Merge branch 'linus' into perfcounters/core

Merge reason: need the upstream facility added by:

  7f1e2ca: hrtimer: fix rq->lock inversion (again)

Signed-off-by: Ingo Molnar <mingo@elte.hu>

13 files changed, 379 insertions, 132 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 7a14a2b504f5..fbb5d94c8bbc 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -840,8 +840,7 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 	 */
 	if (tsk->exit_signal != SIGCHLD && !task_detached(tsk) &&
 	    (tsk->parent_exec_id != tsk->real_parent->self_exec_id ||
-	     tsk->self_exec_id != tsk->parent_exec_id) &&
-	    !capable(CAP_KILL))
+	     tsk->self_exec_id != tsk->parent_exec_id))
 		tsk->exit_signal = SIGCHLD;
 
 	signal = tracehook_notify_death(tsk, &cookie, group_dead);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index f394d2a42ca3..cb8a15c19583 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -651,14 +651,20 @@ static inline void hrtimer_init_timer_hres(struct hrtimer *timer)
  * and expiry check is done in the hrtimer_interrupt or in the softirq.
  */
 static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
-					    struct hrtimer_clock_base *base)
+					    struct hrtimer_clock_base *base,
+					    int wakeup)
 {
 	if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
-		spin_unlock(&base->cpu_base->lock);
-		raise_softirq_irqoff(HRTIMER_SOFTIRQ);
-		spin_lock(&base->cpu_base->lock);
+		if (wakeup) {
+			spin_unlock(&base->cpu_base->lock);
+			raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+			spin_lock(&base->cpu_base->lock);
+		} else
+			__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+
 		return 1;
 	}
+
 	return 0;
 }
 
@@ -703,7 +709,8 @@ static inline int hrtimer_is_hres_enabled(void) { return 0; }
 static inline int hrtimer_switch_to_hres(void) { return 0; }
 static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base) { }
 static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
-					    struct hrtimer_clock_base *base)
+					    struct hrtimer_clock_base *base,
+					    int wakeup)
 {
 	return 0;
 }
@@ -886,20 +893,9 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 	return 0;
 }
 
-/**
- * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
- * @timer:	the timer to be added
- * @tim:	expiry time
- * @delta_ns:	"slack" range for the timer
- * @mode:	expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
- *
- * Returns:
- *  0 on success
- *  1 when the timer was active
- */
-int
-hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_ns,
-			const enum hrtimer_mode mode)
+int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+		unsigned long delta_ns, const enum hrtimer_mode mode,
+		int wakeup)
 {
 	struct hrtimer_clock_base *base, *new_base;
 	unsigned long flags;
@@ -940,12 +936,29 @@ hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_n
 	 * XXX send_remote_softirq() ?
 	 */
 	if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases))
-		hrtimer_enqueue_reprogram(timer, new_base);
+		hrtimer_enqueue_reprogram(timer, new_base, wakeup);
 
 	unlock_hrtimer_base(timer, &flags);
 
 	return ret;
 }
+
+/**
+ * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
+ * @timer:	the timer to be added
+ * @tim:	expiry time
+ * @delta_ns:	"slack" range for the timer
+ * @mode:	expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
+ *
+ * Returns:
+ *  0 on success
+ *  1 when the timer was active
+ */
+int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+		unsigned long delta_ns, const enum hrtimer_mode mode)
+{
+	return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, 1);
+}
 EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
 
 /**
@@ -961,7 +974,7 @@ EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
 int
 hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 {
-	return hrtimer_start_range_ns(timer, tim, 0, mode);
+	return __hrtimer_start_range_ns(timer, tim, 0, mode, 1);
 }
 EXPORT_SYMBOL_GPL(hrtimer_start);
 
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 81b5f33970b8..b0f011866969 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -793,6 +793,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 
 		printk("BUG: MAX_LOCKDEP_KEYS too low!\n");
 		printk("turning off the locking correctness validator.\n");
+		dump_stack();
 		return NULL;
 	}
 	class = lock_classes + nr_lock_classes++;
@@ -856,6 +857,7 @@ static struct lock_list *alloc_list_entry(void)
 
 		printk("BUG: MAX_LOCKDEP_ENTRIES too low!\n");
 		printk("turning off the locking correctness validator.\n");
+		dump_stack();
 		return NULL;
 	}
 	return list_entries + nr_list_entries++;
@@ -1682,6 +1684,7 @@ cache_hit:
 
 		printk("BUG: MAX_LOCKDEP_CHAINS too low!\n");
 		printk("turning off the locking correctness validator.\n");
+		dump_stack();
 		return 0;
 	}
 	chain = lock_chains + nr_lock_chains++;
@@ -2541,6 +2544,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 		debug_locks_off();
 		printk("BUG: MAX_LOCKDEP_SUBCLASSES too low!\n");
 		printk("turning off the locking correctness validator.\n");
+		dump_stack();
 		return 0;
 	}
 
