@@ -15,6 +15,10 @@
#include <crypto/hash.h>
#include <net/busy_poll.h>
+#ifdef CONFIG_ULP_DDP
+#include <net/ulp_ddp.h>
+#endif
+
#include "nvme.h"
#include "fabrics.h"
@@ -103,6 +107,7 @@ 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 {
@@ -130,6 +135,16 @@ struct nvme_tcp_queue {
size_t ddgst_remaining;
unsigned int nr_cqe;
+ /*
+ * resync_req is a speculative PDU header tcp seq number (with
+ * an additional flag at 32 lower 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_req;
+
/* send state */
struct nvme_tcp_request *request;
@@ -169,6 +184,9 @@ struct nvme_tcp_ctrl {
struct delayed_work connect_work;
struct nvme_tcp_request async_req;
u32 io_queues[HCTX_MAX_TYPES];
+
+ struct net_device *offloading_netdev;
+ u32 offload_io_threshold;
};
static LIST_HEAD(nvme_tcp_ctrl_list);
@@ -260,6 +278,190 @@ 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 inline bool is_netdev_ulp_offload_active(struct net_device *netdev)
+{
+ return test_bit(ULP_DDP_C_NVME_TCP_BIT, netdev->ulp_ddp_caps.active);
+}
+
+static bool nvme_tcp_ddp_query_limits(struct net_device *netdev,
+ struct ulp_ddp_limits *limits)
+{
+ int ret;
+
+ if (!netdev || !is_netdev_ulp_offload_active(netdev) ||
+ !netdev->netdev_ops->ulp_ddp_ops->ulp_ddp_limits)
+ return false;
+
+ limits->type = ULP_DDP_NVME;
+ ret = netdev->netdev_ops->ulp_ddp_ops->ulp_ddp_limits(netdev, limits);
+ if (ret == -EOPNOTSUPP) {
+ return false;
+ } else if (ret) {
+ WARN_ONCE(ret, "ddp limits failed (ret=%d)", ret);
+ return false;
+ }
+
+ return true;
+}
+
+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 net_device *netdev = queue->ctrl->offloading_netdev;
+ 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);
+ config.nvmeotcp.io_cpu = queue->io_cpu;
+
+ /* Socket ops keep a netdev reference. It is put in
+ * nvme_tcp_unoffload_socket(). This ref is dropped on
+ * NETDEV_GOING_DOWN events to allow the device to go down
+ */
+ dev_hold(netdev);
+ ret = netdev->netdev_ops->ulp_ddp_ops->ulp_ddp_sk_add(netdev,
+ queue->sock->sk,
+ &config);
+ if (ret) {
+ dev_put(netdev);
+ return ret;
+ }
+
+ inet_csk(queue->sock->sk)->icsk_ulp_ddp_ops = &nvme_tcp_ddp_ulp_ops;
+ set_bit(NVME_TCP_Q_OFF_DDP, &queue->flags);
+ return 0;
+}
+
+static void nvme_tcp_unoffload_socket(struct nvme_tcp_queue *queue)
+{
+ struct net_device *netdev = queue->ctrl->offloading_netdev;
+
+ if (!netdev) {
+ dev_info_ratelimited(queue->ctrl->ctrl.device, "netdev not found\n");
+ return;
+ }
+
+ clear_bit(NVME_TCP_Q_OFF_DDP, &queue->flags);
+
+ netdev->netdev_ops->ulp_ddp_ops->ulp_ddp_sk_del(netdev, queue->sock->sk);
+
+ inet_csk(queue->sock->sk)->icsk_ulp_ddp_ops = NULL;
+ dev_put(netdev); /* held by offload_socket */
+}
+
+static void nvme_tcp_offload_limits(struct nvme_tcp_queue *queue, struct net_device *netdev)
+{
+ struct ulp_ddp_limits limits = {.type = ULP_DDP_NVME };
+
+ if (!nvme_tcp_ddp_query_limits(netdev, &limits)) {
+ queue->ctrl->offloading_netdev = NULL;
+ return;
+ }
+
+ queue->ctrl->offloading_netdev = netdev;
+ dev_dbg_ratelimited(queue->ctrl->ctrl.device,
