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.

Changes in v2:
	- Addressed issue found in https://patchwork.ozlabs.org/patch/1030545/
	  The change was done be removing the enum and passing a boolean to
	  the related functions.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 26 insertions, 4 deletions

diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index 5f818fda96bd..35170f74ed80 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -763,6 +763,7 @@ struct qed_probe_params {
 	u32 dp_module;
 	u8 dp_level;
 	bool is_vf;
+	bool recov_in_prog;
 };
 
 #define QED_DRV_VER_STR_SIZE 12
@@ -809,6 +810,7 @@ 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 {
 			       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.
  *
  * @param cdev
diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h
index 9904617a9730..5a00c7a473bf 100644
--- a/include/linux/qed/qede_rdma.h
+++ b/include/linux/qed/qede_rdma.h
@@ -74,21 +74,23 @@ 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, bool recovery);
 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, bool recovery);
 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,
+				    bool recovery)
 {
 	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,
+					bool recovery) {}
 static inline void qede_rdma_event_changeaddr(struct qede_dev *edr) {}
 #endif
 #endif