[05/13] net/bnxt: handle fatal event from FW under error conditions
Checks
Commit Message
From: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
When firmware hit some unrecoverable error conditions, firmware initiate
the recovery by sending an async event EVENT_CMPL_EVENT_ID_RESET_NOTIFY
with data1 set to RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL
to all host drivers and will reset the chip.
The recovery procedure is same sequence as the one for hot FW upgrade.
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
---
drivers/net/bnxt/bnxt_cpr.c | 13 +++++++++++--
drivers/net/bnxt/bnxt_cpr.h | 5 +++++
drivers/net/bnxt/bnxt_ethdev.c | 3 +++
3 files changed, 19 insertions(+), 2 deletions(-)
@@ -20,6 +20,7 @@ void bnxt_handle_async_event(struct bnxt *bp,
struct hwrm_async_event_cmpl *async_cmp =
(struct hwrm_async_event_cmpl *)cmp;
uint16_t event_id = rte_le_to_cpu_16(async_cmp->event_id);
+ uint32_t event_data;
/* TODO: HWRM async events are not defined yet */
/* Needs to handle: link events, error events, etc. */
@@ -41,6 +42,7 @@ void bnxt_handle_async_event(struct bnxt *bp,
PMD_DRV_LOG(INFO, "Port conn async event\n");
break;
case HWRM_ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY:
+ event_data = rte_le_to_cpu_32(async_cmp->event_data1);
/* timestamp_lo/hi values are in units of 100ms */
bp->fw_reset_max_msecs = async_cmp->timestamp_hi ?
rte_le_to_cpu_16(async_cmp->timestamp_hi) * 100 :
@@ -48,8 +50,15 @@ void bnxt_handle_async_event(struct bnxt *bp,
bp->fw_reset_min_msecs = async_cmp->timestamp_lo ?
async_cmp->timestamp_lo * 100 :
BNXT_MIN_FW_READY_TIMEOUT;
- PMD_DRV_LOG(INFO,
- "Firmware non-fatal reset event received\n");
+ if ((event_data & EVENT_DATA1_REASON_CODE_MASK) ==
+ EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL) {
+ PMD_DRV_LOG(INFO,
+ "Firmware fatal reset event received\n");
+ bp->flags |= BNXT_FLAG_FATAL_ERROR;
+ } else {
+ PMD_DRV_LOG(INFO,
+ "Firmware non-fatal reset event received\n");
+ }
bp->flags |= BNXT_FLAG_FW_RESET;
bnxt_dev_reset_and_resume(bp);
@@ -108,4 +108,9 @@ void bnxt_handle_fwd_req(struct bnxt *bp, struct cmpl_base *cmp);
int bnxt_event_hwrm_resp_handler(struct bnxt *bp, struct cmpl_base *cmp);
int bnxt_dev_reset_and_resume(struct bnxt *bp);
+#define EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL \
+ HWRM_ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL
+#define EVENT_DATA1_REASON_CODE_MASK \
+ HWRM_ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MASK
+
#endif
@@ -3512,6 +3512,9 @@ static void bnxt_dev_recover(void *arg)
int timeout = bp->fw_reset_max_msecs;
int rc = 0;
+ /* Clear Error flag so that device re-init should happen */
+ bp->flags &= ~BNXT_FLAG_FATAL_ERROR;
+
do {
rc = bnxt_hwrm_ver_get(bp);
if (rc == 0)