From 2bb185c68bf4c147f43d932e8a34fa150d148940 Mon Sep 17 00:00:00 2001
From: Luoyouming <luoyouming@huawei.com>
Date: Sat, 24 Dec 2022 18:22:00 +0800
Subject: RDMA/hns: Add compatibility handling for only support userspace rq
 inline

The rq inline makes some changes as follows, Firstly, it is only used in
user space. Secondly, it should notify hardware in QP RTR status. Thirdly,
Add compatibility processing between different user space and kernel
space.

Link: https://lore.kernel.org/r/20221224102201.3114536-3-xuhaoyue1@hisilicon.com
Signed-off-by: Luoyouming <luoyouming@huawei.com>
Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/uapi/rdma/hns-abi.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/uapi/rdma/hns-abi.h b/include/uapi/rdma/hns-abi.h
index 745790ce3c26..6c0940837d93 100644
--- a/include/uapi/rdma/hns-abi.h
+++ b/include/uapi/rdma/hns-abi.h
@@ -87,10 +87,12 @@ struct hns_roce_ib_create_qp_resp {
 
 enum {
 	HNS_ROCE_EXSGE_FLAGS = 1 << 0,
+	HNS_ROCE_RQ_INLINE_FLAGS = 1 << 1,
 };
 
 enum {
 	HNS_ROCE_RSP_EXSGE_FLAGS = 1 << 0,
+	HNS_ROCE_RSP_RQ_INLINE_FLAGS = 1 << 1,
 };
 
 struct hns_roce_ib_alloc_ucontext_resp {
-- 
cgit v1.2.3


From 1d91855304c2046115ee10be2c93161d93d5d40d Mon Sep 17 00:00:00 2001
From: Luoyouming <luoyouming@huawei.com>
Date: Sat, 24 Dec 2022 18:22:01 +0800
Subject: RDMA/hns: Support cqe inline in user space

Enable the CQEIE field and configure the CQEIS field of QPC.  And add
compatibility handling.

Link: https://lore.kernel.org/r/20221224102201.3114536-4-xuhaoyue1@hisilicon.com
Signed-off-by: Luoyouming <luoyouming@huawei.com>
Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/hns/hns_roce_device.h |  1 +
 drivers/infiniband/hw/hns/hns_roce_hw_v2.c  | 12 ++++++++++++
 drivers/infiniband/hw/hns/hns_roce_hw_v2.h  |  3 ++-
 drivers/infiniband/hw/hns/hns_roce_main.c   |  6 ++++++
 include/uapi/rdma/hns-abi.h                 |  2 ++
 5 files changed, 23 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index e9957fc51ffc..84239b907de2 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -144,6 +144,7 @@ enum {
 	HNS_ROCE_CAP_FLAG_DIRECT_WQE		= BIT(12),
 	HNS_ROCE_CAP_FLAG_SDI_MODE		= BIT(14),
 	HNS_ROCE_CAP_FLAG_STASH			= BIT(17),
+	HNS_ROCE_CAP_FLAG_CQE_INLINE		= BIT(19),
 };
 
 #define HNS_ROCE_DB_TYPE_COUNT			2
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index c0b487bcd349..dbf97fe5948f 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -4704,6 +4704,18 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
 		hr_reg_clear(qpc_mask, QPC_RQIE);
 	}
 
+	if (udata &&
+	    (ibqp->qp_type == IB_QPT_RC || ibqp->qp_type == IB_QPT_XRC_TGT) &&
+	    (uctx->config & HNS_ROCE_CQE_INLINE_FLAGS)) {
+		hr_reg_write_bool(context, QPC_CQEIE,
+				  hr_dev->caps.flags &
+				  HNS_ROCE_CAP_FLAG_CQE_INLINE);
+		hr_reg_clear(qpc_mask, QPC_CQEIE);
+
+		hr_reg_write(context, QPC_CQEIS, 0);
+		hr_reg_clear(qpc_mask, QPC_CQEIS);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index b1b3e1e0b84e..af9d00225cdf 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -531,7 +531,8 @@ struct hns_roce_v2_qp_context {
 #define QPC_RQ_RTY_TX_ERR QPC_FIELD_LOC(607, 607)
 #define QPC_RX_CQN QPC_FIELD_LOC(631, 608)
 #define QPC_XRC_QP_TYPE QPC_FIELD_LOC(632, 632)
-#define QPC_RSV3 QPC_FIELD_LOC(634, 633)
+#define QPC_CQEIE QPC_FIELD_LOC(633, 633)
+#define QPC_CQEIS QPC_FIELD_LOC(634, 634)
 #define QPC_MIN_RNR_TIME QPC_FIELD_LOC(639, 635)
 #define QPC_RQ_PRODUCER_IDX QPC_FIELD_LOC(655, 640)
 #define QPC_RQ_CONSUMER_IDX QPC_FIELD_LOC(671, 656)
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index 3e3ece03dec3..485e110ca433 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -385,6 +385,12 @@ static int hns_roce_alloc_ucontext(struct ib_ucontext *uctx,
 			resp.config |= HNS_ROCE_RSP_RQ_INLINE_FLAGS;
 	}
 
+	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_CQE_INLINE) {
+		context->config |= ucmd.config & HNS_ROCE_CQE_INLINE_FLAGS;
+		if (context->config & HNS_ROCE_CQE_INLINE_FLAGS)
+			resp.config |= HNS_ROCE_RSP_CQE_INLINE_FLAGS;
+	}
+
 	ret = hns_roce_uar_alloc(hr_dev, &context->uar);
 	if (ret)
 		goto error_fail_uar_alloc;
diff --git a/include/uapi/rdma/hns-abi.h b/include/uapi/rdma/hns-abi.h
index 6c0940837d93..2e68a8b0c92c 100644
--- a/include/uapi/rdma/hns-abi.h
+++ b/include/uapi/rdma/hns-abi.h
@@ -88,11 +88,13 @@ struct hns_roce_ib_create_qp_resp {
 enum {
 	HNS_ROCE_EXSGE_FLAGS = 1 << 0,
 	HNS_ROCE_RQ_INLINE_FLAGS = 1 << 1,
+	HNS_ROCE_CQE_INLINE_FLAGS = 1 << 2,
 };
 
 enum {
 	HNS_ROCE_RSP_EXSGE_FLAGS = 1 << 0,
 	HNS_ROCE_RSP_RQ_INLINE_FLAGS = 1 << 1,
+	HNS_ROCE_RSP_CQE_INLINE_FLAGS = 1 << 2,
 };
 
 struct hns_roce_ib_alloc_ucontext_resp {
-- 
cgit v1.2.3


From ccae0447af0e471426beea789a52b2b6605663e0 Mon Sep 17 00:00:00 2001
From: Mark Zhang <markzhang@nvidia.com>
Date: Wed, 4 Jan 2023 10:03:41 +0200
Subject: RDMA/cma: Refactor the inbound/outbound path records process flow

Refactors based on comments [1] of the multiple path records support
patchset:
- Return failure if not able to set inbound/outbound PRs;
- Simplify the flow when receiving the PRs from netlink channel: When
  a good PR response is received, unpack it and call the path_query
  callback directly. This saves two memory allocations;
- Define RDMA_PRIMARY_PATH_MAX_REC_NUM in a proper place.

