[ Upstream commit
e8ea058edc2b225a68b307057a65599625daaebf ]
CMDQ may fail during HNS ROCEE initialization. The following is the log
when the execution fails:
hns3 0000:bd:00.2: In reset process RoCE client reinit.
hns3 0000:bd:00.2: CMDQ move tail from 840 to 839
hns3 0000:bd:00.2 hns_2: failed to set gid, ret = -11!
hns3 0000:bd:00.2: CMDQ move tail from 840 to 839
<...>
hns3 0000:bd:00.2: CMDQ move tail from 840 to 839
hns3 0000:bd:00.2: CMDQ move tail from 840 to 0
hns3 0000:bd:00.2: [cmd]token 14e mailbox 20 timeout.
hns3 0000:bd:00.2 hns_2: set HEM step 0 failed!
hns3 0000:bd:00.2 hns_2: set HEM address to HW failed!
hns3 0000:bd:00.2 hns_2: failed to alloc mtpt, ret = -16.
infiniband hns_2: Couldn't create ib_mad PD
infiniband hns_2: Couldn't open port 1
hns3 0000:bd:00.2: Reset done, RoCE client reinit finished.
However, even if ib_mad client registration failed, ib_register_device()
still returns success to the driver.
In the device initialization process, CMDQ execution fails because HW/FW
is abnormal. Therefore, if CMDQ fails, the initialization function should
set CMDQ to a fatal error state and return a failure to the caller.
Fixes:
9a4435375cd1 ("IB/hns: Add driver files for hns RoCE driver")
Link: https://lore.kernel.org/r/20220429093104.26687-1-liangwenpeng@huawei.com
Signed-off-by: Yangyang Li <liyangyang20@huawei.com>
Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
u16 busy;
};
+enum hns_roce_cmdq_state {
+ HNS_ROCE_CMDQ_STATE_NORMAL,
+ HNS_ROCE_CMDQ_STATE_FATAL_ERR,
+};
+
struct hns_roce_cmdq {
struct dma_pool *pool;
struct semaphore poll_sem;
* close device, switch into poll mode(non event mode)
*/
u8 use_events;
+ enum hns_roce_cmdq_state state;
};
struct hns_roce_cmd_mailbox {
return tail == priv->cmq.csq.head;
}
+static void update_cmdq_status(struct hns_roce_dev *hr_dev)
+{
+ struct hns_roce_v2_priv *priv = hr_dev->priv;
+ struct hnae3_handle *handle = priv->handle;
+
+ if (handle->rinfo.reset_state == HNS_ROCE_STATE_RST_INIT ||
+ handle->rinfo.instance_state == HNS_ROCE_STATE_INIT)
+ hr_dev->cmd.state = HNS_ROCE_CMDQ_STATE_FATAL_ERR;
+}
+
static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
struct hns_roce_cmq_desc *desc, int num)
{
csq->head, tail);
csq->head = tail;
+ update_cmdq_status(hr_dev);
+
ret = -EAGAIN;
}
bool busy;
int ret;
+ if (hr_dev->cmd.state == HNS_ROCE_CMDQ_STATE_FATAL_ERR)
+ return -EIO;
+
if (!v2_chk_mbox_is_avail(hr_dev, &busy))
return busy ? -EBUSY : 0;
{
int i;
+ if (hr_dev->cmd.state == HNS_ROCE_CMDQ_STATE_FATAL_ERR)
+ return;
+
for (i = hr_dev->func_num - 1; i >= 0; i--) {
__hns_roce_function_clear(hr_dev, i);
if (i != 0)
mb_st = (struct hns_roce_mbox_status *)desc.data;
end = msecs_to_jiffies(timeout) + jiffies;
while (v2_chk_mbox_is_avail(hr_dev, &busy)) {
+ if (hr_dev->cmd.state == HNS_ROCE_CMDQ_STATE_FATAL_ERR)
+ return -EIO;
+
status = 0;
hns_roce_cmq_setup_basic_desc(&desc, HNS_ROCE_OPC_QUERY_MB_ST,
true);