Merge tag 'trace-3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "Along with the usual minor fixes and clean ups there are a few major
  changes with this pull request.

   1) Multiple buffers for the ftrace facility

  This feature has been requested by many people over the last few
  years.  I even heard that Google was about to implement it themselves.
  I finally had time and cleaned up the code such that you can now
  create multiple instances of the ftrace buffer and have different
  events go to different buffers.  This way, a low frequency event will
  not be lost in the noise of a high frequency event.

  Note, currently only events can go to different buffers, the tracers
  (ie function, function_graph and the latency tracers) still can only
  be written to the main buffer.

   2) The function tracer triggers have now been extended.

  The function tracer had two triggers.  One to enable tracing when a
  function is hit, and one to disable tracing.  Now you can record a
  stack trace on a single (or many) function(s), take a snapshot of the
  buffer (copy it to the snapshot buffer), and you can enable or disable
  an event to be traced when a function is hit.

   3) A perf clock has been added.

  A "perf" clock can be chosen to be used when tracing.  This will cause
  ftrace to use the same clock as perf uses, and hopefully this will
  make it easier to interleave the perf and ftrace data for analysis."

* tag 'trace-3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (82 commits)
  tracepoints: Prevent null probe from being added
  tracing: Compare to 1 instead of zero for is_signed_type()
  tracing: Remove obsolete macro guard _TRACE_PROFILE_INIT
  ftrace: Get rid of ftrace_profile_bits
  tracing: Check return value of tracing_init_dentry()
  tracing: Get rid of unneeded key calculation in ftrace_hash_move()
  tracing: Reset ftrace_graph_filter_enabled if count is zero
  tracing: Fix off-by-one on allocating stat->pages
  kernel: tracing: Use strlcpy instead of strncpy
  tracing: Update debugfs README file
  tracing: Fix ftrace_dump()
  tracing: Rename trace_event_mutex to trace_event_sem
  tracing: Fix comment about prefix in arch_syscall_match_sym_name()
  tracing: Convert trace_destroy_fields() to static
  tracing: Move find_event_field() into trace_events.c
  tracing: Use TRACE_MAX_PRINT instead of constant
  tracing: Use pr_warn_once instead of open coded implementation
  ring-buffer: Add ring buffer startup selftest
  tracing: Bring Documentation/trace/ftrace.txt up to date
  tracing: Add "perf" trace_clock
  ...

Conflicts:
	kernel/trace/ftrace.c
	kernel/trace/trace.c

1 files changed, 69 insertions, 29 deletions

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b3fde6d7b7f..8a5c017bb50 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -486,7 +486,6 @@ struct ftrace_profile_stat {
 #define PROFILES_PER_PAGE					\
 	(PROFILE_RECORDS_SIZE / sizeof(struct ftrace_profile))
 
-static int ftrace_profile_bits __read_mostly;
 static int ftrace_profile_enabled __read_mostly;
 
 /* ftrace_profile_lock - synchronize the enable and disable of the profiler */
@@ -494,7 +493,8 @@ static DEFINE_MUTEX(ftrace_profile_lock);
 
 static DEFINE_PER_CPU(struct ftrace_profile_stat, ftrace_profile_stats);
 
-#define FTRACE_PROFILE_HASH_SIZE 1024 /* must be power of 2 */
+#define FTRACE_PROFILE_HASH_BITS 10
+#define FTRACE_PROFILE_HASH_SIZE (1 << FTRACE_PROFILE_HASH_BITS)
 
 static void *
 function_stat_next(void *v, int idx)
@@ -676,7 +676,7 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
 
 	pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE);
 
-	for (i = 0; i < pages; i++) {
+	for (i = 1; i < pages; i++) {
 		pg->next = (void *)get_zeroed_page(GFP_KERNEL);
 		if (!pg->next)
 			goto out_free;
@@ -724,13 +724,6 @@ static int ftrace_profile_init_cpu(int cpu)
 	if (!stat->hash)
 		return -ENOMEM;
 
-	if (!ftrace_profile_bits) {
-		size--;
-
-		for (; size; size >>= 1)
-			ftrace_profile_bits++;
-	}
-
 	/* Preallocate the function profiling pages */
 	if (ftrace_profile_pages_init(stat) < 0) {
 		kfree(stat->hash);
@@ -763,7 +756,7 @@ ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip)
 	struct hlist_head *hhd;
 	unsigned long key;
 
-	key = hash_long(ip, ftrace_profile_bits);
+	key = hash_long(ip, FTRACE_PROFILE_HASH_BITS);
 	hhd = &stat->hash[key];
 
 	if (hlist_empty(hhd))
@@ -782,7 +775,7 @@ static void ftrace_add_profile(struct ftrace_profile_stat *stat,
 {
 	unsigned long key;
 
-	key = hash_long(rec->ip, ftrace_profile_bits);
+	key = hash_long(rec->ip, FTRACE_PROFILE_HASH_BITS);
 	hlist_add_head_rcu(&rec->node, &stat->hash[key]);
 }
 
