diff options
| author |   Dave Airlie <airlied@redhat.com> | 2022-09-16 17:00:12 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2022-09-16 17:00:13 +1000 |
| commit | e2111ae2c1a6c8dd708243ef631d35a08c8be257 (patch) | |
| tree | ea1cba71eb984b3d78b194cea23cfee9e7a94a82 /drivers/gpu/drm | |
| parent | Linux 6.0-rc5 (diff) | |
| parent | drm/amdgpu: make sure to init common IP before gmc (diff) | |
| download | linux-dev-e2111ae2c1a6c8dd708243ef631d35a08c8be257.tar.xz linux-dev-e2111ae2c1a6c8dd708243ef631d35a08c8be257.zip | |
Merge tag 'amd-drm-fixes-6.0-2022-09-14' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes
amd-drm-fixes-6.0-2022-09-14:
amdgpu:
- BACO fixes for some RDNA2 boards
- PCI AER fixes uncovered by a core PCI change
- Properly hook up dirtyfb helper
- RAS fixes for GC 11.x
- TMR fix
- DCN 3.2.x fixes
- DCN 3.1.4 fixes
- LLVM DML stack size fixes
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220914184030.6145-1-alexander.deucher@amd.com
Diffstat (limited to 'drivers/gpu/drm')
39 files changed, 595 insertions, 834 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 1400abee9f40..be7aff2d4a57 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2365,8 +2365,16 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) } adev->ip_blocks[i].status.sw = true; - /* need to do gmc hw init early so we can allocate gpu mem */ - if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) { + if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON) { + /* need to do common hw init early so everything is set up for gmc */ + r = adev->ip_blocks[i].version->funcs->hw_init((void *)adev); + if (r) { + DRM_ERROR("hw_init %d failed %d\n", i, r); + goto init_failed; + } + adev->ip_blocks[i].status.hw = true; + } else if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) { + /* need to do gmc hw init early so we can allocate gpu mem */ /* Try to reserve bad pages early */ if (amdgpu_sriov_vf(adev)) amdgpu_virt_exchange_data(adev); @@ -3052,8 +3060,8 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev) int i, r; static enum amd_ip_block_type ip_order[] = { - AMD_IP_BLOCK_TYPE_GMC, AMD_IP_BLOCK_TYPE_COMMON, + AMD_IP_BLOCK_TYPE_GMC, AMD_IP_BLOCK_TYPE_PSP, AMD_IP_BLOCK_TYPE_IH, }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index c20922a5af9f..5b09c8f4fe95 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -38,6 +38,7 @@ #include <linux/pci.h> #include <linux/pm_runtime.h> #include <drm/drm_crtc_helper.h> +#include <drm/drm_damage_helper.h> #include <drm/drm_edid.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_fb_helper.h> @@ -496,6 +497,7 @@ bool amdgpu_display_ddc_probe(struct amdgpu_connector *amdgpu_connector, static const struct drm_framebuffer_funcs amdgpu_fb_funcs = { .destroy = drm_gem_fb_destroy, .create_handle = drm_gem_fb_create_handle, + .dirty = drm_atomic_helper_dirtyfb, }; uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 35738db12cd1..c9dec2434f37 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -756,7 +756,7 @@ static int psp_tmr_init(struct psp_context *psp) } pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL; - ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_SIZE(psp->adev), + ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_ALIGNMENT, AMDGPU_GEM_DOMAIN_VRAM, &psp->tmr_bo, &psp->tmr_mc_addr, pptr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h index c32b74bd970f..e593e8c2a54d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h @@ -36,6 +36,7 @@ #define PSP_CMD_BUFFER_SIZE 0x1000 #define PSP_1_MEG 0x100000 #define PSP_TMR_SIZE(adev) ((adev)->asic_type == CHIP_ALDEBARAN ? 0x800000 : 0x400000) +#define PSP_TMR_ALIGNMENT 0x100000 #define PSP_FW_NAME_LEN 0x24 enum psp_shared_mem_size { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index ff5361f5c2d4..12c6f97945a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1811,7 +1811,8 @@ static void amdgpu_ras_log_on_err_counter(struct amdgpu_device *adev) amdgpu_ras_query_error_status(adev, &info); if (adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) && - adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) { + adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4) && + adev->ip_versions[MP0_HWIP][0] != IP_VERSION(13, 0, 0)) { if (amdgpu_ras_reset_error_status(adev, info.head.block)) dev_warn(adev->dev, "Failed to reset error counter and error status"); } diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c index b465baa26762..aa761ff3a5fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c @@ -380,6 +380,7 @@ static void nbio_v2_3_enable_aspm(struct amdgpu_device *adev, WREG32_PCIE(smnPCIE_LC_CNTL, data); } +#ifdef CONFIG_PCIEASPM static void nbio_v2_3_program_ltr(struct amdgpu_device *adev) { uint32_t def, data; @@ -401,9 +402,11 @@ static void nbio_v2_3_program_ltr(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data); } +#endif static void nbio_v2_3_program_aspm(struct amdgpu_device *adev) { +#ifdef CONFIG_PCIEASPM uint32_t def, data; def = data = RREG32_PCIE(smnPCIE_LC_CNTL); @@ -459,7 +462,10 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL6, data); - nbio_v2_3_program_ltr(adev); + /* Don't bother about LTR if LTR is not enabled + * in the path */ + if (adev->pdev->ltr_path) + nbio_v2_3_program_ltr(adev); def = data = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP3); data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT; @@ -483,6 +489,7 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev) data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK; if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL3, data); +#endif } static void nbio_v2_3_apply_lc_spc_mode_wa(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c index f7f6ddebd3e4..37615a77287b 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c @@ -282,6 +282,7 @@ static void nbio_v6_1_init_registers(struct amdgpu_device *adev) mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2; } +#ifdef CONFIG_PCIEASPM static void nbio_v6_1_program_ltr(struct amdgpu_device *adev) { uint32_t def, data; @@ -303,9 +304,11 @@ static void nbio_v6_1_program_ltr(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data); } +#endif static void nbio_v6_1_program_aspm(struct amdgpu_device *adev) { +#ifdef CONFIG_PCIEASPM uint32_t def, data; def = data = RREG32_PCIE(smnPCIE_LC_CNTL); @@ -361,7 +364,10 @@ static void nbio_v6_1_program_aspm(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL6, data); - nbio_v6_1_program_ltr(adev); + /* Don't bother about LTR if LTR is not enabled + * in the path */ + if (adev->pdev->ltr_path) + nbio_v6_1_program_ltr(adev); def = data = RREG32_PCIE(smnRCC_BIF_STRAP3); data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT; @@ -385,6 +391,7 @@ static void nbio_v6_1_program_aspm(struct amdgpu_device *adev) data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK; if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL3, data); +#endif } const struct amdgpu_nbio_funcs nbio_v6_1_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index 11848d1e238b..19455a725939 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -673,6 +673,7 @@ struct amdgpu_nbio_ras nbio_v7_4_ras = { }; +#ifdef CONFIG_PCIEASPM static void nbio_v7_4_program_ltr(struct amdgpu_device *adev) { uint32_t def, data; @@ -694,9 +695,11 @@ static void nbio_v7_4_program_ltr(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data); } +#endif static void nbio_v7_4_program_aspm(struct amdgpu_device *adev) { +#ifdef CONFIG_PCIEASPM uint32_t def, data; if (adev->ip_versions[NBIO_HWIP][0] == IP_VERSION(7, 4, 4)) @@ -755,7 +758,10 @@ static void nbio_v7_4_program_aspm(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL6, data); - nbio_v7_4_program_ltr(adev); + /* Don't bother about LTR if LTR is not enabled + * in the path */ + if (adev->pdev->ltr_path) + nbio_v7_4_program_ltr(adev); def = data = RREG32_PCIE(smnRCC_BIF_STRAP3); data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT; @@ -779,6 +785,7 @@ static void nbio_v7_4_program_aspm(struct amdgpu_device *adev) data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK; if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL3, data); +#endif } const struct amdgpu_nbio_funcs nbio_v7_4_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c index f30bc826a878..def89379b51a 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c @@ -28,6 +28,14 @@ #include "nbio/nbio_7_7_0_sh_mask.h" #include <uapi/linux/kfd_ioctl.h> +static void nbio_v7_7_remap_hdp_registers(struct amdgpu_device *adev) +{ + WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_MEM_FLUSH_CNTL, + adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL); + WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_REG_FLUSH_CNTL, + adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_REG_FLUSH_CNTL); +} + static u32 nbio_v7_7_get_rev_id(struct amdgpu_device *adev) { u32 tmp; @@ -336,4 +344,5 @@ const struct amdgpu_nbio_funcs nbio_v7_7_funcs = { .get_clockgating_state = nbio_v7_7_get_clockgating_state, .ih_control = nbio_v7_7_ih_control, .init_registers = nbio_v7_7_init_registers, + .remap_hdp_registers = nbio_v7_7_remap_hdp_registers, }; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 65181efba50e..56424f75dd2c 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1504,6 +1504,11 @@ static int sdma_v4_0_start(struct amdgpu_device *adev) WREG32_SDMA(i, mmSDMA0_CNTL, temp); if (!amdgpu_sriov_vf(adev)) { + ring = &adev->sdma.instance[i].ring; + adev->nbio.funcs->sdma_doorbell_range(adev, i, + ring->use_doorbell, ring->doorbell_index, + adev->doorbell_index.sdma_doorbell_range); + /* unhalt engine */ temp = RREG32_SDMA(i, mmSDMA0_F32_CNTL); temp = REG_SET_FIELD(temp, SDMA0_F32_CNTL, HALT, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index fde6154f2009..183024d7c184 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1211,25 +1211,6 @@ static int soc15_common_sw_fini(void *handle) return 0; } -static void soc15_doorbell_range_init(struct amdgpu_device *adev) -{ - int i; - struct amdgpu_ring *ring; - - /* sdma/ih doorbell range are programed by hypervisor */ - if (!amdgpu_sriov_vf(adev)) { - for (i = 0; i < adev->sdma.num_instances; i++) { - ring = &adev->sdma.instance[i].ring; - adev->nbio.funcs->sdma_doorbell_range(adev, i, - ring->use_doorbell, ring->doorbell_index, - adev->doorbell_index.sdma_doorbell_range); - } - - adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell, - adev->irq.ih.doorbell_index); - } -} - static int soc15_common_hw_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -1249,12 +1230,6 @@ static int soc15_common_hw_init(void *handle) /* enable the doorbell aperture */ soc15_enable_doorbell_aperture(adev, true); - /* HW doorbell routing policy: doorbell writing not - * in SDMA/IH/MM/ACV range will be routed to CP. So - * we need to init SDMA/IH/MM/ACV doorbell range prior - * to CP ip block init and ring test. - */ - soc15_doorbell_range_init(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 55284b24f113..2e50db3b761e 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -421,6 +421,7 @@ static bool soc21_need_full_reset(struct amdgpu_device *adev) { switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(11, 0, 0): + return amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC); case IP_VERSION(11, 0, 2): return false; default: diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c index 03b7066471f9..1e83db0c5438 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c @@ -289,6 +289,10 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev) } } + if (!amdgpu_sriov_vf(adev)) + adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell, + adev->irq.ih.doorbell_index); + pci_set_master(adev->pdev); /* enable interrupts */ diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c index 2022ffbb8dba..59dfca093155 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c @@ -340,6 +340,10 @@ static int vega20_ih_irq_init(struct amdgpu_device *adev) } } + if (!amdgpu_sriov_vf(adev)) + adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell, + adev->irq.ih.doorbell_index); + pci_set_master(adev->pdev); /* enable interrupts */ diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c index beb025cd3dc2..9781a8dbc238 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c @@ -670,6 +670,8 @@ static void dcn314_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *cl } ASSERT(bw_params->clk_table.entries[i-1].dcfclk_mhz); bw_params->vram_type = bios_info->memory_type; + + bw_params->dram_channel_width_bytes = bios_info->memory_type == 0x22 ? 