Merge branch 'net-qed-qede-critical-hw-error-handling'

Igor Russkikh says:

====================
net: qed/qede: critical hw error handling

FastLinQ devices as a complex systems may observe various hardware
level error conditions, both severe and recoverable.

Driver is able to detect and report this, but so far it only did
trace/dmesg based reporting.

Here we implement an extended hw error detection, service task
handler captures a dump for the later analysis.

I also resubmit a patch from Denis Bolotin on tx timeout handler,
addressing David's comment regarding recovery procedure as an extra
reaction on this event.

v2:

Removing the patch with ethtool dump and udev magic. Its quite isolated,
I'm working on devlink based logic for this separately.

v1:

https://patchwork.ozlabs.org/project/netdev/cover/cover.1588758463.git.irusskikh@marvell.com/
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/qlogic/qed/qed.h

@@ -740,12 +740,6 @@ struct qed_dbg_feature {
 	u32 dumped_dwords;
 };
 
-struct qed_dbg_params {
-	struct qed_dbg_feature features[DBG_FEATURE_NUM];
-	u8 engine_for_debug;
-	bool print_data;
-};
-
 struct qed_dev {
 	u32	dp_module;
 	u8	dp_level;
@@ -844,6 +838,9 @@ struct qed_dev {
 	/* Recovery */
 	bool recov_in_prog;
 
+	/* Indicates whether should prevent attentions from being reasserted */
+	bool attn_clr_en;
+
 	/* LLH info */
 	u8 ppfid_bitmap;
 	struct qed_llh_info *p_llh_info;
@@ -872,17 +869,18 @@ struct qed_dev {
 	} protocol_ops;
 	void				*ops_cookie;
 
-	struct qed_dbg_params		dbg_params;
-
 #ifdef CONFIG_QED_LL2
 	struct qed_cb_ll2_info		*ll2;
 	u8				ll2_mac_address[ETH_ALEN];
 #endif
 	struct qed_dbg_feature dbg_features[DBG_FEATURE_NUM];
+	u8 engine_for_debug;
 	bool disable_ilt_dump;
 	DECLARE_HASHTABLE(connections, 10);
 	const struct firmware		*firmware;
 
+	bool print_dbg_data;
+
 	u32 rdma_max_sge;
 	u32 rdma_max_inline;
 	u32 rdma_max_srq_sge;
@@ -1020,6 +1018,8 @@ u32 qed_unzip_data(struct qed_hwfn *p_hwfn,
 		   u32 input_len, u8 *input_buf,
 		   u32 max_size, u8 *unzip_buf);
 void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn);
+void qed_hw_error_occurred(struct qed_hwfn *p_hwfn,
+			   enum qed_hw_err_type err_type);
 void qed_get_protocol_stats(struct qed_dev *cdev,
 			    enum qed_mcp_protocol_type type,
 			    union qed_mcp_protocol_stats *stats);

drivers/net/ethernet/qlogic/qed/qed_debug.c

@@ -7453,7 +7453,7 @@ static enum dbg_status format_feature(struct qed_hwfn *p_hwfn,
 				      enum qed_dbg_features feature_idx)
 {
 	struct qed_dbg_feature *feature =
-	    &p_hwfn->cdev->dbg_params.features[feature_idx];
+	    &p_hwfn->cdev->dbg_features[feature_idx];
 	u32 text_size_bytes, null_char_pos, i;
 	enum dbg_status rc;
 	char *text_buf;
@@ -7502,7 +7502,7 @@ static enum dbg_status format_feature(struct qed_hwfn *p_hwfn,
 		text_buf[i] = '\n';
 
 	/* Dump printable feature to log */
-	if (p_hwfn->cdev->dbg_params.print_data)
+	if (p_hwfn->cdev->print_dbg_data)
 		qed_dbg_print_feature(text_buf, text_size_bytes);
 
 	/* Free the old dump_buf and point the dump_buf to the newly allocagted
@@ -7523,7 +7523,7 @@ static enum dbg_status qed_dbg_dump(struct qed_hwfn *p_hwfn,
 				    enum qed_dbg_features feature_idx)
 {
 	struct qed_dbg_feature *feature =
-	    &p_hwfn->cdev->dbg_params.features[feature_idx];
+	    &p_hwfn->cdev->dbg_features[feature_idx];
 	u32 buf_size_dwords;
 	enum dbg_status rc;
 
@@ -7648,7 +7648,7 @@ static int qed_dbg_nvm_image(struct qed_dev *cdev, void *buffer,
 			     enum qed_nvm_images image_id)
 {
 	struct qed_hwfn *p_hwfn =
-		&cdev->hwfns[cdev->dbg_params.engine_for_debug];
+		&cdev->hwfns[cdev->engine_for_debug];
 	u32 len_rounded, i;
 	__be32 val;
 	int rc;
@@ -7780,7 +7780,7 @@ int qed_dbg_all_data(struct qed_dev *cdev, void *buffer)
 {
 	u8 cur_engine, omit_engine = 0, org_engine;
 	struct qed_hwfn *p_hwfn =
-		&cdev->hwfns[cdev->dbg_params.engine_for_debug];
+		&cdev->hwfns[cdev->engine_for_debug];
 	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
 	int grc_params[MAX_DBG_GRC_PARAMS], i;
 	u32 offset = 0, feature_size;
@@ -8000,7 +8000,7 @@ int qed_dbg_all_data(struct qed_dev *cdev, void *buffer)
 int qed_dbg_all_data_size(struct qed_dev *cdev)
 {
 	struct qed_hwfn *p_hwfn =
-		&cdev->hwfns[cdev->dbg_params.engine_for_debug];
+		&cdev->hwfns[cdev->engine_for_debug];
 	u32 regs_len = 0, image_len = 0, ilt_len = 0, total_ilt_len = 0;
 	u8 cur_engine, org_engine;
 
@@ -8059,9 +8059,9 @@ int qed_dbg_feature(struct qed_dev *cdev, void *buffer,
 		    enum qed_dbg_features feature, u32 *num_dumped_bytes)
 {
 	struct qed_hwfn *p_hwfn =
-		&cdev->hwfns[cdev->dbg_params.engine_for_debug];
+		&cdev->hwfns[cdev->engine_for_debug];
 	struct qed_dbg_feature *qed_feature =
-		&cdev->dbg_params.features[feature];
+		&cdev->dbg_features[feature];
 	enum dbg_status dbg_rc;
 	struct qed_ptt *p_ptt;
 	int rc = 0;
@@ -8084,7 +8084,7 @@ int qed_dbg_feature(struct qed_dev *cdev, void *buffer,
 	DP_VERBOSE(cdev, QED_MSG_DEBUG,
 		   "copying debugfs feature to external buffer\n");
 	memcpy(buffer, qed_feature->dump_buf, qed_feature->buf_size);
-	*num_dumped_bytes = cdev->dbg_params.features[feature].dumped_dwords *
+	*num_dumped_bytes = cdev->dbg_features[feature].dumped_dwords *
 			    4;
 
