1 files changed, 87 insertions, 104 deletions

diff --git a/fs/pipe.c b/fs/pipe.c
index 429b0714ec57..0c77191a050c 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -111,75 +111,95 @@ void pipe_double_lock(struct pipe_inode_info *pipe1,
 	pipe_lock(pipe2);
 }
 
-#define PIPE_PREALLOC_MAX 8
+static struct page *anon_pipe_prealloc_pop(struct anon_pipe_prealloc *prealloc)
+{
+	if (!prealloc->count)
+		return NULL;
 
-struct anon_pipe_prealloc {
-	struct page *pages[PIPE_PREALLOC_MAX];
-	unsigned int count;
-};
+	prealloc->count--;
+
+	return prealloc->pages[prealloc->count];
+}
+
+/* Push a page to the prealloc pool. Returns true if added, false if full. */
+static bool anon_pipe_prealloc_push(struct anon_pipe_prealloc *prealloc,
+				    struct page *page)
+{
+	if (prealloc->count >= PIPE_PREALLOC_MAX)
+		return false;
+	prealloc->pages[prealloc->count++] = page;
+	return true;
+}
 
 /*
- * Pre-allocate pages outside pipe->mutex for multi-page writes.
- * alloc_page() with GFP_HIGHUSER can sleep in reclaim and runs memcg
- * charging; doing it under the mutex stalls a concurrent reader.
- *
- * Loop alloc_page() instead of alloc_pages_bulk_*(): the bulk path refuses
- * __GFP_ACCOUNT under memcg (see commit 8dcb3060d81d "memcg: page_alloc:
- * skip bulk allocator for __GFP_ACCOUNT") and silently degrades to a single
- * page. A per-page loop keeps memcg accounting and the task NUMA mempolicy
- * honoured for every page; the per-call overhead is small compared to the
- * pipe->mutex hold-time being shrunk. Any shortfall is covered by the
- * in-lock alloc_page() fallback in anon_pipe_get_page().
+ * Top up the pipe's own pool, then take pipe->mutex and return with it held.
+ * The shortfall is allocated outside the lock; the push and the caller's write
+ * then run under a single lock acquisition, avoiding a separate prefill
+ * lock/unlock cycle. anon_pipe_get_page() drains the pool instead of allocating
+ * under the lock.
  */
-static void anon_pipe_get_page_prealloc(struct anon_pipe_prealloc *prealloc,
-					size_t total_len)
+static void anon_pipe_prefill_and_lock(struct pipe_inode_info *pipe, size_t total_len)
 {
-	unsigned int want, i;
-	struct page *page;
-
-	prealloc->count = 0;
-	if (total_len <= PAGE_SIZE)
-		return;
+	struct page *pages[PIPE_PREALLOC_MAX];
+	unsigned int want, have, need, n = 0;
 
 	want = min_t(unsigned int, DIV_ROUND_UP(total_len, PAGE_SIZE),
 		     PIPE_PREALLOC_MAX);
+	/* Unlocked read; the pool is refilled under the lock below. */
+	have = min_t(unsigned int, READ_ONCE(pipe->prealloc.count), want);
+	need = want - have;
+
+	if (!need) {
+		mutex_lock(&pipe->mutex);
+		return;
+	}
+
+	while (n < need) {
+		struct page *page = alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT);
 
-	for (i = 0; i < want; i++) {
-		page = alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT);
 		if (!page)
 			break;
-		prealloc->pages[prealloc->count++] = page;
+		pages[n++] = page;
 	}
+
+	mutex_lock(&pipe->mutex);
+	while (n && anon_pipe_prealloc_push(&pipe->prealloc, pages[n - 1]))
+		n--;
+
+	/*
+	 * Just flush any extra page that got affected by the TOCTOU
+	 * effect
+	 */
+	while (n)
+		put_page(pages[--n]);
 }
 
