Merge tag 'trace-fixes-3.11-rc2' of...

Merge tag 'trace-fixes-3.11-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing fixes from Steven Rostedt:
 "Oleg is working on fixing a very tight race between opening a event
  file and deleting that event at the same time (both must be done as
  root).

  I also found a bug while testing Oleg's patches which has to do with a
  race with kprobes using the function tracer.

  There's also a deadlock fix that was introduced with the previous
  fixes"

* tag 'trace-fixes-3.11-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
  tracing: Remove locking trace_types_lock from tracing_reset_all_online_cpus()
  ftrace: Add check for NULL regs if ops has SAVE_REGS set
  tracing: Kill trace_cpu struct/members
  tracing: Change tracing_fops/snapshot_fops to rely on tracing_get_cpu()
  tracing: Change tracing_entries_fops to rely on tracing_get_cpu()
  tracing: Change tracing_stats_fops to rely on tracing_get_cpu()
  tracing: Change tracing_buffers_fops to rely on tracing_get_cpu()
  tracing: Change tracing_pipe_fops() to rely on tracing_get_cpu()
  tracing: Introduce trace_create_cpu_file() and tracing_get_cpu()

kernel/trace/ftrace.c

@@ -1441,12 +1441,22 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
  * the hashes are freed with call_rcu_sched().
  */
 static int
-ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
+ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 {
 	struct ftrace_hash *filter_hash;
 	struct ftrace_hash *notrace_hash;
 	int ret;
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+	/*
+	 * There's a small race when adding ops that the ftrace handler
+	 * that wants regs, may be called without them. We can not
+	 * allow that handler to be called if regs is NULL.
+	 */
+	if (regs == NULL && (ops->flags & FTRACE_OPS_FL_SAVE_REGS))
+		return 0;
+#endif
+
 	filter_hash = rcu_dereference_raw_notrace(ops->filter_hash);
 	notrace_hash = rcu_dereference_raw_notrace(ops->notrace_hash);
 
@@ -4218,7 +4228,7 @@ static inline void ftrace_startup_enable(int command) { }
 # define ftrace_shutdown_sysctl()	do { } while (0)
 
 static inline int
-ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
+ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 {
 	return 1;
 }
@@ -4241,7 +4251,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
 	do_for_each_ftrace_op(op, ftrace_control_list) {
 		if (!(op->flags & FTRACE_OPS_FL_STUB) &&
 		    !ftrace_function_local_disabled(op) &&
-		    ftrace_ops_test(op, ip))
+		    ftrace_ops_test(op, ip, regs))
 			op->func(ip, parent_ip, op, regs);
 	} while_for_each_ftrace_op(op);
 	trace_recursion_clear(TRACE_CONTROL_BIT);
@@ -4274,7 +4284,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 	 */
 	preempt_disable_notrace();
 	do_for_each_ftrace_op(op, ftrace_ops_list) {
-		if (ftrace_ops_test(op, ip))
+		if (ftrace_ops_test(op, ip, regs))
 			op->func(ip, parent_ip, op, regs);
 	} while_for_each_ftrace_op(op);
 	preempt_enable_notrace();

kernel/trace/trace.c

@@ -1224,18 +1224,17 @@ void tracing_reset_current(int cpu)
 	tracing_reset(&global_trace.trace_buffer, cpu);
 }
 
+/* Must have trace_types_lock held */
 void tracing_reset_all_online_cpus(void)
 {
 	struct trace_array *tr;
 
-	mutex_lock(&trace_types_lock);
 	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
 		tracing_reset_online_cpus(&tr->trace_buffer);
 #ifdef CONFIG_TRACER_MAX_TRACE
 		tracing_reset_online_cpus(&tr->max_buffer);
 #endif
 	}
-	mutex_unlock(&trace_types_lock);
 }
 
 #define SAVED_CMDLINES 128
@@ -2843,6 +2842,17 @@ static int s_show(struct seq_file *m, void *v)
 	return 0;
 }
 
+/*
+ * Should be used after trace_array_get(), trace_types_lock
+ * ensures that i_cdev was already initialized.
+ */
+static inline int tracing_get_cpu(struct inode *inode)
+{
+	if (inode->i_cdev) /* See trace_create_cpu_file() */
+		return (long)inode->i_cdev - 1;
+	return RING_BUFFER_ALL_CPUS;
+}
+
 static const struct seq_operations tracer_seq_ops = {
 	.start		= s_start,
 	.next		= s_next,
@@ -2851,9 +2861,9 @@ static const struct seq_operations tracer_seq_ops = {
 };
 
 static struct trace_iterator *
-__tracing_open(struct trace_array *tr, struct trace_cpu *tc,
-	       struct inode *inode, struct file *file, bool snapshot)
+__tracing_open(struct inode *inode, struct file *file, bool snapshot)
 {
+	struct trace_array *tr = inode->i_private;
 	struct trace_iterator *iter;
 	int cpu;
 
