Merge branch 'drm-next-5.2' of git://people.freedesktop.org/~agd5f/linux into drm-next

amdgpu:
- Switch to HMM for userptr (reverted until HMM fixes land)
- New experimental SMU 11 replacement for powerplay for vega20 (not enabled by default)
- Initial RAS support for vega20
- BACO support for vega12
- BACO fixes for vega20
- Rework IH handling for page fault and retry interrupts
- Cleanly split CPU and GPU paths for GPUVM updates
- Powerplay fixes
- XGMI fixes
- Rework how DC interacts with atomic for planes
- Clean up and simplify DC/Powerplay interfaces
- Misc cleanups and bug fixes

amdkfd:
- Switch to HMM for userptr (reverted until HMM fixes land)
- Add initial RAS support
- MQD fixes

ttm:
- Unify DRM_FILE_PAGE_OFFSET handling
- Account for kernel allocations in kernel zone only
- Misc cleanups

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190402170820.22197-1-alexander.deucher@amd.com

2 files changed, 46 insertions, 1 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 4a53f6cfa034..e3a97da4add9 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -210,6 +210,9 @@ union drm_amdgpu_bo_list {
 #define AMDGPU_CTX_QUERY2_FLAGS_VRAMLOST (1<<1)
 /* indicate some job from this context once cause gpu hang */
 #define AMDGPU_CTX_QUERY2_FLAGS_GUILTY   (1<<2)
+/* indicate some errors are detected by RAS */
+#define AMDGPU_CTX_QUERY2_FLAGS_RAS_CE   (1<<3)
+#define AMDGPU_CTX_QUERY2_FLAGS_RAS_UE   (1<<4)
 
 /* Context priority level */
 #define AMDGPU_CTX_PRIORITY_UNSET       -2048
@@ -680,6 +683,7 @@ struct drm_amdgpu_cs_chunk_data {
 	#define AMDGPU_INFO_FW_GFX_RLC_RESTORE_LIST_SRM_MEM 0x11
 	/* Subquery id: Query DMCU firmware version */
 	#define AMDGPU_INFO_FW_DMCU		0x12
+	#define AMDGPU_INFO_FW_TA		0x13
 /* number of bytes moved for TTM migration */
 #define AMDGPU_INFO_NUM_BYTES_MOVED		0x0f
 /* the used VRAM size */
@@ -733,6 +737,37 @@ struct drm_amdgpu_cs_chunk_data {
 /* Number of VRAM page faults on CPU access. */
 #define AMDGPU_INFO_NUM_VRAM_CPU_PAGE_FAULTS	0x1E
 #define AMDGPU_INFO_VRAM_LOST_COUNTER		0x1F
+/* query ras mask of enabled features*/
+#define AMDGPU_INFO_RAS_ENABLED_FEATURES	0x20
+
+/* RAS MASK: UMC (VRAM) */
+#define AMDGPU_INFO_RAS_ENABLED_UMC			(1 << 0)
+/* RAS MASK: SDMA */
+#define AMDGPU_INFO_RAS_ENABLED_SDMA			(1 << 1)
+/* RAS MASK: GFX */
+#define AMDGPU_INFO_RAS_ENABLED_GFX			(1 << 2)
+/* RAS MASK: MMHUB */
+#define AMDGPU_INFO_RAS_ENABLED_MMHUB			(1 << 3)
+/* RAS MASK: ATHUB */
+#define AMDGPU_INFO_RAS_ENABLED_ATHUB			(1 << 4)
+/* RAS MASK: PCIE */
+#define AMDGPU_INFO_RAS_ENABLED_PCIE			(1 << 5)
+/* RAS MASK: HDP */
+#define AMDGPU_INFO_RAS_ENABLED_HDP			(1 << 6)
+/* RAS MASK: XGMI */
+#define AMDGPU_INFO_RAS_ENABLED_XGMI			(1 << 7)
+/* RAS MASK: DF */
+#define AMDGPU_INFO_RAS_ENABLED_DF			(1 << 8)
+/* RAS MASK: SMN */
+#define AMDGPU_INFO_RAS_ENABLED_SMN			(1 << 9)
+/* RAS MASK: SEM */
+#define AMDGPU_INFO_RAS_ENABLED_SEM			(1 << 10)
+/* RAS MASK: MP0 */
+#define AMDGPU_INFO_RAS_ENABLED_MP0			(1 << 11)
+/* RAS MASK: MP1 */
+#define AMDGPU_INFO_RAS_ENABLED_MP1			(1 << 12)
+/* RAS MASK: FUSE */
+#define AMDGPU_INFO_RAS_ENABLED_FUSE			(1 << 13)
 
 #define AMDGPU_INFO_MMR_SE_INDEX_SHIFT	0
 #define AMDGPU_INFO_MMR_SE_INDEX_MASK	0xff
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index e622fd1fbd46..dc067ed0b72d 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -211,6 +211,11 @@ struct kfd_ioctl_dbg_wave_control_args {
 #define KFD_HW_EXCEPTION_GPU_HANG	0
 #define KFD_HW_EXCEPTION_ECC		1
 
+/* For kfd_hsa_memory_exception_data.ErrorType */
+#define KFD_MEM_ERR_NO_RAS		0
+#define KFD_MEM_ERR_SRAM_ECC		1
+#define KFD_MEM_ERR_POISON_CONSUMED	2
+#define KFD_MEM_ERR_GPU_HANG		3
 
 struct kfd_ioctl_create_event_args {
 	__u64 event_page_offset;	/* from KFD */
@@ -250,7 +255,12 @@ struct kfd_hsa_memory_exception_data {
 	struct kfd_memory_exception_failure failure;
 	__u64 va;
 	__u32 gpu_id;
-	__u32 pad;
+	__u32 ErrorType; /* 0 = no RAS error,
+			  * 1 = ECC_SRAM,
+			  * 2 = Link_SYNFLOOD (poison),
+			  * 3 = GPU hang (not attributable to a specific cause),
+			  * other values reserved
+			  */
 };
 
 /* hw exception data */