@@ -1079,7 +1072,7 @@ struct ftrace_func_probe {
 	unsigned long		flags;
 	unsigned long		ip;
 	void			*data;
-	struct rcu_head		rcu;
+	struct list_head	free_list;
 };
 
 struct ftrace_func_entry {
@@ -1329,7 +1322,6 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
 	struct hlist_head *hhd;
 	struct ftrace_hash *old_hash;
 	struct ftrace_hash *new_hash;
-	unsigned long key;
 	int size = src->count;
 	int bits = 0;
 	int ret;
@@ -1372,10 +1364,6 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
 	for (i = 0; i < size; i++) {
 		hhd = &src->buckets[i];
 		hlist_for_each_entry_safe(entry, tn, hhd, hlist) {
-			if (bits > 0)
-				key = hash_long(entry->ip, bits);
-			else
-				key = 0;
 			remove_hash_entry(src, entry);
 			__add_hash_entry(new_hash, entry);
 		}
@@ -2973,28 +2961,27 @@ static void __disable_ftrace_function_probe(void)
 }
 
 
-static void ftrace_free_entry_rcu(struct rcu_head *rhp)
+static void ftrace_free_entry(struct ftrace_func_probe *entry)
 {
-	struct ftrace_func_probe *entry =
-		container_of(rhp, struct ftrace_func_probe, rcu);
-
 	if (entry->ops->free)
-		entry->ops->free(&entry->data);
+		entry->ops->free(entry->ops, entry->ip, &entry->data);
 	kfree(entry);
 }
 
-
 int
 register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 			      void *data)
 {
 	struct ftrace_func_probe *entry;
+	struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash;
+	struct ftrace_hash *hash;
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;
 	int type, len, not;
 	unsigned long key;
 	int count = 0;
 	char *search;
+	int ret;
 
 	type = filter_parse_regex(glob, strlen(glob), &search, &not);
 	len = strlen(search);
@@ -3005,8 +2992,16 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 
 	mutex_lock(&ftrace_lock);
 
-	if (unlikely(ftrace_disabled))
+	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
+	if (!hash) {
+		count = -ENOMEM;
 		goto out_unlock;
+	}
+
+	if (unlikely(ftrace_disabled)) {
+		count = -ENODEV;
+		goto out_unlock;
+	}
 
 	do_for_each_ftrace_rec(pg, rec) {
 
@@ -3030,14 +3025,21 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 		 * for each function we find. We call the callback
 		 * to give the caller an opportunity to do so.
 		 */
-		if (ops->callback) {
-			if (ops->callback(rec->ip, &entry->data) < 0) {
+		if (ops->init) {
+			if (ops->init(ops, rec->ip, &entry->data) < 0) {
 				/* caller does not like this func */
 				kfree(entry);
 				continue;
 			}
 		}
 
+		ret = enter_record(hash, rec, 0);
+		if (ret < 0) {
+			kfree(entry);
+			count = ret;
+			goto out_unlock;
+		}
+
 		entry->ops = ops;
 		entry->ip = rec->ip;
 
@@ -3045,10 +3047,16 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 		hlist_add_head_rcu(&entry->node, &ftrace_func_hash[key]);
 
 	} while_for_each_ftrace_rec();
+
+	ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+	if (ret < 0)
+		count = ret;
+
 	__enable_ftrace_function_probe();
 
  out_unlock:
 	mutex_unlock(&ftrace_lock);
+	free_ftrace_hash(hash);
 
 	return count;
 }
@@ -3062,7 +3070,12 @@ static void
 __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 				  void *data, int flags)
 {
+	struct ftrace_func_entry *rec_entry;
 	struct ftrace_func_probe *entry;
+	struct ftrace_func_probe *p;
+	struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash;
+	struct list_head free_list;
+	struct ftrace_hash *hash;
 	struct hlist_node *tmp;
 	char str[KSYM_SYMBOL_LEN];
 	int type = MATCH_FULL;
@@ -3083,6 +3096,14 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	}
 
 	mutex_lock(&ftrace_lock);
+
+	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
+	if (!hash)
+		/* Hmm, should report this somehow */
+		goto out_unlock;
+
+	INIT_LIST_HEAD(&free_list);
+
 	for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) {
 		struct hlist_head *hhd = &ftrace_func_hash[i];
 
@@ -3103,12 +3124,30 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 					continue;
 			}
 
+			rec_entry = ftrace_lookup_ip(hash, entry->ip);
+			/* It is possible more than one entry had this ip */
+			if (rec_entry)
+				free_hash_entry(hash, rec_entry);
+
 			hlist_del_rcu(&entry->node);
-			call_rcu_sched(&entry->rcu, ftrace_free_entry_rcu);
+			list_add(&entry->free_list, &free_list);
 		}
 	}
 	__disable_ftrace_function_probe();
+	/*
+	 * Remove after the disable is called. Otherwise, if the last
+	 * probe is removed, a null hash means *all enabled*.
+	 */
+	ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+	synchronize_sched();
+	list_for_each_entry_safe(entry, p, &free_list, free_list) {
+		list_del(&entry->free_list);
+		ftrace_free_entry(entry);
+	}
+		
+ out_unlock:
 	mutex_unlock(&ftrace_lock);
+	free_ftrace_hash(hash);
 }
 
 void
@@ -3736,7 +3775,8 @@ out:
 	if (fail)
 		return -EINVAL;
 
-	ftrace_graph_filter_enabled = 1;
+	ftrace_graph_filter_enabled = !!(*idx);
+
 	return 0;
 }