Subject: [folded-merged] mm-keep-page-cache-radix-tree-nodes-in-check-fix.patch removed from -mm tree
To: hannes@xxxxxxxxxxx,hughd@xxxxxxxxxx,minchan@xxxxxxxxxx,riel@xxxxxxxxxx,mm-commits@xxxxxxxxxxxxxxx
From: akpm@xxxxxxxxxxxxxxxxxxxx
Date: Thu, 03 Apr 2014 14:06:17 -0700
The patch titled
Subject: mm-keep-page-cache-radix-tree-nodes-in-check-fix
has been removed from the -mm tree. Its filename was
mm-keep-page-cache-radix-tree-nodes-in-check-fix.patch
This patch was dropped because it was folded into mm-keep-page-cache-radix-tree-nodes-in-check.patch
------------------------------------------------------
From: Johannes Weiner <hannes@xxxxxxxxxxx>
Subject: mm-keep-page-cache-radix-tree-nodes-in-check-fix
Hugh Dickin reports the following lockdep splat:
======================================================
[ INFO: SOFTIRQ-safe -> SOFTIRQ-unsafe lock order detected ]
3.14.0-rc1-mm1 #1 Not tainted
------------------------------------------------------
kswapd0/48 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire:
(&(&lru->node[i].lock)->rlock){+.+.-.}, at: [<ffffffff81117064>] list_lru_add+0x80/0xf4
s already holding:
(&(&mapping->tree_lock)->rlock){..-.-.}, at: [<ffffffff81108c63>] __remove_mapping+0x3b/0x12d
which would create a new lock dependency:
(&(&mapping->tree_lock)->rlock){..-.-.} -> (&(&lru->node[i].lock)->rlock){+.+.-.}
lru->node[i].lock nests inside the mapping->tree_lock when page cache
insertions and deletions add or remove radix tree nodes to the shadow
LRU list.
However, paths that only hold the IRQ-unsafe lru->node[i].lock, like
the shadow shrinker, can be interrupted at any time by the IO
completion handler, which in turn acquires the mapping->tree_lock.
This is a simple locking order inversion and can deadlock like so:
CPU#0: shadow shrinker CPU#1: page cache modification
lru->node[i].lock
mapping->tree_lock
lru->node[i].lock
<interrupt>
mapping->tree_lock
Make the shadow lru->node[i].lock IRQ-safe to remove the order
dictated by interruption. This slightly increases the IRQ-disabled
section in the shadow shrinker, but it still drops all locks and
enables IRQ after every reclaimed shadow radix tree node.
Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Reported-by: Hugh Dickins <hughd@xxxxxxxxxx>
Tested-by: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/list_lru.h | 6 +++++-
mm/list_lru.c | 4 +++-
mm/workingset.c | 24 ++++++++++++++++++++----
3 files changed, 28 insertions(+), 6 deletions(-)
diff -puN include/linux/list_lru.h~mm-keep-page-cache-radix-tree-nodes-in-check-fix include/linux/list_lru.h
--- a/include/linux/list_lru.h~mm-keep-page-cache-radix-tree-nodes-in-check-fix
+++ a/include/linux/list_lru.h
@@ -34,7 +34,11 @@ struct list_lru {
};
void list_lru_destroy(struct list_lru *lru);
-int list_lru_init(struct list_lru *lru);
+int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key);
+static inline int list_lru_init(struct list_lru *lru)
+{
+ return list_lru_init_key(lru, NULL);
+}
/**
* list_lru_add: add an element to the lru list's tail
diff -puN mm/list_lru.c~mm-keep-page-cache-radix-tree-nodes-in-check-fix mm/list_lru.c
--- a/mm/list_lru.c~mm-keep-page-cache-radix-tree-nodes-in-check-fix
+++ a/mm/list_lru.c
@@ -124,7 +124,7 @@ restart:
}
EXPORT_SYMBOL_GPL(list_lru_walk_node);
-int list_lru_init(struct list_lru *lru)
+int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key)
