All of lore.kernel.org
 help / color / mirror / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Xiubo Li <xiubli@redhat.com>, Jeff Layton <jlayton@kernel.org>,
	Ilya Dryomov <idryomov@gmail.com>,
	Sasha Levin <sashal@kernel.org>,
	ceph-devel@vger.kernel.org
Subject: [PATCH AUTOSEL 5.13 09/19] ceph: remove the capsnaps when removing caps
Date: Mon, 13 Sep 2021 18:34:05 -0400	[thread overview]
Message-ID: <20210913223415.435654-9-sashal@kernel.org> (raw)
In-Reply-To: <20210913223415.435654-1-sashal@kernel.org>

From: Xiubo Li <xiubli@redhat.com>

[ Upstream commit a6d37ccdd240e80f26aaea0e62cda310e0e184d7 ]

capsnaps will take inode references via ihold when queueing to flush.
When force unmounting, the client will just close the sessions and
may never get a flush reply, causing a leak and inode ref leak.

Fix this by removing the capsnaps for an inode when removing the caps.

URL: https://tracker.ceph.com/issues/52295
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/ceph/caps.c       | 68 +++++++++++++++++++++++++++++++++-----------
 fs/ceph/mds_client.c | 31 +++++++++++++++++++-
 fs/ceph/super.h      |  6 ++++
 3 files changed, 87 insertions(+), 18 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 805c656a2e72..883c9d8e4aac 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -3185,7 +3185,16 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 				break;
 			}
 		}
-		BUG_ON(!found);
+
+		if (!found) {
+			/*
+			 * The capsnap should already be removed when removing
+			 * auth cap in the case of a forced unmount.
+			 */
+			WARN_ON_ONCE(ci->i_auth_cap);
+			goto unlock;
+		}
+
 		capsnap->dirty_pages -= nr;
 		if (capsnap->dirty_pages == 0) {
 			complete_capsnap = true;
@@ -3207,6 +3216,7 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 		     complete_capsnap ? " (complete capsnap)" : "");
 	}
 
+unlock:
 	spin_unlock(&ci->i_ceph_lock);
 
 	if (last) {
@@ -3679,6 +3689,43 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
 		iput(inode);
 }
 
+void __ceph_remove_capsnap(struct inode *inode, struct ceph_cap_snap *capsnap,
+			   bool *wake_ci, bool *wake_mdsc)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+	bool ret;
+
+	lockdep_assert_held(&ci->i_ceph_lock);
+
+	dout("removing capsnap %p, inode %p ci %p\n", capsnap, inode, ci);
+
+	list_del_init(&capsnap->ci_item);
+	ret = __detach_cap_flush_from_ci(ci, &capsnap->cap_flush);
+	if (wake_ci)
+		*wake_ci = ret;
+
+	spin_lock(&mdsc->cap_dirty_lock);
+	if (list_empty(&ci->i_cap_flush_list))
+		list_del_init(&ci->i_flushing_item);
+
+	ret = __detach_cap_flush_from_mdsc(mdsc, &capsnap->cap_flush);
+	if (wake_mdsc)
+		*wake_mdsc = ret;
+	spin_unlock(&mdsc->cap_dirty_lock);
+}
+
+void ceph_remove_capsnap(struct inode *inode, struct ceph_cap_snap *capsnap,
+			 bool *wake_ci, bool *wake_mdsc)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	lockdep_assert_held(&ci->i_ceph_lock);
+
+	WARN_ON_ONCE(capsnap->dirty_pages || capsnap->writing);
+	__ceph_remove_capsnap(inode, capsnap, wake_ci, wake_mdsc);
+}
+
 /*
  * Handle FLUSHSNAP_ACK.  MDS has flushed snap data to disk and we can
  * throw away our cap_snap.
@@ -3716,23 +3763,10 @@ static void handle_cap_flushsnap_ack(struct inode *inode, u64 flush_tid,
 			     capsnap, capsnap->follows);
 		}
 	}
-	if (flushed) {
-		WARN_ON(capsnap->dirty_pages || capsnap->writing);
-		dout(" removing %p cap_snap %p follows %lld\n",
-		     inode, capsnap, follows);
-		list_del(&capsnap->ci_item);
-		wake_ci |= __detach_cap_flush_from_ci(ci, &capsnap->cap_flush);
-
-		spin_lock(&mdsc->cap_dirty_lock);
-
-		if (list_empty(&ci->i_cap_flush_list))
-			list_del_init(&ci->i_flushing_item);
-
-		wake_mdsc |= __detach_cap_flush_from_mdsc(mdsc,
-							  &capsnap->cap_flush);
-		spin_unlock(&mdsc->cap_dirty_lock);
-	}
+	if (flushed)
+		ceph_remove_capsnap(inode, capsnap, &wake_ci, &wake_mdsc);
 	spin_unlock(&ci->i_ceph_lock);
+
 	if (flushed) {
 		ceph_put_snap_context(capsnap->context);
 		ceph_put_cap_snap(capsnap);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 9e24fcea152b..a0b77ee2812d 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1588,14 +1588,39 @@ int ceph_iterate_session_caps(struct ceph_mds_session *session,
 	return ret;
 }
 
