Merge tag 'cifs-fixes-7.3-rc6' of https://git.manguebit.org/linux

Pull smb client fixes from Paulo Alcantara:
 "Fix a series of data corruption and I/O error bugs found by running
  generic/363 (fsx) in a loop against Windows Server 2022 and Samba.

   - Stop data dirtied past EOF through an mmap from reappearing as file
     content once the file is extended by a write, truncate, zero range,
     copy range or clone range

   - Flush dirty data and drain in-flight I/O before operations that
     assume the pagecache and the server agree on the file: querying
     allocated ranges, the O_TRUNC open, interior zero range, and
     server-side copy/clone

   - Stop a genuine size-extending zero range or preallocate from being
     refused with -EOPNOTSUPP when the inode is not read caching, by
     querying the server's authoritative EOF instead of trusting a stale
     cached i_size

   - Zero the untransferred tail of a short read, both in the netfs
     read-gaps path (where stale folio content could otherwise be
     written back to the server) and in the DIO/unbuffered read
     collector, and tell a real EOF apart from a stale cached
     remote_i_size after a lease downgrade

   - Require stable pages on signed connections so a buffered write
     can't modify a folio whose signature has already been computed and
     is in flight, which the server rejected with STATUS_ACCESS_DENIED
     and the client surfaced as -EIO

   - Split several cifsFileInfo flags out of a shared bitfield byte so
     concurrent updates taken under different locks no longer clobber
     each other through a byte-level RMW"

* tag 'cifs-fixes-7.3-rc6' of https://git.manguebit.org/linux:
  smb: client: split cifsFileInfo bitfields to avoid shared-byte RMW races
  smb: client: require stable pages for signed connections
  smb: client: distinguish real EOF from a stale remote_i_size on read
  netfs: zero the tail of a short DIO/unbuffered read
  smb: client: only require read lease for size-extending preallocate
  netfs: zero gaps in read-gaps folio to avoid writing back stale data
  smb: client: only require read lease for size-extending zero range
  smb: client: drain and invalidate before server-side copy/clone
  smb: client: flush dirty data before zeroing a range
  smb: client: drain outstanding I/O before truncating on O_TRUNC open
  smb: client: flush and commit data before querying allocated ranges
  smb: client: discard post-EOF pagecache when extending a file via clone range
  smb: client: discard post-EOF pagecache when extending a file via copy range
  smb: client: discard post-EOF pagecache when extending a file via zero range
  smb: client: clear post-EOF pagecache when extending a file via truncate
  netfs: clear post-EOF pagecache when extending a file via write

15 files changed, 347 insertions, 56 deletions

diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index ddd799df6..a9de281db 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -451,6 +451,32 @@ one.
 The inode should be marked ``NETFS_ICTX_SINGLE_NO_UPLOAD`` if this API is to be
 used.  The writeback function requires the buffer to be of ITER_FOLIOQ type.
 
+Clearing Stale Post-EOF Pagecache
+---------------------------------
+
+When a file is extended, data left in the pagecache past the old EOF by a write
+through an mmap must not be exposed as file content.  Netfslib clears this on
+its own write paths, and exports a helper so a filesystem can do the same from
+a resize path (truncate, setattr, fallocate and the like) that holds the
+inode's ``i_rwsem`` exclusively across the whole resize::
+
+	void netfs_clear_stale_post_isize(struct inode *inode, uoff_t from,
+					  uoff_t to);
+
+This zeroes any such data within the ``[from, to)`` hole to be made, where
+@from is the old EOF and @to is the new one, and the caller must have already
+updated ``i_size`` to @to before calling it.  Only the folio straddling @from
+can hold data written past the EOF through an mmap, as pages wholly beyond the
+EOF can't be faulted in, so the zeroing is limited to that folio.  The folio is
+zeroed rather than dropped so that a concurrent extending write can't lose
+data.
+
+This overlaps with ``pagecache_isize_extended()`` but can't reuse it: that
+helper is keyed on a sub-page block size and is a no-op when the block size is
+``>= PAGE_SIZE`` (as on network filesystems), and it doesn't wait for
+writeback.  As both address the same problem, a change to one should probably
+be reflected in the other to keep them in sync.
+
 High-Level VM API
 ==================
 