{
int i;
size_t size = sizeof(*lru->node) * nr_node_ids;
@@ -136,6 +136,8 @@ int list_lru_init(struct list_lru *lru)
nodes_clear(lru->active_nodes);
for (i = 0; i < nr_node_ids; i++) {
spin_lock_init(&lru->node[i].lock);
+ if (key)
+ lockdep_set_class(&lru->node[i].lock, key);
INIT_LIST_HEAD(&lru->node[i].list);
lru->node[i].nr_items = 0;
}
diff -puN mm/workingset.c~mm-keep-page-cache-radix-tree-nodes-in-check-fix mm/workingset.c
--- a/mm/workingset.c~mm-keep-page-cache-radix-tree-nodes-in-check-fix
+++ a/mm/workingset.c
@@ -273,7 +273,10 @@ static unsigned long count_shadow_nodes(
unsigned long max_nodes;
unsigned long pages;
+ local_irq_disable();
shadow_nodes = list_lru_count_node(&workingset_shadow_nodes, sc->nid);
+ local_irq_enable();
+
pages = node_present_pages(sc->nid);
/*
* Active cache pages are limited to 50% of memory, and shadow
@@ -322,7 +325,7 @@ static enum lru_status shadow_lru_isolat
mapping = node->private_data;
/* Coming from the list, invert the lock order */
- if (!spin_trylock_irq(&mapping->tree_lock)) {
+ if (!spin_trylock(&mapping->tree_lock)) {
spin_unlock(lru_lock);
ret = LRU_RETRY;
goto out;
@@ -355,10 +358,12 @@ static enum lru_status shadow_lru_isolat
if (!__radix_tree_delete_node(&mapping->page_tree, node))
BUG();
- spin_unlock_irq(&mapping->tree_lock);
+ spin_unlock(&mapping->tree_lock);
ret = LRU_REMOVED_RETRY;
out:
+ local_irq_enable();
cond_resched();
+ local_irq_disable();
spin_lock(lru_lock);
return ret;
}
@@ -366,8 +371,13 @@ out:
static unsigned long scan_shadow_nodes(struct shrinker *shrinker,
struct shrink_control *sc)
{
- return list_lru_walk_node(&workingset_shadow_nodes, sc->nid,
+ unsigned long ret;
+
+ local_irq_disable();
+ ret = list_lru_walk_node(&workingset_shadow_nodes, sc->nid,
shadow_lru_isolate, NULL, &sc->nr_to_scan);
+ local_irq_enable();
+ return ret;
}
static struct shrinker workingset_shadow_shrinker = {
@@ -377,11 +387,17 @@ static struct shrinker workingset_shadow
.flags = SHRINKER_NUMA_AWARE,
};
+/*
+ * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe
+ * mapping->tree_lock.
+ */
+static struct lock_class_key shadow_nodes_key;
+
static int __init workingset_init(void)
{
int ret;
- ret = list_lru_init(&workingset_shadow_nodes);
+ ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key);
if (ret)
goto err;
ret = register_shrinker(&workingset_shadow_shrinker);
_
Patches currently in -mm which might be from hannes@xxxxxxxxxxx are
mm-vmscan-respect-numa-policy-mask-when-shrinking-slab-on-direct-reclaim.patch
mm-vmscan-move-call-to-shrink_slab-to-shrink_zones.patch
mm-vmscan-remove-shrink_control-arg-from-do_try_to_free_pages.patch
mm-vmstat-fix-up-zone-state-accounting.patch
fs-cachefiles-use-add_to_page_cache_lru.patch
lib-radix-tree-radix_tree_delete_item.patch
mm-shmem-save-one-radix-tree-lookup-when-truncating-swapped-pages.patch
mm-filemap-move-radix-tree-hole-searching-here.patch
mm-fs-prepare-for-non-page-entries-in-page-cache-radix-trees.patch
mm-fs-store-shadow-entries-in-page-cache.patch
mm-thrash-detection-based-file-cache-sizing.patch
lib-radix_tree-tree-node-interface.patch
mm-keep-page-cache-radix-tree-nodes-in-check.patch
mm-keep-page-cache-radix-tree-nodes-in-check-fix-fix.patch
mm-keep-page-cache-radix-tree-nodes-in-check-fix-fix-fix.patch
drop_caches-add-some-documentation-and-info-message.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
