This is a note to let you know that I've just added the patch titled
RDMA/hns: Fix deadlock on SRQ async events.
to the 6.6-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
rdma-hns-fix-deadlock-on-srq-async-events.patch
and it can be found in the queue-6.6 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 3f4ffcd7e7f3706428989e91e3a4497051c30a32
Author: Chengchang Tang <tangchengchang@xxxxxxxxxx>
Date: Fri Apr 12 17:16:10 2024 +0800
RDMA/hns: Fix deadlock on SRQ async events.
[ Upstream commit b46494b6f9c19f141114a57729e198698f40af37 ]
xa_lock for SRQ table may be required in AEQ. Use xa_store_irq()/
xa_erase_irq() to avoid deadlock.
Fixes: 81fce6291d99 ("RDMA/hns: Add SRQ asynchronous event support")
Signed-off-by: Chengchang Tang <tangchengchang@xxxxxxxxxx>
Signed-off-by: Junxian Huang <huangjunxian6@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20240412091616.370789-5-huangjunxian6@xxxxxxxxxxxxx
Signed-off-by: Leon Romanovsky <leon@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index 4a9cd4d21bc99..c8c49110a3378 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -37,6 +37,7 @@
#include <rdma/ib_smi.h>
#include <rdma/ib_user_verbs.h>
#include <rdma/ib_cache.h>
+#include "hnae3.h"
#include "hns_roce_common.h"
#include "hns_roce_device.h"
#include "hns_roce_hem.h"
diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c
index 8dae98f827eb2..6a4923c21cbc6 100644
--- a/drivers/infiniband/hw/hns/hns_roce_srq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_srq.c
@@ -122,7 +122,7 @@ static int alloc_srqc(struct hns_roce_dev *hr_dev, struct hns_roce_srq *srq)
return ret;
}
- ret = xa_err(xa_store(&srq_table->xa, srq->srqn, srq, GFP_KERNEL));
+ ret = xa_err(xa_store_irq(&srq_table->xa, srq->srqn, srq, GFP_KERNEL));
if (ret) {
ibdev_err(ibdev, "failed to store SRQC, ret = %d.\n", ret);
goto err_put;
@@ -135,7 +135,7 @@ static int alloc_srqc(struct hns_roce_dev *hr_dev, struct hns_roce_srq *srq)
return 0;
err_xa:
- xa_erase(&srq_table->xa, srq->srqn);
+ xa_erase_irq(&srq_table->xa, srq->srqn);
err_put:
hns_roce_table_put(hr_dev, &srq_table->table, srq->srqn);
@@ -153,7 +153,7 @@ static void free_srqc(struct hns_roce_dev *hr_dev, struct hns_roce_srq *srq)
dev_err(hr_dev->dev, "DESTROY_SRQ failed (%d) for SRQN %06lx\n",
ret, srq->srqn);
- xa_erase(&srq_table->xa, srq->srqn);
+ xa_erase_irq(&srq_table->xa, srq->srqn);
if (refcount_dec_and_test(&srq->refcount))
complete(&srq->free);