@@ -2894,8 +2904,8 @@ __tracing_open(struct trace_array *tr, struct trace_cpu *tc,
 		iter->trace_buffer = &tr->trace_buffer;
 	iter->snapshot = snapshot;
 	iter->pos = -1;
+	iter->cpu_file = tracing_get_cpu(inode);
 	mutex_init(&iter->mutex);
-	iter->cpu_file = tc->cpu;
 
 	/* Notify the tracer early; before we stop tracing. */
 	if (iter->trace && iter->trace->open)
@@ -2971,44 +2981,22 @@ static int tracing_open_generic_tr(struct inode *inode, struct file *filp)
 	filp->private_data = inode->i_private;
 
 	return 0;
-	
-}
-
-static int tracing_open_generic_tc(struct inode *inode, struct file *filp)
-{
-	struct trace_cpu *tc = inode->i_private;
-	struct trace_array *tr = tc->tr;
-
-	if (tracing_disabled)
-		return -ENODEV;
-
-	if (trace_array_get(tr) < 0)
-		return -ENODEV;
-
-	filp->private_data = inode->i_private;
-
-	return 0;
-	
 }
 
 static int tracing_release(struct inode *inode, struct file *file)
 {
+	struct trace_array *tr = inode->i_private;
 	struct seq_file *m = file->private_data;
 	struct trace_iterator *iter;
-	struct trace_array *tr;
 	int cpu;
 
-	/* Writes do not use seq_file, need to grab tr from inode */
 	if (!(file->f_mode & FMODE_READ)) {
-		struct trace_cpu *tc = inode->i_private;
-
-		trace_array_put(tc->tr);
+		trace_array_put(tr);
 		return 0;
 	}
 
+	/* Writes do not use seq_file */
 	iter = m->private;
-	tr = iter->tr;
-
 	mutex_lock(&trace_types_lock);
 
 	for_each_tracing_cpu(cpu) {
@@ -3044,15 +3032,6 @@ static int tracing_release_generic_tr(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static int tracing_release_generic_tc(struct inode *inode, struct file *file)
-{
-	struct trace_cpu *tc = inode->i_private;
-	struct trace_array *tr = tc->tr;
-
-	trace_array_put(tr);
-	return 0;
-}
-
 static int tracing_single_release_tr(struct inode *inode, struct file *file)
 {
 	struct trace_array *tr = inode->i_private;
@@ -3064,8 +3043,7 @@ static int tracing_single_release_tr(struct inode *inode, struct file *file)
 
 static int tracing_open(struct inode *inode, struct file *file)
 {
-	struct trace_cpu *tc = inode->i_private;
-	struct trace_array *tr = tc->tr;
+	struct trace_array *tr = inode->i_private;
 	struct trace_iterator *iter;
 	int ret = 0;
 
@@ -3073,16 +3051,17 @@ static int tracing_open(struct inode *inode, struct file *file)
 		return -ENODEV;
 
 	/* If this file was open for write, then erase contents */
-	if ((file->f_mode & FMODE_WRITE) &&
-	    (file->f_flags & O_TRUNC)) {
-		if (tc->cpu == RING_BUFFER_ALL_CPUS)
+	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
+		int cpu = tracing_get_cpu(inode);
+
+		if (cpu == RING_BUFFER_ALL_CPUS)
 			tracing_reset_online_cpus(&tr->trace_buffer);
 		else
-			tracing_reset(&tr->trace_buffer, tc->cpu);
+			tracing_reset(&tr->trace_buffer, cpu);
 	}
 
 	if (file->f_mode & FMODE_READ) {
-		iter = __tracing_open(tr, tc, inode, file, false);
+		iter = __tracing_open(inode, file, false);
 		if (IS_ERR(iter))
 			ret = PTR_ERR(iter);
 		else if (trace_flags & TRACE_ITER_LATENCY_FMT)
@@ -3948,8 +3927,7 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf,
 
 static int tracing_open_pipe(struct inode *inode, struct file *filp)
 {
-	struct trace_cpu *tc = inode->i_private;
-	struct trace_array *tr = tc->tr;
+	struct trace_array *tr = inode->i_private;
 	struct trace_iterator *iter;
 	int ret = 0;
 