[1] https://lore.kernel.org/linux-rdma/Yyxp9E9pJtUids2o@nvidia.com/

Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org> #srp
Link: https://lore.kernel.org/r/7610025d57342b8b6da0f19516c9612f9c3fdc37.1672819376.git.leonro@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/core/cma.c             |  30 +++---
 drivers/infiniband/core/sa_query.c        | 171 ++++++++++--------------------
 drivers/infiniband/ulp/ipoib/ipoib_main.c |   2 +-
 drivers/infiniband/ulp/srp/ib_srp.c       |   2 +-
 include/rdma/ib_sa.h                      |   2 +-
 include/rdma/rdma_cm.h                    |   1 -
 6 files changed, 75 insertions(+), 133 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index b9da636fe1fb..1d2bff91d78b 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -2819,8 +2819,8 @@ int rdma_set_min_rnr_timer(struct rdma_cm_id *id, u8 min_rnr_timer)
 }
 EXPORT_SYMBOL(rdma_set_min_rnr_timer);
 
-static void route_set_path_rec_inbound(struct cma_work *work,
-				       struct sa_path_rec *path_rec)
+static int route_set_path_rec_inbound(struct cma_work *work,
+				      struct sa_path_rec *path_rec)
 {
 	struct rdma_route *route = &work->id->id.route;
 
@@ -2828,14 +2828,15 @@ static void route_set_path_rec_inbound(struct cma_work *work,
 		route->path_rec_inbound =
 			kzalloc(sizeof(*route->path_rec_inbound), GFP_KERNEL);
 		if (!route->path_rec_inbound)
-			return;
+			return -ENOMEM;
 	}
 
 	*route->path_rec_inbound = *path_rec;
+	return 0;
 }
 
-static void route_set_path_rec_outbound(struct cma_work *work,
-					struct sa_path_rec *path_rec)
+static int route_set_path_rec_outbound(struct cma_work *work,
+				       struct sa_path_rec *path_rec)
 {
 	struct rdma_route *route = &work->id->id.route;
 
@@ -2843,14 +2844,15 @@ static void route_set_path_rec_outbound(struct cma_work *work,
 		route->path_rec_outbound =
 			kzalloc(sizeof(*route->path_rec_outbound), GFP_KERNEL);
 		if (!route->path_rec_outbound)
-			return;
+			return -ENOMEM;
 	}
 
 	*route->path_rec_outbound = *path_rec;
+	return 0;
 }
 
 static void cma_query_handler(int status, struct sa_path_rec *path_rec,
-			      int num_prs, void *context)
+			      unsigned int num_prs, void *context)
 {
 	struct cma_work *work = context;
 	struct rdma_route *route;
@@ -2865,13 +2867,15 @@ static void cma_query_handler(int status, struct sa_path_rec *path_rec,
 		if (!path_rec[i].flags || (path_rec[i].flags & IB_PATH_GMP))
 			*route->path_rec = path_rec[i];
 		else if (path_rec[i].flags & IB_PATH_INBOUND)
-			route_set_path_rec_inbound(work, &path_rec[i]);
+			status = route_set_path_rec_inbound(work, &path_rec[i]);
 		else if (path_rec[i].flags & IB_PATH_OUTBOUND)
-			route_set_path_rec_outbound(work, &path_rec[i]);
-	}
-	if (!route->path_rec) {
-		status = -EINVAL;
-		goto fail;
+			status = route_set_path_rec_outbound(work,
+							     &path_rec[i]);
+		else
+			status = -EINVAL;
+
+		if (status)
+			goto fail;
 	}
 
 	route->num_pri_alt_paths = 1;
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 0de83d9a4985..59179cfc20ef 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -106,7 +106,7 @@ struct ib_sa_device {
 
 struct ib_sa_query {
 	void (*callback)(struct ib_sa_query *sa_query, int status,
-			 int num_prs, struct ib_sa_mad *mad);
+			 struct ib_sa_mad *mad);
 	void (*release)(struct ib_sa_query *);
 	struct ib_sa_client    *client;
 	struct ib_sa_port      *port;
@@ -118,12 +118,6 @@ struct ib_sa_query {
 	u32			seq; /* Local svc request sequence number */
 	unsigned long		timeout; /* Local svc timeout */
 	u8			path_use; /* How will the pathrecord be used */
-
-	/* A separate buffer to save pathrecords of a response, as in cases
-	 * like IB/netlink, mulptiple pathrecords are supported, so that
-	 * mad->data is not large enough to hold them
-	 */
-	void			*resp_pr_data;
 };
 
 #define IB_SA_ENABLE_LOCAL_SERVICE	0x00000001
@@ -132,7 +126,7 @@ struct ib_sa_query {
 
 struct ib_sa_path_query {
 	void (*callback)(int status, struct sa_path_rec *rec,
-			 int num_paths, void *context);
+			 unsigned int num_paths, void *context);
 	void *context;
 	struct ib_sa_query sa_query;
 	struct sa_path_rec *conv_pr;
@@ -690,6 +684,8 @@ static const struct ib_field guidinfo_rec_table[] = {
 	  .size_bits    = 512 },
 };
 
+#define RDMA_PRIMARY_PATH_MAX_REC_NUM 3
+
 static inline void ib_sa_disable_local_svc(struct ib_sa_query *query)
 {
 	query->flags &= ~IB_SA_ENABLE_LOCAL_SERVICE;
@@ -874,30 +870,21 @@ static void send_handler(struct ib_mad_agent *agent,
 static void ib_nl_process_good_resolve_rsp(struct ib_sa_query *query,
 					   const struct nlmsghdr *nlh)
 {
-	struct ib_path_rec_data *srec, *drec;
+	struct sa_path_rec recs[RDMA_PRIMARY_PATH_MAX_REC_NUM];
 	struct ib_sa_path_query *path_query;
+	struct ib_path_rec_data *rec_data;
 	struct ib_mad_send_wc mad_send_wc;
 	const struct nlattr *head, *curr;
 	struct ib_sa_mad *mad = NULL;
-	int len, rem, num_prs = 0;
+	int len, rem, status = -EIO;
+	unsigned int num_prs = 0;
 	u32 mask = 0;
-	int status = -EIO;
 
 	if (!query->callback)
 		goto out;
 
 	path_query = container_of(query, struct ib_sa_path_query, sa_query);
 	mad = query->mad_buf->mad;
-	if (!path_query->conv_pr &&
-	    (be16_to_cpu(mad->mad_hdr.attr_id) == IB_SA_ATTR_PATH_REC)) {
-		/* Need a larger buffer for possible multiple PRs */
-		query->resp_pr_data = kvcalloc(RDMA_PRIMARY_PATH_MAX_REC_NUM,
-					       sizeof(*drec), GFP_KERNEL);
-		if (!query->resp_pr_data) {
-			query->callback(query, -ENOMEM, 0, NULL);
-			return;
-		}
-	}
 
 	head = (const struct nlattr *) nlmsg_data(nlh);
 	len = nlmsg_len(nlh);
@@ -917,36 +904,41 @@ static void ib_nl_process_good_resolve_rsp(struct ib_sa_query *query,
 		break;
 	}
 
-	drec = (struct ib_path_rec_data *)query->resp_pr_data;
 	nla_for_each_attr(curr, head, len, rem) {
 		if (curr->nla_type != LS_NLA_TYPE_PATH_RECORD)
 			continue;
 
-		srec = nla_data(curr);
-		if ((srec->flags & mask) != mask)
+		rec_data = nla_data(curr);
+		if ((rec_data->flags & mask) != mask)
 			continue;
 
-		status = 0;
-		if (!drec) {
-			memcpy(mad->data, srec->path_rec,
-			       sizeof(srec->path_rec));
-			num_prs = 1;
-			break;
+		if ((query->flags & IB_SA_QUERY_OPA) ||
+		    path_query->conv_pr) {
+			mad->mad_hdr.method |= IB_MGMT_METHOD_RESP;
+			memcpy(mad->data, rec_data->path_rec,
+			       sizeof(rec_data->path_rec));
+			query->callback(query, 0, mad);
+			goto out;
 		}
 
