Merge branch 'qed-introduce-devlink-health-support'

Igor Russkikh says:

====================
qed: introduce devlink health support

This is a followup implementation after series

https://patchwork.ozlabs.org/project/netdev/cover/[email protected]/

This is an implementation of devlink health infrastructure.

With this we are now able to report HW errors to devlink, and it'll take
its own actions depending on user configuration to capture and store the
dump at the bad moment, and to request the driver to recover the device.

So far we do not differentiate global device failures or specific PCI
function failures. This means that some errors specific to one physical
function will affect an entire device. This is not yet fully designed
and verified, will followup in future.

Solution was verified with artificial HW errors generated, existing
tools for dump analysis could be used.

v7: comments from Jesse and Jakub
 - p2: extra edev check
 - p9: removed extra indents
v6: patch 4: changing serial to board.serial and fw to fw.app
v5: improved patch 4 description
v4:
 - commit message and other fixes after Jiri's comments
 - removed one patch (will send to net)
v3: fix uninit var usage in patch 11
v2: fix #include issue from kbuild test robot.
====================

Signed-off-by: David S. Miller <[email protected]>

1 files changed, 46 insertions, 36 deletions

diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index cd6a5c7e56eb..56fa55841d39 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -21,6 +21,7 @@
 #include <linux/qed/common_hsi.h>
 #include <linux/qed/qed_chain.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
+#include <net/devlink.h>
 
 enum dcbx_protocol_type {
 	DCBX_PROTOCOL_ISCSI,
@@ -779,6 +780,11 @@ enum qed_nvm_flash_cmd {
 	QED_NVM_FLASH_CMD_NVM_MAX,
 };
 
+struct qed_devlink {
+	struct qed_dev *cdev;
+	struct devlink_health_reporter *fw_reporter;
+};
+
 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);
@@ -844,10 +850,9 @@ struct qed_common_ops {
 	struct qed_dev*	(*probe)(struct pci_dev *dev,
 				 struct qed_probe_params *params);
 
-	void		(*remove)(struct qed_dev *cdev);
+	void (*remove)(struct qed_dev *cdev);
 
-	int		(*set_power_state)(struct qed_dev *cdev,
-					   pci_power_t state);
+	int (*set_power_state)(struct qed_dev *cdev, pci_power_t state);
 
 	void (*set_name) (struct qed_dev *cdev, char name[]);
 
@@ -855,50 +860,51 @@ struct qed_common_ops {
 	 * PF params required for the call before slowpath_start is
 	 * documented within the qed_pf_params structure definition.
 	 */
-	void		(*update_pf_params)(struct qed_dev *cdev,
-					    struct qed_pf_params *params);
-	int		(*slowpath_start)(struct qed_dev *cdev,
-					  struct qed_slowpath_params *params);
+	void (*update_pf_params)(struct qed_dev *cdev,
+				 struct qed_pf_params *params);
 
-	int		(*slowpath_stop)(struct qed_dev *cdev);
+	int (*slowpath_start)(struct qed_dev *cdev,
+			      struct qed_slowpath_params *params);
+
+	int (*slowpath_stop)(struct qed_dev *cdev);
 
 	/* Requests to use `cnt' interrupts for fastpath.
 	 * upon success, returns number of interrupts allocated for fastpath.
 	 */
-	int		(*set_fp_int)(struct qed_dev *cdev,
-				      u16 cnt);
+	int (*set_fp_int)(struct qed_dev *cdev, u16 cnt);
 
 	/* Fills `info' with pointers required for utilizing interrupts */
-	int		(*get_fp_int)(struct qed_dev *cdev,
-				      struct qed_int_info *info);
-
-	u32		(*sb_init)(struct qed_dev *cdev,
-				   struct qed_sb_info *sb_info,
-				   void *sb_virt_addr,
-				   dma_addr_t sb_phy_addr,
-				   u16 sb_id,
-				   enum qed_sb_type type);
-
-	u32		(*sb_release)(struct qed_dev *cdev,
-				      struct qed_sb_info *sb_info,
-				      u16 sb_id,
-				      enum qed_sb_type type);
-
-	void		(*simd_handler_config)(struct qed_dev *cdev,
-					       void *token,
-					       int index,
-					       void (*handler)(void *));
-
-	void		(*simd_handler_clean)(struct qed_dev *cdev,
-					      int index);
-	int (*dbg_grc)(struct qed_dev *cdev,
-		       void *buffer, u32 *num_dumped_bytes);
+	int (*get_fp_int)(struct qed_dev *cdev, struct qed_int_info *info);
+
+	u32 (*sb_init)(struct qed_dev *cdev,
+		       struct qed_sb_info *sb_info,
+		       void *sb_virt_addr,
+		       dma_addr_t sb_phy_addr,
+		       u16 sb_id,
+		       enum qed_sb_type type);
+
+	u32 (*sb_release)(struct qed_dev *cdev,
+			  struct qed_sb_info *sb_info,
+			  u16 sb_id,
+			  enum qed_sb_type type);
+
+	void (*simd_handler_config)(struct qed_dev *cdev,
+				    void *token,
+				    int index,
+				    void (*handler)(void *));
+
+	void (*simd_handler_clean)(struct qed_dev *cdev, int index);
+
+	int (*dbg_grc)(struct qed_dev *cdev, void *buffer, u32 *num_dumped_bytes);
 
 	int (*dbg_grc_size)(struct qed_dev *cdev);
 
-	int (*dbg_all_data) (struct qed_dev *cdev, void *buffer);
+	int (*dbg_all_data)(struct qed_dev *cdev, void *buffer);
 
-	int (*dbg_all_data_size) (struct qed_dev *cdev);
+	int (*dbg_all_data_size)(struct qed_dev *cdev);
+
+	int (*report_fatal_error)(struct devlink *devlink,
+				  enum qed_hw_err_type err_type);
 
 /**
  * @brief can_link_change - can the instance change the link or not
@@ -1137,6 +1143,10 @@ struct qed_common_ops {
  *
  */
 	int (*set_grc_config)(struct qed_dev *cdev, u32 cfg_id, u32 val);
+
+	struct devlink* (*devlink_register)(struct qed_dev *cdev);
+
+	void (*devlink_unregister)(struct devlink *devlink);
 };
 
 #define MASK_FIELD(_name, _value) \