[dpdk-dev] [PATCH v3 10/15] net/bnxt: add support for FW reset

[Ajit Khaparde]

From: Kalesh AP <kalesh-anakkur.purayil at broadcom.com>

Added code to perform FW_RESET. When the driver detects error in FW,
it has to initiate the recovery by resetting the cores. FW advertise
the method to do a core reset, reset register offsets and values
to perform reset in response of HWRM_ERROR_RECOVERY_QCFG command.

There are 2 ways to recover from the error.
1. Master function issues core resets to recover from error.
2. Master function detects chimp dead condition and notify the Kong
   processor about the chimp dead case through FW_RESET HWRM command.
   Kong Processor send an RESET_NOTIFY async event with
   REASON_CODE_FW_EXCEPTION_FATAL to all the PF’s/VF’s that
   chimp is dead and it is going to reset the chimp.

Signed-off-by: Kalesh AP <kalesh-anakkur.purayil at broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur at broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde at broadcom.com>
---
 drivers/net/bnxt/bnxt.h        |   1 +
 drivers/net/bnxt/bnxt_ethdev.c | 104 ++++++++++++++++++++++++++++++++-
 drivers/net/bnxt/bnxt_hwrm.c   |  26 +++++++++
 drivers/net/bnxt/bnxt_hwrm.h   |   1 +
 4 files changed, 131 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bnxt/bnxt.h b/drivers/net/bnxt/bnxt.h
index 50b9b38565..637ee9a0f7 100644
--- a/drivers/net/bnxt/bnxt.h
+++ b/drivers/net/bnxt/bnxt.h
@@ -388,6 +388,7 @@ struct bnxt_error_recovery_info {
 #define BNXT_FW_STATUS_REG_OFF(reg)	((reg) & ~BNXT_FW_STATUS_REG_TYPE_MASK)
 
 #define BNXT_GRCP_WINDOW_2_BASE		0x2000
+#define BNXT_GRCP_WINDOW_3_BASE		0x3000
 
 #define BNXT_HWRM_SHORT_REQ_LEN		sizeof(struct hwrm_short_input)
 struct bnxt {
diff --git a/drivers/net/bnxt/bnxt_ethdev.c b/drivers/net/bnxt/bnxt_ethdev.c
index d28f1bd8f9..40973c37b9 100644
--- a/drivers/net/bnxt/bnxt_ethdev.c
+++ b/drivers/net/bnxt/bnxt_ethdev.c
@@ -3566,6 +3566,19 @@ static const struct eth_dev_ops bnxt_dev_ops = {
 	.timesync_read_tx_timestamp = bnxt_timesync_read_tx_timestamp,
 };
 
+static uint32_t bnxt_map_reset_regs(struct bnxt *bp, uint32_t reg)
+{
+	uint32_t offset;
+
+	/* Only pre-map the reset GRC registers using window 3 */
+	rte_write32(reg & 0xfffff000, (uint8_t *)bp->bar0 +
+		    BNXT_GRCPF_REG_WINDOW_BASE_OUT + 8);
+
+	offset = BNXT_GRCP_WINDOW_3_BASE + (reg & 0xffc);
+
+	return offset;
+}
+
 int bnxt_map_fw_health_status_regs(struct bnxt *bp)
 {
 	struct bnxt_error_recovery_info *info = bp->recovery_info;
@@ -3600,6 +3613,34 @@ int bnxt_map_fw_health_status_regs(struct bnxt *bp)
 	return 0;
 }
 
+static void bnxt_write_fw_reset_reg(struct bnxt *bp, uint32_t index)
+{
+	struct bnxt_error_recovery_info *info = bp->recovery_info;
+	uint32_t delay = info->delay_after_reset[index];
+	uint32_t val = info->reset_reg_val[index];
+	uint32_t reg = info->reset_reg[index];
+	uint32_t type, offset;
+
+	type = BNXT_FW_STATUS_REG_TYPE(reg);
+	offset = BNXT_FW_STATUS_REG_OFF(reg);
+
+	switch (type) {
+	case BNXT_FW_STATUS_REG_TYPE_CFG:
+		rte_pci_write_config(bp->pdev, &val, sizeof(val), offset);
+		break;
+	case BNXT_FW_STATUS_REG_TYPE_GRC:
+		offset = bnxt_map_reset_regs(bp, offset);
+		rte_write32(val, (uint8_t *)bp->bar0 + offset);
+		break;
+	case BNXT_FW_STATUS_REG_TYPE_BAR0:
+		rte_write32(val, (uint8_t *)bp->bar0 + offset);
+		break;
+	}
+	/* wait on a specific interval of time until core reset is complete */
+	if (delay)
+		rte_delay_ms(delay);
+}
+
 static void bnxt_dev_cleanup(struct bnxt *bp)
 {
 	bnxt_set_hwrm_link_config(bp, false);
@@ -3711,6 +3752,59 @@ uint32_t bnxt_read_fw_status_reg(struct bnxt *bp, uint32_t index)
 	return val;
 }
 
