Merge branch 'qed-Error-recovery-process'

Michal Kalderon says:

====================
qed*: Error recovery process

Parity errors might happen in the device's memories due to momentary bit
flips which are caused by radiation.
Errors that are not correctable initiate a process kill event, which blocks
the device access towards the host and the network, and a recovery process
is started in the management FW and in the driver.

This series adds the support of this process in the qed core module and in
the qede driver (patches 2 & 3).
Patch 1 in the series revises the load sequence, to avoid PCI errors that
might be observed during a recovery process.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -554,7 +554,6 @@ struct qed_hwfn {
 	u8				dp_level;
 	char				name[NAME_SIZE];
 
-	bool				first_on_engine;
 	bool				hw_init_done;
 
 	u8				num_funcs_on_engine;
@@ -805,6 +804,9 @@ struct qed_dev {
 
 	u32				mcp_nvm_resp;
 
+	/* Recovery */
+	bool recov_in_prog;
+
 	/* Linux specific here */
 	struct  qede_dev		*edev;
 	struct  pci_dev			*pdev;
@@ -944,6 +946,7 @@ void qed_link_update(struct qed_hwfn *hwfn, struct qed_ptt *ptt);
 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_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_dev.c

@@ -1959,11 +1959,6 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn,
 		     (p_hwfn->hw_info.personality == QED_PCI_FCOE) ? 1 : 0);
 	STORE_RT_REG(p_hwfn, PRS_REG_SEARCH_ROCE_RT_OFFSET, 0);
 
-	/* Cleanup chip from previous driver if such remains exist */
-	rc = qed_final_cleanup(p_hwfn, p_ptt, rel_pf_id, false);
-	if (rc)
-		return rc;
-
 	/* Sanity check before the PF init sequence that uses DMAE */
 	rc = qed_dmae_sanity(p_hwfn, p_ptt, "pf_phase");
 	if (rc)
@@ -2007,17 +2002,15 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-static int qed_change_pci_hwfn(struct qed_hwfn *p_hwfn,
-			       struct qed_ptt *p_ptt,
-			       u8 enable)
+int qed_pglueb_set_pfid_enable(struct qed_hwfn *p_hwfn,
+			       struct qed_ptt *p_ptt, bool b_enable)
 {
-	u32 delay_idx = 0, val, set_val = enable ? 1 : 0;
+	u32 delay_idx = 0, val, set_val = b_enable ? 1 : 0;
 
-	/* Change PF in PXP */
-	qed_wr(p_hwfn, p_ptt,
-	       PGLUE_B_REG_INTERNAL_PFID_ENABLE_MASTER, set_val);
+	/* Configure the PF's internal FID_enable for master transactions */
+	qed_wr(p_hwfn, p_ptt, PGLUE_B_REG_INTERNAL_PFID_ENABLE_MASTER, set_val);
 
-	/* wait until value is set - try for 1 second every 50us */
+	/* Wait until value is set - try for 1 second every 50us */
 	for (delay_idx = 0; delay_idx < 20000; delay_idx++) {
 		val = qed_rd(p_hwfn, p_ptt,
 			     PGLUE_B_REG_INTERNAL_PFID_ENABLE_MASTER);
@@ -2071,13 +2064,19 @@ static int qed_vf_start(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
+static void qed_pglueb_clear_err(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	qed_wr(p_hwfn, p_ptt, PGLUE_B_REG_WAS_ERROR_PF_31_0_CLR,
+	       BIT(p_hwfn->abs_pf_id));
+}
+
 int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 {
 	struct qed_load_req_params load_req_params;
 	u32 load_code, resp, param, drv_mb_param;
 	bool b_default_mtu = true;
 	struct qed_hwfn *p_hwfn;
-	int rc = 0, mfw_rc, i;
+	int rc = 0, i;
 	u16 ether_type;
 
 	if ((p_params->int_mode == QED_INT_MODE_MSI) && (cdev->num_hwfns > 1)) {
@@ -2092,7 +2091,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 	}
 
 	for_each_hwfn(cdev, i) {
-		struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
+		p_hwfn = &cdev->hwfns[i];
 
 		/* If management didn't provide a default, set one of our own */
 		if (!p_hwfn->hw_info.mtu) {
@@ -2105,9 +2104,6 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 			continue;
 		}
 
-		/* Enable DMAE in PXP */
-		rc = qed_change_pci_hwfn(p_hwfn, p_hwfn->p_main_ptt, true);
-
 		rc = qed_calc_hw_mode(p_hwfn);
 		if (rc)
 			return rc;
@@ -2144,12 +2140,43 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 			   "Load request was sent. Load code: 0x%x\n",
 			   load_code);
 
+		/* Only relevant for recovery:
+		 * Clear the indication after LOAD_REQ is responded by the MFW.
+		 */
+		cdev->recov_in_prog = false;
+
 		qed_mcp_set_capabilities(p_hwfn, p_hwfn->p_main_ptt);
 
 		qed_reset_mb_shadow(p_hwfn, p_hwfn->p_main_ptt);
 
