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

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (162 commits)
  tracing/kprobes: unregister_trace_probe needs to be called under mutex
  perf: expose event__process function
  perf events: Fix mmap offset determination
  perf, powerpc: fsl_emb: Restore setting perf_sample_data.period
  perf, powerpc: Convert the FSL driver to use local64_t
  perf tools: Don't keep unreferenced maps when unmaps are detected
  perf session: Invalidate last_match when removing threads from rb_tree
  perf session: Free the ref_reloc_sym memory at the right place
  x86,mmiotrace: Add support for tracing STOS instruction
  perf, sched migration: Librarize task states and event headers helpers
  perf, sched migration: Librarize the GUI class
  perf, sched migration: Make the GUI class client agnostic
  perf, sched migration: Make it vertically scrollable
  perf, sched migration: Parameterize cpu height and spacing
  perf, sched migration: Fix key bindings
  perf, sched migration: Ignore unhandled task states
  perf, sched migration: Handle ignored migrate out events
  perf: New migration tool overview
  tracing: Drop cpparg() macro
  perf: Use tracepoint_synchronize_unregister() to flush any pending tracepoint call
  ...

Fix up trivial conflicts in Makefile and drivers/cpufreq/cpufreq.c

33 files changed, 1451 insertions, 2925 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 057472fbc272..ce53fb2bd1d9 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -76,8 +76,8 @@ obj-$(CONFIG_GCOV_KERNEL) += gcov/
 obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
 obj-$(CONFIG_KPROBES) += kprobes.o
 obj-$(CONFIG_KGDB) += debug/
-obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o
 obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
+obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
 obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index 71ed3ce29e12..d71a987fd2bf 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -41,6 +41,7 @@
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/list.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>
 
@@ -62,6 +63,9 @@ static DEFINE_PER_CPU(unsigned int, nr_bp_flexible[TYPE_MAX]);
 
 static int nr_slots[TYPE_MAX];
 
+/* Keep track of the breakpoints attached to tasks */
+static LIST_HEAD(bp_task_head);
+
 static int constraints_initialized;
 
 /* Gather the number of total pinned and un-pinned bp in a cpuset */
@@ -103,33 +107,21 @@ static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
 	return 0;
 }
 
-static int task_bp_pinned(struct task_struct *tsk, enum bp_type_idx type)
+/*
+ * Count the number of breakpoints of the same type and same task.
+ * The given event must be not on the list.
+ */
+static int task_bp_pinned(struct perf_event *bp, enum bp_type_idx type)
 {
-	struct perf_event_context *ctx = tsk->perf_event_ctxp;
-	struct list_head *list;
-	struct perf_event *bp;
-	unsigned long flags;
+	struct perf_event_context *ctx = bp->ctx;
+	struct perf_event *iter;
 	int count = 0;
 
-	if (WARN_ONCE(!ctx, "No perf context for this task"))
-		return 0;
-
-	list = &ctx->event_list;
-
-	raw_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)
-			if (find_slot_idx(bp) == type)
-				count += hw_breakpoint_weight(bp);
+	list_for_each_entry(iter, &bp_task_head, hw.bp_list) {
+		if (iter->ctx == ctx && find_slot_idx(iter) == type)
+			count += hw_breakpoint_weight(iter);
 	}
 
-	raw_spin_unlock_irqrestore(&ctx->lock, flags);
-
 	return count;
 }
 
@@ -149,7 +141,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
 		if (!tsk)
 			slots->pinned += max_task_bp_pinned(cpu, type);
 		else
-			slots->pinned += task_bp_pinned(tsk, type);
+			slots->pinned += task_bp_pinned(bp, type);
 		slots->flexible = per_cpu(nr_bp_flexible[type], cpu);
 
 		return;
@@ -162,7 +154,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
 		if (!tsk)
 			nr += max_task_bp_pinned(cpu, type);
 		else
-			nr += task_bp_pinned(tsk, type);
+			nr += task_bp_pinned(bp, type);
 
 		if (nr > slots->pinned)
 			slots->pinned = nr;
@@ -188,7 +180,7 @@ fetch_this_slot(struct bp_busy_slots *slots, int weight)
 /*
  * 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,
+static void toggle_bp_task_slot(struct perf_event *bp, int cpu, bool enable,
 				enum bp_type_idx type, int weight)
 {
 	unsigned int *tsk_pinned;
@@ -196,10 +188,11 @@ static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable,
 	int old_idx = 0;
 	int idx = 0;
 
-	old_count = task_bp_pinned(tsk, type);
+	old_count = task_bp_pinned(bp, type);
 	old_idx = old_count - 1;
 	idx = old_idx + weight;
 
+	/* tsk_pinned[n] is the number of tasks having n breakpoints */
 	tsk_pinned = per_cpu(nr_task_bp_pinned[type], cpu);
 	if (enable) {
 		tsk_pinned[idx]++;
@@ -222,23 +215,30 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
 	int cpu = bp->cpu;
 	struct task_struct *tsk = bp->ctx->task;
 
+	/* Pinned counter cpu profiling */
+	if (!tsk) {
+
+		if (enable)
+			per_cpu(nr_cpu_bp_pinned[type], bp->cpu) += weight;
+		else
+			per_cpu(nr_cpu_bp_pinned[type], bp->cpu) -= weight;
+		return;
+	}
+
 	/* Pinned counter task profiling */
-	if (tsk) {
-		if (cpu >= 0) {
-			toggle_bp_task_slot(tsk, cpu, enable, type, weight);
-			return;
-		}
 
+	if (!enable)
+		list_del(&bp->hw.bp_list);
+
+	if (cpu >= 0) {
+		toggle_bp_task_slot(bp, cpu, enable, type, weight);
+	} else {
 		for_each_online_cpu(cpu)
-			toggle_bp_task_slot(tsk, cpu, enable, type, weight);
-		return;
+			toggle_bp_task_slot(bp, cpu, enable, type, weight);
 	}
 
-	/* Pinned counter cpu profiling */
 	if (enable)
-		per_cpu(nr_cpu_bp_pinned[type], bp->cpu) += weight;
-	else
-		per_cpu(nr_cpu_bp_pinned[type], bp->cpu) -= weight;
+		list_add_tail(&bp->hw.bp_list, &bp_task_head);
 }
 
 /*
@@ -312,6 +312,10 @@ static int __reserve_bp_slot(struct perf_event *bp)
 	weight = hw_breakpoint_weight(bp);
 
 	fetch_bp_busy_slots(&slots, bp, type);
+	/*
+	 * Simulate the addition of this breakpoint to the constraints
+	 * and see the result.
+	 */
 	fetch_this_slot(&slots, weight);
 
 	/* Flexible counters need to keep at least one slot */
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index ff86c558af4c..c772a3d4000d 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -675,7 +675,6 @@ group_sched_in(struct perf_event *group_event,
 	struct perf_event *event, *partial_group = NULL;
 	const struct pmu *pmu = group_event->pmu;
 	bool txn = false;
-	int ret;
 
 	if (group_event->state == PERF_EVENT_STATE_OFF)
 		return 0;
@@ -703,14 +702,8 @@ group_sched_in(struct perf_event *group_event,
 		}
 	}
 
-	if (!txn)
-		return 0;
-
-	ret = pmu->commit_txn(pmu);
-	if (!ret) {
-		pmu->cancel_txn(pmu);
+	if (!txn || !pmu->commit_txn(pmu))
 		return 0;
-	}
 
 group_error:
 	/*
@@ -1155,9 +1148,9 @@ static void __perf_event_sync_stat(struct perf_event *event,
 	 * In order to keep per-task stats reliable we need to flip the event
 	 * values when we flip the contexts.
 	 */
-	value = atomic64_read(&next_event->count);
-	value = atomic64_xchg(&event->count, value);
-	atomic64_set(&next_event->count, value);
+	value = local64_read(&next_event->count);
+	value = local64_xchg(&event->count, value);
+	local64_set(&next_event->count, value);
 
 	swap(event->total_time_enabled, next_event->total_time_enabled);
 	swap(event->total_time_running, next_event->total_time_running);
@@ -1547,10 +1540,10 @@ static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
 
 	hwc->sample_period = sample_period;
 
-	if (atomic64_read(&hwc->period_left) > 8*sample_period) {
+	if (local64_read(&hwc->period_left) > 8*sample_period) {
 		perf_disable();
 		perf_event_stop(event);
-		atomic64_set(&hwc->period_left, 0);
+		local64_set(&hwc->period_left, 0);
 		perf_event_start(event);
 		perf_enable();
 	}
@@ -1591,7 +1584,7 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
 
 		perf_disable();
 		event->pmu->read(event);
-		now = atomic64_read(&event->count);
+		now = local64_read(&event->count);
 		delta = now - hwc->freq_count_stamp;
 		hwc->freq_count_stamp = now;
 
@@ -1743,6 +1736,11 @@ static void __perf_event_read(void *info)
 	event->pmu->read(event);
 }
 
+static inline u64 perf_event_count(struct perf_event *event)
+{
+	return local64_read(&event->count) + atomic64_read(&event->child_count);
+}
+
 static u64 perf_event_read(struct perf_event *event)
 {
 	/*
@@ -1762,7 +1760,7 @@ static u64 perf_event_read(struct perf_event *event)
 		raw_spin_unlock_irqrestore(&ctx->lock, flags);
 	}
 
-	return atomic64_read(&event->count);
+	return perf_event_count(event);
 }
 
 /*
@@ -1883,7 +1881,7 @@ static void free_event_rcu(struct rcu_head *head)
 }
 
 static void perf_pending_sync(struct perf_event *event);
-static void perf_mmap_data_put(struct perf_mmap_data *data);
+static void perf_buffer_put(struct perf_buffer *buffer);
 
 static void free_event(struct perf_event *event)
 {
@@ -1891,7 +1889,7 @@ static void free_event(struct perf_event *event)
 
 	if (!event->parent) {
 		atomic_dec(&nr_events);
-		if (event->attr.mmap)
+		if (event->attr.mmap || event->attr.mmap_data)
 			atomic_dec(&nr_mmap_events);
 		if (event->attr.comm)
 			atomic_dec(&nr_comm_events);
@@ -1899,9 +1897,9 @@ static void free_event(struct perf_event *event)
 			atomic_dec(&nr_task_events);
 	}
 
-	if (event->data) {
-		perf_mmap_data_put(event->data);
-		event->data = NULL;
+	if (event->buffer) {
+		perf_buffer_put(event->buffer);
+		event->buffer = NULL;
 	}
 
 	if (event->destroy)
@@ -2126,13 +2124,13 @@ perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 static unsigned int perf_poll(struct file *file, poll_table *wait)
 {
 	struct perf_event *event = file->private_data;
-	struct perf_mmap_data *data;
+	struct perf_buffer *buffer;
 	unsigned int events = POLL_HUP;
 
 	rcu_read_lock();
-	data = rcu_dereference(event->data);
-	if (data)
-		events = atomic_xchg(&data->poll, 0);
+	buffer = rcu_dereference(event->buffer);
+	if (buffer)
+		events = atomic_xchg(&buffer->poll, 0);
 	rcu_read_unlock();
 
 	poll_wait(file, &event->waitq, wait);
@@ -2143,7 +2141,7 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 static void perf_event_reset(struct perf_event *event)
 {
 	(void)perf_event_read(event);
-	atomic64_set(&event->count, 0);
+	local64_set(&event->count, 0);
 	perf_event_update_userpage(event);
 }
 
@@ -2342,14 +2340,14 @@ static int perf_event_index(struct perf_event *event)
 void perf_event_update_userpage(struct perf_event *event)
 {
 	struct perf_event_mmap_page *userpg;
-	struct perf_mmap_data *data;
+	struct perf_buffer *buffer;
 
 	rcu_read_lock();
-	data = rcu_dereference(event->data);
-	if (!data)
+	buffer = rcu_dereference(event->buffer);
+	if (!buffer)
 		goto unlock;
 
-	userpg = data->user_page;
+	userpg = buffer->user_page;
 
 	/*
 	 * Disable preemption so as to not let the corresponding user-space
@@ -2359,9 +2357,9 @@ void perf_event_update_userpage(struct perf_event *event)
 	++userpg->lock;
 	barrier();
 	userpg->index = perf_event_index(event);
-	userpg->offset = atomic64_read(&event->count);
+	userpg->offset = perf_event_count(event);
 	if (event->state == PERF_EVENT_STATE_ACTIVE)
-		userpg->offset -= atomic64_read(&event->hw.prev_count);
+		userpg->offset -= local64_read(&event->hw.prev_count);
 
 	userpg->time_enabled = event->total_time_enabled +
 			atomic64_read(&event->child_total_time_enabled);
@@ -2376,6 +2374,25 @@ unlock:
 	rcu_read_unlock();
 }
 
+static unsigned long perf_data_size(struct perf_buffer *buffer);
+
+static void
+perf_buffer_init(struct perf_buffer *buffer, long watermark, int flags)
+{
+	long max_size = perf_data_size(buffer);
+
+	if (watermark)
+		buffer->watermark = min(max_size, watermark);
+
+	if (!buffer->watermark)
+		buffer->watermark = max_size / 2;
+
+	if (flags & PERF_BUFFER_WRITABLE)
+		buffer->writable = 1;
+
+	atomic_set(&buffer->refcount, 1);
+}
+
 #ifndef CONFIG_PERF_USE_VMALLOC
 
 /*
@@ -2383,15 +2400,15 @@ unlock:
  */
 
 static struct page *
-perf_mmap_to_page(struct perf_mmap_data *data, unsigned long pgoff)
+perf_mmap_to_page(struct perf_buffer *buffer, unsigned long pgoff)
 {
-	if (pgoff > data->nr_pages)
+	if (pgoff > buffer->nr_pages)
 		return NULL;
 
 	if (pgoff == 0)
-		return virt_to_page(data->user_page);
+		return virt_to_page(buffer->user_page);
 
-	return virt_to_page(data->data_pages[pgoff - 1]);
+	return virt_to_page(buffer->data_pages[pgoff - 1]);
 }
 
 static void *perf_mmap_alloc_page(int cpu)
@@ -2407,42 +2424,44 @@ static void *perf_mmap_alloc_page(int cpu)
 	return page_address(page);
 }
 
-static struct perf_mmap_data *
-perf_mmap_data_alloc(struct perf_event *event, int nr_pages)
+static struct perf_buffer *
+perf_buffer_alloc(int nr_pages, long watermark, int cpu, int flags)
 {
-	struct perf_mmap_data *data;
+	struct perf_buffer *buffer;
 	unsigned long size;
 	int i;
 
-	size = sizeof(struct perf_mmap_data);
+	size = sizeof(struct perf_buffer);
 	size += nr_pages * sizeof(void *);
 
-	data = kzalloc(size, GFP_KERNEL);
-	if (!data)
+	buffer = kzalloc(size, GFP_KERNEL);
+	if (!buffer)
 		goto fail;
 
-	data->user_page = perf_mmap_alloc_page(event->cpu);
-	if (!data->user_page)
+	buffer->user_page = perf_mmap_alloc_page(cpu);
+	if (!buffer->user_page)
 		goto fail_user_page;
 
 	for (i = 0; i < nr_pages; i++) {
-		data->data_pages[i] = perf_mmap_alloc_page(event->cpu);
-		if (!data->data_pages[i])
+		buffer->data_pages[i] = perf_mmap_alloc_page(cpu);
+		if (!buffer->data_pages[i])
 			goto fail_data_pages;
 	}
 
-	data->nr_pages = nr_pages;
+	buffer->nr_pages = nr_pages;
+
+	perf_buffer_init(buffer, watermark, flags);
 
-	return data;
+	return buffer;
 
 fail_data_pages:
 	for (i--; i >= 0; i--)
-		free_page((unsigned long)data->data_pages[i]);
+		free_page((unsigned long)buffer->data_pages[i]);
 
-	free_page((unsigned long)data->user_page);
+	free_page((unsigned long)buffer->user_page);
 
 fail_user_page:
-	kfree(data);
+	kfree(buffer);
 
 fail:
 	return NULL;
@@ -2456,17 +2475,17 @@ static void perf_mmap_free_page(unsigned long addr)
 	__free_page(page);
 }
 
-static void perf_mmap_data_free(struct perf_mmap_data *data)
+static void perf_buffer_free(struct perf_buffer *buffer)
 {
 	int i;
 
-	perf_mmap_free_page((unsigned long)data->user_page);
-	for (i = 0; i < data->nr_pages; i++)
-		perf_mmap_free_page((unsigned long)data->data_pages[i]);
-	kfree(data);
+	perf_mmap_free_page((unsigned long)buffer->user_page);
+	for (i = 0; i < buffer->nr_pages; i++)
+		perf_mmap_free_page((unsigned long)buffer->data_pages[i]);
+	kfree(buffer);
 }
 
-static inline int page_order(struct perf_mmap_data *data)
+static inline int page_order(struct perf_buffer *buffer)
 {
 	return 0;
 }
@@ -2479,18 +2498,18 @@ static inline int page_order(struct perf_mmap_data *data)
  * Required for architectures that have d-cache aliasing issues.
  */
 
-static inline int page_order(struct perf_mmap_data *data)
+static inline int page_order(struct perf_buffer *buffer)
 {
-	return data->page_order;
+	return buffer->page_order;
 }
 
 static struct page *
-perf_mmap_to_page(struct perf_mmap_data *data, unsigned long pgoff)
+perf_mmap_to_page(struct perf_buffer *buffer, unsigned long pgoff)
 {
-	if (pgoff > (1UL << page_order(data)))
+	if (pgoff > (1UL << page_order(buffer)))
 		return NULL;
 
-	return vmalloc_to_page((void *)data->user_page + pgoff * PAGE_SIZE);
+	return vmalloc_to_page((void *)buffer->user_page + pgoff * PAGE_SIZE);
 }
 
 static void perf_mmap_unmark_page(void *addr)
@@ -2500,57 +2519,59 @@ static void perf_mmap_unmark_page(void *addr)
 	page->mapping = NULL;
 }
 
-static void perf_mmap_data_free_work(struct work_struct *work)
+static void perf_buffer_free_work(struct work_struct *work)
 {
-	struct perf_mmap_data *data;
+	struct perf_buffer *buffer;
 	void *base;
 	int i, nr;
 
-	data = container_of(work, struct perf_mmap_data, work);
-	nr = 1 << page_order(data);
+	buffer = container_of(work, struct perf_buffer, work);
+	nr = 1 << page_order(buffer);
 
-	base = data->user_page;
+	base = buffer->user_page;
 	for (i = 0; i < nr + 1; i++)
 		perf_mmap_unmark_page(base + (i * PAGE_SIZE));
 
 	vfree(base);
-	kfree(data);
+	kfree(buffer);
 }
 
-static void perf_mmap_data_free(struct perf_mmap_data *data)
+static void perf_buffer_free(struct perf_buffer *buffer)
 {
-	schedule_work(&data->work);
+	schedule_work(&buffer->work);
 }
 
-static struct perf_mmap_data *
-perf_mmap_data_alloc(struct perf_event *event, int nr_pages)
+static struct perf_buffer *
+perf_buffer_alloc(int nr_pages, long watermark, int cpu, int flags)
 {
-	struct perf_mmap_data *data;
+	struct perf_buffer *buffer;
 	unsigned long size;
 	void *all_buf;
 
-	size = sizeof(struct perf_mmap_data);
+	size = sizeof(struct perf_buffer);
 	size += sizeof(void *);
 
-	data = kzalloc(size, GFP_KERNEL);
-	if (!data)
+	buffer = kzalloc(size, GFP_KERNEL);
+	if (!buffer)
 		goto fail;
 
-	INIT_WORK(&data->work, perf_mmap_data_free_work);
+	INIT_WORK(&buffer->work, perf_buffer_free_work);
 
 	all_buf = vmalloc_user((nr_pages + 1) * PAGE_SIZE);
 	if (!all_buf)
 		goto fail_all_buf;
 
-	data->user_page = all_buf;
-	data->data_pages[0] = all_buf + PAGE_SIZE;
-	data->page_order = ilog2(nr_pages);
-	data->nr_pages = 1;
+	buffer->user_page = all_buf;
+	buffer->data_pages[0] = all_buf + PAGE_SIZE;
+	buffer->page_order = ilog2(nr_pages);
+	buffer->nr_pages = 1;
+
+	perf_buffer_init(buffer, watermark, flags);
 
-	return data;
+	return buffer;
 
 fail_all_buf:
-	kfree(data);
+	kfree(buffer);
 
 fail:
 	return NULL;
@@ -2558,15 +2579,15 @@ fail:
 
 #endif
 
-static unsigned long perf_data_size(struct perf_mmap_data *data)
+static unsigned long perf_data_size(struct perf_buffer *buffer)
 {
-	return data->nr_pages << (PAGE_SHIFT + page_order(data));
+	return buffer->nr_pages << (PAGE_SHIFT + page_order(buffer));
 }
 
 static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct perf_event *event = vma->vm_file->private_data;
-	struct perf_mmap_data *data;
+	struct perf_buffer *buffer;
 	int ret = VM_FAULT_SIGBUS;
 
 	if (vmf->flags & FAULT_FLAG_MKWRITE) {
@@ -2576,14 +2597,14 @@ static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 
 	rcu_read_lock();
-	data = rcu_dereference(event->data);
-	if (!data)
+	buffer = rcu_dereference(event->buffer);
+	if (!buffer)
 		goto unlock;
 
 	if (vmf->pgoff && (vmf->flags & FAULT_FLAG_WRITE))
 		goto unlock;
 
-	vmf->page = perf_mmap_to_page(data, vmf->pgoff);
+	vmf->page = perf_mmap_to_page(buffer, vmf->pgoff);
 	if (!vmf->page)
 		goto unlock;
 
@@ -2598,52 +2619,35 @@ unlock:
 	return ret;
 }
 
-static void
-perf_mmap_data_init(struct perf_event *event, struct perf_mmap_data *data)
-{
-	long max_size = perf_data_size(data);
-
-	if (event->attr.watermark) {
-		data->watermark = min_t(long, max_size,
-					event->attr.wakeup_watermark);
-	}
-
-	if (!data->watermark)
-		data->watermark = max_size / 2;
-
-	atomic_set(&data->refcount, 1);
-	rcu_assign_pointer(event->data, data);
-}
-
-static void perf_mmap_data_free_rcu(struct rcu_head *rcu_head)
+static void perf_buffer_free_rcu(struct rcu_head *rcu_head)
 {
-	struct perf_mmap_data *data;
+	struct perf_buffer *buffer;
 
-	data = container_of(rcu_head, struct perf_mmap_data, rcu_head);
-	perf_mmap_data_free(data);
+	buffer = container_of(rcu_head, struct perf_buffer, rcu_head);
+	perf_buffer_free(buffer);
 }
 
-static struct perf_mmap_data *perf_mmap_data_get(struct perf_event *event)
+static struct perf_buffer *perf_buffer_get(struct perf_event *event)
 {
-	struct perf_mmap_data *data;
+	struct perf_buffer *buffer;
 
 	rcu_read_lock();
-	data = rcu_dereference(event->data);
-	if (data) {
-		if (!atomic_inc_not_zero(&data->refcount))
-			data = NULL;
+	buffer = rcu_dereference(event->buffer);
+	if (buffer) {
+		if (!atomic_inc_not_zero(&buffer->refcount))
+			buffer = NULL;
 	}
 	rcu_read_unlock();
 
-	return data;
+	return buffer;
 }
 
-static void perf_mmap_data_put(struct perf_mmap_data *data)
+static void perf_buffer_put(struct perf_buffer *buffer)
 {
-	if (!atomic_dec_and_test(&data->refcount))
+	if (!atomic_dec_and_test(&buffer->refcount))
 		return;
 
