Merge branch 'tip/perf/core' of git://github.com/rostedt/linux into perf/core

12 files changed, 913 insertions, 452 deletions

diff --git a/kernel/module.c b/kernel/module.c
index 04379f92f84..93342d992f3 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3487,50 +3487,3 @@ void module_layout(struct module *mod,
 }
 EXPORT_SYMBOL(module_layout);
 #endif
-
-#ifdef CONFIG_TRACEPOINTS
-void module_update_tracepoints(void)
-{
-	struct module *mod;
-
-	mutex_lock(&module_mutex);
-	list_for_each_entry(mod, &modules, list)
-		if (!mod->taints)
-			tracepoint_update_probe_range(mod->tracepoints_ptrs,
-				mod->tracepoints_ptrs + mod->num_tracepoints);
-	mutex_unlock(&module_mutex);
-}
-
-/*
- * Returns 0 if current not found.
- * Returns 1 if current found.
- */
-int module_get_iter_tracepoints(struct tracepoint_iter *iter)
-{
-	struct module *iter_mod;
-	int found = 0;
-
-	mutex_lock(&module_mutex);
-	list_for_each_entry(iter_mod, &modules, list) {
-		if (!iter_mod->taints) {
-			/*
-			 * Sorted module list
-			 */
-			if (iter_mod < iter->module)
-				continue;
-			else if (iter_mod > iter->module)
-				iter->tracepoint = NULL;
-			found = tracepoint_get_iter_range(&iter->tracepoint,
-				iter_mod->tracepoints_ptrs,
-				iter_mod->tracepoints_ptrs
-					+ iter_mod->num_tracepoints);
-			if (found) {
-				iter->module = iter_mod;
-				break;
-			}
-		}
-	}
-	mutex_unlock(&module_mutex);
-	return found;
-}
-#endif
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 761c510a06c..b384ed512ba 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -15,6 +15,8 @@ ifdef CONFIG_TRACING_BRANCHES
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 endif
 
+CFLAGS_trace_events_filter.o := -I$(src)
+
 #
 # Make the trace clocks available generally: it's infrastructure
 # relied on by ptrace for example:
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index c3e4575e782..077d8538790 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3863,6 +3863,14 @@ void ftrace_kill(void)
 }
 
 /**
+ * Test if ftrace is dead or not.
+ */
+int ftrace_is_dead(void)
+{
+	return ftrace_disabled;
+}
+
+/**
  * register_ftrace_function - register a function for profiling
  * @ops - ops structure that holds the function for profiling.
  *
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 731201bf4ac..acf6b68dc4a 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -488,12 +488,14 @@ struct ring_buffer_per_cpu {
 	struct buffer_page		*reader_page;
 	unsigned long			lost_events;
 	unsigned long			last_overrun;
+	local_t				entries_bytes;
 	local_t				commit_overrun;
 	local_t				overrun;
 	local_t				entries;
 	local_t				committing;
 	local_t				commits;
 	unsigned long			read;
+	unsigned long			read_bytes;
 	u64				write_stamp;
 	u64				read_stamp;
 };
@@ -1708,6 +1710,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
 		 * the counters.
 		 */
 		local_add(entries, &cpu_buffer->overrun);
+		local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
 
 		/*
 		 * The entries will be zeroed out when we move the
@@ -1863,6 +1866,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	event = __rb_page_index(tail_page, tail);
 	kmemcheck_annotate_bitfield(event, bitfield);
 
+	/* account for padding bytes */
+	local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);
+
 	/*
 	 * Save the original length to the meta data.
 	 * This will be used by the reader to add lost event
@@ -2054,6 +2060,9 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	if (!tail)
 		tail_page->page->time_stamp = ts;
 
+	/* account for these added bytes */
+	local_add(length, &cpu_buffer->entries_bytes);
+
 	return event;
 }
 
