igc: Fix HW RX timestamp when passed by ZC XDP

[PATCH] igc: Fix HW RX timestamp when passed by ZC XDP

Posted by Zdenek Bouska 1 year ago

Fixes HW RX timestamp in the following scenario:
- AF_PACKET socket with enabled HW RX timestamps is created
- AF_XDP socket with enabled zero copy is created
- frame is forwarded to the BPF program, where the timestamp should
  still be readable (extracted by igc_xdp_rx_timestamp(), kfunc
  behind bpf_xdp_metadata_rx_timestamp())
- the frame got XDP_PASS from BPF program, redirecting to the stack
- AF_PACKET socket receives the frame with HW RX timestamp

Moves the skb timestamp setting from igc_dispatch_skb_zc() to
igc_construct_skb_zc() so that igc_construct_skb_zc() is similar to
igc_construct_skb().

This issue can also be reproduced by running:
 # tools/testing/selftests/bpf/xdp_hw_metadata enp1s0
When a frame with the wrong port 9092 (instead of 9091) is used:
 # echo -n xdp | nc -u -q1 192.168.10.9 9092
then the RX timestamp is missing and xdp_hw_metadata prints:
 skb hwtstamp is not found!

With this fix or when copy mode is used:
 # tools/testing/selftests/bpf/xdp_hw_metadata -c enp1s0
then RX timestamp is found and xdp_hw_metadata prints:
 found skb hwtstamp = 1736509937.852786132

Fixes: 069b142f5819 ("igc: Add support for PTP .getcyclesx64()")
Signed-off-by: Zdenek Bouska <zdenek.bouska@siemens.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 27872bdea9bd..d6c3147725b7 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2707,8 +2707,9 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 }
 
 static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring,
-					    struct xdp_buff *xdp)
+					    struct igc_xdp_buff *ctx)
 {
+	struct xdp_buff *xdp = &ctx->xdp;
 	unsigned int totalsize = xdp->data_end - xdp->data_meta;
 	unsigned int metasize = xdp->data - xdp->data_meta;
 	struct sk_buff *skb;
@@ -2727,27 +2728,28 @@ static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring,
 		__skb_pull(skb, metasize);
 	}
 
+	if (ctx->rx_ts) {
+		skb_shinfo(skb)->tx_flags |= SKBTX_HW_TSTAMP_NETDEV;
+		skb_hwtstamps(skb)->netdev_data = ctx->rx_ts;
+	}
+
 	return skb;
 }
 
 static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector,
 				union igc_adv_rx_desc *desc,
-				struct xdp_buff *xdp,
-				ktime_t timestamp)
+				struct igc_xdp_buff *ctx)
 {
 	struct igc_ring *ring = q_vector->rx.ring;
 	struct sk_buff *skb;
 
-	skb = igc_construct_skb_zc(ring, xdp);
+	skb = igc_construct_skb_zc(ring, ctx);
 	if (!skb) {
 		ring->rx_stats.alloc_failed++;
 		set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &ring->flags);
 		return;
 	}
 
-	if (timestamp)
-		skb_hwtstamps(skb)->hwtstamp = timestamp;
-
 	if (igc_cleanup_headers(ring, desc, skb))
 		return;
 
@@ -2783,7 +2785,6 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 		union igc_adv_rx_desc *desc;
 		struct igc_rx_buffer *bi;
 		struct igc_xdp_buff *ctx;
-		ktime_t timestamp = 0;
 		unsigned int size;
 		int res;
 
@@ -2813,6 +2814,8 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 			 */
 			bi->xdp->data_meta += IGC_TS_HDR_LEN;
 			size -= IGC_TS_HDR_LEN;
+		} else {
+			ctx->rx_ts = NULL;
 		}
 
 		bi->xdp->data_end = bi->xdp->data + size;
@@ -2821,7 +2824,7 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 		res = __igc_xdp_run_prog(adapter, prog, bi->xdp);
 		switch (res) {
 		case IGC_XDP_PASS:
-			igc_dispatch_skb_zc(q_vector, desc, bi->xdp, timestamp);
+			igc_dispatch_skb_zc(q_vector, desc, ctx);
 			fallthrough;
 		case IGC_XDP_CONSUMED:
 			xsk_buff_free(bi->xdp);

---
base-commit: ffd294d346d185b70e28b1a28abe367bbfe53c04
change-id: 20250128-igc-fix-hw-rx-timestamp-when-passed-by-zc-xdp-95dea010ff14

