netdev - [PATCH net-next v2 21/22] bnxt_en: Add bnxt_fw_exception() to handle fatal firmware errors.

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1567137305-5853-22-git-send-email-michael.chan@broadcom.com>
Date:   Thu, 29 Aug 2019 23:55:04 -0400
From:   Michael Chan <michael.chan@...adcom.com>
To:     davem@...emloft.net
Cc:     netdev@...r.kernel.org, vasundhara-v.volam@...adcom.com,
        ray.jui@...adcom.com
Subject: [PATCH net-next v2 21/22] bnxt_en: Add bnxt_fw_exception() to handle fatal firmware errors.

This call will handle fatal firmware errors by forcing a reset on the
firmware.  The master function driver will carry out the forced reset.
The sequence will go through the same bnxt_fw_reset_task() workqueue.
This fatal reset differs from the non-fatal reset at the beginning
stages.  From the BNXT_FW_RESET_STATE_ENABLE_DEV state onwards where
the firmware is coming out of reset, it is practically identical to the
non-fatal reset.

The next patch will add the periodic heartbeat check and the devlink
reporter to report the fatal event and to initiate the bnxt_fw_exception()
call.

Signed-off-by: Vasundhara Volam <vasundhara-v.volam@...adcom.com>
Signed-off-by: Michael Chan <michael.chan@...adcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 44 +++++++++++++++++++++++++++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  1 +
 2 files changed, 45 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 51cf679..5c7379e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10003,6 +10003,40 @@ static void bnxt_fw_reset_close(struct bnxt *bp)
 	bp->ctx = NULL;
 }
 
+/* rtnl_lock is acquired before calling this function */
+static void bnxt_force_fw_reset(struct bnxt *bp)
+{
+	struct bnxt_fw_health *fw_health = bp->fw_health;
+	u32 wait_dsecs;
+
+	if (!test_bit(BNXT_STATE_OPEN, &bp->state) ||
+	    test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
+		return;
+
+	set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+	bnxt_fw_reset_close(bp);
+	wait_dsecs = fw_health->master_func_wait_dsecs;
+	if (fw_health->master) {
+		if (fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU)
+			wait_dsecs = 0;
+		bp->fw_reset_state = BNXT_FW_RESET_STATE_RESET_FW;
+	} else {
+		bp->fw_reset_timestamp = jiffies + wait_dsecs * HZ / 10;
+		wait_dsecs = fw_health->normal_func_wait_dsecs;
+		bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV;
+	}
+	bp->fw_reset_max_dsecs = fw_health->post_reset_max_wait_dsecs;
+	bnxt_queue_fw_reset_work(bp, wait_dsecs * HZ / 10);
+}
+
+void bnxt_fw_exception(struct bnxt *bp)
+{
+	set_bit(BNXT_STATE_FW_FATAL_COND, &bp->state);
+	bnxt_rtnl_lock_sp(bp);
+	bnxt_force_fw_reset(bp);
+	bnxt_rtnl_unlock_sp(bp);
+}
+
 void bnxt_fw_reset(struct bnxt *bp)
 {
 	int rc;
@@ -10506,6 +10540,16 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		return;
 	}
 	case BNXT_FW_RESET_STATE_ENABLE_DEV:
+		if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state) &&
+		    bp->fw_health) {
+			u32 val;
+
+			val = bnxt_fw_health_readl(bp,
+						   BNXT_FW_RESET_INPROG_REG);
+			if (val)
+				netdev_warn(bp->dev, "FW reset inprog %x after min wait time.\n",
+					    val);
+		}
 		clear_bit(BNXT_STATE_FW_FATAL_COND, &bp->state);
 		if (pci_enable_device(bp->pdev)) {
 			netdev_err(bp->dev, "Cannot re-enable PCI device\n");
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index f3a6aad..3459b2a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1982,6 +1982,7 @@ int bnxt_open_nic(struct bnxt *, bool, bool);
 int bnxt_half_open_nic(struct bnxt *bp);
 void bnxt_half_close_nic(struct bnxt *bp);
 int bnxt_close_nic(struct bnxt *, bool, bool);
+void bnxt_fw_exception(struct bnxt *bp);
 void bnxt_fw_reset(struct bnxt *bp);
 int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 		     int tx_xdp);
-- 
2.5.1