Although the non-SRQ mode needs more resources that mode has three
advantages over SRQ:
- It works with all RDMA adapters, even those that do not support
SRQ.
- Posting WRs and polling WCs does not trigger lock contention
because only one thread at a time accesses a WR or WC queue in
non-SRQ mode.
- The end-to-end flow control mechanism is used.
>From the IB spec:
C9-150.2.1: For QPs that are not associated with an SRQ, each HCA
receive queue shall generate end-to-end flow control credits. If
a QP is associated with an SRQ, the HCA receive queue shall not
generate end-to-end flow control credits.
Signed-off-by: Bart Van Assche <bart.vanassche@xxxxxxx>
---
drivers/infiniband/ulp/srpt/ib_srpt.c | 130 +++++++++++++++++++++++++---------
drivers/infiniband/ulp/srpt/ib_srpt.h | 4 ++
2 files changed, 99 insertions(+), 35 deletions(-)
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 6cf95ad870cc..a21b7a96635c 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -75,11 +75,19 @@ module_param(srp_max_req_size, int, 0444);
MODULE_PARM_DESC(srp_max_req_size,
"Maximum size of SRP request messages in bytes.");
+static bool use_srq;
+module_param(use_srq, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(use_srq, "Whether or not to use SRQ");
+
static int srpt_srq_size = DEFAULT_SRPT_SRQ_SIZE;
module_param(srpt_srq_size, int, 0444);
MODULE_PARM_DESC(srpt_srq_size,
"Shared receive queue (SRQ) size.");
+static int srpt_sq_size = DEF_SRPT_SQ_SIZE;
+module_param(srpt_sq_size, int, 0444);
+MODULE_PARM_DESC(srpt_sq_size, "Per-channel send queue (SQ) size.");
+
static int srpt_get_u64_x(char *buffer, struct kernel_param *kp)
{
return sprintf(buffer, "0x%016llx", *(u64 *)kp->arg);
@@ -295,6 +303,7 @@ static void srpt_get_ioc(struct srpt_port *sport, u32 slot,
{
struct srpt_device *sdev = sport->sdev;
struct ib_dm_ioc_profile *iocp;
+ int send_queue_depth;
iocp = (struct ib_dm_ioc_profile *)mad->data;
@@ -310,6 +319,12 @@ static void srpt_get_ioc(struct srpt_port *sport, u32 slot,
return;
}
+ if (sdev->use_srq)
+ send_queue_depth = sdev->srq_size;
+ else
+ send_queue_depth = min(SRPT_RQ_SIZE,
+ sdev->device->attrs.max_qp_wr);
+
memset(iocp, 0, sizeof(*iocp));
strcpy(iocp->id_string, SRPT_ID_STRING);
iocp->guid = cpu_to_be64(srpt_service_guid);
@@ -322,7 +337,7 @@ static void srpt_get_ioc(struct srpt_port *sport, u32 slot,
iocp->io_subclass = cpu_to_be16(SRP_IO_SUBCLASS);
iocp->protocol = cpu_to_be16(SRP_PROTOCOL);
iocp->protocol_version = cpu_to_be16(SRP_PROTOCOL_VERSION);
- iocp->send_queue_depth = cpu_to_be16(sdev->srq_size);
+ iocp->send_queue_depth = cpu_to_be16(send_queue_depth);
iocp->rdma_read_depth = 4;
iocp->send_size = cpu_to_be32(srp_max_req_size);
iocp->rdma_size = cpu_to_be32(min(sport->port_attrib.srp_max_rdma_size,
@@ -686,6 +701,9 @@ static void srpt_free_ioctx_ring(struct srpt_ioctx **ioctx_ring,
{
int i;
+ if (!ioctx_ring)
+ return;
+
for (i = 0; i < ring_size; ++i)
srpt_free_ioctx(sdev, ioctx_ring[i], dma_size, dir);
kfree(ioctx_ring);
@@ -757,7 +775,7 @@ static bool srpt_test_and_set_cmd_state(struct srpt_send_ioctx *ioctx,
/**
* srpt_post_recv() - Post an IB receive request.
