* [PATCH rdma-next v2 1/5] RDMA/mana_ib: Optimize shadow queue bookkeeping
2026-09-18 14:04 [PATCH rdma-next v2 0/5] RDMA/mana_ib: Streamline kernel UD/GSI posting and completion handling Konstantin Taranov
@ 2026-09-18 14:04 ` Konstantin Taranov
2026-09-18 14:04 ` [PATCH rdma-next v2 2/5] RDMA/mana_ib: Revise UD send posting and WQE definitions Konstantin Taranov
` (3 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Konstantin Taranov @ 2026-09-18 14:04 UTC (permalink / raw)
To: kotaranov, snsanghvi, longli, jgg, leon; +Cc: linux-rdma, linux-kernel
From: Konstantin Taranov <kotaranov@microsoft.com>
Use compact bitfields for the posted WQE size and send opcode. Flatten
the UD receive shadow entry into the common shadow_wqe_header, retaining
byte_len, src_qpn and the cached status until direct-CQE polling replaces
their readers. Use this common entry for both send and receive queues,
including allocation, posting, CQE handling and WC generation. Derive
the receive WC opcode from the queue rather than storing it per WQE.
Publish initialized entries and release consumed entries with matching
release/acquire operations so posting and polling can run on different
CPUs. Retain the legacy completion cursor until direct-CQE polling and
software flush lists replace it.
Signed-off-by: Konstantin Taranov <kotaranov@microsoft.com>
---
drivers/infiniband/hw/mana/cq.c | 35 ++++++++++++-----------
drivers/infiniband/hw/mana/qp.c | 4 +--
drivers/infiniband/hw/mana/shadow_queue.h | 29 +++++++++----------
drivers/infiniband/hw/mana/wr.c | 15 +++++-----
4 files changed, 40 insertions(+), 43 deletions(-)
diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c
index 6f9ac8b4a..14a48409e 100644
--- a/drivers/infiniband/hw/mana/cq.c
+++ b/drivers/infiniband/hw/mana/cq.c
@@ -190,15 +190,15 @@ static inline void handle_ud_sq_cqe(struct mana_ib_qp *qp, struct gdma_comp *cqe
{
struct mana_rdma_cqe *rdma_cqe = (struct mana_rdma_cqe *)cqe->cqe_data;
struct gdma_queue *wq = qp->ud_qp.queues[MANA_UD_SEND_QUEUE].kmem;
- struct ud_sq_shadow_wqe *shadow_wqe;
+ struct shadow_wqe_header *shadow_wqe;
shadow_wqe = shadow_queue_get_next_to_complete(&qp->shadow_sq);
if (!shadow_wqe)
return;
- shadow_wqe->header.error_code = rdma_cqe->ud_send.vendor_error;
+ shadow_wqe->error_code = rdma_cqe->ud_send.vendor_error;
- wq->tail += shadow_wqe->header.posted_wqe_size;
+ wq->tail += shadow_wqe->wqe_size_in_bu;
shadow_queue_advance_next_to_complete(&qp->shadow_sq);
}
@@ -206,7 +206,7 @@ static inline void handle_ud_rq_cqe(struct mana_ib_qp *qp, struct gdma_comp *cqe
{
struct mana_rdma_cqe *rdma_cqe = (struct mana_rdma_cqe *)cqe->cqe_data;
struct gdma_queue *wq = qp->ud_qp.queues[MANA_UD_RECV_QUEUE].kmem;
- struct ud_rq_shadow_wqe *shadow_wqe;
+ struct shadow_wqe_header *shadow_wqe;
shadow_wqe = shadow_queue_get_next_to_complete(&qp->shadow_rq);
if (!shadow_wqe)
@@ -214,9 +214,9 @@ static inline void handle_ud_rq_cqe(struct mana_ib_qp *qp, struct gdma_comp *cqe
shadow_wqe->byte_len = rdma_cqe->ud_recv.msg_len;
shadow_wqe->src_qpn = rdma_cqe->ud_recv.src_qpn;
- shadow_wqe->header.error_code = IB_WC_SUCCESS;
+ shadow_wqe->error_code = IB_WC_SUCCESS;
- wq->tail += shadow_wqe->header.posted_wqe_size;
+ wq->tail += shadow_wqe->wqe_size_in_bu;
shadow_queue_advance_next_to_complete(&qp->shadow_rq);
}
@@ -238,21 +238,20 @@ static void mana_handle_cqe(struct mana_ib_dev *mdev, struct gdma_comp *cqe)
}
static void fill_verbs_from_shadow_wqe(struct mana_ib_qp *qp, struct ib_wc *wc,
- const struct shadow_wqe_header *shadow_wqe)
+ const struct shadow_wqe_header *shadow_wqe,
+ enum ib_wc_opcode opcode)
{
- const struct ud_rq_shadow_wqe *ud_wqe = (const struct ud_rq_shadow_wqe *)shadow_wqe;
-
wc->wr_id = shadow_wqe->wr_id;
wc->status = shadow_wqe->error_code;
- wc->opcode = shadow_wqe->opcode;
+ wc->opcode = opcode;
wc->vendor_err = shadow_wqe->error_code;
wc->wc_flags = 0;
wc->qp = &qp->ibqp;
wc->pkey_index = 0;
- if (shadow_wqe->opcode == IB_WC_RECV) {
- wc->byte_len = ud_wqe->byte_len;
- wc->src_qp = ud_wqe->src_qpn;
+ if (opcode == IB_WC_RECV) {
+ wc->byte_len = shadow_wqe->byte_len;
+ wc->src_qp = shadow_wqe->src_qpn;
wc->wc_flags |= IB_WC_GRH;
}
}
@@ -270,7 +269,8 @@ static int mana_process_completions(struct mana_ib_cq *cq, int nwc, struct ib_wc
if (wc_index >= nwc)
goto out;
- fill_verbs_from_shadow_wqe(qp, &wc[wc_index], shadow_wqe);
+ fill_verbs_from_shadow_wqe(qp, &wc[wc_index], shadow_wqe,
+ shadow_wqe->send_opcode);
shadow_queue_advance_consumer(&qp->shadow_sq);
wc_index++;
}
@@ -283,7 +283,8 @@ static int mana_process_completions(struct mana_ib_cq *cq, int nwc, struct ib_wc
if (wc_index >= nwc)
goto out;
- fill_verbs_from_shadow_wqe(qp, &wc[wc_index], shadow_wqe);
+ fill_verbs_from_shadow_wqe(qp, &wc[wc_index], shadow_wqe,
+ IB_WC_RECV);
shadow_queue_advance_consumer(&qp->shadow_rq);
wc_index++;
}
@@ -296,13 +297,13 @@ static int mana_process_completions(struct mana_ib_cq *cq, int nwc, struct ib_wc
static void mana_drain_gsi_sq(struct mana_ib_qp *qp)
{
struct mana_ib_cq *cq = container_of(qp->ibqp.send_cq, struct mana_ib_cq, ibcq);
- struct ud_sq_shadow_wqe *shadow_wqe;
+ struct shadow_wqe_header *shadow_wqe;
unsigned long flags;
spin_lock_irqsave(&cq->cq_lock, flags);
while ((shadow_wqe = shadow_queue_get_next_to_complete(&qp->shadow_sq))
!= NULL) {
- shadow_wqe->header.error_code = IB_WC_GENERAL_ERR;
+ shadow_wqe->error_code = IB_WC_GENERAL_ERR;
shadow_queue_advance_next_to_complete(&qp->shadow_sq);
}
spin_unlock_irqrestore(&cq->cq_lock, flags);
diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c
index fac43b3a5..79c9cc944 100644
--- a/drivers/infiniband/hw/mana/qp.c
+++ b/drivers/infiniband/hw/mana/qp.c
@@ -748,13 +748,13 @@ static int mana_ib_create_ud_qp(struct ib_qp *ibqp, struct ib_pd *ibpd,
doorbell = mdev->gdma_dev->doorbell;
err = create_shadow_queue(&qp->shadow_rq, attr->cap.max_recv_wr,
- sizeof(struct ud_rq_shadow_wqe));
+ sizeof(struct shadow_wqe_header));
if (err) {
ibdev_err(&mdev->ib_dev, "Failed to create shadow rq err %d\n", err);
goto destroy_queues;
}
err = create_shadow_queue(&qp->shadow_sq, attr->cap.max_send_wr,
- sizeof(struct ud_sq_shadow_wqe));
+ sizeof(struct shadow_wqe_header));
if (err) {
ibdev_err(&mdev->ib_dev, "Failed to create shadow sq err %d\n", err);
goto destroy_shadow_queues;
diff --git a/drivers/infiniband/hw/mana/shadow_queue.h b/drivers/infiniband/hw/mana/shadow_queue.h
index a4b3818f9..a127edf7a 100644
--- a/drivers/infiniband/hw/mana/shadow_queue.h
+++ b/drivers/infiniband/hw/mana/shadow_queue.h
@@ -7,22 +7,14 @@
#define _MANA_SHADOW_QUEUE_H_
struct shadow_wqe_header {
- u16 opcode;
- u16 error_code;
- u32 posted_wqe_size;
u64 wr_id;
-};
-
-struct ud_rq_shadow_wqe {
- struct shadow_wqe_header header;
+ u64 wqe_size_in_bu : 8;
+ u64 send_opcode : 4;
+ u64 error_code : 16;
u32 byte_len;
u32 src_qpn;
};
-struct ud_sq_shadow_wqe {
- struct shadow_wqe_header header;
-};
-
struct shadow_queue {
/* Unmasked producer index, Incremented on wqe posting */
u64 prod_idx;
@@ -57,12 +49,14 @@ static inline void destroy_shadow_queue(struct shadow_queue *queue)
static inline bool shadow_queue_full(struct shadow_queue *queue)
{
- return (queue->prod_idx - queue->cons_idx) >= queue->length;
+ /* Do not reuse an entry until the poller has finished reading it. */
+ return (queue->prod_idx - smp_load_acquire(&queue->cons_idx)) >= queue->length;
}
static inline bool shadow_queue_empty(struct shadow_queue *queue)
{
- return queue->prod_idx == queue->cons_idx;
+ /* Pair with posting's release of the initialized shadow WQE. */
