From: Aurelien Aptel <aaptel@nvidia.com>
To: linux-nvme@lists.infradead.org, netdev@vger.kernel.org,
sagi@grimberg.me, hch@lst.de, kbusch@kernel.org, axboe@fb.com,
chaitanyak@nvidia.com, davem@davemloft.net, kuba@kernel.org
Cc: aaptel@nvidia.com, aurelien.aptel@gmail.com, smalin@nvidia.com,
malin1024@gmail.com, ogerlitz@nvidia.com, yorayz@nvidia.com,
borisp@nvidia.com, galshalom@nvidia.com, mgurtovoy@nvidia.com
Subject: [PATCH v24 18/20] net/mlx5e: NVMEoTCP, async ddp invalidation
Date: Thu, 4 Apr 2024 12:37:15 +0000 [thread overview]
Message-ID: <20240404123717.11857-19-aaptel@nvidia.com> (raw)
In-Reply-To: <20240404123717.11857-1-aaptel@nvidia.com>
From: Ben Ben-Ishay <benishay@nvidia.com>
After the ULP consumed the buffers of the offloaded request, it calls the
ddp_teardown op to release the NIC mapping for them and allow the NIC to
reuse the HW contexts associated with offloading this IO. We do a
fast/async un-mapping via UMR WQE. In this case, the ULP does holds off
with completing the request towards the upper/application layers until the
HW unmapping is done.
When the corresponding CQE is received, a notification is done via the
the teardown_done ddp callback advertised by the ULP in the ddp context.
Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Signed-off-by: Boris Pismenny <borisp@nvidia.com>
Signed-off-by: Or Gerlitz <ogerlitz@nvidia.com>
Signed-off-by: Yoray Zack <yorayz@nvidia.com>
Signed-off-by: Aurelien Aptel <aaptel@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
---
.../net/ethernet/mellanox/mlx5/core/en/txrx.h | 4 ++
.../mellanox/mlx5/core/en_accel/nvmeotcp.c | 66 ++++++++++++++++---
.../mellanox/mlx5/core/en_accel/nvmeotcp.h | 1 +
.../net/ethernet/mellanox/mlx5/core/en_rx.c | 6 ++
4 files changed, 67 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index c87dca17d5c8..3c124f708afc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -52,6 +52,7 @@ enum mlx5e_icosq_wqe_type {
#endif
#ifdef CONFIG_MLX5_EN_NVMEOTCP
MLX5E_ICOSQ_WQE_UMR_NVMEOTCP,
+ MLX5E_ICOSQ_WQE_UMR_NVMEOTCP_INVALIDATE,
MLX5E_ICOSQ_WQE_SET_PSV_NVMEOTCP,
#endif
};
@@ -230,6 +231,9 @@ struct mlx5e_icosq_wqe_info {
struct {
struct mlx5e_nvmeotcp_queue *queue;
} nvmeotcp_q;
+ struct {
+ struct mlx5e_nvmeotcp_queue_entry *entry;
+ } nvmeotcp_qe;
#endif
};
};
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 d7b416f77c3f..505f4e6d5098 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.c
@@ -142,10 +142,11 @@ build_nvmeotcp_klm_umr(struct mlx5e_nvmeotcp_queue *queue, struct mlx5e_umr_wqe
u16 ccid, int klm_entries, u32 klm_offset, u32 len,
enum wqe_type klm_type)
{
- u32 id = (klm_type == KLM_UMR) ? queue->ccid_table[ccid].klm_mkey :
- (mlx5e_tir_get_tirn(&queue->tir) << MLX5_WQE_CTRL_TIR_TIS_INDEX_SHIFT);
- u8 opc_mod = (klm_type == KLM_UMR) ? MLX5_CTRL_SEGMENT_OPC_MOD_UMR_UMR :
- MLX5_OPC_MOD_TRANSPORT_TIR_STATIC_PARAMS;
+ u32 id = (klm_type == BSF_KLM_UMR) ?
