, if the call above did not
 	 * succeed.
 	 */
-	if (!list_empty(&event->group_entry)) {
+	if (!list_empty(&event->group_entry))
 		list_del_event(event, ctx);
-	}
 	spin_unlock_irq(&ctx->lock);
 }
 
-static inline u64 perf_clock(void)
-{
-	return cpu_clock(smp_processor_id());
-}
-
-/*
- * Update the record of the current time in a context.
- */
-static void update_context_time(struct perf_event_context *ctx)
-{
-	u64 now = perf_clock();
-
-	ctx->time += now - ctx->timestamp;
-	ctx->timestamp = now;
-}
-
-/*
- * Update the total_time_enabled and total_time_running fields for a event.
- */
-static void update_event_times(struct perf_event *event)
-{
-	struct perf_event_context *ctx = event->ctx;
-	u64 run_end;
-
-	if (event->state < PERF_EVENT_STATE_INACTIVE ||
-	    event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
-		return;
-
-	event->total_time_enabled = ctx->time - event->tstamp_enabled;
-
-	if (event->state == PERF_EVENT_STATE_INACTIVE)
-		run_end = event->tstamp_stopped;
-	else
-		run_end = ctx->time;
-
-	event->total_time_running = run_end - event->tstamp_running;
-}
-
 /*
  * Update total_time_enabled and total_time_running for all events in a group.
  */
@@ -1031,10 +1049,10 @@ void __perf_event_sched_out(struct perf_event_context *ctx,
 	update_context_time(ctx);
 
 	perf_disable();
-	if (ctx->nr_active)
+	if (ctx->nr_active) {
 		list_for_each_entry(event, &ctx->group_list, group_entry)
 			group_sched_out(event, cpuctx, ctx);
-
+	}
 	perf_enable();
  out:
 	spin_unlock(&ctx->lock);
@@ -1059,8 +1077,6 @@ static int context_equiv(struct perf_event_context *ctx1,
 		&& !ctx1->pin_count && !ctx2->pin_count;
 }
 
-static void __perf_event_read(void *event);
-
 static void __perf_event_sync_stat(struct perf_event *event,
 				     struct perf_event *next_event)
 {
@@ -1078,8 +1094,8 @@ static void __perf_event_sync_stat(struct perf_event *event,
 	 */
 	switch (event->state) {
 	case PERF_EVENT_STATE_ACTIVE:
-		__perf_event_read(event);
-		break;
+		event->pmu->read(event);
+		/* fall-through */
 
 	case PERF_EVENT_STATE_INACTIVE:
 		update_event_times(event);
@@ -1118,6 +1134,8 @@ static void perf_event_sync_stat(struct perf_event_context *ctx,
 	if (!ctx->nr_stat)
 		return;
 
+	update_context_time(ctx);
+
 	event = list_first_entry(&ctx->event_list,
 				   struct perf_event, event_entry);
 
@@ -1161,8 +1179,6 @@ void perf_event_task_sched_out(struct task_struct *task,
 	if (likely(!ctx || !cpuctx->task_ctx))
 		return;
 
-	update_context_time(ctx);
-
 	rcu_read_lock();
 	parent = rcu_dereference(ctx->parent_ctx);
 	next_ctx = next->perf_event_ctxp;
@@ -1515,7 +1531,6 @@ static void __perf_event_read(void *info)
 	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
-	unsigned long flags;
 
 	/*
 	 * If this is a task context, we need to check whether it is
@@ -1527,12 +1542,12 @@ static void __perf_event_read(void *info)
 	if (ctx->task && cpuctx->task_ctx != ctx)
 		return;
 
