Merge patch series "Random netfs folio fixes"

Matthew Wilcox (Oracle) <willy@infradead.org> says:

A few minor fixes; nothing earth-shattering.

Matthew Wilcox (Oracle) (3):
  netfs: Remove call to folio_index()
  netfs: Fix a few minor bugs in netfs_page_mkwrite()
  netfs: Remove unnecessary references to pages

Link: https://lore.kernel.org/r/20241005182307.3190401-1-willy@infradead.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

10 files changed, 52 insertions, 48 deletions

diff --git a/fs/afs/afs_vl.h b/fs/afs/afs_vl.h
index 9c65ffb8a523..a06296c8827d 100644
--- a/fs/afs/afs_vl.h
+++ b/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 */
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 492d857a3fa0..6762eff97517 100644
--- a/fs/afs/file.c
+++ b/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)
diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index 3546b087e791..428721bbe4f6 100644
--- a/fs/afs/fs_operation.c
+++ b/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)) {
diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c
index 580de4adaaf6..b516d05b0fef 100644
--- a/fs/afs/fs_probe.c
+++ b/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)
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index ed09d4d4c211..d612983d6f38 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -632,8 +632,10 @@ iterate_address:
 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 @@ wait_for_more_probe_results:
 		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;
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index f53977169db4..2b3f9935dbb4 100644
--- a/fs/cachefiles/namei.c
+++ b/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 @@ error_fput:
 	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);
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index c40e226053cc..17aaec00002b 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -646,7 +646,7 @@ static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len,
 	if (unlikely(always_fill)) {
 		if (pos - offset + len <= i_size)
 			return false; /* Page entirely before EOF */
-		zero_user_segment(&folio->page, 0, plen);
+		folio_zero_segment(folio, 0, plen);
 		folio_mark_uptodate(folio);
 		return true;
 	}
@@ -665,7 +665,7 @@ static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len,
 
 	return false;
 zero_out:
-	zero_user_segments(&folio->page, 0, offset, offset + len, plen);
+	folio_zero_segments(folio, 0, offset, offset + len, plen);
 	return true;
 }
 
@@ -732,7 +732,7 @@ retry:
 	if (folio_test_uptodate(folio))
 		goto have_folio;
 
-	/* If the page is beyond the EOF, we want to clear it - unless it's
+	/* If the folio is beyond the EOF, we want to clear it - unless it's
 	 * within the cache granule containing the EOF, in which case we need
 	 * to preload the granule.
 	 */
@@ -792,7 +792,7 @@ error:
 EXPORT_SYMBOL(netfs_write_begin);
 
 /*
- * Preload the data into a page we're proposing to write into.
+ * Preload the data into a folio we're proposing to write into.
  */
 int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 			     size_t offset, size_t len)
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index b3910dfcb56d..b4826360a411 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -83,13 +83,13 @@ static void netfs_update_i_size(struct netfs_inode *ctx, struct inode *inode,
  * netfs_perform_write - Copy data into the pagecache.
  * @iocb: The operation parameters
  * @iter: The source buffer
- * @netfs_group: Grouping for dirty pages (eg. ceph snaps).
+ * @netfs_group: Grouping for dirty folios (eg. ceph snaps).
  *
- * Copy data into pagecache pages attached to the inode specified by @iocb.
+ * Copy data into pagecache folios attached to the inode specified by @iocb.
  * The caller must hold appropriate inode locks.
  *
- * Dirty pages are tagged with a netfs_folio struct if they're not up to date
- * to indicate the range modified.  Dirty pages may also be tagged with a
+ * Dirty folios are tagged with a netfs_folio struct if they're not up to date
+ * to indicate the range modified.  Dirty folios may also be tagged with a
  * netfs-specific grouping such that data from an old group gets flushed before
  * a new one is started.
  */
@@ -223,11 +223,11 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 		 * we try to read it.
 		 */
 		if (fpos >= ctx->zero_point) {
-			zero_user_segment(&folio->page, 0, offset);
+			folio_zero_segment(folio, 0, offset);
 			copied = copy_folio_from_iter_atomic(folio, offset, part, iter);
 			if (unlikely(copied == 0))
 				goto copy_failed;
-			zero_user_segment(&folio->page, offset + copied, flen);
+			folio_zero_segment(folio, offset + copied, flen);
 			__netfs_set_group(folio, netfs_group);
 			folio_mark_uptodate(folio);
 			trace_netfs_folio(folio, netfs_modify_and_clear);
@@ -407,7 +407,7 @@ EXPORT_SYMBOL(netfs_perform_write);
  * netfs_buffered_write_iter_locked - write data to a file
  * @iocb:	IO state structure (file, offset, etc.)
  * @from:	iov_iter with data to write
- * @netfs_group: Grouping for dirty pages (eg. ceph snaps).
+ * @netfs_group: Grouping for dirty folios (eg. ceph snaps).
  *
  * This function does all the work needed for actually writing data to a
  * file. It does all basic checks, removes SUID from the file, updates
@@ -491,7 +491,9 @@ EXPORT_SYMBOL(netfs_file_write_iter);
 
 /*
  * Notification that a previously read-only page is about to become writable.
- * Note that the caller indicates a single page of a multipage folio.
+ * The caller indicates the precise page that needs to be written to, but
+ * we only track group on a per-folio basis, so we block more often than
+ * we might otherwise.
  */
 vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group)
 {
@@ -501,7 +503,7 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = file_inode(file);
 	struct netfs_inode *ictx = netfs_inode(inode);
-	vm_fault_t ret = VM_FAULT_RETRY;
+	vm_fault_t ret = VM_FAULT_NOPAGE;
 	int err;
 
 	_enter("%lx", folio->index);
@@ -510,21 +512,15 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
 
 	if (folio_lock_killable(folio) < 0)
 		goto out;
-	if (folio->mapping != mapping) {
-		folio_unlock(folio);
-		ret = VM_FAULT_NOPAGE;
-		goto out;
-	}
-
-	if (folio_wait_writeback_killable(folio)) {
-		ret = VM_FAULT_LOCKED;
-		goto out;
-	}
+	if (folio->mapping != mapping)
+		goto unlock;
+	if (folio_wait_writeback_killable(folio) < 0)
+		goto unlock;
 
 	/* Can we see a streaming write here? */
 	if (WARN_ON(!folio_test_uptodate(folio))) {
-		ret = VM_FAULT_SIGBUS | VM_FAULT_LOCKED;
-		goto out;
+		ret = VM_FAULT_SIGBUS;
+		goto unlock;
 	}
 
 	group = netfs_folio_group(folio);
@@ -559,5 +555,8 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
 out:
 	sb_end_pagefault(inode->i_sb);
 	return ret;
+unlock:
+	folio_unlock(folio);
+	goto out;
 }
 EXPORT_SYMBOL(netfs_page_mkwrite);
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 0929d9fd4ce7..6293f547e4c3 100644
--- a/fs/netfs/write_issue.c
+++ b/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)
diff --git a/fs/pidfs.c b/fs/pidfs.c
index 7ffdc88dfb52..80675b6bf884 100644
--- a/fs/pidfs.c
+++ b/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;