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 105194de6..e6506942a 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -541,6 +541,13 @@ static int netfs_read_gaps(struct file *file, struct folio *folio)
 
 	ret = netfs_wait_for_read(rreq);
 	if (ret >= 0) {
+		if (ret < flen) {
+			struct iov_iter iter;
+
+			iov_iter_bvec(&iter, ITER_DEST, bvec, i, flen);
+			iov_iter_advance(&iter, ret);
+			iov_iter_zero(flen - ret, &iter);
+		}
 		if (group)
 			folio_change_private(folio, group);
 		else
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 2cdb68e6b..ecf119b4f 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -469,6 +469,7 @@ ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *fr
 					 struct netfs_group *netfs_group)
 {
 	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
 	ssize_t ret;
 
 	trace_netfs_write_iter(iocb, from);
@@ -481,6 +482,14 @@ ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *fr
 	if (ret)
 		return ret;
 
+	if (iocb->ki_pos > i_size_read(inode)) {
+		ret = netfs_clear_stale_pre_isize(inode, i_size_read(inode),
+						  iocb->ki_pos,
+						  iocb->ki_flags & IOCB_NOWAIT);
+		if (ret)
+			return ret;
+	}
+
 	return netfs_perform_write(iocb, from, netfs_group);
 }
 EXPORT_SYMBOL(netfs_buffered_write_iter_locked);
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index 236127741..8be74706d 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -359,6 +359,15 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	ret = file_update_time(file);
 	if (ret < 0)
 		goto out;
+
+	if (iocb->ki_pos > i_size_read(inode)) {
+		ret = netfs_clear_stale_pre_isize(inode, i_size_read(inode),
+						  iocb->ki_pos,
+						  iocb->ki_flags & IOCB_NOWAIT);
+		if (ret < 0)
+			goto out;
+	}
+
 	if (iocb->ki_flags & IOCB_NOWAIT) {
 		/* We could block if there are any pages in the range. */
 		ret = -EAGAIN;
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index c79c8e69d..786af76da 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -80,6 +80,8 @@ ssize_t netfs_wait_for_write(struct netfs_io_request *rreq);
 void netfs_wait_for_paused_read(struct netfs_io_request *rreq);
 void netfs_wait_for_paused_write(struct netfs_io_request *rreq);
 void netfs_wait_for_put_ra_refs(struct netfs_io_request *rreq);
+int netfs_clear_stale_pre_isize(struct inode *inode, uoff_t from,
+				uoff_t to, bool nowait);
 
 /*
  * objects.c
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index f5c1c463f..523057390 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/swap.h>
+#include <linux/rmap.h>
 #include "internal.h"
 