-	call_rcu(&data->rcu_head, perf_mmap_data_free_rcu);
+	call_rcu(&buffer->rcu_head, perf_buffer_free_rcu);
 }
 
 static void perf_mmap_open(struct vm_area_struct *vma)
@@ -2658,16 +2662,16 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 	struct perf_event *event = vma->vm_file->private_data;
 
 	if (atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) {
-		unsigned long size = perf_data_size(event->data);
+		unsigned long size = perf_data_size(event->buffer);
 		struct user_struct *user = event->mmap_user;
-		struct perf_mmap_data *data = event->data;
+		struct perf_buffer *buffer = event->buffer;
 
 		atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
 		vma->vm_mm->locked_vm -= event->mmap_locked;
-		rcu_assign_pointer(event->data, NULL);
+		rcu_assign_pointer(event->buffer, NULL);
 		mutex_unlock(&event->mmap_mutex);
 
-		perf_mmap_data_put(data);
+		perf_buffer_put(buffer);
 		free_uid(user);
 	}
 }
@@ -2685,11 +2689,11 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	unsigned long user_locked, user_lock_limit;
 	struct user_struct *user = current_user();
 	unsigned long locked, lock_limit;
-	struct perf_mmap_data *data;
+	struct perf_buffer *buffer;
 	unsigned long vma_size;
 	unsigned long nr_pages;
 	long user_extra, extra;
-	int ret = 0;
+	int ret = 0, flags = 0;
 
 	/*
 	 * Don't allow mmap() of inherited per-task counters. This would
@@ -2706,7 +2710,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	nr_pages = (vma_size / PAGE_SIZE) - 1;
 
 	/*
-	 * If we have data pages ensure they're a power-of-two number, so we
+	 * If we have buffer pages ensure they're a power-of-two number, so we
 	 * can do bitmasks instead of modulo.
 	 */
 	if (nr_pages != 0 && !is_power_of_2(nr_pages))
@@ -2720,9 +2724,9 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 
 	WARN_ON_ONCE(event->ctx->parent_ctx);
 	mutex_lock(&event->mmap_mutex);
-	if (event->data) {
-		if (event->data->nr_pages == nr_pages)
-			atomic_inc(&event->data->refcount);
+	if (event->buffer) {
+		if (event->buffer->nr_pages == nr_pages)
+			atomic_inc(&event->buffer->refcount);
 		else
 			ret = -EINVAL;
 		goto unlock;
@@ -2752,17 +2756,18 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		goto unlock;
 	}
 
-	WARN_ON(event->data);
+	WARN_ON(event->buffer);
+
+	if (vma->vm_flags & VM_WRITE)
+		flags |= PERF_BUFFER_WRITABLE;
 
-	data = perf_mmap_data_alloc(event, nr_pages);
-	if (!data) {
+	buffer = perf_buffer_alloc(nr_pages, event->attr.wakeup_watermark,
+				   event->cpu, flags);
+	if (!buffer) {
 		ret = -ENOMEM;
 		goto unlock;
 	}
-
-	perf_mmap_data_init(event, data);
-	if (vma->vm_flags & VM_WRITE)
-		event->data->writable = 1;
+	rcu_assign_pointer(event->buffer, buffer);
 
 	atomic_long_add(user_extra, &user->locked_vm);
 	event->mmap_locked = extra;
@@ -2941,11 +2946,6 @@ __weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return NULL;
 }
 
-__weak
-void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
-{
-}
-
 
 /*
  * We assume there is only KVM supporting the callbacks.
@@ -2971,15 +2971,15 @@ EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);
 /*
  * Output
  */
-static bool perf_output_space(struct perf_mmap_data *data, unsigned long tail,
+static bool perf_output_space(struct perf_buffer *buffer, unsigned long tail,
 			      unsigned long offset, unsigned long head)
 {
 	unsigned long mask;
 
-	if (!data->writable)
+	if (!buffer->writable)
 		return true;
 
-	mask = perf_data_size(data) - 1;
+	mask = perf_data_size(buffer) - 1;
 
 	offset = (offset - tail) & mask;
 	head   = (head   - tail) & mask;
@@ -2992,7 +2992,7 @@ static bool perf_output_space(struct perf_mmap_data *data, unsigned long tail,
 
 static void perf_output_wakeup(struct perf_output_handle *handle)
 {
-	atomic_set(&handle->data->poll, POLL_IN);
+	atomic_set(&handle->buffer->poll, POLL_IN);
 
 	if (handle->nmi) {
 		handle->event->pending_wakeup = 1;
@@ -3012,45 +3012,45 @@ static void perf_output_wakeup(struct perf_output_handle *handle)
  */
 static void perf_output_get_handle(struct perf_output_handle *handle)
 {
-	struct perf_mmap_data *data = handle->data;
+	struct perf_buffer *buffer = handle->buffer;
 
 	preempt_disable();
-	local_inc(&data->nest);
-	handle->wakeup = local_read(&data->wakeup);
+	local_inc(&buffer->nest);
+	handle->wakeup = local_read(&buffer->wakeup);
 }
 
 static void perf_output_put_handle(struct perf_output_handle *handle)
 {
-	struct perf_mmap_data *data = handle->data;
+	struct perf_buffer *buffer = handle->buffer;
 	unsigned long head;
 
 again:
-	head = local_read(&data->head);
+	head = local_read(&buffer->head);
 
 	/*
 	 * IRQ/NMI can happen here, which means we can miss a head update.
 	 */
 
-	if (!local_dec_and_test(&data->nest))
+	if (!local_dec_and_test(&buffer->nest))
 		goto out;
 
 	/*
 	 * Publish the known good head. Rely on the full barrier implied
-	 * by atomic_dec_and_test() order the data->head read and this
+	 * by atomic_dec_and_test() order the buffer->head read and this
 	 * write.
 	 */
-	data->user_page->data_head = head;
+	buffer->user_page->data_head = head;
 
 	/*
 	 * Now check if we missed an update, rely on the (compiler)
-	 * barrier in atomic_dec_and_test() to re-read data->head.
+	 * barrier in atomic_dec_and_test() to re-read buffer->head.
 	 */
-	if (unlikely(head != local_read(&data->head))) {
-		local_inc(&data->nest);
+	if (unlikely(head != local_read(&buffer->head))) {
+		local_inc(&buffer->nest);
 		goto again;
 	}
 
-	if (handle->wakeup != local_read(&data->wakeup))
+	if (handle->wakeup != local_read(&buffer->wakeup))
 		perf_output_wakeup(handle);
 
  out:
@@ -3070,12 +3070,12 @@ __always_inline void perf_output_copy(struct perf_output_handle *handle,
 		buf += size;
 		handle->size -= size;
 		if (!handle->size) {
-			struct perf_mmap_data *data = handle->data;
+			struct perf_buffer *buffer = handle->buffer;
 
 			handle->page++;
-			handle->page &= data->nr_pages - 1;
-			handle->addr = data->data_pages[handle->page];
-			handle->size = PAGE_SIZE << page_order(data);
+			handle->page &= buffer->nr_pages - 1;
+			handle->addr = buffer->data_pages[handle->page];
+			handle->size = PAGE_SIZE << page_order(buffer);
 		}
 	} while (len);
 }
@@ -3084,7 +3084,7 @@ int perf_output_begin(struct perf_output_handle *handle,
 		      struct perf_event *event, unsigned int size,
 		      int nmi, int sample)
 {
-	struct perf_mmap_data *data;
+	struct perf_buffer *buffer;
 	unsigned long tail, offset, head;
 	int have_lost;
 	struct {
@@ -3100,19 +3100,19 @@ int perf_output_begin(struct perf_output_handle *handle,
 	if (event->parent)
 		event = event->parent;
 
-	data = rcu_dereference(event->data);
-	if (!data)
+	buffer = rcu_dereference(event->buffer);
+	if (!buffer)
 		goto out;
 
-	handle->data	= data;
+	handle->buffer	= buffer;
 	handle->event	= event;
 	handle->nmi	= nmi;
 	handle->sample	= sample;
 
-	if (!data->nr_pages)
+	if (!buffer->nr_pages)
 		goto out;
 
-	have_lost = local_read(&data->lost);
+	have_lost = local_read(&buffer->lost);
 	if (have_lost)
 		size += sizeof(lost_event);
 
@@ -3124,30 +3124,30 @@ int perf_output_begin(struct perf_output_handle *handle,
 		 * tail pointer. So that all reads will be completed before the
 		 * write is issued.
 		 */
-		tail = ACCESS_ONCE(data->user_page->data_tail);
+		tail = ACCESS_ONCE(buffer->user_page->data_tail);
 		smp_rmb();
-		offset = head = local_read(&data->head);
+		offset = head = local_read(&buffer->head);
 		head += size;
-		if (unlikely(!perf_output_space(data, tail, offset, head)))
+		if (unlikely(!perf_output_space(buffer, tail, offset, head)))
 			goto fail;
-	} while (local_cmpxchg(&data->head, offset, head) != offset);
+	} while (local_cmpxchg(&buffer->head, offset, head) != offset);
 
-	if (head - local_read(&data->wakeup) > data->watermark)
-		local_add(data->watermark, &data->wakeup);
+	if (head - local_read(&buffer->wakeup) > buffer->watermark)
+		local_add(buffer->watermark, &buffer->wakeup);
 
-	handle->page = offset >> (PAGE_SHIFT + page_order(data));
-	handle->page &= data->nr_pages - 1;
-	handle->size = offset & ((PAGE_SIZE << page_order(data)) - 1);
-	handle->addr = data->data_pages[handle->page];
+	handle->page = offset >> (PAGE_SHIFT + page_order(buffer));
+	handle->page &= buffer->nr_pages - 1;
+	handle->size = offset & ((PAGE_SIZE << page_order(buffer)) - 1);
+	handle->addr = buffer->data_pages[handle->page];
 	handle->addr += handle->size;
-	handle->size = (PAGE_SIZE << page_order(data)) - handle->size;
+	handle->size = (PAGE_SIZE << page_order(buffer)) - handle->size;
 
 	if (have_lost) {
 		lost_event.header.type = PERF_RECORD_LOST;
 		lost_event.header.misc = 0;
 		lost_event.header.size = sizeof(lost_event);
 		lost_event.id          = event->id;
-		lost_event.lost        = local_xchg(&data->lost, 0);
+		lost_event.lost        = local_xchg(&buffer->lost, 0);
 
 		perf_output_put(handle, lost_event);
 	}
@@ -3155,7 +3155,7 @@ int perf_output_begin(struct perf_output_handle *handle,
 	return 0;
 
 fail:
-	local_inc(&data->lost);
+	local_inc(&buffer->lost);
 	perf_output_put_handle(handle);
 out:
 	rcu_read_unlock();
@@ -3166,15 +3166,15 @@ out:
 void perf_output_end(struct perf_output_handle *handle)
 {
 	struct perf_event *event = handle->event;
-	struct perf_mmap_data *data = handle->data;
+	struct perf_buffer *buffer = handle->buffer;
 
 	int wakeup_events = event->attr.wakeup_events;
 
 	if (handle->sample && wakeup_events) {
-		int events = local_inc_return(&data->events);
+		int events = local_inc_return(&buffer->events);
 		if (events >= wakeup_events) {
-			local_sub(wakeup_events, &data->events);
-			local_inc(&data->wakeup);
+			local_sub(wakeup_events, &buffer->events);
+			local_inc(&buffer->wakeup);
 		}
 	}
 
@@ -3211,7 +3211,7 @@ static void perf_output_read_one(struct perf_output_handle *handle,
 	u64 values[4];
 	int n = 0;
 
-	values[n++] = atomic64_read(&event->count);
+	values[n++] = perf_event_count(event);
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
 		values[n++] = event->total_time_enabled +
 			atomic64_read(&event->child_total_time_enabled);
@@ -3248,7 +3248,7 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 	if (leader != event)
 		leader->pmu->read(leader);
 
-	values[n++] = atomic64_read(&leader->count);
+	values[n++] = perf_event_count(leader);
 	if (read_format & PERF_FORMAT_ID)
 		values[n++] = primary_event_id(leader);
 
@@ -3260,7 +3260,7 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 		if (sub != event)
 			sub->pmu->read(sub);
 
-		values[n++] = atomic64_read(&sub->count);
+		values[n++] = perf_event_count(sub);
 		if (read_format & PERF_FORMAT_ID)
 			values[n++] = primary_event_id(sub);
 
@@ -3491,7 +3491,7 @@ perf_event_read_event(struct perf_event *event,
 /*
  * task tracking -- fork/exit
  *
- * enabled by: attr.comm | attr.mmap | attr.task
+ * enabled by: attr.comm | attr.mmap | attr.mmap_data | attr.task
  */
 
 struct perf_task_event {
@@ -3541,7 +3541,8 @@ static int perf_event_task_match(struct perf_event *event)
 	if (event->cpu != -1 && event->cpu != smp_processor_id())
 		return 0;
 
-	if (event->attr.comm || event->attr.mmap || event->attr.task)
+	if (event->attr.comm || event->attr.mmap ||
+	    event->attr.mmap_data || event->attr.task)
 		return 1;
 
 	return 0;
@@ -3766,7 +3767,8 @@ static void perf_event_mmap_output(struct perf_event *event,
 }
 
 static int perf_event_mmap_match(struct perf_event *event,
-				   struct perf_mmap_event *mmap_event)
+				   struct perf_mmap_event *mmap_event,
+				   int executable)
 {
 	if (event->state < PERF_EVENT_STATE_INACTIVE)
 		return 0;
@@ -3774,19 +3776,21 @@ static int perf_event_mmap_match(struct perf_event *event,
 	if (event->cpu != -1 && event->cpu != smp_processor_id())
 		return 0;
 
-	if (event->attr.mmap)
+	if ((!executable && event->attr.mmap_data) ||
+	    (executable && event->attr.mmap))
 		return 1;
 
 	return 0;
 }
 
 static void perf_event_mmap_ctx(struct perf_event_context *ctx,
-				  struct perf_mmap_event *mmap_event)
+				  struct perf_mmap_event *mmap_event,
+				  int executable)
 {
 	struct perf_event *event;
 
 	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
-		if (perf_event_mmap_match(event, mmap_event))
+		if (perf_event_mmap_match(event, mmap_event, executable))
 			perf_event_mmap_output(event, mmap_event);
 	}
 }
@@ -3830,6 +3834,14 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 		if (!vma->vm_mm) {
 			name = strncpy(tmp, "[vdso]", sizeof(tmp));
 			goto got_name;
+		} else if (vma->vm_start <= vma->vm_mm->start_brk &&
+				vma->vm_end >= vma->vm_mm->brk) {
+			name = strncpy(tmp, "[heap]", sizeof(tmp));
+			goto got_name;
+		} else if (vma->vm_start <= vma->vm_mm->start_stack &&
+				vma->vm_end >= vma->vm_mm->start_stack) {
+			name = strncpy(tmp, "[stack]", sizeof(tmp));
+			goto got_name;
 		}
 
 		name = strncpy(tmp, "//anon", sizeof(tmp));
@@ -3846,17 +3858,17 @@ got_name:
 
 	rcu_read_lock();
 	cpuctx = &get_cpu_var(perf_cpu_context);
-	perf_event_mmap_ctx(&cpuctx->ctx, mmap_event);
+	perf_event_mmap_ctx(&cpuctx->ctx, mmap_event, vma->vm_flags & VM_EXEC);
 	ctx = rcu_dereference(current->perf_event_ctxp);
 	if (ctx)
-		perf_event_mmap_ctx(ctx, mmap_event);
+		perf_event_mmap_ctx(ctx, mmap_event, vma->vm_flags & VM_EXEC);
 	put_cpu_var(perf_cpu_context);
 	rcu_read_unlock();
 
 	kfree(buf);
 }
 
-void __perf_event_mmap(struct vm_area_struct *vma)
+void perf_event_mmap(struct vm_area_struct *vma)
 {
 	struct perf_mmap_event mmap_event;
 
@@ -4018,14 +4030,14 @@ static u64 perf_swevent_set_period(struct perf_event *event)
 	hwc->last_period = hwc->sample_period;
 
 again:
-	old = val = atomic64_read(&hwc->period_left);
+	old = val = local64_read(&hwc->period_left);
 	if (val < 0)
 		return 0;
 
 	nr = div64_u64(period + val, period);
 	offset = nr * period;
 	val -= offset;
-	if (atomic64_cmpxchg(&hwc->period_left, old, val) != old)
+	if (local64_cmpxchg(&hwc->period_left, old, val) != old)
 		goto again;
 
 	return nr;
@@ -4064,7 +4076,7 @@ static void perf_swevent_add(struct perf_event *event, u64 nr,
 {
 	struct hw_perf_event *hwc = &event->hw;
 
-	atomic64_add(nr, &event->count);
+	local64_add(nr, &event->count);
 
 	if (!regs)
 		return;
@@ -4075,7 +4087,7 @@ static void perf_swevent_add(struct perf_event *event, u64 nr,
 	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))
+	if (local64_add_negative(nr, &hwc->period_left))
 		return;
 
 	perf_swevent_overflow(event, 0, nmi, data, regs);
@@ -4213,14 +4225,12 @@ int perf_swevent_get_recursion_context(void)
 }
 EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context);
 
-void perf_swevent_put_recursion_context(int rctx)
+void inline perf_swevent_put_recursion_context(int rctx)
 {
 	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
 	barrier();
 	cpuctx->recursion[rctx]--;
 }
-EXPORT_SYMBOL_GPL(perf_swevent_put_recursion_context);
-
 
 void __perf_sw_event(u32 event_id, u64 nr, int nmi,
 			    struct pt_regs *regs, u64 addr)
@@ -4368,8 +4378,8 @@ static void cpu_clock_perf_event_update(struct perf_event *event)
 	u64 now;
 
 	now = cpu_clock(cpu);
-	prev = atomic64_xchg(&event->hw.prev_count, now);
-	atomic64_add(now - prev, &event->count);
+	prev = local64_xchg(&event->hw.prev_count, now);
+	local64_add(now - prev, &event->count);
 }
 
 static int cpu_clock_perf_event_enable(struct perf_event *event)
@@ -4377,7 +4387,7 @@ static int cpu_clock_perf_event_enable(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int cpu = raw_smp_processor_id();
 
-	atomic64_set(&hwc->prev_count, cpu_clock(cpu));
+	local64_set(&hwc->prev_count, cpu_clock(cpu));
 	perf_swevent_start_hrtimer(event);
 
 	return 0;
@@ -4409,9 +4419,9 @@ static void task_clock_perf_event_update(struct perf_event *event, u64 now)
 	u64 prev;
 	s64 delta;
 
-	prev = atomic64_xchg(&event->hw.prev_count, now);
+	prev = local64_xchg(&event->hw.prev_count, now);
 	delta = now - prev;
-	atomic64_add(delta, &event->count);
+	local64_add(delta, &event->count);
 }
 
 static int task_clock_perf_event_enable(struct perf_event *event)
@@ -4421,7 +4431,7 @@ static int task_clock_perf_event_enable(struct perf_event *event)
 
 	now = event->ctx->time;
 
-	atomic64_set(&hwc->prev_count, now);
+	local64_set(&hwc->prev_count, now);
 
 	perf_swevent_start_hrtimer(event);
 
@@ -4601,7 +4611,7 @@ static int perf_tp_event_match(struct perf_event *event,
 }
 
 void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
-		   struct pt_regs *regs, struct hlist_head *head)
+		   struct pt_regs *regs, struct hlist_head *head, int rctx)
 {
 	struct perf_sample_data data;
 	struct perf_event *event;
@@ -4615,12 +4625,12 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
 	perf_sample_data_init(&data, addr);
 	data.raw = &raw;
 
-	rcu_read_lock();
 	hlist_for_each_entry_rcu(event, node, head, hlist_entry) {
 		if (perf_tp_event_match(event, &data, regs))
 			perf_swevent_add(event, count, 1, &data, regs);
 	}
-	rcu_read_unlock();
+
+	perf_swevent_put_recursion_context(rctx);
 }
 EXPORT_SYMBOL_GPL(perf_tp_event);
 
@@ -4864,7 +4874,7 @@ perf_event_alloc(struct perf_event_attr *attr,
 		hwc->sample_period = 1;
 	hwc->last_period = hwc->sample_period;
 
-	atomic64_set(&hwc->period_left, hwc->sample_period);
+	local64_set(&hwc->period_left, hwc->sample_period);
 
 	/*
 	 * we currently do not support PERF_FORMAT_GROUP on inherited events
@@ -4913,7 +4923,7 @@ done:
 
 	if (!event->parent) {
 		atomic_inc(&nr_events);
-		if (event->attr.mmap)
+		if (event->attr.mmap || event->attr.mmap_data)
 			atomic_inc(&nr_mmap_events);
 		if (event->attr.comm)
 			atomic_inc(&nr_comm_events);
@@ -5007,7 +5017,7 @@ err_size:
 static int
 perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
 {
-	struct perf_mmap_data *data = NULL, *old_data = NULL;
+	struct perf_buffer *buffer = NULL, *old_buffer = NULL;
 	int ret = -EINVAL;
 
 	if (!output_event)
@@ -5037,19 +5047,19 @@ set:
 
 	if (output_event) {
 		/* get the buffer we want to redirect to */
-		data = perf_mmap_data_get(output_event);
-		if (!data)
+		buffer = perf_buffer_get(output_event);
+		if (!buffer)
 			goto unlock;
 	}
 
-	old_data = event->data;
-	rcu_assign_pointer(event->data, data);
+	old_buffer = event->buffer;
+	rcu_assign_pointer(event->buffer, buffer);
 	ret = 0;
 unlock:
 	mutex_unlock(&event->mmap_mutex);
 
-	if (old_data)
-		perf_mmap_data_put(old_data);
+	if (old_buffer)
+		perf_buffer_put(old_buffer);
 out:
 	return ret;
 }
@@ -5298,7 +5308,7 @@ inherit_event(struct perf_event *parent_event,
 		hwc->sample_period = sample_period;
 		hwc->last_period   = sample_period;
 
-		atomic64_set(&hwc->period_left, sample_period);
+		local64_set(&hwc->period_left, sample_period);
 	}
 
 	child_event->overflow_handler = parent_event->overflow_handler;
@@ -5359,12 +5369,12 @@ static void sync_child_event(struct perf_event *child_event,
 	if (child_event->attr.inherit_stat)
 		perf_event_read_event(child_event, child);
 
-	child_val = atomic64_read(&child_event->count);
+	child_val = perf_event_count(child_event);
 
 	/*
 	 * Add back the child's count to the parent's count:
 	 */
-	atomic64_add(child_val, &parent_event->count);
+	atomic64_add(child_val, &parent_event->child_count);
 	atomic64_add(child_event->total_time_enabled,
 		     &parent_event->child_total_time_enabled);
 	atomic64_add(child_event->total_time_running,
diff --git a/kernel/sched.c b/kernel/sched.c
index f52a8801b7a2..265cf3a2b5d8 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3726,7 +3726,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
  * off of preempt_enable. Kernel preemptions off return from interrupt
  * occur there and call schedule directly.
  */
-asmlinkage void __sched preempt_schedule(void)
+asmlinkage void __sched notrace preempt_schedule(void)
 {
 	struct thread_info *ti = current_thread_info();
 
@@ -3738,9 +3738,9 @@ asmlinkage void __sched preempt_schedule(void)
 		return;
 
 	do {
-		add_preempt_count(PREEMPT_ACTIVE);
+		add_preempt_count_notrace(PREEMPT_ACTIVE);
 		schedule();
-		sub_preempt_count(PREEMPT_ACTIVE);
+		sub_preempt_count_notrace(PREEMPT_ACTIVE);
 