-		memcpy(drec, srec, sizeof(*drec));
-		drec++;
+		status = 0;
+		ib_unpack(path_rec_table, ARRAY_SIZE(path_rec_table),
+			  rec_data->path_rec, &recs[num_prs]);
+		recs[num_prs].flags = rec_data->flags;
+		recs[num_prs].rec_type = SA_PATH_REC_TYPE_IB;
+		sa_path_set_dmac_zero(&recs[num_prs]);
+
 		num_prs++;
 		if (num_prs >= RDMA_PRIMARY_PATH_MAX_REC_NUM)
 			break;
 	}
 
-	if (!status)
+	if (!status) {
 		mad->mad_hdr.method |= IB_MGMT_METHOD_RESP;
-
-	query->callback(query, status, num_prs, mad);
-	kvfree(query->resp_pr_data);
-	query->resp_pr_data = NULL;
+		path_query->callback(status, recs, num_prs,
+				     path_query->context);
+	} else
+		query->callback(query, status, mad);
 
 out:
 	mad_send_wc.send_buf = query->mad_buf;
@@ -1451,11 +1443,26 @@ static int opa_pr_query_possible(struct ib_sa_client *client,
 		return PR_IB_SUPPORTED;
 }
 
-static void ib_sa_pr_callback_single(struct ib_sa_path_query *query,
-				     int status, struct ib_sa_mad *mad)
+static void ib_sa_path_rec_callback(struct ib_sa_query *sa_query,
+				    int status, struct ib_sa_mad *mad)
 {
+	struct ib_sa_path_query *query =
+		container_of(sa_query, struct ib_sa_path_query, sa_query);
 	struct sa_path_rec rec = {};
 
+	if (!mad) {
+		query->callback(status, NULL, 0, query->context);
+		return;
+	}
+
+	if (sa_query->flags & IB_SA_QUERY_OPA) {
+		ib_unpack(opa_path_rec_table, ARRAY_SIZE(opa_path_rec_table),
+			  mad->data, &rec);
+		rec.rec_type = SA_PATH_REC_TYPE_OPA;
+		query->callback(status, &rec, 1, query->context);
+		return;
+	}
+
 	ib_unpack(path_rec_table, ARRAY_SIZE(path_rec_table),
 		  mad->data, &rec);
 	rec.rec_type = SA_PATH_REC_TYPE_IB;
@@ -1472,71 +1479,6 @@ static void ib_sa_pr_callback_single(struct ib_sa_path_query *query,
 	}
 }
 
-/**
- * ib_sa_pr_callback_multiple() - Parse path records then do callback.
- *
- * In a multiple-PR case the PRs are saved in "query->resp_pr_data"
- * (instead of"mad->data") and with "ib_path_rec_data" structure format,
- * so that rec->flags can be set to indicate the type of PR.
- * This is valid only in IB fabric.
- */
-static void ib_sa_pr_callback_multiple(struct ib_sa_path_query *query,
-				       int status, int num_prs,
-				       struct ib_path_rec_data *rec_data)
-{
-	struct sa_path_rec *rec;
-	int i;
-
-	rec = kvcalloc(num_prs, sizeof(*rec), GFP_KERNEL);
-	if (!rec) {
-		query->callback(-ENOMEM, NULL, 0, query->context);
-		return;
-	}
-
-	for (i = 0; i < num_prs; i++) {
-		ib_unpack(path_rec_table, ARRAY_SIZE(path_rec_table),
-			  rec_data[i].path_rec, rec + i);
-		rec[i].rec_type = SA_PATH_REC_TYPE_IB;
-		sa_path_set_dmac_zero(rec + i);
-		rec[i].flags = rec_data[i].flags;
-	}
-
-	query->callback(status, rec, num_prs, query->context);
-	kvfree(rec);
-}
-
-static void ib_sa_path_rec_callback(struct ib_sa_query *sa_query,
-				    int status, int num_prs,
-				    struct ib_sa_mad *mad)
-{
-	struct ib_sa_path_query *query =
-		container_of(sa_query, struct ib_sa_path_query, sa_query);
-	struct sa_path_rec rec;
-
-	if (!mad || !num_prs) {
-		query->callback(status, NULL, 0, query->context);
-		return;
-	}
-
-	if (sa_query->flags & IB_SA_QUERY_OPA) {
-		if (num_prs != 1) {
-			query->callback(-EINVAL, NULL, 0, query->context);
-			return;
-		}
-
-		ib_unpack(opa_path_rec_table, ARRAY_SIZE(opa_path_rec_table),
-			  mad->data, &rec);
-		rec.rec_type = SA_PATH_REC_TYPE_OPA;
-		query->callback(status, &rec, num_prs, query->context);
-	} else {
-		if (!sa_query->resp_pr_data)
-			ib_sa_pr_callback_single(query, status, mad);
-		else
-			ib_sa_pr_callback_multiple(query, status, num_prs,
-						   sa_query->resp_pr_data);
-	}
-}
-
 static void ib_sa_path_rec_release(struct ib_sa_query *sa_query)
 {
 	struct ib_sa_path_query *query =
@@ -1578,7 +1520,7 @@ int ib_sa_path_rec_get(struct ib_sa_client *client,
 		       unsigned long timeout_ms, gfp_t gfp_mask,
 		       void (*callback)(int status,
 					struct sa_path_rec *resp,
-					int num_paths, void *context),
+					unsigned int num_paths, void *context),
 		       void *context,
 		       struct ib_sa_query **sa_query)
 {
@@ -1677,8 +1619,7 @@ err1:
 EXPORT_SYMBOL(ib_sa_path_rec_get);
 
 static void ib_sa_mcmember_rec_callback(struct ib_sa_query *sa_query,
-					int status, int num_prs,
-					struct ib_sa_mad *mad)
+					int status, struct ib_sa_mad *mad)
 {
 	struct ib_sa_mcmember_query *query =
 		container_of(sa_query, struct ib_sa_mcmember_query, sa_query);
@@ -1769,8 +1710,7 @@ err1:
 
 /* Support GuidInfoRecord */
 static void ib_sa_guidinfo_rec_callback(struct ib_sa_query *sa_query,
-					int status, int num_paths,
-					struct ib_sa_mad *mad)
+					int status, struct ib_sa_mad *mad)
 {
 	struct ib_sa_guidinfo_query *query =
 		container_of(sa_query, struct ib_sa_guidinfo_query, sa_query);
@@ -1879,8 +1819,7 @@ static void ib_classportinfo_cb(void *context)
 }
 
 static void ib_sa_classport_info_rec_callback(struct ib_sa_query *sa_query,
-					      int status, int num_prs,
-					      struct ib_sa_mad *mad)
+					      int status, struct ib_sa_mad *mad)
 {
 	unsigned long flags;
 	struct ib_sa_classport_info_query *query =
@@ -2055,13 +1994,13 @@ static void send_handler(struct ib_mad_agent *agent,
 			/* No callback -- already got recv */
 			break;
 		case IB_WC_RESP_TIMEOUT_ERR:
-			query->callback(query, -ETIMEDOUT, 0, NULL);
+			query->callback(query, -ETIMEDOUT, NULL);
 			break;
 		case IB_WC_WR_FLUSH_ERR:
-			query->callback(query, -EINTR, 0, NULL);
+			query->callback(query, -EINTR, NULL);
 			break;
 		default:
-			query->callback(query, -EIO, 0, NULL);
+			query->callback(query, -EIO, NULL);
 			break;
 		}
 