8 : 4; bw_params->num_channels = bios_info->ma_channel_number ? bios_info->ma_channel_number : 4; for (i = 0; i < WM_SET_COUNT; i++) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index f62d50901d92..0c85ab5933b4 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -329,7 +329,7 @@ bool dc_stream_set_cursor_attributes( dc = stream->ctx->dc; - if (attributes->height * attributes->width * 4 > 16384) + if (dc->debug.allow_sw_cursor_fallback && attributes->height * attributes->width * 4 > 16384) if (stream->mall_stream_config.type == SUBVP_MAIN) return false; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 5908b60db313..dbf8158b832e 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -745,6 +745,7 @@ struct dc_debug_options { bool disable_fixed_vs_aux_timeout_wa; bool force_disable_subvp; bool force_subvp_mclk_switch; + bool allow_sw_cursor_fallback; bool force_usr_allow; /* uses value at boot and disables switch */ bool disable_dtb_ref_clk_switch; diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c index 09b304507bad..52a61b3e5a8b 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c @@ -417,44 +417,42 @@ static void populate_subvp_cmd_drr_info(struct dc *dc, struct dc_crtc_timing *main_timing = &subvp_pipe->stream->timing; struct dc_crtc_timing *phantom_timing = &subvp_pipe->stream->mall_stream_config.paired_stream->timing; struct dc_crtc_timing *drr_timing = &vblank_pipe->stream->timing; - int16_t drr_frame_us = 0; - int16_t min_drr_supported_us = 0; - int16_t max_drr_supported_us = 0; - int16_t max_drr_vblank_us = 0; - int16_t max_drr_mallregion_us = 0; - int16_t mall_region_us = 0; - int16_t prefetch_us = 0; - int16_t subvp_active_us = 0; - int16_t drr_active_us = 0; - int16_t min_vtotal_supported = 0; - int16_t max_vtotal_supported = 0; + uint16_t drr_frame_us = 0; + uint16_t min_drr_supported_us = 0; + uint16_t max_drr_supported_us = 0; + uint16_t max_drr_vblank_us = 0; + uint16_t max_drr_mallregion_us = 0; + uint16_t mall_region_us = 0; + uint16_t prefetch_us = 0; + uint16_t subvp_active_us = 0; + uint16_t drr_active_us = 0; + uint16_t min_vtotal_supported = 0; + uint16_t max_vtotal_supported = 0; pipe_data->pipe_config.vblank_data.drr_info.drr_in_use = true; pipe_data->pipe_config.vblank_data.drr_info.use_ramping = false; // for now don't use ramping pipe_data->pipe_config.vblank_data.drr_info.drr_window_size_ms = 4; // hardcode 4ms DRR window for now - drr_frame_us = div64_s64(drr_timing->v_total * drr_timing->h_total, - (int64_t)(drr_timing->pix_clk_100hz * 100) * 1000000); + drr_frame_us = div64_u64(((uint64_t)drr_timing->v_total * drr_timing->h_total * 1000000), + (((uint64_t)drr_timing->pix_clk_100hz * 100))); // P-State allow width and FW delays already included phantom_timing->v_addressable - mall_region_us = div64_s64(phantom_timing->v_addressable * phantom_timing->h_total, - (int64_t)(phantom_timing->pix_clk_100hz * 100) * 1000000); + mall_region_us = div64_u64(((uint64_t)phantom_timing->v_addressable * phantom_timing->h_total * 1000000), + (((uint64_t)phantom_timing->pix_clk_100hz * 100))); min_drr_supported_us = drr_frame_us + mall_region_us + SUBVP_DRR_MARGIN_US; - min_vtotal_supported = div64_s64(drr_timing->pix_clk_100hz * 100 * - (div64_s64((int64_t)min_drr_supported_us, 1000000)), - (int64_t)drr_timing->h_total); - - prefetch_us = div64_s64((phantom_timing->v_total - phantom_timing->v_front_porch) * phantom_timing->h_total, - (int64_t)(phantom_timing->pix_clk_100hz * 100) * 1000000 + - dc->caps.subvp_prefetch_end_to_mall_start_us); - subvp_active_us = div64_s64(main_timing->v_addressable * main_timing->h_total, - (int64_t)(main_timing->pix_clk_100hz * 100) * 1000000); - drr_active_us = div64_s64(drr_timing->v_addressable * drr_timing->h_total, - (int64_t)(drr_timing->pix_clk_100hz * 100) * 1000000); - max_drr_vblank_us = div64_s64((int64_t)(subvp_active_us - prefetch_us - drr_active_us), 2) + drr_active_us; + min_vtotal_supported = div64_u64(((uint64_t)drr_timing->pix_clk_100hz * 100 * min_drr_supported_us), + (((uint64_t)drr_timing->h_total * 1000000))); + + prefetch_us = div64_u64(((uint64_t)(phantom_timing->v_total - phantom_timing->v_front_porch) * phantom_timing->h_total * 1000000), + (((uint64_t)phantom_timing->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us)); + subvp_active_us = div64_u64(((uint64_t)main_timing->v_addressable * main_timing->h_total * 1000000), + (((uint64_t)main_timing->pix_clk_100hz * 100))); + drr_active_us = div64_u64(((uint64_t)drr_timing->v_addressable * drr_timing->h_total * 1000000), + (((uint64_t)drr_timing->pix_clk_100hz * 100))); + max_drr_vblank_us = div64_u64((subvp_active_us - prefetch_us - drr_active_us), 2) + drr_active_us; max_drr_mallregion_us = subvp_active_us - prefetch_us - mall_region_us; max_drr_supported_us = max_drr_vblank_us > max_drr_mallregion_us ? max_drr_vblank_us : max_drr_mallregion_us; - max_vtotal_supported = div64_s64(drr_timing->pix_clk_100hz * 100 * (div64_s64((int64_t)max_drr_supported_us, 1000000)), - (int64_t)drr_timing->h_total); + max_vtotal_supported = div64_u64(((uint64_t)drr_timing->pix_clk_100hz * 100 * max_drr_supported_us), + (((uint64_t)drr_timing->h_total * 1000000))); pipe_data->pipe_config.vblank_data.drr_info.min_vtotal_supported = min_vtotal_supported; pipe_data->pipe_config.vblank_data.drr_info.max_vtotal_supported = max_vtotal_supported; @@ -548,10 +546,12 @@ static void update_subvp_prefetch_end_to_mall_start(struct dc *dc, struct dc_crtc_timing *phantom_timing1 = &subvp_pipes[1]->stream->mall_stream_config.paired_stream->timing; struct dmub_cmd_fw_assisted_mclk_switch_pipe_data_v2 *pipe_data = NULL; - subvp0_prefetch_us = div64_s64((phantom_timing0->v_total - phantom_timing0->v_front_porch) * phantom_timing0->h_total, - (int64_t)(phantom_timing0->pix_clk_100hz * 100) * 1000000 + dc->caps.subvp_prefetch_end_to_mall_start_us); - subvp1_prefetch_us = div64_s64((phantom_timing1->v_total - phantom_timing1->v_front_porch) * phantom_timing1->h_total, - (int64_t)(phantom_timing1->pix_clk_100hz * 100) * 1000000 + dc->caps.subvp_prefetch_end_to_mall_start_us); + subvp0_prefetch_us = div64_u64(((uint64_t)(phantom_timing0->v_total - phantom_timing0->v_front_porch) * + (uint64_t)phantom_timing0->h_total * 1000000), + (((uint64_t)phantom_timing0->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us)); + subvp1_prefetch_us = div64_u64(((uint64_t)(phantom_timing1->v_total - phantom_timing1->v_front_porch) * + (uint64_t)phantom_timing1->h_total * 1000000), + (((uint64_t)phantom_timing1->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us)); // Whichever SubVP PIPE has the smaller prefetch (including the prefetch end to mall start time) // should increase it's prefetch time to match the other @@ -559,16 +559,17 @@ static void update_subvp_prefetch_end_to_mall_start(struct dc *dc, pipe_data = &cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[1]; prefetch_delta_us = subvp0_prefetch_us - subvp1_prefetch_us; pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines = - div64_s64(((div64_s64((int64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us), 1000000)) * - (phantom_timing1->pix_clk_100hz * 100) + phantom_timing1->h_total - 1), - (int64_t)phantom_timing1->h_total); + div64_u64(((uint64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us) * + ((uint64_t)phantom_timing1->pix_clk_100hz * 100) + ((uint64_t)phantom_timing1->h_total * 1000000 - 1)), + ((uint64_t)phantom_timing1->h_total * 1000000)); + } else if (subvp1_prefetch_us > subvp0_prefetch_us) { pipe_data = &cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[0]; prefetch_delta_us = subvp1_prefetch_us - subvp0_prefetch_us; pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines = - div64_s64(((div64_s64((int64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us), 1000000)) * - (phantom_timing0->pix_clk_100hz * 100) + phantom_timing0->h_total - 1), - (int64_t)phantom_timing0->h_total); + div64_u64(((uint64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us) * + ((uint64_t)phantom_timing0->pix_clk_100hz * 100) + ((uint64_t)phantom_timing0->h_total * 1000000 - 1)), + ((uint64_t)phantom_timing0->h_total * 1000000)); } } @@ -630,13 +631,11 @@ static void populate_subvp_cmd_pipe_info(struct dc *dc, // Round up pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines = - div64_s64(((div64_s64((int64_t)dc->caps.subvp_prefetch_end_to_mall_start_us, 1000000)) * - (phantom_timing->pix_clk_100hz * 100) + phantom_timing->h_total - 1), - (int64_t)phantom_timing->h_total); + div64_u64(((uint64_t)dc->caps.subvp_prefetch_end_to_mall_start_us * ((uint64_t)phantom_timing->pix_clk_100hz * 100) + + ((uint64_t)phantom_timing->h_total * 1000000 - 1)), ((uint64_t)phantom_timing->h_total * 1000000)); pipe_data->pipe_config.subvp_data.processing_delay_lines = - div64_s64(((div64_s64((int64_t)dc->caps.subvp_fw_processing_delay_us, 1000000)) * - (phantom_timing->pix_clk_100hz * 100) + phantom_timing->h_total - 1), - (int64_t)phantom_timing->h_total); + div64_u64(((uint64_t)(dc->caps.subvp_fw_processing_delay_us) * ((uint64_t)phantom_timing->pix_clk_100hz * 100) + + ((uint64_t)phantom_timing->h_total * 1000000 - 1)), ((uint64_t)phantom_timing->h_total * 1000000)); // Find phantom pipe index based on phantom stream for (j = 0; j < dc->res_pool->pipe_count; j++) { struct pipe_ctx *phantom_pipe = &context->res_ctx.pipe_ctx[j]; diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c index e3351ddc566c..06d8638db696 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c @@ -67,8 +67,7 @@ static void enc314_disable_fifo(struct stream_encoder *enc) { struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); - REG_UPDATE_2(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 0, - DIG_FIFO_READ_START_LEVEL, 0); + REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 0); } static void enc314_dp_set_odm_combine( diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c index 6ec1c52535b9..2038cbda33f7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c @@ -103,6 +103,11 @@ void hubp32_cursor_set_attributes( enum cursor_lines_per_chunk lpc = hubp2_get_lines_per_chunk( attr->width, attr->color_format); + //Round cursor width up to next multiple of 64 + uint32_t cursor_width = ((attr->width + 63) / 64) * 64; + uint32_t cursor_height = attr->height; + uint32_t cursor_size = cursor_width * cursor_height; + hubp->curs_attr = *attr; REG_UPDATE(CURSOR_SURFACE_ADDRESS_HIGH, @@ -126,7 +131,24 @@ void hubp32_cursor_set_attributes( /* used to shift the cursor chunk request deadline */ CURSOR0_CHUNK_HDL_ADJUST, 3); - if (attr->width * attr->height * 4 > 16384) + switch (attr->color_format) { + case CURSOR_MODE_MONO: + cursor_size /= 2; + break; + case CURSOR_MODE_COLOR_1BIT_AND: + case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA: + case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA: + cursor_size *= 4; + break; + + case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED: + case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED: + default: + cursor_size *= 8; + break; + } + + if (cursor_size > 16384) REG_UPDATE(DCHUBP_MALL_CONFIG, USE_MALL_FOR_CURSOR, true); else REG_UPDATE(DCHUBP_MALL_CONFIG, USE_MALL_FOR_CURSOR, false); diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index 8d9d96c39808..344fe7535df5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -741,7 +741,29 @@ void dcn32_update_mall_sel(struct dc *dc, struct dc_state *context) struct hubp *hubp = pipe->plane_res.hubp; if (pipe->stream && pipe->plane_state && hubp && hubp->funcs->hubp_update_mall_sel) { - if (hubp->curs_attr.width * hubp->curs_attr.height * 4 > 16384) + //Round cursor width up to next multiple of 64 + int cursor_width = ((hubp->curs_attr.width + 63) / 64) * 64; + int cursor_height = hubp->curs_attr.height; + int cursor_size = cursor_width * cursor_height; + + switch (hubp->curs_attr.color_format) { + case CURSOR_MODE_MONO: + cursor_size /= 2; + break; + case CURSOR_MODE_COLOR_1BIT_AND: + case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA: + case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA: + cursor_size *= 4; + break; + + case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED: + case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED: + default: + cursor_size *= 8; + break; + } + + if (cursor_size > 16384) cache_cursor = true; if (pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) { diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c index 8b887b552f2c..c3b783cea8a0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -871,6 +871,7 @@ static const struct dc_debug_options debug_defaults_drv = { .exit_idle_opt_for_cursor_updates = true, .enable_single_display_2to1_odm_policy = true, .enable_dp_dig_pixel_rate_div_policy = 1, + .allow_sw_cursor_fallback = false, }; static const struct dc_debug_options debug_defaults_diags = { @@ -2039,7 +2040,8 @@ static bool dcn32_resource_construct( dc->caps.max_downscale_ratio = 600; dc->caps.i2c_speed_in_khz = 100; dc->caps.i2c_speed_in_khz_hdcp = 100; /*1.4 w/a applied by default*/ - dc->caps.max_cursor_size = 256; + /* TODO: Bring max_cursor_size back to 256 after subvp cursor corruption is fixed*/ + dc->caps.max_cursor_size = 64; dc->caps.min_horizontal_blanking_period = 80; dc->caps.dmdata_alloc_size = 2048; dc->caps.mall_size_per_mem_channel = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h index 1e7e6201c880..cf15d0e5e9b4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h @@ -30,6 +30,9 @@ #define DCN3_2_DET_SEG_SIZE 64 #define DCN3_2_MALL_MBLK_SIZE_BYTES 65536 // 64 * 1024 +#define DCN3_2_MBLK_WIDTH 128 +#define DCN3_2_MBLK_HEIGHT_4BPE 128 +#define DCN3_2_MBLK_HEIGHT_8BPE 64 #define TO_DCN32_RES_POOL(pool)\ container_of(pool, struct dcn32_resource_pool, base) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c index ab918fe38f6a..1f195c5b3377 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c @@ -46,7 +46,6 @@ uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_state *context) { uint32_t num_ways = 0; - uint32_t mall_region_pixels = 0; uint32_t bytes_per_pixel = 0; uint32_t cache_lines_used = 0; uint32_t lines_per_way = 0; @@ -54,20 +53,64 @@ uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_stat uint32_t bytes_in_mall = 0; uint32_t num_mblks = 0; uint32_t cache_lines_per_plane = 0; - uint32_t i = 0; + uint32_t i = 0, j = 0; + uint32_t mblk_width = 0; + uint32_t mblk_height = 0; + uint32_t full_vp_width_blk_aligned = 0; + uint32_t full_vp_height_blk_aligned = 0; + uint32_t mall_alloc_width_blk_aligned = 0; + uint32_t mall_alloc_height_blk_aligned = 0; + uint32_t full_vp_height = 0; for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; // Find the phantom pipes - if (pipe->stream && pipe->plane_state && !pipe->top_pipe && + if (pipe->stream && pipe->plane_state && !pipe->top_pipe && !pipe->prev_odm_pipe && pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) { - bytes_per_pixel = pipe->plane_state->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4; - mall_region_pixels = pipe->plane_state->plane_size.surface_pitch * pipe->stream->timing.v_addressable; + struct pipe_ctx *main_pipe = NULL; + + /* Get full viewport height from main pipe (required for MBLK calculation) */ + for (j = 0; j < dc->res_pool->pipe_count; j++) { + main_pipe = &context->res_ctx.pipe_ctx[j]; + if (main_pipe->stream == pipe->stream->mall_stream_config.paired_stream) { + full_vp_height = main_pipe->plane_res.scl_data.viewport.height; + break; + } + } - // For bytes required in MALL, calculate based on number of MBlks required - num_mblks = (mall_region_pixels * bytes_per_pixel + - DCN3_2_MALL_MBLK_SIZE_BYTES - 