+ return smp_load_acquire(&queue->prod_idx) == queue->cons_idx;
}
static inline void *
@@ -91,7 +85,8 @@ shadow_queue_get_next_to_consume(const struct shadow_queue *queue)
static inline void *
shadow_queue_get_next_to_complete(struct shadow_queue *queue)
{
- if (queue->next_to_complete_idx == queue->prod_idx)
+ /* Observe initialized WQE fields published by the posting CPU. */
+ if (queue->next_to_complete_idx == smp_load_acquire(&queue->prod_idx))
return NULL;
return shadow_queue_get_element(queue, queue->next_to_complete_idx);
@@ -99,12 +94,14 @@ shadow_queue_get_next_to_complete(struct shadow_queue *queue)
static inline void shadow_queue_advance_producer(struct shadow_queue *queue)
{
- queue->prod_idx++;
+ /* Publish all WQE fields to CQ polling on another CPU. */
+ smp_store_release(&queue->prod_idx, queue->prod_idx + 1);
}
static inline void shadow_queue_advance_consumer(struct shadow_queue *queue)
{
- queue->cons_idx++;
+ /* Finish WC generation and queue-tail updates before allowing reuse. */
+ smp_store_release(&queue->cons_idx, queue->cons_idx + 1);
}
static inline void shadow_queue_advance_next_to_complete(struct shadow_queue *queue)
diff --git a/drivers/infiniband/hw/mana/wr.c b/drivers/infiniband/hw/mana/wr.c
index 36a1d506f..8cd2980d4 100644
--- a/drivers/infiniband/hw/mana/wr.c
+++ b/drivers/infiniband/hw/mana/wr.c
@@ -14,7 +14,7 @@ static int mana_ib_post_recv_ud(struct mana_ib_qp *qp, const struct ib_recv_wr *
struct gdma_posted_wqe_info wqe_info = {0};
struct gdma_sge gdma_sgl[MAX_WR_SGL_NUM];
struct gdma_wqe_request wqe_req = {0};
- struct ud_rq_shadow_wqe *shadow_wqe;
+ struct shadow_wqe_header *shadow_wqe;
int err, i;
if (shadow_queue_full(&qp->shadow_rq))
@@ -37,9 +37,8 @@ static int mana_ib_post_recv_ud(struct mana_ib_qp *qp, const struct ib_recv_wr *
shadow_wqe = shadow_queue_producer_entry(&qp->shadow_rq);
memset(shadow_wqe, 0, sizeof(*shadow_wqe));
- shadow_wqe->header.opcode = IB_WC_RECV;
- shadow_wqe->header.wr_id = wr->wr_id;
- shadow_wqe->header.posted_wqe_size = wqe_info.wqe_size_in_bu;
+ shadow_wqe->wr_id = wr->wr_id;
+ shadow_wqe->wqe_size_in_bu = wqe_info.wqe_size_in_bu;
shadow_queue_advance_producer(&qp->shadow_rq);
mana_gd_wq_ring_doorbell(mdev_to_gc(mdev), queue);
@@ -82,7 +81,7 @@ static int mana_ib_post_send_ud(struct mana_ib_qp *qp, const struct ib_ud_wr *wr
struct gdma_posted_wqe_info wqe_info = {0};
struct gdma_wqe_request wqe_req = {0};
struct rdma_send_oob send_oob = {0};
- struct ud_sq_shadow_wqe *shadow_wqe;
+ struct shadow_wqe_header *shadow_wqe;
int err, i;
if (!ndev) {
@@ -132,9 +131,9 @@ static int mana_ib_post_send_ud(struct mana_ib_qp *qp, const struct ib_ud_wr *wr
qp->ud_qp.sq_psn++;
shadow_wqe = shadow_queue_producer_entry(&qp->shadow_sq);
memset(shadow_wqe, 0, sizeof(*shadow_wqe));
- shadow_wqe->header.opcode = IB_WC_SEND;
- shadow_wqe->header.wr_id = wr->wr.wr_id;
- shadow_wqe->header.posted_wqe_size = wqe_info.wqe_size_in_bu;
+ shadow_wqe->send_opcode = IB_WC_SEND;
+ shadow_wqe->wr_id = wr->wr.wr_id;
+ shadow_wqe->wqe_size_in_bu = wqe_info.wqe_size_in_bu;
shadow_queue_advance_producer(&qp->shadow_sq);
mana_gd_wq_ring_doorbell(mdev_to_gc(mdev), queue);
--
2.43.0
^ permalink raw reply [flat|nested] 6+ messages in thread* [PATCH rdma-next v2 2/5] RDMA/mana_ib: Revise UD send posting and WQE definitions
2026-09-18 14:04 [PATCH rdma-next v2 0/5] RDMA/mana_ib: Streamline kernel UD/GSI posting and completion handling Konstantin Taranov
2026-09-18 14:04 ` [PATCH rdma-next v2 1/5] RDMA/mana_ib: Optimize shadow queue bookkeeping Konstantin Taranov
@ 2026-09-18 14:04 ` Konstantin Taranov
2026-09-18 14:04 ` [PATCH rdma-next v2 3/5] RDMA/mana_ib: Revise UD receive posting with GDMA_WR_IB_SGL Konstantin Taranov
` (2 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Konstantin Taranov @ 2026-09-18 14:04 UTC (permalink / raw)
To: kotaranov, snsanghvi, longli, jgg, leon; +Cc: linux-rdma, linux-kernel
From: Konstantin Taranov <kotaranov@microsoft.com>
Batch a linked list of UD or GSI send requests behind one doorbell,
returning the first failed WR while publishing all successful entries.
Move the send PSN into common QP state and describe the extended RDMA
send and receive OOB layouts needed by subsequent RC support.
Keep UD's inline OOB explicitly at INLINE_OOB_LARGE_SIZE even though
the shared software OOB structure now describes larger formats. UD
therefore continues using the existing GDMA encoder; extended GDMA
WQE encoding and RC feature gating remain in their later patches.
Signed-off-by: Konstantin Taranov <kotaranov@microsoft.com>
---
drivers/infiniband/hw/mana/mana_ib.h | 40 ++++++++++++++++++-
drivers/infiniband/hw/mana/wr.c | 58 ++++++++++++++++------------
2 files changed, 72 insertions(+), 26 deletions(-)
diff --git a/drivers/infiniband/hw/mana/mana_ib.h b/drivers/infiniband/hw/mana/mana_ib.h
index 4da110b30..619578f16 100644
--- a/drivers/infiniband/hw/mana/mana_ib.h
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -206,7 +206,6 @@ enum mana_ud_queue_type {
struct mana_ib_ud_qp {
struct mana_ib_queue queues[MANA_UD_QUEUE_TYPE_MAX];
- u32 sq_psn;
};
struct mana_ib_qp {
@@ -222,6 +221,7 @@ struct mana_ib_qp {
/* The port on the IB device, starting with 1 */
u32 port;
+ u32 sq_psn;
struct list_head cq_send_list;
struct list_head cq_recv_list;
@@ -525,7 +525,16 @@ struct mana_rnic_set_qp_state_resp {
enum WQE_OPCODE_TYPES {
WQE_TYPE_UD_SEND = 0,
+ WQE_TYPE_RC_SEND = 2,
+ WQE_TYPE_RC_SEND_IMM = 3,
+ WQE_TYPE_RC_SEND_INV = 4,
+ WQE_TYPE_WRITE = 5,
+ WQE_TYPE_WRITE_IMM = 6,
+ WQE_TYPE_READ = 7,
WQE_TYPE_UD_RECV = 8,
+ WQE_TYPE_RC_RECV = 9,
+ WQE_TYPE_REG_MR = 10,
+ WQE_TYPE_LOCAL_INV = 12,
}; /* HW DATA */
struct rdma_send_oob {
@@ -544,7 +553,36 @@ struct rdma_send_oob {
u32 reserved1;
u32 reserved2;
} ud_send;
+ union {
+ u32 immediate;
+ u32 invalidate_key;
+ } rc_send;
+ struct {
+ u32 address_hi;
+ u32 address_low;
+ u32 rkey;
+ u32 dma_len;
+ } rdma;
+ struct {
+ u32 mkey;
+ } mm;
};
+ union {
+ u32 immediate_ext;
+ struct {
+ u16 rsn;
+ u16 reserved;
+ } read;
+ };
+ u32 fsn : 24;
+ u32 reserved2 : 8;
+}; /* HW DATA */
+
+struct rdma_recv_oob {
+ u32 psn_start : 24;
+ u32 reserved1 : 8;
+ u32 msn : 24;
+ u32 reserved2 : 8;
}; /* HW DATA */
struct mana_rdma_cqe {
diff --git a/drivers/infiniband/hw/mana/wr.c b/drivers/infiniband/hw/mana/wr.c
index 8cd2980d4..f25df2fad 100644
--- a/drivers/infiniband/hw/mana/wr.c
+++ b/drivers/infiniband/hw/mana/wr.c
@@ -71,7 +71,7 @@ int mana_ib_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
return err;
}
-static int mana_ib_post_send_ud(struct mana_ib_qp *qp, const struct ib_ud_wr *wr)
+static int mana_ib_post_send_ud_one(struct mana_ib_qp *qp, const struct ib_ud_wr *wr)
{
struct mana_ib_dev *mdev = container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev);
struct mana_ib_ah *ah = container_of(wr->ah, struct mana_ib_ah, ibah);
@@ -84,11 +84,8 @@ static int mana_ib_post_send_ud(struct mana_ib_qp *qp, const struct ib_ud_wr *wr
struct shadow_wqe_header *shadow_wqe;
int err, i;
- if (!ndev) {
- ibdev_dbg(&mdev->ib_dev, "Invalid port %u in QP %u\n",
- qp->port, qp->ibqp.qp_num);
+ if (!ndev)
return -EINVAL;
- }
if (wr->wr.opcode != IB_WR_SEND)
return -EINVAL;
@@ -110,7 +107,7 @@ static int mana_ib_post_send_ud(struct mana_ib_qp *qp, const struct ib_ud_wr *wr
wqe_req.num_sge = wr->wr.num_sge + 1;
wqe_req.sgl = gdma_sgl;
- wqe_req.inline_oob_size = sizeof(struct rdma_send_oob);
+ wqe_req.inline_oob_size = INLINE_OOB_LARGE_SIZE;
wqe_req.inline_oob_data = &send_oob;
wqe_req.flags = GDMA_WR_OOB_IN_SGL;
