Blob Blame History Raw
From 7881ef3f33bb80f459ea6020d1e021fc524a6348 Mon Sep 17 00:00:00 2001
From: Ross Lagerwall <ross.lagerwall@citrix.com>
Date: Wed, 27 Mar 2019 17:09:17 +0000
Subject: [PATCH] gfs2: Fix lru_count going negative
Git-commit: 7881ef3f33bb80f459ea6020d1e021fc524a6348
Patch-mainline: v5.2-rc1
References: git-fixes

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>
Acked-by: Anthony Iliopoulos <ailiop@suse.com>

---
 fs/gfs2/glock.c |   22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -136,22 +136,26 @@ static int demote_ok(const struct gfs2_g
 
 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);
 }
 
 static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
 {
 	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);
@@ -1049,8 +1053,7 @@ void gfs2_glock_dq(struct gfs2_holder *g
 		    !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);
@@ -1350,6 +1353,7 @@ __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;
 		}
@@ -1357,7 +1361,6 @@ add_back_to_lru:
 			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);
@@ -1393,6 +1396,7 @@ 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;
 		}