On hi08 chip, There is a possibility of chip hanging and
some errors when sending mailbox & doorbell during reset.
We can fix it by prohibiting mailbox and doorbell during
reset and reset occurred to ensure that hardware can work
normally.
Fixes: a04ff739f2a9 ("RDMA/hns: Add command queue support for hip08 RoCE driver")
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@xxxxxxxxxx>
---
drivers/infiniband/hw/hns/hns_roce_cmd.c | 32 ++++--
drivers/infiniband/hw/hns/hns_roce_device.h | 7 ++
drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 154 +++++++++++++++++++++++++++-
drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 3 +
4 files changed, 183 insertions(+), 13 deletions(-)
diff --git a/drivers/infiniband/hw/hns/hns_roce_cmd.c b/drivers/infiniband/hw/hns/hns_roce_cmd.c
index a0ba19d..2acf946 100644
--- a/drivers/infiniband/hw/hns/hns_roce_cmd.c
+++ b/drivers/infiniband/hw/hns/hns_roce_cmd.c
@@ -176,17 +176,33 @@ int hns_roce_cmd_mbox(struct hns_roce_dev *hr_dev, u64 in_param, u64 out_param,
unsigned long in_modifier, u8 op_modifier, u16 op,
unsigned long timeout)
{
- if (hr_dev->is_reset)
- return 0;
+ int ret;
+
+ if (hr_dev->hw->rst_prc_mbox) {
+ ret = hr_dev->hw->rst_prc_mbox(hr_dev);
+ if (ret == CMD_RST_PRC_SUCCESS)
+ return 0;
+ else if (ret == CMD_RST_PRC_EBUSY)
+ return -EBUSY;
+ }
if (hr_dev->cmd.use_events)
- return hns_roce_cmd_mbox_wait(hr_dev, in_param, out_param,
- in_modifier, op_modifier, op,
- timeout);
+ ret = hns_roce_cmd_mbox_wait(hr_dev, in_param, out_param,
+ in_modifier, op_modifier, op,
+ timeout);
else
- return hns_roce_cmd_mbox_poll(hr_dev, in_param, out_param,
- in_modifier, op_modifier, op,
- timeout);
+ ret = hns_roce_cmd_mbox_poll(hr_dev, in_param, out_param,
+ in_modifier, op_modifier, op,
+ timeout);
+
+ if (ret == CMD_RST_PRC_EBUSY)
+ return -EBUSY;
+
+ if (ret && (hr_dev->hw->rst_prc_mbox &&
+ hr_dev->hw->rst_prc_mbox(hr_dev) == CMD_RST_PRC_SUCCESS))
+ return 0;
+
+ return ret;
}
EXPORT_SYMBOL_GPL(hns_roce_cmd_mbox);
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index f4cac63..cd7c2a6 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -236,6 +236,12 @@ enum {
HNS_ROCE_RST_DIRECT_RETURN = 0,
};
+enum {
+ CMD_RST_PRC_OTHERS,
+ CMD_RST_PRC_SUCCESS,
+ CMD_RST_PRC_EBUSY,
+};
+
#define HNS_ROCE_CMD_SUCCESS 1
#define HNS_ROCE_PORT_DOWN 0
@@ -854,6 +860,7 @@ struct hns_roce_hw {
u64 out_param, u32 in_modifier, u8 op_modifier, u16 op,
u16 token, int event);
int (*chk_mbox)(struct hns_roce_dev *hr_dev, unsigned long timeout);
+ int (*rst_prc_mbox)(struct hns_roce_dev *hr_dev);
int (*set_gid)(struct hns_roce_dev *hr_dev, u8 port, int gid_index,
const union ib_gid *gid, const struct ib_gid_attr *attr);
int (*set_mac)(struct hns_roce_dev *hr_dev, u8 phy_port, u8 *addr);
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index dadb685..5f476e9 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -712,6 +712,125 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
return ret;
}
+static int hns_roce_v2_cmd_hw_reseted(struct hns_roce_dev *hr_dev,
+ unsigned long instance_stage,
+ unsigned long reset_stage)
+{
+ /* When hardware reset has been completed once or more, we should stop
+ * sending mailbox&cmq to hardware. If now in .init_instance()
+ * function, we should exit with error. If now at HNAE3_INIT_CLIENT
+ * stage of soft reset process, we should exit with error, and then
+ * HNAE3_INIT_CLIENT related process can rollback the operation like
+ * notifing hardware to free resources, HNAE3_INIT_CLIENT related
+ * process will exit with error to notify NIC driver to reschedule soft
+ * reset process once again.