-	local_irq_save(flags);
-	if (ctx->is_active)
-		update_context_time(ctx);
-	event->pmu->read(event);
+	spin_lock(&ctx->lock);
+	update_context_time(ctx);
 	update_event_times(event);
-	local_irq_restore(flags);
+	spin_unlock(&ctx->lock);
+
+	event->pmu->read(event);
 }
 
 static u64 perf_event_read(struct perf_event *event)
@@ -1545,7 +1560,13 @@ static u64 perf_event_read(struct perf_event *event)
 		smp_call_function_single(event->oncpu,
 					 __perf_event_read, event, 1);
 	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
+		struct perf_event_context *ctx = event->ctx;
+		unsigned long flags;
+
+		spin_lock_irqsave(&ctx->lock, flags);
+		update_context_time(ctx);
 		update_event_times(event);
+		spin_unlock_irqrestore(&ctx->lock, flags);
 	}
 
 	return atomic64_read(&event->count);
@@ -1658,6 +1679,8 @@ static struct perf_event_context *find_get_context(pid_t pid, int cpu)
 	return ERR_PTR(err);
 }
 
+static void perf_event_free_filter(struct perf_event *event);
+
 static void free_event_rcu(struct rcu_head *head)
 {
 	struct perf_event *event;
@@ -1665,6 +1688,7 @@ static void free_event_rcu(struct rcu_head *head)
 	event = container_of(head, struct perf_event, rcu_head);
 	if (event->ns)
 		put_pid_ns(event->ns);
+	perf_event_free_filter(event);
 	kfree(event);
 }
 
@@ -1696,16 +1720,10 @@ static void free_event(struct perf_event *event)
 	call_rcu(&event->rcu_head, free_event_rcu);
 }
 
-/*
- * Called when the last reference to the file is gone.
- */
-static int perf_release(struct inode *inode, struct file *file)
+int perf_event_release_kernel(struct perf_event *event)
 {
-	struct perf_event *event = file->private_data;
 	struct perf_event_context *ctx = event->ctx;
 
-	file->private_data = NULL;
-
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);
 	perf_event_remove_from_context(event);
@@ -1720,6 +1738,19 @@ static int perf_release(struct inode *inode, struct file *file)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(perf_event_release_kernel);
+
+/*
+ * Called when the last reference to the file is gone.
+ */
+static int perf_release(struct inode *inode, struct file *file)
+{
+	struct perf_event *event = file->private_data;
+
+	file->private_data = NULL;
+
+	return perf_event_release_kernel(event);
+}
 
 static int perf_event_read_size(struct perf_event *event)
 {
@@ -1746,91 +1777,94 @@ static int perf_event_read_size(struct perf_event *event)
 	return size;
 }
 
-static u64 perf_event_read_value(struct perf_event *event)
+u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
 {
 	struct perf_event *child;
 	u64 total = 0;
 
+	*enabled = 0;
+	*running = 0;
+
+	mutex_lock(&event->child_mutex);
 	total += perf_event_read(event);
-	list_for_each_entry(child, &event->child_list, child_list)
+	*enabled += event->total_time_enabled +
+			atomic64_read(&event->child_total_time_enabled);
+	*running += event->total_time_running +
+			atomic64_read(&event->child_total_time_running);
+
+	list_for_each_entry(child, &event->child_list, child_list) {
 		total += perf_event_read(child);
+		*enabled += child->total_time_enabled;
+		*running += child->total_time_running;
+	}
+	mutex_unlock(&event->child_mutex);
 
 	return total;
 }
-
-static int perf_event_read_entry(struct perf_event *event,
-				   u64 read_format, char __user *buf)
-{
-	int n = 0, count = 0;
-	u64 values[2];
-
-	values[n++] = perf_event_read_value(event);
-	if (read_format & PERF_FORMAT_ID)
-		values[n++] = primary_event_id(event);
-
-	count = n * sizeof(u64);
-
-	if (copy_to_user(buf, values, count))
-		return -EFAULT;
-
-	return count;
-}
+EXPORT_SYMBOL_GPL(perf_event_read_value);
 
 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, err = -EFAULT;
-	u64 values[3];
+	int n = 0, size = 0, ret = -EFAULT;
+	struct perf_event_context *ctx = leader->ctx;
+	u64 values[5];
+	u64 count, enabled, running;
+
+	mutex_lock(&ctx->mutex);
+	count = perf_event_read_value(leader, &enabled, &running);