 out:
@@ -8095,7 +8095,7 @@ int qed_dbg_feature(struct qed_dev *cdev, void *buffer,
 int qed_dbg_feature_size(struct qed_dev *cdev, enum qed_dbg_features feature)
 {
 	struct qed_hwfn *p_hwfn =
-		&cdev->hwfns[cdev->dbg_params.engine_for_debug];
+		&cdev->hwfns[cdev->engine_for_debug];
 	struct qed_dbg_feature *qed_feature = &cdev->dbg_features[feature];
 	struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn);
 	u32 buf_size_dwords;
@@ -8120,14 +8120,14 @@ int qed_dbg_feature_size(struct qed_dev *cdev, enum qed_dbg_features feature)
 
 u8 qed_get_debug_engine(struct qed_dev *cdev)
 {
-	return cdev->dbg_params.engine_for_debug;
+	return cdev->engine_for_debug;
 }
 
 void qed_set_debug_engine(struct qed_dev *cdev, int engine_number)
 {
 	DP_VERBOSE(cdev, QED_MSG_DEBUG, "set debug engine to %d\n",
 		   engine_number);
-	cdev->dbg_params.engine_for_debug = engine_number;
+	cdev->engine_for_debug = engine_number;
 }
 
 void qed_dbg_pf_init(struct qed_dev *cdev)
@@ -8146,7 +8146,7 @@ void qed_dbg_pf_init(struct qed_dev *cdev)
 	}
 
 	/* Set the hwfn to be 0 as default */
-	cdev->dbg_params.engine_for_debug = 0;
+	cdev->engine_for_debug = 0;
 }
 
 void qed_dbg_pf_exit(struct qed_dev *cdev)

drivers/net/ethernet/qlogic/qed/qed_dev.c

@@ -3085,7 +3085,9 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 			rc = qed_final_cleanup(p_hwfn, p_hwfn->p_main_ptt,
 					       p_hwfn->rel_pf_id, false);
 			if (rc) {
-				DP_NOTICE(p_hwfn, "Final cleanup failed\n");
+				qed_hw_err_notify(p_hwfn, p_hwfn->p_main_ptt,
+						  QED_HW_ERR_RAMROD_FAIL,
+						  "Final cleanup failed\n");
 				goto load_err;
 			}
 		}

drivers/net/ethernet/qlogic/qed/qed_hsi.h

@@ -12400,6 +12400,13 @@ struct load_rsp_stc {
 #define LOAD_RSP_FLAGS0_DRV_EXISTS      (0x1 << 0)
 };
 
+struct mdump_retain_data_stc {
+	u32 valid;
+	u32 epoch;
+	u32 pf;
+	u32 status;
+};
+
 union drv_union_data {
 	u32 ver_str[MCP_DRV_VER_STR_SIZE_DWORD];
 	struct mcp_mac wol_mac;
@@ -12488,10 +12495,14 @@ struct public_drv_mb {
 #define DRV_MSG_CODE_BIST_TEST			0x001e0000
 #define DRV_MSG_CODE_SET_LED_MODE		0x00200000
 #define DRV_MSG_CODE_RESOURCE_CMD		0x00230000
+/* Send crash dump commands with param[3:0] - opcode */
+#define DRV_MSG_CODE_MDUMP_CMD			0x00250000
 #define DRV_MSG_CODE_GET_TLV_DONE		0x002f0000
 #define DRV_MSG_CODE_GET_ENGINE_CONFIG		0x00370000
 #define DRV_MSG_CODE_GET_PPFID_BITMAP		0x43000000
 
+#define DRV_MSG_CODE_DEBUG_DATA_SEND		0xc0040000
+
 #define RESOURCE_CMD_REQ_RESC_MASK		0x0000001F
 #define RESOURCE_CMD_REQ_RESC_SHIFT		0
 #define RESOURCE_CMD_REQ_OPCODE_MASK		0x000000E0
@@ -12517,6 +12528,21 @@ struct public_drv_mb {
 
 #define RESOURCE_DUMP				0
 
+/* DRV_MSG_CODE_MDUMP_CMD parameters */
+#define MDUMP_DRV_PARAM_OPCODE_MASK             0x0000000f
+#define DRV_MSG_CODE_MDUMP_ACK                  0x01
+#define DRV_MSG_CODE_MDUMP_SET_VALUES           0x02
+#define DRV_MSG_CODE_MDUMP_TRIGGER              0x03
+#define DRV_MSG_CODE_MDUMP_GET_CONFIG           0x04
+#define DRV_MSG_CODE_MDUMP_SET_ENABLE           0x05
+#define DRV_MSG_CODE_MDUMP_CLEAR_LOGS           0x06
+#define DRV_MSG_CODE_MDUMP_GET_RETAIN           0x07
+#define DRV_MSG_CODE_MDUMP_CLR_RETAIN           0x08
+
+#define DRV_MSG_CODE_HW_DUMP_TRIGGER            0x0a
+#define DRV_MSG_CODE_MDUMP_GEN_MDUMP2           0x0b
+#define DRV_MSG_CODE_MDUMP_FREE_MDUMP2          0x0c
+
 #define DRV_MSG_CODE_GET_PF_RDMA_PROTOCOL	0x002b0000
 #define DRV_MSG_CODE_OS_WOL			0x002e0000
 
@@ -12626,6 +12652,17 @@ struct public_drv_mb {
 #define DRV_MB_PARAM_FEATURE_SUPPORT_PORT_EEE		0x00000002
 #define DRV_MB_PARAM_FEATURE_SUPPORT_FUNC_VLINK		0x00010000
 
+/* DRV_MSG_CODE_DEBUG_DATA_SEND parameters */
+#define DRV_MSG_CODE_DEBUG_DATA_SEND_SIZE_OFFSET	0
+#define DRV_MSG_CODE_DEBUG_DATA_SEND_SIZE_MASK		0xFF
+
+/* Driver attributes params */
+#define DRV_MB_PARAM_ATTRIBUTE_KEY_OFFSET		0
+#define DRV_MB_PARAM_ATTRIBUTE_KEY_MASK			0x00FFFFFF
+#define DRV_MB_PARAM_ATTRIBUTE_CMD_OFFSET		24
+#define DRV_MB_PARAM_ATTRIBUTE_CMD_MASK			0xFF000000
+
+#define DRV_MB_PARAM_NVM_CFG_OPTION_ID_OFFSET		0
 #define DRV_MB_PARAM_NVM_CFG_OPTION_ID_SHIFT		0
 #define DRV_MB_PARAM_NVM_CFG_OPTION_ID_MASK		0x0000FFFF
 #define DRV_MB_PARAM_NVM_CFG_OPTION_ALL_SHIFT		16
@@ -12678,6 +12715,14 @@ struct public_drv_mb {
 #define FW_MSG_CODE_DRV_CFG_PF_VFS_MSIX_DONE	0x00870000
 #define FW_MSG_SEQ_NUMBER_MASK			0x0000ffff
 
