Skip to contentSkip to conversation

ceph: avoid fs reclaim while using `current->journal_info`

PATCH In review Max Kellermann 3 participants 3 messages Jul 22 – Jul 23

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 ceph: avoid fs reclaim while using `current->journal_info`

handle_reply() stores a ceph_mds_request pointer in current->journal_info while filling the inode and dentry cache from an MDS reply.

An allocation in this section can enter direct reclaim and prune dentries from another filesystem. If this dirties an ext4 inode, ext4 starts a JBD2 transaction. JBD2 interprets the Ceph request in current->journal_info as a journal handle and dereferences the request's r_tid as h_transaction, causing a kernel crash, e.g.:

 Unable to handle kernel paging request at virtual address 00000000077b4818
 [...]
 Internal error: Oops: 0000000096000004 [#1]  SMP
 Modules linked in:
 CPU: 6 UID: 0 PID: 2699135 Comm: kworker/6:3 Tainted: G        W           6.18.38-i3 #1113 NONE
 [...]
 Workqueue: ceph-msgr ceph_con_workfn
 pstate: 80400009 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : jbd2__journal_start+0x2c/0x208
 lr : __ext4_journal_start_sb+0x100/0x178
 [...]
 Call trace:
  jbd2__journal_start+0x2c/0x208 (P)
  __ext4_journal_start_sb+0x100/0x178
  ext4_dirty_inode+0x3c/0x90
  __mark_inode_dirty+0x58/0x400
  iput.part.0+0x2b0/0x370
  iput+0x18/0x30
  dentry_unlink_inode+0xc0/0x158
  __dentry_kill+0x80/0x250
  shrink_dentry_list+0x90/0x130
  prune_dcache_sb+0x60/0x98
  super_cache_scan+0xe8/0x190
  do_shrink_slab+0x174/0x388
  shrink_slab+0xd8/0x4c0
  shrink_node+0x31c/0x908
  do_try_to_free_pages+0xd0/0x508
  try_to_free_pages+0x11c/0x238
  __alloc_frozen_pages_noprof+0x4d0/0xdd0
  __folio_alloc_noprof+0x18/0x70
  __filemap_get_folio+0x248/0x440
  ceph_readdir_prepopulate+0x570/0x9e8
  mds_dispatch+0x1424/0x1ba0
  ceph_con_process_message+0x74/0xa0
  ceph_con_v1_try_read+0x3a0/0x1510
  ceph_con_workfn+0x260/0x460

Enter a scoped NOFS allocation context and leave it after clearing journal_info. This prevents filesystem reclaim from recursing into another filesystem while the field contains Ceph-private data.

Fixes 315f24088048 ("ceph: fix security xattr deadlock")
---
 fs/ceph/mds_client.c | 11 +++++++++++
 1 file changed, 11 insertions(+)
fs/ceph/mds_client.c +11 -0
index 853bf698b356..3c692ad02c85 100644
@@ -6,6 +6,7 @@
 #include <linux/slab.h>
 #include <linux/gfp.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/delay.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -4015,6 +4016,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	struct ceph_mds_reply_head *head = msg->front.iov_base;
 	struct ceph_mds_reply_info_parsed *rinfo;  /* parsed reply info */
 	struct ceph_snap_realm *realm;
+	unsigned int nofs_flags;
 	u64 tid;
 	int err, result;
 	int mds = session->s_mds;
@@ -4158,6 +4160,14 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 
 	/* insert trace into our cache */
 	mutex_lock(&req->r_fill_mutex);
+
+	/* disable fs reclaim while we are using current->journal_info
+	 * for our own purposes, or else shrinkers of other
+	 * filesystems might dereference this pointer as a different
+	 * type
+	 */
+	nofs_flags = memalloc_nofs_save();
+
 	current->journal_info = req;
 	err = ceph_fill_trace(mdsc->fsc->sb, req);
 	if (err == 0) {
@@ -4166,6 +4176,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 			err = ceph_readdir_prepopulate(req, req->r_session);
 	}
 	current->journal_info = NULL;
+	memalloc_nofs_restore(nofs_flags);
 	mutex_unlock(&req->r_fill_mutex);
 
 	up_read(&mdsc->snap_rwsem);
Signature · 1 line
2.47.3
maintainer Reviewed-by on v1 1/1
#1 lore raw
Quoted 107 lines · Max Kellermann

handle_reply() stores a ceph_mds_request pointer in current->journal_info while filling the inode and dentry cache from an MDS reply.

