Merge remote branch 'tip/auto-latest'

Conflicts:
	arch/x86/kernel/kgdb.c
	kernel/irq/chip.c
	scripts/recordmcount.pl

56 files changed, 5474 insertions, 1237 deletions

diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
new file mode 100644
index 000000000000..d1f86db71451
--- /dev/null
+++ b/kernel/Kconfig.locks
@@ -0,0 +1,199 @@
+#
+# The ARCH_INLINE foo is necessary because select ignores "depends on"
+#
+config ARCH_INLINE_SPIN_TRYLOCK
+	bool
+
+config ARCH_INLINE_SPIN_TRYLOCK_BH
+	bool
+
+config ARCH_INLINE_SPIN_LOCK
+	bool
+
+config ARCH_INLINE_SPIN_LOCK_BH
+	bool
+
+config ARCH_INLINE_SPIN_LOCK_IRQ
+	bool
+
+config ARCH_INLINE_SPIN_LOCK_IRQSAVE
+	bool
+
+config ARCH_INLINE_SPIN_UNLOCK
+	bool
+
+config ARCH_INLINE_SPIN_UNLOCK_BH
+	bool
+
+config ARCH_INLINE_SPIN_UNLOCK_IRQ
+	bool
+
+config ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE
+	bool
+
+
+config ARCH_INLINE_READ_TRYLOCK
+	bool
+
+config ARCH_INLINE_READ_LOCK
+	bool
+
+config ARCH_INLINE_READ_LOCK_BH
+	bool
+
+config ARCH_INLINE_READ_LOCK_IRQ
+	bool
+
+config ARCH_INLINE_READ_LOCK_IRQSAVE
+	bool
+
+config ARCH_INLINE_READ_UNLOCK
+	bool
+
+config ARCH_INLINE_READ_UNLOCK_BH
+	bool
+
+config ARCH_INLINE_READ_UNLOCK_IRQ
+	bool
+
+config ARCH_INLINE_READ_UNLOCK_IRQRESTORE
+	bool
+
+
+config ARCH_INLINE_WRITE_TRYLOCK
+	bool
+
+config ARCH_INLINE_WRITE_LOCK
+	bool
+
+config ARCH_INLINE_WRITE_LOCK_BH
+	bool
+
+config ARCH_INLINE_WRITE_LOCK_IRQ
+	bool
+
+config ARCH_INLINE_WRITE_LOCK_IRQSAVE
+	bool
+
+config ARCH_INLINE_WRITE_UNLOCK
+	bool
+
+config ARCH_INLINE_WRITE_UNLOCK_BH
+	bool
+
+config ARCH_INLINE_WRITE_UNLOCK_IRQ
+	bool
+
+config ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
+	bool
+
+#
+# lock_* functions are inlined when:
+#   - DEBUG_SPINLOCK=n and GENERIC_LOCKBREAK=n and ARCH_INLINE_*LOCK=y
+#
+# trylock_* functions are inlined when:
+#   - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
+#
+# unlock and unlock_irq functions are inlined when:
+#   - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
+#  or
+#   - DEBUG_SPINLOCK=n and PREEMPT=n
+#
+# unlock_bh and unlock_irqrestore functions are inlined when:
+#   - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
+#
+
+config INLINE_SPIN_TRYLOCK
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_TRYLOCK
+
+config INLINE_SPIN_TRYLOCK_BH
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_TRYLOCK_BH
+
+config INLINE_SPIN_LOCK
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK
+
+config INLINE_SPIN_LOCK_BH
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_SPIN_LOCK_BH
+
+config INLINE_SPIN_LOCK_IRQ
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_SPIN_LOCK_IRQ
+
+config INLINE_SPIN_LOCK_IRQSAVE
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_SPIN_LOCK_IRQSAVE
+
+config INLINE_SPIN_UNLOCK
+	def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK)
+
+config INLINE_SPIN_UNLOCK_BH
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_BH
+
+config INLINE_SPIN_UNLOCK_IRQ
+	def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK_BH)
+
+config INLINE_SPIN_UNLOCK_IRQRESTORE
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE
+
+
+config INLINE_READ_TRYLOCK
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_TRYLOCK
+
+config INLINE_READ_LOCK
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK
+
+config INLINE_READ_LOCK_BH
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_READ_LOCK_BH
+
+config INLINE_READ_LOCK_IRQ
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_READ_LOCK_IRQ
+
+config INLINE_READ_LOCK_IRQSAVE
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_READ_LOCK_IRQSAVE
+
+config INLINE_READ_UNLOCK
+	def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_READ_UNLOCK)
+
+config INLINE_READ_UNLOCK_BH
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_UNLOCK_BH
+
+config INLINE_READ_UNLOCK_IRQ
+	def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_READ_UNLOCK_BH)
+
+config INLINE_READ_UNLOCK_IRQRESTORE
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_UNLOCK_IRQRESTORE
+
+
+config INLINE_WRITE_TRYLOCK
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_TRYLOCK
+
+config INLINE_WRITE_LOCK
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK
+
+config INLINE_WRITE_LOCK_BH
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_WRITE_LOCK_BH
+
+config INLINE_WRITE_LOCK_IRQ
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_WRITE_LOCK_IRQ
+
+config INLINE_WRITE_LOCK_IRQSAVE
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_WRITE_LOCK_IRQSAVE
+
+config INLINE_WRITE_UNLOCK
+	def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_WRITE_UNLOCK)
+
+config INLINE_WRITE_UNLOCK_BH
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_BH
+
+config INLINE_WRITE_UNLOCK_IRQ
+	def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_WRITE_UNLOCK_BH)
+
+config INLINE_WRITE_UNLOCK_IRQRESTORE
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
diff --git a/kernel/Makefile b/kernel/Makefile
index 1620454b8c52..e27e8acabb70 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-$(CONFIG_FREEZER) += freezer.o
@@ -83,6 +84,7 @@ obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_TREE_RCU) += rcutree.o
 obj-$(CONFIG_TREE_PREEMPT_RCU) += rcutree.o
 obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o
+obj-$(CONFIG_TINY_RCU) += rcutiny.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
@@ -95,6 +97,7 @@ obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_SLOW_WORK) += slow-work.o
+obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
 obj-$(CONFIG_PERF_EVENTS) += perf_event.o
 obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index b5cb469d2545..3cf2183b472d 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -537,8 +537,7 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c)
  *	element of the partition (one sched domain) to be passed to
  *	partition_sched_domains().
  */
-/* FIXME: see the FIXME in partition_sched_domains() */
-static int generate_sched_domains(struct cpumask **domains,
+static int generate_sched_domains(cpumask_var_t **domains,
 			struct sched_domain_attr **attributes)
 {
 	LIST_HEAD(q);		/* queue of cpusets to be scanned */
@@ -546,7 +545,7 @@ static int generate_sched_domains(struct cpumask **domains,
 	struct cpuset **csa;	/* array of all cpuset ptrs */
 	int csn;		/* how many cpuset ptrs in csa so far */
 	int i, j, k;		/* indices for partition finding loops */
-	struct cpumask *doms;	/* resulting partition; i.e. sched domains */
+	cpumask_var_t *doms;	/* resulting partition; i.e. sched domains */
 	struct sched_domain_attr *dattr;  /* attributes for custom domains */
 	int ndoms = 0;		/* number of sched domains in result */
 	int nslot;		/* next empty doms[] struct cpumask slot */
@@ -557,7 +556,8 @@ static int generate_sched_domains(struct cpumask **domains,
 
 	/* Special case for the 99% of systems with one, full, sched domain */
 	if (is_sched_load_balance(&top_cpuset)) {
-		doms = kmalloc(cpumask_size(), GFP_KERNEL);
+		ndoms = 1;
+		doms = alloc_sched_domains(ndoms);
 		if (!doms)
 			goto done;
 
@@ -566,9 +566,8 @@ static int generate_sched_domains(struct cpumask **domains,
 			*dattr = SD_ATTR_INIT;
 			update_domain_attr_tree(dattr, &top_cpuset);
 		}
-		cpumask_copy(doms, top_cpuset.cpus_allowed);
+		cpumask_copy(doms[0], top_cpuset.cpus_allowed);
 
-		ndoms = 1;
 		goto done;
 	}
 
@@ -636,7 +635,7 @@ restart:
 	 * Now we know how many domains to create.
 	 * Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
 	 */
-	doms = kmalloc(ndoms * cpumask_size(), GFP_KERNEL);
+	doms = alloc_sched_domains(ndoms);
 	if (!doms)
 		goto done;
 
@@ -656,7 +655,7 @@ restart:
 			continue;
 		}
 
-		dp = doms + nslot;
+		dp = doms[nslot];
 
 		if (nslot == ndoms) {
 			static int warnings = 10;
@@ -718,7 +717,7 @@ done:
 static void do_rebuild_sched_domains(struct work_struct *unused)
 {
 	struct sched_domain_attr *attr;
-	struct cpumask *doms;
+	cpumask_var_t *doms;
 	int ndoms;
 
 	get_online_cpus();
@@ -2052,7 +2051,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 				unsigned long phase, void *unused_cpu)
 {
 	struct sched_domain_attr *attr;
-	struct cpumask *doms;
+	cpumask_var_t *doms;
 	int ndoms;
 
 	switch (phase) {
@@ -2537,15 +2536,9 @@ const struct file_operations proc_cpuset_operations = {
 };
 #endif /* CONFIG_PROC_PID_CPUSET */
 
-/* Display task cpus_allowed, mems_allowed in /proc/<pid>/status file. */
+/* Display task mems_allowed in /proc/<pid>/status file. */
 void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task)
 {
-	seq_printf(m, "Cpus_allowed:\t");
-	seq_cpumask(m, &task->cpus_allowed);
-	seq_printf(m, "\n");
-	seq_printf(m, "Cpus_allowed_list:\t");
-	seq_cpumask_list(m, &task->cpus_allowed);
-	seq_printf(m, "\n");
 	seq_printf(m, "Mems_allowed:\t");
 	seq_nodemask(m, &task->mems_allowed);
 	seq_printf(m, "\n");
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/hrtimer.c b/kernel/hrtimer.c
index 3e1c36e7998f..ede527708123 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1238,7 +1238,8 @@ hrtimer_interrupt_hanging(struct clock_event_device *dev,
 	force_clock_reprogram = 1;
 	dev->min_delta_ns = (unsigned long)try_time.tv64 * 3;
 	printk(KERN_WARNING "hrtimer: interrupt too slow, "
-		"forcing clock min delta to %lu ns\n", dev->min_delta_ns);
+	       "forcing clock min delta to %llu ns\n",
+	       (unsigned long long) dev->min_delta_ns);
 }
 /*
  * High resolution timer interrupt
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
new file mode 100644
index 000000000000..06d372fc026d
--- /dev/null
+++ b/kernel/hw_breakpoint.c
@@ -0,0 +1,501 @@
+/*
+ * 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 *task_bp_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;
+
+	task_bp_pinned = per_cpu(task_bp_pinned, cpu);
+	if (enable) {
+		task_bp_pinned[count]++;
+		if (count > 0)
+			task_bp_pinned[count-1]--;
+	} else {
+		task_bp_pinned[count]--;
+		if (count > 0)
+			task_bp_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 a breakpoint bound to a task and a given cpu.
+ * If cpu is -1, the breakpoint is active for the task in every cpu
+ * If the task is -1, the breakpoint is active for every tasks in the given
+ * cpu.
+ */
+static struct perf_event *
+register_user_hw_breakpoint_cpu(unsigned long addr,
+				int len,
+				int type,
+				perf_callback_t triggered,
+				pid_t pid,
+				int cpu,
+				bool active)
+{
+	struct perf_event_attr *attr;
+	struct perf_event *bp;
+
+	attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+	if (!attr)
+		return ERR_PTR(-ENOMEM);
+
+	attr->type = PERF_TYPE_BREAKPOINT;
+	attr->size = sizeof(*attr);
+	attr->bp_addr = addr;
+	attr->bp_len = len;
+	attr->bp_type = type;
+	/*
+	 * Such breakpoints are used by debuggers to trigger signals when
+	 * we hit the excepted memory op. We can't miss such events, they
+	 * must be pinned.
+	 */
+	attr->pinned = 1;
+
+	if (!active)
+		attr->disabled = 1;
+
+	bp = perf_event_create_kernel_counter(attr, cpu, pid, triggered);
+	kfree(attr);
+
+	return bp;
+}
+
+/**
+ * register_user_hw_breakpoint - register a hardware breakpoint for user space
+ * @addr: is the memory address that triggers the breakpoint
+ * @len: the length of the access to the memory (1 byte, 2 bytes etc...)
+ * @type: the type of the access to the memory (read/write/exec)
+ * @triggered: callback to trigger when we hit the breakpoint
+ * @tsk: pointer to 'task_struct' of the process to which the address belongs
+ * @active: should we activate it while registering it
+ *
+ */
+struct perf_event *
+register_user_hw_breakpoint(unsigned long addr,
+			    int len,
+			    int type,
+			    perf_callback_t triggered,
+			    struct task_struct *tsk,
+			    bool active)
+{
+	return register_user_hw_breakpoint_cpu(addr, len, type, triggered,
+					       tsk->pid, -1, active);
+}
+EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
+
+/**
+ * modify_user_hw_breakpoint - modify a user-space hardware breakpoint
+ * @bp: the breakpoint structure to modify
+ * @addr: is the memory address that triggers the breakpoint
+ * @len: the length of the access to the memory (1 byte, 2 bytes etc...)
+ * @type: the type of the access to the memory (read/write/exec)
+ * @triggered: callback to trigger when we hit the breakpoint
+ * @tsk: pointer to 'task_struct' of the process to which the address belongs
+ * @active: should we activate it while registering it
+ */
+struct perf_event *
+modify_user_hw_breakpoint(struct perf_event *bp,
+			  unsigned long addr,
+			  int len,
+			  int type,
+			  perf_callback_t triggered,
+			  struct task_struct *tsk,
+			  bool active)
+{
+	/*
+	 * 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 register_user_hw_breakpoint(addr, len, type, triggered,
+					   tsk, active);
+}
+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);
+
+static struct perf_event *
+register_kernel_hw_breakpoint_cpu(unsigned long addr,
+				  int len,
+				  int type,
+				  perf_callback_t triggered,
+				  int cpu,
+				  bool active)
+{
+	return register_user_hw_breakpoint_cpu(addr, len, type, triggered,
+					       -1, cpu, active);
+}
+
+/**
+ * register_wide_hw_breakpoint - register a wide breakpoint in the kernel
+ * @addr: is the memory address that triggers the breakpoint
+ * @len: the length of the access to the memory (1 byte, 2 bytes etc...)
+ * @type: the type of the access to the memory (read/write/exec)
+ * @triggered: callback to trigger when we hit the breakpoint
+ * @active: should we activate it while registering it
+ *
+ * @return a set of per_cpu pointers to perf events
+ */
+struct perf_event **
+register_wide_hw_breakpoint(unsigned long addr,
+			    int len,
+			    int type,
+			    perf_callback_t triggered,
+			    bool active)
+{
+	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 = register_kernel_hw_breakpoint_cpu(addr, len, type,
+					triggered, cpu, active);
+
+		*pevent = bp;
+
+		if (IS_ERR(bp) || !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) || !*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/irq/chip.c b/kernel/irq/chip.c
index ae70e93b29b5..ba566c261adc 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -166,7 +166,7 @@ int set_irq_data(unsigned int irq, void *data)
 EXPORT_SYMBOL(set_irq_data);
 
 /**
- *	set_irq_msi - set irq type data for an irq
+ *	set_irq_msi - set MSI descriptor data for an irq
  *	@irq:	Interrupt number
  *	@entry:	Pointer to MSI descriptor data
  *
@@ -590,7 +590,7 @@ out_unlock:
 }
 
 /**
- *	handle_percpu_IRQ - Per CPU local irq handler
+ *	handle_percpu_irq - Per CPU local irq handler
  *	@irq:	the interrupt number
  *	@desc:	the interrupt description structure for this irq
  *
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index bde4c667d24d..7305b297d1eb 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1067,7 +1067,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 		kfree(action);
 
 #ifdef CONFIG_DEBUG_SHIRQ
-	if (irqflags & IRQF_SHARED) {
+	if (!retval && (irqflags & IRQF_SHARED)) {
 		/*
 		 * It's a shared IRQ -- the driver ought to be prepared for it
 		 * to happen immediately, so let's make sure....
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 692363dd591f..dfef5b9f3845 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -214,6 +214,8 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 
 	/* create /proc/irq/1234 */
 	desc->dir = proc_mkdir(name, root_irq_dir);
+	if (!desc->dir)
+		return;
 
 #ifdef CONFIG_SMP
 	/* create /proc/irq/<irq>/smp_affinity */
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 7a5894e87f24..e49ea1c5232d 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -104,7 +104,7 @@ static int misrouted_irq(int irq)
 	return ok;
 }
 
-static void poll_all_shared_irqs(void)
+static void poll_spurious_irqs(unsigned long dummy)
 {
 	struct irq_desc *desc;
 	int i;
@@ -125,23 +125,11 @@ static void poll_all_shared_irqs(void)
 		try_one_irq(i, desc);
 		local_irq_enable();
 	}
-}
-
-static void poll_spurious_irqs(unsigned long dummy)
-{
-	poll_all_shared_irqs();
 
 	mod_timer(&poll_spurious_irq_timer,
 		  jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
 }
 
-#ifdef CONFIG_DEBUG_SHIRQ
-void debug_poll_all_shared_irqs(void)
-{
-	poll_all_shared_irqs();
-}
-#endif
-
 /*
  * If 99,900 of the previous 100,000 interrupts have not been handled
  * then assume that the IRQ is stuck in some manner. Drop a diagnostic
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/kgdb.c b/kernel/kgdb.c
index 609cbdef5a71..e2c1469d579a 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -876,7 +876,7 @@ static void gdb_cmd_getregs(struct kgdb_state *ks)
 
 	/*
 	 * All threads that don't have debuggerinfo should be
-	 * in __schedule() sleeping, since all other CPUs
+	 * in schedule() sleeping, since all other CPUs
 	 * are in kgdb_wait, and thus have debuggerinfo.
 	 */
 	if (local_debuggerinfo) {
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 5240d75f4c60..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.
  */
@@ -1014,9 +1035,9 @@ int __kprobes register_kretprobe(struct kretprobe *rp)
 	/* Pre-allocate memory for max kretprobe instances */
 	if (rp->maxactive <= 0) {
 #ifdef CONFIG_PREEMPT
-		rp->maxactive = max(10, 2 * NR_CPUS);
+		rp->maxactive = max(10, 2 * num_possible_cpus());
 #else
-		rp->maxactive = NR_CPUS;
+		rp->maxactive = num_possible_cpus();
 #endif
 	}
 	spin_lock_init(&rp->lock);
@@ -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 7c7da1ea9c27..375fb9712e42 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 +337,9 @@ 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);
+	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 +493,11 @@ 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 +1040,10 @@ 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 +1068,6 @@ 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 +1085,8 @@ 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 +1125,8 @@ 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 +1170,6 @@ 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 +1522,6 @@ 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 +1533,12 @@ 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 +1551,13 @@ 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 +1670,8 @@ 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 +1679,7 @@ 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 +1711,10 @@ 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 +1729,19 @@ 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 +1768,94 @@ 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);
 
 	values[n++] = 1 + leader->nr_siblings;
-	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
-		values[n++] = leader->total_time_enabled +
-			atomic64_read(&leader->child_total_time_enabled);
-	}
-	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
-		values[n++] = leader->total_time_running +
-			atomic64_read(&leader->child_total_time_running);
-	}
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		values[n++] = enabled;
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		values[n++] = running;
+	values[n++] = count;
+	if (read_format & PERF_FORMAT_ID)
+		values[n++] = primary_event_id(leader);
 
 	size = n * sizeof(u64);
 
 	if (copy_to_user(buf, values, size))
-		return -EFAULT;
-
-	err = perf_event_read_entry(leader, read_format, buf + size);
-	if (err < 0)
-		return err;
+		goto unlock;
 
-	size += err;
+	ret = size;
 
 	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
-		err = perf_event_read_entry(sub, read_format,
-				buf + size);
-		if (err < 0)
-			return err;
+		n = 0;
+
+		values[n++] = perf_event_read_value(sub, &enabled, &running);
+		if (read_format & PERF_FORMAT_ID)
+			values[n++] = primary_event_id(sub);
+
+		size = n * sizeof(u64);
+
+		if (copy_to_user(buf + size, values, size)) {
+			ret = -EFAULT;
+			goto unlock;
+		}
 
-		size += err;
+		ret += size;
 	}
+unlock:
+	mutex_unlock(&ctx->mutex);
 
-	return size;
+	return ret;
 }
 
 static int perf_event_read_one(struct perf_event *event,
 				 u64 read_format, char __user *buf)
 {
+	u64 enabled, running;
 	u64 values[4];
 	int n = 0;
 
-	values[n++] = perf_event_read_value(event);
-	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
-		values[n++] = event->total_time_enabled +
-			atomic64_read(&event->child_total_time_enabled);
-	}
-	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
-		values[n++] = event->total_time_running +
-			atomic64_read(&event->child_total_time_running);
-	}
+	values[n++] = perf_event_read_value(event, &enabled, &running);
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		values[n++] = enabled;
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		values[n++] = running;
 	if (read_format & PERF_FORMAT_ID)
 		values[n++] = primary_event_id(event);
 
@@ -1861,12 +1886,10 @@ perf_read_hw(struct perf_event *event, char __user *buf, size_t count)
 		return -ENOSPC;
 
 	WARN_ON_ONCE(event->ctx->parent_ctx);
-	mutex_lock(&event->child_mutex);
 	if (read_format & PERF_FORMAT_GROUP)
 		ret = perf_event_read_group(event, read_format, buf);
 	else
 		ret = perf_event_read_one(event, read_format, buf);
-	mutex_unlock(&event->child_mutex);
 
 	return ret;
 }
@@ -1974,7 +1997,8 @@ unlock:
 	return ret;
 }
 
-int perf_event_set_output(struct perf_event *event, int output_fd);
+static int perf_event_set_output(struct perf_event *event, int output_fd);
+static int perf_event_set_filter(struct perf_event *event, void __user *arg);
 
 static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
@@ -2002,6 +2026,9 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case PERF_EVENT_IOC_SET_OUTPUT:
 		return perf_event_set_output(event, arg);
 
+	case PERF_EVENT_IOC_SET_FILTER:
+		return perf_event_set_filter(event, (void __user *)arg);
+
 	default:
 		return -ENOTTY;
 	}
@@ -2307,7 +2334,7 @@ perf_mmap_data_init(struct perf_event *event, struct perf_mmap_data *data)
 	}
 
 	if (!data->watermark)
-		data->watermark = max_t(long, PAGE_SIZE, max_size / 2);
+		data->watermark = max_size / 2;
 
 
 	rcu_assign_pointer(event->data, data);
@@ -2666,20 +2693,21 @@ static void perf_output_wakeup(struct perf_output_handle *handle)
 static void perf_output_lock(struct perf_output_handle *handle)
 {
 	struct perf_mmap_data *data = handle->data;
-	int cpu;
+	int cur, cpu = get_cpu();
 
 	handle->locked = 0;
 
-	local_irq_save(handle->flags);
-	cpu = smp_processor_id();
-
-	if (in_nmi() && atomic_read(&data->lock) == cpu)
-		return;
+	for (;;) {
+		cur = atomic_cmpxchg(&data->lock, -1, cpu);
+		if (cur == -1) {
+			handle->locked = 1;
+			break;
+		}
+		if (cur == cpu)
+			break;
 
-	while (atomic_cmpxchg(&data->lock, -1, cpu) != -1)
 		cpu_relax();
-
-	handle->locked = 1;
+	}
 }
 
 static void perf_output_unlock(struct perf_output_handle *handle)
@@ -2725,7 +2753,7 @@ again:
 	if (atomic_xchg(&data->wakeup, 0))
 		perf_output_wakeup(handle);
 out:
-	local_irq_restore(handle->flags);
+	put_cpu();
 }
 
 void perf_output_copy(struct perf_output_handle *handle,
@@ -3236,15 +3264,10 @@ static void perf_event_task_ctx(struct perf_event_context *ctx,
 {
 	struct perf_event *event;
 
-	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
-		return;
-
-	rcu_read_lock();
 	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
 		if (perf_event_task_match(event))
 			perf_event_task_output(event, task_event);
 	}
-	rcu_read_unlock();
 }
 
 static void perf_event_task_event(struct perf_task_event *task_event)
@@ -3252,11 +3275,11 @@ static void perf_event_task_event(struct perf_task_event *task_event)
 	struct perf_cpu_context *cpuctx;
 	struct perf_event_context *ctx = task_event->task_ctx;
 
+	rcu_read_lock();
 	cpuctx = &get_cpu_var(perf_cpu_context);
 	perf_event_task_ctx(&cpuctx->ctx, task_event);
 	put_cpu_var(perf_cpu_context);
 
-	rcu_read_lock();
 	if (!ctx)
 		ctx = rcu_dereference(task_event->task->perf_event_ctxp);
 	if (ctx)
@@ -3348,15 +3371,10 @@ static void perf_event_comm_ctx(struct perf_event_context *ctx,
 {
 	struct perf_event *event;
 
-	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
-		return;
-
-	rcu_read_lock();
 	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
 		if (perf_event_comm_match(event))
 			perf_event_comm_output(event, comm_event);
 	}
-	rcu_read_unlock();
 }
 
 static void perf_event_comm_event(struct perf_comm_event *comm_event)
@@ -3367,7 +3385,7 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 	char comm[TASK_COMM_LEN];
 
 	memset(comm, 0, sizeof(comm));
-	strncpy(comm, comm_event->task->comm, sizeof(comm));
+	strlcpy(comm, comm_event->task->comm, sizeof(comm));
 	size = ALIGN(strlen(comm)+1, sizeof(u64));
 
 	comm_event->comm = comm;
@@ -3375,11 +3393,11 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 
 	comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;
 
+	rcu_read_lock();
 	cpuctx = &get_cpu_var(perf_cpu_context);
 	perf_event_comm_ctx(&cpuctx->ctx, comm_event);
 	put_cpu_var(perf_cpu_context);
 
-	rcu_read_lock();
 	/*
 	 * doesn't really matter which of the child contexts the
 	 * events ends up in.
@@ -3472,15 +3490,10 @@ static void perf_event_mmap_ctx(struct perf_event_context *ctx,
 {
 	struct perf_event *event;
 
-	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
-		return;
-
-	rcu_read_lock();
 	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
 		if (perf_event_mmap_match(event, mmap_event))
 			perf_event_mmap_output(event, mmap_event);
 	}
-	rcu_read_unlock();
 }
 
 static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
@@ -3536,11 +3549,11 @@ got_name:
 
 	mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
 
+	rcu_read_lock();
 	cpuctx = &get_cpu_var(perf_cpu_context);
 	perf_event_mmap_ctx(&cpuctx->ctx, mmap_event);
 	put_cpu_var(perf_cpu_context);
 
-	rcu_read_lock();
 	/*
 	 * doesn't really matter which of the child contexts the
 	 * events ends up in.
@@ -3679,7 +3692,11 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
 			perf_event_disable(event);
 	}
 
-	perf_event_output(event, nmi, data, regs);
+	if (event->overflow_handler)
+		event->overflow_handler(event, nmi, data, regs);
+	else
+		perf_event_output(event, nmi, data, regs);
+
 	return ret;
 }
 
@@ -3724,16 +3741,16 @@ again:
 	return nr;
 }
 
-static void perf_swevent_overflow(struct perf_event *event,
+static void perf_swevent_overflow(struct perf_event *event, u64 overflow,
 				    int nmi, struct perf_sample_data *data,
 				    struct pt_regs *regs)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int throttle = 0;
-	u64 overflow;
 
 	data->period = event->hw.last_period;
-	overflow = perf_swevent_set_period(event);
+	if (!overflow)
+		overflow = perf_swevent_set_period(event);
 
 	if (hwc->interrupts == MAX_INTERRUPTS)
 		return;
@@ -3766,14 +3783,19 @@ static void perf_swevent_add(struct perf_event *event, u64 nr,
 
 	atomic64_add(nr, &event->count);
 
+	if (!regs)
+		return;
+
 	if (!hwc->sample_period)
 		return;
 
-	if (!regs)
+	if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq)
+		return perf_swevent_overflow(event, 1, nmi, data, regs);
+
+	if (atomic64_add_negative(nr, &hwc->period_left))
 		return;
 
-	if (!atomic64_add_negative(nr, &hwc->period_left))
-		perf_swevent_overflow(event, nmi, data, regs);
+	perf_swevent_overflow(event, 0, nmi, data, regs);
 }
 
 static int perf_swevent_is_counting(struct perf_event *event)
@@ -3806,25 +3828,44 @@ static int perf_swevent_is_counting(struct perf_event *event)
 	return 1;
 }
 
+static int perf_tp_event_match(struct perf_event *event,
+				struct perf_sample_data *data);
+
+static int perf_exclude_event(struct perf_event *event,
+			      struct pt_regs *regs)
+{
+	if (regs) {
+		if (event->attr.exclude_user && user_mode(regs))
+			return 1;
+
+		if (event->attr.exclude_kernel && !user_mode(regs))
+			return 1;
+	}
+
+	return 0;
+}
+
 static int perf_swevent_match(struct perf_event *event,
 				enum perf_type_id type,
-				u32 event_id, struct pt_regs *regs)
+				u32 event_id,
+				struct perf_sample_data *data,
+				struct pt_regs *regs)
 {
 	if (!perf_swevent_is_counting(event))
 		return 0;
 
 	if (event->attr.type != type)
 		return 0;
+
 	if (event->attr.config != event_id)
 		return 0;
 
-	if (regs) {
-		if (event->attr.exclude_user && user_mode(regs))
-			return 0;
+	if (perf_exclude_event(event, regs))
+		return 0;
 
-		if (event->attr.exclude_kernel && !user_mode(regs))
-			return 0;
-	}
+	if (event->attr.type == PERF_TYPE_TRACEPOINT &&
+	    !perf_tp_event_match(event, data))
+		return 0;
 
 	return 1;
 }
@@ -3837,49 +3878,59 @@ static void perf_swevent_ctx_event(struct perf_event_context *ctx,
 {
 	struct perf_event *event;
 
-	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
-		return;
-
-	rcu_read_lock();
 	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
-		if (perf_swevent_match(event, type, event_id, regs))
+		if (perf_swevent_match(event, type, event_id, data, regs))
 			perf_swevent_add(event, nr, nmi, data, regs);
 	}
-	rcu_read_unlock();
 }
 
-static int *perf_swevent_recursion_context(struct perf_cpu_context *cpuctx)
+int perf_swevent_get_recursion_context(void)
 {
+	struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context);
+	int rctx;
+
 	if (in_nmi())
-		return &cpuctx->recursion[3];
+		rctx = 3;
+	else if (in_irq())
+		rctx = 2;
+	else if (in_softirq())
+		rctx = 1;
+	else
+		rctx = 0;
+
+	if (cpuctx->recursion[rctx]) {
+		put_cpu_var(perf_cpu_context);
+		return -1;
+	}
 
-	if (in_irq())
-		return &cpuctx->recursion[2];
+	cpuctx->recursion[rctx]++;
+	barrier();
 
-	if (in_softirq())
-		return &cpuctx->recursion[1];
+	return rctx;
+}
+EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context);
 
-	return &cpuctx->recursion[0];
+void perf_swevent_put_recursion_context(int rctx)
+{
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+	barrier();
+	cpuctx->recursion[rctx]++;
+	put_cpu_var(perf_cpu_context);
 }
+EXPORT_SYMBOL_GPL(perf_swevent_put_recursion_context);
 
 static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
 				    u64 nr, int nmi,
 				    struct perf_sample_data *data,
 				    struct pt_regs *regs)
 {
-	struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context);
-	int *recursion = perf_swevent_recursion_context(cpuctx);
+	struct perf_cpu_context *cpuctx;
 	struct perf_event_context *ctx;
 
-	if (*recursion)
-		goto out;
-
-	(*recursion)++;
-	barrier();
-
+	cpuctx = &__get_cpu_var(perf_cpu_context);
+	rcu_read_lock();
 	perf_swevent_ctx_event(&cpuctx->ctx, type, event_id,
 				 nr, nmi, data, regs);
-	rcu_read_lock();
 	/*
 	 * doesn't really matter which of the child contexts the
 	 * events ends up in.
@@ -3888,23 +3939,24 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
 	if (ctx)
 		perf_swevent_ctx_event(ctx, type, event_id, nr, nmi, data, regs);
 	rcu_read_unlock();
-
-	barrier();
-	(*recursion)--;
-
-out:
-	put_cpu_var(perf_cpu_context);
 }
 
 void __perf_sw_event(u32 event_id, u64 nr, int nmi,
 			    struct pt_regs *regs, u64 addr)
 {
-	struct perf_sample_data data = {
-		.addr = addr,
-	};
+	struct perf_sample_data data;
+	int rctx;
 
-	do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi,
-				&data, regs);
+	rctx = perf_swevent_get_recursion_context();
+	if (rctx < 0)
+		return;
+
+	data.addr = addr;
+	data.raw  = NULL;
+
+	do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, &data, regs);
+
+	perf_swevent_put_recursion_context(rctx);
 }
 
 static void perf_swevent_read(struct perf_event *event)
@@ -4108,6 +4160,7 @@ static const struct pmu perf_ops_task_clock = {
 };
 
 #ifdef CONFIG_EVENT_PROFILE
+
 void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
 			  int entry_size)
 {
@@ -4126,13 +4179,21 @@ void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
 	if (!regs)
 		regs = task_pt_regs(current);
 
+	/* Trace events already protected against recursion */
 	do_perf_sw_event(PERF_TYPE_TRACEPOINT, event_id, count, 1,
 				&data, regs);
 }
 EXPORT_SYMBOL_GPL(perf_tp_event);
 
