Merge tag 'amd-drm-next-6.5-2023-06-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.5-2023-06-02:

amdgpu:
- SR-IOV fixes
- Warning fixes
- Misc code cleanups and spelling fixes
- DCN 3.2 updates
- Improved DC FAMS support for better power management
- Improved DC SubVP support for better power management
- DCN 3.1.x fixes
- Max IB size query
- DC GPU reset fixes
- RAS updates
- DCN 3.0.x fixes
- S/G display fixes
- CP shadow buffer support
- Implement connector force callback
- Z8 power improvements
- PSP 13.0.10 vbflash support
- Mode2 reset fixes
- Store MQDs in VRAM to improve queue switch latency
- VCN 3.x fixes
- JPEG 3.x fixes
- Enable DC_FP on LoongArch
- GFXOFF fixes
- GC 9.4.3 partition support
- SDMA 4.4.2 partition support
- VCN/JPEG 4.0.3 partition support
- VCN 4.0.3 updates
- NBIO 7.9 updates
- GC 9.4.3 updates
- Take NUMA into account when allocating memory
- Handle NUMA for partitions
- SMU 13.0.6 updates
- GC 9.4.3 RAS updates
- Stop including unused swiotlb.h
- SMU 13.0.7 fixes
- Fix clock output ordering on some APUs
- Clean up DC FPGA code
- GFX9 preemption fixes
- Misc irq fixes
- S0ix fixes
- Add new DRM_AMDGPU_WERROR config parameter to help with CI
- PCIe fix for RDNA2
- kdoc fixes
- Documentation updates

amdkfd:
- Query TTM mem limit rather than hardcoding it
- GC 9.4.3 partition support
- Handle NUMA for partitions

radeon:
- Fix possible double free
- Stop including unused swiotlb.h
- Fix possible division by zero

ttm:
- Add query for TTM mem limit
- Add NUMA awareness to pools
- Export ttm_pool_fini()

UAPI:
- Add new ctx query flag to better handle GPU resets
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22290
- Add new interface to query and set shadow buffer for RDNA3
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21986
- Add new INFO query for max IB size
  Proposed userspace: https://gitlab.freedesktop.org/bnieuwenhuizen/mesa/-/commits/ib-rejection-v3

amd-drm-next-6.5-2023-06-09:

amdgpu:
- S0ix fixes
- Initial SMU13 Overdrive support
- kdoc fixes
- Misc clode cleanups
- Flexible array fixes
- Display OTG fixes
- SMU 13.0.6 updates
- Revert some broken clock counter updates
- Misc display fixes
- GFX9 preemption fixes
- Add support for newer EEPROM bad page table format
- Add missing radeon secondary id
- Add support for new colorspace KMS API
- CSA fix
- Stable pstate fixes for APUs
- make vbl interface admin only
- Handle PCI accelerator class

amdkfd:
- Add debugger support for gdb

radeon:
- Fix possible UAF

drm:
- Add Colorspace functionality

UAPI:
- Add debugger interface for enabling gdb
  Proposed userspace: https://github.com/ROCm-Developer-Tools/ROCdbgapi/tree/wip-dbgapi
- Add KMS colorspace API
  Discussion: https://lists.freedesktop.org/archives/dri-devel/2023-June/408128.html

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230609174817.7764-1-alexander.deucher@amd.com

3 files changed, 18 insertions, 7 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c
index a352c703e258..ccb4ad78f667 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c
@@ -674,10 +674,19 @@ void dcn30_fpu_update_bw_bounding_box(struct dc *dc,
 }
 
 /**
- * Finds dummy_latency_index when MCLK switching using firmware based
- * vblank stretch is enabled. This function will iterate through the
- * table of dummy pstate latencies until the lowest value that allows
+ * dcn30_find_dummy_latency_index_for_fw_based_mclk_switch() - Finds
+ * dummy_latency_index when MCLK switching using firmware based vblank stretch
+ * is enabled. This function will iterate through the table of dummy pstate
+ * latencies until the lowest value that allows
  * dm_allow_self_refresh_and_mclk_switch to happen is found
+ *
+ * @dc: Current DC state
+ * @context: new dc state
+ * @pipes: DML pipe params
+ * @pipe_cnt: number of DML pipes
+ * @vlevel: Voltage level calculated by DML
+ *
+ * Return: lowest dummy_latency_index value
  */
 int dcn30_find_dummy_latency_index_for_fw_based_mclk_switch(struct dc *dc,
 							    struct dc_state *context,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
index 7d0626e42ea6..9af1a43c042b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
@@ -4939,8 +4939,8 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					}
 					v->TotImmediateFlipBytes = 0.0;
 					for (k = 0; k <= v->NumberOfActivePlanes - 1; k++) {
-						v->TotImmediateFlipBytes = v->TotImmediateFlipBytes + v->NoOfDPP[i][j][k] * v->PDEAndMetaPTEBytesPerFrame[i][j][k]
-								+ v->MetaRowBytes[i][j][k] + v->DPTEBytesPerRow[i][j][k];
+						v->TotImmediateFlipBytes = v->TotImmediateFlipBytes + v->NoOfDPP[i][j][k] * (v->PDEAndMetaPTEBytesPerFrame[i][j][k]
+								+ v->MetaRowBytes[i][j][k] + v->DPTEBytesPerRow[i][j][k]);
 					}
 
 					for (k = 0; k <= v->NumberOfActivePlanes - 1; k++) {
@@ -5130,7 +5130,7 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 			ViewportExceedsSurface = true;
 
 		if (v->SourcePixelFormat[k] != dm_444_64 && v->SourcePixelFormat[k] != dm_444_32 && v->SourcePixelFormat[k] != dm_444_16
-				&& v->SourcePixelFormat[k] != dm_444_8 && v->SourcePixelFormat[k] != dm_rgbe) {
+				&& v->SourcePixelFormat[k] != dm_444_16 && v->SourcePixelFormat[k] != dm_444_8 && v->SourcePixelFormat[k] != dm_rgbe) {
 			if (v->ViewportWidthChroma[k] > v->SurfaceWidthC[k] || v->ViewportHeightChroma[k] > v->SurfaceHeightC[k]) {
 				ViewportExceedsSurface = true;
 			}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c
index cd3cfcb2a2b0..0497a5d74a62 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c
@@ -980,7 +980,7 @@ static void dml_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib,
 
 	unsigned int vstartup_start = 0;
 	unsigned int dst_x_after_scaler = 0;
-	unsigned int dst_y_after_scaler = 0;
+	int dst_y_after_scaler = 0;
 	double line_wait = 0;
 	double dst_y_prefetch = 0;
 	double dst_y_per_vm_vblank = 0;
@@ -1171,6 +1171,8 @@ static void dml_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib,
 
 	dst_x_after_scaler = get_dst_x_after_scaler(mode_lib, e2e_pipe_param, num_pipes, pipe_idx);
 	dst_y_after_scaler = get_dst_y_after_scaler(mode_lib, e2e_pipe_param, num_pipes, pipe_idx);
+	if (dst_y_after_scaler < 0)
+		dst_y_after_scaler = 0;
 
 	// do some adjustment on the dst_after scaler to account for odm combine mode
 	dml_print("DML_DLG: %s: input dst_x_after_scaler                     = %d\n",