@@ -2076,6 +2085,7 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 	if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
 		unsigned long write_mask =
 			local_read(&bpage->write) & ~RB_WRITE_MASK;
+		unsigned long event_length = rb_event_length(event);
 		/*
 		 * This is on the tail page. It is possible that
 		 * a write could come in and move the tail page
@@ -2085,8 +2095,11 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 		old_index += write_mask;
 		new_index += write_mask;
 		index = local_cmpxchg(&bpage->write, old_index, new_index);
-		if (index == old_index)
+		if (index == old_index) {
+			/* update counters */
+			local_sub(event_length, &cpu_buffer->entries_bytes);
 			return 1;
+		}
 	}
 
 	/* could not discard */
@@ -2661,6 +2674,58 @@ rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer)
 }
 
 /**
+ * ring_buffer_oldest_event_ts - get the oldest event timestamp from the buffer
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to read from.
+ */
+unsigned long ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu)
+{
+	unsigned long flags;
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct buffer_page *bpage;
+	unsigned long ret;
+
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return 0;
+
+	cpu_buffer = buffer->buffers[cpu];
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	/*
+	 * if the tail is on reader_page, oldest time stamp is on the reader
+	 * page
+	 */
+	if (cpu_buffer->tail_page == cpu_buffer->reader_page)
+		bpage = cpu_buffer->reader_page;
+	else
+		bpage = rb_set_head_page(cpu_buffer);
+	ret = bpage->page->time_stamp;
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts);
+
+/**
+ * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to read from.
+ */
+unsigned long ring_buffer_bytes_cpu(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long ret;
+
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return 0;
+
+	cpu_buffer = buffer->buffers[cpu];
+	ret = local_read(&cpu_buffer->entries_bytes) - cpu_buffer->read_bytes;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_bytes_cpu);
+
+/**
  * ring_buffer_entries_cpu - get the number of entries in a cpu buffer
  * @buffer: The ring buffer
  * @cpu: The per CPU buffer to get the entries from.
@@ -3527,11 +3592,13 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->reader_page->read = 0;
 
 	local_set(&cpu_buffer->commit_overrun, 0);
+	local_set(&cpu_buffer->entries_bytes, 0);
 	local_set(&cpu_buffer->overrun, 0);
 	local_set(&cpu_buffer->entries, 0);
 	local_set(&cpu_buffer->committing, 0);
 	local_set(&cpu_buffer->commits, 0);
 	cpu_buffer->read = 0;
+	cpu_buffer->read_bytes = 0;
 
 	cpu_buffer->write_stamp = 0;
 	cpu_buffer->read_stamp = 0;
@@ -3918,6 +3985,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 	} else {
 		/* update the entry counter */
 		cpu_buffer->read += rb_page_entries(reader);
+		cpu_buffer->read_bytes += BUF_PAGE_SIZE;
 
 		/* swap the pages */
 		rb_init_page(bpage);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e5df02c69b1..f86efe90ca4 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -435,6 +435,7 @@ static struct {
 } trace_clocks[] = {
 	{ trace_clock_local,	"local" },
 	{ trace_clock_global,	"global" },
+	{ trace_clock_counter,	"counter" },
 };
 
 int trace_clock_id;
@@ -2159,6 +2160,14 @@ void trace_default_header(struct seq_file *m)
 	}
 }
 
+static void test_ftrace_alive(struct seq_file *m)
+{
+	if (!ftrace_is_dead())
+		return;
+	seq_printf(m, "# WARNING: FUNCTION TRACING IS CORRUPTED\n");
+	seq_printf(m, "#          MAY BE MISSING FUNCTION EVENTS\n");
+}
+
 static int s_show(struct seq_file *m, void *v)
 {
 	struct trace_iterator *iter = v;
@@ -2168,6 +2177,7 @@ static int s_show(struct seq_file *m, void *v)
 		if (iter->tr) {
 			seq_printf(m, "# tracer: %s\n", iter->trace->name);
 			seq_puts(m, "#\n");
+			test_ftrace_alive(m);
 		}
 		if (iter->trace && iter->trace->print_header)
 			iter->trace->print_header(m);
@@ -3569,6 +3579,30 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 }
 