@@ -2089,10 +2028,10 @@ static void recv_handler(struct ib_mad_agent *mad_agent,
 		if (mad_recv_wc->wc->status == IB_WC_SUCCESS)
 			query->callback(query,
 					mad_recv_wc->recv_buf.mad->mad_hdr.status ?
-					-EINVAL : 0, 1,
+					-EINVAL : 0,
 					(struct ib_sa_mad *) mad_recv_wc->recv_buf.mad);
 		else
-			query->callback(query, -EIO, 0, NULL);
+			query->callback(query, -EIO, NULL);
 	}
 
 	ib_free_recv_mad(mad_recv_wc);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index ac25fc80fb33..4b3a7dbc21a4 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -742,7 +742,7 @@ void ipoib_flush_paths(struct net_device *dev)
 
 static void path_rec_completion(int status,
 				struct sa_path_rec *pathrec,
-				int num_prs, void *path_ptr)
+				unsigned int num_prs, void *path_ptr)
 {
 	struct ipoib_path *path = path_ptr;
 	struct net_device *dev = path->dev;
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index b4d6a4a5ae81..df21b30b7735 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -699,7 +699,7 @@ static void srp_free_ch_ib(struct srp_target_port *target,
 
 static void srp_path_rec_completion(int status,
 				    struct sa_path_rec *pathrec,
-				    int num_paths, void *ch_ptr)
+				    unsigned int num_paths, void *ch_ptr)
 {
 	struct srp_rdma_ch *ch = ch_ptr;
 	struct srp_target_port *target = ch->target;
diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h
index e930bec33b31..b46353fc53bf 100644
--- a/include/rdma/ib_sa.h
+++ b/include/rdma/ib_sa.h
@@ -414,7 +414,7 @@ int ib_sa_path_rec_get(struct ib_sa_client *client, struct ib_device *device,
 		       ib_sa_comp_mask comp_mask, unsigned long timeout_ms,
 		       gfp_t gfp_mask,
 		       void (*callback)(int status, struct sa_path_rec *resp,
-					int num_prs, void *context),
+					unsigned int num_prs, void *context),
 		       void *context, struct ib_sa_query **query);
 
 struct ib_sa_multicast {
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index cdc7cafab572..8a8ab2f793ab 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -49,7 +49,6 @@ struct rdma_addr {
 	struct rdma_dev_addr dev_addr;
 };
 
-#define RDMA_PRIMARY_PATH_MAX_REC_NUM 3
 struct rdma_route {
 	struct rdma_addr addr;
 	struct sa_path_rec *path_rec;
-- 
cgit v1.2.3


From 312b8f79eb05479628ee71357749815b2eeeeea8 Mon Sep 17 00:00:00 2001
From: Mark Zhang <markzhang@nvidia.com>
Date: Wed, 4 Jan 2023 11:43:34 +0200
Subject: RDMA/mlx: Calling qp event handler in workqueue context

Move the call of qp event handler from atomic to workqueue context,
so that the handler is able to block. This is needed by following
patches.

Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Link: https://lore.kernel.org/r/0cd17b8331e445f03942f4bb28d447f24ac5669d.1672821186.git.leonro@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx4/main.c       |   8 +++
 drivers/infiniband/hw/mlx4/mlx4_ib.h    |   3 +
 drivers/infiniband/hw/mlx4/qp.c         | 121 ++++++++++++++++++++++----------
 drivers/infiniband/hw/mlx5/main.c       |   7 ++
 drivers/infiniband/hw/mlx5/qp.c         | 119 ++++++++++++++++++++++---------
 drivers/infiniband/hw/mlx5/qp.h         |   2 +
 drivers/infiniband/hw/mlx5/qpc.c        |   3 +-
 drivers/net/ethernet/mellanox/mlx4/qp.c |  14 ++--
 include/linux/mlx4/qp.h                 |   1 +
 include/rdma/ib_verbs.h                 |   2 +-
 10 files changed, 202 insertions(+), 78 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index dceebcd885bb..b18e9f2adc82 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -3303,6 +3303,10 @@ static int __init mlx4_ib_init(void)
 	if (!wq)
 		return -ENOMEM;
 
+	err = mlx4_ib_qp_event_init();
+	if (err)
+		goto clean_qp_event;
+
 	err = mlx4_ib_cm_init();
 	if (err)
 		goto clean_wq;
@@ -3324,6 +3328,9 @@ clean_cm:
 	mlx4_ib_cm_destroy();
 
 clean_wq:
+	mlx4_ib_qp_event_cleanup();
+
+clean_qp_event:
 	destroy_workqueue(wq);
 	return err;
 }
@@ -3333,6 +3340,7 @@ static void __exit mlx4_ib_cleanup(void)
 	mlx4_unregister_interface(&mlx4_ib_interface);
 	mlx4_ib_mcg_destroy();
 	mlx4_ib_cm_destroy();
+	mlx4_ib_qp_event_cleanup();
 	destroy_workqueue(wq);
 }
 
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 6a3b0f121045..17fee1e73a45 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -940,4 +940,7 @@ int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va,
 int mlx4_ib_cm_init(void);
 void mlx4_ib_cm_destroy(void);
 
+int mlx4_ib_qp_event_init(void);
+void mlx4_ib_qp_event_cleanup(void);
+
 #endif /* MLX4_IB_H */
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index b17d6ebc5b70..884825b2e5f7 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -102,6 +102,14 @@ enum mlx4_ib_source_type {
 	MLX4_IB_RWQ_SRC	= 1,
 };
 
+struct mlx4_ib_qp_event_work {
+	struct work_struct work;
+	struct mlx4_qp *qp;
+	enum mlx4_event type;
+};
+
+static struct workqueue_struct *mlx4_ib_qp_event_wq;
+
 static int is_tunnel_qp(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
 {
 	if (!mlx4_is_master(dev->dev))
@@ -200,50 +208,77 @@ static void stamp_send_wqe(struct mlx4_ib_qp *qp, int n)
 	}
 }
 
+static void mlx4_ib_handle_qp_event(struct work_struct *_work)
+{
+	struct mlx4_ib_qp_event_work *qpe_work =
+		container_of(_work, struct mlx4_ib_qp_event_work, work);
+	struct ib_qp *ibqp = &to_mibqp(qpe_work->qp)->ibqp;
+	struct ib_event event = {};
+
+	event.device = ibqp->device;
+	event.element.qp = ibqp;
+
+	switch (qpe_work->type) {
+	case MLX4_EVENT_TYPE_PATH_MIG:
+		event.event = IB_EVENT_PATH_MIG;
+		break;
+	case MLX4_EVENT_TYPE_COMM_EST:
+		event.event = IB_EVENT_COMM_EST;
+		break;
+	case MLX4_EVENT_TYPE_SQ_DRAINED:
+		event.event = IB_EVENT_SQ_DRAINED;
+		break;
+	case MLX4_EVENT_TYPE_SRQ_QP_LAST_WQE:
+		event.event = IB_EVENT_QP_LAST_WQE_REACHED;
+		break;
+	case MLX4_EVENT_TYPE_WQ_CATAS_ERROR:
+		event.event = IB_EVENT_QP_FATAL;
+		break;
+	case MLX4_EVENT_TYPE_PATH_MIG_FAILED:
+		event.event = IB_EVENT_PATH_MIG_ERR;
+		break;
+	case MLX4_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
+		event.event = IB_EVENT_QP_REQ_ERR;
+		break;
+	case MLX4_EVENT_TYPE_WQ_ACCESS_ERROR:
+		event.event = IB_EVENT_QP_ACCESS_ERR;
+		break;
+	default:
+		pr_warn("Unexpected event type %d on QP %06x\n",
+			qpe_work->type, qpe_work->qp->qpn);
+		goto out;
+	}
+
+	ibqp->event_handler(&event, ibqp->qp_context);
+
+out:
+	mlx4_put_qp(qpe_work->qp);
+	kfree(qpe_work);
+}
+
 static void mlx4_ib_qp_event(struct mlx4_qp *qp, enum mlx4_event type)
 {
-	struct ib_event event;
 	struct ib_qp *ibqp = &to_mibqp(qp)->ibqp;
+	struct mlx4_ib_qp_event_work *qpe_work;
 
 	if (type == MLX4_EVENT_TYPE_PATH_MIG)
 		to_mibqp(qp)->port = to_mibqp(qp)->alt_port;
 