1) / DCN3_2_MALL_MBLK_SIZE_BYTES; + bytes_per_pixel = pipe->plane_state->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4; + mblk_width = DCN3_2_MBLK_WIDTH; + mblk_height = bytes_per_pixel == 4 ? DCN3_2_MBLK_HEIGHT_4BPE : DCN3_2_MBLK_HEIGHT_8BPE; + + /* full_vp_width_blk_aligned = FLOOR(vp_x_start + full_vp_width + blk_width - 1, blk_width) - + * FLOOR(vp_x_start, blk_width) + */ + full_vp_width_blk_aligned = ((pipe->plane_res.scl_data.viewport.x + + pipe->plane_res.scl_data.viewport.width + mblk_width - 1) / mblk_width * mblk_width) + + (pipe->plane_res.scl_data.viewport.x / mblk_width * mblk_width); + + /* full_vp_height_blk_aligned = FLOOR(vp_y_start + full_vp_height + blk_height - 1, blk_height) - + * FLOOR(vp_y_start, blk_height) + */ + full_vp_height_blk_aligned = ((pipe->plane_res.scl_data.viewport.y + + full_vp_height + mblk_height - 1) / mblk_height * mblk_height) + + (pipe->plane_res.scl_data.viewport.y / mblk_height * mblk_height); + + /* mall_alloc_width_blk_aligned_l/c = full_vp_width_blk_aligned_l/c */ + mall_alloc_width_blk_aligned = full_vp_width_blk_aligned; + + /* mall_alloc_height_blk_aligned_l/c = CEILING(sub_vp_height_l/c - 1, blk_height_l/c) + blk_height_l/c */ + mall_alloc_height_blk_aligned = (pipe->stream->timing.v_addressable - 1 + mblk_height - 1) / + mblk_height * mblk_height + mblk_height; + + /* full_mblk_width_ub_l/c = mall_alloc_width_blk_aligned_l/c; + * full_mblk_height_ub_l/c = mall_alloc_height_blk_aligned_l/c; + * num_mblk_l/c = (full_mblk_width_ub_l/c / mblk_width_l/c) * (full_mblk_height_ub_l/c / mblk_height_l/c); + * (Should be divisible, but round up if not) + */ + num_mblks = ((mall_alloc_width_blk_aligned + mblk_width - 1) / mblk_width) * + ((mall_alloc_height_blk_aligned + mblk_height - 1) / mblk_height); bytes_in_mall = num_mblks * DCN3_2_MALL_MBLK_SIZE_BYTES; // cache lines used is total bytes / cache_line size. Add +2 for worst case alignment // (MALL is 64-byte aligned) diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c index c8b7d6ff38f4..7309eed33a61 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c @@ -872,6 +872,7 @@ static const struct dc_debug_options debug_defaults_drv = { .exit_idle_opt_for_cursor_updates = true, .enable_single_display_2to1_odm_policy = true, .enable_dp_dig_pixel_rate_div_policy = 1, + .allow_sw_cursor_fallback = false, }; static const struct dc_debug_options debug_defaults_diags = { @@ -1651,7 +1652,8 @@ static bool dcn321_resource_construct( dc->caps.max_downscale_ratio = 600; dc->caps.i2c_speed_in_khz = 100; dc->caps.i2c_speed_in_khz_hdcp = 100; /*1.4 w/a applied by default*/ - dc->caps.max_cursor_size = 256; + /* TODO: Bring max cursor size back to 256 after subvp cursor corruption is fixed*/ + dc->caps.max_cursor_size = 64; dc->caps.min_horizontal_blanking_period = 80; dc->caps.dmdata_alloc_size = 2048; dc->caps.mall_size_per_mem_channel = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index 86a3b5bfd699..cb81ed2fbd53 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -70,6 +70,8 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(fram CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/display_mode_vba_314.o := $(dml_ccflags) $(frame_warn_flag) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/display_rq_dlg_calc_314.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/dcn314_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/dcn30_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn32/dcn32_fpu.o := $(dml_ccflags) @@ -123,6 +125,7 @@ DML += dcn20/display_rq_dlg_calc_20v2.o dcn20/display_mode_vba_20v2.o DML += dcn21/display_rq_dlg_calc_21.o dcn21/display_mode_vba_21.o DML += dcn30/dcn30_fpu.o dcn30/display_mode_vba_30.o dcn30/display_rq_dlg_calc_30.o DML += dcn31/display_mode_vba_31.o dcn31/display_rq_dlg_calc_31.o +DML += dcn314/display_mode_vba_314.o dcn314/display_rq_dlg_calc_314.o DML += dcn32/display_mode_vba_32.o dcn32/display_rq_dlg_calc_32.o dcn32/display_mode_vba_util_32.o DML += dcn31/dcn31_fpu.o DML += dcn32/dcn32_fpu.o 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 876b321b30ca..1cb858dd6ea0 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 @@ -6610,8 +6610,7 @@ static double CalculateUrgentLatency( return ret; } - -static void UseMinimumDCFCLK( +static noinline_for_stack void UseMinimumDCFCLK( struct display_mode_lib *mode_lib, int MaxInterDCNTileRepeaters, int MaxPrefetchMode, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c index d63b4209b14c..8ca66f1644dc 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c @@ -251,33 +251,13 @@ static void CalculateRowBandwidth( static void CalculateFlipSchedule( struct display_mode_lib *mode_lib, + unsigned int k, double HostVMInefficiencyFactor, double UrgentExtraLatency, double UrgentLatency, - unsigned int GPUVMMaxPageTableLevels, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - bool GPUVMEnable, - double HostVMMinPageSize, double PDEAndMetaPTEBytesPerFrame, double MetaRowBytes, - double DPTEBytesPerRow, - double BandwidthAvailableForImmediateFlip, - unsigned int TotImmediateFlipBytes, - enum source_format_class SourcePixelFormat, - double LineTime, - double VRatio, - double VRatioChroma, - double Tno_bw, - bool DCCEnable, - unsigned int dpte_row_height, - unsigned int meta_row_height, - unsigned int dpte_row_height_chroma, - unsigned int meta_row_height_chroma, - double *DestinationLinesToRequestVMInImmediateFlip, - double *DestinationLinesToRequestRowInImmediateFlip, - double *final_flip_bw, - bool *ImmediateFlipSupportedForPipe); + double DPTEBytesPerRow); static double CalculateWriteBackDelay( enum source_format_class WritebackPixelFormat, double WritebackHRatio, @@ -311,64 +291,28 @@ static void CalculateVupdateAndDynamicMetadataParameters( static void CalculateWatermarksAndDRAMSpeedChangeSupport( struct display_mode_lib *mode_lib, unsigned int PrefetchMode, - unsigned int NumberOfActivePlanes, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizedVBlank, - unsigned int dpte_group_bytes[], - unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, - double WritebackLatency, - double WritebackChunkSize, double SOCCLK, - double DRAMClockChangeLatency, - double SRExitTime, - double SREnterPlusExitTime, - double SRExitZ8Time, - double SREnterPlusExitZ8Time, double DCFCLKDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int vtaps[], - unsigned int VTAPsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerPlane[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, int unsigned CompressedBufferSizeInkByte, enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, double *StutterExitWatermark, double *StutterEnterPlusExitWatermark, double *Z8StutterExitWatermark, - double *Z8StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported); + double *Z8StutterEnterPlusExitWatermark); static void CalculateDCFCLKDeepSleep( struct display_mode_lib *mode_lib, @@ -2904,33 +2848,13 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman for (k = 0; k < v->NumberOfActivePlanes; ++k) { CalculateFlipSchedule( mode_lib, + k, HostVMInefficiencyFactor, v->UrgentExtraLatency, v->UrgentLatency, - v->GPUVMMaxPageTableLevels, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->GPUVMEnable, - v->HostVMMinPageSize, v->PDEAndMetaPTEBytesFrame[k], v->MetaRowByte[k], - v->PixelPTEBytesPerRow[k], - v->BandwidthAvailableForImmediateFlip, - v->TotImmediateFlipBytes, - v->SourcePixelFormat[k], - v->HTotal[k] / v->PixelClock[k], - v->VRatio[k], - v->VRatioChroma[k], - v->Tno_bw[k], - v->DCCEnable[k], - v->dpte_row_height[k], - v->meta_row_height[k], - v->dpte_row_height_chroma[k], - v->meta_row_height_chroma[k], - &v->DestinationLinesToRequestVMInImmediateFlip[k], - &v->DestinationLinesToRequestRowInImmediateFlip[k], - &v->final_flip_bw[k], - &v->ImmediateFlipSupportedForPipe[k]); + v->PixelPTEBytesPerRow[k]); } v->total_dcn_read_bw_with_flip = 0.0; @@ -3017,64 +2941,28 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, PrefetchMode, - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->WritebackInterfaceBufferSize, v->DCFCLK, v->ReturnBW, - v->SynchronizedVBlank, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgentLatency, v->UrgentExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLK, - v->DRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, - v->SRExitZ8Time, - v->SREnterPlusExitZ8Time, v->DCFCLKDeepSleep, v->DETBufferSizeY, v->DETBufferSizeC, v->SwathHeightY, v->SwathHeightC, - v->LBBitPerPixel, v->SwathWidthY, v->SwathWidthC, - v->HRatio, - v->HRatioChroma, - v->vtaps, - v->VTAPsChroma, - v->VRatio, - v->VRatioChroma, - v->HTotal, - v->PixelClock, - v->BlendingAndTiming, v->DPPPerPlane, v->BytePerPixelDETY, v->BytePerPixelDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, v->UnboundedRequestEnabled, v->CompressedBufferSizeInkByte, &DRAMClockChangeSupport, - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, &v->StutterExitWatermark, &v->StutterEnterPlusExitWatermark, &v->Z8StutterExitWatermark, - &v->Z8StutterEnterPlusExitWatermark, - &v->MinActiveDRAMClockChangeLatencySupported); + &v->Z8StutterEnterPlusExitWatermark); for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (v->WritebackEnable[k] == true) { @@ -3598,61 +3486,43 @@ static void CalculateRowBandwidth( static void CalculateFlipSchedule( struct display_mode_lib *mode_lib, + unsigned int k, double HostVMInefficiencyFactor, double UrgentExtraLatency, double UrgentLatency, - unsigned int GPUVMMaxPageTableLevels, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - bool GPUVMEnable, - double HostVMMinPageSize, double PDEAndMetaPTEBytesPerFrame, double MetaRowBytes, - double DPTEBytesPerRow, - double BandwidthAvailableForImmediateFlip, - unsigned int TotImmediateFlipBytes, - enum source_format_class SourcePixelFormat, - double LineTime, - double VRatio, - double VRatioChroma, - double Tno_bw, - bool DCCEnable, - unsigned int dpte_row_height, - unsigned int meta_row_height, - unsigned int dpte_row_height_chroma, - unsigned int meta_row_height_chroma, - double *DestinationLinesToRequestVMInImmediateFlip, - double *DestinationLinesToRequestRowInImmediateFlip, - double *final_flip_bw, - bool *ImmediateFlipSupportedForPipe) + double DPTEBytesPerRow) { + struct vba_vars_st *v = &mode_lib->vba; double min_row_time = 0.0; unsigned int HostVMDynamicLevelsTrips; double TimeForFetchingMetaPTEImmediateFlip; double TimeForFetchingRowInVBlankImmediateFlip; double ImmediateFlipBW; + double LineTime = v->HTotal[k] / v->PixelClock[k]; - if (GPUVMEnable == true && HostVMEnable == true) { - HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels; + if (v->GPUVMEnable == true && v->HostVMEnable == true) { + HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels; } else { HostVMDynamicLevelsTrips = 0; } - if (GPUVMEnable == true || DCCEnable == true) { - ImmediateFlipBW = (PDEAndMetaPTEBytesPerFrame + MetaRowBytes + DPTEBytesPerRow) * BandwidthAvailableForImmediateFlip / TotImmediateFlipBytes; + if (v->GPUVMEnable == true || v->DCCEnable[k] == true) { + ImmediateFlipBW = (PDEAndMetaPTEBytesPerFrame + MetaRowBytes + DPTEBytesPerRow) * v->BandwidthAvailableForImmediateFlip / v->TotImmediateFlipBytes; } - if (GPUVMEnable == true) { + if (v->GPUVMEnable == true) { TimeForFetchingMetaPTEImmediateFlip = dml_max3( - Tno_bw + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / ImmediateFlipBW, - UrgentExtraLatency + UrgentLatency * (GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1), + v->Tno_bw[k] + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / ImmediateFlipBW, + UrgentExtraLatency + UrgentLatency * (v->GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1), LineTime / 4.0); } else { TimeForFetchingMetaPTEImmediateFlip = 0; } - *DestinationLinesToRequestVMInImmediateFlip = dml_ceil(4.0 * (TimeForFetchingMetaPTEImmediateFlip / LineTime), 1) / 4.0; - if ((GPUVMEnable == true || DCCEnable == true)) { + v->DestinationLinesToRequestVMInImmediateFlip[k] = dml_ceil(4.0 * (TimeForFetchingMetaPTEImmediateFlip / LineTime), 1) / 4.0; + if ((v->GPUVMEnable == true || v->DCCEnable[k] == true)) { TimeForFetchingRowInVBlankImmediateFlip = dml_max3( (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / ImmediateFlipBW, UrgentLatency * (HostVMDynamicLevelsTrips + 1), @@ -3661,54 +3531,54 @@ static void CalculateFlipSchedule( TimeForFetchingRowInVBlankImmediateFlip = 0; } - *DestinationLinesToRequestRowInImmediateFlip = dml_ceil(4.0 * (TimeForFetchingRowInVBlankImmediateFlip / LineTime), 1) / 4.0; + v->DestinationLinesToRequestRowInImmediateFlip[k] = dml_ceil(4.0 * (TimeForFetchingRowInVBlankImmediateFlip / LineTime), 1) / 4.0; - if (GPUVMEnable == true) { - *final_flip_bw = dml_max( - PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / (*DestinationLinesToRequestVMInImmediateFlip * LineTime), - (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (*DestinationLinesToRequestRowInImmediateFlip * LineTime)); - } else if ((GPUVMEnable == true || DCCEnable == true)) { - *final_flip_bw = (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (*DestinationLinesToRequestRowInImmediateFlip * LineTime); + if (v->GPUVMEnable == true) { + v->final_flip_bw[k] = dml_max( + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / (v->DestinationLinesToRequestVMInImmediateFlip[k] * LineTime), + (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (v->DestinationLinesToRequestRowInImmediateFlip[k] * LineTime)); + } else if ((v->GPUVMEnable == true || v->DCCEnable[k] == true)) { + v->final_flip_bw[k] = (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (v->DestinationLinesToRequestRowInImmediateFlip[k] * LineTime); } else { - *final_flip_bw = 0; + v->final_flip_bw[k] = 0; } - if (SourcePixelFormat == dm_420_8 || SourcePixelFormat == dm_420_10 || SourcePixelFormat == dm_rgbe_alpha) { - if (GPUVMEnable == true && DCCEnable != true) { - min_row_time = dml_min(dpte_row_height * LineTime / VRatio, dpte_row_height_chroma * LineTime / VRatioChroma); - } else if (GPUVMEnable != true && DCCEnable == true) { - min_row_time = dml_min(meta_row_height * LineTime / VRatio, meta_row_height_chroma * LineTime / VRatioChroma); + if (v->SourcePixelFormat[k] == dm_420_8 || v->SourcePixelFormat[k] == dm_420_10 || v->SourcePixelFormat[k] == dm_rgbe_alpha) { + if (v->GPUVMEnable == true && v->DCCEnable[k] != true) { + min_row_time = dml_min(v->dpte_row_height[k] * LineTime / v->VRatio[k], v->dpte_row_height_chroma[k] * LineTime / v->VRatioChroma[k]); + } else if (v->GPUVMEnable != true && v->DCCEnable[k] == true) { + min_row_time = dml_min(v->meta_row_height[k] * LineTime / v->VRatio[k], v->meta_row_height_chroma[k] * LineTime / v->VRatioChroma[k]); } else { min_row_time = dml_min4( - dpte_row_height * LineTime / VRatio, - meta_row_height * LineTime / VRatio, - dpte_row_height_chroma * LineTime / VRatioChroma, - meta_row_height_chroma * LineTime / VRatioChroma); + v->dpte_row_height[k] * LineTime / v->VRatio[k], + v->meta_row_height[k] * LineTime / v->VRatio[k], + v->dpte_row_height_chroma[k] * LineTime / v->VRatioChroma[k], + v->meta_row_height_chroma[k] * LineTime / v->VRatioChroma[k]); } } else { - if (GPUVMEnable == true && DCCEnable != true) { - min_row_time = dpte_row_height * LineTime / VRatio; - } else if (GPUVMEnable != true && DCCEnable == true) { - min_row_time = meta_row_height * LineTime / VRatio; + if (v->GPUVMEnable == true && v->DCCEnable[k] != true) { + min_row_time = v->dpte_row_height[k] * LineTime / v->VRatio[k]; + } else if (v->GPUVMEnable != true && v->DCCEnable[k] == true) { + min_row_time = v->meta_row_height[k] * LineTime / v->VRatio[k]; } else { - min_row_time = dml_min(dpte_row_height * LineTime / VRatio, meta_row_height * LineTime / VRatio); + min_row_time = dml_min(v->dpte_row_height[k] * LineTime / v->VRatio[k], v->meta_row_height[k] * LineTime / v->VRatio[k]); } } - if (*DestinationLinesToRequestVMInImmediateFlip >= 32 || *DestinationLinesToRequestRowInImmediateFlip >= 16 + if (v->DestinationLinesToRequestVMInImmediateFlip[k] >= 32 || v->DestinationLinesToRequestRowInImmediateFlip[k] >= 16 || TimeForFetchingMetaPTEImmediateFlip + 2 * TimeForFetchingRowInVBlankImmediateFlip > min_row_time) { - *ImmediateFlipSupportedForPipe = false; + v->ImmediateFlipSupportedForPipe[k] = false; } else { - *ImmediateFlipSupportedForPipe = true; + v->ImmediateFlipSupportedForPipe[k] = true; } #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: DestinationLinesToRequestVMInImmediateFlip = %f\n", __func__, *DestinationLinesToRequestVMInImmediateFlip); - dml_print("DML::%s: DestinationLinesToRequestRowInImmediateFlip = %f\n", __func__, *DestinationLinesToRequestRowInImmediateFlip); + dml_print("DML::%s: DestinationLinesToRequestVMInImmediateFlip = %f\n", __func__, v->DestinationLinesToRequestVMInImmediateFlip[k]); + dml_print("DML::%s: DestinationLinesToRequestRowInImmediateFlip = %f\n", __func__, v->DestinationLinesToRequestRowInImmediateFlip[k]); dml_print("DML::%s: TimeForFetchingMetaPTEImmediateFlip = %f\n", __func__, TimeForFetchingMetaPTEImmediateFlip); dml_print("DML::%s: TimeForFetchingRowInVBlankImmediateFlip = %f\n", __func__, TimeForFetchingRowInVBlankImmediateFlip); dml_print("DML::%s: min_row_time = %f\n", __func__, min_row_time); - dml_print("DML::%s: ImmediateFlipSupportedForPipe = %d\n", __func__, *ImmediateFlipSupportedForPipe); + dml_print("DML::%s: ImmediateFlipSupportedForPipe = %d\n", __func__, v->ImmediateFlipSupportedForPipe[k]); #endif } @@ -5300,33 +5170,13 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l for (k = 0; k < v->NumberOfActivePlanes; k++) { CalculateFlipSchedule( mode_lib, + k, HostVMInefficiencyFactor, v->ExtraLatency, v->UrgLatency[i], - v->GPUVMMaxPageTableLevels, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->GPUVMEnable, - v->HostVMMinPageSize, v->PDEAndMetaPTEBytesPerFrame[i][j][k], v->MetaRowBytes[i][j][k], - v->DPTEBytesPerRow[i][j][k], - v->BandwidthAvailableForImmediateFlip, - v->TotImmediateFlipBytes, - v->SourcePixelFormat[k], - v->HTotal[k] / v->PixelClock[k], - v->VRatio[k], - v->VRatioChroma[k], - v->Tno_bw[k], - v->DCCEnable[k], - v->dpte_row_height[k], - v->meta_row_height[k], - v->dpte_row_height_chroma[k], - v->meta_row_height_chroma[k], - &v->DestinationLinesToRequestVMInImmediateFlip[k], - &v->DestinationLinesToRequestRowInImmediateFlip[k], - &v->final_flip_bw[k], - &v->ImmediateFlipSupportedForPipe[k]); + v->DPTEBytesPerRow[i][j][k]); } v->total_dcn_read_bw_with_flip = 0.0; for (k = 0; k < v->NumberOfActivePlanes; k++) { @@ -5384,64 +5234,28 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, v->PrefetchModePerState[i][j], - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->WritebackInterfaceBufferSize, v->DCFCLKState[i][j], v->ReturnBWPerState[i][j], - v->SynchronizedVBlank, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgLatency[i], v->ExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLKPerState[i], - v->DRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, - v->SRExitZ8Time, - v->SREnterPlusExitZ8Time, v->ProjectedDCFCLKDeepSleep[i][j], v->DETBufferSizeYThisState, v->DETBufferSizeCThisState, v->SwathHeightYThisState, v->SwathHeightCThisState, - v->LBBitPerPixel, v->SwathWidthYThisState, v->SwathWidthCThisState, - v->HRatio, - v->HRatioChroma, - v->vtaps, - v->VTAPsChroma, - v->VRatio, - v->VRatioChroma, - v->HTotal, - v->PixelClock, - v->BlendingAndTiming, v->NoOfDPPThisState, v->BytePerPixelInDETY, v->BytePerPixelInDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, UnboundedRequestEnabledThisState, CompressedBufferSizeInkByteThisState, &v->DRAMClockChangeSupport[i][j], - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, - &dummy, &dummy, &dummy, &dummy, - &v->MinActiveDRAMClockChangeLatencySupported); + &dummy); } } @@ -5566,64 +5380,28 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l static void CalculateWatermarksAndDRAMSpeedChangeSupport( struct display_mode_lib *mode_lib, unsigned int PrefetchMode, - unsigned int NumberOfActivePlanes, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizedVBlank, - unsigned int dpte_group_bytes[], - unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, - double WritebackLatency, - double WritebackChunkSize, double SOCCLK, - double DRAMClockChangeLatency, - double SRExitTime, - double SREnterPlusExitTime, - double SRExitZ8Time, - double SREnterPlusExitZ8Time, double DCFCLKDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int vtaps[], - unsigned int VTAPsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerPlane[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, int unsigned CompressedBufferSizeInkByte, enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, double *StutterExitWatermark, double *StutterEnterPlusExitWatermark, double *Z8StutterExitWatermark, - double *Z8StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported) + double *Z8StutterEnterPlusExitWatermark) { struct vba_vars_st *v = &mode_lib->vba; double EffectiveLBLatencyHidingY; @@ -5643,103 +5421,103 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( double TotalPixelBW = 0.0; int k, j; - *UrgentWatermark = UrgentLatency + ExtraLatency; + v->UrgentWatermark = UrgentLatency + ExtraLatency; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: UrgentLatency = %f\n", __func__, UrgentLatency); dml_print("DML::%s: ExtraLatency = %f\n", __func__, ExtraLatency); - dml_print("DML::%s: UrgentWatermark = %f\n", __func__, *UrgentWatermark); + dml_print("DML::%s: UrgentWatermark = %f\n", __func__, v->UrgentWatermark); #endif - *DRAMClockChangeWatermark = DRAMClockChangeLatency + *UrgentWatermark; + v->DRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->UrgentWatermark; #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: DRAMClockChangeLatency = %f\n", __func__, DRAMClockChangeLatency); - dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, *DRAMClockChangeWatermark); + dml_print("DML::%s: v->DRAMClockChangeLatency = %f\n", __func__, v->DRAMClockChangeLatency); + dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, v->DRAMClockChangeWatermark); #endif v->TotalActiveWriteback = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (WritebackEnable[k] == true) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->WritebackEnable[k] == true) { v->TotalActiveWriteback = v->TotalActiveWriteback + 1; } } if (v->TotalActiveWriteback <= 1) { - *WritebackUrgentWatermark = WritebackLatency; + v->WritebackUrgentWatermark = v->WritebackLatency; } else { - *WritebackUrgentWatermark = WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->WritebackUrgentWatermark = v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } if (v->TotalActiveWriteback <= 1) { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency; + v->WritebackDRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->WritebackLatency; } else { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->WritebackDRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { TotalPixelBW = TotalPixelBW - + DPPPerPlane[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] + SwathWidthC[k] * BytePerPixelDETC[k] * VRatioChroma[k]) - / (HTotal[k] / PixelClock[k]); + + DPPPerPlane[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] + SwathWidthC[k] * BytePerPixelDETC[k] * v->VRatioChroma[k]) + / (v->HTotal[k] / v->PixelClock[k]); } - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { double EffectiveDETBufferSizeY = DETBufferSizeY[k]; v->LBLatencyHidingSourceLinesY = dml_min( - (double) MaxLineBufferLines, - dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (vtaps[k] - 1); + (double) v->MaxLineBufferLines, + dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(v->HRatio[k], 1.0)), 1)) - (v->vtaps[k] - 1); v->LBLatencyHidingSourceLinesC = dml_min( - (double) MaxLineBufferLines, - dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTAPsChroma[k] - 1); + (double) v->MaxLineBufferLines, + dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(v->HRatioChroma[k], 1.0)), 1)) - (v->VTAPsChroma[k] - 1); - EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / VRatio[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / v->VRatio[k] * (v->HTotal[k] / v->PixelClock[k]); - EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / VRatioChroma[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / v->VRatioChroma[k] * (v->HTotal[k] / v->PixelClock[k]); if (UnboundedRequestEnabled) { EffectiveDETBufferSizeY = EffectiveDETBufferSizeY - + CompressedBufferSizeInkByte * 1024 * SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] / (HTotal[k] / PixelClock[k]) / TotalPixelBW; + + CompressedBufferSizeInkByte * 1024 * SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] / (v->HTotal[k] / v->PixelClock[k]) / TotalPixelBW; } LinesInDETY[k] = (double) EffectiveDETBufferSizeY / BytePerPixelDETY[k] / SwathWidthY[k]; LinesInDETYRoundedDownToSwath[k] = dml_floor(LinesInDETY[k], SwathHeightY[k]); - FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k]; + FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k]; if (BytePerPixelDETC[k] > 0) { LinesInDETC = v->DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k]; LinesInDETCRoundedDownToSwath = dml_floor(LinesInDETC, SwathHeightC[k]); - FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (HTotal[k] / PixelClock[k]) / VRatioChroma[k]; + FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (v->HTotal[k] / v->PixelClock[k]) / v->VRatioChroma[k]; } else { LinesInDETC = 0; FullDETBufferingTimeC = 999999; } ActiveDRAMClockChangeLatencyMarginY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY - - ((double) DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k] - *UrgentWatermark - *DRAMClockChangeWatermark; + - ((double) v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k] - v->UrgentWatermark - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { + if (v->NumberOfActivePlanes > 1) { ActiveDRAMClockChangeLatencyMarginY = ActiveDRAMClockChangeLatencyMarginY - - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightY[k] * HTotal[k] / PixelClock[k] / VRatio[k]; + - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightY[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatio[k]; } if (BytePerPixelDETC[k] > 0) { ActiveDRAMClockChangeLatencyMarginC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC - - ((double) DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k] - *UrgentWatermark - *DRAMClockChangeWatermark; + - ((double) v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k] - v->UrgentWatermark - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { + if (v->NumberOfActivePlanes > 1) { ActiveDRAMClockChangeLatencyMarginC = ActiveDRAMClockChangeLatencyMarginC - - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightC[k] * HTotal[k] / PixelClock[k] / VRatioChroma[k]; + - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightC[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatioChroma[k]; } v->ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMarginY, ActiveDRAMClockChangeLatencyMarginC); } else { v->ActiveDRAMClockChangeLatencyMargin[k] = ActiveDRAMClockChangeLatencyMarginY; } - if (WritebackEnable[k] == true) { - WritebackDRAMClockChangeLatencyHiding = WritebackInterfaceBufferSize * 1024 - / (WritebackDestinationWidth[k] * WritebackDestinationHeight[k] / (WritebackSourceHeight[k] * HTotal[k] / PixelClock[k]) * 4); - if (WritebackPixelFormat[k] == dm_444_64) { + if (v->WritebackEnable[k] == true) { + WritebackDRAMClockChangeLatencyHiding = v->WritebackInterfaceBufferSize * 1024 + / (v->WritebackDestinationWidth[k] * v->WritebackDestinationHeight[k] / (v->WritebackSourceHeight[k] * v->HTotal[k] / v->PixelClock[k]) * 4); + if (v->WritebackPixelFormat[k] == dm_444_64) { WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding / 2; } WritebackDRAMClockChangeLatencyMargin = WritebackDRAMClockChangeLatencyHiding - v->WritebackDRAMClockChangeWatermark; @@ -5749,14 +5527,14 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( v->MinActiveDRAMClockChangeMargin = 999999; PlaneWithMinActiveDRAMClockChangeMargin = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (v->ActiveDRAMClockChangeLatencyMargin[k] < v->MinActiveDRAMClockChangeMargin) { v->MinActiveDRAMClockChangeMargin = v->ActiveDRAMClockChangeLatencyMargin[k]; - if (BlendingAndTiming[k] == k) { + if (v->BlendingAndTiming[k] == k) { PlaneWithMinActiveDRAMClockChangeMargin = k; } else { - for (j = 0; j < NumberOfActivePlanes; ++j) { - if (BlendingAndTiming[k] == j) { + for (j = 0; j < v->NumberOfActivePlanes; ++j) { + if (v->BlendingAndTiming[k] == j) { PlaneWithMinActiveDRAMClockChangeMargin = j; } } @@ -5764,11 +5542,11 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( } } - *MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + DRAMClockChangeLatency; + v->MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + v->DRAMClockChangeLatency ; SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = 999999; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (BlendingAndTiming[k] == k)) && !(BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin) + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (v->BlendingAndTiming[k] == k)) && !(v->BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin) && v->ActiveDRAMClockChangeLatencyMargin[k] < SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank) { SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = v->ActiveDRAMClockChangeLatencyMargin[k]; } @@ -5776,25 +5554,25 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( v->TotalNumberOfActiveOTG = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (BlendingAndTiming[k] == k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->BlendingAndTiming[k] == k) { v->TotalNumberOfActiveOTG = v->TotalNumberOfActiveOTG + 1; } } if (v->MinActiveDRAMClockChangeMargin > 0 && PrefetchMode == 0) { *DRAMClockChangeSupport = dm_dram_clock_change_vactive; - } else if ((SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1 + } else if ((v->SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1 || SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank > 0) && PrefetchMode == 0) { *DRAMClockChangeSupport = dm_dram_clock_change_vblank; } else { *DRAMClockChangeSupport = dm_dram_clock_change_unsupported; } - *StutterExitWatermark = SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; - *StutterEnterPlusExitWatermark = (SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep); - *Z8StutterExitWatermark = SRExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; - *Z8StutterEnterPlusExitWatermark = SREnterPlusExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; + *StutterExitWatermark = v->SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; + *StutterEnterPlusExitWatermark = (v->SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep); + *Z8StutterExitWatermark = v->SRExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; + *Z8StutterEnterPlusExitWatermark = v->SREnterPlusExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: StutterExitWatermark = %f\n", __func__, *StutterExitWatermark); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c index 34a5d0f87b5f..4bb3b31ea7e0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c @@ -194,6 +194,9 @@ void dcn314_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p dcn3_14_ip.max_num_otg = dc->res_pool->res_cap->num_timing_generator; dcn3_14_ip.max_num_dpp = dc->res_pool->pipe_count; + if (bw_params->dram_channel_width_bytes > 0) + dcn3_14_soc.dram_channel_width_bytes = bw_params->dram_channel_width_bytes; + if (bw_params->num_channels > 0) dcn3_14_soc.num_chans = bw_params->num_channels; @@ -262,7 +265,7 @@ void dcn314_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p } if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) - dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN31); + dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN314); else dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN31_FPGA); } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c index fc4d7474c111..01f3fad172f3 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c @@ -61,7 +61,7 @@ // fudge factor for min dcfclk calclation #define __DML_MIN_DCFCLK_FACTOR__ 1.15 -struct { +typedef struct { double DPPCLK; double DISPCLK; double PixelClock; @@ -1599,7 +1599,7 @@ static void CalculateDCCConfiguration( int segment_order_vert_contiguous_luma; int segment_order_vert_contiguous_chroma; - enum { + typedef enum { REQ_256Bytes, REQ_128BytesNonContiguous, REQ_128BytesContiguous, REQ_NA } RequestType; RequestType RequestLuma; @@ -4071,9 +4071,7 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_ v->SourceFormatPixelAndScanSupport = true; for (k = 0; k < v->NumberOfActivePlanes; k++) { - if ((v->SurfaceTiling[k] == dm_sw_linear && (!(v->SourceScan[k] != dm_vert) || v->DCCEnable[k] == true)) - || ((v->SurfaceTiling[k] == dm_sw_64kb_d || v->SurfaceTiling[k] == dm_sw_64kb_d_t - || v->SurfaceTiling[k] == dm_sw_64kb_d_x) && !(v->SourcePixelFormat[k] == dm_444_64))) { + if (v->SurfaceTiling[k] == dm_sw_linear && (!(v->SourceScan[k] != dm_vert) || v->DCCEnable[k] == true)) { v->SourceFormatPixelAndScanSupport = false; } } @@ -7157,12 +7155,13 @@ static double CalculateExtraLatencyBytes( HostVMDynamicLevels = dml_max(0, (int) HostVMMaxNonCachedPageTableLevels - 1); else HostVMDynamicLevels = dml_max(0, (int) HostVMMaxNonCachedPageTableLevels - 2); - else + } else { HostVMDynamicLevels = 0; + } ret = ReorderingBytes + (TotalNumberOfActiveDPP * PixelChunkSizeInKByte + TotalNumberOfDCCActiveDPP * MetaChunkSize) * 1024.0; - if (GPUVMEnable == true) + if (GPUVMEnable == true) { for (k = 0; k < NumberOfActivePlanes; ++k) ret = ret + NumberOfDPP[k] * dpte_group_bytes[k] * (1 + 8 * HostVMDynamicLevels) * HostVMInefficiencyFactor; } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index cb2025771646..9a60f27eceaa 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -755,30 +755,18 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.BytePerPixelY = v->BytePerPixelY[k]; v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.BytePerPixelC = v->BytePerPixelC[k]; v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.ProgressiveToInterlaceUnitInOPP = mode_lib->vba.ProgressiveToInterlaceUnitInOPP; - v->ErrorResult[k] = dml32_CalculatePrefetchSchedule(v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.HostVMInefficiencyFactor, - &v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe, v->DSCDelay[k], - mode_lib->vba.DPPCLKDelaySubtotal + mode_lib->vba.DPPCLKDelayCNVCFormater, - mode_lib->vba.DPPCLKDelaySCL, - mode_lib->vba.DPPCLKDelaySCLLBOnly, - mode_lib->vba.DPPCLKDelayCNVCCursor, - mode_lib->vba.DISPCLKDelaySubtotal, - (unsigned int) (v->SwathWidthY[k] / mode_lib->vba.HRatio[k]), - mode_lib->vba.OutputFormat[k], - mode_lib->vba.MaxInterDCNTileRepeaters, + v->ErrorResult[k] = dml32_CalculatePrefetchSchedule( + v, + k, + v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.HostVMInefficiencyFactor, + &v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe, + v->DSCDelay[k], + (unsigned int) (v->SwathWidthY[k] / v->HRatio[k]), dml_min(v->VStartupLines, v->MaxVStartupLines[k]), v->MaxVStartupLines[k], - mode_lib->vba.GPUVMMaxPageTableLevels, - mode_lib->vba.GPUVMEnable, - mode_lib->vba.HostVMEnable, - mode_lib->vba.HostVMMaxNonCachedPageTableLevels, - mode_lib->vba.HostVMMinPageSize, - mode_lib->vba.DynamicMetadataEnable[k], - mode_lib->vba.DynamicMetadataVMEnabled, - mode_lib->vba.DynamicMetadataLinesBeforeActiveRequired[k], - mode_lib->vba.DynamicMetadataTransmittedBytes[k], v->UrgentLatency, v->UrgentExtraLatency, - mode_lib->vba.TCalc, + v->TCalc, v->PDEAndMetaPTEBytesFrame[k], v->MetaRowByte[k], v->PixelPTEBytesPerRow[k], @@ -792,8 +780,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->MaxNumSwathC[k], v->swath_width_luma_ub[k], v->swath_width_chroma_ub[k], - mode_lib->vba.SwathHeightY[k], - mode_lib->vba.SwathHeightC[k], + v->SwathHeightY[k], + v->SwathHeightC[k], TWait, /* Output */ &v->DSTXAfterScaler[k], @@ -1163,58 +1151,28 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.mmSOCParameters.SMNLatency = mode_lib->vba.SMNLatency; dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( - mode_lib->vba.USRRetrainingRequiredFinal, - mode_lib->vba.UsesMALLForPStateChange, - mode_lib->vba.PrefetchModePerState[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb], - mode_lib->vba.NumberOfActiveSurfaces, - mode_lib->vba.MaxLineBufferLines, - mode_lib->vba.LineBufferSizeFinal, - mode_lib->vba.WritebackInterfaceBufferSize, - mode_lib->vba.DCFCLK, - mode_lib->vba.ReturnBW, - mode_lib->vba.SynchronizeTimingsFinal, - mode_lib->vba.SynchronizeDRRDisplaysForUCLKPStateChangeFinal, - mode_lib->vba.DRRDisplay, - v->dpte_group_bytes, - v->meta_row_height, - v->meta_row_height_chroma, + v, + v->PrefetchModePerState[v->VoltageLevel][v->maxMpcComb], + v->DCFCLK, + v->ReturnBW, v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.mmSOCParameters, - mode_lib->vba.WritebackChunkSize, - mode_lib->vba.SOCCLK, + v->SOCCLK, v->DCFCLKDeepSleep, - mode_lib->vba.DETBufferSizeY, - mode_lib->vba.DETBufferSizeC, - mode_lib->vba.SwathHeightY, - mode_lib->vba.SwathHeightC, - mode_lib->vba.LBBitPerPixel, + v->DETBufferSizeY, + v->DETBufferSizeC, + v->SwathHeightY, + v->SwathHeightC, v->SwathWidthY, v->SwathWidthC, - mode_lib->vba.HRatio, - mode_lib->vba.HRatioChroma, - mode_lib->vba.vtaps, - mode_lib->vba.VTAPsChroma, - mode_lib->vba.VRatio, - mode_lib->vba.VRatioChroma, - mode_lib->vba.HTotal, - mode_lib->vba.VTotal, - mode_lib->vba.VActive, - mode_lib->vba.PixelClock, - mode_lib->vba.BlendingAndTiming, - mode_lib->vba.DPPPerPlane, + v->DPPPerPlane, v->BytePerPixelDETY, v->BytePerPixelDETC, v->DSTXAfterScaler, v->DSTYAfterScaler, - mode_lib->vba.WritebackEnable, - mode_lib->vba.WritebackPixelFormat, - mode_lib->vba.WritebackDestinationWidth, - mode_lib->vba.WritebackDestinationHeight, - mode_lib->vba.WritebackSourceHeight, v->UnboundedRequestEnabled, v->CompressedBufferSizeInkByte, /* Output */ - &v->Watermark, &v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.dummy_dramchange_support, v->MaxActiveDRAMClockChangeLatencySupported, v->SubViewportLinesNeededInMALL, @@ -1806,10 +1764,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l &mode_lib->vba.Read256BlockHeightC[k], &mode_lib->vba.Read256BlockWidthY[k], &mode_lib->vba.Read256BlockWidthC[k], - &mode_lib->vba.MicroTileHeightY[k], - &mode_lib->vba.MicroTileHeightC[k], - &mode_lib->vba.MicroTileWidthY[k], - &mode_lib->vba.MicroTileWidthC[k]); + &mode_lib->vba.MacroTileHeightY[k], + &mode_lib->vba.MacroTileHeightC[k], + &mode_lib->vba.MacroTileWidthY[k], + &mode_lib->vba.MacroTileWidthC[k]); } /*Bandwidth Support Check*/ @@ -2659,10 +2617,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.Read256BlockWidthC, mode_lib->vba.Read256BlockHeightY, mode_lib->vba.Read256BlockHeightC, - mode_lib->vba.MicroTileWidthY, - mode_lib->vba.MicroTileWidthC, - mode_lib->vba.MicroTileHeightY, - mode_lib->vba.MicroTileHeightC, + mode_lib->vba.MacroTileWidthY, + mode_lib->vba.MacroTileWidthC, + mode_lib->vba.MacroTileHeightY, + mode_lib->vba.MacroTileHeightC, /* Output */ mode_lib->vba.SurfaceSizeInMALL, @@ -2709,10 +2667,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeight256BytesY = mode_lib->vba.Read256BlockHeightY[k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidth256BytesC = mode_lib->vba.Read256BlockWidthC[k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeight256BytesC = mode_lib->vba.Read256BlockHeightC[k]; - v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthY = mode_lib->vba.MicroTileWidthY[k]; - v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightY = mode_lib->vba.MicroTileHeightY[k]; - v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthC = mode_lib->vba.MicroTileWidthC[k]; - v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightC = mode_lib->vba.MicroTileHeightC[k]; + v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthY = mode_lib->vba.MacroTileWidthY[k]; + v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightY = mode_lib->vba.MacroTileHeightY[k]; + v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthC = mode_lib->vba.MacroTileWidthC[k]; + v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightC = mode_lib->vba.MacroTileHeightC[k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].InterlaceEnable = mode_lib->vba.Interlace[k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].HTotal = mode_lib->vba.HTotal[k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].DCCEnable = mode_lib->vba.DCCEnable[k]; @@ -3258,63 +3216,47 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.NoTimeForPrefetch[i][j][k] = dml32_CalculatePrefetchSchedule( + v, + k, v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.HostVMInefficiencyFactor, &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.myPipe, - mode_lib->vba.DSCDelayPerState[i][k], - mode_lib->vba.DPPCLKDelaySubtotal + - mode_lib->vba.DPPCLKDelayCNVCFormater, - mode_lib->vba.DPPCLKDelaySCL, - mode_lib->vba.DPPCLKDelaySCLLBOnly, - mode_lib->vba.DPPCLKDelayCNVCCursor, - mode_lib->vba.DISPCLKDelaySubtotal, - mode_lib->vba.SwathWidthYThisState[k] / - mode_lib->vba.HRatio[k], - mode_lib->vba.OutputFormat[k], - mode_lib->vba.MaxInterDCNTileRepeaters, - dml_min(mode_lib->vba.MaxVStartup, - mode_lib->vba.MaximumVStartup[i][j][k]), - mode_lib->vba.MaximumVStartup[i][j][k], - mode_lib->vba.GPUVMMaxPageTableLevels, - mode_lib->vba.GPUVMEnable, mode_lib->vba.HostVMEnable, - mode_lib->vba.HostVMMaxNonCachedPageTableLevels, - mode_lib->vba.HostVMMinPageSize, - mode_lib->vba.DynamicMetadataEnable[k], - mode_lib->vba.DynamicMetadataVMEnabled, - mode_lib->vba.DynamicMetadataLinesBeforeActiveRequired[k], - mode_lib->vba.DynamicMetadataTransmittedBytes[k], - mode_lib->vba.UrgLatency[i], - mode_lib->vba.ExtraLatency, - mode_lib->vba.TimeCalc, - mode_lib->vba.PDEAndMetaPTEBytesPerFrame[i][j][k], - mode_lib->vba.MetaRowBytes[i][j][k], - mode_lib->vba.DPTEBytesPerRow[i][j][k], - mode_lib->vba.PrefetchLinesY[i][j][k], - mode_lib->vba.SwathWidthYThisState[k], - mode_lib->vba.PrefillY[k], - mode_lib->vba.MaxNumSwY[k], - mode_lib->vba.PrefetchLinesC[i][j][k], - mode_lib->vba.SwathWidthCThisState[k], - mode_lib->vba.PrefillC[k], - mode_lib->vba.MaxNumSwC[k], - mode_lib->vba.swath_width_luma_ub_this_state[k], - mode_lib->vba.swath_width_chroma_ub_this_state[k], - mode_lib->vba.SwathHeightYThisState[k], - mode_lib->vba.SwathHeightCThisState[k], mode_lib->vba.TWait, + v->DSCDelayPerState[i][k], + v->SwathWidthYThisState[k] / v->HRatio[k], + dml_min(v->MaxVStartup, v->MaximumVStartup[i][j][k]), + v->MaximumVStartup[i][j][k], + v->UrgLatency[i], + v->ExtraLatency, + v->TimeCalc, + v->PDEAndMetaPTEBytesPerFrame[i][j][k], + v->MetaRowBytes[i][j][k], + v->DPTEBytesPerRow[i][j][k], + v->PrefetchLinesY[i][j][k], + v->SwathWidthYThisState[k], + v->PrefillY[k], + v->MaxNumSwY[k], + v->PrefetchLinesC[i][j][k], + v->SwathWidthCThisState[k], + v->PrefillC[k], + v->MaxNumSwC[k], + v->swath_width_luma_ub_this_state[k], + v->swath_width_chroma_ub_this_state[k], + v->SwathHeightYThisState[k], + v->SwathHeightCThisState[k], v->TWait, /* Output */ &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTXAfterScaler[k], &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTYAfterScaler[k], - &mode_lib->vba.LineTimesForPrefetch[k], - &mode_lib->vba.PrefetchBW[k], - &mode_lib->vba.LinesForMetaPTE[k], - &mode_lib->vba.LinesForMetaAndDPTERow[k], - &mode_lib->vba.VRatioPreY[i][j][k], - &mode_lib->vba.VRatioPreC[i][j][k], - &mode_lib->vba.RequiredPrefetchPixelDataBWLuma[0][0][k], - &mode_lib->vba.RequiredPrefetchPixelDataBWChroma[0][0][k], - &mode_lib->vba.NoTimeForDynamicMetadata[i][j][k], - &mode_lib->vba.Tno_bw[k], - &mode_lib->vba.prefetch_vmrow_bw[k], + &v->LineTimesForPrefetch[k], + &v->PrefetchBW[k], + &v->LinesForMetaPTE[k], + &v->LinesForMetaAndDPTERow[k], + &v->VRatioPreY[i][j][k], + &v->VRatioPreC[i][j][k], + &v->RequiredPrefetchPixelDataBWLuma[0][0][k], + &v->RequiredPrefetchPixelDataBWChroma[0][0][k], + &v->NoTimeForDynamicMetadata[i][j][k], + &v->Tno_bw[k], + &v->prefetch_vmrow_bw[k], &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single[0], // double *Tdmdl_vm &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single[1], // double *Tdmdl &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single[2], // double *TSetup @@ -3557,62 +3499,32 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l { dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( - mode_lib->vba.USRRetrainingRequiredFinal, - mode_lib->vba.UsesMALLForPStateChange, - mode_lib->vba.PrefetchModePerState[i][j], - mode_lib->vba.NumberOfActiveSurfaces, - mode_lib->vba.MaxLineBufferLines, - mode_lib->vba.LineBufferSizeFinal, - mode_lib->vba.WritebackInterfaceBufferSize, - mode_lib->vba.DCFCLKState[i][j], - mode_lib->vba.ReturnBWPerState[i][j], - mode_lib->vba.SynchronizeTimingsFinal, - mode_lib->vba.SynchronizeDRRDisplaysForUCLKPStateChangeFinal, - mode_lib->vba.DRRDisplay, - mode_lib->vba.dpte_group_bytes, - mode_lib->vba.meta_row_height, - mode_lib->vba.meta_row_height_chroma, + v, + v->PrefetchModePerState[i][j], + v->DCFCLKState[i][j], + v->ReturnBWPerState[i][j], v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.mSOCParameters, - mode_lib->vba.WritebackChunkSize, - mode_lib->vba.SOCCLKPerState[i], - mode_lib->vba.ProjectedDCFCLKDeepSleep[i][j], - mode_lib->vba.DETBufferSizeYThisState, - mode_lib->vba.DETBufferSizeCThisState, - mode_lib->vba.SwathHeightYThisState, - mode_lib->vba.SwathHeightCThisState, - mode_lib->vba.LBBitPerPixel, - mode_lib->vba.SwathWidthYThisState, // 24 - mode_lib->vba.SwathWidthCThisState, - mode_lib->vba.HRatio, - mode_lib->vba.HRatioChroma, - mode_lib->vba.vtaps, - mode_lib->vba.VTAPsChroma, - mode_lib->vba.VRatio, - mode_lib->vba.VRatioChroma, - mode_lib->vba.HTotal, - mode_lib->vba.VTotal, - mode_lib->vba.VActive, - mode_lib->vba.PixelClock, - mode_lib->vba.BlendingAndTiming, - mode_lib->vba.NoOfDPPThisState, - mode_lib->vba.BytePerPixelInDETY, - mode_lib->vba.BytePerPixelInDETC, + v->SOCCLKPerState[i], + v->ProjectedDCFCLKDeepSleep[i][j], + v->DETBufferSizeYThisState, + v->DETBufferSizeCThisState, + v->SwathHeightYThisState, + v->SwathHeightCThisState, + v->SwathWidthYThisState, // 24 + v->SwathWidthCThisState, + v->NoOfDPPThisState, + v->BytePerPixelInDETY, + v->BytePerPixelInDETC, v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTXAfterScaler, v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTYAfterScaler, - mode_lib->vba.WritebackEnable, - mode_lib->vba.WritebackPixelFormat, - mode_lib->vba.WritebackDestinationWidth, - mode_lib->vba.WritebackDestinationHeight, - mode_lib->vba.WritebackSourceHeight, - mode_lib->vba.UnboundedRequestEnabledThisState, - mode_lib->vba.CompressedBufferSizeInkByteThisState, + v->UnboundedRequestEnabledThisState, + v->CompressedBufferSizeInkByteThisState, /* Output */ - &mode_lib->vba.Watermark, // Store the values in vba - &mode_lib->vba.DRAMClockChangeSupport[i][j], + &v->DRAMClockChangeSupport[i][j], &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single2[0], // double *MaxActiveDRAMClockChangeLatencySupported &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_integer[0], // Long SubViewportLinesNeededInMALL[] - &mode_lib->vba.FCLKChangeSupport[i][j], + &v->FCLKChangeSupport[i][j], &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single2[1], // double *MinActiveFCLKChangeLatencySupported &mode_lib->vba.USRRetrainingSupport[i][j], mode_lib->vba.ActiveDRAMClockChangeLatencyMargin); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c index 05fc14a47fba..59c2547d01b1 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c @@ -3363,28 +3363,14 @@ double dml32_CalculateExtraLatency( } // CalculateExtraLatency bool dml32_CalculatePrefetchSchedule( + struct vba_vars_st *v, + unsigned int k, double HostVMInefficiencyFactor, DmlPipe *myPipe, unsigned int DSCDelay, - double DPPCLKDelaySubtotalPlusCNVCFormater, - double DPPCLKDelaySCL, - double DPPCLKDelaySCLLBOnly, - double DPPCLKDelayCNVCCursor, - double DISPCLKDelaySubtotal, unsigned int DPP_RECOUT_WIDTH, - enum output_format_class OutputFormat, - unsigned int MaxInterDCNTileRepeaters, unsigned int VStartup, unsigned int MaxVStartup, - unsigned int GPUVMPageTableLevels, - bool GPUVMEnable, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - double HostVMMinPageSize, - bool DynamicMetadataEnable, - bool DynamicMetadataVMEnabled, - int DynamicMetadataLinesBeforeActiveRequired, - unsigned int DynamicMetadataTransmittedBytes, double UrgentLatency, double UrgentExtraLatency, double TCalc, @@ -3425,6 +3411,7 @@ bool dml32_CalculatePrefetchSchedule( double *VUpdateWidthPix, double *VReadyOffsetPix) { + double DPPCLKDelaySubtotalPlusCNVCFormater = v->DPPCLKDelaySubtotal + v->DPPCLKDelayCNVCFormater; bool MyError = false; unsigned int DPPCycles, DISPCLKCycles; double DSTTotalPixelsAfterScaler; @@ -3461,27 +3448,27 @@ bool dml32_CalculatePrefetchSchedule( double Tsw_est1 = 0; double Tsw_est3 = 0; - if (GPUVMEnable == true && HostVMEnable == true) - HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels; + if (v->GPUVMEnable == true && v->HostVMEnable == true) + HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels; else HostVMDynamicLevelsTrips = 0; #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: GPUVMEnable = %d\n", __func__, GPUVMEnable); - dml_print("DML::%s: GPUVMPageTableLevels = %d\n", __func__, GPUVMPageTableLevels); + dml_print("DML::%s: v->GPUVMEnable = %d\n", __func__, v->GPUVMEnable); + dml_print("DML::%s: v->GPUVMMaxPageTableLevels = %d\n", __func__, v->GPUVMMaxPageTableLevels); dml_print("DML::%s: DCCEnable = %d\n", __func__, myPipe->DCCEnable); - dml_print("DML::%s: HostVMEnable=%d HostVMInefficiencyFactor=%f\n", - __func__, HostVMEnable, HostVMInefficiencyFactor); + dml_print("DML::%s: v->HostVMEnable=%d HostVMInefficiencyFactor=%f\n", + __func__, v->HostVMEnable, HostVMInefficiencyFactor); #endif dml32_CalculateVUpdateAndDynamicMetadataParameters( - MaxInterDCNTileRepeaters, + v->MaxInterDCNTileRepeaters, myPipe->Dppclk, myPipe->Dispclk, myPipe->DCFClkDeepSleep, myPipe->PixelClock, myPipe->HTotal, myPipe->VBlank, - DynamicMetadataTransmittedBytes, - DynamicMetadataLinesBeforeActiveRequired, + v->DynamicMetadataTransmittedBytes[k], + v->DynamicMetadataLinesBeforeActiveRequired[k], myPipe->InterlaceEnable, myPipe->ProgressiveToInterlaceUnitInOPP, TSetup, @@ -3496,19 +3483,19 @@ bool dml32_CalculatePrefetchSchedule( LineTime = myPipe->HTotal / myPipe->PixelClock; trip_to_mem = UrgentLatency; - Tvm_trips = UrgentExtraLatency + trip_to_mem * (GPUVMPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1); + Tvm_trips = UrgentExtraLatency + trip_to_mem * (v->GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1); - if (DynamicMetadataVMEnabled == true) + if (v->DynamicMetadataVMEnabled == true) *Tdmdl = TWait + Tvm_trips + trip_to_mem; else *Tdmdl = TWait + UrgentExtraLatency; #ifdef __DML_VBA_ALLOW_DELTA__ - if (DynamicMetadataEnable == false) + if (v->DynamicMetadataEnable[k] == false) *Tdmdl = 0.0; #endif - if (DynamicMetadataEnable == true) { + if (v->DynamicMetadataEnable[k] == true) { if (VStartup * LineTime < *TSetup + *Tdmdl + Tdmbf + Tdmec + Tdmsks) { *NotEnoughTimeForDynamicMetadata = true; #ifdef __DML_VBA_DEBUG__ @@ -3528,17 +3515,17 @@ bool dml32_CalculatePrefetchSchedule( *NotEnoughTimeForDynamicMetadata = false; } - *Tdmdl_vm = (DynamicMetadataEnable == true && DynamicMetadataVMEnabled == true && - GPUVMEnable == true ? TWait + Tvm_trips : 0); + *Tdmdl_vm = (v->DynamicMetadataEnable[k] == true && v->DynamicMetadataVMEnabled == true && + v->GPUVMEnable == true ? TWait + Tvm_trips : 0); if (myPipe->ScalerEnabled) - DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCL; + DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + v->DPPCLKDelaySCL; else - DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCLLBOnly; + DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + v->DPPCLKDelaySCLLBOnly; - DPPCycles = DPPCycles + myPipe->NumberOfCursors * DPPCLKDelayCNVCCursor; + DPPCycles = DPPCycles + myPipe->NumberOfCursors * v->DPPCLKDelayCNVCCursor; - DISPCLKCycles = DISPCLKDelaySubtotal; + DISPCLKCycles = v->DISPCLKDelaySubtotal; if (myPipe->Dppclk == 0.0 || myPipe->Dispclk == 0.0) return true; @@ -3564,7 +3551,7 @@ bool dml32_CalculatePrefetchSchedule( dml_print("DML::%s: DSTXAfterScaler: %d\n", __func__, *DSTXAfterScaler); #endif - if (OutputFormat == dm_420 || (myPipe->InterlaceEnable && myPipe->ProgressiveToInterlaceUnitInOPP)) + if (v->OutputFormat[k] == dm_420 || (myPipe->InterlaceEnable && myPipe->ProgressiveToInterlaceUnitInOPP)) *DSTYAfterScaler = 1; else *DSTYAfterScaler = 0; @@ -3581,13 +3568,13 @@ bool dml32_CalculatePrefetchSchedule( Tr0_trips = trip_to_mem * (HostVMDynamicLevelsTrips + 1); - if (GPUVMEnable == true) { + if (v->GPUVMEnable == true) { Tvm_trips_rounded = dml_ceil(4.0 * Tvm_trips / LineTime, 1.0) / 4.0 * LineTime; Tr0_trips_rounded = dml_ceil(4.0 * Tr0_trips / LineTime, 1.0) / 4.0 * LineTime; - if (GPUVMPageTableLevels >= 3) { + if (v->GPUVMMaxPageTableLevels >= 3) { *Tno_bw = UrgentExtraLatency + trip_to_mem * - (double) ((GPUVMPageTableLevels - 2) * (HostVMDynamicLevelsTrips + 1) - 1); - } else if (GPUVMPageTableLevels == 1 && myPipe->DCCEnable != true) { + (double) ((v->GPUVMMaxPageTableLevels - 2) * (HostVMDynamicLevelsTrips + 1) - 1); + } else if (v->GPUVMMaxPageTableLevels == 1 && myPipe->DCCEnable != true) { Tr0_trips_rounded = dml_ceil(4.0 * UrgentExtraLatency / LineTime, 1.0) / 4.0 * LineTime; // VBA_ERROR *Tno_bw = UrgentExtraLatency; @@ -3622,7 +3609,7 @@ bool dml32_CalculatePrefetchSchedule( min_Lsw = dml_max(min_Lsw, 1.0); Lsw_oto = dml_ceil(4.0 * dml_max(prefetch_sw_bytes / prefetch_bw_oto / LineTime, min_Lsw), 1.0) / 4.0; - if (GPUVMEnable == true) { + if (v->GPUVMEnable == true) { Tvm_oto = dml_max3( Tvm_trips, *Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_oto, @@ -3630,7 +3617,7 @@ bool dml32_CalculatePrefetchSchedule( } else Tvm_oto = LineTime / 4.0; - if ((GPUVMEnable == true || myPipe->DCCEnable == true)) { + if ((v->GPUVMEnable == true || myPipe->DCCEnable == true)) { Tr0_oto = dml_max4( Tr0_trips, (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_oto, @@ -3833,7 +3820,7 @@ bool dml32_CalculatePrefetchSchedule( #endif if (prefetch_bw_equ > 0) { - if (GPUVMEnable == true) { + if (v->GPUVMEnable == true) { Tvm_equ = dml_max3(*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_equ, Tvm_trips, LineTime / 4); @@ -3841,7 +3828,7 @@ bool dml32_CalculatePrefetchSchedule( Tvm_equ = LineTime / 4; } - if ((GPUVMEnable == true || myPipe->DCCEnable == true)) { + if ((v->GPUVMEnable == true || myPipe->DCCEnable == true)) { Tr0_equ = dml_max4((MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_equ, Tr0_trips, (LineTime - Tvm_equ) / 2, LineTime / 4); @@ -4206,58 +4193,28 @@ void dml32_CalculateFlipSchedule( } // CalculateFlipSchedule void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( - bool USRRetrainingRequiredFinal, - enum dm_use_mall_for_pstate_change_mode UseMALLForPStateChange[], + struct vba_vars_st *v, unsigned int PrefetchMode, - unsigned int NumberOfActiveSurfaces, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizeTimingsFinal, - bool SynchronizeDRRDisplaysForUCLKPStateChangeFinal, - bool DRRDisplay[], - unsigned int dpte_group_bytes[], - unsigned int meta_row_height[], - unsigned int meta_row_height_chroma[], SOCParametersList mmSOCParameters, - unsigned int WritebackChunkSize, double SOCCLK, double DCFClkDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int VTaps[], - unsigned int VTapsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - unsigned int VTotal[], - unsigned int VActive[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerSurface[], double BytePerPixelDETY[], double BytePerPixelDETC[], double DSTXAfterScaler[], double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, unsigned int CompressedBufferSizeInkByte, /* Output */ - Watermarks *Watermark, enum clock_change_support *DRAMClockChangeSupport, double MaxActiveDRAMClockChangeLatencySupported[], unsigned int SubViewportLinesNeededInMALL[], @@ -4299,136 +4256,136 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( unsigned int LBLatencyHidingSourceLinesY[DC__NUM_DPP__MAX]; unsigned int