diff options
| author | Yangyang Li <liyangyang20@huawei.com> | 2023-09-26 16:00:26 +0300 |
|---|---|---|
| committer | Leon Romanovsky <leon@kernel.org> | 2023-10-02 11:47:08 +0300 |
| commit | c9813b0b9992eab01a47ad8d10f0add13f898692 (patch) | |
| tree | e09e97292ca45a57782417aa21a5a105948455fe /drivers/infiniband/hw/hns/hns_roce_hw_v2.c | |
| parent | 8dc0fd2f5693ab71f84fb16339c483999a909ab0 (diff) | |
| download | linux-c9813b0b9992eab01a47ad8d10f0add13f898692.tar.xz | |
RDMA/hns: Support SRQ record doorbell
Compared with normal doorbell, using record doorbell can shorten the
process of ringing the doorbell and reduce the latency.
Add a flag HNS_ROCE_CAP_FLAG_SRQ_RECORD_DB to allow FW to
enable/disable SRQ record doorbell.
If the flag above is set, allocate the dma buffer for SRQ record
doorbell and write the buffer address into SRQC during SRQ creation.
For userspace SRQ, add a flag HNS_ROCE_RSP_SRQ_CAP_RECORD_DB to notify
userspace whether the SRQ record doorbell is enabled.
Signed-off-by: Yangyang Li <liyangyang20@huawei.com>
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://lore.kernel.org/r/20230926130026.583088-1-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Diffstat (limited to 'drivers/infiniband/hw/hns/hns_roce_hw_v2.c')
| -rw-r--r-- | drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 31 |
1 files changed, 22 insertions, 9 deletions
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index b48f2c7b2fb0..a17bbf29b64b 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -941,20 +941,23 @@ static void fill_wqe_idx(struct hns_roce_srq *srq, unsigned int wqe_idx) idx_que->head++; } -static void update_srq_db(struct hns_roce_v2_db *db, struct hns_roce_srq *srq) +static void update_srq_db(struct hns_roce_srq *srq) { - hr_reg_write(db, DB_TAG, srq->srqn); - hr_reg_write(db, DB_CMD, HNS_ROCE_V2_SRQ_DB); - hr_reg_write(db, DB_PI, srq->idx_que.head); + struct hns_roce_dev *hr_dev = to_hr_dev(srq->ibsrq.device); + struct hns_roce_v2_db db; + + hr_reg_write(&db, DB_TAG, srq->srqn); + hr_reg_write(&db, DB_CMD, HNS_ROCE_V2_SRQ_DB); + hr_reg_write(&db, DB_PI, srq->idx_que.head); + + hns_roce_write64(hr_dev, (__le32 *)&db, srq->db_reg); } static int hns_roce_v2_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr, const struct ib_recv_wr **bad_wr) { - struct hns_roce_dev *hr_dev = to_hr_dev(ibsrq->device); struct hns_roce_srq *srq = to_hr_srq(ibsrq); - struct hns_roce_v2_db srq_db; unsigned long flags; int ret = 0; u32 max_sge; @@ -985,9 +988,11 @@ static int hns_roce_v2_post_srq_recv(struct ib_srq *ibsrq, } if (likely(nreq)) { - update_srq_db(&srq_db, srq); - - hns_roce_write64(hr_dev, (__le32 *)&srq_db, srq->db_reg); + if (srq->cap_flags & HNS_ROCE_SRQ_CAP_RECORD_DB) + *srq->rdb.db_record = srq->idx_que.head & + V2_DB_PRODUCER_IDX_M; + else + update_srq_db(srq); } spin_unlock_irqrestore(&srq->lock, flags); @@ -5630,6 +5635,14 @@ static int hns_roce_v2_write_srqc(struct hns_roce_srq *srq, void *mb_buf) hr_reg_write(ctx, SRQC_WQE_BUF_PG_SZ, to_hr_hw_page_shift(srq->buf_mtr.hem_cfg.buf_pg_shift)); + if (srq->cap_flags & HNS_ROCE_SRQ_CAP_RECORD_DB) { + hr_reg_enable(ctx, SRQC_DB_RECORD_EN); + hr_reg_write(ctx, SRQC_DB_RECORD_ADDR_L, + lower_32_bits(srq->rdb.dma) >> 1); + hr_reg_write(ctx, SRQC_DB_RECORD_ADDR_H, + upper_32_bits(srq->rdb.dma)); + } + return hns_roce_v2_write_srqc_index_queue(srq, ctx); } |