lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20260106075008.1610195-9-hch@lst.de>
Date: Tue,  6 Jan 2026 08:50:02 +0100
From: Christoph Hellwig <hch@....de>
To: Christian Brauner <brauner@...nel.org>
Cc: Al Viro <viro@...iv.linux.org.uk>,
	David Sterba <dsterba@...e.com>,
	Jan Kara <jack@...e.cz>,
	Mike Marshall <hubcap@...ibond.com>,
	Martin Brandenburg <martin@...ibond.com>,
	Carlos Maiolino <cem@...nel.org>,
	Stefan Roesch <shr@...com>,
	Jeff Layton <jlayton@...nel.org>,
	OGAWA Hirofumi <hirofumi@...l.parknet.co.jp>,
	Trond Myklebust <trondmy@...nel.org>,
	Anna Schumaker <anna@...nel.org>,
	linux-kernel@...r.kernel.org,
	linux-btrfs@...r.kernel.org,
	linux-fsdevel@...r.kernel.org,
	gfs2@...ts.linux.dev,
	io-uring@...r.kernel.org,
	devel@...ts.orangefs.org,
	linux-unionfs@...r.kernel.org,
	linux-mtd@...ts.infradead.org,
	linux-xfs@...r.kernel.org,
	linux-nfs@...r.kernel.org
Subject: [PATCH 08/11] fs: add support for non-blocking timestamp updates

Currently file_update_time_flags unconditionally returns -EAGAIN if any
timestamp needs to be updated and IOCB_NOWAIT is passed.  This makes
non-blocking direct writes impossible on file systems with granular
enough timestamps.

Pass IOCB_NOWAIT to ->update_time and return -EAGAIN if it could block.

Signed-off-by: Christoph Hellwig <hch@....de>
---
 fs/btrfs/inode.c     |  2 ++
 fs/gfs2/inode.c      |  3 +++
 fs/inode.c           | 45 +++++++++++++++++++++++++++++++++-----------
 fs/orangefs/inode.c  |  3 +++
 fs/overlayfs/inode.c |  2 ++
 fs/ubifs/file.c      |  3 +++
 fs/xfs/xfs_iops.c    |  3 +++
 7 files changed, 50 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 23fc38de9be5..241727459c0a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6362,6 +6362,8 @@ static int btrfs_update_time(struct inode *inode, enum fs_update_time type,
 
 	if (btrfs_root_readonly(root))
 		return -EROFS;
+	if (flags & IOCB_NOWAIT)
+		return -EAGAIN;
 
 	dirty = inode_update_time(inode, type, flags);
 	if (dirty <= 0)
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 4ef39ff6889d..c02ebf0ca625 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -2250,6 +2250,9 @@ static int gfs2_update_time(struct inode *inode, enum fs_update_time type,
 	struct gfs2_holder *gh;
 	int error;
 
+	if (flags & IOCB_NOWAIT)
+		return -EAGAIN;
+
 	gh = gfs2_glock_is_locked_by_me(gl);
 	if (gh && gl->gl_state != LM_ST_EXCLUSIVE) {
 		gfs2_glock_dq(gh);
diff --git a/fs/inode.c b/fs/inode.c
index c08682524a8d..01e4f6b9b46e 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -2090,7 +2090,7 @@ static int inode_update_atime(struct inode *inode)
 	return inode_time_dirty_flag(inode);
 }
 
-static int inode_update_cmtime(struct inode *inode)
+static int inode_update_cmtime(struct inode *inode, unsigned int flags)
 {
 	struct timespec64 now = inode_set_ctime_current(inode);
 	struct timespec64 ctime = inode_get_ctime(inode);
@@ -2101,12 +2101,27 @@ static int inode_update_cmtime(struct inode *inode)
 	mtime_changed = !timespec64_equal(&now, &mtime);
 	if (mtime_changed || !timespec64_equal(&now, &ctime))
 		dirty = inode_time_dirty_flag(inode);
-	if (mtime_changed)
-		inode_set_mtime_to_ts(inode, now);
 
