Merge tag 'vfs-6.10-rc2.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs fixes from Christian Brauner:

 - Fix io_uring based write-through after converting cifs to use the
   netfs library

 - Fix aio error handling when doing write-through via netfs library

 - Fix performance regression in iomap when used with non-large folio
   mappings

 - Fix signalfd error code

 - Remove obsolete comment in signalfd code

 - Fix async request indication in netfs_perform_write() by raising
   BDP_ASYNC when IOCB_NOWAIT is set

 - Yield swap device immediately to prevent spurious EBUSY errors

 - Don't cross a .backup mountpoint from backup volumes in afs to avoid
   infinite loops

 - Fix a race between umount and async request completion in 9p after 9p
   was converted to use the netfs library

* tag 'vfs-6.10-rc2.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  netfs, 9p: Fix race between umount and async request completion
  afs: Don't cross .backup mountpoint from backup volume
  swap: yield device immediately
  netfs: Fix setting of BDP_ASYNC from iocb flags
  signalfd: drop an obsolete comment
  signalfd: fix error return code
  iomap: fault in smaller chunks for non-large folio mappings
  filemap: add helper mapping_max_folio_size()
  netfs: Fix AIO error handling when doing write-through
  netfs: Fix io_uring based write-through

14 files changed, 68 insertions, 27 deletions

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 7a3308d77606..fd72fc38c8f5 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -348,6 +348,7 @@ void v9fs_evict_inode(struct inode *inode)
 	__le32 __maybe_unused version;
 
 	if (!is_bad_inode(inode)) {
+		netfs_wait_for_outstanding_io(inode);
 		truncate_inode_pages_final(&inode->i_data);
 
 		version = cpu_to_le32(v9inode->qid.version);
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 94fc049aff58..15bb7989c387 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -648,6 +648,7 @@ void afs_evict_inode(struct inode *inode)
 
 	ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode);
 
+	netfs_wait_for_outstanding_io(inode);
 	truncate_inode_pages_final(&inode->i_data);
 
 	afs_set_cache_aux(vnode, &aux);
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 97f50e9fd9eb..297487ee8323 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -140,6 +140,11 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt)
 		put_page(page);
 		if (ret < 0)
 			return ret;
+
+		/* Don't cross a backup volume mountpoint from a backup volume */
+		if (src_as->volume && src_as->volume->type == AFSVL_BACKVOL &&
+		    ctx->type == AFSVL_BACKVOL)
+			return -ENODEV;
 	}
 
 	return 0;
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 41c8f0c68ef5..c5802a459334 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -898,11 +898,11 @@ static bool iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
 static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 {
 	loff_t length = iomap_length(iter);
-	size_t chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
 	loff_t pos = iter->pos;
 	ssize_t total_written = 0;
 	long status = 0;
 	struct address_space *mapping = iter->inode->i_mapping;
+	size_t chunk = mapping_max_folio_size(mapping);
 	unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0;
 
 	do {
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 1121601536d1..07bc1fd43530 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -181,7 +181,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 	struct folio *folio, *writethrough = NULL;
 	enum netfs_how_to_modify howto;
 	enum netfs_folio_trace trace;
-	unsigned int bdp_flags = (iocb->ki_flags & IOCB_SYNC) ? 0: BDP_ASYNC;
+	unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0;
 	ssize_t written = 0, ret, ret2;
 	loff_t i_size, pos = iocb->ki_pos, from, to;
 	size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index f516460e994e..e14cd53ac9fd 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -12,7 +12,7 @@
 static void netfs_cleanup_dio_write(struct netfs_io_request *wreq)
 {
 	struct inode *inode = wreq->inode;
-	unsigned long long end = wreq->start + wreq->len;
+	unsigned long long end = wreq->start + wreq->transferred;
 
 	if (!wreq->error &&
 	    i_size_read(inode) < end) {
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index c90d482b1650..f4a642727479 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -72,6 +72,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 		}
 	}
 
