Merge tag 'perf-core-for-mingo-5.0-20190126' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

BPF:

Song Liu:

- Fix synthesized PERF_RECORD_KSYMBOL/BPF_EVENT

Arnaldo Carvalho de Melo:

- Add bpf_map() helper, to make BPF map declararions more compact and
allow for BTF annotations to be made transparently.

perf script python:

Tony Jones:

- Remove explicit shebangs.

- Fix the PYTHON=python3 builds.

Core:

Davidlohr Bueso:

- Update rbtree implementation, getting it closer to the kernel one.

- Use cached rbtrees.

Arnaldo Carvalho de Melo:

- Remove some needless headers from .c and .h files fixing up the fallout,
to reduce building time when changes are made to .h files

Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>
Signed-off-by: Ingo Molnar <[e-mail]>

tools/include/linux/rbtree.h

···
 	struct rb_node *rb_node;
 };
 
+/*
+ * Leftmost-cached rbtrees.
+ *
+ * We do not cache the rightmost node based on footprint
+ * size vs number of potential users that could benefit
+ * from O(1) rb_last(). Just not worth it, users that want
+ * this feature can always implement the logic explicitly.
+ * Furthermore, users that want to cache both pointers may
+ * find it a bit asymmetric, but that's ok.
+ */
+struct rb_root_cached {
+	struct rb_root rb_root;
+	struct rb_node *rb_leftmost;
+};
 
 #define rb_parent(r)   ((struct rb_node *)((r)->__rb_parent_color & ~3))
 
 #define RB_ROOT	(struct rb_root) { NULL, }
+#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL }
 #define	rb_entry(ptr, type, member) container_of(ptr, type, member)
 
-#define RB_EMPTY_ROOT(root)  ((root)->rb_node == NULL)
+#define RB_EMPTY_ROOT(root)  (READ_ONCE((root)->rb_node) == NULL)
 
 /* 'empty' nodes are nodes that are known not to be inserted in an rbtree */
 #define RB_EMPTY_NODE(node)  \
···
 extern struct rb_node *rb_first(const struct rb_root *);
 extern struct rb_node *rb_last(const struct rb_root *);
 
+extern void rb_insert_color_cached(struct rb_node *,
+				   struct rb_root_cached *, bool);
+extern void rb_erase_cached(struct rb_node *node, struct rb_root_cached *);
+/* Same as rb_first(), but O(1) */
+#define rb_first_cached(root) (root)->rb_leftmost
+
 /* Postorder iteration - always visit the parent after its children */
 extern struct rb_node *rb_first_postorder(const struct rb_root *);
 extern struct rb_node *rb_next_postorder(const struct rb_node *);
···
 /* Fast replacement of a single node without remove/rebalance/add/rebalance */
 extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
 			    struct rb_root *root);
+extern void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new,
+				   struct rb_root_cached *root);
 
 static inline void rb_link_node(struct rb_node *node, struct rb_node *parent,
 				struct rb_node **rb_link)
···
 	   ____ptr ? rb_entry(____ptr, type, member) : NULL; \
 	})
 
-
-/*
- * Handy for checking that we are not deleting an entry that is
- * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
- * probably should be moved to lib/rbtree.c...
+/**
+ * rbtree_postorder_for_each_entry_safe - iterate in post-order over rb_root of
+ * given type allowing the backing memory of @pos to be invalidated
+ *
+ * @pos:	the 'type *' to use as a loop cursor.
+ * @n:		another 'type *' to use as temporary storage
+ * @root:	'rb_root *' of the rbtree.
+ * @field:	the name of the rb_node field within 'type'.
+ *
+ * rbtree_postorder_for_each_entry_safe() provides a similar guarantee as
+ * list_for_each_entry_safe() and allows the iteration to continue independent
+ * of changes to @pos by the body of the loop.
+ *
+ * Note, however, that it cannot handle other modifications that re-order the
+ * rbtree it is iterating over. This includes calling rb_erase() on @pos, as
+ * rb_erase() may rebalance the tree, causing us to miss some nodes.
  */
+#define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \
+	for (pos = rb_entry_safe(rb_first_postorder(root), typeof(*pos), field); \
+	     pos && ({ n = rb_entry_safe(rb_next_postorder(&pos->field), \
+			typeof(*pos), field); 1; }); \
+	     pos = n)
+
 static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
 {
 	rb_erase(n, root);

tools/include/linux/rbtree_augmented.h

···
 	void (*rotate)(struct rb_node *old, struct rb_node *new);
 };
 
-extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+extern void __rb_insert_augmented(struct rb_node *node,
+				  struct rb_root *root,
+				  bool newleft, struct rb_node **leftmost,
 	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
 /*
  * Fixup the rbtree and update the augmented information when rebalancing.
···
 rb_insert_augmented(struct rb_node *node, struct rb_root *root,
 		    const struct rb_augment_callbacks *augment)
 {
-	__rb_insert_augmented(node, root, augment->rotate);
+	__rb_insert_augmented(node, root, false, NULL, augment->rotate);
+}
+
+static inline void
+rb_insert_augmented_cached(struct rb_node *node,
+			   struct rb_root_cached *root, bool newleft,
+			   const struct rb_augment_callbacks *augment)
+{
+	__rb_insert_augmented(node, &root->rb_root,
+			      newleft, &root->rb_leftmost, augment->rotate);
 }
 
 #define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield,	\
···
 	old->rbaugmented = rbcompute(old);				\
 }									\
 rbstatic const struct rb_augment_callbacks rbname = {			\
-	rbname ## _propagate, rbname ## _copy, rbname ## _rotate	\
+	.propagate = rbname ## _propagate,				\
+	.copy = rbname ## _copy,					\
+	.rotate = rbname ## _rotate					\
 };
 
 
···
 {
 	if (parent) {
 		if (parent->rb_left == old)
-			parent->rb_left = new;
+			WRITE_ONCE(parent->rb_left, new);
 		else
-			parent->rb_right = new;
+			WRITE_ONCE(parent->rb_right, new);
 	} else
-		root->rb_node = new;
+		WRITE_ONCE(root->rb_node, new);
 }
 
 extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
···
 
 static __always_inline struct rb_node *
 __rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+		     struct rb_node **leftmost,
 		     const struct rb_augment_callbacks *augment)
 {
-	struct rb_node *child = node->rb_right, *tmp = node->rb_left;
+	struct rb_node *child = node->rb_right;
+	struct rb_node *tmp = node->rb_left;
 	struct rb_node *parent, *rebalance;
 	unsigned long pc;
+
+	if (leftmost && node == *leftmost)
+		*leftmost = rb_next(node);
 
 	if (!tmp) {
 		/*
···
 		tmp = parent;
 	} else {
 		struct rb_node *successor = child, *child2;
+
 		tmp = child->rb_left;
 		if (!tmp) {
 			/*
···
 			 */
 			parent = successor;
 			child2 = successor->rb_right;
+
 			augment->copy(node, successor);
 		} else {
 			/*
···
 				successor = tmp;
 				tmp = tmp->rb_left;
 			} while (tmp);
-			parent->rb_left = child2 = successor->rb_right;
-			successor->rb_right = child;
+			child2 = successor->rb_right;
+			WRITE_ONCE(parent->rb_left, child2);
+			WRITE_ONCE(successor->rb_right, child);
 			rb_set_parent(child, successor);
+
 			augment->copy(node, successor);
 			augment->propagate(parent, successor);
 		}
 
-		successor->rb_left = tmp = node->rb_left;
+		tmp = node->rb_left;
+		WRITE_ONCE(successor->rb_left, tmp);
 		rb_set_parent(tmp, successor);
 
 		pc = node->__rb_parent_color;
 		tmp = __rb_parent(pc);
 		__rb_change_child(node, successor, tmp, root);
+
 		if (child2) {
 			successor->__rb_parent_color = pc;
 			rb_set_parent_color(child2, parent, RB_BLACK);
···
 rb_erase_augmented(struct rb_node *node, struct rb_root *root,
 		   const struct rb_augment_callbacks *augment)
 {
-	struct rb_node *rebalance = __rb_erase_augmented(node, root, augment);
+	struct rb_node *rebalance = __rb_erase_augmented(node, root,
+							 NULL, augment);
 	if (rebalance)
 		__rb_erase_color(rebalance, root, augment->rotate);
 }
 
-#endif	/* _TOOLS_LINUX_RBTREE_AUGMENTED_H */
+static __always_inline void
+rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root,
+			  const struct rb_augment_callbacks *augment)
+{
+	struct rb_node *rebalance = __rb_erase_augmented(node, &root->rb_root,
+							 &root->rb_leftmost,
+							 augment);
+	if (rebalance)
+		__rb_erase_color(rebalance, &root->rb_root, augment->rotate);
+}
+
+#endif /* _TOOLS_LINUX_RBTREE_AUGMENTED_H */

tools/lib/rbtree.c

···
 */
 
 #include <linux/rbtree_augmented.h>
+#include <linux/export.h>
 
 /*
  * red-black trees properties:  http://en.wikipedia.org/wiki/Rbtree
···
  *  We shall indicate color with case, where black nodes are uppercase and red
  *  nodes will be lowercase. Unknown color nodes shall be drawn as red within
  *  parentheses and have some accompanying text comment.
+ */
+
+/*
+ * Notes on lockless lookups:
+ *
+ * All stores to the tree structure (rb_left and rb_right) must be done using
+ * WRITE_ONCE(). And we must not inadvertently cause (temporary) loops in the
+ * tree structure as seen in program order.
+ *
+ * These two requirements will allow lockless iteration of the tree -- not
+ * correct iteration mind you, tree rotations are not atomic so a lookup might
+ * miss entire subtrees.
+ *
+ * But they do guarantee that any such traversal will only see valid elements
+ * and that it will indeed complete -- does not get stuck in a loop.
+ *
+ * It also guarantees that if the lookup returns an element it is the 'correct'
+ * one. But not returning an element does _NOT_ mean it's not present.
+ *
+ * NOTE:
+ *
+ * Stores to __rb_parent_color are not important for simple lookups so those
+ * are left undone as of now. Nor did I check for loops involving parent
+ * pointers.
  */
 
 static inline void rb_set_black(struct rb_node *rb)
···
 
 static __always_inline void
 __rb_insert(struct rb_node *node, struct rb_root *root,
+	    bool newleft, struct rb_node **leftmost,
 	    void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
 {
 	struct rb_node *parent = rb_red_parent(node), *gparent, *tmp;
 
+	if (newleft)
+		*leftmost = node;
+
 	while (true) {
 		/*
-		 * Loop invariant: node is red
-		 *
-		 * If there is a black parent, we are done.
-		 * Otherwise, take some corrective action as we don't
-		 * want a red root or two consecutive red nodes.
+		 * Loop invariant: node is red.
 		 */
-		if (!parent) {
+		if (unlikely(!parent)) {
+			/*
+			 * The inserted node is root. Either this is the
+			 * first node, or we recursed at Case 1 below and
+			 * are no longer violating 4).
+			 */
 			rb_set_parent_color(node, NULL, RB_BLACK);
 			break;
-		} else if (rb_is_black(parent))
+		}
+
+		/*
+		 * If there is a black parent, we are done.
+		 * Otherwise, take some corrective action as,
+		 * per 4), we don't want a red root or two
+		 * consecutive red nodes.
+		 */
+		if(rb_is_black(parent))
 			break;
 
 		gparent = rb_red_parent(parent);
···
 		if (parent != tmp) {	/* parent == gparent->rb_left */
 			if (tmp && rb_is_red(tmp)) {
 				/*
-				 * Case 1 - color flips
+				 * Case 1 - node's uncle is red (color flips).
 				 *
 				 *       G            g
 				 *      / \          / \
···
 			tmp = parent->rb_right;
 			if (node == tmp) {
 				/*
-				 * Case 2 - left rotate at parent
+				 * Case 2 - node's uncle is black and node is
+				 * the parent's right child (left rotate at parent).
 				 *
 				 *      G             G
 				 *     / \           / \
···
 				 * This still leaves us in violation of 4), the
 				 * continuation into Case 3 will fix that.
 				 */
-				parent->rb_right = tmp = node->rb_left;
-				node->rb_left = parent;
+				tmp = node->rb_left;
+				WRITE_ONCE(parent->rb_right, tmp);
+				WRITE_ONCE(node->rb_left, parent);
 				if (tmp)
 					rb_set_parent_color(tmp, parent,
 							    RB_BLACK);
···
 			}
 
 			/*
-			 * Case 3 - right rotate at gparent
+			 * Case 3 - node's uncle is black and node is
+			 * the parent's left child (right rotate at gparent).
 			 *
 			 *        G           P
 			 *       / \         / \
···
 			 *     /                 \
 			 *    n                   U
 			 */
-			gparent->rb_left = tmp;  /* == parent->rb_right */
-			parent->rb_right = gparent;
+			WRITE_ONCE(gparent->rb_left, tmp); /* == parent->rb_right */
+			WRITE_ONCE(parent->rb_right, gparent);
 			if (tmp)
 				rb_set_parent_color(tmp, gparent, RB_BLACK);
 			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
···
 			tmp = parent->rb_left;
 			if (node == tmp) {
 				/* Case 2 - right rotate at parent */
-				parent->rb_left = tmp = node->rb_right;
-				node->rb_right = parent;
+				tmp = node->rb_right;
+				WRITE_ONCE(parent->rb_left, tmp);
+				WRITE_ONCE(node->rb_right, parent);
 				if (tmp)
 					rb_set_parent_color(tmp, parent,
 							    RB_BLACK);
···
 			}
 