-		p_hwfn->first_on_engine = (load_code ==
-					   FW_MSG_CODE_DRV_LOAD_ENGINE);
+		/* Clean up chip from previous driver if such remains exist.
+		 * This is not needed when the PF is the first one on the
+		 * engine, since afterwards we are going to init the FW.
+		 */
+		if (load_code != FW_MSG_CODE_DRV_LOAD_ENGINE) {
+			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");
+				goto load_err;
+			}
+		}
+
+		/* Log and clear previous pglue_b errors if such exist */
+		qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_main_ptt);
+
+		/* Enable the PF's internal FID_enable in the PXP */
+		rc = qed_pglueb_set_pfid_enable(p_hwfn, p_hwfn->p_main_ptt,
+						true);
+		if (rc)
+			goto load_err;
+
+		/* Clear the pglue_b was_error indication.
+		 * In E4 it must be done after the BME and the internal
+		 * FID_enable for the PF are set, since VDMs may cause the
+		 * indication to be set again.
+		 */
+		qed_pglueb_clear_err(p_hwfn, p_hwfn->p_main_ptt);
 
 		switch (load_code) {
 		case FW_MSG_CODE_DRV_LOAD_ENGINE:
@@ -2180,39 +2207,29 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 			break;
 		}
 
-		if (rc)
+		if (rc) {
 			DP_NOTICE(p_hwfn,
 				  "init phase failed for loadcode 0x%x (rc %d)\n",
-				   load_code, rc);
+				  load_code, rc);
+			goto load_err;
+		}
 
-		/* ACK mfw regardless of success or failure of initialization */
-		mfw_rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
-				     DRV_MSG_CODE_LOAD_DONE,
-				     0, &load_code, &param);
+		rc = qed_mcp_load_done(p_hwfn, p_hwfn->p_main_ptt);
 		if (rc)
 			return rc;
-		if (mfw_rc) {
-			DP_NOTICE(p_hwfn, "Failed sending LOAD_DONE command\n");
-			return mfw_rc;
-		}
-
-		/* Check if there is a DID mismatch between nvm-cfg/efuse */
-		if (param & FW_MB_PARAM_LOAD_DONE_DID_EFUSE_ERROR)
-			DP_NOTICE(p_hwfn,
-				  "warning: device configuration is not supported on this board type. The device may not function as expected.\n");
 
 		/* send DCBX attention request command */
 		DP_VERBOSE(p_hwfn,
 			   QED_MSG_DCB,
 			   "sending phony dcbx set command to trigger DCBx attention handling\n");
-		mfw_rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
-				     DRV_MSG_CODE_SET_DCBX,
-				     1 << DRV_MB_PARAM_DCBX_NOTIFY_SHIFT,
-				     &load_code, &param);
-		if (mfw_rc) {
+		rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
+				 DRV_MSG_CODE_SET_DCBX,
+				 1 << DRV_MB_PARAM_DCBX_NOTIFY_SHIFT,
+				 &resp, &param);
+		if (rc) {
 			DP_NOTICE(p_hwfn,
 				  "Failed to send DCBX attention request\n");
-			return mfw_rc;
+			return rc;
 		}
 
 		p_hwfn->hw_init_done = true;
@@ -2261,6 +2278,12 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 	}
 
 	return 0;
+
+load_err:
+	/* The MFW load lock should be released also when initialization fails.
+	 */
+	qed_mcp_load_done(p_hwfn, p_hwfn->p_main_ptt);
+	return rc;
 }
 
 #define QED_HW_STOP_RETRY_LIMIT (10)
@@ -2273,6 +2296,9 @@ static void qed_hw_timers_stop(struct qed_dev *cdev,
 	qed_wr(p_hwfn, p_ptt, TM_REG_PF_ENABLE_CONN, 0x0);
 	qed_wr(p_hwfn, p_ptt, TM_REG_PF_ENABLE_TASK, 0x0);
 
+	if (cdev->recov_in_prog)
+		return;
+
 	for (i = 0; i < QED_HW_STOP_RETRY_LIMIT; i++) {
 		if ((!qed_rd(p_hwfn, p_ptt,
 			     TM_REG_PF_SCAN_ACTIVE_CONN)) &&
@@ -2335,12 +2361,14 @@ int qed_hw_stop(struct qed_dev *cdev)
 		p_hwfn->hw_init_done = false;
 
 		/* Send unload command to MCP */
-		rc = qed_mcp_unload_req(p_hwfn, p_ptt);
-		if (rc) {
-			DP_NOTICE(p_hwfn,
-				  "Failed sending a UNLOAD_REQ command. rc = %d.\n",
-				  rc);
-			rc2 = -EINVAL;
+		if (!cdev->recov_in_prog) {
+			rc = qed_mcp_unload_req(p_hwfn, p_ptt);
+			if (rc) {
+				DP_NOTICE(p_hwfn,
+					  "Failed sending a UNLOAD_REQ command. rc = %d.\n",
+					  rc);
+				rc2 = -EINVAL;
+			}
 		}
 
 		qed_slowpath_irq_sync(p_hwfn);
@@ -2382,27 +2410,31 @@ int qed_hw_stop(struct qed_dev *cdev)
 		qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_DB_ENABLE, 0);
 		qed_wr(p_hwfn, p_ptt, QM_REG_PF_EN, 0);
 
-		qed_mcp_unload_done(p_hwfn, p_ptt);
-		if (rc) {
-			DP_NOTICE(p_hwfn,
-				  "Failed sending a UNLOAD_DONE command. rc = %d.\n",
-				  rc);
-			rc2 = -EINVAL;
+		if (!cdev->recov_in_prog) {
+			rc = qed_mcp_unload_done(p_hwfn, p_ptt);
+			if (rc) {
+				DP_NOTICE(p_hwfn,
+					  "Failed sending a UNLOAD_DONE command. rc = %d.\n",
+					  rc);
+				rc2 = -EINVAL;
+			}
 		}
 	}
 