@@ -2637,6 +2641,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 		debug_locks_off();
 		printk("BUG: MAX_LOCK_DEPTH too low!\n");
 		printk("turning off the locking correctness validator.\n");
+		dump_stack();
 		return 0;
 	}
 
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index 654c640a6b9c..0f2b0b311304 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -65,6 +65,7 @@ static struct rcu_ctrlblk rcu_ctrlblk = {
 	.lock = __SPIN_LOCK_UNLOCKED(&rcu_ctrlblk.lock),
 	.cpumask = CPU_BITS_NONE,
 };
+
 static struct rcu_ctrlblk rcu_bh_ctrlblk = {
 	.cur = -300,
 	.completed = -300,
@@ -73,8 +74,26 @@ static struct rcu_ctrlblk rcu_bh_ctrlblk = {
 	.cpumask = CPU_BITS_NONE,
 };
 
-DEFINE_PER_CPU(struct rcu_data, rcu_data) = { 0L };
-DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L };
+static DEFINE_PER_CPU(struct rcu_data, rcu_data);
+static DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
+
+/*
+ * Increment the quiescent state counter.
+ * The counter is a bit degenerated: We do not need to know
+ * how many quiescent states passed, just if there was at least
+ * one since the start of the grace period. Thus just a flag.
+ */
+void rcu_qsctr_inc(int cpu)
+{
+	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+	rdp->passed_quiesc = 1;
+}
+
+void rcu_bh_qsctr_inc(int cpu)
+{
+	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
+	rdp->passed_quiesc = 1;
+}
 
 static int blimit = 10;
 static int qhimark = 10000;
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index 5d59e850fb71..ce97a4df64d3 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -147,7 +147,51 @@ struct rcu_ctrlblk {
 	wait_queue_head_t sched_wq;	/* Place for rcu_sched to sleep. */
 };
 
+struct rcu_dyntick_sched {
+	int dynticks;
+	int dynticks_snap;
+	int sched_qs;
+	int sched_qs_snap;
+	int sched_dynticks_snap;
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_dyntick_sched, rcu_dyntick_sched) = {
+	.dynticks = 1,
+};
+
+void rcu_qsctr_inc(int cpu)
+{
+	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
+
+	rdssp->sched_qs++;
+}
+
+#ifdef CONFIG_NO_HZ
+
+void rcu_enter_nohz(void)
+{
+	static DEFINE_RATELIMIT_STATE(rs, 10 * HZ, 1);
+
+	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
+	__get_cpu_var(rcu_dyntick_sched).dynticks++;
+	WARN_ON_RATELIMIT(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1, &rs);
+}
+
+void rcu_exit_nohz(void)
+{
+	static DEFINE_RATELIMIT_STATE(rs, 10 * HZ, 1);
+
+	__get_cpu_var(rcu_dyntick_sched).dynticks++;
+	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+	WARN_ON_RATELIMIT(!(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1),
+				&rs);
+}
+
+#endif /* CONFIG_NO_HZ */
+
+
 static DEFINE_PER_CPU(struct rcu_data, rcu_data);
+
 static struct rcu_ctrlblk rcu_ctrlblk = {
 	.fliplock = __SPIN_LOCK_UNLOCKED(rcu_ctrlblk.fliplock),
 	.completed = 0,
@@ -427,10 +471,6 @@ static void __rcu_advance_callbacks(struct rcu_data *rdp)
 	}
 }
 
-DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_dyntick_sched, rcu_dyntick_sched) = {
-	.dynticks = 1,
-};
-
 #ifdef CONFIG_NO_HZ
 static DEFINE_PER_CPU(int, rcu_update_flag);
 
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 97ce31579ec0..7f3266922572 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -78,6 +78,26 @@ DEFINE_PER_CPU(struct rcu_data, rcu_data);
 struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state);
 DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
 
