While testing and rearranging my pquota/gquota code, I stumbled
on a xfs_shutdown() during a mount. But the mount just hung.
I debugged and found that there is a deadlock involving
&log->l_cilp->xc_ctx_lock.
It is in a code path where &log->l_cilp->xc_ctx_lock is first
acquired in read mode and some levels down the same semaphore
is being acquired in write mode causing a deadlock.
This is the stack:
xfs_log_commit_cil -> acquires &log->l_cilp->xc_ctx_lock in read mode
xlog_print_tic_res
xfs_force_shutdown
xfs_log_force_umount
xlog_cil_force
xlog_cil_force_lsn
xlog_cil_push_foreground
xlog_cil_push - tries to acquire same semaphore in write mode
This patch fixes the deadlock by not calling xfs_force_shutdown() while
holding the semaphore, instead calling it after dropping teh semaphore.
Thanks to Dave for suggesting this solution.
Signed-off-by: Chandra Seetharaman <sekharan@xxxxxxxxxx>
---
fs/xfs/xfs_log.c | 6 +++---
fs/xfs/xfs_log_cil.c | 10 ++++++----
fs/xfs/xfs_log_priv.h | 2 +-
fs/xfs/xfs_trans.c | 2 +-
4 files changed, 11 insertions(+), 9 deletions(-)
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index d852a2b..b9fa2da 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1837,7 +1837,7 @@ xlog_state_finish_copy(
* print out info relating to regions written which consume
* the reservation
*/
-void
+int
xlog_print_tic_res(
struct xfs_mount *mp,
struct xlog_ticket *ticket)
@@ -1941,7 +1941,7 @@ xlog_print_tic_res(
xfs_alert_tag(mp, XFS_PTAG_LOGRES,
"xlog_write: reservation ran out. Need to up reservation");
- xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ return EFSCORRUPTED;
}
/*
@@ -2215,7 +2215,7 @@ xlog_write(
ticket->t_curr_res -= sizeof(xlog_op_header_t);
if (ticket->t_curr_res < 0)
- xlog_print_tic_res(log->l_mp, ticket);
+ return xlog_print_tic_res(log->l_mp, ticket);
index = 0;
lv = log_vector;
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 02b9cf3..93ba7bd 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -730,10 +730,6 @@ xfs_log_commit_cil(
/* xlog_cil_insert_items() destroys log_vector list */
xlog_cil_insert_items(log, log_vector, tp->t_ticket);
- /* check we didn't blow the reservation */
- if (tp->t_ticket->t_curr_res < 0)
- xlog_print_tic_res(log->l_mp, tp->t_ticket);
-
/* attach the transaction to the CIL if it has any busy extents */
if (!list_empty(&tp->t_busy)) {
spin_lock(&log->l_cilp->xc_cil_lock);
@@ -742,6 +738,12 @@ xfs_log_commit_cil(
spin_unlock(&log->l_cilp->xc_cil_lock);
}
+ /* check we didn't blow the reservation */
+ if (tp->t_ticket->t_curr_res < 0) {
+ up_read(&log->l_cilp->xc_ctx_lock);
+ return xlog_print_tic_res(log->l_mp, tp->t_ticket);
+ }
+
tp->t_commit_lsn = *commit_lsn;
xfs_log_done(mp, tp->t_ticket, NULL, log_flags);
xfs_trans_unreserve_and_mod_sb(tp);
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index b9ea262..4f2fa6d 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -576,7 +576,7 @@ xlog_write_adv_cnt(void **ptr, int *len, int *off, size_t bytes)
*off += bytes;
}
-void xlog_print_tic_res(struct xfs_mount *mp, struct xlog_ticket *ticket);
+int xlog_print_tic_res(struct xfs_mount *mp, struct xlog_ticket *ticket);
int
xlog_write(
struct xlog *log,
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 35a2299..d96022f 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -1547,7 +1547,7 @@ xfs_trans_commit(
xfs_trans_apply_dquot_deltas(tp);
error = xfs_log_commit_cil(mp, tp, &commit_lsn, flags);
- if (error == ENOMEM) {
+ if (error) {
xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR);
error = XFS_ERROR(EIO);
goto out_unreserve;
_______________________________________________
xfs mailing list
xfs@xxxxxxxxxxx
http://oss.sgi.com/mailman/listinfo/xfs
