From: Cheng Xu <chengyou@linux.alibaba.com>
Date: Tue, 7 Mar 2023 18:29:23 +0800
Subject: [PATCH] RDMA/erdma: Use fixed hardware page size
References: bsc#1012628
Patch-mainline: 6.3.2
Git-commit: d649c638dc26f3501da510cf7fceb5c15ca54258
[ Upstream commit d649c638dc26f3501da510cf7fceb5c15ca54258 ]
Hardware's page size is 4096, but the kernel's page size may vary. Driver
should use hardware's page size when communicating with hardware.
Fixes: 155055771704 ("RDMA/erdma: Add verbs implementation")
Link: https://lore.kernel.org/r/20230307102924.70577-2-chengyou@linux.alibaba.com
Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
drivers/infiniband/hw/erdma/erdma_hw.h | 4 ++++
drivers/infiniband/hw/erdma/erdma_verbs.c | 17 +++++++++--------
2 files changed, 13 insertions(+), 8 deletions(-)
diff --git a/drivers/infiniband/hw/erdma/erdma_hw.h b/drivers/infiniband/hw/erdma/erdma_hw.h
index 37ad1bb1..76ce2856 100644
--- a/drivers/infiniband/hw/erdma/erdma_hw.h
+++ b/drivers/infiniband/hw/erdma/erdma_hw.h
@@ -112,6 +112,10 @@
#define ERDMA_PAGE_SIZE_SUPPORT 0x7FFFF000
+/* Hardware page size definition */
+#define ERDMA_HW_PAGE_SHIFT 12
+#define ERDMA_HW_PAGE_SIZE 4096
+
/* WQE related. */
#define EQE_SIZE 16
#define EQE_SHIFT 4
diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.c b/drivers/infiniband/hw/erdma/erdma_verbs.c
index 9c30d787..83e1b0d5 100644
--- a/drivers/infiniband/hw/erdma/erdma_verbs.c
+++ b/drivers/infiniband/hw/erdma/erdma_verbs.c
@@ -38,7 +38,7 @@ static int create_qp_cmd(struct erdma_dev *dev, struct erdma_qp *qp)
FIELD_PREP(ERDMA_CMD_CREATE_QP_PD_MASK, pd->pdn);
if (rdma_is_kernel_res(&qp->ibqp.res)) {
- u32 pgsz_range = ilog2(SZ_1M) - PAGE_SHIFT;
+ u32 pgsz_range = ilog2(SZ_1M) - ERDMA_HW_PAGE_SHIFT;
req.sq_cqn_mtt_cfg =
FIELD_PREP(ERDMA_CMD_CREATE_QP_PAGE_SIZE_MASK,
@@ -66,13 +66,13 @@ static int create_qp_cmd(struct erdma_dev *dev, struct erdma_qp *qp)
user_qp = &qp->user_qp;
req.sq_cqn_mtt_cfg = FIELD_PREP(
ERDMA_CMD_CREATE_QP_PAGE_SIZE_MASK,
- ilog2(user_qp->sq_mtt.page_size) - PAGE_SHIFT);
+ ilog2(user_qp->sq_mtt.page_size) - ERDMA_HW_PAGE_SHIFT);
req.sq_cqn_mtt_cfg |=
FIELD_PREP(ERDMA_CMD_CREATE_QP_CQN_MASK, qp->scq->cqn);
req.rq_cqn_mtt_cfg = FIELD_PREP(
ERDMA_CMD_CREATE_QP_PAGE_SIZE_MASK,
- ilog2(user_qp->rq_mtt.page_size) - PAGE_SHIFT);
+ ilog2(user_qp->rq_mtt.page_size) - ERDMA_HW_PAGE_SHIFT);
req.rq_cqn_mtt_cfg |=
FIELD_PREP(ERDMA_CMD_CREATE_QP_CQN_MASK, qp->rcq->cqn);
@@ -162,7 +162,7 @@ static int create_cq_cmd(struct erdma_dev *dev, struct erdma_cq *cq)
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) - PAGE_SHIFT);
+ 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);
@@ -175,8 +175,9 @@ static int create_cq_cmd(struct erdma_dev *dev, struct erdma_cq *cq)
cq->kern_cq.qbuf_dma_addr + (cq->depth << CQE_SHIFT);
} else {
mtt = &cq->user_cq.qbuf_mtt;
- req.cfg0 |= FIELD_PREP(ERDMA_CMD_CREATE_CQ_PAGESIZE_MASK,
- ilog2(mtt->page_size) - PAGE_SHIFT);
+ req.cfg0 |=
+ FIELD_PREP(ERDMA_CMD_CREATE_CQ_PAGESIZE_MASK,
+ ilog2(mtt->page_size) - ERDMA_HW_PAGE_SHIFT);
if (mtt->mtt_nents == 1) {
req.qbuf_addr_l = lower_32_bits(*(u64 *)mtt->mtt_buf);
req.qbuf_addr_h = upper_32_bits(*(u64 *)mtt->mtt_buf);
@@ -636,7 +637,7 @@ static int init_user_qp(struct erdma_qp *qp, struct erdma_ucontext *uctx,
u32 rq_offset;
int ret;
- if (len < (PAGE_ALIGN(qp->attrs.sq_size * SQEBB_SIZE) +
+ if (len < (ALIGN(qp->attrs.sq_size * SQEBB_SIZE, ERDMA_HW_PAGE_SIZE) +
qp->attrs.rq_size * RQE_SIZE))
return -EINVAL;
@@ -646,7 +647,7 @@ static int init_user_qp(struct erdma_qp *qp, struct erdma_ucontext *uctx,
if (ret)
return ret;
- rq_offset = PAGE_ALIGN(qp->attrs.sq_size << SQEBB_SHIFT);
+ rq_offset = ALIGN(qp->attrs.sq_size << SQEBB_SHIFT, ERDMA_HW_PAGE_SIZE);
qp->user_qp.rq_offset = rq_offset;
ret = get_mtt_entries(qp->dev, &qp->user_qp.rq_mtt, va + rq_offset,
--
2.35.3