-static struct page *anon_pipe_prealloc_pop(struct anon_pipe_prealloc *prealloc)
+/*
+ * Called with pipe->mutex held. Trim the pool down to PIPE_PREALLOC_KEEP under
+ * the lock, drop it, then free the excess outside the critical section.
+ */
+static void anon_pipe_trim_and_unlock(struct pipe_inode_info *pipe)
 {
-	if (!prealloc->count)
-		return NULL;
+	struct page *excess[PIPE_PREALLOC_MAX];
+	unsigned int nexcess = 0;
 
-	prealloc->count--;
+	while (pipe->prealloc.count > PIPE_PREALLOC_KEEP)
+		excess[nexcess++] = anon_pipe_prealloc_pop(&pipe->prealloc);
+	mutex_unlock(&pipe->mutex);
 
-	return prealloc->pages[prealloc->count];
+	while (nexcess)
+		put_page(excess[--nexcess]);
 }
 
-static struct page *anon_pipe_get_page(struct pipe_inode_info *pipe,
-				       struct anon_pipe_prealloc *prealloc)
+static struct page *anon_pipe_get_page(struct pipe_inode_info *pipe)
 {
 	struct page *page;
 
-	/* Drain prealloc first to keep tmp_page[] hot for later small writes. */
-	page = anon_pipe_prealloc_pop(prealloc);
+	/* Drain the prealloc pool before allocating. Called with mutex held. */
+	page = anon_pipe_prealloc_pop(&pipe->prealloc);
 	if (page)
 		return page;
 
-	for (int i = 0; i < ARRAY_SIZE(pipe->tmp_page); i++) {
-		if (pipe->tmp_page[i]) {
-			page = pipe->tmp_page[i];
-			pipe->tmp_page[i] = NULL;
-			return page;
-		}
-	}
-
 	/* FWIW: This is called with pipe->mutex held */
 	return alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT);
 }
@@ -187,48 +207,11 @@ static struct page *anon_pipe_get_page(struct pipe_inode_info *pipe,
 static void anon_pipe_put_page(struct pipe_inode_info *pipe,
 			       struct page *page)
 {
-	if (page_count(page) == 1) {
-		for (int i = 0; i < ARRAY_SIZE(pipe->tmp_page); i++) {
-			if (!pipe->tmp_page[i]) {
-				pipe->tmp_page[i] = page;
-				return;
-			}
-		}
-	}
-
-	put_page(page);
-}
-
-/*
- * Stash leftover prealloc pages in tmp_page[] so the next write to this
- * pipe gets a hot page without entering the allocator.
- */
-static void anon_pipe_refill_tmp_pages(struct pipe_inode_info *pipe,
-				       struct anon_pipe_prealloc *prealloc)
-{
-	int i, idx;
-
-	if (!prealloc->count)
+	if (page_count(page) == 1 &&
+	    anon_pipe_prealloc_push(&pipe->prealloc, page))
 		return;
 
-	for (i = 0; i < ARRAY_SIZE(pipe->tmp_page); i++) {
-		if (pipe->tmp_page[i])
-			continue;
-		if (!prealloc->count)
-			return;
-		idx = --prealloc->count;
-		pipe->tmp_page[i] = prealloc->pages[idx];
-		prealloc->pages[idx] = NULL;
-	}
-}
-
-/* Runs after mutex_unlock() to keep put_page() out of the critical section. */
-static void anon_pipe_free_pages(struct anon_pipe_prealloc *prealloc)
-{
-	while (prealloc->count) {
-		prealloc->count--;
-		put_page(prealloc->pages[prealloc->count]);
-	}
+	put_page(page);
 }
 
 static void anon_pipe_buf_release(struct pipe_inode_info *pipe,
@@ -485,7 +468,8 @@ anon_pipe_read(struct kiocb *iocb, struct iov_iter *to)
 	}
 	if (pipe_is_empty(pipe))
 		wake_next_reader = false;
-	mutex_unlock(&pipe->mutex);
+	/* Consumed buffers may have refilled the pool; trim it and unlock. */
+	anon_pipe_trim_and_unlock(pipe);
 
 	if (wake_writer)
 		wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM);
@@ -524,7 +508,6 @@ anon_pipe_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *filp = iocb->ki_filp;
 	struct pipe_inode_info *pipe = filp->private_data;
-	struct anon_pipe_prealloc prealloc;
 	unsigned int head;
 	ssize_t ret = 0;
 	size_t total_len = iov_iter_count(from);
@@ -548,9 +531,7 @@ anon_pipe_write(struct kiocb *iocb, struct iov_iter *from)
 	if (unlikely(total_len == 0))
 		return 0;
 