+#define FW_MSG_CODE_DEBUG_DATA_SEND_INV_ARG	0xb0070000
+#define FW_MSG_CODE_DEBUG_DATA_SEND_BUF_FULL	0xb0080000
+#define FW_MSG_CODE_DEBUG_DATA_SEND_NO_BUF	0xb0090000
+#define FW_MSG_CODE_DEBUG_NOT_ENABLED		0xb00a0000
+#define FW_MSG_CODE_DEBUG_DATA_SEND_OK		0xb00b0000
+
+#define FW_MSG_CODE_MDUMP_INVALID_CMD		0x00030000
+
 	u32 fw_mb_param;
 #define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_MASK	0xFFFF0000
 #define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT	16
@@ -12742,9 +12787,9 @@ enum MFW_DRV_MSG_TYPE {
 	MFW_DRV_MSG_GET_FCOE_STATS,
 	MFW_DRV_MSG_GET_ISCSI_STATS,
 	MFW_DRV_MSG_GET_RDMA_STATS,
-	MFW_DRV_MSG_BW_UPDATE10,
+	MFW_DRV_MSG_FAILURE_DETECTED,
 	MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE,
-	MFW_DRV_MSG_BW_UPDATE11,
+	MFW_DRV_MSG_CRITICAL_ERROR_OCCURRED,
 	MFW_DRV_MSG_RESERVED,
 	MFW_DRV_MSG_GET_TLV_REQ,
 	MFW_DRV_MSG_OEM_CFG_UPDATE,

drivers/net/ethernet/qlogic/qed/qed_hw.c

@@ -762,9 +762,10 @@ static int qed_dmae_execute_command(struct qed_hwfn *p_hwfn,
 							    dst_type,
 							    length_cur);
 		if (qed_status) {
-			DP_NOTICE(p_hwfn,
-				  "qed_dmae_execute_sub_operation Failed with error 0x%x. source_addr 0x%llx, destination addr 0x%llx, size_in_dwords 0x%x\n",
-				  qed_status, src_addr, dst_addr, length_cur);
+			qed_hw_err_notify(p_hwfn, p_ptt, QED_HW_ERR_DMAE_FAIL,
+					  "qed_dmae_execute_sub_operation Failed with error 0x%x. source_addr 0x%llx, destination addr 0x%llx, size_in_dwords 0x%x\n",
+					  qed_status, src_addr,
+					  dst_addr, length_cur);
 			break;
 		}
 	}
@@ -837,6 +838,41 @@ int qed_dmae_host2host(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
+void qed_hw_err_notify(struct qed_hwfn *p_hwfn,
+		       struct qed_ptt *p_ptt,
+		       enum qed_hw_err_type err_type, char *fmt, ...)
+{
+	char buf[QED_HW_ERR_MAX_STR_SIZE];
+	va_list vl;
+	int len;
+
+	if (fmt) {
+		va_start(vl, fmt);
+		len = vsnprintf(buf, QED_HW_ERR_MAX_STR_SIZE, fmt, vl);
+		va_end(vl);
+
+		if (len > QED_HW_ERR_MAX_STR_SIZE - 1)
+			len = QED_HW_ERR_MAX_STR_SIZE - 1;
+
+		DP_NOTICE(p_hwfn, "%s", buf);
+	}
+
+	/* Fan failure cannot be masked by handling of another HW error */
+	if (p_hwfn->cdev->recov_in_prog &&
+	    err_type != QED_HW_ERR_FAN_FAIL) {
+		DP_VERBOSE(p_hwfn,
+			   NETIF_MSG_DRV,
+			   "Recovery is in progress. Avoid notifying about HW error %d.\n",
+			   err_type);
+		return;
+	}
+
+	qed_hw_error_occurred(p_hwfn, err_type);
+
+	if (fmt)
+		qed_mcp_send_raw_debug_data(p_hwfn, p_ptt, buf, len);
+}
+
 int qed_dmae_sanity(struct qed_hwfn *p_hwfn,
 		    struct qed_ptt *p_ptt, const char *phase)
 {

drivers/net/ethernet/qlogic/qed/qed_hw.h

@@ -315,4 +315,19 @@ int qed_init_fw_data(struct qed_dev *cdev,
 int qed_dmae_sanity(struct qed_hwfn *p_hwfn,
 		    struct qed_ptt *p_ptt, const char *phase);
 
+#define QED_HW_ERR_MAX_STR_SIZE 256
+
+/**
+ * @brief qed_hw_err_notify - Notify upper layer driver and management FW
+ *	about a HW error.
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param err_type
+ * @param fmt - debug data buffer to send to the MFW
+ * @param ... - buffer format args
+ */
+void qed_hw_err_notify(struct qed_hwfn *p_hwfn,
+		       struct qed_ptt *p_ptt,
+		       enum qed_hw_err_type err_type, char *fmt, ...);
 #endif

drivers/net/ethernet/qlogic/qed/qed_int.c

@@ -96,6 +96,7 @@ struct aeu_invert_reg_bit {
 #define ATTENTION_BB(value)             (value << ATTENTION_BB_SHIFT)
 #define ATTENTION_BB_DIFFERENT          BIT(23)
 
+#define ATTENTION_CLEAR_ENABLE          BIT(28)
 	unsigned int flags;
 
 	/* Callback to call if attention will be triggered */
@@ -363,6 +364,21 @@ static int qed_pglueb_rbc_attn_cb(struct qed_hwfn *p_hwfn)
 	return qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_dpc_ptt);
 }
 
+static int qed_fw_assertion(struct qed_hwfn *p_hwfn)
+{
+	qed_hw_err_notify(p_hwfn, p_hwfn->p_dpc_ptt, QED_HW_ERR_FW_ASSERT,
+			  "FW assertion!\n");
+
+	return -EINVAL;
+}
+
+static int qed_general_attention_35(struct qed_hwfn *p_hwfn)
+{
+	DP_INFO(p_hwfn, "General attention 35!\n");
+
+	return 0;
+}
+
 #define QED_DORQ_ATTENTION_REASON_MASK  (0xfffff)
 #define QED_DORQ_ATTENTION_OPAQUE_MASK  (0xffff)
 #define QED_DORQ_ATTENTION_OPAQUE_SHIFT (0x0)
@@ -605,13 +621,15 @@ static struct aeu_invert_reg aeu_descs[NUM_ATTN_REGS] = {
 
 	{
 		{       /* After Invert 4 */
-			{"General Attention 32", ATTENTION_SINGLE,
-			 NULL, MAX_BLOCK_ID},
+			{"General Attention 32", ATTENTION_SINGLE |
+			 ATTENTION_CLEAR_ENABLE, qed_fw_assertion,
+			 MAX_BLOCK_ID},
 			{"General Attention %d",
 			 (2 << ATTENTION_LENGTH_SHIFT) |
 			 (33 << ATTENTION_OFFSET_SHIFT), NULL, MAX_BLOCK_ID},
-			{"General Attention 35", ATTENTION_SINGLE,
-			 NULL, MAX_BLOCK_ID},
+			{"General Attention 35", ATTENTION_SINGLE |
+			 ATTENTION_CLEAR_ENABLE, qed_general_attention_35,
+			 MAX_BLOCK_ID},
 			{"NWS Parity",
 			 ATTENTION_PAR | ATTENTION_BB_DIFFERENT |
 			 ATTENTION_BB(AEU_INVERT_REG_SPECIAL_CNIG_0),
@@ -927,9 +945,12 @@ qed_int_deassertion_aeu_bit(struct qed_hwfn *p_hwfn,
 		qed_int_attn_print(p_hwfn, p_aeu->block_index,
 				   ATTN_TYPE_INTERRUPT, !b_fatal);
 