wqe_req.client_data_unit = ib_mtu_enum_to_int(ib_mtu_int_to_enum(ndev->mtu));
@@ -119,7 +116,7 @@ static int mana_ib_post_send_ud(struct mana_ib_qp *qp, const struct ib_ud_wr *wr
send_oob.fence = !!(wr->wr.send_flags & IB_SEND_FENCE);
send_oob.signaled = !!(wr->wr.send_flags & IB_SEND_SIGNALED);
send_oob.solicited = !!(wr->wr.send_flags & IB_SEND_SOLICITED);
- send_oob.psn = qp->ud_qp.sq_psn;
+ send_oob.psn = qp->sq_psn;
send_oob.ssn_or_rqpn = wr->remote_qpn;
send_oob.ud_send.remote_qkey =
qp->ibqp.qp_type == IB_QPT_GSI ? IB_QP1_QKEY : wr->remote_qkey;
@@ -128,40 +125,51 @@ static int mana_ib_post_send_ud(struct mana_ib_qp *qp, const struct ib_ud_wr *wr
if (err)
return err;
- qp->ud_qp.sq_psn++;
+ qp->sq_psn++;
shadow_wqe = shadow_queue_producer_entry(&qp->shadow_sq);
memset(shadow_wqe, 0, sizeof(*shadow_wqe));
- shadow_wqe->send_opcode = IB_WC_SEND;
shadow_wqe->wr_id = wr->wr.wr_id;
shadow_wqe->wqe_size_in_bu = wqe_info.wqe_size_in_bu;
shadow_queue_advance_producer(&qp->shadow_sq);
- mana_gd_wq_ring_doorbell(mdev_to_gc(mdev), queue);
return 0;
}
-int mana_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
- const struct ib_send_wr **bad_wr)
+static int mana_ib_post_send_ud(struct mana_ib_qp *qp, const struct ib_send_wr *wr,
+ const struct ib_send_wr **bad_wr)
{
+ struct mana_ib_dev *mdev = container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev);
+ struct gdma_queue *queue = qp->ud_qp.queues[MANA_UD_SEND_QUEUE].kmem;
+ bool ring_sq = false;
int err = 0;
- struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
for (; wr; wr = wr->next) {
- switch (ibqp->qp_type) {
- case IB_QPT_UD:
- case IB_QPT_GSI:
- err = mana_ib_post_send_ud(qp, ud_wr(wr));
- if (unlikely(err)) {
- *bad_wr = wr;
- return err;
- }
+ err = mana_ib_post_send_ud_one(qp, ud_wr(wr));
+ if (unlikely(err)) {
+ *bad_wr = wr;
break;
- default:
- ibdev_dbg(ibqp->device, "Posting send wr on qp type %u is not supported\n",
- ibqp->qp_type);
- return -EINVAL;
}
+ ring_sq = true;
}
+ if (ring_sq)
+ mana_gd_wq_ring_doorbell(mdev_to_gc(mdev), queue);
+
return err;
}
+
+int mana_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
+ const struct ib_send_wr **bad_wr)
+{
+ struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
+
+ switch (ibqp->qp_type) {
+ case IB_QPT_UD:
+ case IB_QPT_GSI:
+ return mana_ib_post_send_ud(qp, wr, bad_wr);
+ default:
+ /* Unsupported QP type */
+ *bad_wr = wr;
+ return -EINVAL;
+ }
+}
--
2.43.0
^ permalink raw reply [flat|nested] 6+ messages in thread* [PATCH rdma-next v2 3/5] RDMA/mana_ib: Revise UD receive posting with GDMA_WR_IB_SGL
2026-09-18 14:04 [PATCH rdma-next v2 0/5] RDMA/mana_ib: Streamline kernel UD/GSI posting and completion handling Konstantin Taranov
2026-09-18 14:04 ` [PATCH rdma-next v2 1/5] RDMA/mana_ib: Optimize shadow queue bookkeeping Konstantin Taranov
2026-09-18 14:04 ` [PATCH rdma-next v2 2/5] RDMA/mana_ib: Revise UD send posting and WQE definitions Konstantin Taranov
@ 2026-09-18 14:04 ` Konstantin Taranov
2026-09-18 14:04 ` [PATCH rdma-next v2 4/5] RDMA/mana_ib: Make kernel CQ arming robust Konstantin Taranov
2026-09-18 14:04 ` [PATCH rdma-next v2 5/5] RDMA/mana_ib: Poll UD completions and flush software error QPs Konstantin Taranov
4 siblings, 0 replies; 6+ messages in thread
From: Konstantin Taranov @ 2026-09-18 14:04 UTC (permalink / raw)
To: kotaranov, snsanghvi, longli, jgg, leon; +Cc: linux-rdma, linux-kernel
From: Konstantin Taranov <kotaranov@microsoft.com>
Pass receive verbs SGEs directly to GDMA instead of copying them into
a small stack array. Accept the receive SGE limit, supply a dummy SGE
for zero-length requests, and ring once after each successful batch.
Introduce GDMA_WR_IB_SGL, its request union, and the wrap-aware verbs
SGE writer together with their first consumer. These shared GDMA pieces
must precede the later extended-WQE patch so this receive path does not
depend on definitions or encoding support introduced after it.
Address verbs SGEs by ring offset so both scattered-page boundaries and
ring wrap preserve the local kernel baseline's non-contiguous buffers.
Signed-off-by: Konstantin Taranov <kotaranov@microsoft.com>
---
drivers/infiniband/hw/mana/wr.c | 70 +++++++++++--------
.../net/ethernet/microsoft/mana/gdma_main.c | 23 +++++-
include/net/mana/gdma.h | 7 +-
3 files changed, 70 insertions(+), 30 deletions(-)
diff --git a/drivers/infiniband/hw/mana/wr.c b/drivers/infiniband/hw/mana/wr.c
index f25df2fad..eb671b45b 100644
--- a/drivers/infiniband/hw/mana/wr.c
+++ b/drivers/infiniband/hw/mana/wr.c
@@ -7,29 +7,30 @@
#define MAX_WR_SGL_NUM (2)
-static int mana_ib_post_recv_ud(struct mana_ib_qp *qp, const struct ib_recv_wr *wr)
+static int mana_ib_post_rq(struct mana_ib_qp *qp, const struct ib_recv_wr *wr)
{
- struct mana_ib_dev *mdev = container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev);
- struct gdma_queue *queue = qp->ud_qp.queues[MANA_UD_RECV_QUEUE].kmem;
+ struct ib_sge mana_ib_dummy_sge = {.addr = 1, .length = 0, .lkey = 0};
+ struct mana_ib_queue *ib_rq = mana_qp_get_rq(qp);
struct gdma_posted_wqe_info wqe_info = {0};
- struct gdma_sge gdma_sgl[MAX_WR_SGL_NUM];
+ struct gdma_queue *queue = ib_rq->kmem;
struct gdma_wqe_request wqe_req = {0};
struct shadow_wqe_header *shadow_wqe;
- int err, i;
+ int err;
if (shadow_queue_full(&qp->shadow_rq))
return -EINVAL;
- if (wr->num_sge > MAX_WR_SGL_NUM)
+ if (wr->num_sge > MAX_RX_WQE_SGL_ENTRIES)
return -EINVAL;
- for (i = 0; i < wr->num_sge; ++i) {
- gdma_sgl[i].address = wr->sg_list[i].addr;
- gdma_sgl[i].mem_key = wr->sg_list[i].lkey;
- gdma_sgl[i].size = wr->sg_list[i].length;
- }
wqe_req.num_sge = wr->num_sge;
- wqe_req.sgl = gdma_sgl;
+ wqe_req.ib_sgl = wr->sg_list;
+ wqe_req.flags = GDMA_WR_IB_SGL;
+
+ if (wr->num_sge == 0) {
+ wqe_req.ib_sgl = &mana_ib_dummy_sge;
+ wqe_req.num_sge = 1;
+ }
err = mana_gd_post_work_request(queue, &wqe_req, &wqe_info);
if (err)
@@ -41,36 +42,49 @@ static int mana_ib_post_recv_ud(struct mana_ib_qp *qp, const struct ib_recv_wr *
shadow_wqe->wqe_size_in_bu = wqe_info.wqe_size_in_bu;
shadow_queue_advance_producer(&qp->shadow_rq);
- mana_gd_wq_ring_doorbell(mdev_to_gc(mdev), queue);
return 0;
}
-int mana_ib_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
- const struct ib_recv_wr **bad_wr)
+static int mana_ib_post_recv_ud(struct mana_ib_qp *qp, const struct ib_recv_wr *wr,
+ const struct ib_recv_wr **bad_wr)
{
- struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
+ struct mana_ib_dev *mdev = container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev);
+ struct mana_ib_queue *ib_rq = mana_qp_get_rq(qp);
+ struct gdma_queue *rq = ib_rq->kmem;
+ bool ring_rq = false;
int err = 0;
for (; wr; wr = wr->next) {
- switch (ibqp->qp_type) {
- case IB_QPT_UD:
- case IB_QPT_GSI:
- err = mana_ib_post_recv_ud(qp, wr);
- if (unlikely(err)) {
- *bad_wr = wr;
- return err;
- }
+ err = mana_ib_post_rq(qp, wr);
+ if (unlikely(err)) {
+ *bad_wr = wr;
break;
- default:
- ibdev_dbg(ibqp->device, "Posting recv wr on qp type %u is not supported\n",
- ibqp->qp_type);
- return -EINVAL;
}
+ ring_rq = true;
}
+ if (ring_rq)
+ mana_gd_wq_ring_doorbell(mdev_to_gc(mdev), rq);
+
return err;
}
+int mana_ib_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
+ const struct ib_recv_wr **bad_wr)
+{
+ struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
+
+ switch (ibqp->qp_type) {
+ case IB_QPT_UD:
+ case IB_QPT_GSI:
+ return mana_ib_post_recv_ud(qp, wr, bad_wr);
+ default:
+ /* Unsupported QP type */
+ *bad_wr = wr;
+ return -EINVAL;
+ }
+}
+
static int mana_ib_post_send_ud_one(struct mana_ib_qp *qp, const struct ib_ud_wr *wr)
