From: Bob Pearson <rpearsonhpe@gmail.com>
To: jgg@nvidia.com, zyj2000@gmail.com, linux-rdma@vger.kernel.org
Cc: Bob Pearson <rpearsonhpe@gmail.com>
Subject: [PATCH for-next v8 10/10] RDMA/rxe: Disallow MR dereg and invalidate when bound
Date: Tue, 25 May 2021 16:37:52 -0500 [thread overview]
Message-ID: <20210525213751.629017-11-rpearsonhpe@gmail.com> (raw)
In-Reply-To: <20210525213751.629017-1-rpearsonhpe@gmail.com>
Check that an MR has no bound MWs before allowing a dereg or invalidate
operation.
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
---
drivers/infiniband/sw/rxe/rxe_loc.h | 1 +
drivers/infiniband/sw/rxe/rxe_mr.c | 25 +++++++++++++++++++++++++
drivers/infiniband/sw/rxe/rxe_verbs.c | 11 -----------
3 files changed, 26 insertions(+), 11 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index 6e4b5e22541e..1ddb20855dee 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -87,6 +87,7 @@ struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length);
int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
int rxe_invalidate_mr(struct rxe_qp *qp, u32 rkey);
+int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata);
void rxe_mr_cleanup(struct rxe_pool_entry *arg);
/* rxe_mw.c */
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index 3fb58d2c7814..7f169329a8bf 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -546,6 +546,13 @@ int rxe_invalidate_mr(struct rxe_qp *qp, u32 rkey)
goto err_drop_ref;
}
+ if (atomic_read(&mr->num_mw) > 0) {
+ pr_warn("%s: Attempt to invalidate an MR while bound to MWs\n",
+ __func__);
+ ret = -EINVAL;
+ goto err_drop_ref;
+ }
+
mr->state = RXE_MR_STATE_FREE;
ret = 0;
@@ -555,6 +562,24 @@ int rxe_invalidate_mr(struct rxe_qp *qp, u32 rkey)
return ret;
}
+int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
+{
+ struct rxe_mr *mr = to_rmr(ibmr);
+
+ if (atomic_read(&mr->num_mw) > 0) {
+ pr_warn("%s: Attempt to deregister an MR while bound to MWs\n",
+ __func__);
+ return -EINVAL;
+ }
+
+ mr->state = RXE_MR_STATE_ZOMBIE;
+ rxe_drop_ref(mr_pd(mr));
+ rxe_drop_index(mr);
+ rxe_drop_ref(mr);
+
+ return 0;
+}
+
void rxe_mr_cleanup(struct rxe_pool_entry *arg)
{
struct rxe_mr *mr = container_of(arg, typeof(*mr), pelem);
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 4860e8ab378e..3e0bab4994d1 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -913,17 +913,6 @@ static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd,
return ERR_PTR(err);
}
-static int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
-{
- struct rxe_mr *mr = to_rmr(ibmr);
-
- mr->state = RXE_MR_STATE_ZOMBIE;
- rxe_drop_ref(mr_pd(mr));
- rxe_drop_index(mr);
- rxe_drop_ref(mr);
- return 0;
-}
-
static struct ib_mr *rxe_alloc_mr(struct ib_pd *ibpd, enum ib_mr_type mr_type,
u32 max_num_sg)
{
--
2.30.2
next prev parent reply other threads:[~2021-05-25 21:38 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-05-25 21:37 [PATCH for-next v8 00/10] RDMA/rxe: Implement memory windows Bob Pearson
2021-05-25 21:37 ` [PATCH for-next v8 1/9] RDMA/rxe: Add bind MW fields to rxe_send_wr Bob Pearson
2021-05-25 21:37 ` [PATCH for-next v8 02/10] RDMA/rxe: Return errors for add index and key Bob Pearson
2021-05-25 21:37 ` [PATCH for-next v8 03/10] RDMA/rxe: Enable MW object pool Bob Pearson
2021-05-25 21:37 ` [PATCH for-next v8 04/10] RDMA/rxe: Add ib_alloc_mw and ib_dealloc_mw verbs Bob Pearson
2021-05-25 21:37 ` [PATCH for-next v8 05/10] RDMA/rxe: Replace WR_REG_MASK by WR_LOCAL_OP_MASK Bob Pearson
2021-05-25 21:37 ` [PATCH for-next v8 06/10] RDMA/rxe: Move local ops to subroutine Bob Pearson
2021-05-25 21:37 ` [PATCH for-next v8 07/10] RDMA/rxe: Add support for bind MW work requests Bob Pearson
2021-05-25 21:37 ` [PATCH for-next v8 08/10] RDMA/rxe: Implement invalidate MW operations Bob Pearson
2021-05-25 21:37 ` [PATCH for-next v8 09/10] RDMA/rxe: Implement memory access through MWs Bob Pearson
2021-05-25 21:37 ` Bob Pearson [this message]
2021-06-03 18:58 ` [PATCH for-next v8 00/10] RDMA/rxe: Implement memory windows Jason Gunthorpe
2021-06-04 3:22 ` Pearson, Robert B
2021-06-04 5:37 ` Zhu Yanjun
2021-06-04 15:25 ` Pearson, Robert B
2021-06-04 16:22 ` Pearson, Robert B
2021-06-04 17:53 ` Pearson, Robert B
2021-06-04 17:55 ` Jason Gunthorpe
2021-06-04 19:26 ` Pearson, Robert B
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=20210525213751.629017-11-rpearsonhpe@gmail.com \
--to=rpearsonhpe@gmail.com \
--cc=jgg@nvidia.com \
--cc=linux-rdma@vger.kernel.org \
--cc=zyj2000@gmail.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