-
-	/* If the attention is benign, no need to prevent it */
-	if (!rc)
+	/* Reach assertion if attention is fatal */
+	if (b_fatal)
+		qed_hw_err_notify(p_hwfn, p_hwfn->p_dpc_ptt, QED_HW_ERR_HW_ATTN,
+				  "`%s': Fatal attention\n",
+				  p_bit_name);
+	else /* If the attention is benign, no need to prevent it */
 		goto out;
 
 	/* Prevent this Attention from being asserted in the future */
@@ -2349,6 +2370,11 @@ void qed_int_disable_post_isr_release(struct qed_dev *cdev)
 		cdev->hwfns[i].b_int_requested = false;
 }
 
+void qed_int_attn_clr_enable(struct qed_dev *cdev, bool clr_enable)
+{
+	cdev->attn_clr_en = clr_enable;
+}
+
 int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 			  u8 timer_res, u16 sb_id, bool tx)
 {

drivers/net/ethernet/qlogic/qed/qed_int.h

@@ -190,6 +190,17 @@ void qed_int_get_num_sbs(struct qed_hwfn	*p_hwfn,
  */
 void qed_int_disable_post_isr_release(struct qed_dev *cdev);
 
+/**
+ * @brief qed_int_attn_clr_enable - sets whether the general behavior is
+ *        preventing attentions from being reasserted, or following the
+ *        attributes of the specific attention.
+ *
+ * @param cdev
+ * @param clr_enable
+ *
+ */
+void qed_int_attn_clr_enable(struct qed_dev *cdev, bool clr_enable);
+
 /**
  * @brief - Doorbell Recovery handler.
  *          Run doorbell recovery in case of PF overflow (and flush DORQ if

drivers/net/ethernet/qlogic/qed/qed_main.c

@@ -2468,6 +2468,39 @@ void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn)
 		ops->schedule_recovery_handler(cookie);
 }
 
+char *qed_hw_err_type_descr[] = {
+	[QED_HW_ERR_FAN_FAIL]		= "Fan Failure",
+	[QED_HW_ERR_MFW_RESP_FAIL]	= "MFW Response Failure",
+	[QED_HW_ERR_HW_ATTN]		= "HW Attention",
+	[QED_HW_ERR_DMAE_FAIL]		= "DMAE Failure",
+	[QED_HW_ERR_RAMROD_FAIL]	= "Ramrod Failure",
+	[QED_HW_ERR_FW_ASSERT]		= "FW Assertion",
+	[QED_HW_ERR_LAST]		= "Unknown",
+};
+
+void qed_hw_error_occurred(struct qed_hwfn *p_hwfn,
+			   enum qed_hw_err_type err_type)
+{
+	struct qed_common_cb_ops *ops = p_hwfn->cdev->protocol_ops.common;
+	void *cookie = p_hwfn->cdev->ops_cookie;
+	char *err_str;
+
+	if (err_type > QED_HW_ERR_LAST)
+		err_type = QED_HW_ERR_LAST;
+	err_str = qed_hw_err_type_descr[err_type];
+
+	DP_NOTICE(p_hwfn, "HW error occurred [%s]\n", err_str);
+
+	/* Call the HW error handler of the protocol driver.
+	 * If it is not available - perform a minimal handling of preventing
+	 * HW attentions from being reasserted.
+	 */
+	if (ops && ops->schedule_hw_err_handler)
+		ops->schedule_hw_err_handler(cookie, err_type);
+	else
+		qed_int_attn_clr_enable(p_hwfn->cdev, true);
+}
+
 static int qed_set_coalesce(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal,
 			    void *handle)
 {
@@ -2689,6 +2722,7 @@ const struct qed_common_ops qed_common_ops_pass = {
 	.set_led = &qed_set_led,
 	.recovery_process = &qed_recovery_process,
 	.recovery_prolog = &qed_recovery_prolog,
+	.attn_clr_enable = &qed_int_attn_clr_enable,
 	.update_drv_state = &qed_update_drv_state,
 	.update_mac = &qed_update_mac,
 	.update_mtu = &qed_update_mtu,

drivers/net/ethernet/qlogic/qed/qed_mcp.c

@@ -575,6 +575,8 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
 		if (!QED_MB_FLAGS_IS_SET(p_mb_params, AVOID_BLOCK))
 			qed_mcp_cmd_set_blocking(p_hwfn, true);
 
+		qed_hw_err_notify(p_hwfn, p_ptt,
+				  QED_HW_ERR_MFW_RESP_FAIL, NULL);
 		return -EAGAIN;
 	}
 
@@ -1704,6 +1706,127 @@ static void qed_mcp_update_stag(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		    &resp, &param);
 }
 