*/
-static int srpt_post_recv(struct srpt_device *sdev,
+static int srpt_post_recv(struct srpt_device *sdev, struct srpt_rdma_ch *ch,
struct srpt_recv_ioctx *ioctx)
{
struct ib_sge list;
@@ -774,7 +792,10 @@ static int srpt_post_recv(struct srpt_device *sdev,
wr.sg_list = &list;
wr.num_sge = 1;
- return ib_post_srq_recv(sdev->srq, &wr, &bad_wr);
+ if (sdev->use_srq)
+ return ib_post_srq_recv(sdev->srq, &wr, &bad_wr);
+ else
+ return ib_post_recv(ch->qp, &wr, &bad_wr);
}
/**
@@ -1517,7 +1538,7 @@ static void srpt_handle_new_iu(struct srpt_rdma_ch *ch,
break;
}
- srpt_post_recv(ch->sport->sdev, recv_ioctx);
+ srpt_post_recv(ch->sport->sdev, ch, recv_ioctx);
return;
out_wait:
@@ -1616,7 +1637,7 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
struct srpt_device *sdev = sport->sdev;
const struct ib_device_attr *attrs = &sdev->device->attrs;
u32 srp_sq_size = sport->port_attrib.srp_sq_size;
- int ret;
+ int i, ret;
WARN_ON(ch->rq_size < 1);
@@ -1640,7 +1661,6 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
= (void(*)(struct ib_event *, void*))srpt_qp_event;
qp_init->send_cq = ch->cq;
qp_init->recv_cq = ch->cq;
- qp_init->srq = sdev->srq;
qp_init->sq_sig_type = IB_SIGNAL_REQ_WR;
qp_init->qp_type = IB_QPT_RC;
/*
@@ -1654,6 +1674,12 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
qp_init->cap.max_rdma_ctxs = srp_sq_size / 2;
qp_init->cap.max_send_sge = min(attrs->max_sge, SRPT_MAX_SG_PER_WQE);
qp_init->port_num = ch->sport->port;
+ if (sdev->use_srq) {
+ qp_init->srq = sdev->srq;
+ } else {
+ qp_init->cap.max_recv_wr = ch->rq_size;
+ qp_init->cap.max_recv_sge = qp_init->cap.max_send_sge;
+ }
ch->qp = ib_create_qp(sdev->pd, qp_init);
if (IS_ERR(ch->qp)) {
@@ -1669,6 +1695,10 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
goto err_destroy_cq;
}
+ if (!sdev->use_srq)
+ for (i = 0; i < ch->rq_size; i++)
+ srpt_post_recv(sdev, ch, ch->ioctx_recv_ring[i]);
+
atomic_set(&ch->sq_wr_avail, qp_init->cap.max_send_wr);
pr_debug("%s: max_cqe= %d max_sge= %d sq_size = %d cm_id= %p\n",
@@ -1818,6 +1848,10 @@ static void srpt_release_channel_work(struct work_struct *w)
ch->sport->sdev, ch->rq_size,
ch->rsp_size, DMA_TO_DEVICE);
+ srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_recv_ring,
+ sdev, ch->rq_size,
+ srp_max_req_size, DMA_FROM_DEVICE);
+
mutex_lock(&sdev->mutex);
list_del_init(&ch->list);
if (ch->release_done)
@@ -1975,6 +2009,19 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id,
ch->ioctx_ring[i]->ch = ch;
list_add_tail(&ch->ioctx_ring[i]->free_list, &ch->free_list);
}
+ if (!sdev->use_srq) {
+ ch->ioctx_recv_ring = (struct srpt_recv_ioctx **)
+ srpt_alloc_ioctx_ring(ch->sport->sdev, ch->rq_size,
+ sizeof(*ch->ioctx_recv_ring[0]),
+ srp_max_req_size,
+ DMA_FROM_DEVICE);
+ if (!ch->ioctx_recv_ring) {
