net: stmmac: fix the crash issue for zero copy XDP_TX action

[PATCH net] net: stmmac: fix the crash issue for zero copy XDP_TX action

Posted by Wei Fang 2 weeks, 1 day ago

There is a crash issue when running zero copy XDP_TX action, the crash
log is shown below.

[  216.122464] Unable to handle kernel paging request at virtual address fffeffff80000000
[  216.187524] Internal error: Oops: 0000000096000144 [#1]  SMP
[  216.301694] Call trace:
[  216.304130]  dcache_clean_poc+0x20/0x38 (P)
[  216.308308]  __dma_sync_single_for_device+0x1bc/0x1e0
[  216.313351]  stmmac_xdp_xmit_xdpf+0x354/0x400
[  216.317701]  __stmmac_xdp_run_prog+0x164/0x368
[  216.322139]  stmmac_napi_poll_rxtx+0xba8/0xf00
[  216.326576]  __napi_poll+0x40/0x218
[  216.408054] Kernel panic - not syncing: Oops: Fatal exception in interrupt

For XDP_TX action, the xdp_buff is converted to xdp_frame by
xdp_convert_buff_to_frame(). The memory type of the resulting xdp_frame
depends on the memory type of the xdp_buff. For page pool based xdp_buff
it produces xdp_frame with memory type MEM_TYPE_PAGE_POOL. For zero copy
XSK pool based xdp_buff it produces xdp_frame with memory type
MEM_TYPE_PAGE_ORDER0. However, stmmac_xdp_xmit_back() does not check the
memory type and always uses the page pool type, this leads to invalid
mappings and causes the crash. Therefore, check the xdp_buff memory type
in stmmac_xdp_xmit_back() to fix this issue.

Fixes: bba2556efad6 ("net: stmmac: Enable RX via AF_XDP zero-copy")
Signed-off-by: Wei Fang <wei.fang@nxp.com>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c   | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 7b90ecd3a55e..a6664f300e4a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -88,6 +88,7 @@ MODULE_PARM_DESC(phyaddr, "Physical device address");
 #define STMMAC_XDP_CONSUMED	BIT(0)
 #define STMMAC_XDP_TX		BIT(1)
 #define STMMAC_XDP_REDIRECT	BIT(2)
+#define STMMAC_XSK_CONSUMED	BIT(3)
 
 static int flow_ctrl = 0xdead;
 module_param(flow_ctrl, int, 0644);
@@ -4988,6 +4989,7 @@ static int stmmac_xdp_get_tx_queue(struct stmmac_priv *priv,
 static int stmmac_xdp_xmit_back(struct stmmac_priv *priv,
 				struct xdp_buff *xdp)
 {
+	bool zc = !!(xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL);
 	struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
 	int cpu = smp_processor_id();
 	struct netdev_queue *nq;
@@ -5004,9 +5006,18 @@ static int stmmac_xdp_xmit_back(struct stmmac_priv *priv,
 	/* Avoids TX time-out as we are sharing with slow path */
 	txq_trans_cond_update(nq);
 
-	res = stmmac_xdp_xmit_xdpf(priv, queue, xdpf, false);
-	if (res == STMMAC_XDP_TX)
+	/* For zero copy XDP_TX action, dma_map is true */
+	res = stmmac_xdp_xmit_xdpf(priv, queue, xdpf, zc);
+	if (res == STMMAC_XDP_TX) {
 		stmmac_flush_tx_descriptors(priv, queue);
+	} else if (res == STMMAC_XDP_CONSUMED && zc) {
+		/* xdp has been freed by xdp_convert_buff_to_frame(),
+		 * no need to call xsk_buff_free() again, so return
+		 * STMMAC_XSK_CONSUMED.
+		 */
+		res = STMMAC_XSK_CONSUMED;
+		xdp_return_frame(xdpf);
+	}
 
 	__netif_tx_unlock(nq);
 
@@ -5356,6 +5367,8 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue)
 			break;
 		case STMMAC_XDP_CONSUMED:
 			xsk_buff_free(buf->xdp);
+			fallthrough;
+		case STMMAC_XSK_CONSUMED:
 			rx_dropped++;
 			break;
 		case STMMAC_XDP_TX:
-- 
2.34.1