{
struct mana_ib_dev *mdev = container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev);
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index f92b2d0bf..542491a6c 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1738,6 +1738,24 @@ static void mana_gd_write_sgl(struct gdma_queue *wq, u32 sgl_offset,
memcpy(mana_gd_ring_ptr(wq, sgl_offset), address, sgl_size);
}
+static void mana_gd_write_ib_sgl(struct gdma_queue *wq, u32 sgl_offset,
+ const struct gdma_wqe_request *wqe_req)
+{
+ const struct ib_sge *sge = wqe_req->ib_sgl;
+ struct gdma_sge *gdma_sgl;
+ u32 i;
+
+ for (i = 0; i < wqe_req->num_sge; ++i, ++sge) {
+ gdma_sgl = mana_gd_ring_ptr(wq, sgl_offset);
+ gdma_sgl->address = sge->addr;
+ gdma_sgl->size = sge->length;
+ gdma_sgl->mem_key = sge->lkey;
+ sgl_offset += sizeof(*gdma_sgl);
+ if (sgl_offset == wq->queue_size)
+ sgl_offset = 0;
+ }
+}
+
int mana_gd_post_work_request(struct gdma_queue *wq,
const struct gdma_wqe_request *wqe_req,
struct gdma_posted_wqe_info *wqe_info)
@@ -1792,7 +1810,10 @@ int mana_gd_post_work_request(struct gdma_queue *wq,
if (sgl_offset >= wq->queue_size)
sgl_offset -= wq->queue_size;
- mana_gd_write_sgl(wq, sgl_offset, wqe_req);
+ if (wqe_req->flags & GDMA_WR_IB_SGL)
+ mana_gd_write_ib_sgl(wq, sgl_offset, wqe_req);
+ else
+ mana_gd_write_sgl(wq, sgl_offset, wqe_req);
wq->head += wqe_size / GDMA_WQE_BU_SIZE;
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 06af65d50..8ccbe2d57 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -6,6 +6,7 @@
#include <linux/dma-mapping.h>
#include <linux/netdevice.h>
+#include <rdma/ib_verbs.h>
#include "shm_channel.h"
@@ -54,6 +55,7 @@ enum gdma_work_request_flags {
GDMA_WR_NONE = 0,
GDMA_WR_OOB_IN_SGL = BIT(0),
GDMA_WR_PAD_BY_SGE0 = BIT(1),
+ GDMA_WR_IB_SGL = BIT(2),
};
enum gdma_eqe_type {
@@ -212,7 +214,10 @@ struct gdma_sge {
}; /* HW DATA */
struct gdma_wqe_request {
- struct gdma_sge *sgl;
+ union {
+ struct gdma_sge *sgl;
+ struct ib_sge *ib_sgl;
+ };
u32 num_sge;
u32 inline_oob_size;
--
2.43.0
^ permalink raw reply [flat|nested] 6+ messages in thread* [PATCH rdma-next v2 4/5] RDMA/mana_ib: Make kernel CQ arming robust
2026-09-18 14:04 [PATCH rdma-next v2 0/5] RDMA/mana_ib: Streamline kernel UD/GSI posting and completion handling Konstantin Taranov
` (2 preceding siblings ...)
2026-09-18 14:04 ` [PATCH rdma-next v2 3/5] RDMA/mana_ib: Revise UD receive posting with GDMA_WR_IB_SGL Konstantin Taranov
@ 2026-09-18 14:04 ` Konstantin Taranov
2026-09-18 14:04 ` [PATCH rdma-next v2 5/5] RDMA/mana_ib: Poll UD completions and flush software error QPs Konstantin Taranov
4 siblings, 0 replies; 6+ messages in thread
From: Konstantin Taranov @ 2026-09-18 14:04 UTC (permalink / raw)
To: kotaranov, snsanghvi, longli, jgg, leon; +Cc: linux-rdma, linux-kernel
From: Konstantin Taranov <kotaranov@microsoft.com>
Track CQ polling credits across owner-bit wraps and serialize arming
with polling under cq_lock. Check the relevant owner bits before
advancing an outstanding arm, and update the hardware consumer position
when polling exhausts its credits.
Expose the allocated CQ capacity to the core. Pull the explicit-index
GDMA doorbell helper and its declaration forward here because CQ arming
is its first consumer; ordinary GDMA doorbells retain their zero client
offset. RC-specific PSN doorbell use is introduced later.
Preserve the baseline's dynamic interrupt moderation doorbell with a
zero client offset. Read CQ owner bits through the scattered backing
pages when the queue allocation falls back to non-contiguous memory.
Signed-off-by: Konstantin Taranov <kotaranov@microsoft.com>
---
drivers/infiniband/hw/mana/cq.c | 55 ++++++++++++++++++-
drivers/infiniband/hw/mana/mana_ib.h | 1 +
.../net/ethernet/microsoft/mana/gdma_main.c | 20 +++++--
include/net/mana/gdma.h | 2 +
4 files changed, 72 insertions(+), 6 deletions(-)
diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c
index 14a48409e..6764e2de0 100644
--- a/drivers/infiniband/hw/mana/cq.c
+++ b/drivers/infiniband/hw/mana/cq.c
@@ -64,6 +64,9 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
doorbell = mdev->gdma_dev->doorbell;
}
+ ibcq->cqe = cq->cqe;
+ cq->poll_credit = (cq->cqe << (GDMA_CQE_OWNER_BITS - 1)) - 1;
+
if (is_rnic_cq) {
err = mana_ib_gd_create_cq(mdev, cq, doorbell);
if (err) {
@@ -174,15 +177,62 @@ void mana_ib_remove_cq_cb(struct mana_ib_dev *mdev, struct mana_ib_cq *cq)
gc->cq_table[cq->queue.id] = NULL;
}
+static inline bool gdma_cq_idx_produced(struct gdma_queue *gdma_cq, uint32_t idx)
+{
+ struct gdma_mem_info *gmi = &gdma_cq->mem_info;
+ u32 num_cqe = gdma_cq->queue_size / GDMA_CQE_SIZE;
+ u32 expected_bits = (idx / num_cqe) & GDMA_CQE_OWNER_MASK;
+ u32 offset = (idx % num_cqe) * GDMA_CQE_SIZE;
+ struct gdma_cqe *cqe;
+
+ if (gmi->nr_pages)
+ cqe = gmi->pages_va[offset / PAGE_SIZE] +
+ (offset & (PAGE_SIZE - 1));
+ else
+ cqe = gdma_cq->queue_mem_ptr + offset;
+
+ return cqe->cqe_info.owner_bits == expected_bits;
+}
+
+static inline void mana_ib_cq_doorbell(struct mana_ib_cq *cq, uint8_t arm)
+{
+ struct mana_ib_dev *mdev = container_of(cq->ibcq.device, struct mana_ib_dev, ib_dev);
+ struct gdma_queue *gdma_cq = cq->queue.kmem;
+ u32 num_cqe, max_credit, idx;
+
+ num_cqe = gdma_cq->queue_size / GDMA_CQE_SIZE;
+ max_credit = num_cqe << (GDMA_CQE_OWNER_BITS - 1);
+ idx = gdma_cq->head;
+
+ if (cq->poll_credit >= max_credit) {
+ if (gdma_cq_idx_produced(gdma_cq, idx + cq->poll_credit - max_credit))
+ cq->poll_credit++;
+ else
+ return;
+ } else {
+ /* Set index of already polled CQE for unarm */
+ cq->poll_credit = max_credit - (arm ? 0 : 1);
+ }
+
+ idx += (cq->poll_credit - max_credit);
+ idx %= (num_cqe << GDMA_CQE_OWNER_BITS);
+
+ mana_gd_wq_ring_doorbell_ext(mdev_to_gc(mdev), gdma_cq, idx, arm, 0);
+}
+
int mana_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
{
struct mana_ib_cq *cq = container_of(ibcq, struct mana_ib_cq, ibcq);
struct gdma_queue *gdma_cq = cq->queue.kmem;
+ unsigned long irq_flags;
if (!gdma_cq)
return -EINVAL;
- mana_gd_ring_cq(gdma_cq, SET_ARM_BIT);
+ spin_lock_irqsave(&cq->cq_lock, irq_flags);
+ mana_ib_cq_doorbell(cq, SET_ARM_BIT);
+ spin_unlock_irqrestore(&cq->cq_lock, irq_flags);
+
return 0;
}
@@ -343,6 +393,9 @@ int mana_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
comp_read = mana_gd_poll_cq(queue, &gdma_cqe, 1);
if (comp_read < 1)
break;
+ cq->poll_credit--;
+ if (!cq->poll_credit)
+ mana_ib_cq_doorbell(cq, 0);
mana_handle_cqe(mdev, &gdma_cqe);
}
diff --git a/drivers/infiniband/hw/mana/mana_ib.h b/drivers/infiniband/hw/mana/mana_ib.h
index 619578f16..0ad757990 100644
--- a/drivers/infiniband/hw/mana/mana_ib.h
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -170,6 +170,7 @@ struct mana_ib_cq {
struct list_head list_recv_qp;
int cqe;
u32 comp_vector;
+ u32 poll_credit;
mana_handle_t cq_handle;
};
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 542491a6c..cb51fcf57 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -559,11 +559,13 @@ static int mana_gd_disable_queue(struct gdma_queue *queue)
static void mana_gd_ring_doorbell(struct gdma_context *gc, u32 db_index,
enum gdma_queue_type q_type, u32 qid,
- u32 tail_ptr, u8 num_req)
+ u32 tail_ptr, u8 num_req, u8 client_offset)
{
void __iomem *addr = gc->db_page_base + gc->db_page_size * db_index;
union gdma_doorbell_entry e = {};
+ addr += client_offset;
+
switch (q_type) {
case GDMA_EQ:
e.eq.id = qid;
@@ -623,10 +625,18 @@ void mana_gd_wq_ring_doorbell(struct gdma_context *gc, struct gdma_queue *queue)
* wqe_cnt for Receive Queues. This value is not used in Send Queues.