 static ssize_t
+tracing_total_entries_read(struct file *filp, char __user *ubuf,
+				size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	char buf[64];
+	int r, cpu;
+	unsigned long size = 0, expanded_size = 0;
+
+	mutex_lock(&trace_types_lock);
+	for_each_tracing_cpu(cpu) {
+		size += tr->entries >> 10;
+		if (!ring_buffer_expanded)
+			expanded_size += trace_buf_size >> 10;
+	}
+	if (ring_buffer_expanded)
+		r = sprintf(buf, "%lu\n", size);
+	else
+		r = sprintf(buf, "%lu (expanded: %lu)\n", size, expanded_size);
+	mutex_unlock(&trace_types_lock);
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
 tracing_free_buffer_write(struct file *filp, const char __user *ubuf,
 			  size_t cnt, loff_t *ppos)
 {
@@ -3594,22 +3628,24 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static int mark_printk(const char *fmt, ...)
-{
-	int ret;
-	va_list args;
-	va_start(args, fmt);
-	ret = trace_vprintk(0, fmt, args);
-	va_end(args);
-	return ret;
-}
-
 static ssize_t
 tracing_mark_write(struct file *filp, const char __user *ubuf,
 					size_t cnt, loff_t *fpos)
 {
-	char *buf;
-	size_t written;
+	unsigned long addr = (unsigned long)ubuf;
+	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
+	struct print_entry *entry;
+	unsigned long irq_flags;
+	struct page *pages[2];
+	int nr_pages = 1;
+	ssize_t written;
+	void *page1;
+	void *page2;
+	int offset;
+	int size;
+	int len;
+	int ret;
 
 	if (tracing_disabled)
 		return -EINVAL;
@@ -3617,28 +3653,81 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (cnt > TRACE_BUF_SIZE)
 		cnt = TRACE_BUF_SIZE;
 
-	buf = kmalloc(cnt + 2, GFP_KERNEL);
-	if (buf == NULL)
-		return -ENOMEM;
+	/*
+	 * Userspace is injecting traces into the kernel trace buffer.
+	 * We want to be as non intrusive as possible.
+	 * To do so, we do not want to allocate any special buffers
+	 * or take any locks, but instead write the userspace data
+	 * straight into the ring buffer.
+	 *
+	 * First we need to pin the userspace buffer into memory,
+	 * which, most likely it is, because it just referenced it.
+	 * But there's no guarantee that it is. By using get_user_pages_fast()
+	 * and kmap_atomic/kunmap_atomic() we can get access to the
+	 * pages directly. We then write the data directly into the
+	 * ring buffer.
+	 */
+	BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE);
 
-	if (copy_from_user(buf, ubuf, cnt)) {
-		kfree(buf);
-		return -EFAULT;
+	/* check if we cross pages */
+	if ((addr & PAGE_MASK) != ((addr + cnt) & PAGE_MASK))
+		nr_pages = 2;
+
+	offset = addr & (PAGE_SIZE - 1);
+	addr &= PAGE_MASK;
+
+	ret = get_user_pages_fast(addr, nr_pages, 0, pages);
+	if (ret < nr_pages) {
+		while (--ret >= 0)
+			put_page(pages[ret]);
+		written = -EFAULT;
+		goto out;
 	}
-	if (buf[cnt-1] != '\n') {
-		buf[cnt] = '\n';
-		buf[cnt+1] = '\0';
+
+	page1 = kmap_atomic(pages[0]);
+	if (nr_pages == 2)
+		page2 = kmap_atomic(pages[1]);
+
+	local_save_flags(irq_flags);
+	size = sizeof(*entry) + cnt + 2; /* possible \n added */
+	buffer = global_trace.buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
+					  irq_flags, preempt_count());
+	if (!event) {
+		/* Ring buffer disabled, return as if not open for write */
+		written = -EBADF;
+		goto out_unlock;
+	}
+
+	entry = ring_buffer_event_data(event);
+	entry->ip = _THIS_IP_;
+
+	if (nr_pages == 2) {
+		len = PAGE_SIZE - offset;
+		memcpy(&entry->buf, page1 + offset, len);
+		memcpy(&entry->buf[len], page2, cnt - len);
 	} else
-		buf[cnt] = '\0';
+		memcpy(&entry->buf, page1 + offset, cnt);
 
