* [PATCHv3 for-next 1/5] RDMA/rtrs-srv: Set minimal max_send_wr and max_recv_wr
2021-06-14 9:03 [PATCHv3 for-next 0/5] Misc update for RTRS Jack Wang
@ 2021-06-14 9:03 ` Jack Wang
2021-06-14 9:03 ` [PATCHv3 for-next 2/5] RDMA/rtrs-clt: Use minimal max_send_sge when create qp Jack Wang
` (4 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: Jack Wang @ 2021-06-14 9:03 UTC (permalink / raw)
To: linux-rdma
Cc: bvanassche, leon, dledford, jgg, haris.iqbal, jinpu.wang,
Jack Wang, Md Haris Iqbal, Gioh Kim, Leon Romanovsky
From: Jack Wang <jinpu.wang@cloud.ionos.com>
Currently rtrs when create_qp use a coarse numbers (bigger in general),
which leads to hardware create more resources which only waste memory
with no benefits.
For max_send_wr, we don't really need alway max_qp_wr size when creating
qp, reduce it to cq_size.
For max_recv_wr, cq_size is enough.
With the patch when sess_queue_depth=128, per session (2 paths)
memory consumption reduced from 188 MB to 65MB
When always_invalidate is enabled, we need send more wr,
so treat it special.
Fixes: 9cb837480424e ("RDMA/rtrs: server: main functionality")
Signed-off-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Reviewed-by: Md Haris Iqbal <haris.iqbal@cloud.ionos.com>
Signed-off-by: Gioh Kim <gi-oh.kim@ionos.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
---
drivers/infiniband/ulp/rtrs/rtrs-srv.c | 38 +++++++++++++++++---------
1 file changed, 25 insertions(+), 13 deletions(-)
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
index 5639b29b8b02..04ec3080e9b5 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
@@ -1634,7 +1634,7 @@ static int create_con(struct rtrs_srv_sess *sess,
struct rtrs_sess *s = &sess->s;
struct rtrs_srv_con *con;
- u32 cq_size, wr_queue_size;
+ u32 cq_size, max_send_wr, max_recv_wr, wr_limit;
int err, cq_vector;
con = kzalloc(sizeof(*con), GFP_KERNEL);
@@ -1655,30 +1655,42 @@ static int create_con(struct rtrs_srv_sess *sess,
* All receive and all send (each requiring invalidate)
* + 2 for drain and heartbeat
*/
- wr_queue_size = SERVICE_CON_QUEUE_DEPTH * 3 + 2;
- cq_size = wr_queue_size;
+ max_send_wr = SERVICE_CON_QUEUE_DEPTH * 2 + 2;
+ max_recv_wr = SERVICE_CON_QUEUE_DEPTH + 2;
+ cq_size = max_send_wr + max_recv_wr;
} else {
- /*
- * If we have all receive requests posted and
- * all write requests posted and each read request
- * requires an invalidate request + drain
- * and qp gets into error state.
- */
- cq_size = srv->queue_depth * 3 + 1;
/*
* In theory we might have queue_depth * 32
* outstanding requests if an unsafe global key is used
* and we have queue_depth read requests each consisting
* of 32 different addresses. div 3 for mlx5.
*/
- wr_queue_size = sess->s.dev->ib_dev->attrs.max_qp_wr / 3;
+ wr_limit = sess->s.dev->ib_dev->attrs.max_qp_wr / 3;
+ /* when always_invlaidate enalbed, we need linv+rinv+mr+imm */
+ if (always_invalidate)
+ max_send_wr =
+ min_t(int, wr_limit,
+ srv->queue_depth * (1 + 4) + 1);
+ else
+ max_send_wr =
+ min_t(int, wr_limit,
+ srv->queue_depth * (1 + 2) + 1);
+
+ max_recv_wr = srv->queue_depth + 1;
+ /*
+ * If we have all receive requests posted and
+ * all write requests posted and each read request
+ * requires an invalidate request + drain
+ * and qp gets into error state.
