slub: move discard_slab out of node lock (9ada1934) · Commits · 戴 / test

Lockdep reports there is potential deadlock for slub node list_lock. discard_slab() is called with the lock hold in unfreeze_partials(), which could trigger a slab allocation, which could hold the lock again. discard_slab() doesn't need hold the lock actually, if the slab is already removed from partial list. Acked-by:

Christoph Lameter <cl@linux.com> Reported-and-tested-by:

Yong Zhang <yong.zhang0@gmail.com> Reported-and-tested-by:

Julie Sullivan <kernelmail.jms@gmail.com> Signed-off-by:

Shaohua Li <shaohua.li@intel.com> Signed-off-by:

Pekka Enberg <penberg@kernel.org>

mm/slub.c

+12 −4

Original line number	Diff line number	Diff line
		@@ -1862,7 +1862,7 @@ static void unfreeze_partials(struct kmem_cache *s)
		{
		struct kmem_cache_node *n = NULL;
		struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab);
		struct page *page;
		struct page page, discard_page = NULL;

		while ((page = c->partial)) {
		enum slab_modes { M_PARTIAL, M_FREE };
		@@ -1916,14 +1916,22 @@ static void unfreeze_partials(struct kmem_cache *s)
		"unfreezing slab"));

		if (m == M_FREE) {
		stat(s, DEACTIVATE_EMPTY);
		discard_slab(s, page);
		stat(s, FREE_SLAB);
		page->next = discard_page;
		discard_page = page;
		}
		}

		if (n)
		spin_unlock(&n->list_lock);

		while (discard_page) {
		page = discard_page;
		discard_page = discard_page->next;

		stat(s, DEACTIVATE_EMPTY);
		discard_slab(s, page);
		stat(s, FREE_SLAB);
		}
		}

		/*

Admin message