This is a note to let you know that I've just added the patch titled
RDMA/hns: Fix init failure of RoCE VF and HIP08
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-init-failure-of-roce-vf-and-hip08.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 1d945bbfb31df580e23ae1ce37dc4fb7ccc21d7e
Author: Junxian Huang <huangjunxian6@xxxxxxxxxxxxx>
Date: Tue Oct 17 20:52:39 2023 +0800
RDMA/hns: Fix init failure of RoCE VF and HIP08
[ Upstream commit 07f06e0e5cd99555c861e874716d9e2627655fd5 ]
During device init, a struct for HW stats will be allocated. As HW
stats are not supported for VF and HIP08, currently
hns_roce_alloc_hw_port_stats() returns NULL in this case. However,
ib-core considers the returned NULL pointer as memory allocation
failure and returns ENOMEM, eventually leading to the failure of VF
and HIP08 init.
In the case where the driver does not support the .alloc_hw_port_stats()
ops, ib-core will return EOPNOTSUPP and ignore this error code in the
upper layer function. So for VF and HIP08, just don't set the HW stats
ops to ib-core.
Fixes: 5a87279591a1 ("RDMA/hns: Support hns HW stats")
Signed-off-by: Junxian Huang <huangjunxian6@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20231017125239.164455-8-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 e1a88f2d51b6c..4a9cd4d21bc99 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -553,10 +553,6 @@ static struct rdma_hw_stats *hns_roce_alloc_hw_port_stats(
return NULL;
}
- if (hr_dev->pci_dev->revision <= PCI_REVISION_ID_HIP08 ||
- hr_dev->is_vf)
- return NULL;
-
return rdma_alloc_hw_stats_struct(hns_roce_port_stats_descs,
ARRAY_SIZE(hns_roce_port_stats_descs),
RDMA_HW_STATS_DEFAULT_LIFESPAN);
@@ -576,10 +572,6 @@ static int hns_roce_get_hw_stats(struct ib_device *device,
if (port > hr_dev->caps.num_ports)
return -EINVAL;
- if (hr_dev->pci_dev->revision <= PCI_REVISION_ID_HIP08 ||
- hr_dev->is_vf)
- return -EOPNOTSUPP;
-
ret = hr_dev->hw->query_hw_counter(hr_dev, stats->value, port,
&num_counters);
if (ret) {
@@ -633,8 +625,6 @@ static const struct ib_device_ops hns_roce_dev_ops = {
.query_pkey = hns_roce_query_pkey,
.query_port = hns_roce_query_port,
.reg_user_mr = hns_roce_reg_user_mr,
- .alloc_hw_port_stats = hns_roce_alloc_hw_port_stats,
- .get_hw_stats = hns_roce_get_hw_stats,
INIT_RDMA_OBJ_SIZE(ib_ah, hns_roce_ah, ibah),
INIT_RDMA_OBJ_SIZE(ib_cq, hns_roce_cq, ib_cq),
@@ -643,6 +633,11 @@ static const struct ib_device_ops hns_roce_dev_ops = {
INIT_RDMA_OBJ_SIZE(ib_ucontext, hns_roce_ucontext, ibucontext),
};
+static const struct ib_device_ops hns_roce_dev_hw_stats_ops = {
+ .alloc_hw_port_stats = hns_roce_alloc_hw_port_stats,
+ .get_hw_stats = hns_roce_get_hw_stats,
+};
+
static const struct ib_device_ops hns_roce_dev_mr_ops = {
.rereg_user_mr = hns_roce_rereg_user_mr,
};
@@ -719,6 +714,10 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC)
ib_set_device_ops(ib_dev, &hns_roce_dev_xrcd_ops);
+ if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09 &&
+ !hr_dev->is_vf)
+ ib_set_device_ops(ib_dev, &hns_roce_dev_hw_stats_ops);
+
ib_set_device_ops(ib_dev, hr_dev->hw->hns_roce_dev_ops);
ib_set_device_ops(ib_dev, &hns_roce_dev_ops);
ib_set_device_ops(ib_dev, &hns_roce_dev_restrack_ops);