+ */
+ cq_size = max_send_wr + max_recv_wr;
}
- atomic_set(&con->sq_wr_avail, wr_queue_size);
+ atomic_set(&con->sq_wr_avail, max_send_wr);
cq_vector = rtrs_srv_get_next_cq_vector(sess);
/* TODO: SOFTIRQ can be faster, but be careful with softirq context */
err = rtrs_cq_qp_create(&sess->s, &con->c, 1, cq_vector, cq_size,
- wr_queue_size, wr_queue_size,
+ max_send_wr, max_recv_wr,
IB_POLL_WORKQUEUE);
if (err) {
rtrs_err(s, "rtrs_cq_qp_create(), err: %d\n", err);
--
2.25.1
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCHv3 for-next 2/5] RDMA/rtrs-clt: Use minimal max_send_sge when create qp
2021-06-14 9:03 [PATCHv3 for-next 0/5] Misc update for RTRS Jack Wang
2021-06-14 9:03 ` [PATCHv3 for-next 1/5] RDMA/rtrs-srv: Set minimal max_send_wr and max_recv_wr Jack Wang
@ 2021-06-14 9:03 ` Jack Wang
2021-06-14 9:03 ` [PATCHv3 for-next 3/5] RDMA/rtrs: RDMA_RXE requires more number of WR Jack Wang
` (3 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: Jack Wang @ 2021-06-14 9:03 UTC (permalink / raw)
To: linux-rdma
Cc: bvanassche, leon, dledford, jgg, haris.iqbal, jinpu.wang,
Jack Wang, Guoqing Jiang, Leon Romanovsky
From: Jack Wang <jinpu.wang@cloud.ionos.com>
We use device limit max_send_sge, which is suboptimal for memory usage.
We don't need that much for User Con, 1 is enough. And for IO con,
sess->max_segments + 1 is enough
Signed-off-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
---
drivers/infiniband/ulp/rtrs/rtrs-clt.c | 14 ++++++++------
drivers/infiniband/ulp/rtrs/rtrs-clt.h | 1 -
2 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index f1fd7ae9ac53..cd53edddfe1f 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -1417,7 +1417,6 @@ static void query_fast_reg_mode(struct rtrs_clt_sess *sess)
sess->max_pages_per_mr =
min3(sess->max_pages_per_mr, (u32)max_pages_per_mr,
ib_dev->attrs.max_fast_reg_page_list_len);
- sess->max_send_sge = ib_dev->attrs.max_send_sge;
}
static bool rtrs_clt_change_state_get_old(struct rtrs_clt_sess *sess,
@@ -1573,7 +1572,7 @@ static void destroy_con(struct rtrs_clt_con *con)
static int create_con_cq_qp(struct rtrs_clt_con *con)
{
struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
- u32 max_send_wr, max_recv_wr, cq_size;
+ u32 max_send_wr, max_recv_wr, cq_size, max_send_sge;
int err, cq_vector;
struct rtrs_msg_rkey_rsp *rsp;
@@ -1587,6 +1586,7 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
*/
max_send_wr = SERVICE_CON_QUEUE_DEPTH * 2 + 2;
max_recv_wr = SERVICE_CON_QUEUE_DEPTH * 2 + 2;
+ max_send_sge = 1;
/* We must be the first here */
if (WARN_ON(sess->s.dev))
return -EINVAL;
@@ -1625,25 +1625,27 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
max_recv_wr =
min_t(int, sess->s.dev->ib_dev->attrs.max_qp_wr,
sess->queue_depth * 3 + 1);
+ max_send_sge = sess->clt->max_segments + 1;
}
+ cq_size = max_send_wr + max_recv_wr;
/* alloc iu to recv new rkey reply when server reports flags set */
if (sess->flags & RTRS_MSG_NEW_RKEY_F || con->c.cid == 0) {