-	if (IS_PF(cdev)) {
+	if (IS_PF(cdev) && !cdev->recov_in_prog) {
 		p_hwfn = QED_LEADING_HWFN(cdev);
 		p_ptt = QED_LEADING_HWFN(cdev)->p_main_ptt;
 
-		/* Disable DMAE in PXP - in CMT, this should only be done for
-		 * first hw-function, and only after all transactions have
-		 * stopped for all active hw-functions.
+		/* Clear the PF's internal FID_enable in the PXP.
+		 * In CMT this should only be done for first hw-function, and
+		 * only after all transactions have stopped for all active
+		 * hw-functions.
 		 */
-		rc = qed_change_pci_hwfn(p_hwfn, p_ptt, false);
+		rc = qed_pglueb_set_pfid_enable(p_hwfn, p_ptt, false);
 		if (rc) {
 			DP_NOTICE(p_hwfn,
-				  "qed_change_pci_hwfn failed. rc = %d.\n", rc);
+				  "qed_pglueb_set_pfid_enable() failed. rc = %d.\n",
+				  rc);
 			rc2 = -EINVAL;
 		}
 	}
@@ -2502,9 +2534,8 @@ static void qed_hw_hwfn_prepare(struct qed_hwfn *p_hwfn)
 		       PGLUE_B_REG_PGL_ADDR_94_F0_BB, 0);
 	}
 
-	/* Clean Previous errors if such exist */
-	qed_wr(p_hwfn, p_hwfn->p_main_ptt,
-	       PGLUE_B_REG_WAS_ERROR_PF_31_0_CLR, 1 << p_hwfn->abs_pf_id);
+	/* Clean previous pglue_b errors if such exist */
+	qed_pglueb_clear_err(p_hwfn, p_hwfn->p_main_ptt);
 
 	/* enable internal target-read */
 	qed_wr(p_hwfn, p_hwfn->p_main_ptt,
@@ -3440,6 +3471,7 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
 				 void __iomem *p_doorbells,
 				 enum qed_pci_personality personality)
 {
+	struct qed_dev *cdev = p_hwfn->cdev;
 	int rc = 0;
 
 	/* Split PCI bars evenly between hwfns */
@@ -3492,7 +3524,7 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
 	/* Sending a mailbox to the MFW should be done after qed_get_hw_info()
 	 * is called as it sets the ports number in an engine.
 	 */
-	if (IS_LEAD_HWFN(p_hwfn)) {
+	if (IS_LEAD_HWFN(p_hwfn) && !cdev->recov_in_prog) {
 		rc = qed_mcp_initiate_pf_flr(p_hwfn, p_hwfn->p_main_ptt);
 		if (rc)
 			DP_NOTICE(p_hwfn, "Failed to initiate PF FLR\n");

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

@@ -472,6 +472,18 @@ int qed_get_queue_coalesce(struct qed_hwfn *p_hwfn, u16 *coal, void *handle);
 int
 qed_set_queue_coalesce(u16 rx_coal, u16 tx_coal, void *p_handle);
 
+/**
+ * @brief qed_pglueb_set_pfid_enable - Enable or disable PCI BUS MASTER
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param b_enable - true/false
+ *
+ * @return int
+ */
+int qed_pglueb_set_pfid_enable(struct qed_hwfn *p_hwfn,
+			       struct qed_ptt *p_ptt, bool b_enable);
+
 /**
  * @brief db_recovery_add - add doorbell information to the doorbell
  * recovery mechanism.

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

@@ -12827,7 +12827,7 @@ enum MFW_DRV_MSG_TYPE {
 	MFW_DRV_MSG_LLDP_DATA_UPDATED,
 	MFW_DRV_MSG_DCBX_REMOTE_MIB_UPDATED,
 	MFW_DRV_MSG_DCBX_OPERATIONAL_MIB_UPDATED,
-	MFW_DRV_MSG_RESERVED4,
+	MFW_DRV_MSG_ERROR_RECOVERY,
 	MFW_DRV_MSG_BW_UPDATE,
 	MFW_DRV_MSG_S_TAG_UPDATE,
 	MFW_DRV_MSG_GET_LAN_STATS,

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

@@ -703,6 +703,17 @@ static int qed_dmae_execute_command(struct qed_hwfn *p_hwfn,
 	int qed_status = 0;
 	u32 offset = 0;
 
+	if (p_hwfn->cdev->recov_in_prog) {
+		DP_VERBOSE(p_hwfn,
+			   NETIF_MSG_HW,
+			   "Recovery is in progress. Avoid DMAE transaction [{src: addr 0x%llx, type %d}, {dst: addr 0x%llx, type %d}, size %d].\n",
+			   src_addr, src_type, dst_addr, dst_type,
+			   size_in_dwords);
+
+		/* Let the flow complete w/o any error handling */
+		return 0;
+	}
+
 	qed_dmae_opcode(p_hwfn,
 			(src_type == QED_DMAE_ADDRESS_GRC),
 			(dst_type == QED_DMAE_ADDRESS_GRC),

