Netdev Archive on lore.kernel.org
help / color / mirror / Atom feed
* [PATCH 1/1 v3] skbuff: Fix a potential race while recycling page_pool packets
@ 2021-07-16  7:02 Ilias Apalodimas
  2021-07-16 18:50 ` patchwork-bot+netdevbpf
  0 siblings, 1 reply; 2+ messages in thread
From: Ilias Apalodimas @ 2021-07-16  7:02 UTC (permalink / raw)
  To: netdev
  Cc: linyunsheng, Ilias Apalodimas, Alexander Duyck,
	Jesper Dangaard Brouer, David S. Miller, Jakub Kicinski,
	Alexander Lobakin, Jonathan Lemon, Willem de Bruijn, Miaohe Lin,
	Guillaume Nault, Cong Wang, Matteo Croce, linux-kernel

As Alexander points out, when we are trying to recycle a cloned/expanded
SKB we might trigger a race.  The recycling code relies on the
pp_recycle bit to trigger,  which we carry over to cloned SKBs.
If that cloned SKB gets expanded or if we get references to the frags,
call skb_release_data() and overwrite skb->head, we are creating separate
instances accessing the same page frags.  Since the skb_release_data()
will first try to recycle the frags,  there's a potential race between
the original and cloned SKB, since both will have the pp_recycle bit set.

Fix this by explicitly those SKBs not recyclable.
The atomic_sub_return effectively limits us to a single release case,
and when we are calling skb_release_data we are also releasing the
option to perform the recycling, or releasing the pages from the page pool.

Fixes: 6a5bcd84e886 ("page_pool: Allow drivers to hint on SKB recycling")
Reported-by: Alexander Duyck <alexanderduyck@fb.com>
Suggested-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
---
Changes since v1:
- Set the recycle bit to 0 during skb_release_data instead of the
  individual fucntions triggering the issue, in order to catch all
  cases
Changes since v2:
- Add a comment explaining why we need to reset the recycling bit
 net/core/skbuff.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 12aabcda6db2..8ec5c1136692 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -663,7 +663,7 @@ static void skb_release_data(struct sk_buff *skb)
 	if (skb->cloned &&
 	    atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
 			      &shinfo->dataref))
-		return;
+		goto exit;
 
 	skb_zcopy_clear(skb, true);
 
@@ -674,6 +674,17 @@ static void skb_release_data(struct sk_buff *skb)
 		kfree_skb_list(shinfo->frag_list);
 
 	skb_free_head(skb);
+exit:
+	/* When we clone an SKB we copy the reycling bit. The pp_recycle
+	 * bit is only set on the head though, so in order to avoid races
+	 * while trying to recycle fragments on __skb_frag_unref() we need
+	 * to make one SKB responsible for triggering the recycle path.
+	 * So disable the recycling bit if an SKB is cloned and we have
+	 * additional references to to the fragmented part of the SKB.
+	 * Eventually the last SKB will have the recycling bit set and it's
+	 * dataref set to 0, which will trigger the recycling
+	 */
+	skb->pp_recycle = 0;
 }
 
 /*
-- 
2.32.0.rc0


^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2021-07-16 18:50 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-07-16  7:02 [PATCH 1/1 v3] skbuff: Fix a potential race while recycling page_pool packets Ilias Apalodimas
2021-07-16 18:50 ` patchwork-bot+netdevbpf

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).