-extern int ftrace_profile_enable(int);
-extern void ftrace_profile_disable(int);
+static int perf_tp_event_match(struct perf_event *event,
+				struct perf_sample_data *data)
+{
+	void *record = data->raw->data;
+
+	if (likely(!event->filter) || filter_match_preds(event->filter, record))
+		return 1;
+	return 0;
+}
 
 static void tp_perf_event_destroy(struct perf_event *event)
 {
@@ -4157,11 +4218,103 @@ static const struct pmu *tp_perf_event_init(struct perf_event *event)
 
 	return &perf_ops_generic;
 }
+
+static int perf_event_set_filter(struct perf_event *event, void __user *arg)
+{
+	char *filter_str;
+	int ret;
+
+	if (event->attr.type != PERF_TYPE_TRACEPOINT)
+		return -EINVAL;
+
+	filter_str = strndup_user(arg, PAGE_SIZE);
+	if (IS_ERR(filter_str))
+		return PTR_ERR(filter_str);
+
+	ret = ftrace_profile_set_filter(event, event->attr.config, filter_str);
+
+	kfree(filter_str);
+	return ret;
+}
+
+static void perf_event_free_filter(struct perf_event *event)
+{
+	ftrace_profile_free_filter(event);
+}
+
 #else
+
+static int perf_tp_event_match(struct perf_event *event,
+				struct perf_sample_data *data)
+{
+	return 1;
+}
+
 static const struct pmu *tp_perf_event_init(struct perf_event *event)
 {
 	return NULL;
 }
+
+static int perf_event_set_filter(struct perf_event *event, void __user *arg)
+{
+	return -ENOENT;
+}
+
+static void perf_event_free_filter(struct perf_event *event)
+{
+}
+
+#endif /* CONFIG_EVENT_PROFILE */
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+static void bp_perf_event_destroy(struct perf_event *event)
+{
+	release_bp_slot(event);
+}
+
+static const struct pmu *bp_perf_event_init(struct perf_event *bp)
+{
+	int err;
+	/*
+	 * The breakpoint is already filled if we haven't created the counter
+	 * through perf syscall
+	 * FIXME: manage to get trigerred to NULL if it comes from syscalls
+	 */
+	if (!bp->callback)
+		err = register_perf_hw_breakpoint(bp);
+	else
+		err = __register_perf_hw_breakpoint(bp);
+	if (err)
+		return ERR_PTR(err);
+
+	bp->destroy = bp_perf_event_destroy;
+
+	return &perf_ops_bp;
+}
+
+void perf_bp_event(struct perf_event *bp, void *data)
+{
+	struct perf_sample_data sample;
+	struct pt_regs *regs = data;
+
+	sample.addr = bp->attr.bp_addr;
+
+	if (!perf_exclude_event(bp, regs))
+		perf_swevent_add(bp, 1, 1, &sample, regs);
+}
+#else
+static void bp_perf_event_destroy(struct perf_event *event)
+{
+}
+
+static const struct pmu *bp_perf_event_init(struct perf_event *bp)
+{
+	return NULL;
+}
+
+void perf_bp_event(struct perf_event *bp, void *regs)
+{
+}
 #endif
 
 atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
@@ -4208,6 +4361,8 @@ static const struct pmu *sw_perf_event_init(struct perf_event *event)
 	case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
 	case PERF_COUNT_SW_CONTEXT_SWITCHES:
 	case PERF_COUNT_SW_CPU_MIGRATIONS:
+	case PERF_COUNT_SW_ALIGNMENT_FAULTS:
+	case PERF_COUNT_SW_EMULATION_FAULTS:
 		if (!event->parent) {
 			atomic_inc(&perf_swevent_enabled[event_id]);
 			event->destroy = sw_perf_event_destroy;
@@ -4228,6 +4383,7 @@ perf_event_alloc(struct perf_event_attr *attr,
 		   struct perf_event_context *ctx,
 		   struct perf_event *group_leader,
 		   struct perf_event *parent_event,
+		   perf_callback_t callback,
 		   gfp_t gfpflags)
 {
 	const struct pmu *pmu;
@@ -4270,6 +4426,11 @@ perf_event_alloc(struct perf_event_attr *attr,
 
 	event->state		= PERF_EVENT_STATE_INACTIVE;
 
+	if (!callback && parent_event)
+		callback = parent_event->callback;
+	
+	event->callback	= callback;
+
 	if (attr->disabled)
 		event->state = PERF_EVENT_STATE_OFF;
 
@@ -4304,6 +4465,11 @@ perf_event_alloc(struct perf_event_attr *attr,
 		pmu = tp_perf_event_init(event);
 		break;
 
+	case PERF_TYPE_BREAKPOINT:
+		pmu = bp_perf_event_init(event);
+		break;
+
+
 	default:
 		break;
 	}
@@ -4416,7 +4582,7 @@ err_size:
 	goto out;
 }
 
-int perf_event_set_output(struct perf_event *event, int output_fd)
+static int perf_event_set_output(struct perf_event *event, int output_fd)
 {
 	struct perf_event *output_event = NULL;
 	struct file *output_file = NULL;
@@ -4546,7 +4712,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	}
 
 	event = perf_event_alloc(&attr, cpu, ctx, group_leader,
-				     NULL, GFP_KERNEL);
+				     NULL, NULL, GFP_KERNEL);
 	err = PTR_ERR(event);
 	if (IS_ERR(event))
 		goto err_put_context;
@@ -4594,6 +4760,58 @@ err_put_context:
 	return err;
 }
 
+/**
+ * perf_event_create_kernel_counter
+ *
+ * @attr: attributes of the counter to create
+ * @cpu: cpu in which the counter is bound
+ * @pid: task to profile
+ */
+struct perf_event *
+perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
+				 pid_t pid, perf_callback_t callback)
+{
+	struct perf_event *event;
+	struct perf_event_context *ctx;
+	int err;
+
+	/*
+	 * Get the target context (task or percpu):
+	 */
+
+	ctx = find_get_context(pid, cpu);
+	if (IS_ERR(ctx))
+		return NULL;
+
+	event = perf_event_alloc(attr, cpu, ctx, NULL,
+				     NULL, callback, GFP_KERNEL);
+	err = PTR_ERR(event);
+	if (IS_ERR(event))
+		goto err_put_context;
+
+	event->filp = NULL;
+	WARN_ON_ONCE(ctx->parent_ctx);
+	mutex_lock(&ctx->mutex);
+	perf_install_in_context(ctx, event, cpu);
+	++ctx->generation;
+	mutex_unlock(&ctx->mutex);
+
+	event->owner = current;
+	get_task_struct(current);
+	mutex_lock(&current->perf_event_mutex);
+	list_add_tail(&event->owner_entry, &current->perf_event_list);
+	mutex_unlock(&current->perf_event_mutex);
+
+	return event;
+
+err_put_context:
+	if (err < 0)
+		put_ctx(ctx);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter);
+
 /*
  * inherit a event from parent task to child task:
  */
@@ -4619,7 +4837,7 @@ inherit_event(struct perf_event *parent_event,
 	child_event = perf_event_alloc(&parent_event->attr,
 					   parent_event->cpu, child_ctx,
 					   group_leader, parent_event,
-					   GFP_KERNEL);
+					   NULL, GFP_KERNEL);
 	if (IS_ERR(child_event))
 		return child_event;
 	get_ctx(child_ctx);
@@ -4637,6 +4855,8 @@ inherit_event(struct perf_event *parent_event,
 	if (parent_event->attr.freq)
 		child_event->hw.sample_period = parent_event->hw.sample_period;
 
+	child_event->overflow_handler = parent_event->overflow_handler;
+
 	/*
 	 * Link it up in the child's context:
 	 */
@@ -4726,7 +4946,6 @@ __perf_event_exit_task(struct perf_event *child_event,
 {
 	struct perf_event *parent_event;
 
-	update_event_times(child_event);
 	perf_event_remove_from_context(child_event);
 
 	parent_event = child_event->parent;
@@ -4778,6 +4997,7 @@ void perf_event_exit_task(struct task_struct *child)
 	 * the events from it.
 	 */
 	unclone_ctx(child_ctx);
+	update_context_time(child_ctx);
 	spin_unlock_irqrestore(&child_ctx->lock, flags);
 
 	/*
diff --git a/kernel/printk.c b/kernel/printk.c
index f38b07f78a4e..b5ac4d99c667 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -33,6 +33,7 @@
 #include <linux/bootmem.h>
 #include <linux/syscalls.h>
 #include <linux/kexec.h>
+#include <linux/ratelimit.h>
 
 #include <asm/uaccess.h>
 
@@ -1376,11 +1377,11 @@ late_initcall(disable_boot_consoles);
  */
 DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10);
 
-int printk_ratelimit(void)
+int __printk_ratelimit(const char *func)
 {
-	return __ratelimit(&printk_ratelimit_state);
+	return ___ratelimit(&printk_ratelimit_state, func);
 }
-EXPORT_SYMBOL(printk_ratelimit);
+EXPORT_SYMBOL(__printk_ratelimit);
 
 /**
  * printk_timed_ratelimit - caller-controlled printk ratelimiting
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 400183346ad2..7625f207f65e 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -67,6 +67,8 @@ void wakeme_after_rcu(struct rcu_head  *head)
 	complete(&rcu->completion);
 }
 
+#ifndef CONFIG_TINY_RCU
+
 #ifdef CONFIG_TREE_PREEMPT_RCU
 
 /**
@@ -157,6 +159,8 @@ void synchronize_rcu_bh(void)
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
 
+#endif /* #ifndef CONFIG_TINY_RCU */
+
 static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self,
 		unsigned long action, void *hcpu)
 {
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
new file mode 100644
index 000000000000..b33ec3aa377a
--- /dev/null
+++ b/kernel/rcutiny.c
@@ -0,0 +1,291 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
+ *
+ * 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 IBM Corporation, 2008
+ *
+ * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ *
+ * For detailed explanation of Read-Copy Update mechanism see -
+ *		Documentation/RCU
+ */
+#include <linux/moduleparam.h>
+#include <linux/completion.h>
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
+#include <linux/rcupdate.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/time.h>
+#include <linux/cpu.h>
+
+/* Global control variables for rcupdate callback mechanism. */
+struct rcu_ctrlblk {
+	struct rcu_head *rcucblist;	/* List of pending callbacks (CBs). */
+	struct rcu_head **donetail;	/* ->next pointer of last "done" CB. */
+	struct rcu_head **curtail;	/* ->next pointer of last CB. */
+};
+
+/* Definition for rcupdate control block. */
+static struct rcu_ctrlblk rcu_ctrlblk = {
+	.donetail	= &rcu_ctrlblk.rcucblist,
+	.curtail	= &rcu_ctrlblk.rcucblist,
+};
+
+static struct rcu_ctrlblk rcu_bh_ctrlblk = {
+	.donetail	= &rcu_bh_ctrlblk.rcucblist,
+	.curtail	= &rcu_bh_ctrlblk.rcucblist,
+};
+
+#ifdef CONFIG_NO_HZ
+
+static long rcu_dynticks_nesting = 1;
+
+/*
+ * Enter dynticks-idle mode, which is an extended quiescent state
+ * if we have fully entered that mode (i.e., if the new value of
+ * dynticks_nesting is zero).
+ */
+void rcu_enter_nohz(void)
+{
+	if (--rcu_dynticks_nesting == 0)
+		rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */
+}
+
+/*
+ * Exit dynticks-idle mode, so that we are no longer in an extended
+ * quiescent state.
+ */
+void rcu_exit_nohz(void)
+{
+	rcu_dynticks_nesting++;
+}
+
+#endif /* #ifdef CONFIG_NO_HZ */
+
+/*
+ * Helper function for rcu_qsctr_inc() and rcu_bh_qsctr_inc().
+ * Also disable irqs to avoid confusion due to interrupt handlers
+ * invoking call_rcu().
+ */
+static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	if (rcp->rcucblist != NULL &&
+	    rcp->donetail != rcp->curtail) {
+		rcp->donetail = rcp->curtail;
+		local_irq_restore(flags);
+		return 1;
+	}
+	local_irq_restore(flags);
+
+	return 0;
+}
+
+/*
+ * Record an rcu quiescent state.  And an rcu_bh quiescent state while we
+ * are at it, given that any rcu quiescent state is also an rcu_bh
+ * quiescent state.  Use "+" instead of "||" to defeat short circuiting.
+ */
+void rcu_sched_qs(int cpu)
+{
+	if (rcu_qsctr_help(&rcu_ctrlblk) + rcu_qsctr_help(&rcu_bh_ctrlblk))
+		raise_softirq(RCU_SOFTIRQ);
+}
+
+/*
+ * Record an rcu_bh quiescent state.
+ */
+void rcu_bh_qs(int cpu)
+{
+	if (rcu_qsctr_help(&rcu_bh_ctrlblk))
+		raise_softirq(RCU_SOFTIRQ);
+}
+
+/*
+ * Check to see if the scheduling-clock interrupt came from an extended
+ * quiescent state, and, if so, tell RCU about it.
+ */
+void rcu_check_callbacks(int cpu, int user)
+{
+	if (user ||
+	    (idle_cpu(cpu) &&
+	     !in_softirq() &&
+	     hardirq_count() <= (1 << HARDIRQ_SHIFT)))
+		rcu_sched_qs(cpu);
+	else if (!in_softirq())
+		rcu_bh_qs(cpu);
+}
+
+/*
+ * Helper function for rcu_process_callbacks() that operates on the
+ * specified rcu_ctrlkblk structure.
+ */
+static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
+{
+	struct rcu_head *next, *list;
+	unsigned long flags;
+
+	/* If no RCU callbacks ready to invoke, just return. */
+	if (&rcp->rcucblist == rcp->donetail)
+		return;
+
+	/* Move the ready-to-invoke callbacks to a local list. */
+	local_irq_save(flags);
+	list = rcp->rcucblist;
+	rcp->rcucblist = *rcp->donetail;
+	*rcp->donetail = NULL;
+	if (rcp->curtail == rcp->donetail)
+		rcp->curtail = &rcp->rcucblist;
+	rcp->donetail = &rcp->rcucblist;
+	local_irq_restore(flags);
+
+	/* Invoke the callbacks on the local list. */
+	while (list) {
+		next = list->next;
+		prefetch(next);
+		list->func(list);
+		list = next;
+	}
+}
+
+/*
+ * Invoke any callbacks whose grace period has completed.
+ */
+static void rcu_process_callbacks(struct softirq_action *unused)
+{
+	__rcu_process_callbacks(&rcu_ctrlblk);
+	__rcu_process_callbacks(&rcu_bh_ctrlblk);
+}
+
+/*
+ * Null function to handle CPU being onlined.  Longer term, we want to
+ * make TINY_RCU avoid using rcupdate.c, but later...
+ */
+int rcu_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+	return NOTIFY_OK;
+}
+
+/*
+ * Wait for a grace period to elapse.  But it is illegal to invoke
+ * synchronize_sched() from within an RCU read-side critical section.
+ * Therefore, any legal call to synchronize_sched() is a quiescent
+ * state, and so on a UP system, synchronize_sched() need do nothing.
+ * Ditto for synchronize_rcu_bh().  (But Lai Jiangshan points out the
+ * benefits of doing might_sleep() to reduce latency.)
+ *
+ * Cool, huh?  (Due to Josh Triplett.)
+ *
+ * But we want to make this a static inline later.
+ */
+void synchronize_sched(void)
+{
+	cond_resched();
+}
+EXPORT_SYMBOL_GPL(synchronize_sched);
+
+void synchronize_rcu_bh(void)
+{
+	synchronize_sched();
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
+
+/*
+ * Helper function for call_rcu() and call_rcu_bh().
+ */
+static void __call_rcu(struct rcu_head *head,
+		       void (*func)(struct rcu_head *rcu),
+		       struct rcu_ctrlblk *rcp)
+{
+	unsigned long flags;
+
+	head->func = func;
+	head->next = NULL;
+
+	local_irq_save(flags);
+	*rcp->curtail = head;
+	rcp->curtail = &head->next;
+	local_irq_restore(flags);
+}
+
+/*
+ * Post an RCU callback to be invoked after the end of an RCU grace
+ * period.  But since we have but one CPU, that would be after any
+ * quiescent state.
+ */
+void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+	__call_rcu(head, func, &rcu_ctrlblk);
+}
+EXPORT_SYMBOL_GPL(call_rcu);
+
+/*
+ * Post an RCU bottom-half callback to be invoked after any subsequent
+ * quiescent state.
+ */
+void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+	__call_rcu(head, func, &rcu_bh_ctrlblk);
+}
+EXPORT_SYMBOL_GPL(call_rcu_bh);
+
+void rcu_barrier(void)
+{
+	struct rcu_synchronize rcu;
+
+	init_completion(&rcu.completion);
+	/* Will wake me after RCU finished. */
+	call_rcu(&rcu.head, wakeme_after_rcu);
+	/* Wait for it. */
+	wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier);
+
+void rcu_barrier_bh(void)
+{
+	struct rcu_synchronize rcu;
+
+	init_completion(&rcu.completion);
+	/* Will wake me after RCU finished. */
+	call_rcu_bh(&rcu.head, wakeme_after_rcu);
+	/* Wait for it. */
+	wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_bh);
+
+void rcu_barrier_sched(void)
+{
+	struct rcu_synchronize rcu;
+
+	init_completion(&rcu.completion);
+	/* Will wake me after RCU finished. */
+	call_rcu_sched(&rcu.head, wakeme_after_rcu);
+	/* Wait for it. */
+	wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_sched);
+
+void __rcu_init(void)
+{
+	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+}
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 697c0a0229d4..3dd0ca23e191 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -547,6 +547,25 @@ static struct rcu_torture_ops srcu_ops = {
 	.name		= "srcu"
 };
 
+static void srcu_torture_synchronize_expedited(void)
+{
+	synchronize_srcu_expedited(&srcu_ctl);
+}
+
+static struct rcu_torture_ops srcu_expedited_ops = {
+	.init		= srcu_torture_init,
+	.cleanup	= srcu_torture_cleanup,
+	.readlock	= srcu_torture_read_lock,
+	.read_delay	= srcu_read_delay,
+	.readunlock	= srcu_torture_read_unlock,
+	.completed	= srcu_torture_completed,
+	.deferred_free	= rcu_sync_torture_deferred_free,
+	.sync		= srcu_torture_synchronize_expedited,
+	.cb_barrier	= NULL,
+	.stats		= srcu_torture_stats,
+	.name		= "srcu_expedited"
+};
+
 /*
  * Definitions for sched torture testing.
  */
@@ -592,7 +611,7 @@ static struct rcu_torture_ops sched_ops = {
 	.name		= "sched"
 };
 
-static struct rcu_torture_ops sched_ops_sync = {
+static struct rcu_torture_ops sched_sync_ops = {
 	.init		= rcu_sync_torture_init,
 	.cleanup	= NULL,
 	.readlock	= sched_torture_read_lock,
@@ -1098,8 +1117,8 @@ rcu_torture_init(void)
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] =
 		{ &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops,
-		  &sched_expedited_ops,
-		  &srcu_ops, &sched_ops, &sched_ops_sync, };
+		  &srcu_ops, &srcu_expedited_ops,
+		  &sched_ops, &sched_sync_ops, &sched_expedited_ops, };
 
 	mutex_lock(&fullstop_mutex);
 
@@ -1110,8 +1129,12 @@ rcu_torture_init(void)
 			break;
 	}
 	if (i == ARRAY_SIZE(torture_ops)) {
-		printk(KERN_ALERT "rcutorture: invalid torture type: \"%s\"\n",
+		printk(KERN_ALERT "rcu-torture: invalid torture type: \"%s\"\n",
 		       torture_type);
+		printk(KERN_ALERT "rcu-torture types:");
+		for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
+			printk(KERN_ALERT " %s", torture_ops[i]->name);
+		printk(KERN_ALERT "\n");
 		mutex_unlock(&fullstop_mutex);
 		return -EINVAL;
 	}
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index f3077c0ab181..9b36d6d7fb97 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -51,6 +51,8 @@
 
 /* Data structures. */
 
+static struct lock_class_key rcu_root_class;
+
 #define RCU_STATE_INITIALIZER(name) { \
 	.level = { &name.node[0] }, \
 	.levelcnt = { \
@@ -98,7 +100,7 @@ void rcu_sched_qs(int cpu)
 	struct rcu_data *rdp;
 
 	rdp = &per_cpu(rcu_sched_data, cpu);
-	rdp->passed_quiesc_completed = rdp->completed;
+	rdp->passed_quiesc_completed = rdp->gpnum - 1;
 	barrier();
 	rdp->passed_quiesc = 1;
 	rcu_preempt_note_context_switch(cpu);
@@ -109,7 +111,7 @@ void rcu_bh_qs(int cpu)
 	struct rcu_data *rdp;
 
 	rdp = &per_cpu(rcu_bh_data, cpu);
-	rdp->passed_quiesc_completed = rdp->completed;
+	rdp->passed_quiesc_completed = rdp->gpnum - 1;
 	barrier();
 	rdp->passed_quiesc = 1;
 }
@@ -335,28 +337,9 @@ void rcu_irq_exit(void)
 		set_need_resched();
 }
 
-/*
- * Record the specified "completed" value, which is later used to validate
- * dynticks counter manipulations.  Specify "rsp->completed - 1" to
- * unconditionally invalidate any future dynticks manipulations (which is
- * useful at the beginning of a grace period).
- */
-static void dyntick_record_completed(struct rcu_state *rsp, long comp)
-{
-	rsp->dynticks_completed = comp;
-}
-
 #ifdef CONFIG_SMP
 
 /*
- * Recall the previously recorded value of the completion for dynticks.
- */
-static long dyntick_recall_completed(struct rcu_state *rsp)
-{
-	return rsp->dynticks_completed;
-}
-
-/*
  * Snapshot the specified CPU's dynticks counter so that we can later
  * credit them with an implicit quiescent state.  Return 1 if this CPU
  * is in dynticks idle mode, which is an extended quiescent state.
@@ -419,24 +402,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 
 #else /* #ifdef CONFIG_NO_HZ */
 
-static void dyntick_record_completed(struct rcu_state *rsp, long comp)
-{
-}
-
 #ifdef CONFIG_SMP
 
-/*
- * If there are no dynticks, then the only way that a CPU can passively
- * be in a quiescent state is to be offline.  Unlike dynticks idle, which
- * is a point in time during the prior (already finished) grace period,
- * an offline CPU is always in a quiescent state, and thus can be
- * unconditionally applied.  So just return the current value of completed.
- */
-static long dyntick_recall_completed(struct rcu_state *rsp)
-{
-	return rsp->completed;
-}
-
 static int dyntick_save_progress_counter(struct rcu_data *rdp)
 {
 	return 0;
@@ -553,13 +520,33 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 /*
  * Update CPU-local rcu_data state to record the newly noticed grace period.
  * This is used both when we started the grace period and when we notice
- * that someone else started the grace period.
+ * that someone else started the grace period.  The caller must hold the
+ * ->lock of the leaf rcu_node structure corresponding to the current CPU,
+ *  and must have irqs disabled.
  */
+static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
+{
+	if (rdp->gpnum != rnp->gpnum) {
+		rdp->qs_pending = 1;
+		rdp->passed_quiesc = 0;
+		rdp->gpnum = rnp->gpnum;
+	}
+}
+
 static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	rdp->qs_pending = 1;
-	rdp->passed_quiesc = 0;
-	rdp->gpnum = rsp->gpnum;
+	unsigned long flags;
+	struct rcu_node *rnp;
+
+	local_irq_save(flags);
+	rnp = rdp->mynode;
+	if (rdp->gpnum == ACCESS_ONCE(rnp->gpnum) || /* outside lock. */
+	    !spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */
+		local_irq_restore(flags);
+		return;
+	}
+	__note_new_gpnum(rsp, rnp, rdp);
+	spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
 /*
@@ -583,6 +570,79 @@ check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp)
 }
 
 /*
+ * Advance this CPU's callbacks, but only if the current grace period
+ * has ended.  This may be called only from the CPU to whom the rdp
+ * belongs.  In addition, the corresponding leaf rcu_node structure's
+ * ->lock must be held by the caller, with irqs disabled.
+ */
+static void
+__rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
+{
+	/* Did another grace period end? */
+	if (rdp->completed != rnp->completed) {
+
+		/* Advance callbacks.  No harm if list empty. */
+		rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL];
+		rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL];
+		rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+
+		/* Remember that we saw this grace-period completion. */
+		rdp->completed = rnp->completed;
+	}
+}
+
+/*
+ * Advance this CPU's callbacks, but only if the current grace period
+ * has ended.  This may be called only from the CPU to whom the rdp
+ * belongs.
+ */
+static void
+rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+	unsigned long flags;
+	struct rcu_node *rnp;
+
+	local_irq_save(flags);
+	rnp = rdp->mynode;
+	if (rdp->completed == ACCESS_ONCE(rnp->completed) || /* outside lock. */
+	    !spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */
+		local_irq_restore(flags);
+		return;
+	}
+	__rcu_process_gp_end(rsp, rnp, rdp);
+	spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
+/*
+ * Do per-CPU grace-period initialization for running CPU.  The caller
+ * must hold the lock of the leaf rcu_node structure corresponding to
+ * this CPU.
+ */
+static void
+rcu_start_gp_per_cpu(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
+{
+	/* Prior grace period ended, so advance callbacks for current CPU. */
+	__rcu_process_gp_end(rsp, rnp, rdp);
+
+	/*
+	 * Because this CPU just now started the new grace period, we know
+	 * that all of its callbacks will be covered by this upcoming grace
+	 * period, even the ones that were registered arbitrarily recently.
+	 * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL.
+	 *
+	 * Other CPUs cannot be sure exactly when the grace period started.
+	 * Therefore, their recently registered callbacks must pass through
+	 * an additional RCU_NEXT_READY stage, so that they will be handled
+	 * by the next RCU grace period.
+	 */
+	rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+	rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+
+	/* Set state so that this CPU will detect the next quiescent state. */
+	__note_new_gpnum(rsp, rnp, rdp);
+}
+
+/*
  * Start a new RCU grace period if warranted, re-initializing the hierarchy
  * in preparation for detecting the next grace period.  The caller must hold
  * the root node's ->lock, which is released before return.  Hard irqs must
@@ -596,7 +656,23 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	if (!cpu_needs_another_gp(rsp, rdp)) {
-		spin_unlock_irqrestore(&rnp->lock, flags);
+		if (rnp->completed == rsp->completed) {
+			spin_unlock_irqrestore(&rnp->lock, flags);
+			return;
+		}
+		spin_unlock(&rnp->lock);	 /* irqs remain disabled. */
+
+		/*
+		 * Propagate new ->completed value to rcu_node structures
+		 * so that other CPUs don't have to wait until the start
+		 * of the next grace period to process their callbacks.
+		 */
+		rcu_for_each_node_breadth_first(rsp, rnp) {
+			spin_lock(&rnp->lock);	 /* irqs already disabled. */
+			rnp->completed = rsp->completed;
+			spin_unlock(&rnp->lock); /* irqs remain disabled. */
+		}
+		local_irq_restore(flags);
 		return;
 	}
 
@@ -606,29 +682,15 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 	rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */
 	rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
 	record_gp_stall_check_time(rsp);
-	dyntick_record_completed(rsp, rsp->completed - 1);
-	note_new_gpnum(rsp, rdp);
-
-	/*
-	 * Because this CPU just now started the new grace period, we know
-	 * that all of its callbacks will be covered by this upcoming grace
-	 * period, even the ones that were registered arbitrarily recently.
-	 * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL.
-	 *
-	 * Other CPUs cannot be sure exactly when the grace period started.
-	 * Therefore, their recently registered callbacks must pass through
-	 * an additional RCU_NEXT_READY stage, so that they will be handled
-	 * by the next RCU grace period.
-	 */
-	rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
-	rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
 
 	/* Special-case the common single-level case. */
 	if (NUM_RCU_NODES == 1) {
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
 		rnp->gpnum = rsp->gpnum;
+		rnp->completed = rsp->completed;
 		rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */
+		rcu_start_gp_per_cpu(rsp, rnp, rdp);
 		spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
@@ -661,6 +723,9 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
 		rnp->gpnum = rsp->gpnum;
+		rnp->completed = rsp->completed;
+		if (rnp == rdp->mynode)
+			rcu_start_gp_per_cpu(rsp, rnp, rdp);
 		spin_unlock(&rnp->lock);	/* irqs remain disabled. */
 	}
 
@@ -672,34 +737,6 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 }
 
 /*
- * Advance this CPU's callbacks, but only if the current grace period
- * has ended.  This may be called only from the CPU to whom the rdp
- * belongs.
- */
-static void
-rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
-{
-	long completed_snap;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	completed_snap = ACCESS_ONCE(rsp->completed);  /* outside of lock. */
-
-	/* Did another grace period end? */
-	if (rdp->completed != completed_snap) {
-
-		/* Advance callbacks.  No harm if list empty. */
-		rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL];
-		rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL];
-		rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
-
-		/* Remember that we saw this grace-period completion. */
-		rdp->completed = completed_snap;
-	}
-	local_irq_restore(flags);
-}
-
-/*
  * Clean up after the prior grace period and let rcu_start_gp() start up
  * the next grace period if one is needed.  Note that the caller must
  * hold rnp->lock, as required by rcu_start_gp(), which will release it.
@@ -710,7 +747,6 @@ static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags)
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
 	rsp->completed = rsp->gpnum;
 	rsp->signaled = RCU_GP_IDLE;
-	rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]);
 	rcu_start_gp(rsp, flags);  /* releases root node's rnp->lock. */
 }
 
@@ -781,7 +817,7 @@ cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp)
 
 	rnp = rdp->mynode;
 	spin_lock_irqsave(&rnp->lock, flags);
-	if (lastcomp != ACCESS_ONCE(rsp->completed)) {
+	if (lastcomp != rnp->completed) {
 
 		/*
 		 * Someone beat us to it for this grace period, so leave.
@@ -899,7 +935,6 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
 static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
 {
 	unsigned long flags;
-	long lastcomp;
 	unsigned long mask;
 	struct rcu_data *rdp = rsp->rda[cpu];
 	struct rcu_node *rnp;
@@ -935,7 +970,6 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
 		spin_unlock(&rnp->lock);	/* irqs remain disabled. */
 		rnp = rnp->parent;
 	} while (rnp != NULL);
-	lastcomp = rsp->completed;
 
 	spin_unlock_irqrestore(&rsp->onofflock, flags);
 
@@ -1109,7 +1143,7 @@ static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp,
 	rcu_for_each_leaf_node(rsp, rnp) {
 		mask = 0;
 		spin_lock_irqsave(&rnp->lock, flags);
-		if (rsp->completed != lastcomp) {
+		if (rnp->completed != lastcomp) {
 			spin_unlock_irqrestore(&rnp->lock, flags);
 			return 1;
 		}
@@ -1123,7 +1157,7 @@ static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp,
 			if ((rnp->qsmask & bit) != 0 && f(rsp->rda[cpu]))
 				mask |= bit;
 		}
-		if (mask != 0 && rsp->completed == lastcomp) {
+		if (mask != 0 && rnp->completed == lastcomp) {
 
 			/* cpu_quiet_msk() releases rnp->lock. */
 			cpu_quiet_msk(mask, rsp, rnp, flags);
@@ -1144,6 +1178,7 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 	long lastcomp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 	u8 signaled;
+	u8 forcenow;
 
 	if (!rcu_gp_in_progress(rsp))
 		return;  /* No grace period in progress, nothing to force. */
@@ -1156,10 +1191,10 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 		goto unlock_ret; /* no emergency and done recently. */
 	rsp->n_force_qs++;
 	spin_lock(&rnp->lock);
-	lastcomp = rsp->completed;
+	lastcomp = rsp->gpnum - 1;
 	signaled = rsp->signaled;
 	rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
-	if (lastcomp == rsp->gpnum) {
+	if(!rcu_gp_in_progress(rsp)) {
 		rsp->n_force_qs_ngp++;
 		spin_unlock(&rnp->lock);
 		goto unlock_ret;  /* no GP in progress, time updated. */
@@ -1180,21 +1215,29 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 		if (rcu_process_dyntick(rsp, lastcomp,
 					dyntick_save_progress_counter))
 			goto unlock_ret;
+		/* fall into next case. */
+
+	case RCU_SAVE_COMPLETED:
 
 		/* Update state, record completion counter. */
+		forcenow = 0;
 		spin_lock(&rnp->lock);
-		if (lastcomp == rsp->completed &&
-		    rsp->signaled == RCU_SAVE_DYNTICK) {
+		if (lastcomp + 1 == rsp->gpnum &&
+		    lastcomp == rsp->completed &&
+		    rsp->signaled == signaled) {
 			rsp->signaled = RCU_FORCE_QS;
-			dyntick_record_completed(rsp, lastcomp);
+			rsp->completed_fqs = lastcomp;
+			forcenow = signaled == RCU_SAVE_COMPLETED;
 		}
 		spin_unlock(&rnp->lock);
-		break;
+		if (!forcenow)
+			break;
+		/* fall into next case. */
 
 	case RCU_FORCE_QS:
 
 		/* Check dyntick-idle state, send IPI to laggarts. */
-		if (rcu_process_dyntick(rsp, dyntick_recall_completed(rsp),
+		if (rcu_process_dyntick(rsp, rsp->completed_fqs,
 					rcu_implicit_dynticks_qs))
 			goto unlock_ret;
 
@@ -1360,6 +1403,8 @@ EXPORT_SYMBOL_GPL(call_rcu_bh);
  */
 static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 {
+	struct rcu_node *rnp = rdp->mynode;
+
 	rdp->n_rcu_pending++;
 
 	/* Check for CPU stalls, if enabled. */
@@ -1384,13 +1429,13 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	}
 
 	/* Has another RCU grace period completed?  */
-	if (ACCESS_ONCE(rsp->completed) != rdp->completed) { /* outside lock */
+	if (ACCESS_ONCE(rnp->completed) != rdp->completed) { /* outside lock */
 		rdp->n_rp_gp_completed++;
 		return 1;
 	}
 
 	/* Has a new RCU grace period started? */
-	if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) { /* outside lock */
+	if (ACCESS_ONCE(rnp->gpnum) != rdp->gpnum) { /* outside lock */
 		rdp->n_rp_gp_started++;
 		return 1;
 	}
@@ -1544,21 +1589,16 @@ static void __cpuinit
 rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
 {
 	unsigned long flags;
-	long lastcomp;
 	unsigned long mask;
 	struct rcu_data *rdp = rsp->rda[cpu];
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	/* Set up local state, ensuring consistent view of global state. */
 	spin_lock_irqsave(&rnp->lock, flags);
-	lastcomp = rsp->completed;
-	rdp->completed = lastcomp;
-	rdp->gpnum = lastcomp;
 	rdp->passed_quiesc = 0;  /* We could be racing with new GP, */
 	rdp->qs_pending = 1;	 /*  so set up to respond to current GP. */
 	rdp->beenonline = 1;	 /* We have now been online. */
 	rdp->preemptable = preemptable;
-	rdp->passed_quiesc_completed = lastcomp - 1;
 	rdp->qlen_last_fqs_check = 0;
 	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
@@ -1580,6 +1620,11 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
 		spin_lock(&rnp->lock);	/* irqs already disabled. */
 		rnp->qsmaskinit |= mask;
 		mask = rnp->grpmask;
+		if (rnp == rdp->mynode) {
+			rdp->gpnum = rnp->completed; /* if GP in progress... */
+			rdp->completed = rnp->completed;
+			rdp->passed_quiesc_completed = rnp->completed - 1;
+		}
 		spin_unlock(&rnp->lock); /* irqs already disabled. */
 		rnp = rnp->parent;
 	} while (rnp != NULL && !(rnp->qsmaskinit & mask));
@@ -1685,8 +1730,7 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 		cpustride *= rsp->levelspread[i];
 		rnp = rsp->level[i];
 		for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) {
-			if (rnp != rcu_get_root(rsp))
-				spin_lock_init(&rnp->lock);
+			spin_lock_init(&rnp->lock);
 			rnp->gpnum = 0;
 			rnp->qsmask = 0;
 			rnp->qsmaskinit = 0;
@@ -1709,7 +1753,7 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 			INIT_LIST_HEAD(&rnp->blocked_tasks[1]);
 		}
 	}
-	spin_lock_init(&rcu_get_root(rsp)->lock);
+	lockdep_set_class(&rcu_get_root(rsp)->lock, &rcu_root_class);
 }
 