+	atomic_inc(&ctx->io_count);
 	trace_netfs_rreq_ref(rreq->debug_id, 1, netfs_rreq_trace_new);
 	netfs_proc_add_rreq(rreq);
 	netfs_stat(&netfs_n_rh_rreq);
@@ -124,6 +125,7 @@ static void netfs_free_request(struct work_struct *work)
 {
 	struct netfs_io_request *rreq =
 		container_of(work, struct netfs_io_request, work);
+	struct netfs_inode *ictx = netfs_inode(rreq->inode);
 	unsigned int i;
 
 	trace_netfs_rreq(rreq, netfs_rreq_trace_free);
@@ -142,6 +144,9 @@ static void netfs_free_request(struct work_struct *work)
 		}
 		kvfree(rreq->direct_bv);
 	}
+
+	if (atomic_dec_and_test(&ictx->io_count))
+		wake_up_var(&ictx->io_count);
 	call_rcu(&rreq->rcu, netfs_free_request_rcu);
 }
 
diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index 60112e4b2c5e..426cf87aaf2e 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -510,7 +510,7 @@ reassess_streams:
 	 * stream has a gap that can be jumped.
 	 */
 	if (notes & SOME_EMPTY) {
-		unsigned long long jump_to = wreq->start + wreq->len;
+		unsigned long long jump_to = wreq->start + READ_ONCE(wreq->submitted);
 
 		for (s = 0; s < NR_IO_STREAMS; s++) {
 			stream = &wreq->io_streams[s];
@@ -690,10 +690,11 @@ void netfs_write_collection_worker(struct work_struct *work)
 	wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS);
 
 	if (wreq->iocb) {
-		wreq->iocb->ki_pos += wreq->transferred;
+		size_t written = min(wreq->transferred, wreq->len);
+		wreq->iocb->ki_pos += written;
 		if (wreq->iocb->ki_complete)
 			wreq->iocb->ki_complete(
-				wreq->iocb, wreq->error ? wreq->error : wreq->transferred);
+				wreq->iocb, wreq->error ? wreq->error : written);
 		wreq->iocb = VFS_PTR_POISON;
 	}
 
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index e190043bc0da..3aa86e268f40 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -254,7 +254,7 @@ static void netfs_issue_write(struct netfs_io_request *wreq,
 	stream->construct = NULL;
 
 	if (subreq->start + subreq->len > wreq->start + wreq->submitted)
-		wreq->len = wreq->submitted = subreq->start + subreq->len - wreq->start;
+		WRITE_ONCE(wreq->submitted, subreq->start + subreq->len - wreq->start);
 	netfs_do_issue_write(stream, subreq);
 }
 
@@ -636,7 +636,12 @@ int netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_contr
 
 	mutex_unlock(&ictx->wb_lock);
 
-	ret = wreq->error;
+	if (wreq->iocb) {
+		ret = -EIOCBQUEUED;
+	} else {
+		wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS, TASK_UNINTERRUPTIBLE);
+		ret = wreq->error;
+	}
 	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
 	return ret;
 }
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 4a5614442dbf..ec7b2da2477a 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -282,14 +282,10 @@ static int do_signalfd4(int ufd, sigset_t *mask, int flags)
 		if (IS_ERR(file)) {
 			put_unused_fd(ufd);
 			kfree(ctx);
-			return ufd;
+			return PTR_ERR(file);
 		}
 		file->f_mode |= FMODE_NOWAIT;
 
