[PATCH v2 net-next 15/21] net/mlx5e: NVMEoTCP use KLM UMRs
Boris Pismenny
borisp at mellanox.com
Thu Jan 14 10:10:27 EST 2021
From: Ben Ben-Ishay <benishay at nvidia.com>
NVMEoTCP offload uses buffer registration for ddp operation,
every request comprises from SG list that might have elements with size > 4K,
thus the appropriate way to perform buffer registration is with KLM UMRs.
Signed-off-by: Boris Pismenny <borisp at mellanox.com>
Signed-off-by: Ben Ben-Ishay <benishay at nvidia.com>
Signed-off-by: Or Gerlitz <ogerlitz at mellanox.com>
Signed-off-by: Yoray Zack <yorayz at mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 5 +-
.../net/ethernet/mellanox/mlx5/core/en/txrx.h | 3 +
.../mellanox/mlx5/core/en_accel/nvmeotcp.c | 116 ++++++++++++++++++
.../mlx5/core/en_accel/nvmeotcp_utils.h | 12 ++
.../net/ethernet/mellanox/mlx5/core/en_rx.c | 12 +-
5 files changed, 145 insertions(+), 3 deletions(-)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp_utils.h
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 26259d68b98a..dc6ebcfffb1b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -232,7 +232,10 @@ struct mlx5e_umr_wqe {
struct mlx5_wqe_ctrl_seg ctrl;
struct mlx5_wqe_umr_ctrl_seg uctrl;
struct mlx5_mkey_seg mkc;
- struct mlx5_mtt inline_mtts[0];
+ union {
+ struct mlx5_mtt inline_mtts[0];
+ struct mlx5_klm inline_klms[0];
+ };
};
extern const char mlx5e_self_tests[][ETH_GSTRING_LEN];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 7943eb30b837..bfeea906612e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -34,6 +34,9 @@ enum mlx5e_icosq_wqe_type {
MLX5E_ICOSQ_WQE_SET_PSV_TLS,
MLX5E_ICOSQ_WQE_GET_PSV_TLS,
#endif
+#ifdef CONFIG_MLX5_EN_NVMEOTCP
+ MLX5E_ICOSQ_WQE_UMR_NVME_TCP,
+#endif
};
/* General */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.c
index 0834deb7a3ac..bbeded08ef01 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.c
@@ -4,6 +4,7 @@
#include <linux/netdevice.h>
#include <linux/idr.h>
#include "en_accel/nvmeotcp.h"
+#include "en_accel/nvmeotcp_utils.h"
#include "en_accel/fs_tcp.h"
#include "en/txrx.h"
@@ -19,6 +20,121 @@ static const struct rhashtable_params rhash_queues = {
.max_size = MAX_NVMEOTCP_QUEUES,
};
+static void
+fill_nvmeotcp_klm_wqe(struct mlx5e_nvmeotcp_queue *queue,
+ struct mlx5e_umr_wqe *wqe, u16 ccid, u32 klm_entries,
+ u16 klm_offset)
+{
+ struct scatterlist *sgl_mkey;
+ u32 lkey, i;
+
+ lkey = queue->priv->mdev->mlx5e_res.mkey.key;
+ for (i = 0; i < klm_entries; i++) {
+ sgl_mkey = &queue->ccid_table[ccid].sgl[i + klm_offset];
+ wqe->inline_klms[i].bcount = cpu_to_be32(sgl_mkey->length);
+ wqe->inline_klms[i].key = cpu_to_be32(lkey);
+ wqe->inline_klms[i].va = cpu_to_be64(sgl_mkey->dma_address);
+ }
+
+ for (; i < ALIGN(klm_entries, KLM_ALIGNMENT); i++) {
+ wqe->inline_klms[i].bcount = 0;
+ wqe->inline_klms[i].key = 0;
+ wqe->inline_klms[i].va = 0;
+ }
+}
+
+static void
+build_nvmeotcp_klm_umr(struct mlx5e_nvmeotcp_queue *queue,
+ struct mlx5e_umr_wqe *wqe, u16 ccid, int klm_entries,
+ u32 klm_offset, u32 len)
+{
+ u32 id = queue->ccid_table[ccid].klm_mkey.key;
+ struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->uctrl;
+ struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
+ struct mlx5_mkey_seg *mkc = &wqe->mkc;
+
+ u32 sqn = queue->sq->icosq.sqn;
+ u16 pc = queue->sq->icosq.pc;
+
+ cseg->opmod_idx_opcode = cpu_to_be32((pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
+ MLX5_OPCODE_UMR);
+ cseg->qpn_ds = cpu_to_be32((sqn << MLX5_WQE_CTRL_QPN_SHIFT) |
+ MLX5E_KLM_UMR_DS_CNT(ALIGN(klm_entries, KLM_ALIGNMENT)));
+ cseg->general_id = cpu_to_be32(id);
+
+ if (!klm_offset) {
+ ucseg->mkey_mask |= cpu_to_be64(MLX5_MKEY_MASK_XLT_OCT_SIZE |
+ MLX5_MKEY_MASK_LEN | MLX5_MKEY_MASK_FREE);
+ mkc->xlt_oct_size = cpu_to_be32(ALIGN(len, KLM_ALIGNMENT));
+ mkc->len = cpu_to_be64(queue->ccid_table[ccid].size);