-	written = mark_printk("%s", buf);
-	kfree(buf);
-	*fpos += written;
+	if (entry->buf[cnt - 1] != '\n') {
+		entry->buf[cnt] = '\n';
+		entry->buf[cnt + 1] = '\0';
+	} else
+		entry->buf[cnt] = '\0';
 
-	/* don't tell userspace we wrote more - it might confuse them */
-	if (written > cnt)
-		written = cnt;
+	ring_buffer_unlock_commit(buffer, event);
+
+	written = cnt;
+
+	*fpos += written;
 
+ out_unlock:
+	if (nr_pages == 2)
+		kunmap_atomic(page2);
+	kunmap_atomic(page1);
+	while (nr_pages > 0)
+		put_page(pages[--nr_pages]);
+ out:
 	return written;
 }
 
@@ -3739,6 +3828,12 @@ static const struct file_operations tracing_entries_fops = {
 	.llseek		= generic_file_llseek,
 };
 
+static const struct file_operations tracing_total_entries_fops = {
+	.open		= tracing_open_generic,
+	.read		= tracing_total_entries_read,
+	.llseek		= generic_file_llseek,
+};
+
 static const struct file_operations tracing_free_buffer_fops = {
 	.write		= tracing_free_buffer_write,
 	.release	= tracing_free_buffer_release,
@@ -4026,6 +4121,8 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 	struct trace_array *tr = &global_trace;
 	struct trace_seq *s;
 	unsigned long cnt;
+	unsigned long long t;
+	unsigned long usec_rem;
 
 	s = kmalloc(sizeof(*s), GFP_KERNEL);
 	if (!s)
@@ -4042,6 +4139,17 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 	cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu);
 	trace_seq_printf(s, "commit overrun: %ld\n", cnt);
 
+	cnt = ring_buffer_bytes_cpu(tr->buffer, cpu);
+	trace_seq_printf(s, "bytes: %ld\n", cnt);
+
+	t = ns2usecs(ring_buffer_oldest_event_ts(tr->buffer, cpu));
+	usec_rem = do_div(t, USEC_PER_SEC);
+	trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n", t, usec_rem);
+
+	t = ns2usecs(ring_buffer_time_stamp(tr->buffer, cpu));
+	usec_rem = do_div(t, USEC_PER_SEC);
+	trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem);
+
 	count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
 
 	kfree(s);
@@ -4450,6 +4558,9 @@ static __init int tracer_init_debugfs(void)
 	trace_create_file("buffer_size_kb", 0644, d_tracer,
 			&global_trace, &tracing_entries_fops);
 
+	trace_create_file("buffer_total_size_kb", 0444, d_tracer,
+			&global_trace, &tracing_total_entries_fops);
+
 	trace_create_file("free_buffer", 0644, d_tracer,
 			&global_trace, &tracing_free_buffer_fops);
 
@@ -4566,6 +4677,12 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 
 	tracing_off();
 
+	/* Did function tracer already get disabled? */
+	if (ftrace_is_dead()) {
+		printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n");
+		printk("#          MAY BE MISSING FUNCTION EVENTS\n");
+	}
+
 	if (disable_tracing)
 		ftrace_kill();
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 616846bcfee..092e1f8d18d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -579,11 +579,13 @@ static inline int ftrace_trace_task(struct task_struct *task)
 
 	return test_tsk_trace_trace(task);
 }
+extern int ftrace_is_dead(void);
 #else
 static inline int ftrace_trace_task(struct task_struct *task)
 {
 	return 1;
 }
+static inline int ftrace_is_dead(void) { return 0; }
 #endif
 