+static void qed_mcp_handle_fan_failure(struct qed_hwfn *p_hwfn,
+				       struct qed_ptt *p_ptt)
+{
+	/* A single notification should be sent to upper driver in CMT mode */
+	if (p_hwfn != QED_LEADING_HWFN(p_hwfn->cdev))
+		return;
+
+	qed_hw_err_notify(p_hwfn, p_ptt, QED_HW_ERR_FAN_FAIL,
+			  "Fan failure was detected on the network interface card and it's going to be shut down.\n");
+}
+
+struct qed_mdump_cmd_params {
+	u32 cmd;
+	void *p_data_src;
+	u8 data_src_size;
+	void *p_data_dst;
+	u8 data_dst_size;
+	u32 mcp_resp;
+};
+
+static int
+qed_mcp_mdump_cmd(struct qed_hwfn *p_hwfn,
+		  struct qed_ptt *p_ptt,
+		  struct qed_mdump_cmd_params *p_mdump_cmd_params)
+{
+	struct qed_mcp_mb_params mb_params;
+	int rc;
+
+	memset(&mb_params, 0, sizeof(mb_params));
+	mb_params.cmd = DRV_MSG_CODE_MDUMP_CMD;
+	mb_params.param = p_mdump_cmd_params->cmd;
+	mb_params.p_data_src = p_mdump_cmd_params->p_data_src;
+	mb_params.data_src_size = p_mdump_cmd_params->data_src_size;
+	mb_params.p_data_dst = p_mdump_cmd_params->p_data_dst;
+	mb_params.data_dst_size = p_mdump_cmd_params->data_dst_size;
+	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
+	if (rc)
+		return rc;
+
+	p_mdump_cmd_params->mcp_resp = mb_params.mcp_resp;
+
+	if (p_mdump_cmd_params->mcp_resp == FW_MSG_CODE_MDUMP_INVALID_CMD) {
+		DP_INFO(p_hwfn,
+			"The mdump sub command is unsupported by the MFW [mdump_cmd 0x%x]\n",
+			p_mdump_cmd_params->cmd);
+		rc = -EOPNOTSUPP;
+	} else if (p_mdump_cmd_params->mcp_resp == FW_MSG_CODE_UNSUPPORTED) {
+		DP_INFO(p_hwfn,
+			"The mdump command is not supported by the MFW\n");
+		rc = -EOPNOTSUPP;
+	}
+
+	return rc;
+}
+
+static int qed_mcp_mdump_ack(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_mdump_cmd_params mdump_cmd_params;
+
+	memset(&mdump_cmd_params, 0, sizeof(mdump_cmd_params));
+	mdump_cmd_params.cmd = DRV_MSG_CODE_MDUMP_ACK;
+
+	return qed_mcp_mdump_cmd(p_hwfn, p_ptt, &mdump_cmd_params);
+}
+
+int
+qed_mcp_mdump_get_retain(struct qed_hwfn *p_hwfn,
+			 struct qed_ptt *p_ptt,
+			 struct mdump_retain_data_stc *p_mdump_retain)
+{
+	struct qed_mdump_cmd_params mdump_cmd_params;
+	int rc;
+
+	memset(&mdump_cmd_params, 0, sizeof(mdump_cmd_params));
+	mdump_cmd_params.cmd = DRV_MSG_CODE_MDUMP_GET_RETAIN;
+	mdump_cmd_params.p_data_dst = p_mdump_retain;
+	mdump_cmd_params.data_dst_size = sizeof(*p_mdump_retain);
+
+	rc = qed_mcp_mdump_cmd(p_hwfn, p_ptt, &mdump_cmd_params);
+	if (rc)
+		return rc;
+
+	if (mdump_cmd_params.mcp_resp != FW_MSG_CODE_OK) {
+		DP_INFO(p_hwfn,
+			"Failed to get the mdump retained data [mcp_resp 0x%x]\n",
+			mdump_cmd_params.mcp_resp);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void qed_mcp_handle_critical_error(struct qed_hwfn *p_hwfn,
+					  struct qed_ptt *p_ptt)
+{
+	struct mdump_retain_data_stc mdump_retain;
+	int rc;
+
+	/* In CMT mode - no need for more than a single acknowledgment to the
+	 * MFW, and no more than a single notification to the upper driver.
+	 */
+	if (p_hwfn != QED_LEADING_HWFN(p_hwfn->cdev))
+		return;
+
+	rc = qed_mcp_mdump_get_retain(p_hwfn, p_ptt, &mdump_retain);
+	if (rc == 0 && mdump_retain.valid)
+		DP_NOTICE(p_hwfn,
+			  "The MFW notified that a critical error occurred in the device [epoch 0x%08x, pf 0x%x, status 0x%08x]\n",
+			  mdump_retain.epoch,
+			  mdump_retain.pf, mdump_retain.status);
+	else
+		DP_NOTICE(p_hwfn,
+			  "The MFW notified that a critical error occurred in the device\n");
+
+	DP_NOTICE(p_hwfn,
+		  "Acknowledging the notification to not allow the MFW crash dump [driver debug data collection is preferable]\n");
+	qed_mcp_mdump_ack(p_hwfn, p_ptt);
+
+	qed_hw_err_notify(p_hwfn, p_ptt, QED_HW_ERR_HW_ATTN, NULL);
+}
+
 void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	struct public_func shmem_info;
@@ -1850,6 +1973,12 @@ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn,
 		case MFW_DRV_MSG_S_TAG_UPDATE:
 			qed_mcp_update_stag(p_hwfn, p_ptt);
 			break;
+		case MFW_DRV_MSG_FAILURE_DETECTED:
+			qed_mcp_handle_fan_failure(p_hwfn, p_ptt);
+			break;
+		case MFW_DRV_MSG_CRITICAL_ERROR_OCCURRED:
+			qed_mcp_handle_critical_error(p_hwfn, p_ptt);
+			break;
 		case MFW_DRV_MSG_GET_TLV_REQ:
 			qed_mfw_tlv_req(p_hwfn);
 			break;
@@ -3819,3 +3948,127 @@ int qed_mcp_nvm_set_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 				  DRV_MSG_CODE_SET_NVM_CFG_OPTION,
 				  mb_param, &resp, &param, len, (u32 *)p_buf);
 }
+
+#define QED_MCP_DBG_DATA_MAX_SIZE               MCP_DRV_NVM_BUF_LEN
+#define QED_MCP_DBG_DATA_MAX_HEADER_SIZE        sizeof(u32)
+#define QED_MCP_DBG_DATA_MAX_PAYLOAD_SIZE \
+	(QED_MCP_DBG_DATA_MAX_SIZE - QED_MCP_DBG_DATA_MAX_HEADER_SIZE)
+
+static int
+__qed_mcp_send_debug_data(struct qed_hwfn *p_hwfn,
+			  struct qed_ptt *p_ptt, u8 *p_buf, u8 size)
+{
+	struct qed_mcp_mb_params mb_params;
+	int rc;
+
+	if (size > QED_MCP_DBG_DATA_MAX_SIZE) {
+		DP_ERR(p_hwfn,
+		       "Debug data size is %d while it should not exceed %d\n",
+		       size, QED_MCP_DBG_DATA_MAX_SIZE);
+		return -EINVAL;
+	}
+
+	memset(&mb_params, 0, sizeof(mb_params));
+	mb_params.cmd = DRV_MSG_CODE_DEBUG_DATA_SEND;
+	SET_MFW_FIELD(mb_params.param, DRV_MSG_CODE_DEBUG_DATA_SEND_SIZE, size);
+	mb_params.p_data_src = p_buf;
+	mb_params.data_src_size = size;
+	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
+	if (rc)
+		return rc;
+
+	if (mb_params.mcp_resp == FW_MSG_CODE_UNSUPPORTED) {
+		DP_INFO(p_hwfn,
+			"The DEBUG_DATA_SEND command is unsupported by the MFW\n");
+		return -EOPNOTSUPP;
+	} else if (mb_params.mcp_resp == (u32)FW_MSG_CODE_DEBUG_NOT_ENABLED) {
+		DP_INFO(p_hwfn, "The DEBUG_DATA_SEND command is not enabled\n");
+		return -EBUSY;
+	} else if (mb_params.mcp_resp != (u32)FW_MSG_CODE_DEBUG_DATA_SEND_OK) {
+		DP_NOTICE(p_hwfn,
+			  "Failed to send debug data to the MFW [resp 0x%08x]\n",
+			  mb_params.mcp_resp);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+enum qed_mcp_dbg_data_type {
+	QED_MCP_DBG_DATA_TYPE_RAW,
+};
+
+/* Header format: [31:28] PFID, [27:20] flags, [19:12] type, [11:0] S/N */
+#define QED_MCP_DBG_DATA_HDR_SN_OFFSET  0
+#define QED_MCP_DBG_DATA_HDR_SN_MASK            0x00000fff
+#define QED_MCP_DBG_DATA_HDR_TYPE_OFFSET        12
+#define QED_MCP_DBG_DATA_HDR_TYPE_MASK  0x000ff000
+#define QED_MCP_DBG_DATA_HDR_FLAGS_OFFSET       20
+#define QED_MCP_DBG_DATA_HDR_FLAGS_MASK 0x0ff00000
+#define QED_MCP_DBG_DATA_HDR_PF_OFFSET  28
+#define QED_MCP_DBG_DATA_HDR_PF_MASK            0xf0000000
+
+#define QED_MCP_DBG_DATA_HDR_FLAGS_FIRST        0x1
+#define QED_MCP_DBG_DATA_HDR_FLAGS_LAST 0x2
+
+static int
+qed_mcp_send_debug_data(struct qed_hwfn *p_hwfn,
+			struct qed_ptt *p_ptt,
+			enum qed_mcp_dbg_data_type type, u8 *p_buf, u32 size)
+{
+	u8 raw_data[QED_MCP_DBG_DATA_MAX_SIZE], *p_tmp_buf = p_buf;
+	u32 tmp_size = size, *p_header, *p_payload;
+	u8 flags = 0;
+	u16 seq;
+	int rc;
+
+	p_header = (u32 *)raw_data;
+	p_payload = (u32 *)(raw_data + QED_MCP_DBG_DATA_MAX_HEADER_SIZE);
+
+	seq = (u16)atomic_inc_return(&p_hwfn->mcp_info->dbg_data_seq);
+
+	/* First chunk is marked as 'first' */
+	flags |= QED_MCP_DBG_DATA_HDR_FLAGS_FIRST;
+
+	*p_header = 0;
+	SET_MFW_FIELD(*p_header, QED_MCP_DBG_DATA_HDR_SN, seq);
+	SET_MFW_FIELD(*p_header, QED_MCP_DBG_DATA_HDR_TYPE, type);
+	SET_MFW_FIELD(*p_header, QED_MCP_DBG_DATA_HDR_FLAGS, flags);
+	SET_MFW_FIELD(*p_header, QED_MCP_DBG_DATA_HDR_PF, p_hwfn->abs_pf_id);
+
+	while (tmp_size > QED_MCP_DBG_DATA_MAX_PAYLOAD_SIZE) {
+		memcpy(p_payload, p_tmp_buf, QED_MCP_DBG_DATA_MAX_PAYLOAD_SIZE);
+		rc = __qed_mcp_send_debug_data(p_hwfn, p_ptt, raw_data,
+					       QED_MCP_DBG_DATA_MAX_SIZE);
+		if (rc)
+			return rc;
+
+		/* Clear the 'first' marking after sending the first chunk */
+		if (p_tmp_buf == p_buf) {
+			flags &= ~QED_MCP_DBG_DATA_HDR_FLAGS_FIRST;
+			SET_MFW_FIELD(*p_header, QED_MCP_DBG_DATA_HDR_FLAGS,
+				      flags);
+		}
+
+		p_tmp_buf += QED_MCP_DBG_DATA_MAX_PAYLOAD_SIZE;
+		tmp_size -= QED_MCP_DBG_DATA_MAX_PAYLOAD_SIZE;
+	}
+
+	/* Last chunk is marked as 'last' */
+	flags |= QED_MCP_DBG_DATA_HDR_FLAGS_LAST;
+	SET_MFW_FIELD(*p_header, QED_MCP_DBG_DATA_HDR_FLAGS, flags);
+	memcpy(p_payload, p_tmp_buf, tmp_size);
+
+	/* Casting the left size to u8 is ok since at this point it is <= 32 */
+	return __qed_mcp_send_debug_data(p_hwfn, p_ptt, raw_data,
+					 (u8)(QED_MCP_DBG_DATA_MAX_HEADER_SIZE +
+					 tmp_size));
+}
+
+int
+qed_mcp_send_raw_debug_data(struct qed_hwfn *p_hwfn,
+			    struct qed_ptt *p_ptt, u8 *p_buf, u32 size)
+{
+	return qed_mcp_send_debug_data(p_hwfn, p_ptt,
+				       QED_MCP_DBG_DATA_TYPE_RAW, p_buf, size);
+}

