From d99724c3c36ae73ed3908f5e3f2d103a48cd9ad0 Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Fri, 15 Nov 2019 10:45:41 -0500 Subject: [PATCH] gfs2: Close timing window with GLF_INVALIDATE_IN_PROGRESS This patch closes a timing window in which two processes compete and overlap in the execution of do_xmote for the same glock: Process A Process B ------------------------------------ ----------------------------- 1. Grabs gl_lockref and calls do_xmote 2. Grabs gl_lockref but is blocked 3. Sets GLF_INVALIDATE_IN_PROGRESS 4. Unlocks gl_lockref 5. Calls do_xmote 6. Call glops->go_sync 7. test_and_clear_bit GLF_DIRTY 8. Call gfs2_log_flush Call glops->go_sync 9. (slow IO, so it blocks a long time) test_and_clear_bit GLF_DIRTY It's not dirty (step 7) returns 10. Tests GLF_INVALIDATE_IN_PROGRESS 11. Calls go_inval (rgrp_go_inval) 12. gfs2_rgrp_relse does brelse 13. truncate_inode_pages_range 14. Calls lm_lock UN In step 14 we've just told dlm to give the glock to another node when, in fact, process A has not finished the IO and synced all buffer_heads to disk and make sure their revokes are done. This patch fixes the problem by changing the GLF_INVALIDATE_IN_PROGRESS to use test_and_set_bit, and if the bit is already set, process B just ignores it and trusts that process A will do the do_xmote in the proper order. Signed-off-by: Bob Peterson Signed-off-by: Andreas Gruenbacher --- fs/gfs2/glock.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index faa88bd594e2..b7123de7c180 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -558,7 +558,14 @@ __acquires(&gl->gl_lockref.lock) GLOCK_BUG_ON(gl, gl->gl_state == gl->gl_target); if ((target == LM_ST_UNLOCKED || target == LM_ST_DEFERRED) && glops->go_inval) { - set_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags); + /* + * If another process is already doing the invalidate, let that + * finish first. The glock state machine will get back to this + * holder again later. + */ + if (test_and_set_bit(GLF_INVALIDATE_IN_PROGRESS, + &gl->gl_flags)) + return; do_error(gl, 0); /* Fail queued try locks */ } gl->gl_req = target;