 /**
@@ -582,3 +583,101 @@ void netfs_wait_for_put_ra_refs(struct netfs_io_request *rreq)
 	trace_netfs_rreq(rreq, netfs_rreq_trace_waited_put_ra_refs);
 	finish_wait(&rreq->waitq, &myself);
 }
+
+/**
+ * netfs_clear_stale_isize - Clear stale pagecache in a to-be-created hole
+ * @inode: The inode to act upon.
+ * @from: The base of the hole to be made.
+ * @to: The top of the hole to be made.
+ * @nowait: True to return -EAGAIN rather than block.
+ * @exclusive: True if the caller holds i_rwsem exclusively for the resize.
+ *
+ * Zero any data left in the pagecache within the [@from, @to) hole by a
+ * write through an mmap so that it isn't exposed as file content once the
+ * file is extended.  Only the uptodate folio straddling @from can hold such
+ * data as pages wholly beyond the EOF can't be faulted in, so the zeroing
+ * is limited to that folio.  The folio is zeroed rather than dropped so
+ * that a concurrent extending write can't lose data.
+ *
+ * If @exclusive is false, @from is re-read from i_size and used to clamp
+ * the zeroed range, for callers that may race with another writer also
+ * extending the file (eg. multiple buffered writes extending the same file
+ * under a shared i_rwsem).  If @exclusive is true, for callers that hold
+ * i_rwsem exclusively across the whole resize and have already updated
+ * i_size to @to, staleness is decided from the folio's dirty state instead:
+ * since no genuine concurrent buffered writer can be racing, a lockless
+ * stat() adopting a server-confirmed size mid-resize has no data behind it
+ * and never dirties the folio, so it can't fool this check into skipping
+ * the zeroing the way it could fool the @exclusive false clamp.
+ *
+ * pagecache_isize_extended() can't be reused here: it is keyed on a
+ * sub-page block size (a no-op when the block size is >= PAGE_SIZE, as on
+ * network filesystems), runs after i_size is updated, can't honour
+ * @nowait, and doesn't wait for writeback.  Keep the two in sync if either
+ * is changed.
+ *
+ * Return: 0 on success, or -EAGAIN if @nowait is set and the folio is
+ * mapped or under writeback and so can't be cleaned without blocking.
+ */
+static int netfs_clear_stale_isize(struct inode *inode, uoff_t from,
+				   uoff_t to, bool nowait, bool exclusive)
+{
+	struct address_space *mapping = inode->i_mapping;
+	fgf_t fgp = FGP_LOCK;
+	struct folio *folio;
+	int ret;
+
+	if (from >= to)
+		return 0;
+
+	if (nowait)
+		fgp |= FGP_NOWAIT;
+
+	folio = __filemap_get_folio(mapping, from >> PAGE_SHIFT, fgp, 0);
+	if (IS_ERR(folio))
+		return PTR_ERR(folio) == -EAGAIN ? -EAGAIN : 0;
+
+	ret = 0;
+	if (nowait && (folio_mapped(folio) || folio_test_writeback(folio))) {
+		ret = -EAGAIN;
+		goto out;
+	}
+
+	folio_wait_writeback(folio);
+
+	if (folio_mkclean(folio))
+		folio_mark_dirty(folio);
+
+	if (folio_test_uptodate(folio) &&
+	    (!exclusive || folio_test_dirty(folio))) {
+		uoff_t fpos = folio_pos(folio);
+
+		if (!exclusive)
+			from = umax(from, i_size_read(inode));
+		if (from < to && from < fpos + folio_size(folio)) {
+			size_t end = umin(to - fpos, folio_size(folio));
+			size_t offset = from - fpos;
+
+			folio_zero_segment(folio, offset, end);
+		}
+	}
+out:
+	folio_unlock(folio);
+	folio_put(folio);
+	return ret;
+}
+
+/* Clear stale pagecache before an extending buffered/DIO write. */
+int netfs_clear_stale_pre_isize(struct inode *inode, uoff_t from,
+				uoff_t to, bool nowait)
+{
+	return netfs_clear_stale_isize(inode, from, to, nowait, false);
+}
+
+/* Clear stale pagecache when extending a file under an exclusive resize. */
+void netfs_clear_stale_post_isize(struct inode *inode, uoff_t from,
+				  uoff_t to)
+{
+	netfs_clear_stale_isize(inode, from, to, false, true);
+}
+EXPORT_SYMBOL(netfs_clear_stale_post_isize);
diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c
index a94197ef0..c5bfaf2c6 100644
--- a/fs/netfs/read_collect.c
+++ b/fs/netfs/read_collect.c
@@ -33,6 +33,22 @@ static void netfs_clear_unread(struct netfs_io_subrequest *subreq)
 		__set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags);
 }
 
+static void netfs_clear_unread_dio(struct netfs_io_subrequest *subreq)
+{
+	uoff_t pos = subreq->start + subreq->transferred;
+	struct netfs_io_request *rreq = subreq->rreq;
+	size_t fill;
+
+	if (pos >= rreq->i_size)
+		return;
+
+	fill = min_t(uoff_t, rreq->i_size - pos,
+		     subreq->len - subreq->transferred);
+
+	netfs_reset_iter(subreq);
+	subreq->transferred += iov_iter_zero(fill, &subreq->io_iter);
+}
+
 /*
  * Cancel the copy-to-cache mark on a folio.
  */
@@ -311,6 +327,14 @@ reassess:
 			    test_bit(NETFS_SREQ_HIT_EOF, &front->flags))
 				netfs_read_unlock_folios(rreq, &notes);
 		} else {
+			if (!(notes & HIT_PENDING) &&
+			    front->error == 0 &&
+			    transferred < front->len &&
+			    test_bit(NETFS_SREQ_CLEAR_TAIL, &front->flags)) {
+				netfs_clear_unread_dio(front);
+				transferred = front->transferred;
+				trace_netfs_sreq(front, netfs_sreq_trace_clear);
+			}
 			stream->collected_to = front->start + transferred;
 			rreq->collected_to = stream->collected_to;
 		}
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 7ecd70efd..98b610b2a 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1412,6 +1412,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 	 * server could even support copy of range where source = target
 	 */
 	lock_two_nondirectories(target_inode, src_inode);
+	filemap_invalidate_lock(target_inode->i_mapping);
 
 	if (len == 0) {
 		loff_t src_size = i_size_read(src_inode);
@@ -1467,9 +1468,15 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 	i_size = target_inode->i_size;
 	spin_unlock(&target_inode->i_lock);
 