+/*
+ * Increment the quiescent state counter.
+ * The counter is a bit degenerated: We do not need to know
+ * how many quiescent states passed, just if there was at least
+ * one since the start of the grace period. Thus just a flag.
+ */
+void rcu_qsctr_inc(int cpu)
+{
+	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+	rdp->passed_quiesc = 1;
+	rdp->passed_quiesc_completed = rdp->completed;
+}
+
+void rcu_bh_qsctr_inc(int cpu)
+{
+	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
+	rdp->passed_quiesc = 1;
+	rdp->passed_quiesc_completed = rdp->completed;
+}
+
 #ifdef CONFIG_NO_HZ
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = 1,
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
new file mode 100644
index 000000000000..5e872bbf07f5
--- /dev/null
+++ b/kernel/rcutree.h
@@ -0,0 +1,10 @@
+
+/*
+ * RCU implementation internal declarations:
+ */
+extern struct rcu_state rcu_state;
+DECLARE_PER_CPU(struct rcu_data, rcu_data);
+
+extern struct rcu_state rcu_bh_state;
+DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
+
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index d6db3e837826..4ee954f6a8d5 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -43,6 +43,8 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 
+#include "rcutree.h"
+
 static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 {
 	if (!rdp->beenonline)
diff --git a/kernel/sched.c b/kernel/sched.c
index 0de2f814fb18..b66a08c2480e 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -231,13 +231,20 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 
 	spin_lock(&rt_b->rt_runtime_lock);
 	for (;;) {
+		unsigned long delta;
+		ktime_t soft, hard;
+
 		if (hrtimer_active(&rt_b->rt_period_timer))
 			break;
 
 		now = hrtimer_cb_get_time(&rt_b->rt_period_timer);
 		hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period);
-		hrtimer_start_expires(&rt_b->rt_period_timer,
-				HRTIMER_MODE_ABS);
+
+		soft = hrtimer_get_softexpires(&rt_b->rt_period_timer);
+		hard = hrtimer_get_expires(&rt_b->rt_period_timer);
+		delta = ktime_to_ns(ktime_sub(hard, soft));
+		__hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta,
+				HRTIMER_MODE_ABS, 0);
 	}
 	spin_unlock(&rt_b->rt_runtime_lock);
 }
@@ -1147,7 +1154,8 @@ static __init void init_hrtick(void)
  */
 static void hrtick_start(struct rq *rq, u64 delay)
 {
-	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL);
+	__hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
+			HRTIMER_MODE_REL, 0);
 }
 
 static inline void init_hrtick(void)
diff --git a/kernel/softirq.c b/kernel/softirq.c
index d105a82543d0..2fecefacdc5b 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -65,7 +65,7 @@ char *softirq_to_name[NR_SOFTIRQS] = {
  * to the pending events, so lets the scheduler to balance
  * the softirq load for us.
  */
-static inline void wakeup_softirqd(void)
+void wakeup_softirqd(void)
 {
 	/* Interrupts are disabled: no need to stop preemption */
 	struct task_struct *tsk = __get_cpu_var(ksoftirqd);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 82350f8f04f6..b125e3387568 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -97,8 +97,8 @@ static int neg_one = -1;
 #endif
 
 static int zero;
-static int one = 1;
-static int two = 2;
+static int __maybe_unused one = 1;
+static int __maybe_unused two = 2;
 static unsigned long one_ul = 1;
 static int one_hundred = 100;
 
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index ae201b3eda89..5011f4d91e37 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -6,14 +6,16 @@
  * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
  */
 
-#include <linux/dcache.h>
+#include <linux/tracepoint.h>
+#include <linux/seq_file.h>
 #include <linux/debugfs.h>
+#include <linux/dcache.h>
 #include <linux/fs.h>
-#include <linux/seq_file.h>
+
 #include <trace/kmemtrace.h>
 
-#include "trace.h"
 #include "trace_output.h"
+#include "trace.h"
 
 /* Select an alternative, minimalistic output than the original one */
 #define TRACE_KMEM_OPT_MINIMAL	0x1
@@ -25,14 +27,156 @@ static struct tracer_opt kmem_opts[] = {
 };
 
 static struct tracer_flags kmem_tracer_flags = {
-	.val = 0,
-	.opts = kmem_opts
+	.val			= 0,
+	.opts			= kmem_opts
 };
 
-
-static bool kmem_tracing_enabled __read_mostly;
 static struct trace_array *kmemtrace_array;
 
