Merge tag 'vfs-6.12-rc2.fixes' of git://git.kernel.org/pub/scm/linux/…

…kernel/git/vfs/vfs

Pull vfs fixes from Christian Brauner:
 "afs:

   - Fix setting of the server responding flag

   - Remove unused struct afs_address_list and afs_put_address_list()
     function

   - Fix infinite loop because of unresponsive servers

   - Ensure that afs_retry_request() function is correctly added to the
     afs_req_ops netfs operations table

  netfs:

   - Fix netfs_folio tracepoint handling to handle NULL mappings

   - Add a missing folio_queue API documentation

   - Ensure that netfs_write_folio() correctly advances the iterator via
     iov_iter_advance()

   - Fix a dentry leak during concurrent cull and cookie lookup
     operations in cachefiles

  pidfs:

   - Correctly handle accessing another task's pid namespace"

* tag 'vfs-6.12-rc2.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  netfs: Fix the netfs_folio tracepoint to handle NULL mapping
  netfs: Add folio_queue API documentation
  netfs: Advance iterator correctly rather than jumping it
  afs: Fix the setting of the server responding flag
  afs: Remove unused struct and function prototype
  afs: Fix possible infinite loop with unresponsive servers
  pidfs: check for valid pid namespace
  afs: Fix missing wire-up of afs_retry_request()
  cachefiles: fix dentry leak in cachefiles_open_file()

Documentation/core-api/folio_queue.rst

@@ -0,0 +1,212 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+===========
+Folio Queue
+===========
+
+:Author: David Howells <dhowells@redhat.com>
+
+.. Contents:
+
+ * Overview
+ * Initialisation
+ * Adding and removing folios
+ * Querying information about a folio
+ * Querying information about a folio_queue
+ * Folio queue iteration
+ * Folio marks
+ * Lockless simultaneous production/consumption issues
+
+
+Overview
+========
+
+The folio_queue struct forms a single segment in a segmented list of folios
+that can be used to form an I/O buffer.  As such, the list can be iterated over
+using the ITER_FOLIOQ iov_iter type.
+
+The publicly accessible members of the structure are::
+
+	struct folio_queue {
+		struct folio_queue *next;
+		struct folio_queue *prev;
+		...
+	};
+
+A pair of pointers are provided, ``next`` and ``prev``, that point to the
+segments on either side of the segment being accessed.  Whilst this is a
+doubly-linked list, it is intentionally not a circular list; the outward
+sibling pointers in terminal segments should be NULL.
+
+Each segment in the list also stores:
+
+ * an ordered sequence of folio pointers,
+ * the size of each folio and
+ * three 1-bit marks per folio,
+
+but hese should not be accessed directly as the underlying data structure may
+change, but rather the access functions outlined below should be used.
+
+The facility can be made accessible by::
+
+	#include <linux/folio_queue.h>
+
+and to use the iterator::
+
+	#include <linux/uio.h>
+
+
+Initialisation
+==============
+
+A segment should be initialised by calling::
+
+	void folioq_init(struct folio_queue *folioq);
+
+with a pointer to the segment to be initialised.  Note that this will not
+necessarily initialise all the folio pointers, so care must be taken to check
+the number of folios added.
+
+
+Adding and removing folios
+==========================
+
+Folios can be set in the next unused slot in a segment struct by calling one
+of::
+
+	unsigned int folioq_append(struct folio_queue *folioq,
+				   struct folio *folio);
+
+	unsigned int folioq_append_mark(struct folio_queue *folioq,
+					struct folio *folio);
+
+Both functions update the stored folio count, store the folio and note its
+size.  The second function also sets the first mark for the folio added.  Both
+functions return the number of the slot used.  [!] Note that no attempt is made
+to check that the capacity wasn't overrun and the list will not be extended
+automatically.
+
+A folio can be excised by calling::
+
+	void folioq_clear(struct folio_queue *folioq, unsigned int slot);
+
+This clears the slot in the array and also clears all the marks for that folio,
+but doesn't change the folio count - so future accesses of that slot must check
+if the slot is occupied.
+
+
+Querying information about a folio
+==================================
+
+Information about the folio in a particular slot may be queried by the
+following function::
+
+	struct folio *folioq_folio(const struct folio_queue *folioq,
+				   unsigned int slot);
+
+If a folio has not yet been set in that slot, this may yield an undefined
+pointer.  The size of the folio in a slot may be queried with either of::
+
+	unsigned int folioq_folio_order(const struct folio_queue *folioq,
+					unsigned int slot);
+
+	size_t folioq_folio_size(const struct folio_queue *folioq,
+				 unsigned int slot);
+
+The first function returns the size as an order and the second as a number of
+bytes.
+
+
+Querying information about a folio_queue
+========================================
+
+Information may be retrieved about a particular segment with the following
+functions::
+
+	unsigned int folioq_nr_slots(const struct folio_queue *folioq);
+
+	unsigned int folioq_count(struct folio_queue *folioq);
+
+	bool folioq_full(struct folio_queue *folioq);
+
+The first function returns the maximum capacity of a segment.  It must not be
+assumed that this won't vary between segments.  The second returns the number
+of folios added to a segments and the third is a shorthand to indicate if the
+segment has been filled to capacity.
+
+Not that the count and fullness are not affected by clearing folios from the
+segment.  These are more about indicating how many slots in the array have been
+initialised, and it assumed that slots won't get reused, but rather the segment
+will get discarded as the queue is consumed.
+
+
+Folio marks
+===========
+
+Folios within a queue can also have marks assigned to them.  These marks can be
+used to note information such as if a folio needs folio_put() calling upon it.
+There are three marks available to be set for each folio.
+
+The marks can be set by::
+
+	void folioq_mark(struct folio_queue *folioq, unsigned int slot);
+	void folioq_mark2(struct folio_queue *folioq, unsigned int slot);
+	void folioq_mark3(struct folio_queue *folioq, unsigned int slot);
+
+Cleared by::
+
+	void folioq_unmark(struct folio_queue *folioq, unsigned int slot);
+	void folioq_unmark2(struct folio_queue *folioq, unsigned int slot);
+	void folioq_unmark3(struct folio_queue *folioq, unsigned int slot);
+
+And the marks can be queried by::
+
+	bool folioq_is_marked(const struct folio_queue *folioq, unsigned int slot);
+	bool folioq_is_marked2(const struct folio_queue *folioq, unsigned int slot);
+	bool folioq_is_marked3(const struct folio_queue *folioq, unsigned int slot);
+
+The marks can be used for any purpose and are not interpreted by this API.
+
+
+Folio queue iteration
+=====================
+
+A list of segments may be iterated over using the I/O iterator facility using
+an ``iov_iter`` iterator of ``ITER_FOLIOQ`` type.  The iterator may be
+initialised with::
+
+	void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction,
+				  const struct folio_queue *folioq,
+				  unsigned int first_slot, unsigned int offset,
+				  size_t count);
+
+This may be told to start at a particular segment, slot and offset within a
+queue.  The iov iterator functions will follow the next pointers when advancing
+and prev pointers when reverting when needed.
+
+
+Lockless simultaneous production/consumption issues
+===================================================
+
+If properly managed, the list can be extended by the producer at the head end
+and shortened by the consumer at the tail end simultaneously without the need
+to take locks.  The ITER_FOLIOQ iterator inserts appropriate barriers to aid
+with this.
+
+Care must be taken when simultaneously producing and consuming a list.  If the
+last segment is reached and the folios it refers to are entirely consumed by
+the IOV iterators, an iov_iter struct will be left pointing to the last segment
+with a slot number equal to the capacity of that segment.  The iterator will
+try to continue on from this if there's another segment available when it is
+used again, but care must be taken lest the segment got removed and freed by
+the consumer before the iterator was advanced.
+
+It is recommended that the queue always contain at least one segment, even if
+that segment has never been filled or is entirely spent.  This prevents the
+head and tail pointers from collapsing.
+
+
+API Function Reference
+======================
+
+.. kernel-doc:: include/linux/folio_queue.h

