From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: [PATCH net 2/5] igb: fix race accessing page->_count Date: Thu, 9 Oct 2014 22:24:51 -0700 Message-ID: <1412918694-22882-3-git-send-email-edumazet@google.com> References: <1412918694-22882-1-git-send-email-edumazet@google.com> Cc: netdev@vger.kernel.org, Alexander Duyck , Andres Lagar-Cavilla , Greg Thelen , Hugh Dickins , David Rientjes , Eric Dumazet To: "David S. Miller" Return-path: Received: from mail-pa0-f73.google.com ([209.85.220.73]:53201 "EHLO mail-pa0-f73.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751644AbaJJFZE (ORCPT ); Fri, 10 Oct 2014 01:25:04 -0400 Received: by mail-pa0-f73.google.com with SMTP id et14so234692pad.4 for ; Thu, 09 Oct 2014 22:25:04 -0700 (PDT) In-Reply-To: <1412918694-22882-1-git-send-email-edumazet@google.com> Sender: netdev-owner@vger.kernel.org List-ID: This is illegal to use atomic_set(&page->_count, 2) even if we 'own' the page. Other entities in the kernel need to use get_page_unless_zero() to get a reference to the page before testing page properties, so we could loose a refcount increment. Signed-off-by: Eric Dumazet --- drivers/net/ethernet/intel/igb/igb_main.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index ae59c0b108c5..a21b14495ebd 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6545,11 +6545,10 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, /* flip page offset to other buffer */ rx_buffer->page_offset ^= IGB_RX_BUFSZ; - /* since we are the only owner of the page and we need to - * increment it, just set the value to 2 in order to avoid - * an unnecessary locked operation + /* Even if we own the page, we are not allowed to use atomic_set() + * This would break get_page_unless_zero() users. */ - atomic_set(&page->_count, 2); + atomic_inc(&page->_count); #else /* move offset up to the next cache line */ rx_buffer->page_offset += truesize; -- 2.1.0.rc2.206.gedb03e5