 		/*
 		 * Check again in case we missed a preemption opportunity
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
deleted file mode 100644
index 4b493f67dcb5..000000000000
--- a/kernel/softlockup.c
+++ /dev/null
@@ -1,293 +0,0 @@
-/*
- * Detect Soft Lockups
- *
- * started by Ingo Molnar, Copyright (C) 2005, 2006 Red Hat, Inc.
- *
- * this code detects soft lockups: incidents in where on a CPU
- * the kernel does not reschedule for 10 seconds or more.
- */
-#include <linux/mm.h>
-#include <linux/cpu.h>
-#include <linux/nmi.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/freezer.h>
-#include <linux/kthread.h>
-#include <linux/lockdep.h>
-#include <linux/notifier.h>
-#include <linux/module.h>
-#include <linux/sysctl.h>
-
-#include <asm/irq_regs.h>
-
-static DEFINE_SPINLOCK(print_lock);
-
-static DEFINE_PER_CPU(unsigned long, softlockup_touch_ts); /* touch timestamp */
-static DEFINE_PER_CPU(unsigned long, softlockup_print_ts); /* print timestamp */
-static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
-static DEFINE_PER_CPU(bool, softlock_touch_sync);
-
-static int __read_mostly did_panic;
-int __read_mostly softlockup_thresh = 60;
-
-/*
- * Should we panic (and reboot, if panic_timeout= is set) when a
- * soft-lockup occurs:
- */
-unsigned int __read_mostly softlockup_panic =
-				CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
-
-static int __init softlockup_panic_setup(char *str)
-{
-	softlockup_panic = simple_strtoul(str, NULL, 0);
-
-	return 1;
-}
-__setup("softlockup_panic=", softlockup_panic_setup);
-
-static int
-softlock_panic(struct notifier_block *this, unsigned long event, void *ptr)
-{
-	did_panic = 1;
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block panic_block = {
-	.notifier_call = softlock_panic,
-};
-
-/*
- * Returns seconds, approximately.  We don't need nanosecond
- * resolution, and we don't need to waste time with a big divide when
- * 2^30ns == 1.074s.
- */
-static unsigned long get_timestamp(int this_cpu)
-{
-	return cpu_clock(this_cpu) >> 30LL;  /* 2^30 ~= 10^9 */
-}
-
-static void __touch_softlockup_watchdog(void)
-{
-	int this_cpu = raw_smp_processor_id();
-
-	__raw_get_cpu_var(softlockup_touch_ts) = get_timestamp(this_cpu);
-}
-
-void touch_softlockup_watchdog(void)
-{
-	__raw_get_cpu_var(softlockup_touch_ts) = 0;
-}
-EXPORT_SYMBOL(touch_softlockup_watchdog);
-
-void touch_softlockup_watchdog_sync(void)
-{
-	__raw_get_cpu_var(softlock_touch_sync) = true;
-	__raw_get_cpu_var(softlockup_touch_ts) = 0;
-}
-
-void touch_all_softlockup_watchdogs(void)
-{
-	int cpu;
-
-	/* Cause each CPU to re-update its timestamp rather than complain */
-	for_each_online_cpu(cpu)
-		per_cpu(softlockup_touch_ts, cpu) = 0;
-}
-EXPORT_SYMBOL(touch_all_softlockup_watchdogs);
-
-int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
-			     void __user *buffer,
-			     size_t *lenp, loff_t *ppos)
-{
-	touch_all_softlockup_watchdogs();
-	return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-}
-
-/*
- * This callback runs from the timer interrupt, and checks
- * whether the watchdog thread has hung or not:
- */
-void softlockup_tick(void)
-{
-	int this_cpu = smp_processor_id();
-	unsigned long touch_ts = per_cpu(softlockup_touch_ts, this_cpu);
-	unsigned long print_ts;
-	struct pt_regs *regs = get_irq_regs();
-	unsigned long now;
-
-	/* Is detection switched off? */
-	if (!per_cpu(softlockup_watchdog, this_cpu) || softlockup_thresh <= 0) {
-		/* Be sure we don't false trigger if switched back on */
-		if (touch_ts)
-			per_cpu(softlockup_touch_ts, this_cpu) = 0;
-		return;
-	}
-
-	if (touch_ts == 0) {
-		if (unlikely(per_cpu(softlock_touch_sync, this_cpu))) {
-			/*
-			 * If the time stamp was touched atomically
-			 * make sure the scheduler tick is up to date.
-			 */
-			per_cpu(softlock_touch_sync, this_cpu) = false;
-			sched_clock_tick();
-		}
-		__touch_softlockup_watchdog();
-		return;
-	}
-
-	print_ts = per_cpu(softlockup_print_ts, this_cpu);
-
-	/* report at most once a second */
-	if (print_ts == touch_ts || did_panic)
-		return;
-
-	/* do not print during early bootup: */
-	if (unlikely(system_state != SYSTEM_RUNNING)) {
-		__touch_softlockup_watchdog();
-		return;
-	}
-
-	now = get_timestamp(this_cpu);
-
-	/*
-	 * Wake up the high-prio watchdog task twice per
-	 * threshold timespan.
-	 */
-	if (time_after(now - softlockup_thresh/2, touch_ts))
-		wake_up_process(per_cpu(softlockup_watchdog, this_cpu));
-
-	/* Warn about unreasonable delays: */
-	if (time_before_eq(now - softlockup_thresh, touch_ts))
-		return;
-
-	per_cpu(softlockup_print_ts, this_cpu) = touch_ts;
-
-	spin_lock(&print_lock);
-	printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %lus! [%s:%d]\n",
-			this_cpu, now - touch_ts,
-			current->comm, task_pid_nr(current));
-	print_modules();
-	print_irqtrace_events(current);
-	if (regs)
-		show_regs(regs);
-	else
-		dump_stack();
-	spin_unlock(&print_lock);
-
-	if (softlockup_panic)
-		panic("softlockup: hung tasks");
-}
-
-/*
- * The watchdog thread - runs every second and touches the timestamp.
- */
-static int watchdog(void *__bind_cpu)
-{
-	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
-
-	sched_setscheduler(current, SCHED_FIFO, &param);
-
-	/* initialize timestamp */
-	__touch_softlockup_watchdog();
-
-	set_current_state(TASK_INTERRUPTIBLE);
-	/*
-	 * Run briefly once per second to reset the softlockup timestamp.
-	 * If this gets delayed for more than 60 seconds then the
-	 * debug-printout triggers in softlockup_tick().
-	 */
-	while (!kthread_should_stop()) {
-		__touch_softlockup_watchdog();
-		schedule();
-
-		if (kthread_should_stop())
-			break;
-
-		set_current_state(TASK_INTERRUPTIBLE);
-	}
-	__set_current_state(TASK_RUNNING);
-
-	return 0;
-}
-
-/*
- * Create/destroy watchdog threads as CPUs come and go:
- */
-static int __cpuinit
-cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
-{
-	int hotcpu = (unsigned long)hcpu;
-	struct task_struct *p;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		BUG_ON(per_cpu(softlockup_watchdog, hotcpu));
-		p = kthread_create(watchdog, hcpu, "watchdog/%d", hotcpu);
-		if (IS_ERR(p)) {
-			printk(KERN_ERR "watchdog for %i failed\n", hotcpu);
-			return NOTIFY_BAD;
-		}
-		per_cpu(softlockup_touch_ts, hotcpu) = 0;
-		per_cpu(softlockup_watchdog, hotcpu) = p;
-		kthread_bind(p, hotcpu);
-		break;
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		wake_up_process(per_cpu(softlockup_watchdog, hotcpu));
-		break;
-#ifdef CONFIG_HOTPLUG_CPU
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		if (!per_cpu(softlockup_watchdog, hotcpu))
-			break;
-		/* Unbind so it can run.  Fall thru. */
-		kthread_bind(per_cpu(softlockup_watchdog, hotcpu),
-			     cpumask_any(cpu_online_mask));
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		p = per_cpu(softlockup_watchdog, hotcpu);
-		per_cpu(softlockup_watchdog, hotcpu) = NULL;
-		kthread_stop(p);
-		break;
-#endif /* CONFIG_HOTPLUG_CPU */
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block __cpuinitdata cpu_nfb = {
-	.notifier_call = cpu_callback
-};
-
-static int __initdata nosoftlockup;
-
-static int __init nosoftlockup_setup(char *str)
-{
-	nosoftlockup = 1;
-	return 1;
-}
-__setup("nosoftlockup", nosoftlockup_setup);
-
-static int __init spawn_softlockup_task(void)
-{
-	void *cpu = (void *)(long)smp_processor_id();
-	int err;
-
-	if (nosoftlockup)
-		return 0;
-
-	err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
-	if (err == NOTIFY_BAD) {
-		BUG();
-		return 1;
-	}
-	cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
-	register_cpu_notifier(&cpu_nfb);
-
-	atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
-
-	return 0;
-}
-early_initcall(spawn_softlockup_task);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index d24f761f4876..6f79c7f81c96 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -76,6 +76,10 @@
 #include <scsi/sg.h>
 #endif
 
+#ifdef CONFIG_LOCKUP_DETECTOR
+#include <linux/nmi.h>
+#endif
+
 
 #if defined(CONFIG_SYSCTL)
 
@@ -106,7 +110,7 @@ extern int blk_iopoll_enabled;
 #endif
 
 /* Constants used for minimum and  maximum */
-#ifdef CONFIG_DETECT_SOFTLOCKUP
+#ifdef CONFIG_LOCKUP_DETECTOR
 static int sixty = 60;
 static int neg_one = -1;
 #endif
@@ -710,7 +714,34 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0444,
 		.proc_handler	= proc_dointvec,
 	},
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
+#if defined(CONFIG_LOCKUP_DETECTOR)
+	{
+		.procname       = "watchdog",
+		.data           = &watchdog_enabled,
+		.maxlen         = sizeof (int),
+		.mode           = 0644,
+		.proc_handler   = proc_dowatchdog_enabled,
+	},
+	{
+		.procname	= "watchdog_thresh",
+		.data		= &softlockup_thresh,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dowatchdog_thresh,
+		.extra1		= &neg_one,
+		.extra2		= &sixty,
+	},
+	{
+		.procname	= "softlockup_panic",
+		.data		= &softlockup_panic,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+#endif
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) && !defined(CONFIG_LOCKUP_DETECTOR)
 	{
 		.procname       = "unknown_nmi_panic",
 		.data           = &unknown_nmi_panic,
@@ -813,26 +844,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-#ifdef CONFIG_DETECT_SOFTLOCKUP
-	{
-		.procname	= "softlockup_panic",
-		.data		= &softlockup_panic,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
-	},
-	{
-		.procname	= "softlockup_thresh",
-		.data		= &softlockup_thresh,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dosoftlockup_thresh,
-		.extra1		= &neg_one,
-		.extra2		= &sixty,
-	},
-#endif
 #ifdef CONFIG_DETECT_HUNG_TASK
 	{
 		.procname	= "hung_task_panic",
diff --git a/kernel/timer.c b/kernel/timer.c
index efde11e197c4..6aa6f7e69ad5 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1302,7 +1302,6 @@ void run_local_timers(void)
 {
 	hrtimer_run_queues();
 	raise_softirq(TIMER_SOFTIRQ);
-	softlockup_tick();
 }
 
 /*
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 8b1797c4545b..c7683fd8a03a 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -194,15 +194,6 @@ config PREEMPT_TRACER
 	  enabled. This option and the irqs-off timing option can be
 	  used together or separately.)
 
-config SYSPROF_TRACER
-	bool "Sysprof Tracer"
-	depends on X86
-	select GENERIC_TRACER
-	select CONTEXT_SWITCH_TRACER
-	help
-	  This tracer provides the trace needed by the 'Sysprof' userspace
-	  tool.
-
 config SCHED_TRACER
 	bool "Scheduling Latency Tracer"
 	select GENERIC_TRACER
@@ -229,23 +220,6 @@ config FTRACE_SYSCALLS
 	help
 	  Basic tracer to catch the syscall entry and exit events.
 
-config BOOT_TRACER
-	bool "Trace boot initcalls"
-	select GENERIC_TRACER
-	select CONTEXT_SWITCH_TRACER
-	help
-	  This tracer helps developers to optimize boot times: it records
-	  the timings of the initcalls and traces key events and the identity
-	  of tasks that can cause boot delays, such as context-switches.
-
-	  Its aim is to be parsed by the scripts/bootgraph.pl tool to
-	  produce pretty graphics about boot inefficiencies, giving a visual
-	  representation of the delays during initcalls - but the raw
-	  /debug/tracing/trace text output is readable too.
-
-	  You must pass in initcall_debug and ftrace=initcall to the kernel
-	  command line to enable this on bootup.
-
 config TRACE_BRANCH_PROFILING
 	bool
 	select GENERIC_TRACER
@@ -325,28 +299,6 @@ config BRANCH_TRACER
 
 	  Say N if unsure.
 
-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"
 	depends on HAVE_FUNCTION_TRACER
@@ -371,26 +323,6 @@ config STACK_TRACER
 
 	  Say N if unsure.
 
-config KMEMTRACE
-	bool "Trace SLAB allocations"
-	select GENERIC_TRACER
-	help
-	  kmemtrace provides tracing for slab allocator functions, such as
-	  kmalloc, kfree, kmem_cache_alloc, kmem_cache_free, etc. Collected
-	  data is then fed to the userspace application in order to analyse
-	  allocation hotspots, internal fragmentation and so on, making it
-	  possible to see how well an allocator performs, as well as debug
-	  and profile kernel code.
-
-	  This requires an userspace application to use. See
-	  Documentation/trace/kmemtrace.txt for more information.
-
-	  Saying Y will make the kernel somewhat larger and slower. However,
-	  if you disable kmemtrace at run-time or boot-time, the performance
-	  impact is minimal (depending on the arch the kernel is built for).
-
-	  If unsure, say N.
-
 config WORKQUEUE_TRACER
 	bool "Trace workqueues"
 	select GENERIC_TRACER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 4215530b490b..53f338190b26 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -30,7 +30,6 @@ obj-$(CONFIG_TRACING) += trace_output.o
 obj-$(CONFIG_TRACING) += trace_stat.o
 obj-$(CONFIG_TRACING) += trace_printk.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
-obj-$(CONFIG_SYSPROF_TRACER) += trace_sysprof.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
 obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
@@ -38,10 +37,8 @@ obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
 obj-$(CONFIG_NOP_TRACER) += trace_nop.o
 obj-$(CONFIG_STACK_TRACER) += trace_stack.o
 obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
-obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
-obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
 obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
 obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
 ifeq ($(CONFIG_BLOCK),y)
@@ -55,7 +52,6 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
 endif
 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
 ifeq ($(CONFIG_TRACING),y)
 obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6d2cb14f9449..0d88ce9b9fb8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1883,7 +1883,6 @@ function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
 	struct hlist_head *hhd;
 	struct hlist_node *n;
 	unsigned long key;
-	int resched;
 
 	key = hash_long(ip, FTRACE_HASH_BITS);
 
@@ -1897,12 +1896,12 @@ function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
 	 * period. This syncs the hash iteration and freeing of items
 	 * on the hash. rcu_read_lock is too dangerous here.
 	 */
-	resched = ftrace_preempt_disable();
+	preempt_disable_notrace();
 	hlist_for_each_entry_rcu(entry, n, hhd, node) {
 		if (entry->ip == ip)
 			entry->ops->func(ip, parent_ip, &entry->data);
 	}
-	ftrace_preempt_enable(resched);
+	preempt_enable_notrace();
 }
 
 static struct ftrace_ops trace_probe_ops __read_mostly =
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
deleted file mode 100644
index bbfc1bb1660b..000000000000
--- a/kernel/trace/kmemtrace.c
+++ /dev/null
@@ -1,529 +0,0 @@
-/*
- * Memory allocator tracing
- *
- * Copyright (C) 2008 Eduard - Gabriel Munteanu
- * Copyright (C) 2008 Pekka Enberg <penberg@cs.helsinki.fi>
- * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
- */
-
-#include <linux/tracepoint.h>
-#include <linux/seq_file.h>
-#include <linux/debugfs.h>
-#include <linux/dcache.h>
-#include <linux/fs.h>
-
-#include <linux/kmemtrace.h>
-
-#include "trace_output.h"
-#include "trace.h"
-
-/* Select an alternative, minimalistic output than the original one */
-#define TRACE_KMEM_OPT_MINIMAL	0x1
-
-static struct tracer_opt kmem_opts[] = {
-	/* Default disable the minimalistic output */
-	{ TRACER_OPT(kmem_minimalistic, TRACE_KMEM_OPT_MINIMAL) },
-	{ }
-};
-
-static struct tracer_flags kmem_tracer_flags = {
-	.val			= 0,
-	.opts			= kmem_opts
-};
-
-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 ftrace_event_call *call = &event_kmem_alloc;
-	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;
-
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		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 ftrace_event_call *call = &event_kmem_free;
-	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;
-
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
-
-	trace_wake_up();
-}
-
-static void kmemtrace_kmalloc(void *ignore,
-			      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(void *ignore,
-				       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(void *ignore,
-				   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(void *ignore,
-					    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(void *ignore, unsigned long call_site, const void *ptr)
-{
-	kmemtrace_free(KMEMTRACE_TYPE_KMALLOC, call_site, ptr);
-}
-
-static void kmemtrace_kmem_cache_free(void *ignore,
-				      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, NULL);
-	if (err)
-		return err;
-	err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL);
-	if (err)
-		return err;
-	err = register_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL);
-	if (err)
-		return err;
-	err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL);
-	if (err)
-		return err;
-	err = register_trace_kfree(kmemtrace_kfree, NULL);
-	if (err)
-		return err;
-	err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL);
-
-	return err;
-}
-
-static void kmemtrace_stop_probes(void)
-{
-	unregister_trace_kmalloc(kmemtrace_kmalloc, NULL);
-	unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL);
-	unregister_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL);
-	unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL);
-	unregister_trace_kfree(kmemtrace_kfree, NULL);
-	unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL);
-}
-
-static int kmem_trace_init(struct trace_array *tr)
-{
-	kmemtrace_array = tr;
-
-	tracing_reset_online_cpus(tr);
-
-	kmemtrace_start_probes();
-
-	return 0;
-}
-
-static void kmem_trace_reset(struct trace_array *tr)
-{
-	kmemtrace_stop_probes();
-}
-
-static void kmemtrace_headers(struct seq_file *s)
-{
-	/* Don't need headers for the original kmemtrace output */
-	if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL))
-		return;
-
-	seq_printf(s, "#\n");
-	seq_printf(s, "# ALLOC  TYPE  REQ   GIVEN  FLAGS     "
-			"      POINTER         NODE    CALLER\n");
-	seq_printf(s, "# FREE   |      |     |       |       "
-			"       |   |            |        |\n");
-	seq_printf(s, "# |\n\n");
-}
-
-/*
- * 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(struct trace_iterator *iter, int flags,
-		      struct trace_event *event)
-{
-	struct trace_seq *s = &iter->seq;
-	struct kmemtrace_alloc_entry *entry;
-	int ret;
-
-	trace_assign_type(entry, iter->ent);
-
-	ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu "
-	    "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n",
-	    entry->type_id, (void *)entry->call_site, (unsigned long)entry->ptr,
-	    (unsigned long)entry->bytes_req, (unsigned long)entry->bytes_alloc,
-	    (unsigned long)entry->gfp_flags, entry->node);
-
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-	return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t
-kmemtrace_print_free(struct trace_iterator *iter, int flags,
-		     struct trace_event *event)
-{
-	struct trace_seq *s = &iter->seq;
-	struct kmemtrace_free_entry *entry;
-	int ret;
-
-	trace_assign_type(entry, iter->ent);
-
-	ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu\n",
-			       entry->type_id, (void *)entry->call_site,
-			       (unsigned long)entry->ptr);
-
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-	return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t
-kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags,
-			   struct trace_event *event)
-{
-	struct trace_seq *s = &iter->seq;
-	struct kmemtrace_alloc_entry *entry;
-	struct kmemtrace_user_event *ev;
-	struct kmemtrace_user_event_alloc *ev_alloc;
-
-	trace_assign_type(entry, iter->ent);
-
-	ev = trace_seq_reserve(s, sizeof(*ev));
-	if (!ev)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	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;
-
-	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_user(struct trace_iterator *iter, int flags,
-			  struct trace_event *event)
-{
-	struct trace_seq *s = &iter->seq;
-	struct kmemtrace_free_entry *entry;
-	struct kmemtrace_user_event *ev;
-
-	trace_assign_type(entry, iter->ent);
-
-	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)
-{
-	struct kmemtrace_alloc_entry *entry;
-	struct trace_seq *s = &iter->seq;
-	int ret;
-
-	trace_assign_type(entry, iter->ent);
-
-	/* Alloc entry */
-	ret = trace_seq_printf(s, "  +      ");
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	/* Type */
-	switch (entry->type_id) {
-	case KMEMTRACE_TYPE_KMALLOC:
-		ret = trace_seq_printf(s, "K   ");
-		break;
-	case KMEMTRACE_TYPE_CACHE:
-		ret = trace_seq_printf(s, "C   ");
-		break;
-	case KMEMTRACE_TYPE_PAGES:
-		ret = trace_seq_printf(s, "P   ");
-		break;
-	default:
-		ret = trace_seq_printf(s, "?   ");
-	}
-
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	/* Requested */
-	ret = trace_seq_printf(s, "%4zu   ", entry->bytes_req);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	/* Allocated */
-	ret = trace_seq_printf(s, "%4zu   ", entry->bytes_alloc);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	/* Flags
-	 * TODO: would be better to see the name of the GFP flag names
-	 */
-	ret = trace_seq_printf(s, "%08x   ", entry->gfp_flags);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	/* Pointer to allocated */
-	ret = trace_seq_printf(s, "0x%tx   ", (ptrdiff_t)entry->ptr);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	/* Node and call site*/
-	ret = trace_seq_printf(s, "%4d   %pf\n", entry->node,
-						 (void *)entry->call_site);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t
-kmemtrace_print_free_compress(struct trace_iterator *iter)
-{
-	struct kmemtrace_free_entry *entry;
-	struct trace_seq *s = &iter->seq;
-	int ret;
-
-	trace_assign_type(entry, iter->ent);
-
-	/* Free entry */
-	ret = trace_seq_printf(s, "  -      ");
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	/* Type */
-	switch (entry->type_id) {
-	case KMEMTRACE_TYPE_KMALLOC:
-		ret = trace_seq_printf(s, "K     ");
-		break;
-	case KMEMTRACE_TYPE_CACHE:
-		ret = trace_seq_printf(s, "C     ");
-		break;
-	case KMEMTRACE_TYPE_PAGES:
-		ret = trace_seq_printf(s, "P     ");
-		break;
-	default:
-		ret = trace_seq_printf(s, "?     ");
-	}
-
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	/* Skip requested/allocated/flags */
-	ret = trace_seq_printf(s, "                       ");
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	/* Pointer to allocated */
-	ret = trace_seq_printf(s, "0x%tx   ", (ptrdiff_t)entry->ptr);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	/* Skip node and print call site*/
-	ret = trace_seq_printf(s, "       %pf\n", (void *)entry->call_site);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
-{
-	struct trace_entry *entry = iter->ent;
-
-	if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL))
-		return TRACE_TYPE_UNHANDLED;
-
-	switch (entry->type) {
-	case TRACE_KMEM_ALLOC:
-		return kmemtrace_print_alloc_compress(iter);
-	case TRACE_KMEM_FREE:
-		return kmemtrace_print_free_compress(iter);
-	default:
-		return TRACE_TYPE_UNHANDLED;
-	}
-}
-
-static struct trace_event_functions kmem_trace_alloc_funcs = {
-	.trace			= kmemtrace_print_alloc,
-	.binary			= kmemtrace_print_alloc_user,
-};
-
-static struct trace_event kmem_trace_alloc = {
-	.type			= TRACE_KMEM_ALLOC,
-	.funcs			= &kmem_trace_alloc_funcs,
-};
-
-static struct trace_event_functions kmem_trace_free_funcs = {
-	.trace			= kmemtrace_print_free,
-	.binary			= kmemtrace_print_free_user,
-};
-
-static struct trace_event kmem_trace_free = {
-	.type			= TRACE_KMEM_FREE,
-	.funcs			= &kmem_trace_free_funcs,
-};
-
-static struct tracer kmem_tracer __read_mostly = {
-	.name			= "kmemtrace",
-	.init			= kmem_trace_init,
-	.reset			= kmem_trace_reset,
-	.print_line		= kmemtrace_print_line,
-	.print_header		= kmemtrace_headers,
-	.flags			= &kmem_tracer_flags
-};
-
-void kmemtrace_init(void)
-{
-	/* earliest opportunity to start kmem tracing */
-}
-
-static int __init init_kmem_tracer(void)
-{
-	if (!register_ftrace_event(&kmem_trace_alloc)) {
-		pr_warning("Warning: could not register kmem events\n");
-		return 1;
-	}
-
-	if (!register_ftrace_event(&kmem_trace_free)) {
-		pr_warning("Warning: could not register kmem events\n");
-		return 1;
-	}
-
-	if (register_tracer(&kmem_tracer) != 0) {
-		pr_warning("Warning: could not register the kmem tracer\n");
-		return 1;
-	}
-
-	return 0;
-}
-device_initcall(init_kmem_tracer);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 1da7b6ea8b85..3632ce87674f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -443,6 +443,7 @@ int ring_buffer_print_page_header(struct trace_seq *s)
  */
 struct ring_buffer_per_cpu {
 	int				cpu;
+	atomic_t			record_disabled;
 	struct ring_buffer		*buffer;
 	spinlock_t			reader_lock;	/* serialize readers */
 	arch_spinlock_t			lock;
@@ -462,7 +463,6 @@ struct ring_buffer_per_cpu {
 	unsigned long			read;
 	u64				write_stamp;
 	u64				read_stamp;
-	atomic_t			record_disabled;
 };
 
 struct ring_buffer {
@@ -2242,8 +2242,6 @@ static void trace_recursive_unlock(void)
 
