RDMA/hns: Fix deadlock on SRQ async events.

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@huawei.com>
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://lore.kernel.org/r/20240412091616.370789-5-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>

diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index 4d94fcb8685ab0f4b80a9d9bda7a504248a8f883..d202258368ed99bb4d928bb8faa3f31f660e6c39 100644 (file)
--- 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 e4705ccdfa6518060c9f69f42ba7223547428ee9..7210e53a82f339cf24a40a8adbb00e6bc2feeb62 100644 (file)
--- a/drivers/infiniband/hw/hns/hns_roce_srq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_srq.c
@@ -123,7 +123,7 @@ 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;
@@ -136,7 +136,7 @@ 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);
 
@@ -154,7 +154,7 @@ 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);