+ (mlx5e_tir_get_tirn(&queue->tir) << MLX5_WQE_CTRL_TIR_TIS_INDEX_SHIFT) :
+ queue->ccid_table[ccid].klm_mkey;
+ u8 opc_mod = (klm_type == BSF_KLM_UMR) ? MLX5_OPC_MOD_TRANSPORT_TIR_STATIC_PARAMS :
+ MLX5_CTRL_SEGMENT_OPC_MOD_UMR_UMR;
u32 ds_cnt = MLX5E_KLM_UMR_DS_CNT(ALIGN(klm_entries, MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT));
struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->uctrl;
struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
@@ -158,6 +159,13 @@ build_nvmeotcp_klm_umr(struct mlx5e_nvmeotcp_queue *queue, struct mlx5e_umr_wqe
cseg->qpn_ds = cpu_to_be32((sqn << MLX5_WQE_CTRL_QPN_SHIFT) | ds_cnt);
cseg->general_id = cpu_to_be32(id);
+ if (!klm_entries) { /* this is invalidate */
+ ucseg->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE);
+ ucseg->flags = MLX5_UMR_INLINE;
+ mkc->status = MLX5_MKEY_STATUS_FREE;
+ return;
+ }
+
if (klm_type == KLM_UMR && !klm_offset) {
ucseg->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_XLT_OCT_SIZE |
MLX5_MKEY_MASK_LEN | MLX5_MKEY_MASK_FREE);
@@ -259,8 +267,8 @@ build_nvmeotcp_static_params(struct mlx5e_nvmeotcp_queue *queue,
static void
mlx5e_nvmeotcp_fill_wi(struct mlx5e_nvmeotcp_queue *nvmeotcp_queue,
- struct mlx5e_icosq *sq, u32 wqebbs, u16 pi,
- enum wqe_type type)
+ struct mlx5e_icosq *sq, u32 wqebbs,
+ u16 pi, u16 ccid, enum wqe_type type)
{
struct mlx5e_icosq_wqe_info *wi = &sq->db.wqe_info[pi];
@@ -272,6 +280,10 @@ mlx5e_nvmeotcp_fill_wi(struct mlx5e_nvmeotcp_queue *nvmeotcp_queue,
wi->wqe_type = MLX5E_ICOSQ_WQE_SET_PSV_NVMEOTCP;
wi->nvmeotcp_q.queue = nvmeotcp_queue;
break;
+ case KLM_INV_UMR:
+ wi->wqe_type = MLX5E_ICOSQ_WQE_UMR_NVMEOTCP_INVALIDATE;
+ wi->nvmeotcp_qe.entry = &nvmeotcp_queue->ccid_table[ccid];
+ break;
default:
/* cases where no further action is required upon completion, such as ddp setup */
wi->wqe_type = MLX5E_ICOSQ_WQE_UMR_NVMEOTCP;
@@ -290,7 +302,7 @@ mlx5e_nvmeotcp_rx_post_static_params_wqe(struct mlx5e_nvmeotcp_queue *queue, u32
wqebbs = MLX5E_TRANSPORT_SET_STATIC_PARAMS_WQEBBS;
pi = mlx5e_icosq_get_next_pi(sq, wqebbs);
wqe = MLX5E_TRANSPORT_FETCH_SET_STATIC_PARAMS_WQE(sq, pi);
- mlx5e_nvmeotcp_fill_wi(NULL, sq, wqebbs, pi, BSF_UMR);
+ mlx5e_nvmeotcp_fill_wi(NULL, sq, wqebbs, pi, 0, BSF_UMR);
build_nvmeotcp_static_params(queue, wqe, resync_seq, queue->crc_rx);
sq->pc += wqebbs;
mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &wqe->ctrl);
@@ -307,7 +319,7 @@ mlx5e_nvmeotcp_rx_post_progress_params_wqe(struct mlx5e_nvmeotcp_queue *queue, u
wqebbs = MLX5E_NVMEOTCP_PROGRESS_PARAMS_WQEBBS;
pi = mlx5e_icosq_get_next_pi(sq, wqebbs);
wqe = MLX5E_NVMEOTCP_FETCH_PROGRESS_PARAMS_WQE(sq, pi);
- mlx5e_nvmeotcp_fill_wi(queue, sq, wqebbs, pi, SET_PSV_UMR);
+ mlx5e_nvmeotcp_fill_wi(queue, sq, wqebbs, pi, 0, SET_PSV_UMR);
build_nvmeotcp_progress_params(queue, wqe, seq);
sq->pc += wqebbs;
mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &wqe->ctrl);
@@ -330,7 +342,7 @@ post_klm_wqe(struct mlx5e_nvmeotcp_queue *queue,
wqebbs = DIV_ROUND_UP(wqe_sz, MLX5_SEND_WQE_BB);
pi = mlx5e_icosq_get_next_pi(sq, wqebbs);
wqe = MLX5E_NVMEOTCP_FETCH_KLM_WQE(sq, pi);
- mlx5e_nvmeotcp_fill_wi(queue, sq, wqebbs, pi, wqe_type);
+ mlx5e_nvmeotcp_fill_wi(queue, sq, wqebbs, pi, ccid, wqe_type);
build_nvmeotcp_klm_umr(queue, wqe, ccid, cur_klm_entries, klm_offset,
klm_length, wqe_type);