*/
mana_gd_ring_doorbell(gc, queue->gdma_dev->doorbell, queue->type,
- queue->id, queue->head * GDMA_WQE_BU_SIZE, 0);
+ queue->id, queue->head * GDMA_WQE_BU_SIZE, 0, 0);
}
EXPORT_SYMBOL_NS(mana_gd_wq_ring_doorbell, "NET_MANA");
+void mana_gd_wq_ring_doorbell_ext(struct gdma_context *gc, struct gdma_queue *queue,
+ u32 tail_ptr, u8 wqe_cnt, u8 client_offset)
+{
+ mana_gd_ring_doorbell(gc, queue->gdma_dev->doorbell, queue->type,
+ queue->id, tail_ptr, wqe_cnt, client_offset);
+}
+EXPORT_SYMBOL_NS(mana_gd_wq_ring_doorbell_ext, "NET_MANA");
+
void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit)
{
struct gdma_context *gc = cq->gdma_dev->gdma_context;
@@ -636,7 +646,7 @@ void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit)
u32 head = cq->head % (num_cqe << GDMA_CQE_OWNER_BITS);
mana_gd_ring_doorbell(gc, cq->gdma_dev->doorbell, cq->type, cq->id,
- head, arm_bit);
+ head, arm_bit, 0);
}
EXPORT_SYMBOL_NS(mana_gd_ring_cq, "NET_MANA");
@@ -653,7 +663,7 @@ void mana_gd_ring_dim(struct gdma_queue *cq, u32 mod_usec, bool mod_usec_vld,
dim_val |= MANA_INTR_MODR_USEC_VLD;
mana_gd_ring_doorbell(gc, cq->gdma_dev->doorbell, GDMA_DIM, cq->id,
- dim_val, mod_comps_vld);
+ dim_val, mod_comps_vld, 0);
}
EXPORT_SYMBOL_NS(mana_gd_ring_dim, "NET_MANA");
@@ -1023,7 +1033,7 @@ static void mana_gd_process_eq_events(void *arg)
head = eq->head % (num_eqe << GDMA_EQE_OWNER_BITS);
mana_gd_ring_doorbell(gc, eq->gdma_dev->doorbell, eq->type, eq->id,
- head, SET_ARM_BIT);
+ head, SET_ARM_BIT, 0);
}
static int mana_gd_register_irq(struct gdma_queue *queue,
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 8ccbe2d57..02632acd7 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -1068,6 +1068,8 @@ void mana_gd_free_res_map(struct gdma_resource *r);
void mana_gd_wq_ring_doorbell(struct gdma_context *gc,
struct gdma_queue *queue);
+void mana_gd_wq_ring_doorbell_ext(struct gdma_context *gc, struct gdma_queue *queue,
+ u32 tail_ptr, u8 wqe_cnt, u8 client_offset);
int mana_gd_alloc_memory(struct gdma_context *gc, unsigned int length,
struct gdma_mem_info *gmi, bool allow_scatter);
--
2.43.0
^ permalink raw reply [flat|nested] 6+ messages in thread* [PATCH rdma-next v2 5/5] RDMA/mana_ib: Poll UD completions and flush software error QPs
2026-09-18 14:04 [PATCH rdma-next v2 0/5] RDMA/mana_ib: Streamline kernel UD/GSI posting and completion handling Konstantin Taranov
` (3 preceding siblings ...)
2026-09-18 14:04 ` [PATCH rdma-next v2 4/5] RDMA/mana_ib: Make kernel CQ arming robust Konstantin Taranov
@ 2026-09-18 14:04 ` Konstantin Taranov
4 siblings, 0 replies; 6+ messages in thread
From: Konstantin Taranov @ 2026-09-18 14:04 UTC (permalink / raw)
To: kotaranov, snsanghvi, longli, jgg, leon; +Cc: linux-rdma, linux-kernel
From: Konstantin Taranov <kotaranov@microsoft.com>
Build UD and GSI work completions directly from each hardware CQE and
the next published shadow entry. Decode receive length, source QP and
immediate data directly, removing byte_len, src_qpn and cached status
from the common shadow header. Translate ordinary UD send vendor status
and introduce a WC-budgeted poll context with a cached CQE for RC polling.
Match UD send and receive CQEs against the low 24 bits of the posted WQE
offset before consuming the shadow entry.
Replace all-QP CQ membership with persistent send and receive error-QP
lists. After hardware polling, retire pending shadow entries with
IB_WC_WR_FLUSH_ERR within the remaining WC budget. Keep error QPs linked
so subsequently posted drain markers can also be completed.
Keep the explicit GSI send drain path responsible for adding the QP to
the send error list and invoking its CQ handler. Serialize modifications,
unlink QPs and reset their shadow queues on a successful RESET, and unlink
them on destruction. Hold the corresponding CQ lock while unlinking and
resetting each shadow queue to serialize RESET with hardware polling and
software flushing. Remove the legacy completion cursor, leaving a compact
16-byte common shadow entry.
Automatic error-list insertion and CQ notification on a successful ERR
transition are introduced separately with RC support. Hardware error-CQE
decoding and deferred QP error handling also remain in the RC series.
Signed-off-by: Konstantin Taranov <kotaranov@microsoft.com>
---
Changes in v2:
- Serialize each shadow queue reset and error-list removal with CQ polling
and software flushing by holding the corresponding CQ lock.
- Return the unmasked WQE start offset from GDMA posting to ignore CQEs
with mismatched low 24-bit WQE offsets.
drivers/infiniband/hw/mana/cq.c | 282 ++++++++++++------
drivers/infiniband/hw/mana/mana_ib.h | 60 +++-
drivers/infiniband/hw/mana/qp.c | 79 +++--
drivers/infiniband/hw/mana/shadow_queue.h | 38 ++-
drivers/infiniband/hw/mana/wr.c | 2 +
.../net/ethernet/microsoft/mana/gdma_main.c | 6 +-
include/net/mana/gdma.h | 2 +
7 files changed, 325 insertions(+), 144 deletions(-)
diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c
index 6764e2de0..55d7a7d1c 100644
--- a/drivers/infiniband/hw/mana/cq.c
+++ b/drivers/infiniband/hw/mana/cq.c
@@ -5,6 +5,58 @@
#include "mana_ib.h"
+static enum ib_wc_status vendor_error_to_wc_error(uint32_t vendor_error)
+{
+ switch (vendor_error) {
+ case VENDOR_ERR_OK:
+ return IB_WC_SUCCESS;
+ case VENDOR_ERR_RX_PKT_LEN:
+ case VENDOR_ERR_RX_MSG_LEN_OVFL:
+ return IB_WC_LOC_LEN_ERR;
+ case VENDOR_ERR_TX_GDMA_CORRUPTED_WQE:
+ case VENDOR_ERR_TX_PCIE_WQE:
+ case VENDOR_ERR_TX_PCIE_MSG:
+ case VENDOR_ERR_RX_MALFORMED_WQE:
+ case VENDOR_ERR_TX_GDMA_INVALID_STATE:
+ case VENDOR_ERR_TX_MISBEHAVING_CLIENT:
+ case VENDOR_ERR_TX_RDMA_MALFORMED_WQE_SIZE:
+ case VENDOR_ERR_TX_RDMA_MALFORMED_WQE_FIELD:
+ case VENDOR_ERR_TX_RDMA_WQE_UNSUPPORTED:
+ case VENDOR_ERR_TX_RDMA_WQE_LEN_ERR:
+ case VENDOR_ERR_TX_RDMA_MTU_ERR:
+ return IB_WC_LOC_QP_OP_ERR;
+ case VENDOR_ERR_TX_ATB_MSG_ACCESS_VIOLATION:
+ case VENDOR_ERR_TX_ATB_MSG_ADDR_RANGE:
+ case VENDOR_ERR_TX_ATB_MSG_CONFIG_ERR:
+ case VENDOR_ERR_TX_ATB_WQE_ACCESS_VIOLATION:
+ case VENDOR_ERR_TX_ATB_WQE_ADDR_RANGE:
+ case VENDOR_ERR_TX_ATB_WQE_CONFIG_ERR:
+ case VENDOR_ERR_RX_ATB_SGE_ADDR_RANGE:
+ case VENDOR_ERR_RX_ATB_SGE_MISSCONFIG:
+ return IB_WC_LOC_PROT_ERR;
+ case VENDOR_ERR_RX_ATB_SGE_ADDR_RIGHT:
+ case VENDOR_ERR_RX_GFID:
+ return IB_WC_LOC_ACCESS_ERR;
+ case VENDOR_ERR_RX_MISBEHAVING_CLIENT:
+ case VENDOR_ERR_RX_CLIENT_ID:
+ case VENDOR_ERR_RX_PCIE:
+ case VENDOR_ERR_RX_NO_AVAIL_WQE:
+ case VENDOR_ERR_RX_ATB_WQE_MISCONFIG:
+ case VENDOR_ERR_RX_ATB_WQE_ADDR_RIGHT:
+ case VENDOR_ERR_RX_ATB_WQE_ADDR_RANGE:
+ case VENDOR_ERR_TX_RDMA_INVALID_STATE:
+ case VENDOR_ERR_TX_RDMA_INVALID_NPT:
+ case VENDOR_ERR_TX_RDMA_INVALID_SGID:
+ case VENDOR_ERR_TX_RDMA_VFID_MISMATCH:
+ return IB_WC_FATAL_ERR;
+ case VENDOR_ERR_RX_NOT_EMPTY_ON_DISABLE:
+ case VENDOR_ERR_SW_FLUSHED:
+ return IB_WC_WR_FLUSH_ERR;
+ default:
+ return IB_WC_GENERAL_ERR;
+ }
+}
+
int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
struct uverbs_attr_bundle *attrs)
{
@@ -89,8 +141,8 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
}
spin_lock_init(&cq->cq_lock);
- INIT_LIST_HEAD(&cq->list_send_qp);
- INIT_LIST_HEAD(&cq->list_recv_qp);
+ INIT_LIST_HEAD(&cq->send_err_qp_list);
+ INIT_LIST_HEAD(&cq->recv_err_qp_list);
return 0;
@@ -236,126 +288,156 @@ int mana_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
return 0;
}
-static inline void handle_ud_sq_cqe(struct mana_ib_qp *qp, struct gdma_comp *cqe)
-{
- struct mana_rdma_cqe *rdma_cqe = (struct mana_rdma_cqe *)cqe->cqe_data;
- struct gdma_queue *wq = qp->ud_qp.queues[MANA_UD_SEND_QUEUE].kmem;
- struct shadow_wqe_header *shadow_wqe;
+struct mana_cq_poll {
+ struct ib_wc *wc;
+ int budget;
+ int produced;
+};
- shadow_wqe = shadow_queue_get_next_to_complete(&qp->shadow_sq);
- if (!shadow_wqe)
- return;
+static struct ib_wc *mana_fill_wc(struct mana_ib_qp *qp,
+ struct mana_cq_poll *poll,
+ const struct shadow_wqe_header *wqe,
+ enum ib_wc_opcode opcode, u32 vendor_error)
+{
+ struct ib_wc *wc = &poll->wc[poll->produced++];
- shadow_wqe->error_code = rdma_cqe->ud_send.vendor_error;
+ memset(wc, 0, sizeof(*wc));
+ wc->wr_id = wqe->wr_id;
+ wc->status = vendor_error_to_wc_error(vendor_error);
+ wc->opcode = opcode;
+ wc->vendor_err = vendor_error;
+ wc->qp = &qp->ibqp;
- wq->tail += shadow_wqe->wqe_size_in_bu;
- shadow_queue_advance_next_to_complete(&qp->shadow_sq);
+ return wc;
}
-static inline void handle_ud_rq_cqe(struct mana_ib_qp *qp, struct gdma_comp *cqe)
+static void mana_complete_send(struct mana_ib_qp *qp,
+ struct mana_cq_poll *poll, u32 vendor_error)
{
- struct mana_rdma_cqe *rdma_cqe = (struct mana_rdma_cqe *)cqe->cqe_data;
- struct gdma_queue *wq = qp->ud_qp.queues[MANA_UD_RECV_QUEUE].kmem;
- struct shadow_wqe_header *shadow_wqe;
+ struct shadow_queue *shadow = &qp->shadow_sq;
+ struct shadow_wqe_header *wqe = shadow_queue_get_next_to_consume(shadow);
+ struct gdma_queue *queue;
- shadow_wqe = shadow_queue_get_next_to_complete(&qp->shadow_rq);
- if (!shadow_wqe)
+ if (!wqe)
return;
- shadow_wqe->byte_len = rdma_cqe->ud_recv.msg_len;
- shadow_wqe->src_qpn = rdma_cqe->ud_recv.src_qpn;
- shadow_wqe->error_code = IB_WC_SUCCESS;
+ if (vendor_error || !(wqe->flags & MANA_WQ_NO_SIGNAL_WC))
+ mana_fill_wc(qp, poll, wqe, wqe->send_opcode, vendor_error);
- wq->tail += shadow_wqe->wqe_size_in_bu;
- shadow_queue_advance_next_to_complete(&qp->shadow_rq);
+ queue = mana_qp_get_sq(qp)->kmem;
+ queue->tail += wqe->wqe_size_in_bu;
+ shadow_queue_advance_consumer(shadow);
}
-static void mana_handle_cqe(struct mana_ib_dev *mdev, struct gdma_comp *cqe)
+static void handle_ud_sq_cqe(struct mana_ib_qp *qp, struct mana_rdma_cqe *rdma_cqe,
+ struct mana_cq_poll *poll)
{
- struct mana_ib_qp *qp = mana_get_qp_ref(mdev, cqe->wq_num, cqe->is_sq);
+ struct shadow_wqe_header *wqe = shadow_queue_get_next_to_consume(&qp->shadow_sq);
+ u32 offset = rdma_cqe->ud_send.tx_wqe_offset & MANA_WQE_OFFSET_MASK;
- if (!qp)
+ if (!wqe || wqe->wqe_offset_or_psn != offset)
return;
- if (qp->ibqp.qp_type == IB_QPT_GSI || qp->ibqp.qp_type == IB_QPT_UD) {
- if (cqe->is_sq)
- handle_ud_sq_cqe(qp, cqe);
- else
- handle_ud_rq_cqe(qp, cqe);
- }
-
- mana_put_qp_ref(qp);
+ mana_complete_send(qp, poll, rdma_cqe->ud_send.vendor_error);
}
-static void fill_verbs_from_shadow_wqe(struct mana_ib_qp *qp, struct ib_wc *wc,
- const struct shadow_wqe_header *shadow_wqe,
- enum ib_wc_opcode opcode)
+static void handle_rq_cqe(struct mana_ib_qp *qp, struct gdma_comp *cqe,
+ struct mana_cq_poll *poll)
{
- wc->wr_id = shadow_wqe->wr_id;
- wc->status = shadow_wqe->error_code;
- wc->opcode = opcode;
- wc->vendor_err = shadow_wqe->error_code;
- wc->wc_flags = 0;
- wc->qp = &qp->ibqp;
- wc->pkey_index = 0;
+ struct mana_rdma_cqe *rdma_cqe = (struct mana_rdma_cqe *)cqe->cqe_data;
+ u32 offset = rdma_cqe->ud_recv.rx_wqe_offset / GDMA_WQE_BU_SIZE;
+ struct mana_ib_queue *rq = mana_qp_get_rq(qp);
+ struct gdma_queue *wq = rq->kmem;
+ struct shadow_wqe_header *wqe;
+ struct ib_wc *wc;
+
+ wqe = shadow_queue_get_next_to_consume(&qp->shadow_rq);
+ if (!wqe || wqe->wqe_offset_or_psn != (offset & MANA_WQE_OFFSET_MASK))
+ return;
- if (opcode == IB_WC_RECV) {
- wc->byte_len = shadow_wqe->byte_len;
- wc->src_qp = shadow_wqe->src_qpn;
+ wc = mana_fill_wc(qp, poll, wqe, IB_WC_RECV, VENDOR_ERR_OK);
+ switch (rdma_cqe->cqe_type) {
+ case CQE_TYPE_UD_SEND_IMM:
+ wc->ex.imm_data = cpu_to_be32(rdma_cqe->ud_recv.imm_data);
+ wc->wc_flags |= IB_WC_WITH_IMM;
+ fallthrough;
+ case CQE_TYPE_UD_SEND:
+ wc->byte_len = rdma_cqe->ud_recv.msg_len;
+ wc->src_qp = rdma_cqe->ud_recv.src_qpn;
wc->wc_flags |= IB_WC_GRH;
+ break;
+ default:
+ break;
}
+
+ wq->tail += wqe->wqe_size_in_bu;
+ shadow_queue_advance_consumer(&qp->shadow_rq);
}
-static int mana_process_completions(struct mana_ib_cq *cq, int nwc, struct ib_wc *wc)
+static bool mana_handle_cqe(struct mana_ib_cq *cq, struct mana_ib_dev *mdev,
+ struct mana_cq_poll *poll)
{
- struct shadow_wqe_header *shadow_wqe;
- struct mana_ib_qp *qp;
- int wc_index = 0;
+ struct gdma_comp *cqe = &cq->pending_cqe;
+ struct mana_rdma_cqe *rdma_cqe = (struct mana_rdma_cqe *)cqe->cqe_data;
+ struct mana_ib_qp *qp = mana_get_qp_ref(mdev, cqe->wq_num, cqe->is_sq);
- /* process send shadow queue completions */
- list_for_each_entry(qp, &cq->list_send_qp, cq_send_list) {
- while ((shadow_wqe = shadow_queue_get_next_to_consume(&qp->shadow_sq))
- != NULL) {
- if (wc_index >= nwc)
- goto out;
+ if (!qp)
+ return true;
- fill_verbs_from_shadow_wqe(qp, &wc[wc_index], shadow_wqe,
- shadow_wqe->send_opcode);
- shadow_queue_advance_consumer(&qp->shadow_sq);
- wc_index++;
+ switch (rdma_cqe->cqe_type) {
+ case CQE_TYPE_UD_SEND:
+ if (cqe->is_sq) {
+ handle_ud_sq_cqe(qp, rdma_cqe, poll);
+ break;
}
+ fallthrough;
+ case CQE_TYPE_UD_SEND_IMM:
+ handle_rq_cqe(qp, cqe, poll);
+ break;
+ default:
+ ibdev_warn_ratelimited(qp->ibqp.device, "Unexpected CQE type %u\n",
+ rdma_cqe->cqe_type);
+ break;
}
+ mana_put_qp_ref(qp);
+ return true;
+}
- /* process recv shadow queue completions */
- list_for_each_entry(qp, &cq->list_recv_qp, cq_recv_list) {
- while ((shadow_wqe = shadow_queue_get_next_to_consume(&qp->shadow_rq))
- != NULL) {
- if (wc_index >= nwc)
- goto out;
+static void mana_flush_completions(struct mana_ib_cq *cq, struct mana_cq_poll *poll)
+{
+ struct shadow_wqe_header *wqe;
+ struct mana_ib_qp *qp;
+
+ if (poll->produced >= poll->budget)
+ return;
+
+ list_for_each_entry(qp, &cq->send_err_qp_list, send_err_node) {
+ while (poll->produced < poll->budget &&
+ shadow_queue_get_next_to_consume(&qp->shadow_sq))
+ mana_complete_send(qp, poll, VENDOR_ERR_SW_FLUSHED);