 			/* Case 3 - left rotate at gparent */
-			gparent->rb_right = tmp;  /* == parent->rb_left */
-			parent->rb_left = gparent;
+			WRITE_ONCE(gparent->rb_right, tmp); /* == parent->rb_left */
+			WRITE_ONCE(parent->rb_left, gparent);
 			if (tmp)
 				rb_set_parent_color(tmp, gparent, RB_BLACK);
 			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
···
 				 *      / \         / \
 				 *     Sl  Sr      N   Sl
 				 */
-				parent->rb_right = tmp1 = sibling->rb_left;
-				sibling->rb_left = parent;
+				tmp1 = sibling->rb_left;
+				WRITE_ONCE(parent->rb_right, tmp1);
+				WRITE_ONCE(sibling->rb_left, parent);
 				rb_set_parent_color(tmp1, parent, RB_BLACK);
 				__rb_rotate_set_parents(parent, sibling, root,
 							RB_RED);
···
 				 *
 				 *   (p)           (p)
 				 *   / \           / \
-				 *  N   S    -->  N   Sl
+				 *  N   S    -->  N   sl
 				 *     / \             \
-				 *    sl  Sr            s
+				 *    sl  Sr            S
 				 *                       \
 				 *                        Sr
+				 *
+				 * Note: p might be red, and then both
+				 * p and sl are red after rotation(which
+				 * breaks property 4). This is fixed in
+				 * Case 4 (in __rb_rotate_set_parents()
+				 *         which set sl the color of p
+				 *         and set p RB_BLACK)
+				 *
+				 *   (p)            (sl)
+				 *   / \            /  \
+				 *  N   sl   -->   P    S
+				 *       \        /      \
+				 *        S      N        Sr
+				 *         \
+				 *          Sr
 				 */
-				sibling->rb_left = tmp1 = tmp2->rb_right;
-				tmp2->rb_right = sibling;
-				parent->rb_right = tmp2;
+				tmp1 = tmp2->rb_right;
+				WRITE_ONCE(sibling->rb_left, tmp1);
+				WRITE_ONCE(tmp2->rb_right, sibling);
+				WRITE_ONCE(parent->rb_right, tmp2);
 				if (tmp1)
 					rb_set_parent_color(tmp1, sibling,
 							    RB_BLACK);
···
 			 *        / \         / \
 			 *      (sl) sr      N  (sl)
 			 */
-			parent->rb_right = tmp2 = sibling->rb_left;
-			sibling->rb_left = parent;
+			tmp2 = sibling->rb_left;
+			WRITE_ONCE(parent->rb_right, tmp2);
+			WRITE_ONCE(sibling->rb_left, parent);
 			rb_set_parent_color(tmp1, sibling, RB_BLACK);
 			if (tmp2)
 				rb_set_parent(tmp2, parent);
···
 			sibling = parent->rb_left;
 			if (rb_is_red(sibling)) {
 				/* Case 1 - right rotate at parent */
-				parent->rb_left = tmp1 = sibling->rb_right;
-				sibling->rb_right = parent;
+				tmp1 = sibling->rb_right;
+				WRITE_ONCE(parent->rb_left, tmp1);
+				WRITE_ONCE(sibling->rb_right, parent);
 				rb_set_parent_color(tmp1, parent, RB_BLACK);
 				__rb_rotate_set_parents(parent, sibling, root,
 							RB_RED);
···
 					}
 					break;
 				}
-				/* Case 3 - right rotate at sibling */
-				sibling->rb_right = tmp1 = tmp2->rb_left;
-				tmp2->rb_left = sibling;
-				parent->rb_left = tmp2;
+				/* Case 3 - left rotate at sibling */
+				tmp1 = tmp2->rb_left;
+				WRITE_ONCE(sibling->rb_right, tmp1);
+				WRITE_ONCE(tmp2->rb_left, sibling);
+				WRITE_ONCE(parent->rb_left, tmp2);
 				if (tmp1)
 					rb_set_parent_color(tmp1, sibling,
 							    RB_BLACK);
···
 				tmp1 = sibling;
 				sibling = tmp2;
 			}
-			/* Case 4 - left rotate at parent + color flips */
-			parent->rb_left = tmp2 = sibling->rb_right;
-			sibling->rb_right = parent;
+			/* Case 4 - right rotate at parent + color flips */
+			tmp2 = sibling->rb_right;
+			WRITE_ONCE(parent->rb_left, tmp2);
+			WRITE_ONCE(sibling->rb_right, parent);
 			rb_set_parent_color(tmp1, sibling, RB_BLACK);
 			if (tmp2)
 				rb_set_parent(tmp2, parent);
···
 static inline void dummy_rotate(struct rb_node *old, struct rb_node *new) {}
 
 static const struct rb_augment_callbacks dummy_callbacks = {
-	dummy_propagate, dummy_copy, dummy_rotate
+	.propagate = dummy_propagate,
+	.copy = dummy_copy,
+	.rotate = dummy_rotate
 };
 
 void rb_insert_color(struct rb_node *node, struct rb_root *root)
 {
-	__rb_insert(node, root, dummy_rotate);
+	__rb_insert(node, root, false, NULL, dummy_rotate);
 }
 
 void rb_erase(struct rb_node *node, struct rb_root *root)
 {
 	struct rb_node *rebalance;
-	rebalance = __rb_erase_augmented(node, root, &dummy_callbacks);
+	rebalance = __rb_erase_augmented(node, root,
+					 NULL, &dummy_callbacks);
 	if (rebalance)
 		____rb_erase_color(rebalance, root, dummy_rotate);
+}
+
+void rb_insert_color_cached(struct rb_node *node,
+			    struct rb_root_cached *root, bool leftmost)
+{
+	__rb_insert(node, &root->rb_root, leftmost,
+		    &root->rb_leftmost, dummy_rotate);
+}
+
+void rb_erase_cached(struct rb_node *node, struct rb_root_cached *root)
+{
+	struct rb_node *rebalance;
+	rebalance = __rb_erase_augmented(node, &root->rb_root,
+					 &root->rb_leftmost, &dummy_callbacks);
+	if (rebalance)
+		____rb_erase_color(rebalance, &root->rb_root, dummy_rotate);
 }
 
 /*
···
  */
 
 void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+			   bool newleft, struct rb_node **leftmost,
 	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
 {
-	__rb_insert(node, root, augment_rotate);
+	__rb_insert(node, root, newleft, leftmost, augment_rotate);
 }
 
 /*
···
 {
 	struct rb_node *parent = rb_parent(victim);
 
+	/* Copy the pointers/colour from the victim to the replacement */
+	*new = *victim;
+
 	/* Set the surrounding nodes to point to the replacement */
-	__rb_change_child(victim, new, parent, root);
 	if (victim->rb_left)
 		rb_set_parent(victim->rb_left, new);
 	if (victim->rb_right)
 		rb_set_parent(victim->rb_right, new);
+	__rb_change_child(victim, new, parent, root);
+}
 
-	/* Copy the pointers/colour from the victim to the replacement */
-	*new = *victim;
+void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new,
+			    struct rb_root_cached *root)
+{
+	rb_replace_node(victim, new, &root->rb_root);
+
+	if (root->rb_leftmost == victim)
+		root->rb_leftmost = new;
 }
 
 static struct rb_node *rb_left_deepest_node(const struct rb_node *node)

tools/perf/Makefile.perf

···
 	$(call QUIET_INSTALL, python-scripts) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'; \
-		$(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \
-		$(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \
+		$(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \
+		$(INSTALL) scripts/python/*.py -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \
 		$(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
 endif
 	$(call QUIET_INSTALL, perf_completion-script) \

tools/perf/builtin-annotate.c

···
 		 * the DSO?
 		 */
 		if (al->sym != NULL) {
-			rb_erase(&al->sym->rb_node,
+			rb_erase_cached(&al->sym->rb_node,
 				 &al->map->dso->symbols);
 			symbol__delete(al->sym);
 			dso__reset_find_symbol_cache(al->map->dso);
···
 				    struct perf_evsel *evsel,
 				    struct perf_annotate *ann)
 {
-	struct rb_node *nd = rb_first(&hists->entries), *next;
+	struct rb_node *nd = rb_first_cached(&hists->entries), *next;
 	int key = K_RIGHT;
 
 	while (nd) {

tools/perf/builtin-c2c.c

···
 
 static int hists__iterate_cb(struct hists *hists, hists__resort_cb_t cb)
 {
-	struct rb_node *next = rb_first(&hists->entries);
+	struct rb_node *next = rb_first_cached(&hists->entries);
 	int ret = 0;
 
 	while (next) {
···
 	if (WARN_ONCE(ret, "failed to setup sort entries\n"))
 		return;
 
-	nd = rb_first(&c2c.hists.hists.entries);
+	nd = rb_first_cached(&c2c.hists.hists.entries);
 
 	for (; nd; nd = rb_next(nd)) {
 		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
···
 static void c2c_browser__update_nr_entries(struct hist_browser *hb)
 {
 	u64 nr_entries = 0;
-	struct rb_node *nd = rb_first(&hb->hists->entries);
+	struct rb_node *nd = rb_first_cached(&hb->hists->entries);
 
 	while (nd) {
 		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);

tools/perf/builtin-diff.c

···
 
 static void hists__baseline_only(struct hists *hists)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *next;
 
 	if (hists__has(hists, need_collapse))
···
 	else
 		root = hists->entries_in;
 
-	next = rb_first(root);
+	next = rb_first_cached(root);
 	while (next != NULL) {
 		struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node_in);
 
 		next = rb_next(&he->rb_node_in);
 		if (!hist_entry__next_pair(he)) {
-			rb_erase(&he->rb_node_in, root);
+			rb_erase_cached(&he->rb_node_in, root);
 			hist_entry__delete(he);
 		}
 	}
···
 
 static void hists__precompute(struct hists *hists)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *next;
 
 	if (hists__has(hists, need_collapse))
···
 	else
 		root = hists->entries_in;
 
-	next = rb_first(root);
+	next = rb_first_cached(root);
 	while (next != NULL) {
 		struct hist_entry *he, *pair;
 		struct data__file *d;

tools/perf/builtin-probe.c

···
 
 #include "perf.h"
 #include "builtin.h"
+#include "namespaces.h"
 #include "util/util.h"
 #include "util/strlist.h"
 #include "util/strfilter.h"

tools/perf/builtin-report.c

···
 	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
 		struct threads *threads = &machine->threads[i];
 
-		for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) {
+		for (nd = rb_first_cached(&threads->entries); nd;
+		     nd = rb_next(nd)) {
 			task = tasks + itask++;
 
 			task->thread = rb_entry(nd, struct thread, rb_node);

tools/perf/builtin-sched.c

···
 	u64		 all_runtime;
 	u64		 all_count;
 	u64		 cpu_last_switched[MAX_CPUS];
-	struct rb_root	 atom_root, sorted_atom_root, merged_atom_root;
+	struct rb_root_cached atom_root, sorted_atom_root, merged_atom_root;
 	struct list_head sort_list, cmp_pid;
 	bool force;
 	bool skip_merge;
···
 struct idle_thread_runtime {
 	struct thread_runtime	tr;
 	struct thread		*last_thread;
-	struct rb_root		sorted_root;
+	struct rb_root_cached	sorted_root;
 	struct callchain_root	callchain;
 	struct callchain_cursor	cursor;
 };
···
 }
 
 static struct work_atoms *
-thread_atoms_search(struct rb_root *root, struct thread *thread,
+thread_atoms_search(struct rb_root_cached *root, struct thread *thread,
 			 struct list_head *sort_list)
 {
-	struct rb_node *node = root->rb_node;
+	struct rb_node *node = root->rb_root.rb_node;
 	struct work_atoms key = { .thread = thread };
 
 	while (node) {
···
 }
 
 static void
-__thread_latency_insert(struct rb_root *root, struct work_atoms *data,
+__thread_latency_insert(struct rb_root_cached *root, struct work_atoms *data,
 			 struct list_head *sort_list)
 {
-	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct rb_node **new = &(root->rb_root.rb_node), *parent = NULL;
+	bool leftmost = true;
 
 	while (*new) {
 		struct work_atoms *this;
···
 
 		if (cmp > 0)
 			new = &((*new)->rb_left);
-		else
+		else {
 			new = &((*new)->rb_right);
+			leftmost = false;
+		}
 	}
 
 	rb_link_node(&data->node, parent, new);
-	rb_insert_color(&data->node, root);
+	rb_insert_color_cached(&data->node, root, leftmost);
 }
 
 static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread)
···
 static void perf_sched__sort_lat(struct perf_sched *sched)
 {
 	struct rb_node *node;
-	struct rb_root *root = &sched->atom_root;
+	struct rb_root_cached *root = &sched->atom_root;
 again:
 	for (;;) {
 		struct work_atoms *data;
-		node = rb_first(root);
+		node = rb_first_cached(root);
 		if (!node)
 			break;
 
-		rb_erase(node, root);
+		rb_erase_cached(node, root);
 		data = rb_entry(node, struct work_atoms, node);
 		__thread_latency_insert(&sched->sorted_atom_root, data, &sched->sort_list);
 	}
···
 	return ret;
 }
 
-static size_t timehist_print_idlehist_callchain(struct rb_root *root)
+static size_t timehist_print_idlehist_callchain(struct rb_root_cached *root)
 {
 	size_t ret = 0;
 	FILE *fp = stdout;
 	struct callchain_node *chain;
-	struct rb_node *rb_node = rb_first(root);
+	struct rb_node *rb_node = rb_first_cached(root);
 
 	printf("  %16s  %8s  %s\n", "Idle time (msec)", "Count", "Callchains");
 	printf("  %.16s  %.8s  %.50s\n", graph_dotted_line, graph_dotted_line,
···
 			if (itr == NULL)
 				continue;
 