+ */
+ hr_dev->is_reset = true;
+
+ if (reset_stage == HNS_ROCE_STATE_RST_INIT ||
+ instance_stage == HNS_ROCE_STATE_INIT)
+ return CMD_RST_PRC_EBUSY;
+
+ return CMD_RST_PRC_SUCCESS;
+}
+
+static int hns_roce_v2_cmd_hw_resetting(struct hns_roce_dev *hr_dev,
+ unsigned long instance_stage,
+ unsigned long reset_stage)
+{
+ struct hns_roce_v2_priv *priv = (struct hns_roce_v2_priv *)hr_dev->priv;
+ struct hnae3_handle *handle = priv->handle;
+ const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+ unsigned long end;
+
+ /* When hardware reset is detected, we should stop sending mailbox&cmq
+ * to hardware, and wait until hardware reset finished. If now
+ * in .init_instance() function, we should exit with error. If now at
+ * HNAE3_INIT_CLIENT stage of soft reset process, we should exit with
+ * error, and then HNAE3_INIT_CLIENT related process can rollback the
+ * operation like notifing hardware to free resources, HNAE3_INIT_CLIENT
+ * related process will exit with error to notify NIC driver to
+ * reschedule soft reset process once again.
+ */
+ end = msecs_to_jiffies(HNS_ROCE_V2_HW_RST_TIMEOUT) + jiffies;
+ while (ops->get_hw_reset_stat(handle) && time_before(jiffies, end))
+ udelay(1);
+
+ if (!ops->get_hw_reset_stat(handle))
+ hr_dev->is_reset = true;
+ else
+ dev_warn(hr_dev->dev, "hw_resetting!\n");
+
+ if (!hr_dev->is_reset || reset_stage == HNS_ROCE_STATE_RST_INIT ||
+ instance_stage == HNS_ROCE_STATE_INIT)
+ return CMD_RST_PRC_EBUSY;
+
+ return CMD_RST_PRC_SUCCESS;
+}
+
+static int hns_roce_v2_cmd_sw_resetting(struct hns_roce_dev *hr_dev)
+{
+ struct hns_roce_v2_priv *priv = (struct hns_roce_v2_priv *)hr_dev->priv;
+ struct hnae3_handle *handle = priv->handle;
+ const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+ unsigned long end;
+
+ /* When software reset is detected at .init_instance() function, we
+ * should stop sending mailbox&cmq to hardware, and
+ * wait until hardware reset finished, we should exit with error.
+ */
+ end = msecs_to_jiffies(HNS_ROCE_V2_HW_RST_TIMEOUT) + jiffies;
+ while (ops->ae_dev_reset_cnt(handle) == hr_dev->reset_cnt &&
+ time_before(jiffies, end))
+ udelay(1);
+
+ if (ops->ae_dev_reset_cnt(handle) != hr_dev->reset_cnt)
+ hr_dev->is_reset = true;
+ else
+ dev_warn(hr_dev->dev, "reset_cnt no change!\n");
+
+ return CMD_RST_PRC_EBUSY;
+}
+
+static int hns_roce_v2_rst_process_cmd(struct hns_roce_dev *hr_dev)
+{
+ struct hns_roce_v2_priv *priv = (struct hns_roce_v2_priv *)hr_dev->priv;
+ struct hnae3_handle *handle = priv->handle;
+ const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+ unsigned long instance_stage; /* the current instance stage */
+ unsigned long reset_stage; /* the current reset stage */
+ unsigned long reset_cnt;
+ bool sw_resetting;
+ bool hw_resetting;
+
+ if (hr_dev->is_reset)
+ return CMD_RST_PRC_SUCCESS;
+
+ /* Get information about reset from NIC driver or RoCE driver itself,
+ * the meaning of the following variables from NIC driver are described
+ * as below:
+ * reset_cnt -- The count value of completed hardware reset.