 /*
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 1899023b0962..17a28a08b559 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -84,6 +84,9 @@ struct rcu_node {
 	long	gpnum;		/* Current grace period for this node. */
 				/*  This will either be equal to or one */
 				/*  behind the root rcu_node's gpnum. */
+	long	completed;	/* Last grace period completed for this node. */
+				/*  This will either be equal to or one */
+				/*  behind the root rcu_node's gpnum. */
 	unsigned long qsmask;	/* CPUs or groups that need to switch in */
 				/*  order for current grace period to proceed.*/
 				/*  In leaf rcu_node, each bit corresponds to */
@@ -204,11 +207,12 @@ struct rcu_data {
 #define RCU_GP_IDLE		0	/* No grace period in progress. */
 #define RCU_GP_INIT		1	/* Grace period being initialized. */
 #define RCU_SAVE_DYNTICK	2	/* Need to scan dyntick state. */
-#define RCU_FORCE_QS		3	/* Need to force quiescent state. */
+#define RCU_SAVE_COMPLETED	3	/* Need to save rsp->completed. */
+#define RCU_FORCE_QS		4	/* Need to force quiescent state. */
 #ifdef CONFIG_NO_HZ
 #define RCU_SIGNAL_INIT		RCU_SAVE_DYNTICK
 #else /* #ifdef CONFIG_NO_HZ */
-#define RCU_SIGNAL_INIT		RCU_FORCE_QS
+#define RCU_SIGNAL_INIT		RCU_SAVE_COMPLETED
 #endif /* #else #ifdef CONFIG_NO_HZ */
 
 #define RCU_JIFFIES_TILL_FORCE_QS	 3	/* for rsp->jiffies_force_qs */
@@ -260,6 +264,8 @@ struct rcu_state {
 	long orphan_qlen;			/* Number of orphaned cbs. */
 	spinlock_t fqslock;			/* Only one task forcing */
 						/*  quiescent states. */
+	long	completed_fqs;			/* Value of completed @ snap. */
+						/*  Protected by fqslock. */
 	unsigned long jiffies_force_qs;		/* Time at which to invoke */
 						/*  force_quiescent_state(). */
 	unsigned long n_force_qs;		/* Number of calls to */
@@ -274,9 +280,6 @@ struct rcu_state {
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-#ifdef CONFIG_NO_HZ
-	long dynticks_completed;		/* Value of completed @ snap. */
-#endif /* #ifdef CONFIG_NO_HZ */
 };
 
 #ifdef RCU_TREE_NONCORE
@@ -298,7 +301,7 @@ DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
 #else /* #ifdef RCU_TREE_NONCORE */
 
 /* Forward declarations for rcutree_plugin.h */
-static inline void rcu_bootup_announce(void);
+static void rcu_bootup_announce(void);
 long rcu_batches_completed(void);
 static void rcu_preempt_note_context_switch(int cpu);
 static int rcu_preempted_readers(struct rcu_node *rnp);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index ef2a58c2b9d5..5ca2d26c5971 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -33,7 +33,7 @@ DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);
 /*
  * Tell them what RCU they are running.
  */
-static inline void rcu_bootup_announce(void)
+static void __init rcu_bootup_announce(void)
 {
 	printk(KERN_INFO
 	       "Experimental preemptable hierarchical RCU implementation.\n");
@@ -67,7 +67,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed);
 static void rcu_preempt_qs(int cpu)
 {
 	struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
-	rdp->passed_quiesc_completed = rdp->completed;
+	rdp->passed_quiesc_completed = rdp->gpnum - 1;
 	barrier();
 	rdp->passed_quiesc = 1;
 }
@@ -481,7 +481,7 @@ void exit_rcu(void)
 /*
  * Tell them what RCU they are running.
  */
-static inline void rcu_bootup_announce(void)
+static void __init rcu_bootup_announce(void)
 {
 	printk(KERN_INFO "Hierarchical RCU implementation.\n");
 }
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index 4b31c779e62e..1984cdc51e9a 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -155,12 +155,14 @@ static const struct file_operations rcudata_csv_fops = {
 
 static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 {
+	long gpnum;
 	int level = 0;
 	struct rcu_node *rnp;
 
+	gpnum = rsp->gpnum;
 	seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x "
 		      "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld\n",
-		   rsp->completed, rsp->gpnum, rsp->signaled,
+		   rsp->completed, gpnum, rsp->signaled,
 		   (long)(rsp->jiffies_force_qs - jiffies),
 		   (int)(jiffies & 0xffff),
 		   rsp->n_force_qs, rsp->n_force_qs_ngp,
@@ -171,8 +173,10 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 			seq_puts(m, "\n");
 			level = rnp->level;
 		}
-		seq_printf(m, "%lx/%lx %d:%d ^%d    ",
+		seq_printf(m, "%lx/%lx %c>%c %d:%d ^%d    ",
 			   rnp->qsmask, rnp->qsmaskinit,
+			   "T."[list_empty(&rnp->blocked_tasks[gpnum & 1])],
+			   "T."[list_empty(&rnp->blocked_tasks[!(gpnum & 1)])],
 			   rnp->grplo, rnp->grphi, rnp->grpnum);
 	}
 	seq_puts(m, "\n");
diff --git a/kernel/sched.c b/kernel/sched.c
index 3c11ae0a948d..0cbf2ef47b94 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -535,14 +535,12 @@ struct rq {
 	#define CPU_LOAD_IDX_MAX 5
 	unsigned long cpu_load[CPU_LOAD_IDX_MAX];
 #ifdef CONFIG_NO_HZ
-	unsigned long last_tick_seen;
 	unsigned char in_nohz_recently;
 #endif
 	/* capture load from *all* tasks on this cpu: */
 	struct load_weight load;
 	unsigned long nr_load_updates;
 	u64 nr_switches;
-	u64 nr_migrations_in;
 
 	struct cfs_rq cfs;
 	struct rt_rq rt;
@@ -591,6 +589,8 @@ struct rq {
 
 	u64 rt_avg;
 	u64 age_stamp;
+	u64 idle_stamp;
+	u64 avg_idle;
 #endif
 
 	/* calc_load related fields */
@@ -2017,6 +2017,7 @@ void kthread_bind(struct task_struct *p, unsigned int cpu)
 	}
 
 	spin_lock_irqsave(&rq->lock, flags);
+	update_rq_clock(rq);
 	set_task_cpu(p, cpu);
 	p->cpus_allowed = cpumask_of_cpu(cpu);
 	p->rt.nr_cpus_allowed = 1;
@@ -2078,7 +2079,6 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 #endif
 	if (old_cpu != new_cpu) {
 		p->se.nr_migrations++;
-		new_rq->nr_migrations_in++;
 #ifdef CONFIG_SCHEDSTATS
 		if (task_hot(p, old_rq->clock, NULL))
 			schedstat_inc(p, se.nr_forced2_migrations);
@@ -2115,6 +2115,7 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
 	 * it is sufficient to simply update the task's cpu field.
 	 */
 	if (!p->se.on_rq && !task_running(rq, p)) {
+		update_rq_clock(rq);
 		set_task_cpu(p, dest_cpu);
 		return 0;
 	}
@@ -2376,14 +2377,15 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 	task_rq_unlock(rq, &flags);
 
 	cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
-	if (cpu != orig_cpu)
+	if (cpu != orig_cpu) {
+		local_irq_save(flags);
+		rq = cpu_rq(cpu);
+		update_rq_clock(rq);
 		set_task_cpu(p, cpu);
-
+		local_irq_restore(flags);
+	}
 	rq = task_rq_lock(p, &flags);
 
-	if (rq != orig_rq)
-		update_rq_clock(rq);
-
 	WARN_ON(p->state != TASK_WAKING);
 	cpu = task_cpu(p);
 
@@ -2440,6 +2442,17 @@ out_running:
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_wake_up)
 		p->sched_class->task_wake_up(rq, p);
+
+	if (unlikely(rq->idle_stamp)) {
+		u64 delta = rq->clock - rq->idle_stamp;
+		u64 max = 2*sysctl_sched_migration_cost;
+
+		if (delta > max)
+			rq->avg_idle = max;
+		else
+			update_avg(&rq->avg_idle, delta);
+		rq->idle_stamp = 0;
+	}
 #endif
 out:
 	task_rq_unlock(rq, &flags);
@@ -2545,6 +2558,7 @@ static void __sched_fork(struct task_struct *p)
 void sched_fork(struct task_struct *p, int clone_flags)
 {
 	int cpu = get_cpu();
+	unsigned long flags;
 
 	__sched_fork(p);
 
@@ -2581,7 +2595,10 @@ void sched_fork(struct task_struct *p, int clone_flags)
 #ifdef CONFIG_SMP
 	cpu = p->sched_class->select_task_rq(p, SD_BALANCE_FORK, 0);
 #endif
+	local_irq_save(flags);
+	update_rq_clock(cpu_rq(cpu));
 	set_task_cpu(p, cpu);
+	local_irq_restore(flags);
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
 	if (likely(sched_info_on()))
@@ -2751,9 +2768,9 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	prev_state = prev->state;
 	finish_arch_switch(prev);
 	perf_event_task_sched_in(current, cpu_of(rq));
+	fire_sched_in_preempt_notifiers(current);
 	finish_lock_switch(rq, prev);
 
-	fire_sched_in_preempt_notifiers(current);
 	if (mm)
 		mmdrop(mm);
 	if (unlikely(prev_state == TASK_DEAD)) {
@@ -3018,15 +3035,6 @@ static void calc_load_account_active(struct rq *this_rq)
 }
 
 /*
- * Externally visible per-cpu scheduler statistics:
- * cpu_nr_migrations(cpu) - number of migrations into that cpu
- */
-u64 cpu_nr_migrations(int cpu)
-{
-	return cpu_rq(cpu)->nr_migrations_in;
-}
-
-/*
  * Update rq->cpu_load[] statistics. This function is usually called every
  * scheduler tick (TICK_NSEC).
  */
@@ -4126,7 +4134,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 	unsigned long flags;
 	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
-	cpumask_setall(cpus);
+	cpumask_copy(cpus, cpu_online_mask);
 
 	/*
 	 * When power savings policy is enabled for the parent domain, idle
@@ -4289,7 +4297,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
 	int all_pinned = 0;
 	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
-	cpumask_setall(cpus);
+	cpumask_copy(cpus, cpu_online_mask);
 
 	/*
 	 * When power savings policy is enabled for the parent domain, idle
@@ -4429,6 +4437,11 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 	int pulled_task = 0;
 	unsigned long next_balance = jiffies + HZ;
 
+	this_rq->idle_stamp = this_rq->clock;
+
+	if (this_rq->avg_idle < sysctl_sched_migration_cost)
+		return;
+
 	for_each_domain(this_cpu, sd) {
 		unsigned long interval;
 
@@ -4443,8 +4456,10 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 		interval = msecs_to_jiffies(sd->balance_interval);
 		if (time_after(next_balance, sd->last_balance + interval))
 			next_balance = sd->last_balance + interval;
-		if (pulled_task)
+		if (pulled_task) {
+			this_rq->idle_stamp = 0;
 			break;
+		}
 	}
 	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
 		/*
@@ -5046,8 +5061,13 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime,
 	p->gtime = cputime_add(p->gtime, cputime);
 
 	/* Add guest time to cpustat. */
-	cpustat->user = cputime64_add(cpustat->user, tmp);
-	cpustat->guest = cputime64_add(cpustat->guest, tmp);
+	if (TASK_NICE(p) > 0) {
+		cpustat->nice = cputime64_add(cpustat->nice, tmp);
+		cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp);
+	} else {
+		cpustat->user = cputime64_add(cpustat->user, tmp);
+		cpustat->guest = cputime64_add(cpustat->guest, tmp);
+	}
 }
 
 /*
@@ -5172,41 +5192,45 @@ cputime_t task_stime(struct task_struct *p)
 	return p->stime;
 }
 #else
+
+#ifndef nsecs_to_cputime
+# define nsecs_to_cputime(__nsecs) \
+	msecs_to_cputime(div_u64((__nsecs), NSEC_PER_MSEC))
+#endif
+
 cputime_t task_utime(struct task_struct *p)
 {
-	clock_t utime = cputime_to_clock_t(p->utime),
-		total = utime + cputime_to_clock_t(p->stime);
+	cputime_t utime = p->utime, total = utime + p->stime;
 	u64 temp;
 
 	/*
 	 * Use CFS's precise accounting:
 	 */
-	temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);
+	temp = (u64)nsecs_to_cputime(p->se.sum_exec_runtime);
 
 	if (total) {
 		temp *= utime;
 		do_div(temp, total);
 	}
-	utime = (clock_t)temp;
+	utime = (cputime_t)temp;
 
-	p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));
+	p->prev_utime = max(p->prev_utime, utime);
 	return p->prev_utime;
 }
 
 cputime_t task_stime(struct task_struct *p)
 {
-	clock_t stime;
+	cputime_t stime;
 
 	/*
 	 * Use CFS's precise accounting. (we subtract utime from
 	 * the total, to make sure the total observed by userspace
 	 * grows monotonically - apps rely on that):
 	 */
-	stime = nsec_to_clock_t(p->se.sum_exec_runtime) -
-			cputime_to_clock_t(task_utime(p));
+	stime = nsecs_to_cputime(p->se.sum_exec_runtime) - task_utime(p);
 
 	if (stime >= 0)
-		p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));
+		p->prev_stime = max(p->prev_stime, stime);
 
 	return p->prev_stime;
 }
@@ -6175,22 +6199,14 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
 	BUG_ON(p->se.on_rq);
 
 	p->policy = policy;
-	switch (p->policy) {
-	case SCHED_NORMAL:
-	case SCHED_BATCH:
-	case SCHED_IDLE:
-		p->sched_class = &fair_sched_class;
-		break;
-	case SCHED_FIFO:
-	case SCHED_RR:
-		p->sched_class = &rt_sched_class;
-		break;
-	}
-
 	p->rt_priority = prio;
 	p->normal_prio = normal_prio(p);
 	/* we are holding p->pi_lock already */
 	p->prio = rt_mutex_getprio(p);
+	if (rt_prio(p->prio))
+		p->sched_class = &rt_sched_class;
+	else
+		p->sched_class = &fair_sched_class;
 	set_load_weight(p);
 }
 
@@ -7905,6 +7921,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 
 static void free_rootdomain(struct root_domain *rd)
 {
+	synchronize_sched();
+
 	cpupri_cleanup(&rd->cpupri);
 
 	free_cpumask_var(rd->rto_mask);
@@ -8881,7 +8899,7 @@ static int build_sched_domains(const struct cpumask *cpu_map)
 	return __build_sched_domains(cpu_map, NULL);
 }
 
-static struct cpumask *doms_cur;	/* current sched domains */
+static cpumask_var_t *doms_cur;	/* current sched domains */
 static int ndoms_cur;		/* number of sched domains in 'doms_cur' */
 static struct sched_domain_attr *dattr_cur;
 				/* attribues of custom domains in 'doms_cur' */
@@ -8903,6 +8921,31 @@ int __attribute__((weak)) arch_update_cpu_topology(void)
 	return 0;
 }
 
+cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
+{
+	int i;
+	cpumask_var_t *doms;
+
+	doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
+	if (!doms)
+		return NULL;
+	for (i = 0; i < ndoms; i++) {
+		if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
+			free_sched_domains(doms, i);
+			return NULL;
+		}
+	}
+	return doms;
+}
+
+void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
+{
+	unsigned int i;
+	for (i = 0; i < ndoms; i++)
+		free_cpumask_var(doms[i]);
+	kfree(doms);
+}
+
 /*
  * Set up scheduler domains and groups. Callers must hold the hotplug lock.
  * For now this just excludes isolated cpus, but could be used to
@@ -8914,12 +8957,12 @@ static int arch_init_sched_domains(const struct cpumask *cpu_map)
 
 	arch_update_cpu_topology();
 	ndoms_cur = 1;
-	doms_cur = kmalloc(cpumask_size(), GFP_KERNEL);
+	doms_cur = alloc_sched_domains(ndoms_cur);
 	if (!doms_cur)
-		doms_cur = fallback_doms;
-	cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map);
+		doms_cur = &fallback_doms;
+	cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
 	dattr_cur = NULL;
-	err = build_sched_domains(doms_cur);
+	err = build_sched_domains(doms_cur[0]);
 	register_sched_domain_sysctl();
 
 	return err;
@@ -8969,19 +9012,19 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
  * doms_new[] to the current sched domain partitioning, doms_cur[].
  * It destroys each deleted domain and builds each new domain.
  *
- * 'doms_new' is an array of cpumask's of length 'ndoms_new'.
+ * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
  * The masks don't intersect (don't overlap.) We should setup one
  * sched domain for each mask. CPUs not in any of the cpumasks will
  * not be load balanced. If the same cpumask appears both in the
  * current 'doms_cur' domains and in the new 'doms_new', we can leave
  * it as it is.
  *
- * The passed in 'doms_new' should be kmalloc'd. This routine takes
- * ownership of it and will kfree it when done with it. If the caller
- * failed the kmalloc call, then it can pass in doms_new == NULL &&
- * ndoms_new == 1, and partition_sched_domains() will fallback to
- * the single partition 'fallback_doms', it also forces the domains
- * to be rebuilt.
+ * The passed in 'doms_new' should be allocated using
+ * alloc_sched_domains.  This routine takes ownership of it and will
+ * free_sched_domains it when done with it. If the caller failed the
+ * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
+ * and partition_sched_domains() will fallback to the single partition
+ * 'fallback_doms', it also forces the domains to be rebuilt.
  *
  * If doms_new == NULL it will be replaced with cpu_online_mask.
  * ndoms_new == 0 is a special case for destroying existing domains,
@@ -8989,8 +9032,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
  *
  * Call with hotplug lock held
  */
-/* FIXME: Change to struct cpumask *doms_new[] */
-void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
+void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 			     struct sched_domain_attr *dattr_new)
 {
 	int i, j, n;
@@ -9009,40 +9051,40 @@ void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
 	/* Destroy deleted domains */
 	for (i = 0; i < ndoms_cur; i++) {
 		for (j = 0; j < n && !new_topology; j++) {
-			if (cpumask_equal(&doms_cur[i], &doms_new[j])
+			if (cpumask_equal(doms_cur[i], doms_new[j])
 			    && dattrs_equal(dattr_cur, i, dattr_new, j))
 				goto match1;
 		}
 		/* no match - a current sched domain not in new doms_new[] */
-		detach_destroy_domains(doms_cur + i);
+		detach_destroy_domains(doms_cur[i]);
 match1:
 		;
 	}
 
 	if (doms_new == NULL) {
 		ndoms_cur = 0;
-		doms_new = fallback_doms;
-		cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map);
+		doms_new = &fallback_doms;
+		cpumask_andnot(doms_new[0], cpu_online_mask, cpu_isolated_map);
 		WARN_ON_ONCE(dattr_new);
 	}
 
 	/* Build new domains */
 	for (i = 0; i < ndoms_new; i++) {
 		for (j = 0; j < ndoms_cur && !new_topology; j++) {
-			if (cpumask_equal(&doms_new[i], &doms_cur[j])
+			if (cpumask_equal(doms_new[i], doms_cur[j])
 			    && dattrs_equal(dattr_new, i, dattr_cur, j))
 				goto match2;
 		}
 		/* no match - add a new doms_new */
-		__build_sched_domains(doms_new + i,
+		__build_sched_domains(doms_new[i],
 					dattr_new ? dattr_new + i : NULL);
 match2:
 		;
 	}
 
 	/* Remember the new sched domains */
-	if (doms_cur != fallback_doms)
-		kfree(doms_cur);
+	if (doms_cur != &fallback_doms)
+		free_sched_domains(doms_cur, ndoms_cur);
 	kfree(dattr_cur);	/* kfree(NULL) is safe */
 	doms_cur = doms_new;
 	dattr_cur = dattr_new;
@@ -9364,10 +9406,6 @@ void __init sched_init(void)
 #ifdef CONFIG_CPUMASK_OFFSTACK
 	alloc_size += num_possible_cpus() * cpumask_size();
 #endif
-	/*
-	 * As sched_init() is called before page_alloc is setup,
-	 * we use alloc_bootmem().
-	 */
 	if (alloc_size) {
 		ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
 
@@ -9522,6 +9560,8 @@ void __init sched_init(void)
 		rq->cpu = i;
 		rq->online = 0;
 		rq->migration_thread = NULL;
+		rq->idle_stamp = 0;
+		rq->avg_idle = 2*sysctl_sched_migration_cost;
 		INIT_LIST_HEAD(&rq->migration_queue);
 		rq_attach_root(rq, &def_root_domain);
 #endif
@@ -10901,6 +10941,7 @@ void synchronize_sched_expedited(void)
 		spin_unlock_irqrestore(&rq->lock, flags);
 	}
 	rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+	synchronize_sched_expedited_count++;
 	mutex_unlock(&rcu_sched_expedited_mutex);
 	put_online_cpus();
 	if (need_full_sync)
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index efb84409bc43..6988cf08f705 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -285,12 +285,16 @@ static void print_cpu(struct seq_file *m, int cpu)
 
 #ifdef CONFIG_SCHEDSTATS
 #define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, rq->n);
+#define P64(n) SEQ_printf(m, "  .%-30s: %Ld\n", #n, rq->n);
 
 	P(yld_count);
 
 	P(sched_switch);
 	P(sched_count);
 	P(sched_goidle);
+#ifdef CONFIG_SMP
+	P64(avg_idle);
+#endif
 
 	P(ttwu_count);
 	P(ttwu_local);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 37087a7fac22..0ff21af6e297 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1345,6 +1345,37 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 }
 
 /*
+ * Try and locate an idle CPU in the sched_domain.
+ */
+static int
+select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
+{
+	int cpu = smp_processor_id();
+	int prev_cpu = task_cpu(p);
+	int i;
+
+	/*
+	 * If this domain spans both cpu and prev_cpu (see the SD_WAKE_AFFINE
+	 * test in select_task_rq_fair) and the prev_cpu is idle then that's
+	 * always a better target than the current cpu.
+	 */
+	if (target == cpu && !cpu_rq(prev_cpu)->cfs.nr_running)
+		return prev_cpu;
+
+	/*
+	 * Otherwise, iterate the domain and find an elegible idle cpu.
+	 */
+	for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
+		if (!cpu_rq(i)->cfs.nr_running) {
+			target = i;
+			break;
+		}
+	}
+
+	return target;
+}
+
+/*
  * sched_balance_self: balance the current task (running on cpu) in domains
  * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
  * SD_BALANCE_EXEC.
@@ -1398,11 +1429,35 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 				want_sd = 0;
 		}
 
-		if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
-		    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
+		/*
+		 * While iterating the domains looking for a spanning
+		 * WAKE_AFFINE domain, adjust the affine target to any idle cpu
+		 * in cache sharing domains along the way.
+		 */
+		if (want_affine) {
+			int target = -1;
 
-			affine_sd = tmp;
-			want_affine = 0;
+			/*
+			 * If both cpu and prev_cpu are part of this domain,
+			 * cpu is a valid SD_WAKE_AFFINE target.
+			 */
+			if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp)))
+				target = cpu;
+
+			/*
+			 * If there's an idle sibling in this domain, make that
+			 * the wake_affine target instead of the current cpu.
+			 */
+			if (tmp->flags & SD_PREFER_SIBLING)
+				target = select_idle_sibling(p, tmp, target);
+
+			if (target >= 0) {
+				if (tmp->flags & SD_WAKE_AFFINE) {
+					affine_sd = tmp;
+					want_affine = 0;
+				}
+				cpu = target;
+			}
 		}
 
 		if (!want_sd && !want_affine)
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index a4d790cddb19..5c5fef378415 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1153,29 +1153,12 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
 
 static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
 
-static inline int pick_optimal_cpu(int this_cpu,
-				   const struct cpumask *mask)
-{
-	int first;
-
-	/* "this_cpu" is cheaper to preempt than a remote processor */
-	if ((this_cpu != -1) && cpumask_test_cpu(this_cpu, mask))
-		return this_cpu;
-
-	first = cpumask_first(mask);
-	if (first < nr_cpu_ids)
-		return first;
-
-	return -1;
-}
-
 static int find_lowest_rq(struct task_struct *task)
 {
 	struct sched_domain *sd;
 	struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
 	int this_cpu = smp_processor_id();
 	int cpu      = task_cpu(task);
-	cpumask_var_t domain_mask;
 
 	if (task->rt.nr_cpus_allowed == 1)
 		return -1; /* No other targets possible */
@@ -1198,28 +1181,26 @@ static int find_lowest_rq(struct task_struct *task)
 	 * Otherwise, we consult the sched_domains span maps to figure
 	 * out which cpu is logically closest to our hot cache data.
 	 */
-	if (this_cpu == cpu)
-		this_cpu = -1; /* Skip this_cpu opt if the same */
-
-	if (alloc_cpumask_var(&domain_mask, GFP_ATOMIC)) {
-		for_each_domain(cpu, sd) {
-			if (sd->flags & SD_WAKE_AFFINE) {
-				int best_cpu;
+	if (!cpumask_test_cpu(this_cpu, lowest_mask))
+		this_cpu = -1; /* Skip this_cpu opt if not among lowest */
 
-				cpumask_and(domain_mask,
-					    sched_domain_span(sd),
-					    lowest_mask);
+	for_each_domain(cpu, sd) {
+		if (sd->flags & SD_WAKE_AFFINE) {
+			int best_cpu;
 
-				best_cpu = pick_optimal_cpu(this_cpu,
-							    domain_mask);
-
-				if (best_cpu != -1) {
-					free_cpumask_var(domain_mask);
-					return best_cpu;
-				}
-			}
+			/*
+			 * "this_cpu" is cheaper to preempt than a
+			 * remote processor.
+			 */
+			if (this_cpu != -1 &&
+			    cpumask_test_cpu(this_cpu, sched_domain_span(sd)))
+				return this_cpu;
+
+			best_cpu = cpumask_first_and(lowest_mask,
+						     sched_domain_span(sd));
+			if (best_cpu < nr_cpu_ids)
+				return best_cpu;
 		}
-		free_cpumask_var(domain_mask);
 	}
 
 	/*
@@ -1227,7 +1208,13 @@ static int find_lowest_rq(struct task_struct *task)
 	 * just give the caller *something* to work with from the compatible
 	 * locations.
 	 */
-	return pick_optimal_cpu(this_cpu, lowest_mask);
+	if (this_cpu != -1)
+		return this_cpu;
+
+	cpu = cpumask_any(lowest_mask);
+	if (cpu < nr_cpu_ids)
+		return cpu;
+	return -1;
 }
 
 /* Will lock the rq it finds */
diff --git a/kernel/signal.c b/kernel/signal.c
index 6705320784fd..fe08008133da 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -22,6 +22,7 @@
 #include <linux/ptrace.h>
 #include <linux/signal.h>
 #include <linux/signalfd.h>
+#include <linux/ratelimit.h>
 #include <linux/tracehook.h>
 #include <linux/capability.h>
 #include <linux/freezer.h>
@@ -41,6 +42,8 @@
 
 static struct kmem_cache *sigqueue_cachep;
 
+int print_fatal_signals __read_mostly;
+
 static void __user *sig_handler(struct task_struct *t, int sig)
 {
 	return t->sighand->action[sig - 1].sa.sa_handler;
@@ -159,7 +162,7 @@ int next_signal(struct sigpending *pending, sigset_t *mask)
 {
 	unsigned long i, *s, *m, x;
 	int sig = 0;
-	
+
 	s = pending->signal.sig;
 	m = mask->sig;
 	switch (_NSIG_WORDS) {
@@ -184,17 +187,31 @@ int next_signal(struct sigpending *pending, sigset_t *mask)
 			sig = ffz(~x) + 1;
 		break;
 	}
-	
+
 	return sig;
 }
 
+static inline void print_dropped_signal(int sig)
+{
+	static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10);
+
+	if (!print_fatal_signals)
+		return;
+
+	if (!__ratelimit(&ratelimit_state))
+		return;
+
+	printk(KERN_INFO "%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n",
+				current->comm, current->pid, sig);
+}
+
 /*
  * allocate a new signal queue record
  * - this may be called without locks if and only if t == current, otherwise an
  *   appopriate lock must be held to stop the target task from exiting
  */
-static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
-					 int override_rlimit)
+static struct sigqueue *
+__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit)
 {
 	struct sigqueue *q = NULL;
 	struct user_struct *user;
@@ -207,10 +224,15 @@ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
 	 */
 	user = get_uid(__task_cred(t)->user);
 	atomic_inc(&user->sigpending);
+
 	if (override_rlimit ||
 	    atomic_read(&user->sigpending) <=
-			t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur)
+			t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur) {
 		q = kmem_cache_alloc(sigqueue_cachep, flags);
+	} else {
+		print_dropped_signal(sig);
+	}
+
 	if (unlikely(q == NULL)) {
 		atomic_dec(&user->sigpending);
 		free_uid(user);
@@ -869,7 +891,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
 	else
 		override_rlimit = 0;
 
-	q = __sigqueue_alloc(t, GFP_ATOMIC | __GFP_NOTRACK_FALSE_POSITIVE,
+	q = __sigqueue_alloc(sig, t, GFP_ATOMIC | __GFP_NOTRACK_FALSE_POSITIVE,
 		override_rlimit);
 	if (q) {
 		list_add_tail(&q->list, &pending->list);
@@ -925,8 +947,6 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
 	return __send_signal(sig, info, t, group, from_ancestor_ns);
 }
 
-int print_fatal_signals;
-
 static void print_fatal_signal(struct pt_regs *regs, int signr)
 {
 	printk("%s/%d: potentially unexpected fatal signal %d.\n",
@@ -1293,19 +1313,19 @@ EXPORT_SYMBOL(kill_pid);
  * These functions support sending signals using preallocated sigqueue
  * structures.  This is needed "because realtime applications cannot
  * afford to lose notifications of asynchronous events, like timer
- * expirations or I/O completions".  In the case of Posix Timers 
+ * expirations or I/O completions".  In the case of Posix Timers
  * we allocate the sigqueue structure from the timer_create.  If this
  * allocation fails we are able to report the failure to the application
  * with an EAGAIN error.
  */
- 
 struct sigqueue *sigqueue_alloc(void)
 {
-	struct sigqueue *q;
+	struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0);
 
-	if ((q = __sigqueue_alloc(current, GFP_KERNEL, 0)))
+	if (q)
 		q->flags |= SIGQUEUE_PREALLOC;
-	return(q);
+
+	return q;
 }
 
 void sigqueue_free(struct sigqueue *q)
diff --git a/kernel/smp.c b/kernel/smp.c
index c9d1c7835c2f..8bd618f0364d 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -265,9 +265,7 @@ static DEFINE_PER_CPU(struct call_single_data, csd_data);
  * @info: An arbitrary pointer to pass to the function.
  * @wait: If true, wait until function has completed on other CPUs.
  *
- * Returns 0 on success, else a negative status code. Note that @wait
- * will be implicitly turned on in case of allocation failures, since
- * we fall back to on-stack allocation.
+ * Returns 0 on success, else a negative status code.
  */
 int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 			     int wait)
@@ -355,9 +353,7 @@ void __smp_call_function_single(int cpu, struct call_single_data *data,
  * @wait: If true, wait (atomically) until function has completed
  *        on other CPUs.
  *
- * If @wait is true, then returns once @func has returned. Note that @wait
- * will be implicitly turned on in case of allocation failures, since
- * we fall back to on-stack allocation.
+ * If @wait is true, then returns once @func has returned.
  *
  * You must not call this function with disabled interrupts or from a
  * hardware interrupt handler or from a bottom half handler. Preemption
@@ -443,8 +439,7 @@ EXPORT_SYMBOL(smp_call_function_many);
  * Returns 0.
  *
  * If @wait is true, then returns once @func has returned; otherwise
- * it returns just before the target cpu calls @func. In case of allocation
- * failure, @wait will be implicitly turned on.
+ * it returns just before the target cpu calls @func.
  *
  * You must not call this function with disabled interrupts or from a
  * hardware interrupt handler or from a bottom half handler.
diff --git a/kernel/softirq.c b/kernel/softirq.c
index f8749e5216e0..21939d9e830e 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -302,9 +302,9 @@ void irq_exit(void)
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();
 
+	rcu_irq_exit();
 #ifdef CONFIG_NO_HZ
 	/* Make sure that timer wheel updates are propagated */
-	rcu_irq_exit();
 	if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched())
 		tick_nohz_stop_sched_tick(0);
 #endif
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index 5ddab730cb2f..41e042219ff6 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -21,145 +21,28 @@
 #include <linux/debug_locks.h>
 #include <linux/module.h>
 