-	if (ibqp->event_handler) {
-		event.device     = ibqp->device;
-		event.element.qp = ibqp;
-		switch (type) {
-		case MLX4_EVENT_TYPE_PATH_MIG:
-			event.event = IB_EVENT_PATH_MIG;
-			break;
-		case MLX4_EVENT_TYPE_COMM_EST:
-			event.event = IB_EVENT_COMM_EST;
-			break;
-		case MLX4_EVENT_TYPE_SQ_DRAINED:
-			event.event = IB_EVENT_SQ_DRAINED;
-			break;
-		case MLX4_EVENT_TYPE_SRQ_QP_LAST_WQE:
-			event.event = IB_EVENT_QP_LAST_WQE_REACHED;
-			break;
-		case MLX4_EVENT_TYPE_WQ_CATAS_ERROR:
-			event.event = IB_EVENT_QP_FATAL;
-			break;
-		case MLX4_EVENT_TYPE_PATH_MIG_FAILED:
-			event.event = IB_EVENT_PATH_MIG_ERR;
-			break;
-		case MLX4_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
-			event.event = IB_EVENT_QP_REQ_ERR;
-			break;
-		case MLX4_EVENT_TYPE_WQ_ACCESS_ERROR:
-			event.event = IB_EVENT_QP_ACCESS_ERR;
-			break;
-		default:
-			pr_warn("Unexpected event type %d "
-			       "on QP %06x\n", type, qp->qpn);
-			return;
-		}
+	if (!ibqp->event_handler)
+		goto out_no_handler;
 
-		ibqp->event_handler(&event, ibqp->qp_context);
-	}
+	qpe_work = kzalloc(sizeof(*qpe_work), GFP_ATOMIC);
+	if (!qpe_work)
+		goto out_no_handler;
+
+	qpe_work->qp = qp;
+	qpe_work->type = type;
+	INIT_WORK(&qpe_work->work, mlx4_ib_handle_qp_event);
+	queue_work(mlx4_ib_qp_event_wq, &qpe_work->work);
+	return;
+
+out_no_handler:
+	mlx4_put_qp(qp);
 }
 
 static void mlx4_ib_wq_event(struct mlx4_qp *qp, enum mlx4_event type)
@@ -4468,3 +4503,17 @@ void mlx4_ib_drain_rq(struct ib_qp *qp)
 
 	handle_drain_completion(cq, &rdrain, dev);
 }
+
+int mlx4_ib_qp_event_init(void)
+{
+	mlx4_ib_qp_event_wq = alloc_ordered_workqueue("mlx4_ib_qp_event_wq", 0);
+	if (!mlx4_ib_qp_event_wq)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void mlx4_ib_qp_event_cleanup(void)
+{
+	destroy_workqueue(mlx4_ib_qp_event_wq);
+}
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index c669ef6e47e7..8588f2fc0cba 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -4403,6 +4403,10 @@ static int __init mlx5_ib_init(void)
 		return -ENOMEM;
 	}
 
+	ret = mlx5_ib_qp_event_init();
+	if (ret)
+		goto qp_event_err;
+
 	mlx5_ib_odp_init();
 	ret = mlx5r_rep_init();
 	if (ret)
@@ -4420,6 +4424,8 @@ drv_err:
 mp_err:
 	mlx5r_rep_cleanup();
 rep_err:
+	mlx5_ib_qp_event_cleanup();
+qp_event_err:
 	destroy_workqueue(mlx5_ib_event_wq);
 	free_page((unsigned long)xlt_emergency_page);
 	return ret;
@@ -4431,6 +4437,7 @@ static void __exit mlx5_ib_cleanup(void)
 	auxiliary_driver_unregister(&mlx5r_mp_driver);
 	mlx5r_rep_cleanup();
 
+	mlx5_ib_qp_event_cleanup();
 	destroy_workqueue(mlx5_ib_event_wq);
 	free_page((unsigned long)xlt_emergency_page);
 }
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index cf953d23d18d..9b85e1be0aed 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -71,6 +71,14 @@ struct mlx5_modify_raw_qp_param {
 	u32 port;
 };
 
+struct mlx5_ib_qp_event_work {
+	struct work_struct work;
+	struct mlx5_core_qp *qp;
+	int type;
+};
+
+static struct workqueue_struct *mlx5_ib_qp_event_wq;
+
 static void get_cqs(enum ib_qp_type qp_type,
 		    struct ib_cq *ib_send_cq, struct ib_cq *ib_recv_cq,
 		    struct mlx5_ib_cq **send_cq, struct mlx5_ib_cq **recv_cq);
@@ -302,51 +310,78 @@ int mlx5_ib_read_wqe_srq(struct mlx5_ib_srq *srq, int wqe_index, void *buffer,
 	return mlx5_ib_read_user_wqe_srq(srq, wqe_index, buffer, buflen, bc);
 }
 
+static void mlx5_ib_handle_qp_event(struct work_struct *_work)
+{
+	struct mlx5_ib_qp_event_work *qpe_work =
+		container_of(_work, struct mlx5_ib_qp_event_work, work);
+	struct ib_qp *ibqp = &to_mibqp(qpe_work->qp)->ibqp;
+	struct ib_event event = {};
+
+	event.device = ibqp->device;
+	event.element.qp = ibqp;
+	switch (qpe_work->type) {
+	case MLX5_EVENT_TYPE_PATH_MIG:
+		event.event = IB_EVENT_PATH_MIG;
+		break;
+	case MLX5_EVENT_TYPE_COMM_EST:
+		event.event = IB_EVENT_COMM_EST;
+		break;
+	case MLX5_EVENT_TYPE_SQ_DRAINED:
+		event.event = IB_EVENT_SQ_DRAINED;
+		break;
+	case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
+		event.event = IB_EVENT_QP_LAST_WQE_REACHED;
+		break;
+	case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
+		event.event = IB_EVENT_QP_FATAL;
+		break;
+	case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
+		event.event = IB_EVENT_PATH_MIG_ERR;
+		break;
+	case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
+		event.event = IB_EVENT_QP_REQ_ERR;
+		break;
+	case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
+		event.event = IB_EVENT_QP_ACCESS_ERR;
+		break;
+	default:
+		pr_warn("mlx5_ib: Unexpected event type %d on QP %06x\n",
+			qpe_work->type, qpe_work->qp->qpn);
+		goto out;
+	}
+
+	ibqp->event_handler(&event, ibqp->qp_context);
+
+out:
+	mlx5_core_res_put(&qpe_work->qp->common);
+	kfree(qpe_work);
+}
+
 static void mlx5_ib_qp_event(struct mlx5_core_qp *qp, int type)
 {
 	struct ib_qp *ibqp = &to_mibqp(qp)->ibqp;
-	struct ib_event event;
+	struct mlx5_ib_qp_event_work *qpe_work;
 
 	if (type == MLX5_EVENT_TYPE_PATH_MIG) {
 		/* This event is only valid for trans_qps */
 		to_mibqp(qp)->port = to_mibqp(qp)->trans_qp.alt_port;
 	}
 
