diff mbox series

[net,v3,3/3] ice: avoid premature Rx buffer reuse

Message ID 20200825172736.27318-4-bjorn.topel@gmail.com
State New
Headers show
Series None | expand

Commit Message

Björn Töpel Aug. 25, 2020, 5:27 p.m. UTC
From: Björn Töpel <bjorn.topel@intel.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: efc2214b6047 ("ice: Add support for XDP")
Reported-and-analyzed-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 30 ++++++++++++++++-------
 1 file changed, 21 insertions(+), 9 deletions(-)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 9d0d6b0025cf..61279adf3561 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -762,13 +762,15 @@  ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size)
 /**
  * ice_can_reuse_rx_page - Determine if page can be reused for another Rx
  * @rx_buf: buffer containing the page
+ * @rx_buf_pgcnt: rx_buf page refcount pre xdp_do_redirect() call
  *
  * If page is reusable, we have a green light for calling ice_reuse_rx_page,
  * which will assign the current buffer to the buffer that next_to_alloc is
  * pointing to; otherwise, the DMA mapping needs to be destroyed and
  * page freed
  */
-static bool ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf)
+static bool ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf,
+				  int rx_buf_pgcnt)
 {
 	unsigned int pagecnt_bias = rx_buf->pagecnt_bias;
 	struct page *page = rx_buf->page;
@@ -779,7 +781,7 @@  static bool ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf)
 
 #if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
-	if (unlikely((page_count(page) - pagecnt_bias) > 1))
+	if (unlikely((rx_buf_pgcnt - pagecnt_bias) > 1))
 		return false;
 #else
 #define ICE_LAST_OFFSET \
@@ -864,17 +866,25 @@  ice_reuse_rx_page(struct ice_ring *rx_ring, struct ice_rx_buf *old_buf)
  * @rx_ring: Rx descriptor ring to transact packets on
  * @skb: skb to be used
  * @size: size of buffer to add to skb
+ * @rx_buf_pgcnt: rx_buf page refcount
  *
  * This function will pull an Rx buffer from the ring and synchronize it
  * for use by the CPU.
  */
 static struct ice_rx_buf *
 ice_get_rx_buf(struct ice_ring *rx_ring, struct sk_buff **skb,
-	       const unsigned int size)
+	       const unsigned int size,
+	       int *rx_buf_pgcnt)
 {
 	struct ice_rx_buf *rx_buf;
 
 	rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean];
+	*rx_buf_pgcnt =
+#if (PAGE_SIZE < 8192)
+		page_count(rx_buf->page);
+#else
+		0;
+#endif
 	prefetchw(rx_buf->page);
 	*skb = rx_buf->skb;
 
@@ -1012,12 +1022,13 @@  ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
  * ice_put_rx_buf - Clean up used buffer and either recycle or free
  * @rx_ring: Rx descriptor ring to transact packets on
  * @rx_buf: Rx buffer to pull data from
+ * @rx_buf_pgcnt: Rx buffer page count pre xdp_do_redirect()
  *
  * This function will update next_to_clean and then clean up the contents
  * of the rx_buf. It will either recycle the buffer or unmap it and free
  * the associated resources.
  */
-static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
+static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, int rx_buf_pgcnt)
 {
 	u16 ntc = rx_ring->next_to_clean + 1;
 
@@ -1028,7 +1039,7 @@  static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
 	if (!rx_buf)
 		return;
 
-	if (ice_can_reuse_rx_page(rx_buf)) {
+	if (ice_can_reuse_rx_page(rx_buf, rx_buf_pgcnt)) {
 		/* hand second half of page back to the ring */
 		ice_reuse_rx_page(rx_ring, rx_buf);
 	} else {
@@ -1103,6 +1114,7 @@  int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		struct sk_buff *skb;
 		unsigned int size;
 		u16 stat_err_bits;
+		int rx_buf_pgcnt;
 		u16 vlan_tag = 0;
 		u8 rx_ptype;
 
@@ -1125,7 +1137,7 @@  int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		dma_rmb();
 
 		if (rx_desc->wb.rxdid == FDIR_DESC_RXDID || !rx_ring->netdev) {
-			ice_put_rx_buf(rx_ring, NULL);
+			ice_put_rx_buf(rx_ring, NULL, 0);
 			cleaned_count++;
 			continue;
 		}
@@ -1134,7 +1146,7 @@  int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 			ICE_RX_FLX_DESC_PKT_LEN_M;
 
 		/* retrieve a buffer from the ring */
-		rx_buf = ice_get_rx_buf(rx_ring, &skb, size);
+		rx_buf = ice_get_rx_buf(rx_ring, &skb, size, &rx_buf_pgcnt);
 
 		if (!size) {
 			xdp.data = NULL;
@@ -1174,7 +1186,7 @@  int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		total_rx_pkts++;
 
 		cleaned_count++;
-		ice_put_rx_buf(rx_ring, rx_buf);
+		ice_put_rx_buf(rx_ring, rx_buf, rx_buf_pgcnt);
 		continue;
 construct_skb:
 		if (skb) {
@@ -1193,7 +1205,7 @@  int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 			break;
 		}
 
-		ice_put_rx_buf(rx_ring, rx_buf);
+		ice_put_rx_buf(rx_ring, rx_buf, rx_buf_pgcnt);
 		cleaned_count++;
 
 		/* skip if it is NOP desc */