-	/* Discard all the folios that overlap the destination region. */
+	/*
+	 * Discard all the folios that overlap the destination region.  Start at
+	 * the old EOF when extending so the folio straddling it, which may hold
+	 * data written past EOF through an mmap, is dropped too.
+	 */
 	cifs_dbg(FYI, "about to discard pages %llx-%llx\n", fstart, fend);
-	truncate_inode_pages_range(&target_inode->i_data, fstart, fend);
+	truncate_inode_pages_range(&target_inode->i_data,
+				   min(fstart, i_size), fend);
+	netfs_wait_for_outstanding_io(target_inode);
 
 	fscache_invalidate(cifs_inode_cookie(target_inode), NULL, i_size, 0);
 
@@ -1508,6 +1515,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 	if (rc)
 		CIFS_I(target_inode)->time = 0;
 unlock:
+	filemap_invalidate_unlock(target_inode->i_mapping);
 	/* although unlocking in the reverse order from locking is not
 	   strictly necessary here it is a little cleaner to be consistent */
 	unlock_two_nondirectories(src_inode, target_inode);
@@ -1531,6 +1539,9 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	struct cifs_tcon *target_tcon;
 	ssize_t rc;
 
+	if (len == 0)
+		return 0;
+
 	cifs_dbg(FYI, "copychunk range\n");
 
 	if (!src_file->private_data || !dst_file->private_data) {
@@ -1560,6 +1571,7 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	 * server could even support copy of range where source = target
 	 */
 	lock_two_nondirectories(target_inode, src_inode);
+	filemap_invalidate_lock(target_inode->i_mapping);
 
 	cifs_dbg(FYI, "about to flush pages\n");
 
@@ -1581,10 +1593,28 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	/* Flush and invalidate all the folios in the destination region.  If
 	 * the copy was successful, then some of the flush is extra overhead,
 	 * but we need to allow for the copy failing in some way (eg. ENOSPC).
+	 *
+	 * Start at the old EOF when extending so the folio straddling it, which
+	 * may hold data written past EOF through an mmap, is dropped too.
 	 */
-	rc = filemap_invalidate_inode(target_inode, true, destoff, destoff + len - 1);
-	if (rc)
-		goto unlock;
+	if (target_inode->i_mapping->nrpages) {
+		loff_t fstart = min(destoff, i_size_read(target_inode));
+		loff_t fend = destoff + len - 1;
+
+		unmap_mapping_pages(target_inode->i_mapping,
+				    fstart >> PAGE_SHIFT,
+				    (fend >> PAGE_SHIFT) -
+				    (fstart >> PAGE_SHIFT) + 1,
+				    false);
+		rc = filemap_write_and_wait_range(target_inode->i_mapping,
+						  fstart, fend);
+		if (rc)
+			goto unlock;
+		invalidate_inode_pages2_range(target_inode->i_mapping,
+					      fstart >> PAGE_SHIFT,
+					      fend >> PAGE_SHIFT);
+	}
+	netfs_wait_for_outstanding_io(target_inode);
 
 	fscache_invalidate(cifs_inode_cookie(target_inode), NULL,
 			   i_size_read(target_inode), 0);
@@ -1616,6 +1646,7 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	CIFS_I(target_inode)->time = 0;
 
 unlock:
+	filemap_invalidate_unlock(target_inode->i_mapping);
 	/* although unlocking in the reverse order from locking is not
 	 * strictly necessary here it is a little cleaner to be consistent
 	 */
diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h
index 0c85daa83..e3d820c97 100644
--- a/fs/smb/client/cifsfs.h
+++ b/fs/smb/client/cifsfs.h
@@ -146,8 +146,9 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, struct file *src_file,
 				  unsigned int flags);
 
 long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg);
-void cifs_setsize(struct inode *inode, loff_t offset);
-void cifs_resize_file_locked(struct inode *inode, loff_t offset);
+void cifs_setsize(struct inode *inode, loff_t old_size, loff_t offset);
+void cifs_resize_file_locked(struct inode *inode, loff_t old_size,
+			     loff_t offset);
 
 struct fs_context;
 struct smb3_fs_context;
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 79e4e84f8..5c5b76a9e 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1450,11 +1450,11 @@ struct cifsFileInfo {
 	struct dentry *dentry;
 	struct tcon_link *tlink;
 	unsigned int f_flags;
-	bool invalidHandle:1;	/* file closed via session abend */
-	bool swapfile:1;
-	bool oplock_break_cancelled:1;
-	bool status_file_deleted:1; /* file has been deleted */
-	bool offload:1; /* offload final part of _put to a wq */
+	bool invalidHandle;	/* file closed via session abend */
+	bool swapfile;
+	bool oplock_break_cancelled;
+	bool status_file_deleted; /* file has been deleted */
+	bool offload; /* offload final part of _put to a wq */
 	__u16 oplock_epoch; /* epoch from the lease break */
 	__u32 oplock_level; /* oplock/lease level from the lease break */
 	int count;
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 0d428517f..11355d6bf 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -1012,11 +1012,14 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry)
 	}
 	mapping_set_error(inode->i_mapping, rc);
 
