[v9,2/5] ethdev: support proactive error handling mode

diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c
index 0c10c663e9..b716d2a15f 100644
--- a/app/test-pmd/config.c
+++ b/app/test-pmd/config.c
@@ -924,6 +924,8 @@  port_infos_display(portid_t port_id)
 	}
 	if (dev_info.err_handle_mode == RTE_ETH_ERROR_HANDLE_MODE_PASSIVE)
 		printf("Device error handling mode: passive\n");
+	else if (dev_info.err_handle_mode == RTE_ETH_ERROR_HANDLE_MODE_PROACTIVE)
+		printf("Device error handling mode: proactive\n");
 }
 
 void
diff --git a/doc/guides/prog_guide/poll_mode_drv.rst b/doc/guides/prog_guide/poll_mode_drv.rst
index 9d081b1cba..232dc459b0 100644
--- a/doc/guides/prog_guide/poll_mode_drv.rst
+++ b/doc/guides/prog_guide/poll_mode_drv.rst
@@ -627,3 +627,42 @@  by application.
 The PMD itself should not call rte_eth_dev_reset(). The PMD can trigger
 the application to handle reset event. It is duty of application to
 handle all synchronization before it calls rte_eth_dev_reset().
+
+The above error handling mode is known as ``RTE_ETH_ERROR_HANDLE_MODE_PASSIVE``.
+
+Proactive Error Handling Mode
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+If PMD supports ``RTE_ETH_ERROR_HANDLE_MODE_PROACTIVE``, it means once detect
+hardware or firmware errors, the PMD will try to recover from the errors. In
+this process, the PMD sets the data path pointers to dummy functions (which
+will prevent the crash), and also make sure the control path operations failed
+with retcode -EBUSY.
+
+Also in this process, from the perspective of application, services are
+affected. For example, the Rx/Tx bust APIs cannot receive and send packets,
+and the control plane API return failure.
+
+In some service scenarios, application needs to be aware of the event to
+determine whether to migrate services. So three events were introduced:
+
+* RTE_ETH_EVENT_ERR_RECOVERING: used to notify the application that it detected
+  an error and the recovery is being started. Upon receiving the event, the
+  application should not invoke any control path APIs until receiving
+  RTE_ETH_EVENT_RECOVERY_SUCCESS or RTE_ETH_EVENT_RECOVERY_FAILED event.
+
+
+* RTE_ETH_EVENT_RECOVERY_SUCCESS: used to notify the application that it
+  recovers successful from the error, the PMD already re-configures the port to
+  the state prior to the error.
+
+* RTE_ETH_EVENT_RECOVERY_FAILED: used to notify the application that it
+  recovers failed from the error, the port should not usable anymore. the
+  application should close the port.
+
+.. note::
+        * Before the PMD reports the recovery result, the PMD may report the
+          ``RTE_ETH_EVENT_ERR_RECOVERING`` event again, because a larger error
+          may occur during the recovery.
+        * The error handling mode supported by the PMD can be reported through
+          the ``rte_eth_dev_info_get`` API.
diff --git a/doc/guides/rel_notes/release_22_11.rst b/doc/guides/rel_notes/release_22_11.rst
index 8c021cf050..fc85e5fa87 100644
--- a/doc/guides/rel_notes/release_22_11.rst
+++ b/doc/guides/rel_notes/release_22_11.rst
@@ -55,6 +55,18 @@  New Features
      Also, make sure to start the actual text at the margin.
      =======================================================
 
+* **Added proactive error handling mode for ethdev.**
+
+  Added proactive error handling mode for ethdev, and three event were
+  introduced:
+
+  * Added new event: ``RTE_ETH_EVENT_ERR_RECOVERING`` for the PMD to report
+    that the port is recovering from an error.
+  * Added new event: ``RTE_ETH_EVENT_RECOVER_SUCCESS`` for the PMD to report
+    that the port recover successful from an error.
+  * Added new event: ``RTE_ETH_EVENT_RECOVER_FAILED`` for the PMD to report
+    that the prot recover failed from an error.
+
 
 Removed Items
 -------------
diff --git a/lib/ethdev/rte_ethdev.h b/lib/ethdev/rte_ethdev.h
index 930b0a2fff..d3e81b98a7 100644
--- a/lib/ethdev/rte_ethdev.h
+++ b/lib/ethdev/rte_ethdev.h
@@ -1859,6 +1859,12 @@  enum rte_eth_err_handle_mode {
 	 * application invoke @see rte_eth_dev_reset to recover the port.
 	 */
 	RTE_ETH_ERROR_HANDLE_MODE_PASSIVE,
+	/** Proactive error handling, after the PMD detect that a reset is
+	 * required, the PMD reports @see RTE_ETH_EVENT_ERR_RECOVERING event,
+	 * and do recovery internally, finally, reports the recovery result
+	 * event (@see RTE_ETH_EVENT_RECOVERY_*).
+	 */
+	RTE_ETH_ERROR_HANDLE_MODE_PROACTIVE,
 };
 
 /**
@@ -3944,6 +3950,33 @@  enum rte_eth_event_type {
 	 * @see rte_eth_rx_avail_thresh_set()
 	 */
 	RTE_ETH_EVENT_RX_AVAIL_THRESH,
+	/** Port recovering from a hardware or firmware error.
+	 * If PMD supports proactive error recovery, it should trigger this
+	 * event to notify application that it detected an error and the
+	 * recovery is being started. Upon receiving the event, the application
+	 * should not invoke any control path APIs (such as
+	 * rte_eth_dev_configure/rte_eth_dev_stop...) until receiving
+	 * RTE_ETH_EVENT_RECOVERY_SUCCESS or RTE_ETH_EVENT_RECOVERY_FAILED
+	 * event.
+	 * The PMD will set the data path pointers to dummy functions, and
+	 * re-set the data patch pointers to non-dummy functions before reports
+	 * RTE_ETH_EVENT_RECOVERY_SUCCESS event. It means that the application
+	 * cannot send or receive any packets during this period.
+	 * @note Before the PMD reports the recovery result, the PMD may report
+	 * the RTE_ETH_EVENT_ERR_RECOVERING event again, because a larger error
+	 * may occur during the recovery.
+	 */
+	RTE_ETH_EVENT_ERR_RECOVERING,
+	/** Port recovers successful from the error.
+	 * The PMD already re-configures the port to the state prior to the
+	 * error.
+	 */
+	RTE_ETH_EVENT_RECOVERY_SUCCESS,
+	/** Port recovers failed from the error.
+	 * It means that the port should not usable anymore. The application
+	 * should close the port.
+	 */
+	RTE_ETH_EVENT_RECOVERY_FAILED,
 	RTE_ETH_EVENT_MAX       /**< max value of this enum */
 };