drivers/net/ethernet/qlogic/qed/qed_mcp.h

@@ -685,6 +685,18 @@ int qed_mcp_bist_nvm_get_image_att(struct qed_hwfn *p_hwfn,
  */
 int qed_mfw_process_tlv_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
 
+/**
+ * @brief Send raw debug data to the MFW
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param p_buf - raw debug data buffer
+ * @param size - buffer size
+ */
+int
+qed_mcp_send_raw_debug_data(struct qed_hwfn *p_hwfn,
+			    struct qed_ptt *p_ptt, u8 *p_buf, u32 size);
+
 /* Using hwfn number (and not pf_num) is required since in CMT mode,
  * same pf_num may be used by two different hwfn
  * TODO - this shouldn't really be in .h file, but until all fields
@@ -731,6 +743,9 @@ struct qed_mcp_info {
 
 	/* Capabilties negotiated with the MFW */
 	u32					capabilities;
+
+	/* S/N for debug data mailbox commands */
+	atomic_t dbg_data_seq;
 };
 
 struct qed_mcp_mb_params {
@@ -1001,6 +1016,19 @@ int __qed_configure_pf_min_bandwidth(struct qed_hwfn *p_hwfn,
 int qed_mcp_mask_parities(struct qed_hwfn *p_hwfn,
 			  struct qed_ptt *p_ptt, u32 mask_parities);
 
+/* @brief - Gets the mdump retained data from the MFW.
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param p_mdump_retain
+ *
+ * @param return 0 upon success.
+ */
+int
+qed_mcp_mdump_get_retain(struct qed_hwfn *p_hwfn,
+			 struct qed_ptt *p_ptt,
+			 struct mdump_retain_data_stc *p_mdump_retain);
+
 /**
  * @brief - Sets the MFW's max value for the given resource
  *

drivers/net/ethernet/qlogic/qed/qed_spq.c

@@ -160,12 +160,16 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn,
 		return 0;
 	}
 err:
-	DP_NOTICE(p_hwfn,
-		  "Ramrod is stuck [CID %08x cmd %02x protocol %02x echo %04x]\n",
-		  le32_to_cpu(p_ent->elem.hdr.cid),
-		  p_ent->elem.hdr.cmd_id,
-		  p_ent->elem.hdr.protocol_id,
-		  le16_to_cpu(p_ent->elem.hdr.echo));
+	p_ptt = qed_ptt_acquire(p_hwfn);
+	if (!p_ptt)
+		return -EBUSY;
+	qed_hw_err_notify(p_hwfn, p_ptt, QED_HW_ERR_RAMROD_FAIL,
+			  "Ramrod is stuck [CID %08x cmd %02x protocol %02x echo %04x]\n",
+			  le32_to_cpu(p_ent->elem.hdr.cid),
+			  p_ent->elem.hdr.cmd_id,
+			  p_ent->elem.hdr.protocol_id,
+			  le16_to_cpu(p_ent->elem.hdr.echo));
+	qed_ptt_release(p_hwfn, p_ptt);
 
 	return -EBUSY;
 }

drivers/net/ethernet/qlogic/qede/qede.h

@@ -278,6 +278,14 @@ struct qede_dev {
 	struct qede_rdma_dev		rdma_info;
 
 	struct bpf_prog *xdp_prog;
+
+	unsigned long err_flags;
+#define QEDE_ERR_IS_HANDLED	31
+#define QEDE_ERR_ATTN_CLR_EN	0
+#define QEDE_ERR_GET_DBG_INFO	1
+#define QEDE_ERR_IS_RECOVERABLE	2
+#define QEDE_ERR_WARN		3
+
 	struct qede_dump_info		dump_info;
 };
 
