fs/epoll: use faster rb_first_cached()

...  such that we can avoid the tree walks to get the node with the
smallest key.  Semantically the same, as the previously used rb_first(),
but O(1).  The main overhead is the extra footprint for the cached rb_node
pointer, which should not matter for epoll.

Link: http://lkml.kernel.org/r/20170719014603.19029-15-dave@stgolabs.net
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

fs/eventpoll.c

@@ -205,7 +205,7 @@ struct eventpoll {
 	struct list_head rdllist;
 
 	/* RB tree root used to store monitored fd structs */
-	struct rb_root rbr;
+	struct rb_root_cached rbr;
 
 	/*
 	 * This is a single linked list that chains all the "struct epitem" that
@@ -796,7 +796,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi)
 	list_del_rcu(&epi->fllink);
 	spin_unlock(&file->f_lock);
 
-	rb_erase(&epi->rbn, &ep->rbr);
+	rb_erase_cached(&epi->rbn, &ep->rbr);
 
 	spin_lock_irqsave(&ep->lock, flags);
 	if (ep_is_linked(&epi->rdllink))
@@ -840,7 +840,7 @@ static void ep_free(struct eventpoll *ep)
 	/*
 	 * Walks through the whole tree by unregistering poll callbacks.
 	 */
-	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+	for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
 		epi = rb_entry(rbp, struct epitem, rbn);
 
 		ep_unregister_pollwait(ep, epi);
@@ -856,7 +856,7 @@ static void ep_free(struct eventpoll *ep)
 	 * a lockdep warning.
 	 */
 	mutex_lock(&ep->mtx);
-	while ((rbp = rb_first(&ep->rbr)) != NULL) {
+	while ((rbp = rb_first_cached(&ep->rbr)) != NULL) {
 		epi = rb_entry(rbp, struct epitem, rbn);
 		ep_remove(ep, epi);
 		cond_resched();
@@ -963,7 +963,7 @@ static void ep_show_fdinfo(struct seq_file *m, struct file *f)
 	struct rb_node *rbp;
 
 	mutex_lock(&ep->mtx);
-	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+	for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
 		struct epitem *epi = rb_entry(rbp, struct epitem, rbn);
 		struct inode *inode = file_inode(epi->ffd.file);
 
@@ -1040,7 +1040,7 @@ static int ep_alloc(struct eventpoll **pep)
 	init_waitqueue_head(&ep->wq);
 	init_waitqueue_head(&ep->poll_wait);
 	INIT_LIST_HEAD(&ep->rdllist);
-	ep->rbr = RB_ROOT;
+	ep->rbr = RB_ROOT_CACHED;
 	ep->ovflist = EP_UNACTIVE_PTR;
 	ep->user = user;
 
@@ -1066,7 +1066,7 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
 	struct epoll_filefd ffd;
 
 	ep_set_ffd(&ffd, file, fd);
-	for (rbp = ep->rbr.rb_node; rbp; ) {
+	for (rbp = ep->rbr.rb_root.rb_node; rbp; ) {
 		epi = rb_entry(rbp, struct epitem, rbn);
 		kcmp = ep_cmp_ffd(&ffd, &epi->ffd);
 		if (kcmp > 0)
@@ -1088,7 +1088,7 @@ static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long t
 	struct rb_node *rbp;
 	struct epitem *epi;
 
-	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+	for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
 		epi = rb_entry(rbp, struct epitem, rbn);
 		if (epi->ffd.fd == tfd) {
 			if (toff == 0)
@@ -1273,20 +1273,22 @@ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
 static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi)
 {
 	int kcmp;
-	struct rb_node **p = &ep->rbr.rb_node, *parent = NULL;
+	struct rb_node **p = &ep->rbr.rb_root.rb_node, *parent = NULL;
 	struct epitem *epic;
+	bool leftmost = true;
 
 	while (*p) {
 		parent = *p;
 		epic = rb_entry(parent, struct epitem, rbn);
 		kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd);
-		if (kcmp > 0)
+		if (kcmp > 0) {
 			p = &parent->rb_right;
-		else
+			leftmost = false;
+		} else
 			p = &parent->rb_left;
 	}
 	rb_link_node(&epi->rbn, parent, p);
-	rb_insert_color(&epi->rbn, &ep->rbr);
+	rb_insert_color_cached(&epi->rbn, &ep->rbr, leftmost);
 }
 
 
@@ -1530,7 +1532,7 @@ error_remove_epi:
 	list_del_rcu(&epi->fllink);
 	spin_unlock(&tfile->f_lock);
 
-	rb_erase(&epi->rbn, &ep->rbr);
+	rb_erase_cached(&epi->rbn, &ep->rbr);
 
 error_unregister:
 	ep_unregister_pollwait(ep, epi);
@@ -1878,7 +1880,7 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
 	mutex_lock_nested(&ep->mtx, call_nests + 1);
 	ep->visited = 1;
 	list_add(&ep->visited_list_link, &visited_list);
-	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+	for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
 		epi = rb_entry(rbp, struct epitem, rbn);
 		if (unlikely(is_file_epoll(epi->ffd.file))) {
 			ep_tovisit = epi->ffd.file->private_data;