[PATCH v21 05/20] nvme-tcp: Add DDP offload control path

Max Gurtovoy mgurtovoy at nvidia.com
Sat Dec 16 16:18:21 PST 2023



On 14/12/2023 15:26, Aurelien Aptel wrote:
> From: Boris Pismenny <borisp at nvidia.com>
> 
> This commit introduces direct data placement offload to NVME
> TCP. There is a context per queue, which is established after the
> handshake using the sk_add/del NDOs.
> 
> Additionally, a resynchronization routine is used to assist
> hardware recovery from TCP OOO, and continue the offload.
> Resynchronization operates as follows:
> 
> 1. TCP OOO causes the NIC HW to stop the offload
> 
> 2. NIC HW identifies a PDU header at some TCP sequence number,
> and asks NVMe-TCP to confirm it.
> This request is delivered from the NIC driver to NVMe-TCP by first
> finding the socket for the packet that triggered the request, and
> then finding the nvme_tcp_queue that is used by this routine.
> Finally, the request is recorded in the nvme_tcp_queue.
> 
> 3. When NVMe-TCP observes the requested TCP sequence, it will compare
> it with the PDU header TCP sequence, and report the result to the
> NIC driver (resync), which will update the HW, and resume offload
> when all is successful.
> 
> Some HW implementation such as ConnectX-7 assume linear CCID (0...N-1
> for queue of size N) where the linux nvme driver uses part of the 16
> bit CCID for generation counter. To address that, we use the existing
> quirk in the nvme layer when the HW driver advertises if the device is
> not supports the full 16 bit CCID range.
> 
> Furthermore, we let the offloading driver advertise what is the max hw
> sectors/segments via ulp_ddp_limits.
> 
> A follow-up patch introduces the data-path changes required for this
> offload.
> 
> Socket operations need a netdev reference. This reference is
> dropped on NETDEV_GOING_DOWN events to allow the device to go down in
> a follow-up patch.
> 
> Signed-off-by: Boris Pismenny <borisp at nvidia.com>
> Signed-off-by: Ben Ben-Ishay <benishay at nvidia.com>
> Signed-off-by: Or Gerlitz <ogerlitz at nvidia.com>
> Signed-off-by: Yoray Zack <yorayz at nvidia.com>
> Signed-off-by: Shai Malin <smalin at nvidia.com>
> Signed-off-by: Aurelien Aptel <aaptel at nvidia.com>
> Signed-off-by: Max Gurtovoy <mgurtovoy at nvidia.com>
> Reviewed-by: Chaitanya Kulkarni <kch at nvidia.com>
> ---
>   drivers/nvme/host/tcp.c | 264 ++++++++++++++++++++++++++++++++++++++--
>   1 file changed, 251 insertions(+), 13 deletions(-)
> 
> diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
> index d79811cfa0ce..52b129401c78 100644
> --- a/drivers/nvme/host/tcp.c
> +++ b/drivers/nvme/host/tcp.c
> @@ -21,6 +21,10 @@
>   #include <net/busy_poll.h>
>   #include <trace/events/sock.h>
>   
> +#ifdef CONFIG_ULP_DDP
> +#include <net/ulp_ddp.h>
> +#endif
> +
>   #include "nvme.h"
>   #include "fabrics.h"
>   
> @@ -46,6 +50,16 @@ MODULE_PARM_DESC(tls_handshake_timeout,
>   		 "nvme TLS handshake timeout in seconds (default 10)");
>   #endif
>   
> +#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 ddp_offload;
> +module_param(ddp_offload, bool, 0644);
> +MODULE_PARM_DESC(ddp_offload, "Enable or disable NVMeTCP direct data placement 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
> @@ -119,6 +133,7 @@ enum nvme_tcp_queue_flags {
>   	NVME_TCP_Q_ALLOCATED	= 0,
>   	NVME_TCP_Q_LIVE		= 1,
>   	NVME_TCP_Q_POLLING	= 2,
> +	NVME_TCP_Q_OFF_DDP	= 3,
>   };
>   
>   enum nvme_tcp_recv_state {
> @@ -146,6 +161,18 @@ struct nvme_tcp_queue {
>   	size_t			ddgst_remaining;
>   	unsigned int		nr_cqe;
>   
> +#ifdef CONFIG_ULP_DDP
> +	/*
> +	 * resync_tcp_seq is a speculative PDU header tcp seq number (with
> +	 * an additional flag in the lower 32 bits) that the HW send to
> +	 * the SW, for the SW to verify.
