Netdev Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Boris Pismenny <borisp@nvidia.com>
To: <dsahern@gmail.com>, <kuba@kernel.org>, <davem@davemloft.net>,
	<saeedm@nvidia.com>, <hch@lst.de>, <sagi@grimberg.me>,
	<axboe@fb.com>, <kbusch@kernel.org>, <viro@zeniv.linux.org.uk>,
	<edumazet@google.com>, <smalin@marvell.com>
Cc: <boris.pismenny@gmail.com>, <linux-nvme@lists.infradead.org>,
	<netdev@vger.kernel.org>, <benishay@nvidia.com>,
	<ogerlitz@nvidia.com>, <yorayz@nvidia.com>,
	Boris Pismenny <borisp@mellanox.com>,
	Or Gerlitz <ogerlitz@mellanox.com>,
	Yoray Zack <yorayz@mellanox.com>
Subject: [PATCH v5 net-next 18/36] net/mlx5e: NVMEoTCP, data-path for DDP+DDGST offload
Date: Thu, 22 Jul 2021 14:03:07 +0300	[thread overview]
Message-ID: <20210722110325.371-19-borisp@nvidia.com> (raw)
In-Reply-To: <20210722110325.371-1-borisp@nvidia.com>

From: Ben Ben-Ishay <benishay@nvidia.com>

This patch implements the data-path for direct data placement (DDP)
and DDGST offloads. NVMEoTCP DDP constructs an SKB from each CQE, while
pointing at NVME destination buffers. In turn, this enables the offload,
as the NVMe-TCP layer will skip the copy when src == dst.

Additionally, this patch adds support for DDGST (CRC32) offload.
HW will report DDGST offload only if it has not encountered an error
in the received packet. We pass this indication in skb->ddp_crc
up the stack to NVMe-TCP to skip computing the DDGST if all
corresponding SKBs were verified by HW.

This patch also handles context resynchronization requests made by
NIC HW. The resync request is passed to the NVMe-TCP layer
to be handled at a later point in time.

Finally, we also use the skb->ddp_crc bit to avoid skb_condense.
This is critical as every SKB that uses DDP has a hole that fits
perfectly with skb_condense's policy, but filling this hole is
counter-productive as the data there already resides in its
destination buffer.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Yoray Zack <yorayz@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/Makefile  |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en.h  |   1 +
 .../ethernet/mellanox/mlx5/core/en/xsk/rx.c   |   1 +
 .../ethernet/mellanox/mlx5/core/en/xsk/rx.h   |   1 +
 .../mlx5/core/en_accel/nvmeotcp_rxtx.c        | 248 ++++++++++++++++++
 .../mlx5/core/en_accel/nvmeotcp_rxtx.h        |  43 +++
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   |  41 ++-
 7 files changed, 330 insertions(+), 7 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp_rxtx.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp_rxtx.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 0ae9e5e38ec7..992b396907ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -102,4 +102,4 @@ mlx5_core-$(CONFIG_MLX5_SF) += sf/vhca_event.o sf/dev/dev.o sf/dev/driver.o
 #
 mlx5_core-$(CONFIG_MLX5_SF_MANAGER) += sf/cmd.o sf/hw_table.o sf/devlink.o
 
-mlx5_core-$(CONFIG_MLX5_EN_NVMEOTCP) += en_accel/fs_tcp.o en_accel/nvmeotcp.o
+mlx5_core-$(CONFIG_MLX5_EN_NVMEOTCP) += en_accel/fs_tcp.o en_accel/nvmeotcp.o en_accel/nvmeotcp_rxtx.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index d88ecd04d5da..c87f32492ea4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -589,6 +589,7 @@ struct mlx5e_rq;
 typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq*, struct mlx5_cqe64*);
 typedef struct sk_buff *
 (*mlx5e_fp_skb_from_cqe_mpwrq)(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+			       struct mlx5_cqe64 *cqe,
 			       u16 cqe_bcnt, u32 head_offset, u32 page_idx);
 typedef struct sk_buff *
 (*mlx5e_fp_skb_from_cqe)(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
index 8e7b877d8a12..9a6fbd1b1c34 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
@@ -25,6 +25,7 @@ static struct sk_buff *mlx5e_xsk_construct_skb(struct mlx5e_rq *rq, void *data,
 
 struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 						    struct mlx5e_mpw_info *wi,
+						    struct mlx5_cqe64 *cqe,
 						    u16 cqe_bcnt,
 						    u32 head_offset,
 						    u32 page_idx)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
index 7f88ccf67fdd..112c5b3ec165 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
@@ -11,6 +11,7 @@
 
 struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 						    struct mlx5e_mpw_info *wi,
+						    struct mlx5_cqe64 *cqe,
 						    u16 cqe_bcnt,
 						    u32 head_offset,
 						    u32 page_idx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp_rxtx.c
new file mode 100644
index 000000000000..31586f574fc0
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp_rxtx.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2021 Mellanox Technologies. */
+
+#include "en_accel/nvmeotcp_rxtx.h"
+#include "en_accel/nvmeotcp.h"
+#include <linux/mlx5/mlx5_ifc.h>
+
+#define	MLX5E_TC_FLOW_ID_MASK  0x00ffffff
+static void nvmeotcp_update_resync(struct mlx5e_nvmeotcp_queue *queue,
+				   struct mlx5e_cqe128 *cqe128)
+{
+	const struct ulp_ddp_ulp_ops *ulp_ops;
+	u32 seq;
+
+	seq = be32_to_cpu(cqe128->resync_tcp_sn);
+	ulp_ops = inet_csk(queue->sk)->icsk_ulp_ddp_ops;
+	if (ulp_ops && ulp_ops->resync_request)
+		ulp_ops->resync_request(queue->sk, seq, ULP_DDP_RESYNC_REQ);
+}
+
+static void mlx5e_nvmeotcp_advance_sgl_iter(struct mlx5e_nvmeotcp_queue *queue)
+{
+	struct nvmeotcp_queue_entry *nqe = &queue->ccid_table[queue->ccid];
+
+	queue->ccoff += nqe->sgl[queue->ccsglidx].length;
+	queue->ccoff_inner = 0;
+	queue->ccsglidx++;
+}
+
+static inline void
+mlx5e_nvmeotcp_add_skb_frag(struct net_device *netdev, struct sk_buff *skb,
+			    struct mlx5e_nvmeotcp_queue *queue,
+			    struct nvmeotcp_queue_entry *nqe, u32 fragsz)
+{
+	dma_sync_single_for_cpu(&netdev->dev,
+				nqe->sgl[queue->ccsglidx].offset + queue->ccoff_inner,
+				fragsz, DMA_FROM_DEVICE);
+	page_ref_inc(compound_head(sg_page(&nqe->sgl[queue->ccsglidx])));
+	// XXX: consider reducing the truesize, as no new memory is consumed
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+			sg_page(&nqe->sgl[queue->ccsglidx]),
+			nqe->sgl[queue->ccsglidx].offset + queue->ccoff_inner,
+			fragsz,
+			fragsz);
+}
+
+static struct sk_buff*
+mlx5_nvmeotcp_add_tail_nonlinear(struct mlx5e_nvmeotcp_queue *queue,
+				 struct sk_buff *skb, skb_frag_t *org_frags,
+				 int org_nr_frags, int frag_index)
+{
+	struct mlx5e_priv *priv = queue->priv;
+
+	while (org_nr_frags != frag_index) {
+		if (skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS) {
+			dev_kfree_skb_any(skb);
+			return NULL;
+		}
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+				skb_frag_page(&org_frags[frag_index]),
+				skb_frag_off(&org_frags[frag_index]),
+				skb_frag_size(&org_frags[frag_index]),
+				skb_frag_size(&org_frags[frag_index]));
+		page_ref_inc(skb_frag_page(&org_frags[frag_index]));
+		frag_index++;
+	}
+	return skb;
+}
+
+static struct sk_buff*
+mlx5_nvmeotcp_add_tail(struct mlx5e_nvmeotcp_queue *queue, struct sk_buff *skb,
+		       int offset, int len)
+{
+	struct mlx5e_priv *priv = queue->priv;
+
+	if (skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS) {
