Merge branch 'devlink-Add-support-for-region-access'

Alex Vesker says:

====================
devlink: Add support for region access

This is a proposal which will allow access to driver defined address
regions using devlink. Each device can create its supported address
regions and register them. A device which exposes a region will allow
access to it using devlink.

The suggested implementation will allow exposing regions to the user,
reading and dumping snapshots taken from different regions.
A snapshot represents a memory image of a region taken by the driver.

If a device collects a snapshot of an address region it can be later
exposed using devlink region read or dump commands.
This functionality allows for future analyses on the snapshots to be
done.

The major benefit of this support is not only to provide access to
internal address regions which were inaccessible to the user but also
to provide an additional way to debug complex error states using the
region snapshots.

Implemented commands:
$ devlink region help
$ devlink region show [ DEV/REGION ]
$ devlink region del DEV/REGION snapshot SNAPSHOT_ID
$ devlink region dump DEV/REGION [ snapshot SNAPSHOT_ID ]
$ devlink region read DEV/REGION [ snapshot SNAPSHOT_ID ]
	address ADDRESS length length

Show all of the exposed regions with region sizes:
$ devlink region show
pci/0000:00:05.0/cr-space: size 1048576 snapshot [1 2]
pci/0000:00:05.0/fw-health: size 64 snapshot [1 2]

Delete a snapshot using:
$ devlink region del pci/0000:00:05.0/cr-space snapshot 1

Dump a snapshot:
$ devlink region dump pci/0000:00:05.0/fw-health snapshot 1
0000000000000000 0014 95dc 0014 9514 0035 1670 0034 db30
0000000000000010 0000 0000 ffff ff04 0029 8c00 0028 8cc8
0000000000000020 0016 0bb8 0016 1720 0000 0000 c00f 3ffc
0000000000000030 bada cce5 bada cce5 bada cce5 bada cce5

Read a specific part of a snapshot:
$ devlink region read pci/0000:00:05.0/fw-health snapshot 1 address 0
	length 16
0000000000000000 0014 95dc 0014 9514 0035 1670 0034 db30

For more information you can check devlink-region.8 man page

Future:
There is a plan to extend the support to include a write command
as well as performing read and dump live region

v1->v2:
-Add a parameter to enable devlink region snapshot
-Allocate snapshot memory using kvmalloc
-Introduce destructor function devlink_snapshot_data_dest_t to avoid
 double allocation

v2->v3:
-Fix incorrect comment in devlink.h for DEVLINK_ATTR_REGION_SIZE
 from u32 to u64
====================

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

3 files changed, 73 insertions, 0 deletions

diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 122e7e9d3091..dca6ab4eaa99 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -630,6 +630,7 @@ struct mlx4_caps {
 	u32			vf_caps;
 	bool			wol_port[MLX4_MAX_PORTS + 1];
 	struct mlx4_rate_limit_caps rl_caps;
+	u32			health_buffer_addrs;
 };
 
 struct mlx4_buf_list {
@@ -851,6 +852,12 @@ struct mlx4_vf_dev {
 	u8			n_ports;
 };
 
+struct mlx4_fw_crdump {
+	bool snapshot_enable;
+	struct devlink_region *region_crspace;
+	struct devlink_region *region_fw_health;
+};
+
 enum mlx4_pci_status {
 	MLX4_PCI_STATUS_DISABLED,
 	MLX4_PCI_STATUS_ENABLED,
@@ -871,6 +878,7 @@ struct mlx4_dev_persistent {
 	u8	interface_state;
 	struct mutex		pci_status_mutex; /* sync pci state */
 	enum mlx4_pci_status	pci_status;
+	struct mlx4_fw_crdump	crdump;
 };
 
 struct mlx4_dev {
diff --git a/include/net/devlink.h b/include/net/devlink.h
index f67c29cede15..b9b89d6604d4 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -28,6 +28,8 @@ struct devlink {
 	struct list_head dpipe_table_list;
 	struct list_head resource_list;
 	struct list_head param_list;
+	struct list_head region_list;
+	u32 snapshot_id;
 	struct devlink_dpipe_headers *dpipe_headers;
 	const struct devlink_ops *ops;
 	struct device *dev;
@@ -359,6 +361,7 @@ enum devlink_param_generic_id {
 	DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
 	DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
 	DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV,
+	DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
 