+ pr_err("rejected SRP_LOGIN_REQ because creating a new QP RQ ring failed.\n");
+ rej->reason =
+ cpu_to_be32(SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
+ goto free_ring;
+ }
+ }
ret = srpt_create_ch_ib(ch);
if (ret) {
@@ -1982,7 +2029,7 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id,
SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
pr_err("rejected SRP_LOGIN_REQ because creating"
" a new RDMA channel failed.\n");
- goto free_ring;
+ goto free_recv_ring;
}
ret = srpt_ch_qp_rtr(ch, ch->qp);
@@ -2073,6 +2120,11 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id,
destroy_ib:
srpt_destroy_ch_ib(ch);
+free_recv_ring:
+ srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_recv_ring,
+ ch->sport->sdev, ch->rq_size,
+ srp_max_req_size, DMA_FROM_DEVICE);
+
free_ring:
srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_ring,
ch->sport->sdev, ch->rq_size,
@@ -2502,20 +2554,38 @@ static void srpt_add_one(struct ib_device *device)
srq_attr.attr.srq_limit = 0;
srq_attr.srq_type = IB_SRQT_BASIC;
- sdev->srq = ib_create_srq(sdev->pd, &srq_attr);
- if (IS_ERR(sdev->srq))
- goto err_pd;
+ sdev->srq = use_srq ? ib_create_srq(sdev->pd, &srq_attr) :
+ ERR_PTR(-ENOTSUPP);
+ if (IS_ERR(sdev->srq)) {
+ pr_debug("ib_create_srq() failed: %ld\n", PTR_ERR(sdev->srq));
+
+ /* SRQ not supported. */
+ sdev->use_srq = false;
+ } else {
+ pr_debug("create SRQ #wr= %d max_allow=%d dev= %s\n",
+ sdev->srq_size, sdev->device->attrs.max_srq_wr,
+ device->name);
- pr_debug("%s: create SRQ #wr= %d max_allow=%d dev= %s\n",
- __func__, sdev->srq_size, sdev->device->attrs.max_srq_wr,
- device->name);
+ sdev->use_srq = true;
+
+ sdev->ioctx_ring = (struct srpt_recv_ioctx **)
+ srpt_alloc_ioctx_ring(sdev, sdev->srq_size,
+ sizeof(*sdev->ioctx_ring[0]),
+ srp_max_req_size,
+ DMA_FROM_DEVICE);
+ if (!sdev->ioctx_ring)
+ goto err_pd;
+
+ for (i = 0; i < sdev->srq_size; ++i)
+ srpt_post_recv(sdev, NULL, sdev->ioctx_ring[i]);
+ }
if (!srpt_service_guid)
srpt_service_guid = be64_to_cpu(device->node_guid);
sdev->cm_id = ib_create_cm_id(device, srpt_cm_handler, sdev);
if (IS_ERR(sdev->cm_id))
- goto err_srq;
+ goto err_ring;
/* print out target login information */
pr_debug("Target login info: id_ext=%016llx,ioc_guid=%016llx,"
@@ -2535,16 +2605,6 @@ static void srpt_add_one(struct ib_device *device)
srpt_event_handler);
ib_register_event_handler(&sdev->event_handler);
- sdev->ioctx_ring = (struct srpt_recv_ioctx **)
- srpt_alloc_ioctx_ring(sdev, sdev->srq_size,
- sizeof(*sdev->ioctx_ring[0]),
- srp_max_req_size, DMA_FROM_DEVICE);
- if (!sdev->ioctx_ring)
- goto err_event;
-
- for (i = 0; i < sdev->srq_size; ++i)
- srpt_post_recv(sdev, sdev->ioctx_ring[i]);
-
WARN_ON(sdev->device->phys_port_cnt > ARRAY_SIZE(sdev->port));
for (i = 1; i <= sdev->device->phys_port_cnt; i++) {
