CEPH-Devel archive mirror
 help / color / mirror / Atom feed
From: Viacheslav Dubeyko <slava@dubeyko.com>
To: ceph-devel@vger.kernel.org
Cc: idryomov@gmail.com, linux-fsdevel@vger.kernel.org,
	pdonnell@redhat.com, amarkuze@redhat.com, Slava.Dubeyko@ibm.com,
	slava@dubeyko.com
Subject: [PATCH] ceph: fix potentail race condition of operations with CEPH_I_ODIRECT flag
Date: Mon, 14 Jul 2025 14:47:19 -0700	[thread overview]
Message-ID: <20250714214719.589469-1-slava@dubeyko.com> (raw)

From: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>

The Coverity Scan service has detected potential
race conditions in ceph_block_o_direct(), ceph_start_io_read(),
ceph_block_buffered(), and ceph_start_io_direct() [1 - 4].

The CID 1590942, 1590665, 1589664, 1590377 contain explanation:
"The value of the shared data will be determined by
the interleaving of thread execution. Thread shared data is accessed
without holding an appropriate lock, possibly causing
a race condition (CWE-366)".

This patch reworks the pattern of accessing/modification of
CEPH_I_ODIRECT flag by means of adding smp_mb__before_atomic()
before reading the status of CEPH_I_ODIRECT flag and
smp_mb__after_atomic() after clearing set/clear this flag.
Also, it was reworked the pattern of using of ci->i_ceph_lock
in ceph_block_o_direct(), ceph_start_io_read(),
ceph_block_buffered(), and ceph_start_io_direct() methods.

[1] https://scan5.scan.coverity.com/#/project-view/64304/10063?selectedIssue=1590942
[2] https://scan5.scan.coverity.com/#/project-view/64304/10063?selectedIssue=1590665
[3] https://scan5.scan.coverity.com/#/project-view/64304/10063?selectedIssue=1589664
[4] https://scan5.scan.coverity.com/#/project-view/64304/10063?selectedIssue=1590377

Signed-off-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
cc: Alex Markuze <amarkuze@redhat.com>
cc: Ilya Dryomov <idryomov@gmail.com>
cc: Ceph Development <ceph-devel@vger.kernel.org>
---
 fs/ceph/io.c    | 53 +++++++++++++++++++++++++++++++++++++++----------
 fs/ceph/super.h |  3 ++-
 2 files changed, 44 insertions(+), 12 deletions(-)

diff --git a/fs/ceph/io.c b/fs/ceph/io.c
index c456509b31c3..91b73052d708 100644
--- a/fs/ceph/io.c
+++ b/fs/ceph/io.c
@@ -21,14 +21,23 @@
 /* Call with exclusively locked inode->i_rwsem */
 static void ceph_block_o_direct(struct ceph_inode_info *ci, struct inode *inode)
 {
+	bool is_odirect;
+
 	lockdep_assert_held_write(&inode->i_rwsem);
 
-	if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT) {
-		spin_lock(&ci->i_ceph_lock);
-		ci->i_ceph_flags &= ~CEPH_I_ODIRECT;
-		spin_unlock(&ci->i_ceph_lock);
-		inode_dio_wait(inode);
+	spin_lock(&ci->i_ceph_lock);
+	/* ensure that bit state is consistent */
+	smp_mb__before_atomic();
+	is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+	if (is_odirect) {
+		clear_bit(CEPH_I_ODIRECT_BIT, &ci->i_ceph_flags);
+		/* ensure modified bit is visible */
+		smp_mb__after_atomic();
 	}
+	spin_unlock(&ci->i_ceph_lock);
+
+	if (is_odirect)
+		inode_dio_wait(inode);
 }
 
 /**
@@ -51,10 +60,16 @@ void
 ceph_start_io_read(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	bool is_odirect;
 
 	/* Be an optimist! */
 	down_read(&inode->i_rwsem);
-	if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT))
+	spin_lock(&ci->i_ceph_lock);
+	/* ensure that bit state is consistent */
+	smp_mb__before_atomic();
+	is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+	spin_unlock(&ci->i_ceph_lock);
+	if (!is_odirect)
 		return;
 	up_read(&inode->i_rwsem);
 	/* Slow path.... */
@@ -106,12 +121,22 @@ ceph_end_io_write(struct inode *inode)
 /* Call with exclusively locked inode->i_rwsem */
 static void ceph_block_buffered(struct ceph_inode_info *ci, struct inode *inode)
 {
+	bool is_odirect;
+
 	lockdep_assert_held_write(&inode->i_rwsem);
 
-	if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT)) {
-		spin_lock(&ci->i_ceph_lock);
-		ci->i_ceph_flags |= CEPH_I_ODIRECT;
-		spin_unlock(&ci->i_ceph_lock);
+	spin_lock(&ci->i_ceph_lock);
+	/* ensure that bit state is consistent */
+	smp_mb__before_atomic();
+	is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+	if (!is_odirect) {
+		set_bit(CEPH_I_ODIRECT_BIT, &ci->i_ceph_flags);
+		/* ensure modified bit is visible */
+		smp_mb__after_atomic();
+	}
+	spin_unlock(&ci->i_ceph_lock);
+
+	if (!is_odirect) {
 		/* FIXME: unmap_mapping_range? */
 		filemap_write_and_wait(inode->i_mapping);
 	}
@@ -137,10 +162,16 @@ void
 ceph_start_io_direct(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	bool is_odirect;
 
 	/* Be an optimist! */
 	down_read(&inode->i_rwsem);
-	if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT)
+	spin_lock(&ci->i_ceph_lock);
+	/* ensure that bit state is consistent */
+	smp_mb__before_atomic();
+	is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+	spin_unlock(&ci->i_ceph_lock);
+	if (is_odirect)
 		return;
 	up_read(&inode->i_rwsem);
 	/* Slow path.... */
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index bb0db0cc8003..969212637c5b 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -638,7 +638,8 @@ static inline struct inode *ceph_find_inode(struct super_block *sb,
 #define CEPH_I_FLUSH_SNAPS	(1 << 8)  /* need flush snapss */
 #define CEPH_I_ERROR_WRITE	(1 << 9) /* have seen write errors */
 #define CEPH_I_ERROR_FILELOCK	(1 << 10) /* have seen file lock errors */
-#define CEPH_I_ODIRECT		(1 << 11) /* inode in direct I/O mode */
+#define CEPH_I_ODIRECT_BIT	(11) /* inode in direct I/O mode */
+#define CEPH_I_ODIRECT		(1 << CEPH_I_ODIRECT_BIT)
 #define CEPH_ASYNC_CREATE_BIT	(12)	  /* async create in flight for this */
 #define CEPH_I_ASYNC_CREATE	(1 << CEPH_ASYNC_CREATE_BIT)
 #define CEPH_I_SHUTDOWN		(1 << 13) /* inode is no longer usable */
-- 
2.49.0


                 reply	other threads:[~2025-07-14 21:47 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250714214719.589469-1-slava@dubeyko.com \
    --to=slava@dubeyko.com \
    --cc=Slava.Dubeyko@ibm.com \
    --cc=amarkuze@redhat.com \
    --cc=ceph-devel@vger.kernel.org \
    --cc=idryomov@gmail.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=pdonnell@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).