Merge tag 'trace-v4.17' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "New features:

   - Tom Zanussi's extended histogram work.

     This adds the synthetic events to have histograms from multiple
     event data Adds triggers "onmatch" and "onmax" to call the
     synthetic events Several updates to the histogram code from this

   - Allow way to nest ring buffer calls in the same context

   - Allow absolute time stamps in ring buffer

   - Rewrite of filter code parsing based on Al Viro's suggestions

   - Setting of trace_clock to global if TSC is unstable (on boot)

   - Better OOM handling when allocating large ring buffers

   - Added initcall tracepoints (consolidated initcall_debug code with
     them)

  And other various fixes and clean ups"

* tag 'trace-v4.17' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (68 commits)
  init: Have initcall_debug still work without CONFIG_TRACEPOINTS
  init, tracing: Have printk come through the trace events for initcall_debug
  init, tracing: instrument security and console initcall trace events
  init, tracing: Add initcall trace events
  tracing: Add rcu dereference annotation for test func that touches filter->prog
  tracing: Add rcu dereference annotation for filter->prog
  tracing: Fixup logic inversion on setting trace_global_clock defaults
  tracing: Hide global trace clock from lockdep
  ring-buffer: Add set/clear_current_oom_origin() during allocations
  ring-buffer: Check if memory is available before allocation
  lockdep: Add print_irqtrace_events() to __warn
  vsprintf: Do not preprocess non-dereferenced pointers for bprintf (%px and %pK)
  tracing: Uninitialized variable in create_tracing_map_fields()
  tracing: Make sure variable string fields are NULL-terminated
  tracing: Add action comparisons when testing matching hist triggers
  tracing: Don't add flag strings when displaying variable references
  tracing: Fix display of hist trigger expressions containing timestamps
  ftrace: Drop a VLA in module_exists()
  tracing: Mention trace_clock=global when warning about unstable clocks
  tracing: Default to using trace_global_clock if sched_clock is unstable
  ...

1 files changed, 150 insertions, 82 deletions

diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 07e75344725b..5cadb1b8b5fe 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -66,6 +66,73 @@ u64 tracing_map_read_sum(struct tracing_map_elt *elt, unsigned int i)
 	return (u64)atomic64_read(&elt->fields[i].sum);
 }
 
+/**
+ * tracing_map_set_var - Assign a tracing_map_elt's variable field
+ * @elt: The tracing_map_elt
+ * @i: The index of the given variable associated with the tracing_map_elt
+ * @n: The value to assign
+ *
+ * Assign n to variable i associated with the specified tracing_map_elt
+ * instance.  The index i is the index returned by the call to
+ * tracing_map_add_var() when the tracing map was set up.
+ */
+void tracing_map_set_var(struct tracing_map_elt *elt, unsigned int i, u64 n)
+{
+	atomic64_set(&elt->vars[i], n);
+	elt->var_set[i] = true;
+}
+
+/**
+ * tracing_map_var_set - Return whether or not a variable has been set
+ * @elt: The tracing_map_elt
+ * @i: The index of the given variable associated with the tracing_map_elt
+ *
+ * Return true if the variable has been set, false otherwise.  The
+ * index i is the index returned by the call to tracing_map_add_var()
+ * when the tracing map was set up.
+ */
+bool tracing_map_var_set(struct tracing_map_elt *elt, unsigned int i)
+{
+	return elt->var_set[i];
+}
+
+/**
+ * tracing_map_read_var - Return the value of a tracing_map_elt's variable field
+ * @elt: The tracing_map_elt
+ * @i: The index of the given variable associated with the tracing_map_elt
+ *
+ * Retrieve the value of the variable i associated with the specified
+ * tracing_map_elt instance.  The index i is the index returned by the
+ * call to tracing_map_add_var() when the tracing map was set
+ * up.
+ *
+ * Return: The variable value associated with field i for elt.
+ */
+u64 tracing_map_read_var(struct tracing_map_elt *elt, unsigned int i)
+{
+	return (u64)atomic64_read(&elt->vars[i]);
+}
+
+/**
+ * tracing_map_read_var_once - Return and reset a tracing_map_elt's variable field
+ * @elt: The tracing_map_elt
+ * @i: The index of the given variable associated with the tracing_map_elt
+ *
+ * Retrieve the value of the variable i associated with the specified
+ * tracing_map_elt instance, and reset the variable to the 'not set'
+ * state.  The index i is the index returned by the call to
+ * tracing_map_add_var() when the tracing map was set up.  The reset
+ * essentially makes the variable a read-once variable if it's only
+ * accessed using this function.
+ *
+ * Return: The variable value associated with field i for elt.
+ */
+u64 tracing_map_read_var_once(struct tracing_map_elt *elt, unsigned int i)
+{
+	elt->var_set[i] = false;
+	return (u64)atomic64_read(&elt->vars[i]);
+}
+
 int tracing_map_cmp_string(void *val_a, void *val_b)
 {
 	char *a = val_a;
@@ -171,6 +238,28 @@ int tracing_map_add_sum_field(struct tracing_map *map)
 }
 