+/* Trace allocations */
+static inline void kmemtrace_alloc(enum kmemtrace_type_id type_id,
+				   unsigned long call_site,
+				   const void *ptr,
+				   size_t bytes_req,
+				   size_t bytes_alloc,
+				   gfp_t gfp_flags,
+				   int node)
+{
+	struct trace_array *tr = kmemtrace_array;
+	struct kmemtrace_alloc_entry *entry;
+	struct ring_buffer_event *event;
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry));
+	if (!event)
+		return;
+
+	entry = ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, 0, 0);
+
+	entry->ent.type		= TRACE_KMEM_ALLOC;
+	entry->type_id		= type_id;
+	entry->call_site	= call_site;
+	entry->ptr		= ptr;
+	entry->bytes_req	= bytes_req;
+	entry->bytes_alloc	= bytes_alloc;
+	entry->gfp_flags	= gfp_flags;
+	entry->node		= node;
+
+	ring_buffer_unlock_commit(tr->buffer, event);
+
+	trace_wake_up();
+}
+
+static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
+				  unsigned long call_site,
+				  const void *ptr)
+{
+	struct trace_array *tr = kmemtrace_array;
+	struct kmemtrace_free_entry *entry;
+	struct ring_buffer_event *event;
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry));
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, 0, 0);
+
+	entry->ent.type		= TRACE_KMEM_FREE;
+	entry->type_id		= type_id;
+	entry->call_site	= call_site;
+	entry->ptr		= ptr;
+
+	ring_buffer_unlock_commit(tr->buffer, event);
+
+	trace_wake_up();
+}
+
+static void kmemtrace_kmalloc(unsigned long call_site,
+			      const void *ptr,
+			      size_t bytes_req,
+			      size_t bytes_alloc,
+			      gfp_t gfp_flags)
+{
+	kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr,
+			bytes_req, bytes_alloc, gfp_flags, -1);
+}
+
+static void kmemtrace_kmem_cache_alloc(unsigned long call_site,
+				       const void *ptr,
+				       size_t bytes_req,
+				       size_t bytes_alloc,
+				       gfp_t gfp_flags)
+{
+	kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr,
+			bytes_req, bytes_alloc, gfp_flags, -1);
+}
+
+static void kmemtrace_kmalloc_node(unsigned long call_site,
+				   const void *ptr,
+				   size_t bytes_req,
+				   size_t bytes_alloc,
+				   gfp_t gfp_flags,
+				   int node)
+{
+	kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr,
+			bytes_req, bytes_alloc, gfp_flags, node);
+}
+
+static void kmemtrace_kmem_cache_alloc_node(unsigned long call_site,
+					    const void *ptr,
+					    size_t bytes_req,
+					    size_t bytes_alloc,
+					    gfp_t gfp_flags,
+					    int node)
+{
+	kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr,
+			bytes_req, bytes_alloc, gfp_flags, node);
+}
+
+static void kmemtrace_kfree(unsigned long call_site, const void *ptr)
+{
+	kmemtrace_free(KMEMTRACE_TYPE_KMALLOC, call_site, ptr);
+}
+
+static void kmemtrace_kmem_cache_free(unsigned long call_site, const void *ptr)
+{
+	kmemtrace_free(KMEMTRACE_TYPE_CACHE, call_site, ptr);
+}
+
+static int kmemtrace_start_probes(void)
+{
+	int err;
+
+	err = register_trace_kmalloc(kmemtrace_kmalloc);
+	if (err)
+		return err;
+	err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
+	if (err)
+		return err;
+	err = register_trace_kmalloc_node(kmemtrace_kmalloc_node);
+	if (err)
+		return err;
+	err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
+	if (err)
+		return err;
+	err = register_trace_kfree(kmemtrace_kfree);
+	if (err)
+		return err;
+	err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+
+	return err;
+}
+
+static void kmemtrace_stop_probes(void)
+{
+	unregister_trace_kmalloc(kmemtrace_kmalloc);
+	unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
+	unregister_trace_kmalloc_node(kmemtrace_kmalloc_node);
+	unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
+	unregister_trace_kfree(kmemtrace_kfree);
+	unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+}
+
 static int kmem_trace_init(struct trace_array *tr)
 {
 	int cpu;
@@ -41,14 +185,14 @@ static int kmem_trace_init(struct trace_array *tr)
 	for_each_cpu_mask(cpu, cpu_possible_map)
 		tracing_reset(tr, cpu);
 
