From ac983517ec5941da0c58cacdbad10a231dc4e001 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 7 May 2014 08:05:50 +1000 Subject: [PATCH] xfs: don't sleep in xlog_cil_force_lsn on shutdown Reports of a shutdown hang when fsyncing a directory have surfaced, such as this: [ 3663.394472] Call Trace: [ 3663.397199] [] schedule+0x29/0x70 [ 3663.402743] [] xlog_cil_force_lsn+0x185/0x1a0 [xfs] [ 3663.416249] [] _xfs_log_force_lsn+0x6f/0x2f0 [xfs] [ 3663.429271] [] xfs_dir_fsync+0x7d/0xe0 [xfs] [ 3663.435873] [] do_fsync+0x65/0xa0 [ 3663.441408] [] SyS_fsync+0x10/0x20 [ 3663.447043] [] system_call_fastpath+0x16/0x1b If we trigger a shutdown in xlog_cil_push() from xlog_write(), we will never wake waiters on the current push sequence number, so anything waiting in xlog_cil_force_lsn() for that push sequence number to come up will not get woken and hence stall the shutdown. Fix this by ensuring we call wake_up_all(&cil->xc_commit_wait) in the push abort handling, in the log shutdown code when waking all waiters, and adding a shutdown check in the sequence completion wait loops to ensure they abort when a wakeup due to a shutdown occurs. Reported-by: Boris Ranto Reported-by: Eric Sandeen Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_log.c | 9 +++++--- fs/xfs/xfs_log_cil.c | 50 +++++++++++++++++++++++++++++++++++++------- 2 files changed, 48 insertions(+), 11 deletions(-) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 8497a00e399d..82f5602d97e2 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -3915,11 +3915,14 @@ xfs_log_force_umount( retval = xlog_state_ioerror(log); spin_unlock(&log->l_icloglock); } + /* - * Wake up everybody waiting on xfs_log_force. - * Callback all log item committed functions as if the - * log writes were completed. + * Wake up everybody waiting on xfs_log_force. Wake the CIL push first + * as if the log writes were completed. The abort handling in the log + * item committed callback functions will do this again under lock to + * avoid races. */ + wake_up_all(&log->l_cilp->xc_commit_wait); xlog_state_do_callback(log, XFS_LI_ABORTED, NULL); #ifdef XFSERRORDEBUG diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 7e5455391176..039c873e6fb2 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -385,7 +385,15 @@ xlog_cil_committed( xfs_extent_busy_clear(mp, &ctx->busy_extents, (mp->m_flags & XFS_MOUNT_DISCARD) && !abort); + /* + * If we are aborting the commit, wake up anyone waiting on the + * committing list. If we don't, then a shutdown we can leave processes + * waiting in xlog_cil_force_lsn() waiting on a sequence commit that + * will never happen because we aborted it. + */ spin_lock(&ctx->cil->xc_push_lock); + if (abort) + wake_up_all(&ctx->cil->xc_commit_wait); list_del(&ctx->committing); spin_unlock(&ctx->cil->xc_push_lock); @@ -563,9 +571,19 @@ xlog_cil_push( restart: spin_lock(&cil->xc_push_lock); list_for_each_entry(new_ctx, &cil->xc_committing, committing) { + /* + * Avoid getting stuck in this loop because we were woken by the + * shutdown, but then went back to sleep once already in the + * shutdown state. + */ + if (XLOG_FORCED_SHUTDOWN(log)) { + spin_unlock(&cil->xc_push_lock); + goto out_abort_free_ticket; + } + /* * Higher sequences will wait for this one so skip them. - * Don't wait for own own sequence, either. + * Don't wait for our own sequence, either. */ if (new_ctx->sequence >= ctx->sequence) continue; @@ -810,6 +828,13 @@ restart: */ spin_lock(&cil->xc_push_lock); list_for_each_entry(ctx, &cil->xc_committing, committing) { + /* + * Avoid getting stuck in this loop because we were woken by the + * shutdown, but then went back to sleep once already in the + * shutdown state. + */ + if (XLOG_FORCED_SHUTDOWN(log)) + goto out_shutdown; if (ctx->sequence > sequence) continue; if (!ctx->commit_lsn) { @@ -833,14 +858,12 @@ restart: * push sequence after the above wait loop and the CIL still contains * dirty objects. * - * When the push occurs, it will empty the CIL and - * atomically increment the currect sequence past the push sequence and - * move it into the committing list. Of course, if the CIL is clean at - * the time of the push, it won't have pushed the CIL at all, so in that - * case we should try the push for this sequence again from the start - * just in case. + * When the push occurs, it will empty the CIL and atomically increment + * the currect sequence past the push sequence and move it into the + * committing list. Of course, if the CIL is clean at the time of the + * push, it won't have pushed the CIL at all, so in that case we should + * try the push for this sequence again from the start just in case. */ - if (sequence == cil->xc_current_sequence && !list_empty(&cil->xc_cil)) { spin_unlock(&cil->xc_push_lock); @@ -849,6 +872,17 @@ restart: spin_unlock(&cil->xc_push_lock); return commit_lsn; + + /* + * We detected a shutdown in progress. We need to trigger the log force + * to pass through it's iclog state machine error handling, even though + * we are already in a shutdown state. Hence we can't return + * NULLCOMMITLSN here as that has special meaning to log forces (i.e. + * LSN is already stable), so we return a zero LSN instead. + */ +out_shutdown: + spin_unlock(&cil->xc_push_lock); + return 0; } /*