+		dev_kfree_skb_any(skb);
+		return NULL;
+	}
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+			virt_to_page(skb->data),
+			offset,
+			len,
+			len);
+	page_ref_inc(virt_to_page(skb->data));
+	return skb;
+}
+
+static void mlx5_nvmeotcp_trim_nonlinear(struct sk_buff *skb,
+					 skb_frag_t *org_frags,
+					 int *frag_index,
+					 int remaining)
+{
+	unsigned int frag_size;
+	int nr_frags;
+
+	/* skip @remaining bytes in frags */
+	*frag_index = 0;
+	while (remaining) {
+		frag_size = skb_frag_size(&skb_shinfo(skb)->frags[*frag_index]);
+		if (frag_size > remaining) {
+			skb_frag_off_add(&skb_shinfo(skb)->frags[*frag_index],
+					 remaining);
+			skb_frag_size_sub(&skb_shinfo(skb)->frags[*frag_index],
+					  remaining);
+			remaining = 0;
+		} else {
+			remaining -= frag_size;
+			skb_frag_unref(skb, *frag_index);
+			*frag_index += 1;
+		}
+	}
+
+	/* save original frags for the tail and unref */
+	nr_frags = skb_shinfo(skb)->nr_frags;
+	memcpy(&org_frags[*frag_index], &skb_shinfo(skb)->frags[*frag_index],
+	       (nr_frags - *frag_index) * sizeof(skb_frag_t));
+	while (--nr_frags >= *frag_index)
+		skb_frag_unref(skb, nr_frags);
+
+	/* remove frags from skb */
+	skb_shinfo(skb)->nr_frags = 0;
+	skb->len -= skb->data_len;
+	skb->truesize -= skb->data_len;
+	skb->data_len = 0;
+}
+
+struct sk_buff*
+mlx5e_nvmeotcp_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
+			     struct mlx5_cqe64 *cqe, u32 cqe_bcnt,
+			     bool linear)
+{
+	int ccoff, cclen, hlen, ccid, remaining, fragsz, to_copy = 0;
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	skb_frag_t org_frags[MAX_SKB_FRAGS];
+	struct mlx5e_nvmeotcp_queue *queue;
+	struct nvmeotcp_queue_entry *nqe;
+	int org_nr_frags, frag_index;
+	struct mlx5e_cqe128 *cqe128;
+	u32 queue_id;
+
+	queue_id = (be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK);
+	queue = mlx5e_nvmeotcp_get_queue(priv->nvmeotcp, queue_id);
+	if (unlikely(!queue)) {
+		dev_kfree_skb_any(skb);
+		return NULL;
+	}
+
+	cqe128 = container_of(cqe, struct mlx5e_cqe128, cqe64);
+	if (cqe_is_nvmeotcp_resync(cqe)) {
+		nvmeotcp_update_resync(queue, cqe128);
+		mlx5e_nvmeotcp_put_queue(queue);
+		return skb;
+	}
+
+	/* If a resync occurred in the previous cqe,
+	 * the current cqe.crcvalid bit may not be valid,
+	 * so we will treat it as 0
+	 */
+	if (unlikely(queue->after_resync_cqe)) {
+		skb->ddp_crc = 0;
+		queue->after_resync_cqe = 0;
+	} else {
+		if (queue->crc_rx)
+			skb->ddp_crc = cqe_is_nvmeotcp_crcvalid(cqe);
+		else
+			skb->ddp_crc = cqe_is_nvmeotcp_zc(cqe);
+	}
+
+	if (!cqe_is_nvmeotcp_zc(cqe)) {
+		mlx5e_nvmeotcp_put_queue(queue);
+		return skb;
+	}
+
+	/* cc ddp from cqe */
+	ccid = be16_to_cpu(cqe128->ccid);
+	ccoff = be32_to_cpu(cqe128->ccoff);
+	cclen = be16_to_cpu(cqe128->cclen);
+	hlen  = be16_to_cpu(cqe128->hlen);
+
+	/* carve a hole in the skb for DDP data */
+	if (linear) {
+		skb_trim(skb, hlen);
+	} else {
+		org_nr_frags = skb_shinfo(skb)->nr_frags;
+		mlx5_nvmeotcp_trim_nonlinear(skb, org_frags, &frag_index,
+					     cclen);
+	}
+
+	nqe = &queue->ccid_table[ccid];
+
+	/* packet starts new ccid? */
+	if (queue->ccid != ccid || queue->ccid_gen != nqe->ccid_gen) {
+		queue->ccid = ccid;
+		queue->ccoff = 0;