An allocation in this section can enter direct reclaim and prune dentries from another filesystem.  If this dirties an ext4 inode, ext4
starts a JBD2 transaction.  JBD2 interprets the Ceph request in current->journal_info as a journal handle and dereferences the request's r_tid as h_transaction, causing a kernel crash, e.g.:

 Unable to handle kernel paging request at virtual address
00000000077b4818
 [...]
 Internal error: Oops: 0000000096000004 [#1]  SMP
 Modules linked in:
 CPU: 6 UID: 0 PID: 2699135 Comm: kworker/6:3 Tainted: G       
W           6.18.38-i3 #1113 NONE
 [...]
 Workqueue: ceph-msgr ceph_con_workfn
 pstate: 80400009 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : jbd2__journal_start+0x2c/0x208
 lr : __ext4_journal_start_sb+0x100/0x178
 [...]
 Call trace:
  jbd2__journal_start+0x2c/0x208 (P)
  __ext4_journal_start_sb+0x100/0x178
  ext4_dirty_inode+0x3c/0x90
  __mark_inode_dirty+0x58/0x400
  iput.part.0+0x2b0/0x370
  iput+0x18/0x30
  dentry_unlink_inode+0xc0/0x158
  __dentry_kill+0x80/0x250
  shrink_dentry_list+0x90/0x130
  prune_dcache_sb+0x60/0x98
  super_cache_scan+0xe8/0x190
  do_shrink_slab+0x174/0x388
  shrink_slab+0xd8/0x4c0
  shrink_node+0x31c/0x908
  do_try_to_free_pages+0xd0/0x508
  try_to_free_pages+0x11c/0x238
  __alloc_frozen_pages_noprof+0x4d0/0xdd0
  __folio_alloc_noprof+0x18/0x70
  __filemap_get_folio+0x248/0x440
  ceph_readdir_prepopulate+0x570/0x9e8
  mds_dispatch+0x1424/0x1ba0
  ceph_con_process_message+0x74/0xa0
  ceph_con_v1_try_read+0x3a0/0x1510
  ceph_con_workfn+0x260/0x460

Enter a scoped NOFS allocation context and leave it after clearing journal_info.  This prevents filesystem reclaim from recursing into another filesystem while the field contains Ceph-private data.

Fixes 315f24088048 ("ceph: fix security xattr deadlock")

---
 fs/ceph/mds_client.c | 11 +++++++++++

 1 file changed, 11 insertions(+)
fs/ceph/mds_client.c +1 -0
index 853bf698b356..3c692ad02c85 100644
@@ -6,6 +6,7 @@
  #include <linux/slab.h>
  #include <linux/gfp.h>
  #include <linux/sched.h>
+#include <linux/sched/mm.h>
  #include <linux/delay.h>
  #include <linux/debugfs.h>
  #include <linux/seq_file.h>
@@ -4015,6 +4016,7 @@ static void handle_reply(struct
 ceph_mds_session *session, struct ceph_msg *msg)
  	struct ceph_mds_reply_head *head = msg->front.iov_base;

  struct ceph_mds_reply_info_parsed *rinfo;  /* parsed reply info */
  struct ceph_snap_realm *realm;

fs/ceph/mds_client.c +1 -0
+	unsigned int nofs_flags;

  u64 tid;
  int err, result;
  int mds = session->s_mds;

fs/ceph/mds_client.c +0 -0
@@ -4158,6 +4160,14 @@ static void handle_reply(struct
 ceph_mds_session *session, struct ceph_msg *msg)


  /* insert trace into our cache */
  mutex_lock(&req->r_fill_mutex);

fs/ceph/mds_client.c +2 -0
+
+	/* disable fs reclaim while we are using current-
Quoted 1 line

journal_info

fs/ceph/mds_client.c +6 -0
+	 * for our own purposes, or else shrinkers of other
+	 * filesystems might dereference this pointer as a different
+	 * type
+	 */
+	nofs_flags = memalloc_nofs_save();
+

  current->journal_info = req;
  err = ceph_fill_trace(mdsc->fsc->sb, req); if (err == 0) {

fs/ceph/mds_client.c +0 -0
@@ -4166,6 +4176,7 @@ static void handle_reply(struct
 ceph_mds_session *session, struct ceph_msg *msg)

  err = ceph_readdir_prepopulate(req, req-

Quoted 1 line

r_session);

  }
  current->journal_info = NULL;

fs/ceph/mds_client.c +1 -0
+	memalloc_nofs_restore(nofs_flags);
Quoted 3 lines

  mutex_unlock(&req->r_fill_mutex);

  up_read(&mdsc->snap_rwsem);

Makes sense.

Thanks,
Slava.