-		/*
-		 * When we call this, the initialization must be complete, since
-		 * anon_inode_getfd() will install the fd.
-		 */
 		fd_install(ufd, file);
 	} else {
 		struct fd f = fdget(ufd);
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index a665aac9be9f..bb86fc0641d8 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -431,6 +431,7 @@ cifs_free_inode(struct inode *inode)
 static void
 cifs_evict_inode(struct inode *inode)
 {
+	netfs_wait_for_outstanding_io(inode);
 	truncate_inode_pages_final(&inode->i_data);
 	if (inode->i_state & I_PINNING_NETFS_WB)
 		cifs_fscache_unuse_inode_cookie(inode, true);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index d2d291a9cdad..3ca3906bb8da 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -68,6 +68,7 @@ struct netfs_inode {
 	loff_t			remote_i_size;	/* Size of the remote file */
 	loff_t			zero_point;	/* Size after which we assume there's no data
 						 * on the server */
+	atomic_t		io_count;	/* Number of outstanding reqs */
 	unsigned long		flags;
 #define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
 #define NETFS_ICTX_UNBUFFERED	1		/* I/O should not use the pagecache */
@@ -474,6 +475,7 @@ static inline void netfs_inode_init(struct netfs_inode *ctx,
 	ctx->remote_i_size = i_size_read(&ctx->inode);
 	ctx->zero_point = LLONG_MAX;
 	ctx->flags = 0;
+	atomic_set(&ctx->io_count, 0);
 #if IS_ENABLED(CONFIG_FSCACHE)
 	ctx->cache = NULL;
 #endif
@@ -517,4 +519,20 @@ static inline struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx)
 #endif
 }
 
+/**
+ * netfs_wait_for_outstanding_io - Wait for outstanding I/O to complete
+ * @ctx: The netfs inode to wait on
+ *
+ * Wait for outstanding I/O requests of any type to complete.  This is intended
+ * to be called from inode eviction routines.  This makes sure that any
+ * resources held by those requests are cleaned up before we let the inode get
+ * cleaned up.
+ */
+static inline void netfs_wait_for_outstanding_io(struct inode *inode)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+
+	wait_var_event(&ictx->io_count, atomic_read(&ictx->io_count) == 0);
+}
+
 #endif /* _LINUX_NETFS_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 3d69589c00a4..ee633712bba0 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -346,6 +346,19 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
 	m->gfp_mask = mask;
 }
 
+/*
+ * There are some parts of the kernel which assume that PMD entries
+ * are exactly HPAGE_PMD_ORDER.  Those should be fixed, but until then,
+ * limit the maximum allocation order to PMD size.  I'm not aware of any
+ * assumptions about maximum order if THP are disabled, but 8 seems like
+ * a good order (that's 1MB if you're using 4kB pages)
+ */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define MAX_PAGECACHE_ORDER	HPAGE_PMD_ORDER
+#else
+#define MAX_PAGECACHE_ORDER	8
+#endif
+
 /**
  * mapping_set_large_folios() - Indicate the file supports large folios.
  * @mapping: The file.
@@ -372,6 +385,14 @@ static inline bool mapping_large_folio_support(struct address_space *mapping)
 		test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags);
 }
 
+/* Return the maximum folio size for this pagecache mapping, in bytes. */
+static inline size_t mapping_max_folio_size(struct address_space *mapping)
+{
+	if (mapping_large_folio_support(mapping))
+		return PAGE_SIZE << MAX_PAGECACHE_ORDER;
+	return PAGE_SIZE;
+}
+
 static inline int filemap_nr_thps(struct address_space *mapping)
 {
 #ifdef CONFIG_READ_ONLY_THP_FOR_FS
@@ -530,19 +551,6 @@ static inline void *detach_page_private(struct page *page)
 	return folio_detach_private(page_folio(page));
 }
 
-/*
- * There are some parts of the kernel which assume that PMD entries
- * are exactly HPAGE_PMD_ORDER.  Those should be fixed, but until then,
- * limit the maximum allocation order to PMD size.  I'm not aware of any
- * assumptions about maximum order if THP are disabled, but 8 seems like
- * a good order (that's 1MB if you're using 4kB pages)
- */
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define MAX_PAGECACHE_ORDER	HPAGE_PMD_ORDER
-#else
-#define MAX_PAGECACHE_ORDER	8
-#endif
-
 #ifdef CONFIG_NUMA
 struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order);
 #else
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index d9abb7ab031d..753b8dd42a59 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -1595,7 +1595,7 @@ int swsusp_check(bool exclusive)
 
 put:
 		if (error)
-			fput(hib_resume_bdev_file);
+			bdev_fput(hib_resume_bdev_file);
 		else
 			pr_debug("Image signature found, resuming\n");
 	} else {