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

1 files changed, 17 insertions, 9 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 7b16e8cca86a..aecc2bcea145 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -41,7 +41,9 @@
 #include "amdgpu_aca.h"
 
 MODULE_FIRMWARE("amdgpu/gc_9_4_3_mec.bin");
+MODULE_FIRMWARE("amdgpu/gc_9_4_4_mec.bin");
 MODULE_FIRMWARE("amdgpu/gc_9_4_3_rlc.bin");
+MODULE_FIRMWARE("amdgpu/gc_9_4_4_rlc.bin");
 
 #define GFX9_MEC_HPD_SIZE 4096
 #define RLCG_UCODE_LOADING_START_ADDRESS 0x00002000L
@@ -755,6 +757,7 @@ static int gfx_v9_4_3_gpu_early_init(struct amdgpu_device *adev)
 
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(9, 4, 3):
+	case IP_VERSION(9, 4, 4):
 		adev->gfx.config.max_hw_contexts = 8;
 		adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
 		adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
@@ -1392,21 +1395,23 @@ static int gfx_v9_4_3_rlc_resume(struct amdgpu_device *adev)
 static void gfx_v9_4_3_update_spm_vmid(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 				       unsigned vmid)
 {
-	u32 reg, data;
+	u32 reg, pre_data, data;
 
 	reg = SOC15_REG_OFFSET(GC, GET_INST(GC, 0), regRLC_SPM_MC_CNTL);
-	if (amdgpu_sriov_is_pp_one_vf(adev))
-		data = RREG32_NO_KIQ(reg);
+	if (amdgpu_sriov_is_pp_one_vf(adev) && !amdgpu_sriov_runtime(adev))
+		pre_data = RREG32_NO_KIQ(reg);
 	else
-		data = RREG32(reg);
+		pre_data = RREG32(reg);
 
-	data &= ~RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK;
+	data =	pre_data & (~RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK);
 	data |= (vmid & RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK) << RLC_SPM_MC_CNTL__RLC_SPM_VMID__SHIFT;
 
-	if (amdgpu_sriov_is_pp_one_vf(adev))
-		WREG32_SOC15_NO_KIQ(GC, GET_INST(GC, 0), regRLC_SPM_MC_CNTL, data);
-	else
-		WREG32_SOC15(GC, GET_INST(GC, 0), regRLC_SPM_MC_CNTL, data);
+	if (pre_data != data) {
+		if (amdgpu_sriov_is_pp_one_vf(adev) && !amdgpu_sriov_runtime(adev)) {
+			WREG32_SOC15_NO_KIQ(GC, GET_INST(GC, 0), regRLC_SPM_MC_CNTL, data);
+		} else
+			WREG32_SOC15(GC, GET_INST(GC, 0), regRLC_SPM_MC_CNTL, data);
+	}
 }
 
 static const struct soc15_reg_rlcg rlcg_access_gc_9_4_3[] = {
@@ -2502,6 +2507,7 @@ static int gfx_v9_4_3_set_clockgating_state(void *handle,
 	num_xcc = NUM_XCC(adev->gfx.xcc_mask);
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(9, 4, 3):
+	case IP_VERSION(9, 4, 4):
 		for (i = 0; i < num_xcc; i++)
 			gfx_v9_4_3_xcc_update_gfx_clock_gating(
 				adev, state == AMD_CG_STATE_GATE, i);
@@ -4138,6 +4144,7 @@ static void gfx_v9_4_3_set_gds_init(struct amdgpu_device *adev)
 	/* init asci gds info */
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(9, 4, 3):
+	case IP_VERSION(9, 4, 4):
 		/* 9.4.3 removed all the GDS internal memory,
 		 * only support GWS opcode in kernel, like barrier
 		 * semaphore.etc */
@@ -4150,6 +4157,7 @@ static void gfx_v9_4_3_set_gds_init(struct amdgpu_device *adev)
 
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(9, 4, 3):
+	case IP_VERSION(9, 4, 4):
 		/* deprecated for 9.4.3, no usage at all */
 		adev->gds.gds_compute_max_wave_id = 0;
 		break;