> +	 * - The 32 high bits store the seq number
> +	 * - The 32 low bits are used as a flag to know if a request
> +	 *   is pending (ULP_DDP_RESYNC_PENDING).
> +	 */
> +	atomic64_t		resync_tcp_seq;
> +#endif
> +
>   	/* send state */
>   	struct nvme_tcp_request *request;
>   
> @@ -186,6 +213,12 @@ struct nvme_tcp_ctrl {
>   	struct delayed_work	connect_work;
>   	struct nvme_tcp_request async_req;
>   	u32			io_queues[HCTX_MAX_TYPES];
> +
> +	struct net_device	*ddp_netdev;
> +	u32			ddp_threshold;
> +#ifdef CONFIG_ULP_DDP
> +	struct ulp_ddp_limits	ddp_limits;
> +#endif
>   };
>   
>   static LIST_HEAD(nvme_tcp_ctrl_list);
> @@ -297,6 +330,171 @@ static inline size_t nvme_tcp_pdu_last_send(struct nvme_tcp_request *req,
>   	return nvme_tcp_pdu_data_left(req) <= len;
>   }
>   
> +#ifdef CONFIG_ULP_DDP
> +
> +static struct net_device *
> +nvme_tcp_get_ddp_netdev_with_limits(struct nvme_tcp_ctrl *ctrl)
> +{
> +	struct net_device *netdev;
> +	int ret;
> +
> +	if (!ddp_offload)
> +		return NULL;
> +
> +	/* netdev ref is put in nvme_tcp_stop_admin_queue() */
> +	netdev = get_netdev_for_sock(ctrl->queues[0].sock->sk);
> +	if (!netdev) {
> +		dev_dbg(ctrl->ctrl.device, "netdev not found\n");
> +		return NULL;
> +	}
> +
> +	if (!ulp_ddp_is_cap_active(netdev, ULP_DDP_CAP_NVME_TCP))
> +		goto err;
> +
> +	ret = ulp_ddp_get_limits(netdev, &ctrl->ddp_limits, ULP_DDP_NVME);
> +	if (ret)
> +		goto err;
> +
> +	if (ctrl->ctrl.opts->tls && !ctrl->ddp_limits.tls)
> +		goto err;
> +
> +	return netdev;
> +err:
> +	dev_put(netdev);
> +	return NULL;
> +}
> +
> +static bool nvme_tcp_resync_request(struct sock *sk, u32 seq, u32 flags);
> +static const struct ulp_ddp_ulp_ops nvme_tcp_ddp_ulp_ops = {
> +	.resync_request		= nvme_tcp_resync_request,
> +};
> +
> +static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
> +{
> +	struct ulp_ddp_config config = {.type = ULP_DDP_NVME};
> +	int ret;
> +
> +	config.nvmeotcp.pfv = NVME_TCP_PFV_1_0;
> +	config.nvmeotcp.cpda = 0;
> +	config.nvmeotcp.dgst =
> +		queue->hdr_digest ? NVME_TCP_HDR_DIGEST_ENABLE : 0;
> +	config.nvmeotcp.dgst |=
> +		queue->data_digest ? NVME_TCP_DATA_DIGEST_ENABLE : 0;
> +	config.nvmeotcp.queue_size = queue->ctrl->ctrl.sqsize + 1;
> +	config.nvmeotcp.queue_id = nvme_tcp_queue_id(queue);
> +
> +	ret = ulp_ddp_sk_add(queue->ctrl->ddp_netdev,
> +			     queue->sock->sk,
> +			     &config,
> +			     &nvme_tcp_ddp_ulp_ops);
> +	if (ret)
> +		return ret;
> +
> +	set_bit(NVME_TCP_Q_OFF_DDP, &queue->flags);
> +
> +	return 0;
> +}
> +
> +static void nvme_tcp_unoffload_socket(struct nvme_tcp_queue *queue)
> +{
> +	clear_bit(NVME_TCP_Q_OFF_DDP, &queue->flags);
> +	ulp_ddp_sk_del(queue->ctrl->ddp_netdev, queue->sock->sk);
> +}
> +
> +static void nvme_tcp_ddp_apply_limits(struct nvme_tcp_ctrl *ctrl)
> +{
> +	ctrl->ctrl.max_segments = ctrl->ddp_limits.max_ddp_sgl_len;
> +	ctrl->ctrl.max_hw_sectors =
> +		ctrl->ddp_limits.max_ddp_sgl_len << (ilog2(SZ_4K) - SECTOR_SHIFT);
> +	ctrl->ddp_threshold = ctrl->ddp_limits.io_threshold;
> +
> +	/* offloading HW doesn't support full ccid range, apply the quirk */
> +	ctrl->ctrl.quirks |=
> +		ctrl->ddp_limits.nvmeotcp.full_ccid_range ? 0 : NVME_QUIRK_SKIP_CID_GEN;
> +}
> +
> +/* In presence of packet drops or network packet reordering, the device may lose
> + * synchronization between the TCP stream and the L5P framing, and require a
> + * resync with the kernel's TCP stack.