+		queue->ccoff_inner = 0;
+		queue->ccsglidx = 0;
+		queue->ccid_gen = nqe->ccid_gen;
+	}
+
+	/* skip inside cc until the ccoff in the cqe */
+	while (queue->ccoff + queue->ccoff_inner < ccoff) {
+		remaining = nqe->sgl[queue->ccsglidx].length - queue->ccoff_inner;
+		fragsz = min_t(off_t, remaining,
+			       ccoff - (queue->ccoff + queue->ccoff_inner));
+
+		if (fragsz == remaining)
+			mlx5e_nvmeotcp_advance_sgl_iter(queue);
+		else
+			queue->ccoff_inner += fragsz;
+	}
+
+	/* adjust the skb according to the cqe cc */
+	while (to_copy < cclen) {
+		if (skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS) {
+			dev_kfree_skb_any(skb);
+			mlx5e_nvmeotcp_put_queue(queue);
+			return NULL;
+		}
+
+		remaining = nqe->sgl[queue->ccsglidx].length - queue->ccoff_inner;
+		fragsz = min_t(int, remaining, cclen - to_copy);
+
+		mlx5e_nvmeotcp_add_skb_frag(netdev, skb, queue, nqe, fragsz);
+		to_copy += fragsz;
+		if (fragsz == remaining)
+			mlx5e_nvmeotcp_advance_sgl_iter(queue);
+		else
+			queue->ccoff_inner += fragsz;
+	}
+
+	if (cqe_bcnt > hlen + cclen) {
+		remaining = cqe_bcnt - hlen - cclen;
+		if (linear)
+			skb = mlx5_nvmeotcp_add_tail(queue, skb,
+						     offset_in_page(skb->data) +
+								hlen + cclen,
+						     remaining);
+		else
+			skb = mlx5_nvmeotcp_add_tail_nonlinear(queue, skb,
+							       org_frags,
+							       org_nr_frags,
+							       frag_index);
+	}
+
+	mlx5e_nvmeotcp_put_queue(queue);
+	return skb;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp_rxtx.h
new file mode 100644
index 000000000000..65456b46c33f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp_rxtx.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021 Mellanox Technologies. */
+#ifndef __MLX5E_NVMEOTCP_RXTX_H__
+#define __MLX5E_NVMEOTCP_RXTX_H__
+
+#ifdef CONFIG_MLX5_EN_NVMEOTCP
+
+#include <linux/skbuff.h>
+#include "en.h"
+
+struct sk_buff*
+mlx5e_nvmeotcp_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
+			     struct mlx5_cqe64 *cqe, u32 cqe_bcnt, bool linear);
+
+static inline int mlx5_nvmeotcp_get_headlen(struct mlx5_cqe64 *cqe, u32 cqe_bcnt)
+{
+	struct mlx5e_cqe128 *cqe128;
+
+	if (!cqe_is_nvmeotcp_zc(cqe) || cqe_is_nvmeotcp_resync(cqe))
+		return cqe_bcnt;
+
+	cqe128 = container_of(cqe, struct mlx5e_cqe128, cqe64);
+	return be16_to_cpu(cqe128->hlen);
+}
+
+#else
+static inline struct sk_buff*
+mlx5e_nvmeotcp_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
+			     struct mlx5_cqe64 *cqe, u32 cqe_bcnt, bool linear)
+{ return skb; }
+
+static inline int mlx5_nvmeotcp_get_headlen(struct mlx5_cqe64 *cqe, u32 cqe_bcnt)
+{ return cqe_bcnt; }
+
+#endif /* CONFIG_MLX5_EN_NVMEOTCP */
+
+static inline u16 mlx5e_get_headlen_hint(struct mlx5_cqe64 *cqe, u32 cqe_bcnt)
+{
+	return min_t(u32, MLX5E_RX_MAX_HEAD, mlx5_nvmeotcp_get_headlen(cqe, cqe_bcnt));
+}
+
+
+#endif /* __MLX5E_NVMEOTCP_RXTX_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index e92dd4666955..8a20a5800e20 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -48,6 +48,7 @@
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/tls_rxtx.h"
 #include "en_accel/nvmeotcp.h"
+#include "en_accel/nvmeotcp_rxtx.h"
 #include "en/xdp.h"
 #include "en/xsk/rx.h"
 #include "en/health.h"
@@ -57,9 +58,11 @@
 