 #endif
 
-static DEFINE_PER_CPU(int, rb_need_resched);
-
 /**
  * ring_buffer_lock_reserve - reserve a part of the buffer
  * @buffer: the ring buffer to reserve from
@@ -2264,13 +2262,13 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event;
-	int cpu, resched;
+	int cpu;
 
 	if (ring_buffer_flags != RB_BUFFERS_ON)
 		return NULL;
 
 	/* If we are tracing schedule, we don't want to recurse */
-	resched = ftrace_preempt_disable();
+	preempt_disable_notrace();
 
 	if (atomic_read(&buffer->record_disabled))
 		goto out_nocheck;
@@ -2295,21 +2293,13 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 	if (!event)
 		goto out;
 
-	/*
-	 * Need to store resched state on this cpu.
-	 * Only the first needs to.
-	 */
-
-	if (preempt_count() == 1)
-		per_cpu(rb_need_resched, cpu) = resched;
-
 	return event;
 
  out:
 	trace_recursive_unlock();
 
  out_nocheck:
-	ftrace_preempt_enable(resched);
+	preempt_enable_notrace();
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);
@@ -2355,13 +2345,7 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 
 	trace_recursive_unlock();
 
-	/*
-	 * Only the last preempt count needs to restore preemption.
-	 */
-	if (preempt_count() == 1)
-		ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
-	else
-		preempt_enable_no_resched_notrace();
+	preempt_enable_notrace();
 
 	return 0;
 }
@@ -2469,13 +2453,7 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer,
 
 	trace_recursive_unlock();
 
-	/*
-	 * Only the last preempt count needs to restore preemption.
-	 */
-	if (preempt_count() == 1)
-		ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
-	else
-		preempt_enable_no_resched_notrace();
+	preempt_enable_notrace();
 
 }
 EXPORT_SYMBOL_GPL(ring_buffer_discard_commit);
@@ -2501,12 +2479,12 @@ int ring_buffer_write(struct ring_buffer *buffer,
 	struct ring_buffer_event *event;
 	void *body;
 	int ret = -EBUSY;
-	int cpu, resched;
+	int cpu;
 
 	if (ring_buffer_flags != RB_BUFFERS_ON)
 		return -EBUSY;
 
-	resched = ftrace_preempt_disable();
+	preempt_disable_notrace();
 
 	if (atomic_read(&buffer->record_disabled))
 		goto out;
@@ -2536,7 +2514,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 
 	ret = 0;
  out:
-	ftrace_preempt_enable(resched);
+	preempt_enable_notrace();
 
 	return ret;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d6736b93dc2a..ed1032d6f81d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -341,7 +341,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 /* trace_flags holds trace_options default values */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
 	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
-	TRACE_ITER_GRAPH_TIME;
+	TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD;
 
 static int trace_stop_count;
 static DEFINE_SPINLOCK(tracing_start_lock);
@@ -425,6 +425,7 @@ static const char *trace_options[] = {
 	"latency-format",
 	"sleep-time",
 	"graph-time",
+	"record-cmd",
 	NULL
 };
 
@@ -656,6 +657,10 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		return;
 
 	WARN_ON_ONCE(!irqs_disabled());
+	if (!current_trace->use_max_tr) {
+		WARN_ON_ONCE(1);
+		return;
+	}
 	arch_spin_lock(&ftrace_max_lock);
 
 	tr->buffer = max_tr.buffer;
@@ -682,6 +687,11 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		return;
 
 	WARN_ON_ONCE(!irqs_disabled());
+	if (!current_trace->use_max_tr) {
+		WARN_ON_ONCE(1);
+		return;
+	}
+
 	arch_spin_lock(&ftrace_max_lock);
 
 	ftrace_disable_cpu();
@@ -726,7 +736,7 @@ __acquires(kernel_lock)
 		return -1;
 	}
 
-	if (strlen(type->name) > MAX_TRACER_SIZE) {
+	if (strlen(type->name) >= MAX_TRACER_SIZE) {
 		pr_info("Tracer has a name longer than %d\n", MAX_TRACER_SIZE);
 		return -1;
 	}
@@ -1328,61 +1338,6 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags)
 
 #endif /* CONFIG_STACKTRACE */
 
-static void
-ftrace_trace_special(void *__tr,
-		     unsigned long arg1, unsigned long arg2, unsigned long arg3,
-		     int pc)
-{
-	struct ftrace_event_call *call = &event_special;
-	struct ring_buffer_event *event;
-	struct trace_array *tr = __tr;
-	struct ring_buffer *buffer = tr->buffer;
-	struct special_entry *entry;
-
-	event = trace_buffer_lock_reserve(buffer, TRACE_SPECIAL,
-					  sizeof(*entry), 0, pc);
-	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-	entry->arg1			= arg1;
-	entry->arg2			= arg2;
-	entry->arg3			= arg3;
-
-	if (!filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit(buffer, event, 0, pc);
-}
-
-void
-__trace_special(void *__tr, void *__data,
-		unsigned long arg1, unsigned long arg2, unsigned long arg3)
-{
-	ftrace_trace_special(__tr, arg1, arg2, arg3, preempt_count());
-}
-
-void
-ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
-{
-	struct trace_array *tr = &global_trace;
-	struct trace_array_cpu *data;
-	unsigned long flags;
-	int cpu;
-	int pc;
-
-	if (tracing_disabled)
-		return;
-
-	pc = preempt_count();
-	local_irq_save(flags);
-	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
-
-	if (likely(atomic_inc_return(&data->disabled) == 1))
-		ftrace_trace_special(tr, arg1, arg2, arg3, pc);
-
-	atomic_dec(&data->disabled);
-	local_irq_restore(flags);
-}
-
 /**
  * trace_vbprintk - write binary msg to tracing buffer
  *
@@ -1401,7 +1356,6 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	struct bprint_entry *entry;
 	unsigned long flags;
 	int disable;
-	int resched;
 	int cpu, len = 0, size, pc;
 
 	if (unlikely(tracing_selftest_running || tracing_disabled))
@@ -1411,7 +1365,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	pause_graph_tracing();
 
 	pc = preempt_count();
-	resched = ftrace_preempt_disable();
+	preempt_disable_notrace();
 	cpu = raw_smp_processor_id();
 	data = tr->data[cpu];
 
@@ -1449,7 +1403,7 @@ out_unlock:
 
 out:
 	atomic_dec_return(&data->disabled);
-	ftrace_preempt_enable(resched);
+	preempt_enable_notrace();
 	unpause_graph_tracing();
 
 	return len;
@@ -2386,6 +2340,7 @@ static const struct file_operations show_traces_fops = {
 	.open		= show_traces_open,
 	.read		= seq_read,
 	.release	= seq_release,
+	.llseek		= seq_lseek,
 };
 
 /*
@@ -2479,6 +2434,7 @@ static const struct file_operations tracing_cpumask_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_cpumask_read,
 	.write		= tracing_cpumask_write,
+	.llseek		= generic_file_llseek,
 };
 
 static int tracing_trace_options_show(struct seq_file *m, void *v)
@@ -2554,6 +2510,9 @@ static void set_tracer_flags(unsigned int mask, int enabled)
 		trace_flags |= mask;
 	else
 		trace_flags &= ~mask;
+
+	if (mask == TRACE_ITER_RECORD_CMD)
+		trace_event_enable_cmd_record(enabled);
 }
 
 static ssize_t
@@ -2645,6 +2604,7 @@ tracing_readme_read(struct file *filp, char __user *ubuf,
 static const struct file_operations tracing_readme_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_readme_read,
+	.llseek		= generic_file_llseek,
 };
 
 static ssize_t
@@ -2695,6 +2655,7 @@ tracing_saved_cmdlines_read(struct file *file, char __user *ubuf,
 static const struct file_operations tracing_saved_cmdlines_fops = {
     .open       = tracing_open_generic,
     .read       = tracing_saved_cmdlines_read,
+    .llseek	= generic_file_llseek,
 };
 
 static ssize_t
@@ -2790,6 +2751,9 @@ static int tracing_resize_ring_buffer(unsigned long size)
 	if (ret < 0)
 		return ret;
 
+	if (!current_trace->use_max_tr)
+		goto out;
+
 	ret = ring_buffer_resize(max_tr.buffer, size);
 	if (ret < 0) {
 		int r;
@@ -2817,11 +2781,14 @@ static int tracing_resize_ring_buffer(unsigned long size)
 		return ret;
 	}
 
+	max_tr.entries = size;
+ out:
 	global_trace.entries = size;
 
 	return ret;
 }
 
+
 /**
  * tracing_update_buffers - used by tracing facility to expand ring buffers
  *
@@ -2882,12 +2849,26 @@ static int tracing_set_tracer(const char *buf)
 	trace_branch_disable();
 	if (current_trace && current_trace->reset)
 		current_trace->reset(tr);
-
+	if (current_trace && current_trace->use_max_tr) {
+		/*
+		 * We don't free the ring buffer. instead, resize it because
+		 * The max_tr ring buffer has some state (e.g. ring->clock) and
+		 * we want preserve it.
+		 */
+		ring_buffer_resize(max_tr.buffer, 1);
+		max_tr.entries = 1;
+	}
 	destroy_trace_option_files(topts);
 
 	current_trace = t;
 
 	topts = create_trace_option_files(current_trace);
+	if (current_trace->use_max_tr) {
+		ret = ring_buffer_resize(max_tr.buffer, global_trace.entries);
+		if (ret < 0)
+			goto out;
+		max_tr.entries = global_trace.entries;
+	}
 
 	if (t->init) {
 		ret = tracer_init(t, tr);
@@ -3024,6 +3005,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	if (iter->trace->pipe_open)
 		iter->trace->pipe_open(iter);
 
+	nonseekable_open(inode, filp);
 out:
 	mutex_unlock(&trace_types_lock);
 	return ret;
@@ -3469,7 +3451,6 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 	}
 
 	tracing_start();
-	max_tr.entries = global_trace.entries;
 	mutex_unlock(&trace_types_lock);
 
 	return cnt;
@@ -3582,18 +3563,21 @@ static const struct file_operations tracing_max_lat_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_max_lat_read,
 	.write		= tracing_max_lat_write,
+	.llseek		= generic_file_llseek,
 };
 
 static const struct file_operations tracing_ctrl_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_ctrl_read,
 	.write		= tracing_ctrl_write,
+	.llseek		= generic_file_llseek,
 };
 
 static const struct file_operations set_tracer_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_set_trace_read,
 	.write		= tracing_set_trace_write,
+	.llseek		= generic_file_llseek,
 };
 
 static const struct file_operations tracing_pipe_fops = {
@@ -3602,17 +3586,20 @@ static const struct file_operations tracing_pipe_fops = {
 	.read		= tracing_read_pipe,
 	.splice_read	= tracing_splice_read_pipe,
 	.release	= tracing_release_pipe,
+	.llseek		= no_llseek,
 };
 
 static const struct file_operations tracing_entries_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_entries_read,
 	.write		= tracing_entries_write,
+	.llseek		= generic_file_llseek,
 };
 
 static const struct file_operations tracing_mark_fops = {
 	.open		= tracing_open_generic,
 	.write		= tracing_mark_write,
+	.llseek		= generic_file_llseek,
 };
 
 static const struct file_operations trace_clock_fops = {
@@ -3918,6 +3905,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 static const struct file_operations tracing_stats_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_stats_read,
+	.llseek		= generic_file_llseek,
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -3954,6 +3942,7 @@ tracing_read_dyn_info(struct file *filp, char __user *ubuf,
 static const struct file_operations tracing_dyn_info_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_read_dyn_info,
+	.llseek		= generic_file_llseek,
 };
 #endif
 
@@ -4107,6 +4096,7 @@ static const struct file_operations trace_options_fops = {
 	.open = tracing_open_generic,
 	.read = trace_options_read,
 	.write = trace_options_write,
+	.llseek	= generic_file_llseek,
 };
 
 static ssize_t
@@ -4158,6 +4148,7 @@ static const struct file_operations trace_options_core_fops = {
 	.open = tracing_open_generic,
 	.read = trace_options_core_read,
 	.write = trace_options_core_write,
+	.llseek = generic_file_llseek,
 };
 
 struct dentry *trace_create_file(const char *name,
@@ -4347,9 +4338,6 @@ static __init int tracer_init_debugfs(void)
 	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
 			&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
 #endif
-#ifdef CONFIG_SYSPROF_TRACER
-	init_tracer_sysprof_debugfs(d_tracer);
-#endif
 
 	create_trace_options_dir();
 
@@ -4576,16 +4564,14 @@ __init static int tracer_alloc_buffers(void)
 
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	max_tr.buffer = ring_buffer_alloc(ring_buf_size,
-					     TRACE_BUFFER_FLAGS);
+	max_tr.buffer = ring_buffer_alloc(1, TRACE_BUFFER_FLAGS);
 	if (!max_tr.buffer) {
 		printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
 		WARN_ON(1);
 		ring_buffer_free(global_trace.buffer);
 		goto out_free_cpumask;
 	}
-	max_tr.entries = ring_buffer_size(max_tr.buffer);
-	WARN_ON(max_tr.entries != global_trace.entries);
+	max_tr.entries = 1;
 #endif
 
 	/* Allocate the first page for all buffers */
@@ -4598,9 +4584,6 @@ __init static int tracer_alloc_buffers(void)
 
 	register_tracer(&nop_trace);
 	current_trace = &nop_trace;
-#ifdef CONFIG_BOOT_TRACER
-	register_tracer(&boot_tracer);
-#endif
 	/* All seems OK, enable tracing */
 	tracing_disabled = 0;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 0605fc00c176..d39b3c5454a5 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -9,10 +9,7 @@
 #include <linux/mmiotrace.h>
 #include <linux/tracepoint.h>
 #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>
 
@@ -25,30 +22,17 @@ enum trace_type {
 	TRACE_STACK,
 	TRACE_PRINT,
 	TRACE_BPRINT,
-	TRACE_SPECIAL,
 	TRACE_MMIO_RW,
 	TRACE_MMIO_MAP,
 	TRACE_BRANCH,
-	TRACE_BOOT_CALL,
-	TRACE_BOOT_RET,
 	TRACE_GRAPH_RET,
 	TRACE_GRAPH_ENT,
 	TRACE_USER_STACK,
-	TRACE_KMEM_ALLOC,
-	TRACE_KMEM_FREE,
 	TRACE_BLK,
-	TRACE_KSYM,
 
 	__TRACE_LAST_TYPE,
 };
 
-enum kmemtrace_type_id {
-	KMEMTRACE_TYPE_KMALLOC = 0,	/* kmalloc() or kfree(). */
-	KMEMTRACE_TYPE_CACHE,		/* kmem_cache_*(). */
-	KMEMTRACE_TYPE_PAGES,		/* __get_free_pages() and friends. */
-};
-
-extern struct tracer boot_tracer;
 
 #undef __field
 #define __field(type, item)		type	item;
@@ -204,23 +188,15 @@ extern void __ftrace_bad_type(void);
 		IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
 		IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT);	\
 		IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT);	\
-		IF_ASSIGN(var, ent, struct special_entry, 0);		\
 		IF_ASSIGN(var, ent, struct trace_mmiotrace_rw,		\
 			  TRACE_MMIO_RW);				\
 		IF_ASSIGN(var, ent, struct trace_mmiotrace_map,		\
 			  TRACE_MMIO_MAP);				\
-		IF_ASSIGN(var, ent, struct trace_boot_call, TRACE_BOOT_CALL);\
-		IF_ASSIGN(var, ent, struct trace_boot_ret, TRACE_BOOT_RET);\
 		IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
 		IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry,	\
 			  TRACE_GRAPH_ENT);		\
 		IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry,	\
 			  TRACE_GRAPH_RET);		\
-		IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry,	\
-			  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)
 
@@ -298,6 +274,7 @@ struct tracer {
 	struct tracer		*next;
 	int			print_max;
 	struct tracer_flags	*flags;
+	int			use_max_tr;
 };
 
 
@@ -318,7 +295,6 @@ struct dentry *trace_create_file(const char *name,
 				 const struct file_operations *fops);
 
 struct dentry *tracing_init_dentry(void);
-void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
 
 struct ring_buffer_event;
 
@@ -363,11 +339,6 @@ void tracing_sched_wakeup_trace(struct trace_array *tr,
 				struct task_struct *wakee,
 				struct task_struct *cur,
 				unsigned long flags, int pc);
-void trace_special(struct trace_array *tr,
-		   struct trace_array_cpu *data,
-		   unsigned long arg1,
-		   unsigned long arg2,
-		   unsigned long arg3, int pc);
 void trace_function(struct trace_array *tr,
 		    unsigned long ip,
 		    unsigned long parent_ip,
@@ -398,8 +369,6 @@ extern cpumask_var_t __read_mostly tracing_buffer_mask;
 #define for_each_tracing_cpu(cpu)	\
 	for_each_cpu(cpu, tracing_buffer_mask)
 
-extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr);
-
 extern unsigned long nsecs_to_usecs(unsigned long nsecs);
 
 extern unsigned long tracing_thresh;
@@ -469,12 +438,8 @@ extern int trace_selftest_startup_nop(struct tracer *trace,
 					 struct trace_array *tr);
 extern int trace_selftest_startup_sched_switch(struct tracer *trace,
 					       struct trace_array *tr);
-extern int trace_selftest_startup_sysprof(struct tracer *trace,
-					       struct trace_array *tr);
 extern int trace_selftest_startup_branch(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);
@@ -636,6 +601,7 @@ enum trace_iterator_flags {
 	TRACE_ITER_LATENCY_FMT		= 0x20000,
 	TRACE_ITER_SLEEP_TIME		= 0x40000,
 	TRACE_ITER_GRAPH_TIME		= 0x80000,
+	TRACE_ITER_RECORD_CMD		= 0x100000,
 };
 
 /*
@@ -647,54 +613,6 @@ enum trace_iterator_flags {
 
 extern struct tracer nop_trace;
 
-/**
- * ftrace_preempt_disable - disable preemption scheduler safe
- *
- * When tracing can happen inside the scheduler, there exists
- * cases that the tracing might happen before the need_resched
- * flag is checked. If this happens and the tracer calls
- * preempt_enable (after a disable), a schedule might take place
- * causing an infinite recursion.
- *
- * To prevent this, we read the need_resched flag before
- * disabling preemption. When we want to enable preemption we
- * check the flag, if it is set, then we call preempt_enable_no_resched.
- * Otherwise, we call preempt_enable.
- *
- * The rational for doing the above is that if need_resched is set
- * and we have yet to reschedule, we are either in an atomic location
- * (where we do not need to check for scheduling) or we are inside
- * the scheduler and do not want to resched.
- */
-static inline int ftrace_preempt_disable(void)
-{
-	int resched;
-
-	resched = need_resched();
-	preempt_disable_notrace();
-
-	return resched;
-}
-
-/**
- * ftrace_preempt_enable - enable preemption scheduler safe
- * @resched: the return value from ftrace_preempt_disable
- *
- * This is a scheduler safe way to enable preemption and not miss
- * any preemption checks. The disabled saved the state of preemption.
- * If resched is set, then we are either inside an atomic or
- * are inside the scheduler (we would have already scheduled
- * otherwise). In this case, we do not want to call normal
- * preempt_enable, but preempt_enable_no_resched instead.
- */
-static inline void ftrace_preempt_enable(int resched)
-{
-	if (resched)
-		preempt_enable_no_resched_notrace();
-	else
-		preempt_enable_notrace();
-}
-
 #ifdef CONFIG_BRANCH_TRACER
 extern int enable_branch_tracing(struct trace_array *tr);
 extern void disable_branch_tracing(void);
@@ -785,6 +703,8 @@ struct filter_pred {
 	int 			pop_n;
 };
 
+extern struct list_head ftrace_common_fields;
+
 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,
@@ -814,6 +734,8 @@ filter_check_discard(struct ftrace_event_call *call, void *rec,
 	return 0;
 }
 
+extern void trace_event_enable_cmd_record(bool enable);
+
 extern struct mutex event_mutex;
 extern struct list_head ftrace_events;
 