+ if (poll->produced == poll->budget)
+ return;
+ }
- fill_verbs_from_shadow_wqe(qp, &wc[wc_index], shadow_wqe,
- IB_WC_RECV);
+ list_for_each_entry(qp, &cq->recv_err_qp_list, recv_err_node) {
+ while (poll->produced < poll->budget &&
+ (wqe = shadow_queue_get_next_to_consume(&qp->shadow_rq))) {
+ mana_fill_wc(qp, poll, wqe, IB_WC_RECV, VENDOR_ERR_SW_FLUSHED);
shadow_queue_advance_consumer(&qp->shadow_rq);
- wc_index++;
}
+ if (poll->produced == poll->budget)
+ return;
}
-
-out:
- return wc_index;
}
static void mana_drain_gsi_sq(struct mana_ib_qp *qp)
{
struct mana_ib_cq *cq = container_of(qp->ibqp.send_cq, struct mana_ib_cq, ibcq);
- struct shadow_wqe_header *shadow_wqe;
unsigned long flags;
spin_lock_irqsave(&cq->cq_lock, flags);
- while ((shadow_wqe = shadow_queue_get_next_to_complete(&qp->shadow_sq))
- != NULL) {
- shadow_wqe->error_code = IB_WC_GENERAL_ERR;
- shadow_queue_advance_next_to_complete(&qp->shadow_sq);
- }
+ if (list_empty(&qp->send_err_node))
+ list_add_tail(&qp->send_err_node, &cq->send_err_qp_list);
spin_unlock_irqrestore(&cq->cq_lock, flags);
if (cq->ibcq.comp_handler)
@@ -382,25 +464,39 @@ int mana_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
{
struct mana_ib_cq *cq = container_of(ibcq, struct mana_ib_cq, ibcq);
struct mana_ib_dev *mdev = container_of(ibcq->device, struct mana_ib_dev, ib_dev);
+ struct mana_cq_poll poll = { .wc = wc, .budget = num_entries, .produced = 0 };
struct gdma_queue *queue = cq->queue.kmem;
- struct gdma_comp gdma_cqe;
unsigned long flags;
- int num_polled = 0;
- int comp_read, i;
+ bool consumed;
+ int comp_read;
+
+ if (!queue)
+ return -EINVAL;
spin_lock_irqsave(&cq->cq_lock, flags);
- for (i = 0; i < num_entries; i++) {
- comp_read = mana_gd_poll_cq(queue, &gdma_cqe, 1);
- if (comp_read < 1)
- break;
- cq->poll_credit--;
- if (!cq->poll_credit)
- mana_ib_cq_doorbell(cq, 0);
- mana_handle_cqe(mdev, &gdma_cqe);
+ while (poll.produced < poll.budget) {
+ if (!cq->has_pending_cqe) {
+ comp_read = mana_gd_poll_cq(queue, &cq->pending_cqe, 1);
+ if (comp_read < 0) {
+ if (!poll.produced)
+ poll.produced = comp_read;
+ goto out;
+ }
+ if (!comp_read)
+ break;
+
+ cq->poll_credit--;
+ if (!cq->poll_credit)
+ mana_ib_cq_doorbell(cq, 0);
+ }
+
+ consumed = mana_handle_cqe(cq, mdev, &poll);
+ cq->has_pending_cqe = !consumed;
}
- num_polled = mana_process_completions(cq, num_entries, wc);
+ mana_flush_completions(cq, &poll);
+out:
spin_unlock_irqrestore(&cq->cq_lock, flags);
- return num_polled;
+ return poll.produced;
}
diff --git a/drivers/infiniband/hw/mana/mana_ib.h b/drivers/infiniband/hw/mana/mana_ib.h
index 0ad757990..17f110404 100644
--- a/drivers/infiniband/hw/mana/mana_ib.h
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -166,8 +166,10 @@ struct mana_ib_cq {
struct mana_ib_queue queue;
/* protects CQ polling */
spinlock_t cq_lock;
- struct list_head list_send_qp;
- struct list_head list_recv_qp;
+ struct list_head send_err_qp_list;
+ struct list_head recv_err_qp_list;
+ struct gdma_comp pending_cqe;
+ bool has_pending_cqe;
int cqe;
u32 comp_vector;
u32 poll_credit;
@@ -224,8 +226,11 @@ struct mana_ib_qp {
u32 port;
u32 sq_psn;
- struct list_head cq_send_list;
- struct list_head cq_recv_list;
+ /* Serializes QP modification and error-list transitions. */
+ struct mutex modify_lock;
+
+ struct list_head send_err_node;
+ struct list_head recv_err_node;
struct shadow_queue shadow_rq;
struct shadow_queue shadow_sq;
@@ -586,6 +591,53 @@ struct rdma_recv_oob {
u32 reserved2 : 8;
}; /* HW DATA */
+enum mana_ib_error_code {
+ VENDOR_ERR_OK = 0x0,
+ VENDOR_ERR_RX_PKT_LEN = 0x05,
+ VENDOR_ERR_RX_MSG_LEN_OVFL = 0x102,
+ VENDOR_ERR_RX_MISBEHAVING_CLIENT = 0x108,
+ VENDOR_ERR_RX_MALFORMED_WQE = 0x109,
+ VENDOR_ERR_RX_CLIENT_ID = 0x10a,
+ VENDOR_ERR_RX_GFID = 0x10b,
+ VENDOR_ERR_RX_PCIE = 0x10c,
+ VENDOR_ERR_RX_NO_AVAIL_WQE = 0x111,
+ VENDOR_ERR_RX_ATB_SGE_MISSCONFIG = 0x143,
+ VENDOR_ERR_RX_ATB_WQE_MISCONFIG = 0x145,
+ VENDOR_ERR_RX_ATB_SGE_ADDR_RIGHT = 0x183,
+ VENDOR_ERR_RX_ATB_WQE_ADDR_RIGHT = 0x185,
+ VENDOR_ERR_RX_ATB_SGE_ADDR_RANGE = 0x1c3,
+ VENDOR_ERR_RX_ATB_WQE_ADDR_RANGE = 0x1c5,
+ VENDOR_ERR_RX_NOT_EMPTY_ON_DISABLE = 0x1c7,
+ VENDOR_ERR_TX_GDMA_CORRUPTED_WQE = 0x201,
+ VENDOR_ERR_TX_ATB_WQE_ACCESS_VIOLATION = 0x202,
+ VENDOR_ERR_TX_ATB_WQE_ADDR_RANGE = 0x203,
+ VENDOR_ERR_TX_ATB_WQE_CONFIG_ERR = 0x204,
+ VENDOR_ERR_TX_PCIE_WQE = 0x205,
+ VENDOR_ERR_TX_ATB_MSG_ACCESS_VIOLATION = 0x206,
+ VENDOR_ERR_TX_ATB_MSG_ADDR_RANGE = 0x207,
+ VENDOR_ERR_TX_ATB_MSG_CONFIG_ERR = 0x208,
+ VENDOR_ERR_TX_PCIE_MSG = 0x209,
+ VENDOR_ERR_TX_GDMA_INVALID_STATE = 0x20a,
+ VENDOR_ERR_TX_MISBEHAVING_CLIENT = 0x20b,
+ VENDOR_ERR_TX_RDMA_MALFORMED_WQE_SIZE = 0x210,
+ VENDOR_ERR_TX_RDMA_MALFORMED_WQE_FIELD = 0x211,
+ VENDOR_ERR_TX_RDMA_INVALID_STATE = 0x212,
+ VENDOR_ERR_TX_RDMA_INVALID_NPT = 0x213,
+ VENDOR_ERR_TX_RDMA_INVALID_SGID = 0x214,
+ VENDOR_ERR_TX_RDMA_WQE_UNSUPPORTED = 0x215,
+ VENDOR_ERR_TX_RDMA_WQE_LEN_ERR = 0x216,
+ VENDOR_ERR_TX_RDMA_MTU_ERR = 0x217,
+ VENDOR_ERR_TX_RDMA_VFID_MISMATCH = 0x218,
+ VENDOR_ERR_HW_MAX = 0x3ff,
+ /* SW vendor errors */
+ VENDOR_ERR_SW_FLUSHED = 0xfff,
+};
+
+enum mana_ib_cqe_type {
+ CQE_TYPE_UD_SEND = 1,
+ CQE_TYPE_UD_SEND_IMM = 2,
+}; /* HW DATA */
+
struct mana_rdma_cqe {
union {
struct {
diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c
index 79c9cc944..ae413bf7d 100644
--- a/drivers/infiniband/hw/mana/qp.c
+++ b/drivers/infiniband/hw/mana/qp.c
@@ -694,33 +694,23 @@ static int mana_ib_create_uc_qp(struct ib_qp *ibqp, struct ib_pd *ibpd,
return err;
}
-static void mana_add_qp_to_cqs(struct mana_ib_qp *qp)
+static void mana_remove_qp_from_cqs(struct mana_ib_qp *qp, bool reset)
{
struct mana_ib_cq *send_cq = container_of(qp->ibqp.send_cq, struct mana_ib_cq, ibcq);
struct mana_ib_cq *recv_cq = container_of(qp->ibqp.recv_cq, struct mana_ib_cq, ibcq);
unsigned long flags;
spin_lock_irqsave(&send_cq->cq_lock, flags);
- list_add_tail(&qp->cq_send_list, &send_cq->list_send_qp);
+ list_del_init(&qp->send_err_node);
+ /* Keep shadow reset serialized with hardware polling and SW flushing. */
+ if (reset)
+ reset_shadow_queue(&qp->shadow_sq);
spin_unlock_irqrestore(&send_cq->cq_lock, flags);
spin_lock_irqsave(&recv_cq->cq_lock, flags);
- list_add_tail(&qp->cq_recv_list, &recv_cq->list_recv_qp);
- spin_unlock_irqrestore(&recv_cq->cq_lock, flags);
-}
-
-static void mana_remove_qp_from_cqs(struct mana_ib_qp *qp)
-{
- struct mana_ib_cq *send_cq = container_of(qp->ibqp.send_cq, struct mana_ib_cq, ibcq);
- struct mana_ib_cq *recv_cq = container_of(qp->ibqp.recv_cq, struct mana_ib_cq, ibcq);
- unsigned long flags;
-
- spin_lock_irqsave(&send_cq->cq_lock, flags);
- list_del(&qp->cq_send_list);
- spin_unlock_irqrestore(&send_cq->cq_lock, flags);
-
- spin_lock_irqsave(&recv_cq->cq_lock, flags);