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

@@ -255,112 +255,114 @@ static int qed_grc_attn_cb(struct qed_hwfn *p_hwfn)
 #define PGLUE_ATTENTION_ICPL_VALID		(1 << 23)
 #define PGLUE_ATTENTION_ZLR_VALID		(1 << 25)
 #define PGLUE_ATTENTION_ILT_VALID		(1 << 23)
-static int qed_pglub_rbc_attn_cb(struct qed_hwfn *p_hwfn)
+
+int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn,
+				struct qed_ptt *p_ptt)
 {
 	u32 tmp;
 
-	tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-		     PGLUE_B_REG_TX_ERR_WR_DETAILS2);
+	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS2);
 	if (tmp & PGLUE_ATTENTION_VALID) {
 		u32 addr_lo, addr_hi, details;
 
-		addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_lo = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_WR_ADD_31_0);
-		addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_hi = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_WR_ADD_63_32);
-		details = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		details = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_WR_DETAILS);
 
-		DP_INFO(p_hwfn,
-			"Illegal write by chip to [%08x:%08x] blocked.\n"
-			"Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
-			"Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
-			addr_hi, addr_lo, details,
-			(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
-			(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
-			GET_FIELD(details,
-				  PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
-			tmp,
-			GET_FIELD(tmp,
-				  PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1 : 0,
-			GET_FIELD(tmp,
-				  PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
-			GET_FIELD(tmp,
-				  PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1 : 0);
+		DP_NOTICE(p_hwfn,
+			  "Illegal write by chip to [%08x:%08x] blocked.\n"
+			  "Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
+			  "Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
+			  addr_hi, addr_lo, details,
+			  (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
+			  (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
+			  GET_FIELD(details,
+				    PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
+			  tmp,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1 : 0,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1 : 0);
 	}
 
-	tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-		     PGLUE_B_REG_TX_ERR_RD_DETAILS2);
+	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_RD_DETAILS2);
 	if (tmp & PGLUE_ATTENTION_RD_VALID) {
 		u32 addr_lo, addr_hi, details;
 
-		addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_lo = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_RD_ADD_31_0);
-		addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_hi = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_RD_ADD_63_32);
-		details = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		details = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_RD_DETAILS);
 
-		DP_INFO(p_hwfn,
-			"Illegal read by chip from [%08x:%08x] blocked.\n"
-			" Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
-			" Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
-			addr_hi, addr_lo, details,
-			(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
-			(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
-			GET_FIELD(details,
-				  PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
-			tmp,
-			GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1
-									 : 0,
-			GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
-			GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1
-									: 0);
+		DP_NOTICE(p_hwfn,
+			  "Illegal read by chip from [%08x:%08x] blocked.\n"
+			  "Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
+			  "Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
+			  addr_hi, addr_lo, details,
+			  (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
+			  (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
+			  GET_FIELD(details,
+				    PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
+			  tmp,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1 : 0,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1 : 0);
 	}
 
-	tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-		     PGLUE_B_REG_TX_ERR_WR_DETAILS_ICPL);
+	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS_ICPL);
 	if (tmp & PGLUE_ATTENTION_ICPL_VALID)
-		DP_INFO(p_hwfn, "ICPL error - %08x\n", tmp);
+		DP_NOTICE(p_hwfn, "ICPL error - %08x\n", tmp);
 
-	tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-		     PGLUE_B_REG_MASTER_ZLR_ERR_DETAILS);
+	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_MASTER_ZLR_ERR_DETAILS);
 	if (tmp & PGLUE_ATTENTION_ZLR_VALID) {
 		u32 addr_hi, addr_lo;
 
-		addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_lo = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_MASTER_ZLR_ERR_ADD_31_0);
-		addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_hi = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_MASTER_ZLR_ERR_ADD_63_32);
 
-		DP_INFO(p_hwfn, "ZLR eror - %08x [Address %08x:%08x]\n",
-			tmp, addr_hi, addr_lo);
+		DP_NOTICE(p_hwfn, "ZLR error - %08x [Address %08x:%08x]\n",
+			  tmp, addr_hi, addr_lo);
 	}
 
-	tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-		     PGLUE_B_REG_VF_ILT_ERR_DETAILS2);
+	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_VF_ILT_ERR_DETAILS2);
 	if (tmp & PGLUE_ATTENTION_ILT_VALID) {
 		u32 addr_hi, addr_lo, details;
 
-		addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_lo = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_VF_ILT_ERR_ADD_31_0);
-		addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_hi = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_VF_ILT_ERR_ADD_63_32);
-		details = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		details = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_VF_ILT_ERR_DETAILS);
 
-		DP_INFO(p_hwfn,
-			"ILT error - Details %08x Details2 %08x [Address %08x:%08x]\n",
-			details, tmp, addr_hi, addr_lo);
+		DP_NOTICE(p_hwfn,
+			  "ILT error - Details %08x Details2 %08x [Address %08x:%08x]\n",
+			  details, tmp, addr_hi, addr_lo);
 	}
 
