OrgACRN
/
acrn-kernel
mirror of https://github.com/projectacrn/acrn-kernel.git
1
0
Fork 0
Code Issues Releases Wiki Activity

RDMA/rxe: Fix incomplete state save in rxe_requester 

[ Upstream commit 5d122db2ff ]

If a send packet is dropped by the IP layer in rxe_requester()
the call to rxe_xmit_packet() can fail with err == -EAGAIN.
To recover, the state of the wqe is restored to the state before
the packet was sent so it can be resent. However, the routines
that save and restore the state miss a significnt part of the
variable state in the wqe, the dma struct which is used to process
through the sge table. And, the state is not saved before the packet
is built which modifies the dma struct.

Under heavy stress testing with many QPs on a fast node sending
large messages to a slow node dropped packets are observed and
the resent packets are corrupted because the dma struct was not
restored. This patch fixes this behavior and allows the test cases
to succeed.

Fixes: 3050b99850 ("IB/rxe: Fix race condition between requester and completer")
Link: https://lore.kernel.org/r/20230721200748.4604-1-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
Bob Pearson 2023-07-21 15:07:49 -05:00 committed by Greg Kroah-Hartman
parent 59a4f61fec
commit 70518f3aaf
1 changed files with 27 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
drivers/infiniband/sw/rxe/rxe_req.c
View File

@ -529,10 +529,11 @@ static void save_state(struct rxe_send_wqe *wqe,
struct rxe_send_wqe *rollback_wqe,
u32 *rollback_psn)
{
rollback_wqe->state = wqe->state;
rollback_wqe->state = wqe->state;
rollback_wqe->first_psn = wqe->first_psn;
rollback_wqe->last_psn = wqe->last_psn;
*rollback_psn = qp->req.psn;
rollback_wqe->last_psn = wqe->last_psn;
rollback_wqe->dma = wqe->dma;
*rollback_psn = qp->req.psn;
}
static void rollback_state(struct rxe_send_wqe *wqe,
@ -540,10 +541,11 @@ static void rollback_state(struct rxe_send_wqe *wqe,
struct rxe_send_wqe *rollback_wqe,
u32 rollback_psn)
{
wqe->state = rollback_wqe->state;
wqe->state = rollback_wqe->state;
wqe->first_psn = rollback_wqe->first_psn;
wqe->last_psn = rollback_wqe->last_psn;
qp->req.psn = rollback_psn;
wqe->last_psn = rollback_wqe->last_psn;
wqe->dma = rollback_wqe->dma;
qp->req.psn = rollback_psn;
}
static void update_state(struct rxe_qp *qp, struct rxe_pkt_info *pkt)
@ -746,6 +748,9 @@ int rxe_requester(void *arg)
pkt.mask = rxe_opcode[opcode].mask;
pkt.wqe = wqe;
/* save wqe state before we build and send packet */
save_state(wqe, qp, &rollback_wqe, &rollback_psn);
av = rxe_get_av(&pkt, &ah);
if (unlikely(!av)) {
pr_err("qp#%d Failed no address vector\n", qp_num(qp));
@ -778,29 +783,29 @@ int rxe_requester(void *arg)
if (ah)
rxe_put(ah);
/*
* To prevent a race on wqe access between requester and completer,
* wqe members state and psn need to be set before calling
* rxe_xmit_packet().
* Otherwise, completer might initiate an unjustified retry flow.
*/
save_state(wqe, qp, &rollback_wqe, &rollback_psn);
/* update wqe state as though we had sent it */
update_wqe_state(qp, wqe, &pkt);
update_wqe_psn(qp, wqe, &pkt, payload);
err = rxe_xmit_packet(qp, &pkt, skb);
if (err) {
qp->need_req_skb = 1;
rollback_state(wqe, qp, &rollback_wqe, rollback_psn);
if (err == -EAGAIN) {
rxe_sched_task(&qp->req.task);
goto exit;
if (err != -EAGAIN) {
wqe->status = IB_WC_LOC_QP_OP_ERR;
goto err;
}
wqe->status = IB_WC_LOC_QP_OP_ERR;
goto err;
/* the packet was dropped so reset wqe to the state
* before we sent it so we can try to resend
*/
rollback_state(wqe, qp, &rollback_wqe, rollback_psn);
/* force a delay until the dropped packet is freed and
* the send queue is drained below the low water mark
*/
qp->need_req_skb = 1;
rxe_sched_task(&qp->req.task);
goto exit;
}
update_state(qp, &pkt);