diff mbox series

[net,2/4] bnxt_en: fix the handling of PCIE-AER

Message ID 1667518407-15761-3-git-send-email-michael.chan@broadcom.com (mailing list archive)
State Accepted
Commit 0cf736a18a1e804037839bd8df9e36f0efdb8745
Delegated to: Netdev Maintainers
Headers show
Series bnxt_en: Bug fixes | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net
netdev/fixes_present success Fixes tag present in non-next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 5 this patch: 5
netdev/cc_maintainers success CCed 5 of 5 maintainers
netdev/build_clang success Errors and warnings before: 2 this patch: 2
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success Fixes tag looks correct
netdev/build_allmodconfig_warn success Errors and warnings before: 4 this patch: 4
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 62 lines checked
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Michael Chan Nov. 3, 2022, 11:33 p.m. UTC 
From: Vikas Gupta <vikas.gupta@broadcom.com>

Fix the sequence required for PCIE-AER. While slot reset occurs, firmware
might not be ready and the driver needs to check for its recovery.  We
also need to remap the health registers for some chips and clear the
resource reservations.  The resources will be allocated again during
bnxt_io_resume().

Fixes: fb1e6e562b37 ("bnxt_en: Fix AER recovery.")
Signed-off-by: Vikas Gupta <vikas.gupta@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     | 29 ++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     |  1 +
 .../net/ethernet/broadcom/bnxt/bnxt_hwrm.c    |  3 +-
 3 files changed, 31 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 3743d9755eb4..f44f9367b7fd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -13922,7 +13922,9 @@  static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 	pci_ers_result_t result = PCI_ERS_RESULT_DISCONNECT;
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct bnxt *bp = netdev_priv(netdev);
-	int err = 0, off;
+	int retry = 0;
+	int err = 0;
+	int off;
 
 	netdev_info(bp->dev, "PCI Slot Reset\n");
 
@@ -13950,11 +13952,36 @@  static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 		pci_restore_state(pdev);
 		pci_save_state(pdev);
 
+		bnxt_inv_fw_health_reg(bp);
+		bnxt_try_map_fw_health_reg(bp);
+
+		/* In some PCIe AER scenarios, firmware may take up to
+		 * 10 seconds to become ready in the worst case.
+		 */
+		do {
+			err = bnxt_try_recover_fw(bp);
+			if (!err)
+				break;
+			retry++;
+		} while (retry < BNXT_FW_SLOT_RESET_RETRY);
+
+		if (err) {
+			dev_err(&pdev->dev, "Firmware not ready\n");
+			goto reset_exit;
+		}
+
 		err = bnxt_hwrm_func_reset(bp);
 		if (!err)
 			result = PCI_ERS_RESULT_RECOVERED;
+
+		bnxt_ulp_irq_stop(bp);
+		bnxt_clear_int_mode(bp);
+		err = bnxt_init_int_mode(bp);
+		bnxt_ulp_irq_restart(bp, err);
 	}
 
+reset_exit:
+	bnxt_clear_reservations(bp, true);
 	rtnl_unlock();
 
 	return result;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index b1b17f911300..d5fa43cfe524 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1621,6 +1621,7 @@  struct bnxt_fw_health {
 
 #define BNXT_FW_RETRY			5
 #define BNXT_FW_IF_RETRY		10
+#define BNXT_FW_SLOT_RESET_RETRY	4
 
 enum board_idx {
 	BCM57301,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c
index b01d42928a53..132442f16fe6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c
@@ -476,7 +476,8 @@  static int __hwrm_send(struct bnxt *bp, struct bnxt_hwrm_ctx *ctx)
 		memset(ctx->resp, 0, PAGE_SIZE);
 
 	req_type = le16_to_cpu(ctx->req->req_type);
-	if (BNXT_NO_FW_ACCESS(bp) && req_type != HWRM_FUNC_RESET) {
+	if (BNXT_NO_FW_ACCESS(bp) &&
+	    (req_type != HWRM_FUNC_RESET && req_type != HWRM_VER_GET)) {
 		netdev_dbg(bp->dev, "hwrm req_type 0x%x skipped, FW channel down\n",
 			   req_type);
 		goto exit;