+static int bnxt_fw_reset_all(struct bnxt *bp)
+{
+	struct bnxt_error_recovery_info *info = bp->recovery_info;
+	uint32_t i;
+	int rc = 0;
+
+	if (info->flags & BNXT_FLAG_ERROR_RECOVERY_HOST) {
+		/* Reset through master function driver */
+		for (i = 0; i < info->reg_array_cnt; i++)
+			bnxt_write_fw_reset_reg(bp, i);
+		/* Wait for time specified by FW after triggering reset */
+		rte_delay_ms(info->master_func_wait_period_after_reset);
+	} else if (info->flags & BNXT_FLAG_ERROR_RECOVERY_CO_CPU) {
+		/* Reset with the help of Kong processor */
+		rc = bnxt_hwrm_fw_reset(bp);
+		if (rc)
+			PMD_DRV_LOG(ERR, "Failed to reset FW\n");
+	}
+
+	return rc;
+}
+
+static void bnxt_fw_reset_cb(void *arg)
+{
+	struct bnxt *bp = arg;
+	struct bnxt_error_recovery_info *info = bp->recovery_info;
+	int rc = 0;
+
+	/* Only Master function can do FW reset */
+	if (bnxt_is_master_func(bp) &&
+	    bnxt_is_recovery_enabled(bp)) {
+		rc = bnxt_fw_reset_all(bp);
+		if (rc) {
+			PMD_DRV_LOG(ERR, "Adapter recovery failed\n");
+			return;
+		}
+	}
+
+	/* if recovery method is ERROR_RECOVERY_CO_CPU, KONG will send
+	 * EXCEPTION_FATAL_ASYNC event to all the functions
+	 * (including MASTER FUNC). After receiving this Async, all the active
+	 * drivers should treat this case as FW initiated recovery
+	 */
+	if (info->flags & BNXT_FLAG_ERROR_RECOVERY_HOST) {
+		bp->fw_reset_min_msecs = BNXT_MIN_FW_READY_TIMEOUT;
+		bp->fw_reset_max_msecs = BNXT_MAX_FW_RESET_TIMEOUT;
+
+		/* To recover from error */
+		rte_eal_alarm_set(US_PER_MS, bnxt_dev_reset_and_resume,
+				  (void *)bp);
+	}
+}
+
 /* Driver should poll FW heartbeat, reset_counter with the frequency
  * advertised by FW in HWRM_ERROR_RECOVERY_QCFG.
  * When the driver detects heartbeat stop or change in reset_counter,
@@ -3723,7 +3817,7 @@ static void bnxt_check_fw_health(void *arg)
 {
 	struct bnxt *bp = arg;
 	struct bnxt_error_recovery_info *info = bp->recovery_info;
-	uint32_t val = 0;
+	uint32_t val = 0, wait_msec;
 
 	if (!info || !bnxt_is_recovery_enabled(bp) ||
 	    is_bnxt_in_error(bp))
@@ -3751,6 +3845,14 @@ static void bnxt_check_fw_health(void *arg)
 	bp->flags |= BNXT_FLAG_FW_RESET;
 
 	PMD_DRV_LOG(ERR, "Detected FW dead condition\n");
+
+	if (bnxt_is_master_func(bp))
+		wait_msec = info->master_func_wait_period;
+	else
+		wait_msec = info->normal_func_wait_period;
+
+	rte_eal_alarm_set(US_PER_MS * wait_msec,
+			  bnxt_fw_reset_cb, (void *)bp);
 }
 
 void bnxt_schedule_fw_health_check(struct bnxt *bp)
diff --git a/drivers/net/bnxt/bnxt_hwrm.c b/drivers/net/bnxt/bnxt_hwrm.c
index c7d6f9fdc4..e96e6cef91 100644
--- a/drivers/net/bnxt/bnxt_hwrm.c
+++ b/drivers/net/bnxt/bnxt_hwrm.c
@@ -4803,3 +4803,29 @@ int bnxt_hwrm_error_recovery_qcfg(struct bnxt *bp)
 	}
 	return rc;
 }
+
+int bnxt_hwrm_fw_reset(struct bnxt *bp)
+{
+	struct hwrm_fw_reset_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_fw_reset_input req = {0};
+	int rc;
+
+	if (!BNXT_PF(bp))
+		return -EOPNOTSUPP;
+
+	HWRM_PREP(req, FW_RESET, BNXT_USE_KONG(bp));
+
+	req.embedded_proc_type =
+		HWRM_FW_RESET_INPUT_EMBEDDED_PROC_TYPE_CHIP;
+	req.selfrst_status =
+		HWRM_FW_RESET_INPUT_SELFRST_STATUS_SELFRSTASAP;
+	req.flags = HWRM_FW_RESET_INPUT_FLAGS_RESET_GRACEFUL;
+
+	rc = bnxt_hwrm_send_message(bp, &req, sizeof(req),
+				    BNXT_USE_KONG(bp));
+
+	HWRM_CHECK_RESULT();
+	HWRM_UNLOCK();
+
+	return rc;
+}
diff --git a/drivers/net/bnxt/bnxt_hwrm.h b/drivers/net/bnxt/bnxt_hwrm.h
index 44e3355075..db25ad5919 100644
--- a/drivers/net/bnxt/bnxt_hwrm.h
+++ b/drivers/net/bnxt/bnxt_hwrm.h
@@ -205,4 +205,5 @@ int bnxt_hwrm_tunnel_redirect_info(struct bnxt *bp, uint8_t tun_type,
 int bnxt_hwrm_set_mac(struct bnxt *bp);
 int bnxt_hwrm_if_change(struct bnxt *bp, bool state);
 int bnxt_hwrm_error_recovery_qcfg(struct bnxt *bp);
+int bnxt_hwrm_fw_reset(struct bnxt *bp);
 #endif
-- 
2.20.1 (Apple Git-117)