 	/* Clear the indications */
-	qed_wr(p_hwfn, p_hwfn->p_dpc_ptt,
-	       PGLUE_B_REG_LATCHED_ERRORS_CLR, (1 << 2));
+	qed_wr(p_hwfn, p_ptt, PGLUE_B_REG_LATCHED_ERRORS_CLR, BIT(2));
 
 	return 0;
 }
 
+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);
+}
+
 #define QED_DORQ_ATTENTION_REASON_MASK  (0xfffff)
 #define QED_DORQ_ATTENTION_OPAQUE_MASK  (0xffff)
 #define QED_DORQ_ATTENTION_OPAQUE_SHIFT (0x0)
@@ -540,7 +542,7 @@ static struct aeu_invert_reg aeu_descs[NUM_ATTN_REGS] = {
 			{"PGLUE misc_flr", ATTENTION_SINGLE,
 			 NULL, MAX_BLOCK_ID},
 			{"PGLUE B RBC", ATTENTION_PAR_INT,
-			 qed_pglub_rbc_attn_cb, BLOCK_PGLUE_B},
+			 qed_pglueb_rbc_attn_cb, BLOCK_PGLUE_B},
 			{"PGLUE misc_mctp", ATTENTION_SINGLE,
 			 NULL, MAX_BLOCK_ID},
 			{"Flash event", ATTENTION_SINGLE, NULL, MAX_BLOCK_ID},

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

@@ -431,4 +431,7 @@ int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 
 #define QED_MAPPING_MEMORY_SIZE(dev)	(NUM_OF_SBS(dev))
 
+int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn,
+				struct qed_ptt *p_ptt);
+
 #endif

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

@@ -359,6 +359,8 @@ static struct qed_dev *qed_probe(struct pci_dev *pdev,
 
 	qed_init_dp(cdev, params->dp_module, params->dp_level);
 
+	cdev->recov_in_prog = params->recov_in_prog;
+
 	rc = qed_init_pci(cdev, pdev);
 	if (rc) {
 		DP_ERR(cdev, "init pci failed\n");
@@ -2203,6 +2205,15 @@ static int qed_nvm_get_image(struct qed_dev *cdev, enum qed_nvm_images type,
 	return qed_mcp_get_nvm_image(hwfn, type, buf, len);
 }
 
+void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn)
+{
+	struct qed_common_cb_ops *ops = p_hwfn->cdev->protocol_ops.common;
+	void *cookie = p_hwfn->cdev->ops_cookie;
+
+	if (ops && ops->schedule_recovery_handler)
+		ops->schedule_recovery_handler(cookie);
+}
+
 static int qed_set_coalesce(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal,
 			    void *handle)
 {
@@ -2226,6 +2237,23 @@ static int qed_set_led(struct qed_dev *cdev, enum qed_led_mode mode)
 	return status;
 }
 
+static int qed_recovery_process(struct qed_dev *cdev)
+{
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_ptt *p_ptt;
+	int rc = 0;
+
+	p_ptt = qed_ptt_acquire(p_hwfn);
+	if (!p_ptt)
+		return -EAGAIN;
+
+	rc = qed_start_recovery_process(p_hwfn, p_ptt);
+
+	qed_ptt_release(p_hwfn, p_ptt);
+
+	return rc;
+}
+
 static int qed_update_wol(struct qed_dev *cdev, bool enabled)
 {
 	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
@@ -2380,6 +2408,8 @@ const struct qed_common_ops qed_common_ops_pass = {
 	.nvm_get_image = &qed_nvm_get_image,
 	.set_coalesce = &qed_set_coalesce,
 	.set_led = &qed_set_led,
+	.recovery_process = &qed_recovery_process,
+	.recovery_prolog = &qed_recovery_prolog,
 	.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

@@ -1070,6 +1070,27 @@ int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
+int qed_mcp_load_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	u32 resp = 0, param = 0;
+	int rc;
+
+	rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_LOAD_DONE, 0, &resp,
+			 &param);
+	if (rc) {
+		DP_NOTICE(p_hwfn,
+			  "Failed to send a LOAD_DONE command, rc = %d\n", rc);
+		return rc;
+	}
+
+	/* Check if there is a DID mismatch between nvm-cfg/efuse */
+	if (param & FW_MB_PARAM_LOAD_DONE_DID_EFUSE_ERROR)
+		DP_NOTICE(p_hwfn,
+			  "warning: device configuration is not supported on this board type. The device may not function as expected.\n");
+
+	return 0;
+}
+
 int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	struct qed_mcp_mb_params mb_params;
@@ -1528,6 +1549,60 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
 	return 0;
 }
 
