From: Björn Töpel <bjorn.topel@xxxxxxxxx>
[ Upstream commit 75aab4e10ae6a4593a60f66d13de755d4e91f400 ]
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().
Longer explanation:
Intel NICs have a recycle mechanism. The main idea is that a page is
split into two parts. One part is owned by the driver, one part might
be owned by someone else, such as the stack.
t0: Page is allocated, and put on the Rx ring
+---------------
used by NIC ->| upper buffer
(rx_buffer) +---------------
| lower buffer
+---------------
page count == USHRT_MAX
rx_buffer->pagecnt_bias == USHRT_MAX
t1: Buffer is received, and passed to the stack (e.g.)
+---------------
| upper buff (skb)
+---------------
used by NIC ->| lower buffer
(rx_buffer) +---------------
page count == USHRT_MAX
rx_buffer->pagecnt_bias == USHRT_MAX - 1
t2: Buffer is received, and redirected
+---------------
| upper buff (skb)
+---------------
used by NIC ->| lower buffer
(rx_buffer) +---------------
Now, prior calling xdp_do_redirect():
page count == USHRT_MAX
rx_buffer->pagecnt_bias == USHRT_MAX - 2
This means that buffer *cannot* be flipped/reused, because the skb is
still using it.
The problem arises when xdp_do_redirect() actually frees the
segment. Then we get:
page count == USHRT_MAX - 1
rx_buffer->pagecnt_bias == USHRT_MAX - 2
>From a recycle perspective, the buffer can be flipped and reused,
which means that the skb data area is passed to the Rx HW ring!
To work around this, the page count is stored prior calling
xdp_do_redirect().
Note that this is not optimal, since the NIC could actually reuse the
"lower buffer" again. However, then we need to track whether
XDP_REDIRECT consumed the buffer or not.
Fixes: d9314c474d4f ("i40e: add support for XDP_REDIRECT")
Reported-and-analyzed-by: Li RongQing <lirongqing@xxxxxxxxx>
Signed-off-by: Björn Töpel <bjorn.topel@xxxxxxxxx>
Tested-by: George Kuruvinakunnel <george.kuruvinakunnel@xxxxxxxxx>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@xxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 27 +++++++++++++++------
1 file changed, 20 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 89a3be41d6d83..f47841f3a69d5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1869,6 +1869,7 @@ static inline bool i40e_page_is_reusable(struct page *page)
* the adapter for another receive
*
* @rx_buffer: buffer containing the page
+ * @rx_buffer_pgcnt: buffer page refcount pre xdp_do_redirect() call
*
* If page is reusable, rx_buffer->page_offset is adjusted to point to
* an unused region in the page.
@@ -1891,7 +1892,8 @@ static inline bool i40e_page_is_reusable(struct page *page)
*
* In either case, if the page is reusable its refcount is increased.
**/
-static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer)
+static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
+ int rx_buffer_pgcnt)
{
unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
struct page *page = rx_buffer->page;
@@ -1902,7 +1904,7 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer)
#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_buffer_pgcnt - pagecnt_bias) > 1))
return false;
#else
#define I40E_LAST_OFFSET \
@@ -1961,16 +1963,24 @@ static void i40e_add_rx_frag(struct i40e_ring *rx_ring,
* i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use
* @rx_ring: rx descriptor ring to transact packets on
* @size: size of buffer to add to skb
+ * @rx_buffer_pgcnt: buffer page refcount
*
* This function will pull an Rx buffer from the ring and synchronize it
* for use by the CPU.
*/
static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
- const unsigned int size)
+ const unsigned int size,
+ int *rx_buffer_pgcnt)
{
struct i40e_rx_buffer *rx_buffer;
rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
+ *rx_buffer_pgcnt =
+#if (PAGE_SIZE < 8192)
+ page_count(rx_buffer->page);
+#else
+ 0;
+#endif
prefetch_page_address(rx_buffer->page);
/* we are reusing so sync this buffer for CPU use */
@@ -2125,14 +2135,16 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
* i40e_put_rx_buffer - Clean up used buffer and either recycle or free
* @rx_ring: rx descriptor ring to transact packets on
* @rx_buffer: rx buffer to pull data from
+ * @rx_buffer_pgcnt: rx buffer page refcount pre xdp_do_redirect() call
*
* This function will clean up the contents of the rx_buffer. It will
* either recycle the buffer or unmap it and free the associated resources.
*/
static void i40e_put_rx_buffer(struct i40e_ring *rx_ring,
- struct i40e_rx_buffer *rx_buffer)
+ struct i40e_rx_buffer *rx_buffer,
+ int rx_buffer_pgcnt)
{
- if (i40e_can_reuse_rx_page(rx_buffer)) {
+ if (i40e_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) {
/* hand second half of page back to the ring */
i40e_reuse_rx_page(rx_ring, rx_buffer);
} else {
@@ -2345,6 +2357,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
while (likely(total_rx_packets < (unsigned int)budget)) {
struct i40e_rx_buffer *rx_buffer;
union i40e_rx_desc *rx_desc;
+ int rx_buffer_pgcnt;
unsigned int size;
u64 qword;
@@ -2384,7 +2397,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
break;
i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb);
- rx_buffer = i40e_get_rx_buffer(rx_ring, size);
+ rx_buffer = i40e_get_rx_buffer(rx_ring, size, &rx_buffer_pgcnt);
/* retrieve a buffer from the ring */
if (!skb) {
@@ -2424,7 +2437,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
break;
}
- i40e_put_rx_buffer(rx_ring, rx_buffer);
+ i40e_put_rx_buffer(rx_ring, rx_buffer, rx_buffer_pgcnt);
cleaned_count++;
if (i40e_is_non_eop(rx_ring, rx_desc, skb))
--
2.27.0
