From: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
To: linux-rdma@vger.kernel.org, leonro@nvidia.com, jgg@nvidia.com,
zyjzyj2000@gmail.com
Cc: nvdimm@lists.linux.dev, linux-kernel@vger.kernel.org,
rpearsonhpe@gmail.com, yangx.jy@fujitsu.com,
lizhijian@fujitsu.com, y-goto@fujitsu.com,
Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
Subject: [PATCH for-next v3 2/7] RDMA/rxe: Always schedule works before accessing user MRs
Date: Fri, 23 Dec 2022 15:51:53 +0900 [thread overview]
Message-ID: <53e045f842a5519eb905c447eeff9441de609fdb.1671772917.git.matsuda-daisuke@fujitsu.com> (raw)
In-Reply-To: <cover.1671772917.git.matsuda-daisuke@fujitsu.com>
Both responder and completer can sleep to execute page-fault when used
with ODP, and page-fault handler can be invoked when they are going to
access user MRs, so works must be scheduled in such cases.
Signed-off-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
---
drivers/infiniband/sw/rxe/rxe_comp.c | 20 ++++++++++++++++++--
drivers/infiniband/sw/rxe/rxe_loc.h | 4 ++--
drivers/infiniband/sw/rxe/rxe_recv.c | 4 ++--
drivers/infiniband/sw/rxe/rxe_resp.c | 15 ++++++++++-----
4 files changed, 32 insertions(+), 11 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index 046bbacce37c..421f4ffe51a3 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -124,13 +124,29 @@ void retransmit_timer(struct timer_list *t)
}
}
-void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb)
+void rxe_comp_queue_pkt(struct rxe_pkt_info *pkt, struct sk_buff *skb)
{
+ struct rxe_qp *qp = pkt->qp;
int must_sched;
skb_queue_tail(&qp->resp_pkts, skb);
- must_sched = skb_queue_len(&qp->resp_pkts) > 1;
+ /* Schedule a work item if processing READ or ATOMIC acks.
+ * In these cases, completer may sleep to access ODP-enabled MRs.
+ */
+ switch (pkt->opcode) {
+ case IB_OPCODE_RC_RDMA_READ_RESPONSE_ONLY:
+ case IB_OPCODE_RC_RDMA_READ_RESPONSE_FIRST:
+ case IB_OPCODE_RC_RDMA_READ_RESPONSE_MIDDLE:
+ case IB_OPCODE_RC_RDMA_READ_RESPONSE_LAST:
+ case IB_OPCODE_RC_ATOMIC_ACKNOWLEDGE:
+ must_sched = 1;
+ break;
+
+ default:
+ must_sched = skb_queue_len(&qp->resp_pkts) > 1;
+ }
+
if (must_sched != 0)
rxe_counter_inc(SKB_TO_PKT(skb)->rxe, RXE_CNT_COMPLETER_SCHED);
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index 948ce4902b10..d567aa65b5e0 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -176,9 +176,9 @@ int rxe_icrc_init(struct rxe_dev *rxe);
int rxe_icrc_check(struct sk_buff *skb, struct rxe_pkt_info *pkt);
void rxe_icrc_generate(struct sk_buff *skb, struct rxe_pkt_info *pkt);
-void rxe_resp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb);
+void rxe_resp_queue_pkt(struct rxe_pkt_info *pkt, struct sk_buff *skb);
-void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb);
+void rxe_comp_queue_pkt(struct rxe_pkt_info *pkt, struct sk_buff *skb);
static inline unsigned int wr_opcode_mask(int opcode, struct rxe_qp *qp)
{
diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c
index 434a693cd4a5..01d07572a56f 100644
--- a/drivers/infiniband/sw/rxe/rxe_recv.c