-#ifndef _spin_trylock
-int __lockfunc _spin_trylock(spinlock_t *lock)
-{
-	return __spin_trylock(lock);
-}
-EXPORT_SYMBOL(_spin_trylock);
-#endif
-
-#ifndef _read_trylock
-int __lockfunc _read_trylock(rwlock_t *lock)
-{
-	return __read_trylock(lock);
-}
-EXPORT_SYMBOL(_read_trylock);
-#endif
-
-#ifndef _write_trylock
-int __lockfunc _write_trylock(rwlock_t *lock)
-{
-	return __write_trylock(lock);
-}
-EXPORT_SYMBOL(_write_trylock);
-#endif
-
 /*
  * If lockdep is enabled then we use the non-preemption spin-ops
  * even on CONFIG_PREEMPT, because lockdep assumes that interrupts are
  * not re-enabled during lock-acquire (which the preempt-spin-ops do):
  */
 #if !defined(CONFIG_GENERIC_LOCKBREAK) || defined(CONFIG_DEBUG_LOCK_ALLOC)
-
-#ifndef _read_lock
-void __lockfunc _read_lock(rwlock_t *lock)
-{
-	__read_lock(lock);
-}
-EXPORT_SYMBOL(_read_lock);
-#endif
-
-#ifndef _spin_lock_irqsave
-unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock)
-{
-	return __spin_lock_irqsave(lock);
-}
-EXPORT_SYMBOL(_spin_lock_irqsave);
-#endif
-
-#ifndef _spin_lock_irq
-void __lockfunc _spin_lock_irq(spinlock_t *lock)
-{
-	__spin_lock_irq(lock);
-}
-EXPORT_SYMBOL(_spin_lock_irq);
-#endif
-
-#ifndef _spin_lock_bh
-void __lockfunc _spin_lock_bh(spinlock_t *lock)
-{
-	__spin_lock_bh(lock);
-}
-EXPORT_SYMBOL(_spin_lock_bh);
-#endif
-
-#ifndef _read_lock_irqsave
-unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock)
-{
-	return __read_lock_irqsave(lock);
-}
-EXPORT_SYMBOL(_read_lock_irqsave);
-#endif
-
-#ifndef _read_lock_irq
-void __lockfunc _read_lock_irq(rwlock_t *lock)
-{
-	__read_lock_irq(lock);
-}
-EXPORT_SYMBOL(_read_lock_irq);
-#endif
-
-#ifndef _read_lock_bh
-void __lockfunc _read_lock_bh(rwlock_t *lock)
-{
-	__read_lock_bh(lock);
-}
-EXPORT_SYMBOL(_read_lock_bh);
-#endif
-
-#ifndef _write_lock_irqsave
-unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock)
-{
-	return __write_lock_irqsave(lock);
-}
-EXPORT_SYMBOL(_write_lock_irqsave);
-#endif
-
-#ifndef _write_lock_irq
-void __lockfunc _write_lock_irq(rwlock_t *lock)
-{
-	__write_lock_irq(lock);
-}
-EXPORT_SYMBOL(_write_lock_irq);
-#endif
-
-#ifndef _write_lock_bh
-void __lockfunc _write_lock_bh(rwlock_t *lock)
-{
-	__write_lock_bh(lock);
-}
-EXPORT_SYMBOL(_write_lock_bh);
-#endif
-
-#ifndef _spin_lock
-void __lockfunc _spin_lock(spinlock_t *lock)
-{
-	__spin_lock(lock);
-}
-EXPORT_SYMBOL(_spin_lock);
-#endif
-
-#ifndef _write_lock
-void __lockfunc _write_lock(rwlock_t *lock)
-{
-	__write_lock(lock);
-}
-EXPORT_SYMBOL(_write_lock);
-#endif
-
-#else /* CONFIG_PREEMPT: */
-
 /*
+ * The __lock_function inlines are taken from
+ * include/linux/spinlock_api_smp.h
+ */
+#else
+/*
+ * We build the __lock_function inlines here. They are too large for
+ * inlining all over the place, but here is only one user per function
+ * which embedds them into the calling _lock_function below.
+ *
  * This could be a long-held lock. We both prepare to spin for a long
  * time (making _this_ CPU preemptable if possible), and we also signal
  * towards that other CPU that it should break the lock ASAP.
- *
- * (We do this in a function because inlining it would be excessive.)
  */
-
 #define BUILD_LOCK_OPS(op, locktype)					\
-void __lockfunc _##op##_lock(locktype##_t *lock)			\
+void __lockfunc __##op##_lock(locktype##_t *lock)			\
 {									\
 	for (;;) {							\
 		preempt_disable();					\
@@ -175,9 +58,7 @@ void __lockfunc _##op##_lock(locktype##_t *lock)			\
 	(lock)->break_lock = 0;						\
 }									\
 									\
-EXPORT_SYMBOL(_##op##_lock);						\
-									\
-unsigned long __lockfunc _##op##_lock_irqsave(locktype##_t *lock)	\
+unsigned long __lockfunc __##op##_lock_irqsave(locktype##_t *lock)	\
 {									\
 	unsigned long flags;						\
 									\
@@ -198,16 +79,12 @@ unsigned long __lockfunc _##op##_lock_irqsave(locktype##_t *lock)	\
 	return flags;							\
 }									\
 									\
-EXPORT_SYMBOL(_##op##_lock_irqsave);					\
-									\
-void __lockfunc _##op##_lock_irq(locktype##_t *lock)			\
+void __lockfunc __##op##_lock_irq(locktype##_t *lock)			\
 {									\
 	_##op##_lock_irqsave(lock);					\
 }									\
 									\
-EXPORT_SYMBOL(_##op##_lock_irq);					\
-									\
-void __lockfunc _##op##_lock_bh(locktype##_t *lock)			\
+void __lockfunc __##op##_lock_bh(locktype##_t *lock)			\
 {									\
 	unsigned long flags;						\
 									\
@@ -220,23 +97,21 @@ void __lockfunc _##op##_lock_bh(locktype##_t *lock)			\
 	local_bh_disable();						\
 	local_irq_restore(flags);					\
 }									\
-									\
-EXPORT_SYMBOL(_##op##_lock_bh)
 
 /*
  * Build preemption-friendly versions of the following
  * lock-spinning functions:
  *
- *         _[spin|read|write]_lock()
- *         _[spin|read|write]_lock_irq()
- *         _[spin|read|write]_lock_irqsave()
- *         _[spin|read|write]_lock_bh()
+ *         __[spin|read|write]_lock()
+ *         __[spin|read|write]_lock_irq()
+ *         __[spin|read|write]_lock_irqsave()
+ *         __[spin|read|write]_lock_bh()
  */
 BUILD_LOCK_OPS(spin, spinlock);
 BUILD_LOCK_OPS(read, rwlock);
 BUILD_LOCK_OPS(write, rwlock);
 
-#endif /* CONFIG_PREEMPT */
+#endif
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
@@ -248,7 +123,8 @@ void __lockfunc _spin_lock_nested(spinlock_t *lock, int subclass)
 }
 EXPORT_SYMBOL(_spin_lock_nested);
 
-unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclass)
+unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock,
+						   int subclass)
 {
 	unsigned long flags;
 
@@ -272,7 +148,127 @@ EXPORT_SYMBOL(_spin_lock_nest_lock);
 
 #endif
 
-#ifndef _spin_unlock
+#ifndef CONFIG_INLINE_SPIN_TRYLOCK
+int __lockfunc _spin_trylock(spinlock_t *lock)
+{
+	return __spin_trylock(lock);
+}
+EXPORT_SYMBOL(_spin_trylock);
+#endif
+
+#ifndef CONFIG_INLINE_READ_TRYLOCK
+int __lockfunc _read_trylock(rwlock_t *lock)
+{
+	return __read_trylock(lock);
+}
+EXPORT_SYMBOL(_read_trylock);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_TRYLOCK
+int __lockfunc _write_trylock(rwlock_t *lock)
+{
+	return __write_trylock(lock);
+}
+EXPORT_SYMBOL(_write_trylock);
+#endif
+
+#ifndef CONFIG_INLINE_READ_LOCK
+void __lockfunc _read_lock(rwlock_t *lock)
+{
+	__read_lock(lock);
+}
+EXPORT_SYMBOL(_read_lock);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_LOCK_IRQSAVE
+unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock)
+{
+	return __spin_lock_irqsave(lock);
+}
+EXPORT_SYMBOL(_spin_lock_irqsave);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_LOCK_IRQ
+void __lockfunc _spin_lock_irq(spinlock_t *lock)
+{
+	__spin_lock_irq(lock);
+}
+EXPORT_SYMBOL(_spin_lock_irq);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_LOCK_BH
+void __lockfunc _spin_lock_bh(spinlock_t *lock)
+{
+	__spin_lock_bh(lock);
+}
+EXPORT_SYMBOL(_spin_lock_bh);
+#endif
+
+#ifndef CONFIG_INLINE_READ_LOCK_IRQSAVE
+unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock)
+{
+	return __read_lock_irqsave(lock);
+}
+EXPORT_SYMBOL(_read_lock_irqsave);
+#endif
+
+#ifndef CONFIG_INLINE_READ_LOCK_IRQ
+void __lockfunc _read_lock_irq(rwlock_t *lock)
+{
+	__read_lock_irq(lock);
+}
+EXPORT_SYMBOL(_read_lock_irq);
+#endif
+
+#ifndef CONFIG_INLINE_READ_LOCK_BH
+void __lockfunc _read_lock_bh(rwlock_t *lock)
+{
+	__read_lock_bh(lock);
+}
+EXPORT_SYMBOL(_read_lock_bh);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK_IRQSAVE
+unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock)
+{
+	return __write_lock_irqsave(lock);
+}
+EXPORT_SYMBOL(_write_lock_irqsave);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK_IRQ
+void __lockfunc _write_lock_irq(rwlock_t *lock)
+{
+	__write_lock_irq(lock);
+}
+EXPORT_SYMBOL(_write_lock_irq);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK_BH
+void __lockfunc _write_lock_bh(rwlock_t *lock)
+{
+	__write_lock_bh(lock);
+}
+EXPORT_SYMBOL(_write_lock_bh);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_LOCK
+void __lockfunc _spin_lock(spinlock_t *lock)
+{
+	__spin_lock(lock);
+}
+EXPORT_SYMBOL(_spin_lock);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK
+void __lockfunc _write_lock(rwlock_t *lock)
+{
+	__write_lock(lock);
+}
+EXPORT_SYMBOL(_write_lock);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_UNLOCK
 void __lockfunc _spin_unlock(spinlock_t *lock)
 {
 	__spin_unlock(lock);
@@ -280,7 +276,7 @@ void __lockfunc _spin_unlock(spinlock_t *lock)
 EXPORT_SYMBOL(_spin_unlock);
 #endif
 
-#ifndef _write_unlock
+#ifndef CONFIG_INLINE_WRITE_UNLOCK
 void __lockfunc _write_unlock(rwlock_t *lock)
 {
 	__write_unlock(lock);
@@ -288,7 +284,7 @@ void __lockfunc _write_unlock(rwlock_t *lock)
 EXPORT_SYMBOL(_write_unlock);
 #endif
 
-#ifndef _read_unlock
+#ifndef CONFIG_INLINE_READ_UNLOCK
 void __lockfunc _read_unlock(rwlock_t *lock)
 {
 	__read_unlock(lock);
@@ -296,7 +292,7 @@ void __lockfunc _read_unlock(rwlock_t *lock)
 EXPORT_SYMBOL(_read_unlock);
 #endif
 
-#ifndef _spin_unlock_irqrestore
+#ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE
 void __lockfunc _spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags)
 {
 	__spin_unlock_irqrestore(lock, flags);
@@ -304,7 +300,7 @@ void __lockfunc _spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags)
 EXPORT_SYMBOL(_spin_unlock_irqrestore);
 #endif
 
-#ifndef _spin_unlock_irq
+#ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQ
 void __lockfunc _spin_unlock_irq(spinlock_t *lock)
 {
 	__spin_unlock_irq(lock);
@@ -312,7 +308,7 @@ void __lockfunc _spin_unlock_irq(spinlock_t *lock)
 EXPORT_SYMBOL(_spin_unlock_irq);
 #endif
 
-#ifndef _spin_unlock_bh
+#ifndef CONFIG_INLINE_SPIN_UNLOCK_BH
 void __lockfunc _spin_unlock_bh(spinlock_t *lock)
 {
 	__spin_unlock_bh(lock);
@@ -320,7 +316,7 @@ void __lockfunc _spin_unlock_bh(spinlock_t *lock)
 EXPORT_SYMBOL(_spin_unlock_bh);
 #endif
 
-#ifndef _read_unlock_irqrestore
+#ifndef CONFIG_INLINE_READ_UNLOCK_IRQRESTORE
 void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
 {
 	__read_unlock_irqrestore(lock, flags);
@@ -328,7 +324,7 @@ void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
 EXPORT_SYMBOL(_read_unlock_irqrestore);
 #endif
 
-#ifndef _read_unlock_irq
+#ifndef CONFIG_INLINE_READ_UNLOCK_IRQ
 void __lockfunc _read_unlock_irq(rwlock_t *lock)
 {
 	__read_unlock_irq(lock);
@@ -336,7 +332,7 @@ void __lockfunc _read_unlock_irq(rwlock_t *lock)
 EXPORT_SYMBOL(_read_unlock_irq);
 #endif
 
-#ifndef _read_unlock_bh
+#ifndef CONFIG_INLINE_READ_UNLOCK_BH
 void __lockfunc _read_unlock_bh(rwlock_t *lock)
 {
 	__read_unlock_bh(lock);
@@ -344,7 +340,7 @@ void __lockfunc _read_unlock_bh(rwlock_t *lock)
 EXPORT_SYMBOL(_read_unlock_bh);
 #endif
 
-#ifndef _write_unlock_irqrestore
+#ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE
 void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
 {
 	__write_unlock_irqrestore(lock, flags);
@@ -352,7 +348,7 @@ void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
 EXPORT_SYMBOL(_write_unlock_irqrestore);
 #endif
 
-#ifndef _write_unlock_irq
+#ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQ
 void __lockfunc _write_unlock_irq(rwlock_t *lock)
 {
 	__write_unlock_irq(lock);
@@ -360,7 +356,7 @@ void __lockfunc _write_unlock_irq(rwlock_t *lock)
 EXPORT_SYMBOL(_write_unlock_irq);
 #endif
 
-#ifndef _write_unlock_bh
+#ifndef CONFIG_INLINE_WRITE_UNLOCK_BH
 void __lockfunc _write_unlock_bh(rwlock_t *lock)
 {
 	__write_unlock_bh(lock);
@@ -368,7 +364,7 @@ void __lockfunc _write_unlock_bh(rwlock_t *lock)
 EXPORT_SYMBOL(_write_unlock_bh);
 #endif
 
-#ifndef _spin_trylock_bh
+#ifndef CONFIG_INLINE_SPIN_TRYLOCK_BH
 int __lockfunc _spin_trylock_bh(spinlock_t *lock)
 {
 	return __spin_trylock_bh(lock);
diff --git a/kernel/srcu.c b/kernel/srcu.c
index b0aeeaf22ce4..818d7d9aa03c 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -49,6 +49,7 @@ int init_srcu_struct(struct srcu_struct *sp)
 	sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array);
 	return (sp->per_cpu_ref ? 0 : -ENOMEM);
 }
+EXPORT_SYMBOL_GPL(init_srcu_struct);
 
 /*
  * srcu_readers_active_idx -- returns approximate number of readers
@@ -97,6 +98,7 @@ void cleanup_srcu_struct(struct srcu_struct *sp)
 	free_percpu(sp->per_cpu_ref);
 	sp->per_cpu_ref = NULL;
 }
+EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
 
 /**
  * srcu_read_lock - register a new reader for an SRCU-protected structure.
@@ -118,6 +120,7 @@ int srcu_read_lock(struct srcu_struct *sp)
 	preempt_enable();
 	return idx;
 }
+EXPORT_SYMBOL_GPL(srcu_read_lock);
 
 /**
  * srcu_read_unlock - unregister a old reader from an SRCU-protected structure.
@@ -136,22 +139,12 @@ void srcu_read_unlock(struct srcu_struct *sp, int idx)
 	per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]--;
 	preempt_enable();
 }
+EXPORT_SYMBOL_GPL(srcu_read_unlock);
 
-/**
- * synchronize_srcu - wait for prior SRCU read-side critical-section completion
- * @sp: srcu_struct with which to synchronize.
- *
- * Flip the completed counter, and wait for the old count to drain to zero.
- * As with classic RCU, the updater must use some separate means of
- * synchronizing concurrent updates.  Can block; must be called from
- * process context.
- *
- * Note that it is illegal to call synchornize_srcu() from the corresponding
- * SRCU read-side critical section; doing so will result in deadlock.
- * However, it is perfectly legal to call synchronize_srcu() on one
- * srcu_struct from some other srcu_struct's read-side critical section.
+/*
+ * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
  */
-void synchronize_srcu(struct srcu_struct *sp)
+void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
 {
 	int idx;
 
@@ -173,7 +166,7 @@ void synchronize_srcu(struct srcu_struct *sp)
 		return;
 	}
 
-	synchronize_sched();  /* Force memory barrier on all CPUs. */
+	sync_func();  /* Force memory barrier on all CPUs. */
 
 	/*
 	 * The preceding synchronize_sched() ensures that any CPU that
@@ -190,7 +183,7 @@ void synchronize_srcu(struct srcu_struct *sp)
 	idx = sp->completed & 0x1;
 	sp->completed++;
 
-	synchronize_sched();  /* Force memory barrier on all CPUs. */
+	sync_func();  /* Force memory barrier on all CPUs. */
 
 	/*
 	 * At this point, because of the preceding synchronize_sched(),
@@ -203,7 +196,7 @@ void synchronize_srcu(struct srcu_struct *sp)
 	while (srcu_readers_active_idx(sp, idx))
 		schedule_timeout_interruptible(1);
 
-	synchronize_sched();  /* Force memory barrier on all CPUs. */
+	sync_func();  /* Force memory barrier on all CPUs. */
 
 	/*
 	 * The preceding synchronize_sched() forces all srcu_read_unlock()
@@ -237,6 +230,47 @@ void synchronize_srcu(struct srcu_struct *sp)
 }
 
 /**
+ * synchronize_srcu - wait for prior SRCU read-side critical-section completion
+ * @sp: srcu_struct with which to synchronize.
+ *
+ * Flip the completed counter, and wait for the old count to drain to zero.
+ * As with classic RCU, the updater must use some separate means of
+ * synchronizing concurrent updates.  Can block; must be called from
+ * process context.
+ *
+ * Note that it is illegal to call synchronize_srcu() from the corresponding
+ * SRCU read-side critical section; doing so will result in deadlock.
+ * However, it is perfectly legal to call synchronize_srcu() on one
+ * srcu_struct from some other srcu_struct's read-side critical section.
+ */
+void synchronize_srcu(struct srcu_struct *sp)
+{
+	__synchronize_srcu(sp, synchronize_sched);
+}
+EXPORT_SYMBOL_GPL(synchronize_srcu);
+
+/**
+ * synchronize_srcu_expedited - like synchronize_srcu, but less patient
+ * @sp: srcu_struct with which to synchronize.
+ *
+ * Flip the completed counter, and wait for the old count to drain to zero.
+ * As with classic RCU, the updater must use some separate means of
+ * synchronizing concurrent updates.  Can block; must be called from
+ * process context.
+ *
+ * Note that it is illegal to call synchronize_srcu_expedited()
+ * from the corresponding SRCU read-side critical section; doing so
+ * will result in deadlock.  However, it is perfectly legal to call
+ * synchronize_srcu_expedited() on one srcu_struct from some other
+ * srcu_struct's read-side critical section.
+ */
+void synchronize_srcu_expedited(struct srcu_struct *sp)
+{
+	__synchronize_srcu(sp, synchronize_sched_expedited);
+}
+EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
+
+/**
  * srcu_batches_completed - return batches completed.
  * @sp: srcu_struct on which to report batch completion.
  *
@@ -248,10 +282,4 @@ long srcu_batches_completed(struct srcu_struct *sp)
 {
 	return sp->completed;
 }
-
-EXPORT_SYMBOL_GPL(init_srcu_struct);
-EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
-EXPORT_SYMBOL_GPL(srcu_read_lock);
-EXPORT_SYMBOL_GPL(srcu_read_unlock);
-EXPORT_SYMBOL_GPL(synchronize_srcu);
 EXPORT_SYMBOL_GPL(srcu_batches_completed);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 0d949c517412..4dbf93a52ee9 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -36,6 +36,7 @@
 #include <linux/sysrq.h>
 #include <linux/highuid.h>
 #include <linux/writeback.h>
+#include <linux/ratelimit.h>
 #include <linux/hugetlb.h>
 #include <linux/initrd.h>
 #include <linux/key.h>
@@ -158,6 +159,8 @@ extern int no_unaligned_warning;
 extern int unaligned_dump_stack;
 #endif
 
+extern struct ratelimit_state printk_ratelimit_state;
+
 #ifdef CONFIG_RT_MUTEXES
 extern int max_lock_depth;
 #endif
diff --git a/kernel/time.c b/kernel/time.c
index 2e2e469a7fec..2ef4fe2079b6 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -136,7 +136,6 @@ static inline void warp_clock(void)
 	write_seqlock_irq(&xtime_lock);
 	wall_to_monotonic.tv_sec -= sys_tz.tz_minuteswest * 60;
 	xtime.tv_sec += sys_tz.tz_minuteswest * 60;
-	update_xtime_cache(0);
 	write_sequnlock_irq(&xtime_lock);
 	clock_was_set();
 }
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 620b58abdc32..05e8aeedcdf3 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -37,10 +37,9 @@ static DEFINE_SPINLOCK(clockevents_lock);
  *
  * Math helper, returns latch value converted to nanoseconds (bound checked)
  */
-unsigned long clockevent_delta2ns(unsigned long latch,
-				  struct clock_event_device *evt)
+u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
 {
-	u64 clc = ((u64) latch << evt->shift);
+	u64 clc = (u64) latch << evt->shift;
 
 	if (unlikely(!evt->mult)) {
 		evt->mult = 1;
@@ -50,10 +49,10 @@ unsigned long clockevent_delta2ns(unsigned long latch,
 	do_div(clc, evt->mult);
 	if (clc < 1000)
 		clc = 1000;
-	if (clc > LONG_MAX)
-		clc = LONG_MAX;
+	if (clc > KTIME_MAX)
+		clc = KTIME_MAX;
 
-	return (unsigned long) clc;
+	return clc;
 }
 EXPORT_SYMBOL_GPL(clockevent_delta2ns);
 
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 94fea4212601..e85c23404d34 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -107,6 +107,59 @@ u64 timecounter_cyc2time(struct timecounter *tc,
 }
 EXPORT_SYMBOL_GPL(timecounter_cyc2time);
 
+/**
+ * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks
+ * @mult:	pointer to mult variable
+ * @shift:	pointer to shift variable
+ * @from:	frequency to convert from
+ * @to:		frequency to convert to
+ * @minsec:	guaranteed runtime conversion range in seconds
+ *
+ * The function evaluates the shift/mult pair for the scaled math
+ * operations of clocksources and clockevents.
+ *
+ * @to and @from are frequency values in HZ. For clock sources @to is
+ * NSEC_PER_SEC == 1GHz and @from is the counter frequency. For clock
+ * event @to is the counter frequency and @from is NSEC_PER_SEC.
+ *
+ * The @minsec conversion range argument controls the time frame in
+ * seconds which must be covered by the runtime conversion with the
+ * calculated mult and shift factors. This guarantees that no 64bit
+ * overflow happens when the input value of the conversion is
+ * multiplied with the calculated mult factor. Larger ranges may
+ * reduce the conversion accuracy by chosing smaller mult and shift
+ * factors.
+ */
+void
+clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec)
+{
+	u64 tmp;
+	u32 sft, sftacc= 32;
+
+	/*
+	 * Calculate the shift factor which is limiting the conversion
+	 * range:
+	 */
+	tmp = ((u64)minsec * from) >> 32;
+	while (tmp) {
+		tmp >>=1;
+		sftacc--;
+	}
+
+	/*
+	 * Find the conversion shift/mult pair which has the best
+	 * accuracy and fits the maxsec conversion range:
+	 */
+	for (sft = 32; sft > 0; sft--) {
+		tmp = (u64) to << sft;
+		do_div(tmp, from);
+		if ((tmp >> sftacc) == 0)
+			break;
+	}
+	*mult = tmp;
+	*shift = sft;
+}
+
 /*[Clocksource internal variables]---------
  * curr_clocksource:
  *	currently selected clocksource.
@@ -413,6 +466,47 @@ void clocksource_touch_watchdog(void)
 	clocksource_resume_watchdog();
 }
 
+/**
+ * clocksource_max_deferment - Returns max time the clocksource can be deferred
+ * @cs:         Pointer to clocksource
+ *
+ */
+static u64 clocksource_max_deferment(struct clocksource *cs)
+{
+	u64 max_nsecs, max_cycles;
+
+	/*
+	 * Calculate the maximum number of cycles that we can pass to the
+	 * cyc2ns function without overflowing a 64-bit signed result. The
+	 * maximum number of cycles is equal to ULLONG_MAX/cs->mult which
+	 * is equivalent to the below.
+	 * max_cycles < (2^63)/cs->mult
+	 * max_cycles < 2^(log2((2^63)/cs->mult))
+	 * max_cycles < 2^(log2(2^63) - log2(cs->mult))
+	 * max_cycles < 2^(63 - log2(cs->mult))
+	 * max_cycles < 1 << (63 - log2(cs->mult))
+	 * Please note that we add 1 to the result of the log2 to account for
+	 * any rounding errors, ensure the above inequality is satisfied and
+	 * no overflow will occur.
+	 */
+	max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1));
+
+	/*
+	 * The actual maximum number of cycles we can defer the clocksource is
+	 * determined by the minimum of max_cycles and cs->mask.
+	 */
+	max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
+	max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift);
+
+	/*
+	 * To ensure that the clocksource does not wrap whilst we are idle,
+	 * limit the time the clocksource can be deferred by 12.5%. Please
+	 * note a margin of 12.5% is used because this can be computed with
+	 * a shift, versus say 10% which would require division.
+	 */
+	return max_nsecs - (max_nsecs >> 5);
+}
+
 #ifdef CONFIG_GENERIC_TIME
 
 /**
@@ -511,6 +605,9 @@ static void clocksource_enqueue(struct clocksource *cs)
  */
 int clocksource_register(struct clocksource *cs)
 {
+	/* calculate max idle time permitted for this clocksource */
+	cs->max_idle_ns = clocksource_max_deferment(cs);
+
 	mutex_lock(&clocksource_mutex);
 	clocksource_enqueue(cs);
 	clocksource_select();
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index a96c0e2b89cf..0a8a213016f0 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -50,9 +50,9 @@ int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires,
 				dev->min_delta_ns += dev->min_delta_ns >> 1;
 
 			printk(KERN_WARNING
-			       "CE: %s increasing min_delta_ns to %lu nsec\n",
+			       "CE: %s increasing min_delta_ns to %llu nsec\n",
 			       dev->name ? dev->name : "?",
-			       dev->min_delta_ns << 1);
+			       (unsigned long long) dev->min_delta_ns << 1);
 
 			i = 0;
 		}
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 89aed5933ed4..f992762d7f51 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -134,18 +134,13 @@ __setup("nohz=", setup_tick_nohz);
  * value. We do this unconditionally on any cpu, as we don't know whether the
  * cpu, which has the update task assigned is in a long sleep.
  */
-static void tick_nohz_update_jiffies(void)
+static void tick_nohz_update_jiffies(ktime_t now)
 {
 	int cpu = smp_processor_id();
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	unsigned long flags;
-	ktime_t now;
-
-	if (!ts->tick_stopped)
-		return;
 
 	cpumask_clear_cpu(cpu, nohz_cpu_mask);
-	now = ktime_get();
 	ts->idle_waketime = now;
 
 	local_irq_save(flags);
@@ -155,20 +150,17 @@ static void tick_nohz_update_jiffies(void)
 	touch_softlockup_watchdog();
 }
 
-static void tick_nohz_stop_idle(int cpu)
+static void tick_nohz_stop_idle(int cpu, ktime_t now)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	ktime_t delta;
 
-	if (ts->idle_active) {
-		ktime_t now, delta;
-		now = ktime_get();
-		delta = ktime_sub(now, ts->idle_entrytime);
-		ts->idle_lastupdate = now;
-		ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
-		ts->idle_active = 0;
+	delta = ktime_sub(now, ts->idle_entrytime);
+	ts->idle_lastupdate = now;
+	ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+	ts->idle_active = 0;
 
-		sched_clock_idle_wakeup_event(0);
-	}
+	sched_clock_idle_wakeup_event(0);
 }
 
 static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
@@ -216,6 +208,7 @@ void tick_nohz_stop_sched_tick(int inidle)
 	struct tick_sched *ts;
 	ktime_t last_update, expires, now;
 	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+	u64 time_delta;
 	int cpu;
 
 	local_irq_save(flags);
@@ -263,7 +256,7 @@ void tick_nohz_stop_sched_tick(int inidle)
 
 		if (ratelimit < 10) {
 			printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
-			       local_softirq_pending());
+			       (unsigned int) local_softirq_pending());
 			ratelimit++;
 		}
 		goto end;
@@ -275,14 +268,18 @@ void tick_nohz_stop_sched_tick(int inidle)
 		seq = read_seqbegin(&xtime_lock);
 		last_update = last_jiffies_update;
 		last_jiffies = jiffies;
+		time_delta = timekeeping_max_deferment();
 	} while (read_seqretry(&xtime_lock, seq));
 
-	/* Get the next timer wheel timer */
-	next_jiffies = get_next_timer_interrupt(last_jiffies);
-	delta_jiffies = next_jiffies - last_jiffies;
-
-	if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu))
+	if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) ||
+	    arch_needs_cpu(cpu)) {
+		next_jiffies = last_jiffies + 1;
 		delta_jiffies = 1;
+	} else {
+		/* Get the next timer wheel timer */
+		next_jiffies = get_next_timer_interrupt(last_jiffies);
+		delta_jiffies = next_jiffies - last_jiffies;
+	}
 	/*
 	 * Do not stop the tick, if we are only one off
 	 * or if the cpu is required for rcu
@@ -294,22 +291,51 @@ void tick_nohz_stop_sched_tick(int inidle)
 	if ((long)delta_jiffies >= 1) {
 
 		/*
-		* calculate the expiry time for the next timer wheel
-		* timer
-		*/
-		expires = ktime_add_ns(last_update, tick_period.tv64 *
-				   delta_jiffies);
-
-		/*
 		 * If this cpu is the one which updates jiffies, then
 		 * give up the assignment and let it be taken by the
 		 * cpu which runs the tick timer next, which might be
 		 * this cpu as well. If we don't drop this here the
 		 * jiffies might be stale and do_timer() never
-		 * invoked.
+		 * invoked. Keep track of the fact that it was the one
+		 * which had the do_timer() duty last. If this cpu is
+		 * the one which had the do_timer() duty last, we
+		 * limit the sleep time to the timekeeping
+		 * max_deferement value which we retrieved
+		 * above. Otherwise we can sleep as long as we want.
 		 */
-		if (cpu == tick_do_timer_cpu)
+		if (cpu == tick_do_timer_cpu) {
 			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+			ts->do_timer_last = 1;
+		} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
+			time_delta = KTIME_MAX;
+			ts->do_timer_last = 0;
+		} else if (!ts->do_timer_last) {
+			time_delta = KTIME_MAX;
+		}
+
+		/*
+		 * calculate the expiry time for the next timer wheel
+		 * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals
+		 * that there is no timer pending or at least extremely
+		 * far into the future (12 days for HZ=1000). In this
+		 * case we set the expiry to the end of time.
+		 */
+		if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) {
+			/*
+			 * Calculate the time delta for the next timer event.
+			 * If the time delta exceeds the maximum time delta
+			 * permitted by the current clocksource then adjust
+			 * the time delta accordingly to ensure the
+			 * clocksource does not wrap.
+			 */
+			time_delta = min_t(u64, time_delta,
+					   tick_period.tv64 * delta_jiffies);
+		}
+
+		if (time_delta < KTIME_MAX)
+			expires = ktime_add_ns(last_update, time_delta);
+		else
+			expires.tv64 = KTIME_MAX;
 
 		if (delta_jiffies > 1)
 			cpumask_set_cpu(cpu, nohz_cpu_mask);
@@ -342,22 +368,19 @@ void tick_nohz_stop_sched_tick(int inidle)
 
 		ts->idle_sleeps++;
 
+		/* Mark expires */
+		ts->idle_expires = expires;
+
 		/*
-		 * delta_jiffies >= NEXT_TIMER_MAX_DELTA signals that
-		 * there is no timer pending or at least extremly far
-		 * into the future (12 days for HZ=1000). In this case
-		 * we simply stop the tick timer:
+		 * If the expiration time == KTIME_MAX, then
+		 * in this case we simply stop the tick timer.
 		 */
-		if (unlikely(delta_jiffies >= NEXT_TIMER_MAX_DELTA)) {
-			ts->idle_expires.tv64 = KTIME_MAX;
+		 if (unlikely(expires.tv64 == KTIME_MAX)) {
 			if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
 				hrtimer_cancel(&ts->sched_timer);
 			goto out;
 		}
 
-		/* Mark expiries */
-		ts->idle_expires = expires;
-
 		if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
 			hrtimer_start(&ts->sched_timer, expires,
 				      HRTIMER_MODE_ABS_PINNED);
@@ -436,7 +459,11 @@ void tick_nohz_restart_sched_tick(void)
 	ktime_t now;
 
 	local_irq_disable();
-	tick_nohz_stop_idle(cpu);
+	if (ts->idle_active || (ts->inidle && ts->tick_stopped))
+		now = ktime_get();
+
+	if (ts->idle_active)
+		tick_nohz_stop_idle(cpu, now);
 
 	if (!ts->inidle || !ts->tick_stopped) {
 		ts->inidle = 0;
@@ -450,7 +477,6 @@ void tick_nohz_restart_sched_tick(void)
 
 	/* Update jiffies first */
 	select_nohz_load_balancer(0);
-	now = ktime_get();
 	tick_do_update_jiffies64(now);
 	cpumask_clear_cpu(cpu, nohz_cpu_mask);
 
@@ -584,22 +610,18 @@ static void tick_nohz_switch_to_nohz(void)
  * timer and do not touch the other magic bits which need to be done
  * when idle is left.
  */
-static void tick_nohz_kick_tick(int cpu)
+static void tick_nohz_kick_tick(int cpu, ktime_t now)
 {
 #if 0
 	/* Switch back to 2.6.27 behaviour */
 
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-	ktime_t delta, now;
-
-	if (!ts->tick_stopped)
-		return;
+	ktime_t delta;
 
 	/*
 	 * Do not touch the tick device, when the next expiry is either
 	 * already reached or less/equal than the tick period.
 	 */
-	now = ktime_get();
 	delta =	ktime_sub(hrtimer_get_expires(&ts->sched_timer), now);
 	if (delta.tv64 <= tick_period.tv64)
 		return;
@@ -608,9 +630,26 @@ static void tick_nohz_kick_tick(int cpu)
 #endif
 }
 
+static inline void tick_check_nohz(int cpu)
+{
+	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	ktime_t now;
+
+	if (!ts->idle_active && !ts->tick_stopped)
+		return;
+	now = ktime_get();
+	if (ts->idle_active)
+		tick_nohz_stop_idle(cpu, now);
+	if (ts->tick_stopped) {
+		tick_nohz_update_jiffies(now);
+		tick_nohz_kick_tick(cpu, now);
+	}
+}
+
 #else
 
 static inline void tick_nohz_switch_to_nohz(void) { }
+static inline void tick_check_nohz(int cpu) { }
 
 #endif /* NO_HZ */
 
@@ -620,11 +659,7 @@ static inline void tick_nohz_switch_to_nohz(void) { }
 void tick_check_idle(int cpu)
 {
 	tick_check_oneshot_broadcast(cpu);
-#ifdef CONFIG_NO_HZ
-	tick_nohz_stop_idle(cpu);
-	tick_nohz_update_jiffies();
-	tick_nohz_kick_tick(cpu);
-#endif
+	tick_check_nohz(cpu);
 }
 
 /*
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index c3a4e2907eaa..d1aebd73b191 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -165,13 +165,6 @@ struct timespec raw_time;
 /* flag for if timekeeping is suspended */
 int __read_mostly timekeeping_suspended;
 
-static struct timespec xtime_cache __attribute__ ((aligned (16)));
-void update_xtime_cache(u64 nsec)
-{
-	xtime_cache = xtime;
-	timespec_add_ns(&xtime_cache, nsec);
-}
-
 /* must hold xtime_lock */
 void timekeeping_leap_insert(int leapsecond)
 {
@@ -332,8 +325,6 @@ int do_settimeofday(struct timespec *tv)
 
 	xtime = *tv;
 
-	update_xtime_cache(0);
-
 	timekeeper.ntp_error = 0;
 	ntp_clear();
 
@@ -488,6 +479,17 @@ int timekeeping_valid_for_hres(void)
 }
 
 /**
+ * timekeeping_max_deferment - Returns max time the clocksource can be deferred
+ *
+ * Caller must observe xtime_lock via read_seqbegin/read_seqretry to
+ * ensure that the clocksource does not change!
+ */
+u64 timekeeping_max_deferment(void)
+{
+	return timekeeper.clock->max_idle_ns;
+}
+
+/**
  * read_persistent_clock -  Return time from the persistent clock.
  *
  * Weak dummy function for arches that do not yet support it.
@@ -548,7 +550,6 @@ void __init timekeeping_init(void)
 	}
 	set_normalized_timespec(&wall_to_monotonic,
 				-boot.tv_sec, -boot.tv_nsec);
-	update_xtime_cache(0);
 	total_sleep_time.tv_sec = 0;
 	total_sleep_time.tv_nsec = 0;
 	write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -582,7 +583,6 @@ static int timekeeping_resume(struct sys_device *dev)
 		wall_to_monotonic = timespec_sub(wall_to_monotonic, ts);
 		total_sleep_time = timespec_add_safe(total_sleep_time, ts);
 	}
-	update_xtime_cache(0);
 	/* re-base the last cycle value */
 	timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
 	timekeeper.ntp_error = 0;
@@ -723,6 +723,49 @@ static void timekeeping_adjust(s64 offset)
 }
 