-	kmem_tracing_enabled = true;
+	kmemtrace_start_probes();
 
 	return 0;
 }
 
 static void kmem_trace_reset(struct trace_array *tr)
 {
-	kmem_tracing_enabled = false;
+	kmemtrace_stop_probes();
 }
 
 static void kmemtrace_headers(struct seq_file *s)
@@ -66,47 +210,84 @@ static void kmemtrace_headers(struct seq_file *s)
 }
 
 /*
- * The two following functions give the original output from kmemtrace,
- * or something close to....perhaps they need some missing things
+ * The following functions give the original output from kmemtrace,
+ * plus the origin CPU, since reordering occurs in-kernel now.
  */
+
+#define KMEMTRACE_USER_ALLOC	0
+#define KMEMTRACE_USER_FREE	1
+
+struct kmemtrace_user_event {
+	u8			event_id;
+	u8			type_id;
+	u16			event_size;
+	u32			cpu;
+	u64			timestamp;
+	unsigned long		call_site;
+	unsigned long		ptr;
+};
+
+struct kmemtrace_user_event_alloc {
+	size_t			bytes_req;
+	size_t			bytes_alloc;
+	unsigned		gfp_flags;
+	int			node;
+};
+
 static enum print_line_t
-kmemtrace_print_alloc_original(struct trace_iterator *iter,
-				struct kmemtrace_alloc_entry *entry)
+kmemtrace_print_alloc_user(struct trace_iterator *iter,
+			   struct kmemtrace_alloc_entry *entry)
 {
+	struct kmemtrace_user_event_alloc *ev_alloc;
 	struct trace_seq *s = &iter->seq;
-	int ret;
+	struct kmemtrace_user_event *ev;
+
+	ev = trace_seq_reserve(s, sizeof(*ev));
+	if (!ev)
+		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Taken from the old linux/kmemtrace.h */
-	ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu "
-	  "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n",
-	   entry->type_id, entry->call_site, (unsigned long) entry->ptr,
-	   (unsigned long) entry->bytes_req, (unsigned long) entry->bytes_alloc,
-	   (unsigned long) entry->gfp_flags, entry->node);
+	ev->event_id		= KMEMTRACE_USER_ALLOC;
+	ev->type_id		= entry->type_id;
+	ev->event_size		= sizeof(*ev) + sizeof(*ev_alloc);
+	ev->cpu			= iter->cpu;
+	ev->timestamp		= iter->ts;
+	ev->call_site		= entry->call_site;
+	ev->ptr			= (unsigned long)entry->ptr;
 
-	if (!ret)
+	ev_alloc = trace_seq_reserve(s, sizeof(*ev_alloc));
+	if (!ev_alloc)
 		return TRACE_TYPE_PARTIAL_LINE;
 
+	ev_alloc->bytes_req	= entry->bytes_req;
+	ev_alloc->bytes_alloc	= entry->bytes_alloc;
+	ev_alloc->gfp_flags	= entry->gfp_flags;
+	ev_alloc->node		= entry->node;
+
 	return TRACE_TYPE_HANDLED;
 }
 
 static enum print_line_t
-kmemtrace_print_free_original(struct trace_iterator *iter,
-				struct kmemtrace_free_entry *entry)
+kmemtrace_print_free_user(struct trace_iterator *iter,
+			  struct kmemtrace_free_entry *entry)
 {
 	struct trace_seq *s = &iter->seq;
-	int ret;
+	struct kmemtrace_user_event *ev;
 
-	/* Taken from the old linux/kmemtrace.h */
-	ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu\n",
-	   entry->type_id, entry->call_site, (unsigned long) entry->ptr);
-
-	if (!ret)
+	ev = trace_seq_reserve(s, sizeof(*ev));
+	if (!ev)
 		return TRACE_TYPE_PARTIAL_LINE;
 
+	ev->event_id		= KMEMTRACE_USER_FREE;
+	ev->type_id		= entry->type_id;
+	ev->event_size		= sizeof(*ev);
+	ev->cpu			= iter->cpu;
+	ev->timestamp		= iter->ts;
+	ev->call_site		= entry->call_site;
+	ev->ptr			= (unsigned long)entry->ptr;
+
 	return TRACE_TYPE_HANDLED;
 }
 