+u32 qed_get_process_kill_counter(struct qed_hwfn *p_hwfn,
+				 struct qed_ptt *p_ptt)
+{
+	u32 path_offsize_addr, path_offsize, path_addr, proc_kill_cnt;
+
+	if (IS_VF(p_hwfn->cdev))
+		return -EINVAL;
+
+	path_offsize_addr = SECTION_OFFSIZE_ADDR(p_hwfn->mcp_info->public_base,
+						 PUBLIC_PATH);
+	path_offsize = qed_rd(p_hwfn, p_ptt, path_offsize_addr);
+	path_addr = SECTION_ADDR(path_offsize, QED_PATH_ID(p_hwfn));
+
+	proc_kill_cnt = qed_rd(p_hwfn, p_ptt,
+			       path_addr +
+			       offsetof(struct public_path, process_kill)) &
+			PROCESS_KILL_COUNTER_MASK;
+
+	return proc_kill_cnt;
+}
+
+static void qed_mcp_handle_process_kill(struct qed_hwfn *p_hwfn,
+					struct qed_ptt *p_ptt)
+{
+	struct qed_dev *cdev = p_hwfn->cdev;
+	u32 proc_kill_cnt;
+
+	/* Prevent possible attentions/interrupts during the recovery handling
+	 * and till its load phase, during which they will be re-enabled.
+	 */
+	qed_int_igu_disable_int(p_hwfn, p_ptt);
+
+	DP_NOTICE(p_hwfn, "Received a process kill indication\n");
+
+	/* The following operations should be done once, and thus in CMT mode
+	 * are carried out by only the first HW function.
+	 */
+	if (p_hwfn != QED_LEADING_HWFN(cdev))
+		return;
+
+	if (cdev->recov_in_prog) {
+		DP_NOTICE(p_hwfn,
+			  "Ignoring the indication since a recovery process is already in progress\n");
+		return;
+	}
+
+	cdev->recov_in_prog = true;
+
+	proc_kill_cnt = qed_get_process_kill_counter(p_hwfn, p_ptt);
+	DP_NOTICE(p_hwfn, "Process kill counter: %d\n", proc_kill_cnt);
+
+	qed_schedule_recovery_handler(p_hwfn);
+}
+
 static void qed_mcp_send_protocol_stats(struct qed_hwfn *p_hwfn,
 					struct qed_ptt *p_ptt,
 					enum MFW_DRV_MSG_TYPE type)
@@ -1758,6 +1833,9 @@ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn,
 		case MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE:
 			qed_mcp_handle_transceiver_change(p_hwfn, p_ptt);
 			break;
+		case MFW_DRV_MSG_ERROR_RECOVERY:
+			qed_mcp_handle_process_kill(p_hwfn, p_ptt);
+			break;
 		case MFW_DRV_MSG_GET_LAN_STATS:
 		case MFW_DRV_MSG_GET_FCOE_STATS:
 		case MFW_DRV_MSG_GET_ISCSI_STATS:
@@ -2303,6 +2381,43 @@ int qed_mcp_get_flash_size(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
+int qed_start_recovery_process(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_dev *cdev = p_hwfn->cdev;
+
+	if (cdev->recov_in_prog) {
+		DP_NOTICE(p_hwfn,
+			  "Avoid triggering a recovery since such a process is already in progress\n");
+		return -EAGAIN;
+	}
+
+	DP_NOTICE(p_hwfn, "Triggering a recovery process\n");
+	qed_wr(p_hwfn, p_ptt, MISC_REG_AEU_GENERAL_ATTN_35, 0x1);
+
+	return 0;
+}
+
+#define QED_RECOVERY_PROLOG_SLEEP_MS    100
+
+int qed_recovery_prolog(struct qed_dev *cdev)
+{
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_ptt *p_ptt = p_hwfn->p_main_ptt;
+	int rc;
+
+	/* Allow ongoing PCIe transactions to complete */
+	msleep(QED_RECOVERY_PROLOG_SLEEP_MS);
+
+	/* Clear the PF's internal FID_enable in the PXP */
+	rc = qed_pglueb_set_pfid_enable(p_hwfn, p_ptt, false);
+	if (rc)
+		DP_NOTICE(p_hwfn,
+			  "qed_pglueb_set_pfid_enable() failed. rc = %d.\n",
+			  rc);
+
+	return rc;
+}
+
 static int
 qed_mcp_config_vf_msix_bb(struct qed_hwfn *p_hwfn,
 			  struct qed_ptt *p_ptt, u8 vf_id, u8 num)

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

@@ -440,6 +440,38 @@ qed_mcp_send_drv_version(struct qed_hwfn *p_hwfn,
 			 struct qed_ptt *p_ptt,
 			 struct qed_mcp_drv_version *p_ver);
 
+/**
+ * @brief Read the MFW process kill counter
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ *
+ * @return u32
+ */
+u32 qed_get_process_kill_counter(struct qed_hwfn *p_hwfn,
+				 struct qed_ptt *p_ptt);
+
+/**
+ * @brief Trigger a recovery process
+ *
+ *  @param p_hwfn
+ *  @param p_ptt
+ *
+ * @return int
+ */
+int qed_start_recovery_process(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+
+/**
+ * @brief A recovery handler must call this function as its first step.
+ *        It is assumed that the handler is not run from an interrupt context.
+ *
+ *  @param cdev
+ *  @param p_ptt
+ *
+ * @return int
+ */
+int qed_recovery_prolog(struct qed_dev *cdev);
+
 /**
  * @brief Notify MFW about the change in base device properties
  *
@@ -800,6 +832,16 @@ int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
 		     struct qed_ptt *p_ptt,
 		     struct qed_load_req_params *p_params);
 
+/**
+ * @brief Sends a LOAD_DONE message to the MFW
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ *
+ * @return int - 0 - Operation was successful.
+ */
+int qed_mcp_load_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+
 /**
  * @brief Sends a UNLOAD_REQ message to the MFW
  *

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

@@ -518,6 +518,8 @@
 	0x180824UL
 #define  MISC_REG_AEU_GENERAL_ATTN_0 \
 	0x008400UL
+#define MISC_REG_AEU_GENERAL_ATTN_35 \
+	0x00848cUL
 #define  CAU_REG_SB_ADDR_MEMORY \
 	0x1c8000UL
 #define  CAU_REG_SB_VAR_MEMORY \

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

@@ -790,6 +790,17 @@ static int qed_spq_pend_post(struct qed_hwfn *p_hwfn)
 				 SPQ_HIGH_PRI_RESERVE_DEFAULT);
 }
 
