bnxt_en: Avoid sending firmware messages when AER error is detected.

When the driver goes through PCIe AER reset in error state, all
firmware messages will timeout because the PCIe bus is no longer
accessible.  This can lead to AER reset taking many minutes to
complete as each firmware command takes time to timeout.

Define a new macro BNXT_NO_FW_ACCESS() to skip these firmware messages
when either firmware is in fatal error state or when
pci_channel_offline() is true.  It now takes a more reasonable 20 to
30 seconds to complete AER recovery.

Fixes: b4fff20 ("bnxt_en: Do not send firmware messages if firmware is in error state.")
Signed-off-by: Vasundhara Volam <[email protected]>
Signed-off-by: Michael Chan <[email protected]>
Signed-off-by: Jakub Kicinski <[email protected]>

Author: Vasundhara Volam

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

@@ -4305,7 +4305,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
 	u16 dst = BNXT_HWRM_CHNL_CHIMP;
 
-	if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+	if (BNXT_NO_FW_ACCESS(bp))
 		return -EBUSY;
 
 	if (msg_len > BNXT_HWRM_MAX_REQ_LEN) {
@@ -5723,7 +5723,7 @@ static int hwrm_ring_free_send_msg(struct bnxt *bp,
 	struct hwrm_ring_free_output *resp = bp->hwrm_cmd_resp_addr;
 	u16 error_code;
 
-	if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+	if (BNXT_NO_FW_ACCESS(bp))
 		return 0;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, cmpl_ring_id, -1);
@@ -7817,7 +7817,7 @@ static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa)
 
 	if (set_tpa)
 		tpa_flags = bp->flags & BNXT_FLAG_TPA;
-	else if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+	else if (BNXT_NO_FW_ACCESS(bp))
 		return 0;
 	for (i = 0; i < bp->nr_vnics; i++) {
 		rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags);

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

@@ -1737,6 +1737,10 @@ struct bnxt {
 #define BNXT_STATE_FW_FATAL_COND	6
 #define BNXT_STATE_DRV_REGISTERED	7
 
+#define BNXT_NO_FW_ACCESS(bp)					\
+	(test_bit(BNXT_STATE_FW_FATAL_COND, &(bp)->state) ||	\
+	 pci_channel_offline((bp)->pdev))
+
 	struct bnxt_irq	*irq_tbl;
 	int			total_irqs;
 	u8			mac_addr[ETH_ALEN];