 /**
+ * logarithmic_accumulation - shifted accumulation of cycles
+ *
+ * This functions accumulates a shifted interval of cycles into
+ * into a shifted interval nanoseconds. Allows for O(log) accumulation
+ * loop.
+ *
+ * Returns the unconsumed cycles.
+ */
+static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
+{
+	u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
+
+	/* If the offset is smaller then a shifted interval, do nothing */
+	if (offset < timekeeper.cycle_interval<<shift)
+		return offset;
+
+	/* Accumulate one shifted interval */
+	offset -= timekeeper.cycle_interval << shift;
+	timekeeper.clock->cycle_last += timekeeper.cycle_interval << shift;
+
+	timekeeper.xtime_nsec += timekeeper.xtime_interval << shift;
+	while (timekeeper.xtime_nsec >= nsecps) {
+		timekeeper.xtime_nsec -= nsecps;
+		xtime.tv_sec++;
+		second_overflow();
+	}
+
+	/* Accumulate into raw time */
+	raw_time.tv_nsec += timekeeper.raw_interval << shift;;
+	while (raw_time.tv_nsec >= NSEC_PER_SEC) {
+		raw_time.tv_nsec -= NSEC_PER_SEC;
+		raw_time.tv_sec++;
+	}
+
+	/* Accumulate error between NTP and clock interval */
+	timekeeper.ntp_error += tick_length << shift;
+	timekeeper.ntp_error -= timekeeper.xtime_interval <<
+				(timekeeper.ntp_error_shift + shift);
+
+	return offset;
+}
+
+/**
  * update_wall_time - Uses the current clocksource to increment the wall time
  *
  * Called from the timer interrupt, must hold a write on xtime_lock.
@@ -731,7 +774,7 @@ void update_wall_time(void)
 {
 	struct clocksource *clock;
 	cycle_t offset;
-	u64 nsecs;
+	int shift = 0, maxshift;
 
 	/* Make sure we're fully resumed: */
 	if (unlikely(timekeeping_suspended))
@@ -745,33 +788,22 @@ void update_wall_time(void)
 #endif
 	timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift;
 
-	/* normally this loop will run just once, however in the
-	 * case of lost or late ticks, it will accumulate correctly.
+	/*
+	 * With NO_HZ we may have to accumulate many cycle_intervals
+	 * (think "ticks") worth of time at once. To do this efficiently,
+	 * we calculate the largest doubling multiple of cycle_intervals
+	 * that is smaller then the offset. We then accumulate that
+	 * chunk in one go, and then try to consume the next smaller
+	 * doubled multiple.
 	 */
+	shift = ilog2(offset) - ilog2(timekeeper.cycle_interval);
+	shift = max(0, shift);
+	/* Bound shift to one less then what overflows tick_length */
+	maxshift = (8*sizeof(tick_length) - (ilog2(tick_length)+1)) - 1;
+	shift = min(shift, maxshift);
 	while (offset >= timekeeper.cycle_interval) {
-		u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
-
-		/* accumulate one interval */
-		offset -= timekeeper.cycle_interval;
-		clock->cycle_last += timekeeper.cycle_interval;
-
-		timekeeper.xtime_nsec += timekeeper.xtime_interval;
-		if (timekeeper.xtime_nsec >= nsecps) {
-			timekeeper.xtime_nsec -= nsecps;
-			xtime.tv_sec++;
-			second_overflow();
-		}
-
-		raw_time.tv_nsec += timekeeper.raw_interval;
-		if (raw_time.tv_nsec >= NSEC_PER_SEC) {
-			raw_time.tv_nsec -= NSEC_PER_SEC;
-			raw_time.tv_sec++;
-		}
-
-		/* accumulate error between NTP and clock interval */
-		timekeeper.ntp_error += tick_length;
-		timekeeper.ntp_error -= timekeeper.xtime_interval <<
-					timekeeper.ntp_error_shift;
+		offset = logarithmic_accumulation(offset, shift);
+		shift--;
 	}
 
 	/* correct the clock when NTP error is too big */
@@ -807,9 +839,6 @@ void update_wall_time(void)
 	timekeeper.ntp_error +=	timekeeper.xtime_nsec <<
 				timekeeper.ntp_error_shift;
 
-	nsecs = clocksource_cyc2ns(offset, timekeeper.mult, timekeeper.shift);
-	update_xtime_cache(nsecs);
-
 	/* check to see if there is a new clocksource to use */
 	update_vsyscall(&xtime, timekeeper.clock);
 }
@@ -846,13 +875,13 @@ void monotonic_to_bootbased(struct timespec *ts)
 
 unsigned long get_seconds(void)
 {
-	return xtime_cache.tv_sec;
+	return xtime.tv_sec;
 }
 EXPORT_SYMBOL(get_seconds);
 
 struct timespec __current_kernel_time(void)
 {
-	return xtime_cache;
+	return xtime;
 }
 
 struct timespec current_kernel_time(void)
@@ -862,8 +891,7 @@ struct timespec current_kernel_time(void)
 
 	do {
 		seq = read_seqbegin(&xtime_lock);
-
-		now = xtime_cache;
+		now = xtime;
 	} while (read_seqretry(&xtime_lock, seq));
 
 	return now;
@@ -877,8 +905,7 @@ struct timespec get_monotonic_coarse(void)
 
 	do {
 		seq = read_seqbegin(&xtime_lock);
-
-		now = xtime_cache;
+		now = xtime;
 		mono = wall_to_monotonic;
 	} while (read_seqretry(&xtime_lock, seq));
 
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 971c40ae15fd..3b891a14d1e5 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -204,10 +204,12 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
 		return;
 	}
 	SEQ_printf(m, "%s\n", dev->name);
-	SEQ_printf(m, " max_delta_ns:   %lu\n", dev->max_delta_ns);
-	SEQ_printf(m, " min_delta_ns:   %lu\n", dev->min_delta_ns);
-	SEQ_printf(m, " mult:           %lu\n", dev->mult);
-	SEQ_printf(m, " shift:          %d\n", dev->shift);
+	SEQ_printf(m, " max_delta_ns:   %llu\n",
+		   (unsigned long long) dev->max_delta_ns);
+	SEQ_printf(m, " min_delta_ns:   %llu\n",
+		   (unsigned long long) dev->min_delta_ns);
+	SEQ_printf(m, " mult:           %u\n", dev->mult);
+	SEQ_printf(m, " shift:          %u\n", dev->shift);
 	SEQ_printf(m, " mode:           %d\n", dev->mode);
 	SEQ_printf(m, " next_event:     %Ld nsecs\n",
 		   (unsigned long long) ktime_to_ns(dev->next_event));
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index b416512ad17f..d006554888dc 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -339,6 +339,27 @@ config POWER_TRACER
 	  power management decisions, specifically the C-state and P-state
 	  behavior.
 
+config KSYM_TRACER
+	bool "Trace read and write access on kernel memory locations"
+	depends on HAVE_HW_BREAKPOINT
+	select TRACING
+	help
+	  This tracer helps find read and write operations on any given kernel
+	  symbol i.e. /proc/kallsyms.
+
+config PROFILE_KSYM_TRACER
+	bool "Profile all kernel memory accesses on 'watched' variables"
+	depends on KSYM_TRACER
+	help
+	  This tracer profiles kernel accesses on variables watched through the
+	  ksym tracer ftrace plugin. Depending upon the hardware, all read
+	  and write operations on kernel variables can be monitored for
+	  accesses.
+
+	  The results will be displayed in:
+	  /debugfs/tracing/profile_ksym
+
+	  Say N if unsure.
 
 config STACK_TRACER
 	bool "Trace max stack"
@@ -428,6 +449,23 @@ config BLK_DEV_IO_TRACE
 
 	  If unsure, say N.
 
+config KPROBE_EVENT
+	depends on KPROBES
+	depends on X86
+	bool "Enable kprobes-based dynamic events"
+	select TRACING
+	default y
+	help
+	  This allows the user to add tracing events (similar to tracepoints) on the fly
+	  via the ftrace interface. See Documentation/trace/kprobetrace.txt
+	  for more details.
+
+	  Those events can be inserted wherever kprobes can probe, and record
+	  various register and memory values.
+
+	  This option is also required by perf-probe subcommand of perf tools. If
+	  you want to use perf tools, this option is strongly recommended.
+
 config DYNAMIC_FTRACE
 	bool "enable/disable ftrace tracepoints dynamically"
 	depends on FUNCTION_TRACER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 26f03ac07c2b..cd9ecd89ec77 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -53,6 +53,8 @@ obj-$(CONFIG_EVENT_TRACING) += trace_export.o
 obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
 obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
+obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
+obj-$(CONFIG_KSYM_TRACER) += trace_ksym.o
 obj-$(CONFIG_EVENT_TRACING) += power-traces.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6dc4e5ef7a01..7cb6f1922598 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -60,6 +60,13 @@ static int last_ftrace_enabled;
 /* Quick disabling of function tracer. */
 int function_trace_stop;
 
+/* List for set_ftrace_pid's pids. */
+LIST_HEAD(ftrace_pids);
+struct ftrace_pid {
+	struct list_head list;
+	struct pid *pid;
+};
+
 /*
  * ftrace_disabled is set when an anomaly is discovered.
  * ftrace_disabled is much stronger than ftrace_enabled.
@@ -78,6 +85,10 @@ ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
+#endif
+
 static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
 {
 	struct ftrace_ops *op = ftrace_list;
@@ -155,7 +166,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 		else
 			func = ftrace_list_func;
 
-		if (ftrace_pid_trace) {
+		if (!list_empty(&ftrace_pids)) {
 			set_ftrace_pid_function(func);
 			func = ftrace_pid_func;
 		}
@@ -203,7 +214,7 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 		if (ftrace_list->next == &ftrace_list_end) {
 			ftrace_func_t func = ftrace_list->func;
 
-			if (ftrace_pid_trace) {
+			if (!list_empty(&ftrace_pids)) {
 				set_ftrace_pid_function(func);
 				func = ftrace_pid_func;
 			}
@@ -231,7 +242,7 @@ static void ftrace_update_pid_func(void)
 	func = __ftrace_trace_function;
 #endif
 
-	if (ftrace_pid_trace) {
+	if (!list_empty(&ftrace_pids)) {
 		set_ftrace_pid_function(func);
 		func = ftrace_pid_func;
 	} else {
@@ -821,8 +832,6 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
 }
 #endif /* CONFIG_FUNCTION_PROFILER */
 
-/* set when tracing only a pid */
-struct pid *ftrace_pid_trace;
 static struct pid * const ftrace_swapper_pid = &init_struct_pid;
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -1261,12 +1270,34 @@ static int ftrace_update_code(struct module *mod)
 		ftrace_new_addrs = p->newlist;
 		p->flags = 0L;
 
-		/* convert record (i.e, patch mcount-call with NOP) */
-		if (ftrace_code_disable(mod, p)) {
-			p->flags |= FTRACE_FL_CONVERTED;
-			ftrace_update_cnt++;
-		} else
+		/*
+		 * Do the initial record convertion from mcount jump
+		 * to the NOP instructions.
+		 */
+		if (!ftrace_code_disable(mod, p)) {
 			ftrace_free_rec(p);
+			continue;
+		}
+
+		p->flags |= FTRACE_FL_CONVERTED;
+		ftrace_update_cnt++;
+
+		/*
+		 * If the tracing is enabled, go ahead and enable the record.
+		 *
+		 * The reason not to enable the record immediatelly is the
+		 * inherent check of ftrace_make_nop/ftrace_make_call for
+		 * correct previous instructions.  Making first the NOP
+		 * conversion puts the module to the correct state, thus
+		 * passing the ftrace_make_call check.
+		 */
+		if (ftrace_start_up) {
+			int failed = __ftrace_replace_code(p, 1);
+			if (failed) {
+				ftrace_bug(failed, p->ip);
+				ftrace_free_rec(p);
+			}
+		}
 	}
 
 	stop = ftrace_now(raw_smp_processor_id());
@@ -1656,60 +1687,6 @@ ftrace_regex_lseek(struct file *file, loff_t offset, int origin)
 	return ret;
 }
 
-enum {
-	MATCH_FULL,
-	MATCH_FRONT_ONLY,
-	MATCH_MIDDLE_ONLY,
-	MATCH_END_ONLY,
-};
-
-/*
- * (static function - no need for kernel doc)
- *
- * Pass in a buffer containing a glob and this function will
- * set search to point to the search part of the buffer and
- * return the type of search it is (see enum above).
- * This does modify buff.
- *
- * Returns enum type.
- *  search returns the pointer to use for comparison.
- *  not returns 1 if buff started with a '!'
- *     0 otherwise.
- */
-static int
-ftrace_setup_glob(char *buff, int len, char **search, int *not)
-{
-	int type = MATCH_FULL;
-	int i;
-
-	if (buff[0] == '!') {
-		*not = 1;
-		buff++;
-		len--;
-	} else
-		*not = 0;
-
-	*search = buff;
-
-	for (i = 0; i < len; i++) {
-		if (buff[i] == '*') {
-			if (!i) {
-				*search = buff + 1;
-				type = MATCH_END_ONLY;
-			} else {
-				if (type == MATCH_END_ONLY)
-					type = MATCH_MIDDLE_ONLY;
-				else
-					type = MATCH_FRONT_ONLY;
-				buff[i] = 0;
-				break;
-			}
-		}
-	}
-
-	return type;
-}
-
 static int ftrace_match(char *str, char *regex, int len, int type)
 {
 	int matched = 0;
@@ -1758,7 +1735,7 @@ static void ftrace_match_records(char *buff, int len, int enable)
 	int not;
 
 	flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
-	type = ftrace_setup_glob(buff, len, &search, &not);
+	type = filter_parse_regex(buff, len, &search, &not);
 
 	search_len = strlen(search);
 
@@ -1826,7 +1803,7 @@ static void ftrace_match_module_records(char *buff, char *mod, int enable)
 	}
 
 	if (strlen(buff)) {
-		type = ftrace_setup_glob(buff, strlen(buff), &search, &not);
+		type = filter_parse_regex(buff, strlen(buff), &search, &not);
 		search_len = strlen(search);
 	}
 
@@ -1991,7 +1968,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	int count = 0;
 	char *search;
 
-	type = ftrace_setup_glob(glob, strlen(glob), &search, &not);
+	type = filter_parse_regex(glob, strlen(glob), &search, &not);
 	len = strlen(search);
 
 	/* we do not support '!' for function probes */
@@ -2068,7 +2045,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	else if (glob) {
 		int not;
 
-		type = ftrace_setup_glob(glob, strlen(glob), &search, &not);
+		type = filter_parse_regex(glob, strlen(glob), &search, &not);
 		len = strlen(search);
 
 		/* we do not support '!' for function probes */
@@ -2297,6 +2274,7 @@ void ftrace_set_notrace(unsigned char *buf, int len, int reset)
 #define FTRACE_FILTER_SIZE		COMMAND_LINE_SIZE
 static char ftrace_notrace_buf[FTRACE_FILTER_SIZE] __initdata;
 static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata;
+static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
 
 static int __init set_ftrace_notrace(char *str)
 {
@@ -2312,6 +2290,31 @@ static int __init set_ftrace_filter(char *str)
 }
 __setup("ftrace_filter=", set_ftrace_filter);
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int __init set_graph_function(char *str)
+{
+	strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
+	return 1;
+}
+__setup("ftrace_graph_filter=", set_graph_function);
+
+static void __init set_ftrace_early_graph(char *buf)
+{
+	int ret;
+	char *func;
+
+	while (buf) {
+		func = strsep(&buf, ",");
+		/* we allow only one expression at a time */
+		ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
+				      func);
+		if (ret)
+			printk(KERN_DEBUG "ftrace: function %s not "
+					  "traceable\n", func);
+	}
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
 static void __init set_ftrace_early_filter(char *buf, int enable)
 {
 	char *func;
@@ -2328,6 +2331,10 @@ static void __init set_ftrace_early_filters(void)
 		set_ftrace_early_filter(ftrace_filter_buf, 1);
 	if (ftrace_notrace_buf[0])
 		set_ftrace_early_filter(ftrace_notrace_buf, 0);
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	if (ftrace_graph_buf[0])
+		set_ftrace_early_graph(ftrace_graph_buf);
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 }
 
 static int
@@ -2513,7 +2520,7 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
 		return -ENODEV;
 
 	/* decode regex */
-	type = ftrace_setup_glob(buffer, strlen(buffer), &search, &not);
+	type = filter_parse_regex(buffer, strlen(buffer), &search, &not);
 	if (not)
 		return -EINVAL;
 
@@ -2624,7 +2631,7 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
 	return 0;
 }
 
-static int ftrace_convert_nops(struct module *mod,
+static int ftrace_process_locs(struct module *mod,
 			       unsigned long *start,
 			       unsigned long *end)
 {
@@ -2684,7 +2691,7 @@ static void ftrace_init_module(struct module *mod,
 {
 	if (ftrace_disabled || start == end)
 		return;
-	ftrace_convert_nops(mod, start, end);
+	ftrace_process_locs(mod, start, end);
 }
 
 static int ftrace_module_notify(struct notifier_block *self,
@@ -2745,7 +2752,7 @@ void __init ftrace_init(void)
 
 	last_ftrace_enabled = ftrace_enabled = 1;
 
-	ret = ftrace_convert_nops(NULL,
+	ret = ftrace_process_locs(NULL,
 				  __start_mcount_loc,
 				  __stop_mcount_loc);
 
@@ -2778,23 +2785,6 @@ static inline void ftrace_startup_enable(int command) { }
 # define ftrace_shutdown_sysctl()	do { } while (0)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
-static ssize_t
-ftrace_pid_read(struct file *file, char __user *ubuf,
-		       size_t cnt, loff_t *ppos)
-{
-	char buf[64];
-	int r;
-
-	if (ftrace_pid_trace == ftrace_swapper_pid)
-		r = sprintf(buf, "swapper tasks\n");
-	else if (ftrace_pid_trace)
-		r = sprintf(buf, "%u\n", pid_vnr(ftrace_pid_trace));
-	else
-		r = sprintf(buf, "no pid\n");
-
-	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
-}
-
 static void clear_ftrace_swapper(void)
 {
 	struct task_struct *p;
@@ -2845,14 +2835,12 @@ static void set_ftrace_pid(struct pid *pid)
 	rcu_read_unlock();
 }
 
-static void clear_ftrace_pid_task(struct pid **pid)
+static void clear_ftrace_pid_task(struct pid *pid)
 {
-	if (*pid == ftrace_swapper_pid)
+	if (pid == ftrace_swapper_pid)
 		clear_ftrace_swapper();
 	else
-		clear_ftrace_pid(*pid);
-
-	*pid = NULL;
+		clear_ftrace_pid(pid);
 }
 
 static void set_ftrace_pid_task(struct pid *pid)
@@ -2863,11 +2851,140 @@ static void set_ftrace_pid_task(struct pid *pid)
 		set_ftrace_pid(pid);
 }
 
+static int ftrace_pid_add(int p)
+{
+	struct pid *pid;
+	struct ftrace_pid *fpid;
+	int ret = -EINVAL;
+
+	mutex_lock(&ftrace_lock);
+
+	if (!p)
+		pid = ftrace_swapper_pid;
+	else
+		pid = find_get_pid(p);
+
+	if (!pid)
+		goto out;
+
+	ret = 0;
+
+	list_for_each_entry(fpid, &ftrace_pids, list)
+		if (fpid->pid == pid)
+			goto out_put;
+
+	ret = -ENOMEM;
+
+	fpid = kmalloc(sizeof(*fpid), GFP_KERNEL);
+	if (!fpid)
+		goto out_put;
+
+	list_add(&fpid->list, &ftrace_pids);
+	fpid->pid = pid;
+
+	set_ftrace_pid_task(pid);
+
+	ftrace_update_pid_func();
+	ftrace_startup_enable(0);
+
+	mutex_unlock(&ftrace_lock);
+	return 0;
+
+out_put:
+	if (pid != ftrace_swapper_pid)
+		put_pid(pid);
+
+out:
+	mutex_unlock(&ftrace_lock);
+	return ret;
+}
+
+static void ftrace_pid_reset(void)
+{
+	struct ftrace_pid *fpid, *safe;
+
+	mutex_lock(&ftrace_lock);
+	list_for_each_entry_safe(fpid, safe, &ftrace_pids, list) {
+		struct pid *pid = fpid->pid;
+
+		clear_ftrace_pid_task(pid);
+
+		list_del(&fpid->list);
+		kfree(fpid);
+	}
+
+	ftrace_update_pid_func();
+	ftrace_startup_enable(0);
+
+	mutex_unlock(&ftrace_lock);
+}
+
+static void *fpid_start(struct seq_file *m, loff_t *pos)
+{
+	mutex_lock(&ftrace_lock);
+
+	if (list_empty(&ftrace_pids) && (!*pos))
+		return (void *) 1;
+
+	return seq_list_start(&ftrace_pids, *pos);
+}
+
+static void *fpid_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	if (v == (void *)1)
+		return NULL;
+
+	return seq_list_next(v, &ftrace_pids, pos);
+}
+
+static void fpid_stop(struct seq_file *m, void *p)
+{
+	mutex_unlock(&ftrace_lock);
+}
+
+static int fpid_show(struct seq_file *m, void *v)
+{
+	const struct ftrace_pid *fpid = list_entry(v, struct ftrace_pid, list);
+
+	if (v == (void *)1) {
+		seq_printf(m, "no pid\n");
+		return 0;
+	}
+
+	if (fpid->pid == ftrace_swapper_pid)
+		seq_printf(m, "swapper tasks\n");
+	else
+		seq_printf(m, "%u\n", pid_vnr(fpid->pid));
+
+	return 0;
+}
+
+static const struct seq_operations ftrace_pid_sops = {
+	.start = fpid_start,
+	.next = fpid_next,
+	.stop = fpid_stop,
+	.show = fpid_show,
+};
+
+static int
+ftrace_pid_open(struct inode *inode, struct file *file)
+{
+	int ret = 0;
+
+	if ((file->f_mode & FMODE_WRITE) &&
+	    (file->f_flags & O_TRUNC))
+		ftrace_pid_reset();
+
+	if (file->f_mode & FMODE_READ)
+		ret = seq_open(file, &ftrace_pid_sops);
+
+	return ret;
+}
+
 static ssize_t
 ftrace_pid_write(struct file *filp, const char __user *ubuf,
 		   size_t cnt, loff_t *ppos)
 {
-	struct pid *pid;
 	char buf[64];
 	long val;
 	int ret;
@@ -2880,57 +2997,38 @@ ftrace_pid_write(struct file *filp, const char __user *ubuf,
 
 	buf[cnt] = 0;
 
+	/*
+	 * Allow "echo > set_ftrace_pid" or "echo -n '' > set_ftrace_pid"
+	 * to clean the filter quietly.
+	 */
+	strstrip(buf);
+	if (strlen(buf) == 0)
+		return 1;
+
 	ret = strict_strtol(buf, 10, &val);
 	if (ret < 0)
 		return ret;
 
-	mutex_lock(&ftrace_lock);
-	if (val < 0) {
-		/* disable pid tracing */
-		if (!ftrace_pid_trace)
-			goto out;
-
-		clear_ftrace_pid_task(&ftrace_pid_trace);
-
-	} else {
-		/* swapper task is special */
-		if (!val) {
-			pid = ftrace_swapper_pid;
-			if (pid == ftrace_pid_trace)
-				goto out;
-		} else {
-			pid = find_get_pid(val);
+	ret = ftrace_pid_add(val);
 
-			if (pid == ftrace_pid_trace) {
-				put_pid(pid);
-				goto out;
-			}
-		}
-
-		if (ftrace_pid_trace)
-			clear_ftrace_pid_task(&ftrace_pid_trace);
-
-		if (!pid)
-			goto out;
-
-		ftrace_pid_trace = pid;
-
-		set_ftrace_pid_task(ftrace_pid_trace);
-	}
-
-	/* update the function call */
-	ftrace_update_pid_func();
-	ftrace_startup_enable(0);
+	return ret ? ret : cnt;
+}
 
- out:
-	mutex_unlock(&ftrace_lock);
+static int
+ftrace_pid_release(struct inode *inode, struct file *file)
+{
+	if (file->f_mode & FMODE_READ)
+		seq_release(inode, file);
 
-	return cnt;
+	return 0;
 }
 
 static const struct file_operations ftrace_pid_fops = {
-	.read = ftrace_pid_read,
-	.write = ftrace_pid_write,
+	.open		= ftrace_pid_open,
+	.write		= ftrace_pid_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= ftrace_pid_release,
 };
 
 static __init int ftrace_init_debugfs(void)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 5dd017fea6f5..db223fe8887f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -397,18 +397,21 @@ int ring_buffer_print_page_header(struct trace_seq *s)
 	int ret;
 
 	ret = trace_seq_printf(s, "\tfield: u64 timestamp;\t"
-			       "offset:0;\tsize:%u;\n",
-			       (unsigned int)sizeof(field.time_stamp));
+			       "offset:0;\tsize:%u;\tsigned:%u;\n",
+			       (unsigned int)sizeof(field.time_stamp),
+			       (unsigned int)is_signed_type(u64));
 
 	ret = trace_seq_printf(s, "\tfield: local_t commit;\t"
-			       "offset:%u;\tsize:%u;\n",
+			       "offset:%u;\tsize:%u;\tsigned:%u;\n",
 			       (unsigned int)offsetof(typeof(field), commit),
-			       (unsigned int)sizeof(field.commit));
+			       (unsigned int)sizeof(field.commit),
+			       (unsigned int)is_signed_type(long));
 
 	ret = trace_seq_printf(s, "\tfield: char data;\t"
-			       "offset:%u;\tsize:%u;\n",
+			       "offset:%u;\tsize:%u;\tsigned:%u;\n",
 			       (unsigned int)offsetof(typeof(field), data),
-			       (unsigned int)BUF_PAGE_SIZE);
+			       (unsigned int)BUF_PAGE_SIZE,
+			       (unsigned int)is_signed_type(char));
 
 	return ret;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7b49b6751790..1fe8a0e2978f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -129,7 +129,7 @@ static int tracing_set_tracer(const char *buf);
 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
 static char *default_bootup_tracer;
 
-static int __init set_ftrace(char *str)
+static int __init set_cmdline_ftrace(char *str)
 {
 	strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
 	default_bootup_tracer = bootup_tracer_buf;
@@ -137,7 +137,7 @@ static int __init set_ftrace(char *str)
 	ring_buffer_expanded = 1;
 	return 1;
 }
-__setup("ftrace=", set_ftrace);
+__setup("ftrace=", set_cmdline_ftrace);
 
 static int __init set_ftrace_dump_on_oops(char *str)
 {
@@ -3730,7 +3730,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 
 	s = kmalloc(sizeof(*s), GFP_KERNEL);
 	if (!s)
-		return ENOMEM;
+		return -ENOMEM;
 
 	trace_seq_init(s);
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 405cb850b75d..4da6ede74401 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -11,6 +11,7 @@
 #include <linux/ftrace.h>
 #include <trace/boot.h>
 #include <linux/kmemtrace.h>
+#include <linux/hw_breakpoint.h>
 
 #include <linux/trace_seq.h>
 #include <linux/ftrace_event.h>
@@ -37,6 +38,7 @@ enum trace_type {
 	TRACE_KMEM_ALLOC,
 	TRACE_KMEM_FREE,
 	TRACE_BLK,
+	TRACE_KSYM,
 
 	__TRACE_LAST_TYPE,
 };
@@ -101,6 +103,29 @@ struct syscall_trace_exit {
 	unsigned long		ret;
 };
 
+struct kprobe_trace_entry {
+	struct trace_entry	ent;
+	unsigned long		ip;
+	int			nargs;
+	unsigned long		args[];
+};
+
+#define SIZEOF_KPROBE_TRACE_ENTRY(n)			\
+	(offsetof(struct kprobe_trace_entry, args) +	\
+	(sizeof(unsigned long) * (n)))
+
+struct kretprobe_trace_entry {
+	struct trace_entry	ent;
+	unsigned long		func;
+	unsigned long		ret_ip;
+	int			nargs;
+	unsigned long		args[];
+};
+
+#define SIZEOF_KRETPROBE_TRACE_ENTRY(n)			\
+	(offsetof(struct kretprobe_trace_entry, args) +	\
+	(sizeof(unsigned long) * (n)))
+
 /*
  * trace_flag_type is an enumeration that holds different
  * states when a trace occurs. These are:
@@ -209,6 +234,7 @@ extern void __ftrace_bad_type(void);
 			  TRACE_KMEM_ALLOC);	\
 		IF_ASSIGN(var, ent, struct kmemtrace_free_entry,	\
 			  TRACE_KMEM_FREE);	\
+		IF_ASSIGN(var, ent, struct ksym_trace_entry, TRACE_KSYM);\
 		__ftrace_bad_type();					\
 	} while (0)
 
@@ -364,6 +390,8 @@ int register_tracer(struct tracer *type);
 void unregister_tracer(struct tracer *type);
 int is_tracing_stopped(void);
 
+extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr);
+
 extern unsigned long nsecs_to_usecs(unsigned long nsecs);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
@@ -438,6 +466,8 @@ extern int trace_selftest_startup_branch(struct tracer *trace,
 					 struct trace_array *tr);
 extern int trace_selftest_startup_hw_branches(struct tracer *trace,
 					      struct trace_array *tr);
+extern int trace_selftest_startup_ksym(struct tracer *trace,
+					 struct trace_array *tr);
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
@@ -483,10 +513,6 @@ static inline int ftrace_graph_addr(unsigned long addr)
 	return 0;
 }
 #else
-static inline int ftrace_trace_addr(unsigned long addr)
-{
-	return 1;
-}
 static inline int ftrace_graph_addr(unsigned long addr)
 {
 	return 1;
@@ -500,12 +526,12 @@ print_graph_function(struct trace_iterator *iter)
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
-extern struct pid *ftrace_pid_trace;
+extern struct list_head ftrace_pids;
 
 #ifdef CONFIG_FUNCTION_TRACER
 static inline int ftrace_trace_task(struct task_struct *task)
 {
-	if (!ftrace_pid_trace)
+	if (list_empty(&ftrace_pids))
 		return 1;
 
 	return test_tsk_trace_trace(task);
@@ -687,7 +713,6 @@ struct event_filter {
 	int			n_preds;
 	struct filter_pred	**preds;
 	char			*filter_string;
-	bool			no_reset;
 };
 
 struct event_subsystem {
@@ -699,22 +724,40 @@ struct event_subsystem {
 };
 
 struct filter_pred;
+struct regex;
 
 typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
 				 int val1, int val2);
 
+typedef int (*regex_match_func)(char *str, struct regex *r, int len);
+
+enum regex_type {
+	MATCH_FULL = 0,
+	MATCH_FRONT_ONLY,
+	MATCH_MIDDLE_ONLY,
+	MATCH_END_ONLY,
+};
+
+struct regex {
+	char			pattern[MAX_FILTER_STR_VAL];
+	int			len;
+	int			field_len;
+	regex_match_func	match;
+};
+
 struct filter_pred {
-	filter_pred_fn_t fn;
-	u64 val;
-	char str_val[MAX_FILTER_STR_VAL];
-	int str_len;
-	char *field_name;
-	int offset;
-	int not;
-	int op;
-	int pop_n;
+	filter_pred_fn_t 	fn;
+	u64 			val;
+	struct regex		regex;
+	char 			*field_name;
+	int 			offset;
+	int 			not;
+	int 			op;
+	int 			pop_n;
 };
 
+extern enum regex_type
+filter_parse_regex(char *buff, int len, char **search, int *not);
 extern void print_event_filter(struct ftrace_event_call *call,
 			       struct trace_seq *s);
 extern int apply_event_filter(struct ftrace_event_call *call,
@@ -730,7 +773,8 @@ filter_check_discard(struct ftrace_event_call *call, void *rec,
 		     struct ring_buffer *buffer,
 		     struct ring_buffer_event *event)
 {
-	if (unlikely(call->filter_active) && !filter_match_preds(call, rec)) {
+	if (unlikely(call->filter_active) &&
+	    !filter_match_preds(call->filter, rec)) {
 		ring_buffer_discard_commit(buffer, event);
 		return 1;
 	}
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index ead3d724599d..c16a08f399df 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -364,3 +364,19 @@ FTRACE_ENTRY(kmem_free, kmemtrace_free_entry,
 	F_printk("type:%u call_site:%lx ptr:%p",
 		 __entry->type_id, __entry->call_site, __entry->ptr)
 );
+
+FTRACE_ENTRY(ksym_trace, ksym_trace_entry,
+
+	TRACE_KSYM,
+
+	F_STRUCT(
+		__field(	unsigned long,	ip			  )
+		__field(	unsigned char,	type			  )
+		__array(	char	     ,	cmd,	   TASK_COMM_LEN  )
+		__field(	unsigned long,  addr			  )
+	),
+
+	F_printk("ip: %pF type: %d ksym_name: %pS cmd: %s",
+		(void *)__entry->ip, (unsigned int)__entry->type,
+		(void *)__entry->addr,  __entry->cmd)
+);
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c
index 8d5c171cc998..d9c60f80aa0d 100644
--- a/kernel/trace/trace_event_profile.c
+++ b/kernel/trace/trace_event_profile.c
@@ -8,17 +8,14 @@
 #include <linux/module.h>
 #include "trace.h"
 
-/*
- * We can't use a size but a type in alloc_percpu()
- * So let's create a dummy type that matches the desired size
- */
-typedef struct {char buf[FTRACE_MAX_PROFILE_SIZE];} profile_buf_t;
 
-char		*trace_profile_buf;
-EXPORT_SYMBOL_GPL(trace_profile_buf);
+char *perf_trace_buf;
+EXPORT_SYMBOL_GPL(perf_trace_buf);
+
+char *perf_trace_buf_nmi;
+EXPORT_SYMBOL_GPL(perf_trace_buf_nmi);
 
-char		*trace_profile_buf_nmi;
-EXPORT_SYMBOL_GPL(trace_profile_buf_nmi);
+typedef typeof(char [FTRACE_MAX_PROFILE_SIZE]) perf_trace_t ;
 
 /* Count the events in use (per event id, not per instance) */
 static int	total_profile_count;
@@ -32,20 +29,20 @@ static int ftrace_profile_enable_event(struct ftrace_event_call *event)
 		return 0;
 
 	if (!total_profile_count) {
-		buf = (char *)alloc_percpu(profile_buf_t);
+		buf = (char *)alloc_percpu(perf_trace_t);
 		if (!buf)
 			goto fail_buf;
 
-		rcu_assign_pointer(trace_profile_buf, buf);
+		rcu_assign_pointer(perf_trace_buf, buf);
 
-		buf = (char *)alloc_percpu(profile_buf_t);
+		buf = (char *)alloc_percpu(perf_trace_t);
 		if (!buf)
 			goto fail_buf_nmi;
 
-		rcu_assign_pointer(trace_profile_buf_nmi, buf);
+		rcu_assign_pointer(perf_trace_buf_nmi, buf);
 	}
 