 /*
@@ -761,16 +763,10 @@ struct filter_pred {
 	filter_pred_fn_t 	fn;
 	u64 			val;
 	struct regex		regex;
-	/*
-	 * Leaf nodes use field_name, ops is used by AND and OR
-	 * nodes. The field_name is always freed when freeing a pred.
-	 * We can overload field_name for ops and have it freed
-	 * as well.
-	 */
-	union {
-		char		*field_name;
-		unsigned short	*ops;
-	};
+	unsigned short		*ops;
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+	struct ftrace_event_field *field;
+#endif
 	int 			offset;
 	int 			not;
 	int 			op;
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 6302747a139..394783531cb 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -113,3 +113,15 @@ u64 notrace trace_clock_global(void)
 
 	return now;
 }
+
+static atomic64_t trace_counter;
+
+/*
+ * trace_clock_counter(): simply an atomic counter.
+ * Use the trace_counter "counter" for cases where you do not care
+ * about timings, but are interested in strict ordering.
+ */
+u64 notrace trace_clock_counter(void)
+{
+	return atomic64_add_return(1, &trace_counter);
+}
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 256764ecccd..816d3d07497 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -381,6 +381,63 @@ get_pred_parent(struct filter_pred *pred, struct filter_pred *preds,
 	return pred;
 }
 
+enum walk_return {
+	WALK_PRED_ABORT,
+	WALK_PRED_PARENT,
+	WALK_PRED_DEFAULT,
+};
+
+typedef int (*filter_pred_walkcb_t) (enum move_type move,
+				     struct filter_pred *pred,
+				     int *err, void *data);
+
+static int walk_pred_tree(struct filter_pred *preds,
+			  struct filter_pred *root,
+			  filter_pred_walkcb_t cb, void *data)
+{
+	struct filter_pred *pred = root;
+	enum move_type move = MOVE_DOWN;
+	int done = 0;
+
+	if  (!preds)
+		return -EINVAL;
+
+	do {
+		int err = 0, ret;
+
+		ret = cb(move, pred, &err, data);
+		if (ret == WALK_PRED_ABORT)
+			return err;
+		if (ret == WALK_PRED_PARENT)
+			goto get_parent;
+
+		switch (move) {
+		case MOVE_DOWN:
+			if (pred->left != FILTER_PRED_INVALID) {
+				pred = &preds[pred->left];
+				continue;
+			}
+			goto get_parent;
+		case MOVE_UP_FROM_LEFT:
+			pred = &preds[pred->right];
+			move = MOVE_DOWN;
+			continue;
+		case MOVE_UP_FROM_RIGHT:
+ get_parent:
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent,
+					       &move);
+			continue;
+		}
+		done = 1;
+	} while (!done);
+
+	/* We are fine. */
+	return 0;
+}
+
 /*
  * A series of AND or ORs where found together. Instead of
  * climbing up and down the tree branches, an array of the
@@ -410,99 +467,91 @@ static int process_ops(struct filter_pred *preds,
 
 	for (i = 0; i < op->val; i++) {
 		pred = &preds[op->ops[i]];
-		match = pred->fn(pred, rec);
+		if (!WARN_ON_ONCE(!pred->fn))
+			match = pred->fn(pred, rec);
 		if (!!match == type)
 			return match;
 	}
 	return match;
 }
 
+struct filter_match_preds_data {
+	struct filter_pred *preds;
+	int match;
+	void *rec;
+};
+
+static int filter_match_preds_cb(enum move_type move, struct filter_pred *pred,
+				 int *err, void *data)
+{
+	struct filter_match_preds_data *d = data;
+
+	*err = 0;
+	switch (move) {
+	case MOVE_DOWN:
+		/* only AND and OR have children */
+		if (pred->left != FILTER_PRED_INVALID) {
+			/* If ops is set, then it was folded. */
+			if (!pred->ops)
+				return WALK_PRED_DEFAULT;
+			/* We can treat folded ops as a leaf node */
+			d->match = process_ops(d->preds, pred, d->rec);
+		} else {
+			if (!WARN_ON_ONCE(!pred->fn))
+				d->match = pred->fn(pred, d->rec);
+		}
+
+		return WALK_PRED_PARENT;
+	case MOVE_UP_FROM_LEFT:
+		/*
+		 * Check for short circuits.
+		 *
+		 * Optimization: !!match == (pred->op == OP_OR)
+		 *   is the same as:
+		 * if ((match && pred->op == OP_OR) ||
+		 *     (!match && pred->op == OP_AND))
+		 */
+		if (!!d->match == (pred->op == OP_OR))
+			return WALK_PRED_PARENT;
+		break;
+	case MOVE_UP_FROM_RIGHT:
+		break;
+	}
+
+	return WALK_PRED_DEFAULT;
+}
+
 /* return 1 if event matches, 0 otherwise (discard) */
 int filter_match_preds(struct event_filter *filter, void *rec)
 {
-	int match = -1;
-	enum move_type move = MOVE_DOWN;
 	struct filter_pred *preds;
-	struct filter_pred *pred;
 	struct filter_pred *root;
-	int n_preds;
-	int done = 0;
+	struct filter_match_preds_data data = {
+		/* match is currently meaningless */
+		.match = -1,
+		.rec   = rec,
+	};
+	int n_preds, ret;
 