@@ -3995,9 +3973,9 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	if (trace_clocks[tr->clock_id].in_ns)
 		iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
 
-	iter->cpu_file = tc->cpu;
-	iter->tr = tc->tr;
-	iter->trace_buffer = &tc->tr->trace_buffer;
+	iter->tr = tr;
+	iter->trace_buffer = &tr->trace_buffer;
+	iter->cpu_file = tracing_get_cpu(inode);
 	mutex_init(&iter->mutex);
 	filp->private_data = iter;
 
@@ -4020,8 +3998,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 static int tracing_release_pipe(struct inode *inode, struct file *file)
 {
 	struct trace_iterator *iter = file->private_data;
-	struct trace_cpu *tc = inode->i_private;
-	struct trace_array *tr = tc->tr;
+	struct trace_array *tr = inode->i_private;
 
 	mutex_lock(&trace_types_lock);
 
@@ -4374,15 +4351,16 @@ static ssize_t
 tracing_entries_read(struct file *filp, char __user *ubuf,
 		     size_t cnt, loff_t *ppos)
 {
-	struct trace_cpu *tc = filp->private_data;
-	struct trace_array *tr = tc->tr;
+	struct inode *inode = file_inode(filp);
+	struct trace_array *tr = inode->i_private;
+	int cpu = tracing_get_cpu(inode);
 	char buf[64];
 	int r = 0;
 	ssize_t ret;
 
 	mutex_lock(&trace_types_lock);
 
-	if (tc->cpu == RING_BUFFER_ALL_CPUS) {
+	if (cpu == RING_BUFFER_ALL_CPUS) {
 		int cpu, buf_size_same;
 		unsigned long size;
 
@@ -4409,7 +4387,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf,
 		} else
 			r = sprintf(buf, "X\n");
 	} else
-		r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, tc->cpu)->entries >> 10);
+		r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10);
 
 	mutex_unlock(&trace_types_lock);
 
@@ -4421,7 +4399,8 @@ static ssize_t
 tracing_entries_write(struct file *filp, const char __user *ubuf,
 		      size_t cnt, loff_t *ppos)
 {
-	struct trace_cpu *tc = filp->private_data;
+	struct inode *inode = file_inode(filp);
+	struct trace_array *tr = inode->i_private;
 	unsigned long val;
 	int ret;
 
@@ -4435,8 +4414,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 
 	/* value is in KB */
 	val <<= 10;
-
-	ret = tracing_resize_ring_buffer(tc->tr, val, tc->cpu);
+	ret = tracing_resize_ring_buffer(tr, val, tracing_get_cpu(inode));
 	if (ret < 0)
 		return ret;
 
@@ -4697,8 +4675,7 @@ struct ftrace_buffer_info {
 #ifdef CONFIG_TRACER_SNAPSHOT
 static int tracing_snapshot_open(struct inode *inode, struct file *file)
 {
-	struct trace_cpu *tc = inode->i_private;
-	struct trace_array *tr = tc->tr;
+	struct trace_array *tr = inode->i_private;
 	struct trace_iterator *iter;
 	struct seq_file *m;
 	int ret = 0;
@@ -4707,7 +4684,7 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file)
 		return -ENODEV;
 
 	if (file->f_mode & FMODE_READ) {
-		iter = __tracing_open(tr, tc, inode, file, true);
+		iter = __tracing_open(inode, file, true);
 		if (IS_ERR(iter))
 			ret = PTR_ERR(iter);
 	} else {
@@ -4724,8 +4701,8 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file)
 		ret = 0;
 
 		iter->tr = tr;
-		iter->trace_buffer = &tc->tr->max_buffer;
-		iter->cpu_file = tc->cpu;
+		iter->trace_buffer = &tr->max_buffer;
+		iter->cpu_file = tracing_get_cpu(inode);
 		m->private = iter;
 		file->private_data = m;
 	}
@@ -4884,11 +4861,11 @@ static const struct file_operations tracing_pipe_fops = {
 };
 
 static const struct file_operations tracing_entries_fops = {
-	.open		= tracing_open_generic_tc,
+	.open		= tracing_open_generic_tr,
 	.read		= tracing_entries_read,
 	.write		= tracing_entries_write,
 	.llseek		= generic_file_llseek,
-	.release	= tracing_release_generic_tc,
+	.release	= tracing_release_generic_tr,
 };
 
 static const struct file_operations tracing_total_entries_fops = {
@@ -4940,8 +4917,7 @@ static const struct file_operations snapshot_raw_fops = {
 
 static int tracing_buffers_open(struct inode *inode, struct file *filp)
 {
-	struct trace_cpu *tc = inode->i_private;
-	struct trace_array *tr = tc->tr;
+	struct trace_array *tr = inode->i_private;
 	struct ftrace_buffer_info *info;
 	int ret;
 