-	ret = event->profile_enable();
+	ret = event->profile_enable(event);
 	if (!ret) {
 		total_profile_count++;
 		return 0;
@@ -53,10 +50,10 @@ static int ftrace_profile_enable_event(struct ftrace_event_call *event)
 
 fail_buf_nmi:
 	if (!total_profile_count) {
-		free_percpu(trace_profile_buf_nmi);
-		free_percpu(trace_profile_buf);
-		trace_profile_buf_nmi = NULL;
-		trace_profile_buf = NULL;
+		free_percpu(perf_trace_buf_nmi);
+		free_percpu(perf_trace_buf);
+		perf_trace_buf_nmi = NULL;
+		perf_trace_buf = NULL;
 	}
 fail_buf:
 	atomic_dec(&event->profile_count);
@@ -89,14 +86,14 @@ static void ftrace_profile_disable_event(struct ftrace_event_call *event)
 	if (!atomic_add_negative(-1, &event->profile_count))
 		return;
 
-	event->profile_disable();
+	event->profile_disable(event);
 
 	if (!--total_profile_count) {
-		buf = trace_profile_buf;
-		rcu_assign_pointer(trace_profile_buf, NULL);
+		buf = perf_trace_buf;
+		rcu_assign_pointer(perf_trace_buf, NULL);
 
-		nmi_buf = trace_profile_buf_nmi;
-		rcu_assign_pointer(trace_profile_buf_nmi, NULL);
+		nmi_buf = perf_trace_buf_nmi;
+		rcu_assign_pointer(perf_trace_buf_nmi, NULL);
 
 		/*
 		 * Ensure every events in profiling have finished before
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index d128f65778e6..1d18315dc836 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -93,9 +93,7 @@ int trace_define_common_fields(struct ftrace_event_call *call)
 }
 EXPORT_SYMBOL_GPL(trace_define_common_fields);
 
-#ifdef CONFIG_MODULES
-
-static void trace_destroy_fields(struct ftrace_event_call *call)
+void trace_destroy_fields(struct ftrace_event_call *call)
 {
 	struct ftrace_event_field *field, *next;
 
@@ -107,8 +105,6 @@ static void trace_destroy_fields(struct ftrace_event_call *call)
 	}
 }
 
-#endif /* CONFIG_MODULES */
-
 static void ftrace_event_enable_disable(struct ftrace_event_call *call,
 					int enable)
 {
@@ -117,14 +113,14 @@ static void ftrace_event_enable_disable(struct ftrace_event_call *call,
 		if (call->enabled) {
 			call->enabled = 0;
 			tracing_stop_cmdline_record();
-			call->unregfunc(call->data);
+			call->unregfunc(call);
 		}
 		break;
 	case 1:
 		if (!call->enabled) {
 			call->enabled = 1;
 			tracing_start_cmdline_record();
-			call->regfunc(call->data);
+			call->regfunc(call);
 		}
 		break;
 	}
@@ -507,7 +503,7 @@ extern char *__bad_type_size(void);
 #define FIELD(type, name)						\
 	sizeof(type) != sizeof(field.name) ? __bad_type_size() :	\
 	#type, "common_" #name, offsetof(typeof(field), name),		\
-		sizeof(field.name)
+		sizeof(field.name), is_signed_type(type)
 
 static int trace_write_header(struct trace_seq *s)
 {
@@ -515,17 +511,17 @@ static int trace_write_header(struct trace_seq *s)
 
 	/* struct trace_entry */
 	return trace_seq_printf(s,
-				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-				"\n",
-				FIELD(unsigned short, type),
-				FIELD(unsigned char, flags),
-				FIELD(unsigned char, preempt_count),
-				FIELD(int, pid),
-				FIELD(int, lock_depth));
+			"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+			"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+			"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+			"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+			"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+			"\n",
+			FIELD(unsigned short, type),
+			FIELD(unsigned char, flags),
+			FIELD(unsigned char, preempt_count),
+			FIELD(int, pid),
+			FIELD(int, lock_depth));
 }
 
 static ssize_t
@@ -878,9 +874,9 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 			   "'%s/filter' entry\n", name);
 	}
 
-	entry = trace_create_file("enable", 0644, system->entry,
-				  (void *)system->name,
-				  &ftrace_system_enable_fops);
+	trace_create_file("enable", 0644, system->entry,
+			  (void *)system->name,
+			  &ftrace_system_enable_fops);
 
 	return system->entry;
 }
@@ -892,7 +888,6 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 		 const struct file_operations *filter,
 		 const struct file_operations *format)
 {
-	struct dentry *entry;
 	int ret;
 
 	/*
@@ -910,12 +905,12 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 	}
 
 	if (call->regfunc)
-		entry = trace_create_file("enable", 0644, call->dir, call,
-					  enable);
+		trace_create_file("enable", 0644, call->dir, call,
+				  enable);
 
 	if (call->id && call->profile_enable)
-		entry = trace_create_file("id", 0444, call->dir, call,
-					  id);
+		trace_create_file("id", 0444, call->dir, call,
+		 		  id);
 
 	if (call->define_fields) {
 		ret = call->define_fields(call);
@@ -924,41 +919,60 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 				   " events/%s\n", call->name);
 			return ret;
 		}
-		entry = trace_create_file("filter", 0644, call->dir, call,
-					  filter);
+		trace_create_file("filter", 0644, call->dir, call,
+				  filter);
 	}
 
 	/* A trace may not want to export its format */
 	if (!call->show_format)
 		return 0;
 
-	entry = trace_create_file("format", 0444, call->dir, call,
-				  format);
+	trace_create_file("format", 0444, call->dir, call,
+			  format);
 
 	return 0;
 }
 
-#define for_each_event(event, start, end)			\
-	for (event = start;					\
-	     (unsigned long)event < (unsigned long)end;		\
-	     event++)
+static int __trace_add_event_call(struct ftrace_event_call *call)
+{
+	struct dentry *d_events;
+	int ret;
 
-#ifdef CONFIG_MODULES
+	if (!call->name)
+		return -EINVAL;
 
-static LIST_HEAD(ftrace_module_file_list);
+	if (call->raw_init) {
+		ret = call->raw_init(call);
+		if (ret < 0) {
+			if (ret != -ENOSYS)
+				pr_warning("Could not initialize trace "
+				"events/%s\n", call->name);
+			return ret;
+		}
+	}
 
-/*
- * Modules must own their file_operations to keep up with
- * reference counting.
- */
-struct ftrace_module_file_ops {
-	struct list_head		list;
-	struct module			*mod;
-	struct file_operations		id;
-	struct file_operations		enable;
-	struct file_operations		format;
-	struct file_operations		filter;
-};
+	d_events = event_trace_events_dir();
+	if (!d_events)
+		return -ENOENT;
+
+	ret = event_create_dir(call, d_events, &ftrace_event_id_fops,
+				&ftrace_enable_fops, &ftrace_event_filter_fops,
+				&ftrace_event_format_fops);
+	if (!ret)
+		list_add(&call->list, &ftrace_events);
+
+	return ret;
+}
+
+/* Add an additional event_call dynamically */
+int trace_add_event_call(struct ftrace_event_call *call)
+{
+	int ret;
+	mutex_lock(&event_mutex);
+	ret = __trace_add_event_call(call);
+	mutex_unlock(&event_mutex);
+	return ret;
+}
 
 static void remove_subsystem_dir(const char *name)
 {
@@ -986,6 +1000,53 @@ static void remove_subsystem_dir(const char *name)
 	}
 }
 
+/*
+ * Must be called under locking both of event_mutex and trace_event_mutex.
+ */
+static void __trace_remove_event_call(struct ftrace_event_call *call)
+{
+	ftrace_event_enable_disable(call, 0);
+	if (call->event)
+		__unregister_ftrace_event(call->event);
+	debugfs_remove_recursive(call->dir);
+	list_del(&call->list);
+	trace_destroy_fields(call);
+	destroy_preds(call);
+	remove_subsystem_dir(call->system);
+}
+
+/* Remove an event_call */
+void trace_remove_event_call(struct ftrace_event_call *call)
+{
+	mutex_lock(&event_mutex);
+	down_write(&trace_event_mutex);
+	__trace_remove_event_call(call);
+	up_write(&trace_event_mutex);
+	mutex_unlock(&event_mutex);
+}
+
+#define for_each_event(event, start, end)			\
+	for (event = start;					\
+	     (unsigned long)event < (unsigned long)end;		\
+	     event++)
+
+#ifdef CONFIG_MODULES
+
+static LIST_HEAD(ftrace_module_file_list);
+
+/*
+ * Modules must own their file_operations to keep up with
+ * reference counting.
+ */
+struct ftrace_module_file_ops {
+	struct list_head		list;
+	struct module			*mod;
+	struct file_operations		id;
+	struct file_operations		enable;
+	struct file_operations		format;
+	struct file_operations		filter;
+};
+
 static struct ftrace_module_file_ops *
 trace_create_file_ops(struct module *mod)
 {
@@ -1043,7 +1104,7 @@ static void trace_module_add_events(struct module *mod)
 		if (!call->name)
 			continue;
 		if (call->raw_init) {
-			ret = call->raw_init();
+			ret = call->raw_init(call);
 			if (ret < 0) {
 				if (ret != -ENOSYS)
 					pr_warning("Could not initialize trace "
@@ -1061,10 +1122,11 @@ static void trace_module_add_events(struct module *mod)
 				return;
 		}
 		call->mod = mod;
-		list_add(&call->list, &ftrace_events);
-		event_create_dir(call, d_events,
-				 &file_ops->id, &file_ops->enable,
-				 &file_ops->filter, &file_ops->format);
+		ret = event_create_dir(call, d_events,
+				       &file_ops->id, &file_ops->enable,
+				       &file_ops->filter, &file_ops->format);
+		if (!ret)
+			list_add(&call->list, &ftrace_events);
 	}
 }
 
@@ -1078,14 +1140,7 @@ static void trace_module_remove_events(struct module *mod)
 	list_for_each_entry_safe(call, p, &ftrace_events, list) {
 		if (call->mod == mod) {
 			found = true;
-			ftrace_event_enable_disable(call, 0);
-			if (call->event)
-				__unregister_ftrace_event(call->event);
-			debugfs_remove_recursive(call->dir);
-			list_del(&call->list);
-			trace_destroy_fields(call);
-			destroy_preds(call);
-			remove_subsystem_dir(call->system);
+			__trace_remove_event_call(call);
 		}
 	}
 
@@ -1203,7 +1258,7 @@ static __init int event_trace_init(void)
 		if (!call->name)
 			continue;
 		if (call->raw_init) {
-			ret = call->raw_init();
+			ret = call->raw_init(call);
 			if (ret < 0) {
 				if (ret != -ENOSYS)
 					pr_warning("Could not initialize trace "
@@ -1211,10 +1266,12 @@ static __init int event_trace_init(void)
 				continue;
 			}
 		}
-		list_add(&call->list, &ftrace_events);
-		event_create_dir(call, d_events, &ftrace_event_id_fops,
-				 &ftrace_enable_fops, &ftrace_event_filter_fops,
-				 &ftrace_event_format_fops);
+		ret = event_create_dir(call, d_events, &ftrace_event_id_fops,
+				       &ftrace_enable_fops,
+				       &ftrace_event_filter_fops,
+				       &ftrace_event_format_fops);
+		if (!ret)
+			list_add(&call->list, &ftrace_events);
 	}
 
 	while (true) {
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 98a6cc5c64ed..50504cb228de 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -18,11 +18,10 @@
  * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
  */
 
-#include <linux/debugfs.h>
-#include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/mutex.h>
+#include <linux/perf_event.h>
 
 #include "trace.h"
 #include "trace_output.h"
@@ -31,6 +30,7 @@ enum filter_op_ids
 {
 	OP_OR,
 	OP_AND,
+	OP_GLOB,
 	OP_NE,
 	OP_EQ,
 	OP_LT,
@@ -48,16 +48,17 @@ struct filter_op {
 };
 
 static struct filter_op filter_ops[] = {
-	{ OP_OR, "||", 1 },
-	{ OP_AND, "&&", 2 },
-	{ OP_NE, "!=", 4 },
-	{ OP_EQ, "==", 4 },
-	{ OP_LT, "<", 5 },
-	{ OP_LE, "<=", 5 },
-	{ OP_GT, ">", 5 },
-	{ OP_GE, ">=", 5 },
-	{ OP_NONE, "OP_NONE", 0 },
-	{ OP_OPEN_PAREN, "(", 0 },
+	{ OP_OR,	"||",		1 },
+	{ OP_AND,	"&&",		2 },
+	{ OP_GLOB,	"~",		4 },
+	{ OP_NE,	"!=",		4 },
+	{ OP_EQ,	"==",		4 },
+	{ OP_LT,	"<",		5 },
+	{ OP_LE,	"<=",		5 },
+	{ OP_GT,	">",		5 },
+	{ OP_GE,	">=",		5 },
+	{ OP_NONE,	"OP_NONE",	0 },
+	{ OP_OPEN_PAREN, "(",		0 },
 };
 
 enum {
@@ -197,9 +198,9 @@ static int filter_pred_string(struct filter_pred *pred, void *event,
 	char *addr = (char *)(event + pred->offset);
 	int cmp, match;
 
-	cmp = strncmp(addr, pred->str_val, pred->str_len);
+	cmp = pred->regex.match(addr, &pred->regex, pred->regex.field_len);
 
-	match = (!cmp) ^ pred->not;
+	match = cmp ^ pred->not;
 
 	return match;
 }
@@ -211,9 +212,9 @@ static int filter_pred_pchar(struct filter_pred *pred, void *event,
 	char **addr = (char **)(event + pred->offset);
 	int cmp, match;
 
-	cmp = strncmp(*addr, pred->str_val, pred->str_len);
+	cmp = pred->regex.match(*addr, &pred->regex, pred->regex.field_len);
 
-	match = (!cmp) ^ pred->not;
+	match = cmp ^ pred->not;
 
 	return match;
 }
@@ -237,9 +238,9 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event,
 	char *addr = (char *)(event + str_loc);
 	int cmp, match;
 
-	cmp = strncmp(addr, pred->str_val, str_len);
+	cmp = pred->regex.match(addr, &pred->regex, str_len);
 
-	match = (!cmp) ^ pred->not;
+	match = cmp ^ pred->not;
 
 	return match;
 }
@@ -250,10 +251,121 @@ static int filter_pred_none(struct filter_pred *pred, void *event,
 	return 0;
 }
 
+/* Basic regex callbacks */
+static int regex_match_full(char *str, struct regex *r, int len)
+{
+	if (strncmp(str, r->pattern, len) == 0)
+		return 1;
+	return 0;
+}
+
+static int regex_match_front(char *str, struct regex *r, int len)
+{
+	if (strncmp(str, r->pattern, len) == 0)
+		return 1;
+	return 0;
+}
+
+static int regex_match_middle(char *str, struct regex *r, int len)
+{
+	if (strstr(str, r->pattern))
+		return 1;
+	return 0;
+}
+
+static int regex_match_end(char *str, struct regex *r, int len)
+{
+	char *ptr = strstr(str, r->pattern);
+
+	if (ptr && (ptr[r->len] == 0))
+		return 1;
+	return 0;
+}
+
+/**
+ * filter_parse_regex - parse a basic regex
+ * @buff:   the raw regex
+ * @len:    length of the regex
+ * @search: will point to the beginning of the string to compare
+ * @not:    tell whether the match will have to be inverted
+ *
+ * This passes in a buffer containing a regex and this function will
+ * set search to point to the search part of the buffer and
+ * return the type of search it is (see enum above).
+ * This does modify buff.
+ *
+ * Returns enum type.
+ *  search returns the pointer to use for comparison.
+ *  not returns 1 if buff started with a '!'
+ *     0 otherwise.
+ */
+enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not)
+{
+	int type = MATCH_FULL;
+	int i;
+
+	if (buff[0] == '!') {
+		*not = 1;
+		buff++;
+		len--;
+	} else
+		*not = 0;
+
+	*search = buff;
+
+	for (i = 0; i < len; i++) {
+		if (buff[i] == '*') {
+			if (!i) {
+				*search = buff + 1;
+				type = MATCH_END_ONLY;
+			} else {
+				if (type == MATCH_END_ONLY)
+					type = MATCH_MIDDLE_ONLY;
+				else
+					type = MATCH_FRONT_ONLY;
+				buff[i] = 0;
+				break;
+			}
+		}
+	}
+
+	return type;
+}
+
+static void filter_build_regex(struct filter_pred *pred)
+{
+	struct regex *r = &pred->regex;
+	char *search;
+	enum regex_type type = MATCH_FULL;
+	int not = 0;
+
+	if (pred->op == OP_GLOB) {
+		type = filter_parse_regex(r->pattern, r->len, &search, &not);
+		r->len = strlen(search);
+		memmove(r->pattern, search, r->len+1);
+	}
+
+	switch (type) {
+	case MATCH_FULL:
+		r->match = regex_match_full;
+		break;
+	case MATCH_FRONT_ONLY:
+		r->match = regex_match_front;
+		break;
+	case MATCH_MIDDLE_ONLY:
+		r->match = regex_match_middle;
+		break;
+	case MATCH_END_ONLY:
+		r->match = regex_match_end;
+		break;
+	}
+
+	pred->not ^= not;
+}
+
 /* return 1 if event matches, 0 otherwise (discard) */
-int filter_match_preds(struct ftrace_event_call *call, void *rec)
+int filter_match_preds(struct event_filter *filter, void *rec)
 {
-	struct event_filter *filter = call->filter;
 	int match, top = 0, val1 = 0, val2 = 0;
 	int stack[MAX_FILTER_PRED];
 	struct filter_pred *pred;
@@ -396,7 +508,7 @@ static void filter_clear_pred(struct filter_pred *pred)
 {
 	kfree(pred->field_name);
 	pred->field_name = NULL;
-	pred->str_len = 0;
+	pred->regex.len = 0;
 }
 
 static int filter_set_pred(struct filter_pred *dest,
@@ -426,9 +538,8 @@ static void filter_disable_preds(struct ftrace_event_call *call)
 		filter->preds[i]->fn = filter_pred_none;
 }
 
-void destroy_preds(struct ftrace_event_call *call)
+static void __free_preds(struct event_filter *filter)
 {
-	struct event_filter *filter = call->filter;
 	int i;
 
 	if (!filter)
@@ -441,21 +552,24 @@ void destroy_preds(struct ftrace_event_call *call)
 	kfree(filter->preds);
 	kfree(filter->filter_string);
 	kfree(filter);
+}
+
+void destroy_preds(struct ftrace_event_call *call)
+{
+	__free_preds(call->filter);
 	call->filter = NULL;
+	call->filter_active = 0;
 }
 
-static int init_preds(struct ftrace_event_call *call)
+static struct event_filter *__alloc_preds(void)
 {
 	struct event_filter *filter;
 	struct filter_pred *pred;
 	int i;
 
-	if (call->filter)
-		return 0;
-
-	filter = call->filter = kzalloc(sizeof(*filter), GFP_KERNEL);
-	if (!call->filter)
-		return -ENOMEM;
+	filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+	if (!filter)
+		return ERR_PTR(-ENOMEM);
 
 	filter->n_preds = 0;
 
@@ -471,12 +585,24 @@ static int init_preds(struct ftrace_event_call *call)
 		filter->preds[i] = pred;
 	}
 
-	return 0;
+	return filter;
 
 oom:
-	destroy_preds(call);
+	__free_preds(filter);
+	return ERR_PTR(-ENOMEM);
+}
 
-	return -ENOMEM;
+static int init_preds(struct ftrace_event_call *call)
+{
+	if (call->filter)
+		return 0;
+
+	call->filter_active = 0;
+	call->filter = __alloc_preds();
+	if (IS_ERR(call->filter))
+		return PTR_ERR(call->filter);
+
+	return 0;
 }
 
 static int init_subsystem_preds(struct event_subsystem *system)
@@ -499,14 +625,7 @@ static int init_subsystem_preds(struct event_subsystem *system)
 	return 0;
 }
 
-enum {
-	FILTER_DISABLE_ALL,
-	FILTER_INIT_NO_RESET,
-	FILTER_SKIP_NO_RESET,
-};
-
-static void filter_free_subsystem_preds(struct event_subsystem *system,
-					int flag)
+static void filter_free_subsystem_preds(struct event_subsystem *system)
 {
 	struct ftrace_event_call *call;
 
@@ -517,14 +636,6 @@ static void filter_free_subsystem_preds(struct event_subsystem *system,
 		if (strcmp(call->system, system->name) != 0)
 			continue;
 
-		if (flag == FILTER_INIT_NO_RESET) {
-			call->filter->no_reset = false;
-			continue;
-		}
-
-		if (flag == FILTER_SKIP_NO_RESET && call->filter->no_reset)
-			continue;
-
 		filter_disable_preds(call);
 		remove_filter_string(call->filter);
 	}
@@ -532,10 +643,10 @@ static void filter_free_subsystem_preds(struct event_subsystem *system,
 
 static int filter_add_pred_fn(struct filter_parse_state *ps,
 			      struct ftrace_event_call *call,
+			      struct event_filter *filter,
 			      struct filter_pred *pred,
 			      filter_pred_fn_t fn)
 {
-	struct event_filter *filter = call->filter;
 	int idx, err;
 
 	if (filter->n_preds == MAX_FILTER_PRED) {
@@ -550,7 +661,6 @@ static int filter_add_pred_fn(struct filter_parse_state *ps,
 		return err;
 
 	filter->n_preds++;
-	call->filter_active = 1;
 
 	return 0;
 }
@@ -575,7 +685,10 @@ static bool is_string_field(struct ftrace_event_field *field)
 
 static int is_legal_op(struct ftrace_event_field *field, int op)
 {
-	if (is_string_field(field) && (op != OP_EQ && op != OP_NE))
+	if (is_string_field(field) &&
+	    (op != OP_EQ && op != OP_NE && op != OP_GLOB))
+		return 0;
+	if (!is_string_field(field) && op == OP_GLOB)
 		return 0;
 
 	return 1;
@@ -626,6 +739,7 @@ static filter_pred_fn_t select_comparison_fn(int op, int field_size,
 
 static int filter_add_pred(struct filter_parse_state *ps,
 			   struct ftrace_event_call *call,
+			   struct event_filter *filter,
 			   struct filter_pred *pred,
 			   bool dry_run)
 {
@@ -660,21 +774,22 @@ static int filter_add_pred(struct filter_parse_state *ps,
 	}
 
 	if (is_string_field(field)) {
-		pred->str_len = field->size;
+		filter_build_regex(pred);
 
-		if (field->filter_type == FILTER_STATIC_STRING)
+		if (field->filter_type == FILTER_STATIC_STRING) {
 			fn = filter_pred_string;
-		else if (field->filter_type == FILTER_DYN_STRING)
+			pred->regex.field_len = field->size;
+		} else if (field->filter_type == FILTER_DYN_STRING)
 			fn = filter_pred_strloc;
 		else {
 			fn = filter_pred_pchar;
-			pred->str_len = strlen(pred->str_val);
+			pred->regex.field_len = strlen(pred->regex.pattern);
 		}
 	} else {
 		if (field->is_signed)
-			ret = strict_strtoll(pred->str_val, 0, &val);
+			ret = strict_strtoll(pred->regex.pattern, 0, &val);
 		else
-			ret = strict_strtoull(pred->str_val, 0, &val);
+			ret = strict_strtoull(pred->regex.pattern, 0, &val);
 		if (ret) {
 			parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0);
 			return -EINVAL;
@@ -694,45 +809,7 @@ static int filter_add_pred(struct filter_parse_state *ps,
 
 add_pred_fn:
 	if (!dry_run)
-		return filter_add_pred_fn(ps, call, pred, fn);
-	return 0;
-}
-
-static int filter_add_subsystem_pred(struct filter_parse_state *ps,
-				     struct event_subsystem *system,
-				     struct filter_pred *pred,
-				     char *filter_string,
-				     bool dry_run)
-{
-	struct ftrace_event_call *call;
-	int err = 0;
-	bool fail = true;
-
-	list_for_each_entry(call, &ftrace_events, list) {
-
-		if (!call->define_fields)
-			continue;
-
-		if (strcmp(call->system, system->name))
-			continue;
-
-		if (call->filter->no_reset)
-			continue;
-
-		err = filter_add_pred(ps, call, pred, dry_run);
-		if (err)
-			call->filter->no_reset = true;
-		else
-			fail = false;
-
-		if (!dry_run)
-			replace_filter_string(call->filter, filter_string);
-	}
-
-	if (fail) {
-		parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
-		return err;
-	}
+		return filter_add_pred_fn(ps, call, filter, pred, fn);
 	return 0;
 }
 
@@ -1045,8 +1122,8 @@ static struct filter_pred *create_pred(int op, char *operand1, char *operand2)
 		return NULL;
 	}
 
-	strcpy(pred->str_val, operand2);
-	pred->str_len = strlen(operand2);
+	strcpy(pred->regex.pattern, operand2);
+	pred->regex.len = strlen(pred->regex.pattern);
 
 	pred->op = op;
 
@@ -1090,8 +1167,8 @@ static int check_preds(struct filter_parse_state *ps)
 	return 0;
 }
 
-static int replace_preds(struct event_subsystem *system,
-			 struct ftrace_event_call *call,
+static int replace_preds(struct ftrace_event_call *call,
+			 struct event_filter *filter,
 			 struct filter_parse_state *ps,
 			 char *filter_string,
 			 bool dry_run)
@@ -1138,11 +1215,7 @@ static int replace_preds(struct event_subsystem *system,
 add_pred:
 		if (!pred)
 			return -ENOMEM;
-		if (call)
-			err = filter_add_pred(ps, call, pred, false);
-		else
-			err = filter_add_subsystem_pred(ps, system, pred,
-						filter_string, dry_run);
+		err = filter_add_pred(ps, call, filter, pred, dry_run);
 		filter_free_pred(pred);
 		if (err)
 			return err;
@@ -1153,10 +1226,50 @@ add_pred:
 	return 0;
 }
 
-int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
+static int replace_system_preds(struct event_subsystem *system,
+				struct filter_parse_state *ps,
+				char *filter_string)
 {
+	struct ftrace_event_call *call;
+	bool fail = true;
 	int err;
 
+	list_for_each_entry(call, &ftrace_events, list) {
+		struct event_filter *filter = call->filter;
+
+		if (!call->define_fields)
+			continue;
+
+		if (strcmp(call->system, system->name) != 0)
+			continue;
+
+		/* try to see if the filter can be applied */
+		err = replace_preds(call, filter, ps, filter_string, true);
+		if (err)
+			continue;
+
+		/* really apply the filter */
+		filter_disable_preds(call);
+		err = replace_preds(call, filter, ps, filter_string, false);
+		if (err)
+			filter_disable_preds(call);
+		else {
+			call->filter_active = 1;
+			replace_filter_string(filter, filter_string);
+		}
+		fail = false;
+	}
+
+	if (fail) {
+		parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
+{
+	int err;
 	struct filter_parse_state *ps;
 
 	mutex_lock(&event_mutex);
@@ -1168,8 +1281,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 	if (!strcmp(strstrip(filter_string), "0")) {
 		filter_disable_preds(call);
 		remove_filter_string(call->filter);
-		mutex_unlock(&event_mutex);
-		return 0;
+		goto out_unlock;
 	}
 
 	err = -ENOMEM;
@@ -1187,10 +1299,11 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 		goto out;
 	}
 
-	err = replace_preds(NULL, call, ps, filter_string, false);
+	err = replace_preds(call, call->filter, ps, filter_string, false);
 	if (err)
 		append_filter_err(ps, call->filter);
-
+	else
+		call->filter_active = 1;
 out:
 	filter_opstack_clear(ps);
 	postfix_clear(ps);
@@ -1205,7 +1318,6 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 				 char *filter_string)
 {
 	int err;
-
 	struct filter_parse_state *ps;
 
 	mutex_lock(&event_mutex);
@@ -1215,10 +1327,9 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 		goto out_unlock;
 
 	if (!strcmp(strstrip(filter_string), "0")) {
-		filter_free_subsystem_preds(system, FILTER_DISABLE_ALL);
+		filter_free_subsystem_preds(system);
 		remove_filter_string(system->filter);
-		mutex_unlock(&event_mutex);
-		return 0;
+		goto out_unlock;
 	}
 
 	err = -ENOMEM;
@@ -1235,31 +1346,87 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 		goto out;
 	}
 
-	filter_free_subsystem_preds(system, FILTER_INIT_NO_RESET);
-
-	/* try to see the filter can be applied to which events */
-	err = replace_preds(system, NULL, ps, filter_string, true);
-	if (err) {
+	err = replace_system_preds(system, ps, filter_string);
+	if (err)
 		append_filter_err(ps, system->filter);
-		goto out;
+
+out:
+	filter_opstack_clear(ps);
+	postfix_clear(ps);
+	kfree(ps);
+out_unlock:
+	mutex_unlock(&event_mutex);
+
+	return err;
+}
+
+#ifdef CONFIG_EVENT_PROFILE
+
+void ftrace_profile_free_filter(struct perf_event *event)
+{
+	struct event_filter *filter = event->filter;
+
+	event->filter = NULL;
+	__free_preds(filter);
+}
+
+int ftrace_profile_set_filter(struct perf_event *event, int event_id,
+			      char *filter_str)
+{
+	int err;
+	struct event_filter *filter;
+	struct filter_parse_state *ps;
+	struct ftrace_event_call *call = NULL;
+
+	mutex_lock(&event_mutex);
+
+	list_for_each_entry(call, &ftrace_events, list) {
+		if (call->id == event_id)
+			break;
 	}
 
-	filter_free_subsystem_preds(system, FILTER_SKIP_NO_RESET);
+	err = -EINVAL;
+	if (!call)
+		goto out_unlock;
 
-	/* really apply the filter to the events */
-	err = replace_preds(system, NULL, ps, filter_string, false);
-	if (err) {
-		append_filter_err(ps, system->filter);
-		filter_free_subsystem_preds(system, 2);
+	err = -EEXIST;
+	if (event->filter)
+		goto out_unlock;
+
+	filter = __alloc_preds();
+	if (IS_ERR(filter)) {
+		err = PTR_ERR(filter);
+		goto out_unlock;
 	}
 
-out:
+	err = -ENOMEM;
+	ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+	if (!ps)
+		goto free_preds;
+
+	parse_init(ps, filter_ops, filter_str);
+	err = filter_parse(ps);
+	if (err)
+		goto free_ps;
+
+	err = replace_preds(call, filter, ps, filter_str, false);
+	if (!err)
+		event->filter = filter;
+
+free_ps:
 	filter_opstack_clear(ps);
 	postfix_clear(ps);
 	kfree(ps);
+
+free_preds:
+	if (err)
+		__free_preds(filter);
+
 out_unlock:
 	mutex_unlock(&event_mutex);
 
 	return err;
 }
 
+#endif /* CONFIG_EVENT_PROFILE */
+
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 9753fcc61bc5..dff8c84ddf17 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -48,11 +48,11 @@
 struct ____ftrace_##name {					\
 	tstruct							\
 };								\
-static void __used ____ftrace_check_##name(void)		\
+static void __always_unused ____ftrace_check_##name(void)	\
 {								\
 	struct ____ftrace_##name *__entry = NULL;		\
 								\
-	/* force cmpile-time check on F_printk() */		\
+	/* force compile-time check on F_printk() */		\
 	printk(print);						\
 }
 
@@ -66,44 +66,47 @@ static void __used ____ftrace_check_##name(void)		\
 #undef __field
 #define __field(type, item)						\
 	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
-			       "offset:%zu;\tsize:%zu;\n",		\
+			       "offset:%zu;\tsize:%zu;\tsigned:%u;\n",	\
 			       offsetof(typeof(field), item),		\
-			       sizeof(field.item));			\
+			       sizeof(field.item), is_signed_type(type)); \
 	if (!ret)							\
 		return 0;
 
 #undef __field_desc
 #define __field_desc(type, container, item)				\
 	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
-			       "offset:%zu;\tsize:%zu;\n",		\
+			       "offset:%zu;\tsize:%zu;\tsigned:%u;\n",	\
 			       offsetof(typeof(field), container.item),	\
-			       sizeof(field.container.item));		\
+			       sizeof(field.container.item),		\
+			       is_signed_type(type));			\
 	if (!ret)							\
 		return 0;
 
 #undef __array
 #define __array(type, item, len)					\
 	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
-			       "offset:%zu;\tsize:%zu;\n",		\
-			       offsetof(typeof(field), item),	\
-			       sizeof(field.item));		\
+			       "offset:%zu;\tsize:%zu;\tsigned:%u;\n",	\
+			       offsetof(typeof(field), item),		\
+			       sizeof(field.item), is_signed_type(type)); \
 	if (!ret)							\
 		return 0;
 
 #undef __array_desc
 #define __array_desc(type, container, item, len)			\
 	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
-			       "offset:%zu;\tsize:%zu;\n",		\
+			       "offset:%zu;\tsize:%zu;\tsigned:%u;\n",	\
 			       offsetof(typeof(field), container.item),	\
-			       sizeof(field.container.item));		\
+			       sizeof(field.container.item),		\
+			       is_signed_type(type));			\
 	if (!ret)							\
 		return 0;
 
 #undef __dynamic_array
 #define __dynamic_array(type, item)					\
 	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
-			       "offset:%zu;\tsize:0;\n",		\
-			       offsetof(typeof(field), item));		\
+			       "offset:%zu;\tsize:0;\tsigned:%u;\n",	\
+			       offsetof(typeof(field), item),		\
+			       is_signed_type(type));			\
 	if (!ret)							\
 		return 0;
 
@@ -131,7 +134,6 @@ ftrace_format_##name(struct ftrace_event_call *unused,			\
 
 #include "trace_entries.h"
 
-
 #undef __field
 #define __field(type, item)						\
 	ret = trace_define_field(event_call, #type, #item,		\
@@ -193,6 +195,11 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 
 #include "trace_entries.h"
 
+static int ftrace_raw_init_event(struct ftrace_event_call *call)
+{
+	INIT_LIST_HEAD(&call->fields);
+	return 0;
+}
 
 #undef __field
 #define __field(type, item)
@@ -211,7 +218,6 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, type, tstruct, print)		\
-static int ftrace_raw_init_event_##call(void);				\
 									\
 struct ftrace_event_call __used						\
 __attribute__((__aligned__(4)))						\
@@ -219,14 +225,9 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.name			= #call,				\
 	.id			= type,					\
 	.system			= __stringify(TRACE_SYSTEM),		\
-	.raw_init		= ftrace_raw_init_event_##call,		\
+	.raw_init		= ftrace_raw_init_event,		\
 	.show_format		= ftrace_format_##call,			\
 	.define_fields		= ftrace_define_fields_##call,		\
 };									\
-static int ftrace_raw_init_event_##call(void)				\
-{									\
-	INIT_LIST_HEAD(&event_##call.fields);				\
-	return 0;							\
-}									\
 