 	/* add new param generic ids above here*/
 	__DEVLINK_PARAM_GENERIC_ID_MAX,
@@ -374,6 +377,9 @@ enum devlink_param_generic_id {
 #define DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME "enable_sriov"
 #define DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE DEVLINK_PARAM_TYPE_BOOL
 
+#define DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME "region_snapshot_enable"
+#define DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE DEVLINK_PARAM_TYPE_BOOL
+
 #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate)	\
 {									\
 	.id = DEVLINK_PARAM_GENERIC_ID_##_id,				\
@@ -397,6 +403,10 @@ enum devlink_param_generic_id {
 	.validate = _validate,						\
 }
 
+struct devlink_region;
+
+typedef void devlink_snapshot_data_dest_t(const void *data);
+
 struct devlink_ops {
 	int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack);
 	int (*port_type_set)(struct devlink_port *devlink_port,
@@ -543,6 +553,15 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
 int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
 				       union devlink_param_value init_val);
 void devlink_param_value_changed(struct devlink *devlink, u32 param_id);
+struct devlink_region *devlink_region_create(struct devlink *devlink,
+					     const char *region_name,
+					     u32 region_max_snapshots,
+					     u64 region_size);
+void devlink_region_destroy(struct devlink_region *region);
+u32 devlink_region_shapshot_id_get(struct devlink *devlink);
+int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len,
+				   u8 *data, u32 snapshot_id,
+				   devlink_snapshot_data_dest_t *data_destructor);
 
 #else
 
@@ -770,6 +789,34 @@ devlink_param_value_changed(struct devlink *devlink, u32 param_id)
 {
 }
 
+static inline struct devlink_region *
+devlink_region_create(struct devlink *devlink,
+		      const char *region_name,
+		      u32 region_max_snapshots,
+		      u64 region_size)
+{
+	return NULL;
+}
+
+static inline void
+devlink_region_destroy(struct devlink_region *region)
+{
+}
+
+static inline u32
+devlink_region_shapshot_id_get(struct devlink *devlink)
+{
+	return 0;
+}
+
+static inline int
+devlink_region_snapshot_create(struct devlink_region *region, u64 data_len,
+			       u8 *data, u32 snapshot_id,
+			       devlink_snapshot_data_dest_t *data_destructor)
+{
+	return 0;
+}
+
 #endif
 
 #endif /* _NET_DEVLINK_H_ */
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 68641fb56654..79407bbd296d 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -83,6 +83,12 @@ enum devlink_command {
 	DEVLINK_CMD_PARAM_NEW,
 	DEVLINK_CMD_PARAM_DEL,
 
+	DEVLINK_CMD_REGION_GET,
+	DEVLINK_CMD_REGION_SET,
+	DEVLINK_CMD_REGION_NEW,
+	DEVLINK_CMD_REGION_DEL,
+	DEVLINK_CMD_REGION_READ,
+
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -262,6 +268,18 @@ enum devlink_attr {
 	DEVLINK_ATTR_PARAM_VALUE_DATA,		/* dynamic */
 	DEVLINK_ATTR_PARAM_VALUE_CMODE,		/* u8 */
 
+	DEVLINK_ATTR_REGION_NAME,               /* string */
+	DEVLINK_ATTR_REGION_SIZE,               /* u64 */
+	DEVLINK_ATTR_REGION_SNAPSHOTS,          /* nested */
+	DEVLINK_ATTR_REGION_SNAPSHOT,           /* nested */
+	DEVLINK_ATTR_REGION_SNAPSHOT_ID,        /* u32 */
+
+	DEVLINK_ATTR_REGION_CHUNKS,             /* nested */
+	DEVLINK_ATTR_REGION_CHUNK,              /* nested */
+	DEVLINK_ATTR_REGION_CHUNK_DATA,         /* binary */
+	DEVLINK_ATTR_REGION_CHUNK_ADDR,         /* u64 */
+	DEVLINK_ATTR_REGION_CHUNK_LEN,          /* u64 */
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,