From: Cheng Xu <chengyou@linux.alibaba.com>
To: jgg@ziepe.ca, leon@kernel.org
Cc: linux-rdma@vger.kernel.org, KaiShen@linux.alibaba.com
Subject: [PATCH for-next v2 2/4] RDMA/erdma: Support non-contiguous kernel CQ buffers
Date: Thu, 27 Aug 2026 16:25:21 +0800 [thread overview]
Message-ID: <20260827082523.36294-3-chengyou@linux.alibaba.com> (raw)
In-Reply-To: <20260827082523.36294-1-chengyou@linux.alibaba.com>
A single coherent allocation for a kernel CQ can fail when memory is
fragmented.
Use page-sized coherent buffers and describe them with the existing MTT.
Keep the userspace CQ path and doorbell allocation unchanged.
Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com>
---
drivers/infiniband/hw/erdma/erdma_cq.c | 14 ++---
drivers/infiniband/hw/erdma/erdma_verbs.c | 76 +++++++++--------------
drivers/infiniband/hw/erdma/erdma_verbs.h | 3 +-
3 files changed, 36 insertions(+), 57 deletions(-)
diff --git a/drivers/infiniband/hw/erdma/erdma_cq.c b/drivers/infiniband/hw/erdma/erdma_cq.c
index 4cc0254b0ab5..daec74f0aa6d 100644
--- a/drivers/infiniband/hw/erdma/erdma_cq.c
+++ b/drivers/infiniband/hw/erdma/erdma_cq.c
@@ -8,8 +8,8 @@
static void *get_next_valid_cqe(struct erdma_cq *cq)
{
- __be32 *cqe = get_queue_entry(cq->kern_cq.qbuf, cq->kern_cq.ci,
- cq->depth, CQE_SHIFT);
+ __be32 *cqe = erdma_kmem_get_entry(
+ &cq->kern_cq.qbuf_mem, cq->kern_cq.ci, cq->depth, CQE_SHIFT);
u32 owner = FIELD_GET(ERDMA_CQE_HDR_OWNER_MASK,
be32_to_cpu(READ_ONCE(*cqe)));
@@ -242,15 +242,15 @@ void erdma_remove_cqes_of_qp(struct ib_cq *ibcq, u32 qpn)
while (ncqe > 0) {
cur_cq_ci = prev_cq_ci + ncqe - 1;
- cqe = get_queue_entry(cq->kern_cq.qbuf, cur_cq_ci, cq->depth,
- CQE_SHIFT);
+ cqe = erdma_kmem_get_entry(&cq->kern_cq.qbuf_mem, cur_cq_ci,
+ cq->depth, CQE_SHIFT);
if (be32_to_cpu(cqe->qpn) == qpn) {
++nqp_cqe;
} else if (nqp_cqe) {
- dst_cqe = get_queue_entry(cq->kern_cq.qbuf,
- cur_cq_ci + nqp_cqe,
- cq->depth, CQE_SHIFT);
+ dst_cqe = erdma_kmem_get_entry(&cq->kern_cq.qbuf_mem,
+ cur_cq_ci + nqp_cqe,
+ cq->depth, CQE_SHIFT);
owner = FIELD_GET(ERDMA_CQE_HDR_OWNER_MASK,
be32_to_cpu(dst_cqe->hdr));
cqe->hdr = cpu_to_be32(
diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.c b/drivers/infiniband/hw/erdma/erdma_verbs.c
index a2de700bce90..b0a47c82cbdf 100644
--- a/drivers/infiniband/hw/erdma/erdma_verbs.c
+++ b/drivers/infiniband/hw/erdma/erdma_verbs.c
@@ -177,7 +177,6 @@ static int create_cq_cmd(struct erdma_ucontext *uctx, struct erdma_cq *cq)
struct erdma_dev *dev = to_edev(cq->ibcq.device);
struct erdma_cmdq_create_cq_req req;
struct erdma_mem *mem;
- u32 page_size;
erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_RDMA,
CMDQ_OPCODE_CREATE_CQ);
@@ -187,48 +186,34 @@ static int create_cq_cmd(struct erdma_ucontext *uctx, struct erdma_cq *cq)