+static int remove_capsnaps(struct ceph_mds_client *mdsc, struct inode *inode)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_cap_snap *capsnap;
+	int capsnap_release = 0;
+
+	lockdep_assert_held(&ci->i_ceph_lock);
+
+	dout("removing capsnaps, ci is %p, inode is %p\n", ci, inode);
+
+	while (!list_empty(&ci->i_cap_snaps)) {
+		capsnap = list_first_entry(&ci->i_cap_snaps,
+					   struct ceph_cap_snap, ci_item);
+		__ceph_remove_capsnap(inode, capsnap, NULL, NULL);
+		ceph_put_snap_context(capsnap->context);
+		ceph_put_cap_snap(capsnap);
+		capsnap_release++;
+	}
+	wake_up_all(&ci->i_cap_wq);
+	wake_up_all(&mdsc->cap_flushing_wq);
+	return capsnap_release;
+}
+
 static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 				  void *arg)
 {
 	struct ceph_fs_client *fsc = (struct ceph_fs_client *)arg;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	LIST_HEAD(to_remove);
 	bool dirty_dropped = false;
 	bool invalidate = false;
+	int capsnap_release = 0;
 
 	dout("removing cap %p, ci is %p, inode is %p\n",
 	     cap, ci, &ci->vfs_inode);
@@ -1603,7 +1628,6 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 	__ceph_remove_cap(cap, false);
 	if (!ci->i_auth_cap) {
 		struct ceph_cap_flush *cf;
-		struct ceph_mds_client *mdsc = fsc->mdsc;
 
 		if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) {
 			if (inode->i_data.nrpages > 0)
@@ -1667,6 +1691,9 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 			list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove);
 			ci->i_prealloc_cap_flush = NULL;
 		}
+
+		if (!list_empty(&ci->i_cap_snaps))
+			capsnap_release = remove_capsnaps(mdsc, inode);
 	}
 	spin_unlock(&ci->i_ceph_lock);
 	while (!list_empty(&to_remove)) {
@@ -1683,6 +1710,8 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 		ceph_queue_invalidate(inode);
 	if (dirty_dropped)
 		iput(inode);
+	while (capsnap_release--)
+		iput(inode);
 	return 0;
 }
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 3b6a61116036..c7b8933607b9 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1166,6 +1166,12 @@ extern void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci,
 					    int had);
 extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 				       struct ceph_snap_context *snapc);
+extern void __ceph_remove_capsnap(struct inode *inode,
+				  struct ceph_cap_snap *capsnap,
+				  bool *wake_ci, bool *wake_mdsc);
+extern void ceph_remove_capsnap(struct inode *inode,
+				struct ceph_cap_snap *capsnap,
+				bool *wake_ci, bool *wake_mdsc);
 extern void ceph_flush_snaps(struct ceph_inode_info *ci,
 			     struct ceph_mds_session **psession);
 extern bool __ceph_should_report_size(struct ceph_inode_info *ci);
-- 
2.30.2


