Merge tag 'drm-amdkfd-next-2018-07-28' of git://people.freedesktop.org/~gabbayo/linux into drm-next

This is amdkfd pull for 4.19. The major changes are:

- Add Raven support. Raven refers to Ryzen APUs with integrated GFXv9 GPU.
- Integrate GPU reset support

In addition, there are a couple of small fixes and improvements, such as:

- Better handling and reporting to user of VM faults
- Fix race upon context restore
- Allow the user to use specific Compute Units
- Basic power management

Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180728122306.GA5235@ogabbay-vm

1 files changed, 30 insertions, 3 deletions

diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index b4f5073dbac2..01674b56e14f 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -76,6 +76,12 @@ struct kfd_ioctl_update_queue_args {
         __u32 queue_priority;   /* to KFD */
 };
 
+struct kfd_ioctl_set_cu_mask_args {
+        __u32 queue_id;         /* to KFD */
+        __u32 num_cu_mask;              /* to KFD */
+        __u64 cu_mask_ptr;              /* to KFD */
+};
+
 /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */
 #define KFD_IOC_CACHE_POLICY_COHERENT 0
 #define KFD_IOC_CACHE_POLICY_NONCOHERENT 1
@@ -189,6 +195,15 @@ struct kfd_ioctl_dbg_wave_control_args {
 
 #define KFD_SIGNAL_EVENT_LIMIT                  4096
 
+/* For kfd_event_data.hw_exception_data.reset_type. */
+#define KFD_HW_EXCEPTION_WHOLE_GPU_RESET        0
+#define KFD_HW_EXCEPTION_PER_ENGINE_RESET       1
+
+/* For kfd_event_data.hw_exception_data.reset_cause. */
+#define KFD_HW_EXCEPTION_GPU_HANG       0
+#define KFD_HW_EXCEPTION_ECC            1
+
+
 struct kfd_ioctl_create_event_args {
         __u64 event_page_offset;        /* from KFD */
         __u32 event_trigger_data;       /* from KFD - signal events only */
@@ -219,7 +234,7 @@ struct kfd_memory_exception_failure {
         __u32 NotPresent;       /* Page not present or supervisor privilege */
         __u32 ReadOnly; /* Write access to a read-only page */
         __u32 NoExecute;        /* Execute access to a page marked NX */
-        __u32 pad;
+        __u32 imprecise;        /* Can't determine the  exact fault address */
 };
 
 /* memory exception data*/
@@ -230,10 +245,19 @@ struct kfd_hsa_memory_exception_data {
         __u32 pad;
 };
 
-/* Event data*/
+/* hw exception data */
+struct kfd_hsa_hw_exception_data {
+        uint32_t reset_type;
+        uint32_t reset_cause;
+        uint32_t memory_lost;
+        uint32_t gpu_id;
+};
+
+/* Event data */
 struct kfd_event_data {
         union {
                 struct kfd_hsa_memory_exception_data memory_exception_data;
+                struct kfd_hsa_hw_exception_data hw_exception_data;
         };                              /* From KFD */
         __u64 kfd_event_data_ext;       /* pointer to an extension structure
                                            for future exception types */
@@ -448,7 +472,10 @@ struct kfd_ioctl_unmap_memory_from_gpu_args {
 #define AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU        \
                 AMDKFD_IOWR(0x19, struct kfd_ioctl_unmap_memory_from_gpu_args)
 
+#define AMDKFD_IOC_SET_CU_MASK          \
+                AMDKFD_IOW(0x1A, struct kfd_ioctl_set_cu_mask_args)
+
 #define AMDKFD_COMMAND_START            0x01
-#define AMDKFD_COMMAND_END              0x1A
+#define AMDKFD_COMMAND_END              0x1B
 
 #endif