From: Stanislav Fomichev <sdf@google.com>
To: bpf@vger.kernel.org
Cc: ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org,
martin.lau@linux.dev, song@kernel.org, yhs@fb.com,
john.fastabend@gmail.com, kpsingh@kernel.org, sdf@google.com,
haoluo@google.com, jolsa@kernel.org, kuba@kernel.org,
toke@kernel.org, willemb@google.com, dsahern@kernel.org,
magnus.karlsson@intel.com, bjorn@kernel.org,
maciej.fijalkowski@intel.com, hawk@kernel.org,
yoong.siang.song@intel.com, netdev@vger.kernel.org,
xdp-hints@xdp-project.net, Saeed Mahameed <saeedm@nvidia.com>
Subject: [xdp-hints] [PATCH bpf-next v4 04/11] net/mlx5e: Implement AF_XDP TX timestamp and checksum offload
Date: Thu, 19 Oct 2023 10:49:37 -0700 [thread overview]
Message-ID: <20231019174944.3376335-5-sdf@google.com> (raw)
In-Reply-To: <20231019174944.3376335-1-sdf@google.com>
TX timestamp:
- requires passing clock, not sure I'm passing the correct one (from
cq->mdev), but the timestamp value looks convincing
TX checksum:
- looks like device does packet parsing (and doesn't accept custom
start/offset), so I'm ignoring user offsets
Cc: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 4 +-
.../net/ethernet/mellanox/mlx5/core/en/xdp.c | 72 ++++++++++++++++---
.../net/ethernet/mellanox/mlx5/core/en/xdp.h | 11 ++-
.../ethernet/mellanox/mlx5/core/en/xsk/tx.c | 17 ++++-
.../net/ethernet/mellanox/mlx5/core/en_main.c | 1 +
5 files changed, 89 insertions(+), 16 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 2b3254e33fe5..695c609c4707 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -483,10 +483,12 @@ struct mlx5e_xdp_info_fifo {
struct mlx5e_xdpsq;
struct mlx5e_xmit_data;
+struct xsk_tx_metadata;
typedef int (*mlx5e_fp_xmit_xdp_frame_check)(struct mlx5e_xdpsq *);
typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq *,
struct mlx5e_xmit_data *,
- int);
+ int,
+ struct xsk_tx_metadata *);
struct mlx5e_xdpsq {
/* data path */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index cc3fcd24b36d..71df2f26812c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -103,7 +103,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
xdptxd->dma_addr = dma_addr;
if (unlikely(!INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe,
- mlx5e_xmit_xdp_frame, sq, xdptxd, 0)))
+ mlx5e_xmit_xdp_frame, sq, xdptxd, 0, NULL)))
return false;
/* xmit_mode == MLX5E_XDP_XMIT_MODE_FRAME */
@@ -145,7 +145,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
xdptxd->dma_addr = dma_addr;
if (unlikely(!INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe,
- mlx5e_xmit_xdp_frame, sq, xdptxd, 0)))
+ mlx5e_xmit_xdp_frame, sq, xdptxd, 0, NULL)))
return false;
/* xmit_mode == MLX5E_XDP_XMIT_MODE_PAGE */
@@ -261,6 +261,37 @@ const struct xdp_metadata_ops mlx5e_xdp_metadata_ops = {
.xmo_rx_hash = mlx5e_xdp_rx_hash,
};
+struct mlx5e_xsk_tx_complete {
+ struct mlx5_cqe64 *cqe;
+ struct mlx5e_cq *cq;
+};
+
+static u64 mlx5e_xsk_fill_timestamp(void *_priv)
+{
+ struct mlx5e_xsk_tx_complete *priv = _priv;
+ u64 ts;
+
+ ts = get_cqe_ts(priv->cqe);
+
+ if (mlx5_is_real_time_rq(priv->cq->mdev) || mlx5_is_real_time_sq(priv->cq->mdev))
+ return mlx5_real_time_cyc2time(&priv->cq->mdev->clock, ts);
+
+ return mlx5_timecounter_cyc2time(&priv->cq->mdev->clock, ts);
+}
+
+static void mlx5e_xsk_request_checksum(u16 csum_start, u16 csum_offset, void *priv)
+{
+ struct mlx5_wqe_eth_seg *eseg = priv;
+
+ /* HW/FW is doing parsing, so offsets are largely ignored. */
+ eseg->cs_flags |= MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM;
+}
+
+const struct xsk_tx_metadata_ops mlx5e_xsk_tx_metadata_ops = {
+ .tmo_fill_timestamp = mlx5e_xsk_fill_timestamp,
+ .tmo_request_checksum = mlx5e_xsk_request_checksum,
+};
+
/* returns true if packet was consumed by xdp */
