kmod-redhat-bnxt_en/SOURCES/0069-netdrv-bnxt_en-Enable-health-monitoring.patch

From 1d427d9e7f961722a309c6a82f62a9178e5a2c3f Mon Sep 17 00:00:00 2001
From: Jonathan Toppins <jtoppins@redhat.com>
Date: Wed, 2 Oct 2019 18:23:24 -0400
Subject: [PATCH 69/96] [netdrv] bnxt_en: Enable health monitoring

Message-id: <42efde25f8365e758d5336dd899277a3bbab23aa.1570027456.git.jtoppins@redhat.com>
Patchwork-id: 276498
O-Subject: [RHEL-8.2 PATCH 62/78] bnxt_en: Enable health monitoring.
Bugzilla: 1724766
RH-Acked-by: John Linville <linville@redhat.com>
RH-Acked-by: Jarod Wilson <jarod@redhat.com>

Handle the async event from the firmware that enables firmware health
monitoring.  Store initial health metrics.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 7e914027f757b656cd681ba4fe75f3984531ee50)
Bugzilla: 1724766
Build Info: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=23809532
Tested: build, boot, basic ping
Signed-off-by: Jonathan Toppins <jtoppins@redhat.com>
Signed-off-by: Bruno Meneguele <bmeneg@redhat.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 66 ++++++++++++++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  9 +++++
 2 files changed, 73 insertions(+), 2 deletions(-)

Index: src/drivers/net/ethernet/broadcom/bnxt/bnxt.c
===================================================================
--- src.orig/drivers/net/ethernet/broadcom/bnxt/bnxt.c	2020-02-06 16:23:19.432478987 +0100
+++ src/drivers/net/ethernet/broadcom/bnxt/bnxt.c	2020-02-06 16:23:19.590477537 +0100
@@ -254,6 +254,7 @@
 	ASYNC_EVENT_CMPL_EVENT_ID_PORT_CONN_NOT_ALLOWED,
 	ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE,
 	ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE,
+	ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY,
 };
 
 static struct workqueue_struct *bnxt_pf_wq;
@@ -1898,6 +1899,33 @@
 	return bnxt_rx_pkt(bp, cpr, raw_cons, event);
 }
 
+u32 bnxt_fw_health_readl(struct bnxt *bp, int reg_idx)
+{
+	struct bnxt_fw_health *fw_health = bp->fw_health;
+	u32 reg = fw_health->regs[reg_idx];
+	u32 reg_type, reg_off, val = 0;
+
+	reg_type = BNXT_FW_HEALTH_REG_TYPE(reg);
+	reg_off = BNXT_FW_HEALTH_REG_OFF(reg);
+	switch (reg_type) {
+	case BNXT_FW_HEALTH_REG_TYPE_CFG:
+		pci_read_config_dword(bp->pdev, reg_off, &val);
+		break;
+	case BNXT_FW_HEALTH_REG_TYPE_GRC:
+		reg_off = fw_health->mapped_regs[reg_idx];
+		/* fall through */
+	case BNXT_FW_HEALTH_REG_TYPE_BAR0:
+		val = readl(bp->bar0 + reg_off);
+		break;
+	case BNXT_FW_HEALTH_REG_TYPE_BAR1:
+		val = readl(bp->bar1 + reg_off);
+		break;
+	}
+	if (reg_idx == BNXT_FW_RESET_INPROG_REG)
+		val &= fw_health->fw_reset_inprog_reg_mask;
+	return val;
+}
+
 #define BNXT_GET_EVENT_PORT(data)	\
 	((data) &			\
 	 ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_PORT_ID_MASK)
@@ -1953,6 +1981,35 @@
 			goto async_event_process_exit;
 		set_bit(BNXT_RESET_TASK_SILENT_SP_EVENT, &bp->sp_event);
 		break;
+	case ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY: {
+		struct bnxt_fw_health *fw_health = bp->fw_health;
+		u32 data1 = le32_to_cpu(cmpl->event_data1);
+
+		if (!fw_health)
+			goto async_event_process_exit;
+
+		fw_health->enabled = EVENT_DATA1_RECOVERY_ENABLED(data1);
+		fw_health->master = EVENT_DATA1_RECOVERY_MASTER_FUNC(data1);
+		if (!fw_health->enabled)
+			break;
+
+		if (netif_msg_drv(bp))
+			netdev_info(bp->dev, "Error recovery info: error recovery[%d], master[%d], reset count[0x%x], health status: 0x%x\n",
+				    fw_health->enabled, fw_health->master,
+				    bnxt_fw_health_readl(bp,
+							 BNXT_FW_RESET_CNT_REG),
+				    bnxt_fw_health_readl(bp,
+							 BNXT_FW_HEALTH_REG));
+		fw_health->tmr_multiplier =
+			DIV_ROUND_UP(fw_health->polling_dsecs * HZ,
+				     bp->current_interval * 10);
+		fw_health->tmr_counter = fw_health->tmr_multiplier;
+		fw_health->last_fw_heartbeat =
+			bnxt_fw_health_readl(bp, BNXT_FW_HEARTBEAT_REG);
+		fw_health->last_fw_reset_cnt =
+			bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG);
+		goto async_event_process_exit;
+	}
 	default:
 		goto async_event_process_exit;
 	}
@@ -4315,9 +4372,14 @@
 		cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD);
 
 	memset(async_events_bmap, 0, sizeof(async_events_bmap));
-	for (i = 0; i < ARRAY_SIZE(bnxt_async_events_arr); i++)
-		__set_bit(bnxt_async_events_arr[i], async_events_bmap);
+	for (i = 0; i < ARRAY_SIZE(bnxt_async_events_arr); i++) {
+		u16 event_id = bnxt_async_events_arr[i];
 
+		if (event_id == ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY &&
+		    !(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY))
+			continue;
+		__set_bit(bnxt_async_events_arr[i], async_events_bmap);
+	}
 	if (bmap && bmap_size) {
 		for (i = 0; i < bmap_size; i++) {
 			if (test_bit(i, bmap))
Index: src/drivers/net/ethernet/broadcom/bnxt/bnxt.h
===================================================================
--- src.orig/drivers/net/ethernet/broadcom/bnxt/bnxt.h	2020-02-06 16:23:19.432478987 +0100
+++ src/drivers/net/ethernet/broadcom/bnxt/bnxt.h	2020-02-06 16:23:19.591477528 +0100
@@ -472,6 +472,14 @@
 	((le32_to_cpu((rx_tpa_end_ext)->rx_tpa_end_cmp_dup_acks) &	\
 	 RX_TPA_END_CMP_AGG_BUFS_P5) >> RX_TPA_END_CMP_AGG_BUFS_SHIFT_P5)
 
+#define EVENT_DATA1_RECOVERY_MASTER_FUNC(data1)				\
+	!!((data1) &							\
+	   ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASTER_FUNC)
+
+#define EVENT_DATA1_RECOVERY_ENABLED(data1)				\
+	!!((data1) &							\
+	   ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_RECOVERY_ENABLED)
+
 struct nqe_cn {
 	__le16	type;
 	#define NQ_CN_TYPE_MASK           0x3fUL
@@ -1914,6 +1922,7 @@
 int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		       u16 prod, gfp_t gfp);
 void bnxt_reuse_rx_data(struct bnxt_rx_ring_info *rxr, u16 cons, void *data);
+u32 bnxt_fw_health_readl(struct bnxt *bp, int reg_idx);
 void bnxt_set_tpa_flags(struct bnxt *bp);
 void bnxt_set_ring_params(struct bnxt *);
 int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);