- con->rsp_ius = rtrs_iu_alloc(max_recv_wr, sizeof(*rsp),
+ con->rsp_ius = rtrs_iu_alloc(cq_size, sizeof(*rsp),
GFP_KERNEL, sess->s.dev->ib_dev,
DMA_FROM_DEVICE,
rtrs_clt_rdma_done);
if (!con->rsp_ius)
return -ENOMEM;
- con->queue_size = max_recv_wr;
+ con->queue_size = cq_size;
}
cq_size = max_send_wr + max_recv_wr;
cq_vector = con->cpu % sess->s.dev->ib_dev->num_comp_vectors;
if (con->c.cid >= sess->s.irq_con_num)
- err = rtrs_cq_qp_create(&sess->s, &con->c, sess->max_send_sge,
+ err = rtrs_cq_qp_create(&sess->s, &con->c, max_send_sge,
cq_vector, cq_size, max_send_wr,
max_recv_wr, IB_POLL_DIRECT);
else
- err = rtrs_cq_qp_create(&sess->s, &con->c, sess->max_send_sge,
+ err = rtrs_cq_qp_create(&sess->s, &con->c, max_send_sge,
cq_vector, cq_size, max_send_wr,
max_recv_wr, IB_POLL_SOFTIRQ);
/*
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.h b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
index 919c9f96f25b..822a820540d4 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
@@ -141,7 +141,6 @@ struct rtrs_clt_sess {
u32 chunk_size;
size_t queue_depth;
u32 max_pages_per_mr;
- int max_send_sge;
u32 flags;
struct kobject kobj;
u8 for_new_clt;
--
2.25.1
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCHv3 for-next 4/5] RDMA/rtrs: Rename cq_size/queue_size to cq_num/queue_num
2021-06-14 9:03 [PATCHv3 for-next 0/5] Misc update for RTRS Jack Wang
` (2 preceding siblings ...)
2021-06-14 9:03 ` [PATCHv3 for-next 3/5] RDMA/rtrs: RDMA_RXE requires more number of WR Jack Wang
@ 2021-06-14 9:03 ` Jack Wang
2021-06-14 9:03 ` [PATCHv3 for-next 5/5] RDMA/rtrs: Check device max_qp_wr limit when create QP Jack Wang
2021-06-18 16:51 ` [PATCHv3 for-next 0/5] Misc update for RTRS Jason Gunthorpe
5 siblings, 0 replies; 7+ messages in thread
From: Jack Wang @ 2021-06-14 9:03 UTC (permalink / raw)
To: linux-rdma
Cc: bvanassche, leon, dledford, jgg, haris.iqbal, jinpu.wang,
Guoqing Jiang, Md Haris Iqbal, Jack Wang, Leon Romanovsky
From: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
Those variables are passed to create_cq, create_qp, rtrs_iu_alloc and
rtrs_iu_free, so these *_size means the num of unit. And cq_size also
means number of cq element.
Also move the setting of cq_num to common path.
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
Reviewed-by: Md Haris Iqbal <haris.iqbal@cloud.ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
---
drivers/infiniband/ulp/rtrs/rtrs-clt.c | 18 +++++++++---------
drivers/infiniband/ulp/rtrs/rtrs-clt.h | 2 +-
drivers/infiniband/ulp/rtrs/rtrs-pri.h | 10 +++++-----
drivers/infiniband/ulp/rtrs/rtrs-srv.c | 7 +++----
drivers/infiniband/ulp/rtrs/rtrs.c | 24 ++++++++++++------------
5 files changed, 30 insertions(+), 31 deletions(-)
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index acf0fde410c3..67ff5bf9bfa8 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -1572,7 +1572,7 @@ static void destroy_con(struct rtrs_clt_con *con)
static int create_con_cq_qp(struct rtrs_clt_con *con)
{
struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
