Merge tag 'vfs-6.17-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull misc VFS updates from Christian Brauner:
 "This contains the usual selections of misc updates for this cycle.

  Features:

   - Add ext4 IOCB_DONTCACHE support

     This refactors the address_space_operations write_begin() and
     write_end() callbacks to take const struct kiocb * as their first
     argument, allowing IOCB flags such as IOCB_DONTCACHE to propagate
     to the filesystem's buffered I/O path.

     Ext4 is updated to implement handling of the IOCB_DONTCACHE flag
     and advertises support via the FOP_DONTCACHE file operation flag.

     Additionally, the i915 driver's shmem write paths are updated to
     bypass the legacy write_begin/write_end interface in favor of
     directly calling write_iter() with a constructed synchronous kiocb.
     Another i915 change replaces a manual write loop with
     kernel_write() during GEM shmem object creation.

  Cleanups:

   - don't duplicate vfs_open() in kernel_file_open()

   - proc_fd_getattr(): don't bother with S_ISDIR() check

   - fs/ecryptfs: replace snprintf with sysfs_emit in show function

   - vfs: Remove unnecessary list_for_each_entry_safe() from
     evict_inodes()

   - filelock: add new locks_wake_up_waiter() helper

   - fs: Remove three arguments from block_write_end()

   - VFS: change old_dir and new_dir in struct renamedata to dentrys

   - netfs: Remove unused declaration netfs_queue_write_request()

  Fixes:

   - eventpoll: Fix semi-unbounded recursion

   - eventpoll: fix sphinx documentation build warning

   - fs/read_write: Fix spelling typo

   - fs: annotate data race between poll_schedule_timeout() and
     pollwake()

   - fs/pipe: set FMODE_NOWAIT in create_pipe_files()

   - docs/vfs: update references to i_mutex to i_rwsem

   - fs/buffer: remove comment about hard sectorsize

   - fs/buffer: remove the min and max limit checks in __getblk_slow()

   - fs/libfs: don't assume blocksize <= PAGE_SIZE in
     generic_check_addressable

   - fs_context: fix parameter name in infofc() macro

   - fs: Prevent file descriptor table allocations exceeding INT_MAX"

* tag 'vfs-6.17-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (24 commits)
  netfs: Remove unused declaration netfs_queue_write_request()
  eventpoll: fix sphinx documentation build warning
  ext4: support uncached buffered I/O
  mm/pagemap: add write_begin_get_folio() helper function
  fs: change write_begin/write_end interface to take struct kiocb *
  drm/i915: Refactor shmem_pwrite() to use kiocb and write_iter
  drm/i915: Use kernel_write() in shmem object create
  eventpoll: Fix semi-unbounded recursion
  vfs: Remove unnecessary list_for_each_entry_safe() from evict_inodes()
  fs/libfs: don't assume blocksize <= PAGE_SIZE in generic_check_addressable
  fs/buffer: remove the min and max limit checks in __getblk_slow()
  fs: Prevent file descriptor table allocations exceeding INT_MAX
  fs: Remove three arguments from block_write_end()
  fs/ecryptfs: replace snprintf with sysfs_emit in show function
  fs: annotate suspected data race between poll_schedule_timeout() and pollwake()
  docs/vfs: update references to i_mutex to i_rwsem
  fs/buffer: remove comment about hard sectorsize
  fs_context: fix parameter name in infofc() macro
  VFS: change old_dir and new_dir in struct renamedata to dentrys
  proc_fd_getattr(): don't bother with S_ISDIR() check
  ...