 /**
+ * tracing_map_add_var - Add a field describing a tracing_map var
+ * @map: The tracing_map
+ *
+ * Add a var to the map and return the index identifying it in the map
+ * and associated tracing_map_elts.  This is the index used for
+ * instance to update a var for a particular tracing_map_elt using
+ * tracing_map_update_var() or reading it via tracing_map_read_var().
+ *
+ * Return: The index identifying the var in the map and associated
+ * tracing_map_elts, or -EINVAL on error.
+ */
+int tracing_map_add_var(struct tracing_map *map)
+{
+	int ret = -EINVAL;
+
+	if (map->n_vars < TRACING_MAP_VARS_MAX)
+		ret = map->n_vars++;
+
+	return ret;
+}
+
+/**
  * tracing_map_add_key_field - Add a field describing a tracing_map key
  * @map: The tracing_map
  * @offset: The offset within the key
@@ -280,6 +369,11 @@ static void tracing_map_elt_clear(struct tracing_map_elt *elt)
 		if (elt->fields[i].cmp_fn == tracing_map_cmp_atomic64)
 			atomic64_set(&elt->fields[i].sum, 0);
 
+	for (i = 0; i < elt->map->n_vars; i++) {
+		atomic64_set(&elt->vars[i], 0);
+		elt->var_set[i] = false;
+	}
+
 	if (elt->map->ops && elt->map->ops->elt_clear)
 		elt->map->ops->elt_clear(elt);
 }
@@ -306,6 +400,8 @@ static void tracing_map_elt_free(struct tracing_map_elt *elt)
 	if (elt->map->ops && elt->map->ops->elt_free)
 		elt->map->ops->elt_free(elt);
 	kfree(elt->fields);
+	kfree(elt->vars);
+	kfree(elt->var_set);
 	kfree(elt->key);
 	kfree(elt);
 }
@@ -333,6 +429,18 @@ static struct tracing_map_elt *tracing_map_elt_alloc(struct tracing_map *map)
 		goto free;
 	}
 
+	elt->vars = kcalloc(map->n_vars, sizeof(*elt->vars), GFP_KERNEL);
+	if (!elt->vars) {
+		err = -ENOMEM;
+		goto free;
+	}
+
+	elt->var_set = kcalloc(map->n_vars, sizeof(*elt->var_set), GFP_KERNEL);
+	if (!elt->var_set) {
+		err = -ENOMEM;
+		goto free;
+	}
+
 	tracing_map_elt_init_fields(elt);
 
 	if (map->ops && map->ops->elt_alloc) {
@@ -414,7 +522,9 @@ static inline struct tracing_map_elt *
 __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only)
 {
 	u32 idx, key_hash, test_key;
+	int dup_try = 0;
 	struct tracing_map_entry *entry;
+	struct tracing_map_elt *val;
 
 	key_hash = jhash(key, map->key_size, 0);
 	if (key_hash == 0)
@@ -426,11 +536,33 @@ __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only)
 		entry = TRACING_MAP_ENTRY(map->map, idx);
 		test_key = entry->key;
 
-		if (test_key && test_key == key_hash && entry->val &&
-		    keys_match(key, entry->val->key, map->key_size)) {
-			if (!lookup_only)
-				atomic64_inc(&map->hits);
-			return entry->val;
+		if (test_key && test_key == key_hash) {
+			val = READ_ONCE(entry->val);
+			if (val &&
+			    keys_match(key, val->key, map->key_size)) {
+				if (!lookup_only)
+					atomic64_inc(&map->hits);
+				return val;
+			} else if (unlikely(!val)) {
+				/*
+				 * The key is present. But, val (pointer to elt
+				 * struct) is still NULL. which means some other
+				 * thread is in the process of inserting an
+				 * element.
+				 *
+				 * On top of that, it's key_hash is same as the
+				 * one being inserted right now. So, it's
+				 * possible that the element has the same
+				 * key as well.
+				 */
+
+				dup_try++;
+				if (dup_try > map->map_size) {
+					atomic64_inc(&map->drops);
+					break;
+				}
+				continue;
+			}
 		}
 
 		if (!test_key) {
@@ -452,6 +584,13 @@ __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only)
 				atomic64_inc(&map->hits);
 
 				return entry->val;
+			} else {
+				/*
+				 * cmpxchg() failed. Loop around once
+				 * more to check what key was inserted.
+				 */
+				dup_try++;
+				continue;
 			}
 		}
 
