From: Aurelien Aptel <aaptel@nvidia.com>
To: netdev@vger.kernel.org, davem@davemloft.net, kuba@kernel.org,
edumazet@google.com, pabeni@redhat.com, saeedm@nvidia.com,
tariqt@nvidia.com, linux-nvme@lists.infradead.org,
sagi@grimberg.me, hch@lst.de, kbusch@kernel.org, axboe@fb.com,
chaitanyak@nvidia.com
Cc: smalin@nvidia.com, aaptel@nvidia.com, ogerlitz@nvidia.com,
yorayz@nvidia.com, borisp@nvidia.com, aurelien.aptel@gmail.com,
malin1024@gmail.com
Subject: [PATCH v6 09/23] nvme-tcp: Add ulp_offload modparam to control enablement of ULP offload
Date: Thu, 20 Oct 2022 13:18:24 +0300 [thread overview]
Message-ID: <20221020101838.2712846-10-aaptel@nvidia.com> (raw)
In-Reply-To: <20221020101838.2712846-1-aaptel@nvidia.com>
Add ulp_offload module parameter to the nvme-tcp module to control
ULP offload at the NVMe-TCP layer.
Turn ULP offload off be default, regardless of the NIC driver support.
In summary, to enable ULP offload:
- nvme-tcp modparam must be set to 1
- the NIC driver must set
- NETIF_F_HW_ULP_DDP flag in netdev->features
- ULP_DDP_C_NVME_TCP and/or ULP_DDP_C_NVME_TCP_DDGST_RX
flags in ulp_limits->offload_capabilities
Signed-off-by: Yoray Zack <yorayz@nvidia.com>
Signed-off-by: Shai Malin <smalin@nvidia.com>
Signed-off-by: Aurelien Aptel <aaptel@nvidia.com>
---
drivers/nvme/host/tcp.c | 17 +++++++++++++++++
1 file changed, 17 insertions(+)
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 11d9197f59ab..7ee14b8a392e 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -34,6 +34,17 @@ static int so_priority;
module_param(so_priority, int, 0644);
MODULE_PARM_DESC(so_priority, "nvme tcp socket optimize priority");
+#ifdef CONFIG_ULP_DDP
+/* NVMeTCP direct data placement and data digest offload will not
+ * happen if this parameter false (default), regardless of what the
+ * underlying netdev capabilities are.
+ */
+static bool ulp_offload;
+module_param(ulp_offload, bool, 0644);
+MODULE_PARM_DESC(ulp_offload, "Enable or disable NVMeTCP ULP support");
+#endif
+
+
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/* lockdep can detect a circular dependency of the form
* sk_lock -> mmap_lock (page fault) -> fs locks -> sk_lock
@@ -298,6 +309,9 @@ static bool nvme_tcp_ddp_query_limits(struct net_device *netdev,
{
int ret;
+ if (!ulp_offload)
+ return false;
+
if (!netdev || !(netdev->features & NETIF_F_HW_ULP_DDP) ||
!netdev->ulp_ddp_ops || !netdev->ulp_ddp_ops->ulp_ddp_limits)
return false;
@@ -497,6 +511,9 @@ static int nvme_tcp_offload_limits(struct nvme_tcp_queue *queue, struct net_devi
{
struct nvme_tcp_ddp_limits limits = {{ULP_DDP_NVME}};
+ if (!ulp_offload)
+ return 0;
+
if (!nvme_tcp_ddp_query_limits(netdev, &limits)) {
queue->ctrl->offloading_netdev = NULL;
return -EOPNOTSUPP;
--
2.31.1
next prev parent reply other threads:[~2022-10-20 10:21 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-20 10:18 [PATCH v6 00/23] nvme-tcp receive offloads Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 01/23] net: Introduce direct data placement tcp offload Aurelien Aptel
2022-10-21 5:05 ` Jakub Kicinski
2022-10-21 11:19 ` Aurelien Aptel
2022-10-24 11:22 ` Leon Romanovsky
2022-10-24 13:09 ` Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 02/23] iov_iter: DDP copy to iter/pages Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 03/23] net/tls: export get_netdev_for_sock Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 04/23] Revert "nvme-tcp: remove the unused queue_size member in nvme_tcp_queue" Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 05/23] nvme-tcp: Add DDP offload control path Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 06/23] nvme-tcp: Add DDP data-path Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 07/23] nvme-tcp: RX DDGST offload Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 08/23] nvme-tcp: Deal with netdevice DOWN events Aurelien Aptel
2022-10-20 10:18 ` Aurelien Aptel [this message]
2022-10-20 10:18 ` [PATCH v6 10/23] Documentation: add ULP DDP offload documentation Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 11/23] net/mlx5e: Rename from tls to transport static params Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 12/23] net/mlx5e: Refactor ico sq polling to get budget Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 13/23] net/mlx5e: Have mdev pointer directly on the icosq structure Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 14/23] net/mlx5e: Refactor doorbell function to allow avoiding a completion Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 15/23] net/mlx5: Add NVMEoTCP caps, HW bits, 128B CQE and enumerations Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 16/23] net/mlx5e: NVMEoTCP, offload initialization Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 17/23] net/mlx5e: TCP flow steering for nvme-tcp acceleration Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 18/23] net/mlx5e: NVMEoTCP, use KLM UMRs for buffer registration Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 19/23] net/mlx5e: NVMEoTCP, queue init/teardown Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 20/23] net/mlx5e: NVMEoTCP, ddp setup and resync Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 21/23] net/mlx5e: NVMEoTCP, async ddp invalidation Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 22/23] net/mlx5e: NVMEoTCP, data-path for DDP+DDGST offload Aurelien Aptel
2022-10-20 10:18 ` [PATCH v6 23/23] net/mlx5e: NVMEoTCP, statistics Aurelien Aptel
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=20221020101838.2712846-10-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=edumazet@google.com \
--cc=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=kuba@kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=malin1024@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=ogerlitz@nvidia.com \
--cc=pabeni@redhat.com \
--cc=saeedm@nvidia.com \
--cc=sagi@grimberg.me \
--cc=smalin@nvidia.com \
--cc=tariqt@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 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).