> + *
> + * - NIC HW identifies a PDU header at some TCP sequence number,
> + *   and asks NVMe-TCP to confirm it.
> + * - When NVMe-TCP observes the requested TCP sequence, it will compare
> + *   it with the PDU header TCP sequence, and report the result to the
> + *   NIC driver
> + */
> +static void nvme_tcp_resync_response(struct nvme_tcp_queue *queue,
> +				     struct sk_buff *skb, unsigned int offset)
> +{
> +	u64 pdu_seq = TCP_SKB_CB(skb)->seq + offset - queue->pdu_offset;
> +	struct net_device *netdev = queue->ctrl->ddp_netdev;
> +	u64 pdu_val = (pdu_seq << 32) | ULP_DDP_RESYNC_PENDING;
> +	u64 resync_val;
> +	u32 resync_seq;
> +
> +	resync_val = atomic64_read(&queue->resync_tcp_seq);
> +	/* Lower 32 bit flags. Check validity of the request */
> +	if ((resync_val & ULP_DDP_RESYNC_PENDING) == 0)
> +		return;
> +
> +	/*
> +	 * Obtain and check requested sequence number: is this PDU header
> +	 * before the request?
> +	 */
> +	resync_seq = resync_val >> 32;
> +	if (before(pdu_seq, resync_seq))
> +		return;
> +
> +	/*
> +	 * The atomic operation guarantees that we don't miss any NIC driver
> +	 * resync requests submitted after the above checks.
> +	 */
> +	if (atomic64_cmpxchg(&queue->resync_tcp_seq, pdu_val,
> +			     pdu_val & ~ULP_DDP_RESYNC_PENDING) !=
> +			     atomic64_read(&queue->resync_tcp_seq))
> +		ulp_ddp_resync(netdev, queue->sock->sk, pdu_seq);
> +}
> +
> +static bool nvme_tcp_resync_request(struct sock *sk, u32 seq, u32 flags)
> +{
> +	struct nvme_tcp_queue *queue = sk->sk_user_data;
> +
> +	/*
> +	 * "seq" (TCP seq number) is what the HW assumes is the
> +	 * beginning of a PDU.  The nvme-tcp layer needs to store the
> +	 * number along with the "flags" (ULP_DDP_RESYNC_PENDING) to
> +	 * indicate that a request is pending.
> +	 */
> +	atomic64_set(&queue->resync_tcp_seq, (((uint64_t)seq << 32) | flags));
> +
> +	return true;
> +}
> +
> +#else
> +
> +static struct net_device *
> +nvme_tcp_get_ddp_netdev_with_limits(struct nvme_tcp_ctrl *ctrl)
> +{
> +	return NULL;
> +}
> +
> +static void nvme_tcp_ddp_apply_limits(struct nvme_tcp_ctrl *ctrl)
> +{}
> +
> +static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
> +{
> +	return 0;
> +}
> +
> +static void nvme_tcp_unoffload_socket(struct nvme_tcp_queue *queue)
> +{}
> +
> +static void nvme_tcp_resync_response(struct nvme_tcp_queue *queue,
> +				     struct sk_buff *skb, unsigned int offset)
> +{}
> +
> +#endif
> +
>   static void nvme_tcp_init_iter(struct nvme_tcp_request *req,
>   		unsigned int dir)
>   {
> @@ -739,6 +937,9 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
>   	size_t rcv_len = min_t(size_t, *len, queue->pdu_remaining);
>   	int ret;
>   
> +	if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags))
> +		nvme_tcp_resync_response(queue, skb, *offset);

lets try to optimize the fast path with:

if (IS_ENABLED(CONFIG_ULP_DDP) && test_bit(NVME_TCP_Q_OFF_DDP, 
&queue->flags))
     nvme_tcp_resync_response(queue, skb, *offset);


> +
>   	ret = skb_copy_bits(skb, *offset,
>   		&pdu[queue->pdu_offset], rcv_len);
>   	if (unlikely(ret))
> @@ -1804,6 +2005,8 @@ static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue)
>   	kernel_sock_shutdown(queue->sock, SHUT_RDWR);
>   	nvme_tcp_restore_sock_ops(queue);
>   	cancel_work_sync(&queue->io_work);
> +	if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags))
> +		nvme_tcp_unoffload_socket(queue);
>   }
>   
