@@ -98,4 +98,4 @@ 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
@@ -577,6 +577,7 @@ 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,
@@ -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)
@@ -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);
new file mode 100644
@@ -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 tcp_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, TCP_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;
+}
new file mode 100644
@@ -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__ */
@@ -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 "lib/clock.h"
#include "en/xdp.h"
#include "en/xsk/rx.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);
@@ -1185,6 +1188,12 @@ 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;
}
@@ -1193,8 +1202,8 @@ 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;
@@ -1203,7 +1212,7 @@ 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;
@@ -1229,6 +1238,12 @@ 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;
}
@@ -1383,7 +1398,7 @@ 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;
@@ -1414,17 +1429,18 @@ 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;
@@ -1455,11 +1471,18 @@ 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];
@@ -1501,6 +1524,12 @@ 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;
}
@@ -1539,7 +1568,7 @@ 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;