fs/afs/afs_vl.h

@@ -134,13 +134,4 @@ struct afs_uvldbentry__xdr {
 	__be32			spares9;
 };
 
-struct afs_address_list {
-	refcount_t		usage;
-	unsigned int		version;
-	unsigned int		nr_addrs;
-	struct sockaddr_rxrpc	addrs[];
-};
-
-extern void afs_put_address_list(struct afs_address_list *alist);
-
 #endif /* AFS_VL_H */

fs/afs/file.c

@@ -420,6 +420,7 @@ const struct netfs_request_ops afs_req_ops = {
 	.begin_writeback	= afs_begin_writeback,
 	.prepare_write		= afs_prepare_write,
 	.issue_write		= afs_issue_write,
+	.retry_request		= afs_retry_request,
 };
 
 static void afs_add_open_mmap(struct afs_vnode *vnode)

fs/afs/fs_operation.c

@@ -201,7 +201,7 @@ void afs_wait_for_operation(struct afs_operation *op)
 		}
 	}
 
-	if (op->call_responded)
+	if (op->call_responded && op->server)
 		set_bit(AFS_SERVER_FL_RESPONDING, &op->server->flags);
 
 	if (!afs_op_error(op)) {

fs/afs/fs_probe.c

@@ -506,10 +506,10 @@ int afs_wait_for_one_fs_probe(struct afs_server *server, struct afs_endpoint_sta
 	finish_wait(&server->probe_wq, &wait);
 
 dont_wait:
-	if (estate->responsive_set & ~exclude)
-		return 1;
 	if (test_bit(AFS_ESTATE_SUPERSEDED, &estate->flags))
 		return 0;
+	if (estate->responsive_set & ~exclude)
+		return 1;
 	if (is_intr && signal_pending(current))
 		return -ERESTARTSYS;
 	if (timo == 0)

fs/afs/rotate.c

@@ -632,8 +632,10 @@ bool afs_select_fileserver(struct afs_operation *op)
 wait_for_more_probe_results:
 	error = afs_wait_for_one_fs_probe(op->server, op->estate, op->addr_tried,
 					  !(op->flags & AFS_OPERATION_UNINTR));
-	if (!error)
+	if (error == 1)
 		goto iterate_address;
+	if (!error)
+		goto restart_from_beginning;
 