>   static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
> @@ -1820,6 +2023,20 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
>   	mutex_unlock(&queue->queue_lock);
>   }
>   
> +static void nvme_tcp_stop_admin_queue(struct nvme_ctrl *nctrl)
> +{
> +	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
> +
> +	nvme_tcp_stop_queue(nctrl, 0);
> +
> +	/*
> +	 * We are called twice by nvme_tcp_teardown_admin_queue()
> +	 * Set ddp_netdev to NULL to avoid putting it twice
> +	 */
> +	dev_put(ctrl->ddp_netdev);
> +	ctrl->ddp_netdev = NULL;
> +}
> +
>   static void nvme_tcp_setup_sock_ops(struct nvme_tcp_queue *queue)
>   {
>   	write_lock_bh(&queue->sock->sk->sk_callback_lock);
> @@ -1846,19 +2063,37 @@ static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx)
>   	nvme_tcp_init_recv_ctx(queue);
>   	nvme_tcp_setup_sock_ops(queue);
>   
> -	if (idx)
> +	if (idx) {
>   		ret = nvmf_connect_io_queue(nctrl, idx);
> -	else
> +		if (ret)
> +			goto err;
> +
> +		if (ctrl->ddp_netdev) {
> +			ret = nvme_tcp_offload_socket(queue);
> +			if (ret) {
> +				dev_info(nctrl->device,
> +					 "failed to setup offload on queue %d ret=%d\n",
> +					 idx, ret);
> +			}
> +		}
> +	} else {
>   		ret = nvmf_connect_admin_queue(nctrl);
> +		if (ret)
> +			goto err;
> +
> +		ctrl->ddp_netdev = nvme_tcp_get_ddp_netdev_with_limits(ctrl);
> +		if (ctrl->ddp_netdev)
> +			nvme_tcp_ddp_apply_limits(ctrl);
>   
> -	if (!ret) {
> -		set_bit(NVME_TCP_Q_LIVE, &queue->flags);
> -	} else {
> -		if (test_bit(NVME_TCP_Q_ALLOCATED, &queue->flags))
> -			__nvme_tcp_stop_queue(queue);
> -		dev_err(nctrl->device,
> -			"failed to connect queue: %d ret=%d\n", idx, ret);
>   	}
> +
> +	set_bit(NVME_TCP_Q_LIVE, &queue->flags);
> +	return 0;
> +err:
> +	if (test_bit(NVME_TCP_Q_ALLOCATED, &queue->flags))
> +		__nvme_tcp_stop_queue(queue);
> +	dev_err(nctrl->device,
> +		"failed to connect queue: %d ret=%d\n", idx, ret);
>   	return ret;
>   }
>   
> @@ -2070,7 +2305,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
>   
>   static void nvme_tcp_destroy_admin_queue(struct nvme_ctrl *ctrl, bool remove)
>   {
> -	nvme_tcp_stop_queue(ctrl, 0);
> +	nvme_tcp_stop_admin_queue(ctrl);
>   	if (remove)
>   		nvme_remove_admin_tag_set(ctrl);
>   	nvme_tcp_free_admin_queue(ctrl);
> @@ -2113,7 +2348,7 @@ static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new)
>   	nvme_quiesce_admin_queue(ctrl);
>   	blk_sync_queue(ctrl->admin_q);
>   out_stop_queue:
> -	nvme_tcp_stop_queue(ctrl, 0);
> +	nvme_tcp_stop_admin_queue(ctrl);
>   	nvme_cancel_admin_tagset(ctrl);
>   out_cleanup_tagset:
>   	if (new)
> @@ -2128,7 +2363,7 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
>   {
>   	nvme_quiesce_admin_queue(ctrl);
>   	blk_sync_queue(ctrl->admin_q);
> -	nvme_tcp_stop_queue(ctrl, 0);
> +	nvme_tcp_stop_admin_queue(ctrl);
>   	nvme_cancel_admin_tagset(ctrl);
>   	if (remove)
>   		nvme_unquiesce_admin_queue(ctrl);
> @@ -2413,7 +2648,10 @@ static void nvme_tcp_complete_timed_out(struct request *rq)
>   	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
>   	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
>   
> -	nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue));
> +	if (nvme_tcp_admin_queue(req->queue))
> +		nvme_tcp_stop_admin_queue(ctrl);
> +	else
> +		nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue));
>   	nvmf_complete_timed_out_request(rq);
>   }
>   



More information about the Linux-nvme mailing list