+	netfs_wait_for_outstanding_io(inode);
+
 	cfile = find_writable_file(cinode, FIND_FSUID_ONLY);
 	rc = cifs_file_flush(xid, inode, cfile);
 	if (!rc) {
 		if (cfile) {
 			struct netfs_inode *ictx = netfs_inode(inode);
+			loff_t old_size = i_size_read(inode);
 
 			tcon = tlink_tcon(cfile->tlink);
 			server = tcon->ses->server;
@@ -1025,7 +1028,7 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry)
 							cfile, 0, false);
 			if (!rc) {
 				netfs_resize_file(&cinode->netfs, 0, true);
-				cifs_setsize(inode, 0);
+				cifs_setsize(inode, old_size, 0);
 				cifs_invalidate_cache(inode, 0);
 			}
 			netfs_wb_end(ictx);
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 1fe0ef0a9..f29555f3c 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -88,6 +88,8 @@ static void cifs_set_ops(struct inode *inode)
 		else
 			inode->i_data.a_ops = &cifs_addr_ops;
 		mapping_set_large_folios(inode->i_mapping);
+		if (tcon->ses->server->sign)
+			mapping_set_stable_writes(inode->i_mapping);
 		break;
 	case S_IFDIR:
 		if (IS_AUTOMOUNT(inode)) {
@@ -3053,15 +3055,12 @@ int cifs_fiemap(struct inode *inode, struct fiemap_extent_info *fei, u64 start,
 	return -EOPNOTSUPP;
 }
 
-void cifs_setsize(struct inode *inode, loff_t offset)
+void cifs_setsize(struct inode *inode, loff_t old_size, loff_t offset)
 {
-	loff_t old_size;
 	u64 blocks = CIFS_INO_BLOCKS(offset);
 
 	spin_lock(&inode->i_lock);
-	old_size = i_size_read(inode);
 	i_size_write(inode, offset);
-
 	/*
 	 * Extending EOF does not allocate the intervening range. Only clamp
 	 * i_blocks on shrink; allocation growth comes from writes or from the
@@ -3071,20 +3070,28 @@ void cifs_setsize(struct inode *inode, loff_t offset)
 		inode->i_blocks = blocks;
 	spin_unlock(&inode->i_lock);
 	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
+
+	/*
+	 * Zero the tail of the folio straddling the old EOF so data dirtied
+	 * past EOF through an mmap isn't exposed.  truncate_pagecache() then
+	 * drops any pagecache beyond the new EOF, as in truncate_setsize().
+	 */
 	if (offset > old_size)
-		pagecache_isize_extended(inode, old_size, offset);
+		netfs_clear_stale_post_isize(inode, old_size, offset);
+
 	truncate_pagecache(inode, offset);
 	netfs_wait_for_outstanding_io(inode);
 }
 
-void cifs_resize_file_locked(struct inode *inode, loff_t offset)
+void cifs_resize_file_locked(struct inode *inode, loff_t old_size,
+			     loff_t offset)
 {
 	struct fscache_cookie *cookie = cifs_inode_cookie(inode);
 
 	lockdep_assert_held_write(&inode->i_rwsem);
 
 	netfs_resize_file(netfs_inode(inode), offset, true);
-	cifs_setsize(inode, offset);
+	cifs_setsize(inode, old_size, offset);
 
 	if (!cookie)
 		return;
@@ -3101,6 +3108,7 @@ int cifs_file_set_size(const unsigned int xid, struct dentry *dentry,
 	struct inode *inode = d_inode(dentry);
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
+	loff_t old_size = i_size_read(inode);
 	struct tcon_link *tlink = NULL;
 	struct cifs_tcon *tcon = NULL;
 	struct TCP_Server_Info *server;
@@ -3159,7 +3167,7 @@ int cifs_file_set_size(const unsigned int xid, struct dentry *dentry,
 
 set_size_out:
 	if (rc == 0)
-		cifs_resize_file_locked(inode, size);
+		cifs_resize_file_locked(inode, old_size, size);
 
 	return rc;
 }
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index aa142420d..583ab4c4d 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -2287,6 +2287,7 @@ smb2_duplicate_extents(const unsigned int xid,
 	struct duplicate_extents_to_file dup_ext_buf;
 	struct timespec64 ts;
 	struct cifs_tcon *tcon = tlink_tcon(trgtfile->tlink);
+	loff_t old_size;
 	u64 asize;
 