-	anon_pipe_get_page_prealloc(&prealloc, total_len);
-
-	mutex_lock(&pipe->mutex);
+	anon_pipe_prefill_and_lock(pipe, total_len);
 
 	if (!pipe->readers) {
 		if ((iocb->ki_flags & IOCB_NOSIGNAL) == 0)
@@ -607,7 +588,7 @@ anon_pipe_write(struct kiocb *iocb, struct iov_iter *from)
 			struct page *page;
 			int copied;
 
-			page = anon_pipe_get_page(pipe, &prealloc);
+			page = anon_pipe_get_page(pipe);
 			if (unlikely(!page)) {
 				if (!ret)
 					ret = -ENOMEM;
@@ -671,11 +652,9 @@ anon_pipe_write(struct kiocb *iocb, struct iov_iter *from)
 		wake_next_writer = true;
 	}
 out:
-	anon_pipe_refill_tmp_pages(pipe, &prealloc);
 	if (pipe_is_full(pipe))
 		wake_next_writer = false;
-	mutex_unlock(&pipe->mutex);
-	anon_pipe_free_pages(&prealloc);
+	anon_pipe_trim_and_unlock(pipe);
 
 	/*
 	 * If we do do a wakeup event, we do a 'sync' wakeup, because we
@@ -686,10 +665,9 @@ out:
 	 * how (for example) the GNU make jobserver uses small writes to
 	 * wake up pending jobs
 	 *
-	 * Epoll nonsensically wants a wakeup whether the pipe
-	 * was already empty or not.
+	 * ->pseudo_edgetrigger enables per-write wakeups, see pipe_poll()
 	 */
-	if (was_empty || pipe->poll_usage)
+	if (was_empty || READ_ONCE(pipe->pseudo_edgetrigger))
 		wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
 	kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 	if (wake_next_writer)
@@ -752,7 +730,6 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	}
 }
 
-/* No kernel lock held - fine */
 static __poll_t
 pipe_poll(struct file *filp, poll_table *wait)
 {
@@ -760,9 +737,17 @@ pipe_poll(struct file *filp, poll_table *wait)
 	struct pipe_inode_info *pipe = filp->private_data;
 	union pipe_index idx;
 
-	/* Epoll has some historical nasty semantics, this enables them */
-	if (unlikely(!READ_ONCE(pipe->poll_usage)))
-		WRITE_ONCE(pipe->poll_usage, true);
+	/*
+	 * Legacy epoll(EPOLLET) users depend on historical per-write wakeups,
+	 * see 3a34b13a88ca ("pipe: make pipe writes always wake up readers")
+	 * and the ->pseudo_edgetrigger check in anon_pipe_write().
+	 * Currently io_uring sets EPOLLET for multishot polls, so it gets the
+	 * same behaviour.
+	 */
+	if ((filp->f_mode & FMODE_READ) &&
+	    wait && (wait->_key & EPOLLET) &&
+	    unlikely(!READ_ONCE(pipe->pseudo_edgetrigger)))
+		WRITE_ONCE(pipe->pseudo_edgetrigger, true);
 
 	/*
 	 * Reading pipe state only -- no need for acquiring the semaphore.
@@ -956,10 +941,8 @@ void free_pipe_info(struct pipe_inode_info *pipe)
 	if (pipe->watch_queue)
 		put_watch_queue(pipe->watch_queue);
 #endif
-	for (i = 0; i < ARRAY_SIZE(pipe->tmp_page); i++) {
-		if (pipe->tmp_page[i])
-			__free_page(pipe->tmp_page[i]);
-	}
+	for (i = 0; i < pipe->prealloc.count; i++)
+		__free_page(pipe->prealloc.pages[i]);
 	kfree(pipe->bufs);
 	kfree(pipe);
 }