Reviewed-by
#2 lore raw

LGTM.

Thanks & Regards
Xiubo

Quoted 119 lines · Viacheslav Dubeyko
Quoted 109 lines · Max Kellermann

handle_reply() stores a ceph_mds_request pointer in current->journal_info while filling the inode and dentry cache from an MDS reply.

An allocation in this section can enter direct reclaim and prune dentries from another filesystem. If this dirties an ext4 inode, ext4
starts a JBD2 transaction. JBD2 interprets the Ceph request in current->journal_info as a journal handle and dereferences the request's r_tid as h_transaction, causing a kernel crash, e.g.:

 Unable to handle kernel paging request at virtual address
00000000077b4818
 [...]
 Internal error: Oops: 0000000096000004 [#1]  SMP
 Modules linked in:
 CPU: 6 UID: 0 PID: 2699135 Comm: kworker/6:3 Tainted: G
W           6.18.38-i3 #1113 NONE
 [...]
 Workqueue: ceph-msgr ceph_con_workfn
 pstate: 80400009 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : jbd2__journal_start+0x2c/0x208
 lr : __ext4_journal_start_sb+0x100/0x178
 [...]
 Call trace:
  jbd2__journal_start+0x2c/0x208 (P)
  __ext4_journal_start_sb+0x100/0x178
  ext4_dirty_inode+0x3c/0x90
  __mark_inode_dirty+0x58/0x400
  iput.part.0+0x2b0/0x370
  iput+0x18/0x30
  dentry_unlink_inode+0xc0/0x158
  __dentry_kill+0x80/0x250
  shrink_dentry_list+0x90/0x130
  prune_dcache_sb+0x60/0x98
  super_cache_scan+0xe8/0x190
  do_shrink_slab+0x174/0x388
  shrink_slab+0xd8/0x4c0
  shrink_node+0x31c/0x908
  do_try_to_free_pages+0xd0/0x508
  try_to_free_pages+0x11c/0x238
  __alloc_frozen_pages_noprof+0x4d0/0xdd0
  __folio_alloc_noprof+0x18/0x70
  __filemap_get_folio+0x248/0x440
  ceph_readdir_prepopulate+0x570/0x9e8
  mds_dispatch+0x1424/0x1ba0
  ceph_con_process_message+0x74/0xa0
  ceph_con_v1_try_read+0x3a0/0x1510
  ceph_con_workfn+0x260/0x460

Enter a scoped NOFS allocation context and leave it after clearing journal_info. This prevents filesystem reclaim from recursing into another filesystem while the field contains Ceph-private data.

Fixes 315f24088048 ("ceph: fix security xattr deadlock")
---
 fs/ceph/mds_client.c | 11 +++++++++++
 1 file changed, 11 insertions(+)
fs/ceph/mds_client.c +1 -0
index 853bf698b356..3c692ad02c85 100644
@@ -6,6 +6,7 @@
 #include <linux/slab.h>
 #include <linux/gfp.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/delay.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -4015,6 +4016,7 @@ static void handle_reply(struct
 ceph_mds_session *session, struct ceph_msg *msg)
      struct ceph_mds_reply_head *head = msg->front.iov_base;
      struct ceph_mds_reply_info_parsed *rinfo;  /* parsed reply

info */

      struct ceph_snap_realm *realm;
fs/ceph/mds_client.c +3 -0
+     unsigned int nofs_flags;
      u64 tid;
      int err, result;
      int mds = session->s_mds;
@@ -4158,6 +4160,14 @@ static void handle_reply(struct
 ceph_mds_session *session, struct ceph_msg *msg)
 
      /* insert trace into our cache */
      mutex_lock(&req->r_fill_mutex);
+
+     /* disable fs reclaim while we are using current-
Quoted 1 line

journal_info

fs/ceph/mds_client.c +7 -0
+      * for our own purposes, or else shrinkers of other
+      * filesystems might dereference this pointer as a different
+      * type
+      */
+     nofs_flags = memalloc_nofs_save();
+
      current->journal_info = req;
      err = ceph_fill_trace(mdsc->fsc->sb, req);
      if (err == 0) {
@@ -4166,6 +4176,7 @@ static void handle_reply(struct
 ceph_mds_session *session, struct ceph_msg *msg)
                      err = ceph_readdir_prepopulate(req, req-
 >r_session);
      }
      current->journal_info = NULL;
+     memalloc_nofs_restore(nofs_flags);
      mutex_unlock(&req->r_fill_mutex);
Quoted 1 line
      up_read(&mdsc->snap_rwsem);

Makes sense.

Thanks,
Slava.