 static struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+				struct mlx5_cqe64 *cqe,
 				u16 cqe_bcnt, u32 head_offset, u32 page_idx);
 static struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+				   struct mlx5_cqe64 *cqe,
 				   u16 cqe_bcnt, u32 head_offset, u32 page_idx);
 static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
@@ -1186,6 +1189,12 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	/* queue up for recycling/reuse */
 	page_ref_inc(di->page);
 
+#ifdef CONFIG_MLX5_EN_NVMEOTCP
+	if (cqe_is_nvmeotcp(cqe))
+		skb = mlx5e_nvmeotcp_handle_rx_skb(rq->netdev, skb, cqe,
+						   cqe_bcnt, true);
+#endif
+
 	return skb;
 }
 
@@ -1194,8 +1203,8 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 			     struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt)
 {
 	struct mlx5e_rq_frag_info *frag_info = &rq->wqe.info.arr[0];
+	u16 headlen = mlx5e_get_headlen_hint(cqe, cqe_bcnt);
 	struct mlx5e_wqe_frag_info *head_wi = wi;
-	u16 headlen      = min_t(u32, MLX5E_RX_MAX_HEAD, cqe_bcnt);
 	u16 frag_headlen = headlen;
 	u16 byte_cnt     = cqe_bcnt - headlen;
 	struct sk_buff *skb;
@@ -1204,7 +1213,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	 * might spread among multiple pages.
 	 */
 	skb = napi_alloc_skb(rq->cq.napi,
-			     ALIGN(MLX5E_RX_MAX_HEAD, sizeof(long)));
+			     ALIGN(headlen, sizeof(long)));
 	if (unlikely(!skb)) {
 		rq->stats->buff_alloc_err++;
 		return NULL;
@@ -1230,6 +1239,12 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	skb->tail += headlen;
 	skb->len  += headlen;
 
+#ifdef CONFIG_MLX5_EN_NVMEOTCP
+	if (cqe_is_nvmeotcp(cqe))
+		skb = mlx5e_nvmeotcp_handle_rx_skb(rq->netdev, skb, cqe,
+						   cqe_bcnt, false);
+#endif
+
 	return skb;
 }
 
@@ -1389,7 +1404,7 @@ static void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, struct mlx5_cqe64
 	skb = INDIRECT_CALL_2(rq->mpwqe.skb_from_cqe_mpwrq,
 			      mlx5e_skb_from_cqe_mpwrq_linear,
 			      mlx5e_skb_from_cqe_mpwrq_nonlinear,
-			      rq, wi, cqe_bcnt, head_offset, page_idx);
+			      rq, wi, cqe, cqe_bcnt, head_offset, page_idx);
 	if (!skb)
 		goto mpwrq_cqe_out;
 