-			callchain_param.sort(&itr->sorted_root, &itr->callchain,
+			callchain_param.sort(&itr->sorted_root.rb_root, &itr->callchain,
 					     0, &callchain_param);
 
 			printf("  CPU %2d:", i);
···
 	}
 }
 
-static void __merge_work_atoms(struct rb_root *root, struct work_atoms *data)
+static void __merge_work_atoms(struct rb_root_cached *root, struct work_atoms *data)
 {
-	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct rb_node **new = &(root->rb_root.rb_node), *parent = NULL;
 	struct work_atoms *this;
 	const char *comm = thread__comm_str(data->thread), *this_comm;
+	bool leftmost = true;
 
 	while (*new) {
 		int cmp;
···
 			new = &((*new)->rb_left);
 		} else if (cmp < 0) {
 			new = &((*new)->rb_right);
+			leftmost = false;
 		} else {
 			this->num_merged++;
 			this->total_runtime += data->total_runtime;
···
 
 	data->num_merged++;
 	rb_link_node(&data->node, parent, new);
-	rb_insert_color(&data->node, root);
+	rb_insert_color_cached(&data->node, root, leftmost);
 }
 
 static void perf_sched__merge_lat(struct perf_sched *sched)
···
 	if (sched->skip_merge)
 		return;
 
-	while ((node = rb_first(&sched->atom_root))) {
-		rb_erase(node, &sched->atom_root);
+	while ((node = rb_first_cached(&sched->atom_root))) {
+		rb_erase_cached(node, &sched->atom_root);
 		data = rb_entry(node, struct work_atoms, node);
 		__merge_work_atoms(&sched->merged_atom_root, data);
 	}
···
 	printf("  Task                  |   Runtime ms  | Switches | Average delay ms | Maximum delay ms | Maximum delay at       |\n");
 	printf(" -----------------------------------------------------------------------------------------------------------------\n");
 
-	next = rb_first(&sched->sorted_atom_root);
+	next = rb_first_cached(&sched->sorted_atom_root);
 
 	while (next) {
 		struct work_atoms *work_list;

tools/perf/builtin-top.c

···
 	if (p)
 		*p = 0;
 
-	next = rb_first(&hists->entries);
+	next = rb_first_cached(&hists->entries);
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node);
 		if (n->ms.sym && !strcmp(buf, n->ms.sym->name)) {

tools/perf/builtin-trace.c

···
 				goto init_augmented_syscall_tp;
 			}
 
-			if (strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_enter") == 0) {
+			if (trace.syscalls.events.augmented->priv == NULL &&
+			    strstr(perf_evsel__name(evsel), "syscalls:sys_enter")) {
 				struct perf_evsel *augmented = trace.syscalls.events.augmented;
 				if (perf_evsel__init_augmented_syscall_tp(augmented, evsel) ||
 				    perf_evsel__init_augmented_syscall_tp_args(augmented))

tools/perf/examples/bpf/augmented_raw_syscalls.c

···
 #include <pid_filter.h>
 
 /* bpf-output associated map */
-struct bpf_map SEC("maps") __augmented_syscalls__ = {
-	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(u32),
-	.max_entries = __NR_CPUS__,
-};
+bpf_map(__augmented_syscalls__, PERF_EVENT_ARRAY, int, u32, __NR_CPUS__);
 
 struct syscall {
 	bool	enabled;
 };
 
-struct bpf_map SEC("maps") syscalls = {
-	.type	     = BPF_MAP_TYPE_ARRAY,
-	.key_size    = sizeof(int),
-	.value_size  = sizeof(struct syscall),
-	.max_entries = 512,
-};
+bpf_map(syscalls, ARRAY, int, struct syscall, 512);
 
 struct syscall_enter_args {
 	unsigned long long common_tp_fields;

tools/perf/examples/bpf/augmented_syscalls.c

···
 #include <stdio.h>
 #include <linux/socket.h>
 
-struct bpf_map SEC("maps") __augmented_syscalls__ = {
-       .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
-       .key_size = sizeof(int),
-       .value_size = sizeof(u32),
-       .max_entries = __NR_CPUS__,
-};
+/* bpf-output associated map */
+bpf_map(__augmented_syscalls__, PERF_EVENT_ARRAY, int, u32, __NR_CPUS__);
 
 struct syscall_exit_args {
 	unsigned long long common_tp_fields;

tools/perf/examples/bpf/etcsnoop.c

···
 
 #include <stdio.h>
 
-struct bpf_map SEC("maps") __augmented_syscalls__ = {
-       .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
-       .key_size = sizeof(int),
-       .value_size = sizeof(u32),
-       .max_entries = __NR_CPUS__,
-};
+/* bpf-output associated map */
+bpf_map(__augmented_syscalls__, PERF_EVENT_ARRAY, int, u32, __NR_CPUS__);
 
 struct augmented_filename {
 	int	size;

tools/perf/include/bpf/bpf.h

···
         unsigned int numa_node;
 };
 
+#define bpf_map(name, _type, type_key, type_val, _max_entries)	\
+struct bpf_map SEC("maps") name = {				\
+	.type	     = BPF_MAP_TYPE_##_type,			\
+	.key_size    = sizeof(type_key),			\
+	.value_size  = sizeof(type_val),			\
+	.max_entries = _max_entries,				\
+}
+
 /*
  * FIXME: this should receive .max_entries as a parameter, as careful
  *	  tuning of these limits is needed to avoid hitting limits that
···
  *	  For the current need, 'perf trace --filter-pids', 64 should
  *	  be good enough, but this surely needs to be revisited.
  */
-#define pid_map(name, value_type)		\
-struct bpf_map SEC("maps") name = {		\
-	.type	     = BPF_MAP_TYPE_HASH,	\
-	.key_size    = sizeof(pid_t),		\
-	.value_size  = sizeof(value_type),	\
-	.max_entries = 64,			\
-}
+#define pid_map(name, value_type) bpf_map(name, HASH, pid_t, value_type, 64)
 
 static int (*bpf_map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags) = (void *)BPF_FUNC_map_update_elem;
 static void *(*bpf_map_lookup_elem)(struct bpf_map *map, void *key) = (void *)BPF_FUNC_map_lookup_elem;

tools/perf/scripts/python/exported-sql-viewer.py

···
-#!/usr/bin/python2
 # SPDX-License-Identifier: GPL-2.0
 # exported-sql-viewer.py: view data from sql database
 # Copyright (c) 2014-2018, Intel Corporation.

tools/perf/scripts/python/sched-migration.py

···
-#!/usr/bin/python
-#
 # Cpu task migration overview toy
 #
 # Copyright (C) 2010 Frederic Weisbecker <[e-mail]>

tools/perf/scripts/python/stat-cpi.py

···
-#!/usr/bin/env python
 # SPDX-License-Identifier: GPL-2.0
 
 data    = {}

tools/perf/tests/attr.py

···
-#! /usr/bin/python
 # SPDX-License-Identifier: GPL-2.0
+
+from __future__ import print_function
 
 import os
 import sys
···
 import tempfile
 import logging
 import shutil
-import ConfigParser
+
+try:
+    import configparser
+except ImportError:
+    import ConfigParser as configparser
 
 def data_equal(a, b):
     # Allow multiple values in assignment separated by '|'
···
     def equal(self, other):
         for t in Event.terms:
             log.debug("      [%s] %s %s" % (t, self[t], other[t]));
-            if not self.has_key(t) or not other.has_key(t):
+            if t not in self or t not in other:
                 return False
             if not data_equal(self[t], other[t]):
                 return False
         return True
 
     def optional(self):
-        if self.has_key('optional') and self['optional'] == '1':
+        if 'optional' in self and self['optional'] == '1':
             return True
         return False
 
     def diff(self, other):
         for t in Event.terms:
-            if not self.has_key(t) or not other.has_key(t):
+            if t not in self or t not in other:
                 continue
             if not data_equal(self[t], other[t]):
                 log.warning("expected %s=%s, got %s" % (t, self[t], other[t]))
···
 #   - expected values assignments
 class Test(object):
     def __init__(self, path, options):
-        parser = ConfigParser.SafeConfigParser()
+        parser = configparser.SafeConfigParser()
         parser.read(path)
 
         log.warning("running '%s'" % path)
···
         return True
 
     def load_events(self, path, events):
-        parser_event = ConfigParser.SafeConfigParser()
+        parser_event = configparser.SafeConfigParser()
         parser_event.read(path)
 
         # The event record section header contains 'event' word,
···
             # Read parent event if there's any
             if (':' in section):
                 base = section[section.index(':') + 1:]
-                parser_base = ConfigParser.SafeConfigParser()
+                parser_base = configparser.SafeConfigParser()
                 parser_base.read(self.test_dir + '/' + base)
                 base_items = parser_base.items('event')
 
···
     for f in glob.glob(options.test_dir + '/' + options.test):
         try:
             Test(f, options).run()
-        except Unsup, obj:
+        except Unsup as obj:
             log.warning("unsupp  %s" % obj.getMsg())
-        except Notest, obj:
+        except Notest as obj:
             log.warning("skipped %s" % obj.getMsg())
 
 def setup_log(verbose):
···
     parser.add_option("-p", "--perf",
                       action="store", type="string", dest="perf")
     parser.add_option("-v", "--verbose",
-                      action="count", dest="verbose")
+                      default=0, action="count", dest="verbose")
 
     options, args = parser.parse_args()
     if args:
···
     setup_log(options.verbose)
 
     if not options.test_dir:
-        print 'FAILED no -d option specified'
+        print('FAILED no -d option specified')
         sys.exit(-1)
 
     if not options.test:
···
     try:
         run_tests(options)
 
-    except Fail, obj:
-        print "FAILED %s" % obj.getMsg();
+    except Fail as obj:
+        print("FAILED %s" % obj.getMsg())
         sys.exit(-1)
 
     sys.exit(0)

tools/perf/tests/hists_common.c

···
 void print_hists_in(struct hists *hists)
 {
 	int i = 0;
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *node;
 
 	if (hists__has(hists, need_collapse))
···
 		root = hists->entries_in;
 
 	pr_info("----- %s --------\n", __func__);
-	node = rb_first(root);
+	node = rb_first_cached(root);
 	while (node) {
 		struct hist_entry *he;
 
···
 void print_hists_out(struct hists *hists)
 {
 	int i = 0;
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *node;
 
 	root = &hists->entries;
 
 	pr_info("----- %s --------\n", __func__);
-	node = rb_first(root);
+	node = rb_first_cached(root);
 	while (node) {
 		struct hist_entry *he;
 

tools/perf/tests/hists_cumulate.c

···
 static void del_hist_entries(struct hists *hists)
 {
 	struct hist_entry *he;
-	struct rb_root *root_in;
-	struct rb_root *root_out;
+	struct rb_root_cached *root_in;
+	struct rb_root_cached *root_out;
 	struct rb_node *node;
 
 	if (hists__has(hists, need_collapse))
···
 
 	root_out = &hists->entries;
 
-	while (!RB_EMPTY_ROOT(root_out)) {
-		node = rb_first(root_out);
+	while (!RB_EMPTY_ROOT(&root_out->rb_root)) {
+		node = rb_first_cached(root_out);
 
 		he = rb_entry(node, struct hist_entry, rb_node);
-		rb_erase(node, root_out);
-		rb_erase(&he->rb_node_in, root_in);
+		rb_erase_cached(node, root_out);
+		rb_erase_cached(&he->rb_node_in, root_in);
 		hist_entry__delete(he);
 	}
 }
···
 		print_hists_out(hists);
 	}
 
-	root = &hists->entries;
+	root = &hists->entries.rb_root;
 	for (node = rb_first(root), i = 0;
 	     node && (he = rb_entry(node, struct hist_entry, rb_node));
 	     node = rb_next(node), i++) {

tools/perf/tests/hists_link.c

···
 static int __validate_match(struct hists *hists)
 {
 	size_t count = 0;
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *node;
 
 	/*
···
 	else
 		root = hists->entries_in;
 
-	node = rb_first(root);
+	node = rb_first_cached(root);
 	while (node) {
 		struct hist_entry *he;
 
···
 	size_t count = 0;
 	size_t count_pair = 0;
 	size_t count_dummy = 0;
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *node;
 
 	/*
···
 	else
 		root = hists->entries_in;
 
-	node = rb_first(root);
+	node = rb_first_cached(root);
 	while (node) {
 		struct hist_entry *he;
 

tools/perf/tests/hists_output.c

···
 static void del_hist_entries(struct hists *hists)
 {
 	struct hist_entry *he;
-	struct rb_root *root_in;
-	struct rb_root *root_out;
+	struct rb_root_cached *root_in;
+	struct rb_root_cached *root_out;
 	struct rb_node *node;
 
 	if (hists__has(hists, need_collapse))
···
 
 	root_out = &hists->entries;
 