 #include "trace_entries.h"
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
new file mode 100644
index 000000000000..79ce6a2bd74f
--- /dev/null
+++ b/kernel/trace/trace_kprobe.c
@@ -0,0 +1,1503 @@
+/*
+ * Kprobes-based tracing events
+ *
+ * Created by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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
+ */
+
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/kprobes.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/debugfs.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/ptrace.h>
+#include <linux/perf_event.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+#define MAX_TRACE_ARGS 128
+#define MAX_ARGSTR_LEN 63
+#define MAX_EVENT_NAME_LEN 64
+#define KPROBE_EVENT_SYSTEM "kprobes"
+
+/* Reserved field names */
+#define FIELD_STRING_IP "__probe_ip"
+#define FIELD_STRING_NARGS "__probe_nargs"
+#define FIELD_STRING_RETIP "__probe_ret_ip"
+#define FIELD_STRING_FUNC "__probe_func"
+
+const char *reserved_field_names[] = {
+	"common_type",
+	"common_flags",
+	"common_preempt_count",
+	"common_pid",
+	"common_tgid",
+	"common_lock_depth",
+	FIELD_STRING_IP,
+	FIELD_STRING_NARGS,
+	FIELD_STRING_RETIP,
+	FIELD_STRING_FUNC,
+};
+
+struct fetch_func {
+	unsigned long (*func)(struct pt_regs *, void *);
+	void *data;
+};
+
+static __kprobes unsigned long call_fetch(struct fetch_func *f,
+					  struct pt_regs *regs)
+{
+	return f->func(regs, f->data);
+}
+
+/* fetch handlers */
+static __kprobes unsigned long fetch_register(struct pt_regs *regs,
+					      void *offset)
+{
+	return regs_get_register(regs, (unsigned int)((unsigned long)offset));
+}
+
+static __kprobes unsigned long fetch_stack(struct pt_regs *regs,
+					   void *num)
+{
+	return regs_get_kernel_stack_nth(regs,
+					 (unsigned int)((unsigned long)num));
+}
+
+static __kprobes unsigned long fetch_memory(struct pt_regs *regs, void *addr)
+{
+	unsigned long retval;
+
+	if (probe_kernel_address(addr, retval))
+		return 0;
+	return retval;
+}
+
+static __kprobes unsigned long fetch_argument(struct pt_regs *regs, void *num)
+{
+	return regs_get_argument_nth(regs, (unsigned int)((unsigned long)num));
+}
+
+static __kprobes unsigned long fetch_retvalue(struct pt_regs *regs,
+					      void *dummy)
+{
+	return regs_return_value(regs);
+}
+
+static __kprobes unsigned long fetch_stack_address(struct pt_regs *regs,
+						   void *dummy)
+{
+	return kernel_stack_pointer(regs);
+}
+
+/* Memory fetching by symbol */
+struct symbol_cache {
+	char *symbol;
+	long offset;
+	unsigned long addr;
+};
+
+static unsigned long update_symbol_cache(struct symbol_cache *sc)
+{
+	sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol);
+	if (sc->addr)
+		sc->addr += sc->offset;
+	return sc->addr;
+}
+
+static void free_symbol_cache(struct symbol_cache *sc)
+{
+	kfree(sc->symbol);
+	kfree(sc);
+}
+
+static struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
+{
+	struct symbol_cache *sc;
+
+	if (!sym || strlen(sym) == 0)
+		return NULL;
+	sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL);
+	if (!sc)
+		return NULL;
+
+	sc->symbol = kstrdup(sym, GFP_KERNEL);
+	if (!sc->symbol) {
+		kfree(sc);
+		return NULL;
+	}
+	sc->offset = offset;
+
+	update_symbol_cache(sc);
+	return sc;
+}
+
+static __kprobes unsigned long fetch_symbol(struct pt_regs *regs, void *data)
+{
+	struct symbol_cache *sc = data;
+
+	if (sc->addr)
+		return fetch_memory(regs, (void *)sc->addr);
+	else
+		return 0;
+}
+
+/* Special indirect memory access interface */
+struct indirect_fetch_data {
+	struct fetch_func orig;
+	long offset;
+};
+
+static __kprobes unsigned long fetch_indirect(struct pt_regs *regs, void *data)
+{
+	struct indirect_fetch_data *ind = data;
+	unsigned long addr;
+
+	addr = call_fetch(&ind->orig, regs);
+	if (addr) {
+		addr += ind->offset;
+		return fetch_memory(regs, (void *)addr);
+	} else
+		return 0;
+}
+
+static __kprobes void free_indirect_fetch_data(struct indirect_fetch_data *data)
+{
+	if (data->orig.func == fetch_indirect)
+		free_indirect_fetch_data(data->orig.data);
+	else if (data->orig.func == fetch_symbol)
+		free_symbol_cache(data->orig.data);
+	kfree(data);
+}
+
+/**
+ * Kprobe event core functions
+ */
+
+struct probe_arg {
+	struct fetch_func	fetch;
+	const char		*name;
+};
+
+/* Flags for trace_probe */
+#define TP_FLAG_TRACE	1
+#define TP_FLAG_PROFILE	2
+
+struct trace_probe {
+	struct list_head	list;
+	struct kretprobe	rp;	/* Use rp.kp for kprobe use */
+	unsigned long 		nhit;
+	unsigned int		flags;	/* For TP_FLAG_* */
+	const char		*symbol;	/* symbol name */
+	struct ftrace_event_call	call;
+	struct trace_event		event;
+	unsigned int		nr_args;
+	struct probe_arg	args[];
+};
+
+#define SIZEOF_TRACE_PROBE(n)			\
+	(offsetof(struct trace_probe, args) +	\
+	(sizeof(struct probe_arg) * (n)))
+
+static __kprobes int probe_is_return(struct trace_probe *tp)
+{
+	return tp->rp.handler != NULL;
+}
+
+static __kprobes const char *probe_symbol(struct trace_probe *tp)
+{
+	return tp->symbol ? tp->symbol : "unknown";
+}
+
+static int probe_arg_string(char *buf, size_t n, struct fetch_func *ff)
+{
+	int ret = -EINVAL;
+
+	if (ff->func == fetch_argument)
+		ret = snprintf(buf, n, "$arg%lu", (unsigned long)ff->data);
+	else if (ff->func == fetch_register) {
+		const char *name;
+		name = regs_query_register_name((unsigned int)((long)ff->data));
+		ret = snprintf(buf, n, "%%%s", name);
+	} else if (ff->func == fetch_stack)
+		ret = snprintf(buf, n, "$stack%lu", (unsigned long)ff->data);
+	else if (ff->func == fetch_memory)
+		ret = snprintf(buf, n, "@0x%p", ff->data);
+	else if (ff->func == fetch_symbol) {
+		struct symbol_cache *sc = ff->data;
+		ret = snprintf(buf, n, "@%s%+ld", sc->symbol, sc->offset);
+	} else if (ff->func == fetch_retvalue)
+		ret = snprintf(buf, n, "$retval");
+	else if (ff->func == fetch_stack_address)
+		ret = snprintf(buf, n, "$stack");
+	else if (ff->func == fetch_indirect) {
+		struct indirect_fetch_data *id = ff->data;
+		size_t l = 0;
+		ret = snprintf(buf, n, "%+ld(", id->offset);
+		if (ret >= n)
+			goto end;
+		l += ret;
+		ret = probe_arg_string(buf + l, n - l, &id->orig);
+		if (ret < 0)
+			goto end;
+		l += ret;
+		ret = snprintf(buf + l, n - l, ")");
+		ret += l;
+	}
+end:
+	if (ret >= n)
+		return -ENOSPC;
+	return ret;
+}
+
+static int register_probe_event(struct trace_probe *tp);
+static void unregister_probe_event(struct trace_probe *tp);
+
+static DEFINE_MUTEX(probe_lock);
+static LIST_HEAD(probe_list);
+
+static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
+static int kretprobe_dispatcher(struct kretprobe_instance *ri,
+				struct pt_regs *regs);
+
+/*
+ * Allocate new trace_probe and initialize it (including kprobes).
+ */
+static struct trace_probe *alloc_trace_probe(const char *group,
+					     const char *event,
+					     void *addr,
+					     const char *symbol,
+					     unsigned long offs,
+					     int nargs, int is_return)
+{
+	struct trace_probe *tp;
+
+	tp = kzalloc(SIZEOF_TRACE_PROBE(nargs), GFP_KERNEL);
+	if (!tp)
+		return ERR_PTR(-ENOMEM);
+
+	if (symbol) {
+		tp->symbol = kstrdup(symbol, GFP_KERNEL);
+		if (!tp->symbol)
+			goto error;
+		tp->rp.kp.symbol_name = tp->symbol;
+		tp->rp.kp.offset = offs;
+	} else
+		tp->rp.kp.addr = addr;
+
+	if (is_return)
+		tp->rp.handler = kretprobe_dispatcher;
+	else
+		tp->rp.kp.pre_handler = kprobe_dispatcher;
+
+	if (!event)
+		goto error;
+	tp->call.name = kstrdup(event, GFP_KERNEL);
+	if (!tp->call.name)
+		goto error;
+
+	if (!group)
+		goto error;
+	tp->call.system = kstrdup(group, GFP_KERNEL);
+	if (!tp->call.system)
+		goto error;
+
+	INIT_LIST_HEAD(&tp->list);
+	return tp;
+error:
+	kfree(tp->call.name);
+	kfree(tp->symbol);
+	kfree(tp);
+	return ERR_PTR(-ENOMEM);
+}
+
+static void free_probe_arg(struct probe_arg *arg)
+{
+	if (arg->fetch.func == fetch_symbol)
+		free_symbol_cache(arg->fetch.data);
+	else if (arg->fetch.func == fetch_indirect)
+		free_indirect_fetch_data(arg->fetch.data);
+	kfree(arg->name);
+}
+
+static void free_trace_probe(struct trace_probe *tp)
+{
+	int i;
+
+	for (i = 0; i < tp->nr_args; i++)
+		free_probe_arg(&tp->args[i]);
+
+	kfree(tp->call.system);
+	kfree(tp->call.name);
+	kfree(tp->symbol);
+	kfree(tp);
+}
+
+static struct trace_probe *find_probe_event(const char *event,
+					    const char *group)
+{
+	struct trace_probe *tp;
+
+	list_for_each_entry(tp, &probe_list, list)
+		if (strcmp(tp->call.name, event) == 0 &&
+		    strcmp(tp->call.system, group) == 0)
+			return tp;
+	return NULL;
+}
+
+/* Unregister a trace_probe and probe_event: call with locking probe_lock */
+static void unregister_trace_probe(struct trace_probe *tp)
+{
+	if (probe_is_return(tp))
+		unregister_kretprobe(&tp->rp);
+	else
+		unregister_kprobe(&tp->rp.kp);
+	list_del(&tp->list);
+	unregister_probe_event(tp);
+}
+
+/* Register a trace_probe and probe_event */
+static int register_trace_probe(struct trace_probe *tp)
+{
+	struct trace_probe *old_tp;
+	int ret;
+
+	mutex_lock(&probe_lock);
+
+	/* register as an event */
+	old_tp = find_probe_event(tp->call.name, tp->call.system);
+	if (old_tp) {
+		/* delete old event */
+		unregister_trace_probe(old_tp);
+		free_trace_probe(old_tp);
+	}
+	ret = register_probe_event(tp);
+	if (ret) {
+		pr_warning("Faild to register probe event(%d)\n", ret);
+		goto end;
+	}
+
+	tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
+	if (probe_is_return(tp))
+		ret = register_kretprobe(&tp->rp);
+	else
+		ret = register_kprobe(&tp->rp.kp);
+
+	if (ret) {
+		pr_warning("Could not insert probe(%d)\n", ret);
+		if (ret == -EILSEQ) {
+			pr_warning("Probing address(0x%p) is not an "
+				   "instruction boundary.\n",
+				   tp->rp.kp.addr);
+			ret = -EINVAL;
+		}
+		unregister_probe_event(tp);
+	} else
+		list_add_tail(&tp->list, &probe_list);
+end:
+	mutex_unlock(&probe_lock);
+	return ret;
+}
+
+/* Split symbol and offset. */
+static int split_symbol_offset(char *symbol, unsigned long *offset)
+{
+	char *tmp;
+	int ret;
+
+	if (!offset)
+		return -EINVAL;
+
+	tmp = strchr(symbol, '+');
+	if (tmp) {
+		/* skip sign because strict_strtol doesn't accept '+' */
+		ret = strict_strtoul(tmp + 1, 0, offset);
+		if (ret)
+			return ret;
+		*tmp = '\0';
+	} else
+		*offset = 0;
+	return 0;
+}
+
+#define PARAM_MAX_ARGS 16
+#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
+
+static int parse_probe_vars(char *arg, struct fetch_func *ff, int is_return)
+{
+	int ret = 0;
+	unsigned long param;
+
+	if (strcmp(arg, "retval") == 0) {
+		if (is_return) {
+			ff->func = fetch_retvalue;
+			ff->data = NULL;
+		} else
+			ret = -EINVAL;
+	} else if (strncmp(arg, "stack", 5) == 0) {
+		if (arg[5] == '\0') {
+			ff->func = fetch_stack_address;
+			ff->data = NULL;
+		} else if (isdigit(arg[5])) {
+			ret = strict_strtoul(arg + 5, 10, &param);
+			if (ret || param > PARAM_MAX_STACK)
+				ret = -EINVAL;
+			else {
+				ff->func = fetch_stack;
+				ff->data = (void *)param;
+			}
+		} else
+			ret = -EINVAL;
+	} else if (strncmp(arg, "arg", 3) == 0 && isdigit(arg[3])) {
+		ret = strict_strtoul(arg + 3, 10, &param);
+		if (ret || param > PARAM_MAX_ARGS)
+			ret = -EINVAL;
+		else {
+			ff->func = fetch_argument;
+			ff->data = (void *)param;
+		}
+	} else
+		ret = -EINVAL;
+	return ret;
+}
+
+static int parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+{
+	int ret = 0;
+	unsigned long param;
+	long offset;
+	char *tmp;
+
+	switch (arg[0]) {
+	case '$':
+		ret = parse_probe_vars(arg + 1, ff, is_return);
+		break;
+	case '%':	/* named register */
+		ret = regs_query_register_offset(arg + 1);
+		if (ret >= 0) {
+			ff->func = fetch_register;
+			ff->data = (void *)(unsigned long)ret;
+			ret = 0;
+		}
+		break;
+	case '@':	/* memory or symbol */
+		if (isdigit(arg[1])) {
+			ret = strict_strtoul(arg + 1, 0, &param);
+			if (ret)
+				break;
+			ff->func = fetch_memory;
+			ff->data = (void *)param;
+		} else {
+			ret = split_symbol_offset(arg + 1, &offset);
+			if (ret)
+				break;
+			ff->data = alloc_symbol_cache(arg + 1, offset);
+			if (ff->data)
+				ff->func = fetch_symbol;
+			else
+				ret = -EINVAL;
+		}
+		break;
+	case '+':	/* indirect memory */
+	case '-':
+		tmp = strchr(arg, '(');
+		if (!tmp) {
+			ret = -EINVAL;
+			break;
+		}
+		*tmp = '\0';
+		ret = strict_strtol(arg + 1, 0, &offset);
+		if (ret)
+			break;
+		if (arg[0] == '-')
+			offset = -offset;
+		arg = tmp + 1;
+		tmp = strrchr(arg, ')');
+		if (tmp) {
+			struct indirect_fetch_data *id;
+			*tmp = '\0';
+			id = kzalloc(sizeof(struct indirect_fetch_data),
+				     GFP_KERNEL);
+			if (!id)
+				return -ENOMEM;
+			id->offset = offset;
+			ret = parse_probe_arg(arg, &id->orig, is_return);
+			if (ret)
+				kfree(id);
+			else {
+				ff->func = fetch_indirect;
+				ff->data = (void *)id;
+			}
+		} else
+			ret = -EINVAL;
+		break;
+	default:
+		/* TODO: support custom handler */
+		ret = -EINVAL;
+	}
+	return ret;
+}
+
+/* Return 1 if name is reserved or already used by another argument */
+static int conflict_field_name(const char *name,
+			       struct probe_arg *args, int narg)
+{
+	int i;
+	for (i = 0; i < ARRAY_SIZE(reserved_field_names); i++)
+		if (strcmp(reserved_field_names[i], name) == 0)
+			return 1;
+	for (i = 0; i < narg; i++)
+		if (strcmp(args[i].name, name) == 0)
+			return 1;
+	return 0;
+}
+
+static int create_trace_probe(int argc, char **argv)
+{
+	/*
+	 * Argument syntax:
+	 *  - Add kprobe: p[:[GRP/]EVENT] KSYM[+OFFS]|KADDR [FETCHARGS]
+	 *  - Add kretprobe: r[:[GRP/]EVENT] KSYM[+0] [FETCHARGS]
+	 * Fetch args:
+	 *  $argN	: fetch Nth of function argument. (N:0-)
+	 *  $retval	: fetch return value
+	 *  $stack	: fetch stack address
+	 *  $stackN	: fetch Nth of stack (N:0-)
+	 *  @ADDR	: fetch memory at ADDR (ADDR should be in kernel)
+	 *  @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol)
+	 *  %REG	: fetch register REG
+	 * Indirect memory fetch:
+	 *  +|-offs(ARG) : fetch memory at ARG +|- offs address.
+	 * Alias name of args:
+	 *  NAME=FETCHARG : set NAME as alias of FETCHARG.
+	 */
+	struct trace_probe *tp;
+	int i, ret = 0;
+	int is_return = 0;
+	char *symbol = NULL, *event = NULL, *arg = NULL, *group = NULL;
+	unsigned long offset = 0;
+	void *addr = NULL;
+	char buf[MAX_EVENT_NAME_LEN];
+
+	if (argc < 2) {
+		pr_info("Probe point is not specified.\n");
+		return -EINVAL;
+	}
+
+	if (argv[0][0] == 'p')
+		is_return = 0;
+	else if (argv[0][0] == 'r')
+		is_return = 1;
+	else {
+		pr_info("Probe definition must be started with 'p' or 'r'.\n");
+		return -EINVAL;
+	}
+
+	if (argv[0][1] == ':') {
+		event = &argv[0][2];
+		if (strchr(event, '/')) {
+			group = event;
+			event = strchr(group, '/') + 1;
+			event[-1] = '\0';
+			if (strlen(group) == 0) {
+				pr_info("Group name is not specifiled\n");
+				return -EINVAL;
+			}
+		}
+		if (strlen(event) == 0) {
+			pr_info("Event name is not specifiled\n");
+			return -EINVAL;
+		}
+	}
+
+	if (isdigit(argv[1][0])) {
+		if (is_return) {
+			pr_info("Return probe point must be a symbol.\n");
+			return -EINVAL;
+		}
+		/* an address specified */
+		ret = strict_strtoul(&argv[0][2], 0, (unsigned long *)&addr);
+		if (ret) {
+			pr_info("Failed to parse address.\n");
+			return ret;
+		}
+	} else {
+		/* a symbol specified */
+		symbol = argv[1];
+		/* TODO: support .init module functions */
+		ret = split_symbol_offset(symbol, &offset);
+		if (ret) {
+			pr_info("Failed to parse symbol.\n");
+			return ret;
+		}
+		if (offset && is_return) {
+			pr_info("Return probe must be used without offset.\n");
+			return -EINVAL;
+		}
+	}
+	argc -= 2; argv += 2;
+
+	/* setup a probe */
+	if (!group)
+		group = KPROBE_EVENT_SYSTEM;
+	if (!event) {
+		/* Make a new event name */
+		if (symbol)
+			snprintf(buf, MAX_EVENT_NAME_LEN, "%c@%s%+ld",
+				 is_return ? 'r' : 'p', symbol, offset);
+		else
+			snprintf(buf, MAX_EVENT_NAME_LEN, "%c@0x%p",
+				 is_return ? 'r' : 'p', addr);
+		event = buf;
+	}
+	tp = alloc_trace_probe(group, event, addr, symbol, offset, argc,
+			       is_return);
+	if (IS_ERR(tp)) {
+		pr_info("Failed to allocate trace_probe.(%d)\n",
+			(int)PTR_ERR(tp));
+		return PTR_ERR(tp);
+	}
+
+	/* parse arguments */
+	ret = 0;
+	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+		/* Parse argument name */
+		arg = strchr(argv[i], '=');
+		if (arg)
+			*arg++ = '\0';
+		else
+			arg = argv[i];
+
+		if (conflict_field_name(argv[i], tp->args, i)) {
+			pr_info("Argument%d name '%s' conflicts with "
+				"another field.\n", i, argv[i]);
+			ret = -EINVAL;
+			goto error;
+		}
+
+		tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+
+		/* Parse fetch argument */
+		if (strlen(arg) > MAX_ARGSTR_LEN) {
+			pr_info("Argument%d(%s) is too long.\n", i, arg);
+			ret = -ENOSPC;
+			goto error;
+		}
+		ret = parse_probe_arg(arg, &tp->args[i].fetch, is_return);
+		if (ret) {
+			pr_info("Parse error at argument%d. (%d)\n", i, ret);
+			goto error;
+		}
+	}
+	tp->nr_args = i;
+
+	ret = register_trace_probe(tp);
+	if (ret)
+		goto error;
+	return 0;
+
+error:
+	free_trace_probe(tp);
+	return ret;
+}
+
+static void cleanup_all_probes(void)
+{
+	struct trace_probe *tp;
+
+	mutex_lock(&probe_lock);
+	/* TODO: Use batch unregistration */
+	while (!list_empty(&probe_list)) {
+		tp = list_entry(probe_list.next, struct trace_probe, list);
+		unregister_trace_probe(tp);
+		free_trace_probe(tp);
+	}
+	mutex_unlock(&probe_lock);
+}
+
+
+/* Probes listing interfaces */
+static void *probes_seq_start(struct seq_file *m, loff_t *pos)
+{
+	mutex_lock(&probe_lock);
+	return seq_list_start(&probe_list, *pos);
+}
+
+static void *probes_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	return seq_list_next(v, &probe_list, pos);
+}
+
+static void probes_seq_stop(struct seq_file *m, void *v)
+{
+	mutex_unlock(&probe_lock);
+}
+
+static int probes_seq_show(struct seq_file *m, void *v)
+{
+	struct trace_probe *tp = v;
+	int i, ret;
+	char buf[MAX_ARGSTR_LEN + 1];
+
+	seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
+	seq_printf(m, ":%s", tp->call.name);
+
+	if (tp->symbol)
+		seq_printf(m, " %s+%u", probe_symbol(tp), tp->rp.kp.offset);
+	else
+		seq_printf(m, " 0x%p", tp->rp.kp.addr);
+
+	for (i = 0; i < tp->nr_args; i++) {
+		ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i].fetch);
+		if (ret < 0) {
+			pr_warning("Argument%d decoding error(%d).\n", i, ret);
+			return ret;
+		}
+		seq_printf(m, " %s=%s", tp->args[i].name, buf);
+	}
+	seq_printf(m, "\n");
+	return 0;
+}
+
+static const struct seq_operations probes_seq_op = {
+	.start  = probes_seq_start,
+	.next   = probes_seq_next,
+	.stop   = probes_seq_stop,
+	.show   = probes_seq_show
+};
+
+static int probes_open(struct inode *inode, struct file *file)
+{
+	if ((file->f_mode & FMODE_WRITE) &&
+	    (file->f_flags & O_TRUNC))
+		cleanup_all_probes();
+
+	return seq_open(file, &probes_seq_op);
+}
+
+static int command_trace_probe(const char *buf)
+{
+	char **argv;
+	int argc = 0, ret = 0;
+
+	argv = argv_split(GFP_KERNEL, buf, &argc);
+	if (!argv)
+		return -ENOMEM;
+
+	if (argc)
+		ret = create_trace_probe(argc, argv);
+
+	argv_free(argv);
+	return ret;
+}
+
+#define WRITE_BUFSIZE 128
+
+static ssize_t probes_write(struct file *file, const char __user *buffer,
+			    size_t count, loff_t *ppos)
+{
+	char *kbuf, *tmp;
+	int ret;
+	size_t done;
+	size_t size;
+
+	kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL);
+	if (!kbuf)
+		return -ENOMEM;
+
+	ret = done = 0;
+	while (done < count) {
+		size = count - done;
+		if (size >= WRITE_BUFSIZE)
+			size = WRITE_BUFSIZE - 1;
+		if (copy_from_user(kbuf, buffer + done, size)) {
+			ret = -EFAULT;
+			goto out;
+		}
+		kbuf[size] = '\0';
+		tmp = strchr(kbuf, '\n');
+		if (tmp) {
+			*tmp = '\0';
+			size = tmp - kbuf + 1;
+		} else if (done + size < count) {
+			pr_warning("Line length is too long: "
+				   "Should be less than %d.", WRITE_BUFSIZE);
+			ret = -EINVAL;
+			goto out;
+		}
+		done += size;
+		/* Remove comments */
+		tmp = strchr(kbuf, '#');
+		if (tmp)
+			*tmp = '\0';
+
+		ret = command_trace_probe(kbuf);
+		if (ret)
+			goto out;
+	}
+	ret = done;
+out:
+	kfree(kbuf);
+	return ret;
+}
+
+static const struct file_operations kprobe_events_ops = {
+	.owner          = THIS_MODULE,
+	.open           = probes_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = seq_release,
+	.write		= probes_write,
+};
+
+/* Probes profiling interfaces */
+static int probes_profile_seq_show(struct seq_file *m, void *v)
+{
+	struct trace_probe *tp = v;
+
+	seq_printf(m, "  %-44s %15lu %15lu\n", tp->call.name, tp->nhit,
+		   tp->rp.kp.nmissed);
+
+	return 0;
+}
+
+static const struct seq_operations profile_seq_op = {
+	.start  = probes_seq_start,
+	.next   = probes_seq_next,
+	.stop   = probes_seq_stop,
+	.show   = probes_profile_seq_show
+};
+
+static int profile_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &profile_seq_op);
+}
+
+static const struct file_operations kprobe_profile_ops = {
+	.owner          = THIS_MODULE,
+	.open           = profile_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = seq_release,
+};
+
+/* Kprobe handler */
+static __kprobes int kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
+{
+	struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+	struct kprobe_trace_entry *entry;
+	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
+	int size, i, pc;
+	unsigned long irq_flags;
+	struct ftrace_event_call *call = &tp->call;
+
+	tp->nhit++;
+
+	local_save_flags(irq_flags);
+	pc = preempt_count();
+
+	size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+
+	event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
+						  irq_flags, pc);
+	if (!event)
+		return 0;
+
+	entry = ring_buffer_event_data(event);
+	entry->nargs = tp->nr_args;
+	entry->ip = (unsigned long)kp->addr;
+	for (i = 0; i < tp->nr_args; i++)
+		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+
+	if (!filter_current_check_discard(buffer, call, entry, event))
+		trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+	return 0;
+}
+
+/* Kretprobe handler */
+static __kprobes int kretprobe_trace_func(struct kretprobe_instance *ri,
+					  struct pt_regs *regs)
+{
+	struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+	struct kretprobe_trace_entry *entry;
+	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
+	int size, i, pc;
+	unsigned long irq_flags;
+	struct ftrace_event_call *call = &tp->call;
+
+	local_save_flags(irq_flags);
+	pc = preempt_count();
+
+	size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+
+	event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
+						  irq_flags, pc);
+	if (!event)
+		return 0;
+
+	entry = ring_buffer_event_data(event);
+	entry->nargs = tp->nr_args;
+	entry->func = (unsigned long)tp->rp.kp.addr;
+	entry->ret_ip = (unsigned long)ri->ret_addr;
+	for (i = 0; i < tp->nr_args; i++)
+		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+
+	if (!filter_current_check_discard(buffer, call, entry, event))
+		trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+
+	return 0;
+}
+
+/* Event entry printers */
+enum print_line_t
+print_kprobe_event(struct trace_iterator *iter, int flags)
+{
+	struct kprobe_trace_entry *field;
+	struct trace_seq *s = &iter->seq;
+	struct trace_event *event;
+	struct trace_probe *tp;
+	int i;
+
+	field = (struct kprobe_trace_entry *)iter->ent;
+	event = ftrace_find_event(field->ent.type);
+	tp = container_of(event, struct trace_probe, event);
+
+	if (!trace_seq_printf(s, "%s: (", tp->call.name))
+		goto partial;
+
+	if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET))
+		goto partial;
+
+	if (!trace_seq_puts(s, ")"))
+		goto partial;
+
+	for (i = 0; i < field->nargs; i++)
+		if (!trace_seq_printf(s, " %s=%lx",
+				      tp->args[i].name, field->args[i]))
+			goto partial;
+
+	if (!trace_seq_puts(s, "\n"))
+		goto partial;
+
+	return TRACE_TYPE_HANDLED;
+partial:
+	return TRACE_TYPE_PARTIAL_LINE;
+}
+
+enum print_line_t
+print_kretprobe_event(struct trace_iterator *iter, int flags)
+{
+	struct kretprobe_trace_entry *field;
+	struct trace_seq *s = &iter->seq;
+	struct trace_event *event;
+	struct trace_probe *tp;
+	int i;
+
+	field = (struct kretprobe_trace_entry *)iter->ent;
+	event = ftrace_find_event(field->ent.type);
+	tp = container_of(event, struct trace_probe, event);
+
+	if (!trace_seq_printf(s, "%s: (", tp->call.name))
+		goto partial;
+
+	if (!seq_print_ip_sym(s, field->ret_ip, flags | TRACE_ITER_SYM_OFFSET))
+		goto partial;
+
+	if (!trace_seq_puts(s, " <- "))
+		goto partial;
+
+	if (!seq_print_ip_sym(s, field->func, flags & ~TRACE_ITER_SYM_OFFSET))
+		goto partial;
+
+	if (!trace_seq_puts(s, ")"))
+		goto partial;
+
+	for (i = 0; i < field->nargs; i++)
+		if (!trace_seq_printf(s, " %s=%lx",
+				      tp->args[i].name, field->args[i]))
+			goto partial;
+
+	if (!trace_seq_puts(s, "\n"))
+		goto partial;
+
+	return TRACE_TYPE_HANDLED;
+partial:
+	return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static int probe_event_enable(struct ftrace_event_call *call)
+{
+	struct trace_probe *tp = (struct trace_probe *)call->data;
+
+	tp->flags |= TP_FLAG_TRACE;
+	if (probe_is_return(tp))
+		return enable_kretprobe(&tp->rp);
+	else
+		return enable_kprobe(&tp->rp.kp);
+}
+
+static void probe_event_disable(struct ftrace_event_call *call)
+{
+	struct trace_probe *tp = (struct trace_probe *)call->data;
+
+	tp->flags &= ~TP_FLAG_TRACE;
+	if (!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE))) {
+		if (probe_is_return(tp))
+			disable_kretprobe(&tp->rp);
+		else
+			disable_kprobe(&tp->rp.kp);
+	}
+}
+
+static int probe_event_raw_init(struct ftrace_event_call *event_call)
+{
+	INIT_LIST_HEAD(&event_call->fields);
+
+	return 0;
+}
+
+#undef DEFINE_FIELD
+#define DEFINE_FIELD(type, item, name, is_signed)			\
+	do {								\
+		ret = trace_define_field(event_call, #type, name,	\
+					 offsetof(typeof(field), item),	\
+					 sizeof(field.item), is_signed, \
+					 FILTER_OTHER);			\
+		if (ret)						\
+			return ret;					\
+	} while (0)
+
+static int kprobe_event_define_fields(struct ftrace_event_call *event_call)
+{
+	int ret, i;
+	struct kprobe_trace_entry field;
+	struct trace_probe *tp = (struct trace_probe *)event_call->data;
+
+	ret = trace_define_common_fields(event_call);
+	if (!ret)
+		return ret;
+
+	DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
+	DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
+	/* Set argument names as fields */
+	for (i = 0; i < tp->nr_args; i++)
+		DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+	return 0;
+}
+
+static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
+{
+	int ret, i;
+	struct kretprobe_trace_entry field;
+	struct trace_probe *tp = (struct trace_probe *)event_call->data;
+
+	ret = trace_define_common_fields(event_call);
+	if (!ret)
+		return ret;
+
+	DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
+	DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
+	DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
+	/* Set argument names as fields */
+	for (i = 0; i < tp->nr_args; i++)
+		DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+	return 0;
+}
+
+static int __probe_event_show_format(struct trace_seq *s,
+				     struct trace_probe *tp, const char *fmt,
+				     const char *arg)
+{
+	int i;
+
+	/* Show format */
+	if (!trace_seq_printf(s, "\nprint fmt: \"%s", fmt))
+		return 0;
+
+	for (i = 0; i < tp->nr_args; i++)
+		if (!trace_seq_printf(s, " %s=%%lx", tp->args[i].name))
+			return 0;
+
+	if (!trace_seq_printf(s, "\", %s", arg))
+		return 0;
+
+	for (i = 0; i < tp->nr_args; i++)
+		if (!trace_seq_printf(s, ", REC->%s", tp->args[i].name))
+			return 0;
+
+	return trace_seq_puts(s, "\n");
+}
+
+#undef SHOW_FIELD
+#define SHOW_FIELD(type, item, name)					\
+	do {								\
+		ret = trace_seq_printf(s, "\tfield: " #type " %s;\t"	\
+				"offset:%u;\tsize:%u;\n", name,		\
+				(unsigned int)offsetof(typeof(field), item),\
+				(unsigned int)sizeof(type));		\
+		if (!ret)						\
+			return 0;					\
+	} while (0)
+
+static int kprobe_event_show_format(struct ftrace_event_call *call,
+				    struct trace_seq *s)
+{
+	struct kprobe_trace_entry field __attribute__((unused));
+	int ret, i;
+	struct trace_probe *tp = (struct trace_probe *)call->data;
+
+	SHOW_FIELD(unsigned long, ip, FIELD_STRING_IP);
+	SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
+
+	/* Show fields */
+	for (i = 0; i < tp->nr_args; i++)
+		SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
+	trace_seq_puts(s, "\n");
+
+	return __probe_event_show_format(s, tp, "(%lx)",
+					 "REC->" FIELD_STRING_IP);
+}
+
+static int kretprobe_event_show_format(struct ftrace_event_call *call,
+				       struct trace_seq *s)
+{
+	struct kretprobe_trace_entry field __attribute__((unused));
+	int ret, i;
+	struct trace_probe *tp = (struct trace_probe *)call->data;
+
+	SHOW_FIELD(unsigned long, func, FIELD_STRING_FUNC);
+	SHOW_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP);
+	SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
+
+	/* Show fields */
+	for (i = 0; i < tp->nr_args; i++)
+		SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
+	trace_seq_puts(s, "\n");
+
+	return __probe_event_show_format(s, tp, "(%lx <- %lx)",
+					 "REC->" FIELD_STRING_FUNC
+					 ", REC->" FIELD_STRING_RETIP);
+}
+
+#ifdef CONFIG_EVENT_PROFILE
+
+/* Kprobe profile handler */
+static __kprobes int kprobe_profile_func(struct kprobe *kp,
+					 struct pt_regs *regs)
+{
+	struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+	struct ftrace_event_call *call = &tp->call;
+	struct kprobe_trace_entry *entry;
+	struct trace_entry *ent;
+	int size, __size, i, pc, __cpu;
+	unsigned long irq_flags;
+	char *trace_buf;
+	char *raw_data;
+	int rctx;
+
+	pc = preempt_count();
+	__size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+	size = ALIGN(__size + sizeof(u32), sizeof(u64));
+	size -= sizeof(u32);
+	if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+		     "profile buffer not large enough"))
+		return 0;
+
+	/*
+	 * Protect the non nmi buffer
+	 * This also protects the rcu read side
+	 */
+	local_irq_save(irq_flags);
+
+	rctx = perf_swevent_get_recursion_context();
+	if (rctx < 0)
+		goto end_recursion;
+
+	__cpu = smp_processor_id();
+
+	if (in_nmi())
+		trace_buf = rcu_dereference(perf_trace_buf_nmi);
+	else
+		trace_buf = rcu_dereference(perf_trace_buf);
+
+	if (!trace_buf)
+		goto end;
+
+	raw_data = per_cpu_ptr(trace_buf, __cpu);
+
+	/* Zero dead bytes from alignment to avoid buffer leak to userspace */
+	*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+	entry = (struct kprobe_trace_entry *)raw_data;
+	ent = &entry->ent;
+
+	tracing_generic_entry_update(ent, irq_flags, pc);
+	ent->type = call->id;
+	entry->nargs = tp->nr_args;
+	entry->ip = (unsigned long)kp->addr;
+	for (i = 0; i < tp->nr_args; i++)
+		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+	perf_tp_event(call->id, entry->ip, 1, entry, size);
+
+end:
+	perf_swevent_put_recursion_context(rctx);
+end_recursion:
+	local_irq_restore(irq_flags);
+
+	return 0;
+}
+
+/* Kretprobe profile handler */
+static __kprobes int kretprobe_profile_func(struct kretprobe_instance *ri,
+					    struct pt_regs *regs)
+{
+	struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+	struct ftrace_event_call *call = &tp->call;
+	struct kretprobe_trace_entry *entry;
+	struct trace_entry *ent;
+	int size, __size, i, pc, __cpu;
+	unsigned long irq_flags;
+	char *trace_buf;
+	char *raw_data;
+	int rctx;
+
+	pc = preempt_count();
+	__size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+	size = ALIGN(__size + sizeof(u32), sizeof(u64));
+	size -= sizeof(u32);
+	if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+		     "profile buffer not large enough"))
+		return 0;
+
+	/*
+	 * Protect the non nmi buffer
+	 * This also protects the rcu read side
+	 */
+	local_irq_save(irq_flags);
+
+	rctx = perf_swevent_get_recursion_context();
+	if (rctx < 0)
+		goto end_recursion;
+
+	__cpu = smp_processor_id();
+
+	if (in_nmi())
+		trace_buf = rcu_dereference(perf_trace_buf_nmi);
+	else
+		trace_buf = rcu_dereference(perf_trace_buf);
+
+	if (!trace_buf)
+		goto end;
+
+	raw_data = per_cpu_ptr(trace_buf, __cpu);
+
+	/* Zero dead bytes from alignment to avoid buffer leak to userspace */
+	*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+	entry = (struct kretprobe_trace_entry *)raw_data;
+	ent = &entry->ent;
+
+	tracing_generic_entry_update(ent, irq_flags, pc);
+	ent->type = call->id;
+	entry->nargs = tp->nr_args;
+	entry->func = (unsigned long)tp->rp.kp.addr;
+	entry->ret_ip = (unsigned long)ri->ret_addr;
+	for (i = 0; i < tp->nr_args; i++)
+		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+	perf_tp_event(call->id, entry->ret_ip, 1, entry, size);
+
+end:
+	perf_swevent_put_recursion_context(rctx);
+end_recursion:
+	local_irq_restore(irq_flags);
+
+	return 0;
+}
+
+static int probe_profile_enable(struct ftrace_event_call *call)
+{
+	struct trace_probe *tp = (struct trace_probe *)call->data;
+
+	tp->flags |= TP_FLAG_PROFILE;
+
+	if (probe_is_return(tp))
+		return enable_kretprobe(&tp->rp);
+	else
+		return enable_kprobe(&tp->rp.kp);
+}
+
+static void probe_profile_disable(struct ftrace_event_call *call)
+{
+	struct trace_probe *tp = (struct trace_probe *)call->data;
+
+	tp->flags &= ~TP_FLAG_PROFILE;
+
+	if (!(tp->flags & TP_FLAG_TRACE)) {
+		if (probe_is_return(tp))
+			disable_kretprobe(&tp->rp);
+		else
+			disable_kprobe(&tp->rp.kp);
+	}
+}
+#endif	/* CONFIG_EVENT_PROFILE */
+
+
+static __kprobes
+int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
+{
+	struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+
+	if (tp->flags & TP_FLAG_TRACE)
+		kprobe_trace_func(kp, regs);
+#ifdef CONFIG_EVENT_PROFILE
+	if (tp->flags & TP_FLAG_PROFILE)
+		kprobe_profile_func(kp, regs);
+#endif	/* CONFIG_EVENT_PROFILE */
+	return 0;	/* We don't tweek kernel, so just return 0 */
+}
+
+static __kprobes
+int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
+{
+	struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+
+	if (tp->flags & TP_FLAG_TRACE)
+		kretprobe_trace_func(ri, regs);
+#ifdef CONFIG_EVENT_PROFILE
+	if (tp->flags & TP_FLAG_PROFILE)
+		kretprobe_profile_func(ri, regs);
+#endif	/* CONFIG_EVENT_PROFILE */
+	return 0;	/* We don't tweek kernel, so just return 0 */
+}
+
+static int register_probe_event(struct trace_probe *tp)
+{
+	struct ftrace_event_call *call = &tp->call;
+	int ret;
+
+	/* Initialize ftrace_event_call */
+	if (probe_is_return(tp)) {
+		tp->event.trace = print_kretprobe_event;
+		call->raw_init = probe_event_raw_init;
+		call->show_format = kretprobe_event_show_format;
+		call->define_fields = kretprobe_event_define_fields;
+	} else {
+		tp->event.trace = print_kprobe_event;
+		call->raw_init = probe_event_raw_init;
+		call->show_format = kprobe_event_show_format;
+		call->define_fields = kprobe_event_define_fields;
+	}
+	call->event = &tp->event;
+	call->id = register_ftrace_event(&tp->event);
+	if (!call->id)
+		return -ENODEV;
+	call->enabled = 0;
+	call->regfunc = probe_event_enable;
+	call->unregfunc = probe_event_disable;
+
+#ifdef CONFIG_EVENT_PROFILE
+	atomic_set(&call->profile_count, -1);
+	call->profile_enable = probe_profile_enable;
+	call->profile_disable = probe_profile_disable;
+#endif
+	call->data = tp;
+	ret = trace_add_event_call(call);
+	if (ret) {
+		pr_info("Failed to register kprobe event: %s\n", call->name);
+		unregister_ftrace_event(&tp->event);
+	}
+	return ret;
+}
+
+static void unregister_probe_event(struct trace_probe *tp)
+{
+	/* tp->event is unregistered in trace_remove_event_call() */
+	trace_remove_event_call(&tp->call);
+}
+
+/* Make a debugfs interface for controling probe points */
+static __init int init_kprobe_trace(void)
+{
+	struct dentry *d_tracer;
+	struct dentry *entry;
+
+	d_tracer = tracing_init_dentry();
+	if (!d_tracer)
+		return 0;
+
+	entry = debugfs_create_file("kprobe_events", 0644, d_tracer,
+				    NULL, &kprobe_events_ops);
+
+	/* Event list interface */
+	if (!entry)
+		pr_warning("Could not create debugfs "
+			   "'kprobe_events' entry\n");
+
+	/* Profile interface */
+	entry = debugfs_create_file("kprobe_profile", 0444, d_tracer,
+				    NULL, &kprobe_profile_ops);
+
+	if (!entry)
+		pr_warning("Could not create debugfs "
+			   "'kprobe_profile' entry\n");
+	return 0;
+}
+fs_initcall(init_kprobe_trace);
+
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+
+static int kprobe_trace_selftest_target(int a1, int a2, int a3,
+					int a4, int a5, int a6)
+{
+	return a1 + a2 + a3 + a4 + a5 + a6;
+}
+
+static __init int kprobe_trace_self_tests_init(void)
+{
+	int ret;
+	int (*target)(int, int, int, int, int, int);
+
+	target = kprobe_trace_selftest_target;
+
+	pr_info("Testing kprobe tracing: ");
+
+	ret = command_trace_probe("p:testprobe kprobe_trace_selftest_target "
+				  "$arg1 $arg2 $arg3 $arg4 $stack $stack0");
+	if (WARN_ON_ONCE(ret))
+		pr_warning("error enabling function entry\n");
+
+	ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target "
+				  "$retval");
+	if (WARN_ON_ONCE(ret))
+		pr_warning("error enabling function return\n");
+
+	ret = target(1, 2, 3, 4, 5, 6);
+
+	cleanup_all_probes();
+
+	pr_cont("OK\n");
+	return 0;
+}
+
+late_initcall(kprobe_trace_self_tests_init);
+
+#endif
diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c
new file mode 100644
index 000000000000..11935b53a6cb
--- /dev/null
+++ b/kernel/trace/trace_ksym.c
@@ -0,0 +1,554 @@
+/*
+ * trace_ksym.c - Kernel Symbol Tracer
+ *
+ * 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) IBM Corporation, 2009
+ */
+
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+
+#include "trace_output.h"
+#include "trace_stat.h"
+#include "trace.h"
+
+#include <linux/hw_breakpoint.h>
+#include <asm/hw_breakpoint.h>
+
+/*
+ * For now, let us restrict the no. of symbols traced simultaneously to number
+ * of available hardware breakpoint registers.
+ */
+#define KSYM_TRACER_MAX HBP_NUM
+
+#define KSYM_TRACER_OP_LEN 3 /* rw- */
+
+struct trace_ksym {
+	struct perf_event	**ksym_hbp;
+	unsigned long		ksym_addr;
+	int			type;
+	int			len;
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+	unsigned long		counter;
+#endif
+	struct hlist_node	ksym_hlist;
+};
+
+static struct trace_array *ksym_trace_array;
+
+static unsigned int ksym_filter_entry_count;
+static unsigned int ksym_tracing_enabled;
+
+static HLIST_HEAD(ksym_filter_head);
+
+static DEFINE_MUTEX(ksym_tracer_mutex);
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+
+#define MAX_UL_INT 0xffffffff
+
+void ksym_collect_stats(unsigned long hbp_hit_addr)
+{
+	struct hlist_node *node;
+	struct trace_ksym *entry;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(entry, node, &ksym_filter_head, ksym_hlist) {
+		if ((entry->ksym_addr == hbp_hit_addr) &&
+		    (entry->counter <= MAX_UL_INT)) {
+			entry->counter++;
+			break;
+		}
+	}
+	rcu_read_unlock();
+}
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
+
+void ksym_hbp_handler(struct perf_event *hbp, void *data)
+{
+	struct ring_buffer_event *event;
+	struct ksym_trace_entry *entry;
+	struct pt_regs *regs = data;
+	struct ring_buffer *buffer;
+	int pc;
+
+	if (!ksym_tracing_enabled)
+		return;
+
+	buffer = ksym_trace_array->buffer;
+
+	pc = preempt_count();
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_KSYM,
+							sizeof(*entry), 0, pc);
+	if (!event)
+		return;
+
+	entry		= ring_buffer_event_data(event);
+	entry->ip	= instruction_pointer(regs);
+	entry->type	= hw_breakpoint_type(hbp);
+	entry->addr	= hw_breakpoint_addr(hbp);
+	strlcpy(entry->cmd, current->comm, TASK_COMM_LEN);
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+	ksym_collect_stats(hw_breakpoint_addr(hbp));
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
+
+	trace_buffer_unlock_commit(buffer, event, 0, pc);
+}
+
+/* Valid access types are represented as
+ *
+ * rw- : Set Read/Write Access Breakpoint
+ * -w- : Set Write Access Breakpoint
+ * --- : Clear Breakpoints
+ * --x : Set Execution Break points (Not available yet)
+ *
+ */
+static int ksym_trace_get_access_type(char *str)
+{
+	int access = 0;
+
+	if (str[0] == 'r')
+		access |= HW_BREAKPOINT_R;
+
+	if (str[1] == 'w')
+		access |= HW_BREAKPOINT_W;
+
+	if (str[2] == 'x')
+		access |= HW_BREAKPOINT_X;
+
+	switch (access) {
+	case HW_BREAKPOINT_R:
+	case HW_BREAKPOINT_W:
+	case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
+		return access;
+	default:
+		return -EINVAL;
+	}
+}
+
+/*
+ * There can be several possible malformed requests and we attempt to capture
+ * all of them. We enumerate some of the rules
+ * 1. We will not allow kernel symbols with ':' since it is used as a delimiter.
+ *    i.e. multiple ':' symbols disallowed. Possible uses are of the form
+ *    <module>:<ksym_name>:<op>.
+ * 2. No delimiter symbol ':' in the input string
+ * 3. Spurious operator symbols or symbols not in their respective positions
+ * 4. <ksym_name>:--- i.e. clear breakpoint request when ksym_name not in file
+ * 5. Kernel symbol not a part of /proc/kallsyms
+ * 6. Duplicate requests
+ */
+static int parse_ksym_trace_str(char *input_string, char **ksymname,
+							unsigned long *addr)
+{
+	int ret;
+
+	*ksymname = strsep(&input_string, ":");
+	*addr = kallsyms_lookup_name(*ksymname);
+
+	/* Check for malformed request: (2), (1) and (5) */
+	if ((!input_string) ||
+	    (strlen(input_string) != KSYM_TRACER_OP_LEN) ||
+	    (*addr == 0))
+		return -EINVAL;;
+
+	ret = ksym_trace_get_access_type(input_string);
+
+	return ret;
+}
+
+int process_new_ksym_entry(char *ksymname, int op, unsigned long addr)
+{
+	struct trace_ksym *entry;
+	int ret = -ENOMEM;
+
+	if (ksym_filter_entry_count >= KSYM_TRACER_MAX) {
+		printk(KERN_ERR "ksym_tracer: Maximum limit:(%d) reached. No"
+		" new requests for tracing can be accepted now.\n",
+			KSYM_TRACER_MAX);
+		return -ENOSPC;
+	}
+
+	entry = kzalloc(sizeof(struct trace_ksym), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->type = op;
+	entry->ksym_addr = addr;
+	entry->len = HW_BREAKPOINT_LEN_4;
+
+	ret = -EAGAIN;
+	entry->ksym_hbp = register_wide_hw_breakpoint(entry->ksym_addr,
+					entry->len, entry->type,
+					ksym_hbp_handler, true);
+	if (IS_ERR(entry->ksym_hbp)) {
+		entry->ksym_hbp = NULL;
+		ret = PTR_ERR(entry->ksym_hbp);
+	}
+
+	if (!entry->ksym_hbp) {
+		printk(KERN_INFO "ksym_tracer request failed. Try again"
+					" later!!\n");
+		goto err;
+	}
+
+	hlist_add_head_rcu(&(entry->ksym_hlist), &ksym_filter_head);
+	ksym_filter_entry_count++;
+
+	return 0;
+
+err:
+	kfree(entry);
+
+	return ret;
+}
+
+static ssize_t ksym_trace_filter_read(struct file *filp, char __user *ubuf,
+						size_t count, loff_t *ppos)
+{
+	struct trace_ksym *entry;
+	struct hlist_node *node;
+	struct trace_seq *s;
+	ssize_t cnt = 0;
+	int ret;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+	trace_seq_init(s);
+
+	mutex_lock(&ksym_tracer_mutex);
+
+	hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) {
+		ret = trace_seq_printf(s, "%pS:", (void *)entry->ksym_addr);
+		if (entry->type == HW_BREAKPOINT_R)
+			ret = trace_seq_puts(s, "r--\n");
+		else if (entry->type == HW_BREAKPOINT_W)
+			ret = trace_seq_puts(s, "-w-\n");
+		else if (entry->type == (HW_BREAKPOINT_W | HW_BREAKPOINT_R))
+			ret = trace_seq_puts(s, "rw-\n");
+		WARN_ON_ONCE(!ret);
+	}
+
+	cnt = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
+
+	mutex_unlock(&ksym_tracer_mutex);
+
+	kfree(s);
+
+	return cnt;
+}
+
+static void __ksym_trace_reset(void)
+{
+	struct trace_ksym *entry;
+	struct hlist_node *node, *node1;
+
+	mutex_lock(&ksym_tracer_mutex);
+	hlist_for_each_entry_safe(entry, node, node1, &ksym_filter_head,
+								ksym_hlist) {
+		unregister_wide_hw_breakpoint(entry->ksym_hbp);
+		ksym_filter_entry_count--;
+		hlist_del_rcu(&(entry->ksym_hlist));
+		synchronize_rcu();
+		kfree(entry);
+	}
+	mutex_unlock(&ksym_tracer_mutex);
+}
+
+static ssize_t ksym_trace_filter_write(struct file *file,
+					const char __user *buffer,
+						size_t count, loff_t *ppos)
+{
+	struct trace_ksym *entry;
+	struct hlist_node *node;
+	char *input_string, *ksymname = NULL;
+	unsigned long ksym_addr = 0;
+	int ret, op, changed = 0;
+
+	input_string = kzalloc(count + 1, GFP_KERNEL);
+	if (!input_string)
+		return -ENOMEM;
+
+	if (copy_from_user(input_string, buffer, count)) {
+		kfree(input_string);
+		return -EFAULT;
+	}
+	input_string[count] = '\0';
+
+	strstrip(input_string);
+
+	/*
+	 * Clear all breakpoints if:
+	 * 1: echo > ksym_trace_filter
+	 * 2: echo 0 > ksym_trace_filter
+	 * 3: echo "*:---" > ksym_trace_filter
+	 */
+	if (!input_string[0] || !strcmp(input_string, "0") ||
+	    !strcmp(input_string, "*:---")) {
+		__ksym_trace_reset();
+		kfree(input_string);
+		return count;
+	}
+
+	ret = op = parse_ksym_trace_str(input_string, &ksymname, &ksym_addr);
+	if (ret < 0) {
+		kfree(input_string);
+		return ret;
+	}
+
+	mutex_lock(&ksym_tracer_mutex);
+
+	ret = -EINVAL;
+	hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) {
+		if (entry->ksym_addr == ksym_addr) {
+			/* Check for malformed request: (6) */
+			if (entry->type != op)
+				changed = 1;
+			else
+				goto out;
+			break;
+		}
+	}
+	if (changed) {
+		unregister_wide_hw_breakpoint(entry->ksym_hbp);
+		entry->type = op;
+		if (op > 0) {
+			entry->ksym_hbp =
+				register_wide_hw_breakpoint(entry->ksym_addr,
+					entry->len, entry->type,
+					ksym_hbp_handler, true);
+			if (IS_ERR(entry->ksym_hbp))
+				entry->ksym_hbp = NULL;
+			if (!entry->ksym_hbp)
+				goto out;
+		}
+		ksym_filter_entry_count--;
+		hlist_del_rcu(&(entry->ksym_hlist));
+		synchronize_rcu();
+		kfree(entry);
+		ret = 0;
+		goto out;
+	} else {
+		/* Check for malformed request: (4) */
+		if (op == 0)
+			goto out;
+		ret = process_new_ksym_entry(ksymname, op, ksym_addr);
+	}
+out:
+	mutex_unlock(&ksym_tracer_mutex);
+
+	kfree(input_string);
+
+	if (!ret)
+		ret = count;
+	return ret;
+}
+
+static const struct file_operations ksym_tracing_fops = {
+	.open		= tracing_open_generic,
+	.read		= ksym_trace_filter_read,
+	.write		= ksym_trace_filter_write,
+};
+
+static void ksym_trace_reset(struct trace_array *tr)
+{
+	ksym_tracing_enabled = 0;
+	__ksym_trace_reset();
+}
+
+static int ksym_trace_init(struct trace_array *tr)
+{
+	int cpu, ret = 0;
+
+	for_each_online_cpu(cpu)
+		tracing_reset(tr, cpu);
+	ksym_tracing_enabled = 1;
+	ksym_trace_array = tr;
+
+	return ret;
+}
+
+static void ksym_trace_print_header(struct seq_file *m)
+{
+	seq_puts(m,
+		 "#       TASK-PID   CPU#      Symbol                    "
+		 "Type    Function\n");
+	seq_puts(m,
+		 "#          |        |          |                       "
+		 " |         |\n");
+}
+
+static enum print_line_t ksym_trace_output(struct trace_iterator *iter)
+{
+	struct trace_entry *entry = iter->ent;
+	struct trace_seq *s = &iter->seq;
+	struct ksym_trace_entry *field;
+	char str[KSYM_SYMBOL_LEN];
+	int ret;
+
+	if (entry->type != TRACE_KSYM)
+		return TRACE_TYPE_UNHANDLED;
+
+	trace_assign_type(field, entry);
+
+	ret = trace_seq_printf(s, "%11s-%-5d [%03d] %pS", field->cmd,
+				entry->pid, iter->cpu, (char *)field->addr);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	switch (field->type) {
+	case HW_BREAKPOINT_R:
+		ret = trace_seq_printf(s, " R  ");
+		break;
+	case HW_BREAKPOINT_W:
+		ret = trace_seq_printf(s, " W  ");
+		break;
+	case HW_BREAKPOINT_R | HW_BREAKPOINT_W:
+		ret = trace_seq_printf(s, " RW ");
+		break;
+	default:
+		return TRACE_TYPE_PARTIAL_LINE;
+	}
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	sprint_symbol(str, field->ip);
+	ret = trace_seq_printf(s, "%s\n", str);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+struct tracer ksym_tracer __read_mostly =
+{
+	.name		= "ksym_tracer",
+	.init		= ksym_trace_init,
+	.reset		= ksym_trace_reset,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest	= trace_selftest_startup_ksym,
+#endif
+	.print_header   = ksym_trace_print_header,
+	.print_line	= ksym_trace_output
+};
+
+__init static int init_ksym_trace(void)
+{
+	struct dentry *d_tracer;
+	struct dentry *entry;
+
+	d_tracer = tracing_init_dentry();
+	ksym_filter_entry_count = 0;
+
+	entry = debugfs_create_file("ksym_trace_filter", 0644, d_tracer,
+				    NULL, &ksym_tracing_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs "
+			   "'ksym_trace_filter' file\n");
+
+	return register_tracer(&ksym_tracer);
+}
+device_initcall(init_ksym_trace);
+
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+static int ksym_tracer_stat_headers(struct seq_file *m)
+{
+	seq_puts(m, "  Access Type ");
+	seq_puts(m, "  Symbol                                       Counter\n");
+	seq_puts(m, "  ----------- ");
+	seq_puts(m, "  ------                                       -------\n");
+	return 0;
+}
+
+static int ksym_tracer_stat_show(struct seq_file *m, void *v)
+{
+	struct hlist_node *stat = v;
+	struct trace_ksym *entry;
+	int access_type = 0;
+	char fn_name[KSYM_NAME_LEN];
+
+	entry = hlist_entry(stat, struct trace_ksym, ksym_hlist);
+
+	access_type = entry->type;
+
+	switch (access_type) {
+	case HW_BREAKPOINT_R:
+		seq_puts(m, "  R           ");
+		break;
+	case HW_BREAKPOINT_W:
+		seq_puts(m, "  W           ");
+		break;
+	case HW_BREAKPOINT_R | HW_BREAKPOINT_W:
+		seq_puts(m, "  RW          ");
+		break;
+	default:
+		seq_puts(m, "  NA          ");
+	}
+
+	if (lookup_symbol_name(entry->ksym_addr, fn_name) >= 0)
+		seq_printf(m, "  %-36s", fn_name);
+	else
+		seq_printf(m, "  %-36s", "<NA>");
+	seq_printf(m, " %15lu\n", entry->counter);
+
+	return 0;
+}
+
+static void *ksym_tracer_stat_start(struct tracer_stat *trace)
+{
+	return ksym_filter_head.first;
+}
+
+static void *
+ksym_tracer_stat_next(void *v, int idx)
+{
+	struct hlist_node *stat = v;
+
+	return stat->next;
+}
+
+static struct tracer_stat ksym_tracer_stats = {
+	.name = "ksym_tracer",
+	.stat_start = ksym_tracer_stat_start,
+	.stat_next = ksym_tracer_stat_next,
+	.stat_headers = ksym_tracer_stat_headers,
+	.stat_show = ksym_tracer_stat_show
+};
+
+__init static int ksym_tracer_stat_init(void)
+{
+	int ret;
+
+	ret = register_stat_tracer(&ksym_tracer_stats);
+	if (ret) {
+		printk(KERN_WARNING "Warning: could not register "
+				    "ksym tracer stats\n");
+		return 1;
+	}
+
+	return 0;
+}
+fs_initcall(ksym_tracer_stat_init);
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index d2cdbabb4ead..dc98309e839a 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -17,6 +17,7 @@ static inline int trace_valid_entry(struct trace_entry *entry)
 	case TRACE_GRAPH_ENT:
 	case TRACE_GRAPH_RET:
 	case TRACE_HW_BRANCHES:
+	case TRACE_KSYM:
 		return 1;
 	}
 	return 0;
@@ -808,3 +809,57 @@ trace_selftest_startup_hw_branches(struct tracer *trace,
 	return ret;
 }
 #endif /* CONFIG_HW_BRANCH_TRACER */
+
+#ifdef CONFIG_KSYM_TRACER
+static int ksym_selftest_dummy;
+
+int
+trace_selftest_startup_ksym(struct tracer *trace, struct trace_array *tr)
+{
+	unsigned long count;
+	int ret;
+
+	/* start the tracing */
+	ret = tracer_init(trace, tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
+	ksym_selftest_dummy = 0;
+	/* Register the read-write tracing request */
+
+	ret = process_new_ksym_entry("ksym_selftest_dummy",
+				     HW_BREAKPOINT_R | HW_BREAKPOINT_W,
+					(unsigned long)(&ksym_selftest_dummy));
+
+	if (ret < 0) {
+		printk(KERN_CONT "ksym_trace read-write startup test failed\n");
+		goto ret_path;
+	}
+	/* Perform a read and a write operation over the dummy variable to
+	 * trigger the tracer
+	 */
+	if (ksym_selftest_dummy == 0)
+		ksym_selftest_dummy++;
+
+	/* stop the tracing. */
+	tracing_stop();
+	/* check the trace buffer */
+	ret = trace_test_buffer(tr, &count);
+	trace->reset(tr);
+	tracing_start();
+
+	/* read & write operations - one each is performed on the dummy variable
+	 * triggering two entries in the trace buffer
+	 */
+	if (!ret && count != 2) {
+		printk(KERN_CONT "Ksym tracer startup test failed");
+		ret = -1;
+	}
+
+ret_path:
+	return ret;
+}
+#endif /* CONFIG_KSYM_TRACER */
+
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 527e17eae575..9189cbe86079 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -14,6 +14,69 @@ static int sys_refcount_exit;
 static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
 static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
 