 	/* server fileays advertise duplicate extent support with this flag */
@@ -2305,11 +2306,12 @@ smb2_duplicate_extents(const unsigned int xid,
 			       trgtfile->fid.volatile_fid, tcon->tid,
 			       tcon->ses->Suid, src_off, dest_off, len);
 	inode = d_inode(trgtfile->dentry);
-	if (i_size_read(inode) < dest_off + len) {
+	old_size = i_size_read(inode);
+	if (old_size < dest_off + len) {
 		rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false);
 		if (rc)
 			goto duplicate_extents_out;
-		cifs_resize_file_locked(inode, dest_off + len);
+		cifs_resize_file_locked(inode, old_size, dest_off + len);
 	}
 	rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
 			trgtfile->fid.volatile_fid,
@@ -3520,6 +3522,21 @@ static long smb3_zero_data(struct file *file, struct cifs_tcon *tcon,
 			  0, NULL, NULL);
 }
 
+static long query_server_eof(const unsigned int xid,
+			     struct cifs_tcon *tcon,
+			     struct cifsFileInfo *cfile,
+			     unsigned long long *eof)
+{
+	struct smb2_file_all_info file_inf = {};
+	long rc;
+
+	rc = SMB2_query_info(xid, tcon, cfile->fid.persistent_fid,
+			     cfile->fid.volatile_fid, &file_inf);
+	if (!rc)
+		*eof = le64_to_cpu(file_inf.EndOfFile);
+	return rc;
+}
+
 static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 			    unsigned long long offset, unsigned long long len,
 			    bool keep_size)
@@ -3547,25 +3564,32 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	filemap_invalidate_lock(inode->i_mapping);
 
 	netfs_read_sizes(inode, &i_size, &remote_i_size, &zero_point);
-	if (offset + len >= remote_i_size && offset < i_size) {
-		unsigned long long top = umin(offset + len, i_size);
 
-		rc = filemap_write_and_wait_range(inode->i_mapping, offset, top - 1);
-		if (rc < 0)
-			goto zero_range_exit;
-	}
+	rc = filemap_write_and_wait_range(inode->i_mapping, offset,
+					  offset + len - 1);
+	if (rc < 0)
+		goto zero_range_exit;
 
 	/*
 	 * We zero the range through ioctl, so we need remove the page caches
 	 * first, otherwise the data may be inconsistent with the server.
+	 *
+	 * Start at the old EOF when extending so the folio straddling it, which
+	 * may hold data written past EOF through an mmap, is dropped too.
 	 */
-	truncate_pagecache_range(inode, offset, offset + len - 1);
+	truncate_pagecache_range(inode, min(offset, i_size), offset + len - 1);
 	netfs_wait_for_outstanding_io(inode);
 
-	/* if file not oplocked can't be sure whether asking to extend size */
-	rc = -EOPNOTSUPP;
-	if (keep_size == false && !CIFS_CACHE_READ(cifsi))
-		goto zero_range_exit;
+	if (!keep_size && !CIFS_CACHE_READ(cifsi)) {
+		rc = query_server_eof(xid, tcon, cfile, &remote_i_size);
+		if (rc)
+			goto zero_range_exit;
+		i_size = max(i_size, remote_i_size);
+		if (i_size < new_size) {
+			rc = -EOPNOTSUPP;
+			goto zero_range_exit;
+		}
+	}
 
 	fscache_invalidate(cifs_inode_cookie(inode), NULL,
 			   i_size_read(inode), 0);
@@ -3577,7 +3601,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	/*
 	 * do we also need to change the size of the file?
 	 */
-	if (keep_size == false && (unsigned long long)i_size_read(inode) < new_size) {
+	if (!keep_size && umax(i_size, i_size_read(inode)) < new_size) {
 		rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
 				  cfile->fid.volatile_fid, cfile->pid, new_size);
 		if (rc >= 0) {
@@ -3723,7 +3747,8 @@ static int smb3_simple_fallocate_write_range(unsigned int xid,
 static int smb3_simple_fallocate_range(unsigned int xid,
 				       struct cifs_tcon *tcon,
 				       struct cifsFileInfo *cfile,
-				       loff_t off, loff_t len)
+				       loff_t off, loff_t len,
+				       loff_t old_eof)
 {
 	struct file_allocated_range_buffer in_data, *out_data = NULL, *tmp_data;
 	struct inode *inode = d_inode(cfile->dentry);
@@ -3739,12 +3764,30 @@ static int smb3_simple_fallocate_range(unsigned int xid,
 		goto out;
 	}
 