-	while (!RB_EMPTY_ROOT(root_out)) {
-		node = rb_first(root_out);
+	while (!RB_EMPTY_ROOT(&root_out->rb_root)) {
+		node = rb_first_cached(root_out);
 
 		he = rb_entry(node, struct hist_entry, rb_node);
-		rb_erase(node, root_out);
-		rb_erase(&he->rb_node_in, root_in);
+		rb_erase_cached(node, root_out);
+		rb_erase_cached(&he->rb_node_in, root_in);
 		hist_entry__delete(he);
 	}
 }
···
 	int err;
 	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he;
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *node;
 
 	field_order = NULL;
···
 	}
 
 	root = &hists->entries;
-	node = rb_first(root);
+	node = rb_first_cached(root);
 	he = rb_entry(node, struct hist_entry, rb_node);
 	TEST_ASSERT_VAL("Invalid hist entry",
 			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") &&
···
 	int err;
 	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he;
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *node;
 
 	field_order = "overhead,cpu";
···
 	}
 
 	root = &hists->entries;
-	node = rb_first(root);
+	node = rb_first_cached(root);
 	he = rb_entry(node, struct hist_entry, rb_node);
 	TEST_ASSERT_VAL("Invalid hist entry",
 			CPU(he) == 1 && PID(he) == 100 && he->stat.period == 300);
···
 	int err;
 	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he;
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *node;
 
 	field_order = "comm,overhead,dso";
···
 	}
 
 	root = &hists->entries;
-	node = rb_first(root);
+	node = rb_first_cached(root);
 	he = rb_entry(node, struct hist_entry, rb_node);
 	TEST_ASSERT_VAL("Invalid hist entry",
 			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") &&
···
 	int err;
 	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he;
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *node;
 
 	field_order = "dso,sym,comm,overhead,dso";
···
 	}
 
 	root = &hists->entries;
-	node = rb_first(root);
+	node = rb_first_cached(root);
 	he = rb_entry(node, struct hist_entry, rb_node);
 	TEST_ASSERT_VAL("Invalid hist entry",
 			!strcmp(DSO(he), "perf") && !strcmp(SYM(he), "cmd_record") &&
···
 	int err;
 	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he;
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *node;
 
 	field_order = "cpu,pid,comm,dso,sym";
···
 	}
 
 	root = &hists->entries;
-	node = rb_first(root);
+	node = rb_first_cached(root);
 	he = rb_entry(node, struct hist_entry, rb_node);
 
 	TEST_ASSERT_VAL("Invalid hist entry",

tools/perf/ui/browsers/hists.c

···
 	struct hists *hists = browser->hists;
 	int unfolded_rows = 0;
 
-	for (nd = rb_first(&hists->entries);
+	for (nd = rb_first_cached(&hists->entries);
 	     (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL;
 	     nd = rb_hierarchy_next(nd)) {
 		struct hist_entry *he =
···
 	if (he->has_no_entry)
 		return 1;
 
-	node = rb_first(&he->hroot_out);
+	node = rb_first_cached(&he->hroot_out);
 	while (node) {
 		float percent;
 
···
 		he->has_children = !RB_EMPTY_ROOT(&he->sorted_chain);
 		callchain__init_have_children(&he->sorted_chain);
 	} else {
-		he->has_children = !RB_EMPTY_ROOT(&he->hroot_out);
+		he->has_children = !RB_EMPTY_ROOT(&he->hroot_out.rb_root);
 	}
 
 	he->init_have_children = true;
···
 	struct hist_entry *child;
 	int n = 0;
 
-	for (nd = rb_first(&he->hroot_out); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&he->hroot_out); nd; nd = rb_next(nd)) {
 		child = rb_entry(nd, struct hist_entry, rb_node);
 		percent = hist_entry__get_percent_limit(child);
 		if (!child->filtered && percent >= hb->min_pcnt)
···
 	struct rb_node *nd;
 	struct hist_entry *he;
 
-	nd = rb_first(&browser->hists->entries);
+	nd = rb_first_cached(&browser->hists->entries);
 	while (nd) {
 		he = rb_entry(nd, struct hist_entry, rb_node);
 
···
 		struct hist_browser *hb;
 
 		hb = container_of(browser, struct hist_browser, b);
-		browser->top = rb_first(&hb->hists->entries);
+		browser->top = rb_first_cached(&hb->hists->entries);
 	}
 }
 
···
 static void hist_browser__update_nr_entries(struct hist_browser *hb)
 {
 	u64 nr_entries = 0;
-	struct rb_node *nd = rb_first(&hb->hists->entries);
+	struct rb_node *nd = rb_first_cached(&hb->hists->entries);
 
 	if (hb->min_pcnt == 0 && !symbol_conf.report_hierarchy) {
 		hb->nr_non_filtered_entries = hb->hists->nr_non_filtered_entries;
···
 					       double percent)
 {
 	struct hist_entry *he;
-	struct rb_node *nd = rb_first(&hb->hists->entries);
+	struct rb_node *nd = rb_first_cached(&hb->hists->entries);
 	u64 total = hists__total_period(hb->hists);
 	u64 min_callchain_hits = total * (percent / 100);
 

tools/perf/ui/browsers/map.c

···
 #include <linux/bitops.h>
 #include "../../util/util.h"
 #include "../../util/debug.h"
+#include "../../util/map.h"
 #include "../../util/symbol.h"
 #include "../browser.h"
 #include "../helpline.h"

tools/perf/ui/gtk/annotate.c

···
 // SPDX-License-Identifier: GPL-2.0
 #include "gtk.h"
+#include "util/sort.h"
 #include "util/debug.h"
 #include "util/annotate.h"
 #include "util/evsel.h"

tools/perf/ui/gtk/hists.c

···
 
 	g_object_unref(GTK_TREE_MODEL(store));
 
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		GtkTreeIter iter;
 		u64 total = hists__total_period(h->hists);
···
 }
 
 static void perf_gtk__add_hierarchy_entries(struct hists *hists,
-					    struct rb_root *root,
+					    struct rb_root_cached *root,
 					    GtkTreeStore *store,
 					    GtkTreeIter *parent,
 					    struct perf_hpp *hpp,
···
 	u64 total = hists__total_period(hists);
 	int size;
 
-	for (node = rb_first(root); node; node = rb_next(node)) {
+	for (node = rb_first_cached(root); node; node = rb_next(node)) {
 		GtkTreeIter iter;
 		float percent;
 		char *bf;

tools/perf/ui/stdio/hist.c

···
 
 	indent = hists__overhead_width(hists) + 4;
 
-	for (nd = rb_first(&hists->entries); nd; nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD)) {
+	for (nd = rb_first_cached(&hists->entries); nd;
+	     nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		float percent;
 

tools/perf/util/annotate.c

···
 
 #include <errno.h>
 #include <inttypes.h>
+#include <libgen.h>
 #include "util.h"
 #include "ui/ui.h"
 #include "sort.h"

tools/perf/util/annotate.h

···
 
 #include <stdbool.h>
 #include <stdint.h>
+#include <stdio.h>
 #include <linux/types.h>
-#include "symbol.h"
-#include "hist.h"
-#include "sort.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <pthread.h>
 #include <asm/bug.h>
+#include "symbol_conf.h"
 
+struct hist_browser_timer;
+struct hist_entry;
 struct ins_ops;
+struct map;
+struct map_symbol;
+struct addr_map_symbol;
+struct option;
+struct perf_sample;
+struct perf_evsel;
+struct symbol;
 
 struct ins {
 	const char     *name;

tools/perf/util/block-range.c

···
 // SPDX-License-Identifier: GPL-2.0
 #include "block-range.h"
 #include "annotate.h"
+#include <assert.h>
+#include <stdlib.h>
 
 struct {
 	struct rb_root root;

tools/perf/util/block-range.h

···
 #ifndef __PERF_BLOCK_RANGE_H
 #define __PERF_BLOCK_RANGE_H
 
-#include "symbol.h"
+#include <stdbool.h>
+#include <linux/rbtree.h>
+#include <linux/types.h>
+
+struct symbol;
 
 /*
  * struct block_range - non-overlapping parts of basic blocks

tools/perf/util/bpf-event.c

···
 #include "bpf-event.h"
 #include "debug.h"
 #include "symbol.h"
+#include "machine.h"
 
 #define ptr_to_u64(ptr)    ((__u64)(unsigned long)(ptr))
 
···
 		*ksymbol_event = (struct ksymbol_event){
 			.header = {
 				.type = PERF_RECORD_KSYMBOL,
-				.size = sizeof(struct ksymbol_event),
+				.size = offsetof(struct ksymbol_event, name),
 			},
 			.addr = prog_addrs[i],
 			.len = prog_lens[i],
···
 
 		ksymbol_event->header.size += PERF_ALIGN(name_len + 1,
 							 sizeof(u64));
+
+		memset((void *)event + event->header.size, 0, machine->id_hdr_size);
+		event->header.size += machine->id_hdr_size;
 		err = perf_tool__process_synth_event(tool, event,
 						     machine, process);
 	}
···
 			.id = info.id,
 		};
 		memcpy(bpf_event->tag, prog_tags[i], BPF_TAG_SIZE);
+		memset((void *)event + event->header.size, 0, machine->id_hdr_size);
+		event->header.size += machine->id_hdr_size;
 		err = perf_tool__process_synth_event(tool, event,
 						     machine, process);
 	}
···
 	int err;
 	int fd;
 
-	event = malloc(sizeof(event->bpf_event) + KSYM_NAME_LEN);
+	event = malloc(sizeof(event->bpf_event) + KSYM_NAME_LEN + machine->id_hdr_size);
 	if (!event)
 		return -1;
 	while (true) {

tools/perf/util/branch.h

···
 #ifndef _PERF_BRANCH_H
 #define _PERF_BRANCH_H 1
 
+#include <stdio.h>
 #include <stdint.h>
-#include "../perf.h"
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+struct branch_flags {
+	u64 mispred:1;
+	u64 predicted:1;
+	u64 in_tx:1;
+	u64 abort:1;
+	u64 cycles:16;
+	u64 type:4;
+	u64 reserved:40;
+};
+
+struct branch_entry {
+	u64			from;
+	u64			to;
+	struct branch_flags	flags;
+};
+
+struct branch_stack {
+	u64			nr;
+	struct branch_entry	entries[0];
+};
 
 struct branch_type_stat {
 	bool	branch_to;
···
 	u64	cross_4k;
 	u64	cross_2m;
 };
-
-struct branch_flags;
 
 void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags,
 		       u64 from, u64 to);

tools/perf/util/build-id.c

···
 #include <sys/types.h>
 #include "build-id.h"
 #include "event.h"
+#include "namespaces.h"
 #include "symbol.h"
 #include "thread.h"
 #include <linux/kernel.h>
···
 	if (err)
 		return err;
 
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&session->machines.guests); nd;
+	     nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		err = machine__write_buildid_table(pos, fd);
 		if (err)
···
 	if (err)
 		return err;
 
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&session->machines.guests); nd;
+	     nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 
 		err = machine__hit_all_dsos(pos);
···
 
 	ret = machine__cache_build_ids(&session->machines.host);
 
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&session->machines.guests); nd;
+	     nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret |= machine__cache_build_ids(pos);
 	}
···
 	struct rb_node *nd;
 	bool ret = machine__read_build_ids(&session->machines.host, with_hits);
 
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&session->machines.guests); nd;
+	     nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret |= machine__read_build_ids(pos, with_hits);
 	}

tools/perf/util/build-id.h

···
 #define SBUILD_ID_SIZE	(BUILD_ID_SIZE * 2 + 1)
 
 #include "tool.h"
-#include "namespaces.h"
 #include <linux/types.h>
+
+struct nsinfo;
 
 extern struct perf_tool build_id__mark_dso_hit_ops;
 struct dso;

tools/perf/util/callchain.h

···
 #ifndef __PERF_CALLCHAIN_H
 #define __PERF_CALLCHAIN_H
 
-#include "../perf.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include "event.h"

tools/perf/util/color.h

···
 #define __PERF_COLOR_H
 
 #include <stdio.h>
+#include <stdarg.h>
 
 /* "\033[1;38;5;2xx;48;5;2xxm\0" is 23 bytes */
 #define COLOR_MAXLEN 24

tools/perf/util/comm.c

···
 #include <stdio.h>
 #include <string.h>
 #include <linux/refcount.h>
+#include <linux/rbtree.h>
 #include "rwsem.h"
 
 struct comm_str {

tools/perf/util/comm.h

···
 #ifndef __PERF_COMM_H
 #define __PERF_COMM_H
 
-#include "../perf.h"
-#include <linux/rbtree.h>
 #include <linux/list.h>
+#include <linux/types.h>
+#include <stdbool.h>
 
 struct comm_str;
 

tools/perf/util/dso.c

···
 #include <unistd.h>
 #include <errno.h>
 #include <fcntl.h>
+#include <libgen.h>
 #include "compress.h"
+#include "namespaces.h"
 #include "path.h"
 #include "symbol.h"
 #include "srcline.h"
···
 		strcpy(dso->name, name);
 		dso__set_long_name(dso, dso->name, false);
 		dso__set_short_name(dso, dso->name, false);
-		dso->symbols = dso->symbol_names = RB_ROOT;
+		dso->symbols = dso->symbol_names = RB_ROOT_CACHED;
 		dso->data.cache = RB_ROOT;
-		dso->inlined_nodes = RB_ROOT;
-		dso->srclines = RB_ROOT;
+		dso->inlined_nodes = RB_ROOT_CACHED;
+		dso->srclines = RB_ROOT_CACHED;
 		dso->data.fd = -1;
 		dso->data.status = DSO_DATA_STATUS_UNKNOWN;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
···
 	ret += fprintf(fp, "%sloaded, ", dso__loaded(dso) ? "" : "NOT ");
 	ret += dso__fprintf_buildid(dso, fp);
 	ret += fprintf(fp, ")\n");
-	for (nd = rb_first(&dso->symbols); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&dso->symbols); nd; nd = rb_next(nd)) {
 		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
 		ret += symbol__fprintf(pos, fp);
 	}

tools/perf/util/dso.h

···
 #include <linux/rbtree.h>
 #include <sys/types.h>
 #include <stdbool.h>
+#include <stdio.h>
 #include "rwsem.h"
 #include <linux/bitops.h>
-#include "map.h"
-#include "namespaces.h"
 #include "build-id.h"
+
+struct machine;
+struct map;
 
 enum dso_binary_type {
 	DSO_BINARY_TYPE__KALLSYMS = 0,
···
 	struct list_head node;
 	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
 	struct rb_root	 *root;		/* root of rbtree that rb_node is in */
-	struct rb_root	 symbols;
-	struct rb_root	 symbol_names;
-	struct rb_root	 inlined_nodes;
-	struct rb_root	 srclines;
+	struct rb_root_cached symbols;
+	struct rb_root_cached symbol_names;
+	struct rb_root_cached inlined_nodes;
+	struct rb_root_cached srclines;
 	struct {
 		u64		addr;
 		struct symbol	*symbol;
···
 
 static inline bool dso__has_symbols(const struct dso *dso)
 {
-	return !RB_EMPTY_ROOT(&dso->symbols);
+	return !RB_EMPTY_ROOT(&dso->symbols.rb_root);
 }
 
 bool dso__sorted_by_name(const struct dso *dso);

tools/perf/util/event.h

···
 	u64 ips[0];
 };
 