+++ b/drivers/infiniband/sw/rxe/rxe_recv.c
@@ -174,9 +174,9 @@ static int hdr_check(struct rxe_pkt_info *pkt)
static inline void rxe_rcv_pkt(struct rxe_pkt_info *pkt, struct sk_buff *skb)
{
if (pkt->mask & RXE_REQ_MASK)
- rxe_resp_queue_pkt(pkt->qp, skb);
+ rxe_resp_queue_pkt(pkt, skb);
else
- rxe_comp_queue_pkt(pkt->qp, skb);
+ rxe_comp_queue_pkt(pkt, skb);
}
static void rxe_rcv_mcast_pkt(struct rxe_dev *rxe, struct sk_buff *skb)
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index d9134a00a529..991550baef8c 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -85,15 +85,20 @@ static char *resp_state_name[] = {
};
/* rxe_recv calls here to add a request packet to the input queue */
-void rxe_resp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb)
+void rxe_resp_queue_pkt(struct rxe_pkt_info *pkt, struct sk_buff *skb)
{
- int must_sched;
- struct rxe_pkt_info *pkt = SKB_TO_PKT(skb);
+ int must_sched = 1;
+ struct rxe_qp *qp = pkt->qp;
skb_queue_tail(&qp->req_pkts, skb);
- must_sched = (pkt->opcode == IB_OPCODE_RC_RDMA_READ_REQUEST) ||
- (skb_queue_len(&qp->req_pkts) > 1);
+ /* responder can sleep to access an ODP-enabled MR. Always schedule
+ * work items for non-zero-byte operations, RDMA READ, and ATOMIC
+ * operations.
+ */
+ if ((skb_queue_len(&qp->req_pkts) == 1) && (payload_size(pkt) == 0)
+ && !(pkt->mask & RXE_READ_OR_ATOMIC_MASK))
+ must_sched = 0;
if (must_sched)
rxe_sched_task(&qp->resp.task);
--
2.31.1
next prev parent reply other threads:[~2022-12-23 6:53 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-12-23 6:51 [PATCH for-next v3 0/7] On-Demand Paging on SoftRoCE Daisuke Matsuda
2022-12-23 6:51 ` [PATCH for-next v3 1/7] RDMA/rxe: Convert triple tasklets to use workqueue Daisuke Matsuda
2022-12-28 16:56 ` Bob Pearson
2022-12-29 1:23 ` Zhu Yanjun
2022-12-29 7:02 ` Leon Romanovsky
2023-01-06 2:26 ` Daisuke Matsuda (Fujitsu)
2022-12-23 6:51 ` Daisuke Matsuda [this message]
2022-12-23 6:51 ` [PATCH for-next v3 3/7] RDMA/rxe: Cleanup code for responder Atomic operations Daisuke Matsuda
2023-01-16 18:21 ` Jason Gunthorpe
2022-12-23 6:51 ` [PATCH for-next v3 4/7] RDMA/rxe: Add page invalidation support Daisuke Matsuda
2023-01-16 18:23 ` Jason Gunthorpe
2022-12-23 6:51 ` [PATCH for-next v3 5/7] RDMA/rxe: Allow registering MRs for On-Demand Paging Daisuke Matsuda
2022-12-23 6:51 ` [PATCH for-next v3 6/7] RDMA/rxe: Add support for Send/Recv/Write/Read operations with ODP Daisuke Matsuda
2022-12-23 6:51 ` [PATCH for-next v3 7/7] RDMA/rxe: Add support for the traditional Atomic " Daisuke Matsuda
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=53e045f842a5519eb905c447eeff9441de609fdb.1671772917.git.matsuda-daisuke@fujitsu.com \
--to=matsuda-daisuke@fujitsu.com \
--cc=jgg@nvidia.com \
--cc=leonro@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=lizhijian@fujitsu.com \
--cc=nvdimm@lists.linux.dev \
--cc=rpearsonhpe@gmail.com \
--cc=y-goto@fujitsu.com \
--cc=yangx.jy@fujitsu.com \
--cc=zyjzyj2000@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
all inboxes | Powered by JetHome®