- list_del(&qp->cq_recv_list);
+ list_del_init(&qp->recv_err_node);
+ if (reset)
+ reset_shadow_queue(&qp->shadow_rq);
spin_unlock_irqrestore(&recv_cq->cq_lock, flags);
}
@@ -776,8 +766,6 @@ static int mana_ib_create_ud_qp(struct ib_qp *ibqp, struct ib_pd *ibpd,
if (err)
goto destroy_qp;
- mana_add_qp_to_cqs(qp);
-
return 0;
destroy_qp:
@@ -794,6 +782,12 @@ static int mana_ib_create_ud_qp(struct ib_qp *ibqp, struct ib_pd *ibpd,
int mana_ib_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attr,
struct ib_udata *udata)
{
+ struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
+
+ mutex_init(&qp->modify_lock);
+ INIT_LIST_HEAD(&qp->send_err_node);
+ INIT_LIST_HEAD(&qp->recv_err_node);
+
switch (attr->qp_type) {
case IB_QPT_RAW_PACKET:
/* When rwq_ind_tbl is used, it's for creating WQs for RSS */
@@ -891,19 +885,56 @@ static int mana_ib_gd_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
return 0;
}
+static void mana_ib_modify_qp_state(struct ib_qp *ibqp, struct ib_qp_attr *attr,
+ int attr_mask, struct ib_udata *udata)
+{
+ struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
+
+ if (udata)
+ return;
+
+ if (attr_mask & IB_QP_STATE) {
+ switch (attr->qp_state) {
+ case IB_QPS_RESET:
+ mana_remove_qp_from_cqs(qp, true);
+ break;
+ default:
+ break;
+ }
+ }
+
+ if (attr_mask & IB_QP_SQ_PSN)
+ qp->sq_psn = attr->sq_psn;
+}
+
int mana_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
int attr_mask, struct ib_udata *udata)
{
+ struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
+ int ret;
+
+ mutex_lock(&qp->modify_lock);
+
switch (ibqp->qp_type) {
case IB_QPT_RC:
case IB_QPT_UC:
case IB_QPT_UD:
case IB_QPT_GSI:
- return mana_ib_gd_modify_qp(ibqp, attr, attr_mask, udata);
+ ret = mana_ib_gd_modify_qp(ibqp, attr, attr_mask, udata);
+ if (ret)
+ goto out_unlock;
+ break;
default:
- ibdev_dbg(ibqp->device, "Modify QP type %u not supported", ibqp->qp_type);
- return -EOPNOTSUPP;
+ ret = -EOPNOTSUPP;
+ goto out_unlock;
}
+
+ mana_ib_modify_qp_state(ibqp, attr, attr_mask, udata);
+
+out_unlock:
+ mutex_unlock(&qp->modify_lock);
+
+ return ret;
}
static int mana_ib_destroy_qp_rss(struct mana_ib_qp *qp,
@@ -1040,8 +1071,8 @@ static int mana_ib_destroy_ud_qp(struct mana_ib_qp *qp, struct ib_udata *udata)
if (err)
return err;
- mana_remove_qp_from_cqs(qp);
mana_table_remove_qp(mdev, qp);
+ mana_remove_qp_from_cqs(qp, false);
destroy_shadow_queue(&qp->shadow_rq);
destroy_shadow_queue(&qp->shadow_sq);
diff --git a/drivers/infiniband/hw/mana/shadow_queue.h b/drivers/infiniband/hw/mana/shadow_queue.h
index a127edf7a..b5d6bb28b 100644
--- a/drivers/infiniband/hw/mana/shadow_queue.h
+++ b/drivers/infiniband/hw/mana/shadow_queue.h
@@ -6,13 +6,19 @@
#ifndef _MANA_SHADOW_QUEUE_H_
#define _MANA_SHADOW_QUEUE_H_
+#include <linux/build_bug.h>
+
+#define MANA_WQ_FENCE_WC BIT(0)
+#define MANA_WQ_NO_SIGNAL_WC BIT(1)
+#define MANA_WQE_OFFSET_MASK GENMASK(23, 0)
+
struct shadow_wqe_header {
u64 wr_id;
+ u64 wqe_offset_or_psn : 24;
u64 wqe_size_in_bu : 8;
+ u64 fsn : 24;
u64 send_opcode : 4;
- u64 error_code : 16;
- u32 byte_len;
- u32 src_qpn;
+ u64 flags : 2;
};
struct shadow_queue {
@@ -20,8 +26,6 @@ struct shadow_queue {
u64 prod_idx;
/* Unmasked consumer index, Incremented on cq polling */
u64 cons_idx;
- /* Unmasked index of next-to-complete (from HW) shadow WQE */
- u64 next_to_complete_idx;
/* queue size in wqes */
u32 length;
/* distance between elements in bytes */
@@ -42,6 +46,12 @@ static inline int create_shadow_queue(struct shadow_queue *queue, uint32_t lengt
return 0;
}
+static inline void reset_shadow_queue(struct shadow_queue *queue)
+{
+ queue->prod_idx = 0;
+ queue->cons_idx = 0;
+}
+
static inline void destroy_shadow_queue(struct shadow_queue *queue)
{
kvfree(queue->buffer);
@@ -76,22 +86,13 @@ shadow_queue_producer_entry(struct shadow_queue *queue)
static inline void *
shadow_queue_get_next_to_consume(const struct shadow_queue *queue)
{
- if (queue->cons_idx == queue->next_to_complete_idx)
+ /* The producer publishes the WQE before advancing prod_idx. */
+ if (queue->cons_idx == smp_load_acquire(&queue->prod_idx))
return NULL;
return shadow_queue_get_element(queue, queue->cons_idx);
}
-static inline void *
-shadow_queue_get_next_to_complete(struct shadow_queue *queue)
-{
- /* Observe initialized WQE fields published by the posting CPU. */
- if (queue->next_to_complete_idx == smp_load_acquire(&queue->prod_idx))
- return NULL;
-
- return shadow_queue_get_element(queue, queue->next_to_complete_idx);
-}
-
static inline void shadow_queue_advance_producer(struct shadow_queue *queue)
{
/* Publish all WQE fields to CQ polling on another CPU. */
@@ -104,9 +105,4 @@ static inline void shadow_queue_advance_consumer(struct shadow_queue *queue)
smp_store_release(&queue->cons_idx, queue->cons_idx + 1);
}
-static inline void shadow_queue_advance_next_to_complete(struct shadow_queue *queue)
-{
- queue->next_to_complete_idx++;
-}
-
#endif
diff --git a/drivers/infiniband/hw/mana/wr.c b/drivers/infiniband/hw/mana/wr.c
index eb671b45b..15faca661 100644
--- a/drivers/infiniband/hw/mana/wr.c
+++ b/drivers/infiniband/hw/mana/wr.c
@@ -40,6 +40,7 @@ static int mana_ib_post_rq(struct mana_ib_qp *qp, const struct ib_recv_wr *wr)
memset(shadow_wqe, 0, sizeof(*shadow_wqe));
shadow_wqe->wr_id = wr->wr_id;
shadow_wqe->wqe_size_in_bu = wqe_info.wqe_size_in_bu;
+ shadow_wqe->wqe_offset_or_psn = wqe_info.wqe_offset;
shadow_queue_advance_producer(&qp->shadow_rq);
return 0;
@@ -144,6 +145,7 @@ static int mana_ib_post_send_ud_one(struct mana_ib_qp *qp, const struct ib_ud_wr
memset(shadow_wqe, 0, sizeof(*shadow_wqe));
shadow_wqe->wr_id = wr->wr.wr_id;
shadow_wqe->wqe_size_in_bu = wqe_info.wqe_size_in_bu;
+ shadow_wqe->wqe_offset_or_psn = wqe_info.wqe_offset;
shadow_queue_advance_producer(&qp->shadow_sq);
return 0;
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index cb51fcf57..05ba70554 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1807,10 +1807,12 @@ int mana_gd_post_work_request(struct gdma_queue *wq,
if (wq->monitor_avl_buf && wqe_size > mana_gd_wq_avail_space(wq))
return -ENOSPC;
- if (wqe_info)
+ head = wq->head;
+ if (wqe_info) {
wqe_info->wqe_size_in_bu = wqe_size / GDMA_WQE_BU_SIZE;
+ wqe_info->wqe_offset = head;
+ }
- head = wq->head;
wqe_offset = (head * GDMA_WQE_BU_SIZE) & (wq->queue_size - 1);
wqe_ptr = mana_gd_get_wqe_ptr(wq, head);
oob_len = mana_gd_write_client_oob(wqe_req, wq->type, client_oob_size,
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 02632acd7..2a28fcaa6 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -630,6 +630,8 @@ struct gdma_eqe {
struct gdma_posted_wqe_info {
u32 wqe_size_in_bu;
+ /* Unmasked WQE start offset in GDMA basic units. */
+ u32 wqe_offset;
};
/* GDMA_GENERATE_TEST_EQE */
--
2.43.0
^ permalink raw reply [flat|nested] 6+ messages in thread