-struct branch_flags {
-	u64 mispred:1;
-	u64 predicted:1;
-	u64 in_tx:1;
-	u64 abort:1;
-	u64 cycles:16;
-	u64 type:4;
-	u64 reserved:40;
-};
-
-struct branch_entry {
-	u64			from;
-	u64			to;
-	struct branch_flags	flags;
-};
-
-struct branch_stack {
-	u64			nr;
-	struct branch_entry	entries[0];
-};
+struct branch_stack;
 
 enum {
 	PERF_IP_FLAG_BRANCH		= 1ULL << 0,

tools/perf/util/hist.c

···
 
 void hists__output_recalc_col_len(struct hists *hists, int max_rows)
 {
-	struct rb_node *next = rb_first(&hists->entries);
+	struct rb_node *next = rb_first_cached(&hists->entries);
 	struct hist_entry *n;
 	int row = 0;
 
···
 
 	if (!he->leaf) {
 		struct hist_entry *child;
-		struct rb_node *node = rb_first(&he->hroot_out);
+		struct rb_node *node = rb_first_cached(&he->hroot_out);
 		while (node) {
 			child = rb_entry(node, struct hist_entry, rb_node);
 			node = rb_next(node);
···
 
 static void hists__delete_entry(struct hists *hists, struct hist_entry *he)
 {
-	struct rb_root *root_in;
-	struct rb_root *root_out;
+	struct rb_root_cached *root_in;
+	struct rb_root_cached *root_out;
 
 	if (he->parent_he) {
 		root_in  = &he->parent_he->hroot_in;
···
 		root_out = &hists->entries;
 	}
 
-	rb_erase(&he->rb_node_in, root_in);
-	rb_erase(&he->rb_node, root_out);
+	rb_erase_cached(&he->rb_node_in, root_in);
+	rb_erase_cached(&he->rb_node, root_out);
 
 	--hists->nr_entries;
 	if (!he->filtered)
···
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
 {
-	struct rb_node *next = rb_first(&hists->entries);
+	struct rb_node *next = rb_first_cached(&hists->entries);
 	struct hist_entry *n;
 
 	while (next) {
···
 
 void hists__delete_entries(struct hists *hists)
 {
-	struct rb_node *next = rb_first(&hists->entries);
+	struct rb_node *next = rb_first_cached(&hists->entries);
 	struct hist_entry *n;
 
 	while (next) {
···
 	}
 	INIT_LIST_HEAD(&he->pairs.node);
 	thread__get(he->thread);
-	he->hroot_in  = RB_ROOT;
-	he->hroot_out = RB_ROOT;
+	he->hroot_in  = RB_ROOT_CACHED;
+	he->hroot_out = RB_ROOT_CACHED;
 
 	if (!symbol_conf.report_hierarchy)
 		he->leaf = true;
···
 	int64_t cmp;
 	u64 period = entry->stat.period;
 	u64 weight = entry->stat.weight;
+	bool leftmost = true;
 
-	p = &hists->entries_in->rb_node;
+	p = &hists->entries_in->rb_root.rb_node;
 
 	while (*p != NULL) {
 		parent = *p;
···
 
 		if (cmp < 0)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 
 	he = hist_entry__new(entry, sample_self);
···
 	hists->nr_entries++;
 
 	rb_link_node(&he->rb_node_in, parent, p);
-	rb_insert_color(&he->rb_node_in, hists->entries_in);
+	rb_insert_color_cached(&he->rb_node_in, hists->entries_in, leftmost);
 out:
 	if (sample_self)
 		he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
···
 }
 
 static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
-						 struct rb_root *root,
+						 struct rb_root_cached *root,
 						 struct hist_entry *he,
 						 struct hist_entry *parent_he,
 						 struct perf_hpp_list *hpp_list)
 {
-	struct rb_node **p = &root->rb_node;
+	struct rb_node **p = &root->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter, *new;
 	struct perf_hpp_fmt *fmt;
 	int64_t cmp;
+	bool leftmost = true;
 
 	while (*p != NULL) {
 		parent = *p;
···
 
 		if (cmp < 0)
 			p = &parent->rb_left;
-		else
+		else {
 			p = &parent->rb_right;
+			leftmost = false;
+		}
 	}
 
 	new = hist_entry__new(he, true);
···
 	}
 
 	rb_link_node(&new->rb_node_in, parent, p);
-	rb_insert_color(&new->rb_node_in, root);
+	rb_insert_color_cached(&new->rb_node_in, root, leftmost);
 	return new;
 }
 
 static int hists__hierarchy_insert_entry(struct hists *hists,
-					 struct rb_root *root,
+					 struct rb_root_cached *root,
 					 struct hist_entry *he)
 {
 	struct perf_hpp_list_node *node;
···
 }
 
 static int hists__collapse_insert_entry(struct hists *hists,
-					struct rb_root *root,
+					struct rb_root_cached *root,
 					struct hist_entry *he)
 {
-	struct rb_node **p = &root->rb_node;
+	struct rb_node **p = &root->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
 	int64_t cmp;
+	bool leftmost = true;
 
 	if (symbol_conf.report_hierarchy)
 		return hists__hierarchy_insert_entry(hists, root, he);
···
 
 		if (cmp < 0)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 	hists->nr_entries++;
 
 	rb_link_node(&he->rb_node_in, parent, p);
-	rb_insert_color(&he->rb_node_in, root);
+	rb_insert_color_cached(&he->rb_node_in, root, leftmost);
 	return 1;
 }
 
-struct rb_root *hists__get_rotate_entries_in(struct hists *hists)
+struct rb_root_cached *hists__get_rotate_entries_in(struct hists *hists)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 
 	pthread_mutex_lock(&hists->lock);
 
···
 
 int hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *next;
 	struct hist_entry *n;
 	int ret;
···
 
 	root = hists__get_rotate_entries_in(hists);
 
-	next = rb_first(root);
+	next = rb_first_cached(root);
 
 	while (next) {
 		if (session_done())
···
 		n = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&n->rb_node_in);
 
-		rb_erase(&n->rb_node_in, root);
+		rb_erase_cached(&n->rb_node_in, root);
 		ret = hists__collapse_insert_entry(hists, &hists->entries_collapsed, n);
 		if (ret < 0)
 			return -1;
···
 	struct rb_node *node;
 	struct hist_entry *he;
 
-	node = rb_first(&hists->entries);
+	node = rb_first_cached(&hists->entries);
 
 	hists->stats.total_period = 0;
 	hists->stats.total_non_filtered_period = 0;
···
 	}
 }
 
-static void hierarchy_insert_output_entry(struct rb_root *root,
+static void hierarchy_insert_output_entry(struct rb_root_cached *root,
 					  struct hist_entry *he)
 {
-	struct rb_node **p = &root->rb_node;
+	struct rb_node **p = &root->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
 	struct perf_hpp_fmt *fmt;
+	bool leftmost = true;
 
 	while (*p != NULL) {
 		parent = *p;
···
 
 		if (hist_entry__sort(he, iter) > 0)
 			p = &parent->rb_left;
-		else
+		else {
 			p = &parent->rb_right;
+			leftmost = false;
+		}
 	}
 
 	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, root);
+	rb_insert_color_cached(&he->rb_node, root, leftmost);
 
 	/* update column width of dynamic entry */
 	perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) {
···
 
 static void hists__hierarchy_output_resort(struct hists *hists,
 					   struct ui_progress *prog,
-					   struct rb_root *root_in,
-					   struct rb_root *root_out,
+					   struct rb_root_cached *root_in,
+					   struct rb_root_cached *root_out,
 					   u64 min_callchain_hits,
 					   bool use_callchain)
 {
 	struct rb_node *node;
 	struct hist_entry *he;
 
-	*root_out = RB_ROOT;
-	node = rb_first(root_in);
+	*root_out = RB_ROOT_CACHED;
+	node = rb_first_cached(root_in);
 
 	while (node) {
 		he = rb_entry(node, struct hist_entry, rb_node_in);
···
 	}
 }
 
-static void __hists__insert_output_entry(struct rb_root *entries,
+static void __hists__insert_output_entry(struct rb_root_cached *entries,
 					 struct hist_entry *he,
 					 u64 min_callchain_hits,
 					 bool use_callchain)
 {
-	struct rb_node **p = &entries->rb_node;
+	struct rb_node **p = &entries->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
 	struct perf_hpp_fmt *fmt;
+	bool leftmost = true;
 
 	if (use_callchain) {
 		if (callchain_param.mode == CHAIN_GRAPH_REL) {
···
 
 		if (hist_entry__sort(he, iter) > 0)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 
 	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, entries);
+	rb_insert_color_cached(&he->rb_node, entries, leftmost);
 
 	perf_hpp_list__for_each_sort_list(&perf_hpp_list, fmt) {
 		if (perf_hpp__is_dynamic_entry(fmt) &&
···
 static void output_resort(struct hists *hists, struct ui_progress *prog,
 			  bool use_callchain, hists__resort_cb_t cb)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *next;
 	struct hist_entry *n;
 	u64 callchain_total;
···
 	else
 		root = hists->entries_in;
 
-	next = rb_first(root);
-	hists->entries = RB_ROOT;
+	next = rb_first_cached(root);
+	hists->entries = RB_ROOT_CACHED;
 
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node_in);
···
 	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
 
 	while (can_goto_child(he, HMD_NORMAL)) {
-		node = rb_last(&he->hroot_out);
+		node = rb_last(&he->hroot_out.rb_root);
 		he = rb_entry(node, struct hist_entry, rb_node);
 	}
 	return node;
···
 	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
 
 	if (can_goto_child(he, hmd))
-		node = rb_first(&he->hroot_out);
+		node = rb_first_cached(&he->hroot_out);
 	else
 		node = rb_next(node);
 
···
 	if (he->leaf)
 		return false;
 
-	node = rb_first(&he->hroot_out);
+	node = rb_first_cached(&he->hroot_out);
 	child = rb_entry(node, struct hist_entry, rb_node);
 
 	while (node && child->filtered) {
···
 	hists__reset_filter_stats(hists);
 	hists__reset_col_len(hists);
 
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
 		if (filter(hists, h))
···
 	}
 }
 
-static void resort_filtered_entry(struct rb_root *root, struct hist_entry *he)
+static void resort_filtered_entry(struct rb_root_cached *root,
+				  struct hist_entry *he)
 {
-	struct rb_node **p = &root->rb_node;
+	struct rb_node **p = &root->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
-	struct rb_root new_root = RB_ROOT;
+	struct rb_root_cached new_root = RB_ROOT_CACHED;
 	struct rb_node *nd;
+	bool leftmost = true;
 
 	while (*p != NULL) {
 		parent = *p;
···
 
 		if (hist_entry__sort(he, iter) > 0)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 
 	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, root);
+	rb_insert_color_cached(&he->rb_node, root, leftmost);
 
 	if (he->leaf || he->filtered)
 		return;
 
-	nd = rb_first(&he->hroot_out);
+	nd = rb_first_cached(&he->hroot_out);
 	while (nd) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
 		nd = rb_next(nd);
-		rb_erase(&h->rb_node, &he->hroot_out);
+		rb_erase_cached(&h->rb_node, &he->hroot_out);
 
 		resort_filtered_entry(&new_root, h);
 	}
···
 static void hists__filter_hierarchy(struct hists *hists, int type, const void *arg)
 {
 	struct rb_node *nd;
-	struct rb_root new_root = RB_ROOT;
+	struct rb_root_cached new_root = RB_ROOT_CACHED;
 
 	hists->stats.nr_non_filtered_samples = 0;
 
 	hists__reset_filter_stats(hists);
 	hists__reset_col_len(hists);
 
-	nd = rb_first(&hists->entries);
+	nd = rb_first_cached(&hists->entries);
 	while (nd) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		int ret;
···
 	 * resort output after applying a new filter since filter in a lower
 	 * hierarchy can change periods in a upper hierarchy.
 	 */
-	nd = rb_first(&hists->entries);
+	nd = rb_first_cached(&hists->entries);
 	while (nd) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
 		nd = rb_next(nd);
-		rb_erase(&h->rb_node, &hists->entries);
+		rb_erase_cached(&h->rb_node, &hists->entries);
 
 		resort_filtered_entry(&new_root, h);
 	}
···
 static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 						 struct hist_entry *pair)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
 	int64_t cmp;
+	bool leftmost = true;
 
 	if (hists__has(hists, need_collapse))
 		root = &hists->entries_collapsed;
 	else
 		root = hists->entries_in;
 
-	p = &root->rb_node;
+	p = &root->rb_root.rb_node;
 
 	while (*p != NULL) {
 		parent = *p;
···
 
 		if (cmp < 0)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 
 	he = hist_entry__new(pair, true);
···
 		if (symbol_conf.cumulate_callchain)
 			memset(he->stat_acc, 0, sizeof(he->stat));
 		rb_link_node(&he->rb_node_in, parent, p);
-		rb_insert_color(&he->rb_node_in, root);
+		rb_insert_color_cached(&he->rb_node_in, root, leftmost);
 		hists__inc_stats(hists, he);
 		he->dummy = true;
 	}
···
 }
 
 static struct hist_entry *add_dummy_hierarchy_entry(struct hists *hists,
-						    struct rb_root *root,
+						    struct rb_root_cached *root,
 						    struct hist_entry *pair)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
 	struct perf_hpp_fmt *fmt;
+	bool leftmost = true;
 