+extern unsigned long __start_syscalls_metadata[];
+extern unsigned long __stop_syscalls_metadata[];
+
+static struct syscall_metadata **syscalls_metadata;
+
+static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
+{
+	struct syscall_metadata *start;
+	struct syscall_metadata *stop;
+	char str[KSYM_SYMBOL_LEN];
+
+
+	start = (struct syscall_metadata *)__start_syscalls_metadata;
+	stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+	kallsyms_lookup(syscall, NULL, NULL, NULL, str);
+
+	for ( ; start < stop; start++) {
+		/*
+		 * Only compare after the "sys" prefix. Archs that use
+		 * syscall wrappers may have syscalls symbols aliases prefixed
+		 * with "SyS" instead of "sys", leading to an unwanted
+		 * mismatch.
+		 */
+		if (start->name && !strcmp(start->name + 3, str + 3))
+			return start;
+	}
+	return NULL;
+}
+
+static struct syscall_metadata *syscall_nr_to_meta(int nr)
+{
+	if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
+		return NULL;
+
+	return syscalls_metadata[nr];
+}
+
+int syscall_name_to_nr(char *name)
+{
+	int i;
+
+	if (!syscalls_metadata)
+		return -1;
+
+	for (i = 0; i < NR_syscalls; i++) {
+		if (syscalls_metadata[i]) {
+			if (!strcmp(syscalls_metadata[i]->name, name))
+				return i;
+		}
+	}
+	return -1;
+}
+
+void set_syscall_enter_id(int num, int id)
+{
+	syscalls_metadata[num]->enter_id = id;
+}
+
+void set_syscall_exit_id(int num, int id)
+{
+	syscalls_metadata[num]->exit_id = id;
+}
+
 enum print_line_t
 print_syscall_enter(struct trace_iterator *iter, int flags)
 {
@@ -103,7 +166,8 @@ extern char *__bad_type_size(void);
 #define SYSCALL_FIELD(type, name)					\
 	sizeof(type) != sizeof(trace.name) ?				\
 		__bad_type_size() :					\
-		#type, #name, offsetof(typeof(trace), name), sizeof(trace.name)
+		#type, #name, offsetof(typeof(trace), name),		\
+		sizeof(trace.name), is_signed_type(type)
 
 int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
 {
@@ -120,7 +184,8 @@ int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
 	if (!entry)
 		return 0;
 
-	ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
+	ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
+			       "\tsigned:%u;\n",
 			       SYSCALL_FIELD(int, nr));
 	if (!ret)
 		return 0;
@@ -130,8 +195,10 @@ int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
 				        entry->args[i]);
 		if (!ret)
 			return 0;
-		ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;\n", offset,
-				       sizeof(unsigned long));
+		ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;"
+				       "\tsigned:%u;\n", offset,
+				       sizeof(unsigned long),
+				       is_signed_type(unsigned long));
 		if (!ret)
 			return 0;
 		offset += sizeof(unsigned long);
@@ -163,8 +230,10 @@ int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
 	struct syscall_trace_exit trace;
 
 	ret = trace_seq_printf(s,
-			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
+			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
+			       "\tsigned:%u;\n"
+			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
+			       "\tsigned:%u;\n",
 			       SYSCALL_FIELD(int, nr),
 			       SYSCALL_FIELD(long, ret));
 	if (!ret)
@@ -212,7 +281,7 @@ int syscall_exit_define_fields(struct ftrace_event_call *call)
 	if (ret)
 		return ret;
 
-	ret = trace_define_field(call, SYSCALL_FIELD(long, ret), 0,
+	ret = trace_define_field(call, SYSCALL_FIELD(long, ret),
 				 FILTER_OTHER);
 
 	return ret;
@@ -285,13 +354,13 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret)
 		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-int reg_event_syscall_enter(void *ptr)
+int reg_event_syscall_enter(struct ftrace_event_call *call)
 {
 	int ret = 0;
 	int num;
 	char *name;
 
-	name = (char *)ptr;
+	name = (char *)call->data;
 	num = syscall_name_to_nr(name);
 	if (num < 0 || num >= NR_syscalls)
 		return -ENOSYS;
@@ -309,12 +378,12 @@ int reg_event_syscall_enter(void *ptr)
 	return ret;
 }
 
-void unreg_event_syscall_enter(void *ptr)
+void unreg_event_syscall_enter(struct ftrace_event_call *call)
 {
 	int num;
 	char *name;
 
-	name = (char *)ptr;
+	name = (char *)call->data;
 	num = syscall_name_to_nr(name);
 	if (num < 0 || num >= NR_syscalls)
 		return;
@@ -326,13 +395,13 @@ void unreg_event_syscall_enter(void *ptr)
 	mutex_unlock(&syscall_trace_lock);
 }
 
-int reg_event_syscall_exit(void *ptr)
+int reg_event_syscall_exit(struct ftrace_event_call *call)
 {
 	int ret = 0;
 	int num;
 	char *name;
 
-	name = (char *)ptr;
+	name = call->data;
 	num = syscall_name_to_nr(name);
 	if (num < 0 || num >= NR_syscalls)
 		return -ENOSYS;
@@ -350,12 +419,12 @@ int reg_event_syscall_exit(void *ptr)
 	return ret;
 }
 
-void unreg_event_syscall_exit(void *ptr)
+void unreg_event_syscall_exit(struct ftrace_event_call *call)
 {
 	int num;
 	char *name;
 
-	name = (char *)ptr;
+	name = call->data;
 	num = syscall_name_to_nr(name);
 	if (num < 0 || num >= NR_syscalls)
 		return;
@@ -375,6 +444,29 @@ struct trace_event event_syscall_exit = {
 	.trace			= print_syscall_exit,
 };
 
+int __init init_ftrace_syscalls(void)
+{
+	struct syscall_metadata *meta;
+	unsigned long addr;
+	int i;
+
+	syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
+					NR_syscalls, GFP_KERNEL);
+	if (!syscalls_metadata) {
+		WARN_ON(1);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < NR_syscalls; i++) {
+		addr = arch_syscall_addr(i);
+		meta = find_syscall_meta(addr);
+		syscalls_metadata[i] = meta;
+	}
+
+	return 0;
+}
+core_initcall(init_ftrace_syscalls);
+
 #ifdef CONFIG_EVENT_PROFILE
 
 static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls);
@@ -387,8 +479,10 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_enter *rec;
 	unsigned long flags;
+	char *trace_buf;
 	char *raw_data;
 	int syscall_nr;
+	int rctx;
 	int size;
 	int cpu;
 
@@ -412,17 +506,18 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
 	/* Protect the per cpu buffer, begin the rcu read side */
 	local_irq_save(flags);
 
+	rctx = perf_swevent_get_recursion_context();
+	if (rctx < 0)
+		goto end_recursion;
+
 	cpu = smp_processor_id();
 
-	if (in_nmi())
-		raw_data = rcu_dereference(trace_profile_buf_nmi);
-	else
-		raw_data = rcu_dereference(trace_profile_buf);
+	trace_buf = rcu_dereference(perf_trace_buf);
 
-	if (!raw_data)
+	if (!trace_buf)
 		goto end;
 
-	raw_data = per_cpu_ptr(raw_data, cpu);
+	raw_data = per_cpu_ptr(trace_buf, cpu);
 
 	/* zero the dead bytes from align to not leak stack to user */
 	*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
@@ -436,6 +531,8 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
 	perf_tp_event(sys_data->enter_id, 0, 1, rec, size);
 
 end:
+	perf_swevent_put_recursion_context(rctx);
+end_recursion:
 	local_irq_restore(flags);
 }
 
@@ -484,7 +581,9 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
 	struct syscall_trace_exit *rec;
 	unsigned long flags;
 	int syscall_nr;
+	char *trace_buf;
 	char *raw_data;
+	int rctx;
 	int size;
 	int cpu;
 
@@ -510,17 +609,19 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
 
 	/* Protect the per cpu buffer, begin the rcu read side */
 	local_irq_save(flags);
+
+	rctx = perf_swevent_get_recursion_context();
+	if (rctx < 0)
+		goto end_recursion;
+
 	cpu = smp_processor_id();
 
-	if (in_nmi())
-		raw_data = rcu_dereference(trace_profile_buf_nmi);
-	else
-		raw_data = rcu_dereference(trace_profile_buf);
+	trace_buf = rcu_dereference(perf_trace_buf);
 
-	if (!raw_data)
+	if (!trace_buf)
 		goto end;
 
-	raw_data = per_cpu_ptr(raw_data, cpu);
+	raw_data = per_cpu_ptr(trace_buf, cpu);
 
 	/* zero the dead bytes from align to not leak stack to user */
 	*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
@@ -535,6 +636,8 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
 	perf_tp_event(sys_data->exit_id, 0, 1, rec, size);
 
 end:
+	perf_swevent_put_recursion_context(rctx);
+end_recursion:
 	local_irq_restore(flags);
 }