@@ -1423,17 +1438,18 @@ const struct mlx5e_rx_handlers mlx5e_rx_handlers_rep = {
 
 static struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+				   struct mlx5_cqe64 *cqe,
 				   u16 cqe_bcnt, u32 head_offset, u32 page_idx)
 {
-	u16 headlen = min_t(u16, MLX5E_RX_MAX_HEAD, cqe_bcnt);
 	struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx];
+	u16 headlen = mlx5e_get_headlen_hint(cqe, cqe_bcnt);
 	u32 frag_offset    = head_offset + headlen;
 	u32 byte_cnt       = cqe_bcnt - headlen;
 	struct mlx5e_dma_info *head_di = di;
 	struct sk_buff *skb;
 
 	skb = napi_alloc_skb(rq->cq.napi,
-			     ALIGN(MLX5E_RX_MAX_HEAD, sizeof(long)));
+			     ALIGN(headlen, sizeof(long)));
 	if (unlikely(!skb)) {
 		rq->stats->buff_alloc_err++;
 		return NULL;
@@ -1464,11 +1480,18 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	skb->tail += headlen;
 	skb->len  += headlen;
 
+#ifdef CONFIG_MLX5_EN_NVMEOTCP
+	if (cqe_is_nvmeotcp(cqe))
+		skb = mlx5e_nvmeotcp_handle_rx_skb(rq->netdev, skb, cqe,
+						   cqe_bcnt, false);
+#endif
+
 	return skb;
 }
 
 static struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+				struct mlx5_cqe64 *cqe,
 				u16 cqe_bcnt, u32 head_offset, u32 page_idx)
 {
 	struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx];
@@ -1510,6 +1533,12 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 	/* queue up for recycling/reuse */
 	page_ref_inc(di->page);
 
+#ifdef CONFIG_MLX5_EN_NVMEOTCP
+	if (cqe_is_nvmeotcp(cqe))
+		skb = mlx5e_nvmeotcp_handle_rx_skb(rq->netdev, skb, cqe,
+						   cqe_bcnt, true);
+#endif
+
 	return skb;
 }
 
@@ -1548,7 +1577,7 @@ static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cq
 	skb = INDIRECT_CALL_2(rq->mpwqe.skb_from_cqe_mpwrq,
 			      mlx5e_skb_from_cqe_mpwrq_linear,
 			      mlx5e_skb_from_cqe_mpwrq_nonlinear,
-			      rq, wi, cqe_bcnt, head_offset, page_idx);
+			      rq, wi, cqe, cqe_bcnt, head_offset, page_idx);
 	if (!skb)
 		goto mpwrq_cqe_out;
 
-- 
2.24.1


  parent reply	other threads:[~2021-07-22 11:05 UTC|newest]