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
deleted file mode 100644
index c21d5f3956ad..000000000000
--- a/kernel/trace/trace_boot.c
+++ /dev/null
@@ -1,185 +0,0 @@
-/*
- * ring buffer based initcalls tracer
- *
- * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
- *
- */
-
-#include <linux/init.h>
-#include <linux/debugfs.h>
-#include <linux/ftrace.h>
-#include <linux/kallsyms.h>
-#include <linux/time.h>
-
-#include "trace.h"
-#include "trace_output.h"
-
-static struct trace_array *boot_trace;
-static bool pre_initcalls_finished;
-
-/* Tells the boot tracer that the pre_smp_initcalls are finished.
- * So we are ready .
- * It doesn't enable sched events tracing however.
- * You have to call enable_boot_trace to do so.
- */
-void start_boot_trace(void)
-{
-	pre_initcalls_finished = true;
-}
-
-void enable_boot_trace(void)
-{
-	if (boot_trace && pre_initcalls_finished)
-		tracing_start_sched_switch_record();
-}
-
-void disable_boot_trace(void)
-{
-	if (boot_trace && pre_initcalls_finished)
-		tracing_stop_sched_switch_record();
-}
-
-static int boot_trace_init(struct trace_array *tr)
-{
-	boot_trace = tr;
-
-	if (!tr)
-		return 0;
-
-	tracing_reset_online_cpus(tr);
-
-	tracing_sched_switch_assign_trace(tr);
-	return 0;
-}
-
-static enum print_line_t
-initcall_call_print_line(struct trace_iterator *iter)
-{
-	struct trace_entry *entry = iter->ent;
-	struct trace_seq *s = &iter->seq;
-	struct trace_boot_call *field;
-	struct boot_trace_call *call;
-	u64 ts;
-	unsigned long nsec_rem;
-	int ret;
-
-	trace_assign_type(field, entry);
-	call = &field->boot_call;
-	ts = iter->ts;
-	nsec_rem = do_div(ts, NSEC_PER_SEC);
-
-	ret = trace_seq_printf(s, "[%5ld.%09ld] calling  %s @ %i\n",
-			(unsigned long)ts, nsec_rem, call->func, call->caller);
-
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-	else
-		return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t
-initcall_ret_print_line(struct trace_iterator *iter)
-{
-	struct trace_entry *entry = iter->ent;
-	struct trace_seq *s = &iter->seq;
-	struct trace_boot_ret *field;
-	struct boot_trace_ret *init_ret;
-	u64 ts;
-	unsigned long nsec_rem;
-	int ret;
-
-	trace_assign_type(field, entry);
-	init_ret = &field->boot_ret;
-	ts = iter->ts;
-	nsec_rem = do_div(ts, NSEC_PER_SEC);
-
-	ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s "
-			"returned %d after %llu msecs\n",
-			(unsigned long) ts,
-			nsec_rem,
-			init_ret->func, init_ret->result, init_ret->duration);
-
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-	else
-		return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t initcall_print_line(struct trace_iterator *iter)
-{
-	struct trace_entry *entry = iter->ent;
-
-	switch (entry->type) {
-	case TRACE_BOOT_CALL:
-		return initcall_call_print_line(iter);
-	case TRACE_BOOT_RET:
-		return initcall_ret_print_line(iter);
-	default:
-		return TRACE_TYPE_UNHANDLED;
-	}
-}
-
-struct tracer boot_tracer __read_mostly =
-{
-	.name		= "initcall",
-	.init		= boot_trace_init,
-	.reset		= tracing_reset_online_cpus,
-	.print_line	= initcall_print_line,
-};
-
-void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
-{
-	struct ftrace_event_call *call = &event_boot_call;
-	struct ring_buffer_event *event;
-	struct ring_buffer *buffer;
-	struct trace_boot_call *entry;
-	struct trace_array *tr = boot_trace;
-
-	if (!tr || !pre_initcalls_finished)
-		return;
-
-	/* Get its name now since this function could
-	 * disappear because it is in the .init section.
-	 */
-	sprint_symbol(bt->func, (unsigned long)fn);
-	preempt_disable();
-
-	buffer = tr->buffer;
-	event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_CALL,
-					  sizeof(*entry), 0, 0);
-	if (!event)
-		goto out;
-	entry	= ring_buffer_event_data(event);
-	entry->boot_call = *bt;
-	if (!filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit(buffer, event, 0, 0);
- out:
-	preempt_enable();
-}
-
-void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn)
-{
-	struct ftrace_event_call *call = &event_boot_ret;
-	struct ring_buffer_event *event;
-	struct ring_buffer *buffer;
-	struct trace_boot_ret *entry;
-	struct trace_array *tr = boot_trace;
-
-	if (!tr || !pre_initcalls_finished)
-		return;
-
-	sprint_symbol(bt->func, (unsigned long)fn);
-	preempt_disable();
-
-	buffer = tr->buffer;
-	event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_RET,
-					  sizeof(*entry), 0, 0);
-	if (!event)
-		goto out;
-	entry	= ring_buffer_event_data(event);
-	entry->boot_ret = *bt;
-	if (!filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit(buffer, event, 0, 0);
- out:
-	preempt_enable();
-}
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 9d589d8dcd1a..52fda6c04ac3 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -32,16 +32,15 @@
 u64 notrace trace_clock_local(void)
 {
 	u64 clock;
-	int resched;
 
 	/*
 	 * sched_clock() is an architecture implemented, fast, scalable,
 	 * lockless clock. It is not guaranteed to be coherent across
 	 * CPUs, nor across CPU idle events.
 	 */
-	resched = ftrace_preempt_disable();
+	preempt_disable_notrace();
 	clock = sched_clock();
-	ftrace_preempt_enable(resched);
+	preempt_enable_notrace();
 
 	return clock;
 }
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index dc008c1240da..e3dfecaf13e6 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -151,23 +151,6 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry,
 );
 
 /*
- * Special (free-form) trace entry:
- */
-FTRACE_ENTRY(special, special_entry,
-
-	TRACE_SPECIAL,
-
-	F_STRUCT(
-		__field(	unsigned long,	arg1	)
-		__field(	unsigned long,	arg2	)
-		__field(	unsigned long,	arg3	)
-	),
-
-	F_printk("(%08lx) (%08lx) (%08lx)",
-		 __entry->arg1, __entry->arg2, __entry->arg3)
-);
-
-/*
  * Stack-trace entry:
  */
 
@@ -271,33 +254,6 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
 		 __entry->map_id, __entry->opcode)
 );
 
-FTRACE_ENTRY(boot_call, trace_boot_call,
-
-	TRACE_BOOT_CALL,
-
-	F_STRUCT(
-		__field_struct(	struct boot_trace_call,	boot_call	)
-		__field_desc(	pid_t,	boot_call,	caller		)
-		__array_desc(	char,	boot_call,	func,	KSYM_SYMBOL_LEN)
-	),
-
-	F_printk("%d  %s", __entry->caller, __entry->func)
-);
-
-FTRACE_ENTRY(boot_ret, trace_boot_ret,
-
-	TRACE_BOOT_RET,
-
-	F_STRUCT(
-		__field_struct(	struct boot_trace_ret,	boot_ret	)
-		__array_desc(	char,	boot_ret,	func,	KSYM_SYMBOL_LEN)
-		__field_desc(	int,	boot_ret,	result		)
-		__field_desc(	unsigned long, boot_ret, duration	)
-	),
-
-	F_printk("%s %d %lx",
-		 __entry->func, __entry->result, __entry->duration)
-);
 
 #define TRACE_FUNC_SIZE 30
 #define TRACE_FILE_SIZE 20
@@ -318,53 +274,3 @@ FTRACE_ENTRY(branch, trace_branch,
 		 __entry->func, __entry->file, __entry->correct)
 );
 
-FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry,
-
-	TRACE_KMEM_ALLOC,
-
-	F_STRUCT(
-		__field(	enum kmemtrace_type_id,	type_id		)
-		__field(	unsigned long,		call_site	)
-		__field(	const void *,		ptr		)
-		__field(	size_t,			bytes_req	)
-		__field(	size_t,			bytes_alloc	)
-		__field(	gfp_t,			gfp_flags	)
-		__field(	int,			node		)
-	),
-
-	F_printk("type:%u call_site:%lx ptr:%p req:%zi alloc:%zi"
-		 " flags:%x node:%d",
-		 __entry->type_id, __entry->call_site, __entry->ptr,
-		 __entry->bytes_req, __entry->bytes_alloc,
-		 __entry->gfp_flags, __entry->node)
-);
-
-FTRACE_ENTRY(kmem_free, kmemtrace_free_entry,
-
-	TRACE_KMEM_FREE,
-
-	F_STRUCT(
-		__field(	enum kmemtrace_type_id,	type_id		)
-		__field(	unsigned long,		call_site	)
-		__field(	const void *,		ptr		)
-	),
-
-	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_perf.c b/kernel/trace/trace_event_perf.c
index 8a2b73f7c068..000e6e85b445 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -9,8 +9,6 @@
 #include <linux/kprobes.h>
 #include "trace.h"
 
-EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs);
-
 static char *perf_trace_buf[4];
 
 /*
@@ -56,13 +54,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event,
 		}
 	}
 
-	if (tp_event->class->reg)
-		ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER);
-	else
-		ret = tracepoint_probe_register(tp_event->name,
-						tp_event->class->perf_probe,
-						tp_event);
-
+	ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER);
 	if (ret)
 		goto fail;
 
@@ -96,9 +88,7 @@ int perf_trace_init(struct perf_event *p_event)
 	mutex_lock(&event_mutex);
 	list_for_each_entry(tp_event, &ftrace_events, list) {
 		if (tp_event->event.type == event_id &&
-		    tp_event->class &&
-		    (tp_event->class->perf_probe ||
-		     tp_event->class->reg) &&
+		    tp_event->class && tp_event->class->reg &&
 		    try_module_get(tp_event->mod)) {
 			ret = perf_trace_event_init(tp_event, p_event);
 			break;
@@ -138,18 +128,13 @@ void perf_trace_destroy(struct perf_event *p_event)
 	if (--tp_event->perf_refcount > 0)
 		goto out;
 
-	if (tp_event->class->reg)
-		tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
-	else
-		tracepoint_probe_unregister(tp_event->name,
-					    tp_event->class->perf_probe,
-					    tp_event);
+	tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
 
 	/*
-	 * Ensure our callback won't be called anymore. See
-	 * tracepoint_probe_unregister() and __DO_TRACE().
+	 * Ensure our callback won't be called anymore. The buffers
+	 * will be freed after that.
 	 */
-	synchronize_sched();
+	tracepoint_synchronize_unregister();
 
 	free_percpu(tp_event->perf_events);
 	tp_event->perf_events = NULL;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 53cffc0b0801..09b4fa6e4d3b 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -28,6 +28,7 @@
 DEFINE_MUTEX(event_mutex);
 
 LIST_HEAD(ftrace_events);
+LIST_HEAD(ftrace_common_fields);
 
 struct list_head *
 trace_get_fields(struct ftrace_event_call *event_call)
@@ -37,15 +38,11 @@ trace_get_fields(struct ftrace_event_call *event_call)
 	return event_call->class->get_fields(event_call);
 }
 
-int trace_define_field(struct ftrace_event_call *call, const char *type,
-		       const char *name, int offset, int size, int is_signed,
-		       int filter_type)
+static int __trace_define_field(struct list_head *head, const char *type,
+				const char *name, int offset, int size,
+				int is_signed, int filter_type)
 {
 	struct ftrace_event_field *field;
-	struct list_head *head;
-
-	if (WARN_ON(!call->class))
-		return 0;
 
 	field = kzalloc(sizeof(*field), GFP_KERNEL);
 	if (!field)
@@ -68,7 +65,6 @@ int trace_define_field(struct ftrace_event_call *call, const char *type,
 	field->size = size;
 	field->is_signed = is_signed;
 
-	head = trace_get_fields(call);
 	list_add(&field->link, head);
 
 	return 0;
@@ -80,17 +76,32 @@ err:
 
 	return -ENOMEM;
 }
+
+int trace_define_field(struct ftrace_event_call *call, const char *type,
+		       const char *name, int offset, int size, int is_signed,
+		       int filter_type)
+{
+	struct list_head *head;
+
+	if (WARN_ON(!call->class))
+		return 0;
+
+	head = trace_get_fields(call);
+	return __trace_define_field(head, type, name, offset, size,
+				    is_signed, filter_type);
+}
 EXPORT_SYMBOL_GPL(trace_define_field);
 
 #define __common_field(type, item)					\
-	ret = trace_define_field(call, #type, "common_" #item,		\
-				 offsetof(typeof(ent), item),		\
-				 sizeof(ent.item),			\
-				 is_signed_type(type), FILTER_OTHER);	\
+	ret = __trace_define_field(&ftrace_common_fields, #type,	\
+				   "common_" #item,			\
+				   offsetof(typeof(ent), item),		\
+				   sizeof(ent.item),			\
+				   is_signed_type(type), FILTER_OTHER);	\
 	if (ret)							\
 		return ret;
 
-static int trace_define_common_fields(struct ftrace_event_call *call)
+static int trace_define_common_fields(void)
 {
 	int ret;
 	struct trace_entry ent;
@@ -130,6 +141,55 @@ int trace_event_raw_init(struct ftrace_event_call *call)
 }
 EXPORT_SYMBOL_GPL(trace_event_raw_init);
 
+int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type)
+{
+	switch (type) {
+	case TRACE_REG_REGISTER:
+		return tracepoint_probe_register(call->name,
+						 call->class->probe,
+						 call);
+	case TRACE_REG_UNREGISTER:
+		tracepoint_probe_unregister(call->name,
+					    call->class->probe,
+					    call);
+		return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+	case TRACE_REG_PERF_REGISTER:
+		return tracepoint_probe_register(call->name,
+						 call->class->perf_probe,
+						 call);
+	case TRACE_REG_PERF_UNREGISTER:
+		tracepoint_probe_unregister(call->name,
+					    call->class->perf_probe,
+					    call);
+		return 0;
+#endif
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ftrace_event_reg);
+
+void trace_event_enable_cmd_record(bool enable)
+{
+	struct ftrace_event_call *call;
+
+	mutex_lock(&event_mutex);
+	list_for_each_entry(call, &ftrace_events, list) {
+		if (!(call->flags & TRACE_EVENT_FL_ENABLED))
+			continue;
+
+		if (enable) {
+			tracing_start_cmdline_record();
+			call->flags |= TRACE_EVENT_FL_RECORDED_CMD;
+		} else {
+			tracing_stop_cmdline_record();
+			call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD;
+		}
+	}
+	mutex_unlock(&event_mutex);
+}
+
 static int ftrace_event_enable_disable(struct ftrace_event_call *call,
 					int enable)
 {
@@ -139,24 +199,20 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
 	case 0:
 		if (call->flags & TRACE_EVENT_FL_ENABLED) {
 			call->flags &= ~TRACE_EVENT_FL_ENABLED;
-			tracing_stop_cmdline_record();
-			if (call->class->reg)
-				call->class->reg(call, TRACE_REG_UNREGISTER);
-			else
-				tracepoint_probe_unregister(call->name,
-							    call->class->probe,
-							    call);
+			if (call->flags & TRACE_EVENT_FL_RECORDED_CMD) {
+				tracing_stop_cmdline_record();
+				call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD;
+			}
+			call->class->reg(call, TRACE_REG_UNREGISTER);
 		}
 		break;
 	case 1:
 		if (!(call->flags & TRACE_EVENT_FL_ENABLED)) {
-			tracing_start_cmdline_record();
-			if (call->class->reg)
-				ret = call->class->reg(call, TRACE_REG_REGISTER);
-			else
-				ret = tracepoint_probe_register(call->name,
-								call->class->probe,
-								call);
+			if (trace_flags & TRACE_ITER_RECORD_CMD) {
+				tracing_start_cmdline_record();
+				call->flags |= TRACE_EVENT_FL_RECORDED_CMD;
+			}
+			ret = call->class->reg(call, TRACE_REG_REGISTER);
 			if (ret) {
 				tracing_stop_cmdline_record();
 				pr_info("event trace: Could not enable event "
@@ -194,8 +250,7 @@ static int __ftrace_set_clr_event(const char *match, const char *sub,
 	mutex_lock(&event_mutex);
 	list_for_each_entry(call, &ftrace_events, list) {
 
-		if (!call->name || !call->class ||
-		    (!call->class->probe && !call->class->reg))
+		if (!call->name || !call->class || !call->class->reg)
 			continue;
 
 		if (match &&
@@ -321,7 +376,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 		 * The ftrace subsystem is for showing formats only.
 		 * They can not be enabled or disabled via the event files.
 		 */
-		if (call->class && (call->class->probe || call->class->reg))
+		if (call->class && call->class->reg)
 			return call;
 	}
 
@@ -474,8 +529,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 
 	mutex_lock(&event_mutex);
 	list_for_each_entry(call, &ftrace_events, list) {
-		if (!call->name || !call->class ||
-		    (!call->class->probe && !call->class->reg))
+		if (!call->name || !call->class || !call->class->reg)
 			continue;
 
 		if (system && strcmp(call->class->system, system) != 0)
@@ -544,32 +598,10 @@ out:
 	return ret;
 }
 
-static ssize_t
-event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
-		  loff_t *ppos)
+static void print_event_fields(struct trace_seq *s, struct list_head *head)
 {
-	struct ftrace_event_call *call = filp->private_data;
 	struct ftrace_event_field *field;
-	struct list_head *head;
-	struct trace_seq *s;
-	int common_field_count = 5;
-	char *buf;
-	int r = 0;
-
-	if (*ppos)
-		return 0;
-
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
-	if (!s)
-		return -ENOMEM;
-
-	trace_seq_init(s);
-
-	trace_seq_printf(s, "name: %s\n", call->name);
-	trace_seq_printf(s, "ID: %d\n", call->event.type);
-	trace_seq_printf(s, "format:\n");
 
-	head = trace_get_fields(call);
 	list_for_each_entry_reverse(field, head, link) {
 		/*
 		 * Smartly shows the array type(except dynamic array).
@@ -584,29 +616,54 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
 			array_descriptor = NULL;
 
 		if (!array_descriptor) {
-			r = trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;"
+			trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;"
 					"\tsize:%u;\tsigned:%d;\n",
 					field->type, field->name, field->offset,
 					field->size, !!field->is_signed);
 		} else {
-			r = trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;"
+			trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;"
 					"\tsize:%u;\tsigned:%d;\n",
 					(int)(array_descriptor - field->type),
 					field->type, field->name,
 					array_descriptor, field->offset,
 					field->size, !!field->is_signed);
 		}
+	}
+}
 
-		if (--common_field_count == 0)
-			r = trace_seq_printf(s, "\n");
+static ssize_t
+event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
+		  loff_t *ppos)
+{
+	struct ftrace_event_call *call = filp->private_data;
+	struct list_head *head;
+	struct trace_seq *s;
+	char *buf;
+	int r;
 
-		if (!r)
-			break;
-	}
+	if (*ppos)
+		return 0;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	trace_seq_init(s);
+
+	trace_seq_printf(s, "name: %s\n", call->name);
+	trace_seq_printf(s, "ID: %d\n", call->event.type);
+	trace_seq_printf(s, "format:\n");
+
+	/* print common fields */
+	print_event_fields(s, &ftrace_common_fields);
 
-	if (r)
-		r = trace_seq_printf(s, "\nprint fmt: %s\n",
-				call->print_fmt);
+	trace_seq_putc(s, '\n');
+
+	/* print event specific fields */
+	head = trace_get_fields(call);
+	print_event_fields(s, head);
+
+	r = trace_seq_printf(s, "\nprint fmt: %s\n", call->print_fmt);
 
 	if (!r) {
 		/*
@@ -963,35 +1020,31 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 		return -1;
 	}
 
-	if (call->class->probe || call->class->reg)
+	if (call->class->reg)
 		trace_create_file("enable", 0644, call->dir, call,
 				  enable);
 
 #ifdef CONFIG_PERF_EVENTS
-	if (call->event.type && (call->class->perf_probe || call->class->reg))
+	if (call->event.type && call->class->reg)
 		trace_create_file("id", 0444, call->dir, call,
 		 		  id);
 #endif
 
-	if (call->class->define_fields) {
-		/*
-		 * Other events may have the same class. Only update
-		 * the fields if they are not already defined.
-		 */
-		head = trace_get_fields(call);
-		if (list_empty(head)) {
-			ret = trace_define_common_fields(call);
-			if (!ret)
-				ret = call->class->define_fields(call);
-			if (ret < 0) {
-				pr_warning("Could not initialize trace point"
-					   " events/%s\n", call->name);
-				return ret;
-			}
+	/*
+	 * Other events may have the same class. Only update
+	 * the fields if they are not already defined.
+	 */
+	head = trace_get_fields(call);
+	if (list_empty(head)) {
+		ret = call->class->define_fields(call);
+		if (ret < 0) {
+			pr_warning("Could not initialize trace point"
+				   " events/%s\n", call->name);
+			return ret;
 		}
-		trace_create_file("filter", 0644, call->dir, call,
-				  filter);
 	}
+	trace_create_file("filter", 0644, call->dir, call,
+			  filter);
 
 	trace_create_file("format", 0444, call->dir, call,
 			  format);
@@ -999,11 +1052,17 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 	return 0;
 }
 
-static int __trace_add_event_call(struct ftrace_event_call *call)
+static int
+__trace_add_event_call(struct ftrace_event_call *call, struct module *mod,
+		       const struct file_operations *id,
+		       const struct file_operations *enable,
+		       const struct file_operations *filter,
+		       const struct file_operations *format)
 {
 	struct dentry *d_events;
 	int ret;
 
+	/* The linker may leave blanks */
 	if (!call->name)
 		return -EINVAL;
 
@@ -1011,8 +1070,8 @@ static int __trace_add_event_call(struct ftrace_event_call *call)
 		ret = call->class->raw_init(call);
 		if (ret < 0) {
 			if (ret != -ENOSYS)
-				pr_warning("Could not initialize trace "
-				"events/%s\n", call->name);
+				pr_warning("Could not initialize trace events/%s\n",
+					   call->name);
 			return ret;
 		}
 	}
@@ -1021,11 +1080,10 @@ static int __trace_add_event_call(struct ftrace_event_call *call)
 	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);
+	ret = event_create_dir(call, d_events, id, enable, filter, format);
 	if (!ret)
 		list_add(&call->list, &ftrace_events);
+	call->mod = mod;
 
 	return ret;
 }
@@ -1035,7 +1093,10 @@ int trace_add_event_call(struct ftrace_event_call *call)
 {
 	int ret;
 	mutex_lock(&event_mutex);
-	ret = __trace_add_event_call(call);
+	ret = __trace_add_event_call(call, NULL, &ftrace_event_id_fops,
+				     &ftrace_enable_fops,
+				     &ftrace_event_filter_fops,
+				     &ftrace_event_format_fops);
 	mutex_unlock(&event_mutex);
 	return ret;
 }
@@ -1152,8 +1213,6 @@ static void trace_module_add_events(struct module *mod)
 {
 	struct ftrace_module_file_ops *file_ops = NULL;
 	struct ftrace_event_call *call, *start, *end;
-	struct dentry *d_events;
-	int ret;
 
 	start = mod->trace_events;
 	end = mod->trace_events + mod->num_trace_events;
@@ -1161,38 +1220,14 @@ static void trace_module_add_events(struct module *mod)
 	if (start == end)
 		return;
 
-	d_events = event_trace_events_dir();
-	if (!d_events)
+	file_ops = trace_create_file_ops(mod);
+	if (!file_ops)
 		return;
 
 	for_each_event(call, start, end) {
-		/* The linker may leave blanks */
-		if (!call->name)
-			continue;
-		if (call->class->raw_init) {
-			ret = call->class->raw_init(call);
-			if (ret < 0) {
-				if (ret != -ENOSYS)
-					pr_warning("Could not initialize trace "
-					"point events/%s\n", call->name);
-				continue;
-			}
-		}
-		/*
-		 * This module has events, create file ops for this module
-		 * if not already done.
-		 */
-		if (!file_ops) {
-			file_ops = trace_create_file_ops(mod);
-			if (!file_ops)
-				return;
-		}
-		call->mod = mod;
-		ret = event_create_dir(call, d_events,
+		__trace_add_event_call(call, mod,
 				       &file_ops->id, &file_ops->enable,
 				       &file_ops->filter, &file_ops->format);
-		if (!ret)
-			list_add(&call->list, &ftrace_events);
 	}
 }
 
@@ -1319,25 +1354,14 @@ static __init int event_trace_init(void)
 	trace_create_file("enable", 0644, d_events,
 			  NULL, &ftrace_system_enable_fops);
 
