[PATCH AUTOSEL 4.19 001/244] gfs2: Fix lru_count going negative

* [PATCH AUTOSEL 4.19 001/244] gfs2: Fix lru_count going negative
@ 2019-05-22 19:22 ` Sasha Levin
  0 siblings, 0 replies; 97+ messages in thread
From: Sasha Levin @ 2019-05-22 19:22 UTC (permalink / raw)
  To: linux-kernel, stable
  Cc: Ross Lagerwall, Andreas Gruenbacher, Sasha Levin, cluster-devel

From: Ross Lagerwall <ross.lagerwall@citrix.com>

[ Upstream commit 7881ef3f33bb80f459ea6020d1e021fc524a6348 ]

Under certain conditions, lru_count may drop below zero resulting in
a large amount of log spam like this:

vmscan: shrink_slab: gfs2_dump_glock+0x3b0/0x630 [gfs2] \
    negative objects to delete nr=-1

This happens as follows:
1) A glock is moved from lru_list to the dispose list and lru_count is
   decremented.
2) The dispose function calls cond_resched() and drops the lru lock.
3) Another thread takes the lru lock and tries to add the same glock to
   lru_list, checking if the glock is on an lru list.
4) It is on a list (actually the dispose list) and so it avoids
   incrementing lru_count.
5) The glock is moved to lru_list.
5) The original thread doesn't dispose it because it has been re-added
   to the lru list but the lru_count has still decreased by one.

Fix by checking if the LRU flag is set on the glock rather than checking
if the glock is on some list and rearrange the code so that the LRU flag
is added/removed precisely when the glock is added/removed from lru_list.

Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/gfs2/glock.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 9d566e62684c2..775256141e9fb 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -183,15 +183,19 @@ static int demote_ok(const struct gfs2_glock *gl)
 
 void gfs2_glock_add_to_lru(struct gfs2_glock *gl)
 {
+	if (!(gl->gl_ops->go_flags & GLOF_LRU))
+		return;
+
 	spin_lock(&lru_lock);
 
-	if (!list_empty(&gl->gl_lru))
-		list_del_init(&gl->gl_lru);
-	else
+	list_del(&gl->gl_lru);
+	list_add_tail(&gl->gl_lru, &lru_list);
+
+	if (!test_bit(GLF_LRU, &gl->gl_flags)) {
+		set_bit(GLF_LRU, &gl->gl_flags);
 		atomic_inc(&lru_count);
+	}
 
-	list_add_tail(&gl->gl_lru, &lru_list);
-	set_bit(GLF_LRU, &gl->gl_flags);
 	spin_unlock(&lru_lock);
 }
 
@@ -201,7 +205,7 @@ static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
 		return;
 
 	spin_lock(&lru_lock);
-	if (!list_empty(&gl->gl_lru)) {
+	if (test_bit(GLF_LRU, &gl->gl_flags)) {
 		list_del_init(&gl->gl_lru);
 		atomic_dec(&lru_count);
 		clear_bit(GLF_LRU, &gl->gl_flags);
@@ -1158,8 +1162,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
 		    !test_bit(GLF_DEMOTE, &gl->gl_flags))
 			fast_path = 1;
 	}
-	if (!test_bit(GLF_LFLUSH, &gl->gl_flags) && demote_ok(gl) &&
-	    (glops->go_flags & GLOF_LRU))
+	if (!test_bit(GLF_LFLUSH, &gl->gl_flags) && demote_ok(gl))
 		gfs2_glock_add_to_lru(gl);
 
 	trace_gfs2_glock_queue(gh, 0);
@@ -1455,6 +1458,7 @@ __acquires(&lru_lock)
 		if (!spin_trylock(&gl->gl_lockref.lock)) {
 add_back_to_lru:
 			list_add(&gl->gl_lru, &lru_list);
+			set_bit(GLF_LRU, &gl->gl_flags);
 			atomic_inc(&lru_count);
 			continue;
 		}
@@ -1462,7 +1466,6 @@ __acquires(&lru_lock)
 			spin_unlock(&gl->gl_lockref.lock);
 			goto add_back_to_lru;
 		}
-		clear_bit(GLF_LRU, &gl->gl_flags);
 		gl->gl_lockref.count++;
 		if (demote_ok(gl))
 			handle_callback(gl, LM_ST_UNLOCKED, 0, false);
@@ -1497,6 +1500,7 @@ static long gfs2_scan_glock_lru(int nr)
 		if (!test_bit(GLF_LOCK, &gl->gl_flags)) {
 			list_move(&gl->gl_lru, &dispose);
 			atomic_dec(&lru_count);
+			clear_bit(GLF_LRU, &gl->gl_flags);
 			freed++;
 			continue;
 		}
-- 
2.20.1


^ permalink raw reply related	[flat|nested] 97+ messages in thread