Re: [PATCH net] net: stmmac: fix the crash issue for zero copy XDP_TX action

Posted by Hariprasad Kelam 2 days, 6 hours ago

On 2025-12-04 at 12:43:32, Wei Fang (wei.fang@nxp.com) wrote:
> There is a crash issue when running zero copy XDP_TX action, the crash
> log is shown below.
> 
> [  216.122464] Unable to handle kernel paging request at virtual address fffeffff80000000
> [  216.187524] Internal error: Oops: 0000000096000144 [#1]  SMP
> [  216.301694] Call trace:
> [  216.304130]  dcache_clean_poc+0x20/0x38 (P)
> [  216.308308]  __dma_sync_single_for_device+0x1bc/0x1e0
> [  216.313351]  stmmac_xdp_xmit_xdpf+0x354/0x400
> [  216.317701]  __stmmac_xdp_run_prog+0x164/0x368
> [  216.322139]  stmmac_napi_poll_rxtx+0xba8/0xf00
> [  216.326576]  __napi_poll+0x40/0x218
> [  216.408054] Kernel panic - not syncing: Oops: Fatal exception in interrupt
> 
> For XDP_TX action, the xdp_buff is converted to xdp_frame by
> xdp_convert_buff_to_frame(). The memory type of the resulting xdp_frame
> depends on the memory type of the xdp_buff. For page pool based xdp_buff
> it produces xdp_frame with memory type MEM_TYPE_PAGE_POOL. For zero copy
> XSK pool based xdp_buff it produces xdp_frame with memory type
> MEM_TYPE_PAGE_ORDER0. However, stmmac_xdp_xmit_back() does not check the
> memory type and always uses the page pool type, this leads to invalid
> mappings and causes the crash. Therefore, check the xdp_buff memory type
> in stmmac_xdp_xmit_back() to fix this issue.
> 
> Fixes: bba2556efad6 ("net: stmmac: Enable RX via AF_XDP zero-copy")
> Signed-off-by: Wei Fang <wei.fang@nxp.com>
> ---
>  .../net/ethernet/stmicro/stmmac/stmmac_main.c   | 17 +++++++++++++++--
>  1 file changed, 15 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> index 7b90ecd3a55e..a6664f300e4a 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> @@ -88,6 +88,7 @@ MODULE_PARM_DESC(phyaddr, "Physical device address");
>  #define STMMAC_XDP_CONSUMED	BIT(0)
>  #define STMMAC_XDP_TX		BIT(1)
>  #define STMMAC_XDP_REDIRECT	BIT(2)
> +#define STMMAC_XSK_CONSUMED	BIT(3)
>  
>  static int flow_ctrl = 0xdead;
>  module_param(flow_ctrl, int, 0644);
> @@ -4988,6 +4989,7 @@ static int stmmac_xdp_get_tx_queue(struct stmmac_priv *priv,
>  static int stmmac_xdp_xmit_back(struct stmmac_priv *priv,
>  				struct xdp_buff *xdp)
>  {
> +	bool zc = !!(xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL);
>  	struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
>  	int cpu = smp_processor_id();
>  	struct netdev_queue *nq;
> @@ -5004,9 +5006,18 @@ static int stmmac_xdp_xmit_back(struct stmmac_priv *priv,
>  	/* Avoids TX time-out as we are sharing with slow path */
>  	txq_trans_cond_update(nq);
>  
> -	res = stmmac_xdp_xmit_xdpf(priv, queue, xdpf, false);
> -	if (res == STMMAC_XDP_TX)
> +	/* For zero copy XDP_TX action, dma_map is true */
> +	res = stmmac_xdp_xmit_xdpf(priv, queue, xdpf, zc);
	Seems stmmac_xdp_xmit_xdpf is using dma_map_single if we pass zc is true.
        Ideally in case of zc, driver can use page_pool_get_dma_addr, may be you
        need pass zc param as false. Please check

Thanks,
Hariprasad k