+ * hw_resetting -- Whether hardware device is resetting now.
+ * sw_resetting -- Whether NIC's software reset process is running now.
+ */
+ instance_stage = handle->rinfo.instance_state;
+ reset_stage = handle->rinfo.reset_state;
+ reset_cnt = ops->ae_dev_reset_cnt(handle);
+ hw_resetting = ops->get_hw_reset_stat(handle);
+ sw_resetting = ops->ae_dev_resetting(handle);
+
+ if (reset_cnt != hr_dev->reset_cnt)
+ return hns_roce_v2_cmd_hw_reseted(hr_dev, instance_stage,
+ reset_stage);
+ else if (hw_resetting)
+ return hns_roce_v2_cmd_hw_resetting(hr_dev, instance_stage,
+ reset_stage);
+ else if (sw_resetting && instance_stage == HNS_ROCE_STATE_INIT)
+ return hns_roce_v2_cmd_sw_resetting(hr_dev);
+
+ return 0;
+}
+
static int hns_roce_cmq_space(struct hns_roce_v2_cmq_ring *ring)
{
int ntu = ring->next_to_use;
@@ -892,8 +1011,8 @@ static int hns_roce_cmq_csq_clean(struct hns_roce_dev *hr_dev)
return clean;
}
-static int hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
- struct hns_roce_cmq_desc *desc, int num)
+static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
+ struct hns_roce_cmq_desc *desc, int num)
{
struct hns_roce_v2_priv *priv = (struct hns_roce_v2_priv *)hr_dev->priv;
struct hns_roce_v2_cmq_ring *csq = &priv->cmq.csq;
@@ -905,9 +1024,6 @@ static int hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
int ret = 0;
int ntc;
- if (hr_dev->is_reset)
- return 0;
-
spin_lock_bh(&csq->lock);
if (num > hns_roce_cmq_space(csq)) {
@@ -982,6 +1098,30 @@ static int hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
return ret;
}
+int hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
+ struct hns_roce_cmq_desc *desc, int num)
+{
+ int retval;
+ int ret;
+
+ ret = hns_roce_v2_rst_process_cmd(hr_dev);
+ if (ret == CMD_RST_PRC_SUCCESS)
+ return 0;
+ if (ret == CMD_RST_PRC_EBUSY)
+ return ret;
+
+ ret = __hns_roce_cmq_send(hr_dev, desc, num);
+ if (ret) {
+ retval = hns_roce_v2_rst_process_cmd(hr_dev);
+ if (retval == CMD_RST_PRC_SUCCESS)
+ return 0;
+ else if (retval == CMD_RST_PRC_EBUSY)
+ return retval;
+ }
+
+ return ret;
+}
+
static int hns_roce_cmq_query_hw_info(struct hns_roce_dev *hr_dev)
{
struct hns_roce_query_version *resp;
@@ -1735,6 +1875,9 @@ static int hns_roce_v2_chk_mbox(struct hns_roce_dev *hr_dev,
status = hns_roce_v2_cmd_complete(hr_dev);
if (status != 0x1) {
+ if (status == CMD_RST_PRC_EBUSY)
+ return status;
+
dev_err(dev, "mailbox status 0x%x!\n", status);
return -EBUSY;
}
@@ -5758,6 +5901,7 @@ static int hns_roce_v2_post_srq_recv(struct ib_srq *ibsrq,
.hw_exit = hns_roce_v2_exit,
.post_mbox = hns_roce_v2_post_mbox,
.chk_mbox = hns_roce_v2_chk_mbox,
+ .rst_prc_mbox = hns_roce_v2_rst_process_cmd,
.set_gid = hns_roce_v2_set_gid,
.set_mac = hns_roce_v2_set_mac,
.write_mtpt = hns_roce_v2_write_mtpt,
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index 8def828..17b3299 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -90,6 +90,9 @@
#define HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE 2
#define HNS_ROCE_V2_RSV_QPS 8
+/* Time out for hardware to complete reset */
+#define HNS_ROCE_V2_HW_RST_TIMEOUT 1000
+
/* The longest time for software reset process in NIC subsystem, if a timeout
* occurs, it indicates that the network subsystem has encountered a serious
* error and cannot be recovered from the reset processing.
--
1.9.1