-	if (ibqp->event_handler) {
-		event.device     = ibqp->device;
-		event.element.qp = ibqp;
-		switch (type) {
-		case MLX5_EVENT_TYPE_PATH_MIG:
-			event.event = IB_EVENT_PATH_MIG;
-			break;
-		case MLX5_EVENT_TYPE_COMM_EST:
-			event.event = IB_EVENT_COMM_EST;
-			break;
-		case MLX5_EVENT_TYPE_SQ_DRAINED:
-			event.event = IB_EVENT_SQ_DRAINED;
-			break;
-		case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
-			event.event = IB_EVENT_QP_LAST_WQE_REACHED;
-			break;
-		case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
-			event.event = IB_EVENT_QP_FATAL;
-			break;
-		case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
-			event.event = IB_EVENT_PATH_MIG_ERR;
-			break;
-		case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
-			event.event = IB_EVENT_QP_REQ_ERR;
-			break;
-		case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
-			event.event = IB_EVENT_QP_ACCESS_ERR;
-			break;
-		default:
-			pr_warn("mlx5_ib: Unexpected event type %d on QP %06x\n", type, qp->qpn);
-			return;
-		}
+	if (!ibqp->event_handler)
+		goto out_no_handler;
 
-		ibqp->event_handler(&event, ibqp->qp_context);
-	}
+	qpe_work = kzalloc(sizeof(*qpe_work), GFP_ATOMIC);
+	if (!qpe_work)
+		goto out_no_handler;
+
+	qpe_work->qp = qp;
+	qpe_work->type = type;
+	INIT_WORK(&qpe_work->work, mlx5_ib_handle_qp_event);
+	queue_work(mlx5_ib_qp_event_wq, &qpe_work->work);
+	return;
+
+out_no_handler:
+	mlx5_core_res_put(&qp->common);
 }
 
 static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap,
@@ -5720,3 +5755,17 @@ out:
 	mutex_unlock(&mqp->mutex);
 	return err;
 }
+
+int mlx5_ib_qp_event_init(void)
+{
+	mlx5_ib_qp_event_wq = alloc_ordered_workqueue("mlx5_ib_qp_event_wq", 0);
+	if (!mlx5_ib_qp_event_wq)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void mlx5_ib_qp_event_cleanup(void)
+{
+	destroy_workqueue(mlx5_ib_qp_event_wq);
+}
diff --git a/drivers/infiniband/hw/mlx5/qp.h b/drivers/infiniband/hw/mlx5/qp.h
index 5d4e140db99c..fb2f4e030bb8 100644
--- a/drivers/infiniband/hw/mlx5/qp.h
+++ b/drivers/infiniband/hw/mlx5/qp.h
@@ -44,4 +44,6 @@ void mlx5_core_res_put(struct mlx5_core_rsc_common *res);
 int mlx5_core_xrcd_alloc(struct mlx5_ib_dev *dev, u32 *xrcdn);
 int mlx5_core_xrcd_dealloc(struct mlx5_ib_dev *dev, u32 xrcdn);
 int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter);
+int mlx5_ib_qp_event_init(void);
+void mlx5_ib_qp_event_cleanup(void);
 #endif /* _MLX5_IB_QP_H */
diff --git a/drivers/infiniband/hw/mlx5/qpc.c b/drivers/infiniband/hw/mlx5/qpc.c
index 542e4c63a8de..604af1fd6397 100644
--- a/drivers/infiniband/hw/mlx5/qpc.c
+++ b/drivers/infiniband/hw/mlx5/qpc.c
@@ -135,7 +135,8 @@ static int rsc_event_notifier(struct notifier_block *nb,
 	case MLX5_RES_SQ:
 		qp = (struct mlx5_core_qp *)common;
 		qp->event(qp, event_type);
-		break;
+		/* Need to put resource in event handler */
+		return NOTIFY_OK;
 	case MLX5_RES_DCT:
 		dct = (struct mlx5_core_dct *)common;
 		if (event_type == MLX5_EVENT_TYPE_DCT_DRAINED)
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 48cfaa7eaf50..913ed255990f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -46,6 +46,13 @@
 #define MLX4_BF_QP_SKIP_MASK	0xc0
 #define MLX4_MAX_BF_QP_RANGE	0x40
 
+void mlx4_put_qp(struct mlx4_qp *qp)
+{
+	if (refcount_dec_and_test(&qp->refcount))
+		complete(&qp->free);
+}
+EXPORT_SYMBOL_GPL(mlx4_put_qp);
+
 void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type)
 {
 	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
@@ -64,10 +71,8 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type)
 		return;
 	}
 
+	/* Need to call mlx4_put_qp() in event handler */
 	qp->event(qp, event_type);
-
-	if (refcount_dec_and_test(&qp->refcount))
-		complete(&qp->free);
 }
 
 /* used for INIT/CLOSE port logic */
@@ -523,8 +528,7 @@ EXPORT_SYMBOL_GPL(mlx4_qp_remove);
 
 void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp)
 {
-	if (refcount_dec_and_test(&qp->refcount))
-		complete(&qp->free);
+	mlx4_put_qp(qp);
 	wait_for_completion(&qp->free);
 
 	mlx4_qp_free_icm(dev, qp->qpn);
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 9db93e487496..c78b90f2e9a1 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -503,4 +503,5 @@ static inline u16 folded_qp(u32 q)
 
 u16 mlx4_qp_roce_entropy(struct mlx4_dev *dev, u32 qpn);
 
+void mlx4_put_qp(struct mlx4_qp *qp);
 #endif /* MLX4_QP_H */
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index a9a429172c0a..949cf4ffc536 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1168,7 +1168,7 @@ enum ib_qp_create_flags {
  */
 
 struct ib_qp_init_attr {
-	/* Consumer's event_handler callback must not block */
+	/* This callback occurs in workqueue context */
 	void                  (*event_handler)(struct ib_event *, void *);
 
 	void		       *qp_context;
-- 
cgit v1.2.3


From 18b1746bddf5e7f6b2618966596d9517172a5cd7 Mon Sep 17 00:00:00 2001
From: Aharon Landau <aharonl@nvidia.com>
Date: Thu, 26 Jan 2023 00:28:03 +0200
Subject: RDMA/mlx5: Remove implicit ODP cache entry

Implicit ODP mkey doesn't have unique properties. It shares the same
properties as the order 18 cache entry. There is no need to devote a
special entry for that.

Link: https://lore.kernel.org/r/20230125222807.6921-3-michaelgur@nvidia.com
Signed-off-by: Aharon Landau <aharonl@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/mlx5/odp.c | 20 +++++---------------
 include/linux/mlx5/driver.h      |  1 -
 2 files changed, 5 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 8a78580a2a72..72044f8ec883 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -405,6 +405,7 @@ static void mlx5_ib_page_fault_resume(struct mlx5_ib_dev *dev,
 static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr,
 						unsigned long idx)
 {
+	int order = order_base_2(MLX5_IMR_MTT_ENTRIES);
 	struct mlx5_ib_dev *dev = mr_to_mdev(imr);
 	struct ib_umem_odp *odp;
 	struct mlx5_ib_mr *mr;
@@ -417,7 +418,8 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr,
 	if (IS_ERR(odp))
 		return ERR_CAST(odp);
 
-	mr = mlx5_mr_cache_alloc(dev, &dev->cache.ent[MLX5_IMR_MTT_CACHE_ENTRY],
+	BUILD_BUG_ON(order > MKEY_CACHE_LAST_STD_ENTRY);
+	mr = mlx5_mr_cache_alloc(dev, &dev->cache.ent[order],
 				 imr->access_flags);
 	if (IS_ERR(mr)) {
 		ib_umem_odp_release(odp);
@@ -1591,20 +1593,8 @@ void mlx5_odp_init_mkey_cache_entry(struct mlx5_cache_ent *ent)
 {
 	if (!(ent->dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT))
 		return;
-
-	switch (ent->order - 2) {
-	case MLX5_IMR_MTT_CACHE_ENTRY:
-		ent->ndescs = MLX5_IMR_MTT_ENTRIES;
-		ent->access_mode = MLX5_MKC_ACCESS_MODE_MTT;
-		ent->limit = 0;
-		break;
-
-	case MLX5_IMR_KSM_CACHE_ENTRY:
-		ent->ndescs = mlx5_imr_ksm_entries;
-		ent->access_mode = MLX5_MKC_ACCESS_MODE_KSM;
-		ent->limit = 0;
-		break;
-	}
+	ent->ndescs = mlx5_imr_ksm_entries;
+	ent->access_mode = MLX5_MKC_ACCESS_MODE_KSM;
 }
 
 static const struct ib_device_ops mlx5_ib_dev_odp_ops = {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index d476255c9a3f..f79c20d50eb4 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -734,7 +734,6 @@ enum {
 
 enum {
 	MKEY_CACHE_LAST_STD_ENTRY = 20,
-	MLX5_IMR_MTT_CACHE_ENTRY,
 	MLX5_IMR_KSM_CACHE_ENTRY,
 	MAX_MKEY_CACHE_ENTRIES
 };
-- 
cgit v1.2.3


From 68e416255b29c25cbf20018d55849bcb8505c858 Mon Sep 17 00:00:00 2001
From: Deming Wang <wangdeming@inspur.com>
Date: Mon, 6 Feb 2023 03:57:25 -0500
Subject: RDMA/restrack: Correct spelling

Fix spelling errors.