LBLatencyHidingSourceLinesC[DC__NUM_DPP__MAX]; - Watermark->UrgentWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency; - Watermark->USRRetrainingWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency + v->Watermark.UrgentWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency; + v->Watermark.USRRetrainingWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency + mmSOCParameters.USRRetrainingLatency + mmSOCParameters.SMNLatency; - Watermark->DRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + Watermark->UrgentWatermark; - Watermark->FCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + Watermark->UrgentWatermark; - Watermark->StutterExitWatermark = mmSOCParameters.SRExitTime + mmSOCParameters.ExtraLatency + v->Watermark.DRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + v->Watermark.UrgentWatermark; + v->Watermark.FCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + v->Watermark.UrgentWatermark; + v->Watermark.StutterExitWatermark = mmSOCParameters.SRExitTime + mmSOCParameters.ExtraLatency + 10 / DCFClkDeepSleep; - Watermark->StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitTime + mmSOCParameters.ExtraLatency + v->Watermark.StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitTime + mmSOCParameters.ExtraLatency + 10 / DCFClkDeepSleep; - Watermark->Z8StutterExitWatermark = mmSOCParameters.SRExitZ8Time + mmSOCParameters.ExtraLatency + v->Watermark.Z8StutterExitWatermark = mmSOCParameters.SRExitZ8Time + mmSOCParameters.ExtraLatency + 10 / DCFClkDeepSleep; - Watermark->Z8StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitZ8Time + v->Watermark.Z8StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitZ8Time + mmSOCParameters.ExtraLatency + 10 / DCFClkDeepSleep; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: UrgentLatency = %f\n", __func__, mmSOCParameters.UrgentLatency); dml_print("DML::%s: ExtraLatency = %f\n", __func__, mmSOCParameters.ExtraLatency); dml_print("DML::%s: DRAMClockChangeLatency = %f\n", __func__, mmSOCParameters.DRAMClockChangeLatency); - dml_print("DML::%s: UrgentWatermark = %f\n", __func__, Watermark->UrgentWatermark); - dml_print("DML::%s: USRRetrainingWatermark = %f\n", __func__, Watermark->USRRetrainingWatermark); - dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, Watermark->DRAMClockChangeWatermark); - dml_print("DML::%s: FCLKChangeWatermark = %f\n", __func__, Watermark->FCLKChangeWatermark); - dml_print("DML::%s: StutterExitWatermark = %f\n", __func__, Watermark->StutterExitWatermark); - dml_print("DML::%s: StutterEnterPlusExitWatermark = %f\n", __func__, Watermark->StutterEnterPlusExitWatermark); - dml_print("DML::%s: Z8StutterExitWatermark = %f\n", __func__, Watermark->Z8StutterExitWatermark); + dml_print("DML::%s: UrgentWatermark = %f\n", __func__, v->Watermark.UrgentWatermark); + dml_print("DML::%s: USRRetrainingWatermark = %f\n", __func__, v->Watermark.USRRetrainingWatermark); + dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, v->Watermark.DRAMClockChangeWatermark); + dml_print("DML::%s: FCLKChangeWatermark = %f\n", __func__, v->Watermark.FCLKChangeWatermark); + dml_print("DML::%s: StutterExitWatermark = %f\n", __func__, v->Watermark.StutterExitWatermark); + dml_print("DML::%s: StutterEnterPlusExitWatermark = %f\n", __func__, v->Watermark.StutterEnterPlusExitWatermark); + dml_print("DML::%s: Z8StutterExitWatermark = %f\n", __func__, v->Watermark.Z8StutterExitWatermark); dml_print("DML::%s: Z8StutterEnterPlusExitWatermark = %f\n", - __func__, Watermark->Z8StutterEnterPlusExitWatermark); + __func__, v->Watermark.Z8StutterEnterPlusExitWatermark); #endif TotalActiveWriteback = 0; - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - if (WritebackEnable[k] == true) + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + if (v->WritebackEnable[k] == true) TotalActiveWriteback = TotalActiveWriteback + 1; } if (TotalActiveWriteback <= 1) { - Watermark->WritebackUrgentWatermark = mmSOCParameters.WritebackLatency; + v->Watermark.WritebackUrgentWatermark = mmSOCParameters.WritebackLatency; } else { - Watermark->WritebackUrgentWatermark = mmSOCParameters.WritebackLatency - + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->Watermark.WritebackUrgentWatermark = mmSOCParameters.WritebackLatency + + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } - if (USRRetrainingRequiredFinal) - Watermark->WritebackUrgentWatermark = Watermark->WritebackUrgentWatermark + if (v->USRRetrainingRequiredFinal) + v->Watermark.WritebackUrgentWatermark = v->Watermark.WritebackUrgentWatermark + mmSOCParameters.USRRetrainingLatency; if (TotalActiveWriteback <= 1) { - Watermark->WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + v->Watermark.WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + mmSOCParameters.WritebackLatency; - Watermark->WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + v->Watermark.WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + mmSOCParameters.WritebackLatency; } else { - Watermark->WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency - + mmSOCParameters.WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; - Watermark->WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency - + mmSOCParameters.WritebackLatency + WritebackChunkSize * 1024 / 32 / SOCCLK; + v->Watermark.WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + + mmSOCParameters.WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->Watermark.WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + + mmSOCParameters.WritebackLatency + v->WritebackChunkSize * 1024 / 32 / SOCCLK; } - if (USRRetrainingRequiredFinal) - Watermark->WritebackDRAMClockChangeWatermark = Watermark->WritebackDRAMClockChangeWatermark + if (v->USRRetrainingRequiredFinal) + v->Watermark.WritebackDRAMClockChangeWatermark = v->Watermark.WritebackDRAMClockChangeWatermark + mmSOCParameters.USRRetrainingLatency; - if (USRRetrainingRequiredFinal) - Watermark->WritebackFCLKChangeWatermark = Watermark->WritebackFCLKChangeWatermark + if (v->USRRetrainingRequiredFinal) + v->Watermark.WritebackFCLKChangeWatermark = v->Watermark.WritebackFCLKChangeWatermark + mmSOCParameters.USRRetrainingLatency; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: WritebackDRAMClockChangeWatermark = %f\n", - __func__, Watermark->WritebackDRAMClockChangeWatermark); - dml_print("DML::%s: WritebackFCLKChangeWatermark = %f\n", __func__, Watermark->WritebackFCLKChangeWatermark); - dml_print("DML::%s: WritebackUrgentWatermark = %f\n", __func__, Watermark->WritebackUrgentWatermark); - dml_print("DML::%s: USRRetrainingRequiredFinal = %d\n", __func__, USRRetrainingRequiredFinal); + __func__, v->Watermark.WritebackDRAMClockChangeWatermark); + dml_print("DML::%s: WritebackFCLKChangeWatermark = %f\n", __func__, v->Watermark.WritebackFCLKChangeWatermark); + dml_print("DML::%s: WritebackUrgentWatermark = %f\n", __func__, v->Watermark.WritebackUrgentWatermark); + dml_print("DML::%s: v->USRRetrainingRequiredFinal = %d\n", __func__, v->USRRetrainingRequiredFinal); dml_print("DML::%s: USRRetrainingLatency = %f\n", __func__, mmSOCParameters.USRRetrainingLatency); #endif - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - TotalPixelBW = TotalPixelBW + DPPPerSurface[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] + - SwathWidthC[k] * BytePerPixelDETC[k] * VRatioChroma[k]) / (HTotal[k] / PixelClock[k]); + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + TotalPixelBW = TotalPixelBW + DPPPerSurface[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] + + SwathWidthC[k] * BytePerPixelDETC[k] * v->VRatioChroma[k]) / (v->HTotal[k] / v->PixelClock[k]); } - for (k = 0; k < NumberOfActiveSurfaces; ++k) { + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { - LBLatencyHidingSourceLinesY[k] = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (VTaps[k] - 1); - LBLatencyHidingSourceLinesC[k] = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTapsChroma[k] - 1); + LBLatencyHidingSourceLinesY[k] = dml_min((double) v->MaxLineBufferLines, dml_floor(v->LineBufferSizeFinal / v->LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(v->HRatio[k], 1.0)), 1)) - (v->vtaps[k] - 1); + LBLatencyHidingSourceLinesC[k] = dml_min((double) v->MaxLineBufferLines, dml_floor(v->LineBufferSizeFinal / v->LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(v->HRatioChroma[k], 1.0)), 1)) - (v->VTAPsChroma[k] - 1); #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: k=%d, MaxLineBufferLines = %d\n", __func__, k, MaxLineBufferLines); - dml_print("DML::%s: k=%d, LineBufferSize = %d\n", __func__, k, LineBufferSize); - dml_print("DML::%s: k=%d, LBBitPerPixel = %d\n", __func__, k, LBBitPerPixel[k]); - dml_print("DML::%s: k=%d, HRatio = %f\n", __func__, k, HRatio[k]); - dml_print("DML::%s: k=%d, VTaps = %d\n", __func__, k, VTaps[k]); + dml_print("DML::%s: k=%d, v->MaxLineBufferLines = %d\n", __func__, k, v->MaxLineBufferLines); + dml_print("DML::%s: k=%d, v->LineBufferSizeFinal = %d\n", __func__, k, v->LineBufferSizeFinal); + dml_print("DML::%s: k=%d, v->LBBitPerPixel = %d\n", __func__, k, v->LBBitPerPixel[k]); + dml_print("DML::%s: k=%d, v->HRatio = %f\n", __func__, k, v->HRatio[k]); + dml_print("DML::%s: k=%d, v->vtaps = %d\n", __func__, k, v->vtaps[k]); #endif - EffectiveLBLatencyHidingY = LBLatencyHidingSourceLinesY[k] / VRatio[k] * (HTotal[k] / PixelClock[k]); - EffectiveLBLatencyHidingC = LBLatencyHidingSourceLinesC[k] / VRatioChroma[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingY = LBLatencyHidingSourceLinesY[k] / v->VRatio[k] * (v->HTotal[k] / v->PixelClock[k]); + EffectiveLBLatencyHidingC = LBLatencyHidingSourceLinesC[k] / v->VRatioChroma[k] * (v->HTotal[k] / v->PixelClock[k]); EffectiveDETBufferSizeY = DETBufferSizeY[k]; if (UnboundedRequestEnabled) { EffectiveDETBufferSizeY = EffectiveDETBufferSizeY + CompressedBufferSizeInkByte * 1024 - * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k]) - / (HTotal[k] / PixelClock[k]) / TotalPixelBW; + * (SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k]) + / (v->HTotal[k] / v->PixelClock[k]) / TotalPixelBW; } LinesInDETY[k] = (double) EffectiveDETBufferSizeY / BytePerPixelDETY[k] / SwathWidthY[k]; LinesInDETYRoundedDownToSwath[k] = dml_floor(LinesInDETY[k], SwathHeightY[k]); - FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k]; + FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k]; ActiveClockChangeLatencyHidingY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY - - (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k]; + - (DSTXAfterScaler[k] / v->HTotal[k] + DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k]; - if (NumberOfActiveSurfaces > 1) { + if (v->NumberOfActiveSurfaces > 1) { ActiveClockChangeLatencyHidingY = ActiveClockChangeLatencyHidingY - - (1 - 1 / NumberOfActiveSurfaces) * SwathHeightY[k] * HTotal[k] - / PixelClock[k] / VRatio[k]; + - (1 - 1 / v->NumberOfActiveSurfaces) * SwathHeightY[k] * v->HTotal[k] + / v->PixelClock[k] / v->VRatio[k]; } if (BytePerPixelDETC[k] > 0) { LinesInDETC[k] = DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k]; LinesInDETCRoundedDownToSwath[k] = dml_floor(LinesInDETC[k], SwathHeightC[k]); - FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) - / VRatioChroma[k]; + FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) + / v->VRatioChroma[k]; ActiveClockChangeLatencyHidingC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC - - (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] - / PixelClock[k]; - if (NumberOfActiveSurfaces > 1) { + - (DSTXAfterScaler[k] / v->HTotal[k] + DSTYAfterScaler[k]) * v->HTotal[k] + / v->PixelClock[k]; + if (v->NumberOfActiveSurfaces > 1) { ActiveClockChangeLatencyHidingC = ActiveClockChangeLatencyHidingC - - (1 - 1 / NumberOfActiveSurfaces) * SwathHeightC[k] * HTotal[k] - / PixelClock[k] / VRatioChroma[k]; + - (1 - 1 / v->NumberOfActiveSurfaces) * SwathHeightC[k] * v->HTotal[k] + / v->PixelClock[k] / v->VRatioChroma[k]; } ActiveClockChangeLatencyHiding = dml_min(ActiveClockChangeLatencyHidingY, ActiveClockChangeLatencyHidingC); @@ -4436,24 +4393,24 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( ActiveClockChangeLatencyHiding = ActiveClockChangeLatencyHidingY; } - ActiveDRAMClockChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - Watermark->UrgentWatermark - - Watermark->DRAMClockChangeWatermark; - ActiveFCLKChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - Watermark->UrgentWatermark - - Watermark->FCLKChangeWatermark; - USRRetrainingLatencyMargin[k] = ActiveClockChangeLatencyHiding - Watermark->USRRetrainingWatermark; - - if (WritebackEnable[k]) { - WritebackLatencyHiding = WritebackInterfaceBufferSize * 1024 - / (WritebackDestinationWidth[k] * WritebackDestinationHeight[k] - / (WritebackSourceHeight[k] * HTotal[k] / PixelClock[k]) * 4); - if (WritebackPixelFormat[k] == dm_444_64) + ActiveDRAMClockChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - v->Watermark.UrgentWatermark + - v->Watermark.DRAMClockChangeWatermark; + ActiveFCLKChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - v->Watermark.UrgentWatermark + - v->Watermark.FCLKChangeWatermark; + USRRetrainingLatencyMargin[k] = ActiveClockChangeLatencyHiding - v->Watermark.USRRetrainingWatermark; + + if (v->WritebackEnable[k]) { + WritebackLatencyHiding = v->WritebackInterfaceBufferSize * 1024 + / (v->WritebackDestinationWidth[k] * v->WritebackDestinationHeight[k] + / (v->WritebackSourceHeight[k] * v->HTotal[k] / v->PixelClock[k]) * 4); + if (v->WritebackPixelFormat[k] == dm_444_64) WritebackLatencyHiding = WritebackLatencyHiding / 2; WritebackDRAMClockChangeLatencyMargin = WritebackLatencyHiding - - Watermark->WritebackDRAMClockChangeWatermark; + - v->Watermark.WritebackDRAMClockChangeWatermark; WritebackFCLKChangeLatencyMargin = WritebackLatencyHiding - - Watermark->WritebackFCLKChangeWatermark; + - v->Watermark.WritebackFCLKChangeWatermark; ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMargin[k], WritebackFCLKChangeLatencyMargin); @@ -4461,22 +4418,22 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( WritebackDRAMClockChangeLatencyMargin); } MaxActiveDRAMClockChangeLatencySupported[k] = - (UseMALLForPStateChange[k] == dm_use_mall_pstate_change_phantom_pipe) ? + (v->UsesMALLForPStateChange[k] == dm_use_mall_pstate_change_phantom_pipe) ? 