@@ -4960,7 +4936,7 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
 	mutex_lock(&trace_types_lock);
 
 	info->iter.tr		= tr;
-	info->iter.cpu_file	= tc->cpu;
+	info->iter.cpu_file	= tracing_get_cpu(inode);
 	info->iter.trace	= tr->current_trace;
 	info->iter.trace_buffer = &tr->trace_buffer;
 	info->spare		= NULL;
@@ -5277,14 +5253,14 @@ static ssize_t
 tracing_stats_read(struct file *filp, char __user *ubuf,
 		   size_t count, loff_t *ppos)
 {
-	struct trace_cpu *tc = filp->private_data;
-	struct trace_array *tr = tc->tr;
+	struct inode *inode = file_inode(filp);
+	struct trace_array *tr = inode->i_private;
 	struct trace_buffer *trace_buf = &tr->trace_buffer;
+	int cpu = tracing_get_cpu(inode);
 	struct trace_seq *s;
 	unsigned long cnt;
 	unsigned long long t;
 	unsigned long usec_rem;
-	int cpu = tc->cpu;
 
 	s = kmalloc(sizeof(*s), GFP_KERNEL);
 	if (!s)
@@ -5337,10 +5313,10 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 }
 
 static const struct file_operations tracing_stats_fops = {
-	.open		= tracing_open_generic_tc,
+	.open		= tracing_open_generic_tr,
 	.read		= tracing_stats_read,
 	.llseek		= generic_file_llseek,
-	.release	= tracing_release_generic_tc,
+	.release	= tracing_release_generic_tr,
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -5529,10 +5505,20 @@ static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu)
 	return tr->percpu_dir;
 }
 
+static struct dentry *
+trace_create_cpu_file(const char *name, umode_t mode, struct dentry *parent,
+		      void *data, long cpu, const struct file_operations *fops)
+{
+	struct dentry *ret = trace_create_file(name, mode, parent, data, fops);
+
+	if (ret) /* See tracing_get_cpu() */
+		ret->d_inode->i_cdev = (void *)(cpu + 1);
+	return ret;
+}
+
 static void
 tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
 {
-	struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, cpu);
 	struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu);
 	struct dentry *d_cpu;
 	char cpu_dir[30]; /* 30 characters should be more than enough */
@@ -5548,28 +5534,28 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
 	}
 
 	/* per cpu trace_pipe */
-	trace_create_file("trace_pipe", 0444, d_cpu,
-			(void *)&data->trace_cpu, &tracing_pipe_fops);
+	trace_create_cpu_file("trace_pipe", 0444, d_cpu,
+				tr, cpu, &tracing_pipe_fops);
 
 	/* per cpu trace */
-	trace_create_file("trace", 0644, d_cpu,
-			(void *)&data->trace_cpu, &tracing_fops);
+	trace_create_cpu_file("trace", 0644, d_cpu,
+				tr, cpu, &tracing_fops);
 
-	trace_create_file("trace_pipe_raw", 0444, d_cpu,
-			(void *)&data->trace_cpu, &tracing_buffers_fops);
+	trace_create_cpu_file("trace_pipe_raw", 0444, d_cpu,
+				tr, cpu, &tracing_buffers_fops);
 
-	trace_create_file("stats", 0444, d_cpu,
-			(void *)&data->trace_cpu, &tracing_stats_fops);
+	trace_create_cpu_file("stats", 0444, d_cpu,
+				tr, cpu, &tracing_stats_fops);
 
-	trace_create_file("buffer_size_kb", 0444, d_cpu,
-			(void *)&data->trace_cpu, &tracing_entries_fops);
+	trace_create_cpu_file("buffer_size_kb", 0444, d_cpu,
+				tr, cpu, &tracing_entries_fops);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
-	trace_create_file("snapshot", 0644, d_cpu,
-			  (void *)&data->trace_cpu, &snapshot_fops);
+	trace_create_cpu_file("snapshot", 0644, d_cpu,
+				tr, cpu, &snapshot_fops);
 
