diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2026-01-09 06:04:05 -1000 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2026-01-09 06:04:05 -1000 |
| commit | cbd4480cfac54dd4e9f7fb9ac2e0226ea38fecbb (patch) | |
| tree | b1e0dfbea9b5c66631bf904b26e074dbaa6d8d74 /drivers | |
| parent | 2bfe3e0da6e619dbf6157dfad896307ab6b9a58a (diff) | |
| parent | f6eac56d6bf2026437b606a69aff903941282f9a (diff) | |
Merge tag 'drm-fixes-2026-01-09' of https://gitlab.freedesktop.org/drm/kernel
Pull drm fixes from Dave Airlie:
"I missed the drm-rust fixes tree for last week, so this catches up on
that, along with amdgpu, and then some misc fixes across a few
drivers. I hadn't got an xe pull by the time I sent this, I suspect
one will arrive 10 mins after, but I don't think there is anything
that can't wait for next week.
Things seem to have picked up a little with people coming back from
holidays,
MAINTAINERS:
- Fix Nova GPU driver git links
- Fix typo in TYR driver entry preventing correct behavior of
scripts/get_maintainer.pl
- Exclude TYR driver from DRM MISC
nova-core:
- Correctly select RUST_FW_LOADER_ABSTRACTIONS to prevent build
errors
- Regenerate nova-core bindgen bindings with '--explicit-padding' to
avoid uninitialized bytes
- Fix length of received GSP messages, due to miscalculated message
payload size
- Regenerate bindings to derive MaybeZeroable
- Use a bindings alias to derive the firmware version
exynos:
- hdmi: replace system_wq with system_percpu_wq
pl111:
- Fix error handling in probe
mediatek/atomic/tidss:
- Fix tidss in another way and revert reordering of pre-enable and
post-disable operations, as it breaks other bridge drivers
nouveau:
- Fix regression from fwsec s/r fix
pci/vga:
- Fix multiple gpu's being reported a 'boot_display'
fb-helper:
- Fix vblank timeout during suspend/reset
amdgpu:
- Clang fixes
- Navi1x PCIe DPM fixes
- Ring reset fixes
- ISP suspend fix
- Analog DC fixes
- VPE fixes
- Mode1 reset fix
radeon:
- Variable sized array fix"
* tag 'drm-fixes-2026-01-09' of https://gitlab.freedesktop.org/drm/kernel: (32 commits)
Reapply "Revert "drm/amd: Skip power ungate during suspend for VPE""
drm/amd/display: Check NULL before calling dac_load_detection
drm/amd/pm: Disable MMIO access during SMU Mode 1 reset
drm/exynos: hdmi: replace use of system_wq with system_percpu_wq
drm/fb-helper: Fix vblank timeout during suspend/reset
PCI/VGA: Don't assume the only VGA device on a system is `boot_vga`
drm/amdgpu: Fix query for VPE block_type and ip_count
drm/amd/display: Add missing encoder setup to DACnEncoderControl
drm/amd/display: Correct color depth for SelectCRTC_Source
drm/amd/amdgpu: Fix SMU warning during isp suspend-resume
drm/amdgpu: always backup and reemit fences
drm/amdgpu: don't reemit ring contents more than once
drm/amd/pm: force send pcie parmater on navi1x
drm/amd/pm: fix wrong pcie parameter on navi1x
drm/radeon: Remove __counted_by from ClockInfoArray.clockInfo[]
drm/amd/display: Reduce number of arguments of dcn30's CalculateWatermarksAndDRAMSpeedChangeSupport()
drm/amd/display: Reduce number of arguments of dcn30's CalculatePrefetchSchedule()
drm/amd/display: Apply e4479aecf658 to dml
nouveau: don't attempt fwsec on sb on newer platforms
drm/tidss: Fix enable/disable order
...
Diffstat (limited to 'drivers')
38 files changed, 632 insertions, 627 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 12201b8e99b3..d5c44bd34d45 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3445,11 +3445,10 @@ int amdgpu_device_set_pg_state(struct amdgpu_device *adev, (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX || adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SDMA)) continue; - /* skip CG for VCE/UVD/VPE, it's handled specially */ + /* skip CG for VCE/UVD, it's handled specially */ if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCN && - adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VPE && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_JPEG && adev->ip_blocks[i].version->funcs->set_powergating_state) { /* enable powergating to save power */ @@ -5867,6 +5866,9 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev) if (ret) goto mode1_reset_failed; + /* enable mmio access after mode 1 reset completed */ + adev->no_hw_access = false; + amdgpu_device_load_pci_state(adev->pdev); ret = amdgpu_psp_wait_for_bootloader(adev); if (ret) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index c7843e336310..06c333b2213b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -89,6 +89,16 @@ static u32 amdgpu_fence_read(struct amdgpu_ring *ring) return seq; } +static void amdgpu_fence_save_fence_wptr_start(struct amdgpu_fence *af) +{ + af->fence_wptr_start = af->ring->wptr; +} + +static void amdgpu_fence_save_fence_wptr_end(struct amdgpu_fence *af) +{ + af->fence_wptr_end = af->ring->wptr; +} + /** * amdgpu_fence_emit - emit a fence on the requested ring * @@ -116,8 +126,10 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct amdgpu_fence *af, &ring->fence_drv.lock, adev->fence_context + ring->idx, seq); + amdgpu_fence_save_fence_wptr_start(af); amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr, seq, flags | AMDGPU_FENCE_FLAG_INT); + amdgpu_fence_save_fence_wptr_end(af); amdgpu_fence_save_wptr(af); pm_runtime_get_noresume(adev_to_drm(adev)->dev); ptr = &ring->fence_drv.fences[seq & ring->fence_drv.num_fences_mask]; @@ -709,6 +721,7 @@ void amdgpu_fence_driver_guilty_force_completion(struct amdgpu_fence *af) struct amdgpu_ring *ring = af->ring; unsigned long flags; u32 seq, last_seq; + bool reemitted = false; last_seq = amdgpu_fence_read(ring) & ring->fence_drv.num_fences_mask; seq = ring->fence_drv.sync_seq & ring->fence_drv.num_fences_mask; @@ -726,7 +739,9 @@ void amdgpu_fence_driver_guilty_force_completion(struct amdgpu_fence *af) if (unprocessed && !dma_fence_is_signaled_locked(unprocessed)) { fence = container_of(unprocessed, struct amdgpu_fence, base); - if (fence == af) + if (fence->reemitted > 1) + reemitted = true; + else if (fence == af) dma_fence_set_error(&fence->base, -ETIME); else if (fence->context == af->context) dma_fence_set_error(&fence->base, -ECANCELED); @@ -734,9 +749,12 @@ void amdgpu_fence_driver_guilty_force_completion(struct amdgpu_fence *af) rcu_read_unlock(); } while (last_seq != seq); spin_unlock_irqrestore(&ring->fence_drv.lock, flags); - /* signal the guilty fence */ - amdgpu_fence_write(ring, (u32)af->base.seqno); - amdgpu_fence_process(ring); + + if (reemitted) { + /* if we've already reemitted once then just cancel everything */ + amdgpu_fence_driver_force_completion(af->ring); + af->ring->ring_backup_entries_to_copy = 0; + } } void amdgpu_fence_save_wptr(struct amdgpu_fence *af) @@ -784,10 +802,18 @@ void amdgpu_ring_backup_unprocessed_commands(struct amdgpu_ring *ring, /* save everything if the ring is not guilty, otherwise * just save the content from other contexts. */ - if (!guilty_fence || (fence->context != guilty_fence->context)) + if (!fence->reemitted && + (!guilty_fence || (fence->context != guilty_fence->context))) { amdgpu_ring_backup_unprocessed_command(ring, wptr, fence->wptr); + } else if (!fence->reemitted) { + /* always save the fence */ + amdgpu_ring_backup_unprocessed_command(ring, + fence->fence_wptr_start, + fence->fence_wptr_end); + } wptr = fence->wptr; + fence->reemitted++; } rcu_read_unlock(); } while (last_seq != seq); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c index 37270c4dab8d..532f83d783d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c @@ -318,12 +318,36 @@ void isp_kernel_buffer_free(void **buf_obj, u64 *gpu_addr, void **cpu_addr) } EXPORT_SYMBOL(isp_kernel_buffer_free); +static int isp_resume(struct amdgpu_ip_block *ip_block) +{ + struct amdgpu_device *adev = ip_block->adev; + struct amdgpu_isp *isp = &adev->isp; + + if (isp->funcs->hw_resume) + return isp->funcs->hw_resume(isp); + + return -ENODEV; +} + +static int isp_suspend(struct amdgpu_ip_block *ip_block) +{ + struct amdgpu_device *adev = ip_block->adev; + struct amdgpu_isp *isp = &adev->isp; + + if (isp->funcs->hw_suspend) + return isp->funcs->hw_suspend(isp); + + return -ENODEV; +} + static const struct amd_ip_funcs isp_ip_funcs = { .name = "isp_ip", .early_init = isp_early_init, .hw_init = isp_hw_init, .hw_fini = isp_hw_fini, .is_idle = isp_is_idle, + .suspend = isp_suspend, + .resume = isp_resume, .set_clockgating_state = isp_set_clockgating_state, .set_powergating_state = isp_set_powergating_state, }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h index d6f4ffa4c97c..9a5d2b1dff9e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h @@ -38,6 +38,8 @@ struct amdgpu_isp; struct isp_funcs { int (*hw_init)(struct amdgpu_isp *isp); int (*hw_fini)(struct amdgpu_isp *isp); + int (*hw_suspend)(struct amdgpu_isp *isp); + int (*hw_resume)(struct amdgpu_isp *isp); }; struct amdgpu_isp { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 6ee77f431d56..f65edd80cabf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -201,6 +201,9 @@ static enum amd_ip_block_type type = (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_JPEG)) ? AMD_IP_BLOCK_TYPE_JPEG : AMD_IP_BLOCK_TYPE_VCN; break; + case AMDGPU_HW_IP_VPE: + type = AMD_IP_BLOCK_TYPE_VPE; + break; default: type = AMD_IP_BLOCK_TYPE_NUM; break; @@ -721,6 +724,9 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) case AMD_IP_BLOCK_TYPE_UVD: count = adev->uvd.num_uvd_inst; break; + case AMD_IP_BLOCK_TYPE_VPE: + count = adev->vpe.num_instances; + break; /* For all other IP block types not listed in the switch statement * the ip status is valid here and the instance count is one. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 7a27c6c4bb44..055437d4edf9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -144,10 +144,15 @@ struct amdgpu_fence { struct amdgpu_ring *ring; ktime_t start_timestamp; - /* wptr for the fence for resets */ + /* wptr for the total submission for resets */ u64 wptr; /* fence context for resets */ u64 context; + /* has this fence been reemitted */ + unsigned int reemitted; + /* wptr for the fence for the submission */ + u64 fence_wptr_start; + u64 fence_wptr_end; }; extern const struct drm_sched_backend_ops amdgpu_sched_ops; diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c index 4258d3e0b706..0002bcc6c4ec 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c @@ -26,6 +26,7 @@ */ #include <linux/gpio/machine.h> +#include <linux/pm_runtime.h> #include "amdgpu.h" #include "isp_v4_1_1.h" @@ -145,6 +146,9 @@ static int isp_genpd_add_device(struct device *dev, void *data) return -ENODEV; } + /* The devices will be managed by the pm ops from the parent */ + dev_pm_syscore_device(dev, true); + exit: /* Continue to add */ return 0; @@ -177,12 +181,47 @@ static int isp_genpd_remove_device(struct device *dev, void *data) drm_err(&adev->ddev, "Failed to remove dev from genpd %d\n", ret); return -ENODEV; } + dev_pm_syscore_device(dev, false); exit: /* Continue to remove */ return 0; } +static int isp_suspend_device(struct device *dev, void *data) +{ + return pm_runtime_force_suspend(dev); +} + +static int isp_resume_device(struct device *dev, void *data) +{ + return pm_runtime_force_resume(dev); +} + +static int isp_v4_1_1_hw_suspend(struct amdgpu_isp *isp) +{ + int r; + + r = device_for_each_child(isp->parent, NULL, + isp_suspend_device); + if (r) + dev_err(isp->parent, "failed to suspend hw devices (%d)\n", r); + + return r; +} + +static int isp_v4_1_1_hw_resume(struct amdgpu_isp *isp) +{ + int r; + + r = device_for_each_child(isp->parent, NULL, + isp_resume_device); + if (r) + dev_err(isp->parent, "failed to resume hw device (%d)\n", r); + + return r; +} + static int isp_v4_1_1_hw_init(struct amdgpu_isp *isp) { const struct software_node *amd_camera_node, *isp4_node; @@ -369,6 +408,8 @@ static int isp_v4_1_1_hw_fini(struct