@@ -485,12 +493,15 @@ struct qede_fastpath {
 
 #define QEDE_SP_RECOVERY		0
 #define QEDE_SP_RX_MODE			1
+#define QEDE_SP_RSVD1                   2
+#define QEDE_SP_RSVD2                   3
+#define QEDE_SP_HW_ERR                  4
+#define QEDE_SP_ARFS_CONFIG             5
 #define QEDE_SP_AER			7
 
 #ifdef CONFIG_RFS_ACCEL
 int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 		       u16 rxq_index, u32 flow_id);
-#define QEDE_SP_ARFS_CONFIG	4
 #define QEDE_SP_TASK_POLL_DELAY	(5 * HZ)
 #endif
 
@@ -522,7 +533,6 @@ u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb,
 netdev_features_t qede_features_check(struct sk_buff *skb,
 				      struct net_device *dev,
 				      netdev_features_t features);
-void qede_tx_log_print(struct qede_dev *edev, struct qede_fastpath *fp);
 int qede_alloc_rx_buffer(struct qede_rx_queue *rxq, bool allow_lazy);
 int qede_free_tx_pkt(struct qede_dev *edev,
 		     struct qede_tx_queue *txq, int *len);

drivers/net/ethernet/qlogic/qede/qede_ethtool.c

@@ -190,12 +190,14 @@ static const struct {
 enum {
 	QEDE_PRI_FLAG_CMT,
 	QEDE_PRI_FLAG_SMART_AN_SUPPORT, /* MFW supports SmartAN */
+	QEDE_PRI_FLAG_RECOVER_ON_ERROR,
 	QEDE_PRI_FLAG_LEN,
 };
 
 static const char qede_private_arr[QEDE_PRI_FLAG_LEN][ETH_GSTRING_LEN] = {
 	"Coupled-Function",
 	"SmartAN capable",
+	"Recover on error",
 };
 
 enum qede_ethtool_tests {
@@ -417,9 +419,30 @@ static u32 qede_get_priv_flags(struct net_device *dev)
 	if (edev->dev_info.common.smart_an)
 		flags |= BIT(QEDE_PRI_FLAG_SMART_AN_SUPPORT);
 
+	if (edev->err_flags & BIT(QEDE_ERR_IS_RECOVERABLE))
+		flags |= BIT(QEDE_PRI_FLAG_RECOVER_ON_ERROR);
+
 	return flags;
 }
 
+static int qede_set_priv_flags(struct net_device *dev, u32 flags)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+	u32 cflags = qede_get_priv_flags(dev);
+	u32 dflags = flags ^ cflags;
+
+	/* can only change RECOVER_ON_ERROR flag */
+	if (dflags & ~BIT(QEDE_PRI_FLAG_RECOVER_ON_ERROR))
+		return -EINVAL;
+
+	if (flags & BIT(QEDE_PRI_FLAG_RECOVER_ON_ERROR))
+		set_bit(QEDE_ERR_IS_RECOVERABLE, &edev->err_flags);
+	else
+		clear_bit(QEDE_ERR_IS_RECOVERABLE, &edev->err_flags);
+
+	return 0;
+}
+
 struct qede_link_mode_mapping {
 	u32 qed_link_mode;
 	u32 ethtool_link_mode;
@@ -2098,6 +2121,7 @@ static const struct ethtool_ops qede_ethtool_ops = {
 	.set_phys_id = qede_set_phys_id,
 	.get_ethtool_stats = qede_get_ethtool_stats,
 	.get_priv_flags = qede_get_priv_flags,
+	.set_priv_flags = qede_set_priv_flags,
 	.get_sset_count = qede_get_sset_count,
 	.get_rxnfc = qede_get_rxnfc,
 	.set_rxnfc = qede_set_rxnfc,

drivers/net/ethernet/qlogic/qede/qede_main.c

@@ -139,10 +139,12 @@ static void qede_shutdown(struct pci_dev *pdev);
 static void qede_link_update(void *dev, struct qed_link_output *link);
 static void qede_schedule_recovery_handler(void *dev);
 static void qede_recovery_handler(struct qede_dev *edev);
+static void qede_schedule_hw_err_handler(void *dev,
+					 enum qed_hw_err_type err_type);
 static void qede_get_eth_tlv_data(void *edev, void *data);
 static void qede_get_generic_tlv_data(void *edev,
 				      struct qed_generic_tlvs *data);
-
+static void qede_generic_hw_err_handler(struct qede_dev *edev);
 #ifdef CONFIG_QED_SRIOV
 static int qede_set_vf_vlan(struct net_device *ndev, int vf, u16 vlan, u8 qos,
 			    __be16 vlan_proto)
@@ -230,6 +232,7 @@ static struct qed_eth_cb_ops qede_ll_ops = {
 #endif
 		.link_update = qede_link_update,
 		.schedule_recovery_handler = qede_schedule_recovery_handler,
+		.schedule_hw_err_handler = qede_schedule_hw_err_handler,
 		.get_generic_tlv_data = qede_get_generic_tlv_data,
 		.get_protocol_tlv_data = qede_get_eth_tlv_data,
 	},
@@ -536,6 +539,51 @@ static int qede_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return 0;
 }
 
+static void qede_tx_log_print(struct qede_dev *edev, struct qede_tx_queue *txq)
+{
+	DP_NOTICE(edev,
+		  "Txq[%d]: FW cons [host] %04x, SW cons %04x, SW prod %04x [Jiffies %lu]\n",
+		  txq->index, le16_to_cpu(*txq->hw_cons_ptr),
+		  qed_chain_get_cons_idx(&txq->tx_pbl),
+		  qed_chain_get_prod_idx(&txq->tx_pbl),
+		  jiffies);
+}
+
+static void qede_tx_timeout(struct net_device *dev, unsigned int txqueue)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+	struct qede_tx_queue *txq;
+	int cos;
+
+	netif_carrier_off(dev);
+	DP_NOTICE(edev, "TX timeout on queue %u!\n", txqueue);
+
+	if (!(edev->fp_array[txqueue].type & QEDE_FASTPATH_TX))
+		return;
+
+	for_each_cos_in_txq(edev, cos) {
+		txq = &edev->fp_array[txqueue].txq[cos];
+
+		if (qed_chain_get_cons_idx(&txq->tx_pbl) !=
+		    qed_chain_get_prod_idx(&txq->tx_pbl))
+			qede_tx_log_print(edev, txq);
+	}
+
+	if (IS_VF(edev))
+		return;
+
+	if (test_and_set_bit(QEDE_ERR_IS_HANDLED, &edev->err_flags) ||
+	    edev->state == QEDE_STATE_RECOVERY) {
+		DP_INFO(edev,
+			"Avoid handling a Tx timeout while another HW error is being handled\n");
+		return;
+	}
+
+	set_bit(QEDE_ERR_GET_DBG_INFO, &edev->err_flags);
+	set_bit(QEDE_SP_HW_ERR, &edev->sp_flags);
+	schedule_delayed_work(&edev->sp_task, 0);
+}
+
 static int qede_setup_tc(struct net_device *ndev, u8 num_tc)
 {
 	struct qede_dev *edev = netdev_priv(ndev);
@@ -623,6 +671,7 @@ static const struct net_device_ops qede_netdev_ops = {
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_change_mtu = qede_change_mtu,
 	.ndo_do_ioctl = qede_ioctl,
+	.ndo_tx_timeout = qede_tx_timeout,
 #ifdef CONFIG_QED_SRIOV
 	.ndo_set_vf_mac = qede_set_vf_mac,
 	.ndo_set_vf_vlan = qede_set_vf_vlan,
@@ -1009,6 +1058,8 @@ static void qede_sp_task(struct work_struct *work)
 			qede_process_arfs_filters(edev, false);
 	}
 #endif
+	if (test_and_clear_bit(QEDE_SP_HW_ERR, &edev->sp_flags))
+		qede_generic_hw_err_handler(edev);
 	__qede_unlock(edev);
 