-	if (off >= i_size_read(inode)) {
+	if (off >= old_eof) {
 		rc = smb3_simple_fallocate_write_range(xid, tcon, cfile,
 						       off, len, buf);
 		goto out;
 	}
 
+	filemap_invalidate_lock(inode->i_mapping);
+
+	/*
+	 * Flush and commit the data to the server, otherwise
+	 * FSCTL_QUERY_ALLOCATED_RANGES might report recently written data as
+	 * unallocated holes on Windows Servers, and the loop below would
+	 * then zero-fill them and corrupt the file.
+	 */
+	rc = filemap_write_and_wait_range(inode->i_mapping, off,
+					  off + len - 1);
+	if (rc)
+		goto out_unlock;
+	netfs_wait_for_outstanding_io(inode);
+	rc = SMB2_flush(xid, tcon, cfile->fid.persistent_fid,
+			cfile->fid.volatile_fid);
+	if (rc)
+		goto out_unlock;
+
 	in_data.file_offset = cpu_to_le64(off);
 	in_data.length = cpu_to_le64(len);
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
@@ -3754,7 +3797,7 @@ static int smb3_simple_fallocate_range(unsigned int xid,
 			1024 * sizeof(struct file_allocated_range_buffer),
 			(char **)&out_data, &out_data_len);
 	if (rc)
-		goto out;
+		goto out_unlock;
 
 	tmp_data = out_data;
 	while (len) {
@@ -3764,12 +3807,12 @@ static int smb3_simple_fallocate_range(unsigned int xid,
 		if (out_data_len == 0) {
 			rc = smb3_simple_fallocate_write_range(xid, tcon,
 					       cfile, off, len, buf);
-			goto out;
+			goto out_unlock;
 		}
 
 		if (out_data_len < sizeof(struct file_allocated_range_buffer)) {
 			rc = -EINVAL;
-			goto out;
+			goto out_unlock;
 		}
 
 		range_start = le64_to_cpu(tmp_data->file_offset);
@@ -3777,7 +3820,7 @@ static int smb3_simple_fallocate_range(unsigned int xid,
 		if (check_add_overflow(range_start, range_len, &range_end) ||
 		    range_end > S64_MAX) {
 			rc = -EINVAL;
-			goto out;
+			goto out_unlock;
 		}
 
 		if (off < range_start) {
@@ -3792,11 +3835,11 @@ static int smb3_simple_fallocate_range(unsigned int xid,
 			rc = smb3_simple_fallocate_write_range(xid, tcon,
 					       cfile, off, l, buf);
 			if (rc)
-				goto out;
+				goto out_unlock;
 			off = off + l;
 			len = len - l;
 			if (len == 0)
-				goto out;
+				goto out_unlock;
 		}
 		/*
 		 * We are at a section of allocated data, just skip forward
@@ -3815,6 +3858,8 @@ static int smb3_simple_fallocate_range(unsigned int xid,
 		out_data_len -= sizeof(struct file_allocated_range_buffer);
 	}
 
+ out_unlock:
+	filemap_invalidate_unlock(inode->i_mapping);
  out:
 	kfree(out_data);
 	kvfree(buf);
@@ -3830,7 +3875,7 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 	struct cifsFileInfo *cfile = file->private_data;
 	long rc = -EOPNOTSUPP;
 	unsigned int xid;
-	loff_t old_eof, new_eof;
+	loff_t old_eof, new_eof, local_eof;
 	struct smb2_file_all_info file_inf;
 	u64 asize;
 	int qrc;
@@ -3839,18 +3884,37 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 
 	inode = d_inode(cfile->dentry);
 	cifsi = CIFS_I(inode);
-	old_eof = i_size_read(inode);
+	old_eof = local_eof = i_size_read(inode);
 
