Merge tag 'amd-drm-next-6.11-2024-06-07' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.11-2024-06-07:

amdgpu:
- DCN 4.0.x support
- DCN 3.5 updates
- GC 12.0 support
- DP MST fixes
- Cursor fixes
- MES11 updates
- MMHUB 4.1 support
- DML2 Updates
- DCN 3.1.5 fixes
- IPS fixes
- Various code cleanups
- GMC 12.0 support
- SDMA 7.0 support
- SMU 13 updates
- SR-IOV fixes
- VCN 5.x fixes
- MES12 support
- SMU 14.x updates
- Devcoredump improvements
- Fixes for HDP flush on platforms with >4k pages
- GC 9.4.3 fixes
- RAS ACA updates
- Silence UBSAN flex array warnings
- MMHUB 3.3 updates

amdkfd:
- Contiguous VRAM allocations
- GC 12.0 support
- SDMA 7.0 support
- SR-IOV fixes

radeon:
- Backlight workaround for iMac
- Silence UBSAN flex array warnings

UAPI:
- GFX12 modifier and DCC support
  Proposed Mesa changes:
  https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29510
- KFD GFX ALU exceptions
  Proposed ROCdebugger changes:
  https://github.com/ROCm/ROCdbgapi/commit/08c760622b6601abf906f75abbc5e21d9fd425df
  https://github.com/ROCm/ROCgdb/commit/944fe1c1414a68700414e86e32273b6bfa62ba6f
- KFD Contiguous VRAM allocation flag
  Proposed ROCr/HIP changes:
  https://github.com/ROCm/ROCT-Thunk-Interface/commit/f7b4a269914a3ab4f1e2453c2879adb97b5cc9e5
  https://github.com/ROCm/ROCR-Runtime/pull/214/commits/26e8530d05a775872cb06dde6693db72be0c454a
  https://github.com/ROCm/clr/commit/1d48f2a1ab38b632919c4b7274899b3faf4279ff

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240607195900.902537-1-alexander.deucher@amd.com

2 files changed, 34 insertions, 1 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 96e32dafd4f0..e44362e74fa1 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -171,6 +171,8 @@ extern "C" {
  * may override the MTYPE selected in AMDGPU_VA_OP_MAP.
  */
 #define AMDGPU_GEM_CREATE_EXT_COHERENT		(1 << 15)
+/* Set PTE.D and recompress during GTT->VRAM moves according to TILING flags. */
+#define AMDGPU_GEM_CREATE_GFX12_DCC		(1 << 16)
 
 struct drm_amdgpu_gem_create_in  {
 	/** the requested memory size */
@@ -392,7 +394,7 @@ struct drm_amdgpu_gem_userptr {
 #define AMDGPU_TILING_NUM_BANKS_SHIFT			21
 #define AMDGPU_TILING_NUM_BANKS_MASK			0x3
 
-/* GFX9 and later: */
+/* GFX9 - GFX11: */
 #define AMDGPU_TILING_SWIZZLE_MODE_SHIFT		0
 #define AMDGPU_TILING_SWIZZLE_MODE_MASK			0x1f
 #define AMDGPU_TILING_DCC_OFFSET_256B_SHIFT		5
@@ -406,6 +408,17 @@ struct drm_amdgpu_gem_userptr {
 #define AMDGPU_TILING_SCANOUT_SHIFT			63
 #define AMDGPU_TILING_SCANOUT_MASK			0x1
 
