netdev - [PATCH net 2/3] ixgbe: avoid premature Rx buffer reuse

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: <20200825091629.12949-3-bjorn.topel@gmail.com>
Date:   Tue, 25 Aug 2020 11:16:28 +0200
From:   Björn Töpel <bjorn.topel@...il.com>
To:     jeffrey.t.kirsher@...el.com, intel-wired-lan@...ts.osuosl.org
Cc:     Björn Töpel <bjorn.topel@...el.com>,
        magnus.karlsson@...el.com, magnus.karlsson@...il.com,
        netdev@...r.kernel.org, maciej.fijalkowski@...el.com,
        piotr.raczynski@...el.com, maciej.machnikowski@...el.com,
        lirongqing@...du.com
Subject: [PATCH net 2/3] ixgbe: avoid premature Rx buffer reuse

From: Björn Töpel <bjorn.topel@...el.com>

The page recycle code, incorrectly, relied on that a page fragment
could not be freed inside xdp_do_redirect(). This assumption leads to
that page fragments that are used by the stack/XDP redirect can be
reused and overwritten.

To avoid this, store the page count prior invoking xdp_do_redirect().

Fixes: 6453073987ba ("ixgbe: add initial support for xdp redirect")
Signed-off-by: Björn Töpel <bjorn.topel@...el.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 28 ++++++++++++++-----
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 2f8a4cfc5fa1..fb5c311d72b6 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1945,7 +1945,8 @@ static inline bool ixgbe_page_is_reserved(struct page *page)
 	return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page);
 }
 
-static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer)
+static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer,
+				    int rx_buffer_pgcnt)
 {
 	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
 	struct page *page = rx_buffer->page;
@@ -1956,7 +1957,7 @@ static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer)
 
 #if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
-	if (unlikely((page_ref_count(page) - pagecnt_bias) > 1))
+	if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1))
 		return false;
 #else
 	/* The last offset is a bit aggressive in that we assume the
@@ -2018,14 +2019,25 @@ static void ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
 #endif
 }
 
+static int ixgbe_rx_buffer_page_count(struct ixgbe_rx_buffer *rx_buffer)
+{
+#if (PAGE_SIZE < 8192)
+	return page_count(rx_buffer->page);
+#else
+	return 0;
+#endif
+}
+
 static struct ixgbe_rx_buffer *ixgbe_get_rx_buffer(struct ixgbe_ring *rx_ring,
 						   union ixgbe_adv_rx_desc *rx_desc,
 						   struct sk_buff **skb,
-						   const unsigned int size)
+						   const unsigned int size,
+						   int *rx_buffer_pgcnt)
 {
 	struct ixgbe_rx_buffer *rx_buffer;
 
 	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
+	*rx_buffer_pgcnt = ixgbe_rx_buffer_page_count(rx_buffer);
 	prefetchw(rx_buffer->page);
 	*skb = rx_buffer->skb;
 
@@ -2055,9 +2067,10 @@ static struct ixgbe_rx_buffer *ixgbe_get_rx_buffer(struct ixgbe_ring *rx_ring,
 
 static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring,
 				struct ixgbe_rx_buffer *rx_buffer,
-				struct sk_buff *skb)
+				struct sk_buff *skb,
+				int rx_buffer_pgcnt)
 {
-	if (ixgbe_can_reuse_rx_page(rx_buffer)) {
+	if (ixgbe_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) {
 		/* hand second half of page back to the ring */
 		ixgbe_reuse_rx_page(rx_ring, rx_buffer);
 	} else {
@@ -2296,6 +2309,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 	u16 cleaned_count = ixgbe_desc_unused(rx_ring);
 	unsigned int xdp_xmit = 0;
 	struct xdp_buff xdp;
+	int rx_buffer_pgcnt;
 
 	xdp.rxq = &rx_ring->xdp_rxq;
 
@@ -2327,7 +2341,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		 */
 		dma_rmb();
 
-		rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size);
+		rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size, &rx_buffer_pgcnt);
 
 		/* retrieve a buffer from the ring */
 		if (!skb) {
@@ -2372,7 +2386,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 			break;
 		}
 
-		ixgbe_put_rx_buffer(rx_ring, rx_buffer, skb);
+		ixgbe_put_rx_buffer(rx_ring, rx_buffer, skb, rx_buffer_pgcnt);
 		cleaned_count++;
 
 		/* place incomplete frames back on ring for completion */
-- 
2.25.1