- u32 max_send_wr, max_recv_wr, cq_size, max_send_sge;
+ u32 max_send_wr, max_recv_wr, cq_num, max_send_sge;
int err, cq_vector;
struct rtrs_msg_rkey_rsp *rsp;
@@ -1628,26 +1628,26 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
sess->queue_depth * 3 + 1);
max_send_sge = sess->clt->max_segments + 1;
}
- cq_size = max_send_wr + max_recv_wr;
+ cq_num = max_send_wr + max_recv_wr;
/* alloc iu to recv new rkey reply when server reports flags set */
if (sess->flags & RTRS_MSG_NEW_RKEY_F || con->c.cid == 0) {
- con->rsp_ius = rtrs_iu_alloc(cq_size, sizeof(*rsp),
+ con->rsp_ius = rtrs_iu_alloc(cq_num, sizeof(*rsp),
GFP_KERNEL, sess->s.dev->ib_dev,
DMA_FROM_DEVICE,
rtrs_clt_rdma_done);
if (!con->rsp_ius)
return -ENOMEM;
- con->queue_size = cq_size;
+ con->queue_num = cq_num;
}
- cq_size = max_send_wr + max_recv_wr;
+ cq_num = max_send_wr + max_recv_wr;
cq_vector = con->cpu % sess->s.dev->ib_dev->num_comp_vectors;
if (con->c.cid >= sess->s.irq_con_num)
err = rtrs_cq_qp_create(&sess->s, &con->c, max_send_sge,
- cq_vector, cq_size, max_send_wr,
+ cq_vector, cq_num, max_send_wr,
max_recv_wr, IB_POLL_DIRECT);
else
err = rtrs_cq_qp_create(&sess->s, &con->c, max_send_sge,
- cq_vector, cq_size, max_send_wr,
+ cq_vector, cq_num, max_send_wr,
max_recv_wr, IB_POLL_SOFTIRQ);
/*
* In case of error we do not bother to clean previous allocations,
@@ -1667,9 +1667,9 @@ static void destroy_con_cq_qp(struct rtrs_clt_con *con)
lockdep_assert_held(&con->con_mutex);
rtrs_cq_qp_destroy(&con->c);
if (con->rsp_ius) {
- rtrs_iu_free(con->rsp_ius, sess->s.dev->ib_dev, con->queue_size);
+ rtrs_iu_free(con->rsp_ius, sess->s.dev->ib_dev, con->queue_num);
con->rsp_ius = NULL;
- con->queue_size = 0;
+ con->queue_num = 0;
}
if (sess->s.dev_ref && !--sess->s.dev_ref) {
rtrs_ib_dev_put(sess->s.dev);
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.h b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
index 822a820540d4..eed2a20ee9be 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
@@ -71,7 +71,7 @@ struct rtrs_clt_stats {
struct rtrs_clt_con {
struct rtrs_con c;
struct rtrs_iu *rsp_ius;
- u32 queue_size;
+ u32 queue_num;
unsigned int cpu;
struct mutex con_mutex;
atomic_t io_cnt;
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-pri.h b/drivers/infiniband/ulp/rtrs/rtrs-pri.h
index bd06a79fd516..76cca2058f6f 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-pri.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-pri.h
@@ -95,7 +95,7 @@ struct rtrs_con {
struct ib_cq *cq;
struct rdma_cm_id *cm_id;
unsigned int cid;
- u16 cq_size;
+ int nr_cqe;
};
struct rtrs_sess {
@@ -294,10 +294,10 @@ struct rtrs_msg_rdma_hdr {
/* rtrs.c */
-struct rtrs_iu *rtrs_iu_alloc(u32 queue_size, size_t size, gfp_t t,
+struct rtrs_iu *rtrs_iu_alloc(u32 queue_num, size_t size, gfp_t t,
struct ib_device *dev, enum dma_data_direction,
void (*done)(struct ib_cq *cq, struct ib_wc *wc));
-void rtrs_iu_free(struct rtrs_iu *iu, struct ib_device *dev, u32 queue_size);