Signed-off-by: Deming Wang <wangdeming@inspur.com>
Link: https://lore.kernel.org/r/20230206085725.1507-1-wangdeming@inspur.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/rdma/restrack.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/rdma/restrack.h b/include/rdma/restrack.h
index 79d109c47242..8b7c46daeb07 100644
--- a/include/rdma/restrack.h
+++ b/include/rdma/restrack.h
@@ -162,8 +162,8 @@ struct rdma_restrack_entry *rdma_restrack_get_byid(struct ib_device *dev,
  * rdma_restrack_no_track() - don't add resource to the DB
  * @res: resource entry
  *
- * Every user of thie API should be cross examined.
- * Probaby you don't need to use this function.
+ * Every user of this API should be cross examined.
+ * Probably you don't need to use this function.
  */
 static inline void rdma_restrack_no_track(struct rdma_restrack_entry *res)
 {
-- 
cgit v1.2.3


From 91d088a0304941b88c915cc800617ff4068cdd39 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 9 Feb 2023 12:51:36 -0400
Subject: RDMA/umem: Remove unused 'work' member from struct ib_umem

It is not used now.

Fixes: b95df5e3e459 ("drivers/IB,core: reduce scope of mmap_sem")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/0-v1-22a2667fa089+a3-umem_work_jgg@nvidia.com
Reviewed-by: Devesh Sharma <devesh.s.sharma@oracle.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/rdma/ib_umem.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 92a673cd9b4f..95896472a82b 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -25,7 +25,6 @@ struct ib_umem {
 	u32 writable : 1;
 	u32 is_odp : 1;
 	u32 is_dmabuf : 1;
-	struct work_struct	work;
 	struct sg_append_table sgt_append;
 };
 
-- 
cgit v1.2.3


From 4b7296aa6c6618d6a6840fbe857e4990f626bd90 Mon Sep 17 00:00:00 2001
From: Or Har-Toov <ohartoov@nvidia.com>
Date: Tue, 17 Jan 2023 15:14:49 +0200
Subject: net/mlx5: Expose bits for querying special mkeys

Add needed HW bits to query the values of all special mkeys.

Link: https://lore.kernel.org/r/080ebb563a9717c15b1ea75d669aede676df386b.1673960981.git.leon@kernel.org
Signed-off-by: Or Har-Toov <ohartoov@nvidia.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/linux/mlx5/mlx5_ifc.h | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index c3d3a2eef7d4..67cfac8fbe46 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1485,7 +1485,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         relaxed_ordering_write[0x1];
 	u8         relaxed_ordering_read[0x1];
 	u8         log_max_mkey[0x6];
-	u8         reserved_at_f0[0x8];
+	u8         reserved_at_f0[0x6];
+	u8	   terminate_scatter_list_mkey[0x1];
+	u8	   repeated_mkey[0x1];
 	u8         dump_fill_mkey[0x1];
 	u8         reserved_at_f9[0x2];
 	u8         fast_teardown[0x1];
@@ -5210,7 +5212,11 @@ struct mlx5_ifc_query_special_contexts_out_bits {
 
 	u8         null_mkey[0x20];
 
-	u8         reserved_at_a0[0x60];
+	u8	   terminate_scatter_list_mkey[0x20];
+
+	u8	   repeated_mkey[0x20];
+
+	u8         reserved_at_a0[0x20];
 };
 
 struct mlx5_ifc_query_special_contexts_in_bits {
-- 
cgit v1.2.3


From a419bfb7632095410adc3aecb1e863568f049add Mon Sep 17 00:00:00 2001
From: Or Har-Toov <ohartoov@nvidia.com>
Date: Tue, 17 Jan 2023 15:14:50 +0200
Subject: net/mlx5: Change define name for 0x100 lkey value

Change define of 0x100 lkey value from MLX5_INVALID_LKEY to be
MLX5_TERMINATE_SCATTER_LIST_LKEY as 0x100 is the value of
terminate_scatter_list_mkey.

Link: https://lore.kernel.org/r/3a116dc3fbae4cb6b76a63d27d418830b06ade0c.1673960981.git.leon@kernel.org
Signed-off-by: Or Har-Toov <ohartoov@nvidia.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/mlx5/odp.c                  | 10 +++++-----
 drivers/infiniband/hw/mlx5/srq.c                  |  2 +-
 drivers/infiniband/hw/mlx5/wr.c                   |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |  3 ++-
 include/linux/mlx5/qp.h                           |  2 +-
 5 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index e6e021af6aa9..b4ebeadce67c 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -986,7 +986,7 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev,
 {
 	int ret = 0, npages = 0;
 	u64 io_virt;
-	u32 key;
+	__be32 key;
 	u32 byte_count;
 	size_t bcnt;
 	int inline_segment;
@@ -1000,7 +1000,7 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev,
 		struct mlx5_wqe_data_seg *dseg = wqe;
 
 		io_virt = be64_to_cpu(dseg->addr);
-		key = be32_to_cpu(dseg->lkey);
+		key = dseg->lkey;
 		byte_count = be32_to_cpu(dseg->byte_count);
 		inline_segment = !!(byte_count &  MLX5_INLINE_SEG);
 		bcnt	       = byte_count & ~MLX5_INLINE_SEG;
@@ -1014,8 +1014,8 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev,
 		}
 
 		/* receive WQE end of sg list. */
-		if (receive_queue && bcnt == 0 && key == MLX5_INVALID_LKEY &&
-		    io_virt == 0)
+		if (receive_queue && bcnt == 0 &&
+		    key == MLX5_TERMINATE_SCATTER_LIST_LKEY && io_virt == 0)
 			break;
 
 		if (!inline_segment && total_wqe_bytes) {
@@ -1034,7 +1034,7 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev,
 			continue;
 		}
 