+static void qed_spq_recov_set_ret_code(struct qed_spq_entry *p_ent,
+				       u8 *fw_return_code)
+{
+	if (!fw_return_code)
+		return;
+
+	if (p_ent->elem.hdr.protocol_id == PROTOCOLID_ROCE ||
+	    p_ent->elem.hdr.protocol_id == PROTOCOLID_IWARP)
+		*fw_return_code = RDMA_RETURN_OK;
+}
+
 /* Avoid overriding of SPQ entries when getting out-of-order completions, by
  * marking the completions in a bitmap and increasing the chain consumer only
  * for the first successive completed entries.
@@ -825,6 +836,17 @@ int qed_spq_post(struct qed_hwfn *p_hwfn,
 		return -EINVAL;
 	}
 
+	if (p_hwfn->cdev->recov_in_prog) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_SPQ,
+			   "Recovery is in progress. Skip spq post [cmd %02x protocol %02x]\n",
+			   p_ent->elem.hdr.cmd_id, p_ent->elem.hdr.protocol_id);
+
+		/* Let the flow complete w/o any error handling */
+		qed_spq_recov_set_ret_code(p_ent, fw_return_code);
+		return 0;
+	}
+
 	/* Complete the entry */
 	rc = qed_spq_fill_entry(p_hwfn, p_ent);
 

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

@@ -4447,6 +4447,13 @@ int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled)
 	if (cdev->p_iov_info && cdev->p_iov_info->num_vfs && pci_enabled)
 		pci_disable_sriov(cdev->pdev);
 
+	if (cdev->recov_in_prog) {
+		DP_VERBOSE(cdev,
+			   QED_MSG_IOV,
+			   "Skip SRIOV disable operations in the device since a recovery is in progress\n");
+		goto out;
+	}
+
 	for_each_hwfn(cdev, i) {
 		struct qed_hwfn *hwfn = &cdev->hwfns[i];
 		struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
@@ -4486,7 +4493,7 @@ int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled)
 
 		qed_ptt_release(hwfn, ptt);
 	}
-
+out:
 	qed_iov_set_vfs_to_disable(cdev, false);
 
 	return 0;

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

@@ -162,6 +162,7 @@ struct qede_rdma_dev {
 	struct list_head entry;
 	struct list_head rdma_event_list;
 	struct workqueue_struct *rdma_wq;
+	bool exp_recovery;
 };
 
 struct qede_ptp;
@@ -264,6 +265,7 @@ struct qede_dev {
 enum QEDE_STATE {
 	QEDE_STATE_CLOSED,
 	QEDE_STATE_OPEN,
+	QEDE_STATE_RECOVERY,
 };
 
 #define HILO_U64(hi, lo)		((((u64)(hi)) << 32) + (lo))
@@ -462,6 +464,7 @@ struct qede_fastpath {
 #define QEDE_CSUM_UNNECESSARY		BIT(1)
 #define QEDE_TUNN_CSUM_UNNECESSARY	BIT(2)
 
+#define QEDE_SP_RECOVERY		0
 #define QEDE_SP_RX_MODE			1
 
 #ifdef CONFIG_RFS_ACCEL

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

@@ -50,6 +50,8 @@ static void _qede_rdma_dev_add(struct qede_dev *edev)
 	if (!qedr_drv)
 		return;
 
+	/* Leftovers from previous error recovery */
+	edev->rdma_info.exp_recovery = false;
 	edev->rdma_info.qedr_dev = qedr_drv->add(edev->cdev, edev->pdev,
 						 edev->ndev);
 }
@@ -87,21 +89,26 @@ static void qede_rdma_destroy_wq(struct qede_dev *edev)
 	destroy_workqueue(edev->rdma_info.rdma_wq);
 }
 
-int qede_rdma_dev_add(struct qede_dev *edev)
+int qede_rdma_dev_add(struct qede_dev *edev, enum qede_rdma_probe_mode mode)
 {
-	int rc = 0;
+	int rc;
 
-	if (qede_rdma_supported(edev)) {
-		rc = qede_rdma_create_wq(edev);
-		if (rc)
-			return rc;
+	if (!qede_rdma_supported(edev))
+		return 0;
 
-		INIT_LIST_HEAD(&edev->rdma_info.entry);
-		mutex_lock(&qedr_dev_list_lock);
-		list_add_tail(&edev->rdma_info.entry, &qedr_dev_list);
-		_qede_rdma_dev_add(edev);
-		mutex_unlock(&qedr_dev_list_lock);
-	}
+	/* Cannot start qedr while recovering since it wasn't fully stopped */
+	if (mode == QEDE_RDMA_PROBE_RECOVERY)
+		return 0;
+
+	rc = qede_rdma_create_wq(edev);
+	if (rc)
+		return rc;
+
+	INIT_LIST_HEAD(&edev->rdma_info.entry);
+	mutex_lock(&qedr_dev_list_lock);
+	list_add_tail(&edev->rdma_info.entry, &qedr_dev_list);
+	_qede_rdma_dev_add(edev);
+	mutex_unlock(&qedr_dev_list_lock);
 
 	return rc;
 }
@@ -110,19 +117,31 @@ static void _qede_rdma_dev_remove(struct qede_dev *edev)
 {
 	if (qedr_drv && qedr_drv->remove && edev->rdma_info.qedr_dev)
 		qedr_drv->remove(edev->rdma_info.qedr_dev);
-	edev->rdma_info.qedr_dev = NULL;
 }
 
-void qede_rdma_dev_remove(struct qede_dev *edev)
+void qede_rdma_dev_remove(struct qede_dev *edev,
+			  enum qede_rdma_remove_mode mode)
 {
 	if (!qede_rdma_supported(edev))
 		return;
 