+ "netdev %s offload limits: max_ddp_sgl_len %d\n",
+ netdev->name, limits.max_ddp_sgl_len);
+ queue->ctrl->ctrl.max_segments = limits.max_ddp_sgl_len;
+ queue->ctrl->ctrl.max_hw_sectors = limits.max_ddp_sgl_len << (ilog2(SZ_4K) - 9);
+ queue->ctrl->offload_io_threshold = limits.io_threshold;
+
+ /* offloading HW doesn't support full ccid range, apply the quirk */
+ queue->ctrl->ctrl.quirks |=
+ 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->offloading_netdev;
+ u64 pdu_val = (pdu_seq << 32) | ULP_DDP_RESYNC_PENDING;
+ u64 resync_val;
+ u32 resync_seq;
+
+ resync_val = atomic64_read(&queue->resync_req);
+ /* 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_req, pdu_val,
+ pdu_val & ~ULP_DDP_RESYNC_PENDING) !=
+ atomic64_read(&queue->resync_req))
+ netdev->netdev_ops->ulp_ddp_ops->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_req, (((uint64_t)seq << 32) | flags));
+
+ return true;
+}
+
+#else
+
+static inline bool is_netdev_ulp_offload_active(struct net_device *netdev)
+{
+ return false;
+}
+
+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_offload_limits(struct nvme_tcp_queue *queue, struct net_device *netdev)
+{}
+
+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)
{
@@ -702,6 +904,9 @@ 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);
+
ret = skb_copy_bits(skb, *offset,
&pdu[queue->pdu_offset], rcv_len);
if (unlikely(ret))
@@ -1657,6 +1862,8 @@ static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue)
kernel_sock_shutdown(queue->sock, SHUT_RDWR);
nvme_tcp_restore_sock_calls(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)
@@ -1676,21 +1883,48 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx)
{
struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
+ struct net_device *netdev;
int ret;
- if (idx)
+ if (idx) {
ret = nvmf_connect_io_queue(nctrl, idx);
- else
+ if (ret)
+ goto err;
+
+ netdev = ctrl->queues[idx].ctrl->offloading_netdev;
+ if (netdev && is_netdev_ulp_offload_active(netdev)) {
+ ret = nvme_tcp_offload_socket(&ctrl->queues[idx]);
+ if (ret) {
+ dev_err(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;
- if (!ret) {
- set_bit(NVME_TCP_Q_LIVE, &ctrl->queues[idx].flags);
- } else {
- if (test_bit(NVME_TCP_Q_ALLOCATED, &ctrl->queues[idx].flags))
- __nvme_tcp_stop_queue(&ctrl->queues[idx]);
- dev_err(nctrl->device,
- "failed to connect queue: %d ret=%d\n", idx, ret);
+ netdev = get_netdev_for_sock(ctrl->queues[idx].sock->sk);
+ if (!netdev) {
+ dev_info_ratelimited(ctrl->ctrl.device, "netdev not found\n");
+ ctrl->offloading_netdev = NULL;
+ goto done;
+ }
+ if (is_netdev_ulp_offload_active(netdev))
+ nvme_tcp_offload_limits(&ctrl->queues[idx], netdev);
+ /* release the device as no offload context is established yet. */
+ dev_put(netdev);
}
+
+done:
+ set_bit(NVME_TCP_Q_LIVE, &ctrl->queues[idx].flags);
+ return 0;
+err:
+ if (test_bit(NVME_TCP_Q_ALLOCATED, &ctrl->queues[idx].flags))
+ __nvme_tcp_stop_queue(&ctrl->queues[idx]);
+ dev_err(nctrl->device,
+ "failed to connect queue: %d ret=%d\n", idx, ret);
return ret;
}