Thread overview: 62+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-22 11:02 [PATCH v5 net-next 00/36] nvme-tcp receive and tarnsmit offloads Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 01/36] net: Introduce direct data placement tcp offload Boris Pismenny
2021-07-22 11:26   ` Eric Dumazet
2021-07-22 12:18     ` Boris Pismenny
2021-07-22 13:10       ` Eric Dumazet
2021-07-22 13:33         ` Boris Pismenny
2021-07-22 13:39           ` Eric Dumazet
2021-07-22 14:02             ` Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 02/36] iov_iter: DDP copy to iter/pages Boris Pismenny
2021-07-22 13:31   ` Christoph Hellwig
2021-07-22 20:23     ` Boris Pismenny
2021-07-23  5:03       ` Christoph Hellwig
2021-07-23  5:21         ` Al Viro
2021-08-04 14:13           ` Or Gerlitz
2021-08-10 13:29             ` Or Gerlitz
2021-07-22 20:55   ` Al Viro
2021-07-22 11:02 ` [PATCH v5 net-next 03/36] net: skb copy(+hash) iterators for DDP offloads Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 04/36] net/tls: expose get_netdev_for_sock Boris Pismenny
2021-07-23  6:06   ` Christoph Hellwig
2021-08-04 13:26     ` Or Gerlitz
     [not found]       ` <20210804072918.17ba9cff@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com>
2021-08-04 15:07         ` Or Gerlitz
2021-08-10 13:25           ` Or Gerlitz
2021-07-22 11:02 ` [PATCH v5 net-next 05/36] nvme-tcp: Add DDP offload control path Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 06/36] nvme-tcp: Add DDP data-path Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 07/36] nvme-tcp: RX DDGST offload Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 08/36] nvme-tcp: Deal with netdevice DOWN events Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 09/36] net/mlx5: Header file changes for nvme-tcp offload Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 10/36] net/mlx5: Add 128B CQE for NVMEoTCP offload Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 11/36] net/mlx5e: TCP flow steering for nvme-tcp Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 12/36] net/mlx5e: NVMEoTCP offload initialization Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 13/36] net/mlx5e: KLM UMR helper macros Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 14/36] net/mlx5e: NVMEoTCP use KLM UMRs Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 15/36] net/mlx5e: NVMEoTCP queue init/teardown Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 16/36] net/mlx5e: NVMEoTCP async ddp invalidation Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 17/36] net/mlx5e: NVMEoTCP ddp setup and resync Boris Pismenny
2021-07-22 11:03 ` Boris Pismenny [this message]
2021-07-22 11:03 ` [PATCH v5 net-next 19/36] net/mlx5e: NVMEoTCP statistics Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 20/36] Documentation: add ULP DDP offload documentation Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 21/36] net: drop ULP DDP HW offload feature if no CSUM offload feature Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 22/36] net: Add ulp_ddp_pdu_info struct Boris Pismenny
2021-07-23 19:42   ` Sagi Grimberg
2021-07-22 11:03 ` [PATCH v5 net-next 23/36] net: Add to ulp_ddp support for fallback flow Boris Pismenny
2021-07-23  6:09   ` Christoph Hellwig
2021-07-22 11:03 ` [PATCH v5 net-next 24/36] net: Add MSG_DDP_CRC flag Boris Pismenny
2021-07-22 14:23   ` Eric Dumazet
2021-07-22 11:03 ` [PATCH v5 net-next 25/36] nvme-tcp: TX DDGST offload Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 26/36] nvme-tcp: Mapping between Tx NVMEoTCP pdu and TCP sequence Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 27/36] mlx5e: make preparation in TLS code for NVMEoTCP CRC Tx offload Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 28/36] mlx5: Add sq state test bit for nvmeotcp Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 29/36] mlx5: Add support to NETIF_F_HW_TCP_DDP_CRC_TX feature Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 30/36] net/mlx5e: NVMEoTCP DDGST TX offload TIS Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 31/36] net/mlx5e: NVMEoTCP DDGST Tx offload queue init/teardown Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 32/36] net/mlx5e: NVMEoTCP DDGST TX BSF and PSV Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 33/36] net/mlx5e: NVMEoTCP DDGST TX Data path Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 34/36] net/mlx5e: NVMEoTCP DDGST TX handle OOO packets Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 35/36] net/mlx5e: NVMEoTCP DDGST TX offload optimization Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 36/36] net/mlx5e: NVMEoTCP DDGST TX statistics Boris Pismenny
2021-07-23  5:56 ` [PATCH v5 net-next 00/36] nvme-tcp receive and tarnsmit offloads Christoph Hellwig
2021-07-23 19:58   ` Sagi Grimberg
2021-08-04 13:51     ` Or Gerlitz
2021-08-06 19:46       ` Sagi Grimberg
2021-08-10 13:37         ` Or Gerlitz

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

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210722110325.371-19-borisp@nvidia.com \
    --to=borisp@nvidia.com \
    --cc=axboe@fb.com \
    --cc=benishay@nvidia.com \
    --cc=boris.pismenny@gmail.com \
    --cc=borisp@mellanox.com \
    --cc=davem@davemloft.net \
    --cc=dsahern@gmail.com \
    --cc=edumazet@google.com \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=kuba@kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=netdev@vger.kernel.org \
    --cc=ogerlitz@mellanox.com \
    --cc=ogerlitz@nvidia.com \
    --cc=saeedm@nvidia.com \
    --cc=sagi@grimberg.me \
    --cc=smalin@marvell.com \
    --cc=viro@zeniv.linux.org.uk \
    --cc=yorayz@mellanox.com \
    --cc=yorayz@nvidia.com \
    --subject='Re: [PATCH v5 net-next 18/36] net/mlx5e: NVMEoTCP, data-path for DDP+DDGST offload' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).