amdgpu_isp *isp) static const struct isp_funcs isp_v4_1_1_funcs = { .hw_init = isp_v4_1_1_hw_init, .hw_fini = isp_v4_1_1_hw_fini, + .hw_suspend = isp_v4_1_1_hw_suspend, + .hw_resume = isp_v4_1_1_hw_resume, }; void isp_v4_1_1_set_isp_funcs(struct amdgpu_isp *isp) diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c index d1471f34e419..9f11e6ca4051 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c @@ -763,14 +763,14 @@ static enum bp_result bios_parser_encoder_control( return BP_RESULT_FAILURE; return bp->cmd_tbl.dac1_encoder_control( - bp, cntl->action == ENCODER_CONTROL_ENABLE, + bp, cntl->action, cntl->pixel_clock, ATOM_DAC1_PS2); } else if (cntl->engine_id == ENGINE_ID_DACB) { if (!bp->cmd_tbl.dac2_encoder_control) return BP_RESULT_FAILURE; return bp->cmd_tbl.dac2_encoder_control( - bp, cntl->action == ENCODER_CONTROL_ENABLE, + bp, cntl->action, cntl->pixel_clock, ATOM_DAC1_PS2); } diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.c b/drivers/gpu/drm/amd/display/dc/bios/command_table.c index 22457f417e65..76a3559f0ddc 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.c @@ -1797,7 +1797,30 @@ static enum bp_result select_crtc_source_v3( ¶ms.ucEncodeMode)) return BP_RESULT_BADINPUT; - params.ucDstBpc = bp_params->bit_depth; + switch (bp_params->color_depth) { + case COLOR_DEPTH_UNDEFINED: + params.ucDstBpc = PANEL_BPC_UNDEFINE; + break; + case COLOR_DEPTH_666: + params.ucDstBpc = PANEL_6BIT_PER_COLOR; + break; + default: + case COLOR_DEPTH_888: + params.ucDstBpc = PANEL_8BIT_PER_COLOR; + break; + case COLOR_DEPTH_101010: + params.ucDstBpc = PANEL_10BIT_PER_COLOR; + break; + case COLOR_DEPTH_121212: + params.ucDstBpc = PANEL_12BIT_PER_COLOR; + break; + case COLOR_DEPTH_141414: + dm_error("14-bit color not supported by SelectCRTC_Source v3\n"); + break; + case COLOR_DEPTH_161616: + params.ucDstBpc = PANEL_16BIT_PER_COLOR; + break; + } if (EXEC_BIOS_CMD_TABLE(SelectCRTC_Source, params)) result = BP_RESULT_OK; @@ -1815,12 +1838,12 @@ static enum bp_result select_crtc_source_v3( static enum bp_result dac1_encoder_control_v1( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard); static enum bp_result dac2_encoder_control_v1( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard); @@ -1846,12 +1869,15 @@ static void init_dac_encoder_control(struct bios_parser *bp) static void dac_encoder_control_prepare_params( DAC_ENCODER_CONTROL_PS_ALLOCATION *params, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard) { params->ucDacStandard = dac_standard; - if (enable) + if (action == ENCODER_CONTROL_SETUP || + action == ENCODER_CONTROL_INIT) + params->ucAction = ATOM_ENCODER_INIT; + else if (action == ENCODER_CONTROL_ENABLE) params->ucAction = ATOM_ENABLE; else params->ucAction = ATOM_DISABLE; @@ -1864,7 +1890,7 @@ static void dac_encoder_control_prepare_params( static enum bp_result dac1_encoder_control_v1( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard) { @@ -1873,7 +1899,7 @@ static enum bp_result dac1_encoder_control_v1( dac_encoder_control_prepare_params( ¶ms, - enable, + action, pixel_clock, dac_standard); @@ -1885,7 +1911,7 @@ static enum bp_result dac1_encoder_control_v1( static enum bp_result dac2_encoder_control_v1( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard) { @@ -1894,7 +1920,7 @@ static enum bp_result dac2_encoder_control_v1( dac_encoder_control_prepare_params( ¶ms, - enable, + action, pixel_clock, dac_standard); diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.h b/drivers/gpu/drm/amd/display/dc/bios/command_table.h index e89b1ba0048b..78bdbcaa61c8 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table.h +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.h @@ -57,12 +57,12 @@ struct cmd_tbl { struct bp_crtc_source_select *bp_params); enum bp_result (*dac1_encoder_control)( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard); enum bp_result (*dac2_encoder_control)( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard); enum bp_result (*dac1_output_control)( diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index b357683b4255..268b5fbdb48b 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -30,7 +30,11 @@ dml_rcflags := $(CC_FLAGS_NO_FPU) ifneq ($(CONFIG_FRAME_WARN),0) ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y) - frame_warn_limit := 3072 + ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_COMPILE_TEST),yy) + frame_warn_limit := 4096 + else + frame_warn_limit := 3072 + endif else frame_warn_limit := 2048 endif 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 8d24763938ea..1df3412be346 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 @@ -77,32 +77,14 @@ static unsigned int dscceComputeDelay( static unsigned int dscComputeDelay( enum output_format_class pixelFormat, enum output_encoder_class Output); -// Super monster function with some 45 argument static bool CalculatePrefetchSchedule( struct display_mode_lib *mode_lib, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + unsigned int k, Pipe *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, @@ -116,7 +98,6 @@ static bool CalculatePrefetchSchedule( unsigned int MaxNumSwathY, double PrefetchSourceLinesC, unsigned int SwathWidthC, - int BytePerPixelC, double VInitPreFillC, unsigned int MaxNumSwathC, long swath_width_luma_ub, @@ -124,9 +105,6 @@ static bool CalculatePrefetchSchedule( unsigned int SwathHeightY, unsigned int SwathHeightC, double TWait, - bool ProgressiveToInterlaceUnitInOPP, - double *DSTXAfterScaler, - double *DSTYAfterScaler, double *DestinationLinesForPrefetch, double *PrefetchBandwidth, double *DestinationLinesToRequestVMInVBlank, @@ -135,14 +113,7 @@ static bool CalculatePrefetchSchedule( double *VRatioPrefetchC, double *RequiredPrefetchPixDataBWLuma, double *RequiredPrefetchPixDataBWChroma, - bool *NotEnoughTimeForDynamicMetadata, - double *Tno_bw, - double *prefetch_vmrow_bw, - double *Tdmdl_vm, - double *Tdmdl, - unsigned int *VUpdateOffsetPix, - double *VUpdateWidthPix, - double *VReadyOffsetPix); + bool *NotEnoughTimeForDynamicMetadata); static double RoundToDFSGranularityUp(double Clock, double VCOSpeed); static double RoundToDFSGranularityDown(double Clock, double VCOSpeed); static void CalculateDCCConfiguration( @@ -294,62 +265,23 @@ static void CalculateDynamicMetadataParameters( static void CalculateWatermarksAndDRAMSpeedChangeSupport( struct display_mode_lib *mode_lib, unsigned int PrefetchMode, - unsigned int NumberOfActivePlanes, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int DPPOutputBufferPixels, - unsigned int DETBufferSizeInKByte, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool GPUVMEnable, - 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 DCFCLKDeepSleep, unsigned int DPPPerPlane[], - bool DCCEnable[], double DPPCLK[], 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[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], - enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, - double *StutterExitWatermark, - double *StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported); + enum clock_change_support *DRAMClockChangeSupport); static void CalculateDCFCLKDeepSleep( struct display_mode_lib *mode_lib, unsigned int NumberOfActivePlanes, @@ -810,29 +742,12 @@ static unsigned int dscComputeDelay(enum output_format_class pixelFormat, enum o static bool CalculatePrefetchSchedule( struct display_mode_lib *mode_lib, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + unsigned int k, Pipe *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, @@ -846,7 +761,6 @@ static bool CalculatePrefetchSchedule( unsigned int MaxNumSwathY, double PrefetchSourceLinesC, unsigned int SwathWidthC, - int BytePerPixelC, double VInitPreFillC, unsigned int MaxNumSwathC, long swath_width_luma_ub, @@ -854,9 +768,6 @@ static bool CalculatePrefetchSchedule( unsigned int SwathHeightY, unsigned int SwathHeightC, double TWait, - bool ProgressiveToInterlaceUnitInOPP, - double *DSTXAfterScaler, - double *DSTYAfterScaler, double *DestinationLinesForPrefetch, double *PrefetchBandwidth, double *DestinationLinesToRequestVMInVBlank, @@ -865,15 +776,10 @@ static bool CalculatePrefetchSchedule( double *VRatioPrefetchC, double *RequiredPrefetchPixDataBWLuma, double *RequiredPrefetchPixDataBWChroma, - bool *NotEnoughTimeForDynamicMetadata, - double *Tno_bw, - double *prefetch_vmrow_bw, - double *Tdmdl_vm, - double *Tdmdl, - unsigned int *VUpdateOffsetPix, - double *VUpdateWidthPix, - double *VReadyOffsetPix) + bool *NotEnoughTimeForDynamicMetadata) { + struct vba_vars_st *v = &mode_lib->vba; + double DPPCLKDelaySubtotalPlusCNVCFormater = v->DPPCLKDelaySubtotal + v->DPPCLKDelayCNVCFormater; bool MyError = false; unsigned int DPPCycles = 0, DISPCLKCycles = 0; double DSTTotalPixelsAfterScaler = 0; @@ -905,26 +811,26 @@ static bool CalculatePrefetchSchedule( double Tdmec = 0; double Tdmsks = 0; - if (GPUVMEnable == true && HostVMEnable == true) { - HostVMInefficiencyFactor = PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData / PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly; - HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels; + if (v->GPUVMEnable == true && v->HostVMEnable == true) { + HostVMInefficiencyFactor = v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData / v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly; + HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels; } else { HostVMInefficiencyFactor = 1; HostVMDynamicLevelsTrips = 0; } CalculateDynamicMetadataParameters( - 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, - ProgressiveToInterlaceUnitInOPP, + v->ProgressiveToInterlaceUnitInOPP, &Tsetup, &Tdmbf, &Tdmec, @@ -932,16 +838,16 @@ static bool 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 && GPUVMEnable == true) { - *Tdmdl = TWait + Tvm_trips + trip_to_mem; + if (v->DynamicMetadataVMEnabled == true && v->GPUVMEnable == true) { + v->Tdmdl[k] = TWait + Tvm_trips + trip_to_mem; } else { - *Tdmdl = TWait + UrgentExtraLatency; + v->Tdmdl[k] = TWait + UrgentExtraLatency; } - if (DynamicMetadataEnable == true) { - if (VStartup * LineTime < Tsetup + *Tdmdl + Tdmbf + Tdmec + Tdmsks) { + if (v->DynamicMetadataEnable[k] == true) { + if (VStartup * LineTime < Tsetup + v->Tdmdl[k] + Tdmbf + Tdmec + Tdmsks) { *NotEnoughTimeForDynamicMetadata = true; } else { *NotEnoughTimeForDynamicMetadata = false; @@ -949,39 +855,39 @@ static bool CalculatePrefetchSchedule( dml_print("DML: Tdmbf: %fus - time for dmd transfer from dchub to dio output buffer\n", Tdmbf); dml_print("DML: Tdmec: %fus - time dio takes to transfer dmd\n", Tdmec); dml_print("DML: Tdmsks: %fus - time before active dmd must complete transmission at dio\n", Tdmsks); - dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", *Tdmdl); + dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", v->Tdmdl[k]); } } else { *NotEnoughTimeForDynamicMetadata = false; } - *Tdmdl_vm = (DynamicMetadataEnable == true && DynamicMetadataVMEnabled == true && GPUVMEnable == true ? TWait + Tvm_trips : 0); + v->Tdmdl_vm[k] = (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; - *DSTXAfterScaler = DPPCycles * myPipe->PixelClock / myPipe->DPPCLK + DISPCLKCycles * myPipe->PixelClock / myPipe->DISPCLK + v->DSTXAfterScaler[k] = DPPCycles * myPipe->PixelClock / myPipe->DPPCLK + DISPCLKCycles * myPipe->PixelClock / myPipe->DISPCLK + DSCDelay; - *DSTXAfterScaler = *DSTXAfterScaler + ((myPipe->ODMCombineEnabled)?18:0) + (myPipe->DPPPerPlane - 1) * DPP_RECOUT_WIDTH; + v->DSTXAfterScaler[k] = v->DSTXAfterScaler[k] + ((myPipe->ODMCombineEnabled)?18:0) + (myPipe->DPPPerPlane - 1) * DPP_RECOUT_WIDTH; - if (OutputFormat == dm_420 || (myPipe->InterlaceEnable && ProgressiveToInterlaceUnitInOPP)) - *DSTYAfterScaler = 1; + if (v->OutputFormat[k] == dm_420 || (myPipe->InterlaceEnable && v->ProgressiveToInterlaceUnitInOPP)) + v->DSTYAfterScaler[k] = 