-	p = &root->rb_node;
+	p = &root->rb_root.rb_node;
 	while (*p != NULL) {
 		int64_t cmp = 0;
 
···
 
 		if (cmp < 0)
 			p = &parent->rb_left;
-		else
+		else {
 			p = &parent->rb_right;
+			leftmost = false;
+		}
 	}
 
 	he = hist_entry__new(pair, true);
 	if (he) {
 		rb_link_node(&he->rb_node_in, parent, p);
-		rb_insert_color(&he->rb_node_in, root);
+		rb_insert_color_cached(&he->rb_node_in, root, leftmost);
 
 		he->dummy = true;
 		he->hists = hists;
···
 	struct rb_node *n;
 
 	if (hists__has(hists, need_collapse))
-		n = hists->entries_collapsed.rb_node;
+		n = hists->entries_collapsed.rb_root.rb_node;
 	else
-		n = hists->entries_in->rb_node;
+		n = hists->entries_in->rb_root.rb_node;
 
 	while (n) {
 		struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node_in);
···
 	return NULL;
 }
 
-static struct hist_entry *hists__find_hierarchy_entry(struct rb_root *root,
+static struct hist_entry *hists__find_hierarchy_entry(struct rb_root_cached *root,
 						      struct hist_entry *he)
 {
-	struct rb_node *n = root->rb_node;
+	struct rb_node *n = root->rb_root.rb_node;
 
 	while (n) {
 		struct hist_entry *iter;
···
 	return NULL;
 }
 
-static void hists__match_hierarchy(struct rb_root *leader_root,
-				   struct rb_root *other_root)
+static void hists__match_hierarchy(struct rb_root_cached *leader_root,
+				   struct rb_root_cached *other_root)
 {
 	struct rb_node *nd;
 	struct hist_entry *pos, *pair;
 
-	for (nd = rb_first(leader_root); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(leader_root); nd; nd = rb_next(nd)) {
 		pos  = rb_entry(nd, struct hist_entry, rb_node_in);
 		pair = hists__find_hierarchy_entry(other_root, pos);
 
···
  */
 void hists__match(struct hists *leader, struct hists *other)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *nd;
 	struct hist_entry *pos, *pair;
 
···
 	else
 		root = leader->entries_in;
 
-	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(root); nd; nd = rb_next(nd)) {
 		pos  = rb_entry(nd, struct hist_entry, rb_node_in);
 		pair = hists__find_entry(other, pos);
 
···
 
 static int hists__link_hierarchy(struct hists *leader_hists,
 				 struct hist_entry *parent,
-				 struct rb_root *leader_root,
-				 struct rb_root *other_root)
+				 struct rb_root_cached *leader_root,
+				 struct rb_root_cached *other_root)
 {
 	struct rb_node *nd;
 	struct hist_entry *pos, *leader;
 
-	for (nd = rb_first(other_root); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(other_root); nd; nd = rb_next(nd)) {
 		pos = rb_entry(nd, struct hist_entry, rb_node_in);
 
 		if (hist_entry__has_pairs(pos)) {
···
  */
 int hists__link(struct hists *leader, struct hists *other)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *nd;
 	struct hist_entry *pos, *pair;
 
···
 	else
 		root = other->entries_in;
 
-	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(root); nd; nd = rb_next(nd)) {
 		pos = rb_entry(nd, struct hist_entry, rb_node_in);
 
 		if (!hist_entry__has_pairs(pos)) {
···
 int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list)
 {
 	memset(hists, 0, sizeof(*hists));
-	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
+	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT_CACHED;
 	hists->entries_in = &hists->entries_in_array[0];
-	hists->entries_collapsed = RB_ROOT;
-	hists->entries = RB_ROOT;
+	hists->entries_collapsed = RB_ROOT_CACHED;
+	hists->entries = RB_ROOT_CACHED;
 	pthread_mutex_init(&hists->lock, NULL);
 	hists->socket_filter = -1;
 	hists->hpp_list = hpp_list;
···
 	return 0;
 }
 
-static void hists__delete_remaining_entries(struct rb_root *root)
+static void hists__delete_remaining_entries(struct rb_root_cached *root)
 {
 	struct rb_node *node;
 	struct hist_entry *he;
 
-	while (!RB_EMPTY_ROOT(root)) {
-		node = rb_first(root);
-		rb_erase(node, root);
+	while (!RB_EMPTY_ROOT(&root->rb_root)) {
+		node = rb_first_cached(root);
+		rb_erase_cached(node, root);
 
 		he = rb_entry(node, struct hist_entry, rb_node_in);
 		hist_entry__delete(he);

tools/perf/util/hist.h

···
 struct dso;
 
 struct hists {
-	struct rb_root		entries_in_array[2];
-	struct rb_root		*entries_in;
-	struct rb_root		entries;
-	struct rb_root		entries_collapsed;
+	struct rb_root_cached	entries_in_array[2];
+	struct rb_root_cached	*entries_in;
+	struct rb_root_cached	entries;
+	struct rb_root_cached	entries_collapsed;
 	u64			nr_entries;
 	u64			nr_non_filtered_entries;
 	u64			callchain_period;
···
 int hists__init(void);
 int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list);
 
-struct rb_root *hists__get_rotate_entries_in(struct hists *hists);
+struct rb_root_cached *hists__get_rotate_entries_in(struct hists *hists);
 
 struct perf_hpp {
 	char *buf;

tools/perf/util/intlist.h

···
 /* For intlist iteration */
 static inline struct int_node *intlist__first(struct intlist *ilist)
 {
-	struct rb_node *rn = rb_first(&ilist->rblist.entries);
+	struct rb_node *rn = rb_first_cached(&ilist->rblist.entries);
 	return rn ? rb_entry(rn, struct int_node, rb_node) : NULL;
 }
 static inline struct int_node *intlist__next(struct int_node *in)

tools/perf/util/jitdump.c

···
 #include <sys/sysmacros.h>
 #include <sys/types.h>
 #include <errno.h>
+#include <libgen.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>

tools/perf/util/machine.c

···
 
 	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
 		struct threads *threads = &machine->threads[i];
-		threads->entries = RB_ROOT;
+		threads->entries = RB_ROOT_CACHED;
 		init_rwsem(&threads->lock);
 		threads->nr = 0;
 		INIT_LIST_HEAD(&threads->dead);
···
 	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
 		struct threads *threads = &machine->threads[i];
 		down_write(&threads->lock);
-		nd = rb_first(&threads->entries);
+		nd = rb_first_cached(&threads->entries);
 		while (nd) {
 			struct thread *t = rb_entry(nd, struct thread, rb_node);
 
···
 void machines__init(struct machines *machines)
 {
 	machine__init(&machines->host, "", HOST_KERNEL_ID);
-	machines->guests = RB_ROOT;
+	machines->guests = RB_ROOT_CACHED;
 }
 
 void machines__exit(struct machines *machines)
···
 struct machine *machines__add(struct machines *machines, pid_t pid,
 			      const char *root_dir)
 {
-	struct rb_node **p = &machines->guests.rb_node;
+	struct rb_node **p = &machines->guests.rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct machine *pos, *machine = malloc(sizeof(*machine));
+	bool leftmost = true;
 
 	if (machine == NULL)
 		return NULL;
···
 		pos = rb_entry(parent, struct machine, rb_node);
 		if (pid < pos->pid)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 
 	rb_link_node(&machine->rb_node, parent, p);
-	rb_insert_color(&machine->rb_node, &machines->guests);
+	rb_insert_color_cached(&machine->rb_node, &machines->guests, leftmost);
 
 	return machine;
 }
···
 
 	machines->host.comm_exec = comm_exec;
 
-	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *machine = rb_entry(nd, struct machine, rb_node);
 
 		machine->comm_exec = comm_exec;
···
 
 struct machine *machines__find(struct machines *machines, pid_t pid)
 {
-	struct rb_node **p = &machines->guests.rb_node;
+	struct rb_node **p = &machines->guests.rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct machine *machine;
 	struct machine *default_machine = NULL;
···
 {
 	struct rb_node *nd;
 
-	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		process(pos, data);
 	}
···
 
 	machines->host.id_hdr_size = id_hdr_size;
 
-	for (node = rb_first(&machines->guests); node; node = rb_next(node)) {
+	for (node = rb_first_cached(&machines->guests); node;
+	     node = rb_next(node)) {
 		machine = rb_entry(node, struct machine, rb_node);
 		machine->id_hdr_size = id_hdr_size;
 	}
···
 						  pid_t pid, pid_t tid,
 						  bool create)
 {
-	struct rb_node **p = &threads->entries.rb_node;
+	struct rb_node **p = &threads->entries.rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct thread *th;
+	bool leftmost = true;
 
 	th = threads__get_last_match(threads, machine, pid, tid);
 	if (th)
···
 
 		if (tid < th->tid)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 
 	if (!create)
···
 	th = thread__new(pid, tid);
 	if (th != NULL) {
 		rb_link_node(&th->rb_node, parent, p);
-		rb_insert_color(&th->rb_node, &threads->entries);
+		rb_insert_color_cached(&th->rb_node, &threads->entries, leftmost);
 
 		/*
 		 * We have to initialize map_groups separately
···
 		 * leader and that would screwed the rb tree.
 		 */
 		if (thread__init_map_groups(th, machine)) {
-			rb_erase_init(&th->rb_node, &threads->entries);
+			rb_erase_cached(&th->rb_node, &threads->entries);
 			RB_CLEAR_NODE(&th->rb_node);
 			thread__put(th);
 			return NULL;
···
 	struct rb_node *nd;
 	size_t ret = __dsos__fprintf(&machines->host.dsos.head, fp);
 
-	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret += __dsos__fprintf(&pos->dsos.head, fp);
 	}
···
 	struct rb_node *nd;
 	size_t ret = machine__fprintf_dsos_buildid(&machines->host, fp, skip, parm);
 
-	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret += machine__fprintf_dsos_buildid(pos, fp, skip, parm);
 	}
···
 
 		ret = fprintf(fp, "Threads: %u\n", threads->nr);
 
-		for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) {
+		for (nd = rb_first_cached(&threads->entries); nd;
+		     nd = rb_next(nd)) {
 			struct thread *pos = rb_entry(nd, struct thread, rb_node);
 
 			ret += thread__fprintf(pos, fp);
···
 
 void machines__destroy_kernel_maps(struct machines *machines)
 {
-	struct rb_node *next = rb_first(&machines->guests);
+	struct rb_node *next = rb_first_cached(&machines->guests);
 
 	machine__destroy_kernel_maps(&machines->host);
 
···
 		struct machine *pos = rb_entry(next, struct machine, rb_node);
 
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, &machines->guests);
+		rb_erase_cached(&pos->rb_node, &machines->guests);
 		machine__delete(pos);
 	}
 }
···
 	BUG_ON(refcount_read(&th->refcnt) == 0);
 	if (lock)
 		down_write(&threads->lock);
-	rb_erase_init(&th->rb_node, &threads->entries);
+	rb_erase_cached(&th->rb_node, &threads->entries);
 	RB_CLEAR_NODE(&th->rb_node);
 	--threads->nr;
 	/*
···
 
 	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
 		threads = &machine->threads[i];
-		for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) {
+		for (nd = rb_first_cached(&threads->entries); nd;
+		     nd = rb_next(nd)) {
 			thread = rb_entry(nd, struct thread, rb_node);
 			rc = fn(thread, priv);
 			if (rc != 0)
···
 	if (rc != 0)
 		return rc;
 
-	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *machine = rb_entry(nd, struct machine, rb_node);
 
 		rc = machine__for_each_thread(machine, fn, priv);

tools/perf/util/machine.h

···
 #define THREADS__TABLE_SIZE	(1 << THREADS__TABLE_BITS)
 
 struct threads {
-	struct rb_root	  entries;
-	struct rw_semaphore lock;
-	unsigned int	  nr;
-	struct list_head  dead;
-	struct thread	  *last_match;
+	struct rb_root_cached  entries;
+	struct rw_semaphore    lock;
+	unsigned int	       nr;
+	struct list_head       dead;
+	struct thread	       *last_match;
 };
 
 struct machine {
···
 
 struct machines {
 	struct machine host;
-	struct rb_root guests;
+	struct rb_root_cached guests;
 };
 
 void machines__init(struct machines *machines);

tools/perf/util/map.c

···
 
 void map__fixup_start(struct map *map)
 {
-	struct rb_root *symbols = &map->dso->symbols;
-	struct rb_node *nd = rb_first(symbols);
+	struct rb_root_cached *symbols = &map->dso->symbols;
+	struct rb_node *nd = rb_first_cached(symbols);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
 		map->start = sym->start;
···
 
 void map__fixup_end(struct map *map)
 {
-	struct rb_root *symbols = &map->dso->symbols;
-	struct rb_node *nd = rb_last(symbols);
+	struct rb_root_cached *symbols = &map->dso->symbols;
+	struct rb_node *nd = rb_last(&symbols->rb_root);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
 		map->end = sym->end;

tools/perf/util/metricgroup.c

···
 	else if (metrics && !raw)
 		printf("\nMetrics:\n\n");
 
-	for (node = rb_first(&groups.entries); node; node = next) {
+	for (node = rb_first_cached(&groups.entries); node; node = next) {
 		struct mep *me = container_of(node, struct mep, nd);
 
 		if (metricgroups)

tools/perf/util/probe-event.c

···
 
 #include "util.h"
 #include "event.h"
+#include "namespaces.h"
 #include "strlist.h"
 #include "strfilter.h"
 #include "debug.h"
···
 	/* Show all (filtered) symbols */
 	setup_pager();
 