0 : (ActiveDRAMClockChangeLatencyMargin[k] + mmSOCParameters.DRAMClockChangeLatency); } - for (i = 0; i < NumberOfActiveSurfaces; ++i) { - for (j = 0; j < NumberOfActiveSurfaces; ++j) { + for (i = 0; i < v->NumberOfActiveSurfaces; ++i) { + for (j = 0; j < v->NumberOfActiveSurfaces; ++j) { if (i == j || - (BlendingAndTiming[i] == i && BlendingAndTiming[j] == i) || - (BlendingAndTiming[j] == j && BlendingAndTiming[i] == j) || - (BlendingAndTiming[i] == BlendingAndTiming[j] && BlendingAndTiming[i] != i) || - (SynchronizeTimingsFinal && PixelClock[i] == PixelClock[j] && - HTotal[i] == HTotal[j] && VTotal[i] == VTotal[j] && - VActive[i] == VActive[j]) || (SynchronizeDRRDisplaysForUCLKPStateChangeFinal && - (DRRDisplay[i] || DRRDisplay[j]))) { + (v->BlendingAndTiming[i] == i && v->BlendingAndTiming[j] == i) || + (v->BlendingAndTiming[j] == j && v->BlendingAndTiming[i] == j) || + (v->BlendingAndTiming[i] == v->BlendingAndTiming[j] && v->BlendingAndTiming[i] != i) || + (v->SynchronizeTimingsFinal && v->PixelClock[i] == v->PixelClock[j] && + v->HTotal[i] == v->HTotal[j] && v->VTotal[i] == v->VTotal[j] && + v->VActive[i] == v->VActive[j]) || (v->SynchronizeDRRDisplaysForUCLKPStateChangeFinal && + (v->DRRDisplay[i] || v->DRRDisplay[j]))) { SynchronizedSurfaces[i][j] = true; } else { SynchronizedSurfaces[i][j] = false; @@ -4484,8 +4441,8 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( } } - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - if ((UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + if ((v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && (!FoundFirstSurfaceWithMinActiveFCLKChangeMargin || ActiveFCLKChangeLatencyMargin[k] < MinActiveFCLKChangeMargin)) { FoundFirstSurfaceWithMinActiveFCLKChangeMargin = true; @@ -4497,9 +4454,9 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( *MinActiveFCLKChangeLatencySupported = MinActiveFCLKChangeMargin + mmSOCParameters.FCLKChangeLatency; SameTimingForFCLKChange = true; - for (k = 0; k < NumberOfActiveSurfaces; ++k) { + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { if (!SynchronizedSurfaces[k][SurfaceWithMinActiveFCLKChangeMargin]) { - if ((UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && + if ((v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && (SameTimingForFCLKChange || ActiveFCLKChangeLatencyMargin[k] < SecondMinActiveFCLKChangeMarginOneDisplayInVBLank)) { @@ -4519,17 +4476,17 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( } *USRRetrainingSupport = true; - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - if ((UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + if ((v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && (USRRetrainingLatencyMargin[k] < 0)) { *USRRetrainingSupport = false; } } - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - if (UseMALLForPStateChange[k] != dm_use_mall_pstate_change_full_frame && - UseMALLForPStateChange[k] != dm_use_mall_pstate_change_sub_viewport && - UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe && + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + if (v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_full_frame && + v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_sub_viewport && + v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe && ActiveDRAMClockChangeLatencyMargin[k] < 0) { if (PrefetchMode > 0) { DRAMClockChangeSupportNumber = 2; @@ -4543,10 +4500,10 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( } } - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - if (UseMALLForPStateChange[k] == dm_use_mall_pstate_change_full_frame) + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + if (v->UsesMALLForPStateChange[k] == dm_use_mall_pstate_change_full_frame) DRAMClockChangeMethod = 1; - else if (UseMALLForPStateChange[k] == dm_use_mall_pstate_change_sub_viewport) + else if (v->UsesMALLForPStateChange[k] == dm_use_mall_pstate_change_sub_viewport) DRAMClockChangeMethod = 2; } @@ -4573,16 +4530,16 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( *DRAMClockChangeSupport = dm_dram_clock_change_unsupported; } - for (k = 0; k < NumberOfActiveSurfaces; ++k) { + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { unsigned int dst_y_pstate; unsigned int src_y_pstate_l; unsigned int src_y_pstate_c; unsigned int src_y_ahead_l, src_y_ahead_c, sub_vp_lines_l, sub_vp_lines_c; - dst_y_pstate = dml_ceil((mmSOCParameters.DRAMClockChangeLatency + mmSOCParameters.UrgentLatency) / (HTotal[k] / PixelClock[k]), 1); - src_y_pstate_l = dml_ceil(dst_y_pstate * VRatio[k], SwathHeightY[k]); + dst_y_pstate = dml_ceil((mmSOCParameters.DRAMClockChangeLatency + mmSOCParameters.UrgentLatency) / (v->HTotal[k] / v->PixelClock[k]), 1); + src_y_pstate_l = dml_ceil(dst_y_pstate * v->VRatio[k], SwathHeightY[k]); src_y_ahead_l = dml_floor(DETBufferSizeY[k] / BytePerPixelDETY[k] / SwathWidthY[k], SwathHeightY[k]) + LBLatencyHidingSourceLinesY[k]; - sub_vp_lines_l = src_y_pstate_l + src_y_ahead_l + meta_row_height[k]; + sub_vp_lines_l = src_y_pstate_l + src_y_ahead_l + v->meta_row_height[k]; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: k=%d, DETBufferSizeY = %d\n", __func__, k, DETBufferSizeY[k]); @@ -4593,21 +4550,21 @@ dml_print("DML::%s: k=%d, LBLatencyHidingSourceLinesY = %d\n", __func__, k, LBL dml_print("DML::%s: k=%d, dst_y_pstate = %d\n", __func__, k, dst_y_pstate); dml_print("DML::%s: k=%d, src_y_pstate_l = %d\n", __func__, k, src_y_pstate_l); dml_print("DML::%s: k=%d, src_y_ahead_l = %d\n", __func__, k, src_y_ahead_l); -dml_print("DML::%s: k=%d, meta_row_height = %d\n", __func__, k, meta_row_height[k]); +dml_print("DML::%s: k=%d, v->meta_row_height = %d\n", __func__, k, v->meta_row_height[k]); dml_print("DML::%s: k=%d, sub_vp_lines_l = %d\n", __func__, k, sub_vp_lines_l); #endif SubViewportLinesNeededInMALL[k] = sub_vp_lines_l; if (BytePerPixelDETC[k] > 0) { - src_y_pstate_c = dml_ceil(dst_y_pstate * VRatioChroma[k], SwathHeightC[k]); + src_y_pstate_c = dml_ceil(dst_y_pstate * v->VRatioChroma[k], SwathHeightC[k]); src_y_ahead_c = dml_floor(DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k], SwathHeightC[k]) + LBLatencyHidingSourceLinesC[k]; - sub_vp_lines_c = src_y_pstate_c + src_y_ahead_c + meta_row_height_chroma[k]; + sub_vp_lines_c = src_y_pstate_c + src_y_ahead_c + v->meta_row_height_chroma[k]; SubViewportLinesNeededInMALL[k] = dml_max(sub_vp_lines_l, sub_vp_lines_c); #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: k=%d, src_y_pstate_c = %d\n", __func__, k, src_y_pstate_c); dml_print("DML::%s: k=%d, src_y_ahead_c = %d\n", __func__, k, src_y_ahead_c); -dml_print("DML::%s: k=%d, meta_row_height_chroma = %d\n", __func__, k, meta_row_height_chroma[k]); +dml_print("DML::%s: k=%d, v->meta_row_height_chroma = %d\n", __func__, k, v->meta_row_height_chroma[k]); dml_print("DML::%s: k=%d, sub_vp_lines_c = %d\n", __func__, k, sub_vp_lines_c); #endif } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h index d293856ba906..924e361ad243 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h @@ -30,6 +30,7 @@ #include "os_types.h" #include "../dc_features.h" #include "../display_mode_structs.h" +#include "dml/display_mode_vba.h" unsigned int dml32_dscceComputeDelay( unsigned int bpc, @@ -712,28 +713,14 @@ double dml32_CalculateExtraLatency( unsigned int HostVMMaxNonCachedPageTableLevels); bool dml32_CalculatePrefetchSchedule( + struct vba_vars_st *v, + unsigned int k, double HostVMInefficiencyFactor, DmlPipe *myPipe, unsigned int DSCDelay, - double DPPCLKDelaySubtotalPlusCNVCFormater, - double DPPCLKDelaySCL, - double DPPCLKDelaySCLLBOnly, - double DPPCLKDelayCNVCCursor, - double DISPCLKDelaySubtotal, unsigned int DPP_RECOUT_WIDTH, - enum output_format_class OutputFormat, - unsigned int MaxInterDCNTileRepeaters, unsigned int VStartup, unsigned int MaxVStartup, - unsigned int GPUVMPageTableLevels, - bool GPUVMEnable, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - double HostVMMinPageSize, - bool DynamicMetadataEnable, - bool DynamicMetadataVMEnabled, - int DynamicMetadataLinesBeforeActiveRequired, - unsigned int DynamicMetadataTransmittedBytes, double UrgentLatency, double UrgentExtraLatency, double TCalc, @@ -807,58 +794,28 @@ void dml32_CalculateFlipSchedule( bool *ImmediateFlipSupportedForPipe); void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( - bool USRRetrainingRequiredFinal, - enum dm_use_mall_for_pstate_change_mode UseMALLForPStateChange[], + struct vba_vars_st *v, unsigned int PrefetchMode, - unsigned int NumberOfActiveSurfaces, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizeTimingsFinal, - bool SynchronizeDRRDisplaysForUCLKPStateChangeFinal, - bool DRRDisplay[], - unsigned int dpte_group_bytes[], - unsigned int meta_row_height[], - unsigned int meta_row_height_chroma[], SOCParametersList mmSOCParameters, - unsigned int WritebackChunkSize, double SOCCLK, double DCFClkDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int VTaps[], - unsigned int VTapsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - unsigned int VTotal[], - unsigned int VActive[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerSurface[], double BytePerPixelDETY[], double BytePerPixelDETC[], double DSTXAfterScaler[], double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, unsigned int CompressedBufferSizeInkByte, /* Output */ - Watermarks *Watermark, enum clock_change_support *DRAMClockChangeSupport, double MaxActiveDRAMClockChangeLatencySupported[], unsigned int SubViewportLinesNeededInMALL[], diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c index 5d27ff0ebb5f..f5400eda07a5 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c @@ -35,6 +35,8 @@ #include "dcn30/display_rq_dlg_calc_30.h" #include "dcn31/display_mode_vba_31.h" #include "dcn31/display_rq_dlg_calc_31.h" +#include "dcn314/display_mode_vba_314.h" +#include "dcn314/display_rq_dlg_calc_314.h" #include "dcn32/display_mode_vba_32.h" #include "dcn32/display_rq_dlg_calc_32.h" #include "dml_logger.h" @@ -74,6 +76,13 @@ const struct dml_funcs dml31_funcs = { .rq_dlg_get_rq_reg = dml31_rq_dlg_get_rq_reg }; +const struct dml_funcs dml314_funcs = { + .validate = dml314_ModeSupportAndSystemConfigurationFull, + .recalculate = dml314_recalculate, + .rq_dlg_get_dlg_reg = dml314_rq_dlg_get_dlg_reg, + .rq_dlg_get_rq_reg = dml314_rq_dlg_get_rq_reg +}; + const struct dml_funcs dml32_funcs = { .validate = dml32_ModeSupportAndSystemConfigurationFull, .recalculate = dml32_recalculate, @@ -107,6 +116,9 @@ void dml_init_instance(struct display_mode_lib *lib, case DML_PROJECT_DCN31_FPGA: lib->funcs = dml31_funcs; break; + case DML_PROJECT_DCN314: + lib->funcs = dml314_funcs; + break; case DML_PROJECT_DCN32: lib->funcs = dml32_funcs; break; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h index 2bdd6ed22611..b1878a1440e2 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h @@ -41,6 +41,7 @@ enum dml_project { DML_PROJECT_DCN30, DML_PROJECT_DCN31, DML_PROJECT_DCN31_FPGA, + DML_PROJECT_DCN314, DML_PROJECT_DCN32, }; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h index 492aec634b68..2051ddaa641a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h @@ -651,10 +651,10 @@ struct vba_vars_st { unsigned int OutputTypeAndRatePerState[DC__VOLTAGE_STATES][DC__NUM_DPP__MAX]; double RequiredDISPCLKPerSurface[DC__VOLTAGE_STATES][2][DC__NUM_DPP__MAX]; - unsigned int MicroTileHeightY[DC__NUM_DPP__MAX]; - unsigned int MicroTileHeightC[DC__NUM_DPP__MAX]; - unsigned int MicroTileWidthY[DC__NUM_DPP__MAX]; - unsigned int MicroTileWidthC[DC__NUM_DPP__MAX]; + unsigned int MacroTileHeightY[DC__NUM_DPP__MAX]; + unsigned int MacroTileHeightC[DC__NUM_DPP__MAX]; + unsigned int MacroTileWidthY[DC__NUM_DPP__MAX]; + unsigned int MacroTileWidthC[DC__NUM_DPP__MAX]; bool ImmediateFlipRequiredFinal; bool DCCProgrammingAssumesScanDirectionUnknownFinal; bool EnoughWritebackUnits; @@ -800,8 +800,6 @@ struct vba_vars_st { double PSCL_FACTOR[DC__NUM_DPP__MAX]; double PSCL_FACTOR_CHROMA[DC__NUM_DPP__MAX]; double MaximumVStartup[DC__VOLTAGE_STATES][2][DC__NUM_DPP__MAX]; - unsigned int MacroTileWidthY[DC__NUM_DPP__MAX]; - unsigned int MacroTileWidthC[DC__NUM_DPP__MAX]; double AlignedDCCMetaPitch[DC__NUM_DPP__MAX]; double AlignedYPitch[DC__NUM_DPP__MAX]; double AlignedCPitch[DC__NUM_DPP__MAX]; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h index 5d2b028e5dad..d9f1b0a4fbd4 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h @@ -214,6 +214,7 @@ struct dummy_pstate_entry { struct clk_bw_params { unsigned int vram_type; unsigned int num_channels; + unsigned int dram_channel_width_bytes; unsigned int dispclk_vco_khz; unsigned int dc_mode_softmax_memclk; struct clk_limit_table clk_table; diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c index 859ffd8725c5..04f7656906ca 100644 --- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c +++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c @@ -1600,6 +1600,7 @@ static void interpolate_user_regamma(uint32_t hw_points_num, struct fixed31_32 lut2; struct fixed31_32 delta_lut; struct fixed31_32 delta_index; + const struct fixed31_32 one = dc_fixpt_from_int(1); i = 0; /* fixed_pt library has problems handling too small values */ @@ -1628,6 +1629,9 @@ static void interpolate_user_regamma(uint32_t hw_points_num, } else hw_x = coordinates_x[i].x; + if (dc_fixpt_le(one, hw_x)) + hw_x = one; + norm_x = dc_fixpt_mul(norm_factor, hw_x); index = dc_fixpt_floor(norm_x); if (index < 0 || index > 255) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 6db67f082d91..644ea150e075 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -368,6 +368,17 @@ static void sienna_cichlid_check_bxco_support(struct smu_context *smu) smu_baco->platform_support = (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : false; + + /* + * Disable BACO entry/exit completely on below SKUs to + * avoid hardware intermittent failures. + */ + if (((adev->pdev->device == 0x73A1) && + (adev->pdev->revision == 0x00)) || + ((adev->pdev->device == 0x73BF) && + (adev->pdev->revision == 0xCF))) + smu_baco->platform_support = false; + } } |