1; else - *DSTYAfterScaler = 0; + v->DSTYAfterScaler[k] = 0; - DSTTotalPixelsAfterScaler = *DSTYAfterScaler * myPipe->HTotal + *DSTXAfterScaler; - *DSTYAfterScaler = dml_floor(DSTTotalPixelsAfterScaler / myPipe->HTotal, 1); - *DSTXAfterScaler = DSTTotalPixelsAfterScaler - ((double) (*DSTYAfterScaler * myPipe->HTotal)); + DSTTotalPixelsAfterScaler = v->DSTYAfterScaler[k] * myPipe->HTotal + v->DSTXAfterScaler[k]; + v->DSTYAfterScaler[k] = dml_floor(DSTTotalPixelsAfterScaler / myPipe->HTotal, 1); + v->DSTXAfterScaler[k] = DSTTotalPixelsAfterScaler - ((double) (v->DSTYAfterScaler[k] * myPipe->HTotal)); MyError = false; @@ -990,33 +896,33 @@ static bool CalculatePrefetchSchedule( Tvm_trips_rounded = dml_ceil(4.0 * Tvm_trips / LineTime, 1) / 4 * LineTime; Tr0_trips_rounded = dml_ceil(4.0 * Tr0_trips / LineTime, 1) / 4 * LineTime; - if (GPUVMEnable) { - if (GPUVMPageTableLevels >= 3) { - *Tno_bw = UrgentExtraLatency + trip_to_mem * ((GPUVMPageTableLevels - 2) - 1); + if (v->GPUVMEnable) { + if (v->GPUVMMaxPageTableLevels >= 3) { + v->Tno_bw[k] = UrgentExtraLatency + trip_to_mem * ((v->GPUVMMaxPageTableLevels - 2) - 1); } else - *Tno_bw = 0; + v->Tno_bw[k] = 0; } else if (!myPipe->DCCEnable) - *Tno_bw = LineTime; + v->Tno_bw[k] = LineTime; else - *Tno_bw = LineTime / 4; + v->Tno_bw[k] = LineTime / 4; - dst_y_prefetch_equ = VStartup - (Tsetup + dml_max(TWait + TCalc, *Tdmdl)) / LineTime - - (*DSTYAfterScaler + *DSTXAfterScaler / myPipe->HTotal); + dst_y_prefetch_equ = VStartup - (Tsetup + dml_max(TWait + TCalc, v->Tdmdl[k])) / LineTime + - (v->DSTYAfterScaler[k] + v->DSTXAfterScaler[k] / myPipe->HTotal); dst_y_prefetch_equ = dml_min(dst_y_prefetch_equ, 63.75); // limit to the reg limit of U6.2 for DST_Y_PREFETCH Lsw_oto = dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC); Tsw_oto = Lsw_oto * LineTime; - prefetch_bw_oto = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * BytePerPixelC) / Tsw_oto; + prefetch_bw_oto = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * v->BytePerPixelC[k]) / Tsw_oto; - if (GPUVMEnable == true) { - Tvm_oto = dml_max3(*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_oto, + if (v->GPUVMEnable == true) { + Tvm_oto = dml_max3(v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_oto, Tvm_trips, LineTime / 4.0); } else Tvm_oto = LineTime / 4.0; - if ((GPUVMEnable == true || myPipe->DCCEnable == true)) { + if ((v->GPUVMEnable == true || myPipe->DCCEnable == true)) { Tr0_oto = dml_max3( (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_oto, LineTime - Tvm_oto, LineTime / 4); @@ -1042,10 +948,10 @@ static bool CalculatePrefetchSchedule( dml_print("DML: Tdmbf: %fus - time for dmd transfer from dchub to dio output buffer\n", Tdmbf); dml_print("DML: Tdmec: %fus - time dio takes to transfer dmd\n", Tdmec); dml_print("DML: Tdmsks: %fus - time before active dmd must complete transmission at dio\n", Tdmsks); - dml_print("DML: Tdmdl_vm: %fus - time for vm stages of dmd \n", *Tdmdl_vm); - dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", *Tdmdl); - dml_print("DML: dst_x_after_scl: %f pixels - number of pixel clocks pipeline and buffer delay after scaler \n", *DSTXAfterScaler); - dml_print("DML: dst_y_after_scl: %d lines - number of lines of pipeline and buffer delay after scaler \n", (int)*DSTYAfterScaler); + dml_print("DML: Tdmdl_vm: %fus - time for vm stages of dmd \n", v->Tdmdl_vm[k]); + dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", v->Tdmdl[k]); + dml_print("DML: dst_x_after_scl: %f pixels - number of pixel clocks pipeline and buffer delay after scaler \n", v->DSTXAfterScaler[k]); + dml_print("DML: dst_y_after_scl: %d lines - number of lines of pipeline and buffer delay after scaler \n", (int)v->DSTYAfterScaler[k]); *PrefetchBandwidth = 0; *DestinationLinesToRequestVMInVBlank = 0; @@ -1059,26 +965,26 @@ static bool CalculatePrefetchSchedule( double PrefetchBandwidth3 = 0; double PrefetchBandwidth4 = 0; - if (Tpre_rounded - *Tno_bw > 0) + if (Tpre_rounded - v->Tno_bw[k] > 0) PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor + PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY - + PrefetchSourceLinesC * swath_width_chroma_ub * BytePerPixelC) - / (Tpre_rounded - *Tno_bw); + + PrefetchSourceLinesC * swath_width_chroma_ub * v->BytePerPixelC[k]) + / (Tpre_rounded - v->Tno_bw[k]); else PrefetchBandwidth1 = 0; - if (VStartup == MaxVStartup && (PrefetchBandwidth1 > 4 * prefetch_bw_oto) && (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - *Tno_bw) > 0) { - PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor) / (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - *Tno_bw); + if (VStartup == MaxVStartup && (PrefetchBandwidth1 > 4 * prefetch_bw_oto) && (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - v->Tno_bw[k]) > 0) { + PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor) / (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - v->Tno_bw[k]); } - if (Tpre_rounded - *Tno_bw - 2 * Tr0_trips_rounded > 0) + if (Tpre_rounded - v->Tno_bw[k] - 2 * Tr0_trips_rounded > 0) PrefetchBandwidth2 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * - BytePerPixelC) / - (Tpre_rounded - *Tno_bw - 2 * Tr0_trips_rounded); + v->BytePerPixelC[k]) / + (Tpre_rounded - v->Tno_bw[k] - 2 * Tr0_trips_rounded); else PrefetchBandwidth2 = 0; @@ -1086,7 +992,7 @@ static bool CalculatePrefetchSchedule( PrefetchBandwidth3 = (2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor + PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * - swath_width_chroma_ub * BytePerPixelC) / (Tpre_rounded - + swath_width_chroma_ub * v->BytePerPixelC[k]) / (Tpre_rounded - Tvm_trips_rounded); else PrefetchBandwidth3 = 0; @@ -1096,7 +1002,7 @@ static bool CalculatePrefetchSchedule( } if (Tpre_rounded - Tvm_trips_rounded - 2 * Tr0_trips_rounded > 0) - PrefetchBandwidth4 = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * BytePerPixelC) + PrefetchBandwidth4 = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * v->BytePerPixelC[k]) / (Tpre_rounded - Tvm_trips_rounded - 2 * Tr0_trips_rounded); else PrefetchBandwidth4 = 0; @@ -1107,7 +1013,7 @@ static bool CalculatePrefetchSchedule( bool Case3OK; if (PrefetchBandwidth1 > 0) { - if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth1 + if (v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth1 >= Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / PrefetchBandwidth1 >= Tr0_trips_rounded) { Case1OK = true; } else { @@ -1118,7 +1024,7 @@ static bool CalculatePrefetchSchedule( } if (PrefetchBandwidth2 > 0) { - if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth2 + if (v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth2 >= Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / PrefetchBandwidth2 < Tr0_trips_rounded) { Case2OK = true; } else { @@ -1129,7 +1035,7 @@ static bool CalculatePrefetchSchedule( } if (PrefetchBandwidth3 > 0) { - if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth3 + if (v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth3 < Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / PrefetchBandwidth3 >= Tr0_trips_rounded) { Case3OK = true; } else { @@ -1152,13 +1058,13 @@ static bool CalculatePrefetchSchedule( dml_print("DML: prefetch_bw_equ: %f\n", prefetch_bw_equ); if (prefetch_bw_equ > 0) { - if (GPUVMEnable) { - Tvm_equ = dml_max3(*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_equ, Tvm_trips, LineTime / 4); + if (v->GPUVMEnable) { + Tvm_equ = dml_max3(v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_equ, Tvm_trips, LineTime / 4); } else { Tvm_equ = LineTime / 4; } - if ((GPUVMEnable || myPipe->DCCEnable)) { + if ((v->GPUVMEnable || myPipe->DCCEnable)) { Tr0_equ = dml_max4( (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_equ, Tr0_trips, @@ -1227,7 +1133,7 @@ static bool CalculatePrefetchSchedule( } *RequiredPrefetchPixDataBWLuma = (double) PrefetchSourceLinesY / LinesToRequestPrefetchPixelData * BytePerPixelY * swath_width_luma_ub / LineTime; - *RequiredPrefetchPixDataBWChroma = (double) PrefetchSourceLinesC / LinesToRequestPrefetchPixelData * BytePerPixelC * swath_width_chroma_ub / LineTime; + *RequiredPrefetchPixDataBWChroma = (double) PrefetchSourceLinesC / LinesToRequestPrefetchPixelData * v->BytePerPixelC[k] * swath_width_chroma_ub / LineTime; } else { MyError = true; dml_print("DML: MyErr set %s:%d\n", __FILE__, __LINE__); @@ -1243,9 +1149,9 @@ static bool CalculatePrefetchSchedule( dml_print("DML: Tr0: %fus - time to fetch first row of data pagetables and first row of meta data (done in parallel)\n", TimeForFetchingRowInVBlank); dml_print("DML: Tr1: %fus - time to fetch second row of data pagetables and second row of meta data (done in parallel)\n", TimeForFetchingRowInVBlank); dml_print("DML: Tsw: %fus = time to fetch enough pixel data and cursor data to feed the scalers init position and detile\n", (double)LinesToRequestPrefetchPixelData * LineTime); - dml_print("DML: To: %fus - time for propagation from scaler to optc\n", (*DSTYAfterScaler + ((*DSTXAfterScaler) / (double) myPipe->HTotal)) * LineTime); + dml_print("DML: To: %fus - time for propagation from scaler to optc\n", (v->DSTYAfterScaler[k] + ((v->DSTXAfterScaler[k]) / (double) myPipe->HTotal)) * LineTime); dml_print("DML: Tvstartup - Tsetup - Tcalc - Twait - Tpre - To > 0\n"); - dml_print("DML: Tslack(pre): %fus - time left over in schedule\n", VStartup * LineTime - TimeForFetchingMetaPTE - 2 * TimeForFetchingRowInVBlank - (*DSTYAfterScaler + ((*DSTXAfterScaler) / (double) myPipe->HTotal)) * LineTime - TWait - TCalc - Tsetup); + dml_print("DML: Tslack(pre): %fus - time left over in schedule\n", VStartup * LineTime - TimeForFetchingMetaPTE - 2 * TimeForFetchingRowInVBlank - (v->DSTYAfterScaler[k] + ((v->DSTXAfterScaler[k]) / (double) myPipe->HTotal)) * LineTime - TWait - TCalc - Tsetup); dml_print("DML: row_bytes = dpte_row_bytes (per_pipe) = PixelPTEBytesPerRow = : %d\n", PixelPTEBytesPerRow); } else { @@ -1276,7 +1182,7 @@ static bool CalculatePrefetchSchedule( dml_print("DML: MyErr set %s:%d\n", __FILE__, __LINE__); } - *prefetch_vmrow_bw = dml_max(prefetch_vm_bw, prefetch_row_bw); + v->prefetch_vmrow_bw[k] = dml_max(prefetch_vm_bw, prefetch_row_bw); } if (MyError) { @@ -2437,30 +2343,12 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->ErrorResult[k] = CalculatePrefetchSchedule( mode_lib, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + k, &myPipe, v->DSCDelay[k], - v->DPPCLKDelaySubtotal - + v->DPPCLKDelayCNVCFormater, - v->DPPCLKDelaySCL, - v->DPPCLKDelaySCLLBOnly, - v->DPPCLKDelayCNVCCursor, - v->DISPCLKDelaySubtotal, (unsigned int) (v->SwathWidthY[k] / v->HRatio[k]), - v->OutputFormat[k], - v->MaxInterDCNTileRepeaters, dml_min(v->VStartupLines, v->MaxVStartupLines[k]), v->MaxVStartupLines[k], - v->GPUVMMaxPageTableLevels, - v->GPUVMEnable, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->HostVMMinPageSize, - v->DynamicMetadataEnable[k], - v->DynamicMetadataVMEnabled, - v->DynamicMetadataLinesBeforeActiveRequired[k], - v->DynamicMetadataTransmittedBytes[k], v->UrgentLatency, v->UrgentExtraLatency, v->TCalc, @@ -2474,7 +2362,6 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->MaxNumSwathY[k], v->PrefetchSourceLinesC[k], v->SwathWidthC[k], - v->BytePerPixelC[k], v->VInitPreFillC[k], v->MaxNumSwathC[k], v->swath_width_luma_ub[k], @@ -2482,9 +2369,6 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->SwathHeightY[k], v->SwathHeightC[k], TWait, - v->ProgressiveToInterlaceUnitInOPP, - &v->DSTXAfterScaler[k], - &v->DSTYAfterScaler[k], &v->DestinationLinesForPrefetch[k], &v->PrefetchBandwidth[k], &v->DestinationLinesToRequestVMInVBlank[k], @@ -2493,14 +2377,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman &v->VRatioPrefetchC[k], &v->RequiredPrefetchPixDataBWLuma[k], &v->RequiredPrefetchPixDataBWChroma[k], - &v->NotEnoughTimeForDynamicMetadata[k], - &v->Tno_bw[k], - &v->prefetch_vmrow_bw[k], - &v->Tdmdl_vm[k], - &v->Tdmdl[k], - &v->VUpdateOffsetPix[k], - &v->VUpdateWidthPix[k], - &v->VReadyOffsetPix[k]); + &v->NotEnoughTimeForDynamicMetadata[k]); if (v->BlendingAndTiming[k] == k) { double TotalRepeaterDelayTime = v->MaxInterDCNTileRepeaters * (2 / v->DPPCLK[k] + 3 / v->DISPCLK); v->VUpdateWidthPix[k] = (14 / v->DCFCLKDeepSleep + 12 / v->DPPCLK[k] + TotalRepeaterDelayTime) * v->PixelClock[k]; @@ -2730,62 +2607,23 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, PrefetchMode, - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->DPPOutputBufferPixels, - v->DETBufferSizeInKByte[0], - v->WritebackInterfaceBufferSize, v->DCFCLK, v->ReturnBW, - v->GPUVMEnable, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgentLatency, v->UrgentExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLK, - v->FinalDRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, v->DCFCLKDeepSleep, v->DPPPerPlane, - v->DCCEnable, v->DPPCLK, 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->BytePerPixelDETY, v->BytePerPixelDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, - &DRAMClockChangeSupport, - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, - &v->StutterExitWatermark, - &v->StutterEnterPlusExitWatermark, - &v->MinActiveDRAMClockChangeLatencySupported); + &DRAMClockChangeSupport); for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (v->WritebackEnable[k] == true) { @@ -4770,29 +4608,12 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->NoTimeForPrefetch[i][j][k] = CalculatePrefetchSchedule( mode_lib, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + k, &myPipe, v->DSCDelayPerState[i][k], - v->DPPCLKDelaySubtotal + v->DPPCLKDelayCNVCFormater, - v->DPPCLKDelaySCL, - v->DPPCLKDelaySCLLBOnly, - v->DPPCLKDelayCNVCCursor, - v->DISPCLKDelaySubtotal, v->SwathWidthYThisState[k] / v->HRatio[k], - v->OutputFormat[k], - v->MaxInterDCNTileRepeaters, dml_min(v->MaxVStartup, v->MaximumVStartup[i][j][k]), v->MaximumVStartup[i][j][k], - v->GPUVMMaxPageTableLevels, - v->GPUVMEnable, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->HostVMMinPageSize, - v->DynamicMetadataEnable[k], - v->DynamicMetadataVMEnabled, - v->DynamicMetadataLinesBeforeActiveRequired[k], - v->DynamicMetadataTransmittedBytes[k], v->UrgLatency[i], v->ExtraLatency, v->TimeCalc, @@ -4806,7 +4627,6 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->MaxNumSwY[k], v->PrefetchLinesC[i][j][k], v->SwathWidthCThisState[k], - v->BytePerPixelC[k], v->PrefillC[k], v->MaxNumSwC[k], v->swath_width_luma_ub_this_state[k], @@ -4814,9 +4634,6 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->SwathHeightYThisState[k], v->SwathHeightCThisState[k], v->TWait, - v->ProgressiveToInterlaceUnitInOPP, - &v->DSTXAfterScaler[k], - &v->DSTYAfterScaler[k], &v->LineTimesForPrefetch[k], &v->PrefetchBW[k], &v->LinesForMetaPTE[k], @@ -4825,14 +4642,7 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l &v->VRatioPreC[i][j][k], &v->RequiredPrefetchPixelDataBWLuma[i][j][k], &v->RequiredPrefetchPixelDataBWChroma[i][j][k], - &v->NoTimeForDynamicMetadata[i][j][k], - &v->Tno_bw[k], - &v->prefetch_vmrow_bw[k], - &v->Tdmdl_vm[k], - &v->Tdmdl[k], - &v->VUpdateOffsetPix[k], - &v->VUpdateWidthPix[k], - &v->VReadyOffsetPix[k]); + &v->NoTimeForDynamicMetadata[i][j][k]); } for (k = 0; k <= v->NumberOfActivePlanes - 1; k++) { @@ -5007,62 +4817,23 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, v->PrefetchModePerState[i][j], - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->DPPOutputBufferPixels, - v->DETBufferSizeInKByte[0], - v->WritebackInterfaceBufferSize, v->DCFCLKState[i][j], v->ReturnBWPerState[i][j], - v->GPUVMEnable, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgLatency[i], v->ExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLKPerState[i], - v->FinalDRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, v->ProjectedDCFCLKDeepSleep[i][j], v->NoOfDPPThisState, - v->DCCEnable, v->RequiredDPPCLKThisState, 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->BytePerPixelInDETY, v->BytePerPixelInDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, - &v->DRAMClockChangeSupport[i][j], - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, - &v->StutterExitWatermark, - &v->StutterEnterPlusExitWatermark, - &v->MinActiveDRAMClockChangeLatencySupported); + &v->DRAMClockChangeSupport[i][j]); } } @@ -5179,63 +4950,25 @@ void dml30_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 DPPOutputBufferPixels, - unsigned int DETBufferSizeInKByte, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool GPUVMEnable, - 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 DCFCLKDeepSleep, unsigned int DPPPerPlane[], - bool DCCEnable[], double DPPCLK[], 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[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], - enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, - double *StutterExitWatermark, - double *StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported) + enum clock_change_support *DRAMClockChangeSupport) { + struct vba_vars_st *v = &mode_lib->vba; double EffectiveLBLatencyHidingY = 0; double EffectiveLBLatencyHidingC = 0; double LinesInDETY[DC__NUM_DPP__MAX] = { 0 }; @@ -5254,101 +4987,101 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( double WritebackDRAMClockChangeLatencyHiding = 0; unsigned int k, j; - mode_lib->vba.TotalActiveDPP = 0; - mode_lib->vba.TotalDCCActiveDPP = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - mode_lib->vba.TotalActiveDPP = mode_lib->vba.TotalActiveDPP + DPPPerPlane[k]; - if (DCCEnable[k] == true) { - mode_lib->vba.TotalDCCActiveDPP = mode_lib->vba.TotalDCCActiveDPP + DPPPerPlane[k]; + v->TotalActiveDPP = 0; + v->TotalDCCActiveDPP = 0; + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + v->TotalActiveDPP = v->TotalActiveDPP + DPPPerPlane[k]; + if (v->DCCEnable[k] == true) { + v->TotalDCCActiveDPP = v->TotalDCCActiveDPP + DPPPerPlane[k]; } } - *UrgentWatermark = UrgentLatency + ExtraLatency; + v->UrgentWatermark = UrgentLatency + ExtraLatency; - *DRAMClockChangeWatermark = DRAMClockChangeLatency + *UrgentWatermark; + v->DRAMClockChangeWatermark = v->FinalDRAMClockChangeLatency + v->UrgentWatermark; - mode_lib->vba.TotalActiveWriteback = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (WritebackEnable[k] == true) { - mode_lib->vba.TotalActiveWriteback = mode_lib->vba.TotalActiveWriteback + 1; + v->TotalActiveWriteback = 0; + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->WritebackEnable[k] == true) { + v->TotalActiveWriteback = v->TotalActiveWriteback + 1; } } - if (mode_lib->vba.TotalActiveWriteback <= 1) { - *WritebackUrgentWatermark = WritebackLatency; + if (v->TotalActiveWriteback <= 1) { + 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 (mode_lib->vba.TotalActiveWriteback <= 1) { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency; + if (v->TotalActiveWriteback <= 1) { + v->WritebackDRAMClockChangeWatermark = v->FinalDRAMClockChangeLatency + v->WritebackLatency; } else { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->WritebackDRAMClockChangeWatermark = v->FinalDRAMClockChangeLatency + v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { - mode_lib->vba.LBLatencyHidingSourceLinesY = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (vtaps[k] - 1); + v->LBLatencyHidingSourceLinesY = dml_min((double) v->MaxLineBufferLines, dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(v->HRatio[k], 1.0)), 1)) - (v->vtaps[k] - 1); - mode_lib->vba.LBLatencyHidingSourceLinesC = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTAPsChroma[k] - 1); + v->LBLatencyHidingSourceLinesC = dml_min((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 = mode_lib->vba.LBLatencyHidingSourceLinesY / VRatio[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / v->VRatio[k] * (v->HTotal[k] / v->PixelClock[k]); - EffectiveLBLatencyHidingC = mode_lib->vba.LBLatencyHidingSourceLinesC / VRatioChroma[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / v->VRatioChroma[k] * (v->HTotal[k] / v->PixelClock[k]); LinesInDETY[k] = (double) DETBufferSizeY[k] / BytePerPixelDETY[k] / SwathWidthY[k]; LinesInDETYRoundedDownToSwath[k] = dml_floor(LinesInDETY[k], SwathHeightY[k]); - FullDETBufferingTimeY[k] = LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k]; + FullDETBufferingTimeY[k] = LinesInDETYRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k]; if (BytePerPixelDETC[k] > 0) { - LinesInDETC = mode_lib->vba.DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k]; + 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[k] - *UrgentWatermark - (HTotal[k] / PixelClock[k]) * (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) - *DRAMClockChangeWatermark; + ActiveDRAMClockChangeLatencyMarginY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY[k] - v->UrgentWatermark - (v->HTotal[k] / v->PixelClock[k]) * (v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { - ActiveDRAMClockChangeLatencyMarginY = ActiveDRAMClockChangeLatencyMarginY - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightY[k] * HTotal[k] / PixelClock[k] / VRatio[k]; + if (v->NumberOfActivePlanes > 1) { + ActiveDRAMClockChangeLatencyMarginY = ActiveDRAMClockChangeLatencyMarginY - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightY[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatio[k]; } if (BytePerPixelDETC[k] > 0) { - ActiveDRAMClockChangeLatencyMarginC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC - *UrgentWatermark - (HTotal[k] / PixelClock[k]) * (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) - *DRAMClockChangeWatermark; + ActiveDRAMClockChangeLatencyMarginC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC - v->UrgentWatermark - (v->HTotal[k] / v->PixelClock[k]) * (v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { - ActiveDRAMClockChangeLatencyMarginC = ActiveDRAMClockChangeLatencyMarginC - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightC[k] * HTotal[k] / PixelClock[k] / VRatioChroma[k]; + if (v->NumberOfActivePlanes > 1) { + ActiveDRAMClockChangeLatencyMarginC = ActiveDRAMClockChangeLatencyMarginC - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightC[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatioChroma[k]; } - mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMarginY, ActiveDRAMClockChangeLatencyMarginC); + v->ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMarginY, ActiveDRAMClockChangeLatencyMarginC); } else { - mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k] = ActiveDRAMClockChangeLatencyMarginY; + v->ActiveDRAMClockChangeLatencyMargin[k] = ActiveDRAMClockChangeLatencyMarginY; } - if (WritebackEnable[k] == true) { + if (v->WritebackEnable[k] == true) { - WritebackDRAMClockChangeLatencyHiding = WritebackInterfaceBufferSize * 1024 / (WritebackDestinationWidth[k] * WritebackDestinationHeight[k] / (WritebackSourceHeight[k] * HTotal[k] / PixelClock[k]) * 4); - if (WritebackPixelFormat[k] == dm_444_64) { + 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; } - if (mode_lib->vba.WritebackConfiguration == dm_whole_buffer_for_single_stream_interleave) { + if (v->WritebackConfiguration == dm_whole_buffer_for_single_stream_interleave) { WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding * 2; } - WritebackDRAMClockChangeLatencyMargin = WritebackDRAMClockChangeLatencyHiding - mode_lib->vba.WritebackDRAMClockChangeWatermark; - mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k] = dml_min(mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k], WritebackDRAMClockChangeLatencyMargin); + WritebackDRAMClockChangeLatencyMargin = WritebackDRAMClockChangeLatencyHiding - v->WritebackDRAMClockChangeWatermark; + v->ActiveDRAMClockChangeLatencyMargin[k] = dml_min(v->ActiveDRAMClockChangeLatencyMargin[k], WritebackDRAMClockChangeLatencyMargin); } } - mode_lib->vba.MinActiveDRAMClockChangeMargin = 999999; + v->MinActiveDRAMClockChangeMargin = 999999; PlaneWithMinActiveDRAMClockChangeMargin = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k] < mode_lib->vba.MinActiveDRAMClockChangeMargin) { - mode_lib->vba.MinActiveDRAMClockChangeMargin = mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k]; - if (BlendingAndTiming[k] == k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->ActiveDRAMClockChangeLatencyMargin[k] < v->MinActiveDRAMClockChangeMargin) { + v->MinActiveDRAMClockChangeMargin = v->ActiveDRAMClockChangeLatencyMargin[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; } } @@ -5356,40 +5089,40 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( } } - *MinActiveDRAMClockChangeLatencySupported = mode_lib->vba.MinActiveDRAMClockChangeMargin + DRAMClockChangeLatency; + v->MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + v->FinalDRAMClockChangeLatency; SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = 999999; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (BlendingAndTiming[k] == k)) && !(BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin) && mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k] < SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank) { - SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k]; + 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]; } } - mode_lib->vba.TotalNumberOfActiveOTG = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (BlendingAndTiming[k] == k) { - mode_lib->vba.TotalNumberOfActiveOTG = mode_lib->vba.TotalNumberOfActiveOTG + 1; + v->TotalNumberOfActiveOTG = 0; + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->BlendingAndTiming[k] == k) { + v->TotalNumberOfActiveOTG = v->TotalNumberOfActiveOTG + 1; } } - if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 0) { + if (v->MinActiveDRAMClockChangeMargin > 0) { *DRAMClockChangeSupport = dm_dram_clock_change_vactive; - } else if (((mode_lib->vba.SynchronizedVBlank == true || mode_lib->vba.TotalNumberOfActiveOTG == 1 || SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank > 0) && PrefetchMode == 0)) { + } 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; } FullDETBufferingTimeYStutterCriticalPlane = FullDETBufferingTimeY[0]; - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (FullDETBufferingTimeY[k] <= FullDETBufferingTimeYStutterCriticalPlane) { FullDETBufferingTimeYStutterCriticalPlane = FullDETBufferingTimeY[k]; - TimeToFinishSwathTransferStutterCriticalPlane = (SwathHeightY[k] - (LinesInDETY[k] - LinesInDETYRoundedDownToSwath[k])) * (HTotal[k] / PixelClock[k]) / VRatio[k]; + TimeToFinishSwathTransferStutterCriticalPlane = (SwathHeightY[k] - (LinesInDETY[k] - LinesInDETYRoundedDownToSwath[k])) * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k]; } } - *StutterExitWatermark = SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; - *StutterEnterPlusExitWatermark = dml_max(SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep, TimeToFinishSwathTransferStutterCriticalPlane); + v->StutterExitWatermark = v->SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; + v->StutterEnterPlusExitWatermark = dml_max(v->SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep, TimeToFinishSwathTransferStutterCriticalPlane); } diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index 0cdd8c74abdf..ebd74b43e935 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -1610,38 +1610,12 @@ dce110_select_crtc_source(struct pipe_ctx *pipe_ctx) struct dc_bios *bios = link->ctx->dc_bios; struct bp_crtc_source_select crtc_source_select = {0}; enum engine_id engine_id = link->link_enc->preferred_engine; - uint8_t bit_depth; if (dc_is_rgb_signal(pipe_ctx->stream->signal)) engine_id = link->link_enc->analog_engine; - switch (pipe_ctx->stream->timing.display_color_depth) { - case COLOR_DEPTH_UNDEFINED: - bit_depth = 0; - break; - case COLOR_DEPTH_666: - bit_depth = 6; - break; - default: - case COLOR_DEPTH_888: - bit_depth = 8; - break; - case COLOR_DEPTH_101010: - bit_depth = 10; - break; - case COLOR_DEPTH_121212: - bit_depth = 12; - break; - case COLOR_DEPTH_141414: - bit_depth = 14; - break; - case COLOR_DEPTH_161616: - bit_depth = 16; - break; - } - crtc_source_select.controller_id = CONTROLLER_ID_D0 + pipe_ctx->stream_res.tg->inst; - crtc_source_select.bit_depth = bit_depth; + crtc_source_select.color_depth = pipe_ctx->stream->timing.display_color_depth; crtc_source_select.engine_id = engine_id; crtc_source_select.sink_signal = pipe_ctx->stream->signal; diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index 6d31f4967f1a..e1940b8e5bc3 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -932,7 +932,7 @@ static bool link_detect_dac_load_detect(struct dc_link *link) struct link_encoder *link_enc = link->link_enc; enum engine_id engine_id = link_enc->preferred_engine; enum dal_device_type device_type = DEVICE_TYPE_CRT; - enum bp_result bp_result; + enum bp_result bp_result = BP_RESULT_UNSUPPORTED; uint32_t enum_id; switch (engine_id) { @@ -946,7 +946,9 @@ static bool link_detect_dac_load_detect(struct dc_link *link) break; } - bp_result = bios->funcs->dac_load_detection(bios, engine_id, device_type, enum_id); + if (bios->funcs->dac_load_detection) + bp_result = bios->funcs->dac_load_detection(bios, engine_id, device_type, enum_id); + return bp_result == BP_RESULT_OK; } diff --git a/drivers/gpu/drm/amd/display/include/bios_parser_types.h b/drivers/gpu/drm/amd/display/include/bios_parser_types.h index 973b6bdbac63..f40dc612ec73 100644 --- a/drivers/gpu/drm/amd/display/include/bios_parser_types.h +++ b/drivers/gpu/drm/amd/display/include/bios_parser_types.h @@ -136,7 +136,7 @@ struct bp_crtc_source_select { enum engine_id engine_id; enum controller_id controller_id; enum signal_type sink_signal; - uint8_t bit_depth; + enum dc_color_depth color_depth; }; struct bp_transmitter_control { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index 7c9f77124ab2..c4966dcc6875 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -2455,24 +2455,21 @@ static int navi10_update_pcie_parameters(struct smu_context *smu, } for (i = 0; i < NUM_LINK_LEVELS; i++) { - if (pptable->PcieGenSpeed[i] > pcie_gen_cap || - pptable->PcieLaneCount[i] > pcie_width_cap) { - dpm_context->dpm_tables.pcie_table.pcie_gen[i] = - pptable->PcieGenSpeed[i] > pcie_gen_cap ? - pcie_gen_cap : pptable->PcieGenSpeed[i]; - dpm_context->dpm_tables.pcie_table.pcie_lane[i] = - pptable->PcieLaneCount[i] > pcie_width_cap ? - pcie_width_cap : pptable->PcieLaneCount[i]; - smu_pcie_arg = i << 16; - smu_pcie_arg |= pcie_gen_cap << 8; - smu_pcie_arg |= pcie_width_cap; - ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_OverridePcieParameters, - smu_pcie_arg, - NULL); - if (ret) - break; - } + dpm_context->dpm_tables.pcie_table.pcie_gen[i] = + pptable->PcieGenSpeed[i] > pcie_gen_cap ? + pcie_gen_cap : pptable->PcieGenSpeed[i]; + dpm_context->dpm_tables.pcie_table.pcie_lane[i] = + pptable->PcieLaneCount[i] > pcie_width_cap ? + pcie_width_cap : pptable->PcieLaneCount[i]; + smu_pcie_arg = i << 16; + smu_pcie_arg |= dpm_context->dpm_tables.pcie_table.pcie_gen[i] << 8; + smu_pcie_arg |= dpm_context->dpm_tables.pcie_table.pcie_lane[i]; + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_OverridePcieParameters, + smu_pcie_arg, + NULL); + if (ret) + return ret; } return ret; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 677781060246..eaeff6a9bc50 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2923,8 +2923,13 @@ static int smu_v13_0_0_mode1_reset(struct smu_context *smu) break; } - if (!ret) + if (!ret) { + /* disable mmio access while doing mode 1 reset*/ + smu->adev->no_hw_access = true; + /* ensure no_hw_access is globally visible before any MMIO */ + smp_mb(); msleep(SMU13_MODE1_RESET_WAIT_TIME_IN_MS); + } return ret; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index 2cea688c604f..33c3cd2e1e24 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -2143,10 +2143,15 @@ static int smu_v14_0_2_mode1_reset(struct smu_context *smu) ret = smu_cmn_send_debug_smc_msg(smu, DEBUGSMC_MSG_Mode1Reset); if (!ret) { - if (amdgpu_emu_mode == 1) + if (amdgpu_emu_mode == 1) { msleep(50000); - else + } else { + /* disable mmio access while doing mode 1 reset*/ + smu->adev->no_hw_access = true; + /* ensure no_hw_access is globally visible before any MMIO */ + smp_mb(); msleep(1000); + } } return ret; diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 10adac9397cf..5beea645035f 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1162,8 +1162,18 @@ crtc_needs_disable(struct drm_crtc_state *old_state, new_state->self_refresh_active; } -static void -encoder_bridge_disable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_encoder_bridge_disable - disable bridges and encoder + * @dev: DRM device + * @state: the driver state object + * + * Loops over all connectors in the current state and if the CRTC needs + * it, disables the bridge chain all the way, then disables the encoder + * afterwards. + */ +void +drm_atomic_helper_commit_encoder_bridge_disable(struct drm_device *dev, + struct drm_atomic_state *state) { struct drm_connector *connector; struct drm_connector_state *old_conn_state, *new_conn_state; @@ -1229,9 +1239,18 @@ encoder_bridge_disable(struct drm_device *dev, struct drm_atomic_state *state) } } } +EXPORT_SYMBOL(drm_atomic_helper_commit_encoder_bridge_disable); -static void -crtc_disable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_crtc_disable - disable CRTSs + * @dev: DRM device + * @state: the driver state object + * + * Loops over all CRTCs in the current state and if the CRTC needs + * it, disables it. + */ +void +drm_atomic_helper_commit_crtc_disable(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_crtc *crtc; struct drm_crtc_state *old_crtc_state, *new_crtc_state; @@ -1282,9 +1301,18 @@ crtc_disable(struct drm_device *dev, struct drm_atomic_state *state) drm_crtc_vblank_put(crtc); } } +EXPORT_SYMBOL(drm_atomic_helper_commit_crtc_disable); -static void -encoder_bridge_post_disable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_encoder_bridge_post_disable - post-disable encoder bridges + * @dev: DRM device + * @state: the driver state object + * + * Loops over all connectors in the current state and if the CRTC needs + * it, post-disables all encoder bridges. + */ +void +drm_atomic_helper_commit_encoder_bridge_post_disable(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_connector *connector; struct drm_connector_state *old_conn_state, *new_conn_state; @@ -1335,15 +1363,16 @@ encoder_bridge_post_disable(struct drm_device *dev, struct drm_atomic_state *sta drm_bridge_put(bridge); } } +EXPORT_SYMBOL(drm_atomic_helper_commit_encoder_bridge_post_disable); static void disable_outputs(struct drm_device *dev, struct drm_atomic_state *state) { - encoder_bridge_disable(dev, state); + drm_atomic_helper_commit_encoder_bridge_disable(dev, state); - crtc_disable(dev, state); + drm_atomic_helper_commit_encoder_bridge_post_disable(dev, state); - encoder_bridge_post_disable(dev, state); + drm_atomic_helper_commit_crtc_disable(dev, state); } /** @@ -1446,8 +1475,17 @@ void drm_atomic_helper_calc_timestamping_constants(struct drm_atomic_state *stat } EXPORT_SYMBOL(drm_atomic_helper_calc_timestamping_constants); -static void -crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_crtc_set_mode - set the new mode + * @dev: DRM device + * @state: the driver state object + * + * Loops over all connectors in the current state and if the mode has + * changed, change the mode of the CRTC, then call down the bridge + * chain and change the mode in all bridges as well. + */ +void +drm_atomic_helper_commit_crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_crtc *crtc; struct drm_crtc_state *new_crtc_state; @@ -1508,6 +1546,7 @@ crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *state) drm_bridge_put(bridge); } } +EXPORT_SYMBOL(drm_atomic_helper_commit_crtc_set_mode); /** * drm_atomic_helper_commit_modeset_disables - modeset commit to disable outputs @@ -1531,12 +1570,21 @@ void drm_atomic_helper_commit_modeset_disables(struct drm_device *dev, drm_atomic_helper_update_legacy_modeset_state(dev, state); drm_atomic_helper_calc_timestamping_constants(state); - crtc_set_mode(dev, state); + drm_atomic_helper_commit_crtc_set_mode(dev, state); } EXPORT_SYMBOL(drm_atomic_helper_commit_modeset_disables); -static void drm_atomic_helper_commit_writebacks(struct drm_device *dev, - struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_writebacks - issue writebacks + * @dev: DRM device + * @state: atomic state object being committed + * + * This loops over the connectors, checks if the new state requires + * a writeback job to be issued and in that case issues an atomic + * commit on each connector. + */ +void drm_atomic_helper_commit_writebacks(struct drm_device *dev, + struct drm_atomic_state *state) { struct drm_connector *connector; struct drm_connector_state *new_conn_state; @@ -1555,9 +1603,18 @@ static void drm_atomic_helper_commit_writebacks(struct drm_device *dev, } } } +EXPORT_SYMBOL(drm_atomic_helper_commit_writebacks); -static void -encoder_bridge_pre_enable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_encoder_bridge_pre_enable - pre-enable bridges + * @dev: DRM device + * @state: atomic state object being committed + * + * This loops over the connectors and if the CRTC needs it, pre-enables + * the entire bridge chain. + */ +void +drm_atomic_helper_commit_encoder_bridge_pre_enable(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_connector *connector; struct drm_connector_state *new_conn_state; @@ -1588,9 +1645,18 @@ encoder_bridge_pre_enable(struct drm_device *dev, struct drm_atomic_state *state drm_bridge_put(bridge); } } +EXPORT_SYMBOL(drm_atomic_helper_commit_encoder_bridge_pre_enable); -static void -crtc_enable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_crtc_enable - enables the CRTCs + * @dev: DRM device + * @state: atomic state object being committed + * + * This loops over CRTCs in the new state, and of the CRTC needs + * it, enables it. + */ +void +drm_atomic_helper_commit_crtc_enable(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_crtc *crtc; struct drm_crtc_state *old_crtc_state; @@ -1619,9 +1685,18 @@ crtc_enable(struct drm_device *dev, struct drm_atomic_state *state) } } } +EXPORT_SYMBOL(drm_atomic_helper_commit_crtc_enable); -static void -encoder_bridge_enable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_encoder_bridge_enable - enables the bridges + * @dev: DRM device + * @state: atomic state object being committed + * + * This loops over all connectors in the new state, and of the CRTC needs + * it, enables the entire bridge chain. + */ +void +drm_atomic_helper_commit_encoder_bridge_enable(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_connector *connector; struct drm_connector_state *new_conn_state; @@ -1664,6 +1739,7 @@ encoder_bridge_enable(struct drm_device *dev, struct drm_atomic_state *state) drm_bridge_put(bridge); } } +EXPORT_SYMBOL(drm_atomic_helper_commit_encoder_bridge_enable); /** * drm_atomic_helper_commit_modeset_enables - modeset commit to enable outputs @@ -1682,11 +1758,11 @@ encoder_bridge_enable(struct drm_device *dev, struct drm_atomic_state *state) void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev, struct drm_atomic_state *state) { - encoder_bridge_pre_enable(dev, state); + drm_atomic_helper_commit_crtc_enable(dev, state); - crtc_enable(dev, state); + drm_atomic_helper_commit_encoder_bridge_pre_enable(dev, state); - encoder_bridge_enable(dev, state); + drm_atomic_helper_commit_encoder_bridge_enable(dev, state); drm_atomic_helper_commit_writebacks(dev, state); } diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 4a7f72044ab8..4b47aa0dab35 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -366,6 +366,9 @@ static void drm_fb_helper_damage_work(struct work_struct *work) { struct drm_fb_helper *helper = container_of(work, struct drm_fb_helper, damage_work); + if (helper->info->state != FBINFO_STATE_RUNNING) + return; + drm_fb_helper_fb_dirty(helper); } @@ -732,6 +735,13 @@ void drm_fb_helper_set_suspend_unlocked(struct drm_fb_helper *fb_helper, if (fb_helper->info->state != FBINFO_STATE_RUNNING) return; + /* + * Cancel pending damage work. During GPU reset, VBlank + * interrupts are disabled and drm_fb_helper_fb_dirty() + * would wait for VBlank timeout otherwise. + */ + cancel_work_sync(&fb_helper->damage_work); + console_lock(); } else { diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index 01813e11e6c6..8e76ac8ee4e2 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -1692,7 +1692,7 @@ static irqreturn_t hdmi_irq_thread(int irq, void *arg) { struct hdmi_context *hdata = arg; - mod_delayed_work(system_wq, &hdata->hotplug_work, + mod_delayed_work(system_percpu_wq, &hdata->hotplug_work, msecs_to_jiffies(HOTPLUG_DEBOUNCE_MS)); return IRQ_HANDLED; diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 0e2bcd5f67b7..d7726091819c 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -1002,12 +1002,6 @@ static int mtk_dsi_host_attach(struct mipi_dsi_host *host, return PTR_ERR(dsi->next_bridge); } - /* - * set flag to request the DSI host bridge be pre-enabled before device bridge - * in the chain, so the DSI host is ready when the device bridge is pre-enabled - */ - dsi->next_bridge->pre_enable_prev_first = true; - drm_bridge_add(&dsi->bridge); ret = component_add(host->dev, &mtk_dsi_component_ops); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ad102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ad102.c index 35d1fcef520b..c456a9626823 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ad102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ad102.c @@ -30,6 +30,9 @@ ad102_gsp = { .booter.ctor = ga102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c index 503760246660..851140e80122 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c @@ -337,18 +337,12 @@ nvkm_gsp_fwsec_sb(struct nvkm_gsp *gsp) } int -nvkm_gsp_fwsec_sb_ctor(struct nvkm_gsp *gsp) +nvkm_gsp_fwsec_sb_init(struct nvkm_gsp *gsp) { return nvkm_gsp_fwsec_init(gsp, &gsp->fws.falcon.sb, "fwsec-sb", NVFW_FALCON_APPIF_DMEMMAPPER_CMD_SB); } -void -nvkm_gsp_fwsec_sb_dtor(struct nvkm_gsp *gsp) -{ - nvkm_falcon_fw_dtor(&gsp->fws.falcon.sb); -} - int nvkm_gsp_fwsec_frts(struct nvkm_gsp *gsp) { diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c index d201e8697226..27a13aeccd3c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c @@ -47,6 +47,9 @@ ga100_gsp = { .booter.ctor = tu102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga102.c index 917f7e2f6c46..b6b3eb6f4c00 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga102.c @@ -158,6 +158,9 @@ ga102_gsp_r535 = { .booter.ctor = ga102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h index 86bdd203bc10..9dd66a2e3801 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h @@ -7,9 +7,8 @@ enum nvkm_acr_lsf_id; int nvkm_gsp_fwsec_frts(struct nvkm_gsp *); -int nvkm_gsp_fwsec_sb_ctor(struct nvkm_gsp *); int nvkm_gsp_fwsec_sb(struct nvkm_gsp *); -void nvkm_gsp_fwsec_sb_dtor(struct nvkm_gsp *); +int nvkm_gsp_fwsec_sb_init(struct nvkm_gsp *gsp); struct nvkm_gsp_fwif { int version; @@ -52,6 +51,11 @@ struct nvkm_gsp_func { struct nvkm_falcon *, struct nvkm_falcon_fw *); } booter; + struct { + int (*ctor)(struct nvkm_gsp *); + void (*dtor)(struct nvkm_gsp *); + } fwsec_sb; + void (*dtor)(struct nvkm_gsp *); int (*oneinit)(struct nvkm_gsp *); int (*init)(struct nvkm_gsp *); @@ -67,6 +71,8 @@ extern const struct nvkm_falcon_func tu102_gsp_flcn; extern const struct nvkm_falcon_fw_func tu102_gsp_fwsec; int tu102_gsp_booter_ctor(struct nvkm_gsp *, const char *, const struct firmware *, struct nvkm_falcon *, struct nvkm_falcon_fw *); +int tu102_gsp_fwsec_sb_ctor(struct nvkm_gsp *); +void tu102_gsp_fwsec_sb_dtor(struct nvkm_gsp *); int tu102_gsp_oneinit(struct nvkm_gsp *); int tu102_gsp_init(struct nvkm_gsp *); int tu102_gsp_fini(struct nvkm_gsp *, bool suspend); @@ -91,5 +97,18 @@ int r535_gsp_fini(struct nvkm_gsp *, bool suspend); int nvkm_gsp_new_(const struct nvkm_gsp_fwif *, struct nvkm_device *, enum nvkm_subdev_type, int, struct nvkm_gsp **); +static inline int nvkm_gsp_fwsec_sb_ctor(struct nvkm_gsp *gsp) +{ + if (gsp->func->fwsec_sb.ctor) + return gsp->func->fwsec_sb.ctor(gsp); + return 0; +} + +static inline void nvkm_gsp_fwsec_sb_dtor(struct nvkm_gsp *gsp) +{ + if (gsp->func->fwsec_sb.dtor) + gsp->func->fwsec_sb.dtor(gsp); +} + extern const struct nvkm_gsp_func gv100_gsp; #endif diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c index 81e56da0474a..04b642a1f730 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c @@ -30,6 +30,18 @@ #include <nvfw/fw.h> #include <nvfw/hs.h> +int +tu102_gsp_fwsec_sb_ctor(struct nvkm_gsp *gsp) +{ + return nvkm_gsp_fwsec_sb_init(gsp); +} + +void +tu102_gsp_fwsec_sb_dtor(struct nvkm_gsp *gsp) +{ + nvkm_falcon_fw_dtor(&gsp->fws.falcon.sb); +} + static int tu102_gsp_booter_unload(struct nvkm_gsp *gsp, u32 mbox0, u32 mbox1) { @@ -370,6 +382,9 @@ tu102_gsp = { .booter.ctor = tu102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu116.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu116.c index 97eb046c25d0..58cf25842421 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu116.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu116.c @@ -30,6 +30,9 @@ tu116_gsp = { .booter.ctor = tu102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c index 56ff6a3fb483..d7dc83cf7b00 100644 --- a/drivers/gpu/drm/pl111/pl111_drv.c +++ b/drivers/gpu/drm/pl111/pl111_drv.c @@ -295,7 +295,7 @@ static int pl111_amba_probe(struct amba_device *amba_dev, variant->name, priv); if (ret != 0) { dev_err(dev, "%s failed irq %d\n", __func__, ret); - return ret; + goto dev_put; } ret = pl111_modeset_init(drm); diff --git a/drivers/gpu/drm/radeon/pptable.h b/drivers/gpu/drm/radeon/pptable.h index 969a8fb0ee9e..f4e71046dc91 100644 --- a/drivers/gpu/drm/radeon/pptable.h +++ b/drivers/gpu/drm/radeon/pptable.h @@ -450,7 +450,7 @@ typedef struct _ClockInfoArray{ //sizeof(ATOM_PPLIB_CLOCK_INFO) UCHAR ucEntrySize; - UCHAR clockInfo[] __counted_by(ucNumEntries); + UCHAR clockInfo[] /*__counted_by(ucNumEntries)*/; }ClockInfoArray; typedef struct _NonClockInfoArray{ diff --git a/drivers/gpu/drm/tidss/tidss_kms.c b/drivers/gpu/drm/tidss/tidss_kms.c index 86eb5d97410b..8bb93194e5ac 100644 --- a/drivers/gpu/drm/tidss/tidss_kms.c +++ b/drivers/gpu/drm/tidss/tidss_kms.c @@ -26,9 +26,33 @@ static void tidss_atomic_commit_tail(struct drm_atomic_state *old_state) tidss_runtime_get(tidss); - drm_atomic_helper_commit_modeset_disables(ddev, old_state); - drm_atomic_helper_commit_planes(ddev, old_state, DRM_PLANE_COMMIT_ACTIVE_ONLY); - drm_atomic_helper_commit_modeset_enables(ddev, old_state); + /* + * TI's OLDI and DSI encoders need to be set up before the crtc is + * enabled. Thus drm_atomic_helper_commit_modeset_enables() and + * drm_atomic_helper_commit_modeset_disables() cannot be used here, as + * they enable the crtc before bridges' pre-enable, and disable the crtc + * after bridges' post-disable. + * + * Open code the functions here and first call the bridges' pre-enables, + * then crtc enable, then bridges' post-enable (and vice versa for + * disable). + */ + + drm_atomic_helper_commit_encoder_bridge_disable(ddev, old_state); + drm_atomic_helper_commit_crtc_disable(ddev, old_state); + drm_atomic_helper_commit_encoder_bridge_post_disable(ddev, old_state); + + drm_atomic_helper_update_legacy_modeset_state(ddev, old_state); + drm_atomic_helper_calc_timestamping_constants(old_state); + drm_atomic_helper_commit_crtc_set_mode(ddev, old_state); + + drm_atomic_helper_commit_planes(ddev, old_state, + DRM_PLANE_COMMIT_ACTIVE_ONLY); + + drm_atomic_helper_commit_encoder_bridge_pre_enable(ddev, old_state); + drm_atomic_helper_commit_crtc_enable(ddev, old_state); + drm_atomic_helper_commit_encoder_bridge_enable(ddev, old_state); + drm_atomic_helper_commit_writebacks(ddev, old_state); drm_atomic_helper_commit_hw_done(old_state); drm_atomic_helper_wait_for_flip_done(ddev, old_state); diff --git a/drivers/gpu/nova-core/Kconfig b/drivers/gpu/nova-core/Kconfig index 20d3e6d0d796..527920f9c4d3 100644 --- a/drivers/gpu/nova-core/Kconfig +++ b/drivers/gpu/nova-core/Kconfig @@ -3,7 +3,7 @@ config NOVA_CORE depends on 64BIT depends on PCI depends on RUST - depends on RUST_FW_LOADER_ABSTRACTIONS + select RUST_FW_LOADER_ABSTRACTIONS select AUXILIARY_BUS default n help diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs index 6f946d14868a..3991ccc0c10f 100644 --- a/drivers/gpu/nova-core/gsp/cmdq.rs +++ b/drivers/gpu/nova-core/gsp/cmdq.rs @@ -588,21 +588,23 @@ impl Cmdq { header.length(), ); + let payload_length = header.payload_length(); + // Check that the driver read area is large enough for the message. - if slice_1.len() + slice_2.len() < header.length() { + if slice_1.len() + slice_2.len() < payload_length { return Err(EIO); } // Cut the message slices down to the actual length of the message. - let (slice_1, slice_2) = if slice_1.len() > header.length() { - // PANIC: we checked above that `slice_1` is at least as long as `msg_header.length()`. - (slice_1.split_at(header.length()).0, &slice_2[0..0]) + let (slice_1, slice_2) = if slice_1.len() > payload_length { + // PANIC: we checked above that `slice_1` is at least as long as `payload_length`. + (slice_1.split_at(payload_length).0, &slice_2[0..0]) } else { ( slice_1, // PANIC: we checked above that `slice_1.len() + slice_2.len()` is at least as - // large as `msg_header.length()`. - slice_2.split_at(header.length() - slice_1.len()).0, + // large as `payload_length`. + slice_2.split_at(payload_length - slice_1.len()).0, ) }; diff --git a/drivers/gpu/nova-core/gsp/fw.rs b/drivers/gpu/nova-core/gsp/fw.rs index abffd6beec65..caeb0d251fe5 100644 --- a/drivers/gpu/nova-core/gsp/fw.rs +++ b/drivers/gpu/nova-core/gsp/fw.rs @@ -141,8 +141,8 @@ unsafe impl AsBytes for GspFwWprMeta {} // are valid. unsafe impl FromBytes for GspFwWprMeta {} -type GspFwWprMetaBootResumeInfo = r570_144::GspFwWprMeta__bindgen_ty_1; -type GspFwWprMetaBootInfo = r570_144::GspFwWprMeta__bindgen_ty_1__bindgen_ty_1; +type GspFwWprMetaBootResumeInfo = bindings::GspFwWprMeta__bindgen_ty_1; +type GspFwWprMetaBootInfo = bindings::GspFwWprMeta__bindgen_ty_1__bindgen_ty_1; impl GspFwWprMeta { /// Fill in and return a `GspFwWprMeta` suitable for booting `gsp_firmware` using the @@ -150,8 +150,8 @@ impl GspFwWprMeta { pub(crate) fn new(gsp_firmware: &GspFirmware, fb_layout: &FbLayout) -> Self { Self(bindings::GspFwWprMeta { // CAST: we want to store the bits of `GSP_FW_WPR_META_MAGIC` unmodified. - magic: r570_144::GSP_FW_WPR_META_MAGIC as u64, - revision: u64::from(r570_144::GSP_FW_WPR_META_REVISION), + magic: bindings::GSP_FW_WPR_META_MAGIC as u64, + revision: u64::from(bindings::GSP_FW_WPR_META_REVISION), sysmemAddrOfRadix3Elf: gsp_firmware.radix3_dma_handle(), sizeOfRadix3Elf: u64::from_safe_cast(gsp_firmware.size), sysmemAddrOfBootloader: gsp_firmware.bootloader.ucode.dma_handle(), @@ -315,19 +315,19 @@ impl From<MsgFunction> for u32 { #[repr(u32)] pub(crate) enum SeqBufOpcode { // Core operation opcodes - CoreReset = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESET, - CoreResume = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESUME, - CoreStart = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_START, - CoreWaitForHalt = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_WAIT_FOR_HALT, + CoreReset = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESET, + CoreResume = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESUME, + CoreStart = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_START, + CoreWaitForHalt = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_WAIT_FOR_HALT, // Delay opcode - DelayUs = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_DELAY_US, + DelayUs = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_DELAY_US, // Register operation opcodes - RegModify = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_MODIFY, - RegPoll = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_POLL, - RegStore = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_STORE, - RegWrite = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_WRITE, + RegModify = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_MODIFY, + RegPoll = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_POLL, + RegStore = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_STORE, + RegWrite = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_WRITE, } impl fmt::Display for SeqBufOpcode { @@ -351,25 +351,25 @@ impl TryFrom<u32> for SeqBufOpcode { fn try_from(value: u32) -> Result<SeqBufOpcode> { match value { - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESET => { + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESET => { Ok(SeqBufOpcode::CoreReset) } - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESUME => { + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESUME => { Ok(SeqBufOpcode::CoreResume) } - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_START => { + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_START => { Ok(SeqBufOpcode::CoreStart) } - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_WAIT_FOR_HALT => { + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_WAIT_FOR_HALT => { Ok(SeqBufOpcode::CoreWaitForHalt) } - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_DELAY_US => Ok(SeqBufOpcode::DelayUs), - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_MODIFY => { + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_DELAY_US => Ok(SeqBufOpcode::DelayUs), + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_MODIFY => { Ok(SeqBufOpcode::RegModify) } - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_POLL => Ok(SeqBufOpcode::RegPoll), - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_STORE => Ok(SeqBufOpcode::RegStore), - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_WRITE => Ok(SeqBufOpcode::RegWrite), + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_POLL => Ok(SeqBufOpcode::RegPoll), + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_STORE => Ok(SeqBufOpcode::RegStore), + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_WRITE => Ok(SeqBufOpcode::RegWrite), _ => Err(EINVAL), } } @@ -385,7 +385,7 @@ impl From<SeqBufOpcode> for u32 { /// Wrapper for GSP sequencer register write payload. #[repr(transparent)] #[derive(Copy, Clone)] -pub(crate) struct RegWritePayload(r570_144::GSP_SEQ_BUF_PAYLOAD_REG_WRITE); +pub(crate) struct RegWritePayload(bindings::GSP_SEQ_BUF_PAYLOAD_REG_WRITE); impl RegWritePayload { /// Returns the register address. @@ -408,7 +408,7 @@ unsafe impl AsBytes for RegWritePayload {} /// Wrapper for GSP sequencer register modify payload. #[repr(transparent)] #[derive(Copy, Clone)] -pub(crate) struct RegModifyPayload(r570_144::GSP_SEQ_BUF_PAYLOAD_REG_MODIFY); +pub(crate) struct RegModifyPayload(bindings::GSP_SEQ_BUF_PAYLOAD_REG_MODIFY); impl RegModifyPayload { /// Returns the register address. @@ -436,7 +436,7 @@ unsafe impl AsBytes for RegModifyPayload {} /// Wrapper for GSP sequencer register poll payload. #[repr(transparent)] #[derive(Copy, Clone)] -pub(crate) struct RegPollPayload(r570_144::GSP_SEQ_BUF_PAYLOAD_REG_POLL); +pub(crate) struct RegPollPayload(bindings::GSP_SEQ_BUF_PAYLOAD_REG_POLL); impl RegPollPayload { /// Returns the register address. @@ -469,7 +469,7 @@ unsafe impl AsBytes for RegPollPayload {} /// Wrapper for GSP sequencer delay payload. #[repr(transparent)] #[derive(Copy, Clone)] -pub(crate) struct DelayUsPayload(r570_144::GSP_SEQ_BUF_PAYLOAD_DELAY_US); +pub(crate) struct DelayUsPayload(bindings::GSP_SEQ_BUF_PAYLOAD_DELAY_US); impl DelayUsPayload { /// Returns the delay value in microseconds. @@ -487,7 +487,7 @@ unsafe impl AsBytes for DelayUsPayload {} /// Wrapper for GSP sequencer register store payload. #[repr(transparent)] #[derive(Copy, Clone)] -pub(crate) struct RegStorePayload(r570_144::GSP_SEQ_BUF_PAYLOAD_REG_STORE); +pub(crate) struct RegStorePayload(bindings::GSP_SEQ_BUF_PAYLOAD_REG_STORE); impl RegStorePayload { /// Returns the register address. @@ -510,7 +510,7 @@ unsafe impl AsBytes for RegStorePayload {} /// Wrapper for GSP sequencer buffer command. #[repr(transparent)] -pub(crate) struct SequencerBufferCmd(r570_144::GSP_SEQUENCER_BUFFER_CMD); +pub(crate) struct SequencerBufferCmd(bindings::GSP_SEQUENCER_BUFFER_CMD); impl SequencerBufferCmd { /// Returns the opcode as a `SeqBufOpcode` enum, or error if invalid. @@ -612,7 +612,7 @@ unsafe impl AsBytes for SequencerBufferCmd {} /// Wrapper for GSP run CPU sequencer RPC. #[repr(transparent)] -pub(crate) struct RunCpuSequencer(r570_144::rpc_run_cpu_sequencer_v17_00); +pub(crate) struct RunCpuSequencer(bindings::rpc_run_cpu_sequencer_v17_00); impl RunCpuSequencer { /// Returns the command index. @@ -797,13 +797,6 @@ impl bindings::rpc_message_header_v { } } -// SAFETY: We can't derive the Zeroable trait for this binding because the -// procedural macro doesn't support the syntax used by bindgen to create the -// __IncompleteArrayField types. So instead we implement it here, which is safe -// because these are explicitly padded structures only containing types for -// which any bit pattern, including all zeros, is valid. -unsafe impl Zeroable for bindings::rpc_message_header_v {} - /// GSP Message Element. /// /// This is essentially a message header expected to be followed by the message data. @@ -853,11 +846,16 @@ impl GspMsgElement { self.inner.checkSum = checksum; } - /// Returns the total length of the message. + /// Returns the length of the message's payload. + pub(crate) fn payload_length(&self) -> usize { + // `rpc.length` includes the length of the RPC message header. + num::u32_as_usize(self.inner.rpc.length) + .saturating_sub(size_of::<bindings::rpc_message_header_v>()) + } + + /// Returns the total length of the message, message and RPC headers included. pub(crate) fn length(&self) -> usize { - // `rpc.length` includes the length of the GspRpcHeader but not the message header. - size_of::<Self>() - size_of::<bindings::rpc_message_header_v>() - + num::u32_as_usize(self.inner.rpc.length) + size_of::<Self>() + self.payload_length() } // Returns the sequence number of the message. diff --git a/drivers/gpu/nova-core/gsp/fw/r570_144.rs b/drivers/gpu/nova-core/gsp/fw/r570_144.rs index 048234d1a9d1..e99d315ae74c 100644 --- a/drivers/gpu/nova-core/gsp/fw/r570_144.rs +++ b/drivers/gpu/nova-core/gsp/fw/r570_144.rs @@ -24,8 +24,11 @@ unreachable_pub, unsafe_op_in_unsafe_fn )] -use kernel::{ - ffi, - prelude::Zeroable, // -}; +use kernel::ffi; +use pin_init::MaybeZeroable; + include!