sq->pc += wqebbs;
@@ -345,7 +357,10 @@ mlx5e_nvmeotcp_post_klm_wqe(struct mlx5e_nvmeotcp_queue *queue, enum wqe_type wq
struct mlx5e_icosq *sq = &queue->sq;
u32 klm_offset = 0, wqes, i;
- wqes = DIV_ROUND_UP(klm_length, queue->max_klms_per_wqe);
+ if (wqe_type == KLM_INV_UMR)
+ wqes = 1;
+ else
+ wqes = DIV_ROUND_UP(klm_length, queue->max_klms_per_wqe);
spin_lock_bh(&queue->sq_lock);
@@ -844,12 +859,43 @@ void mlx5e_nvmeotcp_ctx_complete(struct mlx5e_icosq_wqe_info *wi)
complete(&queue->static_params_done);
}
+void mlx5e_nvmeotcp_ddp_inv_done(struct mlx5e_icosq_wqe_info *wi)
+{
+ struct mlx5e_nvmeotcp_queue_entry *q_entry = wi->nvmeotcp_qe.entry;
+ struct mlx5e_nvmeotcp_queue *queue = q_entry->queue;
+ struct mlx5_core_dev *mdev = queue->priv->mdev;
+ struct ulp_ddp_io *ddp = q_entry->ddp;
+ const struct ulp_ddp_ulp_ops *ulp_ops;
+
+ dma_unmap_sg(mdev->device, ddp->sg_table.sgl,
+ q_entry->sgl_length, DMA_FROM_DEVICE);
+
+ q_entry->sgl_length = 0;
+
+ ulp_ops = inet_csk(queue->sk)->icsk_ulp_ddp_ops;
+ if (ulp_ops && ulp_ops->ddp_teardown_done)
+ ulp_ops->ddp_teardown_done(q_entry->ddp_ctx);
+}
+
static void
mlx5e_nvmeotcp_ddp_teardown(struct net_device *netdev,
struct sock *sk,
struct ulp_ddp_io *ddp,
void *ddp_ctx)
{
+ struct mlx5e_nvmeotcp_queue_entry *q_entry;
+ struct mlx5e_nvmeotcp_queue *queue;
+
+ queue = container_of(ulp_ddp_get_ctx(sk), struct mlx5e_nvmeotcp_queue, ulp_ddp_ctx);
+ q_entry = &queue->ccid_table[ddp->command_id];
+ WARN_ONCE(q_entry->sgl_length == 0,
+ "Invalidation of empty sgl (CID 0x%x, queue 0x%x)\n",
+ ddp->command_id, queue->id);
+
+ q_entry->ddp_ctx = ddp_ctx;
+ q_entry->queue = queue;
+
+ mlx5e_nvmeotcp_post_klm_wqe(queue, KLM_INV_UMR, ddp->command_id, 0);
}
static void
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.h
index 8b29f3fde7f2..13817d8a0aae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.h
@@ -109,6 +109,7 @@ void mlx5e_nvmeotcp_cleanup(struct mlx5e_priv *priv);
struct mlx5e_nvmeotcp_queue *
mlx5e_nvmeotcp_get_queue(struct mlx5e_nvmeotcp *nvmeotcp, int id);
void mlx5e_nvmeotcp_put_queue(struct mlx5e_nvmeotcp_queue *queue);
+void mlx5e_nvmeotcp_ddp_inv_done(struct mlx5e_icosq_wqe_info *wi);
void mlx5e_nvmeotcp_ctx_complete(struct mlx5e_icosq_wqe_info *wi);
static inline void mlx5e_nvmeotcp_init_rx(struct mlx5e_priv *priv) {}
void mlx5e_nvmeotcp_cleanup_rx(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index c88c4972f708..89ef317bdd2f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -968,6 +968,9 @@ void mlx5e_free_icosq_descs(struct mlx5e_icosq *sq)
break;
#endif
#ifdef CONFIG_MLX5_EN_NVMEOTCP
+ case MLX5E_ICOSQ_WQE_UMR_NVMEOTCP_INVALIDATE:
+ mlx5e_nvmeotcp_ddp_inv_done(wi);
+ break;
case MLX5E_ICOSQ_WQE_SET_PSV_NVMEOTCP:
mlx5e_nvmeotcp_ctx_complete(wi);
break;
@@ -1073,6 +1076,9 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq, int budget)
#ifdef CONFIG_MLX5_EN_NVMEOTCP
case MLX5E_ICOSQ_WQE_UMR_NVMEOTCP:
break;
+ case MLX5E_ICOSQ_WQE_UMR_NVMEOTCP_INVALIDATE:
+ mlx5e_nvmeotcp_ddp_inv_done(wi);
+ break;
case MLX5E_ICOSQ_WQE_SET_PSV_NVMEOTCP:
mlx5e_nvmeotcp_ctx_complete(wi);
break;
--
2.34.1
next prev parent reply other threads:[~2024-04-04 12:39 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-04 12:36 [PATCH v24 00/20] nvme-tcp receive offloads Aurelien Aptel
