netdev - Re: [PATCH 1/4] slab: do ClearSlabPfmemalloc() for all pages of slab

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAAmzW4MfFUH1Mi447sQvPNeae_BShEmbECUaK9eoX-8ughEdJw@mail.gmail.com>
Date:	Fri, 7 Sep 2012 03:05:39 +0900
From:	JoonSoo Kim <js1304@...il.com>
To:	Mel Gorman <mgorman@...e.de>
Cc:	Andrew Morton <akpm@...ux-foundation.org>,
	Linux-MM <linux-mm@...ck.org>,
	Linux-Netdev <netdev@...r.kernel.org>,
	LKML <linux-kernel@...r.kernel.org>,
	David Miller <davem@...emloft.net>,
	Chuck Lever <chuck.lever@...cle.com>,
	Pekka Enberg <penberg@...nel.org>,
	David Rientjes <rientjes@...gle.com>,
	Christoph Lameter <cl@...ux.com>
Subject: Re: [PATCH 1/4] slab: do ClearSlabPfmemalloc() for all pages of slab

Correct Pekka's mail address and resend.
Sorry.

Add "Cc" to "Christoph Lameter" <cl@...ux.com>

2012/9/5 Mel Gorman <mgorman@...e.de>:
> Right now, we call ClearSlabPfmemalloc() for first page of slab when we
> clear SlabPfmemalloc flag. This is fine for most swap-over-network use
> cases as it is expected that order-0 pages are in use. Unfortunately it
> is possible that that __ac_put_obj() checks SlabPfmemalloc on a tail page
> and while this is harmless, it is sloppy. This patch ensures that the head
> page is always used.
>
> This problem was originally identified by Joonsoo Kim.
>
> [js1304@...il.com: Original implementation and problem identification]
> Signed-off-by: Mel Gorman <mgorman@...e.de>
> ---
>  mm/slab.c |    4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/mm/slab.c b/mm/slab.c
> index 811af03..d34a903 100644
> --- a/mm/slab.c
> +++ b/mm/slab.c
> @@ -1000,7 +1000,7 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
>                 l3 = cachep->nodelists[numa_mem_id()];
>                 if (!list_empty(&l3->slabs_free) && force_refill) {
>                         struct slab *slabp = virt_to_slab(objp);
> -                       ClearPageSlabPfmemalloc(virt_to_page(slabp->s_mem));
> +                       ClearPageSlabPfmemalloc(virt_to_head_page(slabp->s_mem));
>                         clear_obj_pfmemalloc(&objp);
>                         recheck_pfmemalloc_active(cachep, ac);
>                         return objp;

We assume that slabp->s_mem's address is always in head page, so
"virt_to_head_page" is not needed.

> @@ -1032,7 +1032,7 @@ static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
>  {
>         if (unlikely(pfmemalloc_active)) {
>                 /* Some pfmemalloc slabs exist, check if this is one */
> -               struct page *page = virt_to_page(objp);
> +               struct page *page = virt_to_head_page(objp);
>                 if (PageSlabPfmemalloc(page))
>                         set_obj_pfmemalloc(&objp);
>         }
> --
> 1.7.9.2
>

If we always use head page, following suggestion is more good to me.
How about you?

diff --git a/mm/slab.c b/mm/slab.c
index f8b0d53..ce70989 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1032,7 +1032,7 @@ static void *__ac_put_obj(struct kmem_cache
*cachep, struct array_cache *ac,
 {
        if (unlikely(pfmemalloc_active)) {
                /* Some pfmemalloc slabs exist, check if this is one */
-               struct page *page = virt_to_page(objp);
+               struct page *page = virt_to_head_page(objp);
                if (PageSlabPfmemalloc(page))
                        set_obj_pfmemalloc(&objp);
        }
@@ -1921,10 +1921,9 @@ static void *kmem_getpages(struct kmem_cache
*cachep, gfp_t flags, int nodeid)
                        NR_SLAB_UNRECLAIMABLE, nr_pages);
        for (i = 0; i < nr_pages; i++) {
                __SetPageSlab(page + i);
-
-               if (page->pfmemalloc)
-                       SetPageSlabPfmemalloc(page + i);
        }
+       if (page->pfmemalloc)
+               SetPageSlabPfmemalloc(page);

        if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) {
                kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid);
@@ -1943,26 +1942,26 @@ static void *kmem_getpages(struct kmem_cache
*cachep, gfp_t flags, int nodeid)
  */
 static void kmem_freepages(struct kmem_cache *cachep, void *addr)
 {
-       unsigned long i = (1 << cachep->gfporder);
+       int nr_pages = (1 << cachep->gfporder);
+       int i;
        struct page *page = virt_to_page(addr);
-       const unsigned long nr_freed = i;

        kmemcheck_free_shadow(page, cachep->gfporder);

        if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
                sub_zone_page_state(page_zone(page),
-                               NR_SLAB_RECLAIMABLE, nr_freed);
+                               NR_SLAB_RECLAIMABLE, nr_pages);
        else
                sub_zone_page_state(page_zone(page),
-                               NR_SLAB_UNRECLAIMABLE, nr_freed);
-       while (i--) {
-               BUG_ON(!PageSlab(page));
-               __ClearPageSlabPfmemalloc(page);
-               __ClearPageSlab(page);
-               page++;
+                               NR_SLAB_UNRECLAIMABLE, nr_pages);
+       for (i = 0; i < nr_pages; i++) {
+               BUG_ON(!PageSlab(page + i));
+               __ClearPageSlab(page + i);
        }
+       __ClearPageSlabPfmemalloc(page);
+
        if (current->reclaim_state)
-               current->reclaim_state->reclaimed_slab += nr_freed;
+               current->reclaim_state->reclaimed_slab += nr_pages;
        free_pages((unsigned long)addr, cachep->gfporder);
 }
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html