+void rtrs_iu_free(struct rtrs_iu *iu, struct ib_device *dev, u32 queue_num);
int rtrs_iu_post_recv(struct rtrs_con *con, struct rtrs_iu *iu);
int rtrs_iu_post_send(struct rtrs_con *con, struct rtrs_iu *iu, size_t size,
struct ib_send_wr *head);
@@ -312,8 +312,8 @@ int rtrs_post_rdma_write_imm_empty(struct rtrs_con *con, struct ib_cqe *cqe,
u32 imm_data, enum ib_send_flags flags,
struct ib_send_wr *head);
-int rtrs_cq_qp_create(struct rtrs_sess *rtrs_sess, struct rtrs_con *con,
- u32 max_send_sge, int cq_vector, int cq_size,
+int rtrs_cq_qp_create(struct rtrs_sess *sess, struct rtrs_con *con,
+ u32 max_send_sge, int cq_vector, int nr_cqe,
u32 max_send_wr, u32 max_recv_wr,
enum ib_poll_context poll_ctx);
void rtrs_cq_qp_destroy(struct rtrs_con *con);
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
index bb73f7762a87..c10dfc296259 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
@@ -1634,7 +1634,7 @@ static int create_con(struct rtrs_srv_sess *sess,
struct rtrs_sess *s = &sess->s;
struct rtrs_srv_con *con;
- u32 cq_size, max_send_wr, max_recv_wr, wr_limit;
+ u32 cq_num, max_send_wr, max_recv_wr, wr_limit;
int err, cq_vector;
con = kzalloc(sizeof(*con), GFP_KERNEL);
@@ -1657,7 +1657,6 @@ static int create_con(struct rtrs_srv_sess *sess,
*/
max_send_wr = SERVICE_CON_QUEUE_DEPTH * 2 + 2;
max_recv_wr = SERVICE_CON_QUEUE_DEPTH * 2 + 2;
- cq_size = max_send_wr + max_recv_wr;
} else {
/*
* In theory we might have queue_depth * 32
@@ -1683,13 +1682,13 @@ static int create_con(struct rtrs_srv_sess *sess,
* requires an invalidate request + drain
* and qp gets into error state.
*/
- cq_size = max_send_wr + max_recv_wr;
}
+ cq_num = max_send_wr + max_recv_wr;
atomic_set(&con->sq_wr_avail, max_send_wr);
cq_vector = rtrs_srv_get_next_cq_vector(sess);
/* TODO: SOFTIRQ can be faster, but be careful with softirq context */
- err = rtrs_cq_qp_create(&sess->s, &con->c, 1, cq_vector, cq_size,
+ err = rtrs_cq_qp_create(&sess->s, &con->c, 1, cq_vector, cq_num,
max_send_wr, max_recv_wr,
IB_POLL_WORKQUEUE);
if (err) {
diff --git a/drivers/infiniband/ulp/rtrs/rtrs.c b/drivers/infiniband/ulp/rtrs/rtrs.c
index 4e602e40f623..08e1f7d82c95 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs.c
@@ -18,7 +18,7 @@
MODULE_DESCRIPTION("RDMA Transport Core");
MODULE_LICENSE("GPL");
-struct rtrs_iu *rtrs_iu_alloc(u32 queue_size, size_t size, gfp_t gfp_mask,
+struct rtrs_iu *rtrs_iu_alloc(u32 iu_num, size_t size, gfp_t gfp_mask,
struct ib_device *dma_dev,
enum dma_data_direction dir,
void (*done)(struct ib_cq *cq, struct ib_wc *wc))
@@ -26,10 +26,10 @@ struct rtrs_iu *rtrs_iu_alloc(u32 queue_size, size_t size, gfp_t gfp_mask,
struct rtrs_iu *ius, *iu;
int i;
- ius = kcalloc(queue_size, sizeof(*ius), gfp_mask);
+ ius = kcalloc(iu_num, sizeof(*ius), gfp_mask);
if (!ius)
return NULL;
- for (i = 0; i < queue_size; i++) {
+ for (i = 0; i < iu_num; i++) {
iu = &ius[i];
iu->direction = dir;
iu->buf = kzalloc(size, gfp_mask);
@@ -50,7 +50,7 @@ struct rtrs_iu *rtrs_iu_alloc(u32 queue_size, size_t size, gfp_t gfp_mask,