 	/* We've now had a failure to respond on all of a server's addresses -
 	 * immediately probe them again and consider retrying the server.
@@ -644,10 +646,13 @@ bool afs_select_fileserver(struct afs_operation *op)
 		error = afs_wait_for_one_fs_probe(op->server, op->estate, op->addr_tried,
 						  !(op->flags & AFS_OPERATION_UNINTR));
 		switch (error) {
-		case 0:
+		case 1:
 			op->flags &= ~AFS_OPERATION_RETRY_SERVER;
-			trace_afs_rotate(op, afs_rotate_trace_retry_server, 0);
+			trace_afs_rotate(op, afs_rotate_trace_retry_server, 1);
 			goto retry_server;
+		case 0:
+			trace_afs_rotate(op, afs_rotate_trace_retry_server, 0);
+			goto restart_from_beginning;
 		case -ERESTARTSYS:
 			afs_op_set_error(op, error);
 			goto failed;

fs/cachefiles/namei.c

@@ -595,14 +595,12 @@ static bool cachefiles_open_file(struct cachefiles_object *object,
 	 * write and readdir but not lookup or open).
 	 */
 	touch_atime(&file->f_path);
-	dput(dentry);
 	return true;
 
 check_failed:
 	fscache_cookie_lookup_negative(object->cookie);
 	cachefiles_unmark_inode_in_use(object, file);
 	fput(file);
-	dput(dentry);
 	if (ret == -ESTALE)
 		return cachefiles_create_file(object);
 	return false;
@@ -611,7 +609,6 @@ static bool cachefiles_open_file(struct cachefiles_object *object,
 	fput(file);
 error:
 	cachefiles_do_unmark_inode_in_use(object, d_inode(dentry));
-	dput(dentry);
 	return false;
 }
 
@@ -654,7 +651,9 @@ bool cachefiles_look_up_object(struct cachefiles_object *object)
 		goto new_file;
 	}
 
-	if (!cachefiles_open_file(object, dentry))
+	ret = cachefiles_open_file(object, dentry);
+	dput(dentry);
+	if (!ret)
 		return false;
 
 	_leave(" = t [%lu]", file_inode(object->file)->i_ino);

fs/netfs/write_issue.c

@@ -317,6 +317,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
 	struct netfs_io_stream *stream;
 	struct netfs_group *fgroup; /* TODO: Use this with ceph */
 	struct netfs_folio *finfo;
+	size_t iter_off = 0;
 	size_t fsize = folio_size(folio), flen = fsize, foff = 0;
 	loff_t fpos = folio_pos(folio), i_size;
 	bool to_eof = false, streamw = false;
@@ -472,7 +473,12 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
 		if (choose_s < 0)
 			break;
 		stream = &wreq->io_streams[choose_s];
-		wreq->io_iter.iov_offset = stream->submit_off;
+
+		/* Advance the iterator(s). */
+		if (stream->submit_off > iter_off) {
+			iov_iter_advance(&wreq->io_iter, stream->submit_off - iter_off);
+			iter_off = stream->submit_off;
+		}
 
 		atomic64_set(&wreq->issued_to, fpos + stream->submit_off);
 		stream->submit_extendable_to = fsize - stream->submit_off;
@@ -487,8 +493,8 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
 			debug = true;
 	}
 
-	wreq->io_iter.iov_offset = 0;
-	iov_iter_advance(&wreq->io_iter, fsize);
+	if (fsize > iter_off)
+		iov_iter_advance(&wreq->io_iter, fsize - iter_off);
 	atomic64_set(&wreq->issued_to, fpos + fsize);
 
 	if (!debug)

fs/pidfs.c

@@ -120,6 +120,7 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	struct nsproxy *nsp __free(put_nsproxy) = NULL;
 	struct pid *pid = pidfd_pid(file);
 	struct ns_common *ns_common = NULL;
+	struct pid_namespace *pid_ns;
 
 	if (arg)
 		return -EINVAL;
@@ -202,7 +203,9 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case PIDFD_GET_PID_NAMESPACE:
 		if (IS_ENABLED(CONFIG_PID_NS)) {
 			rcu_read_lock();
-			ns_common = to_ns_common( get_pid_ns(task_active_pid_ns(task)));
+			pid_ns = task_active_pid_ns(task);
+			if (pid_ns)
+				ns_common = to_ns_common(get_pid_ns(pid_ns));
 			rcu_read_unlock();
 		}
 		break;