-	trace_create_file("snapshot_raw", 0444, d_cpu,
-			(void *)&data->trace_cpu, &snapshot_raw_fops);
+	trace_create_cpu_file("snapshot_raw", 0444, d_cpu,
+				tr, cpu, &snapshot_raw_fops);
 #endif
 }
 
@@ -5878,17 +5864,6 @@ struct dentry *trace_instance_dir;
 static void
 init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer);
 
-static void init_trace_buffers(struct trace_array *tr, struct trace_buffer *buf)
-{
-	int cpu;
-
-	for_each_tracing_cpu(cpu) {
-		memset(per_cpu_ptr(buf->data, cpu), 0, sizeof(struct trace_array_cpu));
-		per_cpu_ptr(buf->data, cpu)->trace_cpu.cpu = cpu;
-		per_cpu_ptr(buf->data, cpu)->trace_cpu.tr = tr;
-	}
-}
-
 static int
 allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size)
 {
@@ -5906,8 +5881,6 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
 		return -ENOMEM;
 	}
 
-	init_trace_buffers(tr, buf);
-
 	/* Allocate the first page for all buffers */
 	set_buffer_entries(&tr->trace_buffer,
 			   ring_buffer_size(tr->trace_buffer.buffer, 0));
@@ -5974,10 +5947,6 @@ static int new_instance_create(const char *name)
 	if (allocate_trace_buffers(tr, trace_buf_size) < 0)
 		goto out_free_tr;
 
-	/* Holder for file callbacks */
-	tr->trace_cpu.cpu = RING_BUFFER_ALL_CPUS;
-	tr->trace_cpu.tr = tr;
-
 	tr->dir = debugfs_create_dir(name, trace_instance_dir);
 	if (!tr->dir)
 		goto out_free_tr;
@@ -6132,13 +6101,13 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
 			  tr, &tracing_iter_fops);
 
 	trace_create_file("trace", 0644, d_tracer,
-			(void *)&tr->trace_cpu, &tracing_fops);
+			  tr, &tracing_fops);
 
 	trace_create_file("trace_pipe", 0444, d_tracer,
-			(void *)&tr->trace_cpu, &tracing_pipe_fops);
+			  tr, &tracing_pipe_fops);
 
 	trace_create_file("buffer_size_kb", 0644, d_tracer,
-			(void *)&tr->trace_cpu, &tracing_entries_fops);
+			  tr, &tracing_entries_fops);
 
 	trace_create_file("buffer_total_size_kb", 0444, d_tracer,
 			  tr, &tracing_total_entries_fops);
@@ -6153,11 +6122,11 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
 			  &trace_clock_fops);
 
 	trace_create_file("tracing_on", 0644, d_tracer,
-			    tr, &rb_simple_fops);
+			  tr, &rb_simple_fops);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
 	trace_create_file("snapshot", 0644, d_tracer,
-			  (void *)&tr->trace_cpu, &snapshot_fops);
+			  tr, &snapshot_fops);
 #endif
 
 	for_each_tracing_cpu(cpu)
@@ -6451,10 +6420,6 @@ __init static int tracer_alloc_buffers(void)
 
 	global_trace.flags = TRACE_ARRAY_FL_GLOBAL;
 
-	/* Holder for file callbacks */
-	global_trace.trace_cpu.cpu = RING_BUFFER_ALL_CPUS;
-	global_trace.trace_cpu.tr = &global_trace;
-
 	INIT_LIST_HEAD(&global_trace.systems);
 	INIT_LIST_HEAD(&global_trace.events);
 	list_add(&global_trace.list, &ftrace_trace_arrays);

kernel/trace/trace.h

@@ -130,19 +130,12 @@ enum trace_flag_type {
 
 struct trace_array;
 
-struct trace_cpu {
-	struct trace_array	*tr;
-	struct dentry		*dir;
-	int			cpu;
-};
-
 /*
  * The CPU trace array - it consists of thousands of trace entries
  * plus some other descriptor data: (for example which task started
  * the trace, etc.)
  */
 struct trace_array_cpu {
-	struct trace_cpu	trace_cpu;
 	atomic_t		disabled;
 	void			*buffer_page;	/* ring buffer spare */
 
@@ -196,7 +189,6 @@ struct trace_array {
 	bool			allocated_snapshot;
 #endif
 	int			buffer_disabled;
-	struct trace_cpu	trace_cpu;	/* place holder */
 #ifdef CONFIG_FTRACE_SYSCALLS
 	int			sys_refcount_enter;
 	int			sys_refcount_exit;