-	qede_rdma_destroy_wq(edev);
-	mutex_lock(&qedr_dev_list_lock);
-	_qede_rdma_dev_remove(edev);
-	list_del(&edev->rdma_info.entry);
-	mutex_unlock(&qedr_dev_list_lock);
+	/* Cannot remove qedr while recovering since it wasn't fully stopped */
+	if (mode == QEDE_RDMA_REMOVE_NORMAL) {
+		qede_rdma_destroy_wq(edev);
+		mutex_lock(&qedr_dev_list_lock);
+		if (!edev->rdma_info.exp_recovery)
+			_qede_rdma_dev_remove(edev);
+		edev->rdma_info.qedr_dev = NULL;
+		list_del(&edev->rdma_info.entry);
+		mutex_unlock(&qedr_dev_list_lock);
+	} else {
+		if (!edev->rdma_info.exp_recovery) {
+			mutex_lock(&qedr_dev_list_lock);
+			_qede_rdma_dev_remove(edev);
+			mutex_unlock(&qedr_dev_list_lock);
+		}
+		edev->rdma_info.exp_recovery = true;
+	}
 }
 
 static void _qede_rdma_dev_open(struct qede_dev *edev)
@@ -204,7 +223,8 @@ void qede_rdma_unregister_driver(struct qedr_driver *drv)
 
 	mutex_lock(&qedr_dev_list_lock);
 	list_for_each_entry(edev, &qedr_dev_list, rdma_info.entry) {
-		if (edev->rdma_info.qedr_dev)
+		/* If device has experienced recovery it was already removed */
+		if (edev->rdma_info.qedr_dev && !edev->rdma_info.exp_recovery)
 			_qede_rdma_dev_remove(edev);
 	}
 	qedr_drv = NULL;
@@ -284,6 +304,10 @@ static void qede_rdma_add_event(struct qede_dev *edev,
 {
 	struct qede_rdma_event_work *event_node;
 
+	/* If a recovery was experienced avoid adding the event */
+	if (edev->rdma_info.exp_recovery)
+		return;
+
 	if (!edev->rdma_info.qedr_dev)
 		return;
 

include/linux/qed/qed_if.h

@@ -764,6 +764,7 @@ struct qed_probe_params {
 	u32 dp_module;
 	u8 dp_level;
 	bool is_vf;
+	bool recov_in_prog;
 };
 
 #define QED_DRV_VER_STR_SIZE 12
@@ -810,6 +811,7 @@ 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 (*schedule_recovery_handler)(void *dev);
 	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);
@@ -1057,6 +1059,24 @@ struct qed_common_ops {
 	int (*db_recovery_del)(struct qed_dev *cdev,
 			       void __iomem *db_addr, void *db_data);
 
+/**
+ * @brief recovery_process - Trigger a recovery process
+ *
+ * @param cdev
+ *
+ * @return 0 on success, error otherwise.
+ */
+	int (*recovery_process)(struct qed_dev *cdev);
+
+/**
+ * @brief recovery_prolog - Execute the prolog operations of a recovery process
+ *
+ * @param cdev
+ *
+ * @return 0 on success, error otherwise.
+ */
+	int (*recovery_prolog)(struct qed_dev *cdev);
+
 /**
  * @brief update_drv_state - API to inform the change in the driver state.
  *

include/linux/qed/qede_rdma.h

@@ -55,6 +55,16 @@ struct qede_rdma_event_work {
 	enum qede_rdma_event event;
 };
 
+enum qede_rdma_probe_mode {
+	QEDE_RDMA_PROBE_NORMAL,
+	QEDE_RDMA_PROBE_RECOVERY,
+};
+
+enum qede_rdma_remove_mode {
+	QEDE_RDMA_REMOVE_NORMAL,
+	QEDE_RDMA_REMOVE_RECOVERY,
+};
+
 struct qedr_driver {
 	unsigned char name[32];
 
@@ -74,21 +84,24 @@ void qede_rdma_unregister_driver(struct qedr_driver *drv);
 bool qede_rdma_supported(struct qede_dev *dev);
 
 #if IS_ENABLED(CONFIG_QED_RDMA)
-int qede_rdma_dev_add(struct qede_dev *dev);
+int qede_rdma_dev_add(struct qede_dev *dev, enum qede_rdma_probe_mode mode);
 void qede_rdma_dev_event_open(struct qede_dev *dev);
 void qede_rdma_dev_event_close(struct qede_dev *dev);
-void qede_rdma_dev_remove(struct qede_dev *dev);
+void qede_rdma_dev_remove(struct qede_dev *dev,
+			  enum qede_rdma_remove_mode mode);
 void qede_rdma_event_changeaddr(struct qede_dev *edr);
 
 #else
-static inline int qede_rdma_dev_add(struct qede_dev *dev)
+static inline int qede_rdma_dev_add(struct qede_dev *dev,
+				    enum qede_rdma_probe_mode mode)
 {
 	return 0;
 }
 
 static inline void qede_rdma_dev_event_open(struct qede_dev *dev) {}
 static inline void qede_rdma_dev_event_close(struct qede_dev *dev) {}
-static inline void qede_rdma_dev_remove(struct qede_dev *dev) {}
+static inline void qede_rdma_dev_remove(struct qede_dev *dev,
+					enum qede_rdma_remove_mode mode) {}
 static inline void qede_rdma_event_changeaddr(struct qede_dev *edr) {}
 #endif
 #endif