bool mlx5e_xdp_handle(struct mlx5e_rq *rq,
struct bpf_prog *prog, struct mlx5e_xdp_buff *mxbuf)
@@ -398,11 +429,11 @@ INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq
INDIRECT_CALLABLE_SCOPE bool
mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
- int check_result);
+ int check_result, struct xsk_tx_metadata *meta);
INDIRECT_CALLABLE_SCOPE bool
mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
- int check_result)
+ int check_result, struct xsk_tx_metadata *meta)
{
struct mlx5e_tx_mpwqe *session = &sq->mpwqe;
struct mlx5e_xdpsq_stats *stats = sq->stats;
@@ -420,7 +451,7 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx
*/
if (unlikely(sq->mpwqe.wqe))
mlx5e_xdp_mpwqe_complete(sq);
- return mlx5e_xmit_xdp_frame(sq, xdptxd, 0);
+ return mlx5e_xmit_xdp_frame(sq, xdptxd, 0, meta);
}
if (!xdptxd->len) {
skb_frag_t *frag = &xdptxdf->sinfo->frags[0];
@@ -450,6 +481,7 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx
* and it's safe to complete it at any time.
*/
mlx5e_xdp_mpwqe_session_start(sq);
+ xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, &session->wqe->eth);
}
mlx5e_xdp_mpwqe_add_dseg(sq, p, stats);
@@ -480,7 +512,7 @@ INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq)
INDIRECT_CALLABLE_SCOPE bool
mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
- int check_result)
+ int check_result, struct xsk_tx_metadata *meta)
{
struct mlx5e_xmit_data_frags *xdptxdf =
container_of(xdptxd, struct mlx5e_xmit_data_frags, xd);
@@ -599,6 +631,8 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
sq->pc++;
}
+ xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, eseg);
+
sq->doorbell_cseg = cseg;
stats->xmit++;
@@ -608,7 +642,9 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
struct mlx5e_xdp_wqe_info *wi,
u32 *xsk_frames,
- struct xdp_frame_bulk *bq)
+ struct xdp_frame_bulk *bq,
+ struct mlx5e_cq *cq,
+ struct mlx5_cqe64 *cqe)
{
struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo;
u16 i;
@@ -668,10 +704,24 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
break;
}
- case MLX5E_XDP_XMIT_MODE_XSK:
+ case MLX5E_XDP_XMIT_MODE_XSK: {
/* AF_XDP send */
+ struct xsk_tx_metadata_compl *compl = NULL;
+ struct mlx5e_xsk_tx_complete priv = {
+ .cqe = cqe,
+ .cq = cq,
+ };
+
+ if (xp_tx_metadata_enabled(sq->xsk_pool)) {
+ xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo);
+ compl = &xdpi.xsk_meta;
+
+ xsk_tx_metadata_complete(compl, &mlx5e_xsk_tx_metadata_ops, &priv);
+ }
+
(*xsk_frames)++;
break;
+ }
default:
WARN_ON_ONCE(true);
}
@@ -720,7 +770,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
sqcc += wi->num_wqebbs;
- mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, &bq);
+ mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, &bq, cq, cqe);
} while (!last_wqe);
if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
@@ -767,7 +817,7 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
sq->cc += wi->num_wqebbs;
- mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, &bq);
+ mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, &bq, NULL, NULL);
}
xdp_flush_frame_bulk(&bq);
@@ -840,7 +890,7 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
}
ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe,
- mlx5e_xmit_xdp_frame, sq, xdptxd, 0);
+ mlx5e_xmit_xdp_frame, sq, xdptxd, 0, NULL);
if (unlikely(!ret)) {
int j;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index ecfe93a479da..e054db1e10f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -33,6 +33,7 @@
#define __MLX5_EN_XDP_H__
#include <linux/indirect_call_wrapper.h>
+#include <net/xdp_sock.h>
#include "en.h"
#include "en/txrx.h"
@@ -82,7 +83,7 @@ enum mlx5e_xdp_xmit_mode {
* num, page_1, page_2, ... , page_num.
