Merge branch 'bnxt_en-error-recovery-improvements'

Michael Chan says:

====================
bnxt_en: Error recovery improvements.

This series contains a number of improvements in the area of error
recovery.  Most error recovery scenarios are tightly coordinated with
the firmware.  A number of patches add retry logic to establish
connection with the firmware if there are indications that the
firmware is still alive and will likely transition back to the
normal state.  Some patches speed up the recovery process and make
it more reliable.  There are some cleanup patches as well.
====================

Link: https://lore.kernel.org/r/1611558501-11022-1-git-send-email-michael.chan@broadcom.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/broadcom/bnxt/bnxt.h

@@ -656,6 +656,7 @@ struct nqe_cn {
 #define BNXT_HWRM_MAX_REQ_LEN		(bp->hwrm_max_req_len)
 #define BNXT_HWRM_SHORT_REQ_LEN		sizeof(struct hwrm_short_input)
 #define DFLT_HWRM_CMD_TIMEOUT		500
+#define HWRM_CMD_MAX_TIMEOUT		40000
 #define SHORT_HWRM_CMD_TIMEOUT		20
 #define HWRM_CMD_TIMEOUT		(bp->hwrm_cmd_timeout)
 #define HWRM_RESET_TIMEOUT		((HWRM_CMD_TIMEOUT) * 4)
@@ -1345,9 +1346,14 @@ struct bnxt_test_info {
 #define BNXT_CAG_REG_LEGACY_INT_STATUS		0x4014
 #define BNXT_CAG_REG_BASE			0x300000
 
+#define BNXT_GRC_REG_STATUS_P5			0x520
+
 #define BNXT_GRCPF_REG_KONG_COMM		0xA00
 #define BNXT_GRCPF_REG_KONG_COMM_TRIGGER	0xB00
 
+#define BNXT_GRC_REG_CHIP_NUM			0x48
+#define BNXT_GRC_REG_BASE			0x260000
+
 #define BNXT_GRC_BASE_MASK			0xfffff000
 #define BNXT_GRC_OFFSET_MASK			0x00000ffc
 
@@ -1441,6 +1447,8 @@ struct bnxt_ctx_pg_info {
 #define BNXT_MAX_TQM_RINGS		\
 	(BNXT_MAX_TQM_SP_RINGS + BNXT_MAX_TQM_FP_RINGS)
 
+#define BNXT_BACKING_STORE_CFG_LEGACY_LEN	256
+
 struct bnxt_ctx_mem_info {
 	u32	qp_max_entries;
 	u16	qp_min_qp1_entries;
@@ -1532,9 +1540,22 @@ struct bnxt_fw_reporter_ctx {
 #define BNXT_FW_HEALTH_WIN_OFF(reg)	(BNXT_FW_HEALTH_WIN_BASE +	\
 					 ((reg) & BNXT_GRC_OFFSET_MASK))
 
+#define BNXT_FW_STATUS_HEALTH_MSK	0xffff
 #define BNXT_FW_STATUS_HEALTHY		0x8000
 #define BNXT_FW_STATUS_SHUTDOWN		0x100000
 
+#define BNXT_FW_IS_HEALTHY(sts)		(((sts) & BNXT_FW_STATUS_HEALTH_MSK) ==\
+					 BNXT_FW_STATUS_HEALTHY)
+
+#define BNXT_FW_IS_BOOTING(sts)		(((sts) & BNXT_FW_STATUS_HEALTH_MSK) < \
+					 BNXT_FW_STATUS_HEALTHY)
+
+#define BNXT_FW_IS_ERR(sts)		(((sts) & BNXT_FW_STATUS_HEALTH_MSK) > \
+					 BNXT_FW_STATUS_HEALTHY)
+
+#define BNXT_FW_RETRY			5
+#define BNXT_FW_IF_RETRY		10
+
 struct bnxt {
 	void __iomem		*bar0;
 	void __iomem		*bar1;
@@ -1788,6 +1809,7 @@ struct bnxt {
 #define BNXT_STATE_FW_FATAL_COND	6
 #define BNXT_STATE_DRV_REGISTERED	7
 #define BNXT_STATE_PCI_CHANNEL_IO_FROZEN	8
+#define BNXT_STATE_NAPI_DISABLED	9
 
 #define BNXT_NO_FW_ACCESS(bp)					\
 	(test_bit(BNXT_STATE_FW_FATAL_COND, &(bp)->state) ||	\

drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c

@@ -44,21 +44,20 @@ static int bnxt_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
 				     struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = devlink_health_reporter_priv(reporter);
-	u32 val, health_status;
+	u32 val;
 	int rc;
 
 	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 		return 0;
 
 	val = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG);
-	health_status = val & 0xffff;
 
-	if (health_status < BNXT_FW_STATUS_HEALTHY) {
+	if (BNXT_FW_IS_BOOTING(val)) {
 		rc = devlink_fmsg_string_pair_put(fmsg, "Description",
 						  "Not yet completed initialization");
 		if (rc)
 			return rc;
-	} else if (health_status > BNXT_FW_STATUS_HEALTHY) {
+	} else if (BNXT_FW_IS_ERR(val)) {
 		rc = devlink_fmsg_string_pair_put(fmsg, "Description",
 						  "Encountered fatal error and cannot recover");
 		if (rc)