-	for (nd = rb_first(&map->dso->symbol_names); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&map->dso->symbol_names); nd;
+	     nd = rb_next(nd)) {
 		struct symbol_name_rb_node *pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
 
 		if (strfilter__compare(_filter, pos->sym.name))

tools/perf/util/probe-event.h

···
 
 #include <linux/compiler.h>
 #include <stdbool.h>
-#include "intlist.h"
-#include "namespaces.h"
+
+struct intlist;
+struct nsinfo;
 
 /* Probe related configurations */
 struct probe_conf {

tools/perf/util/probe-file.c

···
 #include <sys/types.h>
 #include <sys/uio.h>
 #include <unistd.h>
+#include "namespaces.h"
 #include "util.h"
 #include "event.h"
 #include "strlist.h"

tools/perf/util/rb_resort.h

···
 
 /* For 'struct intlist' */
 #define DECLARE_RESORT_RB_INTLIST(__name, __ilist)				\
-	DECLARE_RESORT_RB(__name)(&__ilist->rblist.entries,			\
+	DECLARE_RESORT_RB(__name)(&__ilist->rblist.entries.rb_root,		\
 				  __ilist->rblist.nr_entries)
 
 /* For 'struct machine->threads' */
-#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine, hash_bucket)	\
-	DECLARE_RESORT_RB(__name)(&__machine->threads[hash_bucket].entries,	\
-				  __machine->threads[hash_bucket].nr)
+#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine, hash_bucket)    \
+ DECLARE_RESORT_RB(__name)(&__machine->threads[hash_bucket].entries.rb_root, \
+			   __machine->threads[hash_bucket].nr)
 
 #endif /* _PERF_RESORT_RB_H_ */

tools/perf/util/rblist.c

···
 
 int rblist__add_node(struct rblist *rblist, const void *new_entry)
 {
-	struct rb_node **p = &rblist->entries.rb_node;
+	struct rb_node **p = &rblist->entries.rb_root.rb_node;
 	struct rb_node *parent = NULL, *new_node;
+	bool leftmost = true;
 
 	while (*p != NULL) {
 		int rc;
···
 		rc = rblist->node_cmp(parent, new_entry);
 		if (rc > 0)
 			p = &(*p)->rb_left;
-		else if (rc < 0)
+		else if (rc < 0) {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 		else
 			return -EEXIST;
 	}
···
 		return -ENOMEM;
 
 	rb_link_node(new_node, parent, p);
-	rb_insert_color(new_node, &rblist->entries);
+	rb_insert_color_cached(new_node, &rblist->entries, leftmost);
 	++rblist->nr_entries;
 
 	return 0;
···
 
 void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node)
 {
-	rb_erase(rb_node, &rblist->entries);
+	rb_erase_cached(rb_node, &rblist->entries);
 	--rblist->nr_entries;
 	rblist->node_delete(rblist, rb_node);
 }
···
 					 const void *entry,
 					 bool create)
 {
-	struct rb_node **p = &rblist->entries.rb_node;
+	struct rb_node **p = &rblist->entries.rb_root.rb_node;
 	struct rb_node *parent = NULL, *new_node = NULL;
+	bool leftmost = true;
 
 	while (*p != NULL) {
 		int rc;
···
 		rc = rblist->node_cmp(parent, entry);
 		if (rc > 0)
 			p = &(*p)->rb_left;
-		else if (rc < 0)
+		else if (rc < 0) {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 		else
 			return parent;
 	}
···
 		new_node = rblist->node_new(rblist, entry);
 		if (new_node) {
 			rb_link_node(new_node, parent, p);
-			rb_insert_color(new_node, &rblist->entries);
+			rb_insert_color_cached(new_node,
+					       &rblist->entries, leftmost);
 			++rblist->nr_entries;
 		}
 	}
···
 void rblist__init(struct rblist *rblist)
 {
 	if (rblist != NULL) {
-		rblist->entries	 = RB_ROOT;
+		rblist->entries	 = RB_ROOT_CACHED;
 		rblist->nr_entries = 0;
 	}
 
···
 
 void rblist__exit(struct rblist *rblist)
 {
-	struct rb_node *pos, *next = rb_first(&rblist->entries);
+	struct rb_node *pos, *next = rb_first_cached(&rblist->entries);
 
 	while (next) {
 		pos = next;
···
 {
 	struct rb_node *node;
 
-	for (node = rb_first(&rblist->entries); node; node = rb_next(node)) {
+	for (node = rb_first_cached(&rblist->entries); node;
+	     node = rb_next(node)) {
 		if (!idx--)
 			return node;
 	}

tools/perf/util/rblist.h

···
  */
 
 struct rblist {
-	struct rb_root entries;
+	struct rb_root_cached entries;
 	unsigned int   nr_entries;
 
 	int (*node_cmp)(struct rb_node *rbn, const void *entry);

tools/perf/util/scripting-engines/trace-event-python.c

···
 		Py_FatalError("couldn't create Python dictionary");
 
 	pydict_set_item_string_decref(dict, "ev_name", _PyUnicode_FromString(perf_evsel__name(evsel)));
-	pydict_set_item_string_decref(dict, "attr", _PyUnicode_FromStringAndSize(
-			(const char *)&evsel->attr, sizeof(evsel->attr)));
+	pydict_set_item_string_decref(dict, "attr", _PyBytes_FromStringAndSize((const char *)&evsel->attr, sizeof(evsel->attr)));
 
 	pydict_set_item_string_decref(dict_sample, "pid",
 			_PyLong_FromLong(sample->pid));
···
 static int python_start_script(const char *script, int argc, const char **argv)
 {
 	struct tables *tables = &tables_global;
+	PyMODINIT_FUNC (*initfunc)(void);
 #if PY_MAJOR_VERSION < 3
 	const char **command_line;
 #else
 	wchar_t **command_line;
 #endif
-	char buf[PATH_MAX];
+	/*
+	 * Use a non-const name variable to cope with python 2.6's
+	 * PyImport_AppendInittab prototype
+	 */
+	char buf[PATH_MAX], name[19] = "perf_trace_context";
 	int i, err = 0;
 	FILE *fp;
 
 #if PY_MAJOR_VERSION < 3
+	initfunc = initperf_trace_context;
 	command_line = malloc((argc + 1) * sizeof(const char *));
 	command_line[0] = script;
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = argv[i - 1];
 #else
+	initfunc = PyInit_perf_trace_context;
 	command_line = malloc((argc + 1) * sizeof(wchar_t *));
 	command_line[0] = Py_DecodeLocale(script, NULL);
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = Py_DecodeLocale(argv[i - 1], NULL);
 #endif
 
+	PyImport_AppendInittab(name, initfunc);
 	Py_Initialize();
 
 #if PY_MAJOR_VERSION < 3
-	initperf_trace_context();
 	PySys_SetArgv(argc + 1, (char **)command_line);
 #else
-	PyInit_perf_trace_context();
 	PySys_SetArgv(argc + 1, command_line);
 #endif
 

tools/perf/util/setup.py

···
-#!/usr/bin/python
-
 from os import getenv
 from subprocess import Popen, PIPE
 from re import sub

tools/perf/util/sort.h

···
 	union {
 		/* this is for hierarchical entry structure */
 		struct {
-			struct rb_root	hroot_in;
-			struct rb_root  hroot_out;
+			struct rb_root_cached	hroot_in;
+			struct rb_root_cached   hroot_out;
 		};				/* non-leaf entries */
 		struct rb_root	sorted_chain;	/* leaf entry has callchains */
 	};

tools/perf/util/srcline.c

···
 	struct rb_node		rb_node;
 };
 
-void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline)
+void srcline__tree_insert(struct rb_root_cached *tree, u64 addr, char *srcline)
 {
-	struct rb_node **p = &tree->rb_node;
+	struct rb_node **p = &tree->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct srcline_node *i, *node;
+	bool leftmost = true;
 
 	node = zalloc(sizeof(struct srcline_node));
 	if (!node) {
···
 		i = rb_entry(parent, struct srcline_node, rb_node);
 		if (addr < i->addr)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 	rb_link_node(&node->rb_node, parent, p);
-	rb_insert_color(&node->rb_node, tree);
+	rb_insert_color_cached(&node->rb_node, tree, leftmost);
 }
 
-char *srcline__tree_find(struct rb_root *tree, u64 addr)
+char *srcline__tree_find(struct rb_root_cached *tree, u64 addr)
 {
-	struct rb_node *n = tree->rb_node;
+	struct rb_node *n = tree->rb_root.rb_node;
 
 	while (n) {
 		struct srcline_node *i = rb_entry(n, struct srcline_node,
···
 	return NULL;
 }
 
-void srcline__tree_delete(struct rb_root *tree)
+void srcline__tree_delete(struct rb_root_cached *tree)
 {
 	struct srcline_node *pos;
-	struct rb_node *next = rb_first(tree);
+	struct rb_node *next = rb_first_cached(tree);
 
 	while (next) {
 		pos = rb_entry(next, struct srcline_node, rb_node);
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, tree);
+		rb_erase_cached(&pos->rb_node, tree);
 		free_srcline(pos->srcline);
 		zfree(&pos);
 	}
···
 	free(node);
 }
 
-void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines)
+void inlines__tree_insert(struct rb_root_cached *tree,
+			  struct inline_node *inlines)
 {
-	struct rb_node **p = &tree->rb_node;
+	struct rb_node **p = &tree->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	const u64 addr = inlines->addr;
 	struct inline_node *i;
+	bool leftmost = true;
 
 	while (*p != NULL) {
 		parent = *p;
 		i = rb_entry(parent, struct inline_node, rb_node);
 		if (addr < i->addr)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 	rb_link_node(&inlines->rb_node, parent, p);
-	rb_insert_color(&inlines->rb_node, tree);
+	rb_insert_color_cached(&inlines->rb_node, tree, leftmost);
 }
 
-struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr)
+struct inline_node *inlines__tree_find(struct rb_root_cached *tree, u64 addr)
 {
-	struct rb_node *n = tree->rb_node;
+	struct rb_node *n = tree->rb_root.rb_node;
 
 	while (n) {
 		struct inline_node *i = rb_entry(n, struct inline_node,
···
 	return NULL;
 }
 
-void inlines__tree_delete(struct rb_root *tree)
+void inlines__tree_delete(struct rb_root_cached *tree)
 {
 	struct inline_node *pos;
-	struct rb_node *next = rb_first(tree);
+	struct rb_node *next = rb_first_cached(tree);
 
 	while (next) {
 		pos = rb_entry(next, struct inline_node, rb_node);
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, tree);
+		rb_erase_cached(&pos->rb_node, tree);
 		inline_node__delete(pos);
 	}
 }

tools/perf/util/srcline.h

···
 char *get_srcline_split(struct dso *dso, u64 addr, unsigned *line);
 
 /* insert the srcline into the DSO, which will take ownership */
-void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline);
+void srcline__tree_insert(struct rb_root_cached *tree, u64 addr, char *srcline);
 /* find previously inserted srcline */
-char *srcline__tree_find(struct rb_root *tree, u64 addr);
+char *srcline__tree_find(struct rb_root_cached *tree, u64 addr);
 /* delete all srclines within the tree */
-void srcline__tree_delete(struct rb_root *tree);
+void srcline__tree_delete(struct rb_root_cached *tree);
 
 #define SRCLINE_UNKNOWN  ((char *) "??:0")
 
···
 void inline_node__delete(struct inline_node *node);
 
 /* insert the inline node list into the DSO, which will take ownership */
-void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines);
+void inlines__tree_insert(struct rb_root_cached *tree,
+			  struct inline_node *inlines);
 /* find previously inserted inline node list */
-struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr);
+struct inline_node *inlines__tree_find(struct rb_root_cached *tree, u64 addr);
 /* delete all nodes within the tree of inline_node s */
-void inlines__tree_delete(struct rb_root *tree);
+void inlines__tree_delete(struct rb_root_cached *tree);
 
 #endif /* PERF_SRCLINE_H */

tools/perf/util/stat-display.c

···
 #include <inttypes.h>
 #include <linux/time64.h>
 #include <math.h>
+#include "color.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "stat.h"

tools/perf/util/stat-shadow.c

···
 	struct rb_node *pos, *next;
 
 	rblist = &st->value_list;
-	next = rb_first(&rblist->entries);
+	next = rb_first_cached(&rblist->entries);
 	while (next) {
 		pos = next;
 		next = rb_next(pos);

tools/perf/util/strlist.h

···
 /* For strlist iteration */
 static inline struct str_node *strlist__first(struct strlist *slist)
 {
-	struct rb_node *rn = rb_first(&slist->rblist.entries);
+	struct rb_node *rn = rb_first_cached(&slist->rblist.entries);
 	return rn ? rb_entry(rn, struct str_node, rb_node) : NULL;
 }
 static inline struct str_node *strlist__next(struct str_node *sn)

tools/perf/util/symbol-minimal.c

···
 #include "util.h"
 
 #include <errno.h>
+#include <unistd.h>
 #include <stdio.h>
 #include <fcntl.h>
 #include <string.h>

tools/perf/util/symbol.c

···
 	return arch__choose_best_symbol(syma, symb);
 }
 
-void symbols__fixup_duplicate(struct rb_root *symbols)
+void symbols__fixup_duplicate(struct rb_root_cached *symbols)
 {
 	struct rb_node *nd;
 	struct symbol *curr, *next;
···
 	if (symbol_conf.allow_aliases)
 		return;
 