req.cfg1 = FIELD_PREP(ERDMA_CMD_CREATE_CQ_EQN_MASK, cq->assoc_eqn);
if (rdma_is_kernel_res(&cq->ibcq.res)) {
- page_size = SZ_32M;
- req.cfg0 |= FIELD_PREP(ERDMA_CMD_CREATE_CQ_PAGESIZE_MASK,
- ilog2(page_size) - ERDMA_HW_PAGE_SHIFT);
- req.qbuf_addr_l = lower_32_bits(cq->kern_cq.qbuf_dma_addr);
- req.qbuf_addr_h = upper_32_bits(cq->kern_cq.qbuf_dma_addr);
-
- req.cfg1 |= FIELD_PREP(ERDMA_CMD_CREATE_CQ_MTT_CNT_MASK, 1) |
- FIELD_PREP(ERDMA_CMD_CREATE_CQ_MTT_LEVEL_MASK,
- ERDMA_MR_MTT_0LEVEL);
-
- req.first_page_offset = 0;
+ mem = &cq->kern_cq.qbuf_mem;
req.cq_dbrec_dma = cq->kern_cq.dbrec_dma;
} else {
mem = &cq->user_cq.qbuf_mem;
- req.cfg0 |=
- FIELD_PREP(ERDMA_CMD_CREATE_CQ_PAGESIZE_MASK,
- ilog2(mem->page_size) - ERDMA_HW_PAGE_SHIFT);
- if (mem->mtt_nents == 1) {
- req.qbuf_addr_l = lower_32_bits(mem->mtt->buf[0]);
- req.qbuf_addr_h = upper_32_bits(mem->mtt->buf[0]);
- req.cfg1 |=
- FIELD_PREP(ERDMA_CMD_CREATE_CQ_MTT_LEVEL_MASK,
- ERDMA_MR_MTT_0LEVEL);
- } else {
- req.qbuf_addr_l = lower_32_bits(mem->mtt->buf_dma);
- req.qbuf_addr_h = upper_32_bits(mem->mtt->buf_dma);
- req.cfg1 |=
- FIELD_PREP(ERDMA_CMD_CREATE_CQ_MTT_LEVEL_MASK,
- ERDMA_MR_MTT_1LEVEL);
- }
- req.cfg1 |= FIELD_PREP(ERDMA_CMD_CREATE_CQ_MTT_CNT_MASK,
- mem->mtt_nents);
-
- req.first_page_offset = mem->page_offset;
req.cq_dbrec_dma = cq->user_cq.dbrec_dma;
+ }
- if (uctx->ext_db.enable) {
- req.cfg1 |= FIELD_PREP(
- ERDMA_CMD_CREATE_CQ_MTT_DB_CFG_MASK, 1);
- req.cfg2 = FIELD_PREP(ERDMA_CMD_CREATE_CQ_DB_CFG_MASK,
- uctx->ext_db.cdb_off);
- }
+ req.cfg0 |= FIELD_PREP(ERDMA_CMD_CREATE_CQ_PAGESIZE_MASK,
+ ilog2(mem->page_size) - ERDMA_HW_PAGE_SHIFT);
+ if (mem->mtt_nents == 1) {
+ req.qbuf_addr_l = lower_32_bits(mem->mtt->buf[0]);
+ req.qbuf_addr_h = upper_32_bits(mem->mtt->buf[0]);
+ req.cfg1 |= FIELD_PREP(ERDMA_CMD_CREATE_CQ_MTT_LEVEL_MASK,
+ ERDMA_MR_MTT_0LEVEL);
+ } else {
+ req.qbuf_addr_l = lower_32_bits(mem->mtt->buf_dma);
+ req.qbuf_addr_h = upper_32_bits(mem->mtt->buf_dma);
+ req.cfg1 |= FIELD_PREP(ERDMA_CMD_CREATE_CQ_MTT_LEVEL_MASK,
+ ERDMA_MR_MTT_1LEVEL);
+ }
+ req.cfg1 |=
+ FIELD_PREP(ERDMA_CMD_CREATE_CQ_MTT_CNT_MASK, mem->mtt_nents);
+ req.first_page_offset = mem->page_offset;
+
+ if (uctx && uctx->ext_db.enable) {
+ req.cfg1 |= FIELD_PREP(ERDMA_CMD_CREATE_CQ_MTT_DB_CFG_MASK, 1);
+ req.cfg2 = FIELD_PREP(ERDMA_CMD_CREATE_CQ_DB_CFG_MASK,
+ uctx->ext_db.cdb_off);
}
return erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL,
@@ -1392,8 +1377,7 @@ int erdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
wait_for_completion(&cq->free);
if (rdma_is_kernel_res(&cq->ibcq.res)) {
- dma_free_coherent(&dev->pdev->dev, cq->depth << CQE_SHIFT,
- cq->kern_cq.qbuf, cq->kern_cq.qbuf_dma_addr);
+ put_mtt_entries(dev, &cq->kern_cq.qbuf_mem);
