Merge tag 'amd-drm-next-6.7-2023-10-13' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.7-2023-10-13:

amdgpu:
- DC replay fixes
- Misc code cleanups and spelling fixes
- Documentation updates
- RAS EEPROM Updates
- FRU EEPROM Updates
- IP discovery updates
- SR-IOV fixes
- RAS updates
- DC PQ fixes
- SMU 13.0.6 updates
- GC 11.5 Support
- NBIO 7.11 Support
- GMC 11 Updates
- Reset fixes
- SMU 11.5 Updates
- SMU 13.0 OD support
- Use flexible arrays for bo list handling
- W=1 Fixes
- SubVP fixes
- DPIA fixes
- DCN 3.5 Support
- Devcoredump fixes
- VPE 6.1 support
- VCN 4.0 Updates
- S/G display fixes
- DML fixes
- DML2 Support
- MST fixes
- VRR fixes
- Enable seamless boot in more cases
- Enable content type property for HDMI
- OLED fixes
- Rework and clean up GPUVM TLB flushing
- DC ODM fixes
- DP 2.x fixes
- AGP aperture fixes
- SDMA firmware loading cleanups
- Cyan Skillfish GPU clock counter fix
- GC 11 GART fix
- Cache GPU fault info for userspace queries
- DC cursor check fixes
- eDP fixes
- DC FP handling fixes
- Variable sized array fixes
- SMU 13.0.x fixes
- IB start and size alignment fixes for VCN
- SMU 14 Support
- Suspend and resume sequence rework
- vkms fix

amdkfd:
- GC 11 fixes
- GC 10 fixes
- Doorbell fixes
- CWSR fixes
- SVM fixes
- Clean up GC info enumeration
- Rework memory limit handling
- Coherent memory handling fixes
- Use partial migrations in GPU faults
- TLB flush fixes
- DMA unmap fixes
- GC 9.4.3 fixes
- SQ interrupt fix
- GTT mapping fix
- GC 11.5 Support

radeon:
- Misc code cleanups
- W=1 Fixes
- Fix possible buffer overflow
- Fix possible NULL pointer dereference

UAPI:
- Add EXT_COHERENT memory allocation flags.  These allow for system scope atomics.
  Proposed userspace: https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/pull/88
- Add support for new VPE engine.  This is a memory to memory copy engine with advanced scaling, CSC, and color management features
  Proposed mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25713
- Add INFO IOCTL interface to query GPU faults
  Proposed Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23238
  Proposed libdrm MR: https://gitlab.freedesktop.org/mesa/drm/-/merge_requests/298

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231013175758.1735031-1-alexander.deucher@amd.com

1 files changed, 32 insertions, 4 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index f477eda6a2b8..ad21c613fec8 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -150,7 +150,7 @@ extern "C" {
  */
 #define AMDGPU_GEM_CREATE_DISCARDABLE		(1 << 12)
 /* Flag that BO is shared coherently between multiple devices or CPU threads.
- * May depend on GPU instructions to flush caches explicitly
+ * May depend on GPU instructions to flush caches to system scope explicitly.
  *
  * This influences the choice of MTYPE in the PTEs on GFXv9 and later GPUs and
  * may override the MTYPE selected in AMDGPU_VA_OP_MAP.
@@ -163,6 +163,14 @@ extern "C" {
  * may override the MTYPE selected in AMDGPU_VA_OP_MAP.
  */
 #define AMDGPU_GEM_CREATE_UNCACHED		(1 << 14)
+/* Flag that BO should be coherent across devices when using device-level
+ * atomics. May depend on GPU instructions to flush caches to device scope
+ * explicitly, promoting them to system scope automatically.
+ *
+ * This influences the choice of MTYPE in the PTEs on GFXv9 and later GPUs and
+ * may override the MTYPE selected in AMDGPU_VA_OP_MAP.
+ */
+#define AMDGPU_GEM_CREATE_EXT_COHERENT		(1 << 15)
 
 struct drm_amdgpu_gem_create_in  {
 	/** the requested memory size */
@@ -241,9 +249,9 @@ union drm_amdgpu_bo_list {
 /* unknown cause */
 #define AMDGPU_CTX_UNKNOWN_RESET	3
 
-/* indicate gpu reset occured after ctx created */
+/* indicate gpu reset occurred after ctx created */
 #define AMDGPU_CTX_QUERY2_FLAGS_RESET    (1<<0)
-/* indicate vram lost occured after ctx created */
+/* indicate vram lost occurred after ctx created */
 #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)
@@ -586,7 +594,8 @@ struct drm_amdgpu_gem_va {
  */
 #define AMDGPU_HW_IP_VCN_ENC      7
 #define AMDGPU_HW_IP_VCN_JPEG     8
-#define AMDGPU_HW_IP_NUM          9
+#define AMDGPU_HW_IP_VPE          9
+#define AMDGPU_HW_IP_NUM          10
 
 #define AMDGPU_HW_IP_INSTANCE_MAX_COUNT 1
 
@@ -797,6 +806,8 @@ struct drm_amdgpu_cs_chunk_cp_gfx_shadow {
 	#define AMDGPU_INFO_FW_MES		0x1a
 	/* Subquery id: Query IMU firmware version */
 	#define AMDGPU_INFO_FW_IMU		0x1b
+	/* Subquery id: Query VPE firmware version */
+	#define AMDGPU_INFO_FW_VPE		0x1c
 
 /* number of bytes moved for TTM migration */
 #define AMDGPU_INFO_NUM_BYTES_MOVED		0x0f
@@ -895,6 +906,8 @@ struct drm_amdgpu_cs_chunk_cp_gfx_shadow {
 	#define AMDGPU_INFO_VIDEO_CAPS_ENCODE		1
 /* Query the max number of IBs per gang per submission */
 #define AMDGPU_INFO_MAX_IBS			0x22
+/* query last page fault info */
+#define AMDGPU_INFO_GPUVM_FAULT			0x23
 
 #define AMDGPU_INFO_MMR_SE_INDEX_SHIFT	0
 #define AMDGPU_INFO_MMR_SE_INDEX_MASK	0xff
@@ -1220,6 +1233,20 @@ struct drm_amdgpu_info_video_caps {
 	struct drm_amdgpu_info_video_codec_info codec_info[AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_COUNT];
 };
 
+#define AMDGPU_VMHUB_TYPE_MASK			0xff
+#define AMDGPU_VMHUB_TYPE_SHIFT			0
+#define AMDGPU_VMHUB_TYPE_GFX			0
+#define AMDGPU_VMHUB_TYPE_MM0			1
+#define AMDGPU_VMHUB_TYPE_MM1			2
+#define AMDGPU_VMHUB_IDX_MASK			0xff00
+#define AMDGPU_VMHUB_IDX_SHIFT			8
+
+struct drm_amdgpu_info_gpuvm_fault {
+	__u64 addr;
+	__u32 status;
+	__u32 vmhub;
+};
+
 /*
  * Supported GPU families
  */
@@ -1238,6 +1265,7 @@ struct drm_amdgpu_info_video_caps {
 #define AMDGPU_FAMILY_GC_11_0_1			148 /* GC 11.0.1 */
 #define AMDGPU_FAMILY_GC_10_3_6			149 /* GC 10.3.6 */
 #define AMDGPU_FAMILY_GC_10_3_7			151 /* GC 10.3.7 */
+#define AMDGPU_FAMILY_GC_11_5_0			150 /* GC 11.5.0 */
 
 #if defined(__cplusplus)
 }