 	/* no filter is considered a match */
 	if (!filter)
 		return 1;
 
 	n_preds = filter->n_preds;
-
 	if (!n_preds)
 		return 1;
 
 	/*
 	 * n_preds, root and filter->preds are protect with preemption disabled.
 	 */
-	preds = rcu_dereference_sched(filter->preds);
 	root = rcu_dereference_sched(filter->root);
 	if (!root)
 		return 1;
 
-	pred = root;
-
-	/* match is currently meaningless */
-	match = -1;
-
-	do {
-		switch (move) {
-		case MOVE_DOWN:
-			/* only AND and OR have children */
-			if (pred->left != FILTER_PRED_INVALID) {
-				/* If ops is set, then it was folded. */
-				if (!pred->ops) {
-					/* keep going to down the left side */
-					pred = &preds[pred->left];
-					continue;
-				}
-				/* We can treat folded ops as a leaf node */
-				match = process_ops(preds, pred, rec);
-			} else
-				match = pred->fn(pred, rec);
-			/* If this pred is the only pred */
-			if (pred == root)
-				break;
-			pred = get_pred_parent(pred, preds,
-					       pred->parent, &move);
-			continue;
-		case MOVE_UP_FROM_LEFT:
-			/*
-			 * Check for short circuits.
-			 *
-			 * Optimization: !!match == (pred->op == OP_OR)
-			 *   is the same as:
-			 * if ((match && pred->op == OP_OR) ||
-			 *     (!match && pred->op == OP_AND))
-			 */
-			if (!!match == (pred->op == OP_OR)) {
-				if (pred == root)
-					break;
-				pred = get_pred_parent(pred, preds,
-						       pred->parent, &move);
-				continue;
-			}
-			/* now go down the right side of the tree. */
-			pred = &preds[pred->right];
-			move = MOVE_DOWN;
-			continue;
-		case MOVE_UP_FROM_RIGHT:
-			/* We finished this equation. */
-			if (pred == root)
-				break;
-			pred = get_pred_parent(pred, preds,
-					       pred->parent, &move);
-			continue;
-		}
-		done = 1;
-	} while (!done);
-
-	return match;
+	data.preds = preds = rcu_dereference_sched(filter->preds);
+	ret = walk_pred_tree(preds, root, filter_match_preds_cb, &data);
+	WARN_ON(ret);
+	return data.match;
 }
 EXPORT_SYMBOL_GPL(filter_match_preds);
 
@@ -628,22 +677,6 @@ find_event_field(struct ftrace_event_call *call, char *name)
 	return __find_event_field(head, name);
 }
 
-static void filter_free_pred(struct filter_pred *pred)
-{
-	if (!pred)
-		return;
-
-	kfree(pred->field_name);
-	kfree(pred);
-}
-
-static void filter_clear_pred(struct filter_pred *pred)
-{
-	kfree(pred->field_name);
-	pred->field_name = NULL;
-	pred->regex.len = 0;
-}
-
 static int __alloc_pred_stack(struct pred_stack *stack, int n_preds)
 {
 	stack->preds = kzalloc(sizeof(*stack->preds)*(n_preds + 1), GFP_KERNEL);
@@ -689,20 +722,13 @@ __pop_pred_stack(struct pred_stack *stack)
 static int filter_set_pred(struct event_filter *filter,
 			   int idx,
 			   struct pred_stack *stack,
-			   struct filter_pred *src,
-			   filter_pred_fn_t fn)
+			   struct filter_pred *src)
 {
 	struct filter_pred *dest = &filter->preds[idx];
 	struct filter_pred *left;
 	struct filter_pred *right;
 