+/* GFX12 and later: */
+#define AMDGPU_TILING_GFX12_SWIZZLE_MODE_SHIFT			0
+#define AMDGPU_TILING_GFX12_SWIZZLE_MODE_MASK			0x7
+/* These are DCC recompression setting for memory management: */
+#define AMDGPU_TILING_GFX12_DCC_MAX_COMPRESSED_BLOCK_SHIFT	3
+#define AMDGPU_TILING_GFX12_DCC_MAX_COMPRESSED_BLOCK_MASK	0x3 /* 0:64B, 1:128B, 2:256B */
+#define AMDGPU_TILING_GFX12_DCC_NUMBER_TYPE_SHIFT		5
+#define AMDGPU_TILING_GFX12_DCC_NUMBER_TYPE_MASK		0x7 /* CB_COLOR0_INFO.NUMBER_TYPE */
+#define AMDGPU_TILING_GFX12_DCC_DATA_FORMAT_SHIFT		8
+#define AMDGPU_TILING_GFX12_DCC_DATA_FORMAT_MASK		0x3f /* [0:4]:CB_COLOR0_INFO.FORMAT, [5]:MM */
+
 /* Set/Get helpers for tiling flags. */
 #define AMDGPU_TILING_SET(field, value) \
 	(((__u64)(value) & AMDGPU_TILING_##field##_MASK) << AMDGPU_TILING_##field##_SHIFT)
@@ -1268,6 +1281,7 @@ struct drm_amdgpu_info_gpuvm_fault {
 #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 */
+#define AMDGPU_FAMILY_GC_12_0_0			152 /* GC 12.0.0 */
 
 #if defined(__cplusplus)
 }
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 84d502e42961..d0063ac6e09f 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -1476,6 +1476,7 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
 #define AMD_FMT_MOD_TILE_VER_GFX10 2
 #define AMD_FMT_MOD_TILE_VER_GFX10_RBPLUS 3
 #define AMD_FMT_MOD_TILE_VER_GFX11 4
+#define AMD_FMT_MOD_TILE_VER_GFX12 5
 
 /*
  * 64K_S is the same for GFX9/GFX10/GFX10_RBPLUS and hence has GFX9 as canonical
@@ -1486,6 +1487,8 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
 /*
  * 64K_D for non-32 bpp is the same for GFX9/GFX10/GFX10_RBPLUS and hence has
  * GFX9 as canonical version.
+ *
+ * 64K_D_2D on GFX12 is identical to 64K_D on GFX11.
  */
 #define AMD_FMT_MOD_TILE_GFX9_64K_D 10
 #define AMD_FMT_MOD_TILE_GFX9_64K_S_X 25
@@ -1493,6 +1496,19 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
 #define AMD_FMT_MOD_TILE_GFX9_64K_R_X 27
 #define AMD_FMT_MOD_TILE_GFX11_256K_R_X 31
 
+/* Gfx12 swizzle modes:
+ *    0 - LINEAR
+ *    1 - 256B_2D  - 2D block dimensions
+ *    2 - 4KB_2D
+ *    3 - 64KB_2D
+ *    4 - 256KB_2D
+ *    5 - 4KB_3D   - 3D block dimensions
+ *    6 - 64KB_3D
+ *    7 - 256KB_3D
+ */
+#define AMD_FMT_MOD_TILE_GFX12_64K_2D 3
+#define AMD_FMT_MOD_TILE_GFX12_256K_2D 4
+
 #define AMD_FMT_MOD_DCC_BLOCK_64B 0
 #define AMD_FMT_MOD_DCC_BLOCK_128B 1
 #define AMD_FMT_MOD_DCC_BLOCK_256B 2
@@ -1524,6 +1540,9 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
 #define AMD_FMT_MOD_DCC_MAX_COMPRESSED_BLOCK_SHIFT 18
 #define AMD_FMT_MOD_DCC_MAX_COMPRESSED_BLOCK_MASK 0x3
 
+#define AMD_FMT_MOD_GFX12_DCC_MAX_COMPRESSED_BLOCK_SHIFT     3
+#define AMD_FMT_MOD_GFX12_DCC_MAX_COMPRESSED_BLOCK_MASK      0x3 /* 0:64B, 1:128B, 2:256B */
+
 /*
  * DCC supports embedding some clear colors directly in the DCC surface.
  * However, on older GPUs the rendering HW ignores the embedded clear color