("r570_144/bindings.rs"); + +// SAFETY: This type has a size of zero, so its inclusion into another type should not affect their +// ability to implement `Zeroable`. +unsafe impl<T> kernel::prelude::Zeroable for __IncompleteArrayField<T> {} diff --git a/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs b/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs index 5bcfbcd1ad22..6d25fe0bffa9 100644 --- a/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs +++ b/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs @@ -320,11 +320,12 @@ pub const NV_VGPU_MSG_EVENT_RECOVERY_ACTION: _bindgen_ty_3 = 4130; pub const NV_VGPU_MSG_EVENT_NUM_EVENTS: _bindgen_ty_3 = 4131; pub type _bindgen_ty_3 = ffi::c_uint; #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct NV0080_CTRL_GPU_GET_SRIOV_CAPS_PARAMS { pub totalVFs: u32_, pub firstVfOffset: u32_, pub vfFeatureMask: u32_, + pub __bindgen_padding_0: [u8; 4usize], pub FirstVFBar0Address: u64_, pub FirstVFBar1Address: u64_, pub FirstVFBar2Address: u64_, @@ -340,23 +341,26 @@ pub struct NV0080_CTRL_GPU_GET_SRIOV_CAPS_PARAMS { pub bClientRmAllocatedCtxBuffer: u8_, pub bNonPowerOf2ChannelCountSupported: u8_, pub bVfResizableBAR1Supported: u8_, + pub __bindgen_padding_1: [u8; 7usize], } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct NV2080_CTRL_BIOS_GET_SKU_INFO_PARAMS { pub BoardID: u32_, pub chipSKU: [ffi::c_char; 9usize], pub chipSKUMod: [ffi::c_char; 5usize], + pub __bindgen_padding_0: [u8; 2usize], pub skuConfigVersion: u32_, pub project: [ffi::c_char; 5usize], pub projectSKU: [ffi::c_char; 5usize], pub CDP: [ffi::c_char; 6usize], pub projectSKUMod: [ffi::c_char; 2usize], + pub __bindgen_padding_1: [u8; 2usize], pub businessCycle: u32_, } pub type NV2080_CTRL_CMD_FB_GET_FB_REGION_SURFACE_MEM_TYPE_FLAG = [u8_; 17usize]; #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct NV2080_CTRL_CMD_FB_GET_FB_REGION_FB_REGION_INFO { pub base: u64_, pub limit: u64_, @@ -368,13 +372,14 @@ pub struct NV2080_CTRL_CMD_FB_GET_FB_REGION_FB_REGION_INFO { pub blackList: NV2080_CTRL_CMD_FB_GET_FB_REGION_SURFACE_MEM_TYPE_FLAG, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct NV2080_CTRL_CMD_FB_GET_FB_REGION_INFO_PARAMS { pub numFBRegions: u32_, + pub __bindgen_padding_0: [u8; 4usize], pub fbRegion: [NV2080_CTRL_CMD_FB_GET_FB_REGION_FB_REGION_INFO; 16usize], } #[repr(C)] -#[derive(Debug, Copy, Clone)] +#[derive(Debug, Copy, Clone, MaybeZeroable)] pub struct NV2080_CTRL_GPU_GET_GID_INFO_PARAMS { pub index: u32_, pub flags: u32_, @@ -391,14 +396,14 @@ impl Default for NV2080_CTRL_GPU_GET_GID_INFO_PARAMS { } } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct DOD_METHOD_DATA { pub status: u32_, pub acpiIdListLen: u32_, pub acpiIdList: [u32_; 16usize], } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct JT_METHOD_DATA { pub status: u32_, pub jtCaps: u32_, @@ -407,14 +412,14 @@ pub struct JT_METHOD_DATA { pub __bindgen_padding_0: u8, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct MUX_METHOD_DATA_ELEMENT { pub acpiId: u32_, pub mode: u32_, pub status: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct MUX_METHOD_DATA { pub tableLen: u32_, pub acpiIdMuxModeTable: [MUX_METHOD_DATA_ELEMENT; 16usize], @@ -422,13 +427,13 @@ pub struct MUX_METHOD_DATA { pub acpiIdMuxStateTable: [MUX_METHOD_DATA_ELEMENT; 16usize], } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct CAPS_METHOD_DATA { pub status: u32_, pub optimusCaps: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct ACPI_METHOD_DATA { pub bValid: u8_, pub __bindgen_padding_0: [u8; 3usize], @@ -438,20 +443,20 @@ pub struct ACPI_METHOD_DATA { pub capsMethodData: CAPS_METHOD_DATA, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct VIRTUAL_DISPLAY_GET_MAX_RESOLUTION_PARAMS { pub headIndex: u32_, pub maxHResolution: u32_, pub maxVResolution: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct VIRTUAL_DISPLAY_GET_NUM_HEADS_PARAMS { pub numHeads: u32_, pub maxNumHeads: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct BUSINFO { pub deviceID: u16_, pub vendorID: u16_, @@ -461,7 +466,7 @@ pub struct BUSINFO { pub __bindgen_padding_0: u8, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_VF_INFO { pub totalVFs: u32_, pub firstVFOffset: u32_, @@ -474,34 +479,37 @@ pub struct GSP_VF_INFO { pub __bindgen_padding_0: [u8; 5usize], } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_PCIE_CONFIG_REG { pub linkCap: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct EcidManufacturingInfo { pub ecidLow: u32_, pub ecidHigh: u32_, pub ecidExtended: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct FW_WPR_LAYOUT_OFFSET { pub nonWprHeapOffset: u64_, pub frtsOffset: u64_, } #[repr(C)] -#[derive(Debug, Copy, Clone)] +#[derive(Debug, Copy, Clone, MaybeZeroable)] pub struct GspStaticConfigInfo_t { pub grCapsBits: [u8_; 23usize], + pub __bindgen_padding_0: u8, pub gidInfo: NV2080_CTRL_GPU_GET_GID_INFO_PARAMS, pub SKUInfo: NV2080_CTRL_BIOS_GET_SKU_INFO_PARAMS, + pub __bindgen_padding_1: [u8; 4usize], pub fbRegionInfoParams: NV2080_CTRL_CMD_FB_GET_FB_REGION_INFO_PARAMS, pub sriovCaps: NV0080_CTRL_GPU_GET_SRIOV_CAPS_PARAMS, pub sriovMaxGfid: u32_, pub engineCaps: [u32_; 3usize], pub poisonFuseEnabled: u8_, + pub __bindgen_padding_2: [u8; 7usize], pub fb_length: u64_, pub fbio_mask: u64_, pub fb_bus_width: u32_, @@ -527,16 +535,20 @@ pub struct GspStaticConfigInfo_t { pub bIsMigSupported: u8_, pub RTD3GC6TotalBoardPower: u16_, pub RTD3GC6PerstDelay: u16_, + pub __bindgen_padding_3: [u8; 2usize], pub bar1PdeBase: u64_, pub bar2PdeBase: u64_, pub bVbiosValid: u8_, + pub __bindgen_padding_4: [u8; 3usize], pub vbiosSubVendor: u32_, pub vbiosSubDevice: u32_, pub bPageRetirementSupported: u8_, pub bSplitVasBetweenServerClientRm: u8_, pub bClRootportNeedsNosnoopWAR: u8_, + pub __bindgen_padding_5: u8, pub displaylessMaxHeads: VIRTUAL_DISPLAY_GET_NUM_HEADS_PARAMS, pub displaylessMaxResolution: VIRTUAL_DISPLAY_GET_MAX_RESOLUTION_PARAMS, + pub __bindgen_padding_6: [u8; 4usize], pub displaylessMaxPixels: u64_, pub hInternalClient: u32_, pub hInternalDevice: u32_, @@ -558,7 +570,7 @@ impl Default for GspStaticConfigInfo_t { } } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GspSystemInfo { pub gpuPhysAddr: u64_, pub gpuPhysFbAddr: u64_, @@ -615,7 +627,7 @@ pub struct GspSystemInfo { pub hostPageSize: u64_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct MESSAGE_QUEUE_INIT_ARGUMENTS { pub sharedMemPhysAddr: u64_, pub pageTableEntryCount: u32_, @@ -624,7 +636,7 @@ pub struct MESSAGE_QUEUE_INIT_ARGUMENTS { pub statQueueOffset: u64_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_SR_INIT_ARGUMENTS { pub oldLevel: u32_, pub flags: u32_, @@ -632,7 +644,7 @@ pub struct GSP_SR_INIT_ARGUMENTS { pub __bindgen_padding_0: [u8; 3usize], } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_ARGUMENTS_CACHED { pub messageQueueInitArguments: MESSAGE_QUEUE_INIT_ARGUMENTS, pub srInitArguments: GSP_SR_INIT_ARGUMENTS, @@ -642,13 +654,13 @@ pub struct GSP_ARGUMENTS_CACHED { pub profilerArgs: GSP_ARGUMENTS_CACHED__bindgen_ty_1, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_ARGUMENTS_CACHED__bindgen_ty_1 { pub pa: u64_, pub size: u64_, } #[repr(C)] -#[derive(Copy, Clone, Zeroable)] +#[derive(Copy, Clone, MaybeZeroable)] pub union rpc_message_rpc_union_field_v03_00 { pub spare: u32_, pub cpuRmGfid: u32_, @@ -664,6 +676,7 @@ impl Default for rpc_message_rpc_union_field_v03_00 { } pub type rpc_message_rpc_union_field_v = rpc_message_rpc_union_field_v03_00; #[repr(C)] +#[derive(MaybeZeroable)] pub struct rpc_message_header_v03_00 { pub header_version: u32_, pub signature: u32_, @@ -686,7 +699,7 @@ impl Default for rpc_message_header_v03_00 { } pub type rpc_message_header_v = rpc_message_header_v03_00; #[repr(C)] -#[derive(Copy, Clone, Zeroable)] +#[derive(Copy, Clone, MaybeZeroable)] pub struct GspFwWprMeta { pub magic: u64_, pub revision: u64_, @@ -721,19 +734,19 @@ pub struct GspFwWprMeta { pub verified: u64_, } #[repr(C)] -#[derive(Copy, Clone, Zeroable)] +#[derive(Copy, Clone, MaybeZeroable)] pub union GspFwWprMeta__bindgen_ty_1 { pub __bindgen_anon_1: GspFwWprMeta__bindgen_ty_1__bindgen_ty_1, pub __bindgen_anon_2: GspFwWprMeta__bindgen_ty_1__bindgen_ty_2, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GspFwWprMeta__bindgen_ty_1__bindgen_ty_1 { pub sysmemAddrOfSignature: u64_, pub sizeOfSignature: u64_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GspFwWprMeta__bindgen_ty_1__bindgen_ty_2 { pub gspFwHeapFreeListWprOffset: u32_, pub unused0: u32_, @@ -749,13 +762,13 @@ impl Default for GspFwWprMeta__bindgen_ty_1 { } } #[repr(C)] -#[derive(Copy, Clone, Zeroable)] +#[derive(Copy, Clone, MaybeZeroable)] pub union GspFwWprMeta__bindgen_ty_2 { pub __bindgen_anon_1: GspFwWprMeta__bindgen_ty_2__bindgen_ty_1, pub __bindgen_anon_2: GspFwWprMeta__bindgen_ty_2__bindgen_ty_2, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GspFwWprMeta__bindgen_ty_2__bindgen_ty_1 { pub partitionRpcAddr: u64_, pub partitionRpcRequestOffset: u16_, @@ -767,7 +780,7 @@ pub struct GspFwWprMeta__bindgen_ty_2__bindgen_ty_1 { pub lsUcodeVersion: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GspFwWprMeta__bindgen_ty_2__bindgen_ty_2 { pub partitionRpcPadding: [u32_; 4usize], pub sysmemAddrOfCrashReportQueue: u64_, @@ -802,7 +815,7 @@ pub const LibosMemoryRegionLoc_LIBOS_MEMORY_REGION_LOC_SYSMEM: LibosMemoryRegion pub const LibosMemoryRegionLoc_LIBOS_MEMORY_REGION_LOC_FB: LibosMemoryRegionLoc = 2; pub type LibosMemoryRegionLoc = ffi::c_uint; #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct LibosMemoryRegionInitArgument { pub id8: LibosAddress, pub pa: LibosAddress, @@ -812,7 +825,7 @@ pub struct LibosMemoryRegionInitArgument { pub __bindgen_padding_0: [u8; 6usize], } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct PACKED_REGISTRY_ENTRY { pub nameOffset: u32_, pub type_: u8_, @@ -821,14 +834,14 @@ pub struct PACKED_REGISTRY_ENTRY { pub length: u32_, } #[repr(C)] -#[derive(Debug, Default)] +#[derive(Debug, Default, MaybeZeroable)] pub struct PACKED_REGISTRY_TABLE { pub size: u32_, pub numEntries: u32_, pub entries: __IncompleteArrayField<PACKED_REGISTRY_ENTRY>, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct msgqTxHeader { pub version: u32_, pub size: u32_, @@ -840,13 +853,13 @@ pub struct msgqTxHeader { pub entryOff: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct msgqRxHeader { pub readPtr: u32_, } #[repr(C)] #[repr(align(8))] -#[derive(Zeroable)] +#[derive(MaybeZeroable)] pub struct GSP_MSG_QUEUE_ELEMENT { pub authTagBuffer: [u8_; 16usize], pub aadBuffer: [u8_; 16usize], @@ -866,7 +879,7 @@ impl Default for GSP_MSG_QUEUE_ELEMENT { } } #[repr(C)] -#[derive(Debug, Default)] +#[derive(Debug, Default, MaybeZeroable)] pub struct rpc_run_cpu_sequencer_v17_00 { pub bufferSizeDWord: u32_, pub cmdIndex: u32_, @@ -884,20 +897,20 @@ pub const GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_WAIT_FOR_HALT: GSP_SEQ_BUF_ pub const GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESUME: GSP_SEQ_BUF_OPCODE = 8; pub type GSP_SEQ_BUF_OPCODE = ffi::c_uint; #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_SEQ_BUF_PAYLOAD_REG_WRITE { pub addr: u32_, pub val: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_SEQ_BUF_PAYLOAD_REG_MODIFY { pub addr: u32_, pub mask: u32_, pub val: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_SEQ_BUF_PAYLOAD_REG_POLL { pub addr: u32_, pub mask: u32_, @@ -906,24 +919,24 @@ pub struct GSP_SEQ_BUF_PAYLOAD_REG_POLL { pub error: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_SEQ_BUF_PAYLOAD_DELAY_US { pub val: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_SEQ_BUF_PAYLOAD_REG_STORE { pub addr: u32_, pub index: u32_, } #[repr(C)] -#[derive(Copy, Clone)] +#[derive(Copy, Clone, MaybeZeroable)] pub struct GSP_SEQUENCER_BUFFER_CMD { pub opCode: GSP_SEQ_BUF_OPCODE, pub payload: GSP_SEQUENCER_BUFFER_CMD__bindgen_ty_1, } #[repr(C)] -#[derive(Copy, Clone)] +#[derive(Copy, Clone, MaybeZeroable)] pub union GSP_SEQUENCER_BUFFER_CMD__bindgen_ty_1 { pub regWrite: GSP_SEQ_BUF_PAYLOAD_REG_WRITE, pub regModify: GSP_SEQ_BUF_PAYLOAD_REG_MODIFY, diff --git a/drivers/pci/vgaarb.c b/drivers/pci/vgaarb.c index 436fa7f4c387..baa242b14099 100644 --- a/drivers/pci/vgaarb.c +++ b/drivers/pci/vgaarb.c @@ -652,13 +652,6 @@ static bool vga_is_boot_device(struct vga_device *vgadev) return true; } - /* - * Vgadev has neither IO nor MEM enabled. If we haven't found any - * other VGA devices, it is the best candidate so far. - */ - if (!boot_vga) - return true; - return false; } |