+	if (trace_define_common_fields())
+		pr_warning("tracing: Failed to allocate common fields");
+
 	for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
-		/* The linker may leave blanks */
-		if (!call->name)
-			continue;
-		if (call->class->raw_init) {
-			ret = call->class->raw_init(call);
-			if (ret < 0) {
-				if (ret != -ENOSYS)
-					pr_warning("Could not initialize trace "
-					"point events/%s\n", call->name);
-				continue;
-			}
-		}
-		ret = event_create_dir(call, d_events, &ftrace_event_id_fops,
+		__trace_add_event_call(call, NULL, &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) {
@@ -1524,12 +1548,11 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
 	struct ftrace_entry *entry;
 	unsigned long flags;
 	long disabled;
-	int resched;
 	int cpu;
 	int pc;
 
 	pc = preempt_count();
-	resched = ftrace_preempt_disable();
+	preempt_disable_notrace();
 	cpu = raw_smp_processor_id();
 	disabled = atomic_inc_return(&per_cpu(ftrace_test_event_disable, cpu));
 
@@ -1551,7 +1574,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
 
  out:
 	atomic_dec(&per_cpu(ftrace_test_event_disable, cpu));
-	ftrace_preempt_enable(resched);
+	preempt_enable_notrace();
 }
 
 static struct ftrace_ops trace_ops __initdata  =
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 57bb1bb32999..36d40104b17f 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -497,12 +497,10 @@ void print_subsystem_event_filter(struct event_subsystem *system,
 }
 
 static struct ftrace_event_field *
-find_event_field(struct ftrace_event_call *call, char *name)
+__find_event_field(struct list_head *head, char *name)
 {
 	struct ftrace_event_field *field;
-	struct list_head *head;
 
-	head = trace_get_fields(call);
 	list_for_each_entry(field, head, link) {
 		if (!strcmp(field->name, name))
 			return field;
@@ -511,6 +509,20 @@ find_event_field(struct ftrace_event_call *call, char *name)
 	return NULL;
 }
 
+static struct ftrace_event_field *
+find_event_field(struct ftrace_event_call *call, char *name)
+{
+	struct ftrace_event_field *field;
+	struct list_head *head;
+
+	field = __find_event_field(&ftrace_common_fields, name);
+	if (field)
+		return field;
+
+	head = trace_get_fields(call);
+	return __find_event_field(head, name);
+}
+
 static void filter_free_pred(struct filter_pred *pred)
 {
 	if (!pred)
@@ -627,9 +639,6 @@ static int init_subsystem_preds(struct event_subsystem *system)
 	int err;
 
 	list_for_each_entry(call, &ftrace_events, list) {
-		if (!call->class || !call->class->define_fields)
-			continue;
-
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
@@ -646,9 +655,6 @@ static void filter_free_subsystem_preds(struct event_subsystem *system)
 	struct ftrace_event_call *call;
 
 	list_for_each_entry(call, &ftrace_events, list) {
-		if (!call->class || !call->class->define_fields)
-			continue;
-
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
@@ -1251,9 +1257,6 @@ static int replace_system_preds(struct event_subsystem *system,
 	list_for_each_entry(call, &ftrace_events, list) {
 		struct event_filter *filter = call->filter;
 
-		if (!call->class || !call->class->define_fields)
-			continue;
-
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 8536e2a65969..4ba44deaac25 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -125,12 +125,6 @@ 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->class->fields);
-	return 0;
-}
-
 #undef __entry
 #define __entry REC
 
@@ -158,7 +152,7 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call)
 struct ftrace_event_class event_class_ftrace_##call = {			\
 	.system			= __stringify(TRACE_SYSTEM),		\
 	.define_fields		= ftrace_define_fields_##call,		\
-	.raw_init		= ftrace_raw_init_event,		\
+	.fields			= LIST_HEAD_INIT(event_class_ftrace_##call.fields),\
 };									\
 									\
 struct ftrace_event_call __used						\
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index b3f3776b0cd6..16aee4d44e8f 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -54,14 +54,14 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip)
 	struct trace_array_cpu *data;
 	unsigned long flags;
 	long disabled;
-	int cpu, resched;
+	int cpu;
 	int pc;
 
 	if (unlikely(!ftrace_function_enabled))
 		return;
 
 	pc = preempt_count();
-	resched = ftrace_preempt_disable();
+	preempt_disable_notrace();
 	local_save_flags(flags);
 	cpu = raw_smp_processor_id();
 	data = tr->data[cpu];
@@ -71,7 +71,7 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip)
 		trace_function(tr, ip, parent_ip, flags, pc);
 
 	atomic_dec(&data->disabled);
-	ftrace_preempt_enable(resched);
+	preempt_enable_notrace();
 }
 
 static void
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 79f4bac99a94..6bff23625781 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -641,7 +641,8 @@ trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
 
 	/* Print nsecs (we don't want to exceed 7 numbers) */
 	if (len < 7) {
-		snprintf(nsecs_str, 8 - len, "%03lu", nsecs_rem);
+		snprintf(nsecs_str, min(sizeof(nsecs_str), 8UL - len), "%03lu",
+			 nsecs_rem);
 		ret = trace_seq_printf(s, ".%s", nsecs_str);
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 6fd486e0cef4..73a6b0601f2e 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -649,6 +649,7 @@ static struct tracer irqsoff_tracer __read_mostly =
 #endif
 	.open           = irqsoff_trace_open,
 	.close          = irqsoff_trace_close,
+	.use_max_tr	= 1,
 };
 # define register_irqsoff(trace) register_tracer(&trace)
 #else
@@ -681,6 +682,7 @@ static struct tracer preemptoff_tracer __read_mostly =
 #endif
 	.open		= irqsoff_trace_open,
 	.close		= irqsoff_trace_close,
+	.use_max_tr	= 1,
 };
 # define register_preemptoff(trace) register_tracer(&trace)
 #else
@@ -715,6 +717,7 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
 #endif
 	.open		= irqsoff_trace_open,
 	.close		= irqsoff_trace_close,
+	.use_max_tr	= 1,
 };
 
 # define register_preemptirqsoff(trace) register_tracer(&trace)
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index f52b5f50299d..8b27c9849b42 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -30,6 +30,8 @@
 #include <linux/ptrace.h>
 #include <linux/perf_event.h>
 #include <linux/stringify.h>
+#include <linux/limits.h>
+#include <linux/uaccess.h>
 #include <asm/bitsperlong.h>
 
 #include "trace.h"
@@ -38,6 +40,7 @@
 #define MAX_TRACE_ARGS 128
 #define MAX_ARGSTR_LEN 63
 #define MAX_EVENT_NAME_LEN 64
+#define MAX_STRING_SIZE PATH_MAX
 #define KPROBE_EVENT_SYSTEM "kprobes"
 
 /* Reserved field names */
@@ -58,14 +61,16 @@ const char *reserved_field_names[] = {
 };
 
 /* Printing function type */
-typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *);
+typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *,
+				 void *);
 #define PRINT_TYPE_FUNC_NAME(type)	print_type_##type
 #define PRINT_TYPE_FMT_NAME(type)	print_type_format_##type
 
 /* Printing  in basic type function template */
 #define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt, cast)			\
 static __kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s,	\
-						const char *name, void *data)\
+						const char *name,	\
+						void *data, void *ent)\
 {									\
 	return trace_seq_printf(s, " %s=" fmt, name, (cast)*(type *)data);\
 }									\
@@ -80,6 +85,49 @@ DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d", int)
 DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%ld", long)
 DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%lld", long long)
 
+/* data_rloc: data relative location, compatible with u32 */
+#define make_data_rloc(len, roffs)	\
+	(((u32)(len) << 16) | ((u32)(roffs) & 0xffff))
+#define get_rloc_len(dl)	((u32)(dl) >> 16)
+#define get_rloc_offs(dl)	((u32)(dl) & 0xffff)
+
+static inline void *get_rloc_data(u32 *dl)
+{
+	return (u8 *)dl + get_rloc_offs(*dl);
+}
+
+/* For data_loc conversion */
+static inline void *get_loc_data(u32 *dl, void *ent)
+{
+	return (u8 *)ent + get_rloc_offs(*dl);
+}
+
+/*
+ * Convert data_rloc to data_loc:
+ *  data_rloc stores the offset from data_rloc itself, but data_loc
+ *  stores the offset from event entry.
+ */
+#define convert_rloc_to_loc(dl, offs)	((u32)(dl) + (offs))
+
+/* For defining macros, define string/string_size types */
+typedef u32 string;
+typedef u32 string_size;
+
+/* Print type function for string type */
+static __kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s,
+						  const char *name,
+						  void *data, void *ent)
+{
+	int len = *(u32 *)data >> 16;
+
+	if (!len)
+		return trace_seq_printf(s, " %s=(fault)", name);
+	else
+		return trace_seq_printf(s, " %s=\"%s\"", name,
+					(const char *)get_loc_data(data, ent));
+}
+static const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\"";
+
 /* Data fetch function type */
 typedef	void (*fetch_func_t)(struct pt_regs *, void *, void *);
 
@@ -94,32 +142,38 @@ static __kprobes void call_fetch(struct fetch_param *fprm,
 	return fprm->fn(regs, fprm->data, dest);
 }
 
-#define FETCH_FUNC_NAME(kind, type)	fetch_##kind##_##type
+#define FETCH_FUNC_NAME(method, type)	fetch_##method##_##type
 /*
  * Define macro for basic types - we don't need to define s* types, because
  * we have to care only about bitwidth at recording time.
  */
-#define DEFINE_BASIC_FETCH_FUNCS(kind)  \
-DEFINE_FETCH_##kind(u8)			\
-DEFINE_FETCH_##kind(u16)		\
-DEFINE_FETCH_##kind(u32)		\
-DEFINE_FETCH_##kind(u64)
-
-#define CHECK_BASIC_FETCH_FUNCS(kind, fn)	\
-	((FETCH_FUNC_NAME(kind, u8) == fn) ||	\
-	 (FETCH_FUNC_NAME(kind, u16) == fn) ||	\
-	 (FETCH_FUNC_NAME(kind, u32) == fn) ||	\
-	 (FETCH_FUNC_NAME(kind, u64) == fn))
+#define DEFINE_BASIC_FETCH_FUNCS(method) \
+DEFINE_FETCH_##method(u8)		\
+DEFINE_FETCH_##method(u16)		\
+DEFINE_FETCH_##method(u32)		\
+DEFINE_FETCH_##method(u64)
+
+#define CHECK_FETCH_FUNCS(method, fn)			\
+	(((FETCH_FUNC_NAME(method, u8) == fn) ||	\
+	  (FETCH_FUNC_NAME(method, u16) == fn) ||	\
+	  (FETCH_FUNC_NAME(method, u32) == fn) ||	\
+	  (FETCH_FUNC_NAME(method, u64) == fn) ||	\
+	  (FETCH_FUNC_NAME(method, string) == fn) ||	\
+	  (FETCH_FUNC_NAME(method, string_size) == fn)) \
+	 && (fn != NULL))
 
 /* Data fetch function templates */
 #define DEFINE_FETCH_reg(type)						\
 static __kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs,	\
-					  void *offset, void *dest)	\
+					void *offset, void *dest)	\
 {									\
 	*(type *)dest = (type)regs_get_register(regs,			\
 				(unsigned int)((unsigned long)offset));	\
 }
 DEFINE_BASIC_FETCH_FUNCS(reg)
+/* No string on the register */
+#define fetch_reg_string NULL
+#define fetch_reg_string_size NULL
 
 #define DEFINE_FETCH_stack(type)					\
 static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
@@ -129,6 +183,9 @@ static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
 				(unsigned int)((unsigned long)offset));	\
 }
 DEFINE_BASIC_FETCH_FUNCS(stack)
+/* No string on the stack entry */
+#define fetch_stack_string NULL
+#define fetch_stack_string_size NULL
 
 #define DEFINE_FETCH_retval(type)					\
 static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\
@@ -137,6 +194,9 @@ static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\
 	*(type *)dest = (type)regs_return_value(regs);			\
 }
 DEFINE_BASIC_FETCH_FUNCS(retval)
+/* No string on the retval */
+#define fetch_retval_string NULL
+#define fetch_retval_string_size NULL
 
 #define DEFINE_FETCH_memory(type)					\
 static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
@@ -149,6 +209,62 @@ static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
 		*(type *)dest = retval;					\
 }
 DEFINE_BASIC_FETCH_FUNCS(memory)
+/*
+ * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
+ * length and relative data location.
+ */
+static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
+						      void *addr, void *dest)
+{
+	long ret;
+	int maxlen = get_rloc_len(*(u32 *)dest);
+	u8 *dst = get_rloc_data(dest);
+	u8 *src = addr;
+	mm_segment_t old_fs = get_fs();
+	if (!maxlen)
+		return;
+	/*
+	 * Try to get string again, since the string can be changed while
+	 * probing.
+	 */
+	set_fs(KERNEL_DS);
+	pagefault_disable();
+	do
+		ret = __copy_from_user_inatomic(dst++, src++, 1);
+	while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen);
+	dst[-1] = '\0';
+	pagefault_enable();
+	set_fs(old_fs);
+
+	if (ret < 0) {	/* Failed to fetch string */
+		((u8 *)get_rloc_data(dest))[0] = '\0';
+		*(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest));
+	} else
+		*(u32 *)dest = make_data_rloc(src - (u8 *)addr,
+					      get_rloc_offs(*(u32 *)dest));
+}
+/* Return the length of string -- including null terminal byte */
+static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
+							void *addr, void *dest)
+{
+	int ret, len = 0;
+	u8 c;
+	mm_segment_t old_fs = get_fs();
+
+	set_fs(KERNEL_DS);
+	pagefault_disable();
+	do {
+		ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1);
+		len++;
+	} while (c && ret == 0 && len < MAX_STRING_SIZE);
+	pagefault_enable();
+	set_fs(old_fs);
+
+	if (ret < 0)	/* Failed to check the length */
+		*(u32 *)dest = 0;
+	else
+		*(u32 *)dest = len;
+}
 
 /* Memory fetching by symbol */
 struct symbol_cache {
@@ -203,6 +319,8 @@ static __kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,\
 		*(type *)dest = 0;					\
 }
 DEFINE_BASIC_FETCH_FUNCS(symbol)
+DEFINE_FETCH_symbol(string)
+DEFINE_FETCH_symbol(string_size)
 
 /* Dereference memory access function */
 struct deref_fetch_param {
@@ -224,12 +342,14 @@ static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\
 		*(type *)dest = 0;					\
 }
 DEFINE_BASIC_FETCH_FUNCS(deref)
+DEFINE_FETCH_deref(string)
+DEFINE_FETCH_deref(string_size)
 
 static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
 {
-	if (CHECK_BASIC_FETCH_FUNCS(deref, data->orig.fn))
+	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
 		free_deref_fetch_param(data->orig.data);
-	else if (CHECK_BASIC_FETCH_FUNCS(symbol, data->orig.fn))
+	else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
 		free_symbol_cache(data->orig.data);
 	kfree(data);
 }
@@ -240,23 +360,43 @@ static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
 #define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
 #define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
 
-#define ASSIGN_FETCH_FUNC(kind, type)	\
-	.kind = FETCH_FUNC_NAME(kind, type)
-
-#define ASSIGN_FETCH_TYPE(ptype, ftype, sign)	\
-	{.name = #ptype,			\
-	 .size = sizeof(ftype),			\
-	 .is_signed = sign,			\
-	 .print = PRINT_TYPE_FUNC_NAME(ptype),	\
-	 .fmt = PRINT_TYPE_FMT_NAME(ptype),	\
-ASSIGN_FETCH_FUNC(reg, ftype),			\
-ASSIGN_FETCH_FUNC(stack, ftype),		\
-ASSIGN_FETCH_FUNC(retval, ftype),		\
-ASSIGN_FETCH_FUNC(memory, ftype),		\
-ASSIGN_FETCH_FUNC(symbol, ftype),		\
-ASSIGN_FETCH_FUNC(deref, ftype),		\
+/* Fetch types */
+enum {
+	FETCH_MTD_reg = 0,
+	FETCH_MTD_stack,
+	FETCH_MTD_retval,
+	FETCH_MTD_memory,
+	FETCH_MTD_symbol,
+	FETCH_MTD_deref,
+	FETCH_MTD_END,
+};
+
+#define ASSIGN_FETCH_FUNC(method, type)	\
+	[FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type)
+
+#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype)	\
+	{.name = _name,				\
+	 .size = _size,					\
+	 .is_signed = sign,				\
+	 .print = PRINT_TYPE_FUNC_NAME(ptype),		\
+	 .fmt = PRINT_TYPE_FMT_NAME(ptype),		\
+	 .fmttype = _fmttype,				\
+	 .fetch = {					\
+ASSIGN_FETCH_FUNC(reg, ftype),				\
+ASSIGN_FETCH_FUNC(stack, ftype),			\
+ASSIGN_FETCH_FUNC(retval, ftype),			\
+ASSIGN_FETCH_FUNC(memory, ftype),			\
+ASSIGN_FETCH_FUNC(symbol, ftype),			\
+ASSIGN_FETCH_FUNC(deref, ftype),			\
+	  }						\
 	}
 
+#define ASSIGN_FETCH_TYPE(ptype, ftype, sign)			\
+	__ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype)
+
+#define FETCH_TYPE_STRING 0
+#define FETCH_TYPE_STRSIZE 1
+
 /* Fetch type information table */
 static const struct fetch_type {
 	const char	*name;		/* Name of type */
@@ -264,14 +404,16 @@ static const struct fetch_type {
 	int		is_signed;	/* Signed flag */
 	print_type_func_t	print;	/* Print functions */
 	const char	*fmt;		/* Fromat string */
+	const char	*fmttype;	/* Name in format file */
 	/* Fetch functions */
-	fetch_func_t	reg;
-	fetch_func_t	stack;
-	fetch_func_t	retval;
-	fetch_func_t	memory;
-	fetch_func_t	symbol;
-	fetch_func_t	deref;
+	fetch_func_t	fetch[FETCH_MTD_END];
 } fetch_type_table[] = {
+	/* Special types */
+	[FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
+					sizeof(u32), 1, "__data_loc char[]"),
+	[FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
+					string_size, sizeof(u32), 0, "u32"),
+	/* Basic types */
 	ASSIGN_FETCH_TYPE(u8,  u8,  0),
 	ASSIGN_FETCH_TYPE(u16, u16, 0),
 	ASSIGN_FETCH_TYPE(u32, u32, 0),
@@ -302,12 +444,28 @@ static __kprobes void fetch_stack_address(struct pt_regs *regs,
 	*(unsigned long *)dest = kernel_stack_pointer(regs);
 }
 
+static fetch_func_t get_fetch_size_function(const struct fetch_type *type,
+					    fetch_func_t orig_fn)
+{
+	int i;
+
+	if (type != &fetch_type_table[FETCH_TYPE_STRING])
+		return NULL;	/* Only string type needs size function */
+	for (i = 0; i < FETCH_MTD_END; i++)
+		if (type->fetch[i] == orig_fn)
+			return fetch_type_table[FETCH_TYPE_STRSIZE].fetch[i];
+
+	WARN_ON(1);	/* This should not happen */
+	return NULL;
+}
+
 /**
  * Kprobe event core functions
  */
 
 struct probe_arg {
 	struct fetch_param	fetch;
+	struct fetch_param	fetch_size;
 	unsigned int		offset;	/* Offset from argument entry */
 	const char		*name;	/* Name of this argument */
 	const char		*comm;	/* Command of this argument */
@@ -429,9 +587,9 @@ error:
 
 static void free_probe_arg(struct probe_arg *arg)
 {
-	if (CHECK_BASIC_FETCH_FUNCS(deref, arg->fetch.fn))
+	if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
 		free_deref_fetch_param(arg->fetch.data);
-	else if (CHECK_BASIC_FETCH_FUNCS(symbol, arg->fetch.fn))
+	else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
 		free_symbol_cache(arg->fetch.data);
 	kfree(arg->name);
 	kfree(arg->comm);
@@ -548,7 +706,7 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 
 	if (strcmp(arg, "retval") == 0) {
 		if (is_return)
-			f->fn = t->retval;
+			f->fn = t->fetch[FETCH_MTD_retval];
 		else
 			ret = -EINVAL;
 	} else if (strncmp(arg, "stack", 5) == 0) {
@@ -562,7 +720,7 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 			if (ret || param > PARAM_MAX_STACK)
 				ret = -EINVAL;
 			else {
-				f->fn = t->stack;
+				f->fn = t->fetch[FETCH_MTD_stack];
 				f->data = (void *)param;
 			}
 		} else
@@ -588,7 +746,7 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t,
 	case '%':	/* named register */
 		ret = regs_query_register_offset(arg + 1);
 		if (ret >= 0) {
-			f->fn = t->reg;
+			f->fn = t->fetch[FETCH_MTD_reg];
 			f->data = (void *)(unsigned long)ret;
 			ret = 0;
 		}
@@ -598,7 +756,7 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t,
 			ret = strict_strtoul(arg + 1, 0, &param);
 			if (ret)
 				break;
-			f->fn = t->memory;
+			f->fn = t->fetch[FETCH_MTD_memory];
 			f->data = (void *)param;
 		} else {
 			ret = split_symbol_offset(arg + 1, &offset);
@@ -606,7 +764,7 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t,
 				break;
 			f->data = alloc_symbol_cache(arg + 1, offset);
 			if (f->data)
-				f->fn = t->symbol;
+				f->fn = t->fetch[FETCH_MTD_symbol];
 		}
 		break;
 	case '+':	/* deref memory */
@@ -636,14 +794,17 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t,
 			if (ret)
 				kfree(dprm);
 			else {
-				f->fn = t->deref;
+				f->fn = t->fetch[FETCH_MTD_deref];
 				f->data = (void *)dprm;
 			}
 		}
 		break;
 	}
-	if (!ret && !f->fn)
+	if (!ret && !f->fn) {	/* Parsed, but do not find fetch method */
+		pr_info("%s type has no corresponding fetch method.\n",
+			t->name);
 		ret = -EINVAL;
+	}
 	return ret;
 }
 
@@ -652,6 +813,7 @@ static int parse_probe_arg(char *arg, struct trace_probe *tp,
 			   struct probe_arg *parg, int is_return)
 {
 	const char *t;
+	int ret;
 
 	if (strlen(arg) > MAX_ARGSTR_LEN) {
 		pr_info("Argument is too long.: %s\n",  arg);
@@ -674,7 +836,13 @@ static int parse_probe_arg(char *arg, struct trace_probe *tp,
 	}
 	parg->offset = tp->size;
 	tp->size += parg->type->size;
-	return __parse_probe_arg(arg, parg->type, &parg->fetch, is_return);
+	ret = __parse_probe_arg(arg, parg->type, &parg->fetch, is_return);
+	if (ret >= 0) {
+		parg->fetch_size.fn = get_fetch_size_function(parg->type,
+							      parg->fetch.fn);
+		parg->fetch_size.data = parg->fetch.data;
+	}
+	return ret;
 }
 
 /* Return 1 if name is reserved or already used by another argument */
@@ -757,14 +925,17 @@ static int create_trace_probe(int argc, char **argv)
 			pr_info("Delete command needs an event name.\n");
 			return -EINVAL;
 		}
+		mutex_lock(&probe_lock);
 		tp = find_probe_event(event, group);
 		if (!tp) {
+			mutex_unlock(&probe_lock);
 			pr_info("Event %s/%s doesn't exist.\n", group, event);
 			return -ENOENT;
 		}
 		/* delete an event */
 		unregister_trace_probe(tp);
 		free_trace_probe(tp);
+		mutex_unlock(&probe_lock);
 		return 0;
 	}
 
@@ -1043,6 +1214,54 @@ static const struct file_operations kprobe_profile_ops = {
 	.release        = seq_release,
 };
 