 	*dest = *src;
-	if (src->field_name) {
-		dest->field_name = kstrdup(src->field_name, GFP_KERNEL);
-		if (!dest->field_name)
-			return -ENOMEM;
-	}
-	dest->fn = fn;
 	dest->index = idx;
 
 	if (dest->op == OP_OR || dest->op == OP_AND) {
@@ -743,11 +769,7 @@ static int filter_set_pred(struct event_filter *filter,
 
 static void __free_preds(struct event_filter *filter)
 {
-	int i;
-
 	if (filter->preds) {
-		for (i = 0; i < filter->a_preds; i++)
-			kfree(filter->preds[i].field_name);
 		kfree(filter->preds);
 		filter->preds = NULL;
 	}
@@ -840,23 +862,19 @@ static void filter_free_subsystem_filters(struct event_subsystem *system)
 	}
 }
 
-static int filter_add_pred_fn(struct filter_parse_state *ps,
-			      struct ftrace_event_call *call,
-			      struct event_filter *filter,
-			      struct filter_pred *pred,
-			      struct pred_stack *stack,
-			      filter_pred_fn_t fn)
+static int filter_add_pred(struct filter_parse_state *ps,
+			   struct event_filter *filter,
+			   struct filter_pred *pred,
+			   struct pred_stack *stack)
 {
-	int idx, err;
+	int err;
 
 	if (WARN_ON(filter->n_preds == filter->a_preds)) {
 		parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
 		return -ENOSPC;
 	}
 
-	idx = filter->n_preds;
-	filter_clear_pred(&filter->preds[idx]);
-	err = filter_set_pred(filter, idx, stack, pred, fn);
+	err = filter_set_pred(filter, filter->n_preds, stack, pred);
 	if (err)
 		return err;
 
@@ -937,31 +955,15 @@ static filter_pred_fn_t select_comparison_fn(int op, int field_size,
 	return fn;
 }
 
-static int filter_add_pred(struct filter_parse_state *ps,
-			   struct ftrace_event_call *call,
-			   struct event_filter *filter,
-			   struct filter_pred *pred,
-			   struct pred_stack *stack,
-			   bool dry_run)
+static int init_pred(struct filter_parse_state *ps,
+		     struct ftrace_event_field *field,
+		     struct filter_pred *pred)
+
 {
-	struct ftrace_event_field *field;
-	filter_pred_fn_t fn;
+	filter_pred_fn_t fn = filter_pred_none;
 	unsigned long long val;
 	int ret;
 
-	fn = pred->fn = filter_pred_none;
-
-	if (pred->op == OP_AND)
-		goto add_pred_fn;
-	else if (pred->op == OP_OR)
-		goto add_pred_fn;
-
-	field = find_event_field(call, pred->field_name);
-	if (!field) {
-		parse_error(ps, FILT_ERR_FIELD_NOT_FOUND, 0);
-		return -EINVAL;
-	}
-
 	pred->offset = field->offset;
 
 	if (!is_legal_op(field, pred->op)) {
@@ -1001,9 +1003,7 @@ static int filter_add_pred(struct filter_parse_state *ps,
 	if (pred->op == OP_NE)
 		pred->not = 1;
 
-add_pred_fn:
-	if (!dry_run)
-		return filter_add_pred_fn(ps, call, filter, pred, stack, fn);
+	pred->fn = fn;
 	return 0;
 }
 
@@ -1302,39 +1302,37 @@ parse_operand:
 	return 0;
 }
 
-static struct filter_pred *create_pred(int op, char *operand1, char *operand2)
+static struct filter_pred *create_pred(struct filter_parse_state *ps,
+				       struct ftrace_event_call *call,
+				       int op, char *operand1, char *operand2)
 {
-	struct filter_pred *pred;
+	struct ftrace_event_field *field;
+	static struct filter_pred pred;
 