@@ -816,67 +955,15 @@ create_sort_entry(void *key, struct tracing_map_elt *elt)
 	return sort_entry;
 }
 
-static struct tracing_map_elt *copy_elt(struct tracing_map_elt *elt)
-{
-	struct tracing_map_elt *dup_elt;
-	unsigned int i;
-
-	dup_elt = tracing_map_elt_alloc(elt->map);
-	if (IS_ERR(dup_elt))
-		return NULL;
-
-	if (elt->map->ops && elt->map->ops->elt_copy)
-		elt->map->ops->elt_copy(dup_elt, elt);
-
-	dup_elt->private_data = elt->private_data;
-	memcpy(dup_elt->key, elt->key, elt->map->key_size);
-
-	for (i = 0; i < elt->map->n_fields; i++) {
-		atomic64_set(&dup_elt->fields[i].sum,
-			     atomic64_read(&elt->fields[i].sum));
-		dup_elt->fields[i].cmp_fn = elt->fields[i].cmp_fn;
-	}
-
-	return dup_elt;
-}
-
-static int merge_dup(struct tracing_map_sort_entry **sort_entries,
-		     unsigned int target, unsigned int dup)
-{
-	struct tracing_map_elt *target_elt, *elt;
-	bool first_dup = (target - dup) == 1;
-	int i;
-
-	if (first_dup) {
-		elt = sort_entries[target]->elt;
-		target_elt = copy_elt(elt);
-		if (!target_elt)
-			return -ENOMEM;
-		sort_entries[target]->elt = target_elt;
-		sort_entries[target]->elt_copied = true;
-	} else
-		target_elt = sort_entries[target]->elt;
-
-	elt = sort_entries[dup]->elt;
-
-	for (i = 0; i < elt->map->n_fields; i++)
-		atomic64_add(atomic64_read(&elt->fields[i].sum),
-			     &target_elt->fields[i].sum);
-
-	sort_entries[dup]->dup = true;
-
-	return 0;
-}
-
-static int merge_dups(struct tracing_map_sort_entry **sort_entries,
+static void detect_dups(struct tracing_map_sort_entry **sort_entries,
 		      int n_entries, unsigned int key_size)
 {
 	unsigned int dups = 0, total_dups = 0;
-	int err, i, j;
+	int i;
 	void *key;
 
 	if (n_entries < 2)
-		return total_dups;
+		return;
 
 	sort(sort_entries, n_entries, sizeof(struct tracing_map_sort_entry *),
 	     (int (*)(const void *, const void *))cmp_entries_dup, NULL);
@@ -885,30 +972,14 @@ static int merge_dups(struct tracing_map_sort_entry **sort_entries,
 	for (i = 1; i < n_entries; i++) {
 		if (!memcmp(sort_entries[i]->key, key, key_size)) {
 			dups++; total_dups++;
-			err = merge_dup(sort_entries, i - dups, i);
-			if (err)
-				return err;
 			continue;
 		}
 		key = sort_entries[i]->key;
 		dups = 0;
 	}
 
-	if (!total_dups)
-		return total_dups;
-
-	for (i = 0, j = 0; i < n_entries; i++) {
-		if (!sort_entries[i]->dup) {
-			sort_entries[j] = sort_entries[i];
-			if (j++ != i)
-				sort_entries[i] = NULL;
-		} else {
-			destroy_sort_entry(sort_entries[i]);
-			sort_entries[i] = NULL;
-		}
-	}
-
-	return total_dups;
+	WARN_ONCE(total_dups > 0,
+		  "Duplicates detected: %d\n", total_dups);
 }
 
 static bool is_key(struct tracing_map *map, unsigned int field_idx)
@@ -1034,10 +1105,7 @@ int tracing_map_sort_entries(struct tracing_map *map,
 		return 1;
 	}
 
-	ret = merge_dups(entries, n_entries, map->key_size);
-	if (ret < 0)
-		goto free;
-	n_entries -= ret;
+	detect_dups(entries, n_entries, map->key_size);
 
 	if (is_key(map, sort_keys[0].field_idx))
 		cmp_entries_fn = cmp_entries_key;