}
EXPORT_SYMBOL_GPL(rtrs_iu_alloc);
-void rtrs_iu_free(struct rtrs_iu *ius, struct ib_device *ibdev, u32 queue_size)
+void rtrs_iu_free(struct rtrs_iu *ius, struct ib_device *ibdev, u32 queue_num)
{
struct rtrs_iu *iu;
int i;
@@ -58,7 +58,7 @@ void rtrs_iu_free(struct rtrs_iu *ius, struct ib_device *ibdev, u32 queue_size)
if (!ius)
return;
- for (i = 0; i < queue_size; i++) {
+ for (i = 0; i < queue_num; i++) {
iu = &ius[i];
ib_dma_unmap_single(ibdev, iu->dma_addr, iu->size, iu->direction);
kfree(iu->buf);
@@ -212,20 +212,20 @@ static void qp_event_handler(struct ib_event *ev, void *ctx)
}
}
-static int create_cq(struct rtrs_con *con, int cq_vector, u16 cq_size,
+static int create_cq(struct rtrs_con *con, int cq_vector, int nr_cqe,
enum ib_poll_context poll_ctx)
{
struct rdma_cm_id *cm_id = con->cm_id;
struct ib_cq *cq;
- cq = ib_cq_pool_get(cm_id->device, cq_size, cq_vector, poll_ctx);
+ cq = ib_cq_pool_get(cm_id->device, nr_cqe, cq_vector, poll_ctx);
if (IS_ERR(cq)) {
rtrs_err(con->sess, "Creating completion queue failed, errno: %ld\n",
PTR_ERR(cq));
return PTR_ERR(cq);
}
con->cq = cq;
- con->cq_size = cq_size;
+ con->nr_cqe = nr_cqe;
return 0;
}
@@ -260,20 +260,20 @@ static int create_qp(struct rtrs_con *con, struct ib_pd *pd,
}
int rtrs_cq_qp_create(struct rtrs_sess *sess, struct rtrs_con *con,
- u32 max_send_sge, int cq_vector, int cq_size,
+ u32 max_send_sge, int cq_vector, int nr_cqe,
u32 max_send_wr, u32 max_recv_wr,
enum ib_poll_context poll_ctx)
{
int err;
- err = create_cq(con, cq_vector, cq_size, poll_ctx);
+ err = create_cq(con, cq_vector, nr_cqe, poll_ctx);
if (err)
return err;
err = create_qp(con, sess->dev->ib_pd, max_send_wr, max_recv_wr,
max_send_sge);
if (err) {
- ib_cq_pool_put(con->cq, con->cq_size);
+ ib_cq_pool_put(con->cq, con->nr_cqe);
con->cq = NULL;
return err;
}
@@ -290,7 +290,7 @@ void rtrs_cq_qp_destroy(struct rtrs_con *con)
con->qp = NULL;
}
if (con->cq) {
- ib_cq_pool_put(con->cq, con->cq_size);
+ ib_cq_pool_put(con->cq, con->nr_cqe);
con->cq = NULL;
}
}
--
2.25.1
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCHv3 for-next 5/5] RDMA/rtrs: Check device max_qp_wr limit when create QP
2021-06-14 9:03 [PATCHv3 for-next 0/5] Misc update for RTRS Jack Wang
` (3 preceding siblings ...)
2021-06-14 9:03 ` [PATCHv3 for-next 4/5] RDMA/rtrs: Rename cq_size/queue_size to cq_num/queue_num Jack Wang
@ 2021-06-14 9:03 ` Jack Wang
2021-06-18 16:51 ` [PATCHv3 for-next 0/5] Misc update for RTRS Jason Gunthorpe
5 siblings, 0 replies; 7+ messages in thread
From: Jack Wang @ 2021-06-14 9:03 UTC (permalink / raw)
To: linux-rdma
Cc: bvanassche, leon, dledford, jgg, haris.iqbal, jinpu.wang,
Leon Romanovsky, Gioh Kim
Currently we only check device max_qp_wr limit for IO connection,
but not for service connection. We should check for both.
So save the max_qp_wr device limit in wr_limit, and use it for both
IO connections and service connections.
While at it, also remove an outdated comments.