2024-04-04 12:36 ` [PATCH v24 01/20] net: Introduce direct data placement tcp offload Aurelien Aptel
2024-04-21 11:47 ` Sagi Grimberg
2024-04-26 7:21 ` Aurelien Aptel
2024-04-28 8:15 ` Sagi Grimberg
2024-04-29 11:35 ` Aurelien Aptel
2024-04-30 11:54 ` Sagi Grimberg
2024-05-02 7:04 ` Aurelien Aptel
2024-05-03 7:31 ` Sagi Grimberg
2024-05-06 12:28 ` Aurelien Aptel
2024-04-04 12:36 ` [PATCH v24 02/20] netlink: add new family to manage ULP_DDP enablement and stats Aurelien Aptel
2024-04-04 12:37 ` [PATCH v24 03/20] iov_iter: skip copy if src == dst for direct data placement Aurelien Aptel
2024-04-15 14:28 ` Max Gurtovoy
2024-04-16 20:30 ` David Laight
2024-04-18 8:22 ` Aurelien Aptel
2024-04-04 12:37 ` [PATCH v24 04/20] net/tls,core: export get_netdev_for_sock Aurelien Aptel
2024-04-21 11:45 ` Sagi Grimberg
2024-04-04 12:37 ` [PATCH v24 05/20] nvme-tcp: Add DDP offload control path Aurelien Aptel
2024-04-07 22:08 ` Sagi Grimberg
2024-04-10 6:31 ` Aurelien Aptel
2024-04-04 12:37 ` [PATCH v24 06/20] nvme-tcp: Add DDP data-path Aurelien Aptel
2024-04-07 22:08 ` Sagi Grimberg
2024-04-10 6:31 ` Aurelien Aptel
2024-04-04 12:37 ` [PATCH v24 07/20] nvme-tcp: RX DDGST offload Aurelien Aptel
2024-04-04 12:37 ` [PATCH v24 08/20] nvme-tcp: Deal with netdevice DOWN events Aurelien Aptel
2024-04-04 12:37 ` [PATCH v24 09/20] Documentation: add ULP DDP offload documentation Aurelien Aptel
2024-04-09 8:49 ` Bagas Sanjaya
2024-04-04 12:37 ` [PATCH v24 10/20] net/mlx5e: Rename from tls to transport static params Aurelien Aptel
2024-04-04 12:37 ` [PATCH v24 11/20] net/mlx5e: Refactor ico sq polling to get budget Aurelien Aptel
2024-04-04 12:37 ` [PATCH v24 12/20] net/mlx5: Add NVMEoTCP caps, HW bits, 128B CQE and enumerations Aurelien Aptel
2024-04-04 12:37 ` [PATCH v24 13/20] net/mlx5e: NVMEoTCP, offload initialization Aurelien Aptel
2024-04-04 12:37 ` [PATCH v24 14/20] net/mlx5e: TCP flow steering for nvme-tcp acceleration Aurelien Aptel
2024-04-04 12:37 ` [PATCH v24 15/20] net/mlx5e: NVMEoTCP, use KLM UMRs for buffer registration Aurelien Aptel
2024-04-04 12:37 ` [PATCH v24 16/20] net/mlx5e: NVMEoTCP, queue init/teardown Aurelien Aptel
2024-04-04 12:37 ` [PATCH v24 17/20] net/mlx5e: NVMEoTCP, ddp setup and resync Aurelien Aptel
2024-04-04 12:37 ` Aurelien Aptel [this message]
2024-04-04 12:37 ` [PATCH v24 19/20] net/mlx5e: NVMEoTCP, data-path for DDP+DDGST offload Aurelien Aptel
2024-04-04 12:37 ` [PATCH v24 20/20] net/mlx5e: NVMEoTCP, statistics Aurelien Aptel
2024-04-06 5:45 ` [PATCH v24 00/20] nvme-tcp receive offloads Jakub Kicinski
2024-04-07 22:21 ` Sagi Grimberg
2024-04-09 22:35 ` Chaitanya Kulkarni
2024-04-09 22:59 ` Jakub Kicinski
2024-04-18 8:29 ` Chaitanya Kulkarni
2024-04-18 15:28 ` Jakub Kicinski
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=20240404123717.11857-19-aaptel@nvidia.com \
--to=aaptel@nvidia.com \
--cc=aurelien.aptel@gmail.com \
--cc=axboe@fb.com \
--cc=borisp@nvidia.com \
--cc=chaitanyak@nvidia.com \
--cc=davem@davemloft.net \
--cc=galshalom@nvidia.com \
--cc=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=kuba@kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=malin1024@gmail.com \
--cc=mgurtovoy@nvidia.com \
--cc=netdev@vger.kernel.org \
--cc=ogerlitz@nvidia.com \
--cc=sagi@grimberg.me \
--cc=smalin@nvidia.com \
--cc=yorayz@nvidia.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.