dma_pool_free(dev->db_pool, cq->kern_cq.dbrec,
cq->kern_cq.dbrec_dma);
} else {
@@ -1991,10 +1975,8 @@ static int erdma_init_kernel_cq(struct erdma_cq *cq)
{
struct erdma_dev *dev = to_edev(cq->ibcq.device);
- cq->kern_cq.qbuf =
- dma_alloc_coherent(&dev->pdev->dev, cq->depth << CQE_SHIFT,
- &cq->kern_cq.qbuf_dma_addr, GFP_KERNEL);
- if (!cq->kern_cq.qbuf)
+ if (erdma_alloc_kmem(dev, &cq->kern_cq.qbuf_mem,
+ cq->depth << CQE_SHIFT))
return -ENOMEM;
cq->kern_cq.dbrec = dma_pool_zalloc(dev->db_pool, GFP_KERNEL,
@@ -2009,8 +1991,7 @@ static int erdma_init_kernel_cq(struct erdma_cq *cq)
return 0;
err_out:
- dma_free_coherent(&dev->pdev->dev, cq->depth << CQE_SHIFT,
- cq->kern_cq.qbuf, cq->kern_cq.qbuf_dma_addr);
+ put_mtt_entries(dev, &cq->kern_cq.qbuf_mem);
return -ENOMEM;
}
@@ -2077,8 +2058,7 @@ int erdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
erdma_unmap_user_dbrecords(ctx, &cq->user_cq.user_dbr_page);
put_mtt_entries(dev, &cq->user_cq.qbuf_mem);
} else {
- dma_free_coherent(&dev->pdev->dev, depth << CQE_SHIFT,
- cq->kern_cq.qbuf, cq->kern_cq.qbuf_dma_addr);
+ put_mtt_entries(dev, &cq->kern_cq.qbuf_mem);
dma_pool_free(dev->db_pool, cq->kern_cq.dbrec,
cq->kern_cq.dbrec_dma);
}
diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.h b/drivers/infiniband/hw/erdma/erdma_verbs.h
index eb7318cf7a52..5056d60357db 100644
--- a/drivers/infiniband/hw/erdma/erdma_verbs.h
+++ b/drivers/infiniband/hw/erdma/erdma_verbs.h
@@ -352,8 +352,7 @@ struct erdma_qp {
};
struct erdma_kcq_info {
- void *qbuf;
- dma_addr_t qbuf_dma_addr;
+ struct erdma_mem qbuf_mem;
u32 ci;
u32 cmdsn;
u32 notify_cnt;
--
2.31.1
next prev parent reply other threads:[~2026-08-27 8:25 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-27 8:25 [PATCH for-next v2 0/4] RDMA/erdma: Support non-contiguous kernel queue buffers Cheng Xu
2026-08-27 8:25 ` [PATCH for-next v2 1/4] RDMA/erdma: Support non-contiguous kernel QP buffers Cheng Xu
2026-09-03 9:10 ` Leon Romanovsky
2026-09-03 12:38 ` Cheng Xu
2026-09-09 6:21 ` Cheng Xu
2026-09-10 15:33 ` Leon Romanovsky
2026-09-11 2:41 ` Cheng Xu
2026-09-18 12:47 ` Leon Romanovsky
2026-09-23 10:17 ` Cheng Xu
2026-08-27 8:25 ` Cheng Xu [this message]
2026-08-27 8:25 ` [PATCH for-next v2 3/4] RDMA/erdma: Unify userspace and kernel queue buffer management Cheng Xu
2026-09-03 9:12 ` Leon Romanovsky
2026-09-03 12:40 ` Cheng Xu
2026-08-27 8:25 ` [PATCH for-next v2 4/4] RDMA/erdma: Move kernel QP helpers after memory helpers Cheng Xu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260827082523.36294-3-chengyou@linux.alibaba.com \
--to=chengyou@linux.alibaba.com \
--cc=KaiShen@linux.alibaba.com \
--cc=jgg@ziepe.ca \
--cc=leon@kernel.org \
--cc=linux-rdma@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.