  parent reply	other threads:[~2021-09-13 22:37 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-13 22:33 [PATCH AUTOSEL 5.13 01/19] dmaengine: idxd: depends on !UML Sasha Levin
2021-09-13 22:33 ` [PATCH AUTOSEL 5.13 02/19] dmaengine: sprd: Add missing MODULE_DEVICE_TABLE Sasha Levin
2021-09-13 22:33 ` [PATCH AUTOSEL 5.13 03/19] gfs2: Switch to may_setattr in gfs2_setattr Sasha Levin
2021-09-13 22:33   ` [Cluster-devel] " Sasha Levin
2021-09-13 22:34 ` [PATCH AUTOSEL 5.13 04/19] dmaengine: ioat: depends on !UML Sasha Levin
2021-09-13 22:34 ` [PATCH AUTOSEL 5.13 05/19] dmaengine: xilinx_dma: Set DMA mask for coherent APIs Sasha Levin
2021-09-13 22:34   ` Sasha Levin
2021-09-13 22:34 ` [PATCH AUTOSEL 5.13 06/19] s390: add kmemleak annotation in stack_alloc() Sasha Levin
2021-09-13 22:34 ` [PATCH AUTOSEL 5.13 07/19] ASoC: audio-graph: respawn Platform Support Sasha Levin
2021-09-13 22:34   ` Sasha Levin
2021-09-13 22:34 ` [PATCH AUTOSEL 5.13 08/19] ceph: request Fw caps before updating the mtime in ceph_write_iter Sasha Levin
2021-09-13 22:34 ` Sasha Levin [this message]
2021-09-13 22:34 ` [PATCH AUTOSEL 5.13 10/19] ceph: lockdep annotations for try_nonblocking_invalidate Sasha Levin
2021-09-13 22:34 ` [PATCH AUTOSEL 5.13 11/19] btrfs: update the bdev time directly when closing Sasha Levin
2021-09-13 22:34 ` [PATCH AUTOSEL 5.13 12/19] btrfs: fix lockdep warning while mounting sprout fs Sasha Levin
2021-09-13 22:34 ` [PATCH AUTOSEL 5.13 13/19] connector: send event on write to /proc/[pid]/comm Sasha Levin
2021-09-13 22:34 ` [PATCH AUTOSEL 5.13 14/19] nilfs2: fix memory leak in nilfs_sysfs_create_device_group Sasha Levin
2021-09-13 22:34   ` Sasha Levin
2021-09-13 22:34 ` [PATCH AUTOSEL 5.13 15/19] nilfs2: fix NULL pointer in nilfs_##name##_attr_release Sasha Levin
2021-09-13 22:34   ` Sasha Levin
2021-09-13 22:34 ` [PATCH AUTOSEL 5.13 16/19] nilfs2: fix memory leak in nilfs_sysfs_create_##name##_group Sasha Levin
2021-09-13 22:34   ` Sasha Levin
2021-09-13 22:34 ` [PATCH AUTOSEL 5.13 17/19] nilfs2: fix memory leak in nilfs_sysfs_delete_##name##_group Sasha Levin
2021-09-13 22:34   ` Sasha Levin
2021-09-13 22:34 ` [PATCH AUTOSEL 5.13 18/19] nilfs2: fix memory leak in nilfs_sysfs_create_snapshot_group Sasha Levin
2021-09-13 22:34 ` [PATCH AUTOSEL 5.13 19/19] nilfs2: fix memory leak in nilfs_sysfs_delete_snapshot_group Sasha Levin
2021-09-13 22:34   ` Sasha Levin
2021-09-14  6:56 ` [PATCH AUTOSEL 5.13 01/19] dmaengine: idxd: depends on !UML Johannes Berg

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=20210913223415.435654-9-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=ceph-devel@vger.kernel.org \
    --cc=idryomov@gmail.com \
    --cc=jlayton@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=stable@vger.kernel.org \
    --cc=xiubli@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.