+/* Sum up total data length for dynamic arraies (strings) */
+static __kprobes int __get_data_size(struct trace_probe *tp,
+				     struct pt_regs *regs)
+{
+	int i, ret = 0;
+	u32 len;
+
+	for (i = 0; i < tp->nr_args; i++)
+		if (unlikely(tp->args[i].fetch_size.fn)) {
+			call_fetch(&tp->args[i].fetch_size, regs, &len);
+			ret += len;
+		}
+
+	return ret;
+}
+
+/* Store the value of each argument */
+static __kprobes void store_trace_args(int ent_size, struct trace_probe *tp,
+				       struct pt_regs *regs,
+				       u8 *data, int maxlen)
+{
+	int i;
+	u32 end = tp->size;
+	u32 *dl;	/* Data (relative) location */
+
+	for (i = 0; i < tp->nr_args; i++) {
+		if (unlikely(tp->args[i].fetch_size.fn)) {
+			/*
+			 * First, we set the relative location and
+			 * maximum data length to *dl
+			 */
+			dl = (u32 *)(data + tp->args[i].offset);
+			*dl = make_data_rloc(maxlen, end - tp->args[i].offset);
+			/* Then try to fetch string or dynamic array data */
+			call_fetch(&tp->args[i].fetch, regs, dl);
+			/* Reduce maximum length */
+			end += get_rloc_len(*dl);
+			maxlen -= get_rloc_len(*dl);
+			/* Trick here, convert data_rloc to data_loc */
+			*dl = convert_rloc_to_loc(*dl,
+				 ent_size + tp->args[i].offset);
+		} else
+			/* Just fetching data normally */
+			call_fetch(&tp->args[i].fetch, regs,
+				   data + tp->args[i].offset);
+	}
+}
+
 /* Kprobe handler */
 static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
 {
@@ -1050,8 +1269,7 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
 	struct kprobe_trace_entry_head *entry;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
-	u8 *data;
-	int size, i, pc;
+	int size, dsize, pc;
 	unsigned long irq_flags;
 	struct ftrace_event_call *call = &tp->call;
 
@@ -1060,7 +1278,8 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
 	local_save_flags(irq_flags);
 	pc = preempt_count();
 
-	size = sizeof(*entry) + tp->size;
+	dsize = __get_data_size(tp, regs);
+	size = sizeof(*entry) + tp->size + dsize;
 
 	event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
 						  size, irq_flags, pc);
@@ -1069,9 +1288,7 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
 
 	entry = ring_buffer_event_data(event);
 	entry->ip = (unsigned long)kp->addr;
-	data = (u8 *)&entry[1];
-	for (i = 0; i < tp->nr_args; i++)
-		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
+	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
 
 	if (!filter_current_check_discard(buffer, call, entry, event))
 		trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
@@ -1085,15 +1302,15 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
 	struct kretprobe_trace_entry_head *entry;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
-	u8 *data;
-	int size, i, pc;
+	int size, pc, dsize;
 	unsigned long irq_flags;
 	struct ftrace_event_call *call = &tp->call;
 
 	local_save_flags(irq_flags);
 	pc = preempt_count();
 
-	size = sizeof(*entry) + tp->size;
+	dsize = __get_data_size(tp, regs);
+	size = sizeof(*entry) + tp->size + dsize;
 
 	event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
 						  size, irq_flags, pc);
@@ -1103,9 +1320,7 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
 	entry = ring_buffer_event_data(event);
 	entry->func = (unsigned long)tp->rp.kp.addr;
 	entry->ret_ip = (unsigned long)ri->ret_addr;
-	data = (u8 *)&entry[1];
-	for (i = 0; i < tp->nr_args; i++)
-		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
+	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
 
 	if (!filter_current_check_discard(buffer, call, entry, event))
 		trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
@@ -1137,7 +1352,7 @@ print_kprobe_event(struct trace_iterator *iter, int flags,
 	data = (u8 *)&field[1];
 	for (i = 0; i < tp->nr_args; i++)
 		if (!tp->args[i].type->print(s, tp->args[i].name,
-					     data + tp->args[i].offset))
+					     data + tp->args[i].offset, field))
 			goto partial;
 
 	if (!trace_seq_puts(s, "\n"))
@@ -1179,7 +1394,7 @@ print_kretprobe_event(struct trace_iterator *iter, int flags,
 	data = (u8 *)&field[1];
 	for (i = 0; i < tp->nr_args; i++)
 		if (!tp->args[i].type->print(s, tp->args[i].name,
-					     data + tp->args[i].offset))
+					     data + tp->args[i].offset, field))
 			goto partial;
 
 	if (!trace_seq_puts(s, "\n"))
@@ -1214,11 +1429,6 @@ static void probe_event_disable(struct ftrace_event_call *call)
 	}
 }
 
-static int probe_event_raw_init(struct ftrace_event_call *event_call)
-{
-	return 0;
-}
-
 #undef DEFINE_FIELD
 #define DEFINE_FIELD(type, item, name, is_signed)			\
 	do {								\
@@ -1239,7 +1449,7 @@ static int kprobe_event_define_fields(struct ftrace_event_call *event_call)
 	DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
 	/* Set argument names as fields */
 	for (i = 0; i < tp->nr_args; i++) {
-		ret = trace_define_field(event_call, tp->args[i].type->name,
+		ret = trace_define_field(event_call, tp->args[i].type->fmttype,
 					 tp->args[i].name,
 					 sizeof(field) + tp->args[i].offset,
 					 tp->args[i].type->size,
@@ -1261,7 +1471,7 @@ static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
 	DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
 	/* Set argument names as fields */
 	for (i = 0; i < tp->nr_args; i++) {
-		ret = trace_define_field(event_call, tp->args[i].type->name,
+		ret = trace_define_field(event_call, tp->args[i].type->fmttype,
 					 tp->args[i].name,
 					 sizeof(field) + tp->args[i].offset,
 					 tp->args[i].type->size,
@@ -1301,8 +1511,13 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len)
 	pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
 
 	for (i = 0; i < tp->nr_args; i++) {
-		pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
-				tp->args[i].name);
+		if (strcmp(tp->args[i].type->name, "string") == 0)
+			pos += snprintf(buf + pos, LEN_OR_ZERO,
+					", __get_str(%s)",
+					tp->args[i].name);
+		else
+			pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
+					tp->args[i].name);
 	}
 
 #undef LEN_OR_ZERO
@@ -1339,11 +1554,11 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp,
 	struct ftrace_event_call *call = &tp->call;
 	struct kprobe_trace_entry_head *entry;
 	struct hlist_head *head;
-	u8 *data;
-	int size, __size, i;
+	int size, __size, dsize;
 	int rctx;
 
-	__size = sizeof(*entry) + tp->size;
+	dsize = __get_data_size(tp, regs);
+	__size = sizeof(*entry) + tp->size + dsize;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
@@ -1355,9 +1570,8 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp,
 		return;
 
 	entry->ip = (unsigned long)kp->addr;
-	data = (u8 *)&entry[1];
-	for (i = 0; i < tp->nr_args; i++)
-		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
+	memset(&entry[1], 0, dsize);
+	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
 
 	head = this_cpu_ptr(call->perf_events);
 	perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head);
@@ -1371,11 +1585,11 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
 	struct ftrace_event_call *call = &tp->call;
 	struct kretprobe_trace_entry_head *entry;
 	struct hlist_head *head;
-	u8 *data;
-	int size, __size, i;
+	int size, __size, dsize;
 	int rctx;
 
-	__size = sizeof(*entry) + tp->size;
+	dsize = __get_data_size(tp, regs);
+	__size = sizeof(*entry) + tp->size + dsize;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
@@ -1388,9 +1602,7 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
 
 	entry->func = (unsigned long)tp->rp.kp.addr;
 	entry->ret_ip = (unsigned long)ri->ret_addr;
-	data = (u8 *)&entry[1];
-	for (i = 0; i < tp->nr_args; i++)
-		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
+	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
 
 	head = this_cpu_ptr(call->perf_events);
 	perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head);
@@ -1486,15 +1698,12 @@ static int register_probe_event(struct trace_probe *tp)
 	int ret;
 
 	/* Initialize ftrace_event_call */
+	INIT_LIST_HEAD(&call->class->fields);
 	if (probe_is_return(tp)) {
-		INIT_LIST_HEAD(&call->class->fields);
 		call->event.funcs = &kretprobe_funcs;
-		call->class->raw_init = probe_event_raw_init;
 		call->class->define_fields = kretprobe_event_define_fields;
 	} else {
-		INIT_LIST_HEAD(&call->class->fields);
 		call->event.funcs = &kprobe_funcs;
-		call->class->raw_init = probe_event_raw_init;
 		call->class->define_fields = kprobe_event_define_fields;
 	}
 	if (set_print_fmt(tp) < 0)
diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c
deleted file mode 100644
index 8eaf00749b65..000000000000
--- a/kernel/trace/trace_ksym.c
+++ /dev/null
@@ -1,508 +0,0 @@
-/*
- * 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/slab.h>
-#include <linux/fs.h>
-
-#include "trace_output.h"
-#include "trace.h"
-
-#include <linux/hw_breakpoint.h>
-#include <asm/hw_breakpoint.h>
-
-#include <asm/atomic.h>
-
-#define KSYM_TRACER_OP_LEN 3 /* rw- */
-
-struct trace_ksym {
-	struct perf_event	**ksym_hbp;
-	struct perf_event_attr	attr;
-#ifdef CONFIG_PROFILE_KSYM_TRACER
-	atomic64_t		counter;
-#endif
-	struct hlist_node	ksym_hlist;
-};
-
-static struct trace_array *ksym_trace_array;
-
-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->attr.bp_addr == hbp_hit_addr) {
-			atomic64_inc(&entry->counter);
-			break;
-		}
-	}
-	rcu_read_unlock();
-}
-#endif /* CONFIG_PROFILE_KSYM_TRACER */
-
-void ksym_hbp_handler(struct perf_event *hbp, int nmi,
-		      struct perf_sample_data *data,
-		      struct pt_regs *regs)
-{
-	struct ring_buffer_event *event;
-	struct ksym_trace_entry *entry;
-	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;
-
-	entry = kzalloc(sizeof(struct trace_ksym), GFP_KERNEL);
-	if (!entry)
-		return -ENOMEM;
-
-	hw_breakpoint_init(&entry->attr);
-
-	entry->attr.bp_type = op;
-	entry->attr.bp_addr = addr;
-	entry->attr.bp_len = HW_BREAKPOINT_LEN_4;
-
-	entry->ksym_hbp = register_wide_hw_breakpoint(&entry->attr,
-					ksym_hbp_handler);
-
-	if (IS_ERR(entry->ksym_hbp)) {
-		ret = PTR_ERR(entry->ksym_hbp);
-		if (ret == -ENOSPC) {
-			printk(KERN_ERR "ksym_tracer: Maximum limit reached."
-			" No new requests for tracing can be accepted now.\n");
-		} else {
-			printk(KERN_INFO "ksym_tracer request failed. Try again"
-					 " later!!\n");
-		}
-		goto err;
-	}
-
-	hlist_add_head_rcu(&(entry->ksym_hlist), &ksym_filter_head);
-
-	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 *)(unsigned long)entry->attr.bp_addr);
-		if (entry->attr.bp_type == HW_BREAKPOINT_R)
-			ret = trace_seq_puts(s, "r--\n");
-		else if (entry->attr.bp_type == HW_BREAKPOINT_W)
-			ret = trace_seq_puts(s, "-w-\n");
-		else if (entry->attr.bp_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);
-		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 *buf, *input_string, *ksymname = NULL;
-	unsigned long ksym_addr = 0;
-	int ret, op, changed = 0;
-
-	buf = kzalloc(count + 1, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	ret = -EFAULT;
-	if (copy_from_user(buf, buffer, count))
-		goto out;
-
-	buf[count] = '\0';
-	input_string = strstrip(buf);
-
-	/*
-	 * 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();
-		ret = 0;
-		goto out;
-	}
-
-	ret = op = parse_ksym_trace_str(input_string, &ksymname, &ksym_addr);
-	if (ret < 0)
-		goto out;
-
-	mutex_lock(&ksym_tracer_mutex);
-
-	ret = -EINVAL;
-	hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) {
-		if (entry->attr.bp_addr == ksym_addr) {
-			/* Check for malformed request: (6) */
-			if (entry->attr.bp_type != op)
-				changed = 1;
-			else
-				goto out_unlock;
-			break;
-		}
-	}
-	if (changed) {
-		unregister_wide_hw_breakpoint(entry->ksym_hbp);
-		entry->attr.bp_type = op;
-		ret = 0;
-		if (op > 0) {
-			entry->ksym_hbp =
-				register_wide_hw_breakpoint(&entry->attr,
-					ksym_hbp_handler);
-			if (IS_ERR(entry->ksym_hbp))
-				ret = PTR_ERR(entry->ksym_hbp);
-			else
-				goto out_unlock;
-		}
-		/* Error or "symbol:---" case: drop it */
-		hlist_del_rcu(&(entry->ksym_hlist));
-		synchronize_rcu();
-		kfree(entry);
-		goto out_unlock;
-	} else {
-		/* Check for malformed request: (4) */
-		if (op)
-			ret = process_new_ksym_entry(ksymname, op, ksym_addr);
-	}
-out_unlock:
-	mutex_unlock(&ksym_tracer_mutex);
-out:
-	kfree(buf);
-	return !ret ? count : 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
-};
-
-#ifdef CONFIG_PROFILE_KSYM_TRACER
-static int ksym_profile_show(struct seq_file *m, void *v)
-{
-	struct hlist_node *node;
-	struct trace_ksym *entry;
-	int access_type = 0;
-	char fn_name[KSYM_NAME_LEN];
-
-	seq_puts(m, "  Access Type ");
-	seq_puts(m, "  Symbol                                       Counter\n");
-	seq_puts(m, "  ----------- ");
-	seq_puts(m, "  ------                                       -------\n");
-
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(entry, node, &ksym_filter_head, ksym_hlist) {
-
-		access_type = entry->attr.bp_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->attr.bp_addr, fn_name) >= 0)
-			seq_printf(m, "  %-36s", fn_name);
-		else
-			seq_printf(m, "  %-36s", "<NA>");
-		seq_printf(m, " %15llu\n",
-			   (unsigned long long)atomic64_read(&entry->counter));
-	}
-	rcu_read_unlock();
-
-	return 0;
-}
-
-static int ksym_profile_open(struct inode *node, struct file *file)
-{
-	return single_open(file, ksym_profile_show, NULL);
-}
-
-static const struct file_operations ksym_profile_fops = {
-	.open		= ksym_profile_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-#endif /* CONFIG_PROFILE_KSYM_TRACER */
-
-__init static int init_ksym_trace(void)
-{
-	struct dentry *d_tracer;
-
-	d_tracer = tracing_init_dentry();
-
-	trace_create_file("ksym_trace_filter", 0644, d_tracer,
-			  NULL, &ksym_tracing_fops);
-
-#ifdef CONFIG_PROFILE_KSYM_TRACER
-	trace_create_file("ksym_profile", 0444, d_tracer,
-			  NULL, &ksym_profile_fops);
-#endif
-
-	return register_tracer(&ksym_tracer);
-}
-device_initcall(init_ksym_trace);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 57c1b4596470..02272baa2206 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -16,9 +16,6 @@
 
 DECLARE_RWSEM(trace_event_mutex);
 
-DEFINE_PER_CPU(struct trace_seq, ftrace_event_seq);
-EXPORT_PER_CPU_SYMBOL(ftrace_event_seq);
-
 static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
 
 static int next_event_type = __TRACE_LAST_TYPE + 1;
@@ -1069,65 +1066,6 @@ static struct trace_event trace_wake_event = {
 	.funcs		= &trace_wake_funcs,
 };
 
-/* TRACE_SPECIAL */
-static enum print_line_t trace_special_print(struct trace_iterator *iter,
-					     int flags, struct trace_event *event)
-{
-	struct special_entry *field;
-
-	trace_assign_type(field, iter->ent);
-
-	if (!trace_seq_printf(&iter->seq, "# %ld %ld %ld\n",
-			      field->arg1,
-			      field->arg2,
-			      field->arg3))
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t trace_special_hex(struct trace_iterator *iter,
-					   int flags, struct trace_event *event)
-{
-	struct special_entry *field;
-	struct trace_seq *s = &iter->seq;
-
-	trace_assign_type(field, iter->ent);
-
-	SEQ_PUT_HEX_FIELD_RET(s, field->arg1);
-	SEQ_PUT_HEX_FIELD_RET(s, field->arg2);
-	SEQ_PUT_HEX_FIELD_RET(s, field->arg3);
-
-	return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t trace_special_bin(struct trace_iterator *iter,
-					   int flags, struct trace_event *event)
-{
-	struct special_entry *field;
-	struct trace_seq *s = &iter->seq;
-
-	trace_assign_type(field, iter->ent);
-
-	SEQ_PUT_FIELD_RET(s, field->arg1);
-	SEQ_PUT_FIELD_RET(s, field->arg2);
-	SEQ_PUT_FIELD_RET(s, field->arg3);
-
-	return TRACE_TYPE_HANDLED;
-}
-
-static struct trace_event_functions trace_special_funcs = {
-	.trace		= trace_special_print,
-	.raw		= trace_special_print,
-	.hex		= trace_special_hex,
-	.binary		= trace_special_bin,
-};
-
-static struct trace_event trace_special_event = {
-	.type		= TRACE_SPECIAL,
-	.funcs		= &trace_special_funcs,
-};
-
 /* TRACE_STACK */
 
 static enum print_line_t trace_stack_print(struct trace_iterator *iter,
@@ -1161,9 +1099,6 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
 
 static struct trace_event_functions trace_stack_funcs = {
 	.trace		= trace_stack_print,
-	.raw		= trace_special_print,
-	.hex		= trace_special_hex,
-	.binary		= trace_special_bin,
 };
 
 static struct trace_event trace_stack_event = {
@@ -1194,9 +1129,6 @@ static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
 
 static struct trace_event_functions trace_user_stack_funcs = {
 	.trace		= trace_user_stack_print,
-	.raw		= trace_special_print,
-	.hex		= trace_special_hex,
-	.binary		= trace_special_bin,
 };
 
 static struct trace_event trace_user_stack_event = {
@@ -1314,7 +1246,6 @@ static struct trace_event *events[] __initdata = {
 	&trace_fn_event,
 	&trace_ctx_event,
 	&trace_wake_event,
-	&trace_special_event,
 	&trace_stack_event,
 	&trace_user_stack_event,
 	&trace_bprint_event,
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 0e73bc2ef8c5..4086eae6e81b 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -46,7 +46,6 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
 	struct trace_array_cpu *data;
 	unsigned long flags;
 	long disabled;
-	int resched;
 	int cpu;
 	int pc;
 
@@ -54,7 +53,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
 		return;
 
 	pc = preempt_count();
-	resched = ftrace_preempt_disable();
+	preempt_disable_notrace();
 
 	cpu = raw_smp_processor_id();
 	if (cpu != wakeup_current_cpu)
@@ -74,7 +73,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
  out:
 	atomic_dec(&data->disabled);
  out_enable:
-	ftrace_preempt_enable(resched);
+	preempt_enable_notrace();
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
@@ -383,6 +382,7 @@ static struct tracer wakeup_tracer __read_mostly =
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,
 #endif
+	.use_max_tr	= 1,
 };
 
 static struct tracer wakeup_rt_tracer __read_mostly =
@@ -397,6 +397,7 @@ static struct tracer wakeup_rt_tracer __read_mostly =
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,
 #endif
+	.use_max_tr	= 1,
 };
 
 __init static int init_wakeup_tracer(void)
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 250e7f9bd2f0..155a415b3209 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -13,11 +13,9 @@ static inline int trace_valid_entry(struct trace_entry *entry)
 	case TRACE_WAKE:
 	case TRACE_STACK:
 	case TRACE_PRINT:
-	case TRACE_SPECIAL:
 	case TRACE_BRANCH:
 	case TRACE_GRAPH_ENT:
 	case TRACE_GRAPH_RET:
-	case TRACE_KSYM:
 		return 1;
 	}
 	return 0;
@@ -691,38 +689,6 @@ trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr
 }
 #endif /* CONFIG_CONTEXT_SWITCH_TRACER */
 
-#ifdef CONFIG_SYSPROF_TRACER
-int
-trace_selftest_startup_sysprof(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;
-	}
-
-	/* Sleep for a 1/10 of a second */
-	msleep(100);
-	/* stop the tracing. */
-	tracing_stop();
-	/* check the trace buffer */
-	ret = trace_test_buffer(tr, &count);
-	trace->reset(tr);
-	tracing_start();
-
-	if (!ret && !count) {
-		printk(KERN_CONT ".. no entries found ..");
-		ret = -1;
-	}
-
-	return ret;
-}
-#endif /* CONFIG_SYSPROF_TRACER */
-
 #ifdef CONFIG_BRANCH_TRACER
 int
 trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
@@ -755,56 +721,3 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
 }
 #endif /* CONFIG_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_stack.c b/kernel/trace/trace_stack.c
index f4bc9b27de5f..056468eae7cf 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -110,12 +110,12 @@ static inline void check_stack(void)
 static void
 stack_trace_call(unsigned long ip, unsigned long parent_ip)
 {
-	int cpu, resched;
+	int cpu;
 
 	if (unlikely(!ftrace_enabled || stack_trace_disabled))
 		return;
 
-	resched = ftrace_preempt_disable();
+	preempt_disable_notrace();
 
 	cpu = raw_smp_processor_id();
 	/* no atomic needed, we only modify this variable by this cpu */
@@ -127,7 +127,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
  out:
 	per_cpu(trace_active, cpu)--;
 	/* prevent recursion in schedule */
-	ftrace_preempt_enable(resched);
+	preempt_enable_notrace();
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 34e35804304b..bac752f0cfb5 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -23,6 +23,9 @@ static int syscall_exit_register(struct ftrace_event_call *event,
 static int syscall_enter_define_fields(struct ftrace_event_call *call);
 static int syscall_exit_define_fields(struct ftrace_event_call *call);
 