-	if (IS_I_VERSION(inode) && inode_maybe_inc_iversion(inode, !!dirty))
-		dirty |= I_DIRTY_SYNC;
+	/*
+	 * Pure timestamp updates can be recorded in the inode without blocking
+	 * by not dirtying the inode.  But when the file system requires
+	 * i_version updates, the update of i_version can still block.
+	 * Error out if we'd actually have to update i_version or don't support
+	 * lazytime.
+	 */
+	if (IS_I_VERSION(inode)) {
+		if (flags & IOCB_NOWAIT) {
+			if (!(inode->i_sb->s_flags & SB_LAZYTIME) ||
+			    inode_iversion_need_inc(inode))
+				return -EAGAIN;
+		} else {
+			if (inode_maybe_inc_iversion(inode, !!dirty))
+				dirty |= I_DIRTY_SYNC;
+		}
+	}
 
+	if (mtime_changed)
+		inode_set_mtime_to_ts(inode, now);
 	return dirty;
 }
 
@@ -2131,7 +2146,7 @@ int inode_update_time(struct inode *inode, enum fs_update_time type,
 	case FS_UPD_ATIME:
 		return inode_update_atime(inode);
 	case FS_UPD_CMTIME:
-		return inode_update_cmtime(inode);
+		return inode_update_cmtime(inode, flags);
 	default:
 		WARN_ON_ONCE(1);
 		return -EIO;
@@ -2152,6 +2167,16 @@ int generic_update_time(struct inode *inode, enum fs_update_time type,
 {
 	int dirty;
 
+	/*
+	 * ->dirty_inode is what could make generic timestamp updates block.
+	 * Don't support non-blocking timestamp updates here if it is set.
+	 * File systems that implement ->dirty_inode but want to support
+	 * non-blocking timestamp updates should call inode_update_time
+	 * directly.
+	 */
+	if ((flags & IOCB_NOWAIT) && inode->i_sb->s_op->dirty_inode)
+		return -EAGAIN;
+
 	dirty = inode_update_time(inode, type, flags);
 	if (dirty <= 0)
 		return dirty;
@@ -2380,15 +2405,13 @@ static int file_update_time_flags(struct file *file, unsigned int flags)
 	if (!need_update)
 		return 0;
 
-	if (flags & IOCB_NOWAIT)
-		return -EAGAIN;
-
+	flags &= IOCB_NOWAIT;
 	if (mnt_get_write_access_file(file))
 		return 0;
 	if (inode->i_op->update_time)
-		ret = inode->i_op->update_time(inode, FS_UPD_CMTIME, 0);
+		ret = inode->i_op->update_time(inode, FS_UPD_CMTIME, flags);
 	else
-		ret = generic_update_time(inode, FS_UPD_CMTIME, 0);
+		ret = generic_update_time(inode, FS_UPD_CMTIME, flags);
 	mnt_put_write_access_file(file);
 	return ret;
 }
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index eab16afb5b8a..f420f48fc069 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -878,6 +878,9 @@ int orangefs_update_time(struct inode *inode, enum fs_update_time type,
 	struct iattr iattr = { };
 	int dirty;
 
+	if (flags & IOCB_NOWAIT)
+		return -EAGAIN;
+
 	switch (type) {
 	case FS_UPD_ATIME:
 		iattr.ia_valid = ATTR_ATIME;
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index c0ce3519e4af..00c69707bda9 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -566,6 +566,8 @@ int ovl_update_time(struct inode *inode, enum fs_update_time type,
 		};
 
 		if (upperpath.dentry) {
+			if (flags & IOCB_NOWAIT)
+				return -EAGAIN;
 			touch_atime(&upperpath);
 			inode_set_atime_to_ts(inode,
 					      inode_get_atime(d_inode(upperpath.dentry)));
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 0cc44ad142de..3dc3ca1cd803 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1377,6 +1377,9 @@ int ubifs_update_time(struct inode *inode, enum fs_update_time type,
 	if (!IS_ENABLED(CONFIG_UBIFS_ATIME_SUPPORT))
 		return generic_update_time(inode, type, flags);
 
+	if (flags & IOCB_NOWAIT)
+		return -EAGAIN;
+
 	err = ubifs_budget_space(c, &req);
 	if (err)
 		return err;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index d9eae1af14a8..aef5b05c1b76 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -1195,6 +1195,9 @@ xfs_vn_update_time(
 
 	trace_xfs_update_time(ip);
 
+	if (flags & IOCB_NOWAIT)
+		return -EAGAIN;
+
 	if (inode->i_sb->s_flags & SB_LAZYTIME) {
 		if (type == FS_UPD_ATIME ||
 		    !inode_maybe_inc_iversion(inode, false))
-- 
2.47.3


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