net: hns3: add error handler for hclge_reset()

When hclge_reset() is called, it may fail for several reasons.
For example, an higher-level reset event occurs, memory allocation
failure, hardware reset timeout, etc. Therefore, it is necessary
to add corresponding error handling for these situations.
1. A high-level reset is required due to a high-level reset failure.
2. For memory allocation failure, a high-level reset is initiated by
the timer to recover. The reason for using the timer is to prevent this
new high-level reset to interrupt the reset process of other pf/vf;
3. For the case of hardware reset timeout, reschedule the reset task
to wait for the hardware to complete the reset.
For memory allocation failure and reset timeouts, in order to prevent
an infinite number of scheduled reset tasks, the number of error
recovery needs to be limited.

This patch also add some reset related debug log printing.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 3 insertions, 0 deletions

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 69bdb7f646ee..36f341368683 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -102,6 +102,7 @@ enum HLCGE_PORT_TYPE {
 #define HCLGE_GLOBAL_RESET_REG		0x20A00
 #define HCLGE_GLOBAL_RESET_BIT		0
 #define HCLGE_CORE_RESET_BIT		1
+#define HCLGE_IMP_RESET_BIT		2
 #define HCLGE_FUN_RST_ING		0x20C00
 #define HCLGE_FUN_RST_ING_B		0
 
@@ -601,6 +602,7 @@ struct hclge_dev {
 	unsigned long reset_request;	/* reset has been requested */
 	unsigned long reset_pending;	/* client rst is pending to be served */
 	unsigned long reset_count;	/* the number of reset has been done */
+	u32 reset_fail_cnt;
 	u32 fw_version;
 	u16 num_vmdq_vport;		/* Num vmdq vport this PF has set up */
 	u16 num_tqps;			/* Num task queue pairs of this PF */
@@ -648,6 +650,7 @@ struct hclge_dev {
 	unsigned long service_timer_period;
 	unsigned long service_timer_previous;
 	struct timer_list service_timer;
+	struct timer_list reset_timer;
 	struct work_struct service_task;
 	struct work_struct rst_service_task;
 	struct work_struct mbx_service_task;