+ }
+
+ ucseg->flags = MLX5_UMR_INLINE | MLX5_UMR_TRANSLATION_OFFSET_EN;
+ ucseg->xlt_octowords = cpu_to_be16(ALIGN(klm_entries, KLM_ALIGNMENT));
+ ucseg->xlt_offset = cpu_to_be16(klm_offset);
+ fill_nvmeotcp_klm_wqe(queue, wqe, ccid, klm_entries, klm_offset);
+}
+
+static void
+mlx5e_nvmeotcp_fill_wi(struct mlx5e_nvmeotcp_queue *nvmeotcp_queue,
+ struct mlx5e_icosq *sq, u32 wqe_bbs, u16 pi)
+{
+ struct mlx5e_icosq_wqe_info *wi = &sq->db.wqe_info[pi];
+
+ wi->num_wqebbs = wqe_bbs;
+ wi->wqe_type = MLX5E_ICOSQ_WQE_UMR_NVME_TCP;
+}
+
+static void
+post_klm_wqe(struct mlx5e_nvmeotcp_queue *queue,
+ u16 ccid,
+ u32 klm_length,
+ u32 *klm_offset)
+{
+ struct mlx5e_icosq *sq = &queue->sq->icosq;
+ u32 wqe_bbs, cur_klm_entries;
+ struct mlx5e_umr_wqe *wqe;
+ u16 pi, wqe_sz;
+
+ cur_klm_entries = min_t(int, queue->max_klms_per_wqe,
+ klm_length - *klm_offset);
+ wqe_sz = MLX5E_KLM_UMR_WQE_SZ(ALIGN(cur_klm_entries, KLM_ALIGNMENT));
+ wqe_bbs = DIV_ROUND_UP(wqe_sz, MLX5_SEND_WQE_BB);
+ pi = mlx5e_icosq_get_next_pi(sq, wqe_bbs);
+ wqe = MLX5E_NVMEOTCP_FETCH_KLM_WQE(sq, pi);
+ mlx5e_nvmeotcp_fill_wi(queue, sq, wqe_bbs, pi);
+ build_nvmeotcp_klm_umr(queue, wqe, ccid, cur_klm_entries, *klm_offset,
+ klm_length);
+ *klm_offset += cur_klm_entries;
+ sq->pc += wqe_bbs;
+ sq->doorbell_cseg = &wqe->ctrl;
+}
+
+static int
+mlx5e_nvmeotcp_post_klm_wqe(struct mlx5e_nvmeotcp_queue *queue,
+ u16 ccid,
+ u32 klm_length)
+{
+ u32 klm_offset = 0, wqes, wqe_sz, max_wqe_bbs, i, room;
+ struct mlx5e_icosq *sq = &queue->sq->icosq;
+
+ /* TODO: set stricter wqe_sz; using max for now */
+ wqes = DIV_ROUND_UP(klm_length, queue->max_klms_per_wqe);
+ wqe_sz = MLX5E_KLM_UMR_WQE_SZ(queue->max_klms_per_wqe);
+
+ max_wqe_bbs = DIV_ROUND_UP(wqe_sz, MLX5_SEND_WQE_BB);
+
+ room = mlx5e_stop_room_for_wqe(max_wqe_bbs) * wqes;
+ if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, room)))
+ return -ENOSPC;
+
+ for (i = 0; i < wqes; i++)
+ post_klm_wqe(queue, ccid, klm_length, &klm_offset);
+
+ mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, sq->doorbell_cseg);
+ return 0;
+}
+
static int
mlx5e_nvmeotcp_offload_limits(struct net_device *netdev,
struct tcp_ddp_limits *limits)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp_utils.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp_utils.h
new file mode 100644
index 000000000000..329e114d6571
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp_utils.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021 Mellanox Technologies. */
+#ifndef __MLX5E_NVMEOTCP_UTILS_H__
+#define __MLX5E_NVMEOTCP_UTILS_H__
+
+#include "en.h"
+
+#define MLX5E_NVMEOTCP_FETCH_KLM_WQE(sq, pi) \
+ ((struct mlx5e_umr_wqe *)\
+ mlx5e_fetch_wqe(&(sq)->wq, pi, sizeof(struct mlx5e_umr_wqe)))
+
+#endif /* __MLX5E_NVMEOTCP_UTILS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 377e547840f3..28aa99265c0a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -617,16 +617,20 @@ void mlx5e_free_icosq_descs(struct mlx5e_icosq *sq)
ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
wi = &sq->db.wqe_info[ci];
sqcc += wi->num_wqebbs;
-#ifdef CONFIG_MLX5_EN_TLS
switch (wi->wqe_type) {
+#ifdef CONFIG_MLX5_EN_TLS
case MLX5E_ICOSQ_WQE_SET_PSV_TLS:
mlx5e_ktls_handle_ctx_completion(wi);
break;
case MLX5E_ICOSQ_WQE_GET_PSV_TLS:
mlx5e_ktls_handle_get_psv_completion(wi, sq);
break;
- }
#endif
+#ifdef CONFIG_MLX5_EN_NVMEOTCP
+ case MLX5E_ICOSQ_WQE_UMR_NVME_TCP:
+ break;
+#endif
+ }
}
sq->cc = sqcc;
}
@@ -695,6 +699,10 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
case MLX5E_ICOSQ_WQE_GET_PSV_TLS:
mlx5e_ktls_handle_get_psv_completion(wi, sq);
break;
+#endif
+#ifdef CONFIG_MLX5_EN_NVMEOTCP
+ case MLX5E_ICOSQ_WQE_UMR_NVME_TCP:
+ break;
#endif
default:
netdev_WARN_ONCE(cq->netdev,
--
2.24.1
More information about the Linux-nvme
mailing list