-		ret = pagefault_single_data_segment(dev, NULL, key,
+		ret = pagefault_single_data_segment(dev, NULL, be32_to_cpu(key),
 						    io_virt, bcnt,
 						    &pfault->bytes_committed,
 						    bytes_mapped);
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 09b365a98bbf..0ac8d2c57365 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -447,7 +447,7 @@ int mlx5_ib_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 
 		if (i < srq->msrq.max_avail_gather) {
 			scat[i].byte_count = 0;
-			scat[i].lkey       = cpu_to_be32(MLX5_INVALID_LKEY);
+			scat[i].lkey = MLX5_TERMINATE_SCATTER_LIST_LKEY;
 			scat[i].addr       = 0;
 		}
 	}
diff --git a/drivers/infiniband/hw/mlx5/wr.c b/drivers/infiniband/hw/mlx5/wr.c
index 855f3f4fefad..bc44551493e2 100644
--- a/drivers/infiniband/hw/mlx5/wr.c
+++ b/drivers/infiniband/hw/mlx5/wr.c
@@ -1252,7 +1252,7 @@ int mlx5_ib_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
 
 		if (i < qp->rq.max_gs) {
 			scat[i].byte_count = 0;
-			scat[i].lkey       = cpu_to_be32(MLX5_INVALID_LKEY);
+			scat[i].lkey = MLX5_TERMINATE_SCATTER_LIST_LKEY;
 			scat[i].addr       = 0;
 		}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 85b51039d2a6..a941a4880cc5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -829,7 +829,8 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 			/* check if num_frags is not a pow of two */
 			if (rq->wqe.info.num_frags < (1 << rq->wqe.info.log_num_frags)) {
 				wqe->data[f].byte_count = 0;
-				wqe->data[f].lkey = cpu_to_be32(MLX5_INVALID_LKEY);
+				wqe->data[f].lkey =
+					MLX5_TERMINATE_SCATTER_LIST_LKEY;
 				wqe->data[f].addr = 0;
 			}
 		}
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 4657d5c54abe..df55fbb65717 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -36,7 +36,7 @@
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/driver.h>
 
-#define MLX5_INVALID_LKEY	0x100
+#define MLX5_TERMINATE_SCATTER_LIST_LKEY cpu_to_be32(0x100)
 /* UMR (3 WQE_BB's) + SIG (3 WQE_BB's) + PSV (mem) + PSV (wire) */
 #define MLX5_SIG_WQE_SIZE	(MLX5_SEND_WQE_BB * 8)
 #define MLX5_DIF_SIZE		8
-- 
cgit v1.2.3


From 66fb1d5df6ace316a4a6e2c31e13fc123ea2b644 Mon Sep 17 00:00:00 2001
From: Edward Srouji <edwards@nvidia.com>
Date: Thu, 16 Feb 2023 11:13:45 +0200
Subject: IB/mlx5: Extend debug control for CC parameters

This patch adds rtt_resp_dscp to the current debug controllability of
congestion control (CC) parameters.
rtt_resp_dscp can be read or written through debugfs.
If set, its value overwrites the DSCP of the generated RTT response.

Signed-off-by: Edward Srouji <edwards@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Link: https://lore.kernel.org/r/1dcc3440ee53c688f19f579a051ded81a2aaa70a.1676538714.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/cong.c    | 28 +++++++++++++++++++++++++---
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  2 ++
 include/linux/mlx5/mlx5_ifc.h        | 12 ++++++++++++
 3 files changed, 39 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/cong.c b/drivers/infiniband/hw/mlx5/cong.c
index 290ea8ac3838..f87531318feb 100644
--- a/drivers/infiniband/hw/mlx5/cong.c
+++ b/drivers/infiniband/hw/mlx5/cong.c
@@ -38,6 +38,7 @@
 enum mlx5_ib_cong_node_type {
 	MLX5_IB_RROCE_ECN_RP = 1,
 	MLX5_IB_RROCE_ECN_NP = 2,
+	MLX5_IB_RROCE_GENERAL = 3,
 };
 
 static const char * const mlx5_ib_dbg_cc_name[] = {
@@ -61,6 +62,8 @@ static const char * const mlx5_ib_dbg_cc_name[] = {
 	"np_cnp_dscp",
 	"np_cnp_prio_mode",
 	"np_cnp_prio",
+	"rtt_resp_dscp_valid",
+	"rtt_resp_dscp",
 };
 
 #define MLX5_IB_RP_CLAMP_TGT_RATE_ATTR			BIT(1)
@@ -84,14 +87,18 @@ static const char * const mlx5_ib_dbg_cc_name[] = {
 #define MLX5_IB_NP_CNP_DSCP_ATTR			BIT(3)
 #define MLX5_IB_NP_CNP_PRIO_MODE_ATTR			BIT(4)
 
+#define MLX5_IB_GENERAL_RTT_RESP_DSCP_ATTR		BIT(0)
+
 static enum mlx5_ib_cong_node_type
 mlx5_ib_param_to_node(enum mlx5_ib_dbg_cc_types param_offset)
 {
-	if (param_offset >= MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE &&
-	    param_offset <= MLX5_IB_DBG_CC_RP_GD)
+	if (param_offset <= MLX5_IB_DBG_CC_RP_GD)
 		return MLX5_IB_RROCE_ECN_RP;
-	else
+
+	if (param_offset <= MLX5_IB_DBG_CC_NP_CNP_PRIO)
 		return MLX5_IB_RROCE_ECN_NP;
+
+	return MLX5_IB_RROCE_GENERAL;
 }
 
 static u32 mlx5_get_cc_param_val(void *field, int offset)
@@ -157,6 +164,12 @@ static u32 mlx5_get_cc_param_val(void *field, int offset)
 	case MLX5_IB_DBG_CC_NP_CNP_PRIO:
 		return MLX5_GET(cong_control_r_roce_ecn_np, field,
 				cnp_802p_prio);
+	case MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP_VALID:
+		return MLX5_GET(cong_control_r_roce_general, field,
+				rtt_resp_dscp_valid);
+	case MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP:
+		return MLX5_GET(cong_control_r_roce_general, field,
+				rtt_resp_dscp);
 	default:
 		return 0;
 	}
@@ -264,6 +277,15 @@ static void mlx5_ib_set_cc_param_mask_val(void *field, int offset,
 		MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_prio_mode, 0);
 		MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_802p_prio, var);
 		break;
+	case MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP_VALID:
+		*attr_mask |= MLX5_IB_GENERAL_RTT_RESP_DSCP_ATTR;
+		MLX5_SET(cong_control_r_roce_general, field, rtt_resp_dscp_valid, var);
+		break;
+	case MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP:
+		*attr_mask |= MLX5_IB_GENERAL_RTT_RESP_DSCP_ATTR;
+		MLX5_SET(cong_control_r_roce_general, field, rtt_resp_dscp_valid, 1);
+		MLX5_SET(cong_control_r_roce_general, field, rtt_resp_dscp, var);
+		break;
 	}
 }
 
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index f6c799f75b8e..efa4dc6e7dee 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -888,6 +888,8 @@ enum mlx5_ib_dbg_cc_types {
 	MLX5_IB_DBG_CC_NP_CNP_DSCP,
 	MLX5_IB_DBG_CC_NP_CNP_PRIO_MODE,
 	MLX5_IB_DBG_CC_NP_CNP_PRIO,
+	MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP_VALID,
+	MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP,
 	MLX5_IB_DBG_CC_MAX,
 };
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 67cfac8fbe46..c63b92aa4c96 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -2159,6 +2159,17 @@ struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits {
 	u8         reserved_at_360[0x4a0];
 };
 
+struct mlx5_ifc_cong_control_r_roce_general_bits {
+	u8         reserved_at_0[0x80];
+
+	u8         reserved_at_80[0x10];
+	u8         rtt_resp_dscp_valid[0x1];
+	u8         reserved_at_91[0x9];
+	u8         rtt_resp_dscp[0x6];
+
+	u8         reserved_at_a0[0x760];
+};
+
 struct mlx5_ifc_cong_control_802_1qau_rp_bits {
 	u8         reserved_at_0[0x80];
 
@@ -4304,6 +4315,7 @@ union mlx5_ifc_cong_control_roce_ecn_auto_bits {
 	struct mlx5_ifc_cong_control_802_1qau_rp_bits cong_control_802_1qau_rp;
 	struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits cong_control_r_roce_ecn_rp;
 	struct mlx5_ifc_cong_control_r_roce_ecn_np_bits cong_control_r_roce_ecn_np;
+	struct mlx5_ifc_cong_control_r_roce_general_bits cong_control_r_roce_general;
 	u8         reserved_at_0[0x800];
 };
 
-- 
cgit v1.2.3