Suggested-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jack Wang <jinpu.wang@ionos.com>
Signed-off-by: Gioh Kim <gi-oh.kim@ionos.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
---
drivers/infiniband/ulp/rtrs/rtrs-clt.c | 29 +++++++++++++-------------
drivers/infiniband/ulp/rtrs/rtrs-srv.c | 13 ++++--------
2 files changed, 19 insertions(+), 23 deletions(-)
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 67ff5bf9bfa8..125e0bead262 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -1572,21 +1572,12 @@ static void destroy_con(struct rtrs_clt_con *con)
static int create_con_cq_qp(struct rtrs_clt_con *con)
{
struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
- u32 max_send_wr, max_recv_wr, cq_num, max_send_sge;
+ u32 max_send_wr, max_recv_wr, cq_num, max_send_sge, wr_limit;
int err, cq_vector;
struct rtrs_msg_rkey_rsp *rsp;
lockdep_assert_held(&con->con_mutex);
if (con->c.cid == 0) {
- /*
- * Two (request + registration) completion for send
- * Two for recv if always_invalidate is set on server
- * or one for recv.
- * + 2 for drain and heartbeat
- * in case qp gets into error state.
- */
- max_send_wr = SERVICE_CON_QUEUE_DEPTH * 2 + 2;
- max_recv_wr = SERVICE_CON_QUEUE_DEPTH * 2 + 2;
max_send_sge = 1;
/* We must be the first here */
if (WARN_ON(sess->s.dev))
@@ -1606,6 +1597,17 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
}
sess->s.dev_ref = 1;
query_fast_reg_mode(sess);
+ wr_limit = sess->s.dev->ib_dev->attrs.max_qp_wr;
+ /*
+ * Two (request + registration) completion for send
+ * Two for recv if always_invalidate is set on server
+ * or one for recv.
+ * + 2 for drain and heartbeat
+ * in case qp gets into error state.
+ */
+ max_send_wr =
+ min_t(int, wr_limit, SERVICE_CON_QUEUE_DEPTH * 2 + 2);
+ max_recv_wr = max_send_wr;
} else {
/*
* Here we assume that session members are correctly set.
@@ -1617,14 +1619,13 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
if (WARN_ON(!sess->queue_depth))
return -EINVAL;
+ wr_limit = sess->s.dev->ib_dev->attrs.max_qp_wr;
/* Shared between connections */
sess->s.dev_ref++;
- max_send_wr =
- min_t(int, sess->s.dev->ib_dev->attrs.max_qp_wr,
+ max_send_wr = min_t(int, wr_limit,
/* QD * (REQ + RSP + FR REGS or INVS) + drain */
sess->queue_depth * 3 + 1);
- max_recv_wr =
- min_t(int, sess->s.dev->ib_dev->attrs.max_qp_wr,
+ max_recv_wr = min_t(int, wr_limit,
sess->queue_depth * 3 + 1);
max_send_sge = sess->clt->max_segments + 1;
}
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
index c10dfc296259..1a30fd833792 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
@@ -1649,22 +1649,17 @@ static int create_con(struct rtrs_srv_sess *sess,
con->c.sess = &sess->s;
con->c.cid = cid;
atomic_set(&con->wr_cnt, 1);
+ wr_limit = sess->s.dev->ib_dev->attrs.max_qp_wr;
if (con->c.cid == 0) {
/*
* All receive and all send (each requiring invalidate)
* + 2 for drain and heartbeat
*/
- max_send_wr = SERVICE_CON_QUEUE_DEPTH * 2 + 2;
- max_recv_wr = SERVICE_CON_QUEUE_DEPTH * 2 + 2;
+ max_send_wr = min_t(int, wr_limit,
+ SERVICE_CON_QUEUE_DEPTH * 2 + 2);
+ max_recv_wr = max_send_wr;
} else {
- /*
- * In theory we might have queue_depth * 32
- * outstanding requests if an unsafe global key is used
- * and we have queue_depth read requests each consisting
- * of 32 different addresses. div 3 for mlx5.
- */
- wr_limit = sess->s.dev->ib_dev->attrs.max_qp_wr / 3;
/* when always_invlaidate enalbed, we need linv+rinv+mr+imm */
if (always_invalidate)
max_send_wr =
--
2.25.1
^ permalink raw reply related [flat|nested] 7+ messages in thread