 	if (test_and_clear_bit(QEDE_SP_AER, &edev->sp_flags)) {
@@ -2509,6 +2560,100 @@ static void qede_recovery_handler(struct qede_dev *edev)
 	qede_recovery_failed(edev);
 }
 
+static void qede_atomic_hw_err_handler(struct qede_dev *edev)
+{
+	struct qed_dev *cdev = edev->cdev;
+
+	DP_NOTICE(edev,
+		  "Generic non-sleepable HW error handling started - err_flags 0x%lx\n",
+		  edev->err_flags);
+
+	/* Get a call trace of the flow that led to the error */
+	WARN_ON(test_bit(QEDE_ERR_WARN, &edev->err_flags));
+
+	/* Prevent HW attentions from being reasserted */
+	if (test_bit(QEDE_ERR_ATTN_CLR_EN, &edev->err_flags))
+		edev->ops->common->attn_clr_enable(cdev, true);
+
+	DP_NOTICE(edev, "Generic non-sleepable HW error handling is done\n");
+}
+
+static void qede_generic_hw_err_handler(struct qede_dev *edev)
+{
+	struct qed_dev *cdev = edev->cdev;
+
+	DP_NOTICE(edev,
+		  "Generic sleepable HW error handling started - err_flags 0x%lx\n",
+		  edev->err_flags);
+
+	/* Trigger a recovery process.
+	 * This is placed in the sleep requiring section just to make
+	 * sure it is the last one, and that all the other operations
+	 * were completed.
+	 */
+	if (test_bit(QEDE_ERR_IS_RECOVERABLE, &edev->err_flags))
+		edev->ops->common->recovery_process(cdev);
+
+	clear_bit(QEDE_ERR_IS_HANDLED, &edev->err_flags);
+
+	DP_NOTICE(edev, "Generic sleepable HW error handling is done\n");
+}
+
+static void qede_set_hw_err_flags(struct qede_dev *edev,
+				  enum qed_hw_err_type err_type)
+{
+	unsigned long err_flags = 0;
+
+	switch (err_type) {
+	case QED_HW_ERR_DMAE_FAIL:
+		set_bit(QEDE_ERR_WARN, &err_flags);
+		fallthrough;
+	case QED_HW_ERR_MFW_RESP_FAIL:
+	case QED_HW_ERR_HW_ATTN:
+	case QED_HW_ERR_RAMROD_FAIL:
+	case QED_HW_ERR_FW_ASSERT:
+		set_bit(QEDE_ERR_ATTN_CLR_EN, &err_flags);
+		set_bit(QEDE_ERR_GET_DBG_INFO, &err_flags);
+		break;
+
+	default:
+		DP_NOTICE(edev, "Unexpected HW error [%d]\n", err_type);
+		break;
+	}
+
+	edev->err_flags |= err_flags;
+}
+
+static void qede_schedule_hw_err_handler(void *dev,
+					 enum qed_hw_err_type err_type)
+{
+	struct qede_dev *edev = dev;
+
+	/* Fan failure cannot be masked by handling of another HW error or by a
+	 * concurrent recovery process.
+	 */
+	if ((test_and_set_bit(QEDE_ERR_IS_HANDLED, &edev->err_flags) ||
+	     edev->state == QEDE_STATE_RECOVERY) &&
+	     err_type != QED_HW_ERR_FAN_FAIL) {
+		DP_INFO(edev,
+			"Avoid scheduling an error handling while another HW error is being handled\n");
+		return;
+	}
+
+	if (err_type >= QED_HW_ERR_LAST) {
+		DP_NOTICE(edev, "Unknown HW error [%d]\n", err_type);
+		clear_bit(QEDE_ERR_IS_HANDLED, &edev->err_flags);
+		return;
+	}
+
+	qede_set_hw_err_flags(edev, err_type);
+	qede_atomic_hw_err_handler(edev);
+	set_bit(QEDE_SP_HW_ERR, &edev->sp_flags);
+	schedule_delayed_work(&edev->sp_task, 0);
+
+	DP_INFO(edev, "Scheduled a error handler [err_type %d]\n", err_type);
+}
+
 static bool qede_is_txq_full(struct qede_dev *edev, struct qede_tx_queue *txq)
 {
 	struct netdev_queue *netdev_txq;

include/linux/qed/qed_if.h

@@ -607,6 +607,16 @@ struct qed_sb_info {
 	struct qed_dev *cdev;
 };
 
+enum qed_hw_err_type {
+	QED_HW_ERR_FAN_FAIL,
+	QED_HW_ERR_MFW_RESP_FAIL,
+	QED_HW_ERR_HW_ATTN,
+	QED_HW_ERR_DMAE_FAIL,
+	QED_HW_ERR_RAMROD_FAIL,
+	QED_HW_ERR_FW_ASSERT,
+	QED_HW_ERR_LAST,
+};
+
 enum qed_dev_type {
 	QED_DEV_TYPE_BB,
 	QED_DEV_TYPE_AH,
@@ -811,10 +821,11 @@ enum qed_nvm_flash_cmd {
 
 struct qed_common_cb_ops {
 	void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc);
-	void	(*link_update)(void			*dev,
-			       struct qed_link_output	*link);
+	void (*link_update)(void *dev, struct qed_link_output *link);
 	void (*schedule_recovery_handler)(void *dev);
-	void	(*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type);
+	void (*schedule_hw_err_handler)(void *dev,
+					enum qed_hw_err_type err_type);
+	void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type);
 	void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data);
 	void (*get_protocol_tlv_data)(void *dev, void *data);
 };
@@ -1034,6 +1045,15 @@ struct qed_common_ops {
  */
 	int (*set_led)(struct qed_dev *cdev,
 		       enum qed_led_mode mode);
+
+/**
+ * @brief attn_clr_enable - Prevent attentions from being reasserted
+ *
+ * @param cdev
+ * @param clr_enable
+ */
+	void (*attn_clr_enable)(struct qed_dev *cdev, bool clr_enable);
+
 /**
  * @brief db_recovery_add - add doorbell information to the doorbell
  * recovery mechanism.