-	nd = rb_first(symbols);
+	nd = rb_first_cached(symbols);
 
 	while (nd) {
 		curr = rb_entry(nd, struct symbol, rb_node);
···
 			continue;
 
 		if (choose_best_symbol(curr, next) == SYMBOL_A) {
-			rb_erase(&next->rb_node, symbols);
+			rb_erase_cached(&next->rb_node, symbols);
 			symbol__delete(next);
 			goto again;
 		} else {
 			nd = rb_next(&curr->rb_node);
-			rb_erase(&curr->rb_node, symbols);
+			rb_erase_cached(&curr->rb_node, symbols);
 			symbol__delete(curr);
 		}
 	}
 }
 
-void symbols__fixup_end(struct rb_root *symbols)
+void symbols__fixup_end(struct rb_root_cached *symbols)
 {
-	struct rb_node *nd, *prevnd = rb_first(symbols);
+	struct rb_node *nd, *prevnd = rb_first_cached(symbols);
 	struct symbol *curr, *prev;
 
 	if (prevnd == NULL)
···
 	free(((void *)sym) - symbol_conf.priv_size);
 }
 
-void symbols__delete(struct rb_root *symbols)
+void symbols__delete(struct rb_root_cached *symbols)
 {
 	struct symbol *pos;
-	struct rb_node *next = rb_first(symbols);
+	struct rb_node *next = rb_first_cached(symbols);
 
 	while (next) {
 		pos = rb_entry(next, struct symbol, rb_node);
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, symbols);
+		rb_erase_cached(&pos->rb_node, symbols);
 		symbol__delete(pos);
 	}
 }
 
-void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel)
+void __symbols__insert(struct rb_root_cached *symbols,
+		       struct symbol *sym, bool kernel)
 {
-	struct rb_node **p = &symbols->rb_node;
+	struct rb_node **p = &symbols->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	const u64 ip = sym->start;
 	struct symbol *s;
+	bool leftmost = true;
 
 	if (kernel) {
 		const char *name = sym->name;
···
 		s = rb_entry(parent, struct symbol, rb_node);
 		if (ip < s->start)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 	rb_link_node(&sym->rb_node, parent, p);
-	rb_insert_color(&sym->rb_node, symbols);
+	rb_insert_color_cached(&sym->rb_node, symbols, leftmost);
 }
 
-void symbols__insert(struct rb_root *symbols, struct symbol *sym)
+void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym)
 {
 	__symbols__insert(symbols, sym, false);
 }
 
-static struct symbol *symbols__find(struct rb_root *symbols, u64 ip)
+static struct symbol *symbols__find(struct rb_root_cached *symbols, u64 ip)
 {
 	struct rb_node *n;
 
 	if (symbols == NULL)
 		return NULL;
 
-	n = symbols->rb_node;
+	n = symbols->rb_root.rb_node;
 
 	while (n) {
 		struct symbol *s = rb_entry(n, struct symbol, rb_node);
···
 	return NULL;
 }
 
-static struct symbol *symbols__first(struct rb_root *symbols)
+static struct symbol *symbols__first(struct rb_root_cached *symbols)
 {
-	struct rb_node *n = rb_first(symbols);
+	struct rb_node *n = rb_first_cached(symbols);
 
 	if (n)
 		return rb_entry(n, struct symbol, rb_node);
···
 	return NULL;
 }
 
-static struct symbol *symbols__last(struct rb_root *symbols)
+static struct symbol *symbols__last(struct rb_root_cached *symbols)
 {
-	struct rb_node *n = rb_last(symbols);
+	struct rb_node *n = rb_last(&symbols->rb_root);
 
 	if (n)
 		return rb_entry(n, struct symbol, rb_node);
···
 	return NULL;
 }
 
-static void symbols__insert_by_name(struct rb_root *symbols, struct symbol *sym)
+static void symbols__insert_by_name(struct rb_root_cached *symbols, struct symbol *sym)
 {
-	struct rb_node **p = &symbols->rb_node;
+	struct rb_node **p = &symbols->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct symbol_name_rb_node *symn, *s;
+	bool leftmost = true;
 
 	symn = container_of(sym, struct symbol_name_rb_node, sym);
 
···
 		s = rb_entry(parent, struct symbol_name_rb_node, rb_node);
 		if (strcmp(sym->name, s->sym.name) < 0)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 	rb_link_node(&symn->rb_node, parent, p);
-	rb_insert_color(&symn->rb_node, symbols);
+	rb_insert_color_cached(&symn->rb_node, symbols, leftmost);
 }
 
-static void symbols__sort_by_name(struct rb_root *symbols,
-				  struct rb_root *source)
+static void symbols__sort_by_name(struct rb_root_cached *symbols,
+				  struct rb_root_cached *source)
 {
 	struct rb_node *nd;
 
-	for (nd = rb_first(source); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(source); nd; nd = rb_next(nd)) {
 		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
 		symbols__insert_by_name(symbols, pos);
 	}
···
 		return arch__compare_symbol_names(name, str);
 }
 
-static struct symbol *symbols__find_by_name(struct rb_root *symbols,
+static struct symbol *symbols__find_by_name(struct rb_root_cached *symbols,
 					    const char *name,
 					    enum symbol_tag_include includes)
 {
···
 	if (symbols == NULL)
 		return NULL;
 
-	n = symbols->rb_node;
+	n = symbols->rb_root.rb_node;
 
 	while (n) {
 		int cmp;
···
 {
 	struct symbol *sym;
 	struct dso *dso = arg;
-	struct rb_root *root = &dso->symbols;
+	struct rb_root_cached *root = &dso->symbols;
 
 	if (!symbol_type__filter(type))
 		return 0;
···
 	struct map *curr_map;
 	struct symbol *pos;
 	int count = 0;
-	struct rb_root old_root = dso->symbols;
-	struct rb_root *root = &dso->symbols;
-	struct rb_node *next = rb_first(root);
+	struct rb_root_cached old_root = dso->symbols;
+	struct rb_root_cached *root = &dso->symbols;
+	struct rb_node *next = rb_first_cached(root);
 
 	if (!kmaps)
 		return -1;
 
-	*root = RB_ROOT;
+	*root = RB_ROOT_CACHED;
 
 	while (next) {
 		char *module;
···
 		pos = rb_entry(next, struct symbol, rb_node);
 		next = rb_next(&pos->rb_node);
 
-		rb_erase_init(&pos->rb_node, &old_root);
-
+		rb_erase_cached(&pos->rb_node, &old_root);
+		RB_CLEAR_NODE(&pos->rb_node);
 		module = strchr(pos->name, '\t');
 		if (module)
 			*module = '\0';
···
 	struct map *curr_map = initial_map;
 	struct symbol *pos;
 	int count = 0, moved = 0;
-	struct rb_root *root = &dso->symbols;
-	struct rb_node *next = rb_first(root);
+	struct rb_root_cached *root = &dso->symbols;
+	struct rb_node *next = rb_first_cached(root);
 	int kernel_range = 0;
 	bool x86_64;
 
···
 		}
 add_symbol:
 		if (curr_map != initial_map) {
-			rb_erase(&pos->rb_node, root);
+			rb_erase_cached(&pos->rb_node, root);
 			symbols__insert(&curr_map->dso->symbols, pos);
 			++moved;
 		} else
···
 
 		continue;
 discard_symbol:
-		rb_erase(&pos->rb_node, root);
+		rb_erase_cached(&pos->rb_node, root);
 		symbol__delete(pos);
 	}
 

tools/perf/util/symbol.h

···
 #include <linux/types.h>
 #include <stdbool.h>
 #include <stdint.h>
-#include "map.h"
-#include "../perf.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <stdio.h>
-#include <byteswap.h>
-#include <libgen.h>
-#include "build-id.h"
-#include "event.h"
+#include "branch.h"
 #include "path.h"
+#include "symbol_conf.h"
 
 #ifdef HAVE_LIBELF_SUPPORT
 #include <libelf.h>
···
 #include <elf.h>
 
 #include "dso.h"
+
+struct map;
+struct map_groups;
+struct option;
 
 /*
  * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP;
···
 };
 
 void symbol__delete(struct symbol *sym);
-void symbols__delete(struct rb_root *symbols);
+void symbols__delete(struct rb_root_cached *symbols);
 
 /* symbols__for_each_entry - iterate over symbols (rb_root)
  *
···
  * @nd: the 'struct rb_node *' to use as a temporary storage
  */
 #define symbols__for_each_entry(symbols, pos, nd)			\
-	for (nd = rb_first(symbols);					\
+	for (nd = rb_first_cached(symbols);					\
 	     nd && (pos = rb_entry(nd, struct symbol, rb_node));	\
 	     nd = rb_next(nd))
 
···
 
 struct strlist;
 struct intlist;
-
-struct symbol_conf {
-	unsigned short	priv_size;
-	bool		try_vmlinux_path,
-			init_annotation,
-			force,
-			ignore_vmlinux,
-			ignore_vmlinux_buildid,
-			show_kernel_path,
-			use_modules,
-			allow_aliases,
-			sort_by_name,
-			show_nr_samples,
-			show_total_period,
-			use_callchain,
-			cumulate_callchain,
-			show_branchflag_count,
-			exclude_other,
-			show_cpu_utilization,
-			initialized,
-			kptr_restrict,
-			event_group,
-			demangle,
-			demangle_kernel,
-			filter_relative,
-			show_hist_headers,
-			branch_callstack,
-			has_filter,
-			show_ref_callgraph,
-			hide_unresolved,
-			raw_trace,
-			report_hierarchy,
-			inline_name;
-	const char	*vmlinux_name,
-			*kallsyms_name,
-			*source_prefix,
-			*field_sep,
-			*graph_function;
-	const char	*default_guest_vmlinux_name,
-			*default_guest_kallsyms,
-			*default_guest_modules;
-	const char	*guestmount;
-	const char	*dso_list_str,
-			*comm_list_str,
-			*pid_list_str,
-			*tid_list_str,
-			*sym_list_str,
-			*col_width_list_str,
-			*bt_stop_list_str;
-       struct strlist	*dso_list,
-			*comm_list,
-			*sym_list,
-			*dso_from_list,
-			*dso_to_list,
-			*sym_from_list,
-			*sym_to_list,
-			*bt_stop_list;
-	struct intlist	*pid_list,
-			*tid_list;
-	const char	*symfs;
-};
-
-extern struct symbol_conf symbol_conf;
 
 struct symbol_name_rb_node {
 	struct rb_node	rb_node;
···
 
 char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name);
 
-void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel);
-void symbols__insert(struct rb_root *symbols, struct symbol *sym);
-void symbols__fixup_duplicate(struct rb_root *symbols);
-void symbols__fixup_end(struct rb_root *symbols);
+void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym,
+		       bool kernel);
+void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym);
+void symbols__fixup_duplicate(struct rb_root_cached *symbols);
+void symbols__fixup_end(struct rb_root_cached *symbols);
 void map_groups__fixup_end(struct map_groups *mg);
 
 typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);

tools/perf/util/symbol_conf.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_SYMBOL_CONF
+#define __PERF_SYMBOL_CONF 1
+
+#include <stdbool.h>
+
+struct strlist;
+struct intlist;
+
+struct symbol_conf {
+	unsigned short	priv_size;
+	bool		try_vmlinux_path,
+			init_annotation,
+			force,
+			ignore_vmlinux,
+			ignore_vmlinux_buildid,
+			show_kernel_path,
+			use_modules,
+			allow_aliases,
+			sort_by_name,
+			show_nr_samples,
+			show_total_period,
+			use_callchain,
+			cumulate_callchain,
+			show_branchflag_count,
+			exclude_other,
+			show_cpu_utilization,
+			initialized,
+			kptr_restrict,
+			event_group,
+			demangle,
+			demangle_kernel,
+			filter_relative,
+			show_hist_headers,
+			branch_callstack,
+			has_filter,
+			show_ref_callgraph,
+			hide_unresolved,
+			raw_trace,
+			report_hierarchy,
+			inline_name;
+	const char	*vmlinux_name,
+			*kallsyms_name,
+			*source_prefix,
+			*field_sep,
+			*graph_function;
+	const char	*default_guest_vmlinux_name,
+			*default_guest_kallsyms,
+			*default_guest_modules;
+	const char	*guestmount;
+	const char	*dso_list_str,
+			*comm_list_str,
+			*pid_list_str,
+			*tid_list_str,
+			*sym_list_str,
+			*col_width_list_str,
+			*bt_stop_list_str;
+       struct strlist	*dso_list,
+			*comm_list,
+			*sym_list,
+			*dso_from_list,
+			*dso_to_list,
+			*sym_from_list,
+			*sym_to_list,
+			*bt_stop_list;
+	struct intlist	*pid_list,
+			*tid_list;
+	const char	*symfs;
+};
+
+extern struct symbol_conf symbol_conf;
+
+#endif // __PERF_SYMBOL_CONF

tools/perf/util/symbol_fprintf.c

···
 #include <inttypes.h>
 #include <stdio.h>
 
+#include "map.h"
 #include "symbol.h"
 
 size_t symbol__fprintf(struct symbol *sym, FILE *fp)
···
 	struct rb_node *nd;
 	struct symbol_name_rb_node *pos;
 
-	for (nd = rb_first(&dso->symbol_names); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&dso->symbol_names); nd; nd = rb_next(nd)) {
 		pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
 		fprintf(fp, "%s\n", pos->sym.name);
 	}

tools/perf/util/thread.h

···
 #include <intlist.h>
 #include "rwsem.h"
 
+struct namespaces_event;
 struct thread_stack;
 struct unwind_libunwind_ops;
 

tools/perf/util/util.c

···
 #include "../perf.h"
 #include "util.h"
 #include "debug.h"
+#include "namespaces.h"
 #include <api/fs/fs.h>
 #include <sys/mman.h>
 #include <sys/stat.h>