From: rao Shoaib <rao.shoaib@oracle.com>
To: monis@mellanox.com, dledford@redhat.com, sean.hefty@intel.com,
hal.rosenstock@gmail.com, linux-rdma@vger.kernel.org,
linux-kernel@vger.kernel.org, rao.shoaib@oracle.com
Subject: [PATCH v2 1/2] Introduce maximum WQE size to check limits
Date: Mon, 18 Nov 2019 11:54:38 -0800 [thread overview]
Message-ID: <1574106879-19211-2-git-send-email-rao.shoaib@oracle.com> (raw)
In-Reply-To: <1574106879-19211-1-git-send-email-rao.shoaib@oracle.com>
From: Rao Shoaib <rao.shoaib@oracle.com>
Introduce maximum WQE size to impose limits on max SGE's and inline data
Signed-off-by: Rao Shoaib <rao.shoaib@oracle.com>
---
drivers/infiniband/sw/rxe/rxe_param.h | 3 ++-
drivers/infiniband/sw/rxe/rxe_qp.c | 7 +++++--
2 files changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h
index 1b596fb..31fb5c7 100644
--- a/drivers/infiniband/sw/rxe/rxe_param.h
+++ b/drivers/infiniband/sw/rxe/rxe_param.h
@@ -68,7 +68,6 @@ enum rxe_device_param {
RXE_HW_VER = 0,
RXE_MAX_QP = 0x10000,
RXE_MAX_QP_WR = 0x4000,
- RXE_MAX_INLINE_DATA = 400,
RXE_DEVICE_CAP_FLAGS = IB_DEVICE_BAD_PKEY_CNTR
| IB_DEVICE_BAD_QKEY_CNTR
| IB_DEVICE_AUTO_PATH_MIG
@@ -79,7 +78,9 @@ enum rxe_device_param {
| IB_DEVICE_RC_RNR_NAK_GEN
| IB_DEVICE_SRQ_RESIZE
| IB_DEVICE_MEM_MGT_EXTENSIONS,
+ RXE_MAX_WQE_SIZE = 0x2d0, /* For RXE_MAX_SGE */
RXE_MAX_SGE = 32,
+ RXE_MAX_INLINE_DATA = RXE_MAX_WQE_SIZE,
RXE_MAX_SGE_RD = 32,
RXE_MAX_CQ = 16384,
RXE_MAX_LOG_CQE = 15,
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index aeea994..323e43d 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -78,9 +78,12 @@ static int rxe_qp_chk_cap(struct rxe_dev *rxe, struct ib_qp_cap *cap,
}
}
- if (cap->max_inline_data > rxe->max_inline_data) {
+ if (cap->max_inline_data >
+ rxe->max_inline_data - sizeof(struct rxe_send_wqe)) {
pr_warn("invalid max inline data = %d > %d\n",
- cap->max_inline_data, rxe->max_inline_data);
+ cap->max_inline_data,
+ rxe->max_inline_data -
+ (u32)sizeof(struct rxe_send_wqe));
goto err1;
}
--
1.8.3.1
next prev parent reply other threads:[~2019-11-18 19:54 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-18 19:54 [PATCH v2 0/2] rxe should use same buffer size for SGE's and inline data rao Shoaib
2019-11-18 19:54 ` rao Shoaib [this message]
2019-11-19 20:31 ` [PATCH v2 1/2] Introduce maximum WQE size to check limits Jason Gunthorpe
2019-11-19 22:38 ` Rao Shoaib
2019-11-19 23:13 ` Jason Gunthorpe
2019-11-19 23:55 ` Rao Shoaib
2019-11-20 0:08 ` Jason Gunthorpe
2019-12-17 19:38 ` Rao Shoaib
2019-12-19 18:25 ` Jason Gunthorpe
2019-12-19 18:37 ` Rao Shoaib
2020-01-13 18:35 ` Rao Shoaib
2020-01-13 18:47 ` Jason Gunthorpe
2020-01-13 19:16 ` Rao Shoaib
2019-11-18 19:54 ` [PATCH v2 2/2] SGE buffer and max_inline data must have same size rao Shoaib
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=1574106879-19211-2-git-send-email-rao.shoaib@oracle.com \
--to=rao.shoaib@oracle.com \
--cc=dledford@redhat.com \
--cc=hal.rosenstock@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=monis@mellanox.com \
--cc=sean.hefty@intel.com \
/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).