From: Guoqing Jiang <guoqing.jiang@linux.dev>
To: bmt@zurich.ibm.com, jgg@ziepe.ca, leon@kernel.org
Cc: linux-rdma@vger.kernel.org
Subject: [PATCH V3 16/18] RDMA/siw: Only check attrs->cap.max_send_wr in siw_create_qp
Date: Fri, 27 Oct 2023 10:33:26 +0800 [thread overview]
Message-ID: <20231027023328.30347-17-guoqing.jiang@linux.dev> (raw)
In-Reply-To: <20231027023328.30347-1-guoqing.jiang@linux.dev>
We can just check max_send_wr here given both max_send_wr and
max_recv_wr are defined as u32 type, and we also need to ensure
num_sqe (derived from max_send_wr) shouldn't be zero.
Signed-off-by: Guoqing Jiang <guoqing.jiang@linux.dev>
---
drivers/infiniband/sw/siw/siw_verbs.c | 18 +++++-------------
1 file changed, 5 insertions(+), 13 deletions(-)
diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c
index dcd69fc01176..ef149ed98946 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.c
+++ b/drivers/infiniband/sw/siw/siw_verbs.c
@@ -333,11 +333,10 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs,
goto err_atomic;
}
/*
- * NOTE: we allow for zero element SQ and RQ WQE's SGL's
- * but not for a QP unable to hold any WQE (SQ + RQ)
+ * NOTE: we don't allow for a QP unable to hold any SQ WQE
*/
- if (attrs->cap.max_send_wr + attrs->cap.max_recv_wr == 0) {
- siw_dbg(base_dev, "QP must have send or receive queue\n");
+ if (attrs->cap.max_send_wr == 0) {
+ siw_dbg(base_dev, "QP must have send queue\n");
rv = -EINVAL;
goto err_atomic;
}
@@ -357,21 +356,14 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs,
if (rv)
goto err_atomic;
- num_sqe = attrs->cap.max_send_wr;
- num_rqe = attrs->cap.max_recv_wr;
/* All queue indices are derived from modulo operations
* on a free running 'get' (consumer) and 'put' (producer)
* unsigned counter. Having queue sizes at power of two
* avoids handling counter wrap around.
*/
- if (num_sqe)
- num_sqe = roundup_pow_of_two(num_sqe);
- else {
- /* Zero sized SQ is not supported */
- rv = -EINVAL;
- goto err_out_xa;
- }
+ num_sqe = roundup_pow_of_two(attrs->cap.max_send_wr);
+ num_rqe = attrs->cap.max_recv_wr;
if (num_rqe)
num_rqe = roundup_pow_of_two(num_rqe);
--
2.35.3
next prev parent reply other threads:[~2023-10-27 2:34 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-27 2:33 [PATCH V3 00/18] Cleanup for siw Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 01/18] RDMA/siw: Introduce siw_get_page Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 02/18] RDMA/siw: Introduce siw_update_skb_rcvd Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 03/18] RDMA/siw: Use iov.iov_len in kernel_sendmsg Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 04/18] RDMA/siw: Remove goto lable in siw_mmap Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 05/18] RDMA/siw: Remove rcu from siw_qp Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 06/18] RDMA/siw: No need to check term_info.valid before call siw_send_terminate Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 07/18] RDMA/siw: Also goto out_sem_up if pin_user_pages returns 0 Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 08/18] RDMA/siw: Factor out siw_generic_rx helper Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 09/18] RDMA/siw: Introduce SIW_STAG_MAX_INDEX Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 10/18] RDMA/siw: Add one parameter to siw_destroy_cpulist Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 11/18] RDMA/siw: Introduce siw_cep_set_free_and_put Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 12/18] RDMA/siw: Introduce siw_free_cm_id Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 13/18] RDMA/siw: Cleanup siw_accept Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 14/18] RDMA/siw: Remove siw_sk_save_upcalls Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 15/18] RDMA/siw: Fix typo Guoqing Jiang
2023-10-27 2:33 ` Guoqing Jiang [this message]
2023-10-27 2:33 ` [PATCH V3 17/18] RDMA/siw: Introduce siw_destroy_cep_sock Guoqing Jiang
2023-10-27 2:33 ` [PATCH V3 18/18] RDMA/siw: Update comments for siw_qp_sq_process Guoqing Jiang
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=20231027023328.30347-17-guoqing.jiang@linux.dev \
--to=guoqing.jiang@linux.dev \
--cc=bmt@zurich.ibm.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).