Function ceph_check_delayed_caps() is called from the mdsc->delayed_work workqueue and it can be kept looping for quite some time if caps keep being added back to the mdsc->cap_delay_list. This may result in the watchdog tainting the kernel with the softlockup flag.

This patch breaks this loop if the caps have been recently (i.e. during the loop execution). Any new caps added to the list will be handled in the next run.

Cc: stable@vger.kernel.org Link: https://tracker.ceph.com/issues/46284 Signed-off-by: Luis Henriques lhenriques@suse.de --- fs/ceph/caps.c | 17 ++++++++++++++++- fs/ceph/mds_client.c | 7 ++++--- fs/ceph/super.h | 2 +- 3 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index a5e93b185515..c79b8dff25d7 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -4224,11 +4224,19 @@ void ceph_handle_caps(struct ceph_mds_session *session,

/* * Delayed work handler to process end of delayed cap release LRU list. + * + * If new caps are added to the list while processing it, these won't get + * processed in this run. In this case, the ci->i_hold_caps_max will be + * returned so that the work can be scheduled accordingly. */ -void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) +unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc) { struct inode *inode; struct ceph_inode_info *ci; + struct ceph_mount_options *opt = mdsc->fsc->mount_options; + unsigned long delay_max = opt->caps_wanted_delay_max * HZ; + unsigned long loop_start = jiffies; + unsigned long delay = 0;

dout("check_delayed_caps\n"); spin_lock(&mdsc->cap_delay_lock); @@ -4236,6 +4244,11 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) ci = list_first_entry(&mdsc->cap_delay_list, struct ceph_inode_info, i_cap_delay_list); + if (time_before(loop_start, ci->i_hold_caps_max - delay_max)) { + dout("%s caps added recently. Exiting loop", __func__); + delay = ci->i_hold_caps_max; + break; + } if ((ci->i_ceph_flags & CEPH_I_FLUSH) == 0 && time_before(jiffies, ci->i_hold_caps_max)) break; @@ -4252,6 +4265,8 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) } } spin_unlock(&mdsc->cap_delay_lock); + + return delay; }

/* diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index f5dc58a05f9f..a6f985786d68 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4519,11 +4519,12 @@ static void schedule_delayed(struct ceph_mds_client *mdsc, unsigned long delay)

static void delayed_work(struct work_struct *work) { - int i; struct ceph_mds_client *mdsc = container_of(work, struct ceph_mds_client, delayed_work.work); + unsigned long delay; int renew_interval; int renew_caps; + int i;

dout("mdsc delayed_work\n");

@@ -4563,7 +4564,7 @@ static void delayed_work(struct work_struct *work) } mutex_unlock(&mdsc->mutex);

- ceph_check_delayed_caps(mdsc); + delay = ceph_check_delayed_caps(mdsc);

ceph_queue_cap_reclaim_work(mdsc);

@@ -4571,7 +4572,7 @@ static void delayed_work(struct work_struct *work)

maybe_recover_session(mdsc);

- schedule_delayed(mdsc, 0); + schedule_delayed(mdsc, delay); }

int ceph_mdsc_init(struct ceph_fs_client *fsc) diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 839e6b0239ee..3b5207c82767 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1170,7 +1170,7 @@ extern void ceph_flush_snaps(struct ceph_inode_info *ci, extern bool __ceph_should_report_size(struct ceph_inode_info *ci); extern void ceph_check_caps(struct ceph_inode_info *ci, int flags, struct ceph_mds_session *session); -extern void ceph_check_delayed_caps(struct ceph_mds_client *mdsc); +extern unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc); extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc); extern int ceph_drop_caps_for_unlink(struct inode *inode); extern int ceph_encode_inode_release(void **p, struct inode *inode,