 	trace_smb3_falloc_enter(xid, cfile->fid.persistent_fid, tcon->tid,
 				tcon->ses->Suid, off, len);
-	/* if file not oplocked can't be sure whether asking to extend size */
-	if (!CIFS_CACHE_READ(cifsi))
-		if (!keep_size) {
+
+	if (!keep_size && !CIFS_CACHE_READ(cifsi)) {
+		unsigned long long server_eof;
+
+		rc = filemap_write_and_wait(inode->i_mapping);
+		if (rc) {
 			trace_smb3_falloc_err(xid, cfile->fid.persistent_fid,
 				tcon->tid, tcon->ses->Suid, off, len, rc);
 			free_xid(xid);
 			return rc;
 		}
+		netfs_wait_for_outstanding_io(inode);
+
+		rc = query_server_eof(xid, tcon, cfile, &server_eof);
+		if (rc) {
+			trace_smb3_falloc_err(xid, cfile->fid.persistent_fid,
+				tcon->tid, tcon->ses->Suid, off, len, rc);
+			free_xid(xid);
+			return rc;
+		}
+		/*
+		 * Only use the larger EOF to decide whether we're extending.
+		 * The pagecache zeroing below must still key off the local
+		 * i_size, so keep local_eof for that.
+		 */
+		old_eof = max_t(loff_t, old_eof, server_eof);
+	}
 
 	/*
 	 * Extending the file
@@ -3874,7 +3938,7 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 			}
 
 			rc = smb3_simple_fallocate_range(xid, tcon, cfile,
-							 off, len);
+							 off, len, old_eof);
 			if (rc) {
 				spin_lock(&inode->i_lock);
 				cifsi->time = 0;
@@ -3883,7 +3947,7 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 			}
 
 			new_eof = off + len;
-			cifs_resize_file_locked(inode, new_eof);
+			cifs_resize_file_locked(inode, local_eof, new_eof);
 
 			qrc = SMB2_query_info(xid, tcon,
 					      cfile->fid.persistent_fid,
@@ -3931,7 +3995,7 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 		if (rc)
 			goto out;
 
-		cifs_resize_file_locked(inode, new_eof);
+		cifs_resize_file_locked(inode, local_eof, new_eof);
 
 		qrc = SMB2_query_info(xid, tcon,
 				      cfile->fid.persistent_fid,
@@ -3976,7 +4040,7 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 		}
 	}
 
-	if ((keep_size == true) || (i_size_read(inode) >= off + len)) {
+	if (keep_size || old_eof >= off + len) {
 		/*
 		 * At this point, we are trying to fallocate an internal
 		 * regions of a sparse file. Since smb2 does not have a
@@ -3993,7 +4057,7 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 		 */
 		if (len <= 1024 * 1024) {
 			rc = smb3_simple_fallocate_range(xid, tcon, cfile,
-							 off, len);
+							 off, len, old_eof);
 			goto out;
 		}
 
@@ -4005,7 +4069,7 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 		 * ie potentially making a few extra pages at the beginning
 		 * or end of the file non-sparse via set_sparse is harmless.
 		 */
-		if ((off > 8192) || (off + len + 8192 < i_size_read(inode))) {
+		if (off > 8192 || off + len + 8192 < old_eof) {
 			rc = -EOPNOTSUPP;
 			goto out;
 		}
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 3d7ead36d..cfe3c4b4a 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -4796,14 +4796,20 @@ do_retry:
 				     rdata->got_bytes);
 
 	if (rdata->result == -ENODATA) {
-		__set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags);
 		rdata->result = 0;
+		if (rdata->subreq.start + rdata->subreq.transferred >= i_size_read(inode))
+			__set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags);
+		else
+			__set_bit(NETFS_SREQ_CLEAR_TAIL, &rdata->subreq.flags);
 	} else {
 		size_t trans = rdata->subreq.transferred + rdata->got_bytes;
 		if (trans < rdata->subreq.len &&
 		    rdata->subreq.start + trans >= netfs_read_remote_i_size(inode)) {
-			__set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags);
 			rdata->result = 0;
+			if (rdata->subreq.start + trans >= i_size_read(inode))
+				__set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags);
+			else
+				__set_bit(NETFS_SREQ_CLEAR_TAIL, &rdata->subreq.flags);
 		}
 		if (rdata->got_bytes)
 			__set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index b4dd32863..fe6275e55 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -397,6 +397,8 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from);
 ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter,
 					   struct netfs_group *netfs_group);
 ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from);
+void netfs_clear_stale_post_isize(struct inode *inode, uoff_t from,
+				  uoff_t to);
 
 /* Single, monolithic object read/write API. */
 void netfs_single_mark_inode_dirty(struct inode *inode);