1 files changed, 44 insertions, 14 deletions

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 0fbf5dfedb24..b22d6f819f78 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -218,6 +218,7 @@ struct eventpoll {
 	/* used to optimize loop detection check */
 	u64 gen;
 	struct hlist_head refs;
+	u8 loop_check_depth;
 
 	/*
 	 * usage count, used together with epitem->dying to
@@ -2140,23 +2141,24 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 }
 
 /**
- * ep_loop_check_proc - verify that adding an epoll file inside another
- *                      epoll structure does not violate the constraints, in
- *                      terms of closed loops, or too deep chains (which can
- *                      result in excessive stack usage).
+ * ep_loop_check_proc - verify that adding an epoll file @ep inside another
+ *                      epoll file does not create closed loops, and
+ *                      determine the depth of the subtree starting at @ep
  *
  * @ep: the &struct eventpoll to be currently checked.
  * @depth: Current depth of the path being checked.
  *
- * Return: %zero if adding the epoll @file inside current epoll
- *          structure @ep does not violate the constraints, or %-1 otherwise.
+ * Return: depth of the subtree, or INT_MAX if we found a loop or went too deep.
  */
 static int ep_loop_check_proc(struct eventpoll *ep, int depth)
 {
-	int error = 0;
+	int result = 0;
 	struct rb_node *rbp;
 	struct epitem *epi;
 
+	if (ep->gen == loop_check_gen)
+		return ep->loop_check_depth;
+
 	mutex_lock_nested(&ep->mtx, depth + 1);
 	ep->gen = loop_check_gen;
 	for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
@@ -2164,13 +2166,11 @@ static int ep_loop_check_proc(struct eventpoll *ep, int depth)
 		if (unlikely(is_file_epoll(epi->ffd.file))) {
 			struct eventpoll *ep_tovisit;
 			ep_tovisit = epi->ffd.file->private_data;
-			if (ep_tovisit->gen == loop_check_gen)
-				continue;
 			if (ep_tovisit == inserting_into || depth > EP_MAX_NESTS)
-				error = -1;
+				result = INT_MAX;
 			else
-				error = ep_loop_check_proc(ep_tovisit, depth + 1);
-			if (error != 0)
+				result = max(result, ep_loop_check_proc(ep_tovisit, depth + 1) + 1);
+			if (result > EP_MAX_NESTS)
 				break;
 		} else {
 			/*
@@ -2184,9 +2184,25 @@ static int ep_loop_check_proc(struct eventpoll *ep, int depth)
 			list_file(epi->ffd.file);
 		}
 	}
+	ep->loop_check_depth = result;
 	mutex_unlock(&ep->mtx);
 
-	return error;
+	return result;
+}
+
+/* ep_get_upwards_depth_proc - determine depth of @ep when traversed upwards */
+static int ep_get_upwards_depth_proc(struct eventpoll *ep, int depth)
+{
+	int result = 0;
+	struct epitem *epi;
+
+	if (ep->gen == loop_check_gen)
+		return ep->loop_check_depth;
+	hlist_for_each_entry_rcu(epi, &ep->refs, fllink)
+		result = max(result, ep_get_upwards_depth_proc(epi->ep, depth + 1) + 1);
+	ep->gen = loop_check_gen;
+	ep->loop_check_depth = result;
+	return result;
 }
 
 /**
@@ -2202,8 +2218,22 @@ static int ep_loop_check_proc(struct eventpoll *ep, int depth)
  */
 static int ep_loop_check(struct eventpoll *ep, struct eventpoll *to)
 {
+	int depth, upwards_depth;
+
 	inserting_into = ep;
-	return ep_loop_check_proc(to, 0);
+	/*
+	 * Check how deep down we can get from @to, and whether it is possible
+	 * to loop up to @ep.
+	 */
+	depth = ep_loop_check_proc(to, 0);
+	if (depth > EP_MAX_NESTS)
+		return -1;
+	/* Check how far up we can go from @ep. */
+	rcu_read_lock();
+	upwards_depth = ep_get_upwards_depth_proc(ep, 0);
+	rcu_read_unlock();
+
+	return (depth+1+upwards_depth > EP_MAX_NESTS) ? -1 : 0;
 }
 
 static void clear_tfile_check_list(void)