-
 /* The two other following provide a more minimalistic output */
 static enum print_line_t
 kmemtrace_print_alloc_compress(struct trace_iterator *iter,
@@ -178,7 +359,7 @@ kmemtrace_print_alloc_compress(struct trace_iterator *iter,
 
 static enum print_line_t
 kmemtrace_print_free_compress(struct trace_iterator *iter,
-				struct kmemtrace_free_entry *entry)
+			      struct kmemtrace_free_entry *entry)
 {
 	struct trace_seq *s = &iter->seq;
 	int ret;
@@ -239,20 +420,22 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
 	switch (entry->type) {
 	case TRACE_KMEM_ALLOC: {
 		struct kmemtrace_alloc_entry *field;
+
 		trace_assign_type(field, entry);
 		if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
 			return kmemtrace_print_alloc_compress(iter, field);
 		else
-			return kmemtrace_print_alloc_original(iter, field);
+			return kmemtrace_print_alloc_user(iter, field);
 	}
 
 	case TRACE_KMEM_FREE: {
 		struct kmemtrace_free_entry *field;
+
 		trace_assign_type(field, entry);
 		if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
 			return kmemtrace_print_free_compress(iter, field);
 		else
-			return kmemtrace_print_free_original(iter, field);
+			return kmemtrace_print_free_user(iter, field);
 	}
 
 	default:
@@ -260,70 +443,13 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
 	}
 }
 
-/* Trace allocations */
-void kmemtrace_mark_alloc_node(enum kmemtrace_type_id type_id,
-			     unsigned long call_site,
-			     const void *ptr,
-			     size_t bytes_req,
-			     size_t bytes_alloc,
-			     gfp_t gfp_flags,
-			     int node)
-{
-	struct ring_buffer_event *event;
-	struct kmemtrace_alloc_entry *entry;
-	struct trace_array *tr = kmemtrace_array;
-
-	if (!kmem_tracing_enabled)
-		return;
-
-	event = trace_buffer_lock_reserve(tr, TRACE_KMEM_ALLOC,
-					  sizeof(*entry), 0, 0);
-	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-
-	entry->call_site = call_site;
-	entry->ptr = ptr;
-	entry->bytes_req = bytes_req;
-	entry->bytes_alloc = bytes_alloc;
-	entry->gfp_flags = gfp_flags;
-	entry->node	=	node;
-
-	trace_buffer_unlock_commit(tr, event, 0, 0);
-}
-EXPORT_SYMBOL(kmemtrace_mark_alloc_node);
-
-void kmemtrace_mark_free(enum kmemtrace_type_id type_id,
-		       unsigned long call_site,
-		       const void *ptr)
-{
-	struct ring_buffer_event *event;
-	struct kmemtrace_free_entry *entry;
-	struct trace_array *tr = kmemtrace_array;
-
-	if (!kmem_tracing_enabled)
-		return;
-
-	event = trace_buffer_lock_reserve(tr, TRACE_KMEM_FREE,
-					  sizeof(*entry), 0, 0);
-	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-	entry->type_id	= type_id;
-	entry->call_site = call_site;
-	entry->ptr = ptr;
-
-	trace_buffer_unlock_commit(tr, event, 0, 0);
-}
-EXPORT_SYMBOL(kmemtrace_mark_free);
-
 static struct tracer kmem_tracer __read_mostly = {
-	.name		= "kmemtrace",
-	.init		= kmem_trace_init,
-	.reset		= kmem_trace_reset,
-	.print_line	= kmemtrace_print_line,
-	.print_header = kmemtrace_headers,
-	.flags		= &kmem_tracer_flags
+	.name			= "kmemtrace",
+	.init			= kmem_trace_init,
+	.reset			= kmem_trace_reset,
+	.print_line		= kmemtrace_print_line,
+	.print_header		= kmemtrace_headers,
+	.flags			= &kmem_tracer_flags
 };
 
 void kmemtrace_init(void)
@@ -335,5 +461,4 @@ static int __init init_kmem_tracer(void)
 {
 	return register_tracer(&kmem_tracer);
 }
-
 device_initcall(init_kmem_tracer);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index cb0ce3fc36d3..cbc168f1e43d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -182,6 +182,12 @@ struct trace_power {
 	struct power_trace	state_data;
 };
 
+enum kmemtrace_type_id {
+	KMEMTRACE_TYPE_KMALLOC = 0,	/* kmalloc() or kfree(). */
+	KMEMTRACE_TYPE_CACHE,		/* kmem_cache_*(). */
+	KMEMTRACE_TYPE_PAGES,		/* __get_free_pages() and friends. */
+};
+
 struct kmemtrace_alloc_entry {
 	struct trace_entry	ent;
 	enum kmemtrace_type_id type_id;