+/* All syscall exit events have the same fields */
+static LIST_HEAD(syscall_exit_fields);
+
 static struct list_head *
 syscall_get_enter_fields(struct ftrace_event_call *call)
 {
@@ -34,9 +37,7 @@ syscall_get_enter_fields(struct ftrace_event_call *call)
 static struct list_head *
 syscall_get_exit_fields(struct ftrace_event_call *call)
 {
-	struct syscall_metadata *entry = call->data;
-
-	return &entry->exit_fields;
+	return &syscall_exit_fields;
 }
 
 struct trace_event_functions enter_syscall_print_funcs = {
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
deleted file mode 100644
index a7974a552ca9..000000000000
--- a/kernel/trace/trace_sysprof.c
+++ /dev/null
@@ -1,329 +0,0 @@
-/*
- * trace stack traces
- *
- * Copyright (C) 2004-2008, Soeren Sandmann
- * Copyright (C) 2007 Steven Rostedt <srostedt@redhat.com>
- * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
- */
-#include <linux/kallsyms.h>
-#include <linux/debugfs.h>
-#include <linux/hrtimer.h>
-#include <linux/uaccess.h>
-#include <linux/ftrace.h>
-#include <linux/module.h>
-#include <linux/irq.h>
-#include <linux/fs.h>
-
-#include <asm/stacktrace.h>
-
-#include "trace.h"
-
-static struct trace_array	*sysprof_trace;
-static int __read_mostly	tracer_enabled;
-
-/*
- * 1 msec sample interval by default:
- */
-static unsigned long sample_period = 1000000;
-static const unsigned int sample_max_depth = 512;
-
-static DEFINE_MUTEX(sample_timer_lock);
-/*
- * Per CPU hrtimers that do the profiling:
- */
-static DEFINE_PER_CPU(struct hrtimer, stack_trace_hrtimer);
-
-struct stack_frame {
-	const void __user	*next_fp;
-	unsigned long		return_address;
-};
-
-static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
-{
-	int ret;
-
-	if (!access_ok(VERIFY_READ, fp, sizeof(*frame)))
-		return 0;
-
-	ret = 1;
-	pagefault_disable();
-	if (__copy_from_user_inatomic(frame, fp, sizeof(*frame)))
-		ret = 0;
-	pagefault_enable();
-
-	return ret;
-}
-
-struct backtrace_info {
-	struct trace_array_cpu	*data;
-	struct trace_array	*tr;
-	int			pos;
-};
-
-static void
-backtrace_warning_symbol(void *data, char *msg, unsigned long symbol)
-{
-	/* Ignore warnings */
-}
-
-static void backtrace_warning(void *data, char *msg)
-{
-	/* Ignore warnings */
-}
-
-static int backtrace_stack(void *data, char *name)
-{
-	/* Don't bother with IRQ stacks for now */
-	return -1;
-}
-
-static void backtrace_address(void *data, unsigned long addr, int reliable)
-{
-	struct backtrace_info *info = data;
-
-	if (info->pos < sample_max_depth && reliable) {
-		__trace_special(info->tr, info->data, 1, addr, 0);
-
-		info->pos++;
-	}
-}
-
-static const struct stacktrace_ops backtrace_ops = {
-	.warning		= backtrace_warning,
-	.warning_symbol		= backtrace_warning_symbol,
-	.stack			= backtrace_stack,
-	.address		= backtrace_address,
-	.walk_stack		= print_context_stack,
-};
-
-static int
-trace_kernel(struct pt_regs *regs, struct trace_array *tr,
-	     struct trace_array_cpu *data)
-{
-	struct backtrace_info info;
-	unsigned long bp;
-	char *stack;
-
-	info.tr = tr;
-	info.data = data;
-	info.pos = 1;
-
-	__trace_special(info.tr, info.data, 1, regs->ip, 0);
-
-	stack = ((char *)regs + sizeof(struct pt_regs));
-#ifdef CONFIG_FRAME_POINTER
-	bp = regs->bp;
-#else
-	bp = 0;
-#endif
-
-	dump_trace(NULL, regs, (void *)stack, bp, &backtrace_ops, &info);
-
-	return info.pos;
-}
-
-static void timer_notify(struct pt_regs *regs, int cpu)
-{
-	struct trace_array_cpu *data;
-	struct stack_frame frame;
-	struct trace_array *tr;
-	const void __user *fp;
-	int is_user;
-	int i;
-
-	if (!regs)
-		return;
-
-	tr = sysprof_trace;
-	data = tr->data[cpu];
-	is_user = user_mode(regs);
-
-	if (!current || current->pid == 0)
-		return;
-
-	if (is_user && current->state != TASK_RUNNING)
-		return;
-
-	__trace_special(tr, data, 0, 0, current->pid);
-
-	if (!is_user)
-		i = trace_kernel(regs, tr, data);
-	else
-		i = 0;
-
-	/*
-	 * Trace user stack if we are not a kernel thread
-	 */
-	if (current->mm && i < sample_max_depth) {
-		regs = (struct pt_regs *)current->thread.sp0 - 1;
-
-		fp = (void __user *)regs->bp;
-
-		__trace_special(tr, data, 2, regs->ip, 0);
-
-		while (i < sample_max_depth) {
-			frame.next_fp = NULL;
-			frame.return_address = 0;
-			if (!copy_stack_frame(fp, &frame))
-				break;
-			if ((unsigned long)fp < regs->sp)
-				break;
-
-			__trace_special(tr, data, 2, frame.return_address,
-					(unsigned long)fp);
-			fp = frame.next_fp;
-
-			i++;
-		}
-
-	}
-
-	/*
-	 * Special trace entry if we overflow the max depth:
-	 */
-	if (i == sample_max_depth)
-		__trace_special(tr, data, -1, -1, -1);
-
-	__trace_special(tr, data, 3, current->pid, i);
-}
-
-static enum hrtimer_restart stack_trace_timer_fn(struct hrtimer *hrtimer)
-{
-	/* trace here */
-	timer_notify(get_irq_regs(), smp_processor_id());
-
-	hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
-
-	return HRTIMER_RESTART;
-}
-
-static void start_stack_timer(void *unused)
-{
-	struct hrtimer *hrtimer = &__get_cpu_var(stack_trace_hrtimer);
-
-	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hrtimer->function = stack_trace_timer_fn;
-
-	hrtimer_start(hrtimer, ns_to_ktime(sample_period),
-		      HRTIMER_MODE_REL_PINNED);
-}
-
-static void start_stack_timers(void)
-{
-	on_each_cpu(start_stack_timer, NULL, 1);
-}
-
-static void stop_stack_timer(int cpu)
-{
-	struct hrtimer *hrtimer = &per_cpu(stack_trace_hrtimer, cpu);
-
-	hrtimer_cancel(hrtimer);
-}
-
-static void stop_stack_timers(void)
-{
-	int cpu;
-
-	for_each_online_cpu(cpu)
-		stop_stack_timer(cpu);
-}
-
-static void stop_stack_trace(struct trace_array *tr)
-{
-	mutex_lock(&sample_timer_lock);
-	stop_stack_timers();
-	tracer_enabled = 0;
-	mutex_unlock(&sample_timer_lock);
-}
-
-static int stack_trace_init(struct trace_array *tr)
-{
-	sysprof_trace = tr;
-
-	tracing_start_cmdline_record();
-
-	mutex_lock(&sample_timer_lock);
-	start_stack_timers();
-	tracer_enabled = 1;
-	mutex_unlock(&sample_timer_lock);
-	return 0;
-}
-
-static void stack_trace_reset(struct trace_array *tr)
-{
-	tracing_stop_cmdline_record();
-	stop_stack_trace(tr);
-}
-
-static struct tracer stack_trace __read_mostly =
-{
-	.name		= "sysprof",
-	.init		= stack_trace_init,
-	.reset		= stack_trace_reset,
-#ifdef CONFIG_FTRACE_SELFTEST
-	.selftest    = trace_selftest_startup_sysprof,
-#endif
-};
-
-__init static int init_stack_trace(void)
-{
-	return register_tracer(&stack_trace);
-}
-device_initcall(init_stack_trace);
-
-#define MAX_LONG_DIGITS 22
-
-static ssize_t
-sysprof_sample_read(struct file *filp, char __user *ubuf,
-		    size_t cnt, loff_t *ppos)
-{
-	char buf[MAX_LONG_DIGITS];
-	int r;
-
-	r = sprintf(buf, "%ld\n", nsecs_to_usecs(sample_period));
-
-	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
-}
-
-static ssize_t
-sysprof_sample_write(struct file *filp, const char __user *ubuf,
-		     size_t cnt, loff_t *ppos)
-{
-	char buf[MAX_LONG_DIGITS];
-	unsigned long val;
-
-	if (cnt > MAX_LONG_DIGITS-1)
-		cnt = MAX_LONG_DIGITS-1;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-
-	val = simple_strtoul(buf, NULL, 10);
-	/*
-	 * Enforce a minimum sample period of 100 usecs:
-	 */
-	if (val < 100)
-		val = 100;
-
-	mutex_lock(&sample_timer_lock);
-	stop_stack_timers();
-	sample_period = val * 1000;
-	start_stack_timers();
-	mutex_unlock(&sample_timer_lock);
-
-	return cnt;
-}
-
-static const struct file_operations sysprof_sample_fops = {
-	.read		= sysprof_sample_read,
-	.write		= sysprof_sample_write,
-};
-
-void init_tracer_sysprof_debugfs(struct dentry *d_tracer)
-{
-
-	trace_create_file("sysprof_sample_period", 0644,
-			d_tracer, NULL, &sysprof_sample_fops);
-}
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
new file mode 100644
index 000000000000..613bc1f04610
--- /dev/null
+++ b/kernel/watchdog.c
@@ -0,0 +1,567 @@
+/*
+ * Detect hard and soft lockups on a system
+ *
+ * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
+ *
+ * this code detects hard lockups: incidents in where on a CPU
+ * the kernel does not respond to anything except NMI.
+ *
+ * Note: Most of this code is borrowed heavily from softlockup.c,
+ * so thanks to Ingo for the initial implementation.
+ * Some chunks also taken from arch/x86/kernel/apic/nmi.c, thanks
+ * to those contributors as well.
+ */
+
+#include <linux/mm.h>
+#include <linux/cpu.h>
+#include <linux/nmi.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/freezer.h>
+#include <linux/kthread.h>
+#include <linux/lockdep.h>
+#include <linux/notifier.h>
+#include <linux/module.h>
+#include <linux/sysctl.h>
+
+#include <asm/irq_regs.h>
+#include <linux/perf_event.h>
+
+int watchdog_enabled;
+int __read_mostly softlockup_thresh = 60;
+
+static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
+static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
+static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
+static DEFINE_PER_CPU(bool, softlockup_touch_sync);
+static DEFINE_PER_CPU(bool, soft_watchdog_warn);
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+static DEFINE_PER_CPU(bool, hard_watchdog_warn);
+static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
+static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
+static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
+static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
+#endif
+
+static int __read_mostly did_panic;
+static int __initdata no_watchdog;
+
+
+/* boot commands */
+/*
+ * Should we panic when a soft-lockup or hard-lockup occurs:
+ */
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+static int hardlockup_panic;
+
+static int __init hardlockup_panic_setup(char *str)
+{
+	if (!strncmp(str, "panic", 5))
+		hardlockup_panic = 1;
+	return 1;
+}
+__setup("nmi_watchdog=", hardlockup_panic_setup);
+#endif
+
+unsigned int __read_mostly softlockup_panic =
+			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
+
+static int __init softlockup_panic_setup(char *str)
+{
+	softlockup_panic = simple_strtoul(str, NULL, 0);
+
+	return 1;
+}
+__setup("softlockup_panic=", softlockup_panic_setup);
+
+static int __init nowatchdog_setup(char *str)
+{
+	no_watchdog = 1;
+	return 1;
+}
+__setup("nowatchdog", nowatchdog_setup);
+
+/* deprecated */
+static int __init nosoftlockup_setup(char *str)
+{
+	no_watchdog = 1;
+	return 1;
+}
+__setup("nosoftlockup", nosoftlockup_setup);
+/*  */
+
+
+/*
+ * Returns seconds, approximately.  We don't need nanosecond
+ * resolution, and we don't need to waste time with a big divide when
+ * 2^30ns == 1.074s.
+ */
+static unsigned long get_timestamp(int this_cpu)
+{
+	return cpu_clock(this_cpu) >> 30LL;  /* 2^30 ~= 10^9 */
+}
+
+static unsigned long get_sample_period(void)
+{
+	/*
+	 * convert softlockup_thresh from seconds to ns
+	 * the divide by 5 is to give hrtimer 5 chances to
+	 * increment before the hardlockup detector generates
+	 * a warning
+	 */
+	return softlockup_thresh / 5 * NSEC_PER_SEC;
+}
+
+/* Commands for resetting the watchdog */
+static void __touch_watchdog(void)
+{
+	int this_cpu = smp_processor_id();
+
+	__get_cpu_var(watchdog_touch_ts) = get_timestamp(this_cpu);
+}
+
+void touch_softlockup_watchdog(void)
+{
+	__get_cpu_var(watchdog_touch_ts) = 0;
+}
+EXPORT_SYMBOL(touch_softlockup_watchdog);
+
+void touch_all_softlockup_watchdogs(void)
+{
+	int cpu;
+
+	/*
+	 * this is done lockless
+	 * do we care if a 0 races with a timestamp?
+	 * all it means is the softlock check starts one cycle later
+	 */
+	for_each_online_cpu(cpu)
+		per_cpu(watchdog_touch_ts, cpu) = 0;
+}
+
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+void touch_nmi_watchdog(void)
+{
+	__get_cpu_var(watchdog_nmi_touch) = true;
+	touch_softlockup_watchdog();
+}
+EXPORT_SYMBOL(touch_nmi_watchdog);
+
+#endif
+
+void touch_softlockup_watchdog_sync(void)
+{
+	__raw_get_cpu_var(softlockup_touch_sync) = true;
+	__raw_get_cpu_var(watchdog_touch_ts) = 0;
+}
+
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+/* watchdog detector functions */
+static int is_hardlockup(void)
+{
+	unsigned long hrint = __get_cpu_var(hrtimer_interrupts);
+
+	if (__get_cpu_var(hrtimer_interrupts_saved) == hrint)
+		return 1;
+
+	__get_cpu_var(hrtimer_interrupts_saved) = hrint;
+	return 0;
+}
+#endif
+
+static int is_softlockup(unsigned long touch_ts)
+{
+	unsigned long now = get_timestamp(smp_processor_id());
+
+	/* Warn about unreasonable delays: */
+	if (time_after(now, touch_ts + softlockup_thresh))
+		return now - touch_ts;
+
+	return 0;
+}
+
+static int
+watchdog_panic(struct notifier_block *this, unsigned long event, void *ptr)
+{
+	did_panic = 1;
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block panic_block = {
+	.notifier_call = watchdog_panic,
+};
+
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+static struct perf_event_attr wd_hw_attr = {
+	.type		= PERF_TYPE_HARDWARE,
+	.config		= PERF_COUNT_HW_CPU_CYCLES,
+	.size		= sizeof(struct perf_event_attr),
+	.pinned		= 1,
+	.disabled	= 1,
+};
+
+/* Callback function for perf event subsystem */
+void watchdog_overflow_callback(struct perf_event *event, int nmi,
+		 struct perf_sample_data *data,
+		 struct pt_regs *regs)
+{
+	if (__get_cpu_var(watchdog_nmi_touch) == true) {
+		__get_cpu_var(watchdog_nmi_touch) = false;
+		return;
+	}
+
+	/* check for a hardlockup
+	 * This is done by making sure our timer interrupt
+	 * is incrementing.  The timer interrupt should have
+	 * fired multiple times before we overflow'd.  If it hasn't
+	 * then this is a good indication the cpu is stuck
+	 */
+	if (is_hardlockup()) {
+		int this_cpu = smp_processor_id();
+
+		/* only print hardlockups once */
+		if (__get_cpu_var(hard_watchdog_warn) == true)
+			return;
+
+		if (hardlockup_panic)
+			panic("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
+		else
+			WARN(1, "Watchdog detected hard LOCKUP on cpu %d", this_cpu);
+
+		__get_cpu_var(hard_watchdog_warn) = true;
+		return;
+	}
+
+	__get_cpu_var(hard_watchdog_warn) = false;
+	return;
+}
+static void watchdog_interrupt_count(void)
+{
+	__get_cpu_var(hrtimer_interrupts)++;
+}
+#else
+static inline void watchdog_interrupt_count(void) { return; }
+#endif /* CONFIG_HARDLOCKUP_DETECTOR */
+
+/* watchdog kicker functions */
+static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
+{
+	unsigned long touch_ts = __get_cpu_var(watchdog_touch_ts);
+	struct pt_regs *regs = get_irq_regs();
+	int duration;
+
+	/* kick the hardlockup detector */
+	watchdog_interrupt_count();
+
+	/* kick the softlockup detector */
+	wake_up_process(__get_cpu_var(softlockup_watchdog));
+
+	/* .. and repeat */
+	hrtimer_forward_now(hrtimer, ns_to_ktime(get_sample_period()));
+
+	if (touch_ts == 0) {
+		if (unlikely(__get_cpu_var(softlockup_touch_sync))) {
+			/*
+			 * If the time stamp was touched atomically
+			 * make sure the scheduler tick is up to date.
+			 */
+			__get_cpu_var(softlockup_touch_sync) = false;
+			sched_clock_tick();
+		}
+		__touch_watchdog();
+		return HRTIMER_RESTART;
+	}
+
+	/* check for a softlockup
+	 * This is done by making sure a high priority task is
+	 * being scheduled.  The task touches the watchdog to
+	 * indicate it is getting cpu time.  If it hasn't then
+	 * this is a good indication some task is hogging the cpu
+	 */
+	duration = is_softlockup(touch_ts);
+	if (unlikely(duration)) {
+		/* only warn once */
+		if (__get_cpu_var(soft_watchdog_warn) == true)
+			return HRTIMER_RESTART;
+
+		printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
+			smp_processor_id(), duration,
+			current->comm, task_pid_nr(current));
+		print_modules();
+		print_irqtrace_events(current);
+		if (regs)
+			show_regs(regs);
+		else
+			dump_stack();
+
+		if (softlockup_panic)
+			panic("softlockup: hung tasks");
+		__get_cpu_var(soft_watchdog_warn) = true;
+	} else
+		__get_cpu_var(soft_watchdog_warn) = false;
+
+	return HRTIMER_RESTART;
+}
+
+
+/*
+ * The watchdog thread - touches the timestamp.
+ */
+static int watchdog(void *unused)
+{
+	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
+	struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
+
+	sched_setscheduler(current, SCHED_FIFO, &param);
+
+	/* initialize timestamp */
+	__touch_watchdog();
+
+	/* kick off the timer for the hardlockup detector */
+	/* done here because hrtimer_start can only pin to smp_processor_id() */
+	hrtimer_start(hrtimer, ns_to_ktime(get_sample_period()),
+		      HRTIMER_MODE_REL_PINNED);
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	/*
+	 * Run briefly once per second to reset the softlockup timestamp.
+	 * If this gets delayed for more than 60 seconds then the
+	 * debug-printout triggers in watchdog_timer_fn().
+	 */
+	while (!kthread_should_stop()) {
+		__touch_watchdog();
+		schedule();
+
+		if (kthread_should_stop())
+			break;
+
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+	__set_current_state(TASK_RUNNING);
+
+	return 0;
+}
+
+
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+static int watchdog_nmi_enable(int cpu)
+{
+	struct perf_event_attr *wd_attr;
+	struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+	/* is it already setup and enabled? */
+	if (event && event->state > PERF_EVENT_STATE_OFF)
+		goto out;
+
+	/* it is setup but not enabled */
+	if (event != NULL)
+		goto out_enable;
+
+	/* Try to register using hardware perf events */
+	wd_attr = &wd_hw_attr;
+	wd_attr->sample_period = hw_nmi_get_sample_period();
+	event = perf_event_create_kernel_counter(wd_attr, cpu, -1, watchdog_overflow_callback);
+	if (!IS_ERR(event)) {
+		printk(KERN_INFO "NMI watchdog enabled, takes one hw-pmu counter.\n");
+		goto out_save;
+	}
+
+	printk(KERN_ERR "NMI watchdog failed to create perf event on cpu%i: %p\n", cpu, event);
+	return -1;
+
+	/* success path */
+out_save:
+	per_cpu(watchdog_ev, cpu) = event;
+out_enable:
+	perf_event_enable(per_cpu(watchdog_ev, cpu));
+out:
+	return 0;
+}
+
+static void watchdog_nmi_disable(int cpu)
+{
+	struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+	if (event) {
+		perf_event_disable(event);
+		per_cpu(watchdog_ev, cpu) = NULL;
+
+		/* should be in cleanup, but blocks oprofile */
+		perf_event_release_kernel(event);
+	}
+	return;
+}
+#else
+static int watchdog_nmi_enable(int cpu) { return 0; }
+static void watchdog_nmi_disable(int cpu) { return; }
+#endif /* CONFIG_HARDLOCKUP_DETECTOR */
+
+/* prepare/enable/disable routines */
+static int watchdog_prepare_cpu(int cpu)
+{
+	struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu);
+
+	WARN_ON(per_cpu(softlockup_watchdog, cpu));
+	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer->function = watchdog_timer_fn;
+
+	return 0;
+}
+
+static int watchdog_enable(int cpu)
+{
+	struct task_struct *p = per_cpu(softlockup_watchdog, cpu);
+
+	/* enable the perf event */
+	if (watchdog_nmi_enable(cpu) != 0)
+		return -1;
+
+	/* create the watchdog thread */
+	if (!p) {
+		p = kthread_create(watchdog, (void *)(unsigned long)cpu, "watchdog/%d", cpu);
+		if (IS_ERR(p)) {
+			printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu);
+			return -1;
+		}
+		kthread_bind(p, cpu);
+		per_cpu(watchdog_touch_ts, cpu) = 0;
+		per_cpu(softlockup_watchdog, cpu) = p;
+		wake_up_process(p);
+	}
+
+	return 0;
+}
+
+static void watchdog_disable(int cpu)
+{
+	struct task_struct *p = per_cpu(softlockup_watchdog, cpu);
+	struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu);
+
+	/*
+	 * cancel the timer first to stop incrementing the stats
+	 * and waking up the kthread
+	 */
+	hrtimer_cancel(hrtimer);
+
+	/* disable the perf event */
+	watchdog_nmi_disable(cpu);
+
+	/* stop the watchdog thread */
+	if (p) {
+		per_cpu(softlockup_watchdog, cpu) = NULL;
+		kthread_stop(p);
+	}
+
+	/* if any cpu succeeds, watchdog is considered enabled for the system */
+	watchdog_enabled = 1;
+}
+
+static void watchdog_enable_all_cpus(void)
+{
+	int cpu;
+	int result = 0;
+
+	for_each_online_cpu(cpu)
+		result += watchdog_enable(cpu);
+
+	if (result)
+		printk(KERN_ERR "watchdog: failed to be enabled on some cpus\n");
+
+}
+
+static void watchdog_disable_all_cpus(void)
+{
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		watchdog_disable(cpu);
+
+	/* if all watchdogs are disabled, then they are disabled for the system */
+	watchdog_enabled = 0;
+}
+
+
+/* sysctl functions */
+#ifdef CONFIG_SYSCTL
+/*
+ * proc handler for /proc/sys/kernel/nmi_watchdog
+ */
+
+int proc_dowatchdog_enabled(struct ctl_table *table, int write,
+		     void __user *buffer, size_t *length, loff_t *ppos)
+{
+	proc_dointvec(table, write, buffer, length, ppos);
+
+	if (watchdog_enabled)
+		watchdog_enable_all_cpus();
+	else
+		watchdog_disable_all_cpus();
+	return 0;
+}
+
+int proc_dowatchdog_thresh(struct ctl_table *table, int write,
+			     void __user *buffer,
+			     size_t *lenp, loff_t *ppos)
+{
+	return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+}
+#endif /* CONFIG_SYSCTL */
+
+
+/*
+ * Create/destroy watchdog threads as CPUs come and go:
+ */
+static int __cpuinit
+cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
+{
+	int hotcpu = (unsigned long)hcpu;
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		if (watchdog_prepare_cpu(hotcpu))
+			return NOTIFY_BAD;
+		break;
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		if (watchdog_enable(hotcpu))
+			return NOTIFY_BAD;
+		break;
+#ifdef CONFIG_HOTPLUG_CPU
+	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
+		watchdog_disable(hotcpu);
+		break;
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		watchdog_disable(hotcpu);
+		break;
+#endif /* CONFIG_HOTPLUG_CPU */
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata cpu_nfb = {
+	.notifier_call = cpu_callback
+};
+
+static int __init spawn_watchdog_task(void)
+{
+	void *cpu = (void *)(long)smp_processor_id();
+	int err;
+
+	if (no_watchdog)
+		return 0;
+
+	err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
+	WARN_ON(err == NOTIFY_BAD);
+
+	cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
+	register_cpu_notifier(&cpu_nfb);
+
+	atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
+
+	return 0;
+}
+early_initcall(spawn_watchdog_task);