Best regards,
-- 
Zdenek Bouska

Siemens, s.r.o.
Foundational Technologies

Re: [Intel-wired-lan] [PATCH] igc: Fix HW RX timestamp when passed by ZC XDP

Posted by Mor Bar-Gabay 1 year ago

On 28/01/2025 14:26, Zdenek Bouska wrote:
> Fixes HW RX timestamp in the following scenario:
> - AF_PACKET socket with enabled HW RX timestamps is created
> - AF_XDP socket with enabled zero copy is created
> - frame is forwarded to the BPF program, where the timestamp should
>    still be readable (extracted by igc_xdp_rx_timestamp(), kfunc
>    behind bpf_xdp_metadata_rx_timestamp())
> - the frame got XDP_PASS from BPF program, redirecting to the stack
> - AF_PACKET socket receives the frame with HW RX timestamp
> 
> Moves the skb timestamp setting from igc_dispatch_skb_zc() to
> igc_construct_skb_zc() so that igc_construct_skb_zc() is similar to
> igc_construct_skb().
> 
> This issue can also be reproduced by running:
>   # tools/testing/selftests/bpf/xdp_hw_metadata enp1s0
> When a frame with the wrong port 9092 (instead of 9091) is used:
>   # echo -n xdp | nc -u -q1 192.168.10.9 9092
> then the RX timestamp is missing and xdp_hw_metadata prints:
>   skb hwtstamp is not found!
> 
> With this fix or when copy mode is used:
>   # tools/testing/selftests/bpf/xdp_hw_metadata -c enp1s0
> then RX timestamp is found and xdp_hw_metadata prints:
>   found skb hwtstamp = 1736509937.852786132
> 
> Fixes: 069b142f5819 ("igc: Add support for PTP .getcyclesx64()")
> Signed-off-by: Zdenek Bouska <zdenek.bouska@siemens.com>
> Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
> Reviewed-by: Simon Horman <horms@kernel.org>
> Reviewed-by: Florian Bezdeka <florian.bezdeka@siemens.com>
> Reviewed-by: Song Yoong Siang <yoong.siang.song@intel.com>
> ---
>   drivers/net/ethernet/intel/igc/igc_main.c | 21 ++++++++++++---------
>   1 file changed, 12 insertions(+), 9 deletions(-)
> 
Tested-by: Mor Bar-Gabay <morx.bar.gabay@intel.com>

RE: [PATCH] igc: Fix HW RX timestamp when passed by ZC XDP

Posted by Song, Yoong Siang 1 year ago

On Tuesday, January 28, 2025 8:27 PM, Zdenek Bouska <zdenek.bouska@siemens.com> wrote:
>Fixes HW RX timestamp in the following scenario:
>- AF_PACKET socket with enabled HW RX timestamps is created
>- AF_XDP socket with enabled zero copy is created
>- frame is forwarded to the BPF program, where the timestamp should
>  still be readable (extracted by igc_xdp_rx_timestamp(), kfunc
>  behind bpf_xdp_metadata_rx_timestamp())
>- the frame got XDP_PASS from BPF program, redirecting to the stack
>- AF_PACKET socket receives the frame with HW RX timestamp
>
>Moves the skb timestamp setting from igc_dispatch_skb_zc() to
>igc_construct_skb_zc() so that igc_construct_skb_zc() is similar to
>igc_construct_skb().
>
>This issue can also be reproduced by running:
> # tools/testing/selftests/bpf/xdp_hw_metadata enp1s0
>When a frame with the wrong port 9092 (instead of 9091) is used:
> # echo -n xdp | nc -u -q1 192.168.10.9 9092
>then the RX timestamp is missing and xdp_hw_metadata prints:
> skb hwtstamp is not found!
>
>With this fix or when copy mode is used:
> # tools/testing/selftests/bpf/xdp_hw_metadata -c enp1s0
>then RX timestamp is found and xdp_hw_metadata prints:
> found skb hwtstamp = 1736509937.852786132
>
>Fixes: 069b142f5819 ("igc: Add support for PTP .getcyclesx64()")
>Signed-off-by: Zdenek Bouska <zdenek.bouska@siemens.com>

This patch LGTM and tested working on my side with xdp_hw_metadata
self-test app on XDP_PASS scenario.
Thanks for the patch.
	