@@ -2559,7 +2619,7 @@ static void srpt_add_one(struct ib_device *device)
if (srpt_refresh_port(sport)) {
pr_err("MAD registration failed for %s-%d.\n",
sdev->device->name, i);
- goto err_ring;
+ goto err_event;
}
}
@@ -2572,16 +2632,16 @@ static void srpt_add_one(struct ib_device *device)
pr_debug("added %s.\n", device->name);
return;
-err_ring:
- srpt_free_ioctx_ring((struct srpt_ioctx **)sdev->ioctx_ring, sdev,
- sdev->srq_size, srp_max_req_size,
- DMA_FROM_DEVICE);
err_event:
ib_unregister_event_handler(&sdev->event_handler);
err_cm:
ib_destroy_cm_id(sdev->cm_id);
-err_srq:
- ib_destroy_srq(sdev->srq);
+err_ring:
+ if (sdev->use_srq)
+ ib_destroy_srq(sdev->srq);
+ srpt_free_ioctx_ring((struct srpt_ioctx **)sdev->ioctx_ring, sdev,
+ sdev->srq_size, srp_max_req_size,
+ DMA_FROM_DEVICE);
err_pd:
ib_dealloc_pd(sdev->pd);
free_dev:
@@ -2625,12 +2685,12 @@ static void srpt_remove_one(struct ib_device *device, void *client_data)
spin_unlock(&srpt_dev_lock);
srpt_release_sdev(sdev);
- ib_destroy_srq(sdev->srq);
- ib_dealloc_pd(sdev->pd);
-
+ if (sdev->use_srq)
+ ib_destroy_srq(sdev->srq);
srpt_free_ioctx_ring((struct srpt_ioctx **)sdev->ioctx_ring, sdev,
sdev->srq_size, srp_max_req_size, DMA_FROM_DEVICE);
- sdev->ioctx_ring = NULL;
+ ib_dealloc_pd(sdev->pd);
+
kfree(sdev);
}
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h
index 976e924d7400..e0dbd5444d5e 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.h
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.h
@@ -252,6 +252,7 @@ enum rdma_ch_state {
* @free_list: Head of list with free send I/O contexts.
* @state: channel state. See also enum rdma_ch_state.
* @ioctx_ring: Send ring.
+ * @ioctx_recv_ring: Receive I/O context ring.
* @list: Node for insertion in the srpt_device.rch_list list.
* @cmd_wait_list: List of SCSI commands that arrived before the RTU event. This
* list contains struct srpt_ioctx elements and is protected
@@ -281,6 +282,7 @@ struct srpt_rdma_ch {
struct list_head free_list;
enum rdma_ch_state state;
struct srpt_send_ioctx **ioctx_ring;
+ struct srpt_recv_ioctx **ioctx_recv_ring;
struct list_head list;
struct list_head cmd_wait_list;
struct se_session *sess;
@@ -347,6 +349,7 @@ struct srpt_port {
* @srq: Per-HCA SRQ (shared receive queue).
* @cm_id: Connection identifier.
* @srq_size: SRQ size.
+ * @use_srq: Whether or not to use SRQ.
* @ioctx_ring: Per-HCA SRQ.
* @rch_list: Per-device channel list -- see also srpt_rdma_ch.list.
* @ch_releaseQ: Enables waiting for removal from rch_list.
@@ -362,6 +365,7 @@ struct srpt_device {
struct ib_srq *srq;
struct ib_cm_id *cm_id;
int srq_size;
+ bool use_srq;
struct srpt_recv_ioctx **ioctx_ring;
struct list_head rch_list;
wait_queue_head_t ch_releaseQ;
--
2.14.2
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