-	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
-	if (!pred)
-		return NULL;
+	memset(&pred, 0, sizeof(pred));
+	pred.op = op;
 
-	pred->field_name = kstrdup(operand1, GFP_KERNEL);
-	if (!pred->field_name) {
-		kfree(pred);
+	if (op == OP_AND || op == OP_OR)
+		return &pred;
+
+	if (!operand1 || !operand2) {
+		parse_error(ps, FILT_ERR_MISSING_FIELD, 0);
 		return NULL;
 	}
 
-	strcpy(pred->regex.pattern, operand2);
-	pred->regex.len = strlen(pred->regex.pattern);
-
-	pred->op = op;
-
-	return pred;
-}
-
-static struct filter_pred *create_logical_pred(int op)
-{
-	struct filter_pred *pred;
-
-	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
-	if (!pred)
+	field = find_event_field(call, operand1);
+	if (!field) {
+		parse_error(ps, FILT_ERR_FIELD_NOT_FOUND, 0);
 		return NULL;
+	}
 
-	pred->op = op;
+	strcpy(pred.regex.pattern, operand2);
+	pred.regex.len = strlen(pred.regex.pattern);
 
-	return pred;
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+	pred.field = field;
+#endif
+	return init_pred(ps, field, &pred) ? NULL : &pred;
 }
 
 static int check_preds(struct filter_parse_state *ps)
@@ -1375,6 +1373,23 @@ static int count_preds(struct filter_parse_state *ps)
 	return n_preds;
 }
 
+struct check_pred_data {
+	int count;
+	int max;
+};
+
+static int check_pred_tree_cb(enum move_type move, struct filter_pred *pred,
+			      int *err, void *data)
+{
+	struct check_pred_data *d = data;
+
+	if (WARN_ON(d->count++ > d->max)) {
+		*err = -EINVAL;
+		return WALK_PRED_ABORT;
+	}
+	return WALK_PRED_DEFAULT;
+}
+
 /*
  * The tree is walked at filtering of an event. If the tree is not correctly
  * built, it may cause an infinite loop. Check here that the tree does
@@ -1383,107 +1398,76 @@ static int count_preds(struct filter_parse_state *ps)
 static int check_pred_tree(struct event_filter *filter,
 			   struct filter_pred *root)
 {
-	struct filter_pred *preds;
-	struct filter_pred *pred;
-	enum move_type move = MOVE_DOWN;
-	int count = 0;
-	int done = 0;
-	int max;
-
-	/*
-	 * The max that we can hit a node is three times.
-	 * Once going down, once coming up from left, and
-	 * once coming up from right. This is more than enough
-	 * since leafs are only hit a single time.
-	 */
-	max = 3 * filter->n_preds;
+	struct check_pred_data data = {
+		/*
+		 * The max that we can hit a node is three times.
+		 * Once going down, once coming up from left, and
+		 * once coming up from right. This is more than enough
+		 * since leafs are only hit a single time.
+		 */
+		.max   = 3 * filter->n_preds,
+		.count = 0,
+	};
 
-	preds = filter->preds;
-	if  (!preds)
-		return -EINVAL;
-	pred = root;
+	return walk_pred_tree(filter->preds, root,
+			      check_pred_tree_cb, &data);
+}
 
-	do {
-		if (WARN_ON(count++ > max))
-			return -EINVAL;
+static int count_leafs_cb(enum move_type move, struct filter_pred *pred,
+			  int *err, void *data)
+{
+	int *count = data;
 
-		switch (move) {
-		case MOVE_DOWN:
-			if (pred->left != FILTER_PRED_INVALID) {
-				pred = &preds[pred->left];
-				continue;
-			}
-			/* A leaf at the root is just a leaf in the tree */
-			if (pred == root)
-				break;
-			pred = get_pred_parent(pred, preds,
-					       pred->parent, &move);
-			continue;
-		case MOVE_UP_FROM_LEFT:
-			pred = &preds[pred->right];
-			move = MOVE_DOWN;
-			continue;
-		case MOVE_UP_FROM_RIGHT:
-			if (pred == root)
-				break;
-			pred = get_pred_parent(pred, preds,