Reviewed-by: Song Yoong Siang <yoong.siang.song@intel.com>

Re: [PATCH] igc: Fix HW RX timestamp when passed by ZC XDP

Posted by Florian Bezdeka 1 year ago

On Tue, 2025-01-28 at 13:26 +0100, Zdenek Bouska wrote:
> Fixes HW RX timestamp in the following scenario:
> - AF_PACKET socket with enabled HW RX timestamps is created
> - AF_XDP socket with enabled zero copy is created
> - frame is forwarded to the BPF program, where the timestamp should
>   still be readable (extracted by igc_xdp_rx_timestamp(), kfunc
>   behind bpf_xdp_metadata_rx_timestamp())
> - the frame got XDP_PASS from BPF program, redirecting to the stack
> - AF_PACKET socket receives the frame with HW RX timestamp
> 
> Moves the skb timestamp setting from igc_dispatch_skb_zc() to
> igc_construct_skb_zc() so that igc_construct_skb_zc() is similar to
> igc_construct_skb().
> 
> This issue can also be reproduced by running:
>  # tools/testing/selftests/bpf/xdp_hw_metadata enp1s0
> When a frame with the wrong port 9092 (instead of 9091) is used:
>  # echo -n xdp | nc -u -q1 192.168.10.9 9092
> then the RX timestamp is missing and xdp_hw_metadata prints:
>  skb hwtstamp is not found!
> 
> With this fix or when copy mode is used:
>  # tools/testing/selftests/bpf/xdp_hw_metadata -c enp1s0
> then RX timestamp is found and xdp_hw_metadata prints:
>  found skb hwtstamp = 1736509937.852786132
> 
> Fixes: 069b142f5819 ("igc: Add support for PTP .getcyclesx64()")
> Signed-off-by: Zdenek Bouska <zdenek.bouska@siemens.com>
> ---

Reviewed-by: Florian Bezdeka <florian.bezdeka@siemens.com>

Re: [PATCH] igc: Fix HW RX timestamp when passed by ZC XDP

Posted by Simon Horman 1 year ago

On Tue, Jan 28, 2025 at 01:26:48PM +0100, Zdenek Bouska wrote:
> Fixes HW RX timestamp in the following scenario:
> - AF_PACKET socket with enabled HW RX timestamps is created
> - AF_XDP socket with enabled zero copy is created
> - frame is forwarded to the BPF program, where the timestamp should
>   still be readable (extracted by igc_xdp_rx_timestamp(), kfunc
>   behind bpf_xdp_metadata_rx_timestamp())
> - the frame got XDP_PASS from BPF program, redirecting to the stack
> - AF_PACKET socket receives the frame with HW RX timestamp
> 
> Moves the skb timestamp setting from igc_dispatch_skb_zc() to
> igc_construct_skb_zc() so that igc_construct_skb_zc() is similar to
> igc_construct_skb().
> 
> This issue can also be reproduced by running:
>  # tools/testing/selftests/bpf/xdp_hw_metadata enp1s0
> When a frame with the wrong port 9092 (instead of 9091) is used:
>  # echo -n xdp | nc -u -q1 192.168.10.9 9092
> then the RX timestamp is missing and xdp_hw_metadata prints:
>  skb hwtstamp is not found!
> 
> With this fix or when copy mode is used:
>  # tools/testing/selftests/bpf/xdp_hw_metadata -c enp1s0
> then RX timestamp is found and xdp_hw_metadata prints:
>  found skb hwtstamp = 1736509937.852786132
> 
> Fixes: 069b142f5819 ("igc: Add support for PTP .getcyclesx64()")
> Signed-off-by: Zdenek Bouska <zdenek.bouska@siemens.com>

Reviewed-by: Simon Horman <horms@kernel.org>

Re: [PATCH] igc: Fix HW RX timestamp when passed by ZC XDP

Posted by Vinicius Costa Gomes 1 year ago

Zdenek Bouska <zdenek.bouska@siemens.com> writes:

> Fixes HW RX timestamp in the following scenario:
> - AF_PACKET socket with enabled HW RX timestamps is created
> - AF_XDP socket with enabled zero copy is created
> - frame is forwarded to the BPF program, where the timestamp should
>   still be readable (extracted by igc_xdp_rx_timestamp(), kfunc
>   behind bpf_xdp_metadata_rx_timestamp())
> - the frame got XDP_PASS from BPF program, redirecting to the stack
> - AF_PACKET socket receives the frame with HW RX timestamp
>
> Moves the skb timestamp setting from igc_dispatch_skb_zc() to
> igc_construct_skb_zc() so that igc_construct_skb_zc() is similar to
> igc_construct_skb().
>
> This issue can also be reproduced by running:
>  # tools/testing/selftests/bpf/xdp_hw_metadata enp1s0
> When a frame with the wrong port 9092 (instead of 9091) is used:
>  # echo -n xdp | nc -u -q1 192.168.10.9 9092
> then the RX timestamp is missing and xdp_hw_metadata prints:
>  skb hwtstamp is not found!
>
> With this fix or when copy mode is used:
>  # tools/testing/selftests/bpf/xdp_hw_metadata -c enp1s0
> then RX timestamp is found and xdp_hw_metadata prints:
>  found skb hwtstamp = 1736509937.852786132
>
> Fixes: 069b142f5819 ("igc: Add support for PTP .getcyclesx64()")
> Signed-off-by: Zdenek Bouska <zdenek.bouska@siemens.com>

Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>


Cheers,
-- 
Vinicius