*
* MLX5E_XDP_XMIT_MODE_XSK:
- * none.
+ * frame.xsk_meta.
*/
#define MLX5E_XDP_FIFO_ENTRIES2DS_MAX_RATIO 4
@@ -97,6 +98,7 @@ union mlx5e_xdp_info {
u8 num;
struct page *page;
} page;
+ struct xsk_tx_metadata_compl xsk_meta;
};
struct mlx5e_xsk_param;
@@ -112,13 +114,16 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
u32 flags);
extern const struct xdp_metadata_ops mlx5e_xdp_metadata_ops;
+extern const struct xsk_tx_metadata_ops mlx5e_xsk_tx_metadata_ops;
INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
struct mlx5e_xmit_data *xdptxd,
- int check_result));
+ int check_result,
+ struct xsk_tx_metadata *meta));
INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq,
struct mlx5e_xmit_data *xdptxd,
- int check_result));
+ int check_result,
+ struct xsk_tx_metadata *meta));
INDIRECT_CALLABLE_DECLARE(int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq));
INDIRECT_CALLABLE_DECLARE(int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index 597f319d4770..a59199ed590d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -55,12 +55,16 @@ static void mlx5e_xsk_tx_post_err(struct mlx5e_xdpsq *sq,
nopwqe = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, *xdpi);
+ if (xp_tx_metadata_enabled(sq->xsk_pool))
+ mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo,
+ (union mlx5e_xdp_info) { .xsk_meta = {} });
sq->doorbell_cseg = &nopwqe->ctrl;
}
bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
{
struct xsk_buff_pool *pool = sq->xsk_pool;
+ struct xsk_tx_metadata *meta = NULL;
union mlx5e_xdp_info xdpi;
bool work_done = true;
bool flush = false;
@@ -93,12 +97,13 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
xdptxd.dma_addr = xsk_buff_raw_get_dma(pool, desc.addr);
xdptxd.data = xsk_buff_raw_get_data(pool, desc.addr);
xdptxd.len = desc.len;
+ meta = xsk_buff_get_metadata(pool, desc.addr);
xsk_buff_raw_dma_sync_for_device(pool, xdptxd.dma_addr, xdptxd.len);
ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe,
mlx5e_xmit_xdp_frame, sq, &xdptxd,
- check_result);
+ check_result, meta);
if (unlikely(!ret)) {
if (sq->mpwqe.wqe)
mlx5e_xdp_mpwqe_complete(sq);
@@ -106,6 +111,16 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
mlx5e_xsk_tx_post_err(sq, &xdpi);
} else {
mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);
+ if (xp_tx_metadata_enabled(sq->xsk_pool)) {
+ struct xsk_tx_metadata_compl compl;
+
+ xsk_tx_metadata_to_compl(meta, &compl);
+ XSK_TX_COMPL_FITS(void *);
+
+ mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo,
+ (union mlx5e_xdp_info)
+ { .xsk_meta = compl });
+ }
}
flush = true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index afc3d488b8f6..70c7816c9177 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5160,6 +5160,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
netdev->netdev_ops = &mlx5e_netdev_ops;
netdev->xdp_metadata_ops = &mlx5e_xdp_metadata_ops;
+ netdev->xsk_tx_metadata_ops = &mlx5e_xsk_tx_metadata_ops;
mlx5e_dcbnl_build_netdev(netdev);
--
2.42.0.655.g421f12c284-goog
next prev parent reply other threads:[~2023-10-19 17:49 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-19 17:49 [xdp-hints] [PATCH bpf-next v4 00/11] xsk: TX metadata Stanislav Fomichev
2023-10-19 17:49 ` [xdp-hints] [PATCH bpf-next v4 01/11] xsk: Support tx_metadata_len Stanislav Fomichev
2023-10-20 14:29 ` [xdp-hints] " Song, Yoong Siang
2023-10-21 1:12 ` Jakub Kicinski
2023-10-23 17:33 ` Stanislav Fomichev
2023-10-23 8:28 ` Magnus Karlsson
2023-10-23 18:37 ` Stanislav Fomichev
2023-10-19 17:49 ` [xdp-hints] [PATCH bpf-next v4 02/11] xsk: Add TX timestamp and TX checksum offload support Stanislav Fomichev
2023-10-20 14:31 ` [xdp-hints] " Song, Yoong Siang
2023-10-20 17:49 ` Alexei Starovoitov
2023-10-20 18:06 ` Stanislav Fomichev
2023-10-21 1:04 ` Jakub Kicinski
2023-10-23 17:21 ` Stanislav Fomichev
2023-10-23 18:12 ` Jakub Kicinski
2023-10-23 18:46 ` Stanislav Fomichev
2023-10-19 17:49 ` [xdp-hints] [PATCH bpf-next v4 03/11] tools: ynl: Print xsk-features from the sample Stanislav Fomichev
2023-10-21 1:06 ` [xdp-hints] " Jakub Kicinski
2023-10-23 17:27 ` Stanislav Fomichev
2023-10-19 17:49 ` Stanislav Fomichev [this message]
2023-10-19 17:49 ` [xdp-hints] [PATCH bpf-next v4 05/11] net: stmmac: Add Tx HWTS support to XDP ZC Stanislav Fomichev
2023-10-19 17:49 ` [xdp-hints] [PATCH bpf-next v4 06/11] selftests/xsk: Support tx_metadata_len Stanislav Fomichev
2023-10-19 17:49 ` [xdp-hints] [PATCH bpf-next v4 07/11] selftests/bpf: Add csum helpers Stanislav Fomichev
2023-10-19 17:49 ` [xdp-hints] [PATCH bpf-next v4 08/11] selftests/bpf: Add TX side to xdp_metadata Stanislav Fomichev
2023-10-19 17:49 ` [xdp-hints] [PATCH bpf-next v4 09/11] selftests/bpf: Convert xdp_hw_metadata to XDP_USE_NEED_WAKEUP Stanislav Fomichev
2023-10-19 17:49 ` [xdp-hints] [PATCH bpf-next v4 10/11] selftests/bpf: Add TX side to xdp_hw_metadata Stanislav Fomichev
2023-10-24 2:19 ` [xdp-hints] " Song, Yoong Siang
2023-10-24 16:41 ` Stanislav Fomichev
2023-10-19 17:49 ` [xdp-hints] [PATCH bpf-next v4 11/11] xsk: Document tx_metadata_len layout Stanislav Fomichev
2023-10-23 9:19 ` [xdp-hints] " Magnus Karlsson
2023-10-23 18:31 ` Stanislav Fomichev
2023-10-23 9:52 ` [xdp-hints] Re: [PATCH bpf-next v4 00/11] xsk: TX metadata Magnus Karlsson
2023-10-23 18:38 ` Stanislav Fomichev
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: https://lists.xdp-project.net/postorius/lists/xdp-hints.xdp-project.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20231019174944.3376335-5-sdf@google.com \
--to=sdf@google.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bjorn@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=dsahern@kernel.org \
--cc=haoluo@google.com \
--cc=hawk@kernel.org \
--cc=john.fastabend@gmail.com \
--cc=jolsa@kernel.org \
--cc=kpsingh@kernel.org \
--cc=kuba@kernel.org \
--cc=maciej.fijalkowski@intel.com \
--cc=magnus.karlsson@intel.com \
--cc=martin.lau@linux.dev \
--cc=netdev@vger.kernel.org \
--cc=saeedm@nvidia.com \
--cc=song@kernel.org \
--cc=toke@kernel.org \
--cc